diff options
Diffstat (limited to 'Utilities/cmexpat')
25 files changed, 16481 insertions, 0 deletions
diff --git a/Utilities/cmexpat/.gitattributes b/Utilities/cmexpat/.gitattributes new file mode 100644 index 0000000000..562b12e16e --- /dev/null +++ b/Utilities/cmexpat/.gitattributes @@ -0,0 +1 @@ +* -whitespace diff --git a/Utilities/cmexpat/CMakeLists.txt b/Utilities/cmexpat/CMakeLists.txt new file mode 100644 index 0000000000..9a62b79af9 --- /dev/null +++ b/Utilities/cmexpat/CMakeLists.txt @@ -0,0 +1,27 @@ +# Disable warnings to avoid changing 3rd party code. +IF(CMAKE_C_COMPILER_ID MATCHES + "^(GNU|LCC|Clang|AppleClang|IBMClang|XLClang|XL|VisualAge|SunPro|HP|Intel|IntelLLVM|NVHPC)$") + SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w") +ELSEIF(CMAKE_C_COMPILER_ID STREQUAL "PathScale") + SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -woffall") +ENDIF() + +include(ConfigureChecks.cmake) +configure_file(expat_config.h.cmake expat_config.h @ONLY) + +if(NOT WIN32) + add_definitions(-DXML_DEV_URANDOM) +endif() + +include_directories( + ${CMAKE_CURRENT_BINARY_DIR} + ${CMAKE_CURRENT_SOURCE_DIR}/lib + ) + +add_library(cmexpat STATIC + lib/xmlparse.c + lib/xmlrole.c + lib/xmltok.c + lib/xmltok_impl.c + lib/xmltok_ns.c + ) diff --git a/Utilities/cmexpat/COPYING b/Utilities/cmexpat/COPYING new file mode 100644 index 0000000000..3c0142e71c --- /dev/null +++ b/Utilities/cmexpat/COPYING @@ -0,0 +1,21 @@ +Copyright (c) 1998-2000 Thai Open Source Software Center Ltd and Clark Cooper +Copyright (c) 2001-2019 Expat maintainers + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff --git a/Utilities/cmexpat/ConfigureChecks.cmake b/Utilities/cmexpat/ConfigureChecks.cmake new file mode 100644 index 0000000000..341bab7b9a --- /dev/null +++ b/Utilities/cmexpat/ConfigureChecks.cmake @@ -0,0 +1,56 @@ +include(CheckCCompilerFlag) +include(CheckCSourceCompiles) +include(CheckIncludeFile) +include(CheckIncludeFiles) +include(CheckLibraryExists) +include(CheckSymbolExists) +include(TestBigEndian) + +check_include_file("dlfcn.h" HAVE_DLFCN_H) +check_include_file("fcntl.h" HAVE_FCNTL_H) +check_include_file("inttypes.h" HAVE_INTTYPES_H) +check_include_file("memory.h" HAVE_MEMORY_H) +check_include_file("stdint.h" HAVE_STDINT_H) +check_include_file("stdlib.h" HAVE_STDLIB_H) +check_include_file("strings.h" HAVE_STRINGS_H) +check_include_file("string.h" HAVE_STRING_H) +check_include_file("sys/stat.h" HAVE_SYS_STAT_H) +check_include_file("sys/types.h" HAVE_SYS_TYPES_H) +check_include_file("unistd.h" HAVE_UNISTD_H) + +check_symbol_exists("getpagesize" "unistd.h" HAVE_GETPAGESIZE) +check_symbol_exists("mmap" "sys/mman.h" HAVE_MMAP) +check_symbol_exists("getrandom" "sys/random.h" HAVE_GETRANDOM) + +if(EXPAT_WITH_LIBBSD) + set(CMAKE_REQUIRED_LIBRARIES "${LIB_BSD}") + set(_bsd "bsd/") +else() + set(_bsd "") +endif() +check_symbol_exists("arc4random_buf" "${_bsd}stdlib.h" HAVE_ARC4RANDOM_BUF) +if(NOT HAVE_ARC4RANDOM_BUF) + check_symbol_exists("arc4random" "${_bsd}stdlib.h" HAVE_ARC4RANDOM) +endif() +set(CMAKE_REQUIRED_LIBRARIES) + +#/* Define to 1 if you have the ANSI C header files. */ +check_include_files("stdlib.h;stdarg.h;string.h;float.h" STDC_HEADERS) + +test_big_endian(WORDS_BIGENDIAN) +#/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +if(WORDS_BIGENDIAN) + set(BYTEORDER 4321) +else(WORDS_BIGENDIAN) + set(BYTEORDER 1234) +endif(WORDS_BIGENDIAN) + +check_c_source_compiles(" + #include <stdlib.h> /* for NULL */ + #include <unistd.h> /* for syscall */ + #include <sys/syscall.h> /* for SYS_getrandom */ + int main() { + syscall(SYS_getrandom, NULL, 0, 0); + return 0; + }" + HAVE_SYSCALL_GETRANDOM) diff --git a/Utilities/cmexpat/README.md b/Utilities/cmexpat/README.md new file mode 100644 index 0000000000..959c4a6e94 --- /dev/null +++ b/Utilities/cmexpat/README.md @@ -0,0 +1,269 @@ +[](https://github.com/libexpat/libexpat/actions/workflows/linux.yml) +[](https://ci.appveyor.com/project/libexpat/libexpat) +[](https://repology.org/metapackage/expat/versions) +[](https://sourceforge.net/projects/expat/files/) +[](https://github.com/libexpat/libexpat/releases) + + +# Expat, Release 2.4.6 + +This is Expat, a C library for parsing XML, started by +[James Clark](https://en.wikipedia.org/wiki/James_Clark_%28programmer%29) in 1997. +Expat is a stream-oriented XML parser. This means that you register +handlers with the parser before starting the parse. These handlers +are called when the parser discovers the associated structures in the +document being parsed. A start tag is an example of the kind of +structures for which you may register handlers. + +Expat supports the following compilers: + +- GNU GCC >=4.5 +- LLVM Clang >=3.5 +- Microsoft Visual Studio >=15.0/2017 (rolling `${today} minus 5 years`) + +Windows users can use the +[`expat-win32bin-*.*.*.{exe,zip}` download](https://github.com/libexpat/libexpat/releases), +which includes both pre-compiled libraries and executables, and source code for +developers. + +Expat is [free software](https://www.gnu.org/philosophy/free-sw.en.html). +You may copy, distribute, and modify it under the terms of the License +contained in the file +[`COPYING`](https://github.com/libexpat/libexpat/blob/master/expat/COPYING) +distributed with this package. +This license is the same as the MIT/X Consortium license. + + +## Using libexpat in your CMake-Based Project + +There are two ways of using libexpat with CMake: + +### a) Module Mode + +This approach leverages CMake's own [module `FindEXPAT`](https://cmake.org/cmake/help/latest/module/FindEXPAT.html). + +Notice the *uppercase* `EXPAT` in the following example: + +```cmake +cmake_minimum_required(VERSION 3.0) # or 3.10, see below + +project(hello VERSION 1.0.0) + +find_package(EXPAT 2.2.8 MODULE REQUIRED) + +add_executable(hello + hello.c +) + +# a) for CMake >=3.10 (see CMake's FindEXPAT docs) +target_link_libraries(hello PUBLIC EXPAT::EXPAT) + +# b) for CMake >=3.0 +target_include_directories(hello PRIVATE ${EXPAT_INCLUDE_DIRS}) +target_link_libraries(hello PUBLIC ${EXPAT_LIBRARIES}) +``` + +### b) Config Mode + +This approach requires files from… + +- libexpat >=2.2.8 where packaging uses the CMake build system +or +- libexpat >=2.3.0 where packaging uses the GNU Autotools build system + on Linux +or +- libexpat >=2.4.0 where packaging uses the GNU Autotools build system + on macOS or MinGW. + +Notice the *lowercase* `expat` in the following example: + +```cmake +cmake_minimum_required(VERSION 3.0) + +project(hello VERSION 1.0.0) + +find_package(expat 2.2.8 CONFIG REQUIRED char dtd ns) + +add_executable(hello + hello.c +) + +target_link_libraries(hello PUBLIC expat::expat) +``` + + +## Building from a Git Clone + +If you are building Expat from a check-out from the +[Git repository](https://github.com/libexpat/libexpat/), +you need to run a script that generates the configure script using the +GNU autoconf and libtool tools. To do this, you need to have +autoconf 2.58 or newer. Run the script like this: + +```console +./buildconf.sh +``` + +Once this has been done, follow the same instructions as for building +from a source distribution. + + +## Building from a Source Distribution + +### a) Building with the configure script (i.e. GNU Autotools) + +To build Expat from a source distribution, you first run the +configuration shell script in the top level distribution directory: + +```console +./configure +``` + +There are many options which you may provide to configure (which you +can discover by running configure with the `--help` option). But the +one of most interest is the one that sets the installation directory. +By default, the configure script will set things up to install +libexpat into `/usr/local/lib`, `expat.h` into `/usr/local/include`, and +`xmlwf` into `/usr/local/bin`. If, for example, you'd prefer to install +into `/home/me/mystuff/lib`, `/home/me/mystuff/include`, and +`/home/me/mystuff/bin`, you can tell `configure` about that with: + +```console +./configure --prefix=/home/me/mystuff +``` + +Another interesting option is to enable 64-bit integer support for +line and column numbers and the over-all byte index: + +```console +./configure CPPFLAGS=-DXML_LARGE_SIZE +``` + +However, such a modification would be a breaking change to the ABI +and is therefore not recommended for general use — e.g. as part of +a Linux distribution — but rather for builds with special requirements. + +After running the configure script, the `make` command will build +things and `make install` will install things into their proper +location. Have a look at the `Makefile` to learn about additional +`make` options. Note that you need to have write permission into +the directories into which things will be installed. + +If you are interested in building Expat to provide document +information in UTF-16 encoding rather than the default UTF-8, follow +these instructions (after having run `make distclean`). +Please note that we configure with `--without-xmlwf` as xmlwf does not +support this mode of compilation (yet): + +1. Mass-patch `Makefile.am` files to use `libexpatw.la` for a library name: + <br/> + `find -name Makefile.am -exec sed + -e 's,libexpat\.la,libexpatw.la,' + -e 's,libexpat_la,libexpatw_la,' + -i {} +` + +1. Run `automake` to re-write `Makefile.in` files:<br/> + `automake` + +1. For UTF-16 output as unsigned short (and version/error strings as char), + run:<br/> + `./configure CPPFLAGS=-DXML_UNICODE --without-xmlwf`<br/> + For UTF-16 output as `wchar_t` (incl. version/error strings), run:<br/> + `./configure CFLAGS="-g -O2 -fshort-wchar" CPPFLAGS=-DXML_UNICODE_WCHAR_T + --without-xmlwf` + <br/>Note: The latter requires libc compiled with `-fshort-wchar`, as well. + +1. Run `make` (which excludes xmlwf). + +1. Run `make install` (again, excludes xmlwf). + +Using `DESTDIR` is supported. It works as follows: + +```console +make install DESTDIR=/path/to/image +``` + +overrides the in-makefile set `DESTDIR`, because variable-setting priority is + +1. commandline +1. in-makefile +1. environment + +Note: This only applies to the Expat library itself, building UTF-16 versions +of xmlwf and the tests is currently not supported. + +When using Expat with a project using autoconf for configuration, you +can use the probing macro in `conftools/expat.m4` to determine how to +include Expat. See the comments at the top of that file for more +information. + +A reference manual is available in the file `doc/reference.html` in this +distribution. + + +### b) Building with CMake + +The CMake build system is still *experimental* and may replace the primary +build system based on GNU Autotools at some point when it is ready. + + +#### Available Options + +For an idea of the available (non-advanced) options for building with CMake: + +```console +# rm -f CMakeCache.txt ; cmake -D_EXPAT_HELP=ON -LH . | grep -B1 ':.*=' | sed 's,^--$,,' +// Choose the type of build, options are: None Debug Release RelWithDebInfo MinSizeRel ... +CMAKE_BUILD_TYPE:STRING= + +// Install path prefix, prepended onto install directories. +CMAKE_INSTALL_PREFIX:PATH=/usr/local + +// Path to a program. +DOCBOOK_TO_MAN:FILEPATH=/usr/bin/docbook2x-man + +// build man page for xmlwf +EXPAT_BUILD_DOCS:BOOL=ON + +// build the examples for expat library +EXPAT_BUILD_EXAMPLES:BOOL=ON + +// build fuzzers for the expat library +EXPAT_BUILD_FUZZERS:BOOL=OFF + +// build pkg-config file +EXPAT_BUILD_PKGCONFIG:BOOL=ON + +// build the tests for expat library +EXPAT_BUILD_TESTS:BOOL=ON + +// build the xmlwf tool for expat library +EXPAT_BUILD_TOOLS:BOOL=ON + +// Character type to use (char|ushort|wchar_t) [default=char] +EXPAT_CHAR_TYPE:STRING=char + +// install expat files in cmake install target +EXPAT_ENABLE_INSTALL:BOOL=ON + +// Use /MT flag (static CRT) when compiling in MSVC +EXPAT_MSVC_STATIC_CRT:BOOL=OFF + +// build fuzzers via ossfuzz for the expat library +EXPAT_OSSFUZZ_BUILD:BOOL=OFF + +// build a shared expat library +EXPAT_SHARED_LIBS:BOOL=ON + +// Treat all compiler warnings as errors +EXPAT_WARNINGS_AS_ERRORS:BOOL=OFF + +// Make use of getrandom function (ON|OFF|AUTO) [default=AUTO] +EXPAT_WITH_GETRANDOM:STRING=AUTO + +// utilize libbsd (for arc4random_buf) +EXPAT_WITH_LIBBSD:BOOL=OFF + +// Make use of syscall SYS_getrandom (ON|OFF|AUTO) [default=AUTO] +EXPAT_WITH_SYS_GETRANDOM:STRING=AUTO +``` diff --git a/Utilities/cmexpat/expat_config.h.cmake b/Utilities/cmexpat/expat_config.h.cmake new file mode 100644 index 0000000000..e91861ecf5 --- /dev/null +++ b/Utilities/cmexpat/expat_config.h.cmake @@ -0,0 +1,88 @@ +/* expat_config.h.cmake. Based upon generated expat_config.h.in. */ + +/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +#cmakedefine BYTEORDER @BYTEORDER@ + +/* Define to 1 if you have the `arc4random' function. */ +#cmakedefine HAVE_ARC4RANDOM + +/* Define to 1 if you have the `arc4random_buf' function. */ +#cmakedefine HAVE_ARC4RANDOM_BUF + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#cmakedefine HAVE_DLFCN_H + +/* Define to 1 if you have the <fcntl.h> header file. */ +#cmakedefine HAVE_FCNTL_H + +/* Define to 1 if you have the `getpagesize' function. */ +#cmakedefine HAVE_GETPAGESIZE + +/* Define to 1 if you have the `getrandom' function. */ +#cmakedefine HAVE_GETRANDOM + +/* Define to 1 if you have the <inttypes.h> header file. */ +#cmakedefine HAVE_INTTYPES_H + +/* Define to 1 if you have the `bsd' library (-lbsd). */ +#cmakedefine HAVE_LIBBSD + +/* Define to 1 if you have the <memory.h> header file. */ +#cmakedefine HAVE_MEMORY_H + +/* Define to 1 if you have a working `mmap' system call. */ +#cmakedefine HAVE_MMAP + +/* Define to 1 if you have the <stdint.h> header file. */ +#cmakedefine HAVE_STDINT_H + +/* Define to 1 if you have the <stdlib.h> header file. */ +#cmakedefine HAVE_STDLIB_H + +/* Define to 1 if you have the <strings.h> header file. */ +#cmakedefine HAVE_STRINGS_H + +/* Define to 1 if you have the <string.h> header file. */ +#cmakedefine HAVE_STRING_H + +/* Define to 1 if you have `syscall' and `SYS_getrandom'. */ +#cmakedefine HAVE_SYSCALL_GETRANDOM + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#cmakedefine HAVE_SYS_STAT_H + +/* Define to 1 if you have the <sys/types.h> header file. */ +#cmakedefine HAVE_SYS_TYPES_H + +/* Define to 1 if you have the <unistd.h> header file. */ +#cmakedefine HAVE_UNISTD_H + +/* Define to 1 if you have the ANSI C header files. */ +#cmakedefine STDC_HEADERS + +/* whether byteorder is bigendian */ +#cmakedefine WORDS_BIGENDIAN + +/* Define to allow retrieving the byte offsets for attribute names and values. + */ +#cmakedefine XML_ATTR_INFO + +/* Define to specify how much context to retain around the current parse + point. */ +#define XML_CONTEXT_BYTES 1024 + +#if ! defined(_WIN32) +/* Define to include code reading entropy from `/dev/urandom'. */ + #cmakedefine XML_DEV_URANDOM +#endif + +/* Define to make parameter entity parsing functionality available. */ +/* #undef XML_DTD */ + +/* Define to make XML Namespaces functionality available. */ +/* #undef XML_NS */ + +/* Define to __FUNCTION__ or "" if `__func__' does not conform to ANSI C. */ +#ifdef _MSC_VER +# define __func__ __FUNCTION__ +#endif diff --git a/Utilities/cmexpat/lib/ascii.h b/Utilities/cmexpat/lib/ascii.h new file mode 100644 index 0000000000..1f594d2e54 --- /dev/null +++ b/Utilities/cmexpat/lib/ascii.h @@ -0,0 +1,123 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1999-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2007 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#define ASCII_A 0x41 +#define ASCII_B 0x42 +#define ASCII_C 0x43 +#define ASCII_D 0x44 +#define ASCII_E 0x45 +#define ASCII_F 0x46 +#define ASCII_G 0x47 +#define ASCII_H 0x48 +#define ASCII_I 0x49 +#define ASCII_J 0x4A +#define ASCII_K 0x4B +#define ASCII_L 0x4C +#define ASCII_M 0x4D +#define ASCII_N 0x4E +#define ASCII_O 0x4F +#define ASCII_P 0x50 +#define ASCII_Q 0x51 +#define ASCII_R 0x52 +#define ASCII_S 0x53 +#define ASCII_T 0x54 +#define ASCII_U 0x55 +#define ASCII_V 0x56 +#define ASCII_W 0x57 +#define ASCII_X 0x58 +#define ASCII_Y 0x59 +#define ASCII_Z 0x5A + +#define ASCII_a 0x61 +#define ASCII_b 0x62 +#define ASCII_c 0x63 +#define ASCII_d 0x64 +#define ASCII_e 0x65 +#define ASCII_f 0x66 +#define ASCII_g 0x67 +#define ASCII_h 0x68 +#define ASCII_i 0x69 +#define ASCII_j 0x6A +#define ASCII_k 0x6B +#define ASCII_l 0x6C +#define ASCII_m 0x6D +#define ASCII_n 0x6E +#define ASCII_o 0x6F +#define ASCII_p 0x70 +#define ASCII_q 0x71 +#define ASCII_r 0x72 +#define ASCII_s 0x73 +#define ASCII_t 0x74 +#define ASCII_u 0x75 +#define ASCII_v 0x76 +#define ASCII_w 0x77 +#define ASCII_x 0x78 +#define ASCII_y 0x79 +#define ASCII_z 0x7A + +#define ASCII_0 0x30 +#define ASCII_1 0x31 +#define ASCII_2 0x32 +#define ASCII_3 0x33 +#define ASCII_4 0x34 +#define ASCII_5 0x35 +#define ASCII_6 0x36 +#define ASCII_7 0x37 +#define ASCII_8 0x38 +#define ASCII_9 0x39 + +#define ASCII_TAB 0x09 +#define ASCII_SPACE 0x20 +#define ASCII_EXCL 0x21 +#define ASCII_QUOT 0x22 +#define ASCII_AMP 0x26 +#define ASCII_APOS 0x27 +#define ASCII_MINUS 0x2D +#define ASCII_PERIOD 0x2E +#define ASCII_COLON 0x3A +#define ASCII_SEMI 0x3B +#define ASCII_LT 0x3C +#define ASCII_EQUALS 0x3D +#define ASCII_GT 0x3E +#define ASCII_LSQB 0x5B +#define ASCII_RSQB 0x5D +#define ASCII_UNDERSCORE 0x5F +#define ASCII_LPAREN 0x28 +#define ASCII_RPAREN 0x29 +#define ASCII_FF 0x0C +#define ASCII_SLASH 0x2F +#define ASCII_HASH 0x23 +#define ASCII_PIPE 0x7C +#define ASCII_COMMA 0x2C diff --git a/Utilities/cmexpat/lib/asciitab.h b/Utilities/cmexpat/lib/asciitab.h new file mode 100644 index 0000000000..af766fb247 --- /dev/null +++ b/Utilities/cmexpat/lib/asciitab.h @@ -0,0 +1,66 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, + /* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML, + /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, + /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, + /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, + /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, + /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, + /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, + /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, + /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, + /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/Utilities/cmexpat/lib/expat.h b/Utilities/cmexpat/lib/expat.h new file mode 100644 index 0000000000..46a0e1bcd2 --- /dev/null +++ b/Utilities/cmexpat/lib/expat.h @@ -0,0 +1,1050 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2005 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2022 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Cristian RodrÃguez <crrodriguez@opensuse.org> + Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifndef Expat_INCLUDED +#define Expat_INCLUDED 1 + +#include <stdlib.h> +#include "expat_external.h" + +#ifdef __cplusplus +extern "C" { +#endif + +struct XML_ParserStruct; +typedef struct XML_ParserStruct *XML_Parser; + +typedef unsigned char XML_Bool; +#define XML_TRUE ((XML_Bool)1) +#define XML_FALSE ((XML_Bool)0) + +/* The XML_Status enum gives the possible return values for several + API functions. The preprocessor #defines are included so this + stanza can be added to code that still needs to support older + versions of Expat 1.95.x: + + #ifndef XML_STATUS_OK + #define XML_STATUS_OK 1 + #define XML_STATUS_ERROR 0 + #endif + + Otherwise, the #define hackery is quite ugly and would have been + dropped. +*/ +enum XML_Status { + XML_STATUS_ERROR = 0, +#define XML_STATUS_ERROR XML_STATUS_ERROR + XML_STATUS_OK = 1, +#define XML_STATUS_OK XML_STATUS_OK + XML_STATUS_SUSPENDED = 2 +#define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED +}; + +enum XML_Error { + XML_ERROR_NONE, + XML_ERROR_NO_MEMORY, + XML_ERROR_SYNTAX, + XML_ERROR_NO_ELEMENTS, + XML_ERROR_INVALID_TOKEN, + XML_ERROR_UNCLOSED_TOKEN, + XML_ERROR_PARTIAL_CHAR, + XML_ERROR_TAG_MISMATCH, + XML_ERROR_DUPLICATE_ATTRIBUTE, + XML_ERROR_JUNK_AFTER_DOC_ELEMENT, + XML_ERROR_PARAM_ENTITY_REF, + XML_ERROR_UNDEFINED_ENTITY, + XML_ERROR_RECURSIVE_ENTITY_REF, + XML_ERROR_ASYNC_ENTITY, + XML_ERROR_BAD_CHAR_REF, + XML_ERROR_BINARY_ENTITY_REF, + XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, + XML_ERROR_MISPLACED_XML_PI, + XML_ERROR_UNKNOWN_ENCODING, + XML_ERROR_INCORRECT_ENCODING, + XML_ERROR_UNCLOSED_CDATA_SECTION, + XML_ERROR_EXTERNAL_ENTITY_HANDLING, + XML_ERROR_NOT_STANDALONE, + XML_ERROR_UNEXPECTED_STATE, + XML_ERROR_ENTITY_DECLARED_IN_PE, + XML_ERROR_FEATURE_REQUIRES_XML_DTD, + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, + /* Added in 1.95.7. */ + XML_ERROR_UNBOUND_PREFIX, + /* Added in 1.95.8. */ + XML_ERROR_UNDECLARING_PREFIX, + XML_ERROR_INCOMPLETE_PE, + XML_ERROR_XML_DECL, + XML_ERROR_TEXT_DECL, + XML_ERROR_PUBLICID, + XML_ERROR_SUSPENDED, + XML_ERROR_NOT_SUSPENDED, + XML_ERROR_ABORTED, + XML_ERROR_FINISHED, + XML_ERROR_SUSPEND_PE, + /* Added in 2.0. */ + XML_ERROR_RESERVED_PREFIX_XML, + XML_ERROR_RESERVED_PREFIX_XMLNS, + XML_ERROR_RESERVED_NAMESPACE_URI, + /* Added in 2.2.1. */ + XML_ERROR_INVALID_ARGUMENT, + /* Added in 2.3.0. */ + XML_ERROR_NO_BUFFER, + /* Added in 2.4.0. */ + XML_ERROR_AMPLIFICATION_LIMIT_BREACH +}; + +enum XML_Content_Type { + XML_CTYPE_EMPTY = 1, + XML_CTYPE_ANY, + XML_CTYPE_MIXED, + XML_CTYPE_NAME, + XML_CTYPE_CHOICE, + XML_CTYPE_SEQ +}; + +enum XML_Content_Quant { + XML_CQUANT_NONE, + XML_CQUANT_OPT, + XML_CQUANT_REP, + XML_CQUANT_PLUS +}; + +/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be + XML_CQUANT_NONE, and the other fields will be zero or NULL. + If type == XML_CTYPE_MIXED, then quant will be NONE or REP and + numchildren will contain number of elements that may be mixed in + and children point to an array of XML_Content cells that will be + all of XML_CTYPE_NAME type with no quantification. + + If type == XML_CTYPE_NAME, then the name points to the name, and + the numchildren field will be zero and children will be NULL. The + quant fields indicates any quantifiers placed on the name. + + CHOICE and SEQ will have name NULL, the number of children in + numchildren and children will point, recursively, to an array + of XML_Content cells. + + The EMPTY, ANY, and MIXED types will only occur at top level. +*/ + +typedef struct XML_cp XML_Content; + +struct XML_cp { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + XML_Char *name; + unsigned int numchildren; + XML_Content *children; +}; + +/* This is called for an element declaration. See above for + description of the model argument. It's the caller's responsibility + to free model when finished with it. +*/ +typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, + const XML_Char *name, + XML_Content *model); + +XMLPARSEAPI(void) +XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl); + +/* The Attlist declaration handler is called for *each* attribute. So + a single Attlist declaration with multiple attributes declared will + generate multiple calls to this handler. The "default" parameter + may be NULL in the case of the "#IMPLIED" or "#REQUIRED" + keyword. The "isrequired" parameter will be true and the default + value will be NULL in the case of "#REQUIRED". If "isrequired" is + true and default is non-NULL, then this is a "#FIXED" default. +*/ +typedef void(XMLCALL *XML_AttlistDeclHandler)( + void *userData, const XML_Char *elname, const XML_Char *attname, + const XML_Char *att_type, const XML_Char *dflt, int isrequired); + +XMLPARSEAPI(void) +XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl); + +/* The XML declaration handler is called for *both* XML declarations + and text declarations. The way to distinguish is that the version + parameter will be NULL for text declarations. The encoding + parameter may be NULL for XML declarations. The standalone + parameter will be -1, 0, or 1 indicating respectively that there + was no standalone parameter in the declaration, that it was given + as no, or that it was given as yes. +*/ +typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); + +XMLPARSEAPI(void) +XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl); + +typedef struct { + void *(*malloc_fcn)(size_t size); + void *(*realloc_fcn)(void *ptr, size_t size); + void (*free_fcn)(void *ptr); +} XML_Memory_Handling_Suite; + +/* Constructs a new parser; encoding is the encoding specified by the + external protocol or NULL if there is none specified. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate(const XML_Char *encoding); + +/* Constructs a new parser and namespace processor. Element type + names and attribute names that belong to a namespace will be + expanded; unprefixed attribute names are never expanded; unprefixed + element type names are expanded only if there is a default + namespace. The expanded name is the concatenation of the namespace + URI, the namespace separator character, and the local part of the + name. If the namespace separator is '\0' then the namespace URI + and the local part will be concatenated without any separator. + It is a programming error to use the separator '\0' with namespace + triplets (see XML_SetReturnNSTriplet). +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); + +/* Constructs a new parser using the memory management suite referred to + by memsuite. If memsuite is NULL, then use the standard library memory + suite. If namespaceSeparator is non-NULL it creates a parser with + namespace processing as described above. The character pointed at + will serve as the namespace separator. + + All further memory operations used for the created parser will come from + the given suite. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate_MM(const XML_Char *encoding, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *namespaceSeparator); + +/* Prepare a parser object to be re-used. This is particularly + valuable when memory allocation overhead is disproportionately high, + such as when a large number of small documnents need to be parsed. + All handlers are cleared from the parser, except for the + unknownEncodingHandler. The parser's external state is re-initialized + except for the values of ns and ns_triplets. + + Added in Expat 1.95.3. +*/ +XMLPARSEAPI(XML_Bool) +XML_ParserReset(XML_Parser parser, const XML_Char *encoding); + +/* atts is array of name/value pairs, terminated by 0; + names and values are 0 terminated. +*/ +typedef void(XMLCALL *XML_StartElementHandler)(void *userData, + const XML_Char *name, + const XML_Char **atts); + +typedef void(XMLCALL *XML_EndElementHandler)(void *userData, + const XML_Char *name); + +/* s is not 0 terminated. */ +typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData, + const XML_Char *s, int len); + +/* target and data are 0 terminated */ +typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, + const XML_Char *target, + const XML_Char *data); + +/* data is 0 terminated */ +typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data); + +typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData); +typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData); + +/* This is called for any characters in the XML document for which + there is no applicable handler. This includes both characters that + are part of markup which is of a kind that is not reported + (comments, markup declarations), or characters that are part of a + construct which could be reported but for which no handler has been + supplied. The characters are passed exactly as they were in the XML + document except that they will be encoded in UTF-8 or UTF-16. + Line boundaries are not normalized. Note that a byte order mark + character is not passed to the default handler. There are no + guarantees about how characters are divided between calls to the + default handler: for example, a comment might be split between + multiple calls. +*/ +typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s, + int len); + +/* This is called for the start of the DOCTYPE declaration, before + any DTD or internal subset is parsed. +*/ +typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset); + +/* This is called for the start of the DOCTYPE declaration when the + closing > is encountered, but after processing any external + subset. +*/ +typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); + +/* This is called for entity declarations. The is_parameter_entity + argument will be non-zero if the entity is a parameter entity, zero + otherwise. + + For internal entities (<!ENTITY foo "bar">), value will + be non-NULL and systemId, publicID, and notationName will be NULL. + The value string is NOT null-terminated; the length is provided in + the value_length argument. Since it is legal to have zero-length + values, do not use this argument to test for internal entities. + + For external entities, value will be NULL and systemId will be + non-NULL. The publicId argument will be NULL unless a public + identifier was provided. The notationName argument will have a + non-NULL value only for unparsed entity declarations. + + Note that is_parameter_entity can't be changed to XML_Bool, since + that would break binary compatibility. +*/ +typedef void(XMLCALL *XML_EntityDeclHandler)( + void *userData, const XML_Char *entityName, int is_parameter_entity, + const XML_Char *value, int value_length, const XML_Char *base, + const XML_Char *systemId, const XML_Char *publicId, + const XML_Char *notationName); + +XMLPARSEAPI(void) +XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler); + +/* OBSOLETE -- OBSOLETE -- OBSOLETE + This handler has been superseded by the EntityDeclHandler above. + It is provided here for backward compatibility. + + This is called for a declaration of an unparsed (NDATA) entity. + The base argument is whatever was set by XML_SetBase. The + entityName, systemId and notationName arguments will never be + NULL. The other arguments may be. +*/ +typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)( + void *userData, const XML_Char *entityName, const XML_Char *base, + const XML_Char *systemId, const XML_Char *publicId, + const XML_Char *notationName); + +/* This is called for a declaration of notation. The base argument is + whatever was set by XML_SetBase. The notationName will never be + NULL. The other arguments can be. +*/ +typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* When namespace processing is enabled, these are called once for + each namespace declaration. The call to the start and end element + handlers occur between the calls to the start and end namespace + declaration handlers. For an xmlns attribute, prefix will be + NULL. For an xmlns="" attribute, uri will be NULL. +*/ +typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, + const XML_Char *prefix, + const XML_Char *uri); + +typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, + const XML_Char *prefix); + +/* This is called if the document is not standalone, that is, it has an + external subset or a reference to a parameter entity, but does not + have standalone="yes". If this handler returns XML_STATUS_ERROR, + then processing will not continue, and the parser will return a + XML_ERROR_NOT_STANDALONE error. + If parameter entity parsing is enabled, then in addition to the + conditions above this handler will only be called if the referenced + entity was actually read. +*/ +typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData); + +/* This is called for a reference to an external parsed general + entity. The referenced entity is not automatically parsed. The + application can parse it immediately or later using + XML_ExternalEntityParserCreate. + + The parser argument is the parser parsing the entity containing the + reference; it can be passed as the parser argument to + XML_ExternalEntityParserCreate. The systemId argument is the + system identifier as specified in the entity declaration; it will + not be NULL. + + The base argument is the system identifier that should be used as + the base for resolving systemId if systemId was relative; this is + set by XML_SetBase; it may be NULL. + + The publicId argument is the public identifier as specified in the + entity declaration, or NULL if none was specified; the whitespace + in the public identifier will have been normalized as required by + the XML spec. + + The context argument specifies the parsing context in the format + expected by the context argument to XML_ExternalEntityParserCreate; + context is valid only until the handler returns, so if the + referenced entity is to be parsed later, it must be copied. + context is NULL only when the entity is a parameter entity. + + The handler should return XML_STATUS_ERROR if processing should not + continue because of a fatal error in the handling of the external + entity. In this case the calling parser will return an + XML_ERROR_EXTERNAL_ENTITY_HANDLING error. + + Note that unlike other handlers the first argument is the parser, + not userData. +*/ +typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* This is called in two situations: + 1) An entity reference is encountered for which no declaration + has been read *and* this is not an error. + 2) An internal entity reference is read, but not expanded, because + XML_SetDefaultHandler has been called. + Note: skipped parameter entities in declarations and skipped general + entities in attribute values cannot be reported, because + the event would be out of sync with the reporting of the + declarations or attribute values +*/ +typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData, + const XML_Char *entityName, + int is_parameter_entity); + +/* This structure is filled in by the XML_UnknownEncodingHandler to + provide information to the parser about encodings that are unknown + to the parser. + + The map[b] member gives information about byte sequences whose + first byte is b. + + If map[b] is c where c is >= 0, then b by itself encodes the + Unicode scalar value c. + + If map[b] is -1, then the byte sequence is malformed. + + If map[b] is -n, where n >= 2, then b is the first byte of an + n-byte sequence that encodes a single Unicode scalar value. + + The data member will be passed as the first argument to the convert + function. + + The convert function is used to convert multibyte sequences; s will + point to a n-byte sequence where map[(unsigned char)*s] == -n. The + convert function must return the Unicode scalar value represented + by this byte sequence or -1 if the byte sequence is malformed. + + The convert function may be NULL if the encoding is a single-byte + encoding, that is if map[b] >= -1 for all bytes b. + + When the parser is finished with the encoding, then if release is + not NULL, it will call release passing it the data member; once + release has been called, the convert function will not be called + again. + + Expat places certain restrictions on the encodings that are supported + using this mechanism. + + 1. Every ASCII character that can appear in a well-formed XML document, + other than the characters + + $@\^`{}~ + + must be represented by a single byte, and that byte must be the + same byte that represents that character in ASCII. + + 2. No character may require more than 4 bytes to encode. + + 3. All characters encoded must have Unicode scalar values <= + 0xFFFF, (i.e., characters that would be encoded by surrogates in + UTF-16 are not allowed). Note that this restriction doesn't + apply to the built-in support for UTF-8 and UTF-16. + + 4. No Unicode character may be encoded by more than one distinct + sequence of bytes. +*/ +typedef struct { + int map[256]; + void *data; + int(XMLCALL *convert)(void *data, const char *s); + void(XMLCALL *release)(void *data); +} XML_Encoding; + +/* This is called for an encoding that is unknown to the parser. + + The encodingHandlerData argument is that which was passed as the + second argument to XML_SetUnknownEncodingHandler. + + The name argument gives the name of the encoding as specified in + the encoding declaration. + + If the callback can provide information about the encoding, it must + fill in the XML_Encoding structure, and return XML_STATUS_OK. + Otherwise it must return XML_STATUS_ERROR. + + If info does not describe a suitable encoding, then the parser will + return an XML_ERROR_UNKNOWN_ENCODING error. +*/ +typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); + +XMLPARSEAPI(void) +XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, + XML_EndElementHandler end); + +XMLPARSEAPI(void) +XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler); + +XMLPARSEAPI(void) +XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler); + +XMLPARSEAPI(void) +XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler); + +XMLPARSEAPI(void) +XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler); +XMLPARSEAPI(void) +XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler); + +XMLPARSEAPI(void) +XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end); + +XMLPARSEAPI(void) +XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start); + +XMLPARSEAPI(void) +XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end); + +/* This sets the default handler and also inhibits expansion of + internal entities. These entity references will be passed to the + default handler, or to the skipped entity handler, if one is set. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler); + +/* This sets the default handler but does not inhibit expansion of + internal entities. The entity reference will not be passed to the + default handler. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler); + +XMLPARSEAPI(void) +XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler); + +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler); + +/* If a non-NULL value for arg is specified here, then it will be + passed as the first argument to the external entity ref handler + instead of the parser object. +*/ +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg); + +XMLPARSEAPI(void) +XML_SetSkippedEntityHandler(XML_Parser parser, + XML_SkippedEntityHandler handler); + +XMLPARSEAPI(void) +XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, + void *encodingHandlerData); + +/* This can be called within a handler for a start element, end + element, processing instruction or character data. It causes the + corresponding markup to be passed to the default handler. +*/ +XMLPARSEAPI(void) +XML_DefaultCurrent(XML_Parser parser); + +/* If do_nst is non-zero, and namespace processing is in effect, and + a name has a prefix (i.e. an explicit namespace qualifier) then + that name is returned as a triplet in a single string separated by + the separator character specified when the parser was created: URI + + sep + local_name + sep + prefix. + + If do_nst is zero, then namespace information is returned in the + default manner (URI + sep + local_name) whether or not the name + has a prefix. + + Note: Calling XML_SetReturnNSTriplet after XML_Parse or + XML_ParseBuffer has no effect. +*/ + +XMLPARSEAPI(void) +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); + +/* This value is passed as the userData argument to callbacks. */ +XMLPARSEAPI(void) +XML_SetUserData(XML_Parser parser, void *userData); + +/* Returns the last value set by XML_SetUserData or NULL. */ +#define XML_GetUserData(parser) (*(void **)(parser)) + +/* This is equivalent to supplying an encoding argument to + XML_ParserCreate. On success XML_SetEncoding returns non-zero, + zero otherwise. + Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer + has no effect and returns XML_STATUS_ERROR. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); + +/* If this function is called, then the parser will be passed as the + first argument to callbacks instead of userData. The userData will + still be accessible using XML_GetUserData. +*/ +XMLPARSEAPI(void) +XML_UseParserAsHandlerArg(XML_Parser parser); + +/* If useDTD == XML_TRUE is passed to this function, then the parser + will assume that there is an external subset, even if none is + specified in the document. In such a case the parser will call the + externalEntityRefHandler with a value of NULL for the systemId + argument (the publicId and context arguments will be NULL as well). + Note: For the purpose of checking WFC: Entity Declared, passing + useDTD == XML_TRUE will make the parser behave as if the document + had a DTD with an external subset. + Note: If this function is called, then this must be done before + the first call to XML_Parse or XML_ParseBuffer, since it will + have no effect after that. Returns + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. + Note: If the document does not have a DOCTYPE declaration at all, + then startDoctypeDeclHandler and endDoctypeDeclHandler will not + be called, despite an external subset being parsed. + Note: If XML_DTD is not defined when Expat is compiled, returns + XML_ERROR_FEATURE_REQUIRES_XML_DTD. + Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. +*/ +XMLPARSEAPI(enum XML_Error) +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); + +/* Sets the base to be used for resolving relative URIs in system + identifiers in declarations. Resolving relative identifiers is + left to the application: this value will be passed through as the + base argument to the XML_ExternalEntityRefHandler, + XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base + argument will be copied. Returns XML_STATUS_ERROR if out of memory, + XML_STATUS_OK otherwise. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetBase(XML_Parser parser, const XML_Char *base); + +XMLPARSEAPI(const XML_Char *) +XML_GetBase(XML_Parser parser); + +/* Returns the number of the attribute/value pairs passed in last call + to the XML_StartElementHandler that were specified in the start-tag + rather than defaulted. Each attribute/value pair counts as 2; thus + this corresponds to an index into the atts array passed to the + XML_StartElementHandler. Returns -1 if parser == NULL. +*/ +XMLPARSEAPI(int) +XML_GetSpecifiedAttributeCount(XML_Parser parser); + +/* Returns the index of the ID attribute passed in the last call to + XML_StartElementHandler, or -1 if there is no ID attribute or + parser == NULL. Each attribute/value pair counts as 2; thus this + corresponds to an index into the atts array passed to the + XML_StartElementHandler. +*/ +XMLPARSEAPI(int) +XML_GetIdAttributeIndex(XML_Parser parser); + +#ifdef XML_ATTR_INFO +/* Source file byte offsets for the start and end of attribute names and values. + The value indices are exclusive of surrounding quotes; thus in a UTF-8 source + file an attribute value of "blah" will yield: + info->valueEnd - info->valueStart = 4 bytes. +*/ +typedef struct { + XML_Index nameStart; /* Offset to beginning of the attribute name. */ + XML_Index nameEnd; /* Offset after the attribute name's last byte. */ + XML_Index valueStart; /* Offset to beginning of the attribute value. */ + XML_Index valueEnd; /* Offset after the attribute value's last byte. */ +} XML_AttrInfo; + +/* Returns an array of XML_AttrInfo structures for the attribute/value pairs + passed in last call to the XML_StartElementHandler that were specified + in the start-tag rather than defaulted. Each attribute/value pair counts + as 1; thus the number of entries in the array is + XML_GetSpecifiedAttributeCount(parser) / 2. +*/ +XMLPARSEAPI(const XML_AttrInfo *) +XML_GetAttributeInfo(XML_Parser parser); +#endif + +/* Parses some input. Returns XML_STATUS_ERROR if a fatal error is + detected. The last call to XML_Parse must have isFinal true; len + may be zero for this call (or any other). + + Though the return values for these functions has always been + described as a Boolean value, the implementation, at least for the + 1.95.x series, has always returned exactly one of the XML_Status + values. +*/ +XMLPARSEAPI(enum XML_Status) +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); + +XMLPARSEAPI(void *) +XML_GetBuffer(XML_Parser parser, int len); + +XMLPARSEAPI(enum XML_Status) +XML_ParseBuffer(XML_Parser parser, int len, int isFinal); + +/* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. + Must be called from within a call-back handler, except when aborting + (resumable = 0) an already suspended parser. Some call-backs may + still follow because they would otherwise get lost. Examples: + - endElementHandler() for empty elements when stopped in + startElementHandler(), + - endNameSpaceDeclHandler() when stopped in endElementHandler(), + and possibly others. + + Can be called from most handlers, including DTD related call-backs, + except when parsing an external parameter entity and resumable != 0. + Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. + Possible error codes: + - XML_ERROR_SUSPENDED: when suspending an already suspended parser. + - XML_ERROR_FINISHED: when the parser has already finished. + - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. + + When resumable != 0 (true) then parsing is suspended, that is, + XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. + Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() + return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. + + *Note*: + This will be applied to the current parser instance only, that is, if + there is a parent parser then it will continue parsing when the + externalEntityRefHandler() returns. It is up to the implementation of + the externalEntityRefHandler() to call XML_StopParser() on the parent + parser (recursively), if one wants to stop parsing altogether. + + When suspended, parsing can be resumed by calling XML_ResumeParser(). +*/ +XMLPARSEAPI(enum XML_Status) +XML_StopParser(XML_Parser parser, XML_Bool resumable); + +/* Resumes parsing after it has been suspended with XML_StopParser(). + Must not be called from within a handler call-back. Returns same + status codes as XML_Parse() or XML_ParseBuffer(). + Additional error code XML_ERROR_NOT_SUSPENDED possible. + + *Note*: + This must be called on the most deeply nested child parser instance + first, and on its parent parser only after the child parser has finished, + to be applied recursively until the document entity's parser is restarted. + That is, the parent parser will not resume by itself and it is up to the + application to call XML_ResumeParser() on it at the appropriate moment. +*/ +XMLPARSEAPI(enum XML_Status) +XML_ResumeParser(XML_Parser parser); + +enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED }; + +typedef struct { + enum XML_Parsing parsing; + XML_Bool finalBuffer; +} XML_ParsingStatus; + +/* Returns status of parser with respect to being initialized, parsing, + finished, or suspended and processing the final buffer. + XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, + XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED +*/ +XMLPARSEAPI(void) +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); + +/* Creates an XML_Parser object that can parse an external general + entity; context is a '\0'-terminated string specifying the parse + context; encoding is a '\0'-terminated string giving the name of + the externally specified encoding, or NULL if there is no + externally specified encoding. The context string consists of a + sequence of tokens separated by formfeeds (\f); a token consisting + of a name specifies that the general entity of the name is open; a + token of the form prefix=uri specifies the namespace for a + particular prefix; a token of the form =uri specifies the default + namespace. This can be called at any point after the first call to + an ExternalEntityRefHandler so longer as the parser has not yet + been freed. The new parser is completely independent and may + safely be used in a separate thread. The handlers and userData are + initialized from the parser argument. Returns NULL if out of memory. + Otherwise returns a new XML_Parser object. +*/ +XMLPARSEAPI(XML_Parser) +XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context, + const XML_Char *encoding); + +enum XML_ParamEntityParsing { + XML_PARAM_ENTITY_PARSING_NEVER, + XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, + XML_PARAM_ENTITY_PARSING_ALWAYS +}; + +/* Controls parsing of parameter entities (including the external DTD + subset). If parsing of parameter entities is enabled, then + references to external parameter entities (including the external + DTD subset) will be passed to the handler set with + XML_SetExternalEntityRefHandler. The context passed will be 0. + + Unlike external general entities, external parameter entities can + only be parsed synchronously. If the external parameter entity is + to be parsed, it must be parsed during the call to the external + entity ref handler: the complete sequence of + XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and + XML_ParserFree calls must be made during this call. After + XML_ExternalEntityParserCreate has been called to create the parser + for the external parameter entity (context must be 0 for this + call), it is illegal to make any calls on the old parser until + XML_ParserFree has been called on the newly created parser. + If the library has been compiled without support for parameter + entity parsing (ie without XML_DTD being defined), then + XML_SetParamEntityParsing will return 0 if parsing of parameter + entities is requested; otherwise it will return non-zero. + Note: If XML_SetParamEntityParsing is called after XML_Parse or + XML_ParseBuffer, then it has no effect and will always return 0. + Note: If parser == NULL, the function will do nothing and return 0. +*/ +XMLPARSEAPI(int) +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing parsing); + +/* Sets the hash salt to use for internal hash calculations. + Helps in preventing DoS attacks based on predicting hash + function behavior. This must be called before parsing is started. + Returns 1 if successful, 0 when called after parsing has started. + Note: If parser == NULL, the function will do nothing and return 0. +*/ +XMLPARSEAPI(int) +XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt); + +/* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then + XML_GetErrorCode returns information about the error. +*/ +XMLPARSEAPI(enum XML_Error) +XML_GetErrorCode(XML_Parser parser); + +/* These functions return information about the current parse + location. They may be called from any callback called to report + some parse event; in this case the location is the location of the + first of the sequence of characters that generated the event. When + called from callbacks generated by declarations in the document + prologue, the location identified isn't as neatly defined, but will + be within the relevant markup. When called outside of the callback + functions, the position indicated will be just past the last parse + event (regardless of whether there was an associated callback). + + They may also be called after returning from a call to XML_Parse + or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then + the location is the location of the character at which the error + was detected; otherwise the location is the location of the last + parse event, as described above. + + Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber + return 0 to indicate an error. + Note: XML_GetCurrentByteIndex returns -1 to indicate an error. +*/ +XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); +XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); +XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); + +/* Return the number of bytes in the current event. + Returns 0 if the event is in an internal entity. +*/ +XMLPARSEAPI(int) +XML_GetCurrentByteCount(XML_Parser parser); + +/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets + the integer pointed to by offset to the offset within this buffer + of the current parse position, and sets the integer pointed to by size + to the size of this buffer (the number of input bytes). Otherwise + returns a NULL pointer. Also returns a NULL pointer if a parse isn't + active. + + NOTE: The character pointer returned should not be used outside + the handler that makes the call. +*/ +XMLPARSEAPI(const char *) +XML_GetInputContext(XML_Parser parser, int *offset, int *size); + +/* For backwards compatibility with previous versions. */ +#define XML_GetErrorLineNumber XML_GetCurrentLineNumber +#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber +#define XML_GetErrorByteIndex XML_GetCurrentByteIndex + +/* Frees the content model passed to the element declaration handler */ +XMLPARSEAPI(void) +XML_FreeContentModel(XML_Parser parser, XML_Content *model); + +/* Exposing the memory handling functions used in Expat */ +XMLPARSEAPI(void *) +XML_ATTR_MALLOC +XML_ATTR_ALLOC_SIZE(2) +XML_MemMalloc(XML_Parser parser, size_t size); + +XMLPARSEAPI(void *) +XML_ATTR_ALLOC_SIZE(3) +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); + +XMLPARSEAPI(void) +XML_MemFree(XML_Parser parser, void *ptr); + +/* Frees memory used by the parser. */ +XMLPARSEAPI(void) +XML_ParserFree(XML_Parser parser); + +/* Returns a string describing the error. */ +XMLPARSEAPI(const XML_LChar *) +XML_ErrorString(enum XML_Error code); + +/* Return a string containing the version number of this expat */ +XMLPARSEAPI(const XML_LChar *) +XML_ExpatVersion(void); + +typedef struct { + int major; + int minor; + int micro; +} XML_Expat_Version; + +/* Return an XML_Expat_Version structure containing numeric version + number information for this version of expat. +*/ +XMLPARSEAPI(XML_Expat_Version) +XML_ExpatVersionInfo(void); + +/* Added in Expat 1.95.5. */ +enum XML_FeatureEnum { + XML_FEATURE_END = 0, + XML_FEATURE_UNICODE, + XML_FEATURE_UNICODE_WCHAR_T, + XML_FEATURE_DTD, + XML_FEATURE_CONTEXT_BYTES, + XML_FEATURE_MIN_SIZE, + XML_FEATURE_SIZEOF_XML_CHAR, + XML_FEATURE_SIZEOF_XML_LCHAR, + XML_FEATURE_NS, + XML_FEATURE_LARGE_SIZE, + XML_FEATURE_ATTR_INFO, + /* Added in Expat 2.4.0. */ + XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, + XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT + /* Additional features must be added to the end of this enum. */ +}; + +typedef struct { + enum XML_FeatureEnum feature; + const XML_LChar *name; + long int value; +} XML_Feature; + +XMLPARSEAPI(const XML_Feature *) +XML_GetFeatureList(void); + +#ifdef XML_DTD +/* Added in Expat 2.4.0. */ +XMLPARSEAPI(XML_Bool) +XML_SetBillionLaughsAttackProtectionMaximumAmplification( + XML_Parser parser, float maximumAmplificationFactor); + +/* Added in Expat 2.4.0. */ +XMLPARSEAPI(XML_Bool) +XML_SetBillionLaughsAttackProtectionActivationThreshold( + XML_Parser parser, unsigned long long activationThresholdBytes); +#endif + +/* Expat follows the semantic versioning convention. + See http://semver.org. +*/ +#define XML_MAJOR_VERSION 2 +#define XML_MINOR_VERSION 4 +#define XML_MICRO_VERSION 6 + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_INCLUDED */ diff --git a/Utilities/cmexpat/lib/expat_external.h b/Utilities/cmexpat/lib/expat_external.h new file mode 100644 index 0000000000..e03cb445c2 --- /dev/null +++ b/Utilities/cmexpat/lib/expat_external.h @@ -0,0 +1,168 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2004 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016 Cristian RodrÃguez <crrodriguez@opensuse.org> + Copyright (c) 2016-2019 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2018 Yury Gribov <tetra2005@gmail.com> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifndef Expat_External_INCLUDED +#define Expat_External_INCLUDED 1 + +/* External API definitions */ + +/* Expat tries very hard to make the API boundary very specifically + defined. There are two macros defined to control this boundary; + each of these can be defined before including this header to + achieve some different behavior, but doing so it not recommended or + tested frequently. + + XMLCALL - The calling convention to use for all calls across the + "library boundary." This will default to cdecl, and + try really hard to tell the compiler that's what we + want. + + XMLIMPORT - Whatever magic is needed to note that a function is + to be imported from a dynamically loaded library + (.dll, .so, or .sl, depending on your platform). + + The XMLCALL macro was added in Expat 1.95.7. The only one which is + expected to be directly useful in client code is XMLCALL. + + Note that on at least some Unix versions, the Expat library must be + compiled with the cdecl calling convention as the default since + system headers may assume the cdecl convention. +*/ +#ifndef XMLCALL +# if defined(_MSC_VER) +# define XMLCALL __cdecl +# elif defined(__GNUC__) && defined(__i386) && ! defined(__INTEL_COMPILER) +# define XMLCALL __attribute__((cdecl)) +# else +/* For any platform which uses this definition and supports more than + one calling convention, we need to extend this definition to + declare the convention used on that platform, if it's possible to + do so. + + If this is the case for your platform, please file a bug report + with information on how to identify your platform via the C + pre-processor and how to specify the same calling convention as the + platform's malloc() implementation. +*/ +# define XMLCALL +# endif +#endif /* not defined XMLCALL */ + +/* Build within CMake hard-codes use of a static library. */ +#define XML_STATIC + +#if ! defined(XML_STATIC) && ! defined(XMLIMPORT) +# ifndef XML_BUILDING_EXPAT +/* using Expat from an application */ + +# if defined(_MSC_EXTENSIONS) && ! defined(__BEOS__) && ! defined(__CYGWIN__) +# define XMLIMPORT __declspec(dllimport) +# endif + +# endif +#endif /* not defined XML_STATIC */ + +#ifndef XML_ENABLE_VISIBILITY +# define XML_ENABLE_VISIBILITY 0 +#endif + +#if ! defined(XMLIMPORT) && XML_ENABLE_VISIBILITY +# define XMLIMPORT __attribute__((visibility("default"))) +#endif + +/* If we didn't define it above, define it away: */ +#ifndef XMLIMPORT +# define XMLIMPORT +#endif + +#if defined(__GNUC__) \ + && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)) +# define XML_ATTR_MALLOC __attribute__((__malloc__)) +#else +# define XML_ATTR_MALLOC +#endif + +#if defined(__GNUC__) \ + && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) +# define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x))) +#else +# define XML_ATTR_ALLOC_SIZE(x) +#endif + +#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL + +#ifdef __cplusplus +extern "C" { +#endif + +#ifdef XML_UNICODE_WCHAR_T +# ifndef XML_UNICODE +# define XML_UNICODE +# endif +# if defined(__SIZEOF_WCHAR_T__) && (__SIZEOF_WCHAR_T__ != 2) +# error "sizeof(wchar_t) != 2; Need -fshort-wchar for both Expat and libc" +# endif +#endif + +#ifdef XML_UNICODE /* Information is UTF-16 encoded. */ +# ifdef XML_UNICODE_WCHAR_T +typedef wchar_t XML_Char; +typedef wchar_t XML_LChar; +# else +typedef unsigned short XML_Char; +typedef char XML_LChar; +# endif /* XML_UNICODE_WCHAR_T */ +#else /* Information is UTF-8 encoded. */ +typedef char XML_Char; +typedef char XML_LChar; +#endif /* XML_UNICODE */ + +#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */ +typedef long long XML_Index; +typedef unsigned long long XML_Size; +#else +typedef long XML_Index; +typedef unsigned long XML_Size; +#endif /* XML_LARGE_SIZE */ + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_External_INCLUDED */ diff --git a/Utilities/cmexpat/lib/iasciitab.h b/Utilities/cmexpat/lib/iasciitab.h new file mode 100644 index 0000000000..5d8646f2a3 --- /dev/null +++ b/Utilities/cmexpat/lib/iasciitab.h @@ -0,0 +1,67 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, + /* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML, + /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, + /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, + /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, + /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, + /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, + /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, + /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, + /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, + /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/Utilities/cmexpat/lib/internal.h b/Utilities/cmexpat/lib/internal.h new file mode 100644 index 0000000000..444eba0fb0 --- /dev/null +++ b/Utilities/cmexpat/lib/internal.h @@ -0,0 +1,163 @@ +/* internal.h + + Internal definitions used by Expat. This is not needed to compile + client code. + + The following calling convention macros are defined for frequently + called functions: + + FASTCALL - Used for those internal functions that have a simple + body and a low number of arguments and local variables. + + PTRCALL - Used for functions called though function pointers. + + PTRFASTCALL - Like PTRCALL, but for low number of arguments. + + inline - Used for selected internal functions for which inlining + may improve performance on some platforms. + + Note: Use of these macros is based on judgement, not hard rules, + and therefore subject to change. + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2003 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2016-2021 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2018 Yury Gribov <tetra2005@gmail.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#if defined(__GNUC__) && defined(__i386__) && ! defined(__MINGW32__) +/* We'll use this version by default only where we know it helps. + + regparm() generates warnings on Solaris boxes. See SF bug #692878. + + Instability reported with egcs on a RedHat Linux 7.3. + Let's comment out: + #define FASTCALL __attribute__((stdcall, regparm(3))) + and let's try this: +*/ +# define FASTCALL __attribute__((regparm(3))) +# define PTRFASTCALL __attribute__((regparm(3))) +#endif + +/* Using __fastcall seems to have an unexpected negative effect under + MS VC++, especially for function pointers, so we won't use it for + now on that platform. It may be reconsidered for a future release + if it can be made more effective. + Likely reason: __fastcall on Windows is like stdcall, therefore + the compiler cannot perform stack optimizations for call clusters. +*/ + +/* Make sure all of these are defined if they aren't already. */ + +#ifndef FASTCALL +# define FASTCALL +#endif + +#ifndef PTRCALL +# define PTRCALL +#endif + +#ifndef PTRFASTCALL +# define PTRFASTCALL +#endif + +#ifndef XML_MIN_SIZE +# if ! defined(__cplusplus) && ! defined(inline) +# ifdef __GNUC__ +# define inline __inline +# endif /* __GNUC__ */ +# endif +#endif /* XML_MIN_SIZE */ + +#ifdef __cplusplus +# define inline inline +#else +# ifndef inline +# define inline +# endif +#endif + +#include <limits.h> // ULONG_MAX + +#if defined(_WIN32) && ! defined(__USE_MINGW_ANSI_STDIO) +# define EXPAT_FMT_ULL(midpart) "%" midpart "I64u" +# if defined(_WIN64) // Note: modifiers "td" and "zu" do not work for MinGW +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "I64d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "I64u" +# else +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u" +# endif +#else +# define EXPAT_FMT_ULL(midpart) "%" midpart "llu" +# if ! defined(ULONG_MAX) +# error Compiler did not define ULONG_MAX for us +# elif ULONG_MAX == 18446744073709551615u // 2^64-1 +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "ld" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "lu" +# else +# define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d" +# define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u" +# endif +#endif + +#ifndef UNUSED_P +# define UNUSED_P(p) (void)p +#endif + +/* NOTE BEGIN If you ever patch these defaults to greater values + for non-attack XML payload in your environment, + please file a bug report with libexpat. Thank you! +*/ +#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT \ + 100.0f +#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT \ + 8388608 // 8 MiB, 2^23 +/* NOTE END */ + +#include "expat.h" // so we can use type XML_Parser below + +#ifdef __cplusplus +extern "C" { +#endif + +void _INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef); + +#if defined(XML_DTD) +unsigned long long testingAccountingGetCountBytesDirect(XML_Parser parser); +unsigned long long testingAccountingGetCountBytesIndirect(XML_Parser parser); +const char *unsignedCharToPrintable(unsigned char c); +#endif + +#ifdef __cplusplus +} +#endif diff --git a/Utilities/cmexpat/lib/latin1tab.h b/Utilities/cmexpat/lib/latin1tab.h new file mode 100644 index 0000000000..b681d278af --- /dev/null +++ b/Utilities/cmexpat/lib/latin1tab.h @@ -0,0 +1,66 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, + /* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME, + /* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, + /* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, diff --git a/Utilities/cmexpat/lib/nametab.h b/Utilities/cmexpat/lib/nametab.h new file mode 100644 index 0000000000..63485446b9 --- /dev/null +++ b/Utilities/cmexpat/lib/nametab.h @@ -0,0 +1,136 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +static const unsigned namingBitmap[] = { + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x04000000, + 0x87FFFFFE, 0x07FFFFFE, 0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, + 0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFE00F, 0xFC31FFFF, 0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, + 0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, + 0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, 0xFFFF0003, 0xFFFFFFFF, + 0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, + 0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF, 0x00000000, 0x07FFFFFE, + 0x000007FE, 0xFFFE0000, 0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060, + 0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, 0xFFF99FE0, 0x03C5FDFF, + 0xB0000000, 0x00030003, 0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000, + 0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, 0xFFF99FE0, 0x23CDFDFF, + 0xB0000000, 0x00000003, 0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, + 0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003, 0xFFFDDFE0, 0x03EFFDFF, + 0x40000000, 0x00000003, 0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFE, 0x000D7FFF, + 0x0000003F, 0x00000000, 0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF, 0x0007DAED, 0x50000000, + 0x82315001, 0x002C62AB, 0x40000000, 0xF580C900, 0x00000007, 0x02010800, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0FFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0x03FFFFFF, 0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, + 0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, 0x00000000, 0x00004C40, + 0x00000000, 0x00000000, 0x00000007, 0x00000000, 0x00000000, 0x00000000, + 0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF, 0x001FFFFF, 0xFFFFFFFE, + 0xFFFFFFFF, 0x07FFFFFF, 0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0000000F, + 0x00000000, 0x00000000, 0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, + 0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF, 0x00FFFFFF, 0x00000000, + 0xFFFF0000, 0xFFFFFFFF, 0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000, + 0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, 0xFFFFD7C0, 0xFFFFFFFB, + 0x547F7FFF, 0x000FFFFD, 0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, + 0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000, + 0x027FFFFF, 0xFFFFFFFE, 0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, + 0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF, 0xFFFFFFFF, 0x7CFFFFFF, + 0xFFEF7FFF, 0x03FF3DFF, 0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF, + 0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, 0xFFF987E4, 0xD36DFDFF, + 0x5E003987, 0x001FFFC0, 0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, + 0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, 0xD63DC7EC, 0xC3BFC718, + 0x00803DC7, 0x0000FF80, 0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, + 0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3, 0xFFFDDFEC, 0xC3FFFDFF, + 0x00803DCF, 0x0000FFC3, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, 0xFEF02596, 0x3BFF6CAE, + 0x03FF3F5F, 0x00000000, 0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, + 0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, + 0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF, 0x661FFFFF, 0xFFFFFFFE, + 0xFFFFFFFF, 0x77FFFFFF, +}; +static const unsigned char nmstrtPages[] = { + 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, 0x00, 0x09, 0x0A, 0x0B, + 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x00, 0x14, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x15, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, +}; +static const unsigned char namePages[] = { + 0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, 0x00, 0x1F, 0x20, 0x21, + 0x22, 0x23, 0x24, 0x25, 0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x26, 0x14, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x27, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, +}; diff --git a/Utilities/cmexpat/lib/siphash.h b/Utilities/cmexpat/lib/siphash.h new file mode 100644 index 0000000000..952f1c88b7 --- /dev/null +++ b/Utilities/cmexpat/lib/siphash.h @@ -0,0 +1,404 @@ +/* ========================================================================== + * siphash.h - SipHash-2-4 in a single header file + * -------------------------------------------------------------------------- + * Derived by William Ahern from the reference implementation[1] published[2] + * by Jean-Philippe Aumasson and Daniel J. Berstein. + * Minimal changes by Sebastian Pipping and Victor Stinner on top, see below. + * Licensed under the CC0 Public Domain Dedication license. + * + * 1. https://www.131002.net/siphash/siphash24.c + * 2. https://www.131002.net/siphash/ + * -------------------------------------------------------------------------- + * HISTORY: + * + * 2020-10-03 (Sebastian Pipping) + * - Drop support for Visual Studio 9.0/2008 and earlier + * + * 2019-08-03 (Sebastian Pipping) + * - Mark part of sip24_valid as to be excluded from clang-format + * - Re-format code using clang-format 9 + * + * 2018-07-08 (Anton Maklakov) + * - Add "fall through" markers for GCC's -Wimplicit-fallthrough + * + * 2017-11-03 (Sebastian Pipping) + * - Hide sip_tobin and sip_binof unless SIPHASH_TOBIN macro is defined + * + * 2017-07-25 (Vadim Zeitlin) + * - Fix use of SIPHASH_MAIN macro + * + * 2017-07-05 (Sebastian Pipping) + * - Use _SIP_ULL macro to not require a C++11 compiler if compiled as C++ + * - Add const qualifiers at two places + * - Ensure <=80 characters line length (assuming tab width 4) + * + * 2017-06-23 (Victor Stinner) + * - Address Win64 compile warnings + * + * 2017-06-18 (Sebastian Pipping) + * - Clarify license note in the header + * - Address C89 issues: + * - Stop using inline keyword (and let compiler decide) + * - Replace _Bool by int + * - Turn macro siphash24 into a function + * - Address invalid conversion (void pointer) by explicit cast + * - Address lack of stdint.h for Visual Studio 2003 to 2008 + * - Always expose sip24_valid (for self-tests) + * + * 2012-11-04 - Born. (William Ahern) + * -------------------------------------------------------------------------- + * USAGE: + * + * SipHash-2-4 takes as input two 64-bit words as the key, some number of + * message bytes, and outputs a 64-bit word as the message digest. This + * implementation employs two data structures: a struct sipkey for + * representing the key, and a struct siphash for representing the hash + * state. + * + * For converting a 16-byte unsigned char array to a key, use either the + * macro sip_keyof or the routine sip_tokey. The former instantiates a + * compound literal key, while the latter requires a key object as a + * parameter. + * + * unsigned char secret[16]; + * arc4random_buf(secret, sizeof secret); + * struct sipkey *key = sip_keyof(secret); + * + * For hashing a message, use either the convenience macro siphash24 or the + * routines sip24_init, sip24_update, and sip24_final. + * + * struct siphash state; + * void *msg; + * size_t len; + * uint64_t hash; + * + * sip24_init(&state, key); + * sip24_update(&state, msg, len); + * hash = sip24_final(&state); + * + * or + * + * hash = siphash24(msg, len, key); + * + * To convert the 64-bit hash value to a canonical 8-byte little-endian + * binary representation, use either the macro sip_binof or the routine + * sip_tobin. The former instantiates and returns a compound literal array, + * while the latter requires an array object as a parameter. + * -------------------------------------------------------------------------- + * NOTES: + * + * o Neither sip_keyof, sip_binof, nor siphash24 will work with compilers + * lacking compound literal support. Instead, you must use the lower-level + * interfaces which take as parameters the temporary state objects. + * + * o Uppercase macros may evaluate parameters more than once. Lowercase + * macros should not exhibit any such side effects. + * ========================================================================== + */ +#ifndef SIPHASH_H +#define SIPHASH_H + +#include <stddef.h> /* size_t */ + +#include <cm3p/kwiml/int.h> + +#ifndef KWIML_INT_HAVE_UINT64_T +# define uint64_t KWIML_INT_uint64_t +#endif +#ifndef KWIML_INT_HAVE_UINT32_T +# define uint32_t KWIML_INT_uint32_t +#endif +#ifndef KWIML_INT_HAVE_UINT8_T +# define uint8_t KWIML_INT_uint8_t +#endif + +/* + * Workaround to not require a C++11 compiler for using ULL suffix + * if this code is included and compiled as C++; related GCC warning is: + * warning: use of C++11 long long integer constant [-Wlong-long] + */ +#define _SIP_ULL(high, low) (((uint64_t)high << 32) | low) + +#define SIP_ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b)))) + +#define SIP_U32TO8_LE(p, v) \ + (p)[0] = (uint8_t)((v) >> 0); \ + (p)[1] = (uint8_t)((v) >> 8); \ + (p)[2] = (uint8_t)((v) >> 16); \ + (p)[3] = (uint8_t)((v) >> 24); + +#define SIP_U64TO8_LE(p, v) \ + SIP_U32TO8_LE((p) + 0, (uint32_t)((v) >> 0)); \ + SIP_U32TO8_LE((p) + 4, (uint32_t)((v) >> 32)); + +#define SIP_U8TO64_LE(p) \ + (((uint64_t)((p)[0]) << 0) | ((uint64_t)((p)[1]) << 8) \ + | ((uint64_t)((p)[2]) << 16) | ((uint64_t)((p)[3]) << 24) \ + | ((uint64_t)((p)[4]) << 32) | ((uint64_t)((p)[5]) << 40) \ + | ((uint64_t)((p)[6]) << 48) | ((uint64_t)((p)[7]) << 56)) + +#define SIPHASH_INITIALIZER \ + { 0, 0, 0, 0, {0}, 0, 0 } + +struct siphash { + uint64_t v0, v1, v2, v3; + + unsigned char buf[8], *p; + uint64_t c; +}; /* struct siphash */ + +#define SIP_KEYLEN 16 + +struct sipkey { + uint64_t k[2]; +}; /* struct sipkey */ + +#define sip_keyof(k) sip_tokey(&(struct sipkey){{0}}, (k)) + +static struct sipkey * +sip_tokey(struct sipkey *key, const void *src) { + key->k[0] = SIP_U8TO64_LE((const unsigned char *)src); + key->k[1] = SIP_U8TO64_LE((const unsigned char *)src + 8); + return key; +} /* sip_tokey() */ + +#ifdef SIPHASH_TOBIN + +# define sip_binof(v) sip_tobin((unsigned char[8]){0}, (v)) + +static void * +sip_tobin(void *dst, uint64_t u64) { + SIP_U64TO8_LE((unsigned char *)dst, u64); + return dst; +} /* sip_tobin() */ + +#endif /* SIPHASH_TOBIN */ + +static void +sip_round(struct siphash *H, const int rounds) { + int i; + + for (i = 0; i < rounds; i++) { + H->v0 += H->v1; + H->v1 = SIP_ROTL(H->v1, 13); + H->v1 ^= H->v0; + H->v0 = SIP_ROTL(H->v0, 32); + + H->v2 += H->v3; + H->v3 = SIP_ROTL(H->v3, 16); + H->v3 ^= H->v2; + + H->v0 += H->v3; + H->v3 = SIP_ROTL(H->v3, 21); + H->v3 ^= H->v0; + + H->v2 += H->v1; + H->v1 = SIP_ROTL(H->v1, 17); + H->v1 ^= H->v2; + H->v2 = SIP_ROTL(H->v2, 32); + } +} /* sip_round() */ + +static struct siphash * +sip24_init(struct siphash *H, const struct sipkey *key) { + H->v0 = _SIP_ULL(0x736f6d65U, 0x70736575U) ^ key->k[0]; + H->v1 = _SIP_ULL(0x646f7261U, 0x6e646f6dU) ^ key->k[1]; + H->v2 = _SIP_ULL(0x6c796765U, 0x6e657261U) ^ key->k[0]; + H->v3 = _SIP_ULL(0x74656462U, 0x79746573U) ^ key->k[1]; + + H->p = H->buf; + H->c = 0; + + return H; +} /* sip24_init() */ + +#define sip_endof(a) (&(a)[sizeof(a) / sizeof *(a)]) + +static struct siphash * +sip24_update(struct siphash *H, const void *src, size_t len) { + const unsigned char *p = (const unsigned char *)src, *pe = p + len; + uint64_t m; + + do { + while (p < pe && H->p < sip_endof(H->buf)) + *H->p++ = *p++; + + if (H->p < sip_endof(H->buf)) + break; + + m = SIP_U8TO64_LE(H->buf); + H->v3 ^= m; + sip_round(H, 2); + H->v0 ^= m; + + H->p = H->buf; + H->c += 8; + } while (p < pe); + + return H; +} /* sip24_update() */ + +static uint64_t +sip24_final(struct siphash *H) { + const char left = (char)(H->p - H->buf); + uint64_t b = (H->c + left) << 56; + + switch (left) { + case 7: + b |= (uint64_t)H->buf[6] << 48; + /* fall through */ + case 6: + b |= (uint64_t)H->buf[5] << 40; + /* fall through */ + case 5: + b |= (uint64_t)H->buf[4] << 32; + /* fall through */ + case 4: + b |= (uint64_t)H->buf[3] << 24; + /* fall through */ + case 3: + b |= (uint64_t)H->buf[2] << 16; + /* fall through */ + case 2: + b |= (uint64_t)H->buf[1] << 8; + /* fall through */ + case 1: + b |= (uint64_t)H->buf[0] << 0; + /* fall through */ + case 0: + break; + } + + H->v3 ^= b; + sip_round(H, 2); + H->v0 ^= b; + H->v2 ^= 0xff; + sip_round(H, 4); + + return H->v0 ^ H->v1 ^ H->v2 ^ H->v3; +} /* sip24_final() */ + +static uint64_t +siphash24(const void *src, size_t len, const struct sipkey *key) { + struct siphash state = SIPHASH_INITIALIZER; + return sip24_final(sip24_update(sip24_init(&state, key), src, len)); +} /* siphash24() */ + +/* + * SipHash-2-4 output with + * k = 00 01 02 ... + * and + * in = (empty string) + * in = 00 (1 byte) + * in = 00 01 (2 bytes) + * in = 00 01 02 (3 bytes) + * ... + * in = 00 01 02 ... 3e (63 bytes) + */ +static int +sip24_valid(void) { + /* clang-format off */ + static const unsigned char vectors[64][8] = { + { 0x31, 0x0e, 0x0e, 0xdd, 0x47, 0xdb, 0x6f, 0x72, }, + { 0xfd, 0x67, 0xdc, 0x93, 0xc5, 0x39, 0xf8, 0x74, }, + { 0x5a, 0x4f, 0xa9, 0xd9, 0x09, 0x80, 0x6c, 0x0d, }, + { 0x2d, 0x7e, 0xfb, 0xd7, 0x96, 0x66, 0x67, 0x85, }, + { 0xb7, 0x87, 0x71, 0x27, 0xe0, 0x94, 0x27, 0xcf, }, + { 0x8d, 0xa6, 0x99, 0xcd, 0x64, 0x55, 0x76, 0x18, }, + { 0xce, 0xe3, 0xfe, 0x58, 0x6e, 0x46, 0xc9, 0xcb, }, + { 0x37, 0xd1, 0x01, 0x8b, 0xf5, 0x00, 0x02, 0xab, }, + { 0x62, 0x24, 0x93, 0x9a, 0x79, 0xf5, 0xf5, 0x93, }, + { 0xb0, 0xe4, 0xa9, 0x0b, 0xdf, 0x82, 0x00, 0x9e, }, + { 0xf3, 0xb9, 0xdd, 0x94, 0xc5, 0xbb, 0x5d, 0x7a, }, + { 0xa7, 0xad, 0x6b, 0x22, 0x46, 0x2f, 0xb3, 0xf4, }, + { 0xfb, 0xe5, 0x0e, 0x86, 0xbc, 0x8f, 0x1e, 0x75, }, + { 0x90, 0x3d, 0x84, 0xc0, 0x27, 0x56, 0xea, 0x14, }, + { 0xee, 0xf2, 0x7a, 0x8e, 0x90, 0xca, 0x23, 0xf7, }, + { 0xe5, 0x45, 0xbe, 0x49, 0x61, 0xca, 0x29, 0xa1, }, + { 0xdb, 0x9b, 0xc2, 0x57, 0x7f, 0xcc, 0x2a, 0x3f, }, + { 0x94, 0x47, 0xbe, 0x2c, 0xf5, 0xe9, 0x9a, 0x69, }, + { 0x9c, 0xd3, 0x8d, 0x96, 0xf0, 0xb3, 0xc1, 0x4b, }, + { 0xbd, 0x61, 0x79, 0xa7, 0x1d, 0xc9, 0x6d, 0xbb, }, + { 0x98, 0xee, 0xa2, 0x1a, 0xf2, 0x5c, 0xd6, 0xbe, }, + { 0xc7, 0x67, 0x3b, 0x2e, 0xb0, 0xcb, 0xf2, 0xd0, }, + { 0x88, 0x3e, 0xa3, 0xe3, 0x95, 0x67, 0x53, 0x93, }, + { 0xc8, 0xce, 0x5c, 0xcd, 0x8c, 0x03, 0x0c, 0xa8, }, + { 0x94, 0xaf, 0x49, 0xf6, 0xc6, 0x50, 0xad, 0xb8, }, + { 0xea, 0xb8, 0x85, 0x8a, 0xde, 0x92, 0xe1, 0xbc, }, + { 0xf3, 0x15, 0xbb, 0x5b, 0xb8, 0x35, 0xd8, 0x17, }, + { 0xad, 0xcf, 0x6b, 0x07, 0x63, 0x61, 0x2e, 0x2f, }, + { 0xa5, 0xc9, 0x1d, 0xa7, 0xac, 0xaa, 0x4d, 0xde, }, + { 0x71, 0x65, 0x95, 0x87, 0x66, 0x50, 0xa2, 0xa6, }, + { 0x28, 0xef, 0x49, 0x5c, 0x53, 0xa3, 0x87, 0xad, }, + { 0x42, 0xc3, 0x41, 0xd8, 0xfa, 0x92, 0xd8, 0x32, }, + { 0xce, 0x7c, 0xf2, 0x72, 0x2f, 0x51, 0x27, 0x71, }, + { 0xe3, 0x78, 0x59, 0xf9, 0x46, 0x23, 0xf3, 0xa7, }, + { 0x38, 0x12, 0x05, 0xbb, 0x1a, 0xb0, 0xe0, 0x12, }, + { 0xae, 0x97, 0xa1, 0x0f, 0xd4, 0x34, 0xe0, 0x15, }, + { 0xb4, 0xa3, 0x15, 0x08, 0xbe, 0xff, 0x4d, 0x31, }, + { 0x81, 0x39, 0x62, 0x29, 0xf0, 0x90, 0x79, 0x02, }, + { 0x4d, 0x0c, 0xf4, 0x9e, 0xe5, 0xd4, 0xdc, 0xca, }, + { 0x5c, 0x73, 0x33, 0x6a, 0x76, 0xd8, 0xbf, 0x9a, }, + { 0xd0, 0xa7, 0x04, 0x53, 0x6b, 0xa9, 0x3e, 0x0e, }, + { 0x92, 0x59, 0x58, 0xfc, 0xd6, 0x42, 0x0c, 0xad, }, + { 0xa9, 0x15, 0xc2, 0x9b, 0xc8, 0x06, 0x73, 0x18, }, + { 0x95, 0x2b, 0x79, 0xf3, 0xbc, 0x0a, 0xa6, 0xd4, }, + { 0xf2, 0x1d, 0xf2, 0xe4, 0x1d, 0x45, 0x35, 0xf9, }, + { 0x87, 0x57, 0x75, 0x19, 0x04, 0x8f, 0x53, 0xa9, }, + { 0x10, 0xa5, 0x6c, 0xf5, 0xdf, 0xcd, 0x9a, 0xdb, }, + { 0xeb, 0x75, 0x09, 0x5c, 0xcd, 0x98, 0x6c, 0xd0, }, + { 0x51, 0xa9, 0xcb, 0x9e, 0xcb, 0xa3, 0x12, 0xe6, }, + { 0x96, 0xaf, 0xad, 0xfc, 0x2c, 0xe6, 0x66, 0xc7, }, + { 0x72, 0xfe, 0x52, 0x97, 0x5a, 0x43, 0x64, 0xee, }, + { 0x5a, 0x16, 0x45, 0xb2, 0x76, 0xd5, 0x92, 0xa1, }, + { 0xb2, 0x74, 0xcb, 0x8e, 0xbf, 0x87, 0x87, 0x0a, }, + { 0x6f, 0x9b, 0xb4, 0x20, 0x3d, 0xe7, 0xb3, 0x81, }, + { 0xea, 0xec, 0xb2, 0xa3, 0x0b, 0x22, 0xa8, 0x7f, }, + { 0x99, 0x24, 0xa4, 0x3c, 0xc1, 0x31, 0x57, 0x24, }, + { 0xbd, 0x83, 0x8d, 0x3a, 0xaf, 0xbf, 0x8d, 0xb7, }, + { 0x0b, 0x1a, 0x2a, 0x32, 0x65, 0xd5, 0x1a, 0xea, }, + { 0x13, 0x50, 0x79, 0xa3, 0x23, 0x1c, 0xe6, 0x60, }, + { 0x93, 0x2b, 0x28, 0x46, 0xe4, 0xd7, 0x06, 0x66, }, + { 0xe1, 0x91, 0x5f, 0x5c, 0xb1, 0xec, 0xa4, 0x6c, }, + { 0xf3, 0x25, 0x96, 0x5c, 0xa1, 0x6d, 0x62, 0x9f, }, + { 0x57, 0x5f, 0xf2, 0x8e, 0x60, 0x38, 0x1b, 0xe5, }, + { 0x72, 0x45, 0x06, 0xeb, 0x4c, 0x32, 0x8a, 0x95, } + }; + /* clang-format on */ + + unsigned char in[64]; + struct sipkey k; + size_t i; + + sip_tokey(&k, "\000\001\002\003\004\005\006\007\010\011" + "\012\013\014\015\016\017"); + + for (i = 0; i < sizeof in; ++i) { + in[i] = (unsigned char)i; + + if (siphash24(in, i, &k) != SIP_U8TO64_LE(vectors[i])) + return 0; + } + + return 1; +} /* sip24_valid() */ + +#ifdef SIPHASH_MAIN + +# include <stdio.h> + +int +main(void) { + const int ok = sip24_valid(); + + if (ok) + puts("OK"); + else + puts("FAIL"); + + return ! ok; +} /* main() */ + +#endif /* SIPHASH_MAIN */ + +#endif /* SIPHASH_H */ diff --git a/Utilities/cmexpat/lib/utf8tab.h b/Utilities/cmexpat/lib/utf8tab.h new file mode 100644 index 0000000000..88efcf91cc --- /dev/null +++ b/Utilities/cmexpat/lib/utf8tab.h @@ -0,0 +1,66 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4, + /* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM, diff --git a/Utilities/cmexpat/lib/winconfig.h b/Utilities/cmexpat/lib/winconfig.h new file mode 100644 index 0000000000..a689db69b9 --- /dev/null +++ b/Utilities/cmexpat/lib/winconfig.h @@ -0,0 +1,50 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2005 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017-2021 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifndef WINCONFIG_H +#define WINCONFIG_H + +#define WIN32_LEAN_AND_MEAN +#include <windows.h> +#undef WIN32_LEAN_AND_MEAN + +#include <memory.h> +#include <string.h> + +#if defined(_MSC_VER) +# pragma warning(push,1) +# pragma warning(disable:4311) /* pointer truncation */ +#endif + +#endif /* ndef WINCONFIG_H */ diff --git a/Utilities/cmexpat/lib/xmlparse.c b/Utilities/cmexpat/lib/xmlparse.c new file mode 100644 index 0000000000..7db28d07ac --- /dev/null +++ b/Utilities/cmexpat/lib/xmlparse.c @@ -0,0 +1,8255 @@ +/* a30d2613dcfdef81475a9d1a349134d2d42722172fdaa7d5bb12ed2aa74b9596 (2.4.6+) + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2000-2006 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016 Eric Rahm <erahm@mozilla.com> + Copyright (c) 2016-2022 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Gaurav <g.gupta@samsung.com> + Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> + Copyright (c) 2016 Gustavo Grieco <gustavo.grieco@imag.fr> + Copyright (c) 2016 Pascal Cuoq <cuoq@trust-in-soft.com> + Copyright (c) 2016 Ed Schouten <ed@nuxi.nl> + Copyright (c) 2017-2018 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2017 Václav SlavÃk <vaclav@slavik.io> + Copyright (c) 2017 Viktor Szakats <commit@vsz.me> + Copyright (c) 2017 Chanho Park <chanho61.park@samsung.com> + Copyright (c) 2017 Rolf Eike Beer <eike@sf-mail.de> + Copyright (c) 2017 Hans Wennborg <hans@chromium.org> + Copyright (c) 2018 Anton Maklakov <antmak.pub@gmail.com> + Copyright (c) 2018 Benjamin Peterson <benjamin@python.org> + Copyright (c) 2018 Marco Maggi <marco.maggi-ipsu@poste.it> + Copyright (c) 2018 Mariusz Zaborski <oshogbo@vexillium.org> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2019-2020 Ben Wagner <bungeman@chromium.org> + Copyright (c) 2019 Vadim Zeitlin <vadim@zeitlins.org> + Copyright (c) 2021 Dong-hee Na <donghee.na@python.org> + Copyright (c) 2022 Samanta Navarro <ferivoz@riseup.net> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#define XML_BUILDING_EXPAT 1 + +#include <expat_config.h> + +#if ! defined(_GNU_SOURCE) +# define _GNU_SOURCE 1 /* syscall prototype */ +#endif + +#ifdef _WIN32 +/* force stdlib to define rand_s() */ +# if ! defined(_CRT_RAND_S) +# define _CRT_RAND_S +# endif +#endif + +#include <stddef.h> +#include <string.h> /* memset(), memcpy() */ +#include <assert.h> +#include <limits.h> /* UINT_MAX */ +#include <stdio.h> /* fprintf */ +#include <stdlib.h> /* getenv, rand_s */ +#include <stdint.h> /* uintptr_t */ +#include <math.h> /* isnan */ + +#ifdef _WIN32 +# define getpid GetCurrentProcessId +#else +# include <sys/time.h> /* gettimeofday() */ +# include <sys/types.h> /* getpid() */ +# include <unistd.h> /* getpid() */ +# include <fcntl.h> /* O_RDONLY */ +# include <errno.h> +#endif + +#ifdef _WIN32 +# include "winconfig.h" +#endif + +#include "ascii.h" +#include "expat.h" +#include "siphash.h" + +#if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) +# if defined(HAVE_GETRANDOM) +# include <sys/random.h> /* getrandom */ +# else +# include <unistd.h> /* syscall */ +# include <sys/syscall.h> /* SYS_getrandom */ +# endif +# if ! defined(GRND_NONBLOCK) +# define GRND_NONBLOCK 0x0001 +# endif /* defined(GRND_NONBLOCK) */ +#endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */ + +#if defined(HAVE_LIBBSD) \ + && (defined(HAVE_ARC4RANDOM_BUF) || defined(HAVE_ARC4RANDOM)) +# include <bsd/stdlib.h> +#endif + +#if defined(_WIN32) && ! defined(LOAD_LIBRARY_SEARCH_SYSTEM32) +# define LOAD_LIBRARY_SEARCH_SYSTEM32 0x00000800 +#endif + +#if ! defined(HAVE_GETRANDOM) && ! defined(HAVE_SYSCALL_GETRANDOM) \ + && ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) \ + && ! defined(XML_DEV_URANDOM) && ! defined(_WIN32) \ + && ! defined(XML_POOR_ENTROPY) +# error You do not have support for any sources of high quality entropy \ + enabled. For end user security, that is probably not what you want. \ + \ + Your options include: \ + * Linux >=3.17 + glibc >=2.25 (getrandom): HAVE_GETRANDOM, \ + * Linux >=3.17 + glibc (including <2.25) (syscall SYS_getrandom): HAVE_SYSCALL_GETRANDOM, \ + * BSD / macOS >=10.7 (arc4random_buf): HAVE_ARC4RANDOM_BUF, \ + * BSD / macOS (including <10.7) (arc4random): HAVE_ARC4RANDOM, \ + * libbsd (arc4random_buf): HAVE_ARC4RANDOM_BUF + HAVE_LIBBSD, \ + * libbsd (arc4random): HAVE_ARC4RANDOM + HAVE_LIBBSD, \ + * Linux (including <3.17) / BSD / macOS (including <10.7) (/dev/urandom): XML_DEV_URANDOM, \ + * Windows >=Vista (rand_s): _WIN32. \ + \ + If insist on not using any of these, bypass this error by defining \ + XML_POOR_ENTROPY; you have been warned. \ + \ + If you have reasons to patch this detection code away or need changes \ + to the build system, please open a bug. Thank you! +#endif + +#ifdef XML_UNICODE +# define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX +# define XmlConvert XmlUtf16Convert +# define XmlGetInternalEncoding XmlGetUtf16InternalEncoding +# define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS +# define XmlEncode XmlUtf16Encode +# define MUST_CONVERT(enc, s) (! (enc)->isUtf16 || (((uintptr_t)(s)) & 1)) +typedef unsigned short ICHAR; +#else +# define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX +# define XmlConvert XmlUtf8Convert +# define XmlGetInternalEncoding XmlGetUtf8InternalEncoding +# define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS +# define XmlEncode XmlUtf8Encode +# define MUST_CONVERT(enc, s) (! (enc)->isUtf8) +typedef char ICHAR; +#endif + +#ifndef XML_NS + +# define XmlInitEncodingNS XmlInitEncoding +# define XmlInitUnknownEncodingNS XmlInitUnknownEncoding +# undef XmlGetInternalEncodingNS +# define XmlGetInternalEncodingNS XmlGetInternalEncoding +# define XmlParseXmlDeclNS XmlParseXmlDecl + +#endif + +#ifdef XML_UNICODE + +# ifdef XML_UNICODE_WCHAR_T +# define XML_T(x) (const wchar_t) x +# define XML_L(x) L##x +# else +# define XML_T(x) (const unsigned short)x +# define XML_L(x) x +# endif + +#else + +# define XML_T(x) x +# define XML_L(x) x + +#endif + +/* Round up n to be a multiple of sz, where sz is a power of 2. */ +#define ROUND_UP(n, sz) (((n) + ((sz)-1)) & ~((sz)-1)) + +/* Do safe (NULL-aware) pointer arithmetic */ +#define EXPAT_SAFE_PTR_DIFF(p, q) (((p) && (q)) ? ((p) - (q)) : 0) + +#include "internal.h" +#include "xmltok.h" +#include "xmlrole.h" + +typedef const XML_Char *KEY; + +typedef struct { + KEY name; +} NAMED; + +typedef struct { + NAMED **v; + unsigned char power; + size_t size; + size_t used; + const XML_Memory_Handling_Suite *mem; +} HASH_TABLE; + +static size_t keylen(KEY s); + +static void copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key); + +/* For probing (after a collision) we need a step size relative prime + to the hash table size, which is a power of 2. We use double-hashing, + since we can calculate a second hash value cheaply by taking those bits + of the first hash value that were discarded (masked out) when the table + index was calculated: index = hash & mask, where mask = table->size - 1. + We limit the maximum step size to table->size / 4 (mask >> 2) and make + it odd, since odd numbers are always relative prime to a power of 2. +*/ +#define SECOND_HASH(hash, mask, power) \ + ((((hash) & ~(mask)) >> ((power)-1)) & ((mask) >> 2)) +#define PROBE_STEP(hash, mask, power) \ + ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) + +typedef struct { + NAMED **p; + NAMED **end; +} HASH_TABLE_ITER; + +#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ +#define INIT_DATA_BUF_SIZE 1024 +#define INIT_ATTS_SIZE 16 +#define INIT_ATTS_VERSION 0xFFFFFFFF +#define INIT_BLOCK_SIZE 1024 +#define INIT_BUFFER_SIZE 1024 + +#define EXPAND_SPARE 24 + +typedef struct binding { + struct prefix *prefix; + struct binding *nextTagBinding; + struct binding *prevPrefixBinding; + const struct attribute_id *attId; + XML_Char *uri; + int uriLen; + int uriAlloc; +} BINDING; + +typedef struct prefix { + const XML_Char *name; + BINDING *binding; +} PREFIX; + +typedef struct { + const XML_Char *str; + const XML_Char *localPart; + const XML_Char *prefix; + int strLen; + int uriLen; + int prefixLen; +} TAG_NAME; + +/* TAG represents an open element. + The name of the element is stored in both the document and API + encodings. The memory buffer 'buf' is a separately-allocated + memory area which stores the name. During the XML_Parse()/ + XMLParseBuffer() when the element is open, the memory for the 'raw' + version of the name (in the document encoding) is shared with the + document buffer. If the element is open across calls to + XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to + contain the 'raw' name as well. + + A parser re-uses these structures, maintaining a list of allocated + TAG objects in a free list. +*/ +typedef struct tag { + struct tag *parent; /* parent of this element */ + const char *rawName; /* tagName in the original encoding */ + int rawNameLength; + TAG_NAME name; /* tagName in the API encoding */ + char *buf; /* buffer for name components */ + char *bufEnd; /* end of the buffer */ + BINDING *bindings; +} TAG; + +typedef struct { + const XML_Char *name; + const XML_Char *textPtr; + int textLen; /* length in XML_Chars */ + int processed; /* # of processed bytes - when suspended */ + const XML_Char *systemId; + const XML_Char *base; + const XML_Char *publicId; + const XML_Char *notation; + XML_Bool open; + XML_Bool is_param; + XML_Bool is_internal; /* true if declared in internal subset outside PE */ +} ENTITY; + +typedef struct { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + const XML_Char *name; + int firstchild; + int lastchild; + int childcnt; + int nextsib; +} CONTENT_SCAFFOLD; + +#define INIT_SCAFFOLD_ELEMENTS 32 + +typedef struct block { + struct block *next; + int size; + XML_Char s[1]; +} BLOCK; + +typedef struct { + BLOCK *blocks; + BLOCK *freeBlocks; + const XML_Char *end; + XML_Char *ptr; + XML_Char *start; + const XML_Memory_Handling_Suite *mem; +} STRING_POOL; + +/* The XML_Char before the name is used to determine whether + an attribute has been specified. */ +typedef struct attribute_id { + XML_Char *name; + PREFIX *prefix; + XML_Bool maybeTokenized; + XML_Bool xmlns; +} ATTRIBUTE_ID; + +typedef struct { + const ATTRIBUTE_ID *id; + XML_Bool isCdata; + const XML_Char *value; +} DEFAULT_ATTRIBUTE; + +typedef struct { + unsigned long version; + unsigned long hash; + const XML_Char *uriName; +} NS_ATT; + +typedef struct { + const XML_Char *name; + PREFIX *prefix; + const ATTRIBUTE_ID *idAtt; + int nDefaultAtts; + int allocDefaultAtts; + DEFAULT_ATTRIBUTE *defaultAtts; +} ELEMENT_TYPE; + +typedef struct { + HASH_TABLE generalEntities; + HASH_TABLE elementTypes; + HASH_TABLE attributeIds; + HASH_TABLE prefixes; + STRING_POOL pool; + STRING_POOL entityValuePool; + /* false once a parameter entity reference has been skipped */ + XML_Bool keepProcessing; + /* true once an internal or external PE reference has been encountered; + this includes the reference to an external subset */ + XML_Bool hasParamEntityRefs; + XML_Bool standalone; +#ifdef XML_DTD + /* indicates if external PE has been read */ + XML_Bool paramEntityRead; + HASH_TABLE paramEntities; +#endif /* XML_DTD */ + PREFIX defaultPrefix; + /* === scaffolding for building content model === */ + XML_Bool in_eldecl; + CONTENT_SCAFFOLD *scaffold; + unsigned contentStringLen; + unsigned scaffSize; + unsigned scaffCount; + int scaffLevel; + int *scaffIndex; +} DTD; + +typedef struct open_internal_entity { + const char *internalEventPtr; + const char *internalEventEndPtr; + struct open_internal_entity *next; + ENTITY *entity; + int startTagLevel; + XML_Bool betweenDecl; /* WFC: PE Between Declarations */ +} OPEN_INTERNAL_ENTITY; + +enum XML_Account { + XML_ACCOUNT_DIRECT, /* bytes directly passed to the Expat parser */ + XML_ACCOUNT_ENTITY_EXPANSION, /* intermediate bytes produced during entity + expansion */ + XML_ACCOUNT_NONE /* i.e. do not account, was accounted already */ +}; + +#ifdef XML_DTD +typedef unsigned long long XmlBigCount; +typedef struct accounting { + XmlBigCount countBytesDirect; + XmlBigCount countBytesIndirect; + int debugLevel; + float maximumAmplificationFactor; // >=1.0 + unsigned long long activationThresholdBytes; +} ACCOUNTING; + +typedef struct entity_stats { + unsigned int countEverOpened; + unsigned int currentDepth; + unsigned int maximumDepthSeen; + int debugLevel; +} ENTITY_STATS; +#endif /* XML_DTD */ + +typedef enum XML_Error PTRCALL Processor(XML_Parser parser, const char *start, + const char *end, const char **endPtr); + +static Processor prologProcessor; +static Processor prologInitProcessor; +static Processor contentProcessor; +static Processor cdataSectionProcessor; +#ifdef XML_DTD +static Processor ignoreSectionProcessor; +static Processor externalParEntProcessor; +static Processor externalParEntInitProcessor; +static Processor entityValueProcessor; +static Processor entityValueInitProcessor; +#endif /* XML_DTD */ +static Processor epilogProcessor; +static Processor errorProcessor; +static Processor externalEntityInitProcessor; +static Processor externalEntityInitProcessor2; +static Processor externalEntityInitProcessor3; +static Processor externalEntityContentProcessor; +static Processor internalEntityProcessor; + +static enum XML_Error handleUnknownEncoding(XML_Parser parser, + const XML_Char *encodingName); +static enum XML_Error processXmlDecl(XML_Parser parser, int isGeneralTextEntity, + const char *s, const char *next); +static enum XML_Error initializeEncoding(XML_Parser parser); +static enum XML_Error doProlog(XML_Parser parser, const ENCODING *enc, + const char *s, const char *end, int tok, + const char *next, const char **nextPtr, + XML_Bool haveMore, XML_Bool allowClosingDoctype, + enum XML_Account account); +static enum XML_Error processInternalEntity(XML_Parser parser, ENTITY *entity, + XML_Bool betweenDecl); +static enum XML_Error doContent(XML_Parser parser, int startTagLevel, + const ENCODING *enc, const char *start, + const char *end, const char **endPtr, + XML_Bool haveMore, enum XML_Account account); +static enum XML_Error doCdataSection(XML_Parser parser, const ENCODING *, + const char **startPtr, const char *end, + const char **nextPtr, XML_Bool haveMore, + enum XML_Account account); +#ifdef XML_DTD +static enum XML_Error doIgnoreSection(XML_Parser parser, const ENCODING *, + const char **startPtr, const char *end, + const char **nextPtr, XML_Bool haveMore); +#endif /* XML_DTD */ + +static void freeBindings(XML_Parser parser, BINDING *bindings); +static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, + const char *s, TAG_NAME *tagNamePtr, + BINDING **bindingsPtr, + enum XML_Account account); +static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, + const ATTRIBUTE_ID *attId, const XML_Char *uri, + BINDING **bindingsPtr); +static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, + XML_Bool isId, const XML_Char *dfltValue, + XML_Parser parser); +static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *, + XML_Bool isCdata, const char *, + const char *, STRING_POOL *, + enum XML_Account account); +static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *, + XML_Bool isCdata, const char *, + const char *, STRING_POOL *, + enum XML_Account account); +static ATTRIBUTE_ID *getAttributeId(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); +static enum XML_Error storeEntityValue(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end, + enum XML_Account account); +static int reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int reportComment(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static void reportDefault(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); + +static const XML_Char *getContext(XML_Parser parser); +static XML_Bool setContext(XML_Parser parser, const XML_Char *context); + +static void FASTCALL normalizePublicId(XML_Char *s); + +static DTD *dtdCreate(const XML_Memory_Handling_Suite *ms); +/* do not call if m_parentParser != NULL */ +static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms); +static void dtdDestroy(DTD *p, XML_Bool isDocEntity, + const XML_Memory_Handling_Suite *ms); +static int dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, + const XML_Memory_Handling_Suite *ms); +static int copyEntityTable(XML_Parser oldParser, HASH_TABLE *, STRING_POOL *, + const HASH_TABLE *); +static NAMED *lookup(XML_Parser parser, HASH_TABLE *table, KEY name, + size_t createSize); +static void FASTCALL hashTableInit(HASH_TABLE *, + const XML_Memory_Handling_Suite *ms); +static void FASTCALL hashTableClear(HASH_TABLE *); +static void FASTCALL hashTableDestroy(HASH_TABLE *); +static void FASTCALL hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); +static NAMED *FASTCALL hashTableIterNext(HASH_TABLE_ITER *); + +static void FASTCALL poolInit(STRING_POOL *, + const XML_Memory_Handling_Suite *ms); +static void FASTCALL poolClear(STRING_POOL *); +static void FASTCALL poolDestroy(STRING_POOL *); +static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Bool FASTCALL poolGrow(STRING_POOL *pool); +static const XML_Char *FASTCALL poolCopyString(STRING_POOL *pool, + const XML_Char *s); +static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, + int n); +static const XML_Char *FASTCALL poolAppendString(STRING_POOL *pool, + const XML_Char *s); + +static int FASTCALL nextScaffoldPart(XML_Parser parser); +static XML_Content *build_model(XML_Parser parser); +static ELEMENT_TYPE *getElementType(XML_Parser parser, const ENCODING *enc, + const char *ptr, const char *end); + +static XML_Char *copyString(const XML_Char *s, + const XML_Memory_Handling_Suite *memsuite); + +static unsigned long generate_hash_secret_salt(XML_Parser parser); +static XML_Bool startParsing(XML_Parser parser); + +static XML_Parser parserCreate(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep, DTD *dtd); + +static void parserInit(XML_Parser parser, const XML_Char *encodingName); + +#ifdef XML_DTD +static float accountingGetCurrentAmplification(XML_Parser rootParser); +static void accountingReportStats(XML_Parser originParser, const char *epilog); +static void accountingOnAbort(XML_Parser originParser); +static void accountingReportDiff(XML_Parser rootParser, + unsigned int levelsAwayFromRootParser, + const char *before, const char *after, + ptrdiff_t bytesMore, int source_line, + enum XML_Account account); +static XML_Bool accountingDiffTolerated(XML_Parser originParser, int tok, + const char *before, const char *after, + int source_line, + enum XML_Account account); + +static void entityTrackingReportStats(XML_Parser parser, ENTITY *entity, + const char *action, int sourceLine); +static void entityTrackingOnOpen(XML_Parser parser, ENTITY *entity, + int sourceLine); +static void entityTrackingOnClose(XML_Parser parser, ENTITY *entity, + int sourceLine); + +static XML_Parser getRootParserOf(XML_Parser parser, + unsigned int *outLevelDiff); +#endif /* XML_DTD */ + +static unsigned long getDebugLevel(const char *variableName, + unsigned long defaultDebugLevel); + +#define poolStart(pool) ((pool)->start) +#define poolEnd(pool) ((pool)->ptr) +#define poolLength(pool) ((pool)->ptr - (pool)->start) +#define poolChop(pool) ((void)--(pool->ptr)) +#define poolLastChar(pool) (((pool)->ptr)[-1]) +#define poolDiscard(pool) ((pool)->ptr = (pool)->start) +#define poolFinish(pool) ((pool)->start = (pool)->ptr) +#define poolAppendChar(pool, c) \ + (((pool)->ptr == (pool)->end && ! poolGrow(pool)) \ + ? 0 \ + : ((*((pool)->ptr)++ = c), 1)) + +struct XML_ParserStruct { + /* The first member must be m_userData so that the XML_GetUserData + macro works. */ + void *m_userData; + void *m_handlerArg; + char *m_buffer; + const XML_Memory_Handling_Suite m_mem; + /* first character to be parsed */ + const char *m_bufferPtr; + /* past last character to be parsed */ + char *m_bufferEnd; + /* allocated end of m_buffer */ + const char *m_bufferLim; + XML_Index m_parseEndByteIndex; + const char *m_parseEndPtr; + XML_Char *m_dataBuf; + XML_Char *m_dataBufEnd; + XML_StartElementHandler m_startElementHandler; + XML_EndElementHandler m_endElementHandler; + XML_CharacterDataHandler m_characterDataHandler; + XML_ProcessingInstructionHandler m_processingInstructionHandler; + XML_CommentHandler m_commentHandler; + XML_StartCdataSectionHandler m_startCdataSectionHandler; + XML_EndCdataSectionHandler m_endCdataSectionHandler; + XML_DefaultHandler m_defaultHandler; + XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler; + XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler; + XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler; + XML_NotationDeclHandler m_notationDeclHandler; + XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler; + XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler; + XML_NotStandaloneHandler m_notStandaloneHandler; + XML_ExternalEntityRefHandler m_externalEntityRefHandler; + XML_Parser m_externalEntityRefHandlerArg; + XML_SkippedEntityHandler m_skippedEntityHandler; + XML_UnknownEncodingHandler m_unknownEncodingHandler; + XML_ElementDeclHandler m_elementDeclHandler; + XML_AttlistDeclHandler m_attlistDeclHandler; + XML_EntityDeclHandler m_entityDeclHandler; + XML_XmlDeclHandler m_xmlDeclHandler; + const ENCODING *m_encoding; + INIT_ENCODING m_initEncoding; + const ENCODING *m_internalEncoding; + const XML_Char *m_protocolEncodingName; + XML_Bool m_ns; + XML_Bool m_ns_triplets; + void *m_unknownEncodingMem; + void *m_unknownEncodingData; + void *m_unknownEncodingHandlerData; + void(XMLCALL *m_unknownEncodingRelease)(void *); + PROLOG_STATE m_prologState; + Processor *m_processor; + enum XML_Error m_errorCode; + const char *m_eventPtr; + const char *m_eventEndPtr; + const char *m_positionPtr; + OPEN_INTERNAL_ENTITY *m_openInternalEntities; + OPEN_INTERNAL_ENTITY *m_freeInternalEntities; + XML_Bool m_defaultExpandInternalEntities; + int m_tagLevel; + ENTITY *m_declEntity; + const XML_Char *m_doctypeName; + const XML_Char *m_doctypeSysid; + const XML_Char *m_doctypePubid; + const XML_Char *m_declAttributeType; + const XML_Char *m_declNotationName; + const XML_Char *m_declNotationPublicId; + ELEMENT_TYPE *m_declElementType; + ATTRIBUTE_ID *m_declAttributeId; + XML_Bool m_declAttributeIsCdata; + XML_Bool m_declAttributeIsId; + DTD *m_dtd; + const XML_Char *m_curBase; + TAG *m_tagStack; + TAG *m_freeTagList; + BINDING *m_inheritedBindings; + BINDING *m_freeBindingList; + int m_attsSize; + int m_nSpecifiedAtts; + int m_idAttIndex; + ATTRIBUTE *m_atts; + NS_ATT *m_nsAtts; + unsigned long m_nsAttsVersion; + unsigned char m_nsAttsPower; +#ifdef XML_ATTR_INFO + XML_AttrInfo *m_attInfo; +#endif + POSITION m_position; + STRING_POOL m_tempPool; + STRING_POOL m_temp2Pool; + char *m_groupConnector; + unsigned int m_groupSize; + XML_Char m_namespaceSeparator; + XML_Parser m_parentParser; + XML_ParsingStatus m_parsingStatus; +#ifdef XML_DTD + XML_Bool m_isParamEntity; + XML_Bool m_useForeignDTD; + enum XML_ParamEntityParsing m_paramEntityParsing; +#endif + unsigned long m_hash_secret_salt; +#ifdef XML_DTD + ACCOUNTING m_accounting; + ENTITY_STATS m_entity_stats; +#endif +}; + +#define MALLOC(parser, s) (parser->m_mem.malloc_fcn((s))) +#define REALLOC(parser, p, s) (parser->m_mem.realloc_fcn((p), (s))) +#define FREE(parser, p) (parser->m_mem.free_fcn((p))) + +XML_Parser XMLCALL +XML_ParserCreate(const XML_Char *encodingName) { + return XML_ParserCreate_MM(encodingName, NULL, NULL); +} + +XML_Parser XMLCALL +XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) { + XML_Char tmp[2] = {nsSep, 0}; + return XML_ParserCreate_MM(encodingName, NULL, tmp); +} + +static const XML_Char implicitContext[] + = {ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, + ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, + ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, + ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, + ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, + ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, + ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, ASCII_e, + ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, + '\0'}; + +/* To avoid warnings about unused functions: */ +#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) + +# if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) + +/* Obtain entropy on Linux 3.17+ */ +static int +writeRandomBytes_getrandom_nonblock(void *target, size_t count) { + int success = 0; /* full count bytes written? */ + size_t bytesWrittenTotal = 0; + const unsigned int getrandomFlags = GRND_NONBLOCK; + + do { + void *const currentTarget = (void *)((char *)target + bytesWrittenTotal); + const size_t bytesToWrite = count - bytesWrittenTotal; + + const int bytesWrittenMore = +# if defined(HAVE_GETRANDOM) + getrandom(currentTarget, bytesToWrite, getrandomFlags); +# else + syscall(SYS_getrandom, currentTarget, bytesToWrite, getrandomFlags); +# endif + + if (bytesWrittenMore > 0) { + bytesWrittenTotal += bytesWrittenMore; + if (bytesWrittenTotal >= count) + success = 1; + } + } while (! success && (errno == EINTR)); + + return success; +} + +# endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */ + +# if ! defined(_WIN32) && defined(XML_DEV_URANDOM) + +/* Extract entropy from /dev/urandom */ +static int +writeRandomBytes_dev_urandom(void *target, size_t count) { + int success = 0; /* full count bytes written? */ + size_t bytesWrittenTotal = 0; + + const int fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) { + return 0; + } + + do { + void *const currentTarget = (void *)((char *)target + bytesWrittenTotal); + const size_t bytesToWrite = count - bytesWrittenTotal; + + const ssize_t bytesWrittenMore = read(fd, currentTarget, bytesToWrite); + + if (bytesWrittenMore > 0) { + bytesWrittenTotal += bytesWrittenMore; + if (bytesWrittenTotal >= count) + success = 1; + } + } while (! success && (errno == EINTR)); + + close(fd); + return success; +} + +# endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ + +#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */ + +#if defined(HAVE_ARC4RANDOM) && ! defined(HAVE_ARC4RANDOM_BUF) + +static void +writeRandomBytes_arc4random(void *target, size_t count) { + size_t bytesWrittenTotal = 0; + + while (bytesWrittenTotal < count) { + const uint32_t random32 = arc4random(); + size_t i = 0; + + for (; (i < sizeof(random32)) && (bytesWrittenTotal < count); + i++, bytesWrittenTotal++) { + const uint8_t random8 = (uint8_t)(random32 >> (i * 8)); + ((uint8_t *)target)[bytesWrittenTotal] = random8; + } + } +} + +#endif /* defined(HAVE_ARC4RANDOM) && ! defined(HAVE_ARC4RANDOM_BUF) */ + +#ifdef _WIN32 + +/* Provide declaration of rand_s() for MinGW-32 (not 64, which has it), + as it didn't declare it in its header prior to version 5.3.0 of its + runtime package (mingwrt, containing stdlib.h). The upstream fix + was introduced at https://osdn.net/projects/mingw/ticket/39658 . */ +# if defined(__MINGW32__) && defined(__MINGW32_VERSION) \ + && __MINGW32_VERSION < 5003000L && ! defined(__MINGW64_VERSION_MAJOR) +__declspec(dllimport) int rand_s(unsigned int *); +# endif + +/* Obtain entropy on Windows using the rand_s() function which + * generates cryptographically secure random numbers. Internally it + * uses RtlGenRandom API which is present in Windows XP and later. + */ +static int +writeRandomBytes_rand_s(void *target, size_t count) { + size_t bytesWrittenTotal = 0; + + while (bytesWrittenTotal < count) { + unsigned int random32 = 0; + size_t i = 0; + + if (rand_s(&random32)) + return 0; /* failure */ + + for (; (i < sizeof(random32)) && (bytesWrittenTotal < count); + i++, bytesWrittenTotal++) { + const uint8_t random8 = (uint8_t)(random32 >> (i * 8)); + ((uint8_t *)target)[bytesWrittenTotal] = random8; + } + } + return 1; /* success */ +} + +#endif /* _WIN32 */ + +#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) + +static unsigned long +gather_time_entropy(void) { +# ifdef _WIN32 + FILETIME ft; + GetSystemTimeAsFileTime(&ft); /* never fails */ + return ft.dwHighDateTime ^ ft.dwLowDateTime; +# else + struct timeval tv; + int gettimeofday_res; + + gettimeofday_res = gettimeofday(&tv, NULL); + +# if defined(NDEBUG) + (void)gettimeofday_res; +# else + assert(gettimeofday_res == 0); +# endif /* defined(NDEBUG) */ + + /* Microseconds time is <20 bits entropy */ + return tv.tv_usec; +# endif +} + +#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */ + +static unsigned long +ENTROPY_DEBUG(const char *label, unsigned long entropy) { + if (getDebugLevel("EXPAT_ENTROPY_DEBUG", 0) >= 1u) { + fprintf(stderr, "expat: Entropy: %s --> 0x%0*lx (%lu bytes)\n", label, + (int)sizeof(entropy) * 2, entropy, (unsigned long)sizeof(entropy)); + } + return entropy; +} + +static unsigned long +generate_hash_secret_salt(XML_Parser parser) { + unsigned long entropy; + (void)parser; + + /* "Failproof" high quality providers: */ +#if defined(HAVE_ARC4RANDOM_BUF) + arc4random_buf(&entropy, sizeof(entropy)); + return ENTROPY_DEBUG("arc4random_buf", entropy); +#elif defined(HAVE_ARC4RANDOM) + writeRandomBytes_arc4random((void *)&entropy, sizeof(entropy)); + return ENTROPY_DEBUG("arc4random", entropy); +#else + /* Try high quality providers first .. */ +# ifdef _WIN32 + if (writeRandomBytes_rand_s((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("rand_s", entropy); + } +# elif defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) + if (writeRandomBytes_getrandom_nonblock((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("getrandom", entropy); + } +# endif +# if ! defined(_WIN32) && defined(XML_DEV_URANDOM) + if (writeRandomBytes_dev_urandom((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("/dev/urandom", entropy); + } +# endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ + /* .. and self-made low quality for backup: */ + + /* Process ID is 0 bits entropy if attacker has local access */ + entropy = gather_time_entropy() ^ getpid(); + + /* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */ + if (sizeof(unsigned long) == 4) { + return ENTROPY_DEBUG("fallback(4)", entropy * 2147483647); + } else { + return ENTROPY_DEBUG("fallback(8)", + entropy * (unsigned long)2305843009213693951ULL); + } +#endif +} + +static unsigned long +get_hash_secret_salt(XML_Parser parser) { + if (parser->m_parentParser != NULL) + return get_hash_secret_salt(parser->m_parentParser); + return parser->m_hash_secret_salt; +} + +static XML_Bool /* only valid for root parser */ +startParsing(XML_Parser parser) { + /* hash functions must be initialized before setContext() is called */ + if (parser->m_hash_secret_salt == 0) + parser->m_hash_secret_salt = generate_hash_secret_salt(parser); + if (parser->m_ns) { + /* implicit context only set for root parser, since child + parsers (i.e. external entity parsers) will inherit it + */ + return setContext(parser, implicitContext); + } + return XML_TRUE; +} + +XML_Parser XMLCALL +XML_ParserCreate_MM(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep) { + return parserCreate(encodingName, memsuite, nameSep, NULL); +} + +static XML_Parser +parserCreate(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, const XML_Char *nameSep, + DTD *dtd) { + XML_Parser parser; + + if (memsuite) { + XML_Memory_Handling_Suite *mtemp; + parser = memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); + if (parser != NULL) { + mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); + mtemp->malloc_fcn = memsuite->malloc_fcn; + mtemp->realloc_fcn = memsuite->realloc_fcn; + mtemp->free_fcn = memsuite->free_fcn; + } + } else { + XML_Memory_Handling_Suite *mtemp; + parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct)); + if (parser != NULL) { + mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); + mtemp->malloc_fcn = malloc; + mtemp->realloc_fcn = realloc; + mtemp->free_fcn = free; + } + } + + if (! parser) + return parser; + + parser->m_buffer = NULL; + parser->m_bufferLim = NULL; + + parser->m_attsSize = INIT_ATTS_SIZE; + parser->m_atts + = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE)); + if (parser->m_atts == NULL) { + FREE(parser, parser); + return NULL; + } +#ifdef XML_ATTR_INFO + parser->m_attInfo = (XML_AttrInfo *)MALLOC( + parser, parser->m_attsSize * sizeof(XML_AttrInfo)); + if (parser->m_attInfo == NULL) { + FREE(parser, parser->m_atts); + FREE(parser, parser); + return NULL; + } +#endif + parser->m_dataBuf + = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char)); + if (parser->m_dataBuf == NULL) { + FREE(parser, parser->m_atts); +#ifdef XML_ATTR_INFO + FREE(parser, parser->m_attInfo); +#endif + FREE(parser, parser); + return NULL; + } + parser->m_dataBufEnd = parser->m_dataBuf + INIT_DATA_BUF_SIZE; + + if (dtd) + parser->m_dtd = dtd; + else { + parser->m_dtd = dtdCreate(&parser->m_mem); + if (parser->m_dtd == NULL) { + FREE(parser, parser->m_dataBuf); + FREE(parser, parser->m_atts); +#ifdef XML_ATTR_INFO + FREE(parser, parser->m_attInfo); +#endif + FREE(parser, parser); + return NULL; + } + } + + parser->m_freeBindingList = NULL; + parser->m_freeTagList = NULL; + parser->m_freeInternalEntities = NULL; + + parser->m_groupSize = 0; + parser->m_groupConnector = NULL; + + parser->m_unknownEncodingHandler = NULL; + parser->m_unknownEncodingHandlerData = NULL; + + parser->m_namespaceSeparator = ASCII_EXCL; + parser->m_ns = XML_FALSE; + parser->m_ns_triplets = XML_FALSE; + + parser->m_nsAtts = NULL; + parser->m_nsAttsVersion = 0; + parser->m_nsAttsPower = 0; + + parser->m_protocolEncodingName = NULL; + + poolInit(&parser->m_tempPool, &(parser->m_mem)); + poolInit(&parser->m_temp2Pool, &(parser->m_mem)); + parserInit(parser, encodingName); + + if (encodingName && ! parser->m_protocolEncodingName) { + XML_ParserFree(parser); + return NULL; + } + + if (nameSep) { + parser->m_ns = XML_TRUE; + parser->m_internalEncoding = XmlGetInternalEncodingNS(); + parser->m_namespaceSeparator = *nameSep; + } else { + parser->m_internalEncoding = XmlGetInternalEncoding(); + } + + return parser; +} + +static void +parserInit(XML_Parser parser, const XML_Char *encodingName) { + parser->m_processor = prologInitProcessor; + XmlPrologStateInit(&parser->m_prologState); + if (encodingName != NULL) { + parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem)); + } + parser->m_curBase = NULL; + XmlInitEncoding(&parser->m_initEncoding, &parser->m_encoding, 0); + parser->m_userData = NULL; + parser->m_handlerArg = NULL; + parser->m_startElementHandler = NULL; + parser->m_endElementHandler = NULL; + parser->m_characterDataHandler = NULL; + parser->m_processingInstructionHandler = NULL; + parser->m_commentHandler = NULL; + parser->m_startCdataSectionHandler = NULL; + parser->m_endCdataSectionHandler = NULL; + parser->m_defaultHandler = NULL; + parser->m_startDoctypeDeclHandler = NULL; + parser->m_endDoctypeDeclHandler = NULL; + parser->m_unparsedEntityDeclHandler = NULL; + parser->m_notationDeclHandler = NULL; + parser->m_startNamespaceDeclHandler = NULL; + parser->m_endNamespaceDeclHandler = NULL; + parser->m_notStandaloneHandler = NULL; + parser->m_externalEntityRefHandler = NULL; + parser->m_externalEntityRefHandlerArg = parser; + parser->m_skippedEntityHandler = NULL; + parser->m_elementDeclHandler = NULL; + parser->m_attlistDeclHandler = NULL; + parser->m_entityDeclHandler = NULL; + parser->m_xmlDeclHandler = NULL; + parser->m_bufferPtr = parser->m_buffer; + parser->m_bufferEnd = parser->m_buffer; + parser->m_parseEndByteIndex = 0; + parser->m_parseEndPtr = NULL; + parser->m_declElementType = NULL; + parser->m_declAttributeId = NULL; + parser->m_declEntity = NULL; + parser->m_doctypeName = NULL; + parser->m_doctypeSysid = NULL; + parser->m_doctypePubid = NULL; + parser->m_declAttributeType = NULL; + parser->m_declNotationName = NULL; + parser->m_declNotationPublicId = NULL; + parser->m_declAttributeIsCdata = XML_FALSE; + parser->m_declAttributeIsId = XML_FALSE; + memset(&parser->m_position, 0, sizeof(POSITION)); + parser->m_errorCode = XML_ERROR_NONE; + parser->m_eventPtr = NULL; + parser->m_eventEndPtr = NULL; + parser->m_positionPtr = NULL; + parser->m_openInternalEntities = NULL; + parser->m_defaultExpandInternalEntities = XML_TRUE; + parser->m_tagLevel = 0; + parser->m_tagStack = NULL; + parser->m_inheritedBindings = NULL; + parser->m_nSpecifiedAtts = 0; + parser->m_unknownEncodingMem = NULL; + parser->m_unknownEncodingRelease = NULL; + parser->m_unknownEncodingData = NULL; + parser->m_parentParser = NULL; + parser->m_parsingStatus.parsing = XML_INITIALIZED; +#ifdef XML_DTD + parser->m_isParamEntity = XML_FALSE; + parser->m_useForeignDTD = XML_FALSE; + parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif + parser->m_hash_secret_salt = 0; + +#ifdef XML_DTD + memset(&parser->m_accounting, 0, sizeof(ACCOUNTING)); + parser->m_accounting.debugLevel = getDebugLevel("EXPAT_ACCOUNTING_DEBUG", 0u); + parser->m_accounting.maximumAmplificationFactor + = EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT; + parser->m_accounting.activationThresholdBytes + = EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT; + + memset(&parser->m_entity_stats, 0, sizeof(ENTITY_STATS)); + parser->m_entity_stats.debugLevel = getDebugLevel("EXPAT_ENTITY_DEBUG", 0u); +#endif +} + +/* moves list of bindings to m_freeBindingList */ +static void FASTCALL +moveToFreeBindingList(XML_Parser parser, BINDING *bindings) { + while (bindings) { + BINDING *b = bindings; + bindings = bindings->nextTagBinding; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; + } +} + +XML_Bool XMLCALL +XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { + TAG *tStk; + OPEN_INTERNAL_ENTITY *openEntityList; + + if (parser == NULL) + return XML_FALSE; + + if (parser->m_parentParser) + return XML_FALSE; + /* move m_tagStack to m_freeTagList */ + tStk = parser->m_tagStack; + while (tStk) { + TAG *tag = tStk; + tStk = tStk->parent; + tag->parent = parser->m_freeTagList; + moveToFreeBindingList(parser, tag->bindings); + tag->bindings = NULL; + parser->m_freeTagList = tag; + } + /* move m_openInternalEntities to m_freeInternalEntities */ + openEntityList = parser->m_openInternalEntities; + while (openEntityList) { + OPEN_INTERNAL_ENTITY *openEntity = openEntityList; + openEntityList = openEntity->next; + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; + } + moveToFreeBindingList(parser, parser->m_inheritedBindings); + FREE(parser, parser->m_unknownEncodingMem); + if (parser->m_unknownEncodingRelease) + parser->m_unknownEncodingRelease(parser->m_unknownEncodingData); + poolClear(&parser->m_tempPool); + poolClear(&parser->m_temp2Pool); + FREE(parser, (void *)parser->m_protocolEncodingName); + parser->m_protocolEncodingName = NULL; + parserInit(parser, encodingName); + dtdReset(parser->m_dtd, &parser->m_mem); + return XML_TRUE; +} + +enum XML_Status XMLCALL +XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { + if (parser == NULL) + return XML_STATUS_ERROR; + /* Block after XML_Parse()/XML_ParseBuffer() has been called. + XXX There's no way for the caller to determine which of the + XXX possible error cases caused the XML_STATUS_ERROR return. + */ + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) + return XML_STATUS_ERROR; + + /* Get rid of any previous encoding name */ + FREE(parser, (void *)parser->m_protocolEncodingName); + + if (encodingName == NULL) + /* No new encoding name */ + parser->m_protocolEncodingName = NULL; + else { + /* Copy the new encoding name into allocated memory */ + parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem)); + if (! parser->m_protocolEncodingName) + return XML_STATUS_ERROR; + } + return XML_STATUS_OK; +} + +XML_Parser XMLCALL +XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, + const XML_Char *encodingName) { + XML_Parser parser = oldParser; + DTD *newDtd = NULL; + DTD *oldDtd; + XML_StartElementHandler oldStartElementHandler; + XML_EndElementHandler oldEndElementHandler; + XML_CharacterDataHandler oldCharacterDataHandler; + XML_ProcessingInstructionHandler oldProcessingInstructionHandler; + XML_CommentHandler oldCommentHandler; + XML_StartCdataSectionHandler oldStartCdataSectionHandler; + XML_EndCdataSectionHandler oldEndCdataSectionHandler; + XML_DefaultHandler oldDefaultHandler; + XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler; + XML_NotationDeclHandler oldNotationDeclHandler; + XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler; + XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler; + XML_NotStandaloneHandler oldNotStandaloneHandler; + XML_ExternalEntityRefHandler oldExternalEntityRefHandler; + XML_SkippedEntityHandler oldSkippedEntityHandler; + XML_UnknownEncodingHandler oldUnknownEncodingHandler; + XML_ElementDeclHandler oldElementDeclHandler; + XML_AttlistDeclHandler oldAttlistDeclHandler; + XML_EntityDeclHandler oldEntityDeclHandler; + XML_XmlDeclHandler oldXmlDeclHandler; + ELEMENT_TYPE *oldDeclElementType; + + void *oldUserData; + void *oldHandlerArg; + XML_Bool oldDefaultExpandInternalEntities; + XML_Parser oldExternalEntityRefHandlerArg; +#ifdef XML_DTD + enum XML_ParamEntityParsing oldParamEntityParsing; + int oldInEntityValue; +#endif + XML_Bool oldns_triplets; + /* Note that the new parser shares the same hash secret as the old + parser, so that dtdCopy and copyEntityTable can lookup values + from hash tables associated with either parser without us having + to worry which hash secrets each table has. + */ + unsigned long oldhash_secret_salt; + + /* Validate the oldParser parameter before we pull everything out of it */ + if (oldParser == NULL) + return NULL; + + /* Stash the original parser contents on the stack */ + oldDtd = parser->m_dtd; + oldStartElementHandler = parser->m_startElementHandler; + oldEndElementHandler = parser->m_endElementHandler; + oldCharacterDataHandler = parser->m_characterDataHandler; + oldProcessingInstructionHandler = parser->m_processingInstructionHandler; + oldCommentHandler = parser->m_commentHandler; + oldStartCdataSectionHandler = parser->m_startCdataSectionHandler; + oldEndCdataSectionHandler = parser->m_endCdataSectionHandler; + oldDefaultHandler = parser->m_defaultHandler; + oldUnparsedEntityDeclHandler = parser->m_unparsedEntityDeclHandler; + oldNotationDeclHandler = parser->m_notationDeclHandler; + oldStartNamespaceDeclHandler = parser->m_startNamespaceDeclHandler; + oldEndNamespaceDeclHandler = parser->m_endNamespaceDeclHandler; + oldNotStandaloneHandler = parser->m_notStandaloneHandler; + oldExternalEntityRefHandler = parser->m_externalEntityRefHandler; + oldSkippedEntityHandler = parser->m_skippedEntityHandler; + oldUnknownEncodingHandler = parser->m_unknownEncodingHandler; + oldElementDeclHandler = parser->m_elementDeclHandler; + oldAttlistDeclHandler = parser->m_attlistDeclHandler; + oldEntityDeclHandler = parser->m_entityDeclHandler; + oldXmlDeclHandler = parser->m_xmlDeclHandler; + oldDeclElementType = parser->m_declElementType; + + oldUserData = parser->m_userData; + oldHandlerArg = parser->m_handlerArg; + oldDefaultExpandInternalEntities = parser->m_defaultExpandInternalEntities; + oldExternalEntityRefHandlerArg = parser->m_externalEntityRefHandlerArg; +#ifdef XML_DTD + oldParamEntityParsing = parser->m_paramEntityParsing; + oldInEntityValue = parser->m_prologState.inEntityValue; +#endif + oldns_triplets = parser->m_ns_triplets; + /* Note that the new parser shares the same hash secret as the old + parser, so that dtdCopy and copyEntityTable can lookup values + from hash tables associated with either parser without us having + to worry which hash secrets each table has. + */ + oldhash_secret_salt = parser->m_hash_secret_salt; + +#ifdef XML_DTD + if (! context) + newDtd = oldDtd; +#endif /* XML_DTD */ + + /* Note that the magical uses of the pre-processor to make field + access look more like C++ require that `parser' be overwritten + here. This makes this function more painful to follow than it + would be otherwise. + */ + if (parser->m_ns) { + XML_Char tmp[2] = {parser->m_namespaceSeparator, 0}; + parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); + } else { + parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); + } + + if (! parser) + return NULL; + + parser->m_startElementHandler = oldStartElementHandler; + parser->m_endElementHandler = oldEndElementHandler; + parser->m_characterDataHandler = oldCharacterDataHandler; + parser->m_processingInstructionHandler = oldProcessingInstructionHandler; + parser->m_commentHandler = oldCommentHandler; + parser->m_startCdataSectionHandler = oldStartCdataSectionHandler; + parser->m_endCdataSectionHandler = oldEndCdataSectionHandler; + parser->m_defaultHandler = oldDefaultHandler; + parser->m_unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; + parser->m_notationDeclHandler = oldNotationDeclHandler; + parser->m_startNamespaceDeclHandler = oldStartNamespaceDeclHandler; + parser->m_endNamespaceDeclHandler = oldEndNamespaceDeclHandler; + parser->m_notStandaloneHandler = oldNotStandaloneHandler; + parser->m_externalEntityRefHandler = oldExternalEntityRefHandler; + parser->m_skippedEntityHandler = oldSkippedEntityHandler; + parser->m_unknownEncodingHandler = oldUnknownEncodingHandler; + parser->m_elementDeclHandler = oldElementDeclHandler; + parser->m_attlistDeclHandler = oldAttlistDeclHandler; + parser->m_entityDeclHandler = oldEntityDeclHandler; + parser->m_xmlDeclHandler = oldXmlDeclHandler; + parser->m_declElementType = oldDeclElementType; + parser->m_userData = oldUserData; + if (oldUserData == oldHandlerArg) + parser->m_handlerArg = parser->m_userData; + else + parser->m_handlerArg = parser; + if (oldExternalEntityRefHandlerArg != oldParser) + parser->m_externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; + parser->m_defaultExpandInternalEntities = oldDefaultExpandInternalEntities; + parser->m_ns_triplets = oldns_triplets; + parser->m_hash_secret_salt = oldhash_secret_salt; + parser->m_parentParser = oldParser; +#ifdef XML_DTD + parser->m_paramEntityParsing = oldParamEntityParsing; + parser->m_prologState.inEntityValue = oldInEntityValue; + if (context) { +#endif /* XML_DTD */ + if (! dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem) + || ! setContext(parser, context)) { + XML_ParserFree(parser); + return NULL; + } + parser->m_processor = externalEntityInitProcessor; +#ifdef XML_DTD + } else { + /* The DTD instance referenced by parser->m_dtd is shared between the + document's root parser and external PE parsers, therefore one does not + need to call setContext. In addition, one also *must* not call + setContext, because this would overwrite existing prefix->binding + pointers in parser->m_dtd with ones that get destroyed with the external + PE parser. This would leave those prefixes with dangling pointers. + */ + parser->m_isParamEntity = XML_TRUE; + XmlPrologStateInitExternalEntity(&parser->m_prologState); + parser->m_processor = externalParEntInitProcessor; + } +#endif /* XML_DTD */ + return parser; +} + +static void FASTCALL +destroyBindings(BINDING *bindings, XML_Parser parser) { + for (;;) { + BINDING *b = bindings; + if (! b) + break; + bindings = b->nextTagBinding; + FREE(parser, b->uri); + FREE(parser, b); + } +} + +void XMLCALL +XML_ParserFree(XML_Parser parser) { + TAG *tagList; + OPEN_INTERNAL_ENTITY *entityList; + if (parser == NULL) + return; + /* free m_tagStack and m_freeTagList */ + tagList = parser->m_tagStack; + for (;;) { + TAG *p; + if (tagList == NULL) { + if (parser->m_freeTagList == NULL) + break; + tagList = parser->m_freeTagList; + parser->m_freeTagList = NULL; + } + p = tagList; + tagList = tagList->parent; + FREE(parser, p->buf); + destroyBindings(p->bindings, parser); + FREE(parser, p); + } + /* free m_openInternalEntities and m_freeInternalEntities */ + entityList = parser->m_openInternalEntities; + for (;;) { + OPEN_INTERNAL_ENTITY *openEntity; + if (entityList == NULL) { + if (parser->m_freeInternalEntities == NULL) + break; + entityList = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = NULL; + } + openEntity = entityList; + entityList = entityList->next; + FREE(parser, openEntity); + } + + destroyBindings(parser->m_freeBindingList, parser); + destroyBindings(parser->m_inheritedBindings, parser); + poolDestroy(&parser->m_tempPool); + poolDestroy(&parser->m_temp2Pool); + FREE(parser, (void *)parser->m_protocolEncodingName); +#ifdef XML_DTD + /* external parameter entity parsers share the DTD structure + parser->m_dtd with the root parser, so we must not destroy it + */ + if (! parser->m_isParamEntity && parser->m_dtd) +#else + if (parser->m_dtd) +#endif /* XML_DTD */ + dtdDestroy(parser->m_dtd, (XML_Bool)! parser->m_parentParser, + &parser->m_mem); + FREE(parser, (void *)parser->m_atts); +#ifdef XML_ATTR_INFO + FREE(parser, (void *)parser->m_attInfo); +#endif + FREE(parser, parser->m_groupConnector); + FREE(parser, parser->m_buffer); + FREE(parser, parser->m_dataBuf); + FREE(parser, parser->m_nsAtts); + FREE(parser, parser->m_unknownEncodingMem); + if (parser->m_unknownEncodingRelease) + parser->m_unknownEncodingRelease(parser->m_unknownEncodingData); + FREE(parser, parser); +} + +void XMLCALL +XML_UseParserAsHandlerArg(XML_Parser parser) { + if (parser != NULL) + parser->m_handlerArg = parser; +} + +enum XML_Error XMLCALL +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { + if (parser == NULL) + return XML_ERROR_INVALID_ARGUMENT; +#ifdef XML_DTD + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) + return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; + parser->m_useForeignDTD = useDTD; + return XML_ERROR_NONE; +#else + UNUSED_P(useDTD); + return XML_ERROR_FEATURE_REQUIRES_XML_DTD; +#endif +} + +void XMLCALL +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { + if (parser == NULL) + return; + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) + return; + parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE; +} + +void XMLCALL +XML_SetUserData(XML_Parser parser, void *p) { + if (parser == NULL) + return; + if (parser->m_handlerArg == parser->m_userData) + parser->m_handlerArg = parser->m_userData = p; + else + parser->m_userData = p; +} + +enum XML_Status XMLCALL +XML_SetBase(XML_Parser parser, const XML_Char *p) { + if (parser == NULL) + return XML_STATUS_ERROR; + if (p) { + p = poolCopyString(&parser->m_dtd->pool, p); + if (! p) + return XML_STATUS_ERROR; + parser->m_curBase = p; + } else + parser->m_curBase = NULL; + return XML_STATUS_OK; +} + +const XML_Char *XMLCALL +XML_GetBase(XML_Parser parser) { + if (parser == NULL) + return NULL; + return parser->m_curBase; +} + +int XMLCALL +XML_GetSpecifiedAttributeCount(XML_Parser parser) { + if (parser == NULL) + return -1; + return parser->m_nSpecifiedAtts; +} + +int XMLCALL +XML_GetIdAttributeIndex(XML_Parser parser) { + if (parser == NULL) + return -1; + return parser->m_idAttIndex; +} + +#ifdef XML_ATTR_INFO +const XML_AttrInfo *XMLCALL +XML_GetAttributeInfo(XML_Parser parser) { + if (parser == NULL) + return NULL; + return parser->m_attInfo; +} +#endif + +void XMLCALL +XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, + XML_EndElementHandler end) { + if (parser == NULL) + return; + parser->m_startElementHandler = start; + parser->m_endElementHandler = end; +} + +void XMLCALL +XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler start) { + if (parser != NULL) + parser->m_startElementHandler = start; +} + +void XMLCALL +XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler end) { + if (parser != NULL) + parser->m_endElementHandler = end; +} + +void XMLCALL +XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler) { + if (parser != NULL) + parser->m_characterDataHandler = handler; +} + +void XMLCALL +XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler) { + if (parser != NULL) + parser->m_processingInstructionHandler = handler; +} + +void XMLCALL +XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler) { + if (parser != NULL) + parser->m_commentHandler = handler; +} + +void XMLCALL +XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end) { + if (parser == NULL) + return; + parser->m_startCdataSectionHandler = start; + parser->m_endCdataSectionHandler = end; +} + +void XMLCALL +XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start) { + if (parser != NULL) + parser->m_startCdataSectionHandler = start; +} + +void XMLCALL +XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end) { + if (parser != NULL) + parser->m_endCdataSectionHandler = end; +} + +void XMLCALL +XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler) { + if (parser == NULL) + return; + parser->m_defaultHandler = handler; + parser->m_defaultExpandInternalEntities = XML_FALSE; +} + +void XMLCALL +XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler) { + if (parser == NULL) + return; + parser->m_defaultHandler = handler; + parser->m_defaultExpandInternalEntities = XML_TRUE; +} + +void XMLCALL +XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end) { + if (parser == NULL) + return; + parser->m_startDoctypeDeclHandler = start; + parser->m_endDoctypeDeclHandler = end; +} + +void XMLCALL +XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start) { + if (parser != NULL) + parser->m_startDoctypeDeclHandler = start; +} + +void XMLCALL +XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end) { + if (parser != NULL) + parser->m_endDoctypeDeclHandler = end; +} + +void XMLCALL +XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler) { + if (parser != NULL) + parser->m_unparsedEntityDeclHandler = handler; +} + +void XMLCALL +XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler) { + if (parser != NULL) + parser->m_notationDeclHandler = handler; +} + +void XMLCALL +XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end) { + if (parser == NULL) + return; + parser->m_startNamespaceDeclHandler = start; + parser->m_endNamespaceDeclHandler = end; +} + +void XMLCALL +XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start) { + if (parser != NULL) + parser->m_startNamespaceDeclHandler = start; +} + +void XMLCALL +XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end) { + if (parser != NULL) + parser->m_endNamespaceDeclHandler = end; +} + +void XMLCALL +XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler) { + if (parser != NULL) + parser->m_notStandaloneHandler = handler; +} + +void XMLCALL +XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler) { + if (parser != NULL) + parser->m_externalEntityRefHandler = handler; +} + +void XMLCALL +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) { + if (parser == NULL) + return; + if (arg) + parser->m_externalEntityRefHandlerArg = (XML_Parser)arg; + else + parser->m_externalEntityRefHandlerArg = parser; +} + +void XMLCALL +XML_SetSkippedEntityHandler(XML_Parser parser, + XML_SkippedEntityHandler handler) { + if (parser != NULL) + parser->m_skippedEntityHandler = handler; +} + +void XMLCALL +XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, void *data) { + if (parser == NULL) + return; + parser->m_unknownEncodingHandler = handler; + parser->m_unknownEncodingHandlerData = data; +} + +void XMLCALL +XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl) { + if (parser != NULL) + parser->m_elementDeclHandler = eldecl; +} + +void XMLCALL +XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl) { + if (parser != NULL) + parser->m_attlistDeclHandler = attdecl; +} + +void XMLCALL +XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler) { + if (parser != NULL) + parser->m_entityDeclHandler = handler; +} + +void XMLCALL +XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler handler) { + if (parser != NULL) + parser->m_xmlDeclHandler = handler; +} + +int XMLCALL +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing peParsing) { + if (parser == NULL) + return 0; + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) + return 0; +#ifdef XML_DTD + parser->m_paramEntityParsing = peParsing; + return 1; +#else + return peParsing == XML_PARAM_ENTITY_PARSING_NEVER; +#endif +} + +int XMLCALL +XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt) { + if (parser == NULL) + return 0; + if (parser->m_parentParser) + return XML_SetHashSalt(parser->m_parentParser, hash_salt); + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) + return 0; + parser->m_hash_secret_salt = hash_salt; + return 1; +} + +enum XML_Status XMLCALL +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { + if ((parser == NULL) || (len < 0) || ((s == NULL) && (len != 0))) { + if (parser != NULL) + parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT; + return XML_STATUS_ERROR; + } + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + parser->m_errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + case XML_FINISHED: + parser->m_errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + case XML_INITIALIZED: + if (parser->m_parentParser == NULL && ! startParsing(parser)) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return XML_STATUS_ERROR; + } + /* fall through */ + default: + parser->m_parsingStatus.parsing = XML_PARSING; + } + + if (len == 0) { + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; + if (! isFinal) + return XML_STATUS_OK; + parser->m_positionPtr = parser->m_bufferPtr; + parser->m_parseEndPtr = parser->m_bufferEnd; + + /* If data are left over from last buffer, and we now know that these + data are the final chunk of input, then we have to check them again + to detect errors based on that fact. + */ + parser->m_errorCode + = parser->m_processor(parser, parser->m_bufferPtr, + parser->m_parseEndPtr, &parser->m_bufferPtr); + + if (parser->m_errorCode == XML_ERROR_NONE) { + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + /* It is hard to be certain, but it seems that this case + * cannot occur. This code is cleaning up a previous parse + * with no new data (since len == 0). Changing the parsing + * state requires getting to execute a handler function, and + * there doesn't seem to be an opportunity for that while in + * this circumstance. + * + * Given the uncertainty, we retain the code but exclude it + * from coverage tests. + * + * LCOV_EXCL_START + */ + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; + return XML_STATUS_SUSPENDED; + /* LCOV_EXCL_STOP */ + case XML_INITIALIZED: + case XML_PARSING: + parser->m_parsingStatus.parsing = XML_FINISHED; + /* fall through */ + default: + return XML_STATUS_OK; + } + } + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } +#ifndef XML_CONTEXT_BYTES + else if (parser->m_bufferPtr == parser->m_bufferEnd) { + const char *end; + int nLeftOver; + enum XML_Status result; + /* Detect overflow (a+b > MAX <==> b > MAX-a) */ + if ((XML_Size)len > ((XML_Size)-1) / 2 - parser->m_parseEndByteIndex) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } + parser->m_parseEndByteIndex += len; + parser->m_positionPtr = s; + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; + + parser->m_errorCode + = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end); + + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } else { + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (isFinal) { + parser->m_parsingStatus.parsing = XML_FINISHED; + return XML_STATUS_OK; + } + /* fall through */ + default: + result = XML_STATUS_OK; + } + } + + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, + &parser->m_position); + nLeftOver = s + len - end; + if (nLeftOver) { + if (parser->m_buffer == NULL + || nLeftOver > parser->m_bufferLim - parser->m_buffer) { + /* avoid _signed_ integer overflow */ + char *temp = NULL; + const int bytesToAllocate = (int)((unsigned)len * 2U); + if (bytesToAllocate > 0) { + temp = (char *)REALLOC(parser, parser->m_buffer, bytesToAllocate); + } + if (temp == NULL) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } + parser->m_buffer = temp; + parser->m_bufferLim = parser->m_buffer + bytesToAllocate; + } + memcpy(parser->m_buffer, end, nLeftOver); + } + parser->m_bufferPtr = parser->m_buffer; + parser->m_bufferEnd = parser->m_buffer + nLeftOver; + parser->m_positionPtr = parser->m_bufferPtr; + parser->m_parseEndPtr = parser->m_bufferEnd; + parser->m_eventPtr = parser->m_bufferPtr; + parser->m_eventEndPtr = parser->m_bufferPtr; + return result; + } +#endif /* not defined XML_CONTEXT_BYTES */ + else { + void *buff = XML_GetBuffer(parser, len); + if (buff == NULL) + return XML_STATUS_ERROR; + else { + memcpy(buff, s, len); + return XML_ParseBuffer(parser, len, isFinal); + } + } +} + +enum XML_Status XMLCALL +XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { + const char *start; + enum XML_Status result = XML_STATUS_OK; + + if (parser == NULL) + return XML_STATUS_ERROR; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + parser->m_errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + case XML_FINISHED: + parser->m_errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + case XML_INITIALIZED: + /* Has someone called XML_GetBuffer successfully before? */ + if (! parser->m_bufferPtr) { + parser->m_errorCode = XML_ERROR_NO_BUFFER; + return XML_STATUS_ERROR; + } + + if (parser->m_parentParser == NULL && ! startParsing(parser)) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return XML_STATUS_ERROR; + } + /* fall through */ + default: + parser->m_parsingStatus.parsing = XML_PARSING; + } + + start = parser->m_bufferPtr; + parser->m_positionPtr = start; + parser->m_bufferEnd += len; + parser->m_parseEndPtr = parser->m_bufferEnd; + parser->m_parseEndByteIndex += len; + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; + + parser->m_errorCode = parser->m_processor( + parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr); + + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } else { + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (isFinal) { + parser->m_parsingStatus.parsing = XML_FINISHED; + return result; + } + default:; /* should not happen */ + } + } + + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; + return result; +} + +void *XMLCALL +XML_GetBuffer(XML_Parser parser, int len) { + if (parser == NULL) + return NULL; + if (len < 0) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + parser->m_errorCode = XML_ERROR_SUSPENDED; + return NULL; + case XML_FINISHED: + parser->m_errorCode = XML_ERROR_FINISHED; + return NULL; + default:; + } + + if (len > EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd)) { +#ifdef XML_CONTEXT_BYTES + int keep; +#endif /* defined XML_CONTEXT_BYTES */ + /* Do not invoke signed arithmetic overflow: */ + int neededSize = (int)((unsigned)len + + (unsigned)EXPAT_SAFE_PTR_DIFF( + parser->m_bufferEnd, parser->m_bufferPtr)); + if (neededSize < 0) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } +#ifdef XML_CONTEXT_BYTES + keep = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer); + if (keep > XML_CONTEXT_BYTES) + keep = XML_CONTEXT_BYTES; + /* Detect and prevent integer overflow */ + if (keep > INT_MAX - neededSize) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } + neededSize += keep; +#endif /* defined XML_CONTEXT_BYTES */ + if (neededSize + <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { +#ifdef XML_CONTEXT_BYTES + if (keep < EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer)) { + int offset + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer) + - keep; + /* The buffer pointers cannot be NULL here; we have at least some bytes + * in the buffer */ + memmove(parser->m_buffer, &parser->m_buffer[offset], + parser->m_bufferEnd - parser->m_bufferPtr + keep); + parser->m_bufferEnd -= offset; + parser->m_bufferPtr -= offset; + } +#else + if (parser->m_buffer && parser->m_bufferPtr) { + memmove(parser->m_buffer, parser->m_bufferPtr, + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + parser->m_bufferPtr = parser->m_buffer; + } +#endif /* not defined XML_CONTEXT_BYTES */ + } else { + char *newBuf; + int bufferSize + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferPtr); + if (bufferSize == 0) + bufferSize = INIT_BUFFER_SIZE; + do { + /* Do not invoke signed arithmetic overflow: */ + bufferSize = (int)(2U * (unsigned)bufferSize); + } while (bufferSize < neededSize && bufferSize > 0); + if (bufferSize <= 0) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } + newBuf = (char *)MALLOC(parser, bufferSize); + if (newBuf == 0) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } + parser->m_bufferLim = newBuf + bufferSize; +#ifdef XML_CONTEXT_BYTES + if (parser->m_bufferPtr) { + memcpy(newBuf, &parser->m_bufferPtr[-keep], + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep); + FREE(parser, parser->m_buffer); + parser->m_buffer = newBuf; + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep; + parser->m_bufferPtr = parser->m_buffer + keep; + } else { + /* This must be a brand new buffer with no data in it yet */ + parser->m_bufferEnd = newBuf; + parser->m_bufferPtr = parser->m_buffer = newBuf; + } +#else + if (parser->m_bufferPtr) { + memcpy(newBuf, parser->m_bufferPtr, + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); + FREE(parser, parser->m_buffer); + parser->m_bufferEnd + = newBuf + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + } else { + /* This must be a brand new buffer with no data in it yet */ + parser->m_bufferEnd = newBuf; + } + parser->m_bufferPtr = parser->m_buffer = newBuf; +#endif /* not defined XML_CONTEXT_BYTES */ + } + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_positionPtr = NULL; + } + return parser->m_bufferEnd; +} + +enum XML_Status XMLCALL +XML_StopParser(XML_Parser parser, XML_Bool resumable) { + if (parser == NULL) + return XML_STATUS_ERROR; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + if (resumable) { + parser->m_errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + } + parser->m_parsingStatus.parsing = XML_FINISHED; + break; + case XML_FINISHED: + parser->m_errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + default: + if (resumable) { +#ifdef XML_DTD + if (parser->m_isParamEntity) { + parser->m_errorCode = XML_ERROR_SUSPEND_PE; + return XML_STATUS_ERROR; + } +#endif + parser->m_parsingStatus.parsing = XML_SUSPENDED; + } else + parser->m_parsingStatus.parsing = XML_FINISHED; + } + return XML_STATUS_OK; +} + +enum XML_Status XMLCALL +XML_ResumeParser(XML_Parser parser) { + enum XML_Status result = XML_STATUS_OK; + + if (parser == NULL) + return XML_STATUS_ERROR; + if (parser->m_parsingStatus.parsing != XML_SUSPENDED) { + parser->m_errorCode = XML_ERROR_NOT_SUSPENDED; + return XML_STATUS_ERROR; + } + parser->m_parsingStatus.parsing = XML_PARSING; + + parser->m_errorCode = parser->m_processor( + parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); + + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } else { + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (parser->m_parsingStatus.finalBuffer) { + parser->m_parsingStatus.parsing = XML_FINISHED; + return result; + } + default:; + } + } + + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; + return result; +} + +void XMLCALL +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) { + if (parser == NULL) + return; + assert(status != NULL); + *status = parser->m_parsingStatus; +} + +enum XML_Error XMLCALL +XML_GetErrorCode(XML_Parser parser) { + if (parser == NULL) + return XML_ERROR_INVALID_ARGUMENT; + return parser->m_errorCode; +} + +XML_Index XMLCALL +XML_GetCurrentByteIndex(XML_Parser parser) { + if (parser == NULL) + return -1; + if (parser->m_eventPtr) + return (XML_Index)(parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - parser->m_eventPtr)); + return -1; +} + +int XMLCALL +XML_GetCurrentByteCount(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventEndPtr && parser->m_eventPtr) + return (int)(parser->m_eventEndPtr - parser->m_eventPtr); + return 0; +} + +const char *XMLCALL +XML_GetInputContext(XML_Parser parser, int *offset, int *size) { +#ifdef XML_CONTEXT_BYTES + if (parser == NULL) + return NULL; + if (parser->m_eventPtr && parser->m_buffer) { + if (offset != NULL) + *offset = (int)(parser->m_eventPtr - parser->m_buffer); + if (size != NULL) + *size = (int)(parser->m_bufferEnd - parser->m_buffer); + return parser->m_buffer; + } +#else + (void)parser; + (void)offset; + (void)size; +#endif /* defined XML_CONTEXT_BYTES */ + return (const char *)0; +} + +XML_Size XMLCALL +XML_GetCurrentLineNumber(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); + parser->m_positionPtr = parser->m_eventPtr; + } + return parser->m_position.lineNumber + 1; +} + +XML_Size XMLCALL +XML_GetCurrentColumnNumber(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); + parser->m_positionPtr = parser->m_eventPtr; + } + return parser->m_position.columnNumber; +} + +void XMLCALL +XML_FreeContentModel(XML_Parser parser, XML_Content *model) { + if (parser != NULL) + FREE(parser, model); +} + +void *XMLCALL +XML_MemMalloc(XML_Parser parser, size_t size) { + if (parser == NULL) + return NULL; + return MALLOC(parser, size); +} + +void *XMLCALL +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) { + if (parser == NULL) + return NULL; + return REALLOC(parser, ptr, size); +} + +void XMLCALL +XML_MemFree(XML_Parser parser, void *ptr) { + if (parser != NULL) + FREE(parser, ptr); +} + +void XMLCALL +XML_DefaultCurrent(XML_Parser parser) { + if (parser == NULL) + return; + if (parser->m_defaultHandler) { + if (parser->m_openInternalEntities) + reportDefault(parser, parser->m_internalEncoding, + parser->m_openInternalEntities->internalEventPtr, + parser->m_openInternalEntities->internalEventEndPtr); + else + reportDefault(parser, parser->m_encoding, parser->m_eventPtr, + parser->m_eventEndPtr); + } +} + +const XML_LChar *XMLCALL +XML_ErrorString(enum XML_Error code) { + switch (code) { + case XML_ERROR_NONE: + return NULL; + case XML_ERROR_NO_MEMORY: + return XML_L("out of memory"); + case XML_ERROR_SYNTAX: + return XML_L("syntax error"); + case XML_ERROR_NO_ELEMENTS: + return XML_L("no element found"); + case XML_ERROR_INVALID_TOKEN: + return XML_L("not well-formed (invalid token)"); + case XML_ERROR_UNCLOSED_TOKEN: + return XML_L("unclosed token"); + case XML_ERROR_PARTIAL_CHAR: + return XML_L("partial character"); + case XML_ERROR_TAG_MISMATCH: + return XML_L("mismatched tag"); + case XML_ERROR_DUPLICATE_ATTRIBUTE: + return XML_L("duplicate attribute"); + case XML_ERROR_JUNK_AFTER_DOC_ELEMENT: + return XML_L("junk after document element"); + case XML_ERROR_PARAM_ENTITY_REF: + return XML_L("illegal parameter entity reference"); + case XML_ERROR_UNDEFINED_ENTITY: + return XML_L("undefined entity"); + case XML_ERROR_RECURSIVE_ENTITY_REF: + return XML_L("recursive entity reference"); + case XML_ERROR_ASYNC_ENTITY: + return XML_L("asynchronous entity"); + case XML_ERROR_BAD_CHAR_REF: + return XML_L("reference to invalid character number"); + case XML_ERROR_BINARY_ENTITY_REF: + return XML_L("reference to binary entity"); + case XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF: + return XML_L("reference to external entity in attribute"); + case XML_ERROR_MISPLACED_XML_PI: + return XML_L("XML or text declaration not at start of entity"); + case XML_ERROR_UNKNOWN_ENCODING: + return XML_L("unknown encoding"); + case XML_ERROR_INCORRECT_ENCODING: + return XML_L("encoding specified in XML declaration is incorrect"); + case XML_ERROR_UNCLOSED_CDATA_SECTION: + return XML_L("unclosed CDATA section"); + case XML_ERROR_EXTERNAL_ENTITY_HANDLING: + return XML_L("error in processing external entity reference"); + case XML_ERROR_NOT_STANDALONE: + return XML_L("document is not standalone"); + case XML_ERROR_UNEXPECTED_STATE: + return XML_L("unexpected parser state - please send a bug report"); + case XML_ERROR_ENTITY_DECLARED_IN_PE: + return XML_L("entity declared in parameter entity"); + case XML_ERROR_FEATURE_REQUIRES_XML_DTD: + return XML_L("requested feature requires XML_DTD support in Expat"); + case XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING: + return XML_L("cannot change setting once parsing has begun"); + /* Added in 1.95.7. */ + case XML_ERROR_UNBOUND_PREFIX: + return XML_L("unbound prefix"); + /* Added in 1.95.8. */ + case XML_ERROR_UNDECLARING_PREFIX: + return XML_L("must not undeclare prefix"); + case XML_ERROR_INCOMPLETE_PE: + return XML_L("incomplete markup in parameter entity"); + case XML_ERROR_XML_DECL: + return XML_L("XML declaration not well-formed"); + case XML_ERROR_TEXT_DECL: + return XML_L("text declaration not well-formed"); + case XML_ERROR_PUBLICID: + return XML_L("illegal character(s) in public id"); + case XML_ERROR_SUSPENDED: + return XML_L("parser suspended"); + case XML_ERROR_NOT_SUSPENDED: + return XML_L("parser not suspended"); + case XML_ERROR_ABORTED: + return XML_L("parsing aborted"); + case XML_ERROR_FINISHED: + return XML_L("parsing finished"); + case XML_ERROR_SUSPEND_PE: + return XML_L("cannot suspend in external parameter entity"); + /* Added in 2.0.0. */ + case XML_ERROR_RESERVED_PREFIX_XML: + return XML_L( + "reserved prefix (xml) must not be undeclared or bound to another namespace name"); + case XML_ERROR_RESERVED_PREFIX_XMLNS: + return XML_L("reserved prefix (xmlns) must not be declared or undeclared"); + case XML_ERROR_RESERVED_NAMESPACE_URI: + return XML_L( + "prefix must not be bound to one of the reserved namespace names"); + /* Added in 2.2.5. */ + case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */ + return XML_L("invalid argument"); + /* Added in 2.3.0. */ + case XML_ERROR_NO_BUFFER: + return XML_L( + "a successful prior call to function XML_GetBuffer is required"); + /* Added in 2.4.0. */ + case XML_ERROR_AMPLIFICATION_LIMIT_BREACH: + return XML_L( + "limit on input amplification factor (from DTD and entities) breached"); + } + return NULL; +} + +const XML_LChar *XMLCALL +XML_ExpatVersion(void) { + /* V1 is used to string-ize the version number. However, it would + string-ize the actual version macro *names* unless we get them + substituted before being passed to V1. CPP is defined to expand + a macro, then rescan for more expansions. Thus, we use V2 to expand + the version macros, then CPP will expand the resulting V1() macro + with the correct numerals. */ + /* ### I'm assuming cpp is portable in this respect... */ + +#define V1(a, b, c) XML_L(#a) XML_L(".") XML_L(#b) XML_L(".") XML_L(#c) +#define V2(a, b, c) XML_L("expat_") V1(a, b, c) + + return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); + +#undef V1 +#undef V2 +} + +XML_Expat_Version XMLCALL +XML_ExpatVersionInfo(void) { + XML_Expat_Version version; + + version.major = XML_MAJOR_VERSION; + version.minor = XML_MINOR_VERSION; + version.micro = XML_MICRO_VERSION; + + return version; +} + +const XML_Feature *XMLCALL +XML_GetFeatureList(void) { + static const XML_Feature features[] = { + {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, +#ifdef XML_UNICODE + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, +#endif +#ifdef XML_UNICODE_WCHAR_T + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, +#endif +#ifdef XML_DTD + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, +#endif +#ifdef XML_CONTEXT_BYTES + {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), + XML_CONTEXT_BYTES}, +#endif +#ifdef XML_MIN_SIZE + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, +#endif +#ifdef XML_NS + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, +#endif +#ifdef XML_LARGE_SIZE + {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, +#endif +#ifdef XML_ATTR_INFO + {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, +#endif +#ifdef XML_DTD + /* Added in Expat 2.4.0. */ + {XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, + XML_L("XML_BLAP_MAX_AMP"), + (long int) + EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT}, + {XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT, + XML_L("XML_BLAP_ACT_THRES"), + EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT}, +#endif + {XML_FEATURE_END, NULL, 0}}; + + return features; +} + +#ifdef XML_DTD +XML_Bool XMLCALL +XML_SetBillionLaughsAttackProtectionMaximumAmplification( + XML_Parser parser, float maximumAmplificationFactor) { + if ((parser == NULL) || (parser->m_parentParser != NULL) + || isnan(maximumAmplificationFactor) + || (maximumAmplificationFactor < 1.0f)) { + return XML_FALSE; + } + parser->m_accounting.maximumAmplificationFactor = maximumAmplificationFactor; + return XML_TRUE; +} + +XML_Bool XMLCALL +XML_SetBillionLaughsAttackProtectionActivationThreshold( + XML_Parser parser, unsigned long long activationThresholdBytes) { + if ((parser == NULL) || (parser->m_parentParser != NULL)) { + return XML_FALSE; + } + parser->m_accounting.activationThresholdBytes = activationThresholdBytes; + return XML_TRUE; +} +#endif /* XML_DTD */ + +/* Initially tag->rawName always points into the parse buffer; + for those TAG instances opened while the current parse buffer was + processed, and not yet closed, we need to store tag->rawName in a more + permanent location, since the parse buffer is about to be discarded. +*/ +static XML_Bool +storeRawNames(XML_Parser parser) { + TAG *tag = parser->m_tagStack; + while (tag) { + int bufSize; + int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1); + size_t rawNameLen; + char *rawNameBuf = tag->buf + nameLen; + /* Stop if already stored. Since m_tagStack is a stack, we can stop + at the first entry that has already been copied; everything + below it in the stack is already been accounted for in a + previous call to this function. + */ + if (tag->rawName == rawNameBuf) + break; + /* For re-use purposes we need to ensure that the + size of tag->buf is a multiple of sizeof(XML_Char). + */ + rawNameLen = ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); + /* Detect and prevent integer overflow. */ + if (rawNameLen > (size_t)INT_MAX - nameLen) + return XML_FALSE; + bufSize = nameLen + (int)rawNameLen; + if (bufSize > tag->bufEnd - tag->buf) { + char *temp = (char *)REALLOC(parser, tag->buf, bufSize); + if (temp == NULL) + return XML_FALSE; + /* if tag->name.str points to tag->buf (only when namespace + processing is off) then we have to update it + */ + if (tag->name.str == (XML_Char *)tag->buf) + tag->name.str = (XML_Char *)temp; + /* if tag->name.localPart is set (when namespace processing is on) + then update it as well, since it will always point into tag->buf + */ + if (tag->name.localPart) + tag->name.localPart + = (XML_Char *)temp + (tag->name.localPart - (XML_Char *)tag->buf); + tag->buf = temp; + tag->bufEnd = temp + bufSize; + rawNameBuf = temp + nameLen; + } + memcpy(rawNameBuf, tag->rawName, tag->rawNameLength); + tag->rawName = rawNameBuf; + tag = tag->parent; + } + return XML_TRUE; +} + +static enum XML_Error PTRCALL +contentProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result = doContent( + parser, 0, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_ACCOUNT_DIRECT); + if (result == XML_ERROR_NONE) { + if (! storeRawNames(parser)) + return XML_ERROR_NO_MEMORY; + } + return result; +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + parser->m_processor = externalEntityInitProcessor2; + return externalEntityInitProcessor2(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor2(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + const char *next = start; /* XmlContentTok doesn't always set the last arg */ + int tok = XmlContentTok(parser->m_encoding, start, end, &next); + switch (tok) { + case XML_TOK_BOM: +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, start, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif /* XML_DTD */ + + /* If we are at the end of the buffer, this would cause the next stage, + i.e. externalEntityInitProcessor3, to pass control directly to + doContent (by detecting XML_TOK_NONE) without processing any xml text + declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. + */ + if (next == end && ! parser->m_parsingStatus.finalBuffer) { + *endPtr = next; + return XML_ERROR_NONE; + } + start = next; + break; + case XML_TOK_PARTIAL: + if (! parser->m_parsingStatus.finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + parser->m_eventPtr = start; + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (! parser->m_parsingStatus.finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + parser->m_eventPtr = start; + return XML_ERROR_PARTIAL_CHAR; + } + parser->m_processor = externalEntityInitProcessor3; + return externalEntityInitProcessor3(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor3(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + int tok; + const char *next = start; /* XmlContentTok doesn't always set the last arg */ + parser->m_eventPtr = start; + tok = XmlContentTok(parser->m_encoding, start, end, &next); + /* Note: These bytes are accounted later in: + - processXmlDecl + - externalEntityContentProcessor + */ + parser->m_eventEndPtr = next; + + switch (tok) { + case XML_TOK_XML_DECL: { + enum XML_Error result; + result = processXmlDecl(parser, 1, start, next); + if (result != XML_ERROR_NONE) + return result; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *endPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + start = next; + } + } break; + case XML_TOK_PARTIAL: + if (! parser->m_parsingStatus.finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (! parser->m_parsingStatus.finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + } + parser->m_processor = externalEntityContentProcessor; + parser->m_tagLevel = 1; + return externalEntityContentProcessor(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityContentProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + enum XML_Error result + = doContent(parser, 1, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, + XML_ACCOUNT_ENTITY_EXPANSION); + if (result == XML_ERROR_NONE) { + if (! storeRawNames(parser)) + return XML_ERROR_NO_MEMORY; + } + return result; +} + +static enum XML_Error +doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, + const char *s, const char *end, const char **nextPtr, + XML_Bool haveMore, enum XML_Account account) { + /* save one level of indirection */ + DTD *const dtd = parser->m_dtd; + + const char **eventPP; + const char **eventEndPP; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + + for (;;) { + const char *next = s; /* XmlContentTok doesn't always set the last arg */ + int tok = XmlContentTok(enc, s, end, &next); +#ifdef XML_DTD + const char *accountAfter + = ((tok == XML_TOK_TRAILING_RSQB) || (tok == XML_TOK_TRAILING_CR)) + ? (haveMore ? s /* i.e. 0 bytes */ : end) + : next; + if (! accountingDiffTolerated(parser, tok, s, accountAfter, __LINE__, + account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif + *eventEndPP = next; + switch (tok) { + case XML_TOK_TRAILING_CR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + *eventEndPP = end; + if (parser->m_characterDataHandler) { + XML_Char c = 0xA; + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, end); + /* We are at the end of the final buffer, should we check for + XML_SUSPENDED, XML_FINISHED? + */ + if (startTagLevel == 0) + return XML_ERROR_NO_ELEMENTS; + if (parser->m_tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + *nextPtr = end; + return XML_ERROR_NONE; + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (startTagLevel > 0) { + if (parser->m_tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_NO_ELEMENTS; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { +#ifdef XML_DTD + /* NOTE: We are replacing 4-6 characters original input for 1 character + * so there is no amplification and hence recording without + * protection. */ + accountingDiffTolerated(parser, tok, (char *)&ch, + ((char *)&ch) + sizeof(XML_Char), __LINE__, + XML_ACCOUNT_ENTITY_EXPANSION); +#endif /* XML_DTD */ + if (parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&dtd->pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity or default handler. + */ + if (! dtd->hasParamEntityRefs || dtd->standalone) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->notation) + return XML_ERROR_BINARY_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + if (! parser->m_defaultExpandInternalEntities) { + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, + 0); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + result = processInternalEntity(parser, entity, XML_FALSE); + if (result != XML_ERROR_NONE) + return result; + } else if (parser->m_externalEntityRefHandler) { + const XML_Char *context; + entity->open = XML_TRUE; + context = getContext(parser); + entity->open = XML_FALSE; + if (! context) + return XML_ERROR_NO_MEMORY; + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, context, entity->base, + entity->systemId, entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + poolDiscard(&parser->m_tempPool); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + case XML_TOK_START_TAG_NO_ATTS: + /* fall through */ + case XML_TOK_START_TAG_WITH_ATTS: { + TAG *tag; + enum XML_Error result; + XML_Char *toPtr; + if (parser->m_freeTagList) { + tag = parser->m_freeTagList; + parser->m_freeTagList = parser->m_freeTagList->parent; + } else { + tag = (TAG *)MALLOC(parser, sizeof(TAG)); + if (! tag) + return XML_ERROR_NO_MEMORY; + tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE); + if (! tag->buf) { + FREE(parser, tag); + return XML_ERROR_NO_MEMORY; + } + tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; + } + tag->bindings = NULL; + tag->parent = parser->m_tagStack; + parser->m_tagStack = tag; + tag->name.localPart = NULL; + tag->name.prefix = NULL; + tag->rawName = s + enc->minBytesPerChar; + tag->rawNameLength = XmlNameLength(enc, tag->rawName); + ++parser->m_tagLevel; + { + const char *rawNameEnd = tag->rawName + tag->rawNameLength; + const char *fromPtr = tag->rawName; + toPtr = (XML_Char *)tag->buf; + for (;;) { + int bufSize; + int convLen; + const enum XML_Convert_Result convert_res + = XmlConvert(enc, &fromPtr, rawNameEnd, (ICHAR **)&toPtr, + (ICHAR *)tag->bufEnd - 1); + convLen = (int)(toPtr - (XML_Char *)tag->buf); + if ((fromPtr >= rawNameEnd) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { + tag->name.strLen = convLen; + break; + } + bufSize = (int)(tag->bufEnd - tag->buf) << 1; + { + char *temp = (char *)REALLOC(parser, tag->buf, bufSize); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + tag->buf = temp; + tag->bufEnd = temp + bufSize; + toPtr = (XML_Char *)temp + convLen; + } + } + } + tag->name.str = (XML_Char *)tag->buf; + *toPtr = XML_T('\0'); + result + = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings), account); + if (result) + return result; + if (parser->m_startElementHandler) + parser->m_startElementHandler(parser->m_handlerArg, tag->name.str, + (const XML_Char **)parser->m_atts); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + break; + } + case XML_TOK_EMPTY_ELEMENT_NO_ATTS: + /* fall through */ + case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: { + const char *rawName = s + enc->minBytesPerChar; + enum XML_Error result; + BINDING *bindings = NULL; + XML_Bool noElmHandlers = XML_TRUE; + TAG_NAME name; + name.str = poolStoreString(&parser->m_tempPool, enc, rawName, + rawName + XmlNameLength(enc, rawName)); + if (! name.str) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + result = storeAtts(parser, enc, s, &name, &bindings, + XML_ACCOUNT_NONE /* token spans whole start tag */); + if (result != XML_ERROR_NONE) { + freeBindings(parser, bindings); + return result; + } + poolFinish(&parser->m_tempPool); + if (parser->m_startElementHandler) { + parser->m_startElementHandler(parser->m_handlerArg, name.str, + (const XML_Char **)parser->m_atts); + noElmHandlers = XML_FALSE; + } + if (parser->m_endElementHandler) { + if (parser->m_startElementHandler) + *eventPP = *eventEndPP; + parser->m_endElementHandler(parser->m_handlerArg, name.str); + noElmHandlers = XML_FALSE; + } + if (noElmHandlers && parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + freeBindings(parser, bindings); + } + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + parser->m_processor = epilogProcessor; + else + return epilogProcessor(parser, next, end, nextPtr); + } + break; + case XML_TOK_END_TAG: + if (parser->m_tagLevel == startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + else { + int len; + const char *rawName; + TAG *tag = parser->m_tagStack; + parser->m_tagStack = tag->parent; + tag->parent = parser->m_freeTagList; + parser->m_freeTagList = tag; + rawName = s + enc->minBytesPerChar * 2; + len = XmlNameLength(enc, rawName); + if (len != tag->rawNameLength + || memcmp(tag->rawName, rawName, len) != 0) { + *eventPP = rawName; + return XML_ERROR_TAG_MISMATCH; + } + --parser->m_tagLevel; + if (parser->m_endElementHandler) { + const XML_Char *localPart; + const XML_Char *prefix; + XML_Char *uri; + localPart = tag->name.localPart; + if (parser->m_ns && localPart) { + /* localPart and prefix may have been overwritten in + tag->name.str, since this points to the binding->uri + buffer which gets re-used; so we have to add them again + */ + uri = (XML_Char *)tag->name.str + tag->name.uriLen; + /* don't need to check for space - already done in storeAtts() */ + while (*localPart) + *uri++ = *localPart++; + prefix = (XML_Char *)tag->name.prefix; + if (parser->m_ns_triplets && prefix) { + *uri++ = parser->m_namespaceSeparator; + while (*prefix) + *uri++ = *prefix++; + } + *uri = XML_T('\0'); + } + parser->m_endElementHandler(parser->m_handlerArg, tag->name.str); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + while (tag->bindings) { + BINDING *b = tag->bindings; + if (parser->m_endNamespaceDeclHandler) + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, + b->prefix->name); + tag->bindings = tag->bindings->nextTagBinding; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + parser->m_processor = epilogProcessor; + else + return epilogProcessor(parser, next, end, nextPtr); + } + } + break; + case XML_TOK_CHAR_REF: { + int n = XmlCharRefNumber(enc, s); + if (n < 0) + return XML_ERROR_BAD_CHAR_REF; + if (parser->m_characterDataHandler) { + XML_Char buf[XML_ENCODE_MAX]; + parser->m_characterDataHandler(parser->m_handlerArg, buf, + XmlEncode(n, (ICHAR *)buf)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + case XML_TOK_DATA_NEWLINE: + if (parser->m_characterDataHandler) { + XML_Char c = 0xA; + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_CDATA_SECT_OPEN: { + enum XML_Error result; + if (parser->m_startCdataSectionHandler) + parser->m_startCdataSectionHandler(parser->m_handlerArg); + /* BEGIN disabled code */ + /* Suppose you doing a transformation on a document that involves + changing only the character data. You set up a defaultHandler + and a characterDataHandler. The defaultHandler simply copies + characters through. The characterDataHandler does the + transformation and writes the characters out escaping them as + necessary. This case will fail to work if we leave out the + following two lines (because & and < inside CDATA sections will + be incorrectly escaped). + + However, now we have a start/endCdataSectionHandler, so it seems + easier to let the user deal with this. + */ + else if (0 && parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + result + = doCdataSection(parser, enc, &next, end, nextPtr, haveMore, account); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = cdataSectionProcessor; + return result; + } + } break; + case XML_TOK_TRAILING_RSQB: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (parser->m_characterDataHandler) { + if (MUST_CONVERT(enc, s)) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + parser->m_characterDataHandler( + parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + } else + parser->m_characterDataHandler( + parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, end); + /* We are at the end of the final buffer, should we check for + XML_SUSPENDED, XML_FINISHED? + */ + if (startTagLevel == 0) { + *eventPP = end; + return XML_ERROR_NO_ELEMENTS; + } + if (parser->m_tagLevel != startTagLevel) { + *eventPP = end; + return XML_ERROR_ASYNC_ENTITY; + } + *nextPtr = end; + return XML_ERROR_NONE; + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = s; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; + } + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; + case XML_TOK_PI: + if (! reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (! reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + default: + /* All of the tokens produced by XmlContentTok() have their own + * explicit cases, so this default is not strictly necessary. + * However it is a useful safety net, so we retain the code and + * simply exclude it from the coverage tests. + * + * LCOV_EXCL_START + */ + if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + /* LCOV_EXCL_STOP */ + } + *eventPP = s = next; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default:; + } + } + /* not reached */ +} + +/* This function does not call free() on the allocated memory, merely + * moving it to the parser's m_freeBindingList where it can be freed or + * reused as appropriate. + */ +static void +freeBindings(XML_Parser parser, BINDING *bindings) { + while (bindings) { + BINDING *b = bindings; + + /* m_startNamespaceDeclHandler will have been called for this + * binding in addBindings(), so call the end handler now. + */ + if (parser->m_endNamespaceDeclHandler) + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name); + + bindings = bindings->nextTagBinding; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } +} + +/* Precondition: all arguments must be non-NULL; + Purpose: + - normalize attributes + - check attributes for well-formedness + - generate namespace aware attribute names (URI, prefix) + - build list of attributes for startElementHandler + - default attributes + - process namespace declarations (check and report them) + - generate namespace aware element name (URI, prefix) +*/ +static enum XML_Error +storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, + TAG_NAME *tagNamePtr, BINDING **bindingsPtr, + enum XML_Account account) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + ELEMENT_TYPE *elementType; + int nDefaultAtts; + const XML_Char **appAtts; /* the attribute list for the application */ + int attIndex = 0; + int prefixLen; + int i; + int n; + XML_Char *uri; + int nPrefixes = 0; + BINDING *binding; + const XML_Char *localPart; + + /* lookup the element type name */ + elementType + = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str, 0); + if (! elementType) { + const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str); + if (! name) + return XML_ERROR_NO_MEMORY; + elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, + sizeof(ELEMENT_TYPE)); + if (! elementType) + return XML_ERROR_NO_MEMORY; + if (parser->m_ns && ! setElementTypePrefix(parser, elementType)) + return XML_ERROR_NO_MEMORY; + } + nDefaultAtts = elementType->nDefaultAtts; + + /* get the attributes from the tokenizer */ + n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts); + + /* Detect and prevent integer overflow */ + if (n > INT_MAX - nDefaultAtts) { + return XML_ERROR_NO_MEMORY; + } + + if (n + nDefaultAtts > parser->m_attsSize) { + int oldAttsSize = parser->m_attsSize; + ATTRIBUTE *temp; +#ifdef XML_ATTR_INFO + XML_AttrInfo *temp2; +#endif + + /* Detect and prevent integer overflow */ + if ((nDefaultAtts > INT_MAX - INIT_ATTS_SIZE) + || (n > INT_MAX - (nDefaultAtts + INIT_ATTS_SIZE))) { + return XML_ERROR_NO_MEMORY; + } + + parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(ATTRIBUTE)) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } +#endif + + temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, + parser->m_attsSize * sizeof(ATTRIBUTE)); + if (temp == NULL) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } + parser->m_atts = temp; +#ifdef XML_ATTR_INFO + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +# if UINT_MAX >= SIZE_MAX + if ((unsigned)parser->m_attsSize > (size_t)(-1) / sizeof(XML_AttrInfo)) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } +# endif + + temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, + parser->m_attsSize * sizeof(XML_AttrInfo)); + if (temp2 == NULL) { + parser->m_attsSize = oldAttsSize; + return XML_ERROR_NO_MEMORY; + } + parser->m_attInfo = temp2; +#endif + if (n > oldAttsSize) + XmlGetAttributes(enc, attStr, n, parser->m_atts); + } + + appAtts = (const XML_Char **)parser->m_atts; + for (i = 0; i < n; i++) { + ATTRIBUTE *currAtt = &parser->m_atts[i]; +#ifdef XML_ATTR_INFO + XML_AttrInfo *currAttInfo = &parser->m_attInfo[i]; +#endif + /* add the name and value to the attribute list */ + ATTRIBUTE_ID *attId + = getAttributeId(parser, enc, currAtt->name, + currAtt->name + XmlNameLength(enc, currAtt->name)); + if (! attId) + return XML_ERROR_NO_MEMORY; +#ifdef XML_ATTR_INFO + currAttInfo->nameStart + = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name); + currAttInfo->nameEnd + = currAttInfo->nameStart + XmlNameLength(enc, currAtt->name); + currAttInfo->valueStart = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valuePtr); + currAttInfo->valueEnd = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valueEnd); +#endif + /* Detect duplicate attributes by their QNames. This does not work when + namespace processing is turned on and different prefixes for the same + namespace are used. For this case we have a check further down. + */ + if ((attId->name)[-1]) { + if (enc == parser->m_encoding) + parser->m_eventPtr = parser->m_atts[i].name; + return XML_ERROR_DUPLICATE_ATTRIBUTE; + } + (attId->name)[-1] = 1; + appAtts[attIndex++] = attId->name; + if (! parser->m_atts[i].normalized) { + enum XML_Error result; + XML_Bool isCdata = XML_TRUE; + + /* figure out whether declared as other than CDATA */ + if (attId->maybeTokenized) { + int j; + for (j = 0; j < nDefaultAtts; j++) { + if (attId == elementType->defaultAtts[j].id) { + isCdata = elementType->defaultAtts[j].isCdata; + break; + } + } + } + + /* normalize the attribute value */ + result = storeAttributeValue( + parser, enc, isCdata, parser->m_atts[i].valuePtr, + parser->m_atts[i].valueEnd, &parser->m_tempPool, account); + if (result) + return result; + appAtts[attIndex] = poolStart(&parser->m_tempPool); + poolFinish(&parser->m_tempPool); + } else { + /* the value did not need normalizing */ + appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, + parser->m_atts[i].valuePtr, + parser->m_atts[i].valueEnd); + if (appAtts[attIndex] == 0) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + } + /* handle prefixed attribute names */ + if (attId->prefix) { + if (attId->xmlns) { + /* deal with namespace declarations here */ + enum XML_Error result = addBinding(parser, attId->prefix, attId, + appAtts[attIndex], bindingsPtr); + if (result) + return result; + --attIndex; + } else { + /* deal with other prefixed names later */ + attIndex++; + nPrefixes++; + (attId->name)[-1] = 2; + } + } else + attIndex++; + } + + /* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */ + parser->m_nSpecifiedAtts = attIndex; + if (elementType->idAtt && (elementType->idAtt->name)[-1]) { + for (i = 0; i < attIndex; i += 2) + if (appAtts[i] == elementType->idAtt->name) { + parser->m_idAttIndex = i; + break; + } + } else + parser->m_idAttIndex = -1; + + /* do attribute defaulting */ + for (i = 0; i < nDefaultAtts; i++) { + const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i; + if (! (da->id->name)[-1] && da->value) { + if (da->id->prefix) { + if (da->id->xmlns) { + enum XML_Error result = addBinding(parser, da->id->prefix, da->id, + da->value, bindingsPtr); + if (result) + return result; + } else { + (da->id->name)[-1] = 2; + nPrefixes++; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } else { + (da->id->name)[-1] = 1; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } + } + appAtts[attIndex] = 0; + + /* expand prefixed attribute names, check for duplicates, + and clear flags that say whether attributes were specified */ + i = 0; + if (nPrefixes) { + int j; /* hash table index */ + unsigned long version = parser->m_nsAttsVersion; + + /* Detect and prevent invalid shift */ + if (parser->m_nsAttsPower >= sizeof(unsigned int) * 8 /* bits per byte */) { + return XML_ERROR_NO_MEMORY; + } + + unsigned int nsAttsSize = 1u << parser->m_nsAttsPower; + unsigned char oldNsAttsPower = parser->m_nsAttsPower; + /* size of hash table must be at least 2 * (# of prefixed attributes) */ + if ((nPrefixes << 1) + >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */ + NS_ATT *temp; + /* hash table size must also be a power of 2 and >= 8 */ + while (nPrefixes >> parser->m_nsAttsPower++) + ; + if (parser->m_nsAttsPower < 3) + parser->m_nsAttsPower = 3; + + /* Detect and prevent invalid shift */ + if (parser->m_nsAttsPower >= sizeof(nsAttsSize) * 8 /* bits per byte */) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; + return XML_ERROR_NO_MEMORY; + } + + nsAttsSize = 1u << parser->m_nsAttsPower; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (nsAttsSize > (size_t)(-1) / sizeof(NS_ATT)) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; + return XML_ERROR_NO_MEMORY; + } +#endif + + temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, + nsAttsSize * sizeof(NS_ATT)); + if (! temp) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; + return XML_ERROR_NO_MEMORY; + } + parser->m_nsAtts = temp; + version = 0; /* force re-initialization of m_nsAtts hash table */ + } + /* using a version flag saves us from initializing m_nsAtts every time */ + if (! version) { /* initialize version flags when version wraps around */ + version = INIT_ATTS_VERSION; + for (j = nsAttsSize; j != 0;) + parser->m_nsAtts[--j].version = version; + } + parser->m_nsAttsVersion = --version; + + /* expand prefixed names and check for duplicates */ + for (; i < attIndex; i += 2) { + const XML_Char *s = appAtts[i]; + if (s[-1] == 2) { /* prefixed */ + ATTRIBUTE_ID *id; + const BINDING *b; + unsigned long uriHash; + struct siphash sip_state; + struct sipkey sip_key; + + copy_salt_to_sipkey(parser, &sip_key); + sip24_init(&sip_state, &sip_key); + + ((XML_Char *)s)[-1] = 0; /* clear flag */ + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0); + if (! id || ! id->prefix) { + /* This code is walking through the appAtts array, dealing + * with (in this case) a prefixed attribute name. To be in + * the array, the attribute must have already been bound, so + * has to have passed through the hash table lookup once + * already. That implies that an entry for it already + * exists, so the lookup above will return a pointer to + * already allocated memory. There is no opportunaity for + * the allocator to fail, so the condition above cannot be + * fulfilled. + * + * Since it is difficult to be certain that the above + * analysis is complete, we retain the test and merely + * remove the code from coverage tests. + */ + return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */ + } + b = id->prefix->binding; + if (! b) + return XML_ERROR_UNBOUND_PREFIX; + + for (j = 0; j < b->uriLen; j++) { + const XML_Char c = b->uri[j]; + if (! poolAppendChar(&parser->m_tempPool, c)) + return XML_ERROR_NO_MEMORY; + } + + sip24_update(&sip_state, b->uri, b->uriLen * sizeof(XML_Char)); + + while (*s++ != XML_T(ASCII_COLON)) + ; + + sip24_update(&sip_state, s, keylen(s) * sizeof(XML_Char)); + + do { /* copies null terminator */ + if (! poolAppendChar(&parser->m_tempPool, *s)) + return XML_ERROR_NO_MEMORY; + } while (*s++); + + uriHash = (unsigned long)sip24_final(&sip_state); + + { /* Check hash table for duplicate of expanded name (uriName). + Derived from code in lookup(parser, HASH_TABLE *table, ...). + */ + unsigned char step = 0; + unsigned long mask = nsAttsSize - 1; + j = uriHash & mask; /* index into hash table */ + while (parser->m_nsAtts[j].version == version) { + /* for speed we compare stored hash values first */ + if (uriHash == parser->m_nsAtts[j].hash) { + const XML_Char *s1 = poolStart(&parser->m_tempPool); + const XML_Char *s2 = parser->m_nsAtts[j].uriName; + /* s1 is null terminated, but not s2 */ + for (; *s1 == *s2 && *s1 != 0; s1++, s2++) + ; + if (*s1 == 0) + return XML_ERROR_DUPLICATE_ATTRIBUTE; + } + if (! step) + step = PROBE_STEP(uriHash, mask, parser->m_nsAttsPower); + j < step ? (j += nsAttsSize - step) : (j -= step); + } + } + + if (parser->m_ns_triplets) { /* append namespace separator and prefix */ + parser->m_tempPool.ptr[-1] = parser->m_namespaceSeparator; + s = b->prefix->name; + do { + if (! poolAppendChar(&parser->m_tempPool, *s)) + return XML_ERROR_NO_MEMORY; + } while (*s++); + } + + /* store expanded name in attribute list */ + s = poolStart(&parser->m_tempPool); + poolFinish(&parser->m_tempPool); + appAtts[i] = s; + + /* fill empty slot with new version, uriName and hash value */ + parser->m_nsAtts[j].version = version; + parser->m_nsAtts[j].hash = uriHash; + parser->m_nsAtts[j].uriName = s; + + if (! --nPrefixes) { + i += 2; + break; + } + } else /* not prefixed */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ + } + } + /* clear flags for the remaining attributes */ + for (; i < attIndex; i += 2) + ((XML_Char *)(appAtts[i]))[-1] = 0; + for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) + binding->attId->name[-1] = 0; + + if (! parser->m_ns) + return XML_ERROR_NONE; + + /* expand the element type name */ + if (elementType->prefix) { + binding = elementType->prefix->binding; + if (! binding) + return XML_ERROR_UNBOUND_PREFIX; + localPart = tagNamePtr->str; + while (*localPart++ != XML_T(ASCII_COLON)) + ; + } else if (dtd->defaultPrefix.binding) { + binding = dtd->defaultPrefix.binding; + localPart = tagNamePtr->str; + } else + return XML_ERROR_NONE; + prefixLen = 0; + if (parser->m_ns_triplets && binding->prefix->name) { + for (; binding->prefix->name[prefixLen++];) + ; /* prefixLen includes null terminator */ + } + tagNamePtr->localPart = localPart; + tagNamePtr->uriLen = binding->uriLen; + tagNamePtr->prefix = binding->prefix->name; + tagNamePtr->prefixLen = prefixLen; + for (i = 0; localPart[i++];) + ; /* i includes null terminator */ + + /* Detect and prevent integer overflow */ + if (binding->uriLen > INT_MAX - prefixLen + || i > INT_MAX - (binding->uriLen + prefixLen)) { + return XML_ERROR_NO_MEMORY; + } + + n = i + binding->uriLen + prefixLen; + if (n > binding->uriAlloc) { + TAG *p; + + /* Detect and prevent integer overflow */ + if (n > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(n + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + + uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char)); + if (! uri) + return XML_ERROR_NO_MEMORY; + binding->uriAlloc = n + EXPAND_SPARE; + memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); + for (p = parser->m_tagStack; p; p = p->parent) + if (p->name.str == binding->uri) + p->name.str = uri; + FREE(parser, binding->uri); + binding->uri = uri; + } + /* if m_namespaceSeparator != '\0' then uri includes it already */ + uri = binding->uri + binding->uriLen; + memcpy(uri, localPart, i * sizeof(XML_Char)); + /* we always have a namespace separator between localPart and prefix */ + if (prefixLen) { + uri += i - 1; + *uri = parser->m_namespaceSeparator; /* replace null terminator */ + memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); + } + tagNamePtr->str = binding->uri; + return XML_ERROR_NONE; +} + +/* addBinding() overwrites the value of prefix->binding without checking. + Therefore one must keep track of the old value outside of addBinding(). +*/ +static enum XML_Error +addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, + const XML_Char *uri, BINDING **bindingsPtr) { + static const XML_Char xmlNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, + ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, + ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, + ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, + ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, + ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, + ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, + ASCII_e, '\0'}; + static const int xmlLen = (int)sizeof(xmlNamespace) / sizeof(XML_Char) - 1; + static const XML_Char xmlnsNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, + ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, + ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, + ASCII_2, ASCII_0, ASCII_0, ASCII_0, ASCII_SLASH, ASCII_x, + ASCII_m, ASCII_l, ASCII_n, ASCII_s, ASCII_SLASH, '\0'}; + static const int xmlnsLen + = (int)sizeof(xmlnsNamespace) / sizeof(XML_Char) - 1; + + XML_Bool mustBeXML = XML_FALSE; + XML_Bool isXML = XML_TRUE; + XML_Bool isXMLNS = XML_TRUE; + + BINDING *b; + int len; + + /* empty URI is only valid for default namespace per XML NS 1.0 (not 1.1) */ + if (*uri == XML_T('\0') && prefix->name) + return XML_ERROR_UNDECLARING_PREFIX; + + if (prefix->name && prefix->name[0] == XML_T(ASCII_x) + && prefix->name[1] == XML_T(ASCII_m) + && prefix->name[2] == XML_T(ASCII_l)) { + /* Not allowed to bind xmlns */ + if (prefix->name[3] == XML_T(ASCII_n) && prefix->name[4] == XML_T(ASCII_s) + && prefix->name[5] == XML_T('\0')) + return XML_ERROR_RESERVED_PREFIX_XMLNS; + + if (prefix->name[3] == XML_T('\0')) + mustBeXML = XML_TRUE; + } + + for (len = 0; uri[len]; len++) { + if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) + isXML = XML_FALSE; + + if (! mustBeXML && isXMLNS + && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) + isXMLNS = XML_FALSE; + + // NOTE: While Expat does not validate namespace URIs against RFC 3986, + // we have to at least make sure that the XML processor on top of + // Expat (that is splitting tag names by namespace separator into + // 2- or 3-tuples (uri-local or uri-local-prefix)) cannot be confused + // by an attacker putting additional namespace separator characters + // into namespace declarations. That would be ambiguous and not to + // be expected. + if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)) { + return XML_ERROR_SYNTAX; + } + } + isXML = isXML && len == xmlLen; + isXMLNS = isXMLNS && len == xmlnsLen; + + if (mustBeXML != isXML) + return mustBeXML ? XML_ERROR_RESERVED_PREFIX_XML + : XML_ERROR_RESERVED_NAMESPACE_URI; + + if (isXMLNS) + return XML_ERROR_RESERVED_NAMESPACE_URI; + + if (parser->m_namespaceSeparator) + len++; + if (parser->m_freeBindingList) { + b = parser->m_freeBindingList; + if (len > b->uriAlloc) { + /* Detect and prevent integer overflow */ + if (len > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + + XML_Char *temp = (XML_Char *)REALLOC( + parser, b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + b->uri = temp; + b->uriAlloc = len + EXPAND_SPARE; + } + parser->m_freeBindingList = b->nextTagBinding; + } else { + b = (BINDING *)MALLOC(parser, sizeof(BINDING)); + if (! b) + return XML_ERROR_NO_MEMORY; + + /* Detect and prevent integer overflow */ + if (len > INT_MAX - EXPAND_SPARE) { + return XML_ERROR_NO_MEMORY; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)(len + EXPAND_SPARE) > (size_t)(-1) / sizeof(XML_Char)) { + return XML_ERROR_NO_MEMORY; + } +#endif + + b->uri + = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (! b->uri) { + FREE(parser, b); + return XML_ERROR_NO_MEMORY; + } + b->uriAlloc = len + EXPAND_SPARE; + } + b->uriLen = len; + memcpy(b->uri, uri, len * sizeof(XML_Char)); + if (parser->m_namespaceSeparator) + b->uri[len - 1] = parser->m_namespaceSeparator; + b->prefix = prefix; + b->attId = attId; + b->prevPrefixBinding = prefix->binding; + /* NULL binding when default namespace undeclared */ + if (*uri == XML_T('\0') && prefix == &parser->m_dtd->defaultPrefix) + prefix->binding = NULL; + else + prefix->binding = b; + b->nextTagBinding = *bindingsPtr; + *bindingsPtr = b; + /* if attId == NULL then we are not starting a namespace scope */ + if (attId && parser->m_startNamespaceDeclHandler) + parser->m_startNamespaceDeclHandler(parser->m_handlerArg, prefix->name, + prefix->binding ? uri : 0); + return XML_ERROR_NONE; +} + +/* The idea here is to avoid using stack for each CDATA section when + the whole file is parsed with one call. +*/ +static enum XML_Error PTRCALL +cdataSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result = doCdataSection( + parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_ACCOUNT_DIRECT); + if (result != XML_ERROR_NONE) + return result; + if (start) { + if (parser->m_parentParser) { /* we are parsing an external entity */ + parser->m_processor = externalEntityContentProcessor; + return externalEntityContentProcessor(parser, start, end, endPtr); + } else { + parser->m_processor = contentProcessor; + return contentProcessor(parser, start, end, endPtr); + } + } + return result; +} + +/* startPtr gets set to non-null if the section is closed, and to null if + the section is not yet closed. +*/ +static enum XML_Error +doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore, + enum XML_Account account) { + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + *eventPP = s; + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + *startPtr = NULL; + + for (;;) { + const char *next = s; /* in case of XML_TOK_NONE or XML_TOK_PARTIAL */ + int tok = XmlCdataSectionTok(enc, s, end, &next); +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#else + UNUSED_P(account); +#endif + *eventEndPP = next; + switch (tok) { + case XML_TOK_CDATA_SECT_CLOSE: + if (parser->m_endCdataSectionHandler) + parser->m_endCdataSectionHandler(parser->m_handlerArg); + /* BEGIN disabled code */ + /* see comment under XML_TOK_CDATA_SECT_OPEN */ + else if (0 && parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + *nextPtr = next; + if (parser->m_parsingStatus.parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + else + return XML_ERROR_NONE; + case XML_TOK_DATA_NEWLINE: + if (parser->m_characterDataHandler) { + XML_Char c = 0xA; + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = next; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; + } + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_CDATA_SECTION; + default: + /* Every token returned by XmlCdataSectionTok() has its own + * explicit case, so this default case will never be executed. + * We retain it as a safety net and exclude it from the coverage + * statistics. + * + * LCOV_EXCL_START + */ + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ + } + + *eventPP = s = next; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default:; + } + } + /* not reached */ +} + +#ifdef XML_DTD + +/* The idea here is to avoid using stack for each IGNORE section when + the whole file is parsed with one call. +*/ +static enum XML_Error PTRCALL +ignoreSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doIgnoreSection(parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); + if (result != XML_ERROR_NONE) + return result; + if (start) { + parser->m_processor = prologProcessor; + return prologProcessor(parser, start, end, endPtr); + } + return result; +} + +/* startPtr gets set to non-null is the section is closed, and to null + if the section is not yet closed. +*/ +static enum XML_Error +doIgnoreSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore) { + const char *next = *startPtr; /* in case of XML_TOK_NONE or XML_TOK_PARTIAL */ + int tok; + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + *eventPP = s; + eventEndPP = &parser->m_eventEndPtr; + } else { + /* It's not entirely clear, but it seems the following two lines + * of code cannot be executed. The only occasions on which 'enc' + * is not 'encoding' are when this function is called + * from the internal entity processing, and IGNORE sections are an + * error in internal entities. + * + * Since it really isn't clear that this is true, we keep the code + * and just remove it from our coverage tests. + * + * LCOV_EXCL_START + */ + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + /* LCOV_EXCL_STOP */ + } + *eventPP = s; + *startPtr = NULL; + tok = XmlIgnoreSectionTok(enc, s, end, &next); +# ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +# endif + *eventEndPP = next; + switch (tok) { + case XML_TOK_IGNORE_SECT: + if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + *nextPtr = next; + if (parser->m_parsingStatus.parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + else + return XML_ERROR_NONE; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */ + default: + /* All of the tokens that XmlIgnoreSectionTok() returns have + * explicit cases to handle them, so this default case is never + * executed. We keep it as a safety net anyway, and remove it + * from our test coverage statistics. + * + * LCOV_EXCL_START + */ + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ + } + /* not reached */ +} + +#endif /* XML_DTD */ + +static enum XML_Error +initializeEncoding(XML_Parser parser) { + const char *s; +#ifdef XML_UNICODE + char encodingBuf[128]; + /* See comments about `protocolEncodingName` in parserInit() */ + if (! parser->m_protocolEncodingName) + s = NULL; + else { + int i; + for (i = 0; parser->m_protocolEncodingName[i]; i++) { + if (i == sizeof(encodingBuf) - 1 + || (parser->m_protocolEncodingName[i] & ~0x7f) != 0) { + encodingBuf[0] = '\0'; + break; + } + encodingBuf[i] = (char)parser->m_protocolEncodingName[i]; + } + encodingBuf[i] = '\0'; + s = encodingBuf; + } +#else + s = parser->m_protocolEncodingName; +#endif + if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)( + &parser->m_initEncoding, &parser->m_encoding, s)) + return XML_ERROR_NONE; + return handleUnknownEncoding(parser, parser->m_protocolEncodingName); +} + +static enum XML_Error +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *s, + const char *next) { + const char *encodingName = NULL; + const XML_Char *storedEncName = NULL; + const ENCODING *newEncoding = NULL; + const char *version = NULL; + const char *versionend; + const XML_Char *storedversion = NULL; + int standalone = -1; + +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, XML_TOK_XML_DECL, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif + + if (! (parser->m_ns ? XmlParseXmlDeclNS : XmlParseXmlDecl)( + isGeneralTextEntity, parser->m_encoding, s, next, &parser->m_eventPtr, + &version, &versionend, &encodingName, &newEncoding, &standalone)) { + if (isGeneralTextEntity) + return XML_ERROR_TEXT_DECL; + else + return XML_ERROR_XML_DECL; + } + if (! isGeneralTextEntity && standalone == 1) { + parser->m_dtd->standalone = XML_TRUE; +#ifdef XML_DTD + if (parser->m_paramEntityParsing + == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) + parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif /* XML_DTD */ + } + if (parser->m_xmlDeclHandler) { + if (encodingName != NULL) { + storedEncName = poolStoreString( + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_temp2Pool); + } + if (version) { + storedversion + = poolStoreString(&parser->m_temp2Pool, parser->m_encoding, version, + versionend - parser->m_encoding->minBytesPerChar); + if (! storedversion) + return XML_ERROR_NO_MEMORY; + } + parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, + standalone); + } else if (parser->m_defaultHandler) + reportDefault(parser, parser->m_encoding, s, next); + if (parser->m_protocolEncodingName == NULL) { + if (newEncoding) { + /* Check that the specified encoding does not conflict with what + * the parser has already deduced. Do we have the same number + * of bytes in the smallest representation of a character? If + * this is UTF-16, is it the same endianness? + */ + if (newEncoding->minBytesPerChar != parser->m_encoding->minBytesPerChar + || (newEncoding->minBytesPerChar == 2 + && newEncoding != parser->m_encoding)) { + parser->m_eventPtr = encodingName; + return XML_ERROR_INCORRECT_ENCODING; + } + parser->m_encoding = newEncoding; + } else if (encodingName) { + enum XML_Error result; + if (! storedEncName) { + storedEncName = poolStoreString( + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; + } + result = handleUnknownEncoding(parser, storedEncName); + poolClear(&parser->m_temp2Pool); + if (result == XML_ERROR_UNKNOWN_ENCODING) + parser->m_eventPtr = encodingName; + return result; + } + } + + if (storedEncName || storedversion) + poolClear(&parser->m_temp2Pool); + + return XML_ERROR_NONE; +} + +static enum XML_Error +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) { + if (parser->m_unknownEncodingHandler) { + XML_Encoding info; + int i; + for (i = 0; i < 256; i++) + info.map[i] = -1; + info.convert = NULL; + info.data = NULL; + info.release = NULL; + if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, + encodingName, &info)) { + ENCODING *enc; + parser->m_unknownEncodingMem = MALLOC(parser, XmlSizeOfUnknownEncoding()); + if (! parser->m_unknownEncodingMem) { + if (info.release) + info.release(info.data); + return XML_ERROR_NO_MEMORY; + } + enc = (parser->m_ns ? XmlInitUnknownEncodingNS : XmlInitUnknownEncoding)( + parser->m_unknownEncodingMem, info.map, info.convert, info.data); + if (enc) { + parser->m_unknownEncodingData = info.data; + parser->m_unknownEncodingRelease = info.release; + parser->m_encoding = enc; + return XML_ERROR_NONE; + } + } + if (info.release != NULL) + info.release(info.data); + } + return XML_ERROR_UNKNOWN_ENCODING; +} + +static enum XML_Error PTRCALL +prologInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + parser->m_processor = prologProcessor; + return prologProcessor(parser, s, end, nextPtr); +} + +#ifdef XML_DTD + +static enum XML_Error PTRCALL +externalParEntInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + + /* we know now that XML_Parse(Buffer) has been called, + so we consider the external parameter entity read */ + parser->m_dtd->paramEntityRead = XML_TRUE; + + if (parser->m_prologState.inEntityValue) { + parser->m_processor = entityValueInitProcessor; + return entityValueInitProcessor(parser, s, end, nextPtr); + } else { + parser->m_processor = externalParEntProcessor; + return externalParEntProcessor(parser, s, end, nextPtr); + } +} + +static enum XML_Error PTRCALL +entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + int tok; + const char *start = s; + const char *next = start; + parser->m_eventPtr = start; + + for (;;) { + tok = XmlPrologTok(parser->m_encoding, start, end, &next); + /* Note: Except for XML_TOK_BOM below, these bytes are accounted later in: + - storeEntityValue + - processXmlDecl + */ + parser->m_eventEndPtr = next; + if (tok <= 0) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + /* found end of entity value - can store it now */ + return storeEntityValue(parser, parser->m_encoding, s, end, + XML_ACCOUNT_DIRECT); + } else if (tok == XML_TOK_XML_DECL) { + enum XML_Error result; + result = processXmlDecl(parser, 0, start, next); + if (result != XML_ERROR_NONE) + return result; + /* At this point, m_parsingStatus.parsing cannot be XML_SUSPENDED. For + * that to happen, a parameter entity parsing handler must have attempted + * to suspend the parser, which fails and raises an error. The parser can + * be aborted, but can't be suspended. + */ + if (parser->m_parsingStatus.parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + *nextPtr = next; + /* stop scanning for text declaration - we found one */ + parser->m_processor = entityValueProcessor; + return entityValueProcessor(parser, next, end, nextPtr); + } + /* If we are at the end of the buffer, this would cause XmlPrologTok to + return XML_TOK_NONE on the next call, which would then cause the + function to exit with *nextPtr set to s - that is what we want for other + tokens, but not for the BOM - we would rather like to skip it; + then, when this routine is entered the next time, XmlPrologTok will + return XML_TOK_INVALID, since the BOM is still in the buffer + */ + else if (tok == XML_TOK_BOM && next == end + && ! parser->m_parsingStatus.finalBuffer) { +# ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +# endif + + *nextPtr = next; + return XML_ERROR_NONE; + } + /* If we get this token, we have the start of what might be a + normal tag, but not a declaration (i.e. it doesn't begin with + "<!"). In a DTD context, that isn't legal. + */ + else if (tok == XML_TOK_INSTANCE_START) { + *nextPtr = next; + return XML_ERROR_SYNTAX; + } + start = next; + parser->m_eventPtr = start; + } +} + +static enum XML_Error PTRCALL +externalParEntProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + const char *next = s; + int tok; + + tok = XmlPrologTok(parser->m_encoding, s, end, &next); + if (tok <= 0) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + } + /* This would cause the next stage, i.e. doProlog to be passed XML_TOK_BOM. + However, when parsing an external subset, doProlog will not accept a BOM + as valid, and report a syntax error, so we have to skip the BOM, and + account for the BOM bytes. + */ + else if (tok == XML_TOK_BOM) { + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } + + s = next; + tok = XmlPrologTok(parser->m_encoding, s, end, &next); + } + + parser->m_processor = prologProcessor; + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE, + XML_ACCOUNT_DIRECT); +} + +static enum XML_Error PTRCALL +entityValueProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + const char *start = s; + const char *next = s; + const ENCODING *enc = parser->m_encoding; + int tok; + + for (;;) { + tok = XmlPrologTok(enc, start, end, &next); + /* Note: These bytes are accounted later in: + - storeEntityValue + */ + if (tok <= 0) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + /* found end of entity value - can store it now */ + return storeEntityValue(parser, enc, s, end, XML_ACCOUNT_DIRECT); + } + start = next; + } +} + +#endif /* XML_DTD */ + +static enum XML_Error PTRCALL +prologProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + const char *next = s; + int tok = XmlPrologTok(parser->m_encoding, s, end, &next); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE, + XML_ACCOUNT_DIRECT); +} + +static enum XML_Error +doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, + int tok, const char *next, const char **nextPtr, XML_Bool haveMore, + XML_Bool allowClosingDoctype, enum XML_Account account) { +#ifdef XML_DTD + static const XML_Char externalSubsetName[] = {ASCII_HASH, '\0'}; +#endif /* XML_DTD */ + static const XML_Char atypeCDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; + static const XML_Char atypeID[] = {ASCII_I, ASCII_D, '\0'}; + static const XML_Char atypeIDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; + static const XML_Char atypeIDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; + static const XML_Char atypeENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; + static const XML_Char atypeENTITIES[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; + static const XML_Char atypeNMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; + static const XML_Char atypeNMTOKENS[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; + static const XML_Char notationPrefix[] + = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0'}; + static const XML_Char enumValueSep[] = {ASCII_PIPE, '\0'}; + static const XML_Char enumValueStart[] = {ASCII_LPAREN, '\0'}; + +#ifndef XML_DTD + UNUSED_P(account); +#endif + + /* save one level of indirection */ + DTD *const dtd = parser->m_dtd; + + const char **eventPP; + const char **eventEndPP; + enum XML_Content_Quant quant; + + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + } + + for (;;) { + int role; + XML_Bool handleDefault = XML_TRUE; + *eventPP = s; + *eventEndPP = next; + if (tok <= 0) { + if (haveMore && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case -XML_TOK_PROLOG_S: + tok = -tok; + break; + case XML_TOK_NONE: +#ifdef XML_DTD + /* for internal PE NOT referenced between declarations */ + if (enc != parser->m_encoding + && ! parser->m_openInternalEntities->betweenDecl) { + *nextPtr = s; + return XML_ERROR_NONE; + } + /* WFC: PE Between Declarations - must check that PE contains + complete markup, not only for external PEs, but also for + internal PEs if the reference occurs between declarations. + */ + if (parser->m_isParamEntity || enc != parser->m_encoding) { + if (XmlTokenRole(&parser->m_prologState, XML_TOK_NONE, end, end, enc) + == XML_ROLE_ERROR) + return XML_ERROR_INCOMPLETE_PE; + *nextPtr = s; + return XML_ERROR_NONE; + } +#endif /* XML_DTD */ + return XML_ERROR_NO_ELEMENTS; + default: + tok = -tok; + next = end; + break; + } + } + role = XmlTokenRole(&parser->m_prologState, tok, s, next, enc); +#ifdef XML_DTD + switch (role) { + case XML_ROLE_INSTANCE_START: // bytes accounted in contentProcessor + case XML_ROLE_XML_DECL: // bytes accounted in processXmlDecl + case XML_ROLE_TEXT_DECL: // bytes accounted in processXmlDecl + break; + default: + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } + } +#endif + switch (role) { + case XML_ROLE_XML_DECL: { + enum XML_Error result = processXmlDecl(parser, 0, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; + case XML_ROLE_DOCTYPE_NAME: + if (parser->m_startDoctypeDeclHandler) { + parser->m_doctypeName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_doctypeName) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + parser->m_doctypePubid = NULL; + handleDefault = XML_FALSE; + } + parser->m_doctypeSysid = NULL; /* always initialize to NULL */ + break; + case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: + if (parser->m_startDoctypeDeclHandler) { + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 1); + parser->m_doctypeName = NULL; + poolClear(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + break; +#ifdef XML_DTD + case XML_ROLE_TEXT_DECL: { + enum XML_Error result = processXmlDecl(parser, 1, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; +#endif /* XML_DTD */ + case XML_ROLE_DOCTYPE_PUBLIC_ID: +#ifdef XML_DTD + parser->m_useForeignDTD = XML_FALSE; + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; +#endif /* XML_DTD */ + dtd->hasParamEntityRefs = XML_TRUE; + if (parser->m_startDoctypeDeclHandler) { + XML_Char *pubId; + if (! XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + pubId = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! pubId) + return XML_ERROR_NO_MEMORY; + normalizePublicId(pubId); + poolFinish(&parser->m_tempPool); + parser->m_doctypePubid = pubId; + handleDefault = XML_FALSE; + goto alreadyChecked; + } + /* fall through */ + case XML_ROLE_ENTITY_PUBLIC_ID: + if (! XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + alreadyChecked: + if (dtd->keepProcessing && parser->m_declEntity) { + XML_Char *tem + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + parser->m_declEntity->publicId = tem; + poolFinish(&dtd->pool); + /* Don't suppress the default handler if we fell through from + * the XML_ROLE_DOCTYPE_PUBLIC_ID case. + */ + if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_PUBLIC_ID) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_DOCTYPE_CLOSE: + if (allowClosingDoctype != XML_TRUE) { + /* Must not close doctype from within expanded parameter entities */ + return XML_ERROR_INVALID_TOKEN; + } + + if (parser->m_doctypeName) { + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 0); + poolClear(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + /* parser->m_doctypeSysid will be non-NULL in the case of a previous + XML_ROLE_DOCTYPE_SYSTEM_ID, even if parser->m_startDoctypeDeclHandler + was not set, indicating an external subset + */ +#ifdef XML_DTD + if (parser->m_doctypeSysid || parser->m_useForeignDTD) { + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; + dtd->hasParamEntityRefs = XML_TRUE; + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, + externalSubsetName, sizeof(ENTITY)); + if (! entity) { + /* The external subset name "#" will have already been + * inserted into the hash table at the start of the + * external entity parsing, so no allocation will happen + * and lookup() cannot fail. + */ + return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */ + } + if (parser->m_useForeignDTD) + entity->base = parser->m_curBase; + dtd->paramEntityRead = XML_FALSE; + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + if (dtd->paramEntityRead) { + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else if (! parser->m_doctypeSysid) + dtd->hasParamEntityRefs = hadParamEntityRefs; + /* end of DTD - no need to update dtd->keepProcessing */ + } + parser->m_useForeignDTD = XML_FALSE; + } +#endif /* XML_DTD */ + if (parser->m_endDoctypeDeclHandler) { + parser->m_endDoctypeDeclHandler(parser->m_handlerArg); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_INSTANCE_START: +#ifdef XML_DTD + /* if there is no DOCTYPE declaration then now is the + last chance to read the foreign DTD + */ + if (parser->m_useForeignDTD) { + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; + dtd->hasParamEntityRefs = XML_TRUE; + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, + externalSubsetName, sizeof(ENTITY)); + if (! entity) + return XML_ERROR_NO_MEMORY; + entity->base = parser->m_curBase; + dtd->paramEntityRead = XML_FALSE; + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + if (dtd->paramEntityRead) { + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else + dtd->hasParamEntityRefs = hadParamEntityRefs; + /* end of DTD - no need to update dtd->keepProcessing */ + } + } +#endif /* XML_DTD */ + parser->m_processor = contentProcessor; + return contentProcessor(parser, s, end, nextPtr); + case XML_ROLE_ATTLIST_ELEMENT_NAME: + parser->m_declElementType = getElementType(parser, enc, s, next); + if (! parser->m_declElementType) + return XML_ERROR_NO_MEMORY; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_NAME: + parser->m_declAttributeId = getAttributeId(parser, enc, s, next); + if (! parser->m_declAttributeId) + return XML_ERROR_NO_MEMORY; + parser->m_declAttributeIsCdata = XML_FALSE; + parser->m_declAttributeType = NULL; + parser->m_declAttributeIsId = XML_FALSE; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_CDATA: + parser->m_declAttributeIsCdata = XML_TRUE; + parser->m_declAttributeType = atypeCDATA; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ID: + parser->m_declAttributeIsId = XML_TRUE; + parser->m_declAttributeType = atypeID; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_IDREF: + parser->m_declAttributeType = atypeIDREF; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_IDREFS: + parser->m_declAttributeType = atypeIDREFS; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITY: + parser->m_declAttributeType = atypeENTITY; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES: + parser->m_declAttributeType = atypeENTITIES; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN: + parser->m_declAttributeType = atypeNMTOKEN; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS: + parser->m_declAttributeType = atypeNMTOKENS; + checkAttListDeclHandler: + if (dtd->keepProcessing && parser->m_attlistDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ATTRIBUTE_ENUM_VALUE: + case XML_ROLE_ATTRIBUTE_NOTATION_VALUE: + if (dtd->keepProcessing && parser->m_attlistDeclHandler) { + const XML_Char *prefix; + if (parser->m_declAttributeType) { + prefix = enumValueSep; + } else { + prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE ? notationPrefix + : enumValueStart); + } + if (! poolAppendString(&parser->m_tempPool, prefix)) + return XML_ERROR_NO_MEMORY; + if (! poolAppend(&parser->m_tempPool, enc, s, next)) + return XML_ERROR_NO_MEMORY; + parser->m_declAttributeType = parser->m_tempPool.start; + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: + case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: + if (dtd->keepProcessing) { + if (! defineAttribute(parser->m_declElementType, + parser->m_declAttributeId, + parser->m_declAttributeIsCdata, + parser->m_declAttributeIsId, 0, parser)) + return XML_ERROR_NO_MEMORY; + if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { + if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) + || (*parser->m_declAttributeType == XML_T(ASCII_N) + && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { + /* Enumerated or Notation type */ + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + parser->m_declAttributeType = parser->m_tempPool.start; + poolFinish(&parser->m_tempPool); + } + *eventEndPP = s; + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, 0, + role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); + poolClear(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: + case XML_ROLE_FIXED_ATTRIBUTE_VALUE: + if (dtd->keepProcessing) { + const XML_Char *attVal; + enum XML_Error result = storeAttributeValue( + parser, enc, parser->m_declAttributeIsCdata, + s + enc->minBytesPerChar, next - enc->minBytesPerChar, &dtd->pool, + XML_ACCOUNT_NONE); + if (result) + return result; + attVal = poolStart(&dtd->pool); + poolFinish(&dtd->pool); + /* ID attributes aren't allowed to have a default */ + if (! defineAttribute( + parser->m_declElementType, parser->m_declAttributeId, + parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser)) + return XML_ERROR_NO_MEMORY; + if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { + if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) + || (*parser->m_declAttributeType == XML_T(ASCII_N) + && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { + /* Enumerated or Notation type */ + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + parser->m_declAttributeType = parser->m_tempPool.start; + poolFinish(&parser->m_tempPool); + } + *eventEndPP = s; + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, + attVal, role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); + poolClear(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_ENTITY_VALUE: + if (dtd->keepProcessing) { + enum XML_Error result + = storeEntityValue(parser, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar, XML_ACCOUNT_NONE); + if (parser->m_declEntity) { + parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool); + parser->m_declEntity->textLen + = (int)(poolLength(&dtd->entityValuePool)); + poolFinish(&dtd->entityValuePool); + if (parser->m_entityDeclHandler) { + *eventEndPP = s; + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, parser->m_declEntity->textPtr, + parser->m_declEntity->textLen, parser->m_curBase, 0, 0, 0); + handleDefault = XML_FALSE; + } + } else + poolDiscard(&dtd->entityValuePool); + if (result != XML_ERROR_NONE) + return result; + } + break; + case XML_ROLE_DOCTYPE_SYSTEM_ID: +#ifdef XML_DTD + parser->m_useForeignDTD = XML_FALSE; +#endif /* XML_DTD */ + dtd->hasParamEntityRefs = XML_TRUE; + if (parser->m_startDoctypeDeclHandler) { + parser->m_doctypeSysid = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (parser->m_doctypeSysid == NULL) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + handleDefault = XML_FALSE; + } +#ifdef XML_DTD + else + /* use externalSubsetName to make parser->m_doctypeSysid non-NULL + for the case where no parser->m_startDoctypeDeclHandler is set */ + parser->m_doctypeSysid = externalSubsetName; +#endif /* XML_DTD */ + if (! dtd->standalone +#ifdef XML_DTD + && ! parser->m_paramEntityParsing +#endif /* XML_DTD */ + && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) + return XML_ERROR_NOT_STANDALONE; +#ifndef XML_DTD + break; +#else /* XML_DTD */ + if (! parser->m_declEntity) { + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity->publicId = NULL; + } +#endif /* XML_DTD */ + /* fall through */ + case XML_ROLE_ENTITY_SYSTEM_ID: + if (dtd->keepProcessing && parser->m_declEntity) { + parser->m_declEntity->systemId + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! parser->m_declEntity->systemId) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity->base = parser->m_curBase; + poolFinish(&dtd->pool); + /* Don't suppress the default handler if we fell through from + * the XML_ROLE_DOCTYPE_SYSTEM_ID case. + */ + if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_SYSTEM_ID) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_ENTITY_COMPLETE: + if (dtd->keepProcessing && parser->m_declEntity + && parser->m_entityDeclHandler) { + *eventEndPP = s; + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, 0, 0, parser->m_declEntity->base, + parser->m_declEntity->systemId, parser->m_declEntity->publicId, 0); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_ENTITY_NOTATION_NAME: + if (dtd->keepProcessing && parser->m_declEntity) { + parser->m_declEntity->notation + = poolStoreString(&dtd->pool, enc, s, next); + if (! parser->m_declEntity->notation) + return XML_ERROR_NO_MEMORY; + poolFinish(&dtd->pool); + if (parser->m_unparsedEntityDeclHandler) { + *eventEndPP = s; + parser->m_unparsedEntityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); + handleDefault = XML_FALSE; + } else if (parser->m_entityDeclHandler) { + *eventEndPP = s; + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, 0, 0, 0, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_GENERAL_ENTITY_NAME: { + if (XmlPredefinedEntityName(enc, s, next)) { + parser->m_declEntity = NULL; + break; + } + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (! name) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, + name, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; + if (parser->m_declEntity->name != name) { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; + } else { + poolFinish(&dtd->pool); + parser->m_declEntity->publicId = NULL; + parser->m_declEntity->is_param = XML_FALSE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); + if (parser->m_entityDeclHandler) + handleDefault = XML_FALSE; + } + } else { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; + } + } break; + case XML_ROLE_PARAM_ENTITY_NAME: +#ifdef XML_DTD + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (! name) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, + name, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; + if (parser->m_declEntity->name != name) { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; + } else { + poolFinish(&dtd->pool); + parser->m_declEntity->publicId = NULL; + parser->m_declEntity->is_param = XML_TRUE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); + if (parser->m_entityDeclHandler) + handleDefault = XML_FALSE; + } + } else { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; + } +#else /* not XML_DTD */ + parser->m_declEntity = NULL; +#endif /* XML_DTD */ + break; + case XML_ROLE_NOTATION_NAME: + parser->m_declNotationPublicId = NULL; + parser->m_declNotationName = NULL; + if (parser->m_notationDeclHandler) { + parser->m_declNotationName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_declNotationName) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_NOTATION_PUBLIC_ID: + if (! XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + if (parser + ->m_declNotationName) { /* means m_notationDeclHandler != NULL */ + XML_Char *tem = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + parser->m_declNotationPublicId = tem; + poolFinish(&parser->m_tempPool); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_NOTATION_SYSTEM_ID: + if (parser->m_declNotationName && parser->m_notationDeclHandler) { + const XML_Char *systemId = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! systemId) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + systemId, parser->m_declNotationPublicId); + handleDefault = XML_FALSE; + } + poolClear(&parser->m_tempPool); + break; + case XML_ROLE_NOTATION_NO_SYSTEM_ID: + if (parser->m_declNotationPublicId && parser->m_notationDeclHandler) { + *eventEndPP = s; + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + 0, parser->m_declNotationPublicId); + handleDefault = XML_FALSE; + } + poolClear(&parser->m_tempPool); + break; + case XML_ROLE_ERROR: + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: + /* PE references in internal subset are + not allowed within declarations. */ + return XML_ERROR_PARAM_ENTITY_REF; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + default: + return XML_ERROR_SYNTAX; + } +#ifdef XML_DTD + case XML_ROLE_IGNORE_SECT: { + enum XML_Error result; + if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + handleDefault = XML_FALSE; + result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = ignoreSectionProcessor; + return result; + } + } break; +#endif /* XML_DTD */ + case XML_ROLE_GROUP_OPEN: + if (parser->m_prologState.level >= parser->m_groupSize) { + if (parser->m_groupSize) { + { + /* Detect and prevent integer overflow */ + if (parser->m_groupSize > (unsigned int)(-1) / 2u) { + return XML_ERROR_NO_MEMORY; + } + + char *const new_connector = (char *)REALLOC( + parser, parser->m_groupConnector, parser->m_groupSize *= 2); + if (new_connector == NULL) { + parser->m_groupSize /= 2; + return XML_ERROR_NO_MEMORY; + } + parser->m_groupConnector = new_connector; + } + + if (dtd->scaffIndex) { + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (parser->m_groupSize > (size_t)(-1) / sizeof(int)) { + return XML_ERROR_NO_MEMORY; + } +#endif + + int *const new_scaff_index = (int *)REALLOC( + parser, dtd->scaffIndex, parser->m_groupSize * sizeof(int)); + if (new_scaff_index == NULL) + return XML_ERROR_NO_MEMORY; + dtd->scaffIndex = new_scaff_index; + } + } else { + parser->m_groupConnector + = (char *)MALLOC(parser, parser->m_groupSize = 32); + if (! parser->m_groupConnector) { + parser->m_groupSize = 0; + return XML_ERROR_NO_MEMORY; + } + } + } + parser->m_groupConnector[parser->m_prologState.level] = 0; + if (dtd->in_eldecl) { + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + assert(dtd->scaffIndex != NULL); + dtd->scaffIndex[dtd->scaffLevel] = myindex; + dtd->scaffLevel++; + dtd->scaffold[myindex].type = XML_CTYPE_SEQ; + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_GROUP_SEQUENCE: + if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_PIPE) + return XML_ERROR_SYNTAX; + parser->m_groupConnector[parser->m_prologState.level] = ASCII_COMMA; + if (dtd->in_eldecl && parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_GROUP_CHOICE: + if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_COMMA) + return XML_ERROR_SYNTAX; + if (dtd->in_eldecl + && ! parser->m_groupConnector[parser->m_prologState.level] + && (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + != XML_CTYPE_MIXED)) { + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + = XML_CTYPE_CHOICE; + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + } + parser->m_groupConnector[parser->m_prologState.level] = ASCII_PIPE; + break; + case XML_ROLE_PARAM_ENTITY_REF: +#ifdef XML_DTD + case XML_ROLE_INNER_PARAM_ENTITY_REF: + dtd->hasParamEntityRefs = XML_TRUE; + if (! parser->m_paramEntityParsing) + dtd->keepProcessing = dtd->standalone; + else { + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); + poolDiscard(&dtd->pool); + /* first, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity handler + */ + if (parser->m_prologState.documentEntity + && (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs)) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) { + /* It's hard to exhaustively search the code to be sure, + * but there doesn't seem to be a way of executing the + * following line. There are two cases: + * + * If 'standalone' is false, the DTD must have no + * parameter entities or we wouldn't have passed the outer + * 'if' statement. That measn the only entity in the hash + * table is the external subset name "#" which cannot be + * given as a parameter entity name in XML syntax, so the + * lookup must have returned NULL and we don't even reach + * the test for an internal entity. + * + * If 'standalone' is true, it does not seem to be + * possible to create entities taking this code path that + * are not internal entities, so fail the test above. + * + * Because this analysis is very uncertain, the code is + * being left in place and merely removed from the + * coverage test statistics. + */ + return XML_ERROR_ENTITY_DECLARED_IN_PE; /* LCOV_EXCL_LINE */ + } + } else if (! entity) { + dtd->keepProcessing = dtd->standalone; + /* cannot report skipped entities in declarations */ + if ((role == XML_ROLE_PARAM_ENTITY_REF) + && parser->m_skippedEntityHandler) { + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 1); + handleDefault = XML_FALSE; + } + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + XML_Bool betweenDecl + = (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); + result = processInternalEntity(parser, entity, betweenDecl); + if (result != XML_ERROR_NONE) + return result; + handleDefault = XML_FALSE; + break; + } + if (parser->m_externalEntityRefHandler) { + dtd->paramEntityRead = XML_FALSE; + entity->open = XML_TRUE; + entityTrackingOnOpen(parser, entity, __LINE__); + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { + entityTrackingOnClose(parser, entity, __LINE__); + entity->open = XML_FALSE; + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + } + entityTrackingOnClose(parser, entity, __LINE__); + entity->open = XML_FALSE; + handleDefault = XML_FALSE; + if (! dtd->paramEntityRead) { + dtd->keepProcessing = dtd->standalone; + break; + } + } else { + dtd->keepProcessing = dtd->standalone; + break; + } + } +#endif /* XML_DTD */ + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) + return XML_ERROR_NOT_STANDALONE; + break; + + /* Element declaration stuff */ + + case XML_ROLE_ELEMENT_NAME: + if (parser->m_elementDeclHandler) { + parser->m_declElementType = getElementType(parser, enc, s, next); + if (! parser->m_declElementType) + return XML_ERROR_NO_MEMORY; + dtd->scaffLevel = 0; + dtd->scaffCount = 0; + dtd->in_eldecl = XML_TRUE; + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_ANY: + case XML_ROLE_CONTENT_EMPTY: + if (dtd->in_eldecl) { + if (parser->m_elementDeclHandler) { + XML_Content *content + = (XML_Content *)MALLOC(parser, sizeof(XML_Content)); + if (! content) + return XML_ERROR_NO_MEMORY; + content->quant = XML_CQUANT_NONE; + content->name = NULL; + content->numchildren = 0; + content->children = NULL; + content->type = ((role == XML_ROLE_CONTENT_ANY) ? XML_CTYPE_ANY + : XML_CTYPE_EMPTY); + *eventEndPP = s; + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, content); + handleDefault = XML_FALSE; + } + dtd->in_eldecl = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_PCDATA: + if (dtd->in_eldecl) { + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + = XML_CTYPE_MIXED; + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_ELEMENT: + quant = XML_CQUANT_NONE; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_OPT: + quant = XML_CQUANT_OPT; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_REP: + quant = XML_CQUANT_REP; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_PLUS: + quant = XML_CQUANT_PLUS; + elementContent: + if (dtd->in_eldecl) { + ELEMENT_TYPE *el; + const XML_Char *name; + size_t nameLen; + const char *nxt + = (quant == XML_CQUANT_NONE ? next : next - enc->minBytesPerChar); + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + dtd->scaffold[myindex].type = XML_CTYPE_NAME; + dtd->scaffold[myindex].quant = quant; + el = getElementType(parser, enc, s, nxt); + if (! el) + return XML_ERROR_NO_MEMORY; + name = el->name; + dtd->scaffold[myindex].name = name; + nameLen = 0; + for (; name[nameLen++];) + ; + + /* Detect and prevent integer overflow */ + if (nameLen > UINT_MAX - dtd->contentStringLen) { + return XML_ERROR_NO_MEMORY; + } + + dtd->contentStringLen += (unsigned)nameLen; + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_GROUP_CLOSE: + quant = XML_CQUANT_NONE; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_OPT: + quant = XML_CQUANT_OPT; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_REP: + quant = XML_CQUANT_REP; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_PLUS: + quant = XML_CQUANT_PLUS; + closeGroup: + if (dtd->in_eldecl) { + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + dtd->scaffLevel--; + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant; + if (dtd->scaffLevel == 0) { + if (! handleDefault) { + XML_Content *model = build_model(parser); + if (! model) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, model); + } + dtd->in_eldecl = XML_FALSE; + dtd->contentStringLen = 0; + } + } + break; + /* End element declaration stuff */ + + case XML_ROLE_PI: + if (! reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + handleDefault = XML_FALSE; + break; + case XML_ROLE_COMMENT: + if (! reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + handleDefault = XML_FALSE; + break; + case XML_ROLE_NONE: + switch (tok) { + case XML_TOK_BOM: + handleDefault = XML_FALSE; + break; + } + break; + case XML_ROLE_DOCTYPE_NONE: + if (parser->m_startDoctypeDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ENTITY_NONE: + if (dtd->keepProcessing && parser->m_entityDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_NOTATION_NONE: + if (parser->m_notationDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ATTLIST_NONE: + if (dtd->keepProcessing && parser->m_attlistDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ELEMENT_NONE: + if (parser->m_elementDeclHandler) + handleDefault = XML_FALSE; + break; + } /* end of big switch */ + + if (handleDefault && parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + s = next; + tok = XmlPrologTok(enc, s, end, &next); + } + } + /* not reached */ +} + +static enum XML_Error PTRCALL +epilogProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + parser->m_processor = epilogProcessor; + parser->m_eventPtr = s; + for (;;) { + const char *next = NULL; + int tok = XmlPrologTok(parser->m_encoding, s, end, &next); +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, s, next, __LINE__, + XML_ACCOUNT_DIRECT)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif + parser->m_eventEndPtr = next; + switch (tok) { + /* report partial linebreak - it might be the last token */ + case -XML_TOK_PROLOG_S: + if (parser->m_defaultHandler) { + reportDefault(parser, parser->m_encoding, s, next); + if (parser->m_parsingStatus.parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + } + *nextPtr = next; + return XML_ERROR_NONE; + case XML_TOK_NONE: + *nextPtr = s; + return XML_ERROR_NONE; + case XML_TOK_PROLOG_S: + if (parser->m_defaultHandler) + reportDefault(parser, parser->m_encoding, s, next); + break; + case XML_TOK_PI: + if (! reportProcessingInstruction(parser, parser->m_encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (! reportComment(parser, parser->m_encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_INVALID: + parser->m_eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (! parser->m_parsingStatus.finalBuffer) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (! parser->m_parsingStatus.finalBuffer) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + default: + return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; + } + parser->m_eventPtr = s = next; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default:; + } + } +} + +static enum XML_Error +processInternalEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl) { + const char *textStart, *textEnd; + const char *next; + enum XML_Error result; + OPEN_INTERNAL_ENTITY *openEntity; + + if (parser->m_freeInternalEntities) { + openEntity = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity->next; + } else { + openEntity + = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY)); + if (! openEntity) + return XML_ERROR_NO_MEMORY; + } + entity->open = XML_TRUE; +#ifdef XML_DTD + entityTrackingOnOpen(parser, entity, __LINE__); +#endif + entity->processed = 0; + openEntity->next = parser->m_openInternalEntities; + parser->m_openInternalEntities = openEntity; + openEntity->entity = entity; + openEntity->startTagLevel = parser->m_tagLevel; + openEntity->betweenDecl = betweenDecl; + openEntity->internalEventPtr = NULL; + openEntity->internalEventEndPtr = NULL; + textStart = (const char *)entity->textPtr; + textEnd = (const char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + next = textStart; + +#ifdef XML_DTD + if (entity->is_param) { + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_FALSE, + XML_ACCOUNT_ENTITY_EXPANSION); + } else +#endif /* XML_DTD */ + result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, + textStart, textEnd, &next, XML_FALSE, + XML_ACCOUNT_ENTITY_EXPANSION); + + if (result == XML_ERROR_NONE) { + if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) { + entity->processed = (int)(next - textStart); + parser->m_processor = internalEntityProcessor; + } else { +#ifdef XML_DTD + entityTrackingOnClose(parser, entity, __LINE__); +#endif /* XML_DTD */ + entity->open = XML_FALSE; + parser->m_openInternalEntities = openEntity->next; + /* put openEntity back in list of free instances */ + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; + } + } + return result; +} + +static enum XML_Error PTRCALL +internalEntityProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + ENTITY *entity; + const char *textStart, *textEnd; + const char *next; + enum XML_Error result; + OPEN_INTERNAL_ENTITY *openEntity = parser->m_openInternalEntities; + if (! openEntity) + return XML_ERROR_UNEXPECTED_STATE; + + entity = openEntity->entity; + textStart = ((const char *)entity->textPtr) + entity->processed; + textEnd = (const char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + next = textStart; + +#ifdef XML_DTD + if (entity->is_param) { + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_TRUE, + XML_ACCOUNT_ENTITY_EXPANSION); + } else +#endif /* XML_DTD */ + result = doContent(parser, openEntity->startTagLevel, + parser->m_internalEncoding, textStart, textEnd, &next, + XML_FALSE, XML_ACCOUNT_ENTITY_EXPANSION); + + if (result != XML_ERROR_NONE) + return result; + else if (textEnd != next + && parser->m_parsingStatus.parsing == XML_SUSPENDED) { + entity->processed = (int)(next - (const char *)entity->textPtr); + return result; + } else { +#ifdef XML_DTD + entityTrackingOnClose(parser, entity, __LINE__); +#endif + entity->open = XML_FALSE; + parser->m_openInternalEntities = openEntity->next; + /* put openEntity back in list of free instances */ + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; + } + +#ifdef XML_DTD + if (entity->is_param) { + int tok; + parser->m_processor = prologProcessor; + tok = XmlPrologTok(parser->m_encoding, s, end, &next); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE, + XML_ACCOUNT_DIRECT); + } else +#endif /* XML_DTD */ + { + parser->m_processor = contentProcessor; + /* see externalEntityContentProcessor vs contentProcessor */ + return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, + s, end, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, + XML_ACCOUNT_DIRECT); + } +} + +static enum XML_Error PTRCALL +errorProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + UNUSED_P(s); + UNUSED_P(end); + UNUSED_P(nextPtr); + return parser->m_errorCode; +} + +static enum XML_Error +storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, STRING_POOL *pool, + enum XML_Account account) { + enum XML_Error result + = appendAttributeValue(parser, enc, isCdata, ptr, end, pool, account); + if (result) + return result; + if (! isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) + poolChop(pool); + if (! poolAppendChar(pool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + return XML_ERROR_NONE; +} + +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, STRING_POOL *pool, + enum XML_Account account) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ +#ifndef XML_DTD + UNUSED_P(account); +#endif + + for (;;) { + const char *next + = ptr; /* XmlAttributeValueTok doesn't always set the last arg */ + int tok = XmlAttributeValueTok(enc, ptr, end, &next); +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, ptr, next, __LINE__, account)) { + accountingOnAbort(parser); + return XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + } +#endif + switch (tok) { + case XML_TOK_NONE: + return XML_ERROR_NONE; + case XML_TOK_INVALID: + if (enc == parser->m_encoding) + parser->m_eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, ptr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; + } + if (! isCdata && n == 0x20 /* space */ + && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (! poolAppendChar(pool, buf[i])) + return XML_ERROR_NO_MEMORY; + } + } break; + case XML_TOK_DATA_CHARS: + if (! poolAppend(pool, enc, ptr, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_TRAILING_CR: + next = ptr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_ATTRIBUTE_VALUE_S: + case XML_TOK_DATA_NEWLINE: + if (! isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + if (! poolAppendChar(pool, 0x20)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + char checkEntityDecl; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, ptr + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { +#ifdef XML_DTD + /* NOTE: We are replacing 4-6 characters original input for 1 character + * so there is no amplification and hence recording without + * protection. */ + accountingDiffTolerated(parser, tok, (char *)&ch, + ((char *)&ch) + sizeof(XML_Char), __LINE__, + XML_ACCOUNT_ENTITY_EXPANSION); +#endif /* XML_DTD */ + if (! poolAppendChar(pool, ch)) + return XML_ERROR_NO_MEMORY; + break; + } + name = poolStoreString(&parser->m_temp2Pool, enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&parser->m_temp2Pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal. + */ + if (pool == &dtd->pool) /* are we called from prolog? */ + checkEntityDecl = +#ifdef XML_DTD + parser->m_prologState.documentEntity && +#endif /* XML_DTD */ + (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs); + else /* if (pool == &parser->m_tempPool): we are called from content */ + checkEntityDecl = ! dtd->hasParamEntityRefs || dtd->standalone; + if (checkEntityDecl) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + /* Cannot report skipped entity here - see comments on + parser->m_skippedEntityHandler. + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + */ + /* Cannot call the default handler because this would be + out of sync with the call to the startElementHandler. + if ((pool == &parser->m_tempPool) && parser->m_defaultHandler) + reportDefault(parser, enc, ptr, next); + */ + break; + } + if (entity->open) { + if (enc == parser->m_encoding) { + /* It does not appear that this line can be executed. + * + * The "if (entity->open)" check catches recursive entity + * definitions. In order to be called with an open + * entity, it must have gone through this code before and + * been through the recursive call to + * appendAttributeValue() some lines below. That call + * sets the local encoding ("enc") to the parser's + * internal encoding (internal_utf8 or internal_utf16), + * which can never be the same as the principle encoding. + * It doesn't appear there is another code path that gets + * here with entity->open being TRUE. + * + * Since it is not certain that this logic is watertight, + * we keep the line and merely exclude it from coverage + * tests. + */ + parser->m_eventPtr = ptr; /* LCOV_EXCL_LINE */ + } + return XML_ERROR_RECURSIVE_ENTITY_REF; + } + if (entity->notation) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BINARY_ENTITY_REF; + } + if (! entity->textPtr) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; + } else { + enum XML_Error result; + const XML_Char *textEnd = entity->textPtr + entity->textLen; + entity->open = XML_TRUE; +#ifdef XML_DTD + entityTrackingOnOpen(parser, entity, __LINE__); +#endif + result = appendAttributeValue(parser, parser->m_internalEncoding, + isCdata, (const char *)entity->textPtr, + (const char *)textEnd, pool, + XML_ACCOUNT_ENTITY_EXPANSION); +#ifdef XML_DTD + entityTrackingOnClose(parser, entity, __LINE__); +#endif + entity->open = XML_FALSE; + if (result) + return result; + } + } break; + default: + /* The only token returned by XmlAttributeValueTok() that does + * not have an explicit case here is XML_TOK_PARTIAL_CHAR. + * Getting that would require an entity name to contain an + * incomplete XML character (e.g. \xE2\x82); however previous + * tokenisers will have already recognised and rejected such + * names before XmlAttributeValueTok() gets a look-in. This + * default case should be retained as a safety net, but the code + * excluded from coverage tests. + * + * LCOV_EXCL_START + */ + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ + } + ptr = next; + } + /* not reached */ +} + +static enum XML_Error +storeEntityValue(XML_Parser parser, const ENCODING *enc, + const char *entityTextPtr, const char *entityTextEnd, + enum XML_Account account) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + STRING_POOL *pool = &(dtd->entityValuePool); + enum XML_Error result = XML_ERROR_NONE; +#ifdef XML_DTD + int oldInEntityValue = parser->m_prologState.inEntityValue; + parser->m_prologState.inEntityValue = 1; +#else + UNUSED_P(account); +#endif /* XML_DTD */ + /* never return Null for the value argument in EntityDeclHandler, + since this would indicate an external entity; therefore we + have to make sure that entityValuePool.start is not null */ + if (! pool->blocks) { + if (! poolGrow(pool)) + return XML_ERROR_NO_MEMORY; + } + + for (;;) { + const char *next + = entityTextPtr; /* XmlEntityValueTok doesn't always set the last arg */ + int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next); + +#ifdef XML_DTD + if (! accountingDiffTolerated(parser, tok, entityTextPtr, next, __LINE__, + account)) { + accountingOnAbort(parser); + result = XML_ERROR_AMPLIFICATION_LIMIT_BREACH; + goto endEntityValue; + } +#endif + + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: +#ifdef XML_DTD + if (parser->m_isParamEntity || enc != parser->m_encoding) { + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&parser->m_tempPool, enc, + entityTextPtr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); + poolDiscard(&parser->m_tempPool); + if (! entity) { + /* not a well-formedness error - see XML 1.0: WFC Entity Declared */ + /* cannot report skipped entity here - see comments on + parser->m_skippedEntityHandler + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + */ + dtd->keepProcessing = dtd->standalone; + goto endEntityValue; + } + if (entity->open) { + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_RECURSIVE_ENTITY_REF; + goto endEntityValue; + } + if (entity->systemId) { + if (parser->m_externalEntityRefHandler) { + dtd->paramEntityRead = XML_FALSE; + entity->open = XML_TRUE; + entityTrackingOnOpen(parser, entity, __LINE__); + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { + entityTrackingOnClose(parser, entity, __LINE__); + entity->open = XML_FALSE; + result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; + goto endEntityValue; + } + entityTrackingOnClose(parser, entity, __LINE__); + entity->open = XML_FALSE; + if (! dtd->paramEntityRead) + dtd->keepProcessing = dtd->standalone; + } else + dtd->keepProcessing = dtd->standalone; + } else { + entity->open = XML_TRUE; + entityTrackingOnOpen(parser, entity, __LINE__); + result = storeEntityValue( + parser, parser->m_internalEncoding, (const char *)entity->textPtr, + (const char *)(entity->textPtr + entity->textLen), + XML_ACCOUNT_ENTITY_EXPANSION); + entityTrackingOnClose(parser, entity, __LINE__); + entity->open = XML_FALSE; + if (result) + goto endEntityValue; + } + break; + } +#endif /* XML_DTD */ + /* In the internal subset, PE references are not legal + within markup declarations, e.g entity values in this case. */ + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_PARAM_ENTITY_REF; + goto endEntityValue; + case XML_TOK_NONE: + result = XML_ERROR_NONE; + goto endEntityValue; + case XML_TOK_ENTITY_REF: + case XML_TOK_DATA_CHARS: + if (! poolAppend(pool, enc, entityTextPtr, next)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + break; + case XML_TOK_TRAILING_CR: + next = entityTextPtr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_DATA_NEWLINE: + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + *(pool->ptr)++ = 0xA; + break; + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, entityTextPtr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_BAD_CHAR_REF; + goto endEntityValue; + } + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + *(pool->ptr)++ = buf[i]; + } + } break; + case XML_TOK_PARTIAL: + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_INVALID_TOKEN; + goto endEntityValue; + case XML_TOK_INVALID: + if (enc == parser->m_encoding) + parser->m_eventPtr = next; + result = XML_ERROR_INVALID_TOKEN; + goto endEntityValue; + default: + /* This default case should be unnecessary -- all the tokens + * that XmlEntityValueTok() can return have their own explicit + * cases -- but should be retained for safety. We do however + * exclude it from the coverage statistics. + * + * LCOV_EXCL_START + */ + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_UNEXPECTED_STATE; + goto endEntityValue; + /* LCOV_EXCL_STOP */ + } + entityTextPtr = next; + } +endEntityValue: +#ifdef XML_DTD + parser->m_prologState.inEntityValue = oldInEntityValue; +#endif /* XML_DTD */ + return result; +} + +static void FASTCALL +normalizeLines(XML_Char *s) { + XML_Char *p; + for (;; s++) { + if (*s == XML_T('\0')) + return; + if (*s == 0xD) + break; + } + p = s; + do { + if (*s == 0xD) { + *p++ = 0xA; + if (*++s == 0xA) + s++; + } else + *p++ = *s++; + } while (*s); + *p = XML_T('\0'); +} + +static int +reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end) { + const XML_Char *target; + XML_Char *data; + const char *tem; + if (! parser->m_processingInstructionHandler) { + if (parser->m_defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + start += enc->minBytesPerChar * 2; + tem = start + XmlNameLength(enc, start); + target = poolStoreString(&parser->m_tempPool, enc, start, tem); + if (! target) + return 0; + poolFinish(&parser->m_tempPool); + data = poolStoreString(&parser->m_tempPool, enc, XmlSkipS(enc, tem), + end - enc->minBytesPerChar * 2); + if (! data) + return 0; + normalizeLines(data); + parser->m_processingInstructionHandler(parser->m_handlerArg, target, data); + poolClear(&parser->m_tempPool); + return 1; +} + +static int +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { + XML_Char *data; + if (! parser->m_commentHandler) { + if (parser->m_defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + data = poolStoreString(&parser->m_tempPool, enc, + start + enc->minBytesPerChar * 4, + end - enc->minBytesPerChar * 3); + if (! data) + return 0; + normalizeLines(data); + parser->m_commentHandler(parser->m_handlerArg, data); + poolClear(&parser->m_tempPool); + return 1; +} + +static void +reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, + const char *end) { + if (MUST_CONVERT(enc, s)) { + enum XML_Convert_Result convert_res; + const char **eventPP; + const char **eventEndPP; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + /* To get here, two things must be true; the parser must be + * using a character encoding that is not the same as the + * encoding passed in, and the encoding passed in must need + * conversion to the internal format (UTF-8 unless XML_UNICODE + * is defined). The only occasions on which the encoding passed + * in is not the same as the parser's encoding are when it is + * the internal encoding (e.g. a previously defined parameter + * entity, already converted to internal format). This by + * definition doesn't need conversion, so the whole branch never + * gets executed. + * + * For safety's sake we don't delete these lines and merely + * exclude them from coverage statistics. + * + * LCOV_EXCL_START + */ + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + /* LCOV_EXCL_STOP */ + } + do { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + convert_res + = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = s; + parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + *eventPP = s; + } while ((convert_res != XML_CONVERT_COMPLETED) + && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); + } else + parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); +} + +static int +defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, + XML_Bool isId, const XML_Char *value, XML_Parser parser) { + DEFAULT_ATTRIBUTE *att; + if (value || isId) { + /* The handling of default attributes gets messed up if we have + a default which duplicates a non-default. */ + int i; + for (i = 0; i < type->nDefaultAtts; i++) + if (attId == type->defaultAtts[i].id) + return 1; + if (isId && ! type->idAtt && ! attId->xmlns) + type->idAtt = attId; + } + if (type->nDefaultAtts == type->allocDefaultAtts) { + if (type->allocDefaultAtts == 0) { + type->allocDefaultAtts = 8; + type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC( + parser, type->allocDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! type->defaultAtts) { + type->allocDefaultAtts = 0; + return 0; + } + } else { + DEFAULT_ATTRIBUTE *temp; + + /* Detect and prevent integer overflow */ + if (type->allocDefaultAtts > INT_MAX / 2) { + return 0; + } + + int count = type->allocDefaultAtts * 2; + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if ((unsigned)count > (size_t)(-1) / sizeof(DEFAULT_ATTRIBUTE)) { + return 0; + } +#endif + + temp = (DEFAULT_ATTRIBUTE *)REALLOC(parser, type->defaultAtts, + (count * sizeof(DEFAULT_ATTRIBUTE))); + if (temp == NULL) + return 0; + type->allocDefaultAtts = count; + type->defaultAtts = temp; + } + } + att = type->defaultAtts + type->nDefaultAtts; + att->id = attId; + att->value = value; + att->isCdata = isCdata; + if (! isCdata) + attId->maybeTokenized = XML_TRUE; + type->nDefaultAtts += 1; + return 1; +} + +static int +setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + const XML_Char *name; + for (name = elementType->name; *name; name++) { + if (*name == XML_T(ASCII_COLON)) { + PREFIX *prefix; + const XML_Char *s; + for (s = elementType->name; s != name; s++) { + if (! poolAppendChar(&dtd->pool, *s)) + return 0; + } + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) + return 0; + prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), + sizeof(PREFIX)); + if (! prefix) + return 0; + if (prefix->name == poolStart(&dtd->pool)) + poolFinish(&dtd->pool); + else + poolDiscard(&dtd->pool); + elementType->prefix = prefix; + break; + } + } + return 1; +} + +static ATTRIBUTE_ID * +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + ATTRIBUTE_ID *id; + const XML_Char *name; + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) + return NULL; + name = poolStoreString(&dtd->pool, enc, start, end); + if (! name) + return NULL; + /* skip quotation mark - its storage will be re-used (like in name[-1]) */ + ++name; + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, + sizeof(ATTRIBUTE_ID)); + if (! id) + return NULL; + if (id->name != name) + poolDiscard(&dtd->pool); + else { + poolFinish(&dtd->pool); + if (! parser->m_ns) + ; + else if (name[0] == XML_T(ASCII_x) && name[1] == XML_T(ASCII_m) + && name[2] == XML_T(ASCII_l) && name[3] == XML_T(ASCII_n) + && name[4] == XML_T(ASCII_s) + && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { + if (name[5] == XML_T('\0')) + id->prefix = &dtd->defaultPrefix; + else + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, + sizeof(PREFIX)); + id->xmlns = XML_TRUE; + } else { + int i; + for (i = 0; name[i]; i++) { + /* attributes without prefix are *not* in the default namespace */ + if (name[i] == XML_T(ASCII_COLON)) { + int j; + for (j = 0; j < i; j++) { + if (! poolAppendChar(&dtd->pool, name[j])) + return NULL; + } + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) + return NULL; + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&dtd->pool), sizeof(PREFIX)); + if (! id->prefix) + return NULL; + if (id->prefix->name == poolStart(&dtd->pool)) + poolFinish(&dtd->pool); + else + poolDiscard(&dtd->pool); + break; + } + } + } + } + return id; +} + +#define CONTEXT_SEP XML_T(ASCII_FF) + +static const XML_Char * +getContext(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + HASH_TABLE_ITER iter; + XML_Bool needSep = XML_FALSE; + + if (dtd->defaultPrefix.binding) { + int i; + int len; + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) + return NULL; + len = dtd->defaultPrefix.binding->uriLen; + if (parser->m_namespaceSeparator) + len--; + for (i = 0; i < len; i++) { + if (! poolAppendChar(&parser->m_tempPool, + dtd->defaultPrefix.binding->uri[i])) { + /* Because of memory caching, I don't believe this line can be + * executed. + * + * This is part of a loop copying the default prefix binding + * URI into the parser's temporary string pool. Previously, + * that URI was copied into the same string pool, with a + * terminating NUL character, as part of setContext(). When + * the pool was cleared, that leaves a block definitely big + * enough to hold the URI on the free block list of the pool. + * The URI copy in getContext() therefore cannot run out of + * memory. + * + * If the pool is used between the setContext() and + * getContext() calls, the worst it can do is leave a bigger + * block on the front of the free list. Given that this is + * all somewhat inobvious and program logic can be changed, we + * don't delete the line but we do exclude it from the test + * coverage statistics. + */ + return NULL; /* LCOV_EXCL_LINE */ + } + } + needSep = XML_TRUE; + } + + hashTableIterInit(&iter, &(dtd->prefixes)); + for (;;) { + int i; + int len; + const XML_Char *s; + PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); + if (! prefix) + break; + if (! prefix->binding) { + /* This test appears to be (justifiable) paranoia. There does + * not seem to be a way of injecting a prefix without a binding + * that doesn't get errored long before this function is called. + * The test should remain for safety's sake, so we instead + * exclude the following line from the coverage statistics. + */ + continue; /* LCOV_EXCL_LINE */ + } + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) + return NULL; + for (s = prefix->name; *s; s++) + if (! poolAppendChar(&parser->m_tempPool, *s)) + return NULL; + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) + return NULL; + len = prefix->binding->uriLen; + if (parser->m_namespaceSeparator) + len--; + for (i = 0; i < len; i++) + if (! poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i])) + return NULL; + needSep = XML_TRUE; + } + + hashTableIterInit(&iter, &(dtd->generalEntities)); + for (;;) { + const XML_Char *s; + ENTITY *e = (ENTITY *)hashTableIterNext(&iter); + if (! e) + break; + if (! e->open) + continue; + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) + return NULL; + for (s = e->name; *s; s++) + if (! poolAppendChar(&parser->m_tempPool, *s)) + return 0; + needSep = XML_TRUE; + } + + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return NULL; + return parser->m_tempPool.start; +} + +static XML_Bool +setContext(XML_Parser parser, const XML_Char *context) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + const XML_Char *s = context; + + while (*context != XML_T('\0')) { + if (*s == CONTEXT_SEP || *s == XML_T('\0')) { + ENTITY *e; + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return XML_FALSE; + e = (ENTITY *)lookup(parser, &dtd->generalEntities, + poolStart(&parser->m_tempPool), 0); + if (e) + e->open = XML_TRUE; + if (*s != XML_T('\0')) + s++; + context = s; + poolDiscard(&parser->m_tempPool); + } else if (*s == XML_T(ASCII_EQUALS)) { + PREFIX *prefix; + if (poolLength(&parser->m_tempPool) == 0) + prefix = &dtd->defaultPrefix; + else { + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return XML_FALSE; + prefix + = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&parser->m_tempPool), sizeof(PREFIX)); + if (! prefix) + return XML_FALSE; + if (prefix->name == poolStart(&parser->m_tempPool)) { + prefix->name = poolCopyString(&dtd->pool, prefix->name); + if (! prefix->name) + return XML_FALSE; + } + poolDiscard(&parser->m_tempPool); + } + for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); + context++) + if (! poolAppendChar(&parser->m_tempPool, *context)) + return XML_FALSE; + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + return XML_FALSE; + if (addBinding(parser, prefix, NULL, poolStart(&parser->m_tempPool), + &parser->m_inheritedBindings) + != XML_ERROR_NONE) + return XML_FALSE; + poolDiscard(&parser->m_tempPool); + if (*context != XML_T('\0')) + ++context; + s = context; + } else { + if (! poolAppendChar(&parser->m_tempPool, *s)) + return XML_FALSE; + s++; + } + } + return XML_TRUE; +} + +static void FASTCALL +normalizePublicId(XML_Char *publicId) { + XML_Char *p = publicId; + XML_Char *s; + for (s = publicId; *s; s++) { + switch (*s) { + case 0x20: + case 0xD: + case 0xA: + if (p != publicId && p[-1] != 0x20) + *p++ = 0x20; + break; + default: + *p++ = *s; + } + } + if (p != publicId && p[-1] == 0x20) + --p; + *p = XML_T('\0'); +} + +static DTD * +dtdCreate(const XML_Memory_Handling_Suite *ms) { + DTD *p = ms->malloc_fcn(sizeof(DTD)); + if (p == NULL) + return p; + poolInit(&(p->pool), ms); + poolInit(&(p->entityValuePool), ms); + hashTableInit(&(p->generalEntities), ms); + hashTableInit(&(p->elementTypes), ms); + hashTableInit(&(p->attributeIds), ms); + hashTableInit(&(p->prefixes), ms); +#ifdef XML_DTD + p->paramEntityRead = XML_FALSE; + hashTableInit(&(p->paramEntities), ms); +#endif /* XML_DTD */ + p->defaultPrefix.name = NULL; + p->defaultPrefix.binding = NULL; + + p->in_eldecl = XML_FALSE; + p->scaffIndex = NULL; + p->scaffold = NULL; + p->scaffLevel = 0; + p->scaffSize = 0; + p->scaffCount = 0; + p->contentStringLen = 0; + + p->keepProcessing = XML_TRUE; + p->hasParamEntityRefs = XML_FALSE; + p->standalone = XML_FALSE; + return p; +} + +static void +dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) { + HASH_TABLE_ITER iter; + hashTableIterInit(&iter, &(p->elementTypes)); + for (;;) { + ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (! e) + break; + if (e->allocDefaultAtts != 0) + ms->free_fcn(e->defaultAtts); + } + hashTableClear(&(p->generalEntities)); +#ifdef XML_DTD + p->paramEntityRead = XML_FALSE; + hashTableClear(&(p->paramEntities)); +#endif /* XML_DTD */ + hashTableClear(&(p->elementTypes)); + hashTableClear(&(p->attributeIds)); + hashTableClear(&(p->prefixes)); + poolClear(&(p->pool)); + poolClear(&(p->entityValuePool)); + p->defaultPrefix.name = NULL; + p->defaultPrefix.binding = NULL; + + p->in_eldecl = XML_FALSE; + + ms->free_fcn(p->scaffIndex); + p->scaffIndex = NULL; + ms->free_fcn(p->scaffold); + p->scaffold = NULL; + + p->scaffLevel = 0; + p->scaffSize = 0; + p->scaffCount = 0; + p->contentStringLen = 0; + + p->keepProcessing = XML_TRUE; + p->hasParamEntityRefs = XML_FALSE; + p->standalone = XML_FALSE; +} + +static void +dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) { + HASH_TABLE_ITER iter; + hashTableIterInit(&iter, &(p->elementTypes)); + for (;;) { + ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (! e) + break; + if (e->allocDefaultAtts != 0) + ms->free_fcn(e->defaultAtts); + } + hashTableDestroy(&(p->generalEntities)); +#ifdef XML_DTD + hashTableDestroy(&(p->paramEntities)); +#endif /* XML_DTD */ + hashTableDestroy(&(p->elementTypes)); + hashTableDestroy(&(p->attributeIds)); + hashTableDestroy(&(p->prefixes)); + poolDestroy(&(p->pool)); + poolDestroy(&(p->entityValuePool)); + if (isDocEntity) { + ms->free_fcn(p->scaffIndex); + ms->free_fcn(p->scaffold); + } + ms->free_fcn(p); +} + +/* Do a deep copy of the DTD. Return 0 for out of memory, non-zero otherwise. + The new DTD has already been initialized. +*/ +static int +dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, + const XML_Memory_Handling_Suite *ms) { + HASH_TABLE_ITER iter; + + /* Copy the prefix table. */ + + hashTableIterInit(&iter, &(oldDtd->prefixes)); + for (;;) { + const XML_Char *name; + const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); + if (! oldP) + break; + name = poolCopyString(&(newDtd->pool), oldP->name); + if (! name) + return 0; + if (! lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) + return 0; + } + + hashTableIterInit(&iter, &(oldDtd->attributeIds)); + + /* Copy the attribute id table. */ + + for (;;) { + ATTRIBUTE_ID *newA; + const XML_Char *name; + const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); + + if (! oldA) + break; + /* Remember to allocate the scratch byte before the name. */ + if (! poolAppendChar(&(newDtd->pool), XML_T('\0'))) + return 0; + name = poolCopyString(&(newDtd->pool), oldA->name); + if (! name) + return 0; + ++name; + newA = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), name, + sizeof(ATTRIBUTE_ID)); + if (! newA) + return 0; + newA->maybeTokenized = oldA->maybeTokenized; + if (oldA->prefix) { + newA->xmlns = oldA->xmlns; + if (oldA->prefix == &oldDtd->defaultPrefix) + newA->prefix = &newDtd->defaultPrefix; + else + newA->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), + oldA->prefix->name, 0); + } + } + + /* Copy the element type table. */ + + hashTableIterInit(&iter, &(oldDtd->elementTypes)); + + for (;;) { + int i; + ELEMENT_TYPE *newE; + const XML_Char *name; + const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (! oldE) + break; + name = poolCopyString(&(newDtd->pool), oldE->name); + if (! name) + return 0; + newE = (ELEMENT_TYPE *)lookup(oldParser, &(newDtd->elementTypes), name, + sizeof(ELEMENT_TYPE)); + if (! newE) + return 0; + if (oldE->nDefaultAtts) { + newE->defaultAtts + = ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! newE->defaultAtts) { + return 0; + } + } + if (oldE->idAtt) + newE->idAtt = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), + oldE->idAtt->name, 0); + newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; + if (oldE->prefix) + newE->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), + oldE->prefix->name, 0); + for (i = 0; i < newE->nDefaultAtts; i++) { + newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup( + oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); + newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; + if (oldE->defaultAtts[i].value) { + newE->defaultAtts[i].value + = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); + if (! newE->defaultAtts[i].value) + return 0; + } else + newE->defaultAtts[i].value = NULL; + } + } + + /* Copy the entity tables. */ + if (! copyEntityTable(oldParser, &(newDtd->generalEntities), &(newDtd->pool), + &(oldDtd->generalEntities))) + return 0; + +#ifdef XML_DTD + if (! copyEntityTable(oldParser, &(newDtd->paramEntities), &(newDtd->pool), + &(oldDtd->paramEntities))) + return 0; + newDtd->paramEntityRead = oldDtd->paramEntityRead; +#endif /* XML_DTD */ + + newDtd->keepProcessing = oldDtd->keepProcessing; + newDtd->hasParamEntityRefs = oldDtd->hasParamEntityRefs; + newDtd->standalone = oldDtd->standalone; + + /* Don't want deep copying for scaffolding */ + newDtd->in_eldecl = oldDtd->in_eldecl; + newDtd->scaffold = oldDtd->scaffold; + newDtd->contentStringLen = oldDtd->contentStringLen; + newDtd->scaffSize = oldDtd->scaffSize; + newDtd->scaffLevel = oldDtd->scaffLevel; + newDtd->scaffIndex = oldDtd->scaffIndex; + + return 1; +} /* End dtdCopy */ + +static int +copyEntityTable(XML_Parser oldParser, HASH_TABLE *newTable, + STRING_POOL *newPool, const HASH_TABLE *oldTable) { + HASH_TABLE_ITER iter; + const XML_Char *cachedOldBase = NULL; + const XML_Char *cachedNewBase = NULL; + + hashTableIterInit(&iter, oldTable); + + for (;;) { + ENTITY *newE; + const XML_Char *name; + const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); + if (! oldE) + break; + name = poolCopyString(newPool, oldE->name); + if (! name) + return 0; + newE = (ENTITY *)lookup(oldParser, newTable, name, sizeof(ENTITY)); + if (! newE) + return 0; + if (oldE->systemId) { + const XML_Char *tem = poolCopyString(newPool, oldE->systemId); + if (! tem) + return 0; + newE->systemId = tem; + if (oldE->base) { + if (oldE->base == cachedOldBase) + newE->base = cachedNewBase; + else { + cachedOldBase = oldE->base; + tem = poolCopyString(newPool, cachedOldBase); + if (! tem) + return 0; + cachedNewBase = newE->base = tem; + } + } + if (oldE->publicId) { + tem = poolCopyString(newPool, oldE->publicId); + if (! tem) + return 0; + newE->publicId = tem; + } + } else { + const XML_Char *tem + = poolCopyStringN(newPool, oldE->textPtr, oldE->textLen); + if (! tem) + return 0; + newE->textPtr = tem; + newE->textLen = oldE->textLen; + } + if (oldE->notation) { + const XML_Char *tem = poolCopyString(newPool, oldE->notation); + if (! tem) + return 0; + newE->notation = tem; + } + newE->is_param = oldE->is_param; + newE->is_internal = oldE->is_internal; + } + return 1; +} + +#define INIT_POWER 6 + +static XML_Bool FASTCALL +keyeq(KEY s1, KEY s2) { + for (; *s1 == *s2; s1++, s2++) + if (*s1 == 0) + return XML_TRUE; + return XML_FALSE; +} + +static size_t +keylen(KEY s) { + size_t len = 0; + for (; *s; s++, len++) + ; + return len; +} + +static void +copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key) { + key->k[0] = 0; + key->k[1] = get_hash_secret_salt(parser); +} + +static unsigned long FASTCALL +hash(XML_Parser parser, KEY s) { + struct siphash state; + struct sipkey key; + (void)sip24_valid; + copy_salt_to_sipkey(parser, &key); + sip24_init(&state, &key); + sip24_update(&state, s, keylen(s) * sizeof(XML_Char)); + return (unsigned long)sip24_final(&state); +} + +static NAMED * +lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { + size_t i; + if (table->size == 0) { + size_t tsize; + if (! createSize) + return NULL; + table->power = INIT_POWER; + /* table->size is a power of 2 */ + table->size = (size_t)1 << INIT_POWER; + tsize = table->size * sizeof(NAMED *); + table->v = table->mem->malloc_fcn(tsize); + if (! table->v) { + table->size = 0; + return NULL; + } + memset(table->v, 0, tsize); + i = hash(parser, name) & ((unsigned long)table->size - 1); + } else { + unsigned long h = hash(parser, name); + unsigned long mask = (unsigned long)table->size - 1; + unsigned char step = 0; + i = h & mask; + while (table->v[i]) { + if (keyeq(name, table->v[i]->name)) + return table->v[i]; + if (! step) + step = PROBE_STEP(h, mask, table->power); + i < step ? (i += table->size - step) : (i -= step); + } + if (! createSize) + return NULL; + + /* check for overflow (table is half full) */ + if (table->used >> (table->power - 1)) { + unsigned char newPower = table->power + 1; + + /* Detect and prevent invalid shift */ + if (newPower >= sizeof(unsigned long) * 8 /* bits per byte */) { + return NULL; + } + + size_t newSize = (size_t)1 << newPower; + unsigned long newMask = (unsigned long)newSize - 1; + + /* Detect and prevent integer overflow */ + if (newSize > (size_t)(-1) / sizeof(NAMED *)) { + return NULL; + } + + size_t tsize = newSize * sizeof(NAMED *); + NAMED **newV = table->mem->malloc_fcn(tsize); + if (! newV) + return NULL; + memset(newV, 0, tsize); + for (i = 0; i < table->size; i++) + if (table->v[i]) { + unsigned long newHash = hash(parser, table->v[i]->name); + size_t j = newHash & newMask; + step = 0; + while (newV[j]) { + if (! step) + step = PROBE_STEP(newHash, newMask, newPower); + j < step ? (j += newSize - step) : (j -= step); + } + newV[j] = table->v[i]; + } + table->mem->free_fcn(table->v); + table->v = newV; + table->power = newPower; + table->size = newSize; + i = h & newMask; + step = 0; + while (table->v[i]) { + if (! step) + step = PROBE_STEP(h, newMask, newPower); + i < step ? (i += newSize - step) : (i -= step); + } + } + } + table->v[i] = table->mem->malloc_fcn(createSize); + if (! table->v[i]) + return NULL; + memset(table->v[i], 0, createSize); + table->v[i]->name = name; + (table->used)++; + return table->v[i]; +} + +static void FASTCALL +hashTableClear(HASH_TABLE *table) { + size_t i; + for (i = 0; i < table->size; i++) { + table->mem->free_fcn(table->v[i]); + table->v[i] = NULL; + } + table->used = 0; +} + +static void FASTCALL +hashTableDestroy(HASH_TABLE *table) { + size_t i; + for (i = 0; i < table->size; i++) + table->mem->free_fcn(table->v[i]); + table->mem->free_fcn(table->v); +} + +static void FASTCALL +hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) { + p->power = 0; + p->size = 0; + p->used = 0; + p->v = NULL; + p->mem = ms; +} + +static void FASTCALL +hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) { + iter->p = table->v; + iter->end = iter->p ? iter->p + table->size : NULL; +} + +static NAMED *FASTCALL +hashTableIterNext(HASH_TABLE_ITER *iter) { + while (iter->p != iter->end) { + NAMED *tem = *(iter->p)++; + if (tem) + return tem; + } + return NULL; +} + +static void FASTCALL +poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) { + pool->blocks = NULL; + pool->freeBlocks = NULL; + pool->start = NULL; + pool->ptr = NULL; + pool->end = NULL; + pool->mem = ms; +} + +static void FASTCALL +poolClear(STRING_POOL *pool) { + if (! pool->freeBlocks) + pool->freeBlocks = pool->blocks; + else { + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + p->next = pool->freeBlocks; + pool->freeBlocks = p; + p = tem; + } + } + pool->blocks = NULL; + pool->start = NULL; + pool->ptr = NULL; + pool->end = NULL; +} + +static void FASTCALL +poolDestroy(STRING_POOL *pool) { + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } + p = pool->freeBlocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } +} + +static XML_Char * +poolAppend(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! pool->ptr && ! poolGrow(pool)) + return NULL; + for (;;) { + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + if (! poolGrow(pool)) + return NULL; + } + return pool->start; +} + +static const XML_Char *FASTCALL +poolCopyString(STRING_POOL *pool, const XML_Char *s) { + do { + if (! poolAppendChar(pool, *s)) + return NULL; + } while (*s++); + s = pool->start; + poolFinish(pool); + return s; +} + +static const XML_Char * +poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) { + if (! pool->ptr && ! poolGrow(pool)) { + /* The following line is unreachable given the current usage of + * poolCopyStringN(). Currently it is called from exactly one + * place to copy the text of a simple general entity. By that + * point, the name of the entity is already stored in the pool, so + * pool->ptr cannot be NULL. + * + * If poolCopyStringN() is used elsewhere as it well might be, + * this line may well become executable again. Regardless, this + * sort of check shouldn't be removed lightly, so we just exclude + * it from the coverage statistics. + */ + return NULL; /* LCOV_EXCL_LINE */ + } + for (; n > 0; --n, s++) { + if (! poolAppendChar(pool, *s)) + return NULL; + } + s = pool->start; + poolFinish(pool); + return s; +} + +static const XML_Char *FASTCALL +poolAppendString(STRING_POOL *pool, const XML_Char *s) { + while (*s) { + if (! poolAppendChar(pool, *s)) + return NULL; + s++; + } + return pool->start; +} + +static XML_Char * +poolStoreString(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! poolAppend(pool, enc, ptr, end)) + return NULL; + if (pool->ptr == pool->end && ! poolGrow(pool)) + return NULL; + *(pool->ptr)++ = 0; + return pool->start; +} + +static size_t +poolBytesToAllocateFor(int blockSize) { + /* Unprotected math would be: + ** return offsetof(BLOCK, s) + blockSize * sizeof(XML_Char); + ** + ** Detect overflow, avoiding _signed_ overflow undefined behavior + ** For a + b * c we check b * c in isolation first, so that addition of a + ** on top has no chance of making us accept a small non-negative number + */ + const size_t stretch = sizeof(XML_Char); /* can be 4 bytes */ + + if (blockSize <= 0) + return 0; + + if (blockSize > (int)(INT_MAX / stretch)) + return 0; + + { + const int stretchedBlockSize = blockSize * (int)stretch; + const int bytesToAllocate + = (int)(offsetof(BLOCK, s) + (unsigned)stretchedBlockSize); + if (bytesToAllocate < 0) + return 0; + + return (size_t)bytesToAllocate; + } +} + +static XML_Bool FASTCALL +poolGrow(STRING_POOL *pool) { + if (pool->freeBlocks) { + if (pool->start == 0) { + pool->blocks = pool->freeBlocks; + pool->freeBlocks = pool->freeBlocks->next; + pool->blocks->next = NULL; + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + pool->ptr = pool->start; + return XML_TRUE; + } + if (pool->end - pool->start < pool->freeBlocks->size) { + BLOCK *tem = pool->freeBlocks->next; + pool->freeBlocks->next = pool->blocks; + pool->blocks = pool->freeBlocks; + pool->freeBlocks = tem; + memcpy(pool->blocks->s, pool->start, + (pool->end - pool->start) * sizeof(XML_Char)); + pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + return XML_TRUE; + } + } + if (pool->blocks && pool->start == pool->blocks->s) { + BLOCK *temp; + int blockSize = (int)((unsigned)(pool->end - pool->start) * 2U); + size_t bytesToAllocate; + + /* NOTE: Needs to be calculated prior to calling `realloc` + to avoid dangling pointers: */ + const ptrdiff_t offsetInsideBlock = pool->ptr - pool->start; + + if (blockSize < 0) { + /* This condition traps a situation where either more than + * INT_MAX/2 bytes have already been allocated. This isn't + * readily testable, since it is unlikely that an average + * machine will have that much memory, so we exclude it from the + * coverage statistics. + */ + return XML_FALSE; /* LCOV_EXCL_LINE */ + } + + bytesToAllocate = poolBytesToAllocateFor(blockSize); + if (bytesToAllocate == 0) + return XML_FALSE; + + temp = (BLOCK *)pool->mem->realloc_fcn(pool->blocks, + (unsigned)bytesToAllocate); + if (temp == NULL) + return XML_FALSE; + pool->blocks = temp; + pool->blocks->size = blockSize; + pool->ptr = pool->blocks->s + offsetInsideBlock; + pool->start = pool->blocks->s; + pool->end = pool->start + blockSize; + } else { + BLOCK *tem; + int blockSize = (int)(pool->end - pool->start); + size_t bytesToAllocate; + + if (blockSize < 0) { + /* This condition traps a situation where either more than + * INT_MAX bytes have already been allocated (which is prevented + * by various pieces of program logic, not least this one, never + * mind the unlikelihood of actually having that much memory) or + * the pool control fields have been corrupted (which could + * conceivably happen in an extremely buggy user handler + * function). Either way it isn't readily testable, so we + * exclude it from the coverage statistics. + */ + return XML_FALSE; /* LCOV_EXCL_LINE */ + } + + if (blockSize < INIT_BLOCK_SIZE) + blockSize = INIT_BLOCK_SIZE; + else { + /* Detect overflow, avoiding _signed_ overflow undefined behavior */ + if ((int)((unsigned)blockSize * 2U) < 0) { + return XML_FALSE; + } + blockSize *= 2; + } + + bytesToAllocate = poolBytesToAllocateFor(blockSize); + if (bytesToAllocate == 0) + return XML_FALSE; + + tem = pool->mem->malloc_fcn(bytesToAllocate); + if (! tem) + return XML_FALSE; + tem->size = blockSize; + tem->next = pool->blocks; + pool->blocks = tem; + if (pool->ptr != pool->start) + memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char)); + pool->ptr = tem->s + (pool->ptr - pool->start); + pool->start = tem->s; + pool->end = tem->s + blockSize; + } + return XML_TRUE; +} + +static int FASTCALL +nextScaffoldPart(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + CONTENT_SCAFFOLD *me; + int next; + + if (! dtd->scaffIndex) { + dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int)); + if (! dtd->scaffIndex) + return -1; + dtd->scaffIndex[0] = 0; + } + + if (dtd->scaffCount >= dtd->scaffSize) { + CONTENT_SCAFFOLD *temp; + if (dtd->scaffold) { + /* Detect and prevent integer overflow */ + if (dtd->scaffSize > UINT_MAX / 2u) { + return -1; + } + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (dtd->scaffSize > (size_t)(-1) / 2u / sizeof(CONTENT_SCAFFOLD)) { + return -1; + } +#endif + + temp = (CONTENT_SCAFFOLD *)REALLOC( + parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); + if (temp == NULL) + return -1; + dtd->scaffSize *= 2; + } else { + temp = (CONTENT_SCAFFOLD *)MALLOC(parser, INIT_SCAFFOLD_ELEMENTS + * sizeof(CONTENT_SCAFFOLD)); + if (temp == NULL) + return -1; + dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS; + } + dtd->scaffold = temp; + } + next = dtd->scaffCount++; + me = &dtd->scaffold[next]; + if (dtd->scaffLevel) { + CONTENT_SCAFFOLD *parent + = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]]; + if (parent->lastchild) { + dtd->scaffold[parent->lastchild].nextsib = next; + } + if (! parent->childcnt) + parent->firstchild = next; + parent->lastchild = next; + parent->childcnt++; + } + me->firstchild = me->lastchild = me->childcnt = me->nextsib = 0; + return next; +} + +static XML_Content * +build_model(XML_Parser parser) { + /* Function build_model transforms the existing parser->m_dtd->scaffold + * array of CONTENT_SCAFFOLD tree nodes into a new array of + * XML_Content tree nodes followed by a gapless list of zero-terminated + * strings. */ + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + XML_Content *ret; + XML_Char *str; /* the current string writing location */ + + /* Detect and prevent integer overflow. + * The preprocessor guard addresses the "always false" warning + * from -Wtype-limits on platforms where + * sizeof(unsigned int) < sizeof(size_t), e.g. on x86_64. */ +#if UINT_MAX >= SIZE_MAX + if (dtd->scaffCount > (size_t)(-1) / sizeof(XML_Content)) { + return NULL; + } + if (dtd->contentStringLen > (size_t)(-1) / sizeof(XML_Char)) { + return NULL; + } +#endif + if (dtd->scaffCount * sizeof(XML_Content) + > (size_t)(-1) - dtd->contentStringLen * sizeof(XML_Char)) { + return NULL; + } + + const size_t allocsize = (dtd->scaffCount * sizeof(XML_Content) + + (dtd->contentStringLen * sizeof(XML_Char))); + + ret = (XML_Content *)MALLOC(parser, allocsize); + if (! ret) + return NULL; + + /* What follows is an iterative implementation (of what was previously done + * recursively in a dedicated function called "build_node". The old recursive + * build_node could be forced into stack exhaustion from input as small as a + * few megabyte, and so that was a security issue. Hence, a function call + * stack is avoided now by resolving recursion.) + * + * The iterative approach works as follows: + * + * - We have two writing pointers, both walking up the result array; one does + * the work, the other creates "jobs" for its colleague to do, and leads + * the way: + * + * - The faster one, pointer jobDest, always leads and writes "what job + * to do" by the other, once they reach that place in the + * array: leader "jobDest" stores the source node array index (relative + * to array dtd->scaffold) in field "numchildren". + * + * - The slower one, pointer dest, looks at the value stored in the + * "numchildren" field (which actually holds a source node array index + * at that time) and puts the real data from dtd->scaffold in. + * + * - Before the loop starts, jobDest writes source array index 0 + * (where the root node is located) so that dest will have something to do + * when it starts operation. + * + * - Whenever nodes with children are encountered, jobDest appends + * them as new jobs, in order. As a result, tree node siblings are + * adjacent in the resulting array, for example: + * + * [0] root, has two children + * [1] first child of 0, has three children + * [3] first child of 1, does not have children + * [4] second child of 1, does not have children + * [5] third child of 1, does not have children + * [2] second child of 0, does not have children + * + * Or (the same data) presented in flat array view: + * + * [0] root, has two children + * + * [1] first child of 0, has three children + * [2] second child of 0, does not have children + * + * [3] first child of 1, does not have children + * [4] second child of 1, does not have children + * [5] third child of 1, does not have children + * + * - The algorithm repeats until all target array indices have been processed. + */ + XML_Content *dest = ret; /* tree node writing location, moves upwards */ + XML_Content *const destLimit = &ret[dtd->scaffCount]; + XML_Content *jobDest = ret; /* next free writing location in target array */ + str = (XML_Char *)&ret[dtd->scaffCount]; + + /* Add the starting job, the root node (index 0) of the source tree */ + (jobDest++)->numchildren = 0; + + for (; dest < destLimit; dest++) { + /* Retrieve source tree array index from job storage */ + const int src_node = (int)dest->numchildren; + + /* Convert item */ + dest->type = dtd->scaffold[src_node].type; + dest->quant = dtd->scaffold[src_node].quant; + if (dest->type == XML_CTYPE_NAME) { + const XML_Char *src; + dest->name = str; + src = dtd->scaffold[src_node].name; + for (;;) { + *str++ = *src; + if (! *src) + break; + src++; + } + dest->numchildren = 0; + dest->children = NULL; + } else { + unsigned int i; + int cn; + dest->name = NULL; + dest->numchildren = dtd->scaffold[src_node].childcnt; + dest->children = jobDest; + + /* Append scaffold indices of children to array */ + for (i = 0, cn = dtd->scaffold[src_node].firstchild; + i < dest->numchildren; i++, cn = dtd->scaffold[cn].nextsib) + (jobDest++)->numchildren = (unsigned int)cn; + } + } + + return ret; +} + +static ELEMENT_TYPE * +getElementType(XML_Parser parser, const ENCODING *enc, const char *ptr, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end); + ELEMENT_TYPE *ret; + + if (! name) + return NULL; + ret = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, + sizeof(ELEMENT_TYPE)); + if (! ret) + return NULL; + if (ret->name != name) + poolDiscard(&dtd->pool); + else { + poolFinish(&dtd->pool); + if (! setElementTypePrefix(parser, ret)) + return NULL; + } + return ret; +} + +static XML_Char * +copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) { + size_t charsRequired = 0; + XML_Char *result; + + /* First determine how long the string is */ + while (s[charsRequired] != 0) { + charsRequired++; + } + /* Include the terminator */ + charsRequired++; + + /* Now allocate space for the copy */ + result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char)); + if (result == NULL) + return NULL; + /* Copy the original into place */ + memcpy(result, s, charsRequired * sizeof(XML_Char)); + return result; +} + +#ifdef XML_DTD + +static float +accountingGetCurrentAmplification(XML_Parser rootParser) { + const XmlBigCount countBytesOutput + = rootParser->m_accounting.countBytesDirect + + rootParser->m_accounting.countBytesIndirect; + const float amplificationFactor + = rootParser->m_accounting.countBytesDirect + ? (countBytesOutput + / (float)(rootParser->m_accounting.countBytesDirect)) + : 1.0f; + assert(! rootParser->m_parentParser); + return amplificationFactor; +} + +static void +accountingReportStats(XML_Parser originParser, const char *epilog) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + if (rootParser->m_accounting.debugLevel < 1) { + return; + } + + const float amplificationFactor + = accountingGetCurrentAmplification(rootParser); + fprintf(stderr, + "expat: Accounting(%p): Direct " EXPAT_FMT_ULL( + "10") ", indirect " EXPAT_FMT_ULL("10") ", amplification %8.2f%s", + (void *)rootParser, rootParser->m_accounting.countBytesDirect, + rootParser->m_accounting.countBytesIndirect, + (double)amplificationFactor, epilog); +} + +static void +accountingOnAbort(XML_Parser originParser) { + accountingReportStats(originParser, " ABORTING\n"); +} + +static void +accountingReportDiff(XML_Parser rootParser, + unsigned int levelsAwayFromRootParser, const char *before, + const char *after, ptrdiff_t bytesMore, int source_line, + enum XML_Account account) { + assert(! rootParser->m_parentParser); + + fprintf(stderr, + " (+" EXPAT_FMT_PTRDIFF_T("6") " bytes %s|%d, xmlparse.c:%d) %*s\"", + bytesMore, (account == XML_ACCOUNT_DIRECT) ? "DIR" : "EXP", + levelsAwayFromRootParser, source_line, 10, ""); + + const char ellipis[] = "[..]"; + const size_t ellipsisLength = sizeof(ellipis) /* because compile-time */ - 1; + const unsigned int contextLength = 10; + + /* Note: Performance is of no concern here */ + const char *walker = before; + if ((rootParser->m_accounting.debugLevel >= 3) + || (after - before) + <= (ptrdiff_t)(contextLength + ellipsisLength + contextLength)) { + for (; walker < after; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + } else { + for (; walker < before + contextLength; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + fprintf(stderr, ellipis); + walker = after - contextLength; + for (; walker < after; walker++) { + fprintf(stderr, "%s", unsignedCharToPrintable(walker[0])); + } + } + fprintf(stderr, "\"\n"); +} + +static XML_Bool +accountingDiffTolerated(XML_Parser originParser, int tok, const char *before, + const char *after, int source_line, + enum XML_Account account) { + /* Note: We need to check the token type *first* to be sure that + * we can even access variable <after>, safely. + * E.g. for XML_TOK_NONE <after> may hold an invalid pointer. */ + switch (tok) { + case XML_TOK_INVALID: + case XML_TOK_PARTIAL: + case XML_TOK_PARTIAL_CHAR: + case XML_TOK_NONE: + return XML_TRUE; + } + + if (account == XML_ACCOUNT_NONE) + return XML_TRUE; /* because these bytes have been accounted for, already */ + + unsigned int levelsAwayFromRootParser; + const XML_Parser rootParser + = getRootParserOf(originParser, &levelsAwayFromRootParser); + assert(! rootParser->m_parentParser); + + const int isDirect + = (account == XML_ACCOUNT_DIRECT) && (originParser == rootParser); + const ptrdiff_t bytesMore = after - before; + + XmlBigCount *const additionTarget + = isDirect ? &rootParser->m_accounting.countBytesDirect + : &rootParser->m_accounting.countBytesIndirect; + + /* Detect and avoid integer overflow */ + if (*additionTarget > (XmlBigCount)(-1) - (XmlBigCount)bytesMore) + return XML_FALSE; + *additionTarget += bytesMore; + + const XmlBigCount countBytesOutput + = rootParser->m_accounting.countBytesDirect + + rootParser->m_accounting.countBytesIndirect; + const float amplificationFactor + = accountingGetCurrentAmplification(rootParser); + const XML_Bool tolerated + = (countBytesOutput < rootParser->m_accounting.activationThresholdBytes) + || (amplificationFactor + <= rootParser->m_accounting.maximumAmplificationFactor); + + if (rootParser->m_accounting.debugLevel >= 2) { + accountingReportStats(rootParser, ""); + accountingReportDiff(rootParser, levelsAwayFromRootParser, before, after, + bytesMore, source_line, account); + } + + return tolerated; +} + +unsigned long long +testingAccountingGetCountBytesDirect(XML_Parser parser) { + if (! parser) + return 0; + return parser->m_accounting.countBytesDirect; +} + +unsigned long long +testingAccountingGetCountBytesIndirect(XML_Parser parser) { + if (! parser) + return 0; + return parser->m_accounting.countBytesIndirect; +} + +static void +entityTrackingReportStats(XML_Parser rootParser, ENTITY *entity, + const char *action, int sourceLine) { + assert(! rootParser->m_parentParser); + if (rootParser->m_entity_stats.debugLevel < 1) + return; + +# if defined(XML_UNICODE) + const char *const entityName = "[..]"; +# else + const char *const entityName = entity->name; +# endif + + fprintf( + stderr, + "expat: Entities(%p): Count %9d, depth %2d/%2d %*s%s%s; %s length %d (xmlparse.c:%d)\n", + (void *)rootParser, rootParser->m_entity_stats.countEverOpened, + rootParser->m_entity_stats.currentDepth, + rootParser->m_entity_stats.maximumDepthSeen, + (rootParser->m_entity_stats.currentDepth - 1) * 2, "", + entity->is_param ? "%" : "&", entityName, action, entity->textLen, + sourceLine); +} + +static void +entityTrackingOnOpen(XML_Parser originParser, ENTITY *entity, int sourceLine) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + rootParser->m_entity_stats.countEverOpened++; + rootParser->m_entity_stats.currentDepth++; + if (rootParser->m_entity_stats.currentDepth + > rootParser->m_entity_stats.maximumDepthSeen) { + rootParser->m_entity_stats.maximumDepthSeen++; + } + + entityTrackingReportStats(rootParser, entity, "OPEN ", sourceLine); +} + +static void +entityTrackingOnClose(XML_Parser originParser, ENTITY *entity, int sourceLine) { + const XML_Parser rootParser = getRootParserOf(originParser, NULL); + assert(! rootParser->m_parentParser); + + entityTrackingReportStats(rootParser, entity, "CLOSE", sourceLine); + rootParser->m_entity_stats.currentDepth--; +} + +static XML_Parser +getRootParserOf(XML_Parser parser, unsigned int *outLevelDiff) { + XML_Parser rootParser = parser; + unsigned int stepsTakenUpwards = 0; + while (rootParser->m_parentParser) { + rootParser = rootParser->m_parentParser; + stepsTakenUpwards++; + } + assert(! rootParser->m_parentParser); + if (outLevelDiff != NULL) { + *outLevelDiff = stepsTakenUpwards; + } + return rootParser; +} + +const char * +unsignedCharToPrintable(unsigned char c) { + switch (c) { + case 0: + return "\\0"; + case 1: + return "\\x1"; + case 2: + return "\\x2"; + case 3: + return "\\x3"; + case 4: + return "\\x4"; + case 5: + return "\\x5"; + case 6: + return "\\x6"; + case 7: + return "\\x7"; + case 8: + return "\\x8"; + case 9: + return "\\t"; + case 10: + return "\\n"; + case 11: + return "\\xB"; + case 12: + return "\\xC"; + case 13: + return "\\r"; + case 14: + return "\\xE"; + case 15: + return "\\xF"; + case 16: + return "\\x10"; + case 17: + return "\\x11"; + case 18: + return "\\x12"; + case 19: + return "\\x13"; + case 20: + return "\\x14"; + case 21: + return "\\x15"; + case 22: + return "\\x16"; + case 23: + return "\\x17"; + case 24: + return "\\x18"; + case 25: + return "\\x19"; + case 26: + return "\\x1A"; + case 27: + return "\\x1B"; + case 28: + return "\\x1C"; + case 29: + return "\\x1D"; + case 30: + return "\\x1E"; + case 31: + return "\\x1F"; + case 32: + return " "; + case 33: + return "!"; + case 34: + return "\\\""; + case 35: + return "#"; + case 36: + return "$"; + case 37: + return "%"; + case 38: + return "&"; + case 39: + return "'"; + case 40: + return "("; + case 41: + return ")"; + case 42: + return "*"; + case 43: + return "+"; + case 44: + return ","; + case 45: + return "-"; + case 46: + return "."; + case 47: + return "/"; + case 48: + return "0"; + case 49: + return "1"; + case 50: + return "2"; + case 51: + return "3"; + case 52: + return "4"; + case 53: + return "5"; + case 54: + return "6"; + case 55: + return "7"; + case 56: + return "8"; + case 57: + return "9"; + case 58: + return ":"; + case 59: + return ";"; + case 60: + return "<"; + case 61: + return "="; + case 62: + return ">"; + case 63: + return "?"; + case 64: + return "@"; + case 65: + return "A"; + case 66: + return "B"; + case 67: + return "C"; + case 68: + return "D"; + case 69: + return "E"; + case 70: + return "F"; + case 71: + return "G"; + case 72: + return "H"; + case 73: + return "I"; + case 74: + return "J"; + case 75: + return "K"; + case 76: + return "L"; + case 77: + return "M"; + case 78: + return "N"; + case 79: + return "O"; + case 80: + return "P"; + case 81: + return "Q"; + case 82: + return "R"; + case 83: + return "S"; + case 84: + return "T"; + case 85: + return "U"; + case 86: + return "V"; + case 87: + return "W"; + case 88: + return "X"; + case 89: + return "Y"; + case 90: + return "Z"; + case 91: + return "["; + case 92: + return "\\\\"; + case 93: + return "]"; + case 94: + return "^"; + case 95: + return "_"; + case 96: + return "`"; + case 97: + return "a"; + case 98: + return "b"; + case 99: + return "c"; + case 100: + return "d"; + case 101: + return "e"; + case 102: + return "f"; + case 103: + return "g"; + case 104: + return "h"; + case 105: + return "i"; + case 106: + return "j"; + case 107: + return "k"; + case 108: + return "l"; + case 109: + return "m"; + case 110: + return "n"; + case 111: + return "o"; + case 112: + return "p"; + case 113: + return "q"; + case 114: + return "r"; + case 115: + return "s"; + case 116: + return "t"; + case 117: + return "u"; + case 118: + return "v"; + case 119: + return "w"; + case 120: + return "x"; + case 121: + return "y"; + case 122: + return "z"; + case 123: + return "{"; + case 124: + return "|"; + case 125: + return "}"; + case 126: + return "~"; + case 127: + return "\\x7F"; + case 128: + return "\\x80"; + case 129: + return "\\x81"; + case 130: + return "\\x82"; + case 131: + return "\\x83"; + case 132: + return "\\x84"; + case 133: + return "\\x85"; + case 134: + return "\\x86"; + case 135: + return "\\x87"; + case 136: + return "\\x88"; + case 137: + return "\\x89"; + case 138: + return "\\x8A"; + case 139: + return "\\x8B"; + case 140: + return "\\x8C"; + case 141: + return "\\x8D"; + case 142: + return "\\x8E"; + case 143: + return "\\x8F"; + case 144: + return "\\x90"; + case 145: + return "\\x91"; + case 146: + return "\\x92"; + case 147: + return "\\x93"; + case 148: + return "\\x94"; + case 149: + return "\\x95"; + case 150: + return "\\x96"; + case 151: + return "\\x97"; + case 152: + return "\\x98"; + case 153: + return "\\x99"; + case 154: + return "\\x9A"; + case 155: + return "\\x9B"; + case 156: + return "\\x9C"; + case 157: + return "\\x9D"; + case 158: + return "\\x9E"; + case 159: + return "\\x9F"; + case 160: + return "\\xA0"; + case 161: + return "\\xA1"; + case 162: + return "\\xA2"; + case 163: + return "\\xA3"; + case 164: + return "\\xA4"; + case 165: + return "\\xA5"; + case 166: + return "\\xA6"; + case 167: + return "\\xA7"; + case 168: + return "\\xA8"; + case 169: + return "\\xA9"; + case 170: + return "\\xAA"; + case 171: + return "\\xAB"; + case 172: + return "\\xAC"; + case 173: + return "\\xAD"; + case 174: + return "\\xAE"; + case 175: + return "\\xAF"; + case 176: + return "\\xB0"; + case 177: + return "\\xB1"; + case 178: + return "\\xB2"; + case 179: + return "\\xB3"; + case 180: + return "\\xB4"; + case 181: + return "\\xB5"; + case 182: + return "\\xB6"; + case 183: + return "\\xB7"; + case 184: + return "\\xB8"; + case 185: + return "\\xB9"; + case 186: + return "\\xBA"; + case 187: + return "\\xBB"; + case 188: + return "\\xBC"; + case 189: + return "\\xBD"; + case 190: + return "\\xBE"; + case 191: + return "\\xBF"; + case 192: + return "\\xC0"; + case 193: + return "\\xC1"; + case 194: + return "\\xC2"; + case 195: + return "\\xC3"; + case 196: + return "\\xC4"; + case 197: + return "\\xC5"; + case 198: + return "\\xC6"; + case 199: + return "\\xC7"; + case 200: + return "\\xC8"; + case 201: + return "\\xC9"; + case 202: + return "\\xCA"; + case 203: + return "\\xCB"; + case 204: + return "\\xCC"; + case 205: + return "\\xCD"; + case 206: + return "\\xCE"; + case 207: + return "\\xCF"; + case 208: + return "\\xD0"; + case 209: + return "\\xD1"; + case 210: + return "\\xD2"; + case 211: + return "\\xD3"; + case 212: + return "\\xD4"; + case 213: + return "\\xD5"; + case 214: + return "\\xD6"; + case 215: + return "\\xD7"; + case 216: + return "\\xD8"; + case 217: + return "\\xD9"; + case 218: + return "\\xDA"; + case 219: + return "\\xDB"; + case 220: + return "\\xDC"; + case 221: + return "\\xDD"; + case 222: + return "\\xDE"; + case 223: + return "\\xDF"; + case 224: + return "\\xE0"; + case 225: + return "\\xE1"; + case 226: + return "\\xE2"; + case 227: + return "\\xE3"; + case 228: + return "\\xE4"; + case 229: + return "\\xE5"; + case 230: + return "\\xE6"; + case 231: + return "\\xE7"; + case 232: + return "\\xE8"; + case 233: + return "\\xE9"; + case 234: + return "\\xEA"; + case 235: + return "\\xEB"; + case 236: + return "\\xEC"; + case 237: + return "\\xED"; + case 238: + return "\\xEE"; + case 239: + return "\\xEF"; + case 240: + return "\\xF0"; + case 241: + return "\\xF1"; + case 242: + return "\\xF2"; + case 243: + return "\\xF3"; + case 244: + return "\\xF4"; + case 245: + return "\\xF5"; + case 246: + return "\\xF6"; + case 247: + return "\\xF7"; + case 248: + return "\\xF8"; + case 249: + return "\\xF9"; + case 250: + return "\\xFA"; + case 251: + return "\\xFB"; + case 252: + return "\\xFC"; + case 253: + return "\\xFD"; + case 254: + return "\\xFE"; + case 255: + return "\\xFF"; + default: + assert(0); /* never gets here */ + return "dead code"; + } + assert(0); /* never gets here */ +} + +#endif /* XML_DTD */ + +static unsigned long +getDebugLevel(const char *variableName, unsigned long defaultDebugLevel) { + const char *const valueOrNull = getenv(variableName); + if (valueOrNull == NULL) { + return defaultDebugLevel; + } + const char *const value = valueOrNull; + + errno = 0; + char *afterValue = (char *)value; + unsigned long debugLevel = strtoul(value, &afterValue, 10); + if ((errno != 0) || (afterValue[0] != '\0')) { + errno = 0; + return defaultDebugLevel; + } + + return debugLevel; +} diff --git a/Utilities/cmexpat/lib/xmlrole.c b/Utilities/cmexpat/lib/xmlrole.c new file mode 100644 index 0000000000..3f0f5c150c --- /dev/null +++ b/Utilities/cmexpat/lib/xmlrole.c @@ -0,0 +1,1255 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016-2021 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2021 Dong-hee Na <donghee.na@python.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#include <expat_config.h> + +#include <stddef.h> + +#ifdef _WIN32 +# include "winconfig.h" +#endif + +#include "expat_external.h" +#include "internal.h" +#include "xmlrole.h" +#include "ascii.h" + +/* Doesn't check: + + that ,| are not mixed in a model group + content of literals + +*/ + +static const char KW_ANY[] = {ASCII_A, ASCII_N, ASCII_Y, '\0'}; +static const char KW_ATTLIST[] + = {ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0'}; +static const char KW_CDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_DOCTYPE[] + = {ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0'}; +static const char KW_ELEMENT[] + = {ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0'}; +static const char KW_EMPTY[] + = {ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0'}; +static const char KW_ENTITIES[] = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; +static const char KW_ENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; +static const char KW_FIXED[] + = {ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0'}; +static const char KW_ID[] = {ASCII_I, ASCII_D, '\0'}; +static const char KW_IDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; +static const char KW_IDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; +#ifdef XML_DTD +static const char KW_IGNORE[] + = {ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0'}; +#endif +static const char KW_IMPLIED[] + = {ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0'}; +#ifdef XML_DTD +static const char KW_INCLUDE[] + = {ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0'}; +#endif +static const char KW_NDATA[] + = {ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_NMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; +static const char KW_NMTOKENS[] = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; +static const char KW_NOTATION[] = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, '\0'}; +static const char KW_PCDATA[] + = {ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_PUBLIC[] + = {ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0'}; +static const char KW_REQUIRED[] = {ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, + ASCII_R, ASCII_E, ASCII_D, '\0'}; +static const char KW_SYSTEM[] + = {ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0'}; + +#ifndef MIN_BYTES_PER_CHAR +# define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) +#endif + +#ifdef XML_DTD +# define setTopLevel(state) \ + ((state)->handler \ + = ((state)->documentEntity ? internalSubset : externalSubset1)) +#else /* not XML_DTD */ +# define setTopLevel(state) ((state)->handler = internalSubset) +#endif /* not XML_DTD */ + +typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, int tok, + const char *ptr, const char *end, + const ENCODING *enc); + +static PROLOG_HANDLER prolog0, prolog1, prolog2, doctype0, doctype1, doctype2, + doctype3, doctype4, doctype5, internalSubset, entity0, entity1, entity2, + entity3, entity4, entity5, entity6, entity7, entity8, entity9, entity10, + notation0, notation1, notation2, notation3, notation4, attlist0, attlist1, + attlist2, attlist3, attlist4, attlist5, attlist6, attlist7, attlist8, + attlist9, element0, element1, element2, element3, element4, element5, + element6, element7, +#ifdef XML_DTD + externalSubset0, externalSubset1, condSect0, condSect1, condSect2, +#endif /* XML_DTD */ + declClose, error; + +static int FASTCALL common(PROLOG_STATE *state, int tok); + +static int PTRCALL +prolog0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + state->handler = prolog1; + return XML_ROLE_NONE; + case XML_TOK_XML_DECL: + state->handler = prolog1; + return XML_ROLE_XML_DECL; + case XML_TOK_PI: + state->handler = prolog1; + return XML_ROLE_PI; + case XML_TOK_COMMENT: + state->handler = prolog1; + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + /* This case can never arise. To reach this role function, the + * parse must have passed through prolog0 and therefore have had + * some form of input, even if only a space. At that point, a + * byte order mark is no longer a valid character (though + * technically it should be interpreted as a non-breaking space), + * so will be rejected by the tokenizing stages. + */ + return XML_ROLE_NONE; /* LCOV_EXCL_LINE */ + case XML_TOK_DECL_OPEN: + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +doctype0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = doctype1; + return XML_ROLE_DOCTYPE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +doctype1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = doctype3; + return XML_ROLE_DOCTYPE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = doctype2; + return XML_ROLE_DOCTYPE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +doctype2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype3; + return XML_ROLE_DOCTYPE_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype4; + return XML_ROLE_DOCTYPE_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +doctype5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +internalSubset(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_ENTITY)) { + state->handler = entity0; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_ATTLIST)) { + state->handler = attlist0; + return XML_ROLE_ATTLIST_NONE; + } + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_ELEMENT)) { + state->handler = element0; + return XML_ROLE_ELEMENT_NONE; + } + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_NOTATION)) { + state->handler = notation0; + return XML_ROLE_NOTATION_NONE; + } + break; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_PARAM_ENTITY_REF: + return XML_ROLE_PARAM_ENTITY_REF; + case XML_TOK_CLOSE_BRACKET: + state->handler = doctype5; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NONE: + return XML_ROLE_NONE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +externalSubset0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + state->handler = externalSubset1; + if (tok == XML_TOK_XML_DECL) + return XML_ROLE_TEXT_DECL; + return externalSubset1(state, tok, ptr, end, enc); +} + +static int PTRCALL +externalSubset1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_COND_SECT_OPEN: + state->handler = condSect0; + return XML_ROLE_NONE; + case XML_TOK_COND_SECT_CLOSE: + if (state->includeLevel == 0) + break; + state->includeLevel -= 1; + return XML_ROLE_NONE; + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_CLOSE_BRACKET: + break; + case XML_TOK_NONE: + if (state->includeLevel) + break; + return XML_ROLE_NONE; + default: + return internalSubset(state, tok, ptr, end, enc); + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +entity0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_PERCENT: + state->handler = entity1; + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity2; + return XML_ROLE_GENERAL_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity7; + return XML_ROLE_PARAM_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity4; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity3; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity4; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity5; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_NDATA)) { + state->handler = entity6; + return XML_ROLE_ENTITY_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +entity6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity9; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity8; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity9; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity10; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity10(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + } + return common(state, tok); +} + +static int PTRCALL +notation0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + state->handler = notation1; + return XML_ROLE_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +notation1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = notation3; + return XML_ROLE_NOTATION_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = notation2; + return XML_ROLE_NOTATION_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +notation2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = notation4; + return XML_ROLE_NOTATION_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_NOTATION_NO_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +attlist0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist1; + return XML_ROLE_ATTLIST_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist2; + return XML_ROLE_ATTRIBUTE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: { + static const char *const types[] = { + KW_CDATA, KW_ID, KW_IDREF, KW_IDREFS, + KW_ENTITY, KW_ENTITIES, KW_NMTOKEN, KW_NMTOKENS, + }; + int i; + for (i = 0; i < (int)(sizeof(types) / sizeof(types[0])); i++) + if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { + state->handler = attlist8; + return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; + } + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) { + state->handler = attlist5; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NMTOKEN: + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist4; + return XML_ROLE_ATTRIBUTE_ENUM_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OPEN_PAREN: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + state->handler = attlist7; + return XML_ROLE_ATTRIBUTE_NOTATION_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +/* default value */ +static int PTRCALL +attlist8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, + KW_IMPLIED)) { + state->handler = attlist1; + return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, + KW_REQUIRED)) { + state->handler = attlist1; + return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, + KW_FIXED)) { + state->handler = attlist9; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_FIXED_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +element0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element1; + return XML_ROLE_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +element1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_EMPTY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_EMPTY; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_ANY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_ANY; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = element2; + state->level = 1; + return XML_ROLE_GROUP_OPEN; + } + return common(state, tok); +} + +static int PTRCALL +element2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, + KW_PCDATA)) { + state->handler = element3; + return XML_ROLE_CONTENT_PCDATA; + } + break; + case XML_TOK_OPEN_PAREN: + state->level = 2; + state->handler = element6; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element5; + return XML_ROLE_CONTENT_ELEMENT; + } + return common(state, tok); +} + +static int PTRCALL +element5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_OPEN_PAREN: + state->level += 1; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_CLOSE_PAREN_QUESTION: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_OPT; + case XML_TOK_CLOSE_PAREN_PLUS: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_PLUS; + case XML_TOK_COMMA: + state->handler = element6; + return XML_ROLE_GROUP_SEQUENCE; + case XML_TOK_OR: + state->handler = element6; + return XML_ROLE_GROUP_CHOICE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +condSect0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_INCLUDE)) { + state->handler = condSect1; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_IGNORE)) { + state->handler = condSect2; + return XML_ROLE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +condSect1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + state->includeLevel += 1; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static int PTRCALL +condSect2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + return XML_ROLE_IGNORE_SECT; + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +declClose(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + switch (tok) { + case XML_TOK_PROLOG_S: + return state->role_none; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return state->role_none; + } + return common(state, tok); +} + +/* This function will only be invoked if the internal logic of the + * parser has broken down. It is used in two cases: + * + * 1: When the XML prolog has been finished. At this point the + * processor (the parser level above these role handlers) should + * switch from prologProcessor to contentProcessor and reinitialise + * the handler function. + * + * 2: When an error has been detected (via common() below). At this + * point again the processor should be switched to errorProcessor, + * which will never call a handler. + * + * The result of this is that error() can only be called if the + * processor switch failed to happen, which is an internal error and + * therefore we shouldn't be able to provoke it simply by using the + * library. It is a necessary backstop, however, so we merely exclude + * it from the coverage statistics. + * + * LCOV_EXCL_START + */ +static int PTRCALL +error(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(state); + UNUSED_P(tok); + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); + return XML_ROLE_NONE; +} +/* LCOV_EXCL_STOP */ + +static int FASTCALL +common(PROLOG_STATE *state, int tok) { +#ifdef XML_DTD + if (! state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) + return XML_ROLE_INNER_PARAM_ENTITY_REF; +#else + UNUSED_P(tok); +#endif + state->handler = error; + return XML_ROLE_ERROR; +} + +void +XmlPrologStateInit(PROLOG_STATE *state) { + state->handler = prolog0; +#ifdef XML_DTD + state->documentEntity = 1; + state->includeLevel = 0; + state->inEntityValue = 0; +#endif /* XML_DTD */ +} + +#ifdef XML_DTD + +void +XmlPrologStateInitExternalEntity(PROLOG_STATE *state) { + state->handler = externalSubset0; + state->documentEntity = 0; + state->includeLevel = 0; +} + +#endif /* XML_DTD */ diff --git a/Utilities/cmexpat/lib/xmlrole.h b/Utilities/cmexpat/lib/xmlrole.h new file mode 100644 index 0000000000..d6e1fa150a --- /dev/null +++ b/Utilities/cmexpat/lib/xmlrole.h @@ -0,0 +1,142 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifndef XmlRole_INCLUDED +#define XmlRole_INCLUDED 1 + +#ifdef __VMS +/* 0 1 2 3 0 1 2 3 + 1234567890123456789012345678901 1234567890123456789012345678901 */ +# define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt +#endif + +#include "xmltok.h" + +#ifdef __cplusplus +extern "C" { +#endif + +enum { + XML_ROLE_ERROR = -1, + XML_ROLE_NONE = 0, + XML_ROLE_XML_DECL, + XML_ROLE_INSTANCE_START, + XML_ROLE_DOCTYPE_NONE, + XML_ROLE_DOCTYPE_NAME, + XML_ROLE_DOCTYPE_SYSTEM_ID, + XML_ROLE_DOCTYPE_PUBLIC_ID, + XML_ROLE_DOCTYPE_INTERNAL_SUBSET, + XML_ROLE_DOCTYPE_CLOSE, + XML_ROLE_GENERAL_ENTITY_NAME, + XML_ROLE_PARAM_ENTITY_NAME, + XML_ROLE_ENTITY_NONE, + XML_ROLE_ENTITY_VALUE, + XML_ROLE_ENTITY_SYSTEM_ID, + XML_ROLE_ENTITY_PUBLIC_ID, + XML_ROLE_ENTITY_COMPLETE, + XML_ROLE_ENTITY_NOTATION_NAME, + XML_ROLE_NOTATION_NONE, + XML_ROLE_NOTATION_NAME, + XML_ROLE_NOTATION_SYSTEM_ID, + XML_ROLE_NOTATION_NO_SYSTEM_ID, + XML_ROLE_NOTATION_PUBLIC_ID, + XML_ROLE_ATTRIBUTE_NAME, + XML_ROLE_ATTRIBUTE_TYPE_CDATA, + XML_ROLE_ATTRIBUTE_TYPE_ID, + XML_ROLE_ATTRIBUTE_TYPE_IDREF, + XML_ROLE_ATTRIBUTE_TYPE_IDREFS, + XML_ROLE_ATTRIBUTE_TYPE_ENTITY, + XML_ROLE_ATTRIBUTE_TYPE_ENTITIES, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS, + XML_ROLE_ATTRIBUTE_ENUM_VALUE, + XML_ROLE_ATTRIBUTE_NOTATION_VALUE, + XML_ROLE_ATTLIST_NONE, + XML_ROLE_ATTLIST_ELEMENT_NAME, + XML_ROLE_IMPLIED_ATTRIBUTE_VALUE, + XML_ROLE_REQUIRED_ATTRIBUTE_VALUE, + XML_ROLE_DEFAULT_ATTRIBUTE_VALUE, + XML_ROLE_FIXED_ATTRIBUTE_VALUE, + XML_ROLE_ELEMENT_NONE, + XML_ROLE_ELEMENT_NAME, + XML_ROLE_CONTENT_ANY, + XML_ROLE_CONTENT_EMPTY, + XML_ROLE_CONTENT_PCDATA, + XML_ROLE_GROUP_OPEN, + XML_ROLE_GROUP_CLOSE, + XML_ROLE_GROUP_CLOSE_REP, + XML_ROLE_GROUP_CLOSE_OPT, + XML_ROLE_GROUP_CLOSE_PLUS, + XML_ROLE_GROUP_CHOICE, + XML_ROLE_GROUP_SEQUENCE, + XML_ROLE_CONTENT_ELEMENT, + XML_ROLE_CONTENT_ELEMENT_REP, + XML_ROLE_CONTENT_ELEMENT_OPT, + XML_ROLE_CONTENT_ELEMENT_PLUS, + XML_ROLE_PI, + XML_ROLE_COMMENT, +#ifdef XML_DTD + XML_ROLE_TEXT_DECL, + XML_ROLE_IGNORE_SECT, + XML_ROLE_INNER_PARAM_ENTITY_REF, +#endif /* XML_DTD */ + XML_ROLE_PARAM_ENTITY_REF +}; + +typedef struct prolog_state { + int(PTRCALL *handler)(struct prolog_state *state, int tok, const char *ptr, + const char *end, const ENCODING *enc); + unsigned level; + int role_none; +#ifdef XML_DTD + unsigned includeLevel; + int documentEntity; + int inEntityValue; +#endif /* XML_DTD */ +} PROLOG_STATE; + +void XmlPrologStateInit(PROLOG_STATE *); +#ifdef XML_DTD +void XmlPrologStateInitExternalEntity(PROLOG_STATE *); +#endif /* XML_DTD */ + +#define XmlTokenRole(state, tok, ptr, end, enc) \ + (((state)->handler)(state, tok, ptr, end, enc)) + +#ifdef __cplusplus +} +#endif + +#endif /* not XmlRole_INCLUDED */ diff --git a/Utilities/cmexpat/lib/xmltok.c b/Utilities/cmexpat/lib/xmltok.c new file mode 100644 index 0000000000..c659983b40 --- /dev/null +++ b/Utilities/cmexpat/lib/xmltok.c @@ -0,0 +1,1676 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2001-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2005-2009 Steven Solie <steven@solie.ca> + Copyright (c) 2016-2022 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2016 Pascal Cuoq <cuoq@trust-in-soft.com> + Copyright (c) 2016 Don Lewis <truckman@apache.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2017 Alexander Bluhm <alexander.bluhm@gmx.net> + Copyright (c) 2017 Benbuck Nason <bnason@netflix.com> + Copyright (c) 2017 José Gutiérrez de la Concha <jose@zeroc.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2021 Dong-hee Na <donghee.na@python.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#include <expat_config.h> + +#include <stddef.h> +#include <string.h> /* memcpy */ +#include <stdbool.h> + +#ifdef _WIN32 +# include "winconfig.h" +#endif + +#include "expat_external.h" +#include "internal.h" +#include "xmltok.h" +#include "nametab.h" + +#ifdef XML_DTD +# define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) +#else +# define IGNORE_SECTION_TOK_VTABLE /* as nothing */ +#endif + +#define VTABLE1 \ + {PREFIX(prologTok), PREFIX(contentTok), \ + PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE}, \ + {PREFIX(attributeValueTok), PREFIX(entityValueTok)}, \ + PREFIX(nameMatchesAscii), PREFIX(nameLength), PREFIX(skipS), \ + PREFIX(getAtts), PREFIX(charRefNumber), PREFIX(predefinedEntityName), \ + PREFIX(updatePosition), PREFIX(isPublicId) + +#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) + +#define UCS2_GET_NAMING(pages, hi, lo) \ + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo)&0x1F))) + +/* A 2 byte UTF-8 representation splits the characters 11 bits between + the bottom 5 and 6 bits of the bytes. We need 8 bits to index into + pages, 3 bits to add to that index and 5 bits to generate the mask. +*/ +#define UTF8_GET_NAMING2(pages, byte) \ + (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ + + ((((byte)[0]) & 3) << 1) + ((((byte)[1]) >> 5) & 1)] \ + & (1u << (((byte)[1]) & 0x1F))) + +/* A 3 byte UTF-8 representation splits the characters 16 bits between + the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index + into pages, 3 bits to add to that index and 5 bits to generate the + mask. +*/ +#define UTF8_GET_NAMING3(pages, byte) \ + (namingBitmap \ + [((pages)[((((byte)[0]) & 0xF) << 4) + ((((byte)[1]) >> 2) & 0xF)] \ + << 3) \ + + ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \ + & (1u << (((byte)[2]) & 0x1F))) + +/* Detection of invalid UTF-8 sequences is based on Table 3.1B + of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ + with the additional restriction of not allowing the Unicode + code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE). + Implementation details: + (A & 0x80) == 0 means A < 0x80 + and + (A & 0xC0) == 0xC0 means A > 0xBF +*/ + +#define UTF8_INVALID2(p) \ + ((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0) + +#define UTF8_INVALID3(p) \ + (((p)[2] & 0x80) == 0 \ + || ((*p) == 0xEF && (p)[1] == 0xBF ? (p)[2] > 0xBD \ + : ((p)[2] & 0xC0) == 0xC0) \ + || ((*p) == 0xE0 \ + ? (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) + +#define UTF8_INVALID4(p) \ + (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 || ((p)[2] & 0x80) == 0 \ + || ((p)[2] & 0xC0) == 0xC0 \ + || ((*p) == 0xF0 \ + ? (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) + +static int PTRFASTCALL +isNever(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + UNUSED_P(p); + return 0; +} + +static int PTRFASTCALL +utf8_isName2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isName3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); +} + +#define utf8_isName4 isNever + +static int PTRFASTCALL +utf8_isNmstrt2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isNmstrt3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); +} + +#define utf8_isNmstrt4 isNever + +static int PTRFASTCALL +utf8_isInvalid2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_INVALID2((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_INVALID3((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid4(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return UTF8_INVALID4((const unsigned char *)p); +} + +struct normal_encoding { + ENCODING enc; + unsigned char type[256]; +#ifdef XML_MIN_SIZE + int(PTRFASTCALL *byteType)(const ENCODING *, const char *); + int(PTRFASTCALL *isNameMin)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); + int(PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); + int(PTRCALL *charMatches)(const ENCODING *, const char *, int); +#endif /* XML_MIN_SIZE */ + int(PTRFASTCALL *isName2)(const ENCODING *, const char *); + int(PTRFASTCALL *isName3)(const ENCODING *, const char *); + int(PTRFASTCALL *isName4)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); +}; + +#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *)(enc)) + +#ifdef XML_MIN_SIZE + +# define STANDARD_VTABLE(E) \ + E##byteType, E##isNameMin, E##isNmstrtMin, E##byteToAscii, E##charMatches, + +#else + +# define STANDARD_VTABLE(E) /* as nothing */ + +#endif + +#define NORMAL_VTABLE(E) \ + E##isName2, E##isName3, E##isName4, E##isNmstrt2, E##isNmstrt3, \ + E##isNmstrt4, E##isInvalid2, E##isInvalid3, E##isInvalid4 + +#define NULL_VTABLE \ + /* isName2 */ NULL, /* isName3 */ NULL, /* isName4 */ NULL, \ + /* isNmstrt2 */ NULL, /* isNmstrt3 */ NULL, /* isNmstrt4 */ NULL, \ + /* isInvalid2 */ NULL, /* isInvalid3 */ NULL, /* isInvalid4 */ NULL + +static int FASTCALL checkCharRefNumber(int); + +#include "xmltok_impl.h" +#include "ascii.h" + +#ifdef XML_MIN_SIZE +# define sb_isNameMin isNever +# define sb_isNmstrtMin isNever +#endif + +#ifdef XML_MIN_SIZE +# define MINBPC(enc) ((enc)->minBytesPerChar) +#else +/* minimum bytes per character */ +# define MINBPC(enc) 1 +#endif + +#define SB_BYTE_TYPE(enc, p) \ + (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) + +#ifdef XML_MIN_SIZE +static int PTRFASTCALL +sb_byteType(const ENCODING *enc, const char *p) { + return SB_BYTE_TYPE(enc, p); +} +# define BYTE_TYPE(enc, p) (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) +#else +# define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) +#endif + +#ifdef XML_MIN_SIZE +# define BYTE_TO_ASCII(enc, p) (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) +static int PTRFASTCALL +sb_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return *p; +} +#else +# define BYTE_TO_ASCII(enc, p) (*(p)) +#endif + +#define IS_NAME_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isName##n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isNmstrt##n(enc, p)) +#ifdef XML_MIN_SIZE +# define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n \ + && AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) +#else +# define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) +#endif + +#ifdef XML_MIN_SIZE +# define IS_NAME_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) +#else +# define IS_NAME_CHAR_MINBPC(enc, p) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) +#endif + +#ifdef XML_MIN_SIZE +# define CHAR_MATCHES(enc, p, c) \ + (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) +static int PTRCALL +sb_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return *p == c; +} +#else +/* c is an ASCII character */ +# define CHAR_MATCHES(enc, p, c) (*(p) == c) +#endif + +#define PREFIX(ident) normal_##ident +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ + UTF8_cval1 = 0x00, + UTF8_cval2 = 0xc0, + UTF8_cval3 = 0xe0, + UTF8_cval4 = 0xf0 +}; + +void +_INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef) { + const char *fromLim = *fromLimRef; + size_t walked = 0; + for (; fromLim > from; fromLim--, walked++) { + const unsigned char prev = (unsigned char)fromLim[-1]; + if ((prev & 0xf8u) + == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */ + if (walked + 1 >= 4) { + fromLim += 4 - 1; + break; + } else { + walked = 0; + } + } else if ((prev & 0xf0u) + == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */ + if (walked + 1 >= 3) { + fromLim += 3 - 1; + break; + } else { + walked = 0; + } + } else if ((prev & 0xe0u) + == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */ + if (walked + 1 >= 2) { + fromLim += 2 - 1; + break; + } else { + walked = 0; + } + } else if ((prev & 0x80u) + == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */ + break; + } + } + *fromLimRef = fromLim; +} + +static enum XML_Convert_Result PTRCALL +utf8_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + bool input_incomplete = false; + bool output_exhausted = false; + + /* Avoid copying partial characters (due to limited space). */ + const ptrdiff_t bytesAvailable = fromLim - *fromP; + const ptrdiff_t bytesStorable = toLim - *toP; + UNUSED_P(enc); + if (bytesAvailable > bytesStorable) { + fromLim = *fromP + bytesStorable; + output_exhausted = true; + } + + /* Avoid copying partial characters (from incomplete input). */ + { + const char *const fromLimBefore = fromLim; + _INTERNAL_trim_to_complete_utf8_characters(*fromP, &fromLim); + if (fromLim < fromLimBefore) { + input_incomplete = true; + } + } + + { + const ptrdiff_t bytesToCopy = fromLim - *fromP; + memcpy(*toP, *fromP, bytesToCopy); + *fromP += bytesToCopy; + *toP += bytesToCopy; + } + + if (output_exhausted) /* needs to go first */ + return XML_CONVERT_OUTPUT_EXHAUSTED; + else if (input_incomplete) + return XML_CONVERT_INPUT_INCOMPLETE; + else + return XML_CONVERT_COMPLETED; +} + +static enum XML_Convert_Result PTRCALL +utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { + enum XML_Convert_Result res = XML_CONVERT_COMPLETED; + unsigned short *to = *toP; + const char *from = *fromP; + while (from < fromLim && to < toLim) { + switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) { + case BT_LEAD2: + if (fromLim - from < 2) { + res = XML_CONVERT_INPUT_INCOMPLETE; + goto after; + } + *to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f)); + from += 2; + break; + case BT_LEAD3: + if (fromLim - from < 3) { + res = XML_CONVERT_INPUT_INCOMPLETE; + goto after; + } + *to++ = (unsigned short)(((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) + | (from[2] & 0x3f)); + from += 3; + break; + case BT_LEAD4: { + unsigned long n; + if (toLim - to < 2) { + res = XML_CONVERT_OUTPUT_EXHAUSTED; + goto after; + } + if (fromLim - from < 4) { + res = XML_CONVERT_INPUT_INCOMPLETE; + goto after; + } + n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) + | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); + n -= 0x10000; + to[0] = (unsigned short)((n >> 10) | 0xD800); + to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); + to += 2; + from += 4; + } break; + default: + *to++ = *from++; + break; + } + } + if (from < fromLim) + res = XML_CONVERT_OUTPUT_EXHAUSTED; +after: + *fromP = from; + *toP = to; + return res; +} + +#ifdef XML_NS +static const struct normal_encoding utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; +#endif + +static const struct normal_encoding utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; + +#ifdef XML_NS + +static const struct normal_encoding internal_utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "iasciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; + +#endif + +static const struct normal_encoding internal_utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; + +static enum XML_Convert_Result PTRCALL +latin1_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); + for (;;) { + unsigned char c; + if (*fromP == fromLim) + return XML_CONVERT_COMPLETED; + c = (unsigned char)**fromP; + if (c & 0x80) { + if (toLim - *toP < 2) + return XML_CONVERT_OUTPUT_EXHAUSTED; + *(*toP)++ = (char)((c >> 6) | UTF8_cval2); + *(*toP)++ = (char)((c & 0x3f) | 0x80); + (*fromP)++; + } else { + if (*toP == toLim) + return XML_CONVERT_OUTPUT_EXHAUSTED; + *(*toP)++ = *(*fromP)++; + } + } +} + +static enum XML_Convert_Result PTRCALL +latin1_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { + UNUSED_P(enc); + while (*fromP < fromLim && *toP < toLim) + *(*toP)++ = (unsigned char)*(*fromP)++; + + if ((*toP == toLim) && (*fromP < fromLim)) + return XML_CONVERT_OUTPUT_EXHAUSTED; + else + return XML_CONVERT_COMPLETED; +} + +#ifdef XML_NS + +static const struct normal_encoding latin1_encoding_ns + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; + +#endif + +static const struct normal_encoding latin1_encoding + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; + +static enum XML_Convert_Result PTRCALL +ascii_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); + while (*fromP < fromLim && *toP < toLim) + *(*toP)++ = *(*fromP)++; + + if ((*toP == toLim) && (*fromP < fromLim)) + return XML_CONVERT_OUTPUT_EXHAUSTED; + else + return XML_CONVERT_COMPLETED; +} + +#ifdef XML_NS + +static const struct normal_encoding ascii_encoding_ns + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; + +#endif + +static const struct normal_encoding ascii_encoding + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; + +static int PTRFASTCALL +unicode_byte_type(char hi, char lo) { + switch ((unsigned char)hi) { + /* 0xD800-0xDBFF first 16-bit code unit or high surrogate (W1) */ + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: + return BT_LEAD4; + /* 0xDC00-0xDFFF second 16-bit code unit or low surrogate (W2) */ + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: + return BT_TRAIL; + case 0xFF: + switch ((unsigned char)lo) { + case 0xFF: /* noncharacter-FFFF */ + case 0xFE: /* noncharacter-FFFE */ + return BT_NONXML; + } + break; + } + return BT_NONASCII; +} + +#define DEFINE_UTF16_TO_UTF8(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf8( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + char **toP, const char *toLim) { \ + const char *from = *fromP; \ + UNUSED_P(enc); \ + fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \ + for (; from < fromLim; from += 2) { \ + int plane; \ + unsigned char lo2; \ + unsigned char lo = GET_LO(from); \ + unsigned char hi = GET_HI(from); \ + switch (hi) { \ + case 0: \ + if (lo < 0x80) { \ + if (*toP == toLim) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = lo; \ + break; \ + } \ + /* fall through */ \ + case 0x1: \ + case 0x2: \ + case 0x3: \ + case 0x4: \ + case 0x5: \ + case 0x6: \ + case 0x7: \ + if (toLim - *toP < 2) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + default: \ + if (toLim - *toP < 3) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ + *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ + *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + case 0xD8: \ + case 0xD9: \ + case 0xDA: \ + case 0xDB: \ + if (toLim - *toP < 4) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + if (fromLim - from < 4) { \ + *fromP = from; \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ + *(*toP)++ = (char)((plane >> 2) | UTF8_cval4); \ + *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ + from += 2; \ + lo2 = GET_LO(from); \ + *(*toP)++ = (((lo & 0x3) << 4) | ((GET_HI(from) & 0x3) << 2) \ + | (lo2 >> 6) | 0x80); \ + *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ + break; \ + } \ + } \ + *fromP = from; \ + if (from < fromLim) \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + else \ + return XML_CONVERT_COMPLETED; \ + } + +#define DEFINE_UTF16_TO_UTF16(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf16( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + unsigned short **toP, const unsigned short *toLim) { \ + enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \ + UNUSED_P(enc); \ + fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \ + /* Avoid copying first half only of surrogate */ \ + if (fromLim - *fromP > ((toLim - *toP) << 1) \ + && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \ + fromLim -= 2; \ + res = XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \ + *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ + if ((*toP == toLim) && (*fromP < fromLim)) \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + else \ + return res; \ + } + +#define SET2(ptr, ch) (((ptr)[0] = ((ch)&0xff)), ((ptr)[1] = ((ch) >> 8))) +#define GET_LO(ptr) ((unsigned char)(ptr)[0]) +#define GET_HI(ptr) ((unsigned char)(ptr)[1]) + +DEFINE_UTF16_TO_UTF8(little2_) +DEFINE_UTF16_TO_UTF16(little2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define SET2(ptr, ch) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch)&0xFF))) +#define GET_LO(ptr) ((unsigned char)(ptr)[1]) +#define GET_HI(ptr) ((unsigned char)(ptr)[0]) + +DEFINE_UTF16_TO_UTF8(big2_) +DEFINE_UTF16_TO_UTF16(big2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define LITTLE2_BYTE_TYPE(enc, p) \ + ((p)[1] == 0 ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ + : unicode_byte_type((p)[1], (p)[0])) +#define LITTLE2_BYTE_TO_ASCII(p) ((p)[1] == 0 ? (p)[0] : -1) +#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_IS_NAME_CHAR_MINBPC(p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) +#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +little2_byteType(const ENCODING *enc, const char *p) { + return LITTLE2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +little2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_BYTE_TO_ASCII(p); +} + +static int PTRCALL +little2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return LITTLE2_CHAR_MATCHES(p, c); +} + +static int PTRFASTCALL +little2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NAME_CHAR_MINBPC(p); +} + +static int PTRFASTCALL +little2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NMSTRT_CHAR_MINBPC(p); +} + +# undef VTABLE +# define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +# undef PREFIX +# define PREFIX(ident) little2_##ident +# define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +# define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding little2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 1234 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; + +#endif + +static const struct normal_encoding little2_encoding + = {{VTABLE, 2, 0, +#if BYTEORDER == 1234 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; + +#if BYTEORDER != 4321 + +# ifdef XML_NS + +static const struct normal_encoding internal_little2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; + +# endif + +static const struct normal_encoding internal_little2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; + +#endif + +#define BIG2_BYTE_TYPE(enc, p) \ + ((p)[0] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ + : unicode_byte_type((p)[0], (p)[1])) +#define BIG2_BYTE_TO_ASCII(p) ((p)[0] == 0 ? (p)[1] : -1) +#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_IS_NAME_CHAR_MINBPC(p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) +#define BIG2_IS_NMSTRT_CHAR_MINBPC(p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +big2_byteType(const ENCODING *enc, const char *p) { + return BIG2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +big2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_BYTE_TO_ASCII(p); +} + +static int PTRCALL +big2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return BIG2_CHAR_MATCHES(p, c); +} + +static int PTRFASTCALL +big2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NAME_CHAR_MINBPC(p); +} + +static int PTRFASTCALL +big2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NMSTRT_CHAR_MINBPC(p); +} + +# undef VTABLE +# define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +# undef PREFIX +# define PREFIX(ident) big2_##ident +# define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +# define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding big2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 4321 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; + +#endif + +static const struct normal_encoding big2_encoding + = {{VTABLE, 2, 0, +#if BYTEORDER == 4321 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; + +#if BYTEORDER != 1234 + +# ifdef XML_NS + +static const struct normal_encoding internal_big2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; + +# endif + +static const struct normal_encoding internal_big2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; + +#endif + +#undef PREFIX + +static int FASTCALL +streqci(const char *s1, const char *s2) { + for (;;) { + char c1 = *s1++; + char c2 = *s2++; + if (ASCII_a <= c1 && c1 <= ASCII_z) + c1 += ASCII_A - ASCII_a; + if (ASCII_a <= c2 && c2 <= ASCII_z) + /* The following line will never get executed. streqci() is + * only called from two places, both of which guarantee to put + * upper-case strings into s2. + */ + c2 += ASCII_A - ASCII_a; /* LCOV_EXCL_LINE */ + if (c1 != c2) + return 0; + if (! c1) + break; + } + return 1; +} + +static void PTRCALL +initUpdatePosition(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { + UNUSED_P(enc); + normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); +} + +static int +toAscii(const ENCODING *enc, const char *ptr, const char *end) { + char buf[1]; + char *p = buf; + XmlUtf8Convert(enc, &ptr, end, &p, p + 1); + if (p == buf) + return -1; + else + return buf[0]; +} + +static int FASTCALL +isSpace(int c) { + switch (c) { + case 0x20: + case 0xD: + case 0xA: + case 0x9: + return 1; + } + return 0; +} + +/* Return 1 if there's just optional white space or there's an S + followed by name=val. +*/ +static int +parsePseudoAttribute(const ENCODING *enc, const char *ptr, const char *end, + const char **namePtr, const char **nameEndPtr, + const char **valPtr, const char **nextTokPtr) { + int c; + char open; + if (ptr == end) { + *namePtr = NULL; + return 1; + } + if (! isSpace(toAscii(enc, ptr, end))) { + *nextTokPtr = ptr; + return 0; + } + do { + ptr += enc->minBytesPerChar; + } while (isSpace(toAscii(enc, ptr, end))); + if (ptr == end) { + *namePtr = NULL; + return 1; + } + *namePtr = ptr; + for (;;) { + c = toAscii(enc, ptr, end); + if (c == -1) { + *nextTokPtr = ptr; + return 0; + } + if (c == ASCII_EQUALS) { + *nameEndPtr = ptr; + break; + } + if (isSpace(c)) { + *nameEndPtr = ptr; + do { + ptr += enc->minBytesPerChar; + } while (isSpace(c = toAscii(enc, ptr, end))); + if (c != ASCII_EQUALS) { + *nextTokPtr = ptr; + return 0; + } + break; + } + ptr += enc->minBytesPerChar; + } + if (ptr == *namePtr) { + *nextTokPtr = ptr; + return 0; + } + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + while (isSpace(c)) { + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + } + if (c != ASCII_QUOT && c != ASCII_APOS) { + *nextTokPtr = ptr; + return 0; + } + open = (char)c; + ptr += enc->minBytesPerChar; + *valPtr = ptr; + for (;; ptr += enc->minBytesPerChar) { + c = toAscii(enc, ptr, end); + if (c == open) + break; + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z) + && ! (ASCII_0 <= c && c <= ASCII_9) && c != ASCII_PERIOD + && c != ASCII_MINUS && c != ASCII_UNDERSCORE) { + *nextTokPtr = ptr; + return 0; + } + } + *nextTokPtr = ptr + enc->minBytesPerChar; + return 1; +} + +static const char KW_version[] + = {ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0'}; + +static const char KW_encoding[] = {ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, + ASCII_i, ASCII_n, ASCII_g, '\0'}; + +static const char KW_standalone[] + = {ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, + ASCII_l, ASCII_o, ASCII_n, ASCII_e, '\0'}; + +static const char KW_yes[] = {ASCII_y, ASCII_e, ASCII_s, '\0'}; + +static const char KW_no[] = {ASCII_n, ASCII_o, '\0'}; + +static int +doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, const char *, + const char *), + int isGeneralTextEntity, const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr, const char **versionPtr, + const char **versionEndPtr, const char **encodingName, + const ENCODING **encoding, int *standalone) { + const char *val = NULL; + const char *name = NULL; + const char *nameEnd = NULL; + ptr += 5 * enc->minBytesPerChar; + end -= 2 * enc->minBytesPerChar; + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) + || ! name) { + *badPtr = ptr; + return 0; + } + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { + if (! isGeneralTextEntity) { + *badPtr = name; + return 0; + } + } else { + if (versionPtr) + *versionPtr = val; + if (versionEndPtr) + *versionEndPtr = ptr; + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (! name) { + if (isGeneralTextEntity) { + /* a TextDecl must have an EncodingDecl */ + *badPtr = ptr; + return 0; + } + return 1; + } + } + if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) { + int c = toAscii(enc, val, end); + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z)) { + *badPtr = val; + return 0; + } + if (encodingName) + *encodingName = val; + if (encoding) + *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar); + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (! name) + return 1; + } + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) + || isGeneralTextEntity) { + *badPtr = name; + return 0; + } + if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) { + if (standalone) + *standalone = 1; + } else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { + if (standalone) + *standalone = 0; + } else { + *badPtr = val; + return 0; + } + while (isSpace(toAscii(enc, ptr, end))) + ptr += enc->minBytesPerChar; + if (ptr != end) { + *badPtr = ptr; + return 0; + } + return 1; +} + +static int FASTCALL +checkCharRefNumber(int result) { + switch (result >> 8) { + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: + return -1; + case 0: + if (latin1_encoding.type[result] == BT_NONXML) + return -1; + break; + case 0xFF: + if (result == 0xFFFE || result == 0xFFFF) + return -1; + break; + } + return result; +} + +int FASTCALL +XmlUtf8Encode(int c, char *buf) { + enum { + /* minN is minimum legal resulting value for N byte sequence */ + min2 = 0x80, + min3 = 0x800, + min4 = 0x10000 + }; + + if (c < 0) + return 0; /* LCOV_EXCL_LINE: this case is always eliminated beforehand */ + if (c < min2) { + buf[0] = (char)(c | UTF8_cval1); + return 1; + } + if (c < min3) { + buf[0] = (char)((c >> 6) | UTF8_cval2); + buf[1] = (char)((c & 0x3f) | 0x80); + return 2; + } + if (c < min4) { + buf[0] = (char)((c >> 12) | UTF8_cval3); + buf[1] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[2] = (char)((c & 0x3f) | 0x80); + return 3; + } + if (c < 0x110000) { + buf[0] = (char)((c >> 18) | UTF8_cval4); + buf[1] = (char)(((c >> 12) & 0x3f) | 0x80); + buf[2] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[3] = (char)((c & 0x3f) | 0x80); + return 4; + } + return 0; /* LCOV_EXCL_LINE: this case too is eliminated before calling */ +} + +int FASTCALL +XmlUtf16Encode(int charNum, unsigned short *buf) { + if (charNum < 0) + return 0; + if (charNum < 0x10000) { + buf[0] = (unsigned short)charNum; + return 1; + } + if (charNum < 0x110000) { + charNum -= 0x10000; + buf[0] = (unsigned short)((charNum >> 10) + 0xD800); + buf[1] = (unsigned short)((charNum & 0x3FF) + 0xDC00); + return 2; + } + return 0; +} + +struct unknown_encoding { + struct normal_encoding normal; + CONVERTER convert; + void *userData; + unsigned short utf16[256]; + char utf8[256][4]; +}; + +#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *)(enc)) + +int +XmlSizeOfUnknownEncoding(void) { + return sizeof(struct unknown_encoding); +} + +static int PTRFASTCALL +unknown_isName(const ENCODING *enc, const char *p) { + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isNmstrt(const ENCODING *enc, const char *p) { + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isInvalid(const ENCODING *enc, const char *p) { + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; +} + +static enum XML_Convert_Result PTRCALL +unknown_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + char buf[XML_UTF8_ENCODE_MAX]; + for (;;) { + const char *utf8; + int n; + if (*fromP == fromLim) + return XML_CONVERT_COMPLETED; + utf8 = uenc->utf8[(unsigned char)**fromP]; + n = *utf8++; + if (n == 0) { + int c = uenc->convert(uenc->userData, *fromP); + n = XmlUtf8Encode(c, buf); + if (n > toLim - *toP) + return XML_CONVERT_OUTPUT_EXHAUSTED; + utf8 = buf; + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } else { + if (n > toLim - *toP) + return XML_CONVERT_OUTPUT_EXHAUSTED; + (*fromP)++; + } + memcpy(*toP, utf8, n); + *toP += n; + } +} + +static enum XML_Convert_Result PTRCALL +unknown_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + while (*fromP < fromLim && *toP < toLim) { + unsigned short c = uenc->utf16[(unsigned char)**fromP]; + if (c == 0) { + c = (unsigned short)uenc->convert(uenc->userData, *fromP); + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } else + (*fromP)++; + *(*toP)++ = c; + } + + if ((*toP == toLim) && (*fromP < fromLim)) + return XML_CONVERT_OUTPUT_EXHAUSTED; + else + return XML_CONVERT_COMPLETED; +} + +ENCODING * +XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData) { + int i; + struct unknown_encoding *e = (struct unknown_encoding *)mem; + memcpy(mem, &latin1_encoding, sizeof(struct normal_encoding)); + for (i = 0; i < 128; i++) + if (latin1_encoding.type[i] != BT_OTHER + && latin1_encoding.type[i] != BT_NONXML && table[i] != i) + return 0; + for (i = 0; i < 256; i++) { + int c = table[i]; + if (c == -1) { + e->normal.type[i] = BT_MALFORM; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } else if (c < 0) { + if (c < -4) + return 0; + /* Multi-byte sequences need a converter function */ + if (! convert) + return 0; + e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2)); + e->utf8[i][0] = 0; + e->utf16[i] = 0; + } else if (c < 0x80) { + if (latin1_encoding.type[c] != BT_OTHER + && latin1_encoding.type[c] != BT_NONXML && c != i) + return 0; + e->normal.type[i] = latin1_encoding.type[c]; + e->utf8[i][0] = 1; + e->utf8[i][1] = (char)c; + e->utf16[i] = (unsigned short)(c == 0 ? 0xFFFF : c); + } else if (checkCharRefNumber(c) < 0) { + e->normal.type[i] = BT_NONXML; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } else { + if (c > 0xFFFF) + return 0; + if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NMSTRT; + else if (UCS2_GET_NAMING(namePages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NAME; + else + e->normal.type[i] = BT_OTHER; + e->utf8[i][0] = (char)XmlUtf8Encode(c, e->utf8[i] + 1); + e->utf16[i] = (unsigned short)c; + } + } + e->userData = userData; + e->convert = convert; + if (convert) { + e->normal.isName2 = unknown_isName; + e->normal.isName3 = unknown_isName; + e->normal.isName4 = unknown_isName; + e->normal.isNmstrt2 = unknown_isNmstrt; + e->normal.isNmstrt3 = unknown_isNmstrt; + e->normal.isNmstrt4 = unknown_isNmstrt; + e->normal.isInvalid2 = unknown_isInvalid; + e->normal.isInvalid3 = unknown_isInvalid; + e->normal.isInvalid4 = unknown_isInvalid; + } + e->normal.enc.utf8Convert = unknown_toUtf8; + e->normal.enc.utf16Convert = unknown_toUtf16; + return &(e->normal.enc); +} + +/* If this enumeration is changed, getEncodingIndex and encodings +must also be changed. */ +enum { + UNKNOWN_ENC = -1, + ISO_8859_1_ENC = 0, + US_ASCII_ENC, + UTF_8_ENC, + UTF_16_ENC, + UTF_16BE_ENC, + UTF_16LE_ENC, + /* must match encodingNames up to here */ + NO_ENC +}; + +static const char KW_ISO_8859_1[] + = {ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, + ASCII_5, ASCII_9, ASCII_MINUS, ASCII_1, '\0'}; +static const char KW_US_ASCII[] + = {ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, + ASCII_C, ASCII_I, ASCII_I, '\0'}; +static const char KW_UTF_8[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0'}; +static const char KW_UTF_16[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0'}; +static const char KW_UTF_16BE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_B, ASCII_E, '\0'}; +static const char KW_UTF_16LE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_L, ASCII_E, '\0'}; + +static int FASTCALL +getEncodingIndex(const char *name) { + static const char *const encodingNames[] = { + KW_ISO_8859_1, KW_US_ASCII, KW_UTF_8, KW_UTF_16, KW_UTF_16BE, KW_UTF_16LE, + }; + int i; + if (name == NULL) + return NO_ENC; + for (i = 0; i < (int)(sizeof(encodingNames) / sizeof(encodingNames[0])); i++) + if (streqci(name, encodingNames[i])) + return i; + return UNKNOWN_ENC; +} + +/* For binary compatibility, we store the index of the encoding + specified at initialization in the isUtf16 member. +*/ + +#define INIT_ENC_INDEX(enc) ((int)(enc)->initEnc.isUtf16) +#define SET_INIT_ENC_INDEX(enc, i) ((enc)->initEnc.isUtf16 = (char)i) + +/* This is what detects the encoding. encodingTable maps from + encoding indices to encodings; INIT_ENC_INDEX(enc) is the index of + the external (protocol) specified encoding; state is + XML_CONTENT_STATE if we're parsing an external text entity, and + XML_PROLOG_STATE otherwise. +*/ + +static int +initScan(const ENCODING *const *encodingTable, const INIT_ENCODING *enc, + int state, const char *ptr, const char *end, const char **nextTokPtr) { + const ENCODING **encPtr; + + if (ptr >= end) + return XML_TOK_NONE; + encPtr = enc->encPtr; + if (ptr + 1 == end) { + /* only a single byte available for auto-detection */ +#ifndef XML_DTD /* FIXME */ + /* a well-formed document entity must have more than one byte */ + if (state != XML_CONTENT_STATE) + return XML_TOK_PARTIAL; +#endif + /* so we're parsing an external text entity... */ + /* if UTF-16 was externally specified, then we need at least 2 bytes */ + switch (INIT_ENC_INDEX(enc)) { + case UTF_16_ENC: + case UTF_16LE_ENC: + case UTF_16BE_ENC: + return XML_TOK_PARTIAL; + } + switch ((unsigned char)*ptr) { + case 0xFE: + case 0xFF: + case 0xEF: /* possibly first byte of UTF-8 BOM */ + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) + break; + /* fall through */ + case 0x00: + case 0x3C: + return XML_TOK_PARTIAL; + } + } else { + switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) { + case 0xFEFF: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XML_TOK_BOM; + /* 00 3C is handled in the default case */ + case 0x3C00: + if ((INIT_ENC_INDEX(enc) == UTF_16BE_ENC + || INIT_ENC_INDEX(enc) == UTF_16_ENC) + && state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + case 0xFFFE: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XML_TOK_BOM; + case 0xEFBB: + /* Maybe a UTF-8 BOM (EF BB BF) */ + /* If there's an explicitly specified (external) encoding + of ISO-8859-1 or some flavour of UTF-16 + and this is an external text entity, + don't look for the BOM, + because it might be a legal data. + */ + if (state == XML_CONTENT_STATE) { + int e = INIT_ENC_INDEX(enc); + if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC || e == UTF_16LE_ENC + || e == UTF_16_ENC) + break; + } + if (ptr + 2 == end) + return XML_TOK_PARTIAL; + if ((unsigned char)ptr[2] == 0xBF) { + *nextTokPtr = ptr + 3; + *encPtr = encodingTable[UTF_8_ENC]; + return XML_TOK_BOM; + } + break; + default: + if (ptr[0] == '\0') { + /* 0 isn't a legal data character. Furthermore a document + entity can only start with ASCII characters. So the only + way this can fail to be big-endian UTF-16 if it it's an + external parsed general entity that's labelled as + UTF-16LE. + */ + if (state == XML_CONTENT_STATE && INIT_ENC_INDEX(enc) == UTF_16LE_ENC) + break; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } else if (ptr[1] == '\0') { + /* We could recover here in the case: + - parsing an external entity + - second byte is 0 + - no externally specified encoding + - no encoding declaration + by assuming UTF-16LE. But we don't, because this would mean when + presented just with a single byte, we couldn't reliably determine + whether we needed further bytes. + */ + if (state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } + break; + } + } + *encPtr = encodingTable[INIT_ENC_INDEX(enc)]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); +} + +#define NS(x) x +#define ns(x) x +#define XML_TOK_NS_C +#include "xmltok_ns.c" +#undef XML_TOK_NS_C +#undef NS +#undef ns + +#ifdef XML_NS + +# define NS(x) x##NS +# define ns(x) x##_ns + +# define XML_TOK_NS_C +# include "xmltok_ns.c" +# undef XML_TOK_NS_C + +# undef NS +# undef ns + +ENCODING * +XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData) { + ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData); + if (enc) + ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON; + return enc; +} + +#endif /* XML_NS */ diff --git a/Utilities/cmexpat/lib/xmltok.h b/Utilities/cmexpat/lib/xmltok.h new file mode 100644 index 0000000000..6f630c2f9b --- /dev/null +++ b/Utilities/cmexpat/lib/xmltok.h @@ -0,0 +1,319 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2005 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2017 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifndef XmlTok_INCLUDED +#define XmlTok_INCLUDED 1 + +#ifdef __cplusplus +extern "C" { +#endif + +/* The following token may be returned by XmlContentTok */ +#define XML_TOK_TRAILING_RSQB \ + -5 /* ] or ]] at the end of the scan; might be \ + start of illegal ]]> sequence */ +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_NONE -4 /* The string to be scanned is empty */ +#define XML_TOK_TRAILING_CR \ + -3 /* A CR at the end of the scan; \ + might be part of CRLF sequence */ +#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ +#define XML_TOK_PARTIAL -1 /* only part of a token */ +#define XML_TOK_INVALID 0 + +/* The following tokens are returned by XmlContentTok; some are also + returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok. +*/ +#define XML_TOK_START_TAG_WITH_ATTS 1 +#define XML_TOK_START_TAG_NO_ATTS 2 +#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */ +#define XML_TOK_EMPTY_ELEMENT_NO_ATTS 4 +#define XML_TOK_END_TAG 5 +#define XML_TOK_DATA_CHARS 6 +#define XML_TOK_DATA_NEWLINE 7 +#define XML_TOK_CDATA_SECT_OPEN 8 +#define XML_TOK_ENTITY_REF 9 +#define XML_TOK_CHAR_REF 10 /* numeric character reference */ + +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_PI 11 /* processing instruction */ +#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ +#define XML_TOK_COMMENT 13 +#define XML_TOK_BOM 14 /* Byte order mark */ + +/* The following tokens are returned only by XmlPrologTok */ +#define XML_TOK_PROLOG_S 15 +#define XML_TOK_DECL_OPEN 16 /* <!foo */ +#define XML_TOK_DECL_CLOSE 17 /* > */ +#define XML_TOK_NAME 18 +#define XML_TOK_NMTOKEN 19 +#define XML_TOK_POUND_NAME 20 /* #name */ +#define XML_TOK_OR 21 /* | */ +#define XML_TOK_PERCENT 22 +#define XML_TOK_OPEN_PAREN 23 +#define XML_TOK_CLOSE_PAREN 24 +#define XML_TOK_OPEN_BRACKET 25 +#define XML_TOK_CLOSE_BRACKET 26 +#define XML_TOK_LITERAL 27 +#define XML_TOK_PARAM_ENTITY_REF 28 +#define XML_TOK_INSTANCE_START 29 + +/* The following occur only in element type declarations */ +#define XML_TOK_NAME_QUESTION 30 /* name? */ +#define XML_TOK_NAME_ASTERISK 31 /* name* */ +#define XML_TOK_NAME_PLUS 32 /* name+ */ +#define XML_TOK_COND_SECT_OPEN 33 /* <![ */ +#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */ +#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ +#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ +#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ +#define XML_TOK_COMMA 38 + +/* The following token is returned only by XmlAttributeValueTok */ +#define XML_TOK_ATTRIBUTE_VALUE_S 39 + +/* The following token is returned only by XmlCdataSectionTok */ +#define XML_TOK_CDATA_SECT_CLOSE 40 + +/* With namespace processing this is returned by XmlPrologTok for a + name with a colon. +*/ +#define XML_TOK_PREFIXED_NAME 41 + +#ifdef XML_DTD +# define XML_TOK_IGNORE_SECT 42 +#endif /* XML_DTD */ + +#ifdef XML_DTD +# define XML_N_STATES 4 +#else /* not XML_DTD */ +# define XML_N_STATES 3 +#endif /* not XML_DTD */ + +#define XML_PROLOG_STATE 0 +#define XML_CONTENT_STATE 1 +#define XML_CDATA_SECTION_STATE 2 +#ifdef XML_DTD +# define XML_IGNORE_SECTION_STATE 3 +#endif /* XML_DTD */ + +#define XML_N_LITERAL_TYPES 2 +#define XML_ATTRIBUTE_VALUE_LITERAL 0 +#define XML_ENTITY_VALUE_LITERAL 1 + +/* The size of the buffer passed to XmlUtf8Encode must be at least this. */ +#define XML_UTF8_ENCODE_MAX 4 +/* The size of the buffer passed to XmlUtf16Encode must be at least this. */ +#define XML_UTF16_ENCODE_MAX 2 + +typedef struct position { + /* first line and first column are 0 not 1 */ + XML_Size lineNumber; + XML_Size columnNumber; +} POSITION; + +typedef struct { + const char *name; + const char *valuePtr; + const char *valueEnd; + char normalized; +} ATTRIBUTE; + +struct encoding; +typedef struct encoding ENCODING; + +typedef int(PTRCALL *SCANNER)(const ENCODING *, const char *, const char *, + const char **); + +enum XML_Convert_Result { + XML_CONVERT_COMPLETED = 0, + XML_CONVERT_INPUT_INCOMPLETE = 1, + XML_CONVERT_OUTPUT_EXHAUSTED + = 2 /* and therefore potentially input remaining as well */ +}; + +struct encoding { + SCANNER scanners[XML_N_STATES]; + SCANNER literalScanners[XML_N_LITERAL_TYPES]; + int(PTRCALL *nameMatchesAscii)(const ENCODING *, const char *, const char *, + const char *); + int(PTRFASTCALL *nameLength)(const ENCODING *, const char *); + const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *); + int(PTRCALL *getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts); + int(PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); + int(PTRCALL *predefinedEntityName)(const ENCODING *, const char *, + const char *); + void(PTRCALL *updatePosition)(const ENCODING *, const char *ptr, + const char *end, POSITION *); + int(PTRCALL *isPublicId)(const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr); + enum XML_Convert_Result(PTRCALL *utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, char **toP, + const char *toLim); + enum XML_Convert_Result(PTRCALL *utf16Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + unsigned short **toP, + const unsigned short *toLim); + int minBytesPerChar; + char isUtf8; + char isUtf16; +}; + +/* Scan the string starting at ptr until the end of the next complete + token, but do not scan past eptr. Return an integer giving the + type of token. + + Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set. + + Return XML_TOK_PARTIAL when the string does not contain a complete + token; nextTokPtr will not be set. + + Return XML_TOK_INVALID when the string does not start a valid + token; nextTokPtr will be set to point to the character which made + the token invalid. + + Otherwise the string starts with a valid token; nextTokPtr will be + set to point to the character following the end of that token. + + Each data character counts as a single token, but adjacent data + characters may be returned together. Similarly for characters in + the prolog outside literals, comments and processing instructions. +*/ + +#define XmlTok(enc, state, ptr, end, nextTokPtr) \ + (((enc)->scanners[state])(enc, ptr, end, nextTokPtr)) + +#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) + +#define XmlContentTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) + +#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) + +#ifdef XML_DTD + +# define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) + +#endif /* XML_DTD */ + +/* This is used for performing a 2nd-level tokenization on the content + of a literal that has already been returned by XmlTok. +*/ +#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ + (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr)) + +#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ + (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2)) + +#define XmlNameLength(enc, ptr) (((enc)->nameLength)(enc, ptr)) + +#define XmlSkipS(enc, ptr) (((enc)->skipS)(enc, ptr)) + +#define XmlGetAttributes(enc, ptr, attsMax, atts) \ + (((enc)->getAtts)(enc, ptr, attsMax, atts)) + +#define XmlCharRefNumber(enc, ptr) (((enc)->charRefNumber)(enc, ptr)) + +#define XmlPredefinedEntityName(enc, ptr, end) \ + (((enc)->predefinedEntityName)(enc, ptr, end)) + +#define XmlUpdatePosition(enc, ptr, end, pos) \ + (((enc)->updatePosition)(enc, ptr, end, pos)) + +#define XmlIsPublicId(enc, ptr, end, badPtr) \ + (((enc)->isPublicId)(enc, ptr, end, badPtr)) + +#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim)) + +#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim)) + +typedef struct { + ENCODING initEnc; + const ENCODING **encPtr; +} INIT_ENCODING; + +int XmlParseXmlDecl(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, int *standalonePtr); + +int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncoding(void); +const ENCODING *XmlGetUtf16InternalEncoding(void); +int FASTCALL XmlUtf8Encode(int charNumber, char *buf); +int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf); +int XmlSizeOfUnknownEncoding(void); + +typedef int(XMLCALL *CONVERTER)(void *userData, const char *p); + +ENCODING *XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData); + +int XmlParseXmlDeclNS(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, int *standalonePtr); + +int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncodingNS(void); +const ENCODING *XmlGetUtf16InternalEncodingNS(void); +ENCODING *XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData); +#ifdef __cplusplus +} +#endif + +#endif /* not XmlTok_INCLUDED */ diff --git a/Utilities/cmexpat/lib/xmltok_impl.c b/Utilities/cmexpat/lib/xmltok_impl.c new file mode 100644 index 0000000000..4072b06497 --- /dev/null +++ b/Utilities/cmexpat/lib/xmltok_impl.c @@ -0,0 +1,1817 @@ +/* This file is included (from xmltok.c, 1-3 times depending on XML_MIN_SIZE)! + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2016-2022 Sebastian Pipping <sebastian@pipping.org> + Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> + Copyright (c) 2018 Benjamin Peterson <benjamin@python.org> + Copyright (c) 2018 Anton Maklakov <antmak.pub@gmail.com> + Copyright (c) 2019 David Loffredo <loffredo@steptools.com> + Copyright (c) 2020 Boris Kolpackov <boris@codesynthesis.com> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifdef XML_TOK_IMPL_C + +# ifndef IS_INVALID_CHAR // i.e. for UTF-16 and XML_MIN_SIZE not defined +# define IS_INVALID_CHAR(enc, ptr, n) (0) +# endif + +# define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +# define INVALID_CASES(ptr, nextTokPtr) \ + INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ + case BT_NONXML: \ + case BT_MALFORM: \ + case BT_TRAIL: \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; + +# define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NAME_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +# define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NAME_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + case BT_DIGIT: \ + case BT_NAME: \ + case BT_MINUS: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) + +# define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n) || ! IS_NMSTRT_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +# define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) + +# ifndef PREFIX +# define PREFIX(ident) ident +# endif + +# define HAS_CHARS(enc, ptr, end, count) (end - ptr >= count * MINBPC(enc)) + +# define HAS_CHAR(enc, ptr, end) HAS_CHARS(enc, ptr, end, 1) + +# define REQUIRE_CHARS(enc, ptr, end, count) \ + { \ + if (! HAS_CHARS(enc, ptr, end, count)) { \ + return XML_TOK_PARTIAL; \ + } \ + } + +# define REQUIRE_CHAR(enc, ptr, end) REQUIRE_CHARS(enc, ptr, end, 1) + +/* ptr points to character following "<!-" */ + +static int PTRCALL +PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + if (HAS_CHAR(enc, ptr, end)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_MINUS: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMENT; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<!" */ + +static int PTRCALL +PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COND_SECT_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_PERCNT: + REQUIRE_CHARS(enc, ptr, end, 2); + /* don't allow <!ENTITY% foo "whatever"> */ + switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) { + case BT_S: + case BT_CR: + case BT_LF: + case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* fall through */ + case BT_S: + case BT_CR: + case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DECL_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, + int *tokPtr) { + int upper = 0; + UNUSED_P(enc); + *tokPtr = XML_TOK_PI; + if (end - ptr != MINBPC(enc) * 3) + return 1; + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_x: + break; + case ASCII_X: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_m: + break; + case ASCII_M: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + break; + case ASCII_L: + upper = 1; + break; + default: + return 1; + } + if (upper) + return 0; + *tokPtr = XML_TOK_XML_DECL; + return 1; +} + +/* ptr points to character following "<?" */ + +static int PTRCALL +PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + int tok; + const char *target = ptr; + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_CR: + case BT_LF: + if (! PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUEST: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; + case BT_QUEST: + if (! PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + static const char CDATA_LSQB[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, ASCII_LSQB}; + int i; + UNUSED_P(enc); + /* CDATA[ */ + REQUIRE_CHARS(enc, ptr, end, 6); + for (i = 0; i < 6; i++, ptr += MINBPC(enc)) { + if (! CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + *nextTokPtr = ptr; + return XML_TOK_CDATA_SECT_OPEN; +} + +static int PTRCALL +PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + if (ptr >= end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_RSQB: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CDATA_SECT_CLOSE; + case BT_CR: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + case BT_RSQB: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "</" */ + +static int PTRCALL +PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_CR: + case BT_LF: + for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + break; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +# ifdef XML_NS + case BT_COLON: + /* no need to check qname syntax here, + since end-tag must match exactly */ + ptr += MINBPC(enc); + break; +# endif + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#X" */ + +static int PTRCALL +PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + if (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#" */ + +static int PTRCALL +PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + if (HAS_CHAR(enc, ptr, end)) { + if (CHAR_MATCHES(enc, ptr, ASCII_x)) + return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&" */ + +static int PTRCALL +PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_NUM: + return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following first character of attribute name */ + +static int PTRCALL +PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { +# ifdef XML_NS + int hadColon = 0; +# endif + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +# ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +# endif + case BT_S: + case BT_CR: + case BT_LF: + for (;;) { + int t; + + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + t = BYTE_TYPE(enc, ptr); + if (t == BT_EQUALS) + break; + switch (t) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + /* fall through */ + case BT_EQUALS: { + int open; +# ifdef XML_NS + hadColon = 0; +# endif + for (;;) { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + open = BYTE_TYPE(enc, ptr); + if (open == BT_QUOT || open == BT_APOS) + break; + switch (open) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + ptr += MINBPC(enc); + /* in attribute value */ + for (;;) { + int t; + REQUIRE_CHAR(enc, ptr, end); + t = BYTE_TYPE(enc, ptr); + if (t == open) + break; + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_AMP: { + int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr); + if (tok <= 0) { + if (tok == XML_TOK_INVALID) + *nextTokPtr = ptr; + return tok; + } + break; + } + case BT_LT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + default: + ptr += MINBPC(enc); + break; + } + } + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + break; + case BT_SOL: + goto sol; + case BT_GT: + goto gt; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* ptr points to closing quote */ + for (;;) { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_CR: + case BT_LF: + continue; + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_WITH_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; + } + break; + } + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<" */ + +static int PTRCALL +PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { +# ifdef XML_NS + int hadColon; +# endif + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_EXCL: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), end, nextTokPtr); + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_SOL: + return PREFIX(scanEndTag)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } +# ifdef XML_NS + hadColon = 0; +# endif + /* we have a start-tag */ + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +# ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +# endif + case BT_S: + case BT_CR: + case BT_LF: { + ptr += MINBPC(enc); + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + goto gt; + case BT_SOL: + goto sol; + case BT_S: + case BT_CR: + case BT_LF: + ptr += MINBPC(enc); + continue; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr); + } + return XML_TOK_PARTIAL; + } + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_NO_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_NO_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + if (ptr >= end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_LT: + return PREFIX(scanLt)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_AMP: + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_CR: + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + case BT_RSQB: + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return XML_TOK_TRAILING_RSQB; + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return XML_TOK_TRAILING_RSQB; + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_RSQB: + if (HAS_CHARS(enc, ptr, end, 2)) { + if (! CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { + ptr += MINBPC(enc); + break; + } + if (HAS_CHARS(enc, ptr, end, 3)) { + if (! CHAR_MATCHES(enc, ptr + 2 * MINBPC(enc), ASCII_GT)) { + ptr += MINBPC(enc); + break; + } + *nextTokPtr = ptr + 2 * MINBPC(enc); + return XML_TOK_INVALID; + } + } + /* fall through */ + case BT_AMP: + case BT_LT: + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "%" */ + +static int PTRCALL +PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_LF: + case BT_CR: + case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_PERCENT; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_PARAM_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_CR: + case BT_LF: + case BT_S: + case BT_RPAR: + case BT_GT: + case BT_PERCNT: + case BT_VERBAR: + *nextTokPtr = ptr; + return XML_TOK_POUND_NAME; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -XML_TOK_POUND_NAME; +} + +static int PTRCALL +PREFIX(scanLit)(int open, const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + while (HAS_CHAR(enc, ptr, end)) { + int t = BYTE_TYPE(enc, ptr); + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUOT: + case BT_APOS: + ptr += MINBPC(enc); + if (t != open) + break; + if (! HAS_CHAR(enc, ptr, end)) + return -XML_TOK_LITERAL; + *nextTokPtr = ptr; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + case BT_GT: + case BT_PERCNT: + case BT_LSQB: + return XML_TOK_LITERAL; + default: + return XML_TOK_INVALID; + } + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + int tok; + if (ptr >= end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_QUOT: + return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_APOS: + return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LT: { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_EXCL: + return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_NMSTRT: + case BT_HEX: + case BT_NONASCII: + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + *nextTokPtr = ptr - MINBPC(enc); + return XML_TOK_INSTANCE_START; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + case BT_CR: + if (ptr + MINBPC(enc) == end) { + *nextTokPtr = end; + /* indicate that this might be part of a CR/LF pair */ + return -XML_TOK_PROLOG_S; + } + /* fall through */ + case BT_S: + case BT_LF: + for (;;) { + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + break; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_LF: + break; + case BT_CR: + /* don't split CR/LF pair */ + if (ptr + MINBPC(enc) != end) + break; + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + } + } + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + case BT_PERCNT: + return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_COMMA: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMA; + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_BRACKET; + case BT_RSQB: + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return -XML_TOK_CLOSE_BRACKET; + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + REQUIRE_CHARS(enc, ptr, end, 2); + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) { + *nextTokPtr = ptr + 2 * MINBPC(enc); + return XML_TOK_COND_SECT_CLOSE; + } + } + *nextTokPtr = ptr; + return XML_TOK_CLOSE_BRACKET; + case BT_LPAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_PAREN; + case BT_RPAR: + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return -XML_TOK_CLOSE_PAREN; + switch (BYTE_TYPE(enc, ptr)) { + case BT_AST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_ASTERISK; + case BT_QUEST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_QUESTION; + case BT_PLUS: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_PLUS; + case BT_CR: + case BT_LF: + case BT_S: + case BT_GT: + case BT_COMMA: + case BT_VERBAR: + case BT_RPAR: + *nextTokPtr = ptr; + return XML_TOK_CLOSE_PAREN; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_VERBAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OR; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DECL_CLOSE; + case BT_NUM: + return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr); +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NAME; \ + break; \ + } \ + if (IS_NAME_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NMTOKEN; \ + break; \ + } \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_NMSTRT: + case BT_HEX: + tok = XML_TOK_NAME; + ptr += MINBPC(enc); + break; + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: +# ifdef XML_NS + case BT_COLON: +# endif + tok = XML_TOK_NMTOKEN; + ptr += MINBPC(enc); + break; + case BT_NONASCII: + if (IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NAME; + break; + } + if (IS_NAME_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NMTOKEN; + break; + } + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + case BT_RPAR: + case BT_COMMA: + case BT_VERBAR: + case BT_LSQB: + case BT_PERCNT: + case BT_S: + case BT_CR: + case BT_LF: + *nextTokPtr = ptr; + return tok; +# ifdef XML_NS + case BT_COLON: + ptr += MINBPC(enc); + switch (tok) { + case XML_TOK_NAME: + REQUIRE_CHAR(enc, ptr, end); + tok = XML_TOK_PREFIXED_NAME; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + default: + tok = XML_TOK_NMTOKEN; + break; + } + break; + case XML_TOK_PREFIXED_NAME: + tok = XML_TOK_NMTOKEN; + break; + } + break; +# endif + case BT_PLUS: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_PLUS; + case BT_AST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_ASTERISK; + case BT_QUEST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_QUESTION; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -tok; +} + +static int PTRCALL +PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + const char *start; + if (ptr >= end) + return XML_TOK_NONE; + else if (! HAS_CHAR(enc, ptr, end)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the paranoia + * check is still valuable, however. + */ + return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */ + } + start = ptr; + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LT: + /* this is for inside entity references */ + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_S: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ATTRIBUTE_VALUE_S; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +static int PTRCALL +PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + const char *start; + if (ptr >= end) + return XML_TOK_NONE; + else if (! HAS_CHAR(enc, ptr, end)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the paranoia + * check is still valuable, however. + */ + return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */ + } + start = ptr; + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_PERCNT: + if (ptr == start) { + int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); + return (tok == XML_TOK_PERCENT) ? XML_TOK_INVALID : tok; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (! HAS_CHAR(enc, ptr, end)) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +# ifdef XML_DTD + +static int PTRCALL +PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + int level = 0; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + end = ptr + n; + } + } + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_LT: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_EXCL)) { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_LSQB)) { + ++level; + ptr += MINBPC(enc); + } + } + break; + case BT_RSQB: + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr += MINBPC(enc); + if (level == 0) { + *nextTokPtr = ptr; + return XML_TOK_IGNORE_SECT; + } + --level; + } + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +# endif /* XML_DTD */ + +static int PTRCALL +PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, + const char **badPtr) { + ptr += MINBPC(enc); + end -= MINBPC(enc); + for (; HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + case BT_MINUS: + case BT_APOS: + case BT_LPAR: + case BT_RPAR: + case BT_PLUS: + case BT_COMMA: + case BT_SOL: + case BT_EQUALS: + case BT_QUEST: + case BT_CR: + case BT_LF: + case BT_SEMI: + case BT_EXCL: + case BT_AST: + case BT_PERCNT: + case BT_NUM: +# ifdef XML_NS + case BT_COLON: +# endif + break; + case BT_S: + if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) { + *badPtr = ptr; + return 0; + } + break; + case BT_NAME: + case BT_NMSTRT: + if (! (BYTE_TO_ASCII(enc, ptr) & ~0x7f)) + break; + /* fall through */ + default: + switch (BYTE_TO_ASCII(enc, ptr)) { + case 0x24: /* $ */ + case 0x40: /* @ */ + break; + default: + *badPtr = ptr; + return 0; + } + break; + } + } + return 1; +} + +/* This must only be called for a well-formed start-tag or empty + element tag. Returns the number of attributes. Pointers to the + first attsMax attributes are stored in atts. +*/ + +static int PTRCALL +PREFIX(getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts) { + enum { other, inName, inValue } state = inName; + int nAtts = 0; + int open = 0; /* defined when state == inValue; + initialization just to shut up compilers */ + + for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { +# define START_NAME \ + if (state == other) { \ + if (nAtts < attsMax) { \ + atts[nAtts].name = ptr; \ + atts[nAtts].normalized = 1; \ + } \ + state = inName; \ + } +# define LEAD_CASE(n) \ + case BT_LEAD##n: /* NOTE: The encoding has already been validated. */ \ + START_NAME ptr += (n - MINBPC(enc)); \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: + case BT_HEX: + START_NAME + break; +# undef START_NAME + case BT_QUOT: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_QUOT; + } else if (open == BT_QUOT) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_APOS: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_APOS; + } else if (open == BT_APOS) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_AMP: + if (nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_S: + if (state == inName) + state = other; + else if (state == inValue && nAtts < attsMax && atts[nAtts].normalized + && (ptr == atts[nAtts].valuePtr + || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE + || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE + || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open)) + atts[nAtts].normalized = 0; + break; + case BT_CR: + case BT_LF: + /* This case ensures that the first attribute name is counted + Apart from that we could just change state on the quote. */ + if (state == inName) + state = other; + else if (state == inValue && nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_GT: + case BT_SOL: + if (state != inValue) + return nAtts; + break; + default: + break; + } + } + /* not reached */ +} + +static int PTRFASTCALL +PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) { + int result = 0; + /* skip &# */ + UNUSED_P(enc); + ptr += 2 * MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_x)) { + for (ptr += MINBPC(enc); ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); + ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + switch (c) { + case ASCII_0: + case ASCII_1: + case ASCII_2: + case ASCII_3: + case ASCII_4: + case ASCII_5: + case ASCII_6: + case ASCII_7: + case ASCII_8: + case ASCII_9: + result <<= 4; + result |= (c - ASCII_0); + break; + case ASCII_A: + case ASCII_B: + case ASCII_C: + case ASCII_D: + case ASCII_E: + case ASCII_F: + result <<= 4; + result += 10 + (c - ASCII_A); + break; + case ASCII_a: + case ASCII_b: + case ASCII_c: + case ASCII_d: + case ASCII_e: + case ASCII_f: + result <<= 4; + result += 10 + (c - ASCII_a); + break; + } + if (result >= 0x110000) + return -1; + } + } else { + for (; ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + result *= 10; + result += (c - ASCII_0); + if (result >= 0x110000) + return -1; + } + } + return checkCharRefNumber(result); +} + +static int PTRCALL +PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, + const char *end) { + UNUSED_P(enc); + switch ((end - ptr) / MINBPC(enc)) { + case 2: + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) { + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + return ASCII_LT; + case ASCII_g: + return ASCII_GT; + } + } + break; + case 3: + if (CHAR_MATCHES(enc, ptr, ASCII_a)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_m)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) + return ASCII_AMP; + } + } + break; + case 4: + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_q: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_u)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_t)) + return ASCII_QUOT; + } + } + break; + case ASCII_a: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_s)) + return ASCII_APOS; + } + } + break; + } + } + return 0; +} + +static int PTRCALL +PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, + const char *end1, const char *ptr2) { + UNUSED_P(enc); + for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { + if (end1 - ptr1 < MINBPC(enc)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the + * paranoia check is still valuable, however. + */ + return 0; /* LCOV_EXCL_LINE */ + } + if (! CHAR_MATCHES(enc, ptr1, *ptr2)) + return 0; + } + return ptr1 == end1; +} + +static int PTRFASTCALL +PREFIX(nameLength)(const ENCODING *enc, const char *ptr) { + const char *start = ptr; + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: +# ifdef XML_NS + case BT_COLON: +# endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + ptr += MINBPC(enc); + break; + default: + return (int)(ptr - start); + } + } +} + +static const char *PTRFASTCALL +PREFIX(skipS)(const ENCODING *enc, const char *ptr) { + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_LF: + case BT_CR: + case BT_S: + ptr += MINBPC(enc); + break; + default: + return ptr; + } + } +} + +static void PTRCALL +PREFIX(updatePosition)(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; /* NOTE: The encoding has already been validated. */ \ + pos->columnNumber++; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE + case BT_LF: + pos->columnNumber = 0; + pos->lineNumber++; + ptr += MINBPC(enc); + break; + case BT_CR: + pos->lineNumber++; + ptr += MINBPC(enc); + if (HAS_CHAR(enc, ptr, end) && BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + pos->columnNumber = 0; + break; + default: + ptr += MINBPC(enc); + pos->columnNumber++; + break; + } + } +} + +# undef DO_LEAD_CASE +# undef MULTIBYTE_CASES +# undef INVALID_CASES +# undef CHECK_NAME_CASE +# undef CHECK_NAME_CASES +# undef CHECK_NMSTRT_CASE +# undef CHECK_NMSTRT_CASES + +#endif /* XML_TOK_IMPL_C */ diff --git a/Utilities/cmexpat/lib/xmltok_impl.h b/Utilities/cmexpat/lib/xmltok_impl.h new file mode 100644 index 0000000000..c518aada01 --- /dev/null +++ b/Utilities/cmexpat/lib/xmltok_impl.h @@ -0,0 +1,74 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2017-2019 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +enum { + BT_NONXML, /* e.g. noncharacter-FFFF */ + BT_MALFORM, /* illegal, with regard to encoding */ + BT_LT, /* less than = "<" */ + BT_AMP, /* ampersand = "&" */ + BT_RSQB, /* right square bracket = "[" */ + BT_LEAD2, /* lead byte of a 2-byte UTF-8 character */ + BT_LEAD3, /* lead byte of a 3-byte UTF-8 character */ + BT_LEAD4, /* lead byte of a 4-byte UTF-8 character */ + BT_TRAIL, /* trailing unit, e.g. second 16-bit unit of a 4-byte char. */ + BT_CR, /* carriage return = "\r" */ + BT_LF, /* line feed = "\n" */ + BT_GT, /* greater than = ">" */ + BT_QUOT, /* quotation character = "\"" */ + BT_APOS, /* aposthrophe = "'" */ + BT_EQUALS, /* equal sign = "=" */ + BT_QUEST, /* question mark = "?" */ + BT_EXCL, /* exclamation mark = "!" */ + BT_SOL, /* solidus, slash = "/" */ + BT_SEMI, /* semicolon = ";" */ + BT_NUM, /* number sign = "#" */ + BT_LSQB, /* left square bracket = "[" */ + BT_S, /* white space, e.g. "\t", " "[, "\r"] */ + BT_NMSTRT, /* non-hex name start letter = "G".."Z" + "g".."z" + "_" */ + BT_COLON, /* colon = ":" */ + BT_HEX, /* hex letter = "A".."F" + "a".."f" */ + BT_DIGIT, /* digit = "0".."9" */ + BT_NAME, /* dot and middle dot = "." + chr(0xb7) */ + BT_MINUS, /* minus = "-" */ + BT_OTHER, /* known not to be a name or name start character */ + BT_NONASCII, /* might be a name or name start character */ + BT_PERCNT, /* percent sign = "%" */ + BT_LPAR, /* left parenthesis = "(" */ + BT_RPAR, /* right parenthesis = "(" */ + BT_AST, /* asterisk = "*" */ + BT_PLUS, /* plus sign = "+" */ + BT_COMMA, /* comma = "," */ + BT_VERBAR /* vertical bar = "|" */ +}; + +#include <stddef.h> diff --git a/Utilities/cmexpat/lib/xmltok_ns.c b/Utilities/cmexpat/lib/xmltok_ns.c new file mode 100644 index 0000000000..fbdd3e3c7b --- /dev/null +++ b/Utilities/cmexpat/lib/xmltok_ns.c @@ -0,0 +1,122 @@ +/* This file is included! + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> + Copyright (c) 2002 Greg Stein <gstein@users.sourceforge.net> + Copyright (c) 2002 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> + Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net> + Copyright (c) 2017-2021 Sebastian Pipping <sebastian@pipping.org> + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#ifdef XML_TOK_NS_C + +const ENCODING * +NS(XmlGetUtf8InternalEncoding)(void) { + return &ns(internal_utf8_encoding).enc; +} + +const ENCODING * +NS(XmlGetUtf16InternalEncoding)(void) { +# if BYTEORDER == 1234 + return &ns(internal_little2_encoding).enc; +# elif BYTEORDER == 4321 + return &ns(internal_big2_encoding).enc; +# else + const short n = 1; + return (*(const char *)&n ? &ns(internal_little2_encoding).enc + : &ns(internal_big2_encoding).enc); +# endif +} + +static const ENCODING *const NS(encodings)[] = { + &ns(latin1_encoding).enc, &ns(ascii_encoding).enc, + &ns(utf8_encoding).enc, &ns(big2_encoding).enc, + &ns(big2_encoding).enc, &ns(little2_encoding).enc, + &ns(utf8_encoding).enc /* NO_ENC */ +}; + +static int PTRCALL +NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_PROLOG_STATE, + ptr, end, nextTokPtr); +} + +static int PTRCALL +NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_CONTENT_STATE, + ptr, end, nextTokPtr); +} + +int +NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, + const char *name) { + int i = getEncodingIndex(name); + if (i == UNKNOWN_ENC) + return 0; + SET_INIT_ENC_INDEX(p, i); + p->initEnc.scanners[XML_PROLOG_STATE] = NS(initScanProlog); + p->initEnc.scanners[XML_CONTENT_STATE] = NS(initScanContent); + p->initEnc.updatePosition = initUpdatePosition; + p->encPtr = encPtr; + *encPtr = &(p->initEnc); + return 1; +} + +static const ENCODING * +NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) { +# define ENCODING_MAX 128 + char buf[ENCODING_MAX] = ""; + char *p = buf; + int i; + XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1); + if (ptr != end) + return 0; + *p = 0; + if (streqci(buf, KW_UTF_16) && enc->minBytesPerChar == 2) + return enc; + i = getEncodingIndex(buf); + if (i == UNKNOWN_ENC) + return 0; + return NS(encodings)[i]; +} + +int +NS(XmlParseXmlDecl)(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, + const char **encodingName, const ENCODING **encoding, + int *standalone) { + return doParseXmlDecl(NS(findEncoding), isGeneralTextEntity, enc, ptr, end, + badPtr, versionPtr, versionEndPtr, encodingName, + encoding, standalone); +} + +#endif /* XML_TOK_NS_C */ |