hcq/MaxScale
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update bundled PCRE2-library to version 10.23

Browse Source 
Some manual changes done to the library were lost with this update.
They will be added in the next commit.
This commit is contained in:
Esa Korhonen
2017-05-29 15:31:42 +03:00
parent 7231563937
commit 36af74cb25
218 changed files with 49218 additions and 26130 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
pcre2/src/pcre2posix.c
View File

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge
New API code Copyright (c) 2016 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@ -58,16 +58,49 @@ previously been set. */
# define PCRE2POSIX_EXP_DEFN __declspec(dllexport)
#endif
/* We include pcre2.h before pcre2_internal.h so that the PCRE2 library
functions are declared as "import" for Windows by defining PCRE2_EXP_DECL as
"import". This is needed even though pcre2_internal.h itself includes pcre2.h,
because it does so after it has set PCRE2_EXP_DECL to "export" if it is not
already set. */
/* Older versions of MSVC lack snprintf(). This define allows for
warning/error-free compilation and testing with MSVC compilers back to at least
MSVC 10/2010. Except for VC6 (which is missing some fundamentals and fails). */
#if defined(_MSC_VER) && (_MSC_VER < 1900)
#define snprintf _snprintf
#endif
/* Compile-time error numbers start at this value. It should probably never be
changed. This #define is a copy of the one in pcre2_internal.h. */
#define COMPILE_ERROR_BASE 100
/* Standard C headers */
#include <ctype.h>
#include <limits.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
/* PCRE2 headers */
#include "pcre2.h"
#include "pcre2_internal.h"
#include "pcre2posix.h"
/* When compiling with the MSVC compiler, it is sometimes necessary to include
a "calling convention" before exported function names. (This is secondhand
information; I know nothing about MSVC myself). For example, something like
void __cdecl function(....)
might be needed. In order so make this easy, all the exported functions have
PCRE2_CALL_CONVENTION just before their names. It is rarely needed; if not
set, we ensure here that it has no effect. */
#ifndef PCRE2_CALL_CONVENTION
#define PCRE2_CALL_CONVENTION
#endif
/* Table to translate PCRE2 compile time error codes into POSIX error codes.
Only a few PCRE2 errors with a value greater than 23 turn into special POSIX
codes: most go to REG_BADPAT. The second table lists, in pairs, those that
@ -106,7 +139,7 @@ static const int eint1[] = {
static const int eint2[] = {
30, REG_ECTYPE, /* unknown POSIX class name */
32, REG_INVARG, /* this version of PCRE does not have UTF or UCP support */
32, REG_INVARG, /* this version of PCRE2 does not have Unicode support */
37, REG_EESCAPE, /* PCRE2 does not support \L, \l, \N{name}, \U, or \u */
56, REG_INVARG, /* internal error: unknown newline setting */
};
@ -144,29 +177,23 @@ static const char *const pstring[] = {
PCRE2POSIX_EXP_DEFN size_t PCRE2_CALL_CONVENTION
regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
{
const char *message, *addmessage;
size_t length, addlength;
int used;
const char *message;
message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
message = (errcode <= 0 || errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
"unknown error code" : pstring[errcode];
length = strlen(message) + 1;
addmessage = " at offset ";
addlength = (preg != NULL && (int)preg->re_erroffset != -1)?
strlen(addmessage) + 6 : 0;
if (errbuf_size > 0)
if (preg != NULL && (int)preg->re_erroffset != -1)
{
if (addlength > 0 && errbuf_size >= length + addlength)
sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
else
{
strncpy(errbuf, message, errbuf_size - 1);
errbuf[errbuf_size-1] = 0;
}
used = snprintf(errbuf, errbuf_size, "%s at offset %-6d", message,
(int)preg->re_erroffset);
}
else
{
used = snprintf(errbuf, errbuf_size, "%s", message);
}
return length + addlength;
return used + 1;
}
@ -211,11 +238,11 @@ int re_nsub = 0;
if ((cflags & REG_ICASE) != 0) options |= PCRE2_CASELESS;
if ((cflags & REG_NEWLINE) != 0) options |= PCRE2_MULTILINE;
if ((cflags & REG_DOTALL) != 0) options |= PCRE2_DOTALL;
if ((cflags & REG_NOSUB) != 0) options |= PCRE2_NO_AUTO_CAPTURE;
if ((cflags & REG_UTF) != 0) options |= PCRE2_UTF;
if ((cflags & REG_UCP) != 0) options |= PCRE2_UCP;
if ((cflags & REG_UNGREEDY) != 0) options |= PCRE2_UNGREEDY;
preg->re_cflags = cflags;
preg->re_pcre2_code = pcre2_compile((PCRE2_SPTR)pattern, PCRE2_ZERO_TERMINATED,
options, &errorcode, &erroffset, NULL);
preg->re_erroffset = erroffset;
@ -223,8 +250,13 @@ preg->re_erroffset = erroffset;
if (preg->re_pcre2_code == NULL)
{
unsigned int i;
if (errorcode < 0) return REG_BADPAT; /* UTF error */
/* A negative value is a UTF error; otherwise all error codes are greater
than COMPILE_ERROR_BASE, but check, just in case. */
if (errorcode < COMPILE_ERROR_BASE) return REG_BADPAT;
errorcode -= COMPILE_ERROR_BASE;
if (errorcode < (int)(sizeof(eint1)/sizeof(const int)))
return eint1[errorcode];
for (i = 0; i < sizeof(eint2)/(2*sizeof(const int)); i += 2)
@ -235,8 +267,14 @@ if (preg->re_pcre2_code == NULL)
(void)pcre2_pattern_info((const pcre2_code *)preg->re_pcre2_code,
PCRE2_INFO_CAPTURECOUNT, &re_nsub);
preg->re_nsub = (size_t)re_nsub;
if ((options & PCRE2_NO_AUTO_CAPTURE) != 0) re_nsub = -1;
preg->re_match_data = pcre2_match_data_create(re_nsub + 1, NULL);
if (preg->re_match_data == NULL)
{
pcre2_code_free(preg->re_pcre2_code);
return REG_ESPACE;
}
return 0;
}
@ -248,8 +286,7 @@ return 0;
/* A suitable match_data block, large enough to hold all possible captures, was
obtained when the pattern was compiled, to save having to allocate and free it
for each match. If REG_NOSUB was specified at compile time, the
PCRE_NO_AUTO_CAPTURE flag will be set. When this is the case, the nmatch and
for each match. If REG_NOSUB was specified at compile time, the nmatch and
pmatch arguments are ignored, and the only result is yes/no/error. */
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
@ -266,11 +303,11 @@ if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE2_NOTEMPTY;
((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */
/* When no string data is being returned, or no vector has been passed in which
to put it, ensure that nmatch is zero. */
/* When REG_NOSUB was specified, or if no vector has been passed in which to
put captured strings, ensure that nmatch is zero. This will stop any attempt to
write to pmatch. */
if ((((pcre2_real_code *)(preg->re_pcre2_code))->compile_options &
PCRE2_NO_AUTO_CAPTURE) != 0 || pmatch == NULL) nmatch = 0;
if ((preg->re_cflags & REG_NOSUB) != 0 || pmatch == NULL) nmatch = 0;
/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings.
The man page from OS X says "REG_STARTEND affects only the location of the
@ -279,6 +316,7 @@ start location rather than being passed as a PCRE2 "starting offset". */
if ((eflags & REG_STARTEND) != 0)
{
if (pmatch == NULL) return REG_INVARG;
so = pmatch[0].rm_so;
eo = pmatch[0].rm_eo;
}
@ -296,11 +334,12 @@ rc = pcre2_match((const pcre2_code *)preg->re_pcre2_code,
if (rc >= 0)
{
size_t i;
PCRE2_SIZE *ovector = pcre2_get_ovector_pointer(md);
if ((size_t)rc > nmatch) rc = (int)nmatch;
for (i = 0; i < (size_t)rc; i++)
{
pmatch[i].rm_so = md->ovector[i*2];
pmatch[i].rm_eo = md->ovector[i*2+1];
pmatch[i].rm_so = ovector[i*2];
pmatch[i].rm_eo = ovector[i*2+1];
}
for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1;
return 0;