*/
/*
- * "A fair jaw-cracker dwarf-language must be." --Samwise Gamgee
+ * 'A fair jaw-cracker dwarf-language must be.' --Samwise Gamgee
+ *
+ * [p.285 of _The Lord of the Rings_, II/iii: "The Ring Goes South"]
*/
/* This file contains functions for compiling a regular expression. See
**** Alterations to Henry's code are...
****
**** Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999,
- **** 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007 by Larry Wall and others
+ **** 2000, 2001, 2002, 2003, 2004, 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.
I32 orig_utf8; /* whether the pattern was originally in utf8 */
/* XXX use this for future optimisation of case
* where pattern must be upgraded to utf8. */
- HV *charnames; /* cache of named sequences */
HV *paren_names; /* Paren names */
regnode **recurse; /* Recurse regops */
#define RExC_seen_evals (pRExC_state->seen_evals)
#define RExC_utf8 (pRExC_state->utf8)
#define RExC_orig_utf8 (pRExC_state->orig_utf8)
-#define RExC_charnames (pRExC_state->charnames)
#define RExC_open_parens (pRExC_state->open_parens)
#define RExC_close_parens (pRExC_state->close_parens)
#define RExC_opend (pRExC_state->opend)
(int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
-#define vWARN(loc,m) STMT_START { \
+#define ckWARNreg(loc,m) STMT_START { \
const IV offset = loc - RExC_precomp; \
- Perl_warner(aTHX_ packWARN(WARN_REGEXP), "%s" REPORT_LOCATION, \
- m, (int)offset, RExC_precomp, RExC_precomp + offset); \
+ Perl_ck_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
+ (int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
-#define vWARNdep(loc,m) STMT_START { \
+#define ckWARNregdep(loc,m) STMT_START { \
const IV offset = loc - RExC_precomp; \
- Perl_warner(aTHX_ packWARN2(WARN_DEPRECATED, WARN_REGEXP), \
- "%s" REPORT_LOCATION, \
- m, (int)offset, RExC_precomp, RExC_precomp + offset); \
+ Perl_ck_warner_d(aTHX_ packWARN2(WARN_DEPRECATED, WARN_REGEXP), \
+ m REPORT_LOCATION, \
+ (int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
-
-#define vWARN2(loc, m, a1) STMT_START { \
+#define ckWARN2reg(loc, m, a1) STMT_START { \
const IV offset = loc - RExC_precomp; \
- Perl_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
+ Perl_ck_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
a1, (int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
a1, a2, (int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
+#define ckWARN3reg(loc, m, a1, a2) STMT_START { \
+ const IV offset = loc - RExC_precomp; \
+ Perl_ck_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
+ a1, a2, (int)offset, RExC_precomp, RExC_precomp + offset); \
+} STMT_END
+
#define vWARN4(loc, m, a1, a2, a3) STMT_START { \
const IV offset = loc - RExC_precomp; \
Perl_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
a1, a2, a3, (int)offset, RExC_precomp, RExC_precomp + offset); \
} STMT_END
+#define ckWARN4reg(loc, m, a1, a2, a3) STMT_START { \
+ const IV offset = loc - RExC_precomp; \
+ Perl_ck_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
+ a1, a2, a3, (int)offset, RExC_precomp, RExC_precomp + offset); \
+} STMT_END
+
#define vWARN5(loc, m, a1, a2, a3, a4) STMT_START { \
const IV offset = loc - RExC_precomp; \
Perl_warner(aTHX_ packWARN(WARN_REGEXP), m REPORT_LOCATION, \
if ( folder )
TRIE_BITMAP_SET(trie, folder[ *ch ]);
DEBUG_OPTIMISE_r(
- PerlIO_printf(Perl_debug_log, (char*)ch)
+ PerlIO_printf(Perl_debug_log, "%s", (char*)ch)
);
}
}
}
} else {
/*
- Currently we assume that the trie can handle unicode and ascii
- matches fold cased matches. If this proves true then the following
- define will prevent tries in this situation.
-
- #define TRIE_TYPE_IS_SAFE (UTF || optype==EXACT)
-*/
+ Currently we do not believe that the trie logic can
+ handle case insensitive matching properly when the
+ pattern is not unicode (thus forcing unicode semantics).
+
+ If/when this is fixed the following define can be swapped
+ in below to fully enable trie logic.
+
#define TRIE_TYPE_IS_SAFE 1
+
+*/
+#define TRIE_TYPE_IS_SAFE (UTF || optype==EXACT)
+
if ( last && TRIE_TYPE_IS_SAFE ) {
make_trie( pRExC_state,
startbranch, first, cur, tail, count,
(next_is_eval || !(mincount == 0 && maxcount == 1))
&& (minnext == 0) && (deltanext == 0)
&& data && !(data->flags & (SF_HAS_PAR|SF_IN_PAR))
- && maxcount <= REG_INFTY/3 /* Complement check for big count */
- && ckWARN(WARN_REGEXP))
+ && maxcount <= REG_INFTY/3) /* Complement check for big count */
{
- vWARN(RExC_parse,
- "Quantifier unexpected on zero-length expression");
+ ckWARNreg(RExC_parse,
+ "Quantifier unexpected on zero-length expression");
}
min += minnext * mincount;
data->whilem_c = data_fake.whilem_c;
}
if (f & SCF_DO_STCLASS_AND) {
- const int was = (data->start_class->flags & ANYOF_EOS);
-
- cl_and(data->start_class, &intrnl);
- if (was)
- data->start_class->flags |= ANYOF_EOS;
+ if (flags & SCF_DO_STCLASS_OR) {
+ /* OR before, AND after: ideally we would recurse with
+ * data_fake to get the AND applied by study of the
+ * remainder of the pattern, and then derecurse;
+ * *** HACK *** for now just treat as "no information".
+ * See [perl #56690].
+ */
+ cl_init(pRExC_state, data->start_class);
+ } else {
+ /* AND before and after: combine and continue */
+ const int was = (data->start_class->flags & ANYOF_EOS);
+
+ cl_and(data->start_class, &intrnl);
+ if (was)
+ data->start_class->flags |= ANYOF_EOS;
+ }
}
}
#if PERL_ENABLE_POSITIVE_ASSERTION_STUDY
#ifndef PERL_IN_XSUB_RE
REGEXP *
-Perl_pregcomp(pTHX_ const SV * const pattern, const U32 flags)
+Perl_pregcomp(pTHX_ SV * const pattern, const U32 flags)
{
dVAR;
HV * const table = GvHV(PL_hintgv);
#endif
REGEXP *
-Perl_re_compile(pTHX_ const SV * const pattern, U32 pm_flags)
+Perl_re_compile(pTHX_ SV * const pattern, U32 pm_flags)
{
dVAR;
REGEXP *rx;
struct regexp *r;
register regexp_internal *ri;
STRLEN plen;
- char* exp = SvPV((SV*)pattern, plen);
+ char *exp = SvPV(pattern, plen);
char* xend = exp + plen;
regnode *scan;
I32 flags;
RExC_size = 0L;
RExC_emit = &PL_regdummy;
RExC_whilem_seen = 0;
- RExC_charnames = NULL;
RExC_open_parens = NULL;
RExC_close_parens = NULL;
RExC_opend = NULL;
+ (sizeof(STD_PAT_MODS) - 1)
+ (sizeof("(?:)") - 1);
- p = sv_grow((SV *)rx, wraplen + 1);
+ p = sv_grow(MUTABLE_SV(rx), wraplen + 1);
SvCUR_set(rx, wraplen);
SvPOK_on(rx);
SvFLAGS(rx) |= SvUTF8(pattern);
if (RExC_seen & REG_SEEN_CUTGROUP)
r->intflags |= PREGf_CUTGROUP_SEEN;
if (RExC_paren_names)
- RXp_PAREN_NAMES(r) = (HV*)SvREFCNT_inc(RExC_paren_names);
+ RXp_PAREN_NAMES(r) = MUTABLE_HV(SvREFCNT_inc(RExC_paren_names));
else
RXp_PAREN_NAMES(r) = NULL;
if (flags & RXapif_FETCH) {
return reg_named_buff_fetch(rx, key, flags);
} else if (flags & (RXapif_STORE | RXapif_DELETE | RXapif_CLEAR)) {
- Perl_croak(aTHX_ PL_no_modify);
+ Perl_croak(aTHX_ "%s", PL_no_modify);
return NULL;
} else if (flags & RXapif_EXISTS) {
return reg_named_buff_exists(rx, key, flags)
} else {
ret = newSVsv(&PL_sv_undef);
}
- if (retarray) {
- SvREFCNT_inc_simple_void(ret);
+ if (retarray)
av_push(retarray, ret);
- }
}
if (retarray)
- return newRV((SV*)retarray);
+ return newRV_noinc(MUTABLE_SV(retarray));
}
}
return NULL;
return newSViv(HvTOTALKEYS(RXp_PAREN_NAMES(rx)));
} else if (flags & RXapif_ONE) {
ret = CALLREG_NAMED_BUFF_ALL(r, (flags | RXapif_REGNAMES));
- av = (AV*)SvRV(ret);
+ av = MUTABLE_AV(SvRV(ret));
length = av_len(av);
+ SvREFCNT_dec(ret);
return newSViv(length + 1);
} else {
Perl_croak(aTHX_ "panic: Unknown flags %d in named_buff_scalar", (int)flags);
}
}
- return newRV((SV*)av);
+ return newRV_noinc(MUTABLE_SV(av));
}
void
PERL_UNUSED_ARG(value);
if (!PL_localizing)
- Perl_croak(aTHX_ PL_no_modify);
+ Perl_croak(aTHX_ "%s", PL_no_modify);
}
I32
goto getlen;
} else {
if (ckWARN(WARN_UNINITIALIZED))
- report_uninit((SV*)sv);
+ report_uninit((const SV *)sv);
return 0;
}
}
"panic: reg_scan_name returned NULL");
if (!RExC_paren_names) {
RExC_paren_names= newHV();
- sv_2mortal((SV*)RExC_paren_names);
+ sv_2mortal(MUTABLE_SV(RExC_paren_names));
#ifdef DEBUGGING
RExC_paren_name_list= newAV();
- sv_2mortal((SV*)RExC_paren_name_list);
+ sv_2mortal(MUTABLE_SV(RExC_paren_name_list));
#endif
}
he_str = hv_fetch_ent( RExC_paren_names, svname, 1, 0 );
pv = (I32*)SvGROW(sv_dat, SvCUR(sv_dat) + sizeof(I32)+1);
SvCUR_set(sv_dat, SvCUR(sv_dat) + sizeof(I32));
pv[count] = RExC_npar;
-#ifdef PERL_DEBUG_COW
- ((XPVIV*) SvANY(sv_dat))->xiv_iv++;
-#else
- SvIVX(sv_dat)++;
-#endif
+ SvIV_set(sv_dat, SvIVX(sv_dat) + 1);
}
} else {
(void)SvUPGRADE(sv_dat,SVt_PVNV);
break;
case KEEPCOPY_PAT_MOD: /* 'p' */
if (flagsp == &negflags) {
- if (SIZE_ONLY && ckWARN(WARN_REGEXP))
- vWARN(RExC_parse + 1,"Useless use of (?-p)");
+ if (SIZE_ONLY)
+ ckWARNreg(RExC_parse + 1,"Useless use of (?-p)");
} else {
*flagsp |= RXf_PMf_KEEPCOPY;
}
/* Pick up the branches, linking them together. */
parse_start = RExC_parse; /* MJD */
br = regbranch(pRExC_state, &flags, 1,depth+1);
+
+ if (freeze_paren) {
+ if (RExC_npar > after_freeze)
+ after_freeze = RExC_npar;
+ RExC_npar = freeze_paren;
+ }
+
/* branch_len = (paren != 0); */
if (br == NULL)
*flagp = WORST;
if (max > 0)
*flagp |= HASWIDTH;
- if (max && max < min)
+ if (max < min)
vFAIL("Can't do {n,m} with n > m");
if (!SIZE_ONLY) {
ARG1_SET(ret, (U16)min);
goto do_curly;
}
nest_check:
- if (!SIZE_ONLY && !(flags&(HASWIDTH|POSTPONED)) && max > REG_INFTY/3 && ckWARN(WARN_REGEXP)) {
- vWARN3(RExC_parse,
- "%.*s matches null string many times",
- (int)(RExC_parse >= origparse ? RExC_parse - origparse : 0),
- origparse);
+ if (!SIZE_ONLY && !(flags&(HASWIDTH|POSTPONED)) && max > REG_INFTY/3) {
+ ckWARN3reg(RExC_parse,
+ "%.*s matches null string many times",
+ (int)(RExC_parse >= origparse ? RExC_parse - origparse : 0),
+ origparse);
}
if (RExC_parse < RExC_end && *RExC_parse == '?') {
/* reg_namedseq(pRExC_state,UVp)
This is expected to be called by a parser routine that has
- recognized'\N' and needs to handle the rest. RExC_parse is
+ recognized '\N' and needs to handle the rest. RExC_parse is
expected to point at the first char following the N at the time
of the call.
+
+ The \N may be inside (indicated by valuep not being NULL) or outside a
+ character class.
+
+ \N may begin either a named sequence, or if outside a character class, mean
+ to match a non-newline. For non single-quoted regexes, the tokenizer has
+ attempted to decide which, and in the case of a named sequence converted it
+ into one of the forms: \N{} (if the sequence is null), or \N{U+c1.c2...},
+ where c1... are the characters in the sequence. For single-quoted regexes,
+ the tokenizer passes the \N sequence through unchanged; this code will not
+ attempt to determine this nor expand those. The net effect is that if the
+ beginning of the passed-in pattern isn't '{U+' or there is no '}', it
+ signals that this \N occurrence means to match a non-newline.
+
+ Only the \N{U+...} form should occur in a character class, for the same
+ reason that '.' inside a character class means to just match a period: it
+ just doesn't make sense.
If valuep is non-null then it is assumed that we are parsing inside
of a charclass definition and the first codepoint in the resolved
string is returned via *valuep and the routine will return NULL.
In this mode if a multichar string is returned from the charnames
- handler a warning will be issued, and only the first char in the
+ handler, a warning will be issued, and only the first char in the
sequence will be examined. If the string returned is zero length
then the value of *valuep is undefined and NON-NULL will
be returned to indicate failure. (This will NOT be a valid pointer
to a regnode.)
- If value is null then it is assumed that we are parsing normal text
- and inserts a new EXACT node into the program containing the resolved
- string and returns a pointer to the new node. If the string is
- zerolength a NOTHING node is emitted.
-
+ If valuep is null then it is assumed that we are parsing normal text and a
+ new EXACT node is inserted into the program containing the resolved string,
+ and a pointer to the new node is returned. But if the string is zero length
+ a NOTHING node is emitted instead.
+
On success RExC_parse is set to the char following the endbrace.
- Parsing failures will generate a fatal errorvia vFAIL(...)
-
- NOTE: We cache all results from the charnames handler locally in
- the RExC_charnames hash (created on first use) to prevent a charnames
- handler from playing silly-buggers and returning a short string and
- then a long string for a given pattern. Since the regexp program
- size is calculated during an initial parse this would result
- in a buffer overrun so we cache to prevent the charname result from
- changing during the course of the parse.
-
+ Parsing failures will generate a fatal error via vFAIL(...)
*/
STATIC regnode *
-S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep)
+S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep, I32 *flagp)
{
- char * name; /* start of the content of the name */
- char * endbrace; /* endbrace following the name */
- SV *sv_str = NULL;
- SV *sv_name = NULL;
- STRLEN len; /* this has various purposes throughout the code */
- bool cached = 0; /* if this is true then we shouldn't refcount dev sv_str */
+ char * endbrace; /* '}' following the name */
regnode *ret = NULL;
+#ifdef DEBUGGING
+ char* parse_start = RExC_parse - 2; /* points to the '\N' */
+#endif
+ char* p;
+
+ GET_RE_DEBUG_FLAGS_DECL;
PERL_ARGS_ASSERT_REG_NAMEDSEQ;
+
+ GET_RE_DEBUG_FLAGS;
+
+ /* The [^\n] meaning of \N ignores spaces and comments under the /x
+ * modifier. The other meaning does not */
+ p = (RExC_flags & RXf_PMf_EXTENDED)
+ ? regwhite( pRExC_state, RExC_parse )
+ : RExC_parse;
+ /* Disambiguate between \N meaning a named character versus \N meaning
+ * [^\n]. The former is assumed when it can't be the latter. */
+ if (*p != '{' || regcurly(p)) {
+ RExC_parse = p;
+ if (valuep) {
+ /* no bare \N in a charclass */
+ vFAIL("\\N in a character class must be a named character: \\N{...}");
+ }
+ nextchar(pRExC_state);
+ ret = reg_node(pRExC_state, REG_ANY);
+ *flagp |= HASWIDTH|SIMPLE;
+ RExC_naughty++;
+ RExC_parse--;
+ Set_Node_Length(ret, 1); /* MJD */
+ return ret;
+ }
+
+ /* Here, we have decided it should be a named sequence */
+
+ /* The test above made sure that the next real character is a '{', but
+ * under the /x modifier, it could be separated by space (or a comment and
+ * \n) and this is not allowed (for consistency with \x{...} and the
+ * tokenizer handling of \N{NAME}). */
if (*RExC_parse != '{') {
- vFAIL("Missing braces on \\N{}");
+ vFAIL("Missing braces on \\N{}");
}
- name = RExC_parse+1;
- endbrace = strchr(RExC_parse, '}');
- if ( ! endbrace ) {
- RExC_parse++;
- vFAIL("Missing right brace on \\N{}");
- }
- RExC_parse = endbrace + 1;
-
-
- /* RExC_parse points at the beginning brace,
- endbrace points at the last */
- if ( name[0]=='U' && name[1]=='+' ) {
- /* its a "Unicode hex" notation {U+89AB} */
- I32 fl = PERL_SCAN_ALLOW_UNDERSCORES
- | PERL_SCAN_DISALLOW_PREFIX
- | (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0);
- UV cp;
- char string;
- len = (STRLEN)(endbrace - name - 2);
- cp = grok_hex(name + 2, &len, &fl, NULL);
- if ( len != (STRLEN)(endbrace - name - 2) ) {
- cp = 0xFFFD;
- }
- if (cp > 0xff)
- RExC_utf8 = 1;
- if ( valuep ) {
- *valuep = cp;
- return NULL;
- }
- string = (char)cp;
- sv_str= newSVpvn(&string, 1);
- } else {
- /* fetch the charnames handler for this scope */
- HV * const table = GvHV(PL_hintgv);
- SV **cvp= table ?
- hv_fetchs(table, "charnames", FALSE) :
- NULL;
- SV *cv= cvp ? *cvp : NULL;
- HE *he_str;
- int count;
- /* create an SV with the name as argument */
- sv_name = newSVpvn(name, endbrace - name);
-
- if (!table || !(PL_hints & HINT_LOCALIZE_HH)) {
- vFAIL2("Constant(\\N{%s}) unknown: "
- "(possibly a missing \"use charnames ...\")",
- SvPVX(sv_name));
- }
- if (!cvp || !SvOK(*cvp)) { /* when $^H{charnames} = undef; */
- vFAIL2("Constant(\\N{%s}): "
- "$^H{charnames} is not defined",SvPVX(sv_name));
- }
-
-
-
- if (!RExC_charnames) {
- /* make sure our cache is allocated */
- RExC_charnames = newHV();
- sv_2mortal((SV*)RExC_charnames);
- }
- /* see if we have looked this one up before */
- he_str = hv_fetch_ent( RExC_charnames, sv_name, 0, 0 );
- if ( he_str ) {
- sv_str = HeVAL(he_str);
- cached = 1;
- } else {
- dSP ;
- ENTER ;
- SAVETMPS ;
- PUSHMARK(SP) ;
-
- XPUSHs(sv_name);
-
- PUTBACK ;
-
- count= call_sv(cv, G_SCALAR);
-
- if (count == 1) { /* XXXX is this right? dmq */
- sv_str = POPs;
- SvREFCNT_inc_simple_void(sv_str);
- }
-
- SPAGAIN ;
- PUTBACK ;
- FREETMPS ;
- LEAVE ;
-
- if ( !sv_str || !SvOK(sv_str) ) {
- vFAIL2("Constant(\\N{%s}): Call to &{$^H{charnames}} "
- "did not return a defined value",SvPVX(sv_name));
- }
- if (hv_store_ent( RExC_charnames, sv_name, sv_str, 0))
- cached = 1;
- }
+ RExC_parse++; /* Skip past the '{' */
+
+ if (! (endbrace = strchr(RExC_parse, '}')) /* no trailing brace */
+ || ! (endbrace == RExC_parse /* nothing between the {} */
+ || (endbrace - RExC_parse >= 2 /* U+ (bad hex is checked below */
+ && strnEQ(RExC_parse, "U+", 2)))) /* for a better error msg) */
+ {
+ if (endbrace) RExC_parse = endbrace; /* position msg's '<--HERE' */
+ vFAIL("\\N{NAME} must be resolved by the lexer");
}
- if (valuep) {
- char *p = SvPV(sv_str, len);
- if (len) {
- STRLEN numlen = 1;
- if ( SvUTF8(sv_str) ) {
- *valuep = utf8_to_uvchr((U8*)p, &numlen);
- if (*valuep > 0x7F)
- RExC_utf8 = 1;
- /* XXXX
- We have to turn on utf8 for high bit chars otherwise
- we get failures with
-
- "ss" =~ /[\N{LATIN SMALL LETTER SHARP S}]/i
- "SS" =~ /[\N{LATIN SMALL LETTER SHARP S}]/i
-
- This is different from what \x{} would do with the same
- codepoint, where the condition is > 0xFF.
- - dmq
- */
-
-
- } else {
- *valuep = (UV)*p;
- /* warn if we havent used the whole string? */
- }
- if (numlen<len && SIZE_ONLY && ckWARN(WARN_REGEXP)) {
- vWARN2(RExC_parse,
- "Ignoring excess chars from \\N{%s} in character class",
- SvPVX(sv_name)
- );
- }
- } else if (SIZE_ONLY && ckWARN(WARN_REGEXP)) {
- vWARN2(RExC_parse,
- "Ignoring zero length \\N{%s} in character class",
- SvPVX(sv_name)
- );
- }
- if (sv_name)
- SvREFCNT_dec(sv_name);
- if (!cached)
- SvREFCNT_dec(sv_str);
- return len ? NULL : (regnode *)&len;
- } else if(SvCUR(sv_str)) {
-
- char *s;
- char *p, *pend;
- STRLEN charlen = 1;
-#ifdef DEBUGGING
- char * parse_start = name-3; /* needed for the offsets */
-#endif
- GET_RE_DEBUG_FLAGS_DECL; /* needed for the offsets */
-
- ret = reg_node(pRExC_state,
- (U8)(FOLD ? (LOC ? EXACTFL : EXACTF) : EXACT));
- s= STRING(ret);
-
- if ( RExC_utf8 && !SvUTF8(sv_str) ) {
- sv_utf8_upgrade(sv_str);
- } else if ( !RExC_utf8 && SvUTF8(sv_str) ) {
- RExC_utf8= 1;
- }
-
- p = SvPV(sv_str, len);
- pend = p + len;
- /* len is the length written, charlen is the size the char read */
- for ( len = 0; p < pend; p += charlen ) {
- if (UTF) {
- UV uvc = utf8_to_uvchr((U8*)p, &charlen);
- if (FOLD) {
- STRLEN foldlen,numlen;
- U8 tmpbuf[UTF8_MAXBYTES_CASE+1], *foldbuf;
- uvc = toFOLD_uni(uvc, tmpbuf, &foldlen);
- /* Emit all the Unicode characters. */
-
- for (foldbuf = tmpbuf;
- foldlen;
- foldlen -= numlen)
- {
- uvc = utf8_to_uvchr(foldbuf, &numlen);
- if (numlen > 0) {
- const STRLEN unilen = reguni(pRExC_state, uvc, s);
- s += unilen;
- len += unilen;
- /* In EBCDIC the numlen
- * and unilen can differ. */
- foldbuf += numlen;
- if (numlen >= foldlen)
- break;
- }
- else
- break; /* "Can't happen." */
- }
- } else {
- const STRLEN unilen = reguni(pRExC_state, uvc, s);
- if (unilen > 0) {
- s += unilen;
- len += unilen;
- }
- }
- } else {
- len++;
- REGC(*p, s++);
- }
- }
- if (SIZE_ONLY) {
- RExC_size += STR_SZ(len);
- } else {
- STR_LEN(ret) = len;
- RExC_emit += STR_SZ(len);
- }
- Set_Node_Cur_Length(ret); /* MJD */
- RExC_parse--;
- nextchar(pRExC_state);
- } else {
- ret = reg_node(pRExC_state,NOTHING);
+
+ if (endbrace == RExC_parse) { /* empty: \N{} */
+ if (! valuep) {
+ RExC_parse = endbrace + 1;
+ return reg_node(pRExC_state,NOTHING);
+ }
+
+ if (SIZE_ONLY) {
+ ckWARNreg(RExC_parse,
+ "Ignoring zero length \\N{} in character class"
+ );
+ RExC_parse = endbrace + 1;
+ }
+ *valuep = 0;
+ return (regnode *) &RExC_parse; /* Invalid regnode pointer */
}
- if (!cached) {
- SvREFCNT_dec(sv_str);
+
+ RExC_utf8 = 1; /* named sequences imply Unicode semantics */
+ RExC_parse += 2; /* Skip past the 'U+' */
+
+ if (valuep) { /* In a bracketed char class */
+ /* We only pay attention to the first char of
+ multichar strings being returned. I kinda wonder
+ if this makes sense as it does change the behaviour
+ from earlier versions, OTOH that behaviour was broken
+ as well. XXX Solution is to recharacterize as
+ [rest-of-class]|multi1|multi2... */
+
+ STRLEN length_of_hex;
+ I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
+ | PERL_SCAN_DISALLOW_PREFIX
+ | (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0);
+
+ char * endchar = strchr(RExC_parse, '.');
+ if (endchar) {
+ ckWARNreg(endchar, "Using just the first character returned by \\N{} in character class");
+ }
+ else endchar = endbrace;
+
+ length_of_hex = (STRLEN)(endchar - RExC_parse);
+ *valuep = grok_hex(RExC_parse, &length_of_hex, &flags, NULL);
+
+ /* The tokenizer should have guaranteed validity, but it's possible to
+ * bypass it by using single quoting, so check */
+ if (length_of_hex == 0
+ || length_of_hex != (STRLEN)(endchar - RExC_parse) )
+ {
+ RExC_parse += length_of_hex; /* Includes all the valid */
+ RExC_parse += (RExC_orig_utf8) /* point to after 1st invalid */
+ ? UTF8SKIP(RExC_parse)
+ : 1;
+ /* Guard against malformed utf8 */
+ if (RExC_parse >= endchar) RExC_parse = endchar;
+ vFAIL("Invalid hexadecimal number in \\N{U+...}");
+ }
+
+ RExC_parse = endbrace + 1;
+ if (endchar == endbrace) return NULL;
+
+ ret = (regnode *) &RExC_parse; /* Invalid regnode pointer */
}
- if (sv_name) {
- SvREFCNT_dec(sv_name);
+ else { /* Not a char class */
+ char *s; /* String to put in generated EXACT node */
+ STRLEN len = 0; /* Its current length */
+ char *endchar; /* Points to '.' or '}' ending cur char in the input
+ stream */
+
+ ret = reg_node(pRExC_state,
+ (U8)(FOLD ? (LOC ? EXACTFL : EXACTF) : EXACT));
+ s= STRING(ret);
+
+ /* Exact nodes can hold only a U8 length's of text = 255. Loop through
+ * the input which is of the form now 'c1.c2.c3...}' until find the
+ * ending brace or exeed length 255. The characters that exceed this
+ * limit are dropped. The limit could be relaxed should it become
+ * desirable by reparsing this as (?:\N{NAME}), so could generate
+ * multiple EXACT nodes, as is done for just regular input. But this
+ * is primarily a named character, and not intended to be a huge long
+ * string, so 255 bytes should be good enough */
+ while (1) {
+ STRLEN length_of_hex;
+ I32 grok_flags = PERL_SCAN_ALLOW_UNDERSCORES
+ | PERL_SCAN_DISALLOW_PREFIX
+ | (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0);
+ UV cp; /* Ord of current character */
+
+ /* Code points are separated by dots. If none, there is only one
+ * code point, and is terminated by the brace */
+ endchar = strchr(RExC_parse, '.');
+ if (! endchar) endchar = endbrace;
+
+ /* The values are Unicode even on EBCDIC machines */
+ length_of_hex = (STRLEN)(endchar - RExC_parse);
+ cp = grok_hex(RExC_parse, &length_of_hex, &grok_flags, NULL);
+ if ( length_of_hex == 0
+ || length_of_hex != (STRLEN)(endchar - RExC_parse) )
+ {
+ RExC_parse += length_of_hex; /* Includes all the valid */
+ RExC_parse += (RExC_orig_utf8) /* point to after 1st invalid */
+ ? UTF8SKIP(RExC_parse)
+ : 1;
+ /* Guard against malformed utf8 */
+ if (RExC_parse >= endchar) RExC_parse = endchar;
+ vFAIL("Invalid hexadecimal number in \\N{U+...}");
+ }
+
+ if (! FOLD) { /* Not folding, just append to the string */
+ STRLEN unilen;
+
+ /* Quit before adding this character if would exceed limit */
+ if (len + UNISKIP(cp) > U8_MAX) break;
+
+ unilen = reguni(pRExC_state, cp, s);
+ if (unilen > 0) {
+ s += unilen;
+ len += unilen;
+ }
+ } else { /* Folding, output the folded equivalent */
+ STRLEN foldlen,numlen;
+ U8 tmpbuf[UTF8_MAXBYTES_CASE+1], *foldbuf;
+ cp = toFOLD_uni(cp, tmpbuf, &foldlen);
+
+ /* Quit before exceeding size limit */
+ if (len + foldlen > U8_MAX) break;
+
+ for (foldbuf = tmpbuf;
+ foldlen;
+ foldlen -= numlen)
+ {
+ cp = utf8_to_uvchr(foldbuf, &numlen);
+ if (numlen > 0) {
+ const STRLEN unilen = reguni(pRExC_state, cp, s);
+ s += unilen;
+ len += unilen;
+ /* In EBCDIC the numlen and unilen can differ. */
+ foldbuf += numlen;
+ if (numlen >= foldlen)
+ break;
+ }
+ else
+ break; /* "Can't happen." */
+ }
+ }
+
+ /* Point to the beginning of the next character in the sequence. */
+ RExC_parse = endchar + 1;
+
+ /* Quit if no more characters */
+ if (RExC_parse >= endbrace) break;
+ }
+
+
+ if (SIZE_ONLY) {
+ if (RExC_parse < endbrace) {
+ ckWARNreg(RExC_parse - 1,
+ "Using just the first characters returned by \\N{}");
+ }
+
+ RExC_size += STR_SZ(len);
+ } else {
+ STR_LEN(ret) = len;
+ RExC_emit += STR_SZ(len);
+ }
+
+ RExC_parse = endbrace + 1;
+
+ *flagp |= HASWIDTH; /* Not SIMPLE, as that causes the engine to fail
+ with malformed in t/re/pat_advanced.t */
+ RExC_parse --;
+ Set_Node_Cur_Length(ret); /* MJD */
+ nextchar(pRExC_state);
}
- return ret;
+ return ret;
}
}
break;
case 'N':
- /* Handle \N{NAME} here and not below because it can be
+ /* Handle \N and \N{NAME} here and not below because it can be
multicharacter. join_exact() will join them up later on.
Also this makes sure that things like /\N{BLAH}+/ and
\N{BLAH} being multi char Just Happen. dmq*/
++RExC_parse;
- ret= reg_namedseq(pRExC_state, NULL);
+ ret= reg_namedseq(pRExC_state, NULL, flagp);
break;
case 'k': /* Handle \k<NAME> and \k'NAME' */
parse_named_seq:
I32 flags = 0;
STRLEN numlen = 3;
ender = grok_oct(p, &numlen, &flags, NULL);
+
+ /* An octal above 0xff is interpreted differently
+ * depending on if the re is in utf8 or not. If it
+ * is in utf8, the value will be itself, otherwise
+ * it is interpreted as modulo 0x100. It has been
+ * decided to discourage the use of octal above the
+ * single-byte range. For now, warn only when
+ * it ends up modulo */
+ if (SIZE_ONLY && ender >= 0x100
+ && ! UTF && ! PL_encoding) {
+ ckWARNregdep(p, "Use of octal value above 377 is deprecated");
+ }
p += numlen;
}
else {
{
SV* enc = PL_encoding;
ender = reg_recode((const char)(U8)ender, &enc);
- if (!enc && SIZE_ONLY && ckWARN(WARN_REGEXP))
- vWARN(p, "Invalid escape in the specified encoding");
+ if (!enc && SIZE_ONLY)
+ ckWARNreg(p, "Invalid escape in the specified encoding");
RExC_utf8 = 1;
}
break;
FAIL("Trailing \\");
/* FALL THROUGH */
default:
- if (!SIZE_ONLY&& isALPHA(*p) && ckWARN(WARN_REGEXP))
- vWARN2(p + 1, "Unrecognized escape \\%c passed through", UCHARAT(p));
+ if (!SIZE_ONLY&& isALPHA(*p))
+ ckWARN2reg(p + 1, "Unrecognized escape \\%c passed through", UCHARAT(p));
goto normal_default;
}
break;
while (isALNUM(*s))
s++;
if (*s && c == *s && s[1] == ']') {
- if (ckWARN(WARN_REGEXP))
- vWARN3(s+2,
- "POSIX syntax [%c %c] belongs inside character classes",
- c, c);
+ ckWARN3reg(s+2,
+ "POSIX syntax [%c %c] belongs inside character classes",
+ c, c);
/* [[=foo=]] and [[.foo.]] are still future. */
if (POSIXCC_NOTYET(c)) {
what = WORD; \
break
+/*
+ We dont use PERL_LEGACY_UNICODE_CHARCLASS_MAPPINGS as the direct test
+ so that it is possible to override the option here without having to
+ rebuild the entire core. as we are required to do if we change regcomp.h
+ which is where PERL_LEGACY_UNICODE_CHARCLASS_MAPPINGS is defined.
+*/
+#if PERL_LEGACY_UNICODE_CHARCLASS_MAPPINGS
+#define BROKEN_UNICODE_CHARCLASS_MAPPINGS
+#endif
+
+#ifdef BROKEN_UNICODE_CHARCLASS_MAPPINGS
+#define POSIX_CC_UNI_NAME(CCNAME) CCNAME
+#else
+#define POSIX_CC_UNI_NAME(CCNAME) "Posix" CCNAME
+#endif
+
/*
parse a class specification and produce either an ANYOF node that
matches the pattern or if the pattern matches a single char only and
from earlier versions, OTOH that behaviour was broken
as well. */
UV v; /* value is register so we cant & it /grrr */
- if (reg_namedseq(pRExC_state, &v)) {
+ if (reg_namedseq(pRExC_state, &v, NULL)) {
goto parseit;
}
value= v;
{
SV* enc = PL_encoding;
value = reg_recode((const char)(U8)value, &enc);
- if (!enc && SIZE_ONLY && ckWARN(WARN_REGEXP))
- vWARN(RExC_parse,
- "Invalid escape in the specified encoding");
+ if (!enc && SIZE_ONLY)
+ ckWARNreg(RExC_parse,
+ "Invalid escape in the specified encoding");
break;
}
default:
- if (!SIZE_ONLY && isALPHA(value) && ckWARN(WARN_REGEXP))
- vWARN2(RExC_parse,
- "Unrecognized escape \\%c in character class passed through",
- (int)value);
+ if (!SIZE_ONLY && isALPHA(value))
+ ckWARN2reg(RExC_parse,
+ "Unrecognized escape \\%c in character class passed through",
+ (int)value);
break;
}
} /* end of \blah */
/* a bad range like a-\d, a-[:digit:] ? */
if (range) {
if (!SIZE_ONLY) {
- if (ckWARN(WARN_REGEXP)) {
- const int w =
- RExC_parse >= rangebegin ?
- RExC_parse - rangebegin : 0;
- vWARN4(RExC_parse,
+ const int w =
+ RExC_parse >= rangebegin ?
+ RExC_parse - rangebegin : 0;
+ ckWARN4reg(RExC_parse,
"False [] range \"%*.*s\"",
w, w, rangebegin);
- }
+
if (prevvalue < 256) {
ANYOF_BITMAP_SET(ret, prevvalue);
ANYOF_BITMAP_SET(ret, '-');
* A similar issue a little earlier when switching on value.
* --jhi */
switch ((I32)namedclass) {
+
+ case _C_C_T_(ALNUMC, isALNUMC(value), POSIX_CC_UNI_NAME("Alnum"));
+ case _C_C_T_(ALPHA, isALPHA(value), POSIX_CC_UNI_NAME("Alpha"));
+ case _C_C_T_(BLANK, isBLANK(value), POSIX_CC_UNI_NAME("Blank"));
+ case _C_C_T_(CNTRL, isCNTRL(value), POSIX_CC_UNI_NAME("Cntrl"));
+ case _C_C_T_(GRAPH, isGRAPH(value), POSIX_CC_UNI_NAME("Graph"));
+ case _C_C_T_(LOWER, isLOWER(value), POSIX_CC_UNI_NAME("Lower"));
+ case _C_C_T_(PRINT, isPRINT(value), POSIX_CC_UNI_NAME("Print"));
+ case _C_C_T_(PSXSPC, isPSXSPC(value), POSIX_CC_UNI_NAME("Space"));
+ case _C_C_T_(PUNCT, isPUNCT(value), POSIX_CC_UNI_NAME("Punct"));
+ case _C_C_T_(UPPER, isUPPER(value), POSIX_CC_UNI_NAME("Upper"));
+#ifdef BROKEN_UNICODE_CHARCLASS_MAPPINGS
case _C_C_T_(ALNUM, isALNUM(value), "Word");
- case _C_C_T_(ALNUMC, isALNUMC(value), "Alnum");
- case _C_C_T_(ALPHA, isALPHA(value), "Alpha");
- case _C_C_T_(BLANK, isBLANK(value), "Blank");
- case _C_C_T_(CNTRL, isCNTRL(value), "Cntrl");
- case _C_C_T_(GRAPH, isGRAPH(value), "Graph");
- case _C_C_T_(LOWER, isLOWER(value), "Lower");
- case _C_C_T_(PRINT, isPRINT(value), "Print");
- case _C_C_T_(PSXSPC, isPSXSPC(value), "Space");
- case _C_C_T_(PUNCT, isPUNCT(value), "Punct");
case _C_C_T_(SPACE, isSPACE(value), "SpacePerl");
- case _C_C_T_(UPPER, isUPPER(value), "Upper");
+#else
+ case _C_C_T_(SPACE, isSPACE(value), "PerlSpace");
+ case _C_C_T_(ALNUM, isALNUM(value), "PerlWord");
+#endif
case _C_C_T_(XDIGIT, isXDIGIT(value), "XDigit");
case _C_C_T_NOLOC_(VERTWS, is_VERTWS_latin1(&value), "VertSpace");
case _C_C_T_NOLOC_(HORIZWS, is_HORIZWS_latin1(&value), "HorizSpace");
ANYOF_BITMAP_SET(ret, value);
}
yesno = '+';
- what = "Digit";
+ what = POSIX_CC_UNI_NAME("Digit");
break;
case ANYOF_NDIGIT:
if (LOC)
ANYOF_BITMAP_SET(ret, value);
}
yesno = '!';
- what = "Digit";
+ what = POSIX_CC_UNI_NAME("Digit");
break;
case ANYOF_MAX:
/* this is to handle \p and \P */
*STRING(ret)= (char)value;
STR_LEN(ret)= 1;
RExC_emit += STR_SZ(1);
+ SvREFCNT_dec(listsv);
return ret;
}
/* optimize case-insensitive simple patterns (e.g. /[a-z]/i) */
* used later (regexec.c:S_reginclass()). */
av_store(av, 0, listsv);
av_store(av, 1, NULL);
- av_store(av, 2, (SV*)unicode_alternate);
- rv = newRV_noinc((SV*)av);
+ av_store(av, 2, MUTABLE_SV(unicode_alternate));
+ rv = newRV_noinc(MUTABLE_SV(av));
n = add_data(pRExC_state, 1, "s");
RExC_rxi->data->data[n] = (void*)rv;
ARG_SET(ret, n);
/*
- regcurly - a little FSA that accepts {\d+,?\d*}
*/
-STATIC I32
-S_regcurly(register const char *s)
+#ifndef PERL_IN_XSUB_RE
+I32
+Perl_regcurly(register const char *s)
{
PERL_ARGS_ASSERT_REGCURLY;
return FALSE;
return TRUE;
}
-
+#endif
/*
- regdump - dump a regexp onto Perl_debug_log in vaguely comprehensible form
*/
#ifdef DEBUGGING
-void
+static void
S_regdump_extflags(pTHX_ const char *lead, const U32 flags)
{
int bit;
/*
- regprop - printable representation of opcode
*/
+#define EMIT_ANYOF_TEST_SEPARATOR(do_sep,sv,flags) \
+STMT_START { \
+ if (do_sep) { \
+ Perl_sv_catpvf(aTHX_ sv,"%s][%s",PL_colors[1],PL_colors[0]); \
+ if (flags & ANYOF_INVERT) \
+ /*make sure the invert info is in each */ \
+ sv_catpvs(sv, "^"); \
+ do_sep = 0; \
+ } \
+} STMT_END
+
void
Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o)
{
PERL_ARGS_ASSERT_REGPROP;
- sv_setpvn(sv, "", 0);
+ sv_setpvs(sv, "");
if (OP(o) > REGNODE_MAX) /* regnode.type is unsigned */
/* It would be nice to FAIL() here, but this may be called from
Perl_sv_catpvf(aTHX_ sv, "%d", (int)ARG(o)); /* Parenth number */
if ( RXp_PAREN_NAMES(prog) ) {
if ( k != REF || OP(o) < NREF) {
- AV *list= (AV *)progi->data->data[progi->name_list_idx];
+ AV *list= MUTABLE_AV(progi->data->data[progi->name_list_idx]);
SV **name= av_fetch(list, ARG(o), 0 );
if (name)
Perl_sv_catpvf(aTHX_ sv, " '%"SVf"'", SVfARG(*name));
}
else {
- AV *list= (AV *)progi->data->data[ progi->name_list_idx ];
- SV *sv_dat=(SV*)progi->data->data[ ARG( o ) ];
+ AV *list= MUTABLE_AV(progi->data->data[ progi->name_list_idx ]);
+ SV *sv_dat= MUTABLE_SV(progi->data->data[ ARG( o ) ]);
I32 *nums=(I32*)SvPVX(sv_dat);
SV **name= av_fetch(list, nums[0], 0 );
I32 n;
else if (k == VERB) {
if (!o->flags)
Perl_sv_catpvf(aTHX_ sv, ":%"SVf,
- SVfARG((SV*)progi->data->data[ ARG( o ) ]));
+ SVfARG((MUTABLE_SV(progi->data->data[ ARG( o ) ]))));
} else if (k == LOGICAL)
Perl_sv_catpvf(aTHX_ sv, "[%d]", o->flags); /* 2: embedded, otherwise 1 */
else if (k == FOLDCHAR)
else if (k == ANYOF) {
int i, rangestart = -1;
const U8 flags = ANYOF_FLAGS(o);
+ int do_sep = 0;
/* Should be synchronized with * ANYOF_ #xdefines in regcomp.h */
static const char * const anyofs[] = {
"[:^alpha:]",
"[:ascii:]",
"[:^ascii:]",
- "[:ctrl:]",
- "[:^ctrl:]",
+ "[:cntrl:]",
+ "[:^cntrl:]",
"[:graph:]",
"[:^graph:]",
"[:lower:]",
Perl_sv_catpvf(aTHX_ sv, "[%s", PL_colors[0]);
if (flags & ANYOF_INVERT)
sv_catpvs(sv, "^");
+
+ /* output what the standard cp 0-255 bitmap matches */
for (i = 0; i <= 256; i++) {
if (i < 256 && ANYOF_BITMAP_TEST(o,i)) {
if (rangestart == -1)
sv_catpvs(sv, "-");
put_byte(sv, i - 1);
}
+ do_sep = 1;
rangestart = -1;
}
}
-
+
+ EMIT_ANYOF_TEST_SEPARATOR(do_sep,sv,flags);
+ /* output any special charclass tests (used mostly under use locale) */
if (o->flags & ANYOF_CLASS)
for (i = 0; i < (int)(sizeof(anyofs)/sizeof(char*)); i++)
- if (ANYOF_CLASS_TEST(o,i))
+ if (ANYOF_CLASS_TEST(o,i)) {
sv_catpv(sv, anyofs[i]);
-
+ do_sep = 1;
+ }
+
+ EMIT_ANYOF_TEST_SEPARATOR(do_sep,sv,flags);
+
+ /* output information about the unicode matching */
if (flags & ANYOF_UNICODE)
sv_catpvs(sv, "{unicode}");
else if (flags & ANYOF_UNICODE_ALL)
if (lv) {
if (sw) {
U8 s[UTF8_MAXBYTES_CASE+1];
-
+
for (i = 0; i <= 256; i++) { /* just the first 256 */
uvchr_to_utf8(s, i);
ReREFCNT_dec(r->mother_re);
} else {
CALLREGFREE_PVT(rx); /* free the private data */
- if (RXp_PAREN_NAMES(r))
- SvREFCNT_dec(RXp_PAREN_NAMES(r));
+ SvREFCNT_dec(RXp_PAREN_NAMES(r));
}
if (r->substrs) {
- if (r->anchored_substr)
- SvREFCNT_dec(r->anchored_substr);
- if (r->anchored_utf8)
- SvREFCNT_dec(r->anchored_utf8);
- if (r->float_substr)
- SvREFCNT_dec(r->float_substr);
- if (r->float_utf8)
- SvREFCNT_dec(r->float_utf8);
+ SvREFCNT_dec(r->anchored_substr);
+ SvREFCNT_dec(r->anchored_utf8);
+ SvREFCNT_dec(r->float_substr);
+ SvREFCNT_dec(r->float_utf8);
Safefree(r->substrs);
}
RX_MATCH_COPY_FREE(rx);
#ifdef PERL_OLD_COPY_ON_WRITE
- if (r->saved_copy)
- SvREFCNT_dec(r->saved_copy);
+ SvREFCNT_dec(r->saved_copy);
#endif
- Safefree(r->swap);
Safefree(r->offs);
}
REGEXP *
-Perl_reg_temp_copy (pTHX_ REGEXP *rx)
+Perl_reg_temp_copy (pTHX_ REGEXP *ret_x, REGEXP *rx)
{
- REGEXP *ret_x = (REGEXP*) newSV_type(SVt_REGEXP);
- struct regexp *ret = (struct regexp *)SvANY(ret_x);
+ struct regexp *ret;
struct regexp *const r = (struct regexp *)SvANY(rx);
register const I32 npar = r->nparens+1;
PERL_ARGS_ASSERT_REG_TEMP_COPY;
+ if (!ret_x)
+ ret_x = (REGEXP*) newSV_type(SVt_REGEXP);
+ ret = (struct regexp *)SvANY(ret_x);
+
(void)ReREFCNT_inc(rx);
/* We can take advantage of the existing "copied buffer" mechanism in SVs
by pointing directly at the buffer, but flagging that the allocated
a case of zero-ing that, rather than copying the current length. */
SvPV_set(ret_x, RX_WRAPPED(rx));
SvFLAGS(ret_x) |= SvFLAGS(rx) & (SVf_POK|SVp_POK|SVf_UTF8);
- StructCopy(&(r->xpv_cur), &(ret->xpv_cur), struct regexp_allocated);
+ memcpy(&(ret->xpv_cur), &(r->xpv_cur),
+ sizeof(regexp) - STRUCT_OFFSET(regexp, xpv_cur));
SvLEN_set(ret_x, 0);
+ SvSTASH_set(ret_x, NULL);
+ SvMAGIC_set(ret_x, NULL);
Newx(ret->offs, npar, regexp_paren_pair);
Copy(r->offs, ret->offs, npar, regexp_paren_pair);
if (r->substrs) {
ret->saved_copy = NULL;
#endif
ret->mother_re = rx;
- ret->swap = NULL;
return ret_x;
}
case 's':
case 'S':
case 'u':
- SvREFCNT_dec((SV*)ri->data->data[n]);
+ SvREFCNT_dec(MUTABLE_SV(ri->data->data[n]));
break;
case 'f':
Safefree(ri->data->data[n]);
break;
case 'p':
- new_comppad = (AV*)ri->data->data[n];
+ new_comppad = MUTABLE_AV(ri->data->data[n]);
break;
case 'o':
if (new_comppad == NULL)
op_free((OP_4tree*)ri->data->data[n]);
PAD_RESTORE_LOCAL(old_comppad);
- SvREFCNT_dec((SV*)new_comppad);
+ SvREFCNT_dec(MUTABLE_SV(new_comppad));
new_comppad = NULL;
break;
case 'n':
}
#define sv_dup_inc(s,t) SvREFCNT_inc(sv_dup(s,t))
-#define av_dup_inc(s,t) (AV*)SvREFCNT_inc(sv_dup((SV*)s,t))
-#define hv_dup_inc(s,t) (HV*)SvREFCNT_inc(sv_dup((SV*)s,t))
+#define av_dup_inc(s,t) MUTABLE_AV(SvREFCNT_inc(sv_dup((const SV *)s,t)))
+#define hv_dup_inc(s,t) MUTABLE_HV(SvREFCNT_inc(sv_dup((const SV *)s,t)))
#define SAVEPVN(p,n) ((p) ? savepvn(p,n) : NULL)
/*
ret->saved_copy = NULL;
#endif
- ret->mother_re = NULL;
+ if (ret->mother_re) {
+ if (SvPVX_const(dstr) == SvPVX_const(ret->mother_re)) {
+ /* Our storage points directly to our mother regexp, but that's
+ 1: a buffer in a different thread
+ 2: something we no longer hold a reference on
+ so we need to copy it locally. */
+ /* Note we need to sue SvCUR() on our mother_re, because it, in
+ turn, may well be pointing to its own mother_re. */
+ SvPV_set(dstr, SAVEPVN(SvPVX_const(ret->mother_re),
+ SvCUR(ret->mother_re)+1));
+ SvLEN_set(dstr, SvCUR(ret->mother_re)+1);
+ }
+ ret->mother_re = NULL;
+ }
ret->gofs = 0;
}
#endif /* PERL_IN_XSUB_RE */
npar = r->nparens+1;
len = ProgLen(ri);
- Newxc(reti, sizeof(regexp_internal) + (len+1)*sizeof(regnode), char, regexp_internal);
+ Newxc(reti, sizeof(regexp_internal) + len*sizeof(regnode), char, regexp_internal);
Copy(ri->program, reti->program, len+1, regnode);
case 'S':
case 'p': /* actually an AV, but the dup function is identical. */
case 'u': /* actually an HV, but the dup function is identical. */
- d->data[i] = sv_dup_inc((SV *)ri->data->data[i], param);
+ d->data[i] = sv_dup_inc((const SV *)ri->data->data[i], param);
break;
case 'f':
/* This is cheating. */
const reg_trie_data * const trie =
(reg_trie_data*)ri->data->data[op<AHOCORASICK ? n : ac->trie];
#ifdef DEBUGGING
- AV *const trie_words = (AV *) ri->data->data[n + TRIE_WORDS_OFFSET];
+ AV *const trie_words = MUTABLE_AV(ri->data->data[n + TRIE_WORDS_OFFSET]);
#endif
const regnode *nextbranch= NULL;
I32 word_idx;
- sv_setpvn(sv, "", 0);
+ sv_setpvs(sv, "");
for (word_idx= 0; word_idx < (I32)trie->wordcount; word_idx++) {
SV ** const elem_ptr = av_fetch(trie_words,word_idx,0);