From 12cfcf08fffc6e4ec597e0396016d09afdb89fa8 Mon Sep 17 00:00:00 2001 From: wrowe, Petr Pisar Date: Fri, DEC 9 19:06:06 2016 UTC Subject: [PATCH] backport Switch from PCRE to PCRE2 Conflict:NA Reference:https://github.com/apache/httpd/commit/12cfcf08fffc6e4ec597e0396016d09afdb89fa8 --- configure.in | 26 +++++----- server/util_pcre.c | 140 +++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 118 insertions(+), 48 deletions(-) diff --git a/configure.in b/configure.in index 916377b..db7edc3 100644 --- a/configure.in +++ b/configure.in @@ -214,29 +214,33 @@ fi AC_ARG_WITH(pcre, APACHE_HELP_STRING(--with-pcre=PATH,Use external PCRE library)) - -AC_PATH_PROG(PCRE_CONFIG, pcre-config, false) -if test -d "$with_pcre" && test -x "$with_pcre/bin/pcre-config"; then - PCRE_CONFIG=$with_pcre/bin/pcre-config -elif test -x "$with_pcre"; then - PCRE_CONFIG=$with_pcre +if test "x$with_pcre" = "x" || test "$with_pcre" = "yes"; then + with_pcre="$PATH" +else if which $with_pcre 2>/dev/null; then :; else + with_pcre="$with_pcre/bin:$with_pcre" +fi fi +AC_CHECK_TARGET_TOOLS(PCRE_CONFIG, [pcre2-config pcre-config], + [`which $with_pcre 2>/dev/null`], $with_pcre) -if test "$PCRE_CONFIG" != "false"; then +if test "x$PCRE_CONFIG" != "x"; then if $PCRE_CONFIG --version >/dev/null 2>&1; then :; else - AC_MSG_ERROR([Did not find pcre-config script at $PCRE_CONFIG]) + AC_MSG_ERROR([Did not find working script at $PCRE_CONFIG]) fi case `$PCRE_CONFIG --version` in + [1[0-9].*]) + AC_DEFINE(HAVE_PCRE2, 1, [Detected PCRE2]) + ;; [[1-5].*]) - AC_MSG_ERROR([Need at least pcre version 6.0]) + AC_MSG_ERROR([Need at least pcre version 6.7]) ;; esac AC_MSG_NOTICE([Using external PCRE library from $PCRE_CONFIG]) APR_ADDTO(PCRE_INCLUDES, [`$PCRE_CONFIG --cflags`]) - APR_ADDTO(PCRE_LIBS, [`$PCRE_CONFIG --libs`]) + APR_ADDTO(PCRE_LIBS, [`$PCRE_CONFIG --libs8 2>/dev/null || $PCRE_CONFIG --libs`]) APR_ADDTO(HTTPD_LIBS, [\$(PCRE_LIBS)]) else - AC_MSG_ERROR([pcre-config for libpcre not found. PCRE is required and available from http://pcre.org/]) + AC_MSG_ERROR([pcre(2)-config for libpcre not found. PCRE is required and available from http://pcre.org/]) fi APACHE_SUBST(PCRE_LIBS) diff --git a/server/util_pcre.c b/server/util_pcre.c index 78fc983..0fdf5f9 100644 --- a/server/util_pcre.c +++ b/server/util_pcre.c @@ -55,10 +55,18 @@ POSSIBILITY OF SUCH DAMAGE. #include "httpd.h" #include "apr_strings.h" #include "apr_tables.h" + +#ifdef HAVE_PCRE2 +#define PCRE2_CODE_UNIT_WIDTH 8 +#include "pcre2.h" +#define PCREn(x) PCRE2_ ## x +#else #include "pcre.h" +#define PCREn(x) PCRE_ ## x +#endif /* PCRE_DUPNAMES is only present since version 6.7 of PCRE */ -#ifndef PCRE_DUPNAMES +#if !defined(PCRE_DUPNAMES) && !defined(HAVE_PCRE2) #error PCRE Version 6.7 or later required! #else @@ -115,7 +123,11 @@ AP_DECLARE(apr_size_t) ap_regerror(int errcode, const ap_regex_t *preg, AP_DECLARE(void) ap_regfree(ap_regex_t *preg) { +#ifdef HAVE_PCRE2 + pcre2_code_free(preg->re_pcre); +#else (pcre_free)(preg->re_pcre); +#endif } @@ -168,25 +180,37 @@ AP_DECLARE(int) ap_regcomp_default_cflag_by_name(const char *name) */ AP_DECLARE(int) ap_regcomp(ap_regex_t * preg, const char *pattern, int cflags) { +#ifdef HAVE_PCRE2 + uint32_t capcount; + size_t erroffset; +#else const char *errorptr; int erroffset; +#endif int errcode = 0; - int options = PCRE_DUPNAMES; + int options = PCREn(DUPNAMES); if ((cflags & AP_REG_NO_DEFAULT) == 0) cflags |= default_cflags; if ((cflags & AP_REG_ICASE) != 0) - options |= PCRE_CASELESS; + options |= PCREn(CASELESS); if ((cflags & AP_REG_NEWLINE) != 0) - options |= PCRE_MULTILINE; + options |= PCREn(MULTILINE); if ((cflags & AP_REG_DOTALL) != 0) - options |= PCRE_DOTALL; + options |= PCREn(DOTALL); if ((cflags & AP_REG_DOLLAR_ENDONLY) != 0) - options |= PCRE_DOLLAR_ENDONLY; + options |= PCREn(DOLLAR_ENDONLY); + +#ifdef HAVE_PCRE2 + preg->re_pcre = pcre2_compile((const unsigned char *)pattern, + PCRE2_ZERO_TERMINATED, options, &errcode, + &erroffset, NULL); +#else + preg->re_pcre = pcre_compile2(pattern, options, &errcode, + &errorptr, &erroffset, NULL); +#endif - preg->re_pcre = - pcre_compile2(pattern, options, &errcode, &errorptr, &erroffset, NULL); preg->re_erroffset = erroffset; if (preg->re_pcre == NULL) { @@ -199,8 +223,14 @@ AP_DECLARE(int) ap_regcomp(ap_regex_t * preg, const char *pattern, int cflags) return AP_REG_INVARG; } +#ifdef HAVE_PCRE2 + pcre2_pattern_info((const pcre2_code *)preg->re_pcre, + PCRE2_INFO_CAPTURECOUNT, &capcount); + preg->re_nsub = capcount; +#else pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT, &(preg->re_nsub)); +#endif return 0; } @@ -232,17 +262,29 @@ AP_DECLARE(int) ap_regexec_len(const ap_regex_t *preg, const char *buff, { int rc; int options = 0; - int *ovector = NULL; +#ifdef HAVE_PCRE2 + pcre2_match_data *matchdata; + size_t *ovector; +#else int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; int allocated_ovector = 0; + int *ovector = NULL; +#endif if ((eflags & AP_REG_NOTBOL) != 0) - options |= PCRE_NOTBOL; + options |= PCREn(NOTBOL); if ((eflags & AP_REG_NOTEOL) != 0) - options |= PCRE_NOTEOL; - - ((ap_regex_t *)preg)->re_erroffset = (apr_size_t)(-1); /* Only has meaning after compile */ - + options |= PCREn(NOTEOL); + +#ifdef HAVE_PCRE2 + matchdata = pcre2_match_data_create(nmatch, NULL); + if (matchdata == NULL) + return AP_REG_ESPACE; + ovector = pcre2_get_ovector_pointer(matchdata); + rc = pcre2_match((const pcre2_code *)preg->re_pcre, + (const unsigned char *)buff, len, + 0, options, matchdata, NULL); +#else if (nmatch > 0) { if (nmatch <= POSIX_MALLOC_THRESHOLD) { ovector = &(small_ovector[0]); @@ -257,49 +299,62 @@ AP_DECLARE(int) ap_regexec_len(const ap_regex_t *preg, const char *buff, rc = pcre_exec((const pcre *)preg->re_pcre, NULL, buff, (int)len, 0, options, ovector, nmatch * 3); +#endif if (rc == 0) rc = nmatch; /* All captured slots were filled in */ if (rc >= 0) { apr_size_t i; - for (i = 0; i < (apr_size_t)rc; i++) { + apr_size_t nlim = (apr_size_t)rc < nmatch ? (apr_size_t)rc : nmatch; + for (i = 0; i < nlim; i++) { pmatch[i].rm_so = ovector[i * 2]; pmatch[i].rm_eo = ovector[i * 2 + 1]; } - if (allocated_ovector) - free(ovector); for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; + } + +#ifdef HAVE_PCRE2 + pcre2_match_data_free(matchdata); +#else + if (allocated_ovector) + free(ovector); +#endif + if (rc >= 0) { return 0; } else { - if (allocated_ovector) - free(ovector); +#ifdef HAVE_PCRE2 + if (rc <= PCRE2_ERROR_UTF8_ERR1 && rc >= PCRE2_ERROR_UTF8_ERR21) + return AP_REG_INVARG; +#endif switch (rc) { - case PCRE_ERROR_NOMATCH: + case PCREn(ERROR_NOMATCH): return AP_REG_NOMATCH; - case PCRE_ERROR_NULL: + case PCREn(ERROR_NULL): return AP_REG_INVARG; - case PCRE_ERROR_BADOPTION: + case PCREn(ERROR_BADOPTION): return AP_REG_INVARG; - case PCRE_ERROR_BADMAGIC: + case PCREn(ERROR_BADMAGIC): return AP_REG_INVARG; - case PCRE_ERROR_UNKNOWN_NODE: - return AP_REG_ASSERT; - case PCRE_ERROR_NOMEMORY: + case PCREn(ERROR_NOMEMORY): return AP_REG_ESPACE; -#ifdef PCRE_ERROR_MATCHLIMIT - case PCRE_ERROR_MATCHLIMIT: +#if defined(HAVE_PCRE2) || defined(PCRE_ERROR_MATCHLIMIT) + case PCREn(ERROR_MATCHLIMIT): return AP_REG_ESPACE; #endif -#ifdef PCRE_ERROR_BADUTF8 - case PCRE_ERROR_BADUTF8: +#if defined(PCRE_ERROR_UNKNOWN_NODE) + case PCRE_ERROR_UNKNOWN_NODE: + return AP_REG_ASSERT; +#endif +#if defined(PCRE_ERROR_BADUTF8) + case PCREn(ERROR_BADUTF8): return AP_REG_INVARG; #endif -#ifdef PCRE_ERROR_BADUTF8_OFFSET - case PCRE_ERROR_BADUTF8_OFFSET: +#if defined(PCRE_ERROR_BADUTF8_OFFSET) + case PCREn(ERROR_BADUTF8_OFFSET): return AP_REG_INVARG; #endif default: @@ -312,18 +367,29 @@ AP_DECLARE(int) ap_regname(const ap_regex_t *preg, apr_array_header_t *names, const char *prefix, int upper) { + char *nametable; +#ifdef HAVE_PCRE2 + uint32_t namecount; + uint32_t nameentrysize; + uint32_t i; + pcre2_pattern_info((const pcre2_code *)preg->re_pcre, + PCRE2_INFO_NAMECOUNT, &namecount); + pcre2_pattern_info((const pcre2_code *)preg->re_pcre, + PCRE2_INFO_NAMEENTRYSIZE, &nameentrysize); + pcre2_pattern_info((const pcre2_code *)preg->re_pcre, + PCRE2_INFO_NAMETABLE, &nametable); +#else int namecount; int nameentrysize; int i; - char *nametable; pcre_fullinfo((const pcre *)preg->re_pcre, NULL, - PCRE_INFO_NAMECOUNT, &namecount); + PCRE_INFO_NAMECOUNT, &namecount); pcre_fullinfo((const pcre *)preg->re_pcre, NULL, - PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); + PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); pcre_fullinfo((const pcre *)preg->re_pcre, NULL, - PCRE_INFO_NAMETABLE, &nametable); - + PCRE_INFO_NAMETABLE, &nametable); +#endif for (i = 0; i < namecount; i++) { const char *offset = nametable + i * nameentrysize; int capture = ((offset[0] << 8) + offset[1]); -- 1.8.3.1