#define HOP3(pos,off,lim) (PL_reg_match_utf8 ? reghop3((U8*)(pos), off, (U8*)(lim)) : (U8*)(pos + off))
#define HOP3c(pos,off,lim) ((char*)HOP3(pos,off,lim))
+
+#define NEXTCHR_EOS -10 /* nextchr has fallen off the end */
+#define NEXTCHR_IS_EOS (nextchr < 0)
+
+#define SET_nextchr \
+ nextchr = ((locinput < PL_regeol) ? UCHARAT(locinput) : NEXTCHR_EOS)
+
+#define SET_locinput(p) \
+ locinput = (p); \
+ SET_nextchr
+
+
/* these are unrolled below in the CCC_TRY_XXX defined */
#define LOAD_UTF8_CHARCLASS(class,str) STMT_START { \
if (!CAT2(PL_utf8_,class)) { \
* fails, or advance to the next character */
#define _CCC_TRY_CODE(POS_OR_NEG, FUNC, UTF8_TEST, CLASS, STR) \
- if (locinput >= PL_regeol) { \
+ if (NEXTCHR_IS_EOS) { \
sayNO; \
} \
if (utf8_target && UTF8_IS_CONTINUED(nextchr)) { \
if (POS_OR_NEG (UTF8_TEST)) { \
sayNO; \
} \
- locinput += PL_utf8skip[nextchr]; \
- nextchr = UCHARAT(locinput); \
- break; \
} \
- if (POS_OR_NEG (FUNC(nextchr))) { \
- sayNO; \
+ else if (POS_OR_NEG (FUNC(nextchr))) { \
+ sayNO; \
} \
- nextchr = UCHARAT(++locinput); \
- break;
+ goto increment_locinput;
/* Handle the non-locale cases for a character class and its complement. It
* calls _CCC_TRY_CODE with a ! to complement the test for the character class.
_CCC_TRY_CODE( PLACEHOLDER, LCFUNC, LCFUNC_utf8((U8*)locinput), \
CLASS, STR) \
case NAMEA: \
- if (locinput >= PL_regeol || ! FUNCA(nextchr)) { \
+ if (NEXTCHR_IS_EOS || ! FUNCA(nextchr)) { \
sayNO; \
} \
/* Matched a utf8-invariant, so don't have to worry about utf8 */ \
- nextchr = UCHARAT(++locinput); \
+ locinput++; \
break; \
case NNAMEA: \
- if (locinput >= PL_regeol || FUNCA(nextchr)) { \
+ if (NEXTCHR_IS_EOS || FUNCA(nextchr)) { \
sayNO; \
} \
- if (utf8_target) { \
- locinput += PL_utf8skip[nextchr]; \
- nextchr = UCHARAT(locinput); \
- } \
- else { \
- nextchr = UCHARAT(++locinput); \
- } \
- break; \
+ goto increment_locinput; \
/* Generate the non-locale cases */ \
_CCC_TRY_NONLOCALE(NAME, NNAME, FUNC, CLASS, STR)
goto fail;
}
- strbeg = (sv && SvPOK(sv)) ? strend - SvCUR(sv) : strpos;
+ /* XXX we need to pass strbeg as a separate arg: the following is
+ * guesswork and can be wrong... */
+ if (sv && SvPOK(sv)) {
+ char * p = SvPVX(sv);
+ STRLEN cur = SvCUR(sv);
+ if (p <= strpos && strpos < p + cur) {
+ strbeg = p;
+ assert(p <= strend && strend <= p + cur);
+ }
+ else
+ strbeg = strend - cur;
+ }
+ else
+ strbeg = strpos;
+
PL_regeol = strend;
if (utf8_target) {
if (!prog->check_utf8 && prog->check_substr)
#define REXEC_FBC_UTF8_SCAN(CoDe) \
STMT_START { \
- while (s + (uskip = UTF8SKIP(s)) <= strend) { \
+ while (s < strend && s + (uskip = UTF8SKIP(s)) <= strend) { \
CoDe \
s += uskip; \
} \
break;
case LNBREAK:
REXEC_FBC_CSCAN(
- is_LNBREAK_utf8(s),
- is_LNBREAK_latin1(s)
+ is_LNBREAK_utf8_safe(s, strend),
+ is_LNBREAK_latin1_safe(s, strend)
);
break;
case VERTWS:
REXEC_FBC_CSCAN(
- is_VERTWS_utf8(s),
- is_VERTWS_latin1(s)
+ is_VERTWS_utf8_safe(s, strend),
+ is_VERTWS_latin1_safe(s, strend)
);
break;
case NVERTWS:
REXEC_FBC_CSCAN(
- !is_VERTWS_utf8(s),
- !is_VERTWS_latin1(s)
+ !is_VERTWS_utf8_safe(s, strend),
+ !is_VERTWS_latin1_safe(s, strend)
);
break;
case HORIZWS:
REXEC_FBC_CSCAN(
- is_HORIZWS_utf8(s),
- is_HORIZWS_latin1(s)
+ is_HORIZWS_utf8_safe(s, strend),
+ is_HORIZWS_latin1_safe(s, strend)
);
break;
case NHORIZWS:
REXEC_FBC_CSCAN(
- !is_HORIZWS_utf8(s),
- !is_HORIZWS_latin1(s)
+ !is_HORIZWS_utf8_safe(s, strend),
+ !is_HORIZWS_latin1_safe(s, strend)
);
break;
case POSIXA:
}
points[pointpos++ % maxlen]= uc;
- REXEC_TRIE_READ_CHAR(trie_type, trie, widecharmap, uc,
+ if (foldlen || uc < (U8*)strend) {
+ REXEC_TRIE_READ_CHAR(trie_type, trie,
+ widecharmap, uc,
uscan, len, uvc, charid, foldlen,
foldbuf, uniflags);
- DEBUG_TRIE_EXECUTE_r({
- dump_exec_pos( (char *)uc, c, strend, real_start,
- s, utf8_target );
- PerlIO_printf(Perl_debug_log,
- " Charid:%3u CP:%4"UVxf" ",
- charid, uvc);
- });
+ DEBUG_TRIE_EXECUTE_r({
+ dump_exec_pos( (char *)uc, c, strend,
+ real_start, s, utf8_target);
+ PerlIO_printf(Perl_debug_log,
+ " Charid:%3u CP:%4"UVxf" ",
+ charid, uvc);
+ });
+ }
+ else {
+ len = 0;
+ charid = 0;
+ }
+
do {
#ifdef DEBUGGING
while (s <= last1) {
if (regtry(®info, &s))
goto got_it;
- s += UTF8SKIP(s);
+ if (s >= last1) {
+ s++; /* to break out of outer loop */
+ break;
+ }
+ s += UTF8SKIP(s);
}
}
else {
Safefree(prog->offs);
prog->offs = swap;
}
-
return 0;
}
regnode *next;
U32 n = 0; /* general value; init to avoid compiler warning */
I32 ln = 0; /* len or last; init to avoid compiler warning */
- char *reginput = startpos;
- char *locinput = reginput;
+ char *locinput = startpos;
char *pushinput; /* where to continue after a PUSH */
I32 nextchr; /* is always set to UCHARAT(locinput) */
U32 state_num;
bool no_final = 0; /* prevent failure from backtracking? */
bool do_cutgroup = 0; /* no_final only until next branch/trie entry */
- char *startpoint = reginput;
+ char *startpoint = locinput;
SV *popmark = NULL; /* are we looking for a mark? */
SV *sv_commit = NULL; /* last mark name seen in failure */
SV *sv_yes_mark = NULL; /* last mark name we have seen
st = PL_regmatch_state = S_push_slab(aTHX);
/* Note that nextchr is a byte even in UTF */
- nextchr = UCHARAT(locinput);
+ SET_nextchr;
scan = prog;
while (scan != NULL) {
reenter_switch:
+ SET_nextchr;
+
switch (state_num) {
- case BOL:
+ case BOL: /* /^../ */
if (locinput == PL_bostr)
{
/* reginfo->till = reginfo->bol; */
break;
}
sayNO;
- case MBOL:
+
+ case MBOL: /* /^../m */
if (locinput == PL_bostr ||
- ((nextchr || locinput < PL_regeol) && locinput[-1] == '\n'))
+ (!NEXTCHR_IS_EOS && locinput[-1] == '\n'))
{
break;
}
sayNO;
- case SBOL:
+
+ case SBOL: /* /^../s */
if (locinput == PL_bostr)
break;
sayNO;
- case GPOS:
+
+ case GPOS: /* \G */
if (locinput == reginfo->ganch)
break;
sayNO;
- case KEEPS:
+ case KEEPS: /* \K */
/* update the startpoint */
st->u.keeper.val = rex->offs[0].start;
- reginput = locinput;
rex->offs[0].start = locinput - PL_bostr;
PUSH_STATE_GOTO(KEEPS_next, next, locinput);
/*NOT-REACHED*/
rex->offs[0].start = st->u.keeper.val;
sayNO_SILENT;
/*NOT-REACHED*/
- case EOL:
+
+ case EOL: /* /..$/ */
goto seol;
- case MEOL:
- if ((nextchr || locinput < PL_regeol) && nextchr != '\n')
+
+ case MEOL: /* /..$/m */
+ if (!NEXTCHR_IS_EOS && nextchr != '\n')
sayNO;
break;
- case SEOL:
+
+ case SEOL: /* /..$/s */
seol:
- if ((nextchr || locinput < PL_regeol) && nextchr != '\n')
+ if (!NEXTCHR_IS_EOS && nextchr != '\n')
sayNO;
if (PL_regeol - locinput > 1)
sayNO;
break;
- case EOS:
- if (PL_regeol != locinput)
+
+ case EOS: /* \z */
+ if (!NEXTCHR_IS_EOS)
sayNO;
break;
- case SANY:
- if (!nextchr && locinput >= PL_regeol)
+
+ case SANY: /* /./s */
+ if (NEXTCHR_IS_EOS)
sayNO;
- if (utf8_target) {
- locinput += PL_utf8skip[nextchr];
- if (locinput > PL_regeol)
- sayNO;
- nextchr = UCHARAT(locinput);
- }
- else
- nextchr = UCHARAT(++locinput);
- break;
- case CANY:
- if (!nextchr && locinput >= PL_regeol)
+ goto increment_locinput;
+
+ case CANY: /* \C */
+ if (NEXTCHR_IS_EOS)
sayNO;
- nextchr = UCHARAT(++locinput);
+ locinput++;
break;
- case REG_ANY:
- if ((!nextchr && locinput >= PL_regeol) || nextchr == '\n')
+
+ case REG_ANY: /* /./ */
+ if ((NEXTCHR_IS_EOS) || nextchr == '\n')
sayNO;
- if (utf8_target) {
- locinput += PL_utf8skip[nextchr];
- if (locinput > PL_regeol)
- sayNO;
- nextchr = UCHARAT(locinput);
- }
- else
- nextchr = UCHARAT(++locinput);
- break;
+ goto increment_locinput;
+
#undef ST
#define ST st->u.trie
- case TRIEC:
+ case TRIEC: /* (ab|cd) with known charclass */
/* In this case the charclass data is available inline so
we can fail fast without a lot of extra overhead.
*/
- if(!ANYOF_BITMAP_TEST(scan, *locinput)) {
+ if(!NEXTCHR_IS_EOS && !ANYOF_BITMAP_TEST(scan, nextchr)) {
DEBUG_EXECUTE_r(
PerlIO_printf(Perl_debug_log,
"%*s %sfailed to match trie start class...%s\n",
assert(0); /* NOTREACHED */
}
/* FALL THROUGH */
- case TRIE:
+ case TRIE: /* (ab|cd) */
/* the basic plan of execution of the trie is:
* At the beginning, run though all the states, and
* find the longest-matching word. Also remember the position
* ab|a|x|abcd|abc
* when matched against the string "abcde", will generate
* accept states for all words except 3, with the longest
- * matching word being 4, and the shortest being 1 (with
+ * matching word being 4, and the shortest being 2 (with
* the position being after char 1 of the string).
*
* Then for each matching word, in word order (i.e. 1,2,4,5),
HV * widecharmap = MUTABLE_HV(rexi->data->data[ ARG( scan ) + 1 ]);
U32 state = trie->startstate;
- if (trie->bitmap && !TRIE_BITMAP_TEST(trie,*locinput) ) {
+ if ( trie->bitmap
+ && (NEXTCHR_IS_EOS || !TRIE_BITMAP_TEST(trie, nextchr)))
+ {
if (trie->states[ state ].wordnum) {
DEBUG_EXECUTE_r(
PerlIO_printf(Perl_debug_log,
});
/* read a char and goto next state */
- if ( base ) {
+ if ( base && (foldlen || uc < (U8*)PL_regeol)) {
I32 offset;
REXEC_TRIE_READ_CHAR(trie_type, trie, widecharmap, uc,
uscan, len, uvc, charid, foldlen,
});
locinput = (char*)uc;
- nextchr = UCHARAT(locinput);
continue; /* execute rest of RE */
assert(0); /* NOTREACHED */
}
#undef ST
- case EXACT: {
+ case EXACT: { /* /abc/ */
char *s = STRING(scan);
ln = STR_LEN(scan);
if (utf8_target != UTF_PATTERN) {
const char * const e = s + ln;
if (utf8_target) {
- /* The target is utf8, the pattern is not utf8. */
+ /* The target is utf8, the pattern is not utf8.
+ * Above-Latin1 code points can't match the pattern;
+ * invariants match exactly, and the other Latin1 ones need
+ * to be downgraded to a single byte in order to do the
+ * comparison. (If we could be confident that the target
+ * is not malformed, this could be refactored to have fewer
+ * tests by just assuming that if the first bytes match, it
+ * is an invariant, but there are tests in the test suite
+ * dealing with (??{...}) which violate this) */
while (s < e) {
- STRLEN ulen;
if (l >= PL_regeol)
sayNO;
- if (NATIVE_TO_UNI(*(U8*)s) !=
- utf8n_to_uvuni((U8*)l, UTF8_MAXBYTES, &ulen,
- uniflags))
- sayNO;
- l += ulen;
- s ++;
+ if (UTF8_IS_ABOVE_LATIN1(* (U8*) l)) {
+ sayNO;
+ }
+ if (UTF8_IS_INVARIANT(*(U8*)l)) {
+ if (*l != *s) {
+ sayNO;
+ }
+ l++;
+ }
+ else {
+ if (TWO_BYTE_UTF8_TO_UNI(*l, *(l+1)) != * (U8*) s) {
+ sayNO;
+ }
+ l += 2;
+ }
+ s++;
}
}
else {
/* The target is not utf8, the pattern is utf8. */
while (s < e) {
- STRLEN ulen;
- if (l >= PL_regeol)
- sayNO;
- if (NATIVE_TO_UNI(*((U8*)l)) !=
- utf8n_to_uvuni((U8*)s, UTF8_MAXBYTES, &ulen,
- uniflags))
- sayNO;
- s += ulen;
- l ++;
+ if (l >= PL_regeol || UTF8_IS_ABOVE_LATIN1(* (U8*) s))
+ {
+ sayNO;
+ }
+ if (UTF8_IS_INVARIANT(*(U8*)s)) {
+ if (*s != *l) {
+ sayNO;
+ }
+ s++;
+ }
+ else {
+ if (TWO_BYTE_UTF8_TO_UNI(*s, *(s+1)) != * (U8*) l) {
+ sayNO;
+ }
+ s += 2;
+ }
+ l++;
}
}
locinput = l;
- nextchr = UCHARAT(locinput);
break;
}
/* The target and the pattern have the same utf8ness. */
if (ln > 1 && memNE(s, locinput, ln))
sayNO;
locinput += ln;
- nextchr = UCHARAT(locinput);
break;
}
- case EXACTFL: {
+
+ case EXACTFL: { /* /abc/il */
re_fold_t folder;
const U8 * fold_array;
const char * s;
fold_utf8_flags = FOLDEQ_UTF8_LOCALE;
goto do_exactf;
- case EXACTFU_SS:
- case EXACTFU_TRICKYFOLD:
- case EXACTFU:
+ case EXACTFU_SS: /* /\x{df}/iu */
+ case EXACTFU_TRICKYFOLD: /* /\x{390}/iu */
+ case EXACTFU: /* /abc/iu */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
fold_utf8_flags = (UTF_PATTERN) ? FOLDEQ_S1_ALREADY_FOLDED : 0;
goto do_exactf;
- case EXACTFA:
+ case EXACTFA: /* /abc/iaa */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
fold_utf8_flags = FOLDEQ_UTF8_NOMIX_ASCII;
goto do_exactf;
- case EXACTF:
+ case EXACTF: /* /abc/i */
folder = foldEQ;
fold_array = PL_fold;
fold_utf8_flags = 0;
sayNO;
}
locinput = e;
- nextchr = UCHARAT(locinput);
break;
}
if (ln > 1 && ! folder(s, locinput, ln))
sayNO;
locinput += ln;
- nextchr = UCHARAT(locinput);
break;
}
/* XXX Could improve efficiency by separating these all out using a
* macro or in-line function. At that point regcomp.c would no longer
* have to set the FLAGS fields of these */
- case BOUNDL:
- case NBOUNDL:
+ case BOUNDL: /* /\b/l */
+ case NBOUNDL: /* /\B/l */
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
- case BOUND:
- case BOUNDU:
- case BOUNDA:
- case NBOUND:
- case NBOUNDU:
- case NBOUNDA:
+ case BOUND: /* /\b/ */
+ case BOUNDU: /* /\b/u */
+ case BOUNDA: /* /\b/a */
+ case NBOUND: /* /\B/ */
+ case NBOUNDU: /* /\B/u */
+ case NBOUNDA: /* /\B/a */
/* was last char in word? */
if (utf8_target
&& FLAGS(scan) != REGEX_ASCII_RESTRICTED_CHARSET
}
if (FLAGS(scan) != REGEX_LOCALE_CHARSET) {
ln = isALNUM_uni(ln);
- LOAD_UTF8_CHARCLASS_ALNUM();
- n = swash_fetch(PL_utf8_alnum, (U8*)locinput, utf8_target);
+ if (NEXTCHR_IS_EOS)
+ n = 0;
+ else {
+ LOAD_UTF8_CHARCLASS_ALNUM();
+ n = swash_fetch(PL_utf8_alnum, (U8*)locinput,
+ utf8_target);
+ }
}
else {
ln = isALNUM_LC_uvchr(UNI_TO_NATIVE(ln));
- n = isALNUM_LC_utf8((U8*)locinput);
+ n = NEXTCHR_IS_EOS ? 0 : isALNUM_LC_utf8((U8*)locinput);
}
}
else {
switch (FLAGS(scan)) {
case REGEX_UNICODE_CHARSET:
ln = isWORDCHAR_L1(ln);
- n = isWORDCHAR_L1(nextchr);
+ n = NEXTCHR_IS_EOS ? 0 : isWORDCHAR_L1(nextchr);
break;
case REGEX_LOCALE_CHARSET:
ln = isALNUM_LC(ln);
- n = isALNUM_LC(nextchr);
+ n = NEXTCHR_IS_EOS ? 0 : isALNUM_LC(nextchr);
break;
case REGEX_DEPENDS_CHARSET:
ln = isALNUM(ln);
- n = isALNUM(nextchr);
+ n = NEXTCHR_IS_EOS ? 0 : isALNUM(nextchr);
break;
case REGEX_ASCII_RESTRICTED_CHARSET:
case REGEX_ASCII_MORE_RESTRICTED_CHARSET:
ln = isWORDCHAR_A(ln);
- n = isWORDCHAR_A(nextchr);
+ n = NEXTCHR_IS_EOS ? 0 : isWORDCHAR_A(nextchr);
break;
default:
Perl_croak(aTHX_ "panic: Unexpected FLAGS %u in op %u", FLAGS(scan), OP(scan));
if (((!ln) == (!n)) == (OP(scan) < NBOUND))
sayNO;
break;
- case ANYOFV:
- case ANYOF:
+
+ case ANYOFV: /* /[abx{df}]/i */
+ case ANYOF: /* /[abc]/ */
+ if (NEXTCHR_IS_EOS)
+ sayNO;
if (utf8_target || state_num == ANYOFV) {
STRLEN inclasslen = PL_regeol - locinput;
- if (locinput >= PL_regeol)
- sayNO;
-
if (!reginclass(rex, scan, (U8*)locinput, &inclasslen, utf8_target))
sayNO;
locinput += inclasslen;
- nextchr = UCHARAT(locinput);
break;
}
else {
- if (nextchr < 0)
- nextchr = UCHARAT(locinput);
- if (!nextchr && locinput >= PL_regeol)
- sayNO;
if (!REGINCLASS(rex, scan, (U8*)locinput))
sayNO;
- nextchr = UCHARAT(++locinput);
+ locinput++;
break;
}
break;
- /* Special char classes - The defines start on line 129 or so */
+
+ /* Special char classes: \d, \w etc.
+ * The defines start on line 166 or so */
CCC_TRY_U(ALNUM, NALNUM, isWORDCHAR,
ALNUML, NALNUML, isALNUM_LC, isALNUM_LC_utf8,
ALNUMU, NALNUMU, isWORDCHAR_L1,
DIGITA, NDIGITA, isDIGIT_A,
digit, "0");
- case POSIXA:
- if (locinput >= PL_regeol || ! _generic_isCC_A(nextchr, FLAGS(scan))) {
+ case POSIXA: /* /[[:ascii:]]/ etc */
+ if (NEXTCHR_IS_EOS || ! _generic_isCC_A(nextchr, FLAGS(scan))) {
sayNO;
}
/* Matched a utf8-invariant, so don't have to worry about utf8 */
- nextchr = UCHARAT(++locinput);
+ locinput++;
break;
- case NPOSIXA:
- if (locinput >= PL_regeol || _generic_isCC_A(nextchr, FLAGS(scan))) {
+
+ case NPOSIXA: /* /[^[:ascii:]]/ etc */
+ if (NEXTCHR_IS_EOS || _generic_isCC_A(nextchr, FLAGS(scan))) {
sayNO;
}
- if (utf8_target) {
- locinput += PL_utf8skip[nextchr];
- nextchr = UCHARAT(locinput);
- }
- else {
- nextchr = UCHARAT(++locinput);
- }
- break;
+ goto increment_locinput;
case CLUMP: /* Match \X: logical Unicode character. This is defined as
a Unicode extended Grapheme Cluster */
Prepend, that one will be a suitable Begin.
*/
- if (locinput >= PL_regeol)
+ if (NEXTCHR_IS_EOS)
sayNO;
if (! utf8_target) {
/* Utf8: See if is ( CR LF ); already know that locinput <
* PL_regeol, so locinput+1 is in bounds */
- if (nextchr == '\r' && UCHARAT(locinput + 1) == '\n') {
+ if ( nextchr == '\r' && locinput+1 < PL_regeol
+ && UCHARAT(locinput + 1) == '\n')
+ {
locinput += 2;
}
else {
exit_utf8:
if (locinput > PL_regeol) sayNO;
}
- nextchr = UCHARAT(locinput);
break;
- case NREFFL:
+ case NREFFL: /* /\g{name}/il */
{ /* The capture buffer cases. The ones beginning with N for the
named buffers just convert to the equivalent numbered and
pretend they were called as the corresponding numbered buffer
utf8_fold_flags = FOLDEQ_UTF8_LOCALE;
goto do_nref;
- case NREFFA:
+ case NREFFA: /* /\g{name}/iaa */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
type = REFFA;
utf8_fold_flags = FOLDEQ_UTF8_NOMIX_ASCII;
goto do_nref;
- case NREFFU:
+ case NREFFU: /* /\g{name}/iu */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
type = REFFU;
utf8_fold_flags = 0;
goto do_nref;
- case NREFF:
+ case NREFF: /* /\g{name}/i */
folder = foldEQ;
fold_array = PL_fold;
type = REFF;
utf8_fold_flags = 0;
goto do_nref;
- case NREF:
+ case NREF: /* /\g{name}/ */
type = REF;
folder = NULL;
fold_array = NULL;
}
goto do_nref_ref_common;
- case REFFL:
+ case REFFL: /* /\1/il */
PL_reg_flags |= RF_tainted;
folder = foldEQ_locale;
fold_array = PL_fold_locale;
utf8_fold_flags = FOLDEQ_UTF8_LOCALE;
goto do_ref;
- case REFFA:
+ case REFFA: /* /\1/iaa */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
utf8_fold_flags = FOLDEQ_UTF8_NOMIX_ASCII;
goto do_ref;
- case REFFU:
+ case REFFU: /* /\1/iu */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
utf8_fold_flags = 0;
goto do_ref;
- case REFF:
+ case REFF: /* /\1/i */
folder = foldEQ;
fold_array = PL_fold;
utf8_fold_flags = 0;
goto do_ref;
- case REF:
+ case REF: /* /\1/ */
folder = NULL;
fold_array = NULL;
utf8_fold_flags = 0;
sayNO;
}
locinput = limit;
- nextchr = UCHARAT(locinput);
break;
}
/* Not utf8: Inline the first character, for speed. */
- if (UCHARAT(s) != nextchr &&
+ if (!NEXTCHR_IS_EOS &&
+ UCHARAT(s) != nextchr &&
(type == REF ||
UCHARAT(s) != fold_array[nextchr]))
sayNO;
: ! folder(s, locinput, ln)))
sayNO;
locinput += ln;
- nextchr = UCHARAT(locinput);
break;
}
- case NOTHING:
- case TAIL:
+
+ case NOTHING: /* null op; e.g. the 'nothing' following
+ * the '*' in m{(a+|b)*}' */
break;
- case BACK:
+ case TAIL: /* placeholder while compiling (A|B|C) */
+ break;
+
+ case BACK: /* ??? doesn't appear to be used ??? */
break;
#undef ST
regexp_internal *rei;
regnode *startpoint;
- case GOSTART:
+ case GOSTART: /* (?R) */
case GOSUB: /* /(...(?1))/ /(...(?&foo))/ */
if (cur_eval && cur_eval->locinput==locinput) {
if (cur_eval->u.eval.close_paren == (U32)ARG(scan))
}
goto eval_recurse_doit;
assert(0); /* NOTREACHED */
+
case EVAL: /* /(?{A})B/ /(??{A})B/ and /(?(?{A})X|Y)B/ */
if (cur_eval && cur_eval->locinput==locinput) {
if ( ++nochange_depth > max_nochange_depth )
re->lastparen = 0;
re->lastcloseparen = 0;
- reginput = locinput;
PL_regsize = 0;
/* XXXX This is too dramatic a measure... */
rex = (struct regexp *)SvANY(rex_sv);
rexi = RXi_GET(rex);
- reginput = locinput;
REGCP_UNWIND(ST.lastcp);
regcppop(rex);
cur_eval = ST.prev_eval;
sayNO_SILENT;
#undef ST
- case OPEN:
+ case OPEN: /* ( */
n = ARG(scan); /* which paren pair */
rex->offs[n].start_tmp = locinput - PL_bostr;
if (n > PL_regsize)
(IV)rex->offs[n].end \
))
- case CLOSE:
+ case CLOSE: /* ) */
n = ARG(scan); /* which paren pair */
CLOSE_CAPTURE;
/*if (n > PL_regsize)
goto fake_end;
}
break;
- case ACCEPT:
+
+ case ACCEPT: /* (*ACCEPT) */
if (ARG(scan)){
regnode *cursor;
for (cursor=scan;
}
goto fake_end;
/*NOTREACHED*/
- case GROUPP:
+
+ case GROUPP: /* (?(1)) */
n = ARG(scan); /* which paren pair */
sw = cBOOL(rex->lastparen >= n && rex->offs[n].end != -1);
break;
- case NGROUPP:
+
+ case NGROUPP: /* (?(<name>)) */
/* reg_check_named_buff_matched returns 0 for no match */
sw = cBOOL(0 < reg_check_named_buff_matched(rex,scan));
break;
- case INSUBP:
+
+ case INSUBP: /* (?(R)) */
n = ARG(scan);
sw = (cur_eval && (!n || cur_eval->u.eval.close_paren == n));
break;
- case DEFINEP:
+
+ case DEFINEP: /* (?(DEFINE)) */
sw = 0;
break;
- case IFTHEN:
+
+ case IFTHEN: /* (?(cond)A|B) */
PL_reg_leftiter = PL_reg_maxiter; /* Void cache */
if (sw)
next = NEXTOPER(NEXTOPER(scan));
next = NEXTOPER(NEXTOPER(next));
}
break;
- case LOGICAL:
+
+ case LOGICAL: /* modifier for EVAL and IFMATCH */
logical = scan->flags;
break;
ST.cache_offset = 0;
ST.cache_mask = 0;
- reginput = locinput;
DEBUG_EXECUTE_r( PerlIO_printf(Perl_debug_log,
"%*s whilem: matched %ld out of %d..%d\n",
case WHILEM_A_max_fail: /* just failed to match A in a maximal match */
REGCP_UNWIND(ST.lastcp);
regcppop(rex); /* Restore some previous $<digit>s? */
- reginput = locinput;
DEBUG_EXECUTE_r(PerlIO_printf(Perl_debug_log,
"%*s whilem: failed, trying continuation...\n",
REPORT_CODE_OFF+depth*2, "")
"%*s trying longer...\n", REPORT_CODE_OFF+depth*2, "")
);
/* Try grabbing another A and see if it helps. */
- reginput = locinput;
cur_curlyx->u.curlyx.lastloc = locinput;
ST.cp = regcppush(rex, cur_curlyx->u.curlyx.parenfloor);
REGCP_SET(ST.lastcp);
PUSH_STATE_GOTO(BRANCH_next, scan, locinput);
}
assert(0); /* NOTREACHED */
- case CUTGROUP:
+
+ case CUTGROUP: /* /(*THEN)/ */
sv_yes_mark = st->u.mark.mark_name = scan->flags ? NULL :
MUTABLE_SV(rexi->data->data[ ARG( scan ) ]);
PUSH_STATE_GOTO(CUTGROUP_next, next, locinput);
assert(0); /* NOTREACHED */
+
case CUTGROUP_next_fail:
do_cutgroup = 1;
no_final = 1;
sv_commit = st->u.mark.mark_name;
sayNO;
assert(0); /* NOTREACHED */
+
case BRANCH_next:
sayYES;
assert(0); /* NOTREACHED */
+
case BRANCH_next_fail: /* that branch failed; try the next, if any */
if (do_cutgroup) {
do_cutgroup = 0;
continue; /* execute next BRANCH[J] op */
assert(0); /* NOTREACHED */
- case MINMOD:
+ case MINMOD: /* next op will be non-greedy, e.g. A*? */
minmod = 1;
break;
assert(0); /* NOTREACHED */
case CURLYM_A: /* we've just matched an A */
- locinput = st->locinput;
- nextchr = UCHARAT(locinput);
-
ST.count++;
/* after first match, determine A's length: u.curlym.alen */
if (ST.count == 1) {
if (PL_reg_match_utf8) {
- char *s = locinput;
- while (s < reginput) {
+ char *s = st->locinput;
+ while (s < locinput) {
ST.alen++;
s += UTF8SKIP(s);
}
}
else {
- ST.alen = reginput - locinput;
+ ST.alen = locinput - st->locinput;
}
if (ST.alen == 0)
ST.count = ST.minmod ? ARG1(ST.me) : ARG2(ST.me);
(IV) ST.count, (IV)ST.alen)
);
- locinput = reginput;
-
if (cur_eval && cur_eval->u.eval.close_paren &&
cur_eval->u.eval.close_paren == (U32)ST.me->flags)
goto fake_end;
sayNO;
curlym_do_B: /* execute the B in /A{m,n}B/ */
- reginput = locinput;
if (ST.c1 == CHRTEST_UNINIT) {
/* calculate c1 and c2 for possible match of 1st char
* following curly */
(int)(REPORT_CODE_OFF+(depth*2)),
"", (IV)ST.count)
);
- if (ST.c1 != CHRTEST_VOID
- && UCHARAT(reginput) != ST.c1
- && UCHARAT(reginput) != ST.c2)
+ if ( !NEXTCHR_IS_EOS
+ && ST.c1 != CHRTEST_VOID
+ && nextchr != ST.c1
+ && nextchr != ST.c2)
{
/* simulate B failing */
DEBUG_OPTIMISE_r(
I32 paren = ST.me->flags;
if (ST.count) {
rex->offs[paren].start
- = HOPc(reginput, -ST.alen) - PL_bostr;
- rex->offs[paren].end = reginput - PL_bostr;
+ = HOPc(locinput, -ST.alen) - PL_bostr;
+ rex->offs[paren].end = locinput - PL_bostr;
if ((U32)paren > rex->lastparen)
rex->lastparen = paren;
rex->lastcloseparen = paren;
if (ST.count == ARG1(ST.me) /* min */)
sayNO;
ST.count--;
- locinput = HOPc(locinput, -ST.alen);
+ SET_locinput(HOPc(locinput, -ST.alen));
goto curlym_do_B; /* try to match B */
#undef ST
ST.max = REG_INFTY;
scan = NEXTOPER(scan);
goto repeat;
+
case PLUS: /* /A+B/ where A is width 1 */
ST.paren = 0;
ST.min = 1;
ST.max = REG_INFTY;
scan = NEXTOPER(scan);
goto repeat;
+
case CURLYN: /* /(A){m,n}B/ where A is width 1 */
ST.paren = scan->flags; /* Which paren to set */
ST.lastparen = rex->lastparen;
}
scan = regnext(NEXTOPER(scan) + NODE_STEP_REGNODE);
goto repeat;
+
case CURLY: /* /A{m,n}B/ where A is width 1 */
ST.paren = 0;
ST.min = ARG1(scan); /* min to match */
ST.A = scan;
ST.B = next;
- reginput = locinput;
if (minmod) {
- /* avoid taking address of reginput, so it can remain
- * a register var */
- char *ri = reginput;
+ char *li = locinput;
minmod = 0;
- if (ST.min && regrepeat(rex, &ri, ST.A, ST.min, depth) < ST.min)
+ if (ST.min && regrepeat(rex, &li, ST.A, ST.min, depth) < ST.min)
sayNO;
- reginput = ri;
+ SET_locinput(li);
ST.count = ST.min;
- locinput = reginput;
REGCP_SET(ST.cp);
if (ST.c1 == CHRTEST_VOID)
goto curly_try_B_min;
}
else {
- char *ri = reginput;
- ST.count = regrepeat(rex, &ri, ST.A, ST.max, depth);
- reginput = ri;
- locinput = reginput;
+ /* avoid taking address of locinput, so it can remain
+ * a register var */
+ char *li = locinput;
+ ST.count = regrepeat(rex, &li, ST.A, ST.max, depth);
if (ST.count < ST.min)
sayNO;
+ SET_locinput(li);
if ((ST.count > ST.min)
&& (PL_regkind[OP(ST.B)] == EOL) && (OP(ST.B) != MEOL))
{
/* ...except that $ and \Z can match before *and* after
newline at the end. Consider "\n\n" =~ /\n+\Z\n/.
We may back off by one in this case. */
- if (UCHARAT(reginput - 1) == '\n' && OP(ST.B) != EOS)
+ if (UCHARAT(locinput - 1) == '\n' && OP(ST.B) != EOS)
ST.min--;
}
REGCP_SET(ST.cp);
case CURLY_B_min_known_fail:
/* failed to find B in a non-greedy match where c1,c2 valid */
- reginput = locinput; /* Could be reset... */
REGCP_UNWIND(ST.cp);
if (ST.paren) {
UNWIND_PAREN(ST.lastparen, ST.lastcloseparen);
}
if (locinput > ST.maxpos)
sayNO;
- /* reginput == oldloc now */
if (n) {
- char *ri = reginput;
+ /* In /a{m,n}b/, ST.oldloc is at "a" x m, locinput is
+ * at b; check that everything between oldloc and
+ * locinput matches */
+ char *li = ST.oldloc;
ST.count += n;
- if (regrepeat(rex, &ri, ST.A, n, depth) < n)
+ if (regrepeat(rex, &li, ST.A, n, depth) < n)
sayNO;
- reginput = ri;
+ assert(n == REG_INFTY || locinput == li);
}
- reginput = locinput;
CURLY_SETPAREN(ST.paren, ST.count);
if (cur_eval && cur_eval->u.eval.close_paren &&
cur_eval->u.eval.close_paren == (U32)ST.paren) {
UNWIND_PAREN(ST.lastparen, ST.lastcloseparen);
}
/* failed -- move forward one */
- reginput = locinput;
{
- char *ri = reginput;
- if (!regrepeat(rex, &ri, ST.A, 1, depth)) {
+ char *li = locinput;
+ if (!regrepeat(rex, &li, ST.A, 1, depth)) {
sayNO;
}
- reginput = ri;
+ locinput = li;
}
{
ST.count++;
- locinput = reginput;
if (ST.count <= ST.max || (ST.max == REG_INFTY &&
ST.count > 0)) /* count overflow ? */
{
}
{
UV c = 0;
- if (ST.c1 != CHRTEST_VOID)
- c = utf8_target ? utf8n_to_uvchr((U8*)reginput,
+ if (ST.c1 != CHRTEST_VOID && locinput < PL_regeol)
+ c = utf8_target ? utf8n_to_uvchr((U8*)locinput,
UTF8_MAXBYTES, 0, uniflags)
- : (UV) UCHARAT(reginput);
+ : (UV) UCHARAT(locinput);
/* If it could work, try it. */
- if (ST.c1 == CHRTEST_VOID || c == (UV)ST.c1 || c == (UV)ST.c2) {
+ if (ST.c1 == CHRTEST_VOID
+ || (locinput < PL_regeol &&
+ (c == (UV)ST.c1 || c == (UV)ST.c2)))
+ {
CURLY_SETPAREN(ST.paren, ST.count);
PUSH_STATE_GOTO(CURLY_B_max, ST.B, locinput);
assert(0); /* NOTREACHED */
}
}
/* FALL THROUGH */
+
case CURLY_B_max_fail:
/* failed to find B in a greedy match */
/* back up. */
if (--ST.count < ST.min)
sayNO;
- reginput = locinput = HOPc(locinput, -1);
+ locinput = HOPc(locinput, -1);
goto curly_try_B_max;
#undef ST
- case END:
+ case END: /* last op of main pattern */
fake_end:
if (cur_eval) {
/* we've just finished A in /(??{A})B/; now continue with B */
cur_curlyx = cur_eval->u.eval.prev_curlyx;
REGCP_SET(st->u.eval.lastcp);
- reginput = locinput;
/* Restore parens of the outer rex without popping the
* savestack */
sayNO_SILENT; /* Cannot match: too short. */
}
- reginput = locinput; /* put where regtry can find it */
sayYES; /* Success! */
case SUCCEED: /* successful SUSPEND/UNLESSM/IFMATCH/CURLYM */
PerlIO_printf(Perl_debug_log,
"%*s %ssubpattern success...%s\n",
REPORT_CODE_OFF+depth*2, "", PL_colors[4], PL_colors[5]));
- reginput = locinput; /* put where regtry can find it */
sayYES; /* Success! */
#undef ST
if (OP(ST.me) != SUSPEND) {
/* restore old position except for (?>...) */
locinput = st->locinput;
- nextchr = UCHARAT(locinput);
}
scan = ST.me + ARG(ST.me);
if (scan == ST.me)
#undef ST
- case LONGJMP:
+ case LONGJMP: /* alternative with many branches compiles to
+ * (BRANCHJ; EXACT ...; LONGJMP ) x N */
next = scan + ARG(scan);
if (next == scan)
next = NULL;
break;
- case COMMIT:
+
+ case COMMIT: /* (*COMMIT) */
reginfo->cutpoint = PL_regeol;
/* FALLTHROUGH */
- case PRUNE:
- reginput = locinput;
+
+ case PRUNE: /* (*PRUNE) */
if (!scan->flags)
sv_yes_mark = sv_commit = MUTABLE_SV(rexi->data->data[ ARG( scan ) ]);
PUSH_STATE_GOTO(COMMIT_next, next, locinput);
assert(0); /* NOTREACHED */
+
case COMMIT_next_fail:
no_final = 1;
/* FALLTHROUGH */
- case OPFAIL:
+
+ case OPFAIL: /* (*FAIL) */
sayNO;
assert(0); /* NOTREACHED */
#define ST st->u.mark
- case MARKPOINT:
+ case MARKPOINT: /* (*MARK:foo) */
ST.prev_mark = mark_state;
ST.mark_name = sv_commit = sv_yes_mark
= MUTABLE_SV(rexi->data->data[ ARG( scan ) ]);
ST.mark_loc = locinput;
PUSH_YES_STATE_GOTO(MARKPOINT_next, next, locinput);
assert(0); /* NOTREACHED */
+
case MARKPOINT_next:
mark_state = ST.prev_mark;
sayYES;
assert(0); /* NOTREACHED */
+
case MARKPOINT_next_fail:
if (popmark && sv_eq(ST.mark_name,popmark))
{
mark_state->u.mark.mark_name : NULL;
sayNO;
assert(0); /* NOTREACHED */
- case SKIP:
- reginput = locinput;
+
+ case SKIP: /* (*SKIP) */
if (scan->flags) {
/* (*SKIP) : if we fail we cut here*/
ST.mark_name = NULL;
}
/* Didn't find our (*MARK:NAME) so ignore this (*SKIP:NAME) */
break;
+
case SKIP_next_fail:
if (ST.mark_name) {
/* (*CUT:NAME) - Set up to search for the name as we
sayNO;
assert(0); /* NOTREACHED */
#undef ST
- case LNBREAK:
- if ((n=is_LNBREAK(locinput,utf8_target))) {
+
+ case LNBREAK: /* \R */
+ if ((n=is_LNBREAK_safe(locinput, PL_regeol, utf8_target))) {
locinput += n;
- nextchr = UCHARAT(locinput);
} else
sayNO;
break;
#define CASE_CLASS(nAmE) \
case nAmE: \
- if (locinput >= PL_regeol) \
+ if (NEXTCHR_IS_EOS) \
sayNO; \
if ((n=is_##nAmE(locinput,utf8_target))) { \
locinput += n; \
- nextchr = UCHARAT(locinput); \
} else \
sayNO; \
break; \
case N##nAmE: \
- if (locinput >= PL_regeol) \
+ if (NEXTCHR_IS_EOS) \
sayNO; \
if ((n=is_##nAmE(locinput,utf8_target))) { \
sayNO; \
} else { \
locinput += UTF8SKIP(locinput); \
- nextchr = UCHARAT(locinput); \
} \
break
- CASE_CLASS(VERTWS);
- CASE_CLASS(HORIZWS);
+ CASE_CLASS(VERTWS); /* \v \V */
+ CASE_CLASS(HORIZWS); /* \h \H */
#undef CASE_CLASS
default:
PerlIO_printf(Perl_error_log, "%"UVxf" %d\n",
PTR2UV(scan), OP(scan));
Perl_croak(aTHX_ "regexp memory corruption");
+
+ /* this is a point to jump to in order to increment
+ * locinput by one character */
+ increment_locinput:
+ if (utf8_target) {
+ locinput += PL_utf8skip[nextchr];
+ /* locinput is allowed to go 1 char off the end, but not 2+ */
+ if (locinput > PL_regeol)
+ sayNO;
+ }
+ else
+ locinput++;
+ break;
} /* end switch */
PL_regmatch_state = newst;
locinput = pushinput;
- nextchr = UCHARAT(locinput);
st = newst;
continue;
assert(0); /* NOTREACHED */
yes_state = st->u.yes.prev_yes_state;
PL_regmatch_state = st;
- if (no_final) {
+ if (no_final)
locinput= st->locinput;
- nextchr = UCHARAT(locinput);
- }
state_num = st->resume_state + no_final;
goto reenter_switch;
}
}
PL_regmatch_state = st;
locinput= st->locinput;
- nextchr = UCHARAT(locinput);
DEBUG_STATE_pp("pop");
depth--;
/* clean up; in particular, free all slabs above current one */
LEAVE_SCOPE(oldsave);
- assert(!result || reginput - PL_bostr >= 0);
- return result ? reginput - PL_bostr : -1;
+ assert(!result || locinput - PL_bostr >= 0);
+ return result ? locinput - PL_bostr : -1;
}
/*
- regrepeat - repeatedly match something simple, report how many
- */
-/*
- * [This routine now assumes that it will only match on things of length 1.
- * That was true before, but now we assume scan - reginput is the count,
- * rather than incrementing count on every character. [Er, except utf8.]]
+ *
+ * startposp - pointer a pointer to the start position. This is updated
+ * to point to the byte following the highest successful
+ * match.
+ * p - the regnode to be repeatedly matched against.
+ * max - maximum number of characters to match.
+ * depth - (for debugging) backtracking depth.
*/
STATIC I32
S_regrepeat(pTHX_ const regexp *prog, char **startposp, const regnode *p, I32 max, int depth)
case LNBREAK:
if (utf8_target) {
loceol = PL_regeol;
- while (hardcount < max && scan < loceol && (c=is_LNBREAK_utf8(scan))) {
+ while (hardcount < max && scan < loceol &&
+ (c=is_LNBREAK_utf8_safe(scan, loceol))) {
scan += c;
hardcount++;
}
because we have a null terminated string, but we
have to use hardcount in this situation
*/
- while (scan < loceol && (c=is_LNBREAK_latin1(scan))) {
+ while (scan < loceol && (c=is_LNBREAK_latin1_safe(scan, loceol))) {
scan+=c;
hardcount++;
}
case HORIZWS:
if (utf8_target) {
loceol = PL_regeol;
- while (hardcount < max && scan < loceol && (c=is_HORIZWS_utf8(scan))) {
+ while (hardcount < max && scan < loceol &&
+ (c=is_HORIZWS_utf8_safe(scan, loceol)))
+ {
scan += c;
hardcount++;
}
} else {
- while (scan < loceol && is_HORIZWS_latin1(scan))
+ while (scan < loceol && is_HORIZWS_latin1_safe(scan, loceol))
scan++;
}
break;
case NHORIZWS:
if (utf8_target) {
loceol = PL_regeol;
- while (hardcount < max && scan < loceol && !is_HORIZWS_utf8(scan)) {
+ while (hardcount < max && scan < loceol &&
+ !is_HORIZWS_utf8_safe(scan, loceol))
+ {
scan += UTF8SKIP(scan);
hardcount++;
}
} else {
- while (scan < loceol && !is_HORIZWS_latin1(scan))
+ while (scan < loceol && !is_HORIZWS_latin1_safe(scan, loceol))
scan++;
}
case VERTWS:
if (utf8_target) {
loceol = PL_regeol;
- while (hardcount < max && scan < loceol && (c=is_VERTWS_utf8(scan))) {
+ while (hardcount < max && scan < loceol &&
+ (c=is_VERTWS_utf8_safe(scan, loceol)))
+ {
scan += c;
hardcount++;
}
} else {
- while (scan < loceol && is_VERTWS_latin1(scan))
+ while (scan < loceol && is_VERTWS_latin1_safe(scan, loceol))
scan++;
}
case NVERTWS:
if (utf8_target) {
loceol = PL_regeol;
- while (hardcount < max && scan < loceol && !is_VERTWS_utf8(scan)) {
+ while (hardcount < max && scan < loceol &&
+ !is_VERTWS_utf8_safe(scan, loceol))
+ {
scan += UTF8SKIP(scan);
hardcount++;
}
} else {
- while (scan < loceol && !is_VERTWS_latin1(scan))
+ while (scan < loceol && !is_VERTWS_latin1_safe(scan, loceol))
scan++;
}