--- code/trunk/pcre_internal.h 2007/04/04 14:06:52 145 +++ code/trunk/pcre_internal.h 2007/09/10 13:23:56 230 @@ -67,10 +67,6 @@ #endif -/* Get the definitions provided by running "configure" */ - -#include "config.h" - /* Standard C headers plus the external interface definition. The only time setjmp and stdarg are used is when NO_RECURSE is set. */ @@ -86,10 +82,11 @@ /* When compiling a DLL for Windows, the exported symbols have to be declared using some MS magic. I found some useful information on this web page: http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllesport) without "extern" we have a +information there, using __declspec(dllexport) without "extern" we have a definition; with "extern" we have a declaration. The settings here override the setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, -which is all that is needed for applications, which import the symbols. We use: +which is all that is needed for applications (they just import the symbols). We +use: PCRE_EXP_DECL for declarations PCRE_EXP_DEFN for definitions of exported functions @@ -102,7 +99,7 @@ The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, which is an application, but needs to import this file in order to "peek" at -internals, can #include pcre.h first, can get an application's-eye view. +internals, can #include pcre.h first to get an application's-eye view. In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, special-purpose environments) might want to stick other stuff in front of @@ -111,7 +108,7 @@ #ifndef PCRE_EXP_DECL # ifdef _WIN32 -# ifdef DLL_EXPORT +# ifndef PCRE_STATIC # define PCRE_EXP_DECL extern __declspec(dllexport) # define PCRE_EXP_DEFN __declspec(dllexport) # define PCRE_EXP_DATA_DEFN __declspec(dllexport) @@ -120,7 +117,6 @@ # define PCRE_EXP_DEFN # define PCRE_EXP_DATA_DEFN # endif -# # else # ifdef __cplusplus # define PCRE_EXP_DECL extern "C" @@ -174,21 +170,22 @@ #define NOTACHAR 0xffffffff /* PCRE is able to support several different kinds of newline (CR, LF, CRLF, -and "all" at present). The following macros are used to package up testing for -newlines. NLBLOCK, PSSTART, and PSEND are defined in the various modules to -indicate in which datablock the parameters exist, and what the start/end of -string field names are. */ - -#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ -#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +"any" and "anycrlf" at present). The following macros are used to package up +testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various +modules to indicate in which datablock the parameters exist, and what the +start/end of string field names are. */ + +#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ +#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ /* This macro checks for a newline at the given position */ #define IS_NEWLINE(p) \ ((NLBLOCK->nltype != NLTYPE_FIXED)? \ ((p) < NLBLOCK->PSEND && \ - _pcre_is_newline((p), NLBLOCK->PSEND, &(NLBLOCK->nllen), utf8) \ - ) \ + _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ + utf8)) \ : \ ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ (p)[0] == NLBLOCK->nl[0] && \ @@ -201,8 +198,8 @@ #define WAS_NEWLINE(p) \ ((NLBLOCK->nltype != NLTYPE_FIXED)? \ ((p) > NLBLOCK->PSSTART && \ - _pcre_was_newline((p), NLBLOCK->PSSTART, &(NLBLOCK->nllen), utf8) \ - ) \ + _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ + &(NLBLOCK->nllen), utf8)) \ : \ ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ @@ -232,7 +229,7 @@ /* Include the public PCRE header and the definitions of UCP character property values. */ -#include +#include "pcre.h" #include "ucp.h" /* When compiling for use with the Virtual Pascal compiler, these functions @@ -361,7 +358,9 @@ /* When UTF-8 encoding is being used, a character is no longer just a single byte. The macros for character handling generate simple sequences when used in -byte-mode, and more complicated ones for UTF-8 characters. */ +byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should +never be called in byte mode. To make sure it can never even appear when UTF-8 +support is omitted, we don't even define it. */ #ifndef SUPPORT_UTF8 #define GETCHAR(c, eptr) c = *eptr; @@ -369,7 +368,7 @@ #define GETCHARINC(c, eptr) c = *eptr++; #define GETCHARINCTEST(c, eptr) c = *eptr++; #define GETCHARLEN(c, eptr, len) c = *eptr; -#define BACKCHAR(eptr) +/* #define BACKCHAR(eptr) */ #else /* SUPPORT_UTF8 */ @@ -462,9 +461,10 @@ } /* If the pointer is not at the start of a character, move it back until -it is. Called only in UTF-8 mode. */ +it is. This is called only in UTF-8 mode - we don't put a test within the macro +because almost all calls are already within a block of UTF-8 only code. */ -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--; +#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- #endif @@ -481,17 +481,16 @@ #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) -/* Private options flags start at the most significant end of the four bytes. -The public options defined in pcre.h start at the least significant end. Make -sure they don't overlap! The bits are getting a bit scarce now -- when we run -out, there is a dummy word in the structure that could be used for the private -bits. */ - -#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ -#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */ +/* Private flags containing information about the compiled regex. They used to +live at the top end of the options word, but that got almost full, so now they +are in a 16-bit flags word. */ + +#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ +#define PCRE_FIRSTSET 0x0002 /* first_byte is set */ +#define PCRE_REQCHSET 0x0004 /* req_byte is set */ +#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */ +#define PCRE_JCHANGED 0x0010 /* j option used in regex */ +#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */ /* Options for the "extra" block produced by pcre_study(). */ @@ -500,7 +499,8 @@ /* Masks for identifying the public options that are permitted at compile time, run time, or study time, respectively. */ -#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY) +#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ + PCRE_NEWLINE_ANYCRLF) #define PUBLIC_OPTIONS \ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ @@ -602,19 +602,14 @@ consume characters. If any new escapes are put in between that don't consume a character, that code will have to change. */ -enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_X, ESC_Z, ESC_z, - ESC_E, ESC_Q, ESC_k, ESC_REF }; +enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, + ESC_W, ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h, + ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_k, ESC_REF }; -/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets -that extract substrings. Starting from 1 (i.e. after OP_END), the values up to +/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to OP_EOD must correspond in order to the list of escapes immediately above. -To keep stored, compiled patterns compatible, new opcodes should be added -immediately before OP_BRA, where (since release 7.0) a gap is left for this -purpose. - *** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions that follow must also be updated to match. There is also a table called "coptable" in pcre_dfa_exec.c that must be updated. */ @@ -626,133 +621,150 @@ OP_SOD, /* 1 Start of data: \A */ OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_ANYNL, /* 15 \R (any newline sequence) */ - OP_EXTUNI, /* 16 \X (extended Unicode sequence */ - OP_EODN, /* 17 End of data or \n at end of data: \Z. */ - OP_EOD, /* 18 End of data: \z */ - - OP_OPT, /* 19 Set runtime options */ - OP_CIRC, /* 20 Start of line - varies with multiline switch */ - OP_DOLL, /* 21 End of line - varies with multiline switch */ - OP_CHAR, /* 22 Match one character, casefully */ - OP_CHARNC, /* 23 Match one character, caselessly */ - OP_NOT, /* 24 Match one character, not the following one */ - - OP_STAR, /* 25 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 26 these six opcodes must come in pairs, with */ - OP_PLUS, /* 27 the minimizing one second. */ - OP_MINPLUS, /* 28 This first set applies to single characters.*/ - OP_QUERY, /* 29 */ - OP_MINQUERY, /* 30 */ - - OP_UPTO, /* 31 From 0 to n matches */ - OP_MINUPTO, /* 32 */ - OP_EXACT, /* 33 Exactly n matches */ - - OP_POSSTAR, /* 34 Possessified star */ - OP_POSPLUS, /* 35 Possessified plus */ - OP_POSQUERY, /* 36 Posesssified query */ - OP_POSUPTO, /* 37 Possessified upto */ - - OP_NOTSTAR, /* 38 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 39 these six opcodes must come in pairs, with */ - OP_NOTPLUS, /* 40 the minimizing one second. They must be in */ - OP_NOTMINPLUS, /* 41 exactly the same order as those above. */ - OP_NOTQUERY, /* 42 This set applies to "not" single characters. */ - OP_NOTMINQUERY, /* 43 */ - - OP_NOTUPTO, /* 44 From 0 to n matches */ - OP_NOTMINUPTO, /* 45 */ - OP_NOTEXACT, /* 46 Exactly n matches */ - - OP_NOTPOSSTAR, /* 47 Possessified versions */ - OP_NOTPOSPLUS, /* 48 */ - OP_NOTPOSQUERY, /* 49 */ - OP_NOTPOSUPTO, /* 50 */ - - OP_TYPESTAR, /* 51 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 52 these six opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 53 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 55 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 56 */ - - OP_TYPEUPTO, /* 57 From 0 to n matches */ - OP_TYPEMINUPTO, /* 58 */ - OP_TYPEEXACT, /* 59 Exactly n matches */ - - OP_TYPEPOSSTAR, /* 60 Possessified versions */ - OP_TYPEPOSPLUS, /* 61 */ - OP_TYPEPOSQUERY, /* 62 */ - OP_TYPEPOSUPTO, /* 63 */ - - OP_CRSTAR, /* 64 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 65 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 66 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 67 be in exactly the same order as those above. */ - OP_CRQUERY, /* 68 These are for character classes and back refs */ - OP_CRMINQUERY, /* 69 */ - OP_CRRANGE, /* 70 These are different to the three sets above. */ - OP_CRMINRANGE, /* 71 */ + OP_SET_SOM, /* 3 Set start of match (\K) */ + OP_NOT_WORD_BOUNDARY, /* 4 \B */ + OP_WORD_BOUNDARY, /* 5 \b */ + OP_NOT_DIGIT, /* 6 \D */ + OP_DIGIT, /* 7 \d */ + OP_NOT_WHITESPACE, /* 8 \S */ + OP_WHITESPACE, /* 9 \s */ + OP_NOT_WORDCHAR, /* 10 \W */ + OP_WORDCHAR, /* 11 \w */ + OP_ANY, /* 12 Match any character */ + OP_ANYBYTE, /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 14 \P (not Unicode property) */ + OP_PROP, /* 15 \p (Unicode property) */ + OP_ANYNL, /* 16 \R (any newline sequence) */ + OP_NOT_HSPACE, /* 17 \H (not horizontal whitespace) */ + OP_HSPACE, /* 18 \h (horizontal whitespace) */ + OP_NOT_VSPACE, /* 19 \V (not vertical whitespace) */ + OP_VSPACE, /* 20 \v (vertical whitespace) */ + OP_EXTUNI, /* 21 \X (extended Unicode sequence */ + OP_EODN, /* 22 End of data or \n at end of data: \Z. */ + OP_EOD, /* 23 End of data: \z */ + + OP_OPT, /* 24 Set runtime options */ + OP_CIRC, /* 25 Start of line - varies with multiline switch */ + OP_DOLL, /* 26 End of line - varies with multiline switch */ + OP_CHAR, /* 27 Match one character, casefully */ + OP_CHARNC, /* 28 Match one character, caselessly */ + OP_NOT, /* 29 Match one character, not the following one */ + + OP_STAR, /* 30 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 31 these six opcodes must come in pairs, with */ + OP_PLUS, /* 32 the minimizing one second. */ + OP_MINPLUS, /* 33 This first set applies to single characters.*/ + OP_QUERY, /* 34 */ + OP_MINQUERY, /* 35 */ + + OP_UPTO, /* 36 From 0 to n matches */ + OP_MINUPTO, /* 37 */ + OP_EXACT, /* 38 Exactly n matches */ + + OP_POSSTAR, /* 39 Possessified star */ + OP_POSPLUS, /* 40 Possessified plus */ + OP_POSQUERY, /* 41 Posesssified query */ + OP_POSUPTO, /* 42 Possessified upto */ + + OP_NOTSTAR, /* 43 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 44 these six opcodes must come in pairs, with */ + OP_NOTPLUS, /* 45 the minimizing one second. They must be in */ + OP_NOTMINPLUS, /* 46 exactly the same order as those above. */ + OP_NOTQUERY, /* 47 This set applies to "not" single characters. */ + OP_NOTMINQUERY, /* 48 */ + + OP_NOTUPTO, /* 49 From 0 to n matches */ + OP_NOTMINUPTO, /* 50 */ + OP_NOTEXACT, /* 51 Exactly n matches */ + + OP_NOTPOSSTAR, /* 52 Possessified versions */ + OP_NOTPOSPLUS, /* 53 */ + OP_NOTPOSQUERY, /* 54 */ + OP_NOTPOSUPTO, /* 55 */ + + OP_TYPESTAR, /* 56 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 57 these six opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 58 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 59 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 60 This set applies to character types such as \d */ + OP_TYPEMINQUERY, /* 61 */ + + OP_TYPEUPTO, /* 62 From 0 to n matches */ + OP_TYPEMINUPTO, /* 63 */ + OP_TYPEEXACT, /* 64 Exactly n matches */ + + OP_TYPEPOSSTAR, /* 65 Possessified versions */ + OP_TYPEPOSPLUS, /* 66 */ + OP_TYPEPOSQUERY, /* 67 */ + OP_TYPEPOSUPTO, /* 68 */ + + OP_CRSTAR, /* 69 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 70 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 71 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 72 be in exactly the same order as those above. */ + OP_CRQUERY, /* 73 These are for character classes and back refs */ + OP_CRMINQUERY, /* 74 */ + OP_CRRANGE, /* 75 These are different to the three sets above. */ + OP_CRMINRANGE, /* 76 */ - OP_CLASS, /* 72 Match a character class, chars < 256 only */ - OP_NCLASS, /* 73 Same, but the bitmap was created from a negative + OP_CLASS, /* 77 Match a character class, chars < 256 only */ + OP_NCLASS, /* 78 Same, but the bitmap was created from a negative class - the difference is relevant only when a UTF-8 character > 255 is encountered. */ - OP_XCLASS, /* 74 Extended class for handling UTF-8 chars within the + OP_XCLASS, /* 79 Extended class for handling UTF-8 chars within the class. This does both positive and negative. */ - OP_REF, /* 75 Match a back reference */ - OP_RECURSE, /* 76 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 77 Call out to external function if provided */ - - OP_ALT, /* 78 Start of alternation */ - OP_KET, /* 79 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 80 These two must remain together and in this */ - OP_KETRMIN, /* 81 order. They are for groups the repeat for ever. */ + OP_REF, /* 80 Match a back reference */ + OP_RECURSE, /* 81 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 82 Call out to external function if provided */ + + OP_ALT, /* 83 Start of alternation */ + OP_KET, /* 84 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 85 These two must remain together and in this */ + OP_KETRMIN, /* 86 order. They are for groups the repeat for ever. */ /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ - OP_ASSERT, /* 82 Positive lookahead */ - OP_ASSERT_NOT, /* 83 Negative lookahead */ - OP_ASSERTBACK, /* 84 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 85 Negative lookbehind */ - OP_REVERSE, /* 86 Move pointer back - used in lookbehind assertions */ + OP_ASSERT, /* 87 Positive lookahead */ + OP_ASSERT_NOT, /* 88 Negative lookahead */ + OP_ASSERTBACK, /* 89 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */ + OP_REVERSE, /* 91 Move pointer back - used in lookbehind assertions */ /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, as there's a test for >= ONCE for a subpattern that isn't an assertion. */ - OP_ONCE, /* 87 Atomic group */ - OP_BRA, /* 88 Start of non-capturing bracket */ - OP_CBRA, /* 89 Start of capturing bracket */ - OP_COND, /* 90 Conditional group */ + OP_ONCE, /* 92 Atomic group */ + OP_BRA, /* 93 Start of non-capturing bracket */ + OP_CBRA, /* 94 Start of capturing bracket */ + OP_COND, /* 95 Conditional group */ /* These three must follow the previous three, in the same order. There's a check for >= SBRA to distinguish the two sets. */ - OP_SBRA, /* 91 Start of non-capturing bracket, check empty */ - OP_SCBRA, /* 92 Start of capturing bracket, check empty */ - OP_SCOND, /* 93 Conditional group, check empty */ - - OP_CREF, /* 94 Used to hold a capture number as condition */ - OP_RREF, /* 95 Used to hold a recursion number as condition */ - OP_DEF, /* 96 The DEFINE condition */ + OP_SBRA, /* 96 Start of non-capturing bracket, check empty */ + OP_SCBRA, /* 97 Start of capturing bracket, check empty */ + OP_SCOND, /* 98 Conditional group, check empty */ + + OP_CREF, /* 99 Used to hold a capture number as condition */ + OP_RREF, /* 100 Used to hold a recursion number as condition */ + OP_DEF, /* 101 The DEFINE condition */ + + OP_BRAZERO, /* 102 These two must remain together and in this */ + OP_BRAMINZERO, /* 103 order. */ - OP_BRAZERO, /* 97 These two must remain together and in this */ - OP_BRAMINZERO /* 98 order. */ + /* These are backtracking control verbs */ + + OP_PRUNE, /* 104 */ + OP_SKIP, /* 105 */ + OP_THEN, /* 106 */ + OP_COMMIT, /* 107 */ + + /* These are forced failure and success verbs */ + + OP_FAIL, /* 108 */ + OP_ACCEPT /* 109 */ }; @@ -760,10 +772,10 @@ for debugging. The macro is referenced only in pcre_printint.c. */ #define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ + "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "anynl", "extuni", \ - "\\Z", "\\z", \ + "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ + "extuni", "\\Z", "\\z", \ "Opt", "^", "$", "char", "charnc", "not", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ "*+","++", "?+", "{", \ @@ -775,8 +787,9 @@ "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ "AssertB", "AssertB not", "Reverse", \ - "Once", "Bra 0", "Bra", "Cond", "SBra 0", "SBra", "SCond", \ - "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero" + "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \ + "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \ + "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT" /* This macro defines the length of fixed length operations in the compiled @@ -790,9 +803,11 @@ #define OP_LENGTHS \ 1, /* End */ \ - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ + 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ 1, 1, /* Any, Anybyte */ \ - 3, 3, 1, 1, /* NOTPROP, PROP, EXTUNI, ANYNL */ \ + 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ 2, /* Char - the minimum length */ \ 2, /* Charnc - the minimum length */ \ @@ -838,6 +853,8 @@ 3, /* RREF */ \ 1, /* DEF */ \ 1, 1, /* BRAZERO, BRAMINZERO */ \ + 1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \ + 1, 1 /* FAIL, ACCEPT */ /* A magic value for OP_RREF to indicate the "any recursion" condition. */ @@ -852,7 +869,8 @@ ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57 }; + ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, + ERR60, ERR61 }; /* The real format of the start of the pcre block; the index of names and the code vector run on as long as necessary after the end. We store an explicit @@ -874,9 +892,9 @@ typedef struct real_pcre { pcre_uint32 magic_number; pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - pcre_uint32 dummy1; /* For future use, maybe */ - + pcre_uint32 options; /* Public options */ + pcre_uint16 flags; /* Private flags */ + pcre_uint16 dummy1; /* For future use */ pcre_uint16 top_bracket; pcre_uint16 top_backref; pcre_uint16 first_byte; @@ -919,8 +937,9 @@ int top_backref; /* Maximum back reference */ unsigned int backref_map; /* Bitmap of low back refs */ int external_options; /* External (initial) options */ + int external_flags; /* External flag bits to be set */ int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL nopartial; /* Set TRUE if partial won't work */ + BOOL had_accept; /* (*ACCEPT) encountered */ int nltype; /* Newline type */ int nllen; /* Newline string length */ uschar nl[4]; /* Newline string when fixed length */ @@ -941,21 +960,11 @@ struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ int group_num; /* Number of group that was called */ const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of md->start_match */ + USPTR save_start; /* Old value of mstart */ int *offset_save; /* Pointer to start of saved offsets */ int saved_max; /* Number of saved offsets */ } recursion_info; -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre_exec.c, close to the match() function, so that it is easy to keep it in -step with any changes of local variable. However, the pointer to the current -frame must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. NOTE: -This isn't used for a "normal" compilation of pcre. */ - -struct heapframe; - /* Structure for building a chain of data for holding the values of the subject pointer at the start of each subpattern, so as to detect when an empty string has been matched by a subpattern - to break infinite loops. */ @@ -992,7 +1001,7 @@ const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ - USPTR start_match; /* Start of this match attempt */ + USPTR start_match_ptr; /* Start of matched string */ USPTR end_match_ptr; /* Subject position at end match */ int end_offset_top; /* Highwater mark at end of match */ int capture_last; /* Most recent capture number */ @@ -1001,7 +1010,6 @@ int eptrn; /* Next free eptrblock */ recursion_info *recursive; /* Linked list of recursion data */ void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ } match_data; /* A similar structure is used for the same purpose by the DFA matching @@ -1087,16 +1095,16 @@ one of the exported public functions. They have to be "external" in the C sense, but are not part of the PCRE public API. */ -extern BOOL _pcre_is_newline(const uschar *, const uschar *, int *, - BOOL); +extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, + int *, BOOL); extern int _pcre_ord2utf8(int, uschar *); extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, const pcre_study_data *, pcre_study_data *); extern int _pcre_ucp_findprop(const unsigned int, int *, int *); extern unsigned int _pcre_ucp_othercase(const unsigned int); extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_was_newline(const uschar *, const uschar *, int *, - BOOL); +extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, + int *, BOOL); extern BOOL _pcre_xclass(int, const uschar *); #endif