X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=regexp.h;h=27f17e71c940f86c40d91b7f6631ca763dd28a89;hb=88307081960aa9b8190f0fe9acb8906b2372e7ec;hp=0bf886bf2ed38c077f6af282a24c058e7d58034d;hpb=bcdf74043c1fd4b60b7764f5cd7d87525cf77e74;p=p5sagit%2Fp5-mst-13.2.git diff --git a/regexp.h b/regexp.h index 0bf886b..27f17e7 100644 --- a/regexp.h +++ b/regexp.h @@ -31,6 +31,7 @@ struct reg_substr_data; struct reg_data; struct regexp_engine; +struct regexp; struct reg_substr_datum { I32 min_offset; @@ -48,11 +49,27 @@ struct reg_substr_data { #else #define SV_SAVED_COPY #endif -/* this is ordered such that the most commonly used - fields are at the start of the struct */ + +typedef struct regexp_paren_pair { + I32 start; + I32 end; +} regexp_paren_pair; + +/* + 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. +*/ + 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 */ @@ -71,17 +88,19 @@ typedef struct regexp { /* 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 (@+) */ + 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 */ + I32 sublen; /* Length of string pointed by subbeg */ /* Information about the match that isn't often used */ - char *precomp; /* pre-compilation regular expression */ I32 prelen; /* length of precomp */ + const char *precomp; /* pre-compilation regular expression */ + /* 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 */ @@ -102,20 +121,101 @@ 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); + REGEXP* (*comp) (pTHX_ const SV * const pattern, const 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; +/* + 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 * @@ -137,6 +237,7 @@ typedef struct regexp_engine { #define RXf_ANCH_SINGLE (RXf_ANCH_SBOL|RXf_ANCH_GPOS) /* Flags indicating special patterns */ +#define RXf_SKIPWHITE 0x00000100 /* Pattern is for a split / / */ #define RXf_START_ONLY 0x00000200 /* Pattern is /^/ */ #define RXf_WHITE 0x00000400 /* Pattern is /\s+/ */ @@ -146,7 +247,7 @@ typedef struct regexp_engine { #define RXf_PMf_SINGLELINE 0x00002000 /* /s */ #define RXf_PMf_FOLD 0x00004000 /* /i */ #define RXf_PMf_EXTENDED 0x00008000 /* /x */ -#define RXf_PMf_KEEPCOPY 0x00010000 /* /k */ +#define RXf_PMf_KEEPCOPY 0x00010000 /* /p */ /* 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) @@ -159,9 +260,13 @@ typedef struct regexp_engine { /* 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 'k' +#define KEEPCOPY_PAT_MOD 'p' #define ONCE_PAT_MOD 'o' #define GLOBAL_PAT_MOD 'g' #define CONTINUE_PAT_MOD 'c' @@ -171,7 +276,7 @@ typedef struct regexp_engine { #define XTENDED_PAT_MOD 'x' #define ONCE_PAT_MODS "o" -#define KEEPCOPY_PAT_MODS "k" +#define KEEPCOPY_PAT_MODS "p" #define EXEC_PAT_MODS "e" #define LOOP_PAT_MODS "gc" @@ -202,13 +307,20 @@ typedef struct regexp_engine { #define RXf_USE_INTUIT_NOML 0x01000000 #define RXf_USE_INTUIT_ML 0x02000000 #define RXf_INTUIT_TAIL 0x04000000 -/* one bit here */ + +/* + 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 0x08000000 + #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_TAINTED 0x80000000 /* this pattern is tainted */ #define RX_HAS_CUTGROUP(prog) ((prog)->intflags & PREGf_CUTGROUP_SEEN) @@ -293,7 +405,9 @@ 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; @@ -310,16 +424,41 @@ 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; @@ -331,20 +470,42 @@ typedef struct regmatch_state { 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 { /* 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 */ + 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 */ @@ -365,14 +526,6 @@ 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 */ @@ -393,25 +546,6 @@ 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; - - struct { - int val; - } keeper; } u; } regmatch_state; @@ -431,8 +565,7 @@ typedef struct regmatch_slab { #define PL_bostr PL_reg_state.re_state_bostr #define PL_reginput PL_reg_state.re_state_reginput #define PL_regeol PL_reg_state.re_state_regeol -#define PL_regstartp PL_reg_state.re_state_regstartp -#define PL_regendp PL_reg_state.re_state_regendp +#define PL_regoffs PL_reg_state.re_state_regoffs #define PL_reglastparen PL_reg_state.re_state_reglastparen #define PL_reglastcloseparen PL_reg_state.re_state_reglastcloseparen #define PL_reg_start_tmp PL_reg_state.re_state_reg_start_tmp @@ -455,28 +588,27 @@ 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. */ - I32 *re_state_regstartp; /* Pointer to startp array. */ - I32 *re_state_regendp; /* Ditto for endp. */ + regexp_paren_pair *re_state_regoffs; /* Pointer to start/end pairs */ 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 */