* 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;
struct regexp_engine;
-typedef struct regexp_paren_ofs {
- I32 *startp;
- I32 *endp;
-} regexp_paren_ofs;
+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
#define SV_SAVED_COPY SV *saved_copy; /* If non-NULL, SV which is COW from original */
#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 {
- /* Generic details */
- const struct regexp_engine* engine; /* what created this regexp? */
- I32 refcnt; /* Refcount of this regexp */
-
- /* The original string as passed to the compilation routine */
- char *precomp; /* pre-compilation regular expression */
- I32 prelen; /* length of precomp */
-
- /* Used for generic optimisations by the perl core.
- All engines are expected to provide this information. */
+ /* 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 */
- U32 nparens; /* number of capture buffers */
- HV *paren_names; /* Optional hash of paren names */
- struct reg_substr_data *substrs; /* substring data about strings that must appear
+ 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 */
- /* Data about the last/current match. Used by the core and therefore
- must be populated by all engines. */
+ /* 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 */
- I32 *startp; /* Array of offsets from start of string (@-) */
- I32 *endp; /* Array of offsets from start of string (@+) */
-
SV_SAVED_COPY /* If non-NULL, SV which is COW from original */
- U32 lastparen; /* last open paren matched */
- U32 lastcloseparen; /* last close paren matched */
-
- /* Perl Regex Engine specific data. Other engines shouldn't need
- to touch this. Should be refactored out into a different structure
- and accessed via the *pprivate field. (except intflags) */
- U32 intflags; /* Internal flags */
- void *pprivate; /* Data private to the regex engine which
- created this object. Perl will never mess with
- this member at all. */
+
+
+ /* Information about the match that isn't often used */
+ char *precomp; /* pre-compilation regular expression */
+ I32 prelen; /* length of precomp */
+ 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;
-
-typedef struct regexp_internal {
- regexp_paren_ofs *swap; /* Swap copy of *startp / *endp */
- U32 *offsets; /* offset annotations 20001228 MJD
- data about mapping the program to the
- string*/
- regnode *regstclass; /* Optional startclass as identified or constructed
- by the optimiser */
- struct reg_data *data; /* Additional miscellaneous data used by the program.
- Used to make it easier to clone and free arbitrary
- data that the regops need. Often the ARG field of
- a regop is an index into this structure */
- regnode program[1]; /* Unwarranted chumminess with compiler. */
-} regexp_internal;
-
-#define RXi_SET(x,y) (x)->pprivate = (void*)(y)
-#define RXi_GET(x) ((regexp_internal *)((x)->pprivate))
-#define RXi_GET_DECL(r,ri) regexp_internal *ri = RXi_GET(r)
-
+/* 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,
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);
#ifdef USE_ITHREADS
- regexp* (*dupe) (pTHX_ const regexp *r, CLONE_PARAMS *param);
+ void* (*dupe) (pTHX_ const regexp *r, CLONE_PARAMS *param);
#endif
} regexp_engine;
-/*
- * Flags stored in regexp->intflags
- * These are used only internally to the regexp engine
- */
-#define PREGf_SKIP 0x00000001
-#define PREGf_IMPLICIT 0x00000002 /* Converted .* to ^.* */
-#define PREGf_NAUGHTY 0x00000004 /* how exponential is this pattern? */
-#define PREGf_VERBARG_SEEN 0x00000008
-#define PREGf_CUTGROUP_SEEN 0x00000010
-
-
/* Flags stored in regexp->extflags
* These are used by code external to the regexp engine
*/
projects / p5sagit/p5-mst-13.2.git / blobdiff