X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=regexp.h;h=90e3406a965941ba683673f60b389ba9d466a964;hb=fa58a56f3cdf71021d7d7a49e98845f57652a3fe;hp=e195f67053b7c6b2af4ca9e7fa1eff8474b3c575;hpb=d7b3331898f84d163479fe03eff5bc0b654de391;p=p5sagit%2Fp5-mst-13.2.git diff --git a/regexp.h b/regexp.h index e195f67..90e3406 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 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. @@ -55,52 +55,63 @@ typedef struct regexp_paren_pair { I32 end; } regexp_paren_pair; -/* this is ordered such that the most commonly used - fields are at the start of the struct */ +/* + The regexp/REGEXP struct, see L for further documentation + on the individual fields. The struct is ordered so that the most + commonly used fields are placed at the start. + + Any patch that adds items to this struct will need to include + changes to F (C) and F + (C). This involves freeing or cloning items in the + 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? */ \ + /* 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 { - /* what engine created this regexp? */ - const struct regexp_engine* engine; - struct 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. */ - I32 sublen; /* Length of string pointed by subbeg */ - SV_SAVED_COPY /* If non-NULL, SV which is COW from original */ - - - /* Information about the match that isn't often used */ - const char *precomp; /* pre-compilation regular expression */ - I32 prelen; /* length of precomp */ - /* wrapped can't be const char*, as it is returned by sv_2pv_flags */ - char *wrapped; /* wrapped version of the pattern */ - I32 wraplen; /* length of wrapped */ - I32 seen_evals; /* number of eval groups in the pattern - for security checks */ - HV *paren_names; /* Optional hash of paren names */ - - /* Refcount of this regexp */ - I32 refcnt; /* Refcount of this regexp */ + _XPV_HEAD; + _XPVMG_HEAD; + _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) + /* used for high speed searches */ typedef struct re_scream_pos_data_s { @@ -112,54 +123,124 @@ 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_ char* exp, char* xend, PMOP* pm); - I32 (*exec) (pTHX_ regexp* prog, char* stringarg, char* strend, - char* strbeg, I32 minend, SV* screamer, - void* data, U32 flags); - char* (*intuit) (pTHX_ regexp *prog, SV *sv, char *strpos, - char *strend, U32 flags, - struct re_scream_pos_data_s *data); - SV* (*checkstr) (pTHX_ regexp *prog); - void (*free) (pTHX_ struct regexp* r); - SV* (*numbered_buff_get) (pTHX_ const REGEXP * const rx, I32 paren, SV* usesv); - SV* (*named_buff_get)(pTHX_ const REGEXP * const rx, SV* namesv, 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); + char* (*intuit) (pTHX_ REGEXP * const rx, SV *sv, char *strpos, + char *strend, const U32 flags, + re_scream_pos_data *data); + SV* (*checkstr) (pTHX_ REGEXP * const rx); + void (*free) (pTHX_ REGEXP * const rx); + void (*numbered_buff_FETCH) (pTHX_ REGEXP * const rx, const I32 paren, + SV * const sv); + void (*numbered_buff_STORE) (pTHX_ REGEXP * const rx, const I32 paren, + SV const * const value); + I32 (*numbered_buff_LENGTH) (pTHX_ REGEXP * const rx, const SV * const sv, + const I32 paren); + SV* (*named_buff) (pTHX_ REGEXP * const rx, SV * const key, + SV * const value, const U32 flags); + SV* (*named_buff_iter) (pTHX_ REGEXP * const rx, const SV * const lastkey, + const U32 flags); + SV* (*qr_package)(pTHX_ REGEXP * const rx); #ifdef USE_ITHREADS - void* (*dupe) (pTHX_ const regexp *r, CLONE_PARAMS *param); -#endif + void* (*dupe) (pTHX_ REGEXP * const rx, CLONE_PARAMS *param); +#endif } regexp_engine; -/* Flags stored in regexp->extflags +/* + These are passed to the numbered capture variable callbacks as the + paren name. >= 1 is reserved for actual numbered captures, i.e. $1, + $2 etc. +*/ +#define RX_BUFF_IDX_PREMATCH -2 /* $` / ${^PREMATCH} */ +#define RX_BUFF_IDX_POSTMATCH -1 /* $' / ${^POSTMATCH} */ +#define RX_BUFF_IDX_FULLMATCH 0 /* $& / ${^MATCH} */ + +/* + Flags that are passed to the named_buff and named_buff_iter + callbacks above. Those routines are called from universal.c via the + Tie::Hash::NamedCapture interface for %+ and %- and the re:: + functions in the same file. +*/ + +/* The Tie::Hash::NamedCapture operation this is part of, if any */ +#define RXapif_FETCH 0x0001 +#define RXapif_STORE 0x0002 +#define RXapif_DELETE 0x0004 +#define RXapif_CLEAR 0x0008 +#define RXapif_EXISTS 0x0010 +#define RXapif_SCALAR 0x0020 +#define RXapif_FIRSTKEY 0x0040 +#define RXapif_NEXTKEY 0x0080 + +/* Whether %+ or %- is being operated on */ +#define RXapif_ONE 0x0100 /* %+ */ +#define RXapif_ALL 0x0200 /* %- */ + +/* Whether this is being called from a re:: function */ +#define RXapif_REGNAME 0x0400 +#define RXapif_REGNAMES 0x0800 +#define RXapif_REGNAMES_COUNT 0x1000 + +/* +=head1 REGEXP Functions + +=for apidoc Am|REGEXP *|SvRX|SV *sv + +Convenience macro to get the REGEXP from a SV. This is approximately +equivalent to the following snippet: + + if (SvMAGICAL(sv)) + mg_get(sv); + if (SvROK(sv) && + (tmpsv = (SV*)SvRV(sv)) && + SvTYPE(tmpsv) == SVt_PVMG && + (tmpmg = mg_find(tmpsv, PERL_MAGIC_qr))) + { + return (REGEXP *)tmpmg->mg_obj; + } + +NULL will be returned if a REGEXP* is not found. + +=for apidoc Am|bool|SvRXOK|SV* sv + +Returns a boolean indicating whether the SV contains qr magic +(PERL_MAGIC_qr). + +If you want to do something with the REGEXP* later use SvRX instead +and check for NULL. + +=cut +*/ + +#define SvRX(sv) (Perl_get_re_arg(aTHX_ sv)) +#define SvRXOK(sv) (Perl_get_re_arg(aTHX_ sv) ? TRUE : FALSE) + + +/* 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: if you modify any RXf flags you should run regen.pl or regcomp.pl + * so that regnodes.h is updated with the changes. + * */ -/* Anchor and GPOS related stuff */ -#define RXf_ANCH_BOL 0x00000001 -#define RXf_ANCH_MBOL 0x00000002 -#define RXf_ANCH_SBOL 0x00000004 -#define RXf_ANCH_GPOS 0x00000008 -#define RXf_GPOS_SEEN 0x00000010 -#define RXf_GPOS_FLOAT 0x00000020 -/* 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) - -/* Flags indicating special patterns */ -#define RXf_START_ONLY 0x00000200 /* Pattern is /^/ */ -#define RXf_WHITE 0x00000400 /* Pattern is /\s+/ */ - -/* 0x1F800 of extflags is used by (RXf_)PMf_COMPILETIME */ -#define RXf_PMf_LOCALE 0x00000800 /* use locale */ -#define RXf_PMf_MULTILINE 0x00001000 /* /m */ -#define RXf_PMf_SINGLELINE 0x00002000 /* /s */ -#define RXf_PMf_FOLD 0x00004000 /* /i */ -#define RXf_PMf_EXTENDED 0x00008000 /* /x */ -#define RXf_PMf_KEEPCOPY 0x00010000 /* /k */ +/* 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 #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) @@ -200,83 +281,206 @@ typedef struct regexp_engine { #define M_PAT_MODS QR_PAT_MODS LOOP_PAT_MODS #define S_PAT_MODS M_PAT_MODS EXEC_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. + * + */ + +/* 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 +/* 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 0x00020000 -#define RXf_EVAL_SEEN 0x00040000 -#define RXf_CANY_SEEN 0x00080000 +#define RXf_LOOKBEHIND_SEEN 0x00004000 +#define RXf_EVAL_SEEN 0x00008000 +#define RXf_CANY_SEEN 0x00010000 /* Special */ -#define RXf_NOSCAN 0x00100000 -#define RXf_CHECK_ALL 0x00200000 +#define RXf_NOSCAN 0x00020000 +#define RXf_CHECK_ALL 0x00040000 /* UTF8 related */ -#define RXf_UTF8 0x00400000 -#define RXf_MATCH_UTF8 0x00800000 +#define RXf_MATCH_UTF8 0x00100000 /* Intuit related */ -#define RXf_USE_INTUIT_NOML 0x01000000 -#define RXf_USE_INTUIT_ML 0x02000000 -#define RXf_INTUIT_TAIL 0x04000000 -/* one bit here */ +#define RXf_USE_INTUIT_NOML 0x00200000 +#define RXf_USE_INTUIT_ML 0x00400000 +#define RXf_INTUIT_TAIL 0x00800000 + +/* + 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_USE_INTUIT (RXf_USE_INTUIT_NOML|RXf_USE_INTUIT_ML) /* Copy and tainted info */ -#define RXf_COPY_DONE 0x10000000 -#define RXf_TAINTED_SEEN 0x20000000 -/* two bits here */ +#define RXf_COPY_DONE 0x02000000 +#define RXf_TAINTED_SEEN 0x04000000 +#define RXf_TAINTED 0x08000000 /* 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 // */ + +/* + * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl + * so that regnodes.h is updated with the changes. + * + */ #define RX_HAS_CUTGROUP(prog) ((prog)->intflags & PREGf_CUTGROUP_SEEN) -#define RX_MATCH_TAINTED(prog) ((prog)->extflags & RXf_TAINTED_SEEN) -#define RX_MATCH_TAINTED_on(prog) ((prog)->extflags |= RXf_TAINTED_SEEN) -#define RX_MATCH_TAINTED_off(prog) ((prog)->extflags &= ~RXf_TAINTED_SEEN) +#define RXp_MATCH_TAINTED(prog) (RXp_EXTFLAGS(prog) & RXf_TAINTED_SEEN) +#define RX_MATCH_TAINTED(prog) (RX_EXTFLAGS(prog) & RXf_TAINTED_SEEN) +#define RX_MATCH_TAINTED_on(prog) (RX_EXTFLAGS(prog) |= RXf_TAINTED_SEEN) +#define RX_MATCH_TAINTED_off(prog) (RX_EXTFLAGS(prog) &= ~RXf_TAINTED_SEEN) #define RX_MATCH_TAINTED_set(prog, t) ((t) \ ? RX_MATCH_TAINTED_on(prog) \ : RX_MATCH_TAINTED_off(prog)) -#define RX_MATCH_COPIED(prog) ((prog)->extflags & RXf_COPY_DONE) -#define RX_MATCH_COPIED_on(prog) ((prog)->extflags |= RXf_COPY_DONE) -#define RX_MATCH_COPIED_off(prog) ((prog)->extflags &= ~RXf_COPY_DONE) +#define RXp_MATCH_COPIED(prog) (RXp_EXTFLAGS(prog) & RXf_COPY_DONE) +#define RX_MATCH_COPIED(prog) (RX_EXTFLAGS(prog) & RXf_COPY_DONE) +#define RXp_MATCH_COPIED_on(prog) (RXp_EXTFLAGS(prog) |= RXf_COPY_DONE) +#define RX_MATCH_COPIED_on(prog) (RX_EXTFLAGS(prog) |= RXf_COPY_DONE) +#define RXp_MATCH_COPIED_off(prog) (RXp_EXTFLAGS(prog) &= ~RXf_COPY_DONE) +#define RX_MATCH_COPIED_off(prog) (RX_EXTFLAGS(prog) &= ~RXf_COPY_DONE) #define RX_MATCH_COPIED_set(prog,t) ((t) \ ? RX_MATCH_COPIED_on(prog) \ : RX_MATCH_COPIED_off(prog)) +#define RXp_EXTFLAGS(rx) ((rx)->extflags) + +/* 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_REFCNT(prog) SvREFCNT(prog) +#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_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) +#define RX_LASTPAREN(prog) (((struct regexp *)SvANY(prog))->lastparen) +#define RX_LASTCLOSEPAREN(prog) (((struct regexp *)SvANY(prog))->lastcloseparen) +#define RX_SEEN_EVALS(prog) (((struct regexp *)SvANY(prog))->seen_evals) +#define RX_SAVED_COPY(prog) (((struct regexp *)SvANY(prog))->saved_copy) + #endif /* PLUGGABLE_RE_EXTENSION */ /* Stuff that needs to be included in the plugable extension goes below here */ #ifdef PERL_OLD_COPY_ON_WRITE #define RX_MATCH_COPY_FREE(rx) \ - STMT_START {if (rx->saved_copy) { \ - SV_CHECK_THINKFIRST_COW_DROP(rx->saved_copy); \ + STMT_START {if (RX_SAVED_COPY(rx)) { \ + SV_CHECK_THINKFIRST_COW_DROP(RX_SAVED_COPY(rx)); \ } \ if (RX_MATCH_COPIED(rx)) { \ - Safefree(rx->subbeg); \ + Safefree(RX_SUBBEG(rx)); \ RX_MATCH_COPIED_off(rx); \ }} STMT_END #else #define RX_MATCH_COPY_FREE(rx) \ STMT_START {if (RX_MATCH_COPIED(rx)) { \ - Safefree(rx->subbeg); \ + Safefree(RX_SUBBEG(rx)); \ RX_MATCH_COPIED_off(rx); \ }} STMT_END #endif -#define RX_MATCH_UTF8(prog) ((prog)->extflags & RXf_MATCH_UTF8) -#define RX_MATCH_UTF8_on(prog) ((prog)->extflags |= RXf_MATCH_UTF8) -#define RX_MATCH_UTF8_off(prog) ((prog)->extflags &= ~RXf_MATCH_UTF8) +#define RXp_MATCH_UTF8(prog) (RXp_EXTFLAGS(prog) & RXf_MATCH_UTF8) +#define RX_MATCH_UTF8(prog) (RX_EXTFLAGS(prog) & RXf_MATCH_UTF8) +#define RX_MATCH_UTF8_on(prog) (RX_EXTFLAGS(prog) |= RXf_MATCH_UTF8) +#define RX_MATCH_UTF8_off(prog) (RX_EXTFLAGS(prog) &= ~RXf_MATCH_UTF8) #define RX_MATCH_UTF8_set(prog, t) ((t) \ ? (RX_MATCH_UTF8_on(prog), (PL_reg_match_utf8 = 1)) \ : (RX_MATCH_UTF8_off(prog), (PL_reg_match_utf8 = 0))) - + +/* 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. */ -#define ReREFCNT_inc(re) ((void)(re && re->refcnt++), re) -#define ReREFCNT_dec(re) CALLREGFREE(re) +#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 _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 _rerefcnt_dec = (re); \ + SvREFCNT_dec(_rerefcnt_dec); \ + }) +#else +# define ReREFCNT_dec(re) SvREFCNT_dec(re) +# define ReREFCNT_inc(re) ((REGEXP *) SvREFCNT_inc(re)) +#endif + +/* FIXME for plugins. */ #define FBMcf_TAIL_DOLLAR 1 #define FBMcf_TAIL_DOLLARM 2 @@ -297,7 +501,7 @@ typedef struct _reg_trie_accepted reg_trie_accepted; * Perl_regexec_flags and then passed to regtry(), regmatch() etc */ typedef struct { - regexp *prog; + REGEXP *prog; char *bol; char *till; SV *sv; @@ -367,14 +571,14 @@ typedef struct regmatch_state { struct regmatch_state *prev_yes_state; struct regmatch_state *prev_eval; struct regmatch_state *prev_curlyx; - regexp *prev_rex; + REGEXP *prev_rex; U32 toggle_reg_flags; /* what bits in PL_reg_flags to flip when transitioning between inner and outer rexen */ CHECKPOINT cp; /* remember current savestack indexes */ CHECKPOINT lastcp; - regnode *B; /* the node following us */ U32 close_paren; /* which close bracket is our end */ + regnode *B; /* the node following us */ } eval; struct { @@ -403,12 +607,12 @@ 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/ */ 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 */ - regnode *A, *B; /* the nodes corresponding to /A*B/ */ /* these two are modified by WHILEM */ int count; /* how many instances of A we've matched */ @@ -491,6 +695,9 @@ typedef struct regmatch_slab { struct re_save_state { U32 re_state_reg_flags; /* from regexec.c */ + U32 re_state_reg_start_tmpl; /* from regexec.c */ + I32 re_state_reg_eval_set; /* from regexec.c */ + bool re_state_reg_match_utf8; /* from regexec.c */ char *re_state_bostr; char *re_state_reginput; /* String-input pointer. */ char *re_state_regeol; /* End of input, for $ check. */ @@ -498,20 +705,17 @@ struct re_save_state { U32 *re_state_reglastparen; /* Similarly for lastparen. */ U32 *re_state_reglastcloseparen; /* Similarly for lastcloseparen. */ char **re_state_reg_start_tmp; /* from regexec.c */ - U32 re_state_reg_start_tmpl; /* from regexec.c */ - I32 re_state_reg_eval_set; /* from regexec.c */ - bool re_state_reg_match_utf8; /* from regexec.c */ MAGIC *re_state_reg_magic; /* from regexec.c */ - I32 re_state_reg_oldpos; /* from regexec.c */ PMOP *re_state_reg_oldcurpm; /* from regexec.c */ PMOP *re_state_reg_curpm; /* from regexec.c */ char *re_state_reg_oldsaved; /* old saved substr during match */ STRLEN re_state_reg_oldsavedlen; /* old length of saved substr during match */ + STRLEN re_state_reg_poscache_size; /* size of pos cache of WHILEM */ + I32 re_state_reg_oldpos; /* from regexec.c */ I32 re_state_reg_maxiter; /* max wait until caching pos */ I32 re_state_reg_leftiter; /* wait until caching pos */ - char *re_state_reg_poscache; /* cache of pos of WHILEM */ - STRLEN re_state_reg_poscache_size; /* size of pos cache of WHILEM */ U32 re_state_regsize; /* from regexec.c */ + char *re_state_reg_poscache; /* cache of pos of WHILEM */ char *re_state_reg_starttry; /* from regexec.c */ #ifdef PERL_OLD_COPY_ON_WRITE SV *re_state_nrs; /* was placeholder: unused since 5.8.0 (5.7.2 patch #12027 for bug ID 20010815.012). Used to save rx->saved_copy */