summaryrefslogtreecommitdiff
path: root/pcre_newline.c
diff options
context:
space:
mode:
authornigel <nigel@2f5784b3-3f2a-0410-8824-cb99058d5e15>2007-02-24 21:41:42 +0000
committernigel <nigel@2f5784b3-3f2a-0410-8824-cb99058d5e15>2007-02-24 21:41:42 +0000
commit876a1a775acdc16384b603754a67010ca8e80cda (patch)
treee9b25e0bf3c35e0455cdffef8f42cb72ca3c31f3 /pcre_newline.c
parent78d9c9e331dc39ca5131981dd347b7b3aeca459f (diff)
downloadpcre-876a1a775acdc16384b603754a67010ca8e80cda.tar.gz
Load pcre-7.0 into code/trunk.
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@93 2f5784b3-3f2a-0410-8824-cb99058d5e15
Diffstat (limited to 'pcre_newline.c')
-rw-r--r--pcre_newline.c135
1 files changed, 135 insertions, 0 deletions
diff --git a/pcre_newline.c b/pcre_newline.c
new file mode 100644
index 0000000..348791b
--- /dev/null
+++ b/pcre_newline.c
@@ -0,0 +1,135 @@
+/*************************************************
+* Perl-Compatible Regular Expressions *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+ Written by Philip Hazel
+ Copyright (c) 1997-2006 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+ * Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+
+ * Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+ * Neither the name of the University of Cambridge nor the names of its
+ contributors may be used to endorse or promote products derived from
+ this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains internal functions for testing newlines when more than
+one kind of newline is to be recognized. When a newline is found, its length is
+returned. In principle, we could implement several newline "types", each
+referring to a different set of newline characters. At present, PCRE supports
+only NLTYPE_FIXED, which gets handled without these functions, and NLTYPE_ALL,
+so for now the type isn't passed into the functions. It can easily be added
+later if required. The full list of Unicode newline characters is taken from
+http://unicode.org/unicode/reports/tr18/. */
+
+
+#include "pcre_internal.h"
+
+
+
+/*************************************************
+* Check for newline at given position *
+*************************************************/
+
+/* It is guaranteed that the initial value of ptr is less than the end of the
+string that is being processed.
+
+Arguments:
+ ptr pointer to possible newline
+ endptr pointer to the end of the string
+ lenptr where to return the length
+ utf8 TRUE if in utf8 mode
+
+Returns: TRUE or FALSE
+*/
+
+BOOL
+_pcre_is_newline(const uschar *ptr, const uschar *endptr, int *lenptr,
+ BOOL utf8)
+{
+int c;
+if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
+switch(c)
+ {
+ case 0x000a: /* LF */
+ case 0x000b: /* VT */
+ case 0x000c: *lenptr = 1; return TRUE; /* FF */
+ case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
+ return TRUE; /* CR */
+ case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */
+ case 0x2028: /* LS */
+ case 0x2029: *lenptr = 3; return TRUE; /* PS */
+ default: return FALSE;
+ }
+}
+
+
+
+/*************************************************
+* Check for newline at previous position *
+*************************************************/
+
+/* It is guaranteed that the initial value of ptr is greater than the start of
+the string that is being processed.
+
+Arguments:
+ ptr pointer to possible newline
+ startptr pointer to the start of the string
+ lenptr where to return the length
+ utf8 TRUE if in utf8 mode
+
+Returns: TRUE or FALSE
+*/
+
+BOOL
+_pcre_was_newline(const uschar *ptr, const uschar *startptr, int *lenptr,
+ BOOL utf8)
+{
+int c;
+ptr--;
+if (utf8)
+ {
+ BACKCHAR(ptr);
+ GETCHAR(c, ptr);
+ }
+else c = *ptr;
+switch(c)
+ {
+ case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
+ return TRUE; /* LF */
+ case 0x000b: /* VT */
+ case 0x000c: /* FF */
+ case 0x000d: *lenptr = 1; return TRUE; /* CR */
+ case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */
+ case 0x2028: /* LS */
+ case 0x2029: *lenptr = 3; return TRUE; /* PS */
+ default: return FALSE;
+ }
+}
+
+/* End of pcre_newline.c */