summaryrefslogtreecommitdiff
path: root/regex
diff options
context:
space:
mode:
Diffstat (limited to 'regex')
-rw-r--r--regex/CHANGES19
-rw-r--r--regex/CMakeLists.txt21
-rw-r--r--regex/COPYRIGHT20
-rw-r--r--regex/README32
-rw-r--r--regex/WHATSNEW92
-rw-r--r--regex/cclass.h22
-rw-r--r--regex/cname.h104
-rw-r--r--regex/debug.c246
-rw-r--r--regex/debug.ih14
-rw-r--r--regex/engine.c1028
-rw-r--r--regex/engine.ih35
-rw-r--r--regex/main.c509
-rw-r--r--regex/main.ih19
-rw-r--r--regex/my_regex.h88
-rw-r--r--regex/regcomp.c1610
-rw-r--r--regex/regcomp.ih50
-rw-r--r--regex/regerror.c116
-rw-r--r--regex/regerror.ih12
-rw-r--r--regex/regex.3502
-rw-r--r--regex/regex.7233
-rw-r--r--regex/regex2.h143
-rw-r--r--regex/regexec.c140
-rw-r--r--regex/regexp.c1348
-rw-r--r--regex/regfree.c38
-rw-r--r--regex/reginit.c85
-rw-r--r--regex/split.c316
-rw-r--r--regex/tests474
-rw-r--r--regex/utils.h22
28 files changed, 0 insertions, 7338 deletions
diff --git a/regex/CHANGES b/regex/CHANGES
deleted file mode 100644
index 2bd0fb7639f..00000000000
--- a/regex/CHANGES
+++ /dev/null
@@ -1,19 +0,0 @@
-This is an altered distribution of regexp for mysql.
-The follwing changes has been done to use the mysql configuration system and
-ISOLATIN1 characters.
-
-New Makefile
-
-Changed all files to include global.h
-
-Some changes in types to suppress warning errors from gcc.
-
-debug.c ; extra parameter to regchar
-
-Made regex_init & regex_end calls to init & free dynamic cclasses array.
-
-Fixed memory allocation bug in 'matcher'
-
-Changed regcomp.c to use bmove_upp() instead of memmove()
-
-Changed name of function try to rx_try in main.cc for Digitial C compiler.
diff --git a/regex/CMakeLists.txt b/regex/CMakeLists.txt
deleted file mode 100644
index b4a72620ac5..00000000000
--- a/regex/CMakeLists.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# Copyright (c) 2006, 2010, Oracle and/or its affiliates. All rights reserved.
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; version 2 of the License.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-
-INCLUDE_DIRECTORIES(${CMAKE_SOURCE_DIR}/include)
-
-SET(REGEX_SOURCES regcomp.c regerror.c regexec.c regfree.c reginit.c)
-ADD_CONVENIENCE_LIBRARY(regex ${REGEX_SOURCES})
-
-INSTALL(FILES "my_regex.h" DESTINATION ${INSTALL_INCLUDEDIR}/private COMPONENT Development)
diff --git a/regex/COPYRIGHT b/regex/COPYRIGHT
deleted file mode 100644
index d43362fbfc9..00000000000
--- a/regex/COPYRIGHT
+++ /dev/null
@@ -1,20 +0,0 @@
-Copyright 1992, 1993, 1994 Henry Spencer. All rights reserved.
-This software is not subject to any license of the American Telephone
-and Telegraph Company or of the Regents of the University of California.
-
-Permission is granted to anyone to use this software for any purpose on
-any computer system, and to alter it and redistribute it, subject
-to the following restrictions:
-
-1. The author is not responsible for the consequences of use of this
- software, no matter how awful, even if they arise from flaws in it.
-
-2. The origin of this software must not be misrepresented, either by
- explicit claim or by omission. Since few users ever read sources,
- credits must appear in the documentation.
-
-3. Altered versions must be plainly marked as such, and must not be
- misrepresented as being the original software. Since few users
- ever read sources, credits must appear in the documentation.
-
-4. This notice may not be removed or altered.
diff --git a/regex/README b/regex/README
deleted file mode 100644
index cea9b67b666..00000000000
--- a/regex/README
+++ /dev/null
@@ -1,32 +0,0 @@
-alpha3.4 release.
-Thu Mar 17 23:17:18 EST 1994
-henry@zoo.toronto.edu
-
-See WHATSNEW for change listing.
-
-installation notes:
---------
-Read the comments at the beginning of Makefile before running.
-
-Utils.h contains some things that just might have to be modified on
-some systems, as well as a nested include (ugh) of <assert.h>.
-
-The "fake" directory contains quick-and-dirty fakes for some header
-files and routines that old systems may not have. Note also that
--DUSEBCOPY will make utils.h substitute bcopy() for memmove().
-
-After that, "make r" will build regcomp.o, regexec.o, regfree.o,
-and regerror.o (the actual routines), bundle them together into a test
-program, and run regression tests on them. No output is good output.
-
-"make lib" builds just the .o files for the actual routines (when
-you're happy with testing and have adjusted CFLAGS for production),
-and puts them together into libregex.a. You can pick up either the
-library or *.o ("make lib" makes sure there are no other .o files left
-around to confuse things).
-
-Main.c, debug.c, split.c are used for regression testing but are not part
-of the RE routines themselves.
-
-Regex.h goes in /usr/include. All other .h files are internal only.
---------
diff --git a/regex/WHATSNEW b/regex/WHATSNEW
deleted file mode 100644
index 6e82e1dae0c..00000000000
--- a/regex/WHATSNEW
+++ /dev/null
@@ -1,92 +0,0 @@
-New in alpha3.4: The complex bug alluded to below has been fixed (in a
-slightly kludgey temporary way that may hurt efficiency a bit; this is
-another "get it out the door for 4.4" release). The tests at the end of
-the tests file have accordingly been uncommented. The primary sign of
-the bug was that something like a?b matching ab matched b rather than ab.
-(The bug was essentially specific to this exact situation, else it would
-have shown up earlier.)
-
-New in alpha3.3: The definition of word boundaries has been altered
-slightly, to more closely match the usual programming notion that "_"
-is an alphabetic. Stuff used for pre-ANSI systems is now in a subdir,
-and the makefile no longer alludes to it in mysterious ways. The
-makefile has generally been cleaned up some. Fixes have been made
-(again!) so that the regression test will run without -DREDEBUG, at
-the cost of weaker checking. A workaround for a bug in some folks'
-<assert.h> has been added. And some more things have been added to
-tests, including a couple right at the end which are commented out
-because the code currently flunks them (complex bug; fix coming).
-Plus the usual minor cleanup.
-
-New in alpha3.2: Assorted bits of cleanup and portability improvement
-(the development base is now a BSDI system using GCC instead of an ancient
-Sun system, and the newer compiler exposed some glitches). Fix for a
-serious bug that affected REs using many [] (including REG_ICASE REs
-because of the way they are implemented), *sometimes*, depending on
-memory-allocation patterns. The header-file prototypes no longer name
-the parameters, avoiding possible name conflicts. The possibility that
-some clot has defined CHAR_MIN as (say) `-128' instead of `(-128)' is
-now handled gracefully. "uchar" is no longer used as an internal type
-name (too many people have the same idea). Still the same old lousy
-performance, alas.
-
-New in alpha3.1: Basically nothing, this release is just a bookkeeping
-convenience. Stay tuned.
-
-New in alpha3.0: Performance is no better, alas, but some fixes have been
-made and some functionality has been added. (This is basically the "get
-it out the door in time for 4.4" release.) One bug fix: regfree() didn't
-free the main internal structure (how embarrassing). It is now possible
-to put NULs in either the RE or the target string, using (resp.) a new
-REG_PEND flag and the old REG_STARTEND flag. The REG_NOSPEC flag to
-regcomp() makes all characters ordinary, so you can match a literal
-string easily (this will become more useful when performance improves!).
-There are now primitives to match beginnings and ends of words, although
-the syntax is disgusting and so is the implementation. The REG_ATOI
-debugging interface has changed a bit. And there has been considerable
-internal cleanup of various kinds.
-
-New in alpha2.3: Split change list out of README, and moved flags notes
-into Makefile. Macro-ized the name of regex(7) in regex(3), since it has
-to change for 4.4BSD. Cleanup work in engine.c, and some new regression
-tests to catch tricky cases thereof.
-
-New in alpha2.2: Out-of-date manpages updated. Regerror() acquires two
-small extensions -- REG_ITOA and REG_ATOI -- which avoid debugging kludges
-in my own test program and might be useful to others for similar purposes.
-The regression test will now compile (and run) without REDEBUG. The
-BRE \$ bug is fixed. Most uses of "uchar" are gone; it's all chars now.
-Char/uchar parameters are now written int/unsigned, to avoid possible
-portability problems with unpromoted parameters. Some unsigned casts have
-been introduced to minimize portability problems with shifting into sign
-bits.
-
-New in alpha2.1: Lots of little stuff, cleanup and fixes. The one big
-thing is that regex.h is now generated, using mkh, rather than being
-supplied in the distribution; due to circularities in dependencies,
-you have to build regex.h explicitly by "make h". The two known bugs
-have been fixed (and the regression test now checks for them), as has a
-problem with assertions not being suppressed in the absence of REDEBUG.
-No performance work yet.
-
-New in alpha2: Backslash-anything is an ordinary character, not an
-error (except, of course, for the handful of backslashed metacharacters
-in BREs), which should reduce script breakage. The regression test
-checks *where* null strings are supposed to match, and has generally
-been tightened up somewhat. Small bug fixes in parameter passing (not
-harmful, but technically errors) and some other areas. Debugging
-invoked by defining REDEBUG rather than not defining NDEBUG.
-
-New in alpha+3: full prototyping for internal routines, using a little
-helper program, mkh, which extracts prototypes given in stylized comments.
-More minor cleanup. Buglet fix: it's CHAR_BIT, not CHAR_BITS. Simple
-pre-screening of input when a literal string is known to be part of the
-RE; this does wonders for performance.
-
-New in alpha+2: minor bits of cleanup. Notably, the number "32" for the
-word width isn't hardwired into regexec.c any more, the public header
-file prototypes the functions if __STDC__ is defined, and some small typos
-in the manpages have been fixed.
-
-New in alpha+1: improvements to the manual pages, and an important
-extension, the REG_STARTEND option to regexec().
diff --git a/regex/cclass.h b/regex/cclass.h
deleted file mode 100644
index b877b5dee6b..00000000000
--- a/regex/cclass.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* character-class table */
-
-#define CCLASS_ALNUM 0
-#define CCLASS_ALPHA 1
-#define CCLASS_BLANK 2
-#define CCLASS_CNTRL 3
-#define CCLASS_DIGIT 4
-#define CCLASS_GRAPH 5
-#define CCLASS_LOWER 6
-#define CCLASS_PRINT 7
-#define CCLASS_PUNCT 8
-#define CCLASS_SPACE 9
-#define CCLASS_UPPER 10
-#define CCLASS_XDIGIT 11
-#define CCLASS_LAST 12
-
-extern struct cclass {
- const char *name;
- const char *chars;
- const char *multis;
- uint mask;
-} cclasses[];
diff --git a/regex/cname.h b/regex/cname.h
deleted file mode 100644
index 06865f3e102..00000000000
--- a/regex/cname.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/* character-name table */
-static struct cname {
- const char *name;
- const char code;
-} cnames[] = {
- {"NUL", '\0'},
- {"SOH", '\001'},
- {"STX", '\002'},
- {"ETX", '\003'},
- {"EOT", '\004'},
- {"ENQ", '\005'},
- {"ACK", '\006'},
- {"BEL", '\007'},
- {"alert", '\007'},
- {"BS", '\010'},
- {"backspace", '\b'},
- {"HT", '\011'},
- {"tab", '\t'},
- {"LF", '\012'},
- {"newline", '\n'},
- {"VT", '\013'},
- {"vertical-tab",'\v'},
- {"FF", '\014'},
- {"form-feed", '\f'},
- {"CR", '\015'},
- {"carriage-return", '\r'},
- {"SO", '\016'},
- {"SI", '\017'},
- {"DLE", '\020'},
- {"DC1", '\021'},
- {"DC2", '\022'},
- {"DC3", '\023'},
- {"DC4", '\024'},
- {"NAK", '\025'},
- {"SYN", '\026'},
- {"ETB", '\027'},
- {"CAN", '\030'},
- {"EM", '\031'},
- {"SUB", '\032'},
- {"ESC", '\033'},
- {"IS4", '\034'},
- {"FS", '\034'},
- {"IS3", '\035'},
- {"GS", '\035'},
- {"IS2", '\036'},
- {"RS", '\036'},
- {"IS1", '\037'},
- {"US", '\037'},
- {"space", ' '},
- {"exclamation-mark", '!'},
- {"quotation-mark", '"'},
- {"number-sign", '#'},
- {"dollar-sign", '$'},
- {"percent-sign", '%'},
- {"ampersand", '&'},
- {"apostrophe", '\''},
- {"left-parenthesis", '('},
- {"right-parenthesis", ')'},
- {"asterisk", '*'},
- {"plus-sign", '+'},
- {"comma", ','},
- {"hyphen", '-'},
- {"hyphen-minus", '-'},
- {"period", '.'},
- {"full-stop", '.'},
- {"slash", '/'},
- {"solidus", '/'},
- {"zero", '0'},
- {"one", '1'},
- {"two", '2'},
- {"three", '3'},
- {"four", '4'},
- {"five", '5'},
- {"six", '6'},
- {"seven", '7'},
- {"eight", '8'},
- {"nine", '9'},
- {"colon", ':'},
- {"semicolon", ';'},
- {"less-than-sign", '<'},
- {"equals-sign", '='},
- {"greater-than-sign", '>'},
- {"question-mark", '?'},
- {"commercial-at", '@'},
- {"left-square-bracket", '['},
- {"backslash", '\\'},
- {"reverse-solidus", '\\'},
- {"right-square-bracket",']'},
- {"circumflex", '^'},
- {"circumflex-accent", '^'},
- {"underscore", '_'},
- {"low-line", '_'},
- {"grave-accent", '`'},
- {"left-brace", '{'},
- {"left-curly-bracket", '{'},
- {"vertical-line", '|'},
- {"right-brace", '}'},
- {"right-curly-bracket", '}'},
- {"tilde", '~'},
- {"DEL", '\177'},
- {NULL, 0},
-};
-
-
diff --git a/regex/debug.c b/regex/debug.c
deleted file mode 100644
index 271b09bb27a..00000000000
--- a/regex/debug.c
+++ /dev/null
@@ -1,246 +0,0 @@
-#include <my_global.h>
-#include <m_ctype.h>
-#include <m_string.h>
-#include <sys/types.h>
-
-#include "my_regex.h"
-#include "utils.h"
-#include "regex2.h"
-#include "debug.ih"
-
-/* Added extra paramter to regchar to remove static buffer ; Monty 96.11.27 */
-
-/*
- - regprint - print a regexp for debugging
- == void regprint(regex_t *r, FILE *d);
- */
-void
-regprint(r, d)
-my_regex_t *r;
-FILE *d;
-{
- register struct re_guts *g = r->re_g;
- register int i;
- register int c;
- register int last;
- int nincat[NC];
- char buf[10];
-
- fprintf(d, "%ld states, %d categories", (long)g->nstates,
- g->ncategories);
- fprintf(d, ", first %ld last %ld", (long)g->firststate,
- (long)g->laststate);
- if (g->iflags&USEBOL)
- fprintf(d, ", USEBOL");
- if (g->iflags&USEEOL)
- fprintf(d, ", USEEOL");
- if (g->iflags&BAD)
- fprintf(d, ", BAD");
- if (g->nsub > 0)
- fprintf(d, ", nsub=%ld", (long)g->nsub);
- if (g->must != NULL)
- fprintf(d, ", must(%ld) `%*s'", (long)g->mlen, (int)g->mlen,
- g->must);
- if (g->backrefs)
- fprintf(d, ", backrefs");
- if (g->nplus > 0)
- fprintf(d, ", nplus %ld", (long)g->nplus);
- fprintf(d, "\n");
- s_print(r->charset, g, d);
- for (i = 0; i < g->ncategories; i++) {
- nincat[i] = 0;
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (g->categories[c] == i)
- nincat[i]++;
- }
- fprintf(d, "cc0#%d", nincat[0]);
- for (i = 1; i < g->ncategories; i++)
- if (nincat[i] == 1) {
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (g->categories[c] == i)
- break;
- fprintf(d, ", %d=%s", i, regchar(r->charset,c,buf));
- }
- fprintf(d, "\n");
- for (i = 1; i < g->ncategories; i++)
- if (nincat[i] != 1) {
- fprintf(d, "cc%d\t", i);
- last = -1;
- for (c = CHAR_MIN; c <= CHAR_MAX+1; c++) /* +1 does flush */
- if (c <= CHAR_MAX && g->categories[c] == i) {
- if (last < 0) {
- fprintf(d, "%s", regchar(r->charset,c,buf));
- last = c;
- }
- } else {
- if (last >= 0) {
- if (last != c-1)
- fprintf(d, "-%s",
- regchar(r->charset,c-1,buf));
- last = -1;
- }
- }
- fprintf(d, "\n");
- }
-}
-
-/*
- - s_print - print the strip for debugging
- == static void s_print(register struct re_guts *g, FILE *d);
- */
-static void
-s_print(charset, g, d)
-CHARSET_INFO *charset;
-register struct re_guts *g;
-FILE *d;
-{
- register sop *s;
- register cset *cs;
- register int i;
- register int done = 0;
- register sop opnd;
- register int col = 0;
- register int last;
- register sopno offset = 2;
- char buf[10];
-# define GAP() { if (offset % 5 == 0) { \
- if (col > 40) { \
- fprintf(d, "\n\t"); \
- col = 0; \
- } else { \
- fprintf(d, " "); \
- col++; \
- } \
- } else \
- col++; \
- offset++; \
- }
-
- if (OP(g->strip[0]) != OEND)
- fprintf(d, "missing initial OEND!\n");
- for (s = &g->strip[1]; !done; s++) {
- opnd = OPND(*s);
- switch (OP(*s)) {
- case OEND:
- fprintf(d, "\n");
- done = 1;
- break;
- case OCHAR:
- if (strchr("\\|()^$.[+*?{}!<> ", (char)opnd) != NULL)
- fprintf(d, "\\%c", (char)opnd);
- else
- fprintf(d, "%s", regchar(charset,(char)opnd,buf));
- break;
- case OBOL:
- fprintf(d, "^");
- break;
- case OEOL:
- fprintf(d, "$");
- break;
- case OBOW:
- fprintf(d, "\\{");
- break;
- case OEOW:
- fprintf(d, "\\}");
- break;
- case OANY:
- fprintf(d, ".");
- break;
- case OANYOF:
- fprintf(d, "[(%ld)", (long)opnd);
- cs = &g->sets[opnd];
- last = -1;
- for (i = 0; i < g->csetsize+1; i++) /* +1 flushes */
- if (CHIN(cs, i) && i < g->csetsize) {
- if (last < 0) {
- fprintf(d, "%s", regchar(charset,i,buf));
- last = i;
- }
- } else {
- if (last >= 0) {
- if (last != i-1)
- fprintf(d, "-%s",
- regchar(charset,i-1,buf));
- last = -1;
- }
- }
- fprintf(d, "]");
- break;
- case OBACK_:
- fprintf(d, "(\\<%ld>", (long)opnd);
- break;
- case O_BACK:
- fprintf(d, "<%ld>\\)", (long)opnd);
- break;
- case OPLUS_:
- fprintf(d, "(+");
- if (OP(*(s+opnd)) != O_PLUS)
- fprintf(d, "<%ld>", (long)opnd);
- break;
- case O_PLUS:
- if (OP(*(s-opnd)) != OPLUS_)
- fprintf(d, "<%ld>", (long)opnd);
- fprintf(d, "+)");
- break;
- case OQUEST_:
- fprintf(d, "(?");
- if (OP(*(s+opnd)) != O_QUEST)
- fprintf(d, "<%ld>", (long)opnd);
- break;
- case O_QUEST:
- if (OP(*(s-opnd)) != OQUEST_)
- fprintf(d, "<%ld>", (long)opnd);
- fprintf(d, "?)");
- break;
- case OLPAREN:
- fprintf(d, "((<%ld>", (long)opnd);
- break;
- case ORPAREN:
- fprintf(d, "<%ld>))", (long)opnd);
- break;
- case OCH_:
- fprintf(d, "<");
- if (OP(*(s+opnd)) != OOR2)
- fprintf(d, "<%ld>", (long)opnd);
- break;
- case OOR1:
- if (OP(*(s-opnd)) != OOR1 && OP(*(s-opnd)) != OCH_)
- fprintf(d, "<%ld>", (long)opnd);
- fprintf(d, "|");
- break;
- case OOR2:
- fprintf(d, "|");
- if (OP(*(s+opnd)) != OOR2 && OP(*(s+opnd)) != O_CH)
- fprintf(d, "<%ld>", (long)opnd);
- break;
- case O_CH:
- if (OP(*(s-opnd)) != OOR1)
- fprintf(d, "<%ld>", (long)opnd);
- fprintf(d, ">");
- break;
- default:
- fprintf(d, "!%ld(%ld)!", OP(*s), opnd);
- break;
- }
- if (!done)
- GAP();
- }
-}
-
-/*
- - regchar - make a character printable
- == static char *regchar(int ch);
- */
-static char * /* -> representation */
-regchar(charset,ch,buf)
-CHARSET_INFO *charset;
-int ch;
-char *buf;
-{
-
- if (my_isprint(charset,ch) || ch == ' ')
- sprintf(buf, "%c", ch);
- else
- sprintf(buf, "\\%o", ch);
- return(buf);
-}
diff --git a/regex/debug.ih b/regex/debug.ih
deleted file mode 100644
index 1e1fb11177c..00000000000
--- a/regex/debug.ih
+++ /dev/null
@@ -1,14 +0,0 @@
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* === debug.c === */
-void regprint(my_regex_t *r, FILE *d);
-static void s_print(CHARSET_INFO *charset, register struct re_guts *g, FILE *d);
-static char *regchar(CHARSET_INFO *charset, int ch,char *buf);
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
diff --git a/regex/engine.c b/regex/engine.c
deleted file mode 100644
index 5db8df210bd..00000000000
--- a/regex/engine.c
+++ /dev/null
@@ -1,1028 +0,0 @@
-/*
- * The matching engine and friends. This file is #included by regexec.c
- * after suitable #defines of a variety of macros used herein, so that
- * different state representations can be used without duplicating masses
- * of code.
- */
-
-#ifdef SNAMES
-#define matcher smatcher
-#define fast sfast
-#define slow sslow
-#define dissect sdissect
-#define backref sbackref
-#define step sstep
-#define print sprint
-#define at sat
-#define match smat
-#endif
-#ifdef LNAMES
-#define matcher lmatcher
-#define fast lfast
-#define slow lslow
-#define dissect ldissect
-#define backref lbackref
-#define step lstep
-#define print lprint
-#define at lat
-#define match lmat
-#endif
-
-/* another structure passed up and down to avoid zillions of parameters */
-struct match {
- struct re_guts *g;
- int eflags;
- my_regmatch_t *pmatch; /* [nsub+1] (0 element unused) */
- const char *offp; /* offsets work from here */
- const char *beginp; /* start of string -- virtual NUL precedes */
- const char *endp; /* end of string -- virtual NUL here */
- const char *coldp; /* can be no match starting before here */
- const char **lastpos; /* [nplus+1] */
- STATEVARS;
- states st; /* current states */
- states fresh; /* states for a fresh start */
- states tmp; /* temporary */
- states empty; /* empty set of states */
-};
-
-#include "engine.ih"
-
-#ifdef REDEBUG
-#define SP(t, s, c) print(m, t, s, c, stdout)
-#define AT(t, p1, p2, s1, s2) at(m, t, p1, p2, s1, s2)
-#define NOTE(str) { if (m->eflags&REG_TRACE) printf("=%s\n", (str)); }
-#else
-#define SP(t, s, c) /* nothing */
-#define AT(t, p1, p2, s1, s2) /* nothing */
-#define NOTE(s) /* nothing */
-#endif
-
-/*
- - matcher - the actual matching engine
- == static int matcher(register struct re_guts *g, char *string, \
- == size_t nmatch, regmatch_t pmatch[], int eflags);
- */
-static int /* 0 success, REG_NOMATCH failure */
-matcher(charset,g, str, nmatch, pmatch, eflags)
-CHARSET_INFO *charset;
-register struct re_guts *g;
-const char *str;
-size_t nmatch;
-my_regmatch_t pmatch[];
-int eflags;
-{
- register const char *endp;
- register uint i;
- struct match mv;
- register struct match *m = &mv;
- register const char *dp;
- register const sopno gf = g->firststate+1; /* +1 for OEND */
- register const sopno gl = g->laststate;
- const char *start;
- const char *stop;
-
- /* simplify the situation where possible */
- if (g->cflags&REG_NOSUB)
- nmatch = 0;
- if (eflags&REG_STARTEND) {
- start = str + pmatch[0].rm_so;
- stop = str + pmatch[0].rm_eo;
- } else {
- start = str;
- stop = start + strlen(start);
- }
- if (stop < start)
- return(REG_INVARG);
-
- /* prescreening; this does wonders for this rather slow code */
- if (g->must != NULL) {
- for (dp = start; dp < stop; dp++)
- if (*dp == g->must[0] && stop - dp >= g->mlen &&
- memcmp(dp, g->must, (size_t)g->mlen) == 0)
- break;
- if (dp == stop) /* we didn't find g->must */
- return(REG_NOMATCH);
- }
-
- /* match struct setup */
- m->g = g;
- m->eflags = eflags;
- m->pmatch = NULL;
- m->lastpos = NULL;
- m->offp = str;
- m->beginp = start;
- m->endp = stop;
- STATESETUP(m, 4);
- SETUP(m->st);
- SETUP(m->fresh);
- SETUP(m->tmp);
- SETUP(m->empty);
- CLEAR(m->empty);
-
- /* this loop does only one repetition except for backrefs */
- for (;;) {
- endp = fast(charset, m, start, stop, gf, gl);
- if (endp == NULL) { /* a miss */
- if (m->pmatch != NULL)
- free((char *)m->pmatch);
- if (m->lastpos != NULL)
- free((char *)m->lastpos);
- STATETEARDOWN(m);
- return(REG_NOMATCH);
- }
- if (nmatch == 0 && !g->backrefs)
- break; /* no further info needed */
-
- /* where? */
- assert(m->coldp != NULL);
- for (;;) {
- NOTE("finding start");
- endp = slow(charset, m, m->coldp, stop, gf, gl);
- if (endp != NULL)
- break;
- assert(m->coldp < m->endp);
- m->coldp++;
- }
- if (nmatch == 1 && !g->backrefs)
- break; /* no further info needed */
-
- /* oh my, he wants the subexpressions... */
- if (m->pmatch == NULL)
- m->pmatch = (my_regmatch_t *)malloc((m->g->nsub + 1) *
- sizeof(my_regmatch_t));
- if (m->pmatch == NULL) {
- if (m->lastpos != NULL)
- free((char *)m->lastpos);
- STATETEARDOWN(m);
- return(REG_ESPACE);
- }
- for (i = 1; i <= m->g->nsub; i++)
- m->pmatch[i].rm_so = m->pmatch[i].rm_eo = -1;
- if (!g->backrefs && !(m->eflags&REG_BACKR)) {
- NOTE("dissecting");
- dp = dissect(charset, m, m->coldp, endp, gf, gl);
- } else {
- if (g->nplus > 0 && m->lastpos == NULL)
- m->lastpos = (const char **)malloc((g->nplus+1) *
- sizeof(char *));
- if (g->nplus > 0 && m->lastpos == NULL) {
- free(m->pmatch);
- STATETEARDOWN(m);
- return(REG_ESPACE);
- }
- NOTE("backref dissect");
- dp = backref(charset, m, m->coldp, endp, gf, gl, (sopno)0);
- }
- if (dp != NULL)
- break;
-
- /* uh-oh... we couldn't find a subexpression-level match */
- assert(g->backrefs); /* must be back references doing it */
- assert(g->nplus == 0 || m->lastpos != NULL);
- for (;;) {
- if (dp != NULL || endp <= m->coldp)
- break; /* defeat */
- NOTE("backoff");
- endp = slow(charset, m, m->coldp, endp-1, gf, gl);
- if (endp == NULL)
- break; /* defeat */
- /* try it on a shorter possibility */
-#ifndef NDEBUG
- for (i = 1; i <= m->g->nsub; i++) {
- assert(m->pmatch[i].rm_so == -1);
- assert(m->pmatch[i].rm_eo == -1);
- }
-#endif
- NOTE("backoff dissect");
- dp = backref(charset, m, m->coldp, endp, gf, gl, (sopno)0);
- }
- assert(dp == NULL || dp == endp);
- if (dp != NULL) /* found a shorter one */
- break;
-
- /* despite initial appearances, there is no match here */
- NOTE("false alarm");
- start = m->coldp + 1; /* recycle starting later */
- assert(start <= stop);
- }
-
- /* fill in the details if requested */
- if (nmatch > 0) {
- pmatch[0].rm_so = m->coldp - m->offp;
- pmatch[0].rm_eo = endp - m->offp;
- }
- if (nmatch > 1) {
- assert(m->pmatch != NULL);
- for (i = 1; i < nmatch; i++)
- if (i <= m->g->nsub)
- pmatch[i] = m->pmatch[i];
- else {
- pmatch[i].rm_so = -1;
- pmatch[i].rm_eo = -1;
- }
- }
-
- if (m->pmatch != NULL)
- free((char *)m->pmatch);
- if (m->lastpos != NULL)
- free((char *)m->lastpos);
- STATETEARDOWN(m);
- return(0);
-}
-
-/*
- - dissect - figure out what matched what, no back references
- == static char *dissect(register struct match *m, char *start, \
- == char *stop, sopno startst, sopno stopst);
- */
-static const char * /* == stop (success) always */
-dissect(charset, m, start, stop, startst, stopst)
-CHARSET_INFO *charset;
-register struct match *m;
-const char *start;
-const char *stop;
-sopno startst;
-sopno stopst;
-{
- register uint i;
- register sopno ss; /* start sop of current subRE */
- register sopno es; /* end sop of current subRE */
- register const char *sp; /* start of string matched by it */
- register const char *stp; /* string matched by it cannot pass here */
- register const char *rest; /* start of rest of string */
- register const char *tail; /* string unmatched by rest of RE */
- register sopno ssub; /* start sop of subsubRE */
- register sopno esub; /* end sop of subsubRE */
- register const char *ssp; /* start of string matched by subsubRE */
- register const char *sep; /* end of string matched by subsubRE */
- register const char *oldssp; /* previous ssp */
-
- AT("diss", start, stop, startst, stopst);
- sp = start;
- for (ss = startst; ss < stopst; ss = es) {
- /* identify end of subRE */
- es = ss;
- switch (OP(m->g->strip[es])) {
- case OPLUS_:
- case OQUEST_:
- es += OPND(m->g->strip[es]);
- break;
- case OCH_:
- while (OP(m->g->strip[es]) != O_CH)
- es += OPND(m->g->strip[es]);
- break;
- }
- es++;
-
- /* figure out what it matched */
- switch (OP(m->g->strip[ss])) {
- case OEND:
- assert(nope);
- break;
- case OCHAR:
- sp++;
- break;
- case OBOL:
- case OEOL:
- case OBOW:
- case OEOW:
- break;
- case OANY:
- case OANYOF:
- sp++;
- break;
- case OBACK_:
- case O_BACK:
- assert(nope);
- break;
- /* cases where length of match is hard to find */
- case OQUEST_:
- stp = stop;
- for (;;) {
- /* how long could this one be? */
- rest = slow(charset, m, sp, stp, ss, es);
- assert(rest != NULL); /* it did match */
- /* could the rest match the rest? */
- tail = slow(charset, m, rest, stop, es, stopst);
- if (tail == stop)
- break; /* yes! */
- /* no -- try a shorter match for this one */
- stp = rest - 1;
- assert(stp >= sp); /* it did work */
- }
- ssub = ss + 1;
- esub = es - 1;
- /* did innards match? */
- if (slow(charset, m, sp, rest, ssub, esub) != NULL)
- sp = dissect(charset, m, sp, rest, ssub, esub);
- assert(sp == rest);
- sp = rest;
- break;
- case OPLUS_:
- stp = stop;
- for (;;) {
- /* how long could this one be? */
- rest = slow(charset, m, sp, stp, ss, es);
- assert(rest != NULL); /* it did match */
- /* could the rest match the rest? */
- tail = slow(charset, m, rest, stop, es, stopst);
- if (tail == stop)
- break; /* yes! */
- /* no -- try a shorter match for this one */
- stp = rest - 1;
- assert(stp >= sp); /* it did work */
- }
- ssub = ss + 1;
- esub = es - 1;
- ssp = sp;
- oldssp = ssp;
- for (;;) { /* find last match of innards */
- sep = slow(charset, m, ssp, rest, ssub, esub);
- if (sep == NULL || sep == ssp)
- break; /* failed or matched null */
- oldssp = ssp; /* on to next try */
- ssp = sep;
- }
- if (sep == NULL) {
- /* last successful match */
- sep = ssp;
- ssp = oldssp;
- }
- assert(sep == rest); /* must exhaust substring */
- assert(slow(charset, m, ssp, sep, ssub, esub) == rest);
- sp = dissect(charset, m, ssp, sep, ssub, esub);
- assert(sp == sep);
- sp = rest;
- break;
- case OCH_:
- stp = stop;
- for (;;) {
- /* how long could this one be? */
- rest = slow(charset, m, sp, stp, ss, es);
- assert(rest != NULL); /* it did match */
- /* could the rest match the rest? */
- tail = slow(charset, m, rest, stop, es, stopst);
- if (tail == stop)
- break; /* yes! */
- /* no -- try a shorter match for this one */
- stp = rest - 1;
- assert(stp >= sp); /* it did work */
- }
- ssub = ss + 1;
- esub = ss + OPND(m->g->strip[ss]) - 1;
- assert(OP(m->g->strip[esub]) == OOR1);
- for (;;) { /* find first matching branch */
- if (slow(charset, m, sp, rest, ssub, esub) == rest)
- break; /* it matched all of it */
- /* that one missed, try next one */
- assert(OP(m->g->strip[esub]) == OOR1);
- esub++;
- assert(OP(m->g->strip[esub]) == OOR2);
- ssub = esub + 1;
- esub += OPND(m->g->strip[esub]);
- if (OP(m->g->strip[esub]) == OOR2)
- esub--;
- else
- assert(OP(m->g->strip[esub]) == O_CH);
- }
- sp = dissect(charset, m, sp, rest, ssub, esub);
- assert(sp == rest);
- sp = rest;
- break;
- case O_PLUS:
- case O_QUEST:
- case OOR1:
- case OOR2:
- case O_CH:
- assert(nope);
- break;
- case OLPAREN:
- i = OPND(m->g->strip[ss]);
- assert(0 < i && i <= m->g->nsub);
- m->pmatch[i].rm_so = sp - m->offp;
- break;
- case ORPAREN:
- i = OPND(m->g->strip[ss]);
- assert(0 < i && i <= m->g->nsub);
- m->pmatch[i].rm_eo = sp - m->offp;
- break;
- default: /* uh oh */
- assert(nope);
- break;
- }
- }
-
- assert(sp == stop);
- return(sp);
-}
-
-/*
- - backref - figure out what matched what, figuring in back references
- == static char *backref(register struct match *m, char *start, \
- == char *stop, sopno startst, sopno stopst, sopno lev);
- */
-static const char * /* == stop (success) or NULL (failure) */
-backref(charset,m, start, stop, startst, stopst, lev)
-CHARSET_INFO *charset;
-register struct match *m;
-const char *start;
-const char *stop;
-sopno startst;
-sopno stopst;
-sopno lev; /* PLUS nesting level */
-{
- register uint i;
- register sopno ss; /* start sop of current subRE */
- register const char *sp; /* start of string matched by it */
- register sopno ssub; /* start sop of subsubRE */
- register sopno esub; /* end sop of subsubRE */
- register const char *ssp; /* start of string matched by subsubRE */
- register const char *dp;
- register size_t len;
- register int hard;
- register sop s;
- register regoff_t offsave;
- register cset *cs;
-
- AT("back", start, stop, startst, stopst);
- sp = start;
-
- /* get as far as we can with easy stuff */
- hard = 0;
- for (ss = startst; !hard && ss < stopst; ss++)
- switch (OP(s = m->g->strip[ss])) {
- case OCHAR:
- if (sp == stop || *sp++ != (char)OPND(s))
- return(NULL);
- break;
- case OANY:
- if (sp == stop)
- return(NULL);
- sp++;
- break;
- case OANYOF:
- cs = &m->g->sets[OPND(s)];
- if (sp == stop || !CHIN(cs, *sp++))
- return(NULL);
- break;
- case OBOL:
- if ( (sp == m->beginp && !(m->eflags&REG_NOTBOL)) ||
- (sp < m->endp && *(sp-1) == '\n' &&
- (m->g->cflags&REG_NEWLINE)) )
- { /* yes */ }
- else
- return(NULL);
- break;
- case OEOL:
- if ( (sp == m->endp && !(m->eflags&REG_NOTEOL)) ||
- (sp < m->endp && *sp == '\n' &&
- (m->g->cflags&REG_NEWLINE)) )
- { /* yes */ }
- else
- return(NULL);
- break;
- case OBOW:
- if (( (sp == m->beginp && !(m->eflags&REG_NOTBOL)) ||
- (sp < m->endp && *(sp-1) == '\n' &&
- (m->g->cflags&REG_NEWLINE)) ||
- (sp > m->beginp &&
- !ISWORD(charset,*(sp-1))) ) &&
- (sp < m->endp && ISWORD(charset,*sp)) )
- { /* yes */ }
- else
- return(NULL);
- break;
- case OEOW:
- if (( (sp == m->endp && !(m->eflags&REG_NOTEOL)) ||
- (sp < m->endp && *sp == '\n' &&
- (m->g->cflags&REG_NEWLINE)) ||
- (sp < m->endp && !ISWORD(charset,*sp)) ) &&
- (sp > m->beginp && ISWORD(charset,*(sp-1))) )
- { /* yes */ }
- else
- return(NULL);
- break;
- case O_QUEST:
- break;
- case OOR1: /* matches null but needs to skip */
- ss++;
- s = m->g->strip[ss];
- do {
- assert(OP(s) == OOR2);
- ss += OPND(s);
- } while (OP(s = m->g->strip[ss]) != O_CH);
- /* note that the ss++ gets us past the O_CH */
- break;
- default: /* have to make a choice */
- hard = 1;
- break;
- }
- if (!hard) { /* that was it! */
- if (sp != stop)
- return(NULL);
- return(sp);
- }
- ss--; /* adjust for the for's final increment */
-
- /* the hard stuff */
- AT("hard", sp, stop, ss, stopst);
- s = m->g->strip[ss];
- switch (OP(s)) {
- case OBACK_: /* the vilest depths */
- i = OPND(s);
- assert(0 < i && i <= m->g->nsub);
- if (m->pmatch[i].rm_eo == -1)
- return(NULL);
- assert(m->pmatch[i].rm_so != -1);
- len = m->pmatch[i].rm_eo - m->pmatch[i].rm_so;
- assert((size_t) (stop - m->beginp) >= len);
- if (sp > stop - len)
- return(NULL); /* not enough left to match */
- ssp = m->offp + m->pmatch[i].rm_so;
- if (memcmp(sp, ssp, len) != 0)
- return(NULL);
- while (m->g->strip[ss] != SOP(O_BACK, i))
- ss++;
- return(backref(charset, m, sp+len, stop, ss+1, stopst, lev));
- break;
- case OQUEST_: /* to null or not */
- dp = backref(charset, m, sp, stop, ss+1, stopst, lev);
- if (dp != NULL)
- return(dp); /* not */
- return(backref(charset, m, sp, stop, ss+OPND(s)+1, stopst, lev));
- break;
- case OPLUS_:
- assert(m->lastpos != NULL);
- assert(lev+1 <= m->g->nplus);
- m->lastpos[lev+1] = sp;
- return(backref(charset, m, sp, stop, ss+1, stopst, lev+1));
- break;
- case O_PLUS:
- if (sp == m->lastpos[lev]) /* last pass matched null */
- return(backref(charset, m, sp, stop, ss+1, stopst, lev-1));
- /* try another pass */
- m->lastpos[lev] = sp;
- dp = backref(charset, m, sp, stop, ss-OPND(s)+1, stopst, lev);
- if (dp == NULL)
- return(backref(charset, m, sp, stop, ss+1, stopst, lev-1));
- else
- return(dp);
- break;
- case OCH_: /* find the right one, if any */
- ssub = ss + 1;
- esub = ss + OPND(s) - 1;
- assert(OP(m->g->strip[esub]) == OOR1);
- for (;;) { /* find first matching branch */
- dp = backref(charset, m, sp, stop, ssub, esub, lev);
- if (dp != NULL)
- return(dp);
- /* that one missed, try next one */
- if (OP(m->g->strip[esub]) == O_CH)
- return(NULL); /* there is none */
- esub++;
- assert(OP(m->g->strip[esub]) == OOR2);
- ssub = esub + 1;
- esub += OPND(m->g->strip[esub]);
- if (OP(m->g->strip[esub]) == OOR2)
- esub--;
- else
- assert(OP(m->g->strip[esub]) == O_CH);
- }
- break;
- case OLPAREN: /* must undo assignment if rest fails */
- i = OPND(s);
- assert(0 < i && i <= m->g->nsub);
- offsave = m->pmatch[i].rm_so;
- m->pmatch[i].rm_so = sp - m->offp;
- dp = backref(charset, m, sp, stop, ss+1, stopst, lev);
- if (dp != NULL)
- return(dp);
- m->pmatch[i].rm_so = offsave;
- return(NULL);
- break;
- case ORPAREN: /* must undo assignment if rest fails */
- i = OPND(s);
- assert(0 < i && i <= m->g->nsub);
- offsave = m->pmatch[i].rm_eo;
- m->pmatch[i].rm_eo = sp - m->offp;
- dp = backref(charset, m, sp, stop, ss+1, stopst, lev);
- if (dp != NULL)
- return(dp);
- m->pmatch[i].rm_eo = offsave;
- return(NULL);
- break;
- default: /* uh oh */
- assert(nope);
- break;
- }
-
- /* "can't happen" */
- assert(nope);
- /* NOTREACHED */
- return 0; /* Keep gcc happy */
-}
-
-/*
- - fast - step through the string at top speed
- == static char *fast(register struct match *m, char *start, \
- == char *stop, sopno startst, sopno stopst);
- */
-static const char * /* where tentative match ended, or NULL */
-fast(charset, m, start, stop, startst, stopst)
-CHARSET_INFO *charset;
-register struct match *m;
-const char *start;
-const char *stop;
-sopno startst;
-sopno stopst;
-{
- register states st = m->st;
- register states fresh = m->fresh;
- register states tmp = m->tmp;
- register const char *p = start;
- register int c = (start == m->beginp) ? OUT : *(start-1);
- register int lastc; /* previous c */
- register int flagch;
- register int i;
- register const char *coldp; /* last p after which no match was underway */
-
- CLEAR(st);
- SET1(st, startst);
- st = step(m->g, startst, stopst, st, NOTHING, st);
- ASSIGN(fresh, st);
- SP("start", st, *p);
- coldp = NULL;
- for (;;) {
- /* next character */
- lastc = c;
- c = (p == m->endp) ? OUT : *p;
- if (EQ(st, fresh))
- coldp = p;
-
- /* is there an EOL and/or BOL between lastc and c? */
- flagch = '\0';
- i = 0;
- if ( (lastc == '\n' && m->g->cflags&REG_NEWLINE) ||
- (lastc == OUT && !(m->eflags&REG_NOTBOL)) ) {
- flagch = BOL;
- i = m->g->nbol;
- }
- if ( (c == '\n' && m->g->cflags&REG_NEWLINE) ||
- (c == OUT && !(m->eflags&REG_NOTEOL)) ) {
- flagch = (flagch == BOL) ? BOLEOL : EOL;
- i += m->g->neol;
- }
- if (i != 0) {
- for (; i > 0; i--)
- st = step(m->g, startst, stopst, st, flagch, st);
- SP("boleol", st, c);
- }
-
- /* how about a word boundary? */
- if ( (flagch == BOL || (lastc != OUT && !ISWORD(charset,lastc))) &&
- (c != OUT && ISWORD(charset,c)) ) {
- flagch = BOW;
- }
- if ( (lastc != OUT && ISWORD(charset,lastc)) &&
- (flagch == EOL || (c != OUT && !ISWORD(charset,c))) ) {
- flagch = EOW;
- }
- if (flagch == BOW || flagch == EOW) {
- st = step(m->g, startst, stopst, st, flagch, st);
- SP("boweow", st, c);
- }
-
- /* are we done? */
- if (ISSET(st, stopst) || p == stop)
- break; /* NOTE BREAK OUT */
-
- /* no, we must deal with this character */
- ASSIGN(tmp, st);
- ASSIGN(st, fresh);
- assert(c != OUT);
- st = step(m->g, startst, stopst, tmp, c, st);
- SP("aft", st, c);
- assert(EQ(step(m->g, startst, stopst, st, NOTHING, st), st));
- p++;
- }
-
- assert(coldp != NULL);
- m->coldp = coldp;
- if (ISSET(st, stopst))
- return(p+1);
- else
- return(NULL);
-}
-
-/*
- - slow - step through the string more deliberately
- == static char *slow(register struct match *m, char *start, \
- == char *stop, sopno startst, sopno stopst);
- */
-static const char * /* where it ended */
-slow(charset, m, start, stop, startst, stopst)
-CHARSET_INFO *charset;
-register struct match *m;
-const char *start;
-const char *stop;
-sopno startst;
-sopno stopst;
-{
- register states st = m->st;
- register states empty = m->empty;
- register states tmp = m->tmp;
- register const char *p = start;
- register int c = (start == m->beginp) ? OUT : *(start-1);
- register int lastc; /* previous c */
- register int flagch;
- register int i;
- register const char *matchp; /* last p at which a match ended */
-
- AT("slow", start, stop, startst, stopst);
- CLEAR(st);
- SET1(st, startst);
- SP("sstart", st, *p);
- st = step(m->g, startst, stopst, st, NOTHING, st);
- matchp = NULL;
- for (;;) {
- /* next character */
- lastc = c;
- c = (p == m->endp) ? OUT : *p;
-
- /* is there an EOL and/or BOL between lastc and c? */
- flagch = '\0';
- i = 0;
- if ( (lastc == '\n' && m->g->cflags&REG_NEWLINE) ||
- (lastc == OUT && !(m->eflags&REG_NOTBOL)) ) {
- flagch = BOL;
- i = m->g->nbol;
- }
- if ( (c == '\n' && m->g->cflags&REG_NEWLINE) ||
- (c == OUT && !(m->eflags&REG_NOTEOL)) ) {
- flagch = (flagch == BOL) ? BOLEOL : EOL;
- i += m->g->neol;
- }
- if (i != 0) {
- for (; i > 0; i--)
- st = step(m->g, startst, stopst, st, flagch, st);
- SP("sboleol", st, c);
- }
-
- /* how about a word boundary? */
- if ( (flagch == BOL || (lastc != OUT && !ISWORD(charset,lastc))) &&
- (c != OUT && ISWORD(charset,c)) ) {
- flagch = BOW;
- }
- if ( (lastc != OUT && ISWORD(charset,lastc)) &&
- (flagch == EOL || (c != OUT && !ISWORD(charset,c))) ) {
- flagch = EOW;
- }
- if (flagch == BOW || flagch == EOW) {
- st = step(m->g, startst, stopst, st, flagch, st);
- SP("sboweow", st, c);
- }
-
- /* are we done? */
- if (ISSET(st, stopst))
- matchp = p;
- if (EQ(st, empty) || p == stop)
- break; /* NOTE BREAK OUT */
-
- /* no, we must deal with this character */
- ASSIGN(tmp, st);
- ASSIGN(st, empty);
- assert(c != OUT);
- st = step(m->g, startst, stopst, tmp, c, st);
- SP("saft", st, c);
- assert(EQ(step(m->g, startst, stopst, st, NOTHING, st), st));
- p++;
- }
-
- return(matchp);
-}
-
-
-/*
- - step - map set of states reachable before char to set reachable after
- == static states step(register struct re_guts *g, sopno start, sopno stop, \
- == register states bef, int ch, register states aft);
- == #define BOL (OUT+1)
- == #define EOL (BOL+1)
- == #define BOLEOL (BOL+2)
- == #define NOTHING (BOL+3)
- == #define BOW (BOL+4)
- == #define EOW (BOL+5)
- == #define CODEMAX (BOL+5) // highest code used
- == #define NONCHAR(c) ((c) > CHAR_MAX)
- == #define NNONCHAR (CODEMAX-CHAR_MAX)
- */
-static states
-step(g, start, stop, bef, ch, aft)
-register struct re_guts *g;
-sopno start; /* start state within strip */
-sopno stop; /* state after stop state within strip */
-register states bef; /* states reachable before */
-int ch; /* character or NONCHAR code */
-register states aft; /* states already known reachable after */
-{
- register cset *cs;
- register sop s;
- register sopno pc;
- register onestate here; /* note, macros know this name */
- register sopno look;
- register onestate i; /* Changed from int by Monty */
-
- for (pc = start, INIT(here, pc); pc != stop; pc++, INC(here)) {
- s = g->strip[pc];
- switch (OP(s)) {
- case OEND:
- assert(pc == stop-1);
- break;
- case OCHAR:
- /* only characters can match */
- assert(!NONCHAR(ch) || ch != (char)OPND(s));
- if (ch == (char)OPND(s))
- FWD(aft, bef, 1);
- break;
- case OBOL:
- if (ch == BOL || ch == BOLEOL)
- FWD(aft, bef, 1);
- break;
- case OEOL:
- if (ch == EOL || ch == BOLEOL)
- FWD(aft, bef, 1);
- break;
- case OBOW:
- if (ch == BOW)
- FWD(aft, bef, 1);
- break;
- case OEOW:
- if (ch == EOW)
- FWD(aft, bef, 1);
- break;
- case OANY:
- if (!NONCHAR(ch))
- FWD(aft, bef, 1);
- break;
- case OANYOF:
- cs = &g->sets[OPND(s)];
- if (!NONCHAR(ch) && CHIN(cs, ch))
- FWD(aft, bef, 1);
- break;
- case OBACK_: /* ignored here */
- case O_BACK:
- FWD(aft, aft, 1);
- break;
- case OPLUS_: /* forward, this is just an empty */
- FWD(aft, aft, 1);
- break;
- case O_PLUS: /* both forward and back */
- FWD(aft, aft, 1);
- i = ISSETBACK(aft, OPND(s));
- BACK(aft, aft, OPND(s));
- if (!i && ISSETBACK(aft, OPND(s))) {
- /* oho, must reconsider loop body */
- pc -= OPND(s) + 1;
- INIT(here, pc);
- }
- break;
- case OQUEST_: /* two branches, both forward */
- FWD(aft, aft, 1);
- FWD(aft, aft, OPND(s));
- break;
- case O_QUEST: /* just an empty */
- FWD(aft, aft, 1);
- break;
- case OLPAREN: /* not significant here */
- case ORPAREN:
- FWD(aft, aft, 1);
- break;
- case OCH_: /* mark the first two branches */
- FWD(aft, aft, 1);
- assert(OP(g->strip[pc+OPND(s)]) == OOR2);
- FWD(aft, aft, OPND(s));
- break;
- case OOR1: /* done a branch, find the O_CH */
- if (ISSTATEIN(aft, here)) {
- for (look = 1;
- OP(s = g->strip[pc+look]) != O_CH;
- look += OPND(s))
- assert(OP(s) == OOR2);
- FWD(aft, aft, look);
- }
- break;
- case OOR2: /* propagate OCH_'s marking */
- FWD(aft, aft, 1);
- if (OP(g->strip[pc+OPND(s)]) != O_CH) {
- assert(OP(g->strip[pc+OPND(s)]) == OOR2);
- FWD(aft, aft, OPND(s));
- }
- break;
- case O_CH: /* just empty */
- FWD(aft, aft, 1);
- break;
- default: /* ooooops... */
- assert(nope);
- break;
- }
- }
-
- return(aft);
-}
-
-#ifdef REDEBUG
-/*
- - print - print a set of states
- == #ifdef REDEBUG
- == static void print(struct match *m, char *caption, states st, \
- == int ch, FILE *d);
- == #endif
- */
-static void
-print(m, caption, st, ch, d)
-struct match *m;
-char *caption;
-states st;
-int ch;
-FILE *d;
-{
- register struct re_guts *g = m->g;
- register int i;
- register int first = 1;
- char buf[10];
-
- if (!(m->eflags&REG_TRACE))
- return;
-
- fprintf(d, "%s", caption);
- if (ch != '\0')
- fprintf(d, " %s", printchar(ch,buf));
- for (i = 0; i < g->nstates; i++)
- if (ISSET(st, i)) {
- fprintf(d, "%s%d", (first) ? "\t" : ", ", i);
- first = 0;
- }
- fprintf(d, "\n");
-}
-
-/*
- - at - print current situation
- == #ifdef REDEBUG
- == static void at(struct match *m, char *title, char *start, char *stop, \
- == sopno startst, sopno stopst);
- == #endif
- */
-static void
-at(m, title, start, stop, startst, stopst)
-struct match *m;
-char *title;
-char *start;
-char *stop;
-sopno startst;
-sopno stopst;
-{
- char buf[10];
- if (!(m->eflags&REG_TRACE))
- return;
-
- printf("%s %s-", title, printchar(*start,buf));
- printf("%s ", printchar(*stop,buf));
- printf("%ld-%ld\n", (long)startst, (long)stopst,buf);
-}
-
-#ifndef PCHARDONE
-#define PCHARDONE /* never again */
-/*
- - printchar - make a character printable
- == #ifdef REDEBUG
- == static char *printchar(int ch);
- == #endif
- *
- * Is this identical to regchar() over in debug.c? Well, yes. But a
- * duplicate here avoids having a debugging-capable regexec.o tied to
- * a matching debug.o, and this is convenient. It all disappears in
- * the non-debug compilation anyway, so it doesn't matter much.
- */
-static char * /* -> representation */
-printchar(ch,pbuf)
-int ch;
-char *pbuf;
-{
- if (isprint(ch) || ch == ' ')
- sprintf(pbuf, "%c", ch);
- else
- sprintf(pbuf, "\\%o", ch);
- return(pbuf);
-}
-#endif
-#endif
-
-#undef matcher
-#undef fast
-#undef slow
-#undef dissect
-#undef backref
-#undef step
-#undef print
-#undef at
-#undef match
diff --git a/regex/engine.ih b/regex/engine.ih
deleted file mode 100644
index aa0f83e8e2e..00000000000
--- a/regex/engine.ih
+++ /dev/null
@@ -1,35 +0,0 @@
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* === engine.c === */
-static int matcher(CHARSET_INFO *charset,register struct re_guts *g, const char *string, size_t nmatch, my_regmatch_t pmatch[], int eflags);
-static const char *dissect(CHARSET_INFO *charset,register struct match *m, const char *start, const char *stop, sopno startst, sopno stopst);
-static const char *backref(CHARSET_INFO *charset, register struct match *m, const char *start, const char *stop, sopno startst, sopno stopst, sopno lev);
-static const char *fast(CHARSET_INFO *charset, register struct match *m, const char *start, const char *stop, sopno startst, sopno stopst);
-static const char *slow(CHARSET_INFO *charset, register struct match *m, const char *start, const char *stop, sopno startst, sopno stopst);
-static states step(register struct re_guts *g, sopno start, sopno stop, register states bef, int ch, register states aft);
-#define BOL (OUT+1)
-#define EOL (BOL+1)
-#define BOLEOL (BOL+2)
-#define NOTHING (BOL+3)
-#define BOW (BOL+4)
-#define EOW (BOL+5)
-#define CODEMAX (BOL+5) /* highest code used */
-#define NONCHAR(c) ((c) > CHAR_MAX)
-#define NNONCHAR (CODEMAX-CHAR_MAX)
-#ifdef REDEBUG
-static void print(struct match *m, char *caption, states st, int ch, FILE *d);
-#endif
-#ifdef REDEBUG
-static void at(struct match *m, char *title, char *start, char *stop, sopno startst, sopno stopst);
-#endif
-#ifdef REDEBUG
-static char *printchar(int ch,char *buf);
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
diff --git a/regex/main.c b/regex/main.c
deleted file mode 100644
index f5b591907cf..00000000000
--- a/regex/main.c
+++ /dev/null
@@ -1,509 +0,0 @@
-#include <my_global.h>
-#include <m_string.h>
-#include <sys/types.h>
-#include <assert.h>
-
-#include "my_regex.h"
-#include "main.ih"
-
-char *progname;
-int debug = 0;
-int line = 0;
-int status = 0;
-
-int copts = REG_EXTENDED;
-int eopts = 0;
-regoff_t startoff = 0;
-regoff_t endoff = 0;
-
-
-extern int split(char *string, char *fields[], int nfields, char *sep);
-extern void regprint(my_regex_t *r, FILE *d);
-
-/*
- - main - do the simple case, hand off to regress() for regression
- */
-int main(argc, argv)
-int argc;
-char *argv[];
-{
- my_regex_t re;
-# define NS 10
- my_regmatch_t subs[NS];
- char erbuf[100];
- int err;
- size_t len;
- int c;
- int errflg = 0;
- register int i;
- extern int optind;
- extern char *optarg;
-
- progname = argv[0];
-
- while ((c = getopt(argc, argv, "c:e:S:E:x")) != EOF)
- switch (c) {
- case 'c': /* compile options */
- copts = options('c', optarg);
- break;
- case 'e': /* execute options */
- eopts = options('e', optarg);
- break;
- case 'S': /* start offset */
- startoff = (regoff_t)atoi(optarg);
- break;
- case 'E': /* end offset */
- endoff = (regoff_t)atoi(optarg);
- break;
- case 'x': /* Debugging. */
- debug++;
- break;
- case '?':
- default:
- errflg++;
- break;
- }
- if (errflg) {
- fprintf(stderr, "usage: %s ", progname);
- fprintf(stderr, "[-c copt][-C][-d] [re]\n");
- exit(2);
- }
-
- if (optind >= argc) {
- regress(stdin);
- exit(status);
- }
-
- err = my_regcomp(&re, argv[optind++], copts, &my_charset_latin1);
- if (err) {
- len = my_regerror(err, &re, erbuf, sizeof(erbuf));
- fprintf(stderr, "error %s, %d/%d `%s'\n",
- eprint(err), (int) len, (int) sizeof(erbuf), erbuf);
- exit(status);
- }
- regprint(&re, stdout);
-
- if (optind >= argc) {
- my_regfree(&re);
- exit(status);
- }
-
- if (eopts&REG_STARTEND) {
- subs[0].rm_so = startoff;
- subs[0].rm_eo = strlen(argv[optind]) - endoff;
- }
- err = my_regexec(&re, argv[optind], (size_t)NS, subs, eopts);
- if (err) {
- len = my_regerror(err, &re, erbuf, sizeof(erbuf));
- fprintf(stderr, "error %s, %d/%d `%s'\n",
- eprint(err), (int) len, (int) sizeof(erbuf), erbuf);
- exit(status);
- }
- if (!(copts&REG_NOSUB)) {
- len = (int)(subs[0].rm_eo - subs[0].rm_so);
- if (subs[0].rm_so != -1) {
- if (len != 0)
- printf("match `%.*s'\n", (int)len,
- argv[optind] + subs[0].rm_so);
- else
- printf("match `'@%.1s\n",
- argv[optind] + subs[0].rm_so);
- }
- for (i = 1; i < NS; i++)
- if (subs[i].rm_so != -1)
- printf("(%d) `%.*s'\n", i,
- (int)(subs[i].rm_eo - subs[i].rm_so),
- argv[optind] + subs[i].rm_so);
- }
- exit(status);
-}
-
-/*
- - regress - main loop of regression test
- == void regress(FILE *in);
- */
-void
-regress(in)
-FILE *in;
-{
- char inbuf[1000];
-# define MAXF 10
- char *f[MAXF];
- int nf;
- int i;
- char erbuf[100];
- size_t ne;
- const char *badpat = "invalid regular expression";
-# define SHORT 10
- const char *bpname = "REG_BADPAT";
- my_regex_t re;
-
- while (fgets(inbuf, sizeof(inbuf), in) != NULL) {
- line++;
- if (inbuf[0] == '#' || inbuf[0] == '\n')
- continue; /* NOTE CONTINUE */
- inbuf[strlen(inbuf)-1] = '\0'; /* get rid of stupid \n */
- if (debug)
- fprintf(stdout, "%d:\n", line);
- nf = split(inbuf, f, MAXF, (char*) "\t\t");
- if (nf < 3) {
- fprintf(stderr, "bad input, line %d\n", line);
- exit(1);
- }
- for (i = 0; i < nf; i++)
- if (strcmp(f[i], "\"\"") == 0)
- f[i] = (char*) "";
- if (nf <= 3)
- f[3] = NULL;
- if (nf <= 4)
- f[4] = NULL;
- rx_try(f[0], f[1], f[2], f[3], f[4], options('c', f[1]));
- if (opt('&', f[1])) /* try with either type of RE */
- rx_try(f[0], f[1], f[2], f[3], f[4],
- options('c', f[1]) &~ REG_EXTENDED);
- }
-
- ne = my_regerror(REG_BADPAT, (my_regex_t *)NULL, erbuf, sizeof(erbuf));
- if (strcmp(erbuf, badpat) != 0 || ne != strlen(badpat)+1) {
- fprintf(stderr, "end: regerror() test gave `%s' not `%s'\n",
- erbuf, badpat);
- status = 1;
- }
- ne = my_regerror(REG_BADPAT, (my_regex_t *)NULL, erbuf, (size_t)SHORT);
- if (strncmp(erbuf, badpat, SHORT-1) != 0 || erbuf[SHORT-1] != '\0' ||
- ne != strlen(badpat)+1) {
- fprintf(stderr, "end: regerror() short test gave `%s' not `%.*s'\n",
- erbuf, SHORT-1, badpat);
- status = 1;
- }
- ne = my_regerror(REG_ITOA|REG_BADPAT, (my_regex_t *)NULL, erbuf, sizeof(erbuf));
- if (strcmp(erbuf, bpname) != 0 || ne != strlen(bpname)+1) {
- fprintf(stderr, "end: regerror() ITOA test gave `%s' not `%s'\n",
- erbuf, bpname);
- status = 1;
- }
- re.re_endp = bpname;
- ne = my_regerror(REG_ATOI, &re, erbuf, sizeof(erbuf));
- if (atoi(erbuf) != (int)REG_BADPAT) {
- fprintf(stderr, "end: regerror() ATOI test gave `%s' not `%ld'\n",
- erbuf, (long)REG_BADPAT);
- status = 1;
- } else if (ne != strlen(erbuf)+1) {
- fprintf(stderr, "end: regerror() ATOI test len(`%s') = %ld\n",
- erbuf, (long)REG_BADPAT);
- status = 1;
- }
-}
-
-/*
- - rx_try - try it, and report on problems
- == void rx_try(char *f0, char *f1, char *f2, char *f3, char *f4, int opts);
- */
-void
-rx_try(f0, f1, f2, f3, f4, opts)
-char *f0;
-char *f1;
-char *f2;
-char *f3;
-char *f4;
-int opts; /* may not match f1 */
-{
- my_regex_t re;
-# define NSUBS 10
- my_regmatch_t subs[NSUBS];
-# define NSHOULD 15
- char *should[NSHOULD];
- int nshould;
- char erbuf[100];
- int err;
- int len;
- const char *type = (opts & REG_EXTENDED) ? "ERE" : "BRE";
- register int i;
- char *grump;
- char f0copy[1000];
- char f2copy[1000];
-
- strcpy(f0copy, f0);
- re.re_endp = (opts&REG_PEND) ? f0copy + strlen(f0copy) : NULL;
- fixstr(f0copy);
- err = my_regcomp(&re, f0copy, opts, &my_charset_latin1);
- if (err != 0 && (!opt('C', f1) || err != efind(f2))) {
- /* unexpected error or wrong error */
- len = my_regerror(err, &re, erbuf, sizeof(erbuf));
- fprintf(stderr, "%d: %s error %s, %d/%d `%s'\n",
- line, type, eprint(err), len,
- (int) sizeof(erbuf), erbuf);
- status = 1;
- } else if (err == 0 && opt('C', f1)) {
- /* unexpected success */
- fprintf(stderr, "%d: %s should have given REG_%s\n",
- line, type, f2);
- status = 1;
- err = 1; /* so we won't try regexec */
- }
-
- if (err != 0) {
- my_regfree(&re);
- return;
- }
-
- strcpy(f2copy, f2);
- fixstr(f2copy);
-
- if (options('e', f1)&REG_STARTEND) {
- if (strchr(f2, '(') == NULL || strchr(f2, ')') == NULL)
- fprintf(stderr, "%d: bad STARTEND syntax\n", line);
- subs[0].rm_so = strchr(f2, '(') - f2 + 1;
- subs[0].rm_eo = strchr(f2, ')') - f2;
- }
- err = my_regexec(&re, f2copy, NSUBS, subs, options('e', f1));
-
- if (err != 0 && (f3 != NULL || err != REG_NOMATCH)) {
- /* unexpected error or wrong error */
- len = my_regerror(err, &re, erbuf, sizeof(erbuf));
- fprintf(stderr, "%d: %s exec error %s, %d/%d `%s'\n",
- line, type, eprint(err), len,
- (int) sizeof(erbuf), erbuf);
- status = 1;
- } else if (err != 0) {
- /* nothing more to check */
- } else if (f3 == NULL) {
- /* unexpected success */
- fprintf(stderr, "%d: %s exec should have failed\n",
- line, type);
- status = 1;
- err = 1; /* just on principle */
- } else if (opts&REG_NOSUB) {
- /* nothing more to check */
- } else if ((grump = check(f2, subs[0], f3)) != NULL) {
- fprintf(stderr, "%d: %s %s\n", line, type, grump);
- status = 1;
- err = 1;
- }
-
- if (err != 0 || f4 == NULL) {
- my_regfree(&re);
- return;
- }
-
- for (i = 1; i < NSHOULD; i++)
- should[i] = NULL;
- nshould = split(f4, should+1, NSHOULD-1, (char*) ",");
- if (nshould == 0) {
- nshould = 1;
- should[1] = (char*) "";
- }
- for (i = 1; i < NSUBS; i++) {
- grump = check(f2, subs[i], should[i]);
- if (grump != NULL) {
- fprintf(stderr, "%d: %s $%d %s\n", line,
- type, i, grump);
- status = 1;
- err = 1;
- }
- }
-
- my_regfree(&re);
-}
-
-/*
- - options - pick options out of a regression-test string
- == int options(int type, char *s);
- */
-int
-options(type, s)
-int type; /* 'c' compile, 'e' exec */
-char *s;
-{
- register char *p;
- register int o = (type == 'c') ? copts : eopts;
- register const char *legal = (type == 'c') ? "bisnmp" : "^$#tl";
-
- for (p = s; *p != '\0'; p++)
- if (strchr(legal, *p) != NULL)
- switch (*p) {
- case 'b':
- o &= ~REG_EXTENDED;
- break;
- case 'i':
- o |= REG_ICASE;
- break;
- case 's':
- o |= REG_NOSUB;
- break;
- case 'n':
- o |= REG_NEWLINE;
- break;
- case 'm':
- o &= ~REG_EXTENDED;
- o |= REG_NOSPEC;
- break;
- case 'p':
- o |= REG_PEND;
- break;
- case '^':
- o |= REG_NOTBOL;
- break;
- case '$':
- o |= REG_NOTEOL;
- break;
- case '#':
- o |= REG_STARTEND;
- break;
- case 't': /* trace */
- o |= REG_TRACE;
- break;
- case 'l': /* force long representation */
- o |= REG_LARGE;
- break;
- case 'r': /* force backref use */
- o |= REG_BACKR;
- break;
- }
- return(o);
-}
-
-/*
- - opt - is a particular option in a regression string?
- == int opt(int c, char *s);
- */
-int /* predicate */
-opt(c, s)
-int c;
-char *s;
-{
- return(strchr(s, c) != NULL);
-}
-
-/*
- - fixstr - transform magic characters in strings
- == void fixstr(register char *p);
- */
-void
-fixstr(p)
-register char *p;
-{
- if (p == NULL)
- return;
-
- for (; *p != '\0'; p++)
- if (*p == 'N')
- *p = '\n';
- else if (*p == 'T')
- *p = '\t';
- else if (*p == 'S')
- *p = ' ';
- else if (*p == 'Z')
- *p = '\0';
-}
-
-/*
- - check - check a substring match
- == char *check(char *str, regmatch_t sub, char *should);
- */
-char * /* NULL or complaint */
-check(str, sub, should)
-char *str;
-my_regmatch_t sub;
-char *should;
-{
- register int len;
- register int shlen;
- register char *p;
- static char grump[500];
- register char *at = NULL;
-
- if (should != NULL && strcmp(should, "-") == 0)
- should = NULL;
- if (should != NULL && should[0] == '@') {
- at = should + 1;
- should = (char*) "";
- }
-
- /* check rm_so and rm_eo for consistency */
- if (sub.rm_so > sub.rm_eo || (sub.rm_so == -1 && sub.rm_eo != -1) ||
- (sub.rm_so != -1 && sub.rm_eo == -1) ||
- (sub.rm_so != -1 && sub.rm_so < 0) ||
- (sub.rm_eo != -1 && sub.rm_eo < 0) ) {
- sprintf(grump, "start %ld end %ld", (long)sub.rm_so,
- (long)sub.rm_eo);
- return(grump);
- }
-
- /* check for no match */
- if (sub.rm_so == -1 && should == NULL)
- return(NULL);
- if (sub.rm_so == -1)
- return((char*) "did not match");
-
- /* check for in range */
- if ((int) sub.rm_eo > (int) strlen(str)) {
- sprintf(grump, "start %ld end %ld, past end of string",
- (long)sub.rm_so, (long)sub.rm_eo);
- return(grump);
- }
-
- len = (int)(sub.rm_eo - sub.rm_so);
- shlen = (int)strlen(should);
- p = str + sub.rm_so;
-
- /* check for not supposed to match */
- if (should == NULL) {
- sprintf(grump, "matched `%.*s'", len, p);
- return(grump);
- }
-
- /* check for wrong match */
- if (len != shlen || strncmp(p, should, (size_t)shlen) != 0) {
- sprintf(grump, "matched `%.*s' instead", len, p);
- return(grump);
- }
- if (shlen > 0)
- return(NULL);
-
- /* check null match in right place */
- if (at == NULL)
- return(NULL);
- shlen = strlen(at);
- if (shlen == 0)
- shlen = 1; /* force check for end-of-string */
- if (strncmp(p, at, shlen) != 0) {
- sprintf(grump, "matched null at `%.20s'", p);
- return(grump);
- }
- return(NULL);
-}
-
-/*
- - eprint - convert error number to name
- == static char *eprint(int err);
- */
-static char *
-eprint(err)
-int err;
-{
- static char epbuf[100];
- size_t len;
-
- len = my_regerror(REG_ITOA|err, (my_regex_t *)NULL, epbuf, sizeof(epbuf));
- assert(len <= sizeof(epbuf));
- return(epbuf);
-}
-
-/*
- - efind - convert error name to number
- == static int efind(char *name);
- */
-static int
-efind(name)
-char *name;
-{
- static char efbuf[100];
- my_regex_t re;
-
- sprintf(efbuf, "REG_%s", name);
- assert(strlen(efbuf) < sizeof(efbuf));
- re.re_endp = efbuf;
- (void) my_regerror(REG_ATOI, &re, efbuf, sizeof(efbuf));
- return(atoi(efbuf));
-}
diff --git a/regex/main.ih b/regex/main.ih
deleted file mode 100644
index f0104cc18c0..00000000000
--- a/regex/main.ih
+++ /dev/null
@@ -1,19 +0,0 @@
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* === main.c === */
-void regress(FILE *in);
-void rx_try(char *f0, char *f1, char *f2, char *f3, char *f4, int opts);
-int options(int type, char *s);
-int opt(int c, char *s);
-void fixstr(register char *p);
-char *check(char *str, my_regmatch_t sub, char *should);
-static char *eprint(int err);
-static int efind(char *name);
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
diff --git a/regex/my_regex.h b/regex/my_regex.h
deleted file mode 100644
index 1f96b8c461e..00000000000
--- a/regex/my_regex.h
+++ /dev/null
@@ -1,88 +0,0 @@
-#ifndef _REGEX_H_
-#define _REGEX_H_ /* never again */
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include "m_ctype.h"
-
-/* === regex2.h === */
-#ifdef _WIN64
-typedef __int64 regoff_t;
-#else
-typedef off_t regoff_t;
-#endif
-struct re_guts; /* none of your business :-) */
-typedef struct {
- int re_magic;
- size_t re_nsub; /* number of parenthesized subexpressions */
- const char *re_endp; /* end pointer for REG_PEND */
- struct re_guts *re_g; /* none of your business :-) */
- CHARSET_INFO *charset; /* For ctype things */
-} my_regex_t;
-typedef struct {
- regoff_t rm_so; /* start of match */
- regoff_t rm_eo; /* end of match */
-} my_regmatch_t;
-
-
-/* === regcomp.c === */
-typedef int (*my_regex_stack_check_t)(int);
-extern int my_regcomp(my_regex_t *, const char *, int, CHARSET_INFO *charset);
-#define REG_BASIC 0000
-#define REG_EXTENDED 0001
-#define REG_ICASE 0002
-#define REG_NOSUB 0004
-#define REG_NEWLINE 0010
-#define REG_NOSPEC 0020
-#define REG_PEND 0040
-#define REG_DUMP 0200
-
-
-/* === regerror.c === */
-#define REG_NOMATCH 1
-#define REG_BADPAT 2
-#define REG_ECOLLATE 3
-#define REG_ECTYPE 4
-#define REG_EESCAPE 5
-#define REG_ESUBREG 6
-#define REG_EBRACK 7
-#define REG_EPAREN 8
-#define REG_EBRACE 9
-#define REG_BADBR 10
-#define REG_ERANGE 11
-#define REG_ESPACE 12
-#define REG_BADRPT 13
-#define REG_EMPTY 14
-#define REG_ASSERT 15
-#define REG_INVARG 16
-#define REG_ATOI 255 /* convert name to number (!) */
-#define REG_ITOA 0400 /* convert number to name (!) */
-extern size_t my_regerror(int, const my_regex_t *, char *, size_t);
-
-
-/* === regexec.c === */
-extern int my_regexec(const my_regex_t *, const char *, size_t, my_regmatch_t [], int);
-#define REG_NOTBOL 00001
-#define REG_NOTEOL 00002
-#define REG_STARTEND 00004
-#define REG_TRACE 00400 /* tracing of execution */
-#define REG_LARGE 01000 /* force large representation */
-#define REG_BACKR 02000 /* force use of backref code */
-
-
-/* === regfree.c === */
-extern void my_regfree(my_regex_t *);
-
-/* === reginit.c === */
-
-/* Should be called for multithread progs */
-extern void my_regex_init(CHARSET_INFO *cs, my_regex_stack_check_t func);
-extern void my_regex_end(void); /* If one wants a clean end */
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
-#endif
diff --git a/regex/regcomp.c b/regex/regcomp.c
deleted file mode 100644
index abc18174f56..00000000000
--- a/regex/regcomp.c
+++ /dev/null
@@ -1,1610 +0,0 @@
-#include <my_global.h>
-#include <m_string.h>
-#include <m_ctype.h>
-#ifdef __WIN__
-#include <limits.h>
-#endif
-
-#include "my_regex.h"
-#include "utils.h"
-#include "regex2.h"
-
-#include "cclass.h"
-#include "cname.h"
-
-/*
- * parse structure, passed up and down to avoid global variables and
- * other clumsinesses
- */
-struct parse {
- char *next; /* next character in RE */
- char *end; /* end of string (-> NUL normally) */
- int error; /* has an error been seen? */
- sop *strip; /* malloced strip */
- sopno ssize; /* malloced strip size (allocated) */
- sopno slen; /* malloced strip length (used) */
- int ncsalloc; /* number of csets allocated */
- struct re_guts *g;
-# define NPAREN 10 /* we need to remember () 1-9 for back refs */
- sopno pbegin[NPAREN]; /* -> ( ([0] unused) */
- sopno pend[NPAREN]; /* -> ) ([0] unused) */
- CHARSET_INFO *charset; /* for ctype things */
-};
-
-/* Check if there is enough stack space for recursion. */
-my_regex_stack_check_t my_regex_enough_mem_in_stack= NULL;
-
-#include "regcomp.ih"
-
-static char nuls[10]; /* place to point scanner in event of error */
-
-struct cclass cclasses[CCLASS_LAST+1]= {
- { "alnum", "","", _MY_U | _MY_L | _MY_NMR},
- { "alpha", "","", _MY_U | _MY_L },
- { "blank", "","", _MY_B },
- { "cntrl", "","", _MY_CTR },
- { "digit", "","", _MY_NMR },
- { "graph", "","", _MY_PNT | _MY_U | _MY_L | _MY_NMR},
- { "lower", "","", _MY_L },
- { "print", "","", _MY_PNT | _MY_U | _MY_L | _MY_NMR | _MY_B },
- { "punct", "","", _MY_PNT },
- { "space", "","", _MY_SPC },
- { "upper", "","", _MY_U },
- { "xdigit", "","", _MY_X },
- { NULL,NULL,NULL, 0 }
-};
-
-/*
- * macros for use with parse structure
- * BEWARE: these know that the parse structure is named `p' !!!
- */
-#define PEEK() (*p->next)
-#define PEEK2() (*(p->next+1))
-#define MORE() (p->next < p->end)
-#define MORE2() (p->next+1 < p->end)
-#define SEE(c) (MORE() && PEEK() == (c))
-#define SEETWO(a, b) (MORE() && MORE2() && PEEK() == (a) && PEEK2() == (b))
-#define EAT(c) ((SEE(c)) ? (NEXT(), 1) : 0)
-#define EATTWO(a, b) ((SEETWO(a, b)) ? (NEXT2(), 1) : 0)
-#define NEXT() (p->next++)
-#define NEXT2() (p->next += 2)
-#define NEXTn(n) (p->next += (n))
-#define GETNEXT() (*p->next++)
-#define SETERROR(e) seterr(p, (e))
-#define REQUIRE(co, e) ((co) || SETERROR(e))
-#define MUSTSEE(c, e) (REQUIRE(MORE() && PEEK() == (c), e))
-#define MUSTEAT(c, e) (REQUIRE(MORE() && GETNEXT() == (c), e))
-#define MUSTNOTSEE(c, e) (REQUIRE(!MORE() || PEEK() != (c), e))
-#define EMIT(op, sopnd) doemit(p, (sop)(op), (size_t)(sopnd))
-#define INSERT(op, pos) doinsert(p, (sop)(op), HERE()-(pos)+1, pos)
-#define AHEAD(pos) dofwd(p, pos, HERE()-(pos))
-#define ASTERN(sop, pos) EMIT(sop, HERE()-pos)
-#define HERE() (p->slen)
-#define THERE() (p->slen - 1)
-#define THERETHERE() (p->slen - 2)
-#define DROP(n) (p->slen -= (n))
-
-#ifndef NDEBUG
-static int never = 0; /* for use in asserts; shuts lint up */
-#else
-#define never 0 /* some <assert.h>s have bugs too */
-#endif
-
-/*
- - regcomp - interface for parser and compilation
- = extern int regcomp(regex_t *, const char *, int);
- = #define REG_BASIC 0000
- = #define REG_EXTENDED 0001
- = #define REG_ICASE 0002
- = #define REG_NOSUB 0004
- = #define REG_NEWLINE 0010
- = #define REG_NOSPEC 0020
- = #define REG_PEND 0040
- = #define REG_DUMP 0200
- */
-int /* 0 success, otherwise REG_something */
-my_regcomp(preg, pattern, cflags, charset)
-my_regex_t *preg;
-const char *pattern;
-int cflags;
-CHARSET_INFO *charset;
-{
- struct parse pa;
- register struct re_guts *g;
- register struct parse *p = &pa;
- register int i;
- register size_t len;
-#ifdef REDEBUG
-# define GOODFLAGS(f) (f)
-#else
-# define GOODFLAGS(f) ((f)&~REG_DUMP)
-#endif
-
- my_regex_init(charset, NULL); /* Init cclass if neaded */
- preg->charset=charset;
- cflags = GOODFLAGS(cflags);
- if ((cflags&REG_EXTENDED) && (cflags&REG_NOSPEC))
- return(REG_INVARG);
-
- if (cflags&REG_PEND) {
- if (preg->re_endp < pattern)
- return(REG_INVARG);
- len = preg->re_endp - pattern;
- } else
- len = strlen((char *)pattern);
-
- /* do the mallocs early so failure handling is easy */
- g = (struct re_guts *)malloc(sizeof(struct re_guts) +
- (NC-1)*sizeof(cat_t));
- if (g == NULL)
- return(REG_ESPACE);
- p->ssize = (long) (len/(size_t)2*(size_t)3 + (size_t)1); /* ugh */
- p->strip = (sop *)malloc(p->ssize * sizeof(sop));
- p->slen = 0;
- if (p->strip == NULL) {
- free((char *)g);
- return(REG_ESPACE);
- }
-
- /* set things up */
- p->g = g;
- p->next = (char *)pattern; /* convenience; we do not modify it */
- p->end = p->next + len;
- p->error = 0;
- p->ncsalloc = 0;
- p->charset = preg->charset;
- for (i = 0; i < NPAREN; i++) {
- p->pbegin[i] = 0;
- p->pend[i] = 0;
- }
- g->csetsize = NC;
- g->sets = NULL;
- g->setbits = NULL;
- g->ncsets = 0;
- g->cflags = cflags;
- g->iflags = 0;
- g->nbol = 0;
- g->neol = 0;
- g->must = NULL;
- g->mlen = 0;
- g->nsub = 0;
- g->ncategories = 1; /* category 0 is "everything else" */
- g->categories = &g->catspace[-(CHAR_MIN)];
- (void) memset((char *)g->catspace, 0, NC*sizeof(cat_t));
- g->backrefs = 0;
-
- /* do it */
- EMIT(OEND, 0);
- g->firststate = THERE();
- if (cflags&REG_EXTENDED)
- p_ere(p, OUT);
- else if (cflags&REG_NOSPEC)
- p_str(p);
- else
- p_bre(p, OUT, OUT);
- EMIT(OEND, 0);
- g->laststate = THERE();
-
- /* tidy up loose ends and fill things in */
- categorize(p, g);
- stripsnug(p, g);
- findmust(p, g);
- g->nplus = pluscount(p, g);
- g->magic = MAGIC2;
- preg->re_nsub = g->nsub;
- preg->re_g = g;
- preg->re_magic = MAGIC1;
-#ifndef REDEBUG
- /* not debugging, so can't rely on the assert() in regexec() */
- if (g->iflags&BAD)
- SETERROR(REG_ASSERT);
-#endif
-
- /* win or lose, we're done */
- if (p->error != 0) /* lose */
- my_regfree(preg);
- return(p->error);
-}
-
-/*
- - p_ere - ERE parser top level, concatenation and alternation
- == static void p_ere(register struct parse *p, int stop);
- */
-static void
-p_ere(p, stop)
-register struct parse *p;
-int stop; /* character this ERE should end at */
-{
- register char c;
- register sopno UNINIT_VAR(prevback);
- register sopno UNINIT_VAR(prevfwd);
- register sopno conc;
- register int first = 1; /* is this the first alternative? */
-
- for (;;) {
- /* do a bunch of concatenated expressions */
- conc = HERE();
- while (MORE() && (c = PEEK()) != '|' && c != stop)
- {
- if (my_regex_enough_mem_in_stack &&
- my_regex_enough_mem_in_stack(0))
- {
- SETERROR(REG_ESPACE);
- return;
- }
- p_ere_exp(p);
- }
- if(REQUIRE(HERE() != conc, REG_EMPTY)) {}/* require nonempty */
-
- if (!EAT('|'))
- break; /* NOTE BREAK OUT */
-
- if (first) {
- INSERT(OCH_, conc); /* offset is wrong */
- prevfwd = conc;
- prevback = conc;
- first = 0;
- }
- ASTERN(OOR1, prevback);
- prevback = THERE();
- AHEAD(prevfwd); /* fix previous offset */
- prevfwd = HERE();
- EMIT(OOR2, 0); /* offset is very wrong */
- }
-
- if (!first) { /* tail-end fixups */
- AHEAD(prevfwd);
- ASTERN(O_CH, prevback);
- }
-
- assert(!MORE() || SEE(stop));
-}
-
-/*
- - p_ere_exp - parse one subERE, an atom possibly followed by a repetition op
- == static void p_ere_exp(register struct parse *p);
- */
-static void
-p_ere_exp(p)
-register struct parse *p;
-{
- register char c;
- register sopno pos;
- register int count;
- register int count2;
- register sopno subno;
- int wascaret = 0;
-
- assert(MORE()); /* caller should have ensured this */
- c = GETNEXT();
-
- pos = HERE();
- switch (c) {
- case '(':
- if(REQUIRE(MORE(), REG_EPAREN)) {}
- p->g->nsub++;
- subno = (sopno) p->g->nsub;
- if (subno < NPAREN)
- p->pbegin[subno] = HERE();
- EMIT(OLPAREN, subno);
- if (!SEE(')'))
- p_ere(p, ')');
- if (subno < NPAREN) {
- p->pend[subno] = HERE();
- assert(p->pend[subno] != 0);
- }
- EMIT(ORPAREN, subno);
- if(MUSTEAT(')', REG_EPAREN)) {}
- break;
- case '^':
- EMIT(OBOL, 0);
- p->g->iflags |= USEBOL;
- p->g->nbol++;
- wascaret = 1;
- break;
- case '$':
- EMIT(OEOL, 0);
- p->g->iflags |= USEEOL;
- p->g->neol++;
- break;
- case '|':
- SETERROR(REG_EMPTY);
- break;
- case '*':
- case '+':
- case '?':
- SETERROR(REG_BADRPT);
- break;
- case '.':
- if (p->g->cflags&REG_NEWLINE)
- nonnewline(p);
- else
- EMIT(OANY, 0);
- break;
- case '[':
- p_bracket(p);
- break;
- case '\\':
- if(REQUIRE(MORE(), REG_EESCAPE)) {}
- c = GETNEXT();
- ordinary(p, c);
- break;
- case '{': /* okay as ordinary except if digit follows */
- if(REQUIRE(!MORE() || !my_isdigit(p->charset,PEEK()), REG_BADRPT)) {}
- /* FALLTHROUGH */
- default:
- ordinary(p, c);
- break;
- }
-
- if (!MORE())
- return;
- c = PEEK();
- /* we call { a repetition if followed by a digit */
- if (!( c == '*' || c == '+' || c == '?' ||
- (c == '{' && MORE2() &&
- my_isdigit(p->charset,PEEK2())) ))
- return; /* no repetition, we're done */
- NEXT();
-
- if(REQUIRE(!wascaret, REG_BADRPT)) {}
- switch (c) {
- case '*': /* implemented as +? */
- /* this case does not require the (y|) trick, noKLUDGE */
- INSERT(OPLUS_, pos);
- ASTERN(O_PLUS, pos);
- INSERT(OQUEST_, pos);
- ASTERN(O_QUEST, pos);
- break;
- case '+':
- INSERT(OPLUS_, pos);
- ASTERN(O_PLUS, pos);
- break;
- case '?':
- /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
- INSERT(OCH_, pos); /* offset slightly wrong */
- ASTERN(OOR1, pos); /* this one's right */
- AHEAD(pos); /* fix the OCH_ */
- EMIT(OOR2, 0); /* offset very wrong... */
- AHEAD(THERE()); /* ...so fix it */
- ASTERN(O_CH, THERETHERE());
- break;
- case '{':
- count = p_count(p);
- if (EAT(',')) {
- if (my_isdigit(p->charset,PEEK())) {
- count2 = p_count(p);
- if(REQUIRE(count <= count2, REG_BADBR)) {}
- } else /* single number with comma */
- count2 = RE_INFINITY;
- } else /* just a single number */
- count2 = count;
- repeat(p, pos, count, count2);
- if (!EAT('}')) { /* error heuristics */
- while (MORE() && PEEK() != '}')
- NEXT();
- if(REQUIRE(MORE(), REG_EBRACE)) {}
- SETERROR(REG_BADBR);
- }
- break;
- }
-
- if (!MORE())
- return;
- c = PEEK();
- if (!( c == '*' || c == '+' || c == '?' ||
- (c == '{' && MORE2() &&
- my_isdigit(p->charset,PEEK2())) ) )
- return;
- SETERROR(REG_BADRPT);
-}
-
-/*
- - p_str - string (no metacharacters) "parser"
- == static void p_str(register struct parse *p);
- */
-static void
-p_str(p)
-register struct parse *p;
-{
- if(REQUIRE(MORE(), REG_EMPTY)) {}
- while (MORE())
- ordinary(p, GETNEXT());
-}
-
-/*
- - p_bre - BRE parser top level, anchoring and concatenation
- == static void p_bre(register struct parse *p, register int end1, \
- == register int end2);
- * Giving end1 as OUT essentially eliminates the end1/end2 check.
- *
- * This implementation is a bit of a kludge, in that a trailing $ is first
- * taken as an ordinary character and then revised to be an anchor. The
- * only undesirable side effect is that '$' gets included as a character
- * category in such cases. This is fairly harmless; not worth fixing.
- * The amount of lookahead needed to avoid this kludge is excessive.
- */
-static void
-p_bre(p, end1, end2)
-register struct parse *p;
-register int end1; /* first terminating character */
-register int end2; /* second terminating character */
-{
- register sopno start = HERE();
- register int first = 1; /* first subexpression? */
- register int wasdollar = 0;
-
- if (EAT('^')) {
- EMIT(OBOL, 0);
- p->g->iflags |= USEBOL;
- p->g->nbol++;
- }
- while (MORE() && !SEETWO(end1, end2)) {
- wasdollar = p_simp_re(p, first);
- first = 0;
- }
- if (wasdollar) { /* oops, that was a trailing anchor */
- DROP(1);
- EMIT(OEOL, 0);
- p->g->iflags |= USEEOL;
- p->g->neol++;
- }
-
- if(REQUIRE(HERE() != start, REG_EMPTY)) {} /* require nonempty */
-}
-
-/*
- - p_simp_re - parse a simple RE, an atom possibly followed by a repetition
- == static int p_simp_re(register struct parse *p, int starordinary);
- */
-static int /* was the simple RE an unbackslashed $? */
-p_simp_re(p, starordinary)
-register struct parse *p;
-int starordinary; /* is a leading * an ordinary character? */
-{
- register int c;
- register int count;
- register int count2;
- register sopno pos;
- register int i;
- register sopno subno;
-# define BACKSL (1<<CHAR_BIT)
-
- pos = HERE(); /* repetion op, if any, covers from here */
-
- assert(MORE()); /* caller should have ensured this */
- c = GETNEXT();
- if (c == '\\') {
- if(REQUIRE(MORE(), REG_EESCAPE)) {}
- c = BACKSL | (unsigned char)GETNEXT();
- }
- switch (c) {
- case '.':
- if (p->g->cflags&REG_NEWLINE)
- nonnewline(p);
- else
- EMIT(OANY, 0);
- break;
- case '[':
- p_bracket(p);
- break;
- case BACKSL|'{':
- SETERROR(REG_BADRPT);
- break;
- case BACKSL|'(':
- p->g->nsub++;
- subno = (sopno) p->g->nsub;
- if (subno < NPAREN)
- p->pbegin[subno] = HERE();
- EMIT(OLPAREN, subno);
- /* the MORE here is an error heuristic */
- if (MORE() && !SEETWO('\\', ')'))
- p_bre(p, '\\', ')');
- if (subno < NPAREN) {
- p->pend[subno] = HERE();
- assert(p->pend[subno] != 0);
- }
- EMIT(ORPAREN, subno);
- if(REQUIRE(EATTWO('\\', ')'), REG_EPAREN)) {}
- break;
- case BACKSL|')': /* should not get here -- must be user */
- case BACKSL|'}':
- SETERROR(REG_EPAREN);
- break;
- case BACKSL|'1':
- case BACKSL|'2':
- case BACKSL|'3':
- case BACKSL|'4':
- case BACKSL|'5':
- case BACKSL|'6':
- case BACKSL|'7':
- case BACKSL|'8':
- case BACKSL|'9':
- i = (c&~BACKSL) - '0';
- assert(i < NPAREN);
- if (p->pend[i] != 0) {
- assert((uint) i <= p->g->nsub);
- EMIT(OBACK_, i);
- assert(p->pbegin[i] != 0);
- assert(OP(p->strip[p->pbegin[i]]) == OLPAREN);
- assert(OP(p->strip[p->pend[i]]) == ORPAREN);
- (void) dupl(p, p->pbegin[i]+1, p->pend[i]);
- EMIT(O_BACK, i);
- } else
- SETERROR(REG_ESUBREG);
- p->g->backrefs = 1;
- break;
- case '*':
- if(REQUIRE(starordinary, REG_BADRPT)) {}
- /* FALLTHROUGH */
- default:
- ordinary(p, c &~ BACKSL);
- break;
- }
-
- if (EAT('*')) { /* implemented as +? */
- /* this case does not require the (y|) trick, noKLUDGE */
- INSERT(OPLUS_, pos);
- ASTERN(O_PLUS, pos);
- INSERT(OQUEST_, pos);
- ASTERN(O_QUEST, pos);
- } else if (EATTWO('\\', '{')) {
- count = p_count(p);
- if (EAT(',')) {
- if (MORE() && my_isdigit(p->charset,PEEK())) {
- count2 = p_count(p);
- if(REQUIRE(count <= count2, REG_BADBR)) {}
- } else /* single number with comma */
- count2 = RE_INFINITY;
- } else /* just a single number */
- count2 = count;
- repeat(p, pos, count, count2);
- if (!EATTWO('\\', '}')) { /* error heuristics */
- while (MORE() && !SEETWO('\\', '}'))
- NEXT();
- if(REQUIRE(MORE(), REG_EBRACE)) {}
- SETERROR(REG_BADBR);
- }
- } else if (c == (unsigned char)'$') /* $ (but not \$) ends it */
- return(1);
-
- return(0);
-}
-
-/*
- - p_count - parse a repetition count
- == static int p_count(register struct parse *p);
- */
-static int /* the value */
-p_count(p)
-register struct parse *p;
-{
- register int count = 0;
- register int ndigits = 0;
-
- while (MORE() && my_isdigit(p->charset,PEEK()) && count <= DUPMAX) {
- count = count*10 + (GETNEXT() - '0');
- ndigits++;
- }
-
- if(REQUIRE(ndigits > 0 && count <= DUPMAX, REG_BADBR)) {}
- return(count);
-}
-
-/*
- - p_bracket - parse a bracketed character list
- == static void p_bracket(register struct parse *p);
- *
- * Note a significant property of this code: if the allocset() did SETERROR,
- * no set operations are done.
- */
-static void
-p_bracket(p)
-register struct parse *p;
-{
- register cset *cs = allocset(p);
- register int invert = 0;
-
- /* Dept of Truly Sickening Special-Case Kludges */
- if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) {
- EMIT(OBOW, 0);
- NEXTn(6);
- return;
- }
- if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) {
- EMIT(OEOW, 0);
- NEXTn(6);
- return;
- }
-
- if (EAT('^'))
- invert++; /* make note to invert set at end */
- if (EAT(']'))
- CHadd(cs, ']');
- else if (EAT('-'))
- CHadd(cs, '-');
- while (MORE() && PEEK() != ']' && !SEETWO('-', ']'))
- p_b_term(p, cs);
- if (EAT('-'))
- CHadd(cs, '-');
- if(MUSTEAT(']', REG_EBRACK)) {}
-
- if (p->error != 0) /* don't mess things up further */
- return;
-
- if (p->g->cflags&REG_ICASE) {
- register int i;
- register int ci;
-
- for (i = p->g->csetsize - 1; i >= 0; i--)
- if (CHIN(cs, i) && my_isalpha(p->charset,i)) {
- ci = othercase(p->charset,i);
- if (ci != i)
- CHadd(cs, ci);
- }
- if (cs->multis != NULL)
- mccase(p, cs);
- }
- if (invert) {
- register int i;
-
- for (i = p->g->csetsize - 1; i >= 0; i--)
- if (CHIN(cs, i))
- CHsub(cs, i);
- else
- CHadd(cs, i);
- if (p->g->cflags&REG_NEWLINE)
- CHsub(cs, '\n');
- if (cs->multis != NULL)
- mcinvert(p, cs);
- }
-
- assert(cs->multis == NULL); /* xxx */
-
- if (nch(p, cs) == 1) { /* optimize singleton sets */
- ordinary(p, firstch(p, cs));
- freeset(p, cs);
- } else
- EMIT(OANYOF, freezeset(p, cs));
-}
-
-/*
- - p_b_term - parse one term of a bracketed character list
- == static void p_b_term(register struct parse *p, register cset *cs);
- */
-static void
-p_b_term(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register char c;
- register char start, finish;
- register int i;
-
- /* classify what we've got */
- switch ((MORE()) ? PEEK() : '\0') {
- case '[':
- c = (MORE2()) ? PEEK2() : '\0';
- break;
- case '-':
- SETERROR(REG_ERANGE);
- return; /* NOTE RETURN */
- default:
- c = '\0';
- break;
- }
-
- switch (c) {
- case ':': /* character class */
- NEXT2();
- if(REQUIRE(MORE(), REG_EBRACK)) {}
- c = PEEK();
- if(REQUIRE(c != '-' && c != ']', REG_ECTYPE)) {}
- p_b_cclass(p, cs);
- if(REQUIRE(MORE(), REG_EBRACK)) {}
- if(REQUIRE(EATTWO(':', ']'), REG_ECTYPE)) {}
- break;
- case '=': /* equivalence class */
- NEXT2();
- if(REQUIRE(MORE(), REG_EBRACK)) {}
- c = PEEK();
- if(REQUIRE(c != '-' && c != ']', REG_ECOLLATE)) {}
- p_b_eclass(p, cs);
- if(REQUIRE(MORE(), REG_EBRACK)) {}
- if(REQUIRE(EATTWO('=', ']'), REG_ECOLLATE)) {}
- break;
- default: /* symbol, ordinary character, or range */
-/* xxx revision needed for multichar stuff */
- start = p_b_symbol(p);
- if (SEE('-') && MORE2() && PEEK2() != ']') {
- /* range */
- NEXT();
- if (EAT('-'))
- finish = '-';
- else
- finish = p_b_symbol(p);
- } else
- finish = start;
-/* xxx what about signed chars here... */
- if(REQUIRE(start <= finish, REG_ERANGE)) {}
- for (i = start; i <= finish; i++)
- CHadd(cs, i);
- break;
- }
-}
-
-/*
- - p_b_cclass - parse a character-class name and deal with it
- == static void p_b_cclass(register struct parse *p, register cset *cs);
- */
-static void
-p_b_cclass(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register char *sp = p->next;
- register struct cclass *cp;
- register size_t len;
-
- while (MORE() && my_isalpha(p->charset,PEEK()))
- NEXT();
- len = p->next - sp;
- for (cp = cclasses; cp->name != NULL; cp++)
- if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
- break;
- if (cp->name == NULL) {
- /* oops, didn't find it */
- SETERROR(REG_ECTYPE);
- return;
- }
-
-#ifndef USE_ORIG_REGEX_CODE
- {
- register size_t i;
- for (i=1 ; i<256 ; i++)
- if (p->charset->ctype[i+1] & cp->mask)
- CHadd(cs, i);
- }
-#else
- {
- register char *u = (char*) cp->chars;
- register char c;
-
- while ((c = *u++) != '\0')
- CHadd(cs, c);
-
- for (u = (char*) cp->multis; *u != '\0'; u += strlen(u) + 1)
- MCadd(p, cs, u);
- }
-#endif
-
-}
-
-/*
- - p_b_eclass - parse an equivalence-class name and deal with it
- == static void p_b_eclass(register struct parse *p, register cset *cs);
- *
- * This implementation is incomplete. xxx
- */
-static void
-p_b_eclass(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register char c;
-
- c = p_b_coll_elem(p, '=');
- CHadd(cs, c);
-}
-
-/*
- - p_b_symbol - parse a character or [..]ed multicharacter collating symbol
- == static char p_b_symbol(register struct parse *p);
- */
-static char /* value of symbol */
-p_b_symbol(p)
-register struct parse *p;
-{
- register char value;
-
- if(REQUIRE(MORE(), REG_EBRACK)) {}
- if (!EATTWO('[', '.'))
- return(GETNEXT());
-
- /* collating symbol */
- value = p_b_coll_elem(p, '.');
- if(REQUIRE(EATTWO('.', ']'), REG_ECOLLATE)) {}
- return(value);
-}
-
-/*
- - p_b_coll_elem - parse a collating-element name and look it up
- == static char p_b_coll_elem(register struct parse *p, int endc);
- */
-static char /* value of collating element */
-p_b_coll_elem(p, endc)
-register struct parse *p;
-int endc; /* name ended by endc,']' */
-{
- register char *sp = p->next;
- register struct cname *cp;
-#ifdef _WIN64
- register __int64 len;
-#else
- register int len;
-#endif
- while (MORE() && !SEETWO(endc, ']'))
- NEXT();
- if (!MORE()) {
- SETERROR(REG_EBRACK);
- return(0);
- }
- len = p->next - sp;
- for (cp = cnames; cp->name != NULL; cp++)
- if (strncmp(cp->name, sp, len) == 0 && cp->name[len] == '\0')
- return(cp->code); /* known name */
- if (len == 1)
- return(*sp); /* single character */
- SETERROR(REG_ECOLLATE); /* neither */
- return(0);
-}
-
-/*
- - othercase - return the case counterpart of an alphabetic
- == static char othercase(int ch);
- */
-static char /* if no counterpart, return ch */
-othercase(charset,ch)
-CHARSET_INFO *charset;
-int ch;
-{
- /*
- In MySQL some multi-byte character sets
- have 'ctype' array but don't have 'to_lower'
- and 'to_upper' arrays. In this case we handle
- only basic latin letters a..z and A..Z.
-
- If 'to_lower' and 'to_upper' arrays are empty in a character set,
- then my_isalpha(cs, ch) should never return TRUE for characters
- other than basic latin letters. Otherwise it should be
- considered as a mistake in character set definition.
- */
- assert(my_isalpha(charset,ch));
- if (my_isupper(charset,ch))
- {
- return(charset->to_lower ? my_tolower(charset,ch) :
- ch - 'A' + 'a');
- }
- else if (my_islower(charset,ch))
- {
- return(charset->to_upper ? my_toupper(charset,ch) :
- ch - 'a' + 'A');
- }
- else /* peculiar, but could happen */
- return(ch);
-}
-
-/*
- - bothcases - emit a dualcase version of a two-case character
- == static void bothcases(register struct parse *p, int ch);
- *
- * Boy, is this implementation ever a kludge...
- */
-static void
-bothcases(p, ch)
-register struct parse *p;
-int ch;
-{
- register char *oldnext = p->next;
- register char *oldend = p->end;
- char bracket[3];
-
- assert(othercase(p->charset, ch) != ch); /* p_bracket() would recurse */
- p->next = bracket;
- p->end = bracket+2;
- bracket[0] = ch;
- bracket[1] = ']';
- bracket[2] = '\0';
- p_bracket(p);
- assert(p->next == bracket+2);
- p->next = oldnext;
- p->end = oldend;
-}
-
-/*
- - ordinary - emit an ordinary character
- == static void ordinary(register struct parse *p, register int ch);
- */
-static void
-ordinary(p, ch)
-register struct parse *p;
-register int ch;
-{
- register cat_t *cap = p->g->categories;
-
- if ((p->g->cflags&REG_ICASE) && my_isalpha(p->charset,ch) &&
- othercase(p->charset,ch) != ch)
- bothcases(p, ch);
- else {
- EMIT(OCHAR, (unsigned char)ch);
- if (cap[ch] == 0)
- cap[ch] = p->g->ncategories++;
- }
-}
-
-/*
- - nonnewline - emit REG_NEWLINE version of OANY
- == static void nonnewline(register struct parse *p);
- *
- * Boy, is this implementation ever a kludge...
- */
-static void
-nonnewline(p)
-register struct parse *p;
-{
- register char *oldnext = p->next;
- register char *oldend = p->end;
- char bracket[4];
-
- p->next = bracket;
- p->end = bracket+3;
- bracket[0] = '^';
- bracket[1] = '\n';
- bracket[2] = ']';
- bracket[3] = '\0';
- p_bracket(p);
- assert(p->next == bracket+3);
- p->next = oldnext;
- p->end = oldend;
-}
-
-/*
- - repeat - generate code for a bounded repetition, recursively if needed
- == static void repeat(register struct parse *p, sopno start, int from, int to);
- */
-static void
-repeat(p, start, from, to)
-register struct parse *p;
-sopno start; /* operand from here to end of strip */
-int from; /* repeated from this number */
-int to; /* to this number of times (maybe RE_INFINITY) */
-{
- register sopno finish = HERE();
-# define N 2
-# define INF 3
-# define REP(f, t) ((f)*8 + (t))
-# define MAP(n) (((n) <= 1) ? (n) : ((n) == RE_INFINITY) ? INF : N)
- register sopno copy;
-
- if (p->error != 0) /* head off possible runaway recursion */
- return;
-
- assert(from <= to);
-
- switch (REP(MAP(from), MAP(to))) {
- case REP(0, 0): /* must be user doing this */
- DROP(finish-start); /* drop the operand */
- break;
- case REP(0, 1): /* as x{1,1}? */
- case REP(0, N): /* as x{1,n}? */
- case REP(0, INF): /* as x{1,}? */
- /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
- INSERT(OCH_, start); /* offset is wrong... */
- repeat(p, start+1, 1, to);
- ASTERN(OOR1, start);
- AHEAD(start); /* ... fix it */
- EMIT(OOR2, 0);
- AHEAD(THERE());
- ASTERN(O_CH, THERETHERE());
- break;
- case REP(1, 1): /* trivial case */
- /* done */
- break;
- case REP(1, N): /* as x?x{1,n-1} */
- /* KLUDGE: emit y? as (y|) until subtle bug gets fixed */
- INSERT(OCH_, start);
- ASTERN(OOR1, start);
- AHEAD(start);
- EMIT(OOR2, 0); /* offset very wrong... */
- AHEAD(THERE()); /* ...so fix it */
- ASTERN(O_CH, THERETHERE());
- copy = dupl(p, start+1, finish+1);
- assert(copy == finish+4);
- repeat(p, copy, 1, to-1);
- break;
- case REP(1, INF): /* as x+ */
- INSERT(OPLUS_, start);
- ASTERN(O_PLUS, start);
- break;
- case REP(N, N): /* as xx{m-1,n-1} */
- copy = dupl(p, start, finish);
- repeat(p, copy, from-1, to-1);
- break;
- case REP(N, INF): /* as xx{n-1,INF} */
- copy = dupl(p, start, finish);
- repeat(p, copy, from-1, to);
- break;
- default: /* "can't happen" */
- SETERROR(REG_ASSERT); /* just in case */
- break;
- }
-}
-
-/*
- - seterr - set an error condition
- == static int seterr(register struct parse *p, int e);
- */
-static int /* useless but makes type checking happy */
-seterr(p, e)
-register struct parse *p;
-int e;
-{
- if (p->error == 0) /* keep earliest error condition */
- p->error = e;
- p->next = nuls; /* try to bring things to a halt */
- p->end = nuls;
- return(0); /* make the return value well-defined */
-}
-
-/*
- - allocset - allocate a set of characters for []
- == static cset *allocset(register struct parse *p);
- */
-static cset *
-allocset(p)
-register struct parse *p;
-{
- register int no = p->g->ncsets++;
- register size_t nc;
- register size_t nbytes;
- register cset *cs;
- register size_t css = (size_t)p->g->csetsize;
- register int i;
-
- if (no >= p->ncsalloc) { /* need another column of space */
- p->ncsalloc += CHAR_BIT;
- nc = p->ncsalloc;
- assert(nc % CHAR_BIT == 0);
- nbytes = nc / CHAR_BIT * css;
- if (p->g->sets == NULL)
- p->g->sets = (cset *)malloc(nc * sizeof(cset));
- else
- p->g->sets = (cset *)realloc((char *)p->g->sets,
- nc * sizeof(cset));
- if (p->g->setbits == NULL)
- p->g->setbits = (uch *)malloc(nbytes);
- else {
- p->g->setbits = (uch *)realloc((char *)p->g->setbits,
- nbytes);
- /* xxx this isn't right if setbits is now NULL */
- for (i = 0; i < no; i++)
- p->g->sets[i].ptr = p->g->setbits + css*(i/CHAR_BIT);
- }
- if (p->g->sets != NULL && p->g->setbits != NULL)
- (void) memset((char *)p->g->setbits + (nbytes - css),
- 0, css);
- else {
- no = 0;
- SETERROR(REG_ESPACE);
- /* caller's responsibility not to do set ops */
- }
- }
-
- assert(p->g->sets != NULL); /* xxx */
- cs = &p->g->sets[no];
- cs->ptr = p->g->setbits + css*((no)/CHAR_BIT);
- cs->mask = 1 << ((no) % CHAR_BIT);
- cs->hash = 0;
- cs->smultis = 0;
- cs->multis = NULL;
-
- return(cs);
-}
-
-/*
- - freeset - free a now-unused set
- == static void freeset(register struct parse *p, register cset *cs);
- */
-static void
-freeset(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register size_t i;
- register cset *top = &p->g->sets[p->g->ncsets];
- register size_t css = (size_t)p->g->csetsize;
-
- for (i = 0; i < css; i++)
- CHsub(cs, i);
- if (cs == top-1) /* recover only the easy case */
- p->g->ncsets--;
-}
-
-/*
- - freezeset - final processing on a set of characters
- == static int freezeset(register struct parse *p, register cset *cs);
- *
- * The main task here is merging identical sets. This is usually a waste
- * of time (although the hash code minimizes the overhead), but can win
- * big if REG_ICASE is being used. REG_ICASE, by the way, is why the hash
- * is done using addition rather than xor -- all ASCII [aA] sets xor to
- * the same value!
- */
-static int /* set number */
-freezeset(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register uch h = cs->hash;
- register size_t i;
- register cset *top = &p->g->sets[p->g->ncsets];
- register cset *cs2;
- register size_t css = (size_t)p->g->csetsize;
-
- /* look for an earlier one which is the same */
- for (cs2 = &p->g->sets[0]; cs2 < top; cs2++)
- if (cs2->hash == h && cs2 != cs) {
- /* maybe */
- for (i = 0; i < css; i++)
- if (!!CHIN(cs2, i) != !!CHIN(cs, i))
- break; /* no */
- if (i == css)
- break; /* yes */
- }
-
- if (cs2 < top) { /* found one */
- freeset(p, cs);
- cs = cs2;
- }
-
- return((int)(cs - p->g->sets));
-}
-
-/*
- - firstch - return first character in a set (which must have at least one)
- == static int firstch(register struct parse *p, register cset *cs);
- */
-static int /* character; there is no "none" value */
-firstch(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register size_t i;
- register size_t css = (size_t)p->g->csetsize;
-
- for (i = 0; i < css; i++)
- if (CHIN(cs, i))
- return((char)i);
- assert(never);
- return(0); /* arbitrary */
-}
-
-/*
- - nch - number of characters in a set
- == static int nch(register struct parse *p, register cset *cs);
- */
-static int
-nch(p, cs)
-register struct parse *p;
-register cset *cs;
-{
- register size_t i;
- register size_t css = (size_t)p->g->csetsize;
- register int n = 0;
-
- for (i = 0; i < css; i++)
- if (CHIN(cs, i))
- n++;
- return(n);
-}
-
-#ifdef USE_ORIG_REGEX_CODE
-/*
- - mcadd - add a collating element to a cset
- == static void mcadd(register struct parse *p, register cset *cs, \
- == register char *cp);
- */
-static void
-mcadd(p, cs, cp)
-register struct parse *p;
-register cset *cs;
-register char *cp;
-{
- register size_t oldend = cs->smultis;
-
- cs->smultis += strlen(cp) + 1;
- if (cs->multis == NULL)
- cs->multis = malloc(cs->smultis);
- else
- cs->multis = realloc(cs->multis, cs->smultis);
- if (cs->multis == NULL) {
- SETERROR(REG_ESPACE);
- return;
- }
-
- (void) strcpy(cs->multis + oldend - 1, cp);
- cs->multis[cs->smultis - 1] = '\0';
-}
-#endif
-
-/*
- - mcinvert - invert the list of collating elements in a cset
- == static void mcinvert(register struct parse *p, register cset *cs);
- *
- * This would have to know the set of possibilities. Implementation
- * is deferred.
- */
-static void
-mcinvert(p, cs)
- register struct parse *p __attribute__((unused));
- register cset *cs __attribute__((unused));
-{
- assert(cs->multis == NULL); /* xxx */
-}
-
-/*
- - mccase - add case counterparts of the list of collating elements in a cset
- == static void mccase(register struct parse *p, register cset *cs);
- *
- * This would have to know the set of possibilities. Implementation
- * is deferred.
- */
-static void
-mccase(p, cs)
-register struct parse *p __attribute__((unused));
-register cset *cs __attribute__((unused));
-{
- assert(cs->multis == NULL); /* xxx */
-}
-
-/*
- - isinsets - is this character in any sets?
- == static int isinsets(register struct re_guts *g, int c);
- */
-static int /* predicate */
-isinsets(g, c)
-register struct re_guts *g;
-int c;
-{
- register uch *col;
- register int i;
- register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
- register unsigned uc = (unsigned char)c;
-
- for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
- if (col[uc] != 0)
- return(1);
- return(0);
-}
-
-/*
- - samesets - are these two characters in exactly the same sets?
- == static int samesets(register struct re_guts *g, int c1, int c2);
- */
-static int /* predicate */
-samesets(g, c1, c2)
-register struct re_guts *g;
-int c1;
-int c2;
-{
- register uch *col;
- register int i;
- register int ncols = (g->ncsets+(CHAR_BIT-1)) / CHAR_BIT;
- register unsigned uc1 = (unsigned char)c1;
- register unsigned uc2 = (unsigned char)c2;
-
- for (i = 0, col = g->setbits; i < ncols; i++, col += g->csetsize)
- if (col[uc1] != col[uc2])
- return(0);
- return(1);
-}
-
-/*
- - categorize - sort out character categories
- == static void categorize(struct parse *p, register struct re_guts *g);
- */
-static void
-categorize(p, g)
-struct parse *p;
-register struct re_guts *g;
-{
- register cat_t *cats = g->categories;
- register int c;
- register int c2;
- register cat_t cat;
-
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- for (c = CHAR_MIN; c <= CHAR_MAX; c++)
- if (cats[c] == 0 && isinsets(g, c)) {
- cat = g->ncategories++;
- cats[c] = cat;
- for (c2 = c+1; c2 <= CHAR_MAX; c2++)
- if (cats[c2] == 0 && samesets(g, c, c2))
- cats[c2] = cat;
- }
-}
-
-/*
- - dupl - emit a duplicate of a bunch of sops
- == static sopno dupl(register struct parse *p, sopno start, sopno finish);
- */
-static sopno /* start of duplicate */
-dupl(p, start, finish)
-register struct parse *p;
-sopno start; /* from here */
-sopno finish; /* to this less one */
-{
- register sopno ret = HERE();
- register sopno len = finish - start;
-
- assert(finish >= start);
- if (len == 0)
- return(ret);
- enlarge(p, p->ssize + len); /* this many unexpected additions */
- assert(p->ssize >= p->slen + len);
- (void) memcpy((char *)(p->strip + p->slen),
- (char *)(p->strip + start), (size_t)len*sizeof(sop));
- p->slen += len;
- return(ret);
-}
-
-/*
- - doemit - emit a strip operator
- == static void doemit(register struct parse *p, sop op, size_t opnd);
- *
- * It might seem better to implement this as a macro with a function as
- * hard-case backup, but it's just too big and messy unless there are
- * some changes to the data structures. Maybe later.
- */
-static void
-doemit(p, op, opnd)
-register struct parse *p;
-sop op;
-size_t opnd;
-{
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- /* deal with oversize operands ("can't happen", more or less) */
- assert(opnd < 1<<OPSHIFT);
-
- /* deal with undersized strip */
- if (p->slen >= p->ssize)
- enlarge(p, (p->ssize+1) / 2 * 3); /* +50% */
- assert(p->slen < p->ssize);
-
- /* finally, it's all reduced to the easy case */
- p->strip[p->slen++] = SOP(op, opnd);
-}
-
-/*
- - doinsert - insert a sop into the strip
- == static void doinsert(register struct parse *p, sop op, size_t opnd, sopno pos);
- */
-static void
-doinsert(p, op, opnd, pos)
-register struct parse *p;
-sop op;
-size_t opnd;
-sopno pos;
-{
- register sopno sn;
- register sop s;
- register int i;
-
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- sn = HERE();
- EMIT(op, opnd); /* do checks, ensure space */
- assert(HERE() == sn+1);
- s = p->strip[sn];
-
- /* adjust paren pointers */
- assert(pos > 0);
- for (i = 1; i < NPAREN; i++) {
- if (p->pbegin[i] >= pos) {
- p->pbegin[i]++;
- }
- if (p->pend[i] >= pos) {
- p->pend[i]++;
- }
- }
- {
- int length=(HERE()-pos-1)*sizeof(sop);
- bmove_upp((uchar *) &p->strip[pos+1]+length,
- (uchar *) &p->strip[pos]+length,
- length);
- }
-#ifdef OLD_CODE
- memmove((char *)&p->strip[pos+1], (char *)&p->strip[pos],
- (HERE()-pos-1)*sizeof(sop));
-#endif
- p->strip[pos] = s;
-}
-
-/*
- - dofwd - complete a forward reference
- == static void dofwd(register struct parse *p, sopno pos, sop value);
- */
-static void
-dofwd(p, pos, value)
-register struct parse *p;
-register sopno pos;
-sop value;
-{
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- assert(value < 1<<OPSHIFT);
- p->strip[pos] = OP(p->strip[pos]) | value;
-}
-
-/*
- - enlarge - enlarge the strip
- == static void enlarge(register struct parse *p, sopno size);
- */
-static void
-enlarge(p, size)
-register struct parse *p;
-register sopno size;
-{
- register sop *sp;
-
- if (p->ssize >= size)
- return;
-
- sp = (sop *)realloc(p->strip, size*sizeof(sop));
- if (sp == NULL) {
- SETERROR(REG_ESPACE);
- return;
- }
- p->strip = sp;
- p->ssize = size;
-}
-
-/*
- - stripsnug - compact the strip
- == static void stripsnug(register struct parse *p, register struct re_guts *g);
- */
-static void
-stripsnug(p, g)
-register struct parse *p;
-register struct re_guts *g;
-{
- g->nstates = p->slen;
- g->strip = (sop *)realloc((char *)p->strip, p->slen * sizeof(sop));
- if (g->strip == NULL) {
- SETERROR(REG_ESPACE);
- g->strip = p->strip;
- }
-}
-
-/*
- - findmust - fill in must and mlen with longest mandatory literal string
- == static void findmust(register struct parse *p, register struct re_guts *g);
- *
- * This algorithm could do fancy things like analyzing the operands of |
- * for common subsequences. Someday. This code is simple and finds most
- * of the interesting cases.
- *
- * Note that must and mlen got initialized during setup.
- */
-static void
-findmust(p, g)
-struct parse *p;
-register struct re_guts *g;
-{
- register sop *scan;
- sop *UNINIT_VAR(start);
- register sop *UNINIT_VAR(newstart);
- register sopno newlen;
- register sop s;
- register char *cp;
- register sopno i;
-
- /* avoid making error situations worse */
- if (p->error != 0)
- return;
-
- /* find the longest OCHAR sequence in strip */
- newlen = 0;
- scan = g->strip + 1;
- do {
- s = *scan++;
- switch (OP(s)) {
- case OCHAR: /* sequence member */
- if (newlen == 0) /* new sequence */
- newstart = scan - 1;
- newlen++;
- break;
- case OPLUS_: /* things that don't break one */
- case OLPAREN:
- case ORPAREN:
- break;
- case OQUEST_: /* things that must be skipped */
- case OCH_:
- scan--;
- do {
- scan += OPND(s);
- s = *scan;
- /* assert() interferes w debug printouts */
- if (OP(s) != O_QUEST && OP(s) != O_CH &&
- OP(s) != OOR2) {
- g->iflags |= BAD;
- return;
- }
- } while (OP(s) != O_QUEST && OP(s) != O_CH);
- /* fallthrough */
- default: /* things that break a sequence */
- if (newlen > g->mlen) { /* ends one */
- start = newstart;
- g->mlen = newlen;
- }
- newlen = 0;
- break;
- }
- } while (OP(s) != OEND);
-
- if (g->mlen == 0) /* there isn't one */
- return;
-
- /* turn it into a character string */
- g->must = malloc((size_t)g->mlen + 1);
- if (g->must == NULL) { /* argh; just forget it */
- g->mlen = 0;
- return;
- }
- cp = g->must;
- scan = start;
- for (i = g->mlen; i > 0; i--) {
- while (OP(s = *scan++) != OCHAR)
- continue;
- assert(cp < g->must + g->mlen);
- *cp++ = (char)OPND(s);
- }
- assert(cp == g->must + g->mlen);
- *cp++ = '\0'; /* just on general principles */
-}
-
-/*
- - pluscount - count + nesting
- == static sopno pluscount(register struct parse *p, register struct re_guts *g);
- */
-static sopno /* nesting depth */
-pluscount(p, g)
-struct parse *p;
-register struct re_guts *g;
-{
- register sop *scan;
- register sop s;
- register sopno plusnest = 0;
- register sopno maxnest = 0;
-
- if (p->error != 0)
- return(0); /* there may not be an OEND */
-
- scan = g->strip + 1;
- do {
- s = *scan++;
- switch (OP(s)) {
- case OPLUS_:
- plusnest++;
- break;
- case O_PLUS:
- if (plusnest > maxnest)
- maxnest = plusnest;
- plusnest--;
- break;
- }
- } while (OP(s) != OEND);
- if (plusnest != 0)
- g->iflags |= BAD;
- return(maxnest);
-}
diff --git a/regex/regcomp.ih b/regex/regcomp.ih
deleted file mode 100644
index cb93286e32f..00000000000
--- a/regex/regcomp.ih
+++ /dev/null
@@ -1,50 +0,0 @@
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* === regcomp.c === */
-static void p_ere(register struct parse *p, int stop);
-static void p_ere_exp(register struct parse *p);
-static void p_str(register struct parse *p);
-static void p_bre(register struct parse *p, register int end1, register int end2);
-static int p_simp_re(register struct parse *p, int starordinary);
-static int p_count(register struct parse *p);
-static void p_bracket(register struct parse *p);
-static void p_b_term(register struct parse *p, register cset *cs);
-static void p_b_cclass(register struct parse *p, register cset *cs);
-static void p_b_eclass(register struct parse *p, register cset *cs);
-static char p_b_symbol(register struct parse *p);
-static char p_b_coll_elem(register struct parse *p, int endc);
-static char othercase(CHARSET_INFO *charset,int ch);
-static void bothcases(register struct parse *p, int ch);
-static void ordinary(register struct parse *p, register int ch);
-static void nonnewline(register struct parse *p);
-static void repeat(register struct parse *p, sopno start, int from, int to);
-static int seterr(register struct parse *p, int e);
-static cset *allocset(register struct parse *p);
-static void freeset(register struct parse *p, register cset *cs);
-static int freezeset(register struct parse *p, register cset *cs);
-static int firstch(register struct parse *p, register cset *cs);
-static int nch(register struct parse *p, register cset *cs);
-#ifdef USE_ORIG_REGEX_CODE
-static void mcadd(register struct parse *p, register cset *cs, register char *cp);
-#endif
-static void mcinvert(register struct parse *p, register cset *cs);
-static void mccase(register struct parse *p, register cset *cs);
-static int isinsets(register struct re_guts *g, int c);
-static int samesets(register struct re_guts *g, int c1, int c2);
-static void categorize(struct parse *p, register struct re_guts *g);
-static sopno dupl(register struct parse *p, sopno start, sopno finish);
-static void doemit(register struct parse *p, sop op, size_t opnd);
-static void doinsert(register struct parse *p, sop op, size_t opnd, sopno pos);
-static void dofwd(register struct parse *p, sopno pos, sop value);
-static void enlarge(register struct parse *p, sopno size);
-static void stripsnug(register struct parse *p, register struct re_guts *g);
-static void findmust(register struct parse *p, register struct re_guts *g);
-static sopno pluscount(register struct parse *p, register struct re_guts *g);
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
diff --git a/regex/regerror.c b/regex/regerror.c
deleted file mode 100644
index 489f2e35abb..00000000000
--- a/regex/regerror.c
+++ /dev/null
@@ -1,116 +0,0 @@
-#include <my_global.h>
-#include <m_string.h>
-#include <m_ctype.h>
-
-#include "my_regex.h"
-#include "utils.h"
-#include "regerror.ih"
-
-/*
- = #define REG_NOMATCH 1
- = #define REG_BADPAT 2
- = #define REG_ECOLLATE 3
- = #define REG_ECTYPE 4
- = #define REG_EESCAPE 5
- = #define REG_ESUBREG 6
- = #define REG_EBRACK 7
- = #define REG_EPAREN 8
- = #define REG_EBRACE 9
- = #define REG_BADBR 10
- = #define REG_ERANGE 11
- = #define REG_ESPACE 12
- = #define REG_BADRPT 13
- = #define REG_EMPTY 14
- = #define REG_ASSERT 15
- = #define REG_INVARG 16
- = #define REG_ATOI 255 // convert name to number (!)
- = #define REG_ITOA 0400 // convert number to name (!)
- */
-static struct rerr {
- int code;
- const char *name;
- const char *explain;
-} rerrs[] = {
- {REG_NOMATCH, "REG_NOMATCH", "regexec() failed to match"},
- {REG_BADPAT, "REG_BADPAT", "invalid regular expression"},
- {REG_ECOLLATE, "REG_ECOLLATE", "invalid collating element"},
- {REG_ECTYPE, "REG_ECTYPE", "invalid character class"},
- {REG_EESCAPE, "REG_EESCAPE", "trailing backslash (\\)"},
- {REG_ESUBREG, "REG_ESUBREG", "invalid backreference number"},
- {REG_EBRACK, "REG_EBRACK", "brackets ([ ]) not balanced"},
- {REG_EPAREN, "REG_EPAREN", "parentheses not balanced"},
- {REG_EBRACE, "REG_EBRACE", "braces not balanced"},
- {REG_BADBR, "REG_BADBR", "invalid repetition count(s)"},
- {REG_ERANGE, "REG_ERANGE", "invalid character range"},
- {REG_ESPACE, "REG_ESPACE", "out of memory"},
- {REG_BADRPT, "REG_BADRPT", "repetition-operator operand invalid"},
- {REG_EMPTY, "REG_EMPTY", "empty (sub)expression"},
- {REG_ASSERT, "REG_ASSERT", "\"can't happen\" -- you found a bug"},
- {REG_INVARG, "REG_INVARG", "invalid argument to regex routine"},
- {0, "", "*** unknown regexp error code ***"},
-};
-
-/*
- - regerror - the interface to error numbers
- = extern size_t regerror(int, const regex_t *, char *, size_t);
- */
-/* ARGSUSED */
-size_t
-my_regerror(int errcode, const my_regex_t *preg, char *errbuf, size_t errbuf_size)
-{
- register struct rerr *r;
- register size_t len;
- register int target = errcode &~ REG_ITOA;
- register char *s;
- char convbuf[50];
-
- if (errcode == REG_ATOI)
- s = regatoi(preg, convbuf);
- else {
- for (r = rerrs; r->code != 0; r++)
- if (r->code == target)
- break;
-
- if (errcode&REG_ITOA) {
- if (r->code != 0)
- (void) strcpy(convbuf, r->name);
- else
- sprintf(convbuf, "REG_0x%x", target);
- assert(strlen(convbuf) < sizeof(convbuf));
- s = convbuf;
- } else
- s = (char*) r->explain;
- }
-
- len = strlen(s) + 1;
- if (errbuf_size > 0) {
- if (errbuf_size > len)
- (void) strcpy(errbuf, s);
- else {
- (void) strncpy(errbuf, s, errbuf_size-1);
- errbuf[errbuf_size-1] = '\0';
- }
- }
-
- return(len);
-}
-
-/*
- - regatoi - internal routine to implement REG_ATOI
- == static char *regatoi(const regex_t *preg, char *localbuf);
- */
-static char *
-regatoi(preg, localbuf)
-const my_regex_t *preg;
-char *localbuf;
-{
- register struct rerr *r;
- for (r = rerrs; r->code != 0; r++)
- if (strcmp(r->name, preg->re_endp) == 0)
- break;
- if (r->code == 0)
- return((char*) "0");
-
- sprintf(localbuf, "%d", r->code);
- return(localbuf);
-}
diff --git a/regex/regerror.ih b/regex/regerror.ih
deleted file mode 100644
index a4d048022f8..00000000000
--- a/regex/regerror.ih
+++ /dev/null
@@ -1,12 +0,0 @@
-/* ========= begin header generated by ./mkh ========= */
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/* === regerror.c === */
-static char *regatoi(const my_regex_t *preg, char *localbuf);
-
-#ifdef __cplusplus
-}
-#endif
-/* ========= end header generated by ./mkh ========= */
diff --git a/regex/regex.3 b/regex/regex.3
deleted file mode 100644
index 100c8a7f71c..00000000000
--- a/regex/regex.3
+++ /dev/null
@@ -1,502 +0,0 @@
-.TH REGEX 3 "17 May 1993"
-.BY "Henry Spencer"
-.de ZR
-.\" one other place knows this name: the SEE ALSO section
-.IR regex (7) \\$1
-..
-.SH NAME
-regcomp, regexec, regerror, regfree \- regular-expression library
-.SH SYNOPSIS
-.ft B
-.\".na
-#include <sys/types.h>
-.br
-#include <regex.h>
-.HP 10
-int regcomp(regex_t\ *preg, const\ char\ *pattern, int\ cflags);
-.HP
-int\ regexec(const\ regex_t\ *preg, const\ char\ *string,
-size_t\ nmatch, regmatch_t\ pmatch[], int\ eflags);
-.HP
-size_t\ regerror(int\ errcode, const\ regex_t\ *preg,
-char\ *errbuf, size_t\ errbuf_size);
-.HP
-void\ regfree(regex_t\ *preg);
-.\".ad
-.ft
-.SH DESCRIPTION
-These routines implement POSIX 1003.2 regular expressions (``RE''s);
-see
-.ZR .
-.I Regcomp
-compiles an RE written as a string into an internal form,
-.I regexec
-matches that internal form against a string and reports results,
-.I regerror
-transforms error codes from either into human-readable messages,
-and
-.I regfree
-frees any dynamically-allocated storage used by the internal form
-of an RE.
-.PP
-The header
-.I <regex.h>
-declares two structure types,
-.I regex_t
-and
-.IR regmatch_t ,
-the former for compiled internal forms and the latter for match reporting.
-It also declares the four functions,
-a type
-.IR regoff_t ,
-and a number of constants with names starting with ``REG_''.
-.PP
-.I Regcomp
-compiles the regular expression contained in the
-.I pattern
-string,
-subject to the flags in
-.IR cflags ,
-and places the results in the
-.I regex_t
-structure pointed to by
-.IR preg .
-.I Cflags
-is the bitwise OR of zero or more of the following flags:
-.IP REG_EXTENDED \w'REG_EXTENDED'u+2n
-Compile modern (``extended'') REs,
-rather than the obsolete (``basic'') REs that
-are the default.
-.IP REG_BASIC
-This is a synonym for 0,
-provided as a counterpart to REG_EXTENDED to improve readability.
-.IP REG_NOSPEC
-Compile with recognition of all special characters turned off.
-All characters are thus considered ordinary,
-so the ``RE'' is a literal string.
-This is an extension,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-REG_EXTENDED and REG_NOSPEC may not be used
-in the same call to
-.IR regcomp .
-.IP REG_ICASE
-Compile for matching that ignores upper/lower case distinctions.
-See
-.ZR .
-.IP REG_NOSUB
-Compile for matching that need only report success or failure,
-not what was matched.
-.IP REG_NEWLINE
-Compile for newline-sensitive matching.
-By default, newline is a completely ordinary character with no special
-meaning in either REs or strings.
-With this flag,
-`[^' bracket expressions and `.' never match newline,
-a `^' anchor matches the null string after any newline in the string
-in addition to its normal function,
-and the `$' anchor matches the null string before any newline in the
-string in addition to its normal function.
-.IP REG_PEND
-The regular expression ends,
-not at the first NUL,
-but just before the character pointed to by the
-.I re_endp
-member of the structure pointed to by
-.IR preg .
-The
-.I re_endp
-member is of type
-.IR const\ char\ * .
-This flag permits inclusion of NULs in the RE;
-they are considered ordinary characters.
-This is an extension,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-.PP
-When successful,
-.I regcomp
-returns 0 and fills in the structure pointed to by
-.IR preg .
-One member of that structure
-(other than
-.IR re_endp )
-is publicized:
-.IR re_nsub ,
-of type
-.IR size_t ,
-contains the number of parenthesized subexpressions within the RE
-(except that the value of this member is undefined if the
-REG_NOSUB flag was used).
-If
-.I regcomp
-fails, it returns a non-zero error code;
-see DIAGNOSTICS.
-.PP
-.I Regexec
-matches the compiled RE pointed to by
-.I preg
-against the
-.IR string ,
-subject to the flags in
-.IR eflags ,
-and reports results using
-.IR nmatch ,
-.IR pmatch ,
-and the returned value.
-The RE must have been compiled by a previous invocation of
-.IR regcomp .
-The compiled form is not altered during execution of
-.IR regexec ,
-so a single compiled RE can be used simultaneously by multiple threads.
-.PP
-By default,
-the NUL-terminated string pointed to by
-.I string
-is considered to be the text of an entire line, minus any terminating
-newline.
-The
-.I eflags
-argument is the bitwise OR of zero or more of the following flags:
-.IP REG_NOTBOL \w'REG_STARTEND'u+2n
-The first character of
-the string
-is not the beginning of a line, so the `^' anchor should not match before it.
-This does not affect the behavior of newlines under REG_NEWLINE.
-.IP REG_NOTEOL
-The NUL terminating
-the string
-does not end a line, so the `$' anchor should not match before it.
-This does not affect the behavior of newlines under REG_NEWLINE.
-.IP REG_STARTEND
-The string is considered to start at
-\fIstring\fR\ + \fIpmatch\fR[0].\fIrm_so\fR
-and to have a terminating NUL located at
-\fIstring\fR\ + \fIpmatch\fR[0].\fIrm_eo\fR
-(there need not actually be a NUL at that location),
-regardless of the value of
-.IR nmatch .
-See below for the definition of
-.IR pmatch
-and
-.IR nmatch .
-This is an extension,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-Note that a non-zero \fIrm_so\fR does not imply REG_NOTBOL;
-REG_STARTEND affects only the location of the string,
-not how it is matched.
-.PP
-See
-.ZR
-for a discussion of what is matched in situations where an RE or a
-portion thereof could match any of several substrings of
-.IR string .
-.PP
-Normally,
-.I regexec
-returns 0 for success and the non-zero code REG_NOMATCH for failure.
-Other non-zero error codes may be returned in exceptional situations;
-see DIAGNOSTICS.
-.PP
-If REG_NOSUB was specified in the compilation of the RE,
-or if
-.I nmatch
-is 0,
-.I regexec
-ignores the
-.I pmatch
-argument (but see below for the case where REG_STARTEND is specified).
-Otherwise,
-.I pmatch
-points to an array of
-.I nmatch
-structures of type
-.IR regmatch_t .
-Such a structure has at least the members
-.I rm_so
-and
-.IR rm_eo ,
-both of type
-.I regoff_t
-(a signed arithmetic type at least as large as an
-.I off_t
-and a
-.IR ssize_t ),
-containing respectively the offset of the first character of a substring
-and the offset of the first character after the end of the substring.
-Offsets are measured from the beginning of the
-.I string
-argument given to
-.IR regexec .
-An empty substring is denoted by equal offsets,
-both indicating the character following the empty substring.
-.PP
-The 0th member of the
-.I pmatch
-array is filled in to indicate what substring of
-.I string
-was matched by the entire RE.
-Remaining members report what substring was matched by parenthesized
-subexpressions within the RE;
-member
-.I i
-reports subexpression
-.IR i ,
-with subexpressions counted (starting at 1) by the order of their opening
-parentheses in the RE, left to right.
-Unused entries in the array\(emcorresponding either to subexpressions that
-did not participate in the match at all, or to subexpressions that do not
-exist in the RE (that is, \fIi\fR\ > \fIpreg\fR\->\fIre_nsub\fR)\(emhave both
-.I rm_so
-and
-.I rm_eo
-set to \-1.
-If a subexpression participated in the match several times,
-the reported substring is the last one it matched.
-(Note, as an example in particular, that when the RE `(b*)+' matches `bbb',
-the parenthesized subexpression matches each of the three `b's and then
-an infinite number of empty strings following the last `b',
-so the reported substring is one of the empties.)
-.PP
-If REG_STARTEND is specified,
-.I pmatch
-must point to at least one
-.I regmatch_t
-(even if
-.I nmatch
-is 0 or REG_NOSUB was specified),
-to hold the input offsets for REG_STARTEND.
-Use for output is still entirely controlled by
-.IR nmatch ;
-if
-.I nmatch
-is 0 or REG_NOSUB was specified,
-the value of
-.IR pmatch [0]
-will not be changed by a successful
-.IR regexec .
-.PP
-.I Regerror
-maps a non-zero
-.I errcode
-from either
-.I regcomp
-or
-.I regexec
-to a human-readable, printable message.
-If
-.I preg
-is non-NULL,
-the error code should have arisen from use of
-the
-.I regex_t
-pointed to by
-.IR preg ,
-and if the error code came from
-.IR regcomp ,
-it should have been the result from the most recent
-.I regcomp
-using that
-.IR regex_t .
-.RI ( Regerror
-may be able to supply a more detailed message using information
-from the
-.IR regex_t .)
-.I Regerror
-places the NUL-terminated message into the buffer pointed to by
-.IR errbuf ,
-limiting the length (including the NUL) to at most
-.I errbuf_size
-bytes.
-If the whole message won't fit,
-as much of it as will fit before the terminating NUL is supplied.
-In any case,
-the returned value is the size of buffer needed to hold the whole
-message (including terminating NUL).
-If
-.I errbuf_size
-is 0,
-.I errbuf
-is ignored but the return value is still correct.
-.PP
-If the
-.I errcode
-given to
-.I regerror
-is first ORed with REG_ITOA,
-the ``message'' that results is the printable name of the error code,
-e.g. ``REG_NOMATCH'',
-rather than an explanation thereof.
-If
-.I errcode
-is REG_ATOI,
-then
-.I preg
-shall be non-NULL and the
-.I re_endp
-member of the structure it points to
-must point to the printable name of an error code;
-in this case, the result in
-.I errbuf
-is the decimal digits of
-the numeric value of the error code
-(0 if the name is not recognized).
-REG_ITOA and REG_ATOI are intended primarily as debugging facilities;
-they are extensions,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-Be warned also that they are considered experimental and changes are possible.
-.PP
-.I Regfree
-frees any dynamically-allocated storage associated with the compiled RE
-pointed to by
-.IR preg .
-The remaining
-.I regex_t
-is no longer a valid compiled RE
-and the effect of supplying it to
-.I regexec
-or
-.I regerror
-is undefined.
-.PP
-None of these functions references global variables except for tables
-of constants;
-all are safe for use from multiple threads if the arguments are safe.
-.SH IMPLEMENTATION CHOICES
-There are a number of decisions that 1003.2 leaves up to the implementor,
-either by explicitly saying ``undefined'' or by virtue of them being
-forbidden by the RE grammar.
-This implementation treats them as follows.
-.PP
-See
-.ZR
-for a discussion of the definition of case-independent matching.
-.PP
-There is no particular limit on the length of REs,
-except insofar as memory is limited.
-Memory usage is approximately linear in RE size, and largely insensitive
-to RE complexity, except for bounded repetitions.
-See BUGS for one short RE using them
-that will run almost any system out of memory.
-.PP
-A backslashed character other than one specifically given a magic meaning
-by 1003.2 (such magic meanings occur only in obsolete [``basic''] REs)
-is taken as an ordinary character.
-.PP
-Any unmatched [ is a REG_EBRACK error.
-.PP
-Equivalence classes cannot begin or end bracket-expression ranges.
-The endpoint of one range cannot begin another.
-.PP
-RE_DUP_MAX, the limit on repetition counts in bounded repetitions, is 255.
-.PP
-A repetition operator (?, *, +, or bounds) cannot follow another
-repetition operator.
-A repetition operator cannot begin an expression or subexpression
-or follow `^' or `|'.
-.PP
-`|' cannot appear first or last in a (sub)expression or after another `|',
-i.e. an operand of `|' cannot be an empty subexpression.
-An empty parenthesized subexpression, `()', is legal and matches an
-empty (sub)string.
-An empty string is not a legal RE.
-.PP
-A `{' followed by a digit is considered the beginning of bounds for a
-bounded repetition, which must then follow the syntax for bounds.
-A `{' \fInot\fR followed by a digit is considered an ordinary character.
-.PP
-`^' and `$' beginning and ending subexpressions in obsolete (``basic'')
-REs are anchors, not ordinary characters.
-.SH SEE ALSO
-grep(1), regex(7)
-.PP
-POSIX 1003.2, sections 2.8 (Regular Expression Notation)
-and
-B.5 (C Binding for Regular Expression Matching).
-.SH DIAGNOSTICS
-Non-zero error codes from
-.I regcomp
-and
-.I regexec
-include the following:
-.PP
-.nf
-.ta \w'REG_ECOLLATE'u+3n
-REG_NOMATCH regexec() failed to match
-REG_BADPAT invalid regular expression
-REG_ECOLLATE invalid collating element
-REG_ECTYPE invalid character class
-REG_EESCAPE \e applied to unescapable character
-REG_ESUBREG invalid backreference number
-REG_EBRACK brackets [ ] not balanced
-REG_EPAREN parentheses ( ) not balanced
-REG_EBRACE braces { } not balanced
-REG_BADBR invalid repetition count(s) in { }
-REG_ERANGE invalid character range in [ ]
-REG_ESPACE ran out of memory
-REG_BADRPT ?, *, or + operand invalid
-REG_EMPTY empty (sub)expression
-REG_ASSERT ``can't happen''\(emyou found a bug
-REG_INVARG invalid argument, e.g. negative-length string
-.fi
-.SH HISTORY
-Written by Henry Spencer at University of Toronto,
-henry@zoo.toronto.edu.
-.SH BUGS
-This is an alpha release with known defects.
-Please report problems.
-.PP
-There is one known functionality bug.
-The implementation of internationalization is incomplete:
-the locale is always assumed to be the default one of 1003.2,
-and only the collating elements etc. of that locale are available.
-.PP
-The back-reference code is subtle and doubts linger about its correctness
-in complex cases.
-.PP
-.I Regexec
-performance is poor.
-This will improve with later releases.
-.I Nmatch
-exceeding 0 is expensive;
-.I nmatch
-exceeding 1 is worse.
-.I Regexec
-is largely insensitive to RE complexity \fIexcept\fR that back
-references are massively expensive.
-RE length does matter; in particular, there is a strong speed bonus
-for keeping RE length under about 30 characters,
-with most special characters counting roughly double.
-.PP
-.I Regcomp
-implements bounded repetitions by macro expansion,
-which is costly in time and space if counts are large
-or bounded repetitions are nested.
-An RE like, say,
-`((((a{1,100}){1,100}){1,100}){1,100}){1,100}'
-will (eventually) run almost any existing machine out of swap space.
-.PP
-There are suspected problems with response to obscure error conditions.
-Notably,
-certain kinds of internal overflow,
-produced only by truly enormous REs or by multiply nested bounded repetitions,
-are probably not handled well.
-.PP
-Due to a mistake in 1003.2, things like `a)b' are legal REs because `)' is
-a special character only in the presence of a previous unmatched `('.
-This can't be fixed until the spec is fixed.
-.PP
-The standard's definition of back references is vague.
-For example, does
-`a\e(\e(b\e)*\e2\e)*d' match `abbbd'?
-Until the standard is clarified,
-behavior in such cases should not be relied on.
-.PP
-The implementation of word-boundary matching is a bit of a kludge,
-and bugs may lurk in combinations of word-boundary matching and anchoring.
diff --git a/regex/regex.7 b/regex/regex.7
deleted file mode 100644
index d89012bda1d..00000000000
--- a/regex/regex.7
+++ /dev/null
@@ -1,233 +0,0 @@
-.TH REGEX 7 "7 Feb 1994"
-.BY "Henry Spencer"
-.SH NAME
-regex \- POSIX 1003.2 regular expressions
-.SH DESCRIPTION
-Regular expressions (``RE''s),
-as defined in POSIX 1003.2, come in two forms:
-modern REs (roughly those of
-.IR egrep ;
-1003.2 calls these ``extended'' REs)
-and obsolete REs (roughly those of
-.IR ed ;
-1003.2 ``basic'' REs).
-Obsolete REs mostly exist for backward compatibility in some old programs;
-they will be discussed at the end.
-1003.2 leaves some aspects of RE syntax and semantics open;
-`\(dg' marks decisions on these aspects that
-may not be fully portable to other 1003.2 implementations.
-.PP
-A (modern) RE is one\(dg or more non-empty\(dg \fIbranches\fR,
-separated by `|'.
-It matches anything that matches one of the branches.
-.PP
-A branch is one\(dg or more \fIpieces\fR, concatenated.
-It matches a match for the first, followed by a match for the second, etc.
-.PP
-A piece is an \fIatom\fR possibly followed
-by a single\(dg `*', `+', `?', or \fIbound\fR.
-An atom followed by `*' matches a sequence of 0 or more matches of the atom.
-An atom followed by `+' matches a sequence of 1 or more matches of the atom.
-An atom followed by `?' matches a sequence of 0 or 1 matches of the atom.
-.PP
-A \fIbound\fR is `{' followed by an unsigned decimal integer,
-possibly followed by `,'
-possibly followed by another unsigned decimal integer,
-always followed by `}'.
-The integers must lie between 0 and RE_DUP_MAX (255\(dg) inclusive,
-and if there are two of them, the first may not exceed the second.
-An atom followed by a bound containing one integer \fIi\fR
-and no comma matches
-a sequence of exactly \fIi\fR matches of the atom.
-An atom followed by a bound
-containing one integer \fIi\fR and a comma matches
-a sequence of \fIi\fR or more matches of the atom.
-An atom followed by a bound
-containing two integers \fIi\fR and \fIj\fR matches
-a sequence of \fIi\fR through \fIj\fR (inclusive) matches of the atom.
-.PP
-An atom is a regular expression enclosed in `()' (matching a match for the
-regular expression),
-an empty set of `()' (matching the null string)\(dg,
-a \fIbracket expression\fR (see below), `.'
-(matching any single character), `^' (matching the null string at the
-beginning of a line), `$' (matching the null string at the
-end of a line), a `\e' followed by one of the characters
-`^.[$()|*+?{\e'
-(matching that character taken as an ordinary character),
-a `\e' followed by any other character\(dg
-(matching that character taken as an ordinary character,
-as if the `\e' had not been present\(dg),
-or a single character with no other significance (matching that character).
-A `{' followed by a character other than a digit is an ordinary
-character, not the beginning of a bound\(dg.
-It is illegal to end an RE with `\e'.
-.PP
-A \fIbracket expression\fR is a list of characters enclosed in `[]'.
-It normally matches any single character from the list (but see below).
-If the list begins with `^',
-it matches any single character
-(but see below) \fInot\fR from the rest of the list.
-If two characters in the list are separated by `\-', this is shorthand
-for the full \fIrange\fR of characters between those two (inclusive) in the
-collating sequence,
-e.g. `[0-9]' in ASCII matches any decimal digit.
-It is illegal\(dg for two ranges to share an
-endpoint, e.g. `a-c-e'.
-Ranges are very collating-sequence-dependent,
-and portable programs should avoid relying on them.
-.PP
-To include a literal `]' in the list, make it the first character
-(following a possible `^').
-To include a literal `\-', make it the first or last character,
-or the second endpoint of a range.
-To use a literal `\-' as the first endpoint of a range,
-enclose it in `[.' and `.]' to make it a collating element (see below).
-With the exception of these and some combinations using `[' (see next
-paragraphs), all other special characters, including `\e', lose their
-special significance within a bracket expression.
-.PP
-Within a bracket expression, a collating element (a character,
-a multi-character sequence that collates as if it were a single character,
-or a collating-sequence name for either)
-enclosed in `[.' and `.]' stands for the
-sequence of characters of that collating element.
-The sequence is a single element of the bracket expression's list.
-A bracket expression containing a multi-character collating element
-can thus match more than one character,
-e.g. if the collating sequence includes a `ch' collating element,
-then the RE `[[.ch.]]*c' matches the first five characters
-of `chchcc'.
-.PP
-Within a bracket expression, a collating element enclosed in `[=' and
-`=]' is an equivalence class, standing for the sequences of characters
-of all collating elements equivalent to that one, including itself.
-(If there are no other equivalent collating elements,
-the treatment is as if the enclosing delimiters were `[.' and `.]'.)
-For example, if o and \o'o^' are the members of an equivalence class,
-then `[[=o=]]', `[[=\o'o^'=]]', and `[o\o'o^']' are all synonymous.
-An equivalence class may not\(dg be an endpoint
-of a range.
-.PP
-Within a bracket expression, the name of a \fIcharacter class\fR enclosed
-in `[:' and `:]' stands for the list of all characters belonging to that
-class.
-Standard character class names are:
-.PP
-.RS
-.nf
-.ta 3c 6c 9c
-alnum digit punct
-alpha graph space
-blank lower upper
-cntrl print xdigit
-.fi
-.RE
-.PP
-These stand for the character classes defined in
-.IR ctype (3).
-A locale may provide others.
-A character class may not be used as an endpoint of a range.
-.PP
-There are two special cases\(dg of bracket expressions:
-the bracket expressions `[[:<:]]' and `[[:>:]]' match the null string at
-the beginning and end of a word respectively.
-A word is defined as a sequence of
-word characters
-which is neither preceded nor followed by
-word characters.
-A word character is an
-.I alnum
-character (as defined by
-.IR ctype (3))
-or an underscore.
-This is an extension,
-compatible with but not specified by POSIX 1003.2,
-and should be used with
-caution in software intended to be portable to other systems.
-.PP
-In the event that an RE could match more than one substring of a given
-string,
-the RE matches the one starting earliest in the string.
-If the RE could match more than one substring starting at that point,
-it matches the longest.
-Subexpressions also match the longest possible substrings, subject to
-the constraint that the whole match be as long as possible,
-with subexpressions starting earlier in the RE taking priority over
-ones starting later.
-Note that higher-level subexpressions thus take priority over
-their lower-level component subexpressions.
-.PP
-Match lengths are measured in characters, not collating elements.
-A null string is considered longer than no match at all.
-For example,
-`bb*' matches the three middle characters of `abbbc',
-`(wee|week)(knights|nights)' matches all ten characters of `weeknights',
-when `(.*).*' is matched against `abc' the parenthesized subexpression
-matches all three characters, and
-when `(a*)*' is matched against `bc' both the whole RE and the parenthesized
-subexpression match the null string.
-.PP
-If case-independent matching is specified,
-the effect is much as if all case distinctions had vanished from the
-alphabet.
-When an alphabetic that exists in multiple cases appears as an
-ordinary character outside a bracket expression, it is effectively
-transformed into a bracket expression containing both cases,
-e.g. `x' becomes `[xX]'.
-When it appears inside a bracket expression, all case counterparts
-of it are added to the bracket expression, so that (e.g.) `[x]'
-becomes `[xX]' and `[^x]' becomes `[^xX]'.
-.PP
-No particular limit is imposed on the length of REs\(dg.
-Programs intended to be portable should not employ REs longer
-than 256 bytes,
-as an implementation can refuse to accept such REs and remain
-POSIX-compliant.
-.PP
-Obsolete (``basic'') regular expressions differ in several respects.
-`|', `+', and `?' are ordinary characters and there is no equivalent
-for their functionality.
-The delimiters for bounds are `\e{' and `\e}',
-with `{' and `}' by themselves ordinary characters.
-The parentheses for nested subexpressions are `\e(' and `\e)',
-with `(' and `)' by themselves ordinary characters.
-`^' is an ordinary character except at the beginning of the
-RE or\(dg the beginning of a parenthesized subexpression,
-`$' is an ordinary character except at the end of the
-RE or\(dg the end of a parenthesized subexpression,
-and `*' is an ordinary character if it appears at the beginning of the
-RE or the beginning of a parenthesized subexpression
-(after a possible leading `^').
-Finally, there is one new type of atom, a \fIback reference\fR:
-`\e' followed by a non-zero decimal digit \fId\fR
-matches the same sequence of characters
-matched by the \fId\fRth parenthesized subexpression
-(numbering subexpressions by the positions of their opening parentheses,
-left to right),
-so that (e.g.) `\e([bc]\e)\e1' matches `bb' or `cc' but not `bc'.
-.SH SEE ALSO
-regex(3)
-.PP
-POSIX 1003.2, section 2.8 (Regular Expression Notation).
-.SH BUGS
-Having two kinds of REs is a botch.
-.PP
-The current 1003.2 spec says that `)' is an ordinary character in
-the absence of an unmatched `(';
-this was an unintentional result of a wording error,
-and change is likely.
-Avoid relying on it.
-.PP
-Back references are a dreadful botch,
-posing major problems for efficient implementations.
-They are also somewhat vaguely defined
-(does
-`a\e(\e(b\e)*\e2\e)*d' match `abbbd'?).
-Avoid using them.
-.PP
-1003.2's specification of case-independent matching is vague.
-The ``one case implies all cases'' definition given above
-is current consensus among implementors as to the right interpretation.
-.PP
-The syntax for word boundaries is incredibly ugly.
diff --git a/regex/regex2.h b/regex/regex2.h
deleted file mode 100644
index 2ab32c62da8..00000000000
--- a/regex/regex2.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * First, the stuff that ends up in the outside-world include file
- = typedef off_t regoff_t;
- = typedef struct {
- = int re_magic;
- = size_t re_nsub; // number of parenthesized subexpressions
- = const char *re_endp; // end pointer for REG_PEND
- = struct re_guts *re_g; // none of your business :-)
- = } regex_t;
- = typedef struct {
- = regoff_t rm_so; // start of match
- = regoff_t rm_eo; // end of match
- = } regmatch_t;
- */
-/*
- * internals of regex_t
- */
-#ifndef __regex2_h__
-#define __regex2_h__
-
-#define MAGIC1 ((('r'^0200)<<8) | 'e')
-
-/*
- * The internal representation is a *strip*, a sequence of
- * operators ending with an endmarker. (Some terminology etc. is a
- * historical relic of earlier versions which used multiple strips.)
- * Certain oddities in the representation are there to permit running
- * the machinery backwards; in particular, any deviation from sequential
- * flow must be marked at both its source and its destination. Some
- * fine points:
- *
- * - OPLUS_ and O_PLUS are *inside* the loop they create.
- * - OQUEST_ and O_QUEST are *outside* the bypass they create.
- * - OCH_ and O_CH are *outside* the multi-way branch they create, while
- * OOR1 and OOR2 are respectively the end and the beginning of one of
- * the branches. Note that there is an implicit OOR2 following OCH_
- * and an implicit OOR1 preceding O_CH.
- *
- * In state representations, an operator's bit is on to signify a state
- * immediately *preceding* "execution" of that operator.
- */
-typedef unsigned long sop; /* strip operator */
-typedef long sopno;
-#define OPRMASK 0xf8000000
-#define OPDMASK 0x07ffffff
-#define OPSHIFT ((unsigned long)27)
-#define OP(n) ((unsigned long) ((n)&OPRMASK))
-#define OPND(n) ((unsigned long) ((n)&OPDMASK))
-#define SOP(op, opnd) (unsigned long) ((op)|(opnd))
-#define OSHIFT(A) ((unsigned long) (A) << OPSHIFT)
-/* operators meaning operand */
-/* (back, fwd are offsets) */
-#define OEND OSHIFT(1) /* endmarker - */
-#define OCHAR OSHIFT(2) /* character unsigned char */
-#define OBOL OSHIFT(3) /* left anchor - */
-#define OEOL OSHIFT(4) /* right anchor - */
-#define OANY OSHIFT(5) /* . - */
-#define OANYOF OSHIFT(6) /* [...] set number */
-#define OBACK_ OSHIFT(7) /* begin \d paren number */
-#define O_BACK OSHIFT(8) /* end \d paren number */
-#define OPLUS_ OSHIFT(9) /* + prefix fwd to suffix */
-#define O_PLUS OSHIFT(10) /* + suffix back to prefix */
-#define OQUEST_ OSHIFT(11) /* ? prefix fwd to suffix */
-#define O_QUEST OSHIFT(12) /* ? suffix back to prefix */
-#define OLPAREN OSHIFT(13) /* ( fwd to ) */
-#define ORPAREN OSHIFT(14) /* ) back to ( */
-#define OCH_ OSHIFT(15) /* begin choice fwd to OOR2 */
-#define OOR1 OSHIFT(16) /* | pt. 1 back to OOR1 or OCH_ */
-#define OOR2 OSHIFT(17) /* | pt. 2 fwd to OOR2 or O_CH */
-#define O_CH OSHIFT(18) /* end choice back to OOR1 */
-#define OBOW OSHIFT(19) /* begin word - */
-#define OEOW OSHIFT(20) /* end word - */
-
-/*
- * Structure for [] character-set representation. Character sets are
- * done as bit vectors, grouped 8 to a byte vector for compactness.
- * The individual set therefore has both a pointer to the byte vector
- * and a mask to pick out the relevant bit of each byte. A hash code
- * simplifies testing whether two sets could be identical.
- *
- * This will get trickier for multicharacter collating elements. As
- * preliminary hooks for dealing with such things, we also carry along
- * a string of multi-character elements, and decide the size of the
- * vectors at run time.
- */
-
-
-typedef struct {
- uch *ptr; /* -> uch [csetsize] */
- uch mask; /* bit within array */
- uch hash; /* hash code */
- size_t smultis;
- char *multis; /* -> char[smulti] ab\0cd\0ef\0\0 */
-} cset;
-/* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
-#define CHadd(cs, c) ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (uch) (c))
-#define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (uch)(c))
-#define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask)
-#define MCadd(p, cs, cp) mcadd(p, cs, cp) /* regcomp() internal fns */
-#define MCsub(p, cs, cp) mcsub(p, cs, cp)
-#define MCin(p, cs, cp) mcin(p, cs, cp)
-
-/* stuff for character categories */
-typedef unsigned char cat_t;
-
-/*
- * main compiled-expression structure
- */
-struct re_guts {
- int magic;
-# define MAGIC2 ((('R'^0200)<<8)|'E')
- sop *strip; /* malloced area for strip */
- int csetsize; /* number of bits in a cset vector */
- int ncsets; /* number of csets in use */
- cset *sets; /* -> cset [ncsets] */
- uch *setbits; /* -> uch[csetsize][ncsets/CHAR_BIT] */
- int cflags; /* copy of regcomp() cflags argument */
- sopno nstates; /* = number of sops */
- sopno firststate; /* the initial OEND (normally 0) */
- sopno laststate; /* the final OEND */
- int iflags; /* internal flags */
-# define USEBOL 01 /* used ^ */
-# define USEEOL 02 /* used $ */
-# define BAD 04 /* something wrong */
- int nbol; /* number of ^ used */
- int neol; /* number of $ used */
- int ncategories; /* how many character categories */
- cat_t *categories; /* ->catspace[-CHAR_MIN] */
- char *must; /* match must contain this string */
- int mlen; /* length of must */
- size_t nsub; /* copy of re_nsub */
- int backrefs; /* does it use back references? */
- sopno nplus; /* how deep does it nest +s? */
- /* catspace must be last */
- cat_t catspace[1]; /* actually [NC] */
-};
-
-/* misc utilities */
-#undef OUT /* May be defined in windows */
-#define OUT (CHAR_MAX+1) /* a non-character value */
-#define ISWORD(s,c) (my_isalnum(s,c) || (c) == '_')
-
-#endif /* __regex2_h__ */
diff --git a/regex/regexec.c b/regex/regexec.c
deleted file mode 100644
index c0d03335b41..00000000000
--- a/regex/regexec.c
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- * the outer shell of regexec()
- *
- * This file includes engine.c *twice*, after muchos fiddling with the
- * macros that code uses. This lets the same code operate on two different
- * representations for state sets.
- */
-#include <my_global.h>
-#include <m_string.h>
-#include <m_ctype.h>
-#ifdef __WIN__
-#include <limits.h>
-#endif
-#include "my_regex.h"
-#include "utils.h"
-#include "regex2.h"
-
-/* for use in asserts */
-#define nope 0
-
-/* macros for manipulating states, small version */
-#define states long
-#define states1 long /* for later use in regexec() decision. Ensure Win64 definition is correct.*/
-#define CLEAR(v) ((v) = 0)
-#define SET0(v, n) ((v) &= ~((states) 1 << (n)))
-#define SET1(v, n) ((v) |= (states) 1 << (n))
-#define ISSET(v, n) ((v) & ((states) 1 << (n)))
-#define ASSIGN(d, s) ((d) = (s))
-#define EQ(a, b) ((a) == (b))
-#define STATEVARS int dummy /* dummy version */
-#define STATESETUP(m, n) /* nothing */
-#define STATETEARDOWN(m) /* nothing */
-#define SETUP(v) ((v) = 0)
-#define onestate long /* Changed from int by Monty */
-#define INIT(o, n) ((o) = (unsigned states)1 << (n))
-#define INC(o) ((o) <<= 1)
-#define ISSTATEIN(v, o) ((v) & (o))
-/* some abbreviations; note that some of these know variable names! */
-/* do "if I'm here, I can also be there" etc without branches */
-#define FWD(dst, src, n) ((dst) |= ((unsigned states)(src)&(here)) << (n))
-#define BACK(dst, src, n) ((dst) |= ((unsigned states)(src)&(here)) >> (n))
-#define ISSETBACK(v, n) ((v) & ((unsigned states)here >> (n)))
-/* function names */
-#define SNAMES /* engine.c looks after details */
-
-#include "engine.c"
-
-/* now undo things */
-#undef states
-#undef CLEAR
-#undef SET0
-#undef SET1
-#undef ISSET
-#undef ASSIGN
-#undef EQ
-#undef STATEVARS
-#undef STATESETUP
-#undef STATETEARDOWN
-#undef SETUP
-#undef onestate
-#undef INIT
-#undef INC
-#undef ISSTATEIN
-#undef FWD
-#undef BACK
-#undef ISSETBACK
-#undef SNAMES
-
-/* macros for manipulating states, large version */
-#define states char *
-#define CLEAR(v) memset(v, 0, m->g->nstates)
-#define SET0(v, n) ((v)[n] = 0)
-#define SET1(v, n) ((v)[n] = 1)
-#define ISSET(v, n) ((v)[n])
-#define ASSIGN(d, s) memcpy(d, s, m->g->nstates)
-#define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0)
-#define STATEVARS int vn; char *space
-#define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \
- if ((m)->space == NULL) return(REG_ESPACE); \
- (m)->vn = 0; }
-#define STATETEARDOWN(m) { free((m)->space); }
-#define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates])
-#define onestate int
-#define INIT(o, n) ((o) = (n))
-#define INC(o) ((o)++)
-#define ISSTATEIN(v, o) ((v)[o])
-/* some abbreviations; note that some of these know variable names! */
-/* do "if I'm here, I can also be there" etc without branches */
-#define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here])
-#define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here])
-#define ISSETBACK(v, n) ((v)[here - (n)])
-/* function names */
-#define LNAMES /* flag */
-
-#include "engine.c"
-
-/*
- - regexec - interface for matching
- = extern int regexec(const regex_t *, const char *, size_t, \
- = regmatch_t [], int);
- = #define REG_NOTBOL 00001
- = #define REG_NOTEOL 00002
- = #define REG_STARTEND 00004
- = #define REG_TRACE 00400 // tracing of execution
- = #define REG_LARGE 01000 // force large representation
- = #define REG_BACKR 02000 // force use of backref code
- *
- * We put this here so we can exploit knowledge of the state representation
- * when choosing which matcher to call. Also, by this point the matchers
- * have been prototyped.
- */
-int /* 0 success, REG_NOMATCH failure */
-my_regexec(preg, str, nmatch, pmatch, eflags)
-const my_regex_t *preg;
-const char *str;
-size_t nmatch;
-my_regmatch_t pmatch[];
-int eflags;
-{
- char *pstr = (char *) str;
- register struct re_guts *g = preg->re_g;
-#ifdef REDEBUG
-# define GOODFLAGS(f) (f)
-#else
-# define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
-#endif
-
- if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
- return(REG_BADPAT);
- assert(!(g->iflags&BAD));
- if (g->iflags&BAD) /* backstop for no-debug case */
- return(REG_BADPAT);
- eflags = GOODFLAGS(eflags);
-
- if ((size_t) g->nstates <= CHAR_BIT*sizeof(states1) &&
- !(eflags&REG_LARGE))
- return(smatcher(preg->charset, g, pstr, nmatch, pmatch, eflags));
- else
- return(lmatcher(preg->charset, g, pstr, nmatch, pmatch, eflags));
-}
diff --git a/regex/regexp.c b/regex/regexp.c
deleted file mode 100644
index 8ddf90f2943..00000000000
--- a/regex/regexp.c
+++ /dev/null
@@ -1,1348 +0,0 @@
-/*
- *
- * regexp.c - regular expression matching
- *
- * DESCRIPTION
- *
- * Underneath the reformatting and comment blocks which were added to
- * make it consistent with the rest of the code, you will find a
- * modified version of Henry Specer's regular expression library.
- * Henry's functions were modified to provide the minimal regular
- * expression matching, as required by P1003. Henry's code was
- * copyrighted, and copy of the copyright message and restrictions
- * are provided, verbatim, below:
- *
- * Copyright (c) 1986 by University of Toronto.
- * Written by Henry Spencer. Not derived from licensed software.
- *
- * Permission is granted to anyone to use this software for any
- * purpose on any computer system, and to redistribute it freely,
- * subject to the following restrictions:
- *
- * 1. The author is not responsible for the consequences of use of
- * this software, no matter how awful, even if they arise
- * from defects in it.
- *
- * 2. The origin of this software must not be misrepresented, either
- * by explicit claim or by omission.
- *
- * 3. Altered versions must be plainly marked as such, and must not
- * be misrepresented as being the original software.
- *
- *
- * This version modified by Ian Phillipps to return pointer to terminating
- * NUL on substitution string. [ Temp mail address ex-igp@camcon.co.uk ]
- *
- * Altered by amylaar to support excompatible option and the
- * operators \< and >\ . ( 7.Sep. 1991 )
- *
- * regsub altered by amylaar to take an additional parameter specifying
- * maximum number of bytes that can be written to the memory region
- * pointed to by dest
- *
- * Also altered by Fredrik Hubinette to handle the + operator and
- * eight-bit chars. Mars 22 1996
- *
- *
- * Beware that some of this code is subtly aware of the way operator
- * precedence is structured in regular expressions. Serious changes in
- * regular-expression syntax might require a total rethink.
- *
- * AUTHORS
- *
- * Mark H. Colburn, NAPS International (mark@jhereg.mn.org)
- * Henry Spencer, University of Torronto (henry@utzoo.edu)
- *
- * Sponsored by The USENIX Association for public distribution.
- *
- */
-
-/* Headers */
-#include "my_global.h"
-#include <ctype.h>
-#include "regexp.h"
-#ifdef __WIN__
-#include <string.h>
-#else
-#include "memory.h"
-#include "error.h"
-#endif
-
-/*
- * The "internal use only" fields in regexp.h are present to pass info from
- * compile to execute that permits the execute phase to run lots faster on
- * simple cases. They are:
- *
- * regstart char that must begin a match; '\0' if none obvious
- * reganch is the match anchored (at beginning-of-line only)?
- * regmust string (pointer into program) that match must include, or NULL
- * regmlen length of regmust string
- *
- * Regstart and reganch permit very fast decisions on suitable starting points
- * for a match, cutting down the work a lot. Regmust permits fast rejection
- * of lines that cannot possibly match. The regmust tests are costly enough
- * that regcomp() supplies a regmust only if the r.e. contains something
- * potentially expensive (at present, the only such thing detected is * or +
- * at the start of the r.e., which can involve a lot of backup). Regmlen is
- * supplied because the test in regexec() needs it and regcomp() is computing
- * it anyway.
- */
-
-/*
- * Structure for regexp "program". This is essentially a linear encoding
- * of a nondeterministic finite-state machine (aka syntax charts or
- * "railroad normal form" in parsing technology). Each node is an opcode
- * plus a "nxt" pointer, possibly plus an operand. "Nxt" pointers of
- * all nodes except BRANCH implement concatenation; a "nxt" pointer with
- * a BRANCH on both ends of it is connecting two alternatives. (Here we
- * have one of the subtle syntax dependencies: an individual BRANCH (as
- * opposed to a collection of them) is never concatenated with anything
- * because of operator precedence.) The operand of some types of node is
- * a literal string; for others, it is a node leading into a sub-FSM. In
- * particular, the operand of a BRANCH node is the first node of the branch.
- * (NB this is *not* a tree structure: the tail of the branch connects
- * to the thing following the set of BRANCHes.) The opcodes are:
- */
-
-/* definition number opnd? meaning */
-#define END 0 /* no End of program. */
-#define BOL 1 /* no Match "" at beginning of line. */
-#define EOL 2 /* no Match "" at end of line. */
-#define ANY 3 /* no Match any one character. */
-#define ANYOF 4 /* str Match any character in this string. */
-#define ANYBUT 5 /* str Match any character not in this
- * string. */
-#define BRANCH 6 /* node Match this alternative, or the
- * nxt... */
-#define BACK 7 /* no Match "", "nxt" ptr points backward. */
-#define EXACTLY 8 /* str Match this string. */
-#define NOTHING 9 /* no Match empty string. */
-#define STAR 10 /* node Match this (simple) thing 0 or more
- * times. */
-#define WORDSTART 11 /* node matching a start of a word */
-#define WORDEND 12 /* node matching an end of a word */
-#define OPEN 20 /* no Mark this point in input as start of
- * #n. */
- /* OPEN+1 is number 1, etc. */
-#define CLOSE 30 /* no Analogous to OPEN. */
-
-/*
- * Opcode notes:
- *
- * BRANCH The set of branches constituting a single choice are hooked
- * together with their "nxt" pointers, since precedence prevents
- * anything being concatenated to any individual branch. The
- * "nxt" pointer of the last BRANCH in a choice points to the
- * thing following the whole choice. This is also where the
- * final "nxt" pointer of each individual branch points; each
- * branch starts with the operand node of a BRANCH node.
- *
- * BACK Normal "nxt" pointers all implicitly point forward; BACK
- * exists to make loop structures possible.
- *
- * STAR complex '*', are implemented as circular BRANCH structures
- * using BACK. Simple cases (one character per match) are
- * implemented with STAR for speed and to minimize recursive
- * plunges.
- *
- * OPEN,CLOSE ...are numbered at compile time.
- */
-
-/*
- * A node is one char of opcode followed by two chars of "nxt" pointer.
- * "Nxt" pointers are stored as two 8-bit pieces, high order first. The
- * value is a positive offset from the opcode of the node containing it.
- * An operand, if any, simply follows the node. (Note that much of the
- * code generation knows about this implicit relationship.)
- *
- * Using two bytes for the "nxt" pointer is vast overkill for most things,
- * but allows patterns to get big without disasters.
- */
-#define OP(p) (*(p))
-#define NEXT(p) (((*((p)+1)&0377)<<8) + (*((p)+2)&0377))
-#define OPERAND(p) ((p) + 3)
-
-/*
- * The first byte of the regexp internal "program" is actually this magic
- * number; the start node begins in the second byte.
- */
-#define MAGIC 0234
-
-/*
- * Utility definitions.
- */
-
-#ifdef __WIN__
-#define error(X,Y) fprintf(stderr, X, Y)
-#endif
-#define regerror(X) error("Regexp: %s\n",X);
-#define SPECIAL 0x100
-#define LBRAC ('('|SPECIAL)
-#define RBRAC (')'|SPECIAL)
-#define ASTERIX ('*'|SPECIAL)
-#define PLUS ('+'|SPECIAL)
-#define OR_OP ('|'|SPECIAL)
-#define DOLLAR ('$'|SPECIAL)
-#define DOT ('.'|SPECIAL)
-#define CARET ('^'|SPECIAL)
-#define LSQBRAC ('['|SPECIAL)
-#define RSQBRAC (']'|SPECIAL)
-#define LSHBRAC ('<'|SPECIAL)
-#define RSHBRAC ('>'|SPECIAL)
-#define FAIL(m) { regerror(m); return(NULL); }
-#define ISMULT(c) ((c) == ASTERIX || (c)==PLUS)
-#define META "^$.[()|*+\\"
-#ifndef CHARBITS
-#define CHARBITS 0xff
-#define UCHARAT(p) ((int)*(unsigned char *)(p))
-#else
-#define UCHARAT(p) ((int)*(p)&CHARBITS)
-#endif
-#define ISWORDPART(c) ( isalnum(c) || (c) == '_' )
-
-/*
- * Flags to be passed up and down.
- */
-#define HASWIDTH 01 /* Known never to match null string. */
-#define SIMPLE 02 /* Simple enough to be STAR operand. */
-#define SPSTART 04 /* Starts with * */
-#define WORST 0 /* Worst case. */
-#ifdef __WIN__
-#define STRCHR(A,B) strchr(A,B)
-#endif
-
-/*
- * Global work variables for regcomp().
- */
-static short *regparse; /* Input-scan pointer. */
-static int regnpar; /* () count. */
-static char regdummy;
-static char *regcode; /* Code-emit pointer; &regdummy = don't. */
-static long regsize; /* Code size. */
-
-/*
- * Forward declarations for regcomp()'s friends.
- */
-#ifndef STATIC
-#define STATIC static
-#endif
-STATIC char *reg();
-STATIC char *regbranch();
-STATIC char *regpiece();
-STATIC char *regatom();
-STATIC char *regnode();
-STATIC char *regnext();
-STATIC void regc();
-STATIC void reginsert();
-STATIC void regtail();
-STATIC void regoptail();
-
-/*
- - regcomp - compile a regular expression into internal code
- *
- * We can't allocate space until we know how big the compiled form will be,
- * but we can't compile it (and thus know how big it is) until we've got a
- * place to put the code. So we cheat: we compile it twice, once with code
- * generation turned off and size counting turned on, and once "for real".
- * This also means that we don't allocate space until we are sure that the
- * thing really will compile successfully, and we never have to move the
- * code and thus invalidate pointers into it. (Note that it has to be in
- * one piece because free() must be able to free it all.)
- *
- * Beware that the optimization-preparation code in here knows about some
- * of the structure of the compiled regexp.
- */
-regexp *regcomp(exp,excompat)
-char *exp;
-int excompat; /* \( \) operators like in unix ex */
-{
- register regexp *r;
- register char *scan;
- register char *longest;
- register int len;
- int flags;
- short *exp2,*dest,c;
-
- if (exp == (char *)NULL)
- FAIL("NULL argument");
-
- exp2=(short*)malloc( (strlen(exp)+1) * (sizeof(short[8])/sizeof(char[8])) );
- for ( scan=exp,dest=exp2;( c= UCHARAT(scan++)); ) {
- switch (c) {
- case '(':
- case ')':
- *dest++ = excompat ? c : c | SPECIAL;
- break;
- case '.':
- case '*':
- case '+':
- case '|':
- case '$':
- case '^':
- case '[':
- case ']':
- *dest++ = c | SPECIAL;
- break;
- case '\\':
- switch ( c = *scan++ ) {
- case '(':
- case ')':
- *dest++ = excompat ? c | SPECIAL : c;
- break;
- case '<':
- case '>':
- *dest++ = c | SPECIAL;
- break;
- case '{':
- case '}':
- FAIL("sorry, unimplemented operator");
- case 'b': *dest++ = '\b'; break;
- case 't': *dest++ = '\t'; break;
- case 'r': *dest++ = '\r'; break;
- default:
- *dest++ = c;
- }
- break;
- default:
- *dest++ = c;
- }
- }
- *dest=0;
- /* First pass: determine size, legality. */
- regparse = exp2;
- regnpar = 1;
- regsize = 0L;
- regcode = &regdummy;
- regc(MAGIC);
- if (reg(0, &flags) == (char *)NULL)
- return ((regexp *)NULL);
-
- /* Small enough for pointer-storage convention? */
- if (regsize >= 32767L) /* Probably could be 65535L. */
- FAIL("regexp too big");
-
- /* Allocate space. */
- r = (regexp *) malloc(sizeof(regexp) + (unsigned) regsize);
- if (r == (regexp *) NULL)
- FAIL("out of space");
- (void) bzero(r, sizeof(regexp) + (unsigned)regsize);
-
- /* Second pass: emit code. */
- regparse = exp2;
- regnpar = 1;
- regcode = r->program;
- regc(MAGIC);
- if (reg(0, &flags) == NULL)
- return ((regexp *) NULL);
-
- /* Dig out information for optimizations. */
- r->regstart = '\0'; /* Worst-case defaults. */
- r->reganch = 0;
- r->regmust = NULL;
- r->regmlen = 0;
- scan = r->program + 1; /* First BRANCH. */
- if (OP(regnext(scan)) == END) { /* Only one top-level choice. */
- scan = OPERAND(scan);
-
- /* Starting-point info. */
- if (OP(scan) == EXACTLY)
- r->regstart = *OPERAND(scan);
- else if (OP(scan) == BOL)
- r->reganch++;
-
- /*
- * If there's something expensive in the r.e., find the longest
- * literal string that must appear and make it the regmust. Resolve
- * ties in favor of later strings, since the regstart check works
- * with the beginning of the r.e. and avoiding duplication
- * strengthens checking. Not a strong reason, but sufficient in the
- * absence of others.
- */
- if (flags & SPSTART) {
- longest = NULL;
- len = 0;
- for (; scan != NULL; scan = regnext(scan))
- if (OP(scan) == EXACTLY &&
- (int)strlen(OPERAND(scan)) >= len) {
- longest = OPERAND(scan);
- len = strlen(OPERAND(scan));
- }
- r->regmust = longest;
- r->regmlen = len;
- }
- }
- free((char*)exp2);
- return (r);
-}
-
-/*
- - reg - regular expression, i.e. main body or parenthesized thing
- *
- * Caller must absorb opening parenthesis.
- *
- * Combining parenthesis handling with the base level of regular expression
- * is a trifle forced, but the need to tie the tails of the branches to what
- * follows makes it hard to avoid.
- */
-static char *reg(paren, flagp)
-int paren; /* Parenthesized? */
-int *flagp;
-{
- register char *ret;
- register char *br;
- register char *ender;
- register int parno=0; /* make gcc happy */
- int flags;
-
- *flagp = HASWIDTH; /* Tentatively. */
-
- /* Make an OPEN node, if parenthesized. */
- if (paren) {
- if (regnpar >= NSUBEXP)
- FAIL("too many ()");
- parno = regnpar;
- regnpar++;
- ret = regnode(OPEN + parno);
- } else
- ret = (char *)NULL;
-
- /* Pick up the branches, linking them together. */
- br = regbranch(&flags);
- if (br == (char *)NULL)
- return ((char *)NULL);
- if (ret != (char *)NULL)
- regtail(ret, br); /* OPEN -> first. */
- else
- ret = br;
- if (!(flags & HASWIDTH))
- *flagp &= ~HASWIDTH;
- *flagp |= flags & SPSTART;
- while (*regparse == OR_OP) {
- regparse++;
- br = regbranch(&flags);
- if (br == (char *)NULL)
- return ((char *)NULL);
- regtail(ret, br); /* BRANCH -> BRANCH. */
- if (!(flags & HASWIDTH))
- *flagp &= ~HASWIDTH;
- *flagp |= flags & SPSTART;
- }
-
- /* Make a closing node, and hook it on the end. */
- ender = regnode((paren) ? CLOSE + parno : END);
- regtail(ret, ender);
-
- /* Hook the tails of the branches to the closing node. */
- for (br = ret; br != (char *)NULL; br = regnext(br))
- regoptail(br, ender);
-
- /* Check for proper termination. */
- if (paren && *regparse++ != RBRAC) {
- FAIL("unmatched ()");
- } else if (!paren && *regparse != '\0') {
- if (*regparse == RBRAC) {
- FAIL("unmatched ()");
- } else
- FAIL("junk on end");/* "Can't happen". */
- /* NOTREACHED */
- }
- return (ret);
-}
-
-/*
- - regbranch - one alternative of an | operator
- *
- * Implements the concatenation operator.
- */
-static char *regbranch(flagp)
-int *flagp;
-{
- register char *ret;
- register char *chain;
- register char *latest;
- int flags;
-
- *flagp = WORST; /* Tentatively. */
-
- ret = regnode(BRANCH);
- chain = (char *)NULL;
- while (*regparse != '\0' && *regparse != OR_OP && *regparse != RBRAC) {
- latest = regpiece(&flags);
- if (latest == (char *)NULL)
- return ((char *)NULL);
- *flagp |= flags & HASWIDTH;
- if (chain == (char *)NULL) /* First piece. */
- *flagp |= flags & SPSTART;
- else
- regtail(chain, latest);
- chain = latest;
- }
- if (chain == (char *)NULL) /* Loop ran zero times. */
- regnode(NOTHING);
-
- return (ret);
-}
-
-/*
- - regpiece - something followed by possible [*]
- *
- * Note that the branching code sequence used for * is somewhat optimized:
- * they use the same NOTHING node as both the endmarker for their branch
- * list and the body of the last branch. It might seem that this node could
- * be dispensed with entirely, but the endmarker role is not redundant.
- */
-static char *regpiece(flagp)
-int *flagp;
-{
- register char *ret;
- register short op;
- /* register char *nxt; */
- int flags;
-
- ret = regatom(&flags);
- if (ret == (char *)NULL)
- return ((char *)NULL);
-
- op = *regparse;
- if (!ISMULT(op)) {
- *flagp = flags;
- return (ret);
- }
- if (!(flags & HASWIDTH))
- FAIL("* or + operand could be empty");
- *flagp = (WORST | SPSTART);
-
- if(op == ASTERIX)
- {
- if (flags & SIMPLE)
- {
- reginsert(STAR, ret);
- }
- else
- {
- /* Emit x* as (x&|), where & means "self". */
- reginsert(BRANCH, ret); /* Either x */
- regoptail(ret, regnode(BACK)); /* and loop */
- regoptail(ret, ret); /* back */
- regtail(ret, regnode(BRANCH)); /* or */
- regtail(ret, regnode(NOTHING)); /* null. */
- }
- }
- else if(op == PLUS)
- {
- /* Emit a+ as (a&) where & means "self" /Fredrik Hubinette */
- char *tmp;
- tmp=regnode(BACK);
- reginsert(BRANCH, tmp);
- regtail(ret, tmp);
- regoptail(tmp, ret);
- regtail(ret, regnode(BRANCH));
- regtail(ret, regnode(NOTHING));
- }
-
- regparse++;
- if (ISMULT(*regparse))
- FAIL("nested * or +");
-
- return (ret);
-}
-
-
-/*
- - regatom - the lowest level
- *
- * Optimization: gobbles an entire sequence of ordinary characters so that
- * it can turn them into a single node, which is smaller to store and
- * faster to run.
- */
-static char *regatom(flagp)
-int *flagp;
-{
- register char *ret;
- int flags;
-
- *flagp = WORST; /* Tentatively. */
-
- switch (*regparse++) {
- case CARET:
- ret = regnode(BOL);
- break;
- case DOLLAR:
- ret = regnode(EOL);
- break;
- case DOT:
- ret = regnode(ANY);
- *flagp |= HASWIDTH | SIMPLE;
- break;
- case LSHBRAC:
- ret = regnode(WORDSTART);
- break;
- case RSHBRAC:
- ret = regnode(WORDEND);
- break;
- case LSQBRAC:{
- register int class;
- register int classend;
-
- if (*regparse == CARET) { /* Complement of range. */
- ret = regnode(ANYBUT);
- regparse++;
- } else
- ret = regnode(ANYOF);
- if (*regparse == RSQBRAC || *regparse == '-')
- regc(*regparse++);
- while (*regparse != '\0' && *regparse != RSQBRAC) {
- if (*regparse == '-') {
- regparse++;
- if (*regparse == RSQBRAC || *regparse == '\0')
- regc('-');
- else {
- class = (CHARBITS & *(regparse - 2)) + 1;
- classend = (CHARBITS & *(regparse));
- if (class > classend + 1)
- FAIL("invalid [] range");
- for (; class <= classend; class++)
- regc(class);
- regparse++;
- }
- } else
- regc(*regparse++);
- }
- regc('\0');
- if (*regparse != RSQBRAC)
- FAIL("unmatched []");
- regparse++;
- *flagp |= HASWIDTH | SIMPLE;
- }
- break;
- case LBRAC:
- ret = reg(1, &flags);
- if (ret == (char *)NULL)
- return ((char *)NULL);
- *flagp |= flags & (HASWIDTH | SPSTART);
- break;
- case '\0':
- case OR_OP:
- case RBRAC:
- FAIL("internal urp"); /* Supposed to be caught earlier. */
-
- case ASTERIX:
- FAIL("* follows nothing\n");
-
- default:{
- register int len;
- register short ender;
-
- regparse--;
- for (len=0; regparse[len] &&
- !(regparse[len]&SPECIAL) && regparse[len] != RSQBRAC; len++) ;
- if (len <= 0)
- {
- FAIL("internal disaster");
- }
- ender = *(regparse + len);
- if (len > 1 && ISMULT(ender))
- len--; /* Back off clear of * operand. */
- *flagp |= HASWIDTH;
- if (len == 1)
- *flagp |= SIMPLE;
- ret = regnode(EXACTLY);
- while (len > 0) {
- regc(*regparse++);
- len--;
- }
- regc('\0');
- }
- break;
- }
-
- return (ret);
-}
-
-/*
- - regnode - emit a node
- */
-static char *regnode(op)
-char op;
-{
- register char *ret;
- register char *ptr;
-
- ret = regcode;
- if (ret == &regdummy) {
- regsize += 3;
- return (ret);
- }
- ptr = ret;
- *ptr++ = op;
- *ptr++ = '\0'; /* Null "nxt" pointer. */
- *ptr++ = '\0';
- regcode = ptr;
-
- return (ret);
-}
-
-/*
- - regc - emit (if appropriate) a byte of code
- */
-static void regc(b)
-char b;
-{
- if (regcode != &regdummy)
- *regcode++ = b;
- else
- regsize++;
-}
-
-/*
- - reginsert - insert an operator in front of already-emitted operand
- *
- * Means relocating the operand.
- */
-static void reginsert(op, opnd)
-char op;
-char *opnd;
-{
- register char *src;
- register char *dst;
- register char *place;
-
- if (regcode == &regdummy) {
- regsize += 3;
- return;
- }
- src = regcode;
- regcode += 3;
- dst = regcode;
- while (src > opnd)
- *--dst = *--src;
-
- place = opnd; /* Op node, where operand used to be. */
- *place++ = op;
- *place++ = '\0';
- *place++ = '\0';
-}
-
-/*
- - regtail - set the next-pointer at the end of a node chain
- */
-static void regtail(p, val)
-char *p;
-char *val;
-{
- register char *scan;
- register char *temp;
- register int offset;
-
- if (p == &regdummy)
- return;
-
- /* Find last node. */
- scan = p;
- for (;;) {
- temp = regnext(scan);
- if (temp == (char *)NULL)
- break;
- scan = temp;
- }
-
- if (OP(scan) == BACK)
- offset = scan - val;
- else
- offset = val - scan;
- *(scan + 1) = (offset >> 8) & 0377;
- *(scan + 2) = offset & 0377;
-}
-
-/*
- - regoptail - regtail on operand of first argument; nop if operandless
- */
-static void regoptail(p, val)
-char *p;
-char *val;
-{
- /* "Operandless" and "op != BRANCH" are synonymous in practice. */
- if (p == (char *)NULL || p == &regdummy || OP(p) != BRANCH)
- return;
- regtail(OPERAND(p), val);
-}
-
-/*
- * regexec and friends
- */
-
-/*
- * Global work variables for regexec().
- */
-static char *reginput; /* String-input pointer. */
-static char *regbol; /* Beginning of input, for ^ check. */
-static char **regstartp; /* Pointer to startp array. */
-static char **regendp; /* Ditto for endp. */
-
-/*
- * Forwards.
- */
-STATIC int regtry();
-STATIC int regmatch();
-STATIC int regrepeat();
-
-#ifdef DEBUG
-int regnarrate = 0;
-void regdump();
-STATIC char *regprop();
-#endif
-
-/*
- - regexec - match a regexp against a string
- */
-int regexec(prog, string)
-register regexp *prog;
-register char *string;
-{
- register char *s;
-
- /* Be paranoid... */
- if (prog == (regexp *)NULL || string == (char *)NULL) {
- regerror("NULL parameter");
- return (0);
- }
- /* Check validity of program. */
- if (UCHARAT(prog->program) != MAGIC) {
- regerror("corrupted program");
- return (0);
- }
- /* If there is a "must appear" string, look for it. */
- if (prog->regmust != (char *)NULL) {
- s = string;
- while ((s = STRCHR(s, prog->regmust[0])) != (char *)NULL) {
- if (strncmp(s, prog->regmust, prog->regmlen) == 0)
- break; /* Found it. */
- s++;
- }
- if (s == (char *)NULL) /* Not present. */
- return (0);
- }
- /* Mark beginning of line for ^ . */
- regbol = string;
-
- /* Simplest case: anchored match need be tried only once. */
- if (prog->reganch)
- return (regtry(prog, string));
-
- /* Messy cases: unanchored match. */
- s = string;
- if (prog->regstart != '\0')
- /* We know what char it must start with. */
- while ((s = STRCHR(s, prog->regstart)) != (char *)NULL) {
- if (regtry(prog, s))
- return (1);
- s++;
- }
- else
- /* We don't -- general case. */
- do {
- if (regtry(prog, s))
- return (1);
- } while (*s++ != '\0');
-
- /* Failure. */
- return (0);
-}
-
-/*
- - regtry - try match at specific point
- */
-
-static int regtry(regexp *prog, char *string)
-{
- register int i;
- register char **sp;
- register char **ep;
-
- reginput = string;
- regstartp = prog->startp;
- regendp = prog->endp;
-
- sp = prog->startp;
- ep = prog->endp;
- for (i = NSUBEXP; i > 0; i--) {
- *sp++ = (char *)NULL;
- *ep++ = (char *)NULL;
- }
- if (regmatch(prog->program + 1)) {
- prog->startp[0] = string;
- prog->endp[0] = reginput;
- return (1);
- } else
- return (0);
-}
-
-/*
- - regmatch - main matching routine
- *
- * Conceptually the strategy is simple: check to see whether the current
- * node matches, call self recursively to see whether the rest matches,
- * and then act accordingly. In practice we make some effort to avoid
- * recursion, in particular by going through "ordinary" nodes (that don't
- * need to know whether the rest of the match failed) by a loop instead of
- * by recursion.
- */
-
-static int regmatch(char *prog)
-{
- register char *scan; /* Current node. */
- char *nxt; /* nxt node. */
-
- scan = prog;
-#ifdef DEBUG
- if (scan != (char *)NULL && regnarrate)
- fprintf(stderr, "%s(\n", regprop(scan));
-#endif
- while (scan != (char *)NULL) {
-#ifdef DEBUG
- if (regnarrate)
- fprintf(stderr, "%s...\n", regprop(scan));
-#endif
- nxt = regnext(scan);
-
- switch (OP(scan)) {
- case BOL:
- if (reginput != regbol)
- return (0);
- break;
- case EOL:
- if (*reginput != '\0')
- return (0);
- break;
- case ANY:
- if (*reginput == '\0')
- return (0);
- reginput++;
- break;
- case WORDSTART:
- if (reginput == regbol)
- break;
- if (*reginput == '\0' ||
- ISWORDPART( *(reginput-1) ) || !ISWORDPART( *reginput ) )
- return (0);
- break;
- case WORDEND:
- if (*reginput == '\0')
- break;
- if ( reginput == regbol ||
- !ISWORDPART( *(reginput-1) ) || ISWORDPART( *reginput ) )
- return (0);
- break;
- case EXACTLY:{
- register int len;
- register char *opnd;
-
- opnd = OPERAND(scan);
- /* Inline the first character, for speed. */
- if (*opnd != *reginput)
- return (0);
- len = strlen(opnd);
- if (len > 1 && strncmp(opnd, reginput, len) != 0)
- return (0);
- reginput += len;
- }
- break;
- case ANYOF:
- if (*reginput == '\0' ||
- STRCHR(OPERAND(scan), *reginput) == (char *)NULL)
- return (0);
- reginput++;
- break;
- case ANYBUT:
- if (*reginput == '\0' ||
- STRCHR(OPERAND(scan), *reginput) != (char *)NULL)
- return (0);
- reginput++;
- break;
- case NOTHING:
- break;
- case BACK:
- break;
- case OPEN + 1:
- case OPEN + 2:
- case OPEN + 3:
- case OPEN + 4:
- case OPEN + 5:
- case OPEN + 6:
- case OPEN + 7:
- case OPEN + 8:
- case OPEN + 9:{
- register int no;
- register char *save;
-
- no = OP(scan) - OPEN;
- save = reginput;
-
- if (regmatch(nxt)) {
- /*
- * Don't set startp if some later invocation of the same
- * parentheses already has.
- */
- if (regstartp[no] == (char *)NULL)
- regstartp[no] = save;
- return (1);
- } else
- return (0);
- }
-
- case CLOSE + 1:
- case CLOSE + 2:
- case CLOSE + 3:
- case CLOSE + 4:
- case CLOSE + 5:
- case CLOSE + 6:
- case CLOSE + 7:
- case CLOSE + 8:
- case CLOSE + 9:{
- register int no;
- register char *save;
-
- no = OP(scan) - CLOSE;
- save = reginput;
-
- if (regmatch(nxt)) {
- /*
- * Don't set endp if some later invocation of the same
- * parentheses already has.
- */
- if (regendp[no] == (char *)NULL)
- regendp[no] = save;
- return (1);
- } else
- return (0);
- }
-
- case BRANCH:{
- register char *save;
-
- if (OP(nxt) != BRANCH) /* No choice. */
- nxt = OPERAND(scan); /* Avoid recursion. */
- else {
- do {
- save = reginput;
- if (regmatch(OPERAND(scan)))
- return (1);
- reginput = save;
- scan = regnext(scan);
- } while (scan != (char *)NULL && OP(scan) == BRANCH);
- return (0);
- /* NOTREACHED */
- }
- }
- break;
- case STAR:{
- register char nextch;
- register int no;
- register char *save;
- register int minimum;
-
- /*
- * Lookahead to avoid useless match attempts when we know
- * what character comes next.
- */
- nextch = '\0';
- if (OP(nxt) == EXACTLY)
- nextch = *OPERAND(nxt);
- minimum = (OP(scan) == STAR) ? 0 : 1;
- save = reginput;
- no = regrepeat(OPERAND(scan));
- while (no >= minimum) {
- /* If it could work, try it. */
- if (nextch == '\0' || *reginput == nextch)
- if (regmatch(nxt))
- return (1);
- /* Couldn't or didn't -- back up. */
- no--;
- reginput = save + no;
- }
- return (0);
- }
-
- case END:
- return (1); /* Success! */
-
- default:
- regerror("memory corruption");
- return (0);
-
- }
-
- scan = nxt;
- }
-
- /*
- * We get here only if there's trouble -- normally "case END" is the
- * terminating point.
- */
- regerror("corrupted pointers");
- return (0);
-}
-
-/*
- - regrepeat - repeatedly match something simple, report how many
- */
-
-static int regrepeat(char *p)
-{
- register int count = 0;
- register char *scan;
- register char *opnd;
-
- scan = reginput;
- opnd = OPERAND(p);
- switch (OP(p)) {
- case ANY:
- count = strlen(scan);
- scan += count;
- break;
- case EXACTLY:
- while (*opnd == *scan) {
- count++;
- scan++;
- }
- break;
- case ANYOF:
- while (*scan != '\0' && STRCHR(opnd, *scan) != (char *)NULL) {
- count++;
- scan++;
- }
- break;
- case ANYBUT:
- while (*scan != '\0' && STRCHR(opnd, *scan) == (char *)NULL) {
- count++;
- scan++;
- }
- break;
- default: /* Oh dear. Called inappropriately. */
- regerror("internal foulup");
- count = 0; /* Best compromise. */
- break;
- }
- reginput = scan;
-
- return (count);
-}
-
-
-/*
- - regnext - dig the "nxt" pointer out of a node
- */
-
-static char *regnext(register char *p)
-{
- register int offset;
-
- if (p == &regdummy)
- return ((char *)NULL);
-
- offset = NEXT(p);
- if (offset == 0)
- return ((char *)NULL);
-
- if (OP(p) == BACK)
- return (p - offset);
- else
- return (p + offset);
-}
-
-#ifdef DEBUG
-
-STATIC char *regprop();
-
-/*
- - regdump - dump a regexp onto stdout in vaguely comprehensible form
- */
-void regdump(regexp *r)
-{
- register char *s;
- register char op = EXACTLY; /* Arbitrary non-END op. */
- register char *nxt;
-
- s = r->program + 1;
- while (op != END) { /* While that wasn't END last time... */
- op = OP(s);
- printf("%2ld%s", (long)(s - r->program), regprop(s)); /* Where, what. */
- nxt = regnext(s);
- if (nxt == (char *)NULL) /* nxt ptr. */
- printf("(0)");
- else
- printf("(%ld)", (long)( (s - r->program) + (nxt - s)));
- s += 3;
- if (op == ANYOF || op == ANYBUT || op == EXACTLY) {
- /* Literal string, where present. */
- while (*s != '\0') {
- putchar(*s);
- s++;
- }
- s++;
- }
- putchar('\n');
- }
-
- /* Header fields of interest. */
- if (r->regstart != '\0')
- printf("start `%c' ", r->regstart);
- if (r->reganch)
- printf("anchored ");
- if (r->regmust != (char *)NULL)
- printf("must have \"%s\"", r->regmust);
- printf("\n");
-}
-
-/*
- - regprop - printable representation of opcode
- */
-
-static char *regprop(char *op)
-{
- register char *p;
- static char buf[50];
-
- strcpy(buf, ":");
-
- switch (OP(op)) {
- case BOL:
- p = "BOL";
- break;
- case EOL:
- p = "EOL";
- break;
- case ANY:
- p = "ANY";
- break;
- case ANYOF:
- p = "ANYOF";
- break;
- case ANYBUT:
- p = "ANYBUT";
- break;
- case BRANCH:
- p = "BRANCH";
- break;
- case EXACTLY:
- p = "EXACTLY";
- break;
- case NOTHING:
- p = "NOTHING";
- break;
- case BACK:
- p = "BACK";
- break;
- case END:
- p = "END";
- break;
- case OPEN + 1:
- case OPEN + 2:
- case OPEN + 3:
- case OPEN + 4:
- case OPEN + 5:
- case OPEN + 6:
- case OPEN + 7:
- case OPEN + 8:
- case OPEN + 9:
- sprintf(buf + strlen(buf), "OPEN%d", OP(op) - OPEN);
- p = (char *)NULL;
- break;
- case CLOSE + 1:
- case CLOSE + 2:
- case CLOSE + 3:
- case CLOSE + 4:
- case CLOSE + 5:
- case CLOSE + 6:
- case CLOSE + 7:
- case CLOSE + 8:
- case CLOSE + 9:
- sprintf(buf + strlen(buf), "CLOSE%d", OP(op) - CLOSE);
- p = (char *)NULL;
- break;
- case STAR:
- p = "STAR";
- break;
- default:
- regerror("corrupted opcode");
- p=(char *)NULL;
- break;
- }
- if (p != (char *)NULL)
- strcat(buf, p);
- return (buf);
-}
-#endif
-
-/*
- - regsub - perform substitutions after a regexp match
- */
-
-char *regsub(regexp *prog, char *source, char *dest, int n)
-{
- register char *src;
- register char *dst;
- register char c;
- register int no;
- register int len;
- extern char *strncpy();
-
- if (prog == (regexp *)NULL ||
- source == (char *)NULL || dest == (char *)NULL) {
- regerror("NULL parm to regsub");
- return NULL;
- }
- if (UCHARAT(prog->program) != MAGIC) {
- regerror("damaged regexp fed to regsub");
- return NULL;
- }
- src = source;
- dst = dest;
- while ((c = *src++) != '\0') {
- if (c == '&')
- no = 0;
- else if (c == '\\' && '0' <= *src && *src <= '9')
- no = *src++ - '0';
- else
- no = -1;
-
- if (no < 0) { /* Ordinary character. */
- if (c == '\\' && (*src == '\\' || *src == '&'))
- c = *src++;
- if (--n < 0) { /* amylaar */
- regerror("line too long");
- return NULL;
- }
- *dst++ = c;
- } else if (prog->startp[no] != (char *)NULL &&
- prog->endp[no] != (char *)NULL) {
- len = prog->endp[no] - prog->startp[no];
- if ( (n-=len) < 0 ) { /* amylaar */
- regerror("line too long");
- return NULL;
- }
- strncpy(dst, prog->startp[no], len);
- dst += len;
- if (len != 0 && *(dst - 1) == '\0') { /* strncpy hit NUL. */
- regerror("damaged match string");
- return NULL;
- }
- }
- }
- if (--n < 0) { /* amylaar */
- regerror("line too long");
- return NULL;
- }
- *dst = '\0';
- return dst;
-}
-
-
-#if 0 /* Use the local regerror() in ed.c */
-
-void regerror(char *s)
-{
- fprintf(stderr, "regexp(3): %s", s);
- exit(1);
-}
-#endif /* 0 */
diff --git a/regex/regfree.c b/regex/regfree.c
deleted file mode 100644
index f764fcdf84e..00000000000
--- a/regex/regfree.c
+++ /dev/null
@@ -1,38 +0,0 @@
-#include <my_global.h>
-#include <sys/types.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include "my_regex.h"
-
-#include "utils.h"
-#include "regex2.h"
-
-/*
- - regfree - free everything
- = extern void regfree(regex_t *);
- */
-void
-my_regfree(preg)
-my_regex_t *preg;
-{
- register struct re_guts *g;
-
- if (preg->re_magic != MAGIC1) /* oops */
- return; /* nice to complain, but hard */
-
- g = preg->re_g;
- if (g == NULL || g->magic != MAGIC2) /* oops again */
- return;
- preg->re_magic = 0; /* mark it invalid */
- g->magic = 0; /* mark it invalid */
-
- if (g->strip != NULL)
- free((char *)g->strip);
- if (g->sets != NULL)
- free((char *)g->sets);
- if (g->setbits != NULL)
- free((char *)g->setbits);
- if (g->must != NULL)
- free(g->must);
- free((char *)g);
-}
diff --git a/regex/reginit.c b/regex/reginit.c
deleted file mode 100644
index 3d2cd64d1e7..00000000000
--- a/regex/reginit.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/* Init cclasses array from ctypes */
-
-#include <my_global.h>
-#include <m_ctype.h>
-#include <m_string.h>
-#include "cclass.h"
-#include "my_regex.h"
-
-static my_bool regex_inited=0;
-extern my_regex_stack_check_t my_regex_enough_mem_in_stack;
-
-void my_regex_init(CHARSET_INFO *cs, my_regex_stack_check_t func)
-{
- char buff[CCLASS_LAST][256];
- int count[CCLASS_LAST];
- uint i;
-
- if (!regex_inited)
- {
- regex_inited=1;
- my_regex_enough_mem_in_stack= func;
- bzero((uchar*) &count,sizeof(count));
-
- for (i=1 ; i<= 255; i++)
- {
- if (my_isalnum(cs,i))
- buff[CCLASS_ALNUM][count[CCLASS_ALNUM]++]=(char) i;
- if (my_isalpha(cs,i))
- buff[CCLASS_ALPHA][count[CCLASS_ALPHA]++]=(char) i;
- if (my_iscntrl(cs,i))
- buff[CCLASS_CNTRL][count[CCLASS_CNTRL]++]=(char) i;
- if (my_isdigit(cs,i))
- buff[CCLASS_DIGIT][count[CCLASS_DIGIT]++]=(char) i;
- if (my_isgraph(cs,i))
- buff[CCLASS_GRAPH][count[CCLASS_GRAPH]++]=(char) i;
- if (my_islower(cs,i))
- buff[CCLASS_LOWER][count[CCLASS_LOWER]++]=(char) i;
- if (my_isprint(cs,i))
- buff[CCLASS_PRINT][count[CCLASS_PRINT]++]=(char) i;
- if (my_ispunct(cs,i))
- buff[CCLASS_PUNCT][count[CCLASS_PUNCT]++]=(char) i;
- if (my_isspace(cs,i))
- buff[CCLASS_SPACE][count[CCLASS_SPACE]++]=(char) i;
- if (my_isupper(cs,i))
- buff[CCLASS_UPPER][count[CCLASS_UPPER]++]=(char) i;
- if (my_isxdigit(cs,i))
- buff[CCLASS_XDIGIT][count[CCLASS_XDIGIT]++]=(char) i;
- }
- buff[CCLASS_BLANK][0]=' ';
- buff[CCLASS_BLANK][1]='\t';
- count[CCLASS_BLANK]=2;
- for (i=0; i < CCLASS_LAST ; i++)
- {
- char *tmp=(char*) malloc(count[i]+1);
- if (!tmp)
- {
- /*
- This is very unlikely to happen as this function is called once
- at program startup
- */
- fprintf(stderr,
- "Fatal error: Can't allocate memory in regex_init\n");
- exit(1);
- }
- memcpy(tmp,buff[i],count[i]*sizeof(char));
- tmp[count[i]]=0;
- cclasses[i].chars=tmp;
- }
- }
- return;
-}
-
-void my_regex_end()
-{
- if (regex_inited)
- {
- int i;
- for (i=0; i < CCLASS_LAST ; i++)
- free((char*) cclasses[i].chars);
- my_regex_enough_mem_in_stack= NULL;
- regex_inited=0;
- }
-}
-
-
diff --git a/regex/split.c b/regex/split.c
deleted file mode 100644
index bd2a53c01e3..00000000000
--- a/regex/split.c
+++ /dev/null
@@ -1,316 +0,0 @@
-#include <stdio.h>
-#include <string.h>
-
-/*
- - split - divide a string into fields, like awk split()
- = int split(char *string, char *fields[], int nfields, char *sep);
- */
-int /* number of fields, including overflow */
-split(string, fields, nfields, sep)
-char *string;
-char *fields[]; /* list is not NULL-terminated */
-int nfields; /* number of entries available in fields[] */
-char *sep; /* "" white, "c" single char, "ab" [ab]+ */
-{
- register char *p = string;
- register char c; /* latest character */
- register char sepc = sep[0];
- register char sepc2;
- register int fn;
- register char **fp = fields;
- register char *sepp;
- register int trimtrail;
-
- /* white space */
- if (sepc == '\0') {
- while ((c = *p++) == ' ' || c == '\t')
- continue;
- p--;
- trimtrail = 1;
- sep = (char*) " \t"; /* note, code below knows this is 2 long */
- sepc = ' ';
- } else
- trimtrail = 0;
- sepc2 = sep[1]; /* now we can safely pick this up */
-
- /* catch empties */
- if (*p == '\0')
- return(0);
-
- /* single separator */
- if (sepc2 == '\0') {
- fn = nfields;
- for (;;) {
- *fp++ = p;
- fn--;
- if (fn == 0)
- break;
- while ((c = *p++) != sepc)
- if (c == '\0')
- return(nfields - fn);
- *(p-1) = '\0';
- }
- /* we have overflowed the fields vector -- just count them */
- fn = nfields;
- for (;;) {
- while ((c = *p++) != sepc)
- if (c == '\0')
- return(fn);
- fn++;
- }
- /* not reached */
- }
-
- /* two separators */
- if (sep[2] == '\0') {
- fn = nfields;
- for (;;) {
- *fp++ = p;
- fn--;
- while ((c = *p++) != sepc && c != sepc2)
- if (c == '\0') {
- if (trimtrail && **(fp-1) == '\0')
- fn++;
- return(nfields - fn);
- }
- if (fn == 0)
- break;
- *(p-1) = '\0';
- while ((c = *p++) == sepc || c == sepc2)
- continue;
- p--;
- }
- /* we have overflowed the fields vector -- just count them */
- fn = nfields;
- while (c != '\0') {
- while ((c = *p++) == sepc || c == sepc2)
- continue;
- p--;
- fn++;
- while ((c = *p++) != '\0' && c != sepc && c != sepc2)
- continue;
- }
- /* might have to trim trailing white space */
- if (trimtrail) {
- p--;
- while ((c = *--p) == sepc || c == sepc2)
- continue;
- p++;
- if (*p != '\0') {
- if (fn == nfields+1)
- *p = '\0';
- fn--;
- }
- }
- return(fn);
- }
-
- /* n separators */
- fn = 0;
- for (;;) {
- if (fn < nfields)
- *fp++ = p;
- fn++;
- for (;;) {
- c = *p++;
- if (c == '\0')
- return(fn);
- sepp = sep;
- while ((sepc = *sepp++) != '\0' && sepc != c)
- continue;
- if (sepc != '\0') /* it was a separator */
- break;
- }
- if (fn < nfields)
- *(p-1) = '\0';
- for (;;) {
- c = *p++;
- sepp = sep;
- while ((sepc = *sepp++) != '\0' && sepc != c)
- continue;
- if (sepc == '\0') /* it wasn't a separator */
- break;
- }
- p--;
- }
-
- /* not reached */
-}
-
-#ifdef TEST_SPLIT
-
-
-/*
- * test program
- * pgm runs regression
- * pgm sep splits stdin lines by sep
- * pgm str sep splits str by sep
- * pgm str sep n splits str by sep n times
- */
-int
-main(argc, argv)
-int argc;
-char *argv[];
-{
- char buf[512];
- register int n;
-# define MNF 10
- char *fields[MNF];
-
- if (argc > 4)
- for (n = atoi(argv[3]); n > 0; n--) {
- (void) strcpy(buf, argv[1]);
- }
- else if (argc > 3)
- for (n = atoi(argv[3]); n > 0; n--) {
- (void) strcpy(buf, argv[1]);
- (void) split(buf, fields, MNF, argv[2]);
- }
- else if (argc > 2)
- dosplit(argv[1], argv[2]);
- else if (argc > 1)
- while (fgets(buf, sizeof(buf), stdin) != NULL) {
- buf[strlen(buf)-1] = '\0'; /* stomp newline */
- dosplit(buf, argv[1]);
- }
- else
- regress();
-
- exit(0);
-}
-
-dosplit(string, seps)
-char *string;
-char *seps;
-{
-# define NF 5
- char *fields[NF];
- register int nf;
-
- nf = split(string, fields, NF, seps);
- print(nf, NF, fields);
-}
-
-print(nf, nfp, fields)
-int nf;
-int nfp;
-char *fields[];
-{
- register int fn;
- register int bound;
-
- bound = (nf > nfp) ? nfp : nf;
- printf("%d:\t", nf);
- for (fn = 0; fn < bound; fn++)
- printf("\"%s\"%s", fields[fn], (fn+1 < nf) ? ", " : "\n");
-}
-
-#define RNF 5 /* some table entries know this */
-struct {
- char *str;
- char *seps;
- int nf;
- char *fi[RNF];
-} tests[] = {
- "", " ", 0, { "" },
- " ", " ", 2, { "", "" },
- "x", " ", 1, { "x" },
- "xy", " ", 1, { "xy" },
- "x y", " ", 2, { "x", "y" },
- "abc def g ", " ", 5, { "abc", "def", "", "g", "" },
- " a bcd", " ", 4, { "", "", "a", "bcd" },
- "a b c d e f", " ", 6, { "a", "b", "c", "d", "e f" },
- " a b c d ", " ", 6, { "", "a", "b", "c", "d " },
-
- "", " _", 0, { "" },
- " ", " _", 2, { "", "" },
- "x", " _", 1, { "x" },
- "x y", " _", 2, { "x", "y" },
- "ab _ cd", " _", 2, { "ab", "cd" },
- " a_b c ", " _", 5, { "", "a", "b", "c", "" },
- "a b c_d e f", " _", 6, { "a", "b", "c", "d", "e f" },
- " a b c d ", " _", 6, { "", "a", "b", "c", "d " },
-
- "", " _~", 0, { "" },
- " ", " _~", 2, { "", "" },
- "x", " _~", 1, { "x" },
- "x y", " _~", 2, { "x", "y" },
- "ab _~ cd", " _~", 2, { "ab", "cd" },
- " a_b c~", " _~", 5, { "", "a", "b", "c", "" },
- "a b_c d~e f", " _~", 6, { "a", "b", "c", "d", "e f" },
- "~a b c d ", " _~", 6, { "", "a", "b", "c", "d " },
-
- "", " _~-", 0, { "" },
- " ", " _~-", 2, { "", "" },
- "x", " _~-", 1, { "x" },
- "x y", " _~-", 2, { "x", "y" },
- "ab _~- cd", " _~-", 2, { "ab", "cd" },
- " a_b c~", " _~-", 5, { "", "a", "b", "c", "" },
- "a b_c-d~e f", " _~-", 6, { "a", "b", "c", "d", "e f" },
- "~a-b c d ", " _~-", 6, { "", "a", "b", "c", "d " },
-
- "", " ", 0, { "" },
- " ", " ", 2, { "", "" },
- "x", " ", 1, { "x" },
- "xy", " ", 1, { "xy" },
- "x y", " ", 2, { "x", "y" },
- "abc def g ", " ", 4, { "abc", "def", "g", "" },
- " a bcd", " ", 3, { "", "a", "bcd" },
- "a b c d e f", " ", 6, { "a", "b", "c", "d", "e f" },
- " a b c d ", " ", 6, { "", "a", "b", "c", "d " },
-
- "", "", 0, { "" },
- " ", "", 0, { "" },
- "x", "", 1, { "x" },
- "xy", "", 1, { "xy" },
- "x y", "", 2, { "x", "y" },
- "abc def g ", "", 3, { "abc", "def", "g" },
- "\t a bcd", "", 2, { "a", "bcd" },
- " a \tb\t c ", "", 3, { "a", "b", "c" },
- "a b c d e ", "", 5, { "a", "b", "c", "d", "e" },
- "a b\tc d e f", "", 6, { "a", "b", "c", "d", "e f" },
- " a b c d e f ", "", 6, { "a", "b", "c", "d", "e f " },
-
- NULL, NULL, 0, { NULL },
-};
-
-regress()
-{
- char buf[512];
- register int n;
- char *fields[RNF+1];
- register int nf;
- register int i;
- register int printit;
- register char *f;
-
- for (n = 0; tests[n].str != NULL; n++) {
- (void) strcpy(buf, tests[n].str);
- fields[RNF] = NULL;
- nf = split(buf, fields, RNF, tests[n].seps);
- printit = 0;
- if (nf != tests[n].nf) {
- printf("split `%s' by `%s' gave %d fields, not %d\n",
- tests[n].str, tests[n].seps, nf, tests[n].nf);
- printit = 1;
- } else if (fields[RNF] != NULL) {
- printf("split() went beyond array end\n");
- printit = 1;
- } else {
- for (i = 0; i < nf && i < RNF; i++) {
- f = fields[i];
- if (f == NULL)
- f = "(NULL)";
- if (strcmp(f, tests[n].fi[i]) != 0) {
- printf("split `%s' by `%s', field %d is `%s', not `%s'\n",
- tests[n].str, tests[n].seps,
- i, fields[i], tests[n].fi[i]);
- printit = 1;
- }
- }
- }
- if (printit)
- print(nf, RNF, fields);
- }
-}
-#endif
diff --git a/regex/tests b/regex/tests
deleted file mode 100644
index 2886449d519..00000000000
--- a/regex/tests
+++ /dev/null
@@ -1,474 +0,0 @@
-# regular expression test set
-# Lines are at least three fields, separated by one or more tabs. "" stands
-# for an empty field. First field is an RE. Second field is flags. If
-# C flag given, regcomp() is expected to fail, and the third field is the
-# error name (minus the leading REG_).
-#
-# Otherwise it is expected to succeed, and the third field is the string to
-# try matching it against. If there is no fourth field, the match is
-# expected to fail. If there is a fourth field, it is the substring that
-# the RE is expected to match. If there is a fifth field, it is a comma-
-# separated list of what the subexpressions should match, with - indicating
-# no match for that one. In both the fourth and fifth fields, a (sub)field
-# starting with @ indicates that the (sub)expression is expected to match
-# a null string followed by the stuff after the @; this provides a way to
-# test where null strings match. The character `N' in REs and strings
-# is newline, `S' is space, `T' is tab, `Z' is NUL.
-#
-# The full list of flags:
-# - placeholder, does nothing
-# b RE is a BRE, not an ERE
-# & try it as both an ERE and a BRE
-# C regcomp() error expected, third field is error name
-# i REG_ICASE
-# m ("mundane") REG_NOSPEC
-# s REG_NOSUB (not really testable)
-# n REG_NEWLINE
-# ^ REG_NOTBOL
-# $ REG_NOTEOL
-# # REG_STARTEND (see below)
-# p REG_PEND
-#
-# For REG_STARTEND, the start/end offsets are those of the substring
-# enclosed in ().
-
-# basics
-a & a a
-abc & abc abc
-abc|de - abc abc
-a|b|c - abc a
-
-# parentheses and perversions thereof
-a(b)c - abc abc
-a\(b\)c b abc abc
-a( C EPAREN
-a( b a( a(
-a\( - a( a(
-a\( bC EPAREN
-a\(b bC EPAREN
-a(b C EPAREN
-a(b b a(b a(b
-# gag me with a right parenthesis -- 1003.2 goofed here (my fault, partly)
-a) - a) a)
-) - ) )
-# end gagging (in a just world, those *should* give EPAREN)
-a) b a) a)
-a\) bC EPAREN
-\) bC EPAREN
-a()b - ab ab
-a\(\)b b ab ab
-
-# anchoring and REG_NEWLINE
-^abc$ & abc abc
-a^b - a^b
-a^b b a^b a^b
-a$b - a$b
-a$b b a$b a$b
-^ & abc @abc
-$ & abc @
-^$ & "" @
-$^ - "" @
-\($\)\(^\) b "" @
-# stop retching, those are legitimate (although disgusting)
-^^ - "" @
-$$ - "" @
-b$ & abNc
-b$ &n abNc b
-^b$ & aNbNc
-^b$ &n aNbNc b
-^$ &n aNNb @Nb
-^$ n abc
-^$ n abcN @
-$^ n aNNb @Nb
-\($\)\(^\) bn aNNb @Nb
-^^ n^ aNNb @Nb
-$$ n aNNb @NN
-^a ^ a
-a$ $ a
-^a ^n aNb
-^b ^n aNb b
-a$ $n bNa
-b$ $n bNa b
-a*(^b$)c* - b b
-a*\(^b$\)c* b b b
-
-# certain syntax errors and non-errors
-| C EMPTY
-| b | |
-* C BADRPT
-* b * *
-+ C BADRPT
-? C BADRPT
-"" &C EMPTY
-() - abc @abc
-\(\) b abc @abc
-a||b C EMPTY
-|ab C EMPTY
-ab| C EMPTY
-(|a)b C EMPTY
-(a|)b C EMPTY
-(*a) C BADRPT
-(+a) C BADRPT
-(?a) C BADRPT
-({1}a) C BADRPT
-\(\{1\}a\) bC BADRPT
-(a|*b) C BADRPT
-(a|+b) C BADRPT
-(a|?b) C BADRPT
-(a|{1}b) C BADRPT
-^* C BADRPT
-^* b * *
-^+ C BADRPT
-^? C BADRPT
-^{1} C BADRPT
-^\{1\} bC BADRPT
-
-# metacharacters, backslashes
-a.c & abc abc
-a[bc]d & abd abd
-a\*c & a*c a*c
-a\\b & a\b a\b
-a\\\*b & a\*b a\*b
-a\bc & abc abc
-a\ &C EESCAPE
-a\\bc & a\bc a\bc
-\{ bC BADRPT
-a\[b & a[b a[b
-a[b &C EBRACK
-# trailing $ is a peculiar special case for the BRE code
-a$ & a a
-a$ & a$
-a\$ & a
-a\$ & a$ a$
-a\\$ & a
-a\\$ & a$
-a\\$ & a\$
-a\\$ & a\ a\
-
-# back references, ugh
-a\(b\)\2c bC ESUBREG
-a\(b\1\)c bC ESUBREG
-a\(b*\)c\1d b abbcbbd abbcbbd bb
-a\(b*\)c\1d b abbcbd
-a\(b*\)c\1d b abbcbbbd
-^\(.\)\1 b abc
-a\([bc]\)\1d b abcdabbd abbd b
-a\(\([bc]\)\2\)*d b abbccd abbccd
-a\(\([bc]\)\2\)*d b abbcbd
-# actually, this next one probably ought to fail, but the spec is unclear
-a\(\(b\)*\2\)*d b abbbd abbbd
-# here is a case that no NFA implementation does right
-\(ab*\)[ab]*\1 b ababaaa ababaaa a
-# check out normal matching in the presence of back refs
-\(a\)\1bcd b aabcd aabcd
-\(a\)\1bc*d b aabcd aabcd
-\(a\)\1bc*d b aabd aabd
-\(a\)\1bc*d b aabcccd aabcccd
-\(a\)\1bc*[ce]d b aabcccd aabcccd
-^\(a\)\1b\(c\)*cd$ b aabcccd aabcccd
-
-# ordinary repetitions
-ab*c & abc abc
-ab+c - abc abc
-ab?c - abc abc
-a\(*\)b b a*b a*b
-a\(**\)b b ab ab
-a\(***\)b bC BADRPT
-*a b *a *a
-**a b a a
-***a bC BADRPT
-
-# the dreaded bounded repetitions
-{ & { {
-{abc & {abc {abc
-{1 C BADRPT
-{1} C BADRPT
-a{b & a{b a{b
-a{1}b - ab ab
-a\{1\}b b ab ab
-a{1,}b - ab ab
-a\{1,\}b b ab ab
-a{1,2}b - aab aab
-a\{1,2\}b b aab aab
-a{1 C EBRACE
-a\{1 bC EBRACE
-a{1a C EBRACE
-a\{1a bC EBRACE
-a{1a} C BADBR
-a\{1a\} bC BADBR
-a{,2} - a{,2} a{,2}
-a\{,2\} bC BADBR
-a{,} - a{,} a{,}
-a\{,\} bC BADBR
-a{1,x} C BADBR
-a\{1,x\} bC BADBR
-a{1,x C EBRACE
-a\{1,x bC EBRACE
-a{300} C BADBR
-a\{300\} bC BADBR
-a{1,0} C BADBR
-a\{1,0\} bC BADBR
-ab{0,0}c - abcac ac
-ab\{0,0\}c b abcac ac
-ab{0,1}c - abcac abc
-ab\{0,1\}c b abcac abc
-ab{0,3}c - abbcac abbc
-ab\{0,3\}c b abbcac abbc
-ab{1,1}c - acabc abc
-ab\{1,1\}c b acabc abc
-ab{1,3}c - acabc abc
-ab\{1,3\}c b acabc abc
-ab{2,2}c - abcabbc abbc
-ab\{2,2\}c b abcabbc abbc
-ab{2,4}c - abcabbc abbc
-ab\{2,4\}c b abcabbc abbc
-((a{1,10}){1,10}){1,10} - a a a,a
-
-# multiple repetitions
-a** &C BADRPT
-a++ C BADRPT
-a?? C BADRPT
-a*+ C BADRPT
-a*? C BADRPT
-a+* C BADRPT
-a+? C BADRPT
-a?* C BADRPT
-a?+ C BADRPT
-a{1}{1} C BADRPT
-a*{1} C BADRPT
-a+{1} C BADRPT
-a?{1} C BADRPT
-a{1}* C BADRPT
-a{1}+ C BADRPT
-a{1}? C BADRPT
-a*{b} - a{b} a{b}
-a\{1\}\{1\} bC BADRPT
-a*\{1\} bC BADRPT
-a\{1\}* bC BADRPT
-
-# brackets, and numerous perversions thereof
-a[b]c & abc abc
-a[ab]c & abc abc
-a[^ab]c & adc adc
-a[]b]c & a]c a]c
-a[[b]c & a[c a[c
-a[-b]c & a-c a-c
-a[^]b]c & adc adc
-a[^-b]c & adc adc
-a[b-]c & a-c a-c
-a[b &C EBRACK
-a[] &C EBRACK
-a[1-3]c & a2c a2c
-a[3-1]c &C ERANGE
-a[1-3-5]c &C ERANGE
-a[[.-.]--]c & a-c a-c
-a[1- &C ERANGE
-a[[. &C EBRACK
-a[[.x &C EBRACK
-a[[.x. &C EBRACK
-a[[.x.] &C EBRACK
-a[[.x.]] & ax ax
-a[[.x,.]] &C ECOLLATE
-a[[.one.]]b & a1b a1b
-a[[.notdef.]]b &C ECOLLATE
-a[[.].]]b & a]b a]b
-a[[:notdef:]]c &C ECTYPE
-a[[: &C EBRACK
-a[[:alpha &C EBRACK
-a[[:alpha:] &C EBRACK
-a[[:alpha,:] &C ECTYPE
-a[[:]:]]b &C ECTYPE
-a[[:-:]]b &C ECTYPE
-a[[:alph:]] &C ECTYPE
-a[[:alphabet:]] &C ECTYPE
-[[:alnum:]]+ - -%@aÄX- aÄX
-[[:alpha:]]+ - -%@aX0- aX
-[[:blank:]]+ - aSSTb SST
-[[:cntrl:]]+ - aNTb NT
-[[:digit:]]+ - a019b 019
-[[:graph:]]+ - Sa%bS a%b
-[[:lower:]]+ - AabC ab
-[[:print:]]+ - NaSbN aSb
-[[:punct:]]+ - S%-&T %-&
-[[:space:]]+ - aSNTb SNT
-[[:upper:]]+ - aBCd BC
-[[:xdigit:]]+ - p0f3Cq 0f3C
-a[[=b=]]c & abc abc
-a[[= &C EBRACK
-a[[=b &C EBRACK
-a[[=b= &C EBRACK
-a[[=b=] &C EBRACK
-a[[=b,=]] &C ECOLLATE
-a[[=one=]]b & a1b a1b
-
-# complexities
-a(((b)))c - abc abc
-a(b|(c))d - abd abd
-a(b*|c)d - abbd abbd
-# just gotta have one DFA-buster, of course
-a[ab]{20} - aaaaabaaaabaaaabaaaab aaaaabaaaabaaaabaaaab
-# and an inline expansion in case somebody gets tricky
-a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab] - aaaaabaaaabaaaabaaaab aaaaabaaaabaaaabaaaab
-# and in case somebody just slips in an NFA...
-a[ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab][ab](wee|week)(knights|night) - aaaaabaaaabaaaabaaaabweeknights aaaaabaaaabaaaabaaaabweeknights
-# fish for anomalies as the number of states passes 32
-12345678901234567890123456789 - a12345678901234567890123456789b 12345678901234567890123456789
-123456789012345678901234567890 - a123456789012345678901234567890b 123456789012345678901234567890
-1234567890123456789012345678901 - a1234567890123456789012345678901b 1234567890123456789012345678901
-12345678901234567890123456789012 - a12345678901234567890123456789012b 12345678901234567890123456789012
-123456789012345678901234567890123 - a123456789012345678901234567890123b 123456789012345678901234567890123
-# and one really big one, beyond any plausible word width
-1234567890123456789012345678901234567890123456789012345678901234567890 - a1234567890123456789012345678901234567890123456789012345678901234567890b 1234567890123456789012345678901234567890123456789012345678901234567890
-# fish for problems as brackets go past 8
-[ab][cd][ef][gh][ij][kl][mn] - xacegikmoq acegikm
-[ab][cd][ef][gh][ij][kl][mn][op] - xacegikmoq acegikmo
-[ab][cd][ef][gh][ij][kl][mn][op][qr] - xacegikmoqy acegikmoq
-[ab][cd][ef][gh][ij][kl][mn][op][q] - xacegikmoqy acegikmoq
-
-# subtleties of matching
-abc & xabcy abc
-a\(b\)?c\1d b acd
-aBc i Abc Abc
-a[Bc]*d i abBCcd abBCcd
-0[[:upper:]]1 &i 0a1 0a1
-0[[:lower:]]1 &i 0A1 0A1
-a[^b]c &i abc
-a[^b]c &i aBc
-a[^b]c &i adc adc
-[a]b[c] - abc abc
-[a]b[a] - aba aba
-[abc]b[abc] - abc abc
-[abc]b[abd] - abd abd
-a(b?c)+d - accd accd
-(wee|week)(knights|night) - weeknights weeknights
-(we|wee|week|frob)(knights|night|day) - weeknights weeknights
-a[bc]d - xyzaaabcaababdacd abd
-a[ab]c - aaabc abc
-abc s abc abc
-a* & b @b
-
-# Let's have some fun -- try to match a C comment.
-# first the obvious, which looks okay at first glance...
-/\*.*\*/ - /*x*/ /*x*/
-# but...
-/\*.*\*/ - /*x*/y/*z*/ /*x*/y/*z*/
-# okay, we must not match */ inside; try to do that...
-/\*([^*]|\*[^/])*\*/ - /*x*/ /*x*/
-/\*([^*]|\*[^/])*\*/ - /*x*/y/*z*/ /*x*/
-# but...
-/\*([^*]|\*[^/])*\*/ - /*x**/y/*z*/ /*x**/y/*z*/
-# and a still fancier version, which does it right (I think)...
-/\*([^*]|\*+[^*/])*\*+/ - /*x*/ /*x*/
-/\*([^*]|\*+[^*/])*\*+/ - /*x*/y/*z*/ /*x*/
-/\*([^*]|\*+[^*/])*\*+/ - /*x**/y/*z*/ /*x**/
-/\*([^*]|\*+[^*/])*\*+/ - /*x****/y/*z*/ /*x****/
-/\*([^*]|\*+[^*/])*\*+/ - /*x**x*/y/*z*/ /*x**x*/
-/\*([^*]|\*+[^*/])*\*+/ - /*x***x/y/*z*/ /*x***x/y/*z*/
-
-# subexpressions
-a(b)(c)d - abcd abcd b,c
-a(((b)))c - abc abc b,b,b
-a(b|(c))d - abd abd b,-
-a(b*|c|e)d - abbd abbd bb
-a(b*|c|e)d - acd acd c
-a(b*|c|e)d - ad ad @d
-a(b?)c - abc abc b
-a(b?)c - ac ac @c
-a(b+)c - abc abc b
-a(b+)c - abbbc abbbc bbb
-a(b*)c - ac ac @c
-(a|ab)(bc([de]+)f|cde) - abcdef abcdef a,bcdef,de
-# the regression tester only asks for 9 subexpressions
-a(b)(c)(d)(e)(f)(g)(h)(i)(j)k - abcdefghijk abcdefghijk b,c,d,e,f,g,h,i,j
-a(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)l - abcdefghijkl abcdefghijkl b,c,d,e,f,g,h,i,j,k
-a([bc]?)c - abc abc b
-a([bc]?)c - ac ac @c
-a([bc]+)c - abc abc b
-a([bc]+)c - abcc abcc bc
-a([bc]+)bc - abcbc abcbc bc
-a(bb+|b)b - abb abb b
-a(bbb+|bb+|b)b - abb abb b
-a(bbb+|bb+|b)b - abbb abbb bb
-a(bbb+|bb+|b)bb - abbb abbb b
-(.*).* - abcdef abcdef abcdef
-(a*)* - bc @b @b
-
-# do we get the right subexpression when it is used more than once?
-a(b|c)*d - ad ad -
-a(b|c)*d - abcd abcd c
-a(b|c)+d - abd abd b
-a(b|c)+d - abcd abcd c
-a(b|c?)+d - ad ad @d
-a(b|c?)+d - abcd abcd @d
-a(b|c){0,0}d - ad ad -
-a(b|c){0,1}d - ad ad -
-a(b|c){0,1}d - abd abd b
-a(b|c){0,2}d - ad ad -
-a(b|c){0,2}d - abcd abcd c
-a(b|c){0,}d - ad ad -
-a(b|c){0,}d - abcd abcd c
-a(b|c){1,1}d - abd abd b
-a(b|c){1,1}d - acd acd c
-a(b|c){1,2}d - abd abd b
-a(b|c){1,2}d - abcd abcd c
-a(b|c){1,}d - abd abd b
-a(b|c){1,}d - abcd abcd c
-a(b|c){2,2}d - acbd acbd b
-a(b|c){2,2}d - abcd abcd c
-a(b|c){2,4}d - abcd abcd c
-a(b|c){2,4}d - abcbd abcbd b
-a(b|c){2,4}d - abcbcd abcbcd c
-a(b|c){2,}d - abcd abcd c
-a(b|c){2,}d - abcbd abcbd b
-a(b+|((c)*))+d - abd abd @d,@d,-
-a(b+|((c)*))+d - abcd abcd @d,@d,-
-
-# check out the STARTEND option
-[abc] &# a(b)c b
-[abc] &# a(d)c
-[abc] &# a(bc)d b
-[abc] &# a(dc)d c
-. &# a()c
-b.*c &# b(bc)c bc
-b.* &# b(bc)c bc
-.*c &# b(bc)c bc
-
-# plain strings, with the NOSPEC flag
-abc m abc abc
-abc m xabcy abc
-abc m xyz
-a*b m aba*b a*b
-a*b m ab
-"" mC EMPTY
-
-# cases involving NULs
-aZb & a a
-aZb &p a
-aZb &p# (aZb) aZb
-aZ*b &p# (ab) ab
-a.b &# (aZb) aZb
-a.* &# (aZb)c aZb
-
-# word boundaries (ick)
-[[:<:]]a & a a
-[[:<:]]a & ba
-[[:<:]]a & -a a
-a[[:>:]] & a a
-a[[:>:]] & ab
-a[[:>:]] & a- a
-[[:<:]]a.c[[:>:]] & axcd-dayc-dazce-abc abc
-[[:<:]]a.c[[:>:]] & axcd-dayc-dazce-abc-q abc
-[[:<:]]a.c[[:>:]] & axc-dayc-dazce-abc axc
-[[:<:]]b.c[[:>:]] & a_bxc-byc_d-bzc-q bzc
-[[:<:]].x..[[:>:]] & y_xa_-_xb_y-_xc_-axdc _xc_
-[[:<:]]a_b[[:>:]] & x_a_b
-
-# past problems, and suspected problems
-(A[1])|(A[2])|(A[3])|(A[4])|(A[5])|(A[6])|(A[7])|(A[8])|(A[9])|(A[A]) - A1 A1
-abcdefghijklmnop i abcdefghijklmnop abcdefghijklmnop
-abcdefghijklmnopqrstuv i abcdefghijklmnopqrstuv abcdefghijklmnopqrstuv
-(ALAK)|(ALT[AB])|(CC[123]1)|(CM[123]1)|(GAMC)|(LC[23][EO ])|(SEM[1234])|(SL[ES][12])|(SLWW)|(SLF )|(SLDT)|(VWH[12])|(WH[34][EW])|(WP1[ESN]) - CC11 CC11
-CC[13]1|a{21}[23][EO][123][Es][12]a{15}aa[34][EW]aaaaaaa[X]a - CC11 CC11
-Char \([a-z0-9_]*\)\[.* b Char xyz[k Char xyz[k xyz
-a?b - ab ab
--\{0,1\}[0-9]*$ b -5 -5
diff --git a/regex/utils.h b/regex/utils.h
deleted file mode 100644
index 8f85b705bb5..00000000000
--- a/regex/utils.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* utility definitions */
-#ifdef _POSIX2_RE_DUP_MAX
-#define DUPMAX _POSIX2_RE_DUP_MAX /* xxx is this right? */
-#else
-#define DUPMAX 255
-#endif
-#define RE_INFINITY (DUPMAX + 1)
-#define NC (CHAR_MAX - CHAR_MIN + 1)
-typedef unsigned char uch;
-
-/* switch off assertions (if not already off) if no REDEBUG */
-#ifndef REDEBUG
-#ifndef NDEBUG
-#define NDEBUG /* no assertions please */
-#endif
-#endif
-#include <assert.h>
-
-/* for old systems with bcopy() but no memmove() */
-#ifdef USEBCOPY
-#define memmove(d, s, c) bcopy(s, d, c)
-#endif
View Lorry Controller Status