X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=regexp.h;h=d12df9209a0bf609aea054bc0af31eb099543eb9;hb=25ff0154ccf606eb5512a8cde622caf50e20fba3;hp=f71aefa7c8f6bf16998ac38297b24bede0d50337;hpb=5d458dd8ef53373c3f90d568f6668084b0ccbc62;p=p5sagit%2Fp5-mst-13.2.git diff --git a/regexp.h b/regexp.h index f71aefa..d12df92 100644 --- a/regexp.h +++ b/regexp.h @@ -1,7 +1,7 @@ /* regexp.h * * Copyright (C) 1993, 1994, 1996, 1997, 1999, 2000, 2001, 2003, - * by Larry Wall and others + * 2005, 2006 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. @@ -15,8 +15,8 @@ * not the System V one. */ #ifndef PLUGGABLE_RE_EXTENSION -/* we don't want to include this stuff if we are inside Nicholas' - * pluggable regex engine code */ +/* we don't want to include this stuff if we are inside of + an external regex engine based on the core one - like re 'debug'*/ struct regnode { U8 flags; @@ -32,41 +32,75 @@ struct reg_data; struct regexp_engine; -typedef struct regexp { - I32 *startp; - I32 *endp; - regnode *regstclass; - struct reg_substr_data *substrs; - char *precomp; /* pre-compilation regular expression */ - struct reg_data *data; /* Additional data. */ - char *subbeg; /* saved or original string - so \digit works forever. */ +struct reg_substr_datum { + I32 min_offset; + I32 max_offset; + SV *substr; /* non-utf8 variant */ + SV *utf8_substr; /* utf8 variant */ + I32 end_shift; +}; +struct reg_substr_data { + struct reg_substr_datum data[3]; /* Actual array */ +}; + #ifdef PERL_OLD_COPY_ON_WRITE - SV *saved_copy; /* If non-NULL, SV which is COW from original */ +#define SV_SAVED_COPY SV *saved_copy; /* If non-NULL, SV which is COW from original */ +#else +#define SV_SAVED_COPY #endif - U32 *offsets; /* offset annotations 20001228 MJD */ - I32 sublen; /* Length of string pointed by subbeg */ - I32 refcnt; +/* this is ordered such that the most commonly used + fields are at the start of the struct */ +typedef struct regexp { + /* what engine created this regexp? */ + const struct regexp_engine* engine; + + /* 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 */ + I32 *startp; /* Array of offsets from start of string (@-) */ + I32 *endp; /* Array of offsets from start of string (@+) */ + 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 */ + char *precomp; /* pre-compilation regular expression */ I32 prelen; /* length of precomp */ - U32 nparens; /* number of parentheses */ - U32 lastparen; /* last paren matched */ - U32 lastcloseparen; /* last paren matched */ - U32 reganch; /* Internal use only + - Tainted information used by regexec? */ - HV *paren_names; /* Paren names */ - const struct regexp_engine* engine; - regnode program[1]; /* Unwarranted chumminess with compiler. */ + 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 */ } regexp; - +/* used for high speed searches */ typedef struct re_scream_pos_data_s { char **scream_olds; /* match pos */ I32 *scream_pos; /* Internal iterator of scream. */ } re_scream_pos_data; +/* regexp_engine structure. This is the dispatch table for regexes. + * 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, @@ -77,64 +111,123 @@ typedef struct regexp_engine { struct re_scream_pos_data_s *data); SV* (*checkstr) (pTHX_ regexp *prog); void (*free) (pTHX_ struct regexp* r); - char* (*as_str) (pTHX_ MAGIC *mg, STRLEN *lp, U32 *flags, I32 *haseval); + 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); #ifdef USE_ITHREADS - regexp* (*dupe) (pTHX_ const regexp *r, CLONE_PARAMS *param); + void* (*dupe) (pTHX_ const regexp *r, CLONE_PARAMS *param); #endif } regexp_engine; -#define ROPT_ANCH (ROPT_ANCH_BOL|ROPT_ANCH_MBOL|ROPT_ANCH_GPOS|ROPT_ANCH_SBOL) -#define ROPT_ANCH_SINGLE (ROPT_ANCH_SBOL|ROPT_ANCH_GPOS) -#define ROPT_ANCH_BOL 0x00000001 -#define ROPT_ANCH_MBOL 0x00000002 -#define ROPT_ANCH_SBOL 0x00000004 -#define ROPT_ANCH_GPOS 0x00000008 -#define ROPT_SKIP 0x00000010 -#define ROPT_IMPLICIT 0x00000020 /* Converted .* to ^.* */ -#define ROPT_NOSCAN 0x00000040 /* Check-string always at start. */ -#define ROPT_GPOS_SEEN 0x00000080 -#define ROPT_CHECK_ALL 0x00000100 -#define ROPT_LOOKBEHIND_SEEN 0x00000200 -#define ROPT_EVAL_SEEN 0x00000400 -#define ROPT_CANY_SEEN 0x00000800 -#define ROPT_SANY_SEEN ROPT_CANY_SEEN /* src bckwrd cmpt */ -#define ROPT_GPOS_CHECK (ROPT_GPOS_SEEN|ROPT_ANCH_GPOS) - -/* 0xF800 of reganch is used by PMf_COMPILETIME */ - -#define ROPT_UTF8 0x00010000 -#define ROPT_NAUGHTY 0x00020000 /* how exponential is this pattern? */ -#define ROPT_COPY_DONE 0x00040000 /* subbeg is a copy of the string */ -#define ROPT_TAINTED_SEEN 0x00080000 -#define ROPT_MATCH_UTF8 0x10000000 /* subbeg is utf-8 */ -#define ROPT_VERBARG_SEEN 0x20000000 -#define ROPT_CUTGROUP_SEEN 0x40000000 - -#define RE_USE_INTUIT_NOML 0x00100000 /* Best to intuit before matching */ -#define RE_USE_INTUIT_ML 0x00200000 -#define REINT_AUTORITATIVE_NOML 0x00400000 /* Can trust a positive answer */ -#define REINT_AUTORITATIVE_ML 0x00800000 -#define REINT_ONCE_NOML 0x01000000 /* Intuit can succed once only. */ -#define REINT_ONCE_ML 0x02000000 -#define RE_INTUIT_ONECHAR 0x04000000 -#define RE_INTUIT_TAIL 0x08000000 - - -#define RE_USE_INTUIT (RE_USE_INTUIT_NOML|RE_USE_INTUIT_ML) -#define REINT_AUTORITATIVE (REINT_AUTORITATIVE_NOML|REINT_AUTORITATIVE_ML) -#define REINT_ONCE (REINT_ONCE_NOML|REINT_ONCE_ML) - -#define RX_HAS_CUTGROUP(prog) ((prog)->reganch & ROPT_CUTGROUP_SEEN) -#define RX_MATCH_TAINTED(prog) ((prog)->reganch & ROPT_TAINTED_SEEN) -#define RX_MATCH_TAINTED_on(prog) ((prog)->reganch |= ROPT_TAINTED_SEEN) -#define RX_MATCH_TAINTED_off(prog) ((prog)->reganch &= ~ROPT_TAINTED_SEEN) +/* 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. + */ + +/* 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 */ +/* these flags are transfered from the PMOP->op_pmflags member during compilation */ +#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; \ + case MULTILINE_PAT_MOD: *(pmfl) |= RXf_PMf_MULTILINE; break; \ + case SINGLE_PAT_MOD: *(pmfl) |= RXf_PMf_SINGLELINE; break; \ + case XTENDED_PAT_MOD: *(pmfl) |= RXf_PMf_EXTENDED; break + +/* chars and strings used as regex pattern modifiers + * Singlular is a 'c'har, plural is a "string" + * + * NOTE, KEEPCOPY was originally 'k', but was changed to 'p' for preserve + * for compatibility reasons with Regexp::Common which highjacked (?k:...) + * for its own uses. So 'k' is out as well. + */ +#define EXEC_PAT_MOD 'e' +#define KEEPCOPY_PAT_MOD 'p' +#define ONCE_PAT_MOD 'o' +#define GLOBAL_PAT_MOD 'g' +#define CONTINUE_PAT_MOD 'c' +#define MULTILINE_PAT_MOD 'm' +#define SINGLE_PAT_MOD 's' +#define IGNORE_PAT_MOD 'i' +#define XTENDED_PAT_MOD 'x' + +#define ONCE_PAT_MODS "o" +#define KEEPCOPY_PAT_MODS "p" +#define EXEC_PAT_MODS "e" +#define LOOP_PAT_MODS "gc" + +#define STD_PAT_MODS "msix" + +#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 + + +/* What we have seen */ +#define RXf_LOOKBEHIND_SEEN 0x00020000 +#define RXf_EVAL_SEEN 0x00040000 +#define RXf_CANY_SEEN 0x00080000 + +/* Special */ +#define RXf_NOSCAN 0x00100000 +#define RXf_CHECK_ALL 0x00200000 + +/* UTF8 related */ +#define RXf_UTF8 0x00400000 +#define RXf_MATCH_UTF8 0x00800000 + +/* 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 (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 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 RX_MATCH_TAINTED_set(prog, t) ((t) \ ? RX_MATCH_TAINTED_on(prog) \ : RX_MATCH_TAINTED_off(prog)) -#define RX_MATCH_COPIED(prog) ((prog)->reganch & ROPT_COPY_DONE) -#define RX_MATCH_COPIED_on(prog) ((prog)->reganch |= ROPT_COPY_DONE) -#define RX_MATCH_COPIED_off(prog) ((prog)->reganch &= ~ROPT_COPY_DONE) +#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 RX_MATCH_COPIED_set(prog,t) ((t) \ ? RX_MATCH_COPIED_on(prog) \ : RX_MATCH_COPIED_off(prog)) @@ -143,10 +236,6 @@ typedef struct regexp_engine { /* Stuff that needs to be included in the plugable extension goes below here */ -#define RE_DEBUG_BIT 0x20000000 -#define RX_DEBUG(prog) ((prog)->reganch & RE_DEBUG_BIT) -#define RX_DEBUG_on(prog) ((prog)->reganch |= RE_DEBUG_BIT) - #ifdef PERL_OLD_COPY_ON_WRITE #define RX_MATCH_COPY_FREE(rx) \ STMT_START {if (rx->saved_copy) { \ @@ -164,9 +253,9 @@ typedef struct regexp_engine { }} STMT_END #endif -#define RX_MATCH_UTF8(prog) ((prog)->reganch & ROPT_MATCH_UTF8) -#define RX_MATCH_UTF8_on(prog) ((prog)->reganch |= ROPT_MATCH_UTF8) -#define RX_MATCH_UTF8_off(prog) ((prog)->reganch &= ~ROPT_MATCH_UTF8) +#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 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))) @@ -188,8 +277,6 @@ typedef struct regexp_engine { #define FBMrf_MULTILINE 1 -struct re_scream_pos_data_s; - /* an accepting state/position*/ struct _reg_trie_accepted { U8 *endpos; @@ -212,7 +299,9 @@ typedef struct { /* structures for holding and saving the state maintained by regmatch() */ -#define MAX_RECURSE_EVAL_NOCHANGE_DEPTH 50 +#ifndef MAX_RECURSE_EVAL_NOCHANGE_DEPTH +#define MAX_RECURSE_EVAL_NOCHANGE_DEPTH 1000 +#endif typedef I32 CHECKPOINT; @@ -229,16 +318,41 @@ typedef struct regmatch_state { struct regmatch_state *prev_yes_state; } yes; - struct { + /* branchlike members */ + /* this is a fake union member that matches the first elements + * of each member that needs to behave like a branch */ + struct { /* this first element must match u.yes */ struct regmatch_state *prev_yes_state; - reg_trie_accepted *accept_buff; + U32 lastparen; + CHECKPOINT cp; + + } branchlike; + + struct { + /* the first elements must match u.branchlike */ + struct regmatch_state *prev_yes_state; + U32 lastparen; + CHECKPOINT cp; + + regnode *next_branch; /* next branch node */ + } branch; + + struct { + /* the first elements must match u.branchlike */ + struct regmatch_state *prev_yes_state; + U32 lastparen; + CHECKPOINT cp; + + reg_trie_accepted *accept_buff; /* accepting states we have seen */ U32 accepted; /* how many accepting states we have seen */ U16 *jump; /* positive offsets from me */ regnode *B; /* node following the trie */ regnode *me; /* Which node am I - needed for jump tries*/ } trie; + /* special types - these members are used to store state for special + regops like eval, if/then, lookaround and the markpoint state */ struct { /* this first element must match u.yes */ struct regmatch_state *prev_yes_state; @@ -257,6 +371,28 @@ typedef struct regmatch_state { struct { /* this first element must match u.yes */ struct regmatch_state *prev_yes_state; + I32 wanted; + I32 logical; /* saved copy of 'logical' var */ + regnode *me; /* the IFMATCH/SUSPEND/UNLESSM node */ + } ifmatch; /* and SUSPEND/UNLESSM */ + + struct { + /* this first element must match u.yes */ + struct regmatch_state *prev_yes_state; + struct regmatch_state *prev_mark; + SV* mark_name; + char *mark_loc; + } mark; + + struct { + int val; + } keeper; + + /* quantifiers - these members are used for storing state for + for the regops used to implement quantifiers */ + struct { + /* this first element must match u.yes */ + struct regmatch_state *prev_yes_state; struct regmatch_state *prev_curlyx; /* previous cur_curlyx */ CHECKPOINT cp; /* remember current savestack index */ bool minmod; @@ -284,14 +420,6 @@ typedef struct regmatch_state { struct { /* this first element must match u.yes */ struct regmatch_state *prev_yes_state; - U32 lastparen; - regnode *next_branch; /* next branch node */ - CHECKPOINT cp; - } branch; - - struct { - /* this first element must match u.yes */ - struct regmatch_state *prev_yes_state; I32 c1, c2; /* case fold search */ CHECKPOINT cp; I32 alen; /* length of first-matched A string */ @@ -312,21 +440,6 @@ typedef struct regmatch_state { regnode *A, *B; /* the nodes corresponding to /A*B/ */ } curly; /* and CURLYN/PLUS/STAR */ - struct { - /* this first element must match u.yes */ - struct regmatch_state *prev_yes_state; - I32 wanted; - I32 logical; /* saved copy of 'logical' var */ - regnode *me; /* the IFMATCH/SUSPEND/UNLESSM node */ - } ifmatch; /* and SUSPEND/UNLESSM */ - - struct { - /* this first element must match u.yes */ - struct regmatch_state *prev_yes_state; - struct regmatch_state *prev_mark; - SV* mark_name; - char *mark_loc; - } mark; } u; } regmatch_state; @@ -400,6 +513,7 @@ struct re_save_state { #define SAVESTACK_ALLOC_FOR_RE_SAVE_STATE \ (1 + ((sizeof(struct re_save_state) - 1) / sizeof(*PL_savestack))) + /* * Local variables: * c-indentation-style: bsd