diff options
Diffstat (limited to 'ext/pcre/pcrelib/pcre_compile.c')
| -rw-r--r-- | ext/pcre/pcrelib/pcre_compile.c | 158 |
1 files changed, 127 insertions, 31 deletions
diff --git a/ext/pcre/pcrelib/pcre_compile.c b/ext/pcre/pcrelib/pcre_compile.c index 53027e603d..b0d81ac94c 100644 --- a/ext/pcre/pcrelib/pcre_compile.c +++ b/ext/pcre/pcrelib/pcre_compile.c @@ -406,6 +406,7 @@ static const char error_texts[] = "different names for subpatterns of the same number are not allowed\0" "(*MARK) must have an argument\0" "this version of PCRE is not compiled with PCRE_UCP support\0" + "\\c must be followed by an ASCII character\0" ; /* Table to identify digits and hex digits. This is used when compiling @@ -839,7 +840,8 @@ else break; /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. - This coding is ASCII-specific, but then the whole concept of \cx is + An error is given if the byte following \c is not an ASCII character. This + coding is ASCII-specific, but then the whole concept of \cx is ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ case CHAR_c: @@ -849,11 +851,15 @@ else *errorcodeptr = ERR2; break; } - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ +#ifndef EBCDIC /* ASCII/UTF-8 coding */ + if (c > 127) /* Excludes all non-ASCII in either mode */ + { + *errorcodeptr = ERR68; + break; + } if (c >= CHAR_a && c <= CHAR_z) c -= 32; c ^= 0x40; -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (c >= CHAR_a && c <= CHAR_z) c += 64; c ^= 0xC0; #endif @@ -1097,10 +1103,21 @@ top-level call starts at the beginning of the pattern. All other calls must start at a parenthesis. It scans along a pattern's text looking for capturing subpatterns, and counting them. If it finds a named pattern that matches the name it is given, it returns its number. Alternatively, if the name is NULL, it -returns when it reaches a given numbered subpattern. We know that if (?P< is -encountered, the name will be terminated by '>' because that is checked in the -first pass. Recursion is used to keep track of subpatterns that reset the -capturing group numbers - the (?| feature. +returns when it reaches a given numbered subpattern. Recursion is used to keep +track of subpatterns that reset the capturing group numbers - the (?| feature. + +This function was originally called only from the second pass, in which we know +that if (?< or (?' or (?P< is encountered, the name will be correctly +terminated because that is checked in the first pass. There is now one call to +this function in the first pass, to check for a recursive back reference by +name (so that we can make the whole group atomic). In this case, we need check +only up to the current position in the pattern, and that is still OK because +and previous occurrences will have been checked. To make this work, the test +for "end of pattern" is a check against cd->end_pattern in the main loop, +instead of looking for a binary zero. This means that the special first-pass +call can adjust cd->end_pattern temporarily. (Checks for binary zero while +processing items within the loop are OK, because afterwards the main loop will +terminate.) Arguments: ptrptr address of the current character pointer (updated) @@ -1108,6 +1125,7 @@ Arguments: name name to seek, or NULL if seeking a numbered subpattern lorn name length, or subpattern number if name is NULL xmode TRUE if we are in /x mode + utf8 TRUE if we are in UTF-8 mode count pointer to the current capturing subpattern number (updated) Returns: the number of the named subpattern, or -1 if not found @@ -1115,7 +1133,7 @@ Returns: the number of the named subpattern, or -1 if not found static int find_parens_sub(uschar **ptrptr, compile_data *cd, const uschar *name, int lorn, - BOOL xmode, int *count) + BOOL xmode, BOOL utf8, int *count) { uschar *ptr = *ptrptr; int start_count = *count; @@ -1200,9 +1218,11 @@ if (ptr[0] == CHAR_LEFT_PARENTHESIS) } /* Past any initial parenthesis handling, scan for parentheses or vertical -bars. */ +bars. Stop if we get to cd->end_pattern. Note that this is important for the +first-pass call when this value is temporarily adjusted to stop at the current +position. So DO NOT change this to a test for binary zero. */ -for (; *ptr != 0; ptr++) +for (; ptr < cd->end_pattern; ptr++) { /* Skip over backslashed characters and also entire \Q...\E */ @@ -1276,7 +1296,15 @@ for (; *ptr != 0; ptr++) if (xmode && *ptr == CHAR_NUMBER_SIGN) { - while (*(++ptr) != 0 && *ptr != CHAR_NL) {}; + ptr++; + while (*ptr != 0) + { + if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } + ptr++; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*ptr & 0xc0) == 0x80) ptr++; +#endif + } if (*ptr == 0) goto FAIL_EXIT; continue; } @@ -1285,7 +1313,7 @@ for (; *ptr != 0; ptr++) if (*ptr == CHAR_LEFT_PARENTHESIS) { - int rc = find_parens_sub(&ptr, cd, name, lorn, xmode, count); + int rc = find_parens_sub(&ptr, cd, name, lorn, xmode, utf8, count); if (rc > 0) return rc; if (*ptr == 0) goto FAIL_EXIT; } @@ -1331,12 +1359,14 @@ Arguments: name name to seek, or NULL if seeking a numbered subpattern lorn name length, or subpattern number if name is NULL xmode TRUE if we are in /x mode + utf8 TRUE if we are in UTF-8 mode Returns: the number of the found subpattern, or -1 if not found */ static int -find_parens(compile_data *cd, const uschar *name, int lorn, BOOL xmode) +find_parens(compile_data *cd, const uschar *name, int lorn, BOOL xmode, + BOOL utf8) { uschar *ptr = (uschar *)cd->start_pattern; int count = 0; @@ -1349,7 +1379,7 @@ matching closing parens. That is why we have to have a loop. */ for (;;) { - rc = find_parens_sub(&ptr, cd, name, lorn, xmode, &count); + rc = find_parens_sub(&ptr, cd, name, lorn, xmode, utf8, &count); if (rc > 0 || *ptr++ == 0) break; } @@ -1722,9 +1752,12 @@ for (;;) case OP_MARK: case OP_PRUNE_ARG: case OP_SKIP_ARG: - case OP_THEN_ARG: code += code[1]; break; + + case OP_THEN_ARG: + code += code[1+LINK_SIZE]; + break; } /* Add in the fixed length from the table */ @@ -1825,9 +1858,12 @@ for (;;) case OP_MARK: case OP_PRUNE_ARG: case OP_SKIP_ARG: - case OP_THEN_ARG: code += code[1]; break; + + case OP_THEN_ARG: + code += code[1+LINK_SIZE]; + break; } /* Add in the fixed length from the table */ @@ -2103,10 +2139,13 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE case OP_MARK: case OP_PRUNE_ARG: case OP_SKIP_ARG: - case OP_THEN_ARG: code += code[1]; break; + case OP_THEN_ARG: + code += code[1+LINK_SIZE]; + break; + /* None of the remaining opcodes are required to match a character. */ default: @@ -2504,8 +2543,15 @@ if ((options & PCRE_EXTENDED) != 0) while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; if (*ptr == CHAR_NUMBER_SIGN) { - while (*(++ptr) != 0) + ptr++; + while (*ptr != 0) + { if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + ptr++; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*ptr & 0xc0) == 0x80) ptr++; +#endif + } } else break; } @@ -2541,8 +2587,15 @@ if ((options & PCRE_EXTENDED) != 0) while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; if (*ptr == CHAR_NUMBER_SIGN) { - while (*(++ptr) != 0) + ptr++; + while (*ptr != 0) + { if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } + ptr++; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*ptr & 0xc0) == 0x80) ptr++; +#endif + } } else break; } @@ -3115,9 +3168,14 @@ for (;; ptr++) if ((cd->ctypes[c] & ctype_space) != 0) continue; if (c == CHAR_NUMBER_SIGN) { - while (*(++ptr) != 0) + ptr++; + while (*ptr != 0) { if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } + ptr++; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*ptr & 0xc0) == 0x80) ptr++; +#endif } if (*ptr != 0) continue; @@ -3492,9 +3550,14 @@ for (;; ptr++) for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; continue; + /* Perl 5.004 onwards omits VT from \s, but we must preserve it + if it was previously set by something earlier in the character + class. */ + case ESC_s: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; - classbits[1] &= ~0x08; /* Perl 5.004 onwards omits VT from \s */ + classbits[0] |= cbits[cbit_space]; + classbits[1] |= cbits[cbit_space+1] & ~0x08; + for (c = 2; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; continue; case ESC_S: @@ -4806,7 +4869,12 @@ for (;; ptr++) *errorcodeptr = ERR66; goto FAILED; } - *code++ = verbs[i].op; + *code = verbs[i].op; + if (*code++ == OP_THEN) + { + PUT(code, 0, code - bcptr->current_branch - 1); + code += LINK_SIZE; + } } else @@ -4816,7 +4884,12 @@ for (;; ptr++) *errorcodeptr = ERR59; goto FAILED; } - *code++ = verbs[i].op_arg; + *code = verbs[i].op_arg; + if (*code++ == OP_THEN_ARG) + { + PUT(code, 0, code - bcptr->current_branch - 1); + code += LINK_SIZE; + } *code++ = arglen; memcpy(code, arg, arglen); code += arglen; @@ -5010,7 +5083,7 @@ for (;; ptr++) /* Search the pattern for a forward reference */ else if ((i = find_parens(cd, name, namelen, - (options & PCRE_EXTENDED) != 0)) > 0) + (options & PCRE_EXTENDED) != 0, utf8)) > 0) { PUT2(code, 2+LINK_SIZE, i); code[1+LINK_SIZE]++; @@ -5311,11 +5384,17 @@ for (;; ptr++) while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; namelen = (int)(ptr - name); - /* In the pre-compile phase, do a syntax check and set a dummy - reference number. */ + /* In the pre-compile phase, do a syntax check. We used to just set + a dummy reference number, because it was not used in the first pass. + However, with the change of recursive back references to be atomic, + we have to look for the number so that this state can be identified, as + otherwise the incorrect length is computed. If it's not a backwards + reference, the dummy number will do. */ if (lengthptr != NULL) { + const uschar *temp; + if (namelen == 0) { *errorcodeptr = ERR62; @@ -5331,7 +5410,22 @@ for (;; ptr++) *errorcodeptr = ERR48; goto FAILED; } - recno = 0; + + /* The name table does not exist in the first pass, so we cannot + do a simple search as in the code below. Instead, we have to scan the + pattern to find the number. It is important that we scan it only as + far as we have got because the syntax of named subpatterns has not + been checked for the rest of the pattern, and find_parens() assumes + correct syntax. In any case, it's a waste of resources to scan + further. We stop the scan at the current point by temporarily + adjusting the value of cd->endpattern. */ + + temp = cd->end_pattern; + cd->end_pattern = ptr; + recno = find_parens(cd, name, namelen, + (options & PCRE_EXTENDED) != 0, utf8); + cd->end_pattern = temp; + if (recno < 0) recno = 0; /* Forward ref; set dummy number */ } /* In the real compile, seek the name in the table. We check the name @@ -5356,7 +5450,7 @@ for (;; ptr++) } else if ((recno = /* Forward back reference */ find_parens(cd, name, namelen, - (options & PCRE_EXTENDED) != 0)) <= 0) + (options & PCRE_EXTENDED) != 0, utf8)) <= 0) { *errorcodeptr = ERR15; goto FAILED; @@ -5467,7 +5561,7 @@ for (;; ptr++) if (called == NULL) { if (find_parens(cd, NULL, recno, - (options & PCRE_EXTENDED) != 0) < 0) + (options & PCRE_EXTENDED) != 0, utf8) < 0) { *errorcodeptr = ERR15; goto FAILED; @@ -6797,6 +6891,8 @@ while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && { skipatstart += 7; options |= PCRE_UTF8; continue; } else if (strncmp((char *)(ptr+skipatstart+2), STRING_UCP_RIGHTPAR, 4) == 0) { skipatstart += 6; options |= PCRE_UCP; continue; } + else if (strncmp((char *)(ptr+skipatstart+2), STRING_NO_START_OPT_RIGHTPAR, 13) == 0) + { skipatstart += 15; options |= PCRE_NO_START_OPTIMIZE; continue; } if (strncmp((char *)(ptr+skipatstart+2), STRING_CR_RIGHTPAR, 3) == 0) { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } |