X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/1af6200d185d478f416345eedc9641a043650e1b..7de25fd5debd2eed43b1bce72ba3d1ac712173bd:/regexp.h diff --git a/regexp.h b/regexp.h index ad59cc7..5acdc5e 100644 --- a/regexp.h +++ b/regexp.h @@ -1,7 +1,7 @@ /* regexp.h * * Copyright (C) 1993, 1994, 1996, 1997, 1999, 2000, 2001, 2003, - * 2005, 2006, 2007, by Larry Wall and others + * 2005, 2006, 2007, 2008 by Larry Wall and others * * You may distribute under the terms of either the GNU General Public * License or the Artistic License, as specified in the README file. @@ -66,48 +66,48 @@ typedef struct regexp_paren_pair { regexp's data array based on the data item's type. */ +#define _REGEXP_COMMON \ + /* what engine created this regexp? */ \ + const struct regexp_engine* engine; \ + REGEXP *mother_re; /* what re is this a lightweight copy of? */ \ + HV *paren_names; /* Optional hash of paren names */ \ + /* Information about the match that the perl core uses to */ \ + /* manage things */ \ + U32 extflags; /* Flags used both externally and internally */ \ + I32 minlen; /* mininum possible length of string to match */\ + I32 minlenret; /* mininum possible length of $& */ \ + U32 gofs; /* chars left of pos that we search from */ \ + /* substring data about strings that must appear in the */ \ + /* final match, used for optimisations */ \ + struct reg_substr_data *substrs; \ + U32 nparens; /* number of capture buffers */ \ + /* private engine specific data */ \ + U32 intflags; /* Engine Specific Internal flags */ \ + void *pprivate; /* Data private to the regex engine which */ \ + /* created this object. */ \ + /* Data about the last/current match. These are modified */ \ + /* during matching */ \ + U32 lastparen; /* last open paren matched */ \ + U32 lastcloseparen; /* last close paren matched */ \ + regexp_paren_pair *swap; /* Unused: 5.10.1 and later */ \ + /* Array of offsets for (@-) and (@+) */ \ + regexp_paren_pair *offs; \ + /* saved or original string so \digit works forever. */ \ + char *subbeg; \ + SV_SAVED_COPY /* If non-NULL, SV which is COW from original */\ + I32 sublen; /* Length of string pointed by subbeg */ \ + /* Information about the match that isn't often used */ \ + /* offset from wrapped to the start of precomp */ \ + PERL_BITFIELD32 pre_prefix:4; \ + /* number of eval groups in the pattern - for security checks */\ + PERL_BITFIELD32 seen_evals:28 + typedef struct regexp { _XPV_HEAD; - _XPVMG_HEAD; - /* what engine created this regexp? */ - const struct regexp_engine* engine; - REGEXP *mother_re; /* what re is this a lightweight copy of? */ - - /* Information about the match that the perl core uses to manage things */ - U32 extflags; /* Flags used both externally and internally */ - I32 minlen; /* mininum possible length of string to match */ - I32 minlenret; /* mininum possible length of $& */ - U32 gofs; /* chars left of pos that we search from */ - struct reg_substr_data *substrs; /* substring data about strings that must appear - in the final match, used for optimisations */ - U32 nparens; /* number of capture buffers */ - - /* private engine specific data */ - U32 intflags; /* Engine Specific Internal flags */ - void *pprivate; /* Data private to the regex engine which - created this object. */ - - /* Data about the last/current match. These are modified during matching*/ - U32 lastparen; /* last open paren matched */ - U32 lastcloseparen; /* last close paren matched */ - regexp_paren_pair *swap; /* Swap copy of *offs */ - regexp_paren_pair *offs; /* Array of offsets for (@-) and (@+) */ - - char *subbeg; /* saved or original string - so \digit works forever. */ - SV_SAVED_COPY /* If non-NULL, SV which is COW from original */ - I32 sublen; /* Length of string pointed by subbeg */ - - - /* Information about the match that isn't often used */ - unsigned pre_prefix:4; /* offset from wrapped to the start of precomp */ - unsigned seen_evals:28; /* number of eval groups in the pattern - for security checks */ + _REGEXP_COMMON; } regexp; -/* HV *paren_names; Optional hash of paren names - now stored in the IV union */ - -#define RXp_PAREN_NAMES(rx) ((rx)->xiv_u.xivu_hv) +#define RXp_PAREN_NAMES(rx) ((rx)->paren_names) /* used for high speed searches */ typedef struct re_scream_pos_data_s @@ -120,7 +120,7 @@ typedef struct re_scream_pos_data_s * Any regex engine implementation must be able to build one of these. */ typedef struct regexp_engine { - REGEXP* (*comp) (pTHX_ const SV * const pattern, const U32 flags); + REGEXP* (*comp) (pTHX_ SV * const pattern, U32 flags); I32 (*exec) (pTHX_ REGEXP * const rx, char* stringarg, char* strend, char* strbeg, I32 minend, SV* screamer, void* data, U32 flags); @@ -178,7 +178,7 @@ typedef struct regexp_engine { /* Whether this is being called from a re:: function */ #define RXapif_REGNAME 0x0400 #define RXapif_REGNAMES 0x0800 -#define RXapif_REGNAMES_COUNT 0x1000 +#define RXapif_REGNAMES_COUNT 0x1000 /* =head1 REGEXP Functions @@ -215,31 +215,20 @@ and check for NULL. #define SvRXOK(sv) (Perl_get_re_arg(aTHX_ sv) ? TRUE : FALSE) -/* Flags stored in regexp->extflags +/* Flags stored in regexp->extflags * These are used by code external to the regexp engine * - * Note that flags starting with RXf_PMf_ have exact equivalents - * stored in op_pmflags and which are defined in op.h, they are defined - * numerically here only for clarity. + * Note that the flags whose names start with RXf_PMf_ are defined in + * op_reg_common.h, being copied from the parallel flags of op_pmflags * - * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl - * so that regnodes.h is updated with the changes. + * NOTE: if you modify any RXf flags you should run regen.pl or + * regen/regcomp.pl so that regnodes.h is updated with the changes. * */ -/* 0x3F of extflags is used by (RXf_)PMf_COMPILETIME - * If you change these you need to change the equivalent flags in op.h, and - * vice versa. */ -#define RXf_PMf_MULTILINE 0x00000001 /* /m */ -#define RXf_PMf_SINGLELINE 0x00000002 /* /s */ -#define RXf_PMf_FOLD 0x00000004 /* /i */ -#define RXf_PMf_EXTENDED 0x00000008 /* /x */ -#define RXf_PMf_KEEPCOPY 0x00000010 /* /p */ -#define RXf_PMf_LOCALE 0x00000020 /* use locale */ -/* these flags are transfered from the PMOP->op_pmflags member during compilation */ -#define RXf_PMf_STD_PMMOD_SHIFT 0 +#include "op_reg_common.h" + #define RXf_PMf_STD_PMMOD (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_FOLD|RXf_PMf_EXTENDED) -#define RXf_PMf_COMPILETIME (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_LOCALE|RXf_PMf_FOLD|RXf_PMf_EXTENDED|RXf_PMf_KEEPCOPY) #define CASE_STD_PMMOD_FLAGS_PARSE_SET(pmfl) \ case IGNORE_PAT_MOD: *(pmfl) |= RXf_PMf_FOLD; break; \ @@ -247,6 +236,10 @@ and check for NULL. case SINGLE_PAT_MOD: *(pmfl) |= RXf_PMf_SINGLELINE; break; \ case XTENDED_PAT_MOD: *(pmfl) |= RXf_PMf_EXTENDED; break +/* Note, includes locale, unicode */ +#define STD_PMMOD_FLAGS_CLEAR(pmfl) \ + *(pmfl) &= ~(RXf_PMf_FOLD|RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_EXTENDED|RXf_PMf_LOCALE|RXf_PMf_UNICODE) + /* chars and strings used as regex pattern modifiers * Singlular is a 'c'har, plural is a "string" * @@ -254,6 +247,7 @@ and check for NULL. * for compatibility reasons with Regexp::Common which highjacked (?k:...) * for its own uses. So 'k' is out as well. */ +#define DEFAULT_PAT_MOD '^' /* Short for all the default modifiers */ #define EXEC_PAT_MOD 'e' #define KEEPCOPY_PAT_MOD 'p' #define ONCE_PAT_MOD 'o' @@ -263,79 +257,100 @@ and check for NULL. #define SINGLE_PAT_MOD 's' #define IGNORE_PAT_MOD 'i' #define XTENDED_PAT_MOD 'x' +#define NONDESTRUCT_PAT_MOD 'r' +#define LOCALE_PAT_MOD 'l' +#define UNICODE_PAT_MOD 'u' +#define DUAL_PAT_MOD 'd' #define ONCE_PAT_MODS "o" #define KEEPCOPY_PAT_MODS "p" #define EXEC_PAT_MODS "e" #define LOOP_PAT_MODS "gc" - +#define NONDESTRUCT_PAT_MODS "r" +#define LOCALE_PAT_MODS "l" +#define UNICODE_PAT_MODS "u" +#define DUAL_PAT_MODS "d" + +/* This string is expected by regcomp.c to be ordered so that the first + * character is the flag in bit RXf_PMf_STD_PMMOD_SHIFT of extflags; the next + * character is bit +1, etc. */ #define STD_PAT_MODS "msix" +/* This string is expected by XS_re_regexp_pattern() in universal.c to be ordered + * so that the first character is the flag in bit RXf_PMf_STD_PMMOD_SHIFT of + * extflags; the next character is in bit +1, etc. */ #define INT_PAT_MODS STD_PAT_MODS KEEPCOPY_PAT_MODS #define EXT_PAT_MODS ONCE_PAT_MODS KEEPCOPY_PAT_MODS #define QR_PAT_MODS STD_PAT_MODS EXT_PAT_MODS #define M_PAT_MODS QR_PAT_MODS LOOP_PAT_MODS -#define S_PAT_MODS M_PAT_MODS EXEC_PAT_MODS +#define S_PAT_MODS M_PAT_MODS EXEC_PAT_MODS NONDESTRUCT_PAT_MODS /* - * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl - * so that regnodes.h is updated with the changes. + * NOTE: if you modify any RXf flags you should run regen.pl or + * regen/regcomp.pl so that regnodes.h is updated with the changes. * */ +/* Leave some space, so future bit allocations can go either in the shared or + * unshared area without affecting binary compatibility */ +#define RXf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT+2) + /* Anchor and GPOS related stuff */ -#define RXf_ANCH_BOL 0x00000100 -#define RXf_ANCH_MBOL 0x00000200 -#define RXf_ANCH_SBOL 0x00000400 -#define RXf_ANCH_GPOS 0x00000800 -#define RXf_GPOS_SEEN 0x00001000 -#define RXf_GPOS_FLOAT 0x00002000 +#define RXf_ANCH_BOL (1<<(RXf_BASE_SHIFT+0)) +#define RXf_ANCH_MBOL (1<<(RXf_BASE_SHIFT+1)) +#define RXf_ANCH_SBOL (1<<(RXf_BASE_SHIFT+2)) +#define RXf_ANCH_GPOS (1<<(RXf_BASE_SHIFT+3)) +#define RXf_GPOS_SEEN (1<<(RXf_BASE_SHIFT+4)) +#define RXf_GPOS_FLOAT (1<<(RXf_BASE_SHIFT+5)) /* two bits here */ #define RXf_ANCH (RXf_ANCH_BOL|RXf_ANCH_MBOL|RXf_ANCH_GPOS|RXf_ANCH_SBOL) #define RXf_GPOS_CHECK (RXf_GPOS_SEEN|RXf_ANCH_GPOS) #define RXf_ANCH_SINGLE (RXf_ANCH_SBOL|RXf_ANCH_GPOS) /* What we have seen */ -#define RXf_LOOKBEHIND_SEEN 0x00004000 -#define RXf_EVAL_SEEN 0x00008000 -#define RXf_CANY_SEEN 0x00010000 +#define RXf_LOOKBEHIND_SEEN (1<<(RXf_BASE_SHIFT+6)) +#define RXf_EVAL_SEEN (1<<(RXf_BASE_SHIFT+7)) +#define RXf_CANY_SEEN (1<<(RXf_BASE_SHIFT+8)) /* Special */ -#define RXf_NOSCAN 0x00020000 -#define RXf_CHECK_ALL 0x00040000 +#define RXf_NOSCAN (1<<(RXf_BASE_SHIFT+9)) +#define RXf_CHECK_ALL (1<<(RXf_BASE_SHIFT+10)) /* UTF8 related */ -#define RXf_MATCH_UTF8 0x00100000 +#define RXf_MATCH_UTF8 (1<<(RXf_BASE_SHIFT+11)) /* Intuit related */ -#define RXf_USE_INTUIT_NOML 0x00200000 -#define RXf_USE_INTUIT_ML 0x00400000 -#define RXf_INTUIT_TAIL 0x00800000 +#define RXf_USE_INTUIT_NOML (1<<(RXf_BASE_SHIFT+12)) +#define RXf_USE_INTUIT_ML (1<<(RXf_BASE_SHIFT+13)) +#define RXf_INTUIT_TAIL (1<<(RXf_BASE_SHIFT+14)) /* Set in Perl_pmruntime if op_flags & OPf_SPECIAL, i.e. split. Will be used by regex engines to check whether they should set RXf_SKIPWHITE */ -#define RXf_SPLIT 0x01000000 +#define RXf_SPLIT (1<<(RXf_BASE_SHIFT+15)) #define RXf_USE_INTUIT (RXf_USE_INTUIT_NOML|RXf_USE_INTUIT_ML) /* Copy and tainted info */ -#define RXf_COPY_DONE 0x02000000 -#define RXf_TAINTED_SEEN 0x04000000 -#define RXf_TAINTED 0x08000000 /* this pattern is tainted */ +#define RXf_COPY_DONE (1<<(RXf_BASE_SHIFT+16)) +#define RXf_TAINTED_SEEN (1<<(RXf_BASE_SHIFT+17)) +#define RXf_TAINTED (1<<(RXf_BASE_SHIFT+18)) /* this pattern is tainted */ /* Flags indicating special patterns */ -#define RXf_START_ONLY 0x10000000 /* Pattern is /^/ */ -#define RXf_SKIPWHITE 0x20000000 /* Pattern is for a split / / */ -#define RXf_WHITE 0x40000000 /* Pattern is /\s+/ */ -#define RXf_NULL 0x80000000 /* Pattern is // */ +#define RXf_START_ONLY (1<<(RXf_BASE_SHIFT+19)) /* Pattern is /^/ */ +#define RXf_SKIPWHITE (1<<(RXf_BASE_SHIFT+20)) /* Pattern is for a split / / */ +#define RXf_WHITE (1<<(RXf_BASE_SHIFT+21)) /* Pattern is /\s+/ */ +#define RXf_NULL (1<<(RXf_BASE_SHIFT+22)) /* Pattern is // */ +#if RXf_BASE_SHIFT+22 > 31 +# error Too many RXf_PMf bits used. See regnodes.h for any spare in middle +#endif /* - * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl - * so that regnodes.h is updated with the changes. + * NOTE: if you modify any RXf flags you should run regen.pl or + * regen/regcomp.pl so that regnodes.h is updated with the changes. * */ @@ -362,21 +377,55 @@ and check for NULL. /* For source compatibility. We used to store these explicitly. */ #define RX_PRECOMP(prog) (RX_WRAPPED(prog) + ((struct regexp *)SvANY(prog))->pre_prefix) +#define RX_PRECOMP_const(prog) (RX_WRAPPED_const(prog) + ((struct regexp *)SvANY(prog))->pre_prefix) /* FIXME? Are we hardcoding too much here and constraining plugin extension writers? Specifically, the value 1 assumes that the wrapped version always has exactly one character at the end, a ')'. Will that always be true? */ #define RX_PRELEN(prog) (RX_WRAPLEN(prog) - ((struct regexp *)SvANY(prog))->pre_prefix - 1) #define RX_WRAPPED(prog) SvPVX(prog) +#define RX_WRAPPED_const(prog) SvPVX_const(prog) #define RX_WRAPLEN(prog) SvCUR(prog) #define RX_CHECK_SUBSTR(prog) (((struct regexp *)SvANY(prog))->check_substr) -#define RX_EXTFLAGS(prog) RXp_EXTFLAGS((struct regexp *)SvANY(prog)) #define RX_REFCNT(prog) SvREFCNT(prog) -#define RX_ENGINE(prog) (((struct regexp *)SvANY(prog))->engine) -#define RX_SUBBEG(prog) (((struct regexp *)SvANY(prog))->subbeg) -#define RX_OFFS(prog) (((struct regexp *)SvANY(prog))->offs) -#define RX_NPARENS(prog) (((struct regexp *)SvANY(prog))->nparens) +#if defined(__GNUC__) && !defined(PERL_GCC_BRACE_GROUPS_FORBIDDEN) +# define RX_EXTFLAGS(prog) \ + (*({ \ + const REGEXP *const _rx_extflags = (prog); \ + assert(SvTYPE(_rx_extflags) == SVt_REGEXP); \ + &RXp_EXTFLAGS(SvANY(_rx_extflags)); \ + })) +# define RX_ENGINE(prog) \ + (*({ \ + const REGEXP *const _rx_engine = (prog); \ + assert(SvTYPE(_rx_engine) == SVt_REGEXP); \ + &SvANY(_rx_engine)->engine; \ + })) +# define RX_SUBBEG(prog) \ + (*({ \ + const REGEXP *const _rx_subbeg = (prog); \ + assert(SvTYPE(_rx_subbeg) == SVt_REGEXP); \ + &SvANY(_rx_subbeg)->subbeg; \ + })) +# define RX_OFFS(prog) \ + (*({ \ + const REGEXP *const _rx_offs = (prog); \ + assert(SvTYPE(_rx_offs) == SVt_REGEXP); \ + &SvANY(_rx_offs)->offs; \ + })) +# define RX_NPARENS(prog) \ + (*({ \ + const REGEXP *const _rx_nparens = (prog); \ + assert(SvTYPE(_rx_nparens) == SVt_REGEXP); \ + &SvANY(_rx_nparens)->nparens; \ + })) +#else +# define RX_EXTFLAGS(prog) RXp_EXTFLAGS((struct regexp *)SvANY(prog)) +# define RX_ENGINE(prog) (((struct regexp *)SvANY(prog))->engine) +# define RX_SUBBEG(prog) (((struct regexp *)SvANY(prog))->subbeg) +# define RX_OFFS(prog) (((struct regexp *)SvANY(prog))->offs) +# define RX_NPARENS(prog) (((struct regexp *)SvANY(prog))->nparens) +#endif #define RX_SUBLEN(prog) (((struct regexp *)SvANY(prog))->sublen) -#define RX_SUBBEG(prog) (((struct regexp *)SvANY(prog))->subbeg) #define RX_MINLEN(prog) (((struct regexp *)SvANY(prog))->minlen) #define RX_MINLENRET(prog) (((struct regexp *)SvANY(prog))->minlenret) #define RX_GOFS(prog) (((struct regexp *)SvANY(prog))->gofs) @@ -416,29 +465,31 @@ and check for NULL. /* Whether the pattern stored at RX_WRAPPED is in UTF-8 */ #define RX_UTF8(prog) SvUTF8(prog) - + #define REXEC_COPY_STR 0x01 /* Need to copy the string. */ #define REXEC_CHECKED 0x02 /* check_substr already checked. */ #define REXEC_SCREAM 0x04 /* use scream table. */ #define REXEC_IGNOREPOS 0x08 /* \G matches at start. */ #define REXEC_NOT_FIRST 0x10 /* This is another iteration of //g. */ -#if defined(__GNUC__) && !defined(__STRICT_ANSI__) && !defined(PERL_GCC_PEDANTIC) +#if defined(__GNUC__) && !defined(PERL_GCC_BRACE_GROUPS_FORBIDDEN) # define ReREFCNT_inc(re) \ ({ \ /* This is here to generate a casting warning if incorrect. */ \ - REGEXP *const zwapp = (re); \ - SvREFCNT_inc(zwapp); \ + REGEXP *const _rerefcnt_inc = (re); \ + assert(SvTYPE(_rerefcnt_inc) == SVt_REGEXP); \ + SvREFCNT_inc(_rerefcnt_inc); \ + _rerefcnt_inc; \ }) # define ReREFCNT_dec(re) \ ({ \ /* This is here to generate a casting warning if incorrect. */ \ - REGEXP *const boff = (re); \ - SvREFCNT_dec(boff); \ + REGEXP *const _rerefcnt_dec = (re); \ + SvREFCNT_dec(_rerefcnt_dec); \ }) #else # define ReREFCNT_dec(re) SvREFCNT_dec(re) -# define ReREFCNT_inc(re) SvREFCNT_inc(re) +# define ReREFCNT_inc(re) ((REGEXP *) SvREFCNT_inc(re)) #endif /* FIXME for plugins. */ @@ -451,13 +502,6 @@ and check for NULL. #define FBMrf_MULTILINE 1 -/* an accepting state/position*/ -struct _reg_trie_accepted { - U8 *endpos; - U16 wordnum; -}; -typedef struct _reg_trie_accepted reg_trie_accepted; - /* some basic information about the current match that is created by * Perl_regexec_flags and then passed to regtry(), regmatch() etc */ @@ -518,11 +562,15 @@ typedef struct regmatch_state { U32 lastparen; CHECKPOINT cp; - reg_trie_accepted *accept_buff; /* accepting states we have seen */ - U32 accepted; /* how many accepting states we have seen */ + U32 accepted; /* how many accepting states left */ U16 *jump; /* positive offsets from me */ regnode *B; /* node following the trie */ regnode *me; /* Which node am I - needed for jump tries*/ + U8 *firstpos;/* pos in string of first trie match */ + U32 firstchars;/* len in chars of firstpos from start */ + U16 nextword;/* next word to try */ + U16 topword; /* longest accepted word */ + bool longfold;/* saw a fold with a 1->n char mapping */ } trie; /* special types - these members are used to store state for special @@ -568,12 +616,11 @@ typedef struct regmatch_state { /* this first element must match u.yes */ struct regmatch_state *prev_yes_state; struct regmatch_state *prev_curlyx; /* previous cur_curlyx */ - regnode *A, *B; /* the nodes corresponding to /A*B/ */ + regnode *me; /* the CURLYX node */ + regnode *B; /* the B node in /A*B/ */ CHECKPOINT cp; /* remember current savestack index */ bool minmod; int parenfloor;/* how far back to strip paren data */ - int min; /* the minimal number of A's to match */ - int max; /* the maximal number of A's to match */ /* these two are modified by WHILEM */ int count; /* how many instances of A we've matched */