* the end pointer. */
if ( !first ) {
first = cur;
- trietype = noper_trietype;
if ( noper_trietype == NOTHING ) {
#if !defined(DEBUGGING) && !defined(NOJUMPTRIE)
regnode * const noper_next = regnext( noper );
U8 noper_next_trietype = noper_next_type ? TRIE_TYPE( noper_next_type ) :0;
#endif
- if ( noper_next_trietype )
+ if ( noper_next_trietype ) {
trietype = noper_next_trietype;
+ } else if (noper_next_type) {
+ /* a NOTHING regop is 1 regop wide. We need at least two
+ * for a trie so we can't merge this in */
+ first = NULL;
+ }
+ } else {
+ trietype = noper_trietype;
}
} else {
if ( trietype == NOTHING )
OP *o = NULL;
int n = 0;
bool utf8 = 0;
+ STRLEN orig_patlen = 0;
if (pRExC_state->num_code_blocks) {
o = cLISTOPx(expr)->op_first;
o = o->op_sibling;;
}
+ if ((SvAMAGIC(pat) || SvAMAGIC(msv)) &&
+ (sv = amagic_call(pat, msv, concat_amg, AMGf_assign)))
+ {
+ sv_setsv(pat, sv);
+ /* overloading involved: all bets are off over literal
+ * code. Pretend we haven't seen it */
+ pRExC_state->num_code_blocks -= n;
+ n = 0;
+ rx = NULL;
+
+ }
+ else {
+ while (SvAMAGIC(msv)
+ && (sv = AMG_CALLunary(msv, string_amg))
+ && sv != msv)
+ {
+ msv = sv;
+ SvGETMAGIC(msv);
+ }
+ if (SvROK(msv) && SvTYPE(SvRV(msv)) == SVt_REGEXP)
+ msv = SvRV(msv);
+ orig_patlen = SvCUR(pat);
+ sv_catsv_nomg(pat, msv);
+ rx = msv;
+ if (code)
+ pRExC_state->code_blocks[n-1].end = SvCUR(pat)-1;
+ }
+
/* extract any code blocks within any embedded qr//'s */
- rx = msv;
- if (SvROK(rx))
- rx = SvRV(rx);
- if (SvTYPE(rx) == SVt_REGEXP
+ if (rx && SvTYPE(rx) == SVt_REGEXP
&& RX_ENGINE((REGEXP*)rx)->op_comp)
{
pRExC_state->num_code_blocks += ri->num_code_blocks;
for (i=0; i < ri->num_code_blocks; i++) {
struct reg_code_block *src, *dst;
- STRLEN offset = SvCUR(pat)
+ STRLEN offset = orig_patlen
+ ((struct regexp *)SvANY(rx))->pre_prefix;
assert(n < pRExC_state->num_code_blocks);
src = &ri->code_blocks[i];
}
}
}
-
- if ((SvAMAGIC(pat) || SvAMAGIC(msv)) &&
- (sv = amagic_call(pat, msv, concat_amg, AMGf_assign)))
- {
- sv_setsv(pat, sv);
- /* overloading involved: all bets are off over literal
- * code. Pretend we haven't seen it */
- pRExC_state->num_code_blocks -= n;
- n = 0;
-
- }
- else {
- if (SvROK(msv) && SvTYPE(SvRV(msv)) == SVt_REGEXP)
- msv = SvRV(msv);
- sv_catsv_nomg(pat, msv);
- if (code)
- pRExC_state->code_blocks[n-1].end = SvCUR(pat)-1;
- }
}
SvSETMAGIC(pat);
}
- else
+ else {
+ SV *sv;
pat = *patternp;
+ while (SvAMAGIC(pat)
+ && (sv = AMG_CALLunary(pat, string_amg))
+ && sv != pat)
+ {
+ pat = sv;
+ SvGETMAGIC(pat);
+ }
+ }
/* handle bare regex: foo =~ $re */
{
do {
RExC_parse++;
} while (isALNUM(*RExC_parse));
+ } else {
+ RExC_parse++; /* so the <- from the vFAIL is after the offending character */
+ vFAIL("Group name must start with a non-digit word character");
}
-
if ( flags ) {
SV* sv_name
= newSVpvn_flags(name_start, (int)(RExC_parse - name_start),
sequence, we return.
Note: we have to be careful with escapes, as they can be both literal
- and special, and in the case of \10 and friends can either, depending
- on context. Specifically there are two separate switches for handling
+ and special, and in the case of \10 and friends, context determines which.
+
+ A summary of the code structure is:
+
+ switch (first_byte) {
+ cases for each special:
+ handle this special;
+ break;
+ case '\\':
+ switch (2nd byte) {
+ cases for each unambiguous special:
+ handle this special;
+ break;
+ cases for each ambigous special/literal:
+ disambiguate;
+ if (special) handle here
+ else goto defchar;
+ default: // unambiguously literal:
+ goto defchar;
+ }
+ default: // is a literal char
+ // FALL THROUGH
+ defchar:
+ create EXACTish node for literal;
+ while (more input and node isn't full) {
+ switch (input_byte) {
+ cases for each special;
+ make sure parse pointer is set so that the next call to
+ regatom will see this special first
+ goto loopdone; // EXACTish node terminated by prev. char
+ default:
+ append char to EXACTISH node;
+ }
+ get next input byte;
+ }
+ loopdone:
+ }
+ return the generated node;
+
+ Specifically there are two separate switches for handling
escape sequences, with the one for handling literal escapes requiring
a dummy entry for all of the special escapes that are actually handled
by the other.
vFAIL("Reference to nonexistent or unclosed group");
}
if (!isg && num > 9 && num >= RExC_npar)
+ /* Probably a character specified in octal, e.g. \35 */
goto defchar;
else {
char * const parse_start = RExC_parse - 1; /* MJD */
break;
}
case 'x':
- if (*++p == '{') {
- char* const e = strchr(p, '}');
+ {
+ STRLEN brace_len = len;
+ UV result;
+ const char* error_msg;
- if (!e) {
- RExC_parse = p + 1;
- vFAIL("Missing right brace on \\x{}");
+ bool valid = grok_bslash_x(p,
+ &result,
+ &brace_len,
+ &error_msg,
+ 1);
+ p += brace_len;
+ if (! valid) {
+ RExC_parse = p; /* going to die anyway; point
+ to exact spot of failure */
+ vFAIL(error_msg);
}
else {
- I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
- | PERL_SCAN_DISALLOW_PREFIX;
- STRLEN numlen = e - p - 1;
- ender = grok_hex(p + 1, &numlen, &flags, NULL);
- if (ender > 0xff)
- REQUIRE_UTF8;
- p = e + 1;
+ ender = result;
}
+ if (PL_encoding && ender < 0x100) {
+ goto recode_encoding;
+ }
+ if (ender > 0xff) {
+ REQUIRE_UTF8;
+ }
+ break;
}
- else {
- I32 flags = PERL_SCAN_DISALLOW_PREFIX;
- STRLEN numlen = 2;
- ender = grok_hex(p, &numlen, &flags, NULL);
- p += numlen;
- }
- if (PL_encoding && ender < 0x100)
- goto recode_encoding;
- break;
case 'c':
p++;
ender = grok_bslash_c(*p++, UTF, SIZE_ONLY);
break;
case '0': case '1': case '2': case '3':case '4':
- case '5': case '6': case '7': case '8':case '9':
+ case '5': case '6': case '7':
if (*p == '0' ||
(isDIGIT(p[1]) && atoi(p) >= RExC_npar))
{
FAIL("Trailing \\");
/* FALL THROUGH */
default:
- if (!SIZE_ONLY&& isALPHA(*p)) {
+ if (!SIZE_ONLY&& isALNUMC(*p)) {
ckWARN2reg(p + 1, "Unrecognized escape \\%.1s passed through", p);
}
goto normal_default;
} \
}
-STATIC U8
-S_set_regclass_bit_fold(pTHX_ RExC_state_t *pRExC_state, regnode* node, const U8 value, SV** invlist_ptr, AV** alternate_ptr)
-{
-
- /* Handle the setting of folds in the bitmap for non-locale ANYOF nodes.
- * Locale folding is done at run-time, so this function should not be
- * called for nodes that are for locales.
- *
- * This function sets the bit corresponding to the fold of the input
- * 'value', if not already set. The fold of 'f' is 'F', and the fold of
- * 'F' is 'f'.
- *
- * It also knows about the characters that are in the bitmap that have
- * folds that are matchable only outside it, and sets the appropriate lists
- * and flags.
- *
- * It returns the number of bits that actually changed from 0 to 1 */
-
- U8 stored = 0;
- U8 fold;
-
- PERL_ARGS_ASSERT_SET_REGCLASS_BIT_FOLD;
-
- fold = (AT_LEAST_UNI_SEMANTICS) ? PL_fold_latin1[value]
- : PL_fold[value];
-
- /* It assumes the bit for 'value' has already been set */
- if (fold != value && ! ANYOF_BITMAP_TEST(node, fold)) {
- ANYOF_BITMAP_SET(node, fold);
- stored++;
- }
- if (_HAS_NONLATIN1_FOLD_CLOSURE_ONLY_FOR_USE_BY_REGCOMP_DOT_C_AND_REGEXEC_DOT_C(value) && (! isASCII(value) || ! MORE_ASCII_RESTRICTED)) {
- /* Certain Latin1 characters have matches outside the bitmap. To get
- * here, 'value' is one of those characters. None of these matches is
- * valid for ASCII characters under /aa, which have been excluded by
- * the 'if' above. The matches fall into three categories:
- * 1) They are singly folded-to or -from an above 255 character, as
- * LATIN SMALL LETTER Y WITH DIAERESIS and LATIN CAPITAL LETTER Y
- * WITH DIAERESIS;
- * 2) They are part of a multi-char fold with another character in the
- * bitmap, only LATIN SMALL LETTER SHARP S => "ss" fits that bill;
- * 3) They are part of a multi-char fold with a character not in the
- * bitmap, such as various ligatures.
- * We aren't dealing fully with multi-char folds, except we do deal
- * with the pattern containing a character that has a multi-char fold
- * (not so much the inverse).
- * For types 1) and 3), the matches only happen when the target string
- * is utf8; that's not true for 2), and we set a flag for it.
- *
- * The code below adds to the passed in inversion list the single fold
- * closures for 'value'. The values are hard-coded here so that an
- * innocent-looking character class, like /[ks]/i won't have to go out
- * to disk to find the possible matches. XXX It would be better to
- * generate these via regen, in case a new version of the Unicode
- * standard adds new mappings, though that is not really likely. */
- switch (value) {
- case 'k':
- case 'K':
- /* KELVIN SIGN */
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr, 0x212A);
- break;
- case 's':
- case 'S':
- /* LATIN SMALL LETTER LONG S */
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr, 0x017F);
- break;
- case MICRO_SIGN:
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr,
- GREEK_SMALL_LETTER_MU);
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr,
- GREEK_CAPITAL_LETTER_MU);
- break;
- case LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE:
- case LATIN_SMALL_LETTER_A_WITH_RING_ABOVE:
- /* ANGSTROM SIGN */
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr, 0x212B);
- if (DEPENDS_SEMANTICS) { /* See DEPENDS comment below */
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr,
- PL_fold_latin1[value]);
- }
- break;
- case LATIN_SMALL_LETTER_Y_WITH_DIAERESIS:
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr,
- LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS);
- break;
- case LATIN_SMALL_LETTER_SHARP_S:
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr,
- LATIN_CAPITAL_LETTER_SHARP_S);
-
- /* Under /a, /d, and /u, this can match the two chars "ss" */
- if (! MORE_ASCII_RESTRICTED) {
- add_alternate(alternate_ptr, (U8 *) "ss", 2);
-
- /* And under /u or /a, it can match even if the target is
- * not utf8 */
- if (AT_LEAST_UNI_SEMANTICS) {
- ANYOF_FLAGS(node) |= ANYOF_NONBITMAP_NON_UTF8;
- }
- }
- break;
- case 'F': case 'f':
- case 'I': case 'i':
- case 'L': case 'l':
- case 'T': case 't':
- case 'A': case 'a':
- case 'H': case 'h':
- case 'J': case 'j':
- case 'N': case 'n':
- case 'W': case 'w':
- case 'Y': case 'y':
- /* These all are targets of multi-character folds from code
- * points that require UTF8 to express, so they can't match
- * unless the target string is in UTF-8, so no action here is
- * necessary, as regexec.c properly handles the general case
- * for UTF-8 matching */
- break;
- default:
- /* Use deprecated warning to increase the chances of this
- * being output */
- ckWARN2regdep(RExC_parse, "Perl folding rules are not up-to-date for 0x%x; please use the perlbug utility to report;", value);
- break;
- }
- }
- else if (DEPENDS_SEMANTICS
- && ! isASCII(value)
- && PL_fold_latin1[value] != value)
- {
- /* Under DEPENDS rules, non-ASCII Latin1 characters match their
- * folds only when the target string is in UTF-8. We add the fold
- * here to the list of things to match outside the bitmap, which
- * won't be looked at unless it is UTF8 (or else if something else
- * says to look even if not utf8, but those things better not happen
- * under DEPENDS semantics. */
- *invlist_ptr = add_cp_to_invlist(*invlist_ptr, PL_fold_latin1[value]);
- }
-
- return stored;
-}
-
-
-PERL_STATIC_INLINE U8
-S_set_regclass_bit(pTHX_ RExC_state_t *pRExC_state, regnode* node, const U8 value, SV** invlist_ptr, AV** alternate_ptr)
-{
- /* This inline function sets a bit in the bitmap if not already set, and if
- * appropriate, its fold, returning the number of bits that actually
- * changed from 0 to 1 */
-
- U8 stored;
-
- PERL_ARGS_ASSERT_SET_REGCLASS_BIT;
-
- if (ANYOF_BITMAP_TEST(node, value)) { /* Already set */
- return 0;
- }
-
- ANYOF_BITMAP_SET(node, value);
- stored = 1;
-
- if (FOLD && ! LOC) { /* Locale folds aren't known until runtime */
- stored += set_regclass_bit_fold(pRExC_state, node, value, invlist_ptr, alternate_ptr);
- }
-
- return stored;
-}
-
STATIC void
S_add_alternate(pTHX_ AV** alternate_ptr, U8* string, STRLEN len)
{
/* code points this node matches that can't be stored in the bitmap */
SV* nonbitmap = NULL;
- /* The items that are to match that aren't stored in the bitmap, but are a
- * result of things that are stored there. This is the fold closure of
- * such a character, either because it has DEPENDS semantics and shouldn't
- * be matched unless the target string is utf8, or is a code point that is
- * too large for the bit map, as for example, the fold of the MICRO SIGN is
- * above 255. This all is solely for performance reasons. By having this
- * code know the outside-the-bitmap folds that the bitmapped characters are
- * involved with, we don't have to go out to disk to find the list of
- * matches, unless the character class includes code points that aren't
- * storable in the bit map. That means that a character class with an 's'
- * in it, for example, doesn't need to go out to disk to find everything
- * that matches. A 2nd list is used so that the 'nonbitmap' list is kept
- * empty unless there is something whose fold we don't know about, and will
- * have to go out to the disk to find. */
- SV* l1_fold_invlist = NULL;
+ /* inversion list of code points this node matches only when the target
+ * string is in UTF-8. (Because is under /d) */
+ SV* depends_list = NULL;
/* List of multi-character folds that are matched by this node */
AV* unicode_alternate = NULL;
#ifdef EBCDIC
+ /* In a range, counts how many 0-2 of the ends of it came from literals,
+ * not escapes. Thus we can tell if 'A' was input vs \x{C1} */
UV literal_endpoint = 0;
#endif
UV stored = 0; /* how many chars stored in the bitmap */
}
break;
case 'x':
- if (*RExC_parse == '{') {
- I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
- | PERL_SCAN_DISALLOW_PREFIX;
- char * const e = strchr(RExC_parse++, '}');
- if (!e)
- vFAIL("Missing right brace on \\x{}");
-
- numlen = e - RExC_parse;
- value = grok_hex(RExC_parse, &numlen, &flags, NULL);
- RExC_parse = e + 1;
- }
- else {
- I32 flags = PERL_SCAN_DISALLOW_PREFIX;
- numlen = 2;
- value = grok_hex(RExC_parse, &numlen, &flags, NULL);
+ RExC_parse--; /* function expects to be pointed at the 'x' */
+ {
+ const char* error_msg;
+ bool valid = grok_bslash_x(RExC_parse,
+ &value,
+ &numlen,
+ &error_msg,
+ 1);
RExC_parse += numlen;
+ if (! valid) {
+ vFAIL(error_msg);
+ }
}
if (PL_encoding && value < 0x100)
goto recode_encoding;
ckWARN4reg(RExC_parse,
"False [] range \"%*.*s\"",
w, w, rangebegin);
-
- stored +=
- set_regclass_bit(pRExC_state, ret, '-', &l1_fold_invlist, &unicode_alternate);
- if (prevvalue < 256) {
- stored +=
- set_regclass_bit(pRExC_state, ret, (U8) prevvalue, &l1_fold_invlist, &unicode_alternate);
- }
- else {
- nonbitmap = add_cp_to_invlist(nonbitmap, prevvalue);
- }
+ nonbitmap = add_cp_to_invlist(nonbitmap, '-');
+ nonbitmap = add_cp_to_invlist(nonbitmap, prevvalue);
}
range = 0; /* this was not a true range */
"False [] range \"%*.*s\"",
w, w, rangebegin);
}
- if (!SIZE_ONLY)
- stored +=
- set_regclass_bit(pRExC_state, ret, '-', &l1_fold_invlist, &unicode_alternate);
+ if (!SIZE_ONLY)
+ nonbitmap = add_cp_to_invlist(nonbitmap, '-');
} else
range = 1; /* yeah, it's a range! */
continue; /* but do it the next time */
/* now is the next time */
if (!SIZE_ONLY) {
- if (prevvalue < 256) {
- const IV ceilvalue = value < 256 ? value : 255;
- IV i;
-#ifdef EBCDIC
- /* In EBCDIC [\x89-\x91] should include
- * the \x8e but [i-j] should not. */
- if (literal_endpoint == 2 &&
- ((isLOWER(prevvalue) && isLOWER(ceilvalue)) ||
- (isUPPER(prevvalue) && isUPPER(ceilvalue))))
- {
- if (isLOWER(prevvalue)) {
- for (i = prevvalue; i <= ceilvalue; i++)
- if (isLOWER(i) && !ANYOF_BITMAP_TEST(ret,i)) {
- stored +=
- set_regclass_bit(pRExC_state, ret, (U8) i, &l1_fold_invlist, &unicode_alternate);
- }
- } else {
- for (i = prevvalue; i <= ceilvalue; i++)
- if (isUPPER(i) && !ANYOF_BITMAP_TEST(ret,i)) {
- stored +=
- set_regclass_bit(pRExC_state, ret, (U8) i, &l1_fold_invlist, &unicode_alternate);
- }
- }
- }
- else
-#endif
- for (i = prevvalue; i <= ceilvalue; i++) {
- stored += set_regclass_bit(pRExC_state, ret, (U8) i, &l1_fold_invlist, &unicode_alternate);
- }
- }
- if (value > 255) {
- const UV prevnatvalue = NATIVE_TO_UNI(prevvalue);
- const UV natvalue = NATIVE_TO_UNI(value);
- nonbitmap = _add_range_to_invlist(nonbitmap, prevnatvalue, natvalue);
- }
-#ifdef EBCDIC
- literal_endpoint = 0;
+#ifndef EBCDIC
+ nonbitmap = _add_range_to_invlist(nonbitmap, prevvalue, value);
+#else
+ UV* this_range = _new_invlist(1);
+ _append_range_to_invlist(this_range, prevvalue, value);
+
+ /* In EBCDIC, the ranges 'A-Z' and 'a-z' are each not contiguous.
+ * If this range was specified using something like 'i-j', we want
+ * to include only the 'i' and the 'j', and not anything in
+ * between, so exclude non-ASCII, non-alphabetics from it.
+ * However, if the range was specified with something like
+ * [\x89-\x91] or [\x89-j], all code points within it should be
+ * included. literal_endpoint==2 means both ends of the range used
+ * a literal character, not \x{foo} */
+ if (literal_endpoint == 2
+ && (prevvalue >= 'a' && value <= 'z')
+ || (prevvalue >= 'A' && value <= 'Z'))
+ {
+ _invlist_intersection(this_range, PL_ASCII, &this_range, );
+ _invlist_intersection(this_range, PL_Alpha, &this_range, );
+ }
+ _invlist_union(nonbitmap, this_range, &nonbitmap);
+ literal_endpoint = 0;
#endif
}
range = 0; /* this range (if it was one) is done now */
}
-
-
if (SIZE_ONLY)
return ret;
/****** !SIZE_ONLY AFTER HERE *********/
- /* If folding and there are code points above 255, we calculate all
- * characters that could fold to or from the ones already on the list */
+ /* If folding, we calculate all characters that could fold to or from the
+ * ones already on the list */
if (FOLD && nonbitmap) {
UV start, end; /* End points of code point ranges */
SV* fold_intersection = NULL;
- /* This is a list of all the characters that participate in folds
- * (except marks, etc in multi-char folds */
- if (! PL_utf8_foldable) {
- SV* swash = swash_init("utf8", "Cased", &PL_sv_undef, 1, 0);
- PL_utf8_foldable = _swash_to_invlist(swash);
- SvREFCNT_dec(swash);
- }
-
- /* This is a hash that for a particular fold gives all characters
- * that are involved in it */
- if (! PL_utf8_foldclosures) {
-
- /* If we were unable to find any folds, then we likely won't be
- * able to find the closures. So just create an empty list.
- * Folding will effectively be restricted to the non-Unicode rules
- * hard-coded into Perl. (This case happens legitimately during
- * compilation of Perl itself before the Unicode tables are
- * generated) */
- if (invlist_len(PL_utf8_foldable) == 0) {
- PL_utf8_foldclosures = newHV();
- } else {
- /* If the folds haven't been read in, call a fold function
- * to force that */
- if (! PL_utf8_tofold) {
- U8 dummy[UTF8_MAXBYTES+1];
- STRLEN dummy_len;
-
- /* This particular string is above \xff in both UTF-8 and
- * UTFEBCDIC */
- to_utf8_fold((U8*) "\xC8\x80", dummy, &dummy_len);
- assert(PL_utf8_tofold); /* Verify that worked */
- }
- PL_utf8_foldclosures = _swash_inversion_hash(PL_utf8_tofold);
- }
- }
+ const UV highest_index = invlist_len(nonbitmap) - 1;
+
+ /* In the Latin1 range, the characters that can be folded-to or -from
+ * are precisely the alphabetic characters. If the highest code point
+ * is within Latin1, we can use the compiled-in list, and not have to
+ * go out to disk. If the last element in the array is in the
+ * inversion list set, it starts a range that goes to infinity, so the
+ * maximum of the inversion list is definitely above Latin1.
+ * Otherwise, it starts a range that isn't in the set, so the max is
+ * one less than it */
+ if (! ELEMENT_RANGE_MATCHES_INVLIST(highest_index)
+ && invlist_array(nonbitmap)[highest_index] <= 256)
+ {
+ _invlist_intersection(PL_L1PosixAlpha, nonbitmap, &fold_intersection);
+ }
+ else {
+
+ /* This is a list of all the characters that participate in folds
+ * (except marks, etc in multi-char folds */
+ if (! PL_utf8_foldable) {
+ SV* swash = swash_init("utf8", "Cased", &PL_sv_undef, 1, 0);
+ PL_utf8_foldable = _swash_to_invlist(swash);
+ SvREFCNT_dec(swash);
+ }
- /* Only the characters in this class that participate in folds need be
- * checked. Get the intersection of this class and all the possible
- * characters that are foldable. This can quickly narrow down a large
- * class */
- _invlist_intersection(PL_utf8_foldable, nonbitmap, &fold_intersection);
+ /* This is a hash that for a particular fold gives all characters
+ * that are involved in it */
+ if (! PL_utf8_foldclosures) {
+
+ /* If we were unable to find any folds, then we likely won't be
+ * able to find the closures. So just create an empty list.
+ * Folding will effectively be restricted to the non-Unicode
+ * rules hard-coded into Perl. (This case happens legitimately
+ * during compilation of Perl itself before the Unicode tables
+ * are generated) */
+ if (invlist_len(PL_utf8_foldable) == 0) {
+ PL_utf8_foldclosures = newHV();
+ }
+ else {
+ /* If the folds haven't been read in, call a fold function
+ * to force that */
+ if (! PL_utf8_tofold) {
+ U8 dummy[UTF8_MAXBYTES+1];
+ STRLEN dummy_len;
+
+ /* This particular string is above \xff in both UTF-8
+ * and UTFEBCDIC */
+ to_utf8_fold((U8*) "\xC8\x80", dummy, &dummy_len);
+ assert(PL_utf8_tofold); /* Verify that worked */
+ }
+ PL_utf8_foldclosures =
+ _swash_inversion_hash(PL_utf8_tofold);
+ }
+ }
+
+ /* Only the characters in this class that participate in folds need
+ * be checked. Get the intersection of this class and all the
+ * possible characters that are foldable. This can quickly narrow
+ * down a large class */
+ _invlist_intersection(PL_utf8_foldable, nonbitmap,
+ &fold_intersection);
+ }
/* Now look at the foldable characters in this class individually */
invlist_iterinit(fold_intersection);
while (invlist_iternext(fold_intersection, &start, &end)) {
UV j;
+ /* Locale folding for Latin1 characters is deferred until runtime */
+ if (LOC && start < 256) {
+ start = 256;
+ }
+
/* Look at every character in the range */
for (j = start; j <= end; j++) {
- /* Get its fold */
U8 foldbuf[UTF8_MAXBYTES_CASE+1];
STRLEN foldlen;
- const UV f =
- _to_uni_fold_flags(j, foldbuf, &foldlen,
- (allow_full_fold) ? FOLD_FLAGS_FULL : 0);
+ UV f;
+
+ if (j < 256) {
+
+ /* We have the latin1 folding rules hard-coded here so that
+ * an innocent-looking character class, like /[ks]/i won't
+ * have to go out to disk to find the possible matches.
+ * XXX It would be better to generate these via regen, in
+ * case a new version of the Unicode standard adds new
+ * mappings, though that is not really likely, and may be
+ * caught by the default: case of the switch below. */
+
+ if (PL_fold_latin1[j] != j) {
+
+ /* ASCII is always matched; non-ASCII is matched only
+ * under Unicode rules */
+ if (isASCII(j) || AT_LEAST_UNI_SEMANTICS) {
+ nonbitmap =
+ add_cp_to_invlist(nonbitmap, PL_fold_latin1[j]);
+ }
+ else {
+ depends_list =
+ add_cp_to_invlist(depends_list, PL_fold_latin1[j]);
+ }
+ }
+
+ if (HAS_NONLATIN1_FOLD_CLOSURE(j)
+ && (! isASCII(j) || ! MORE_ASCII_RESTRICTED))
+ {
+ /* Certain Latin1 characters have matches outside
+ * Latin1, or are multi-character. To get here, 'j' is
+ * one of those characters. None of these matches is
+ * valid for ASCII characters under /aa, which is why
+ * the 'if' just above excludes those. The matches
+ * fall into three categories:
+ * 1) They are singly folded-to or -from an above 255
+ * character, e.g., LATIN SMALL LETTER Y WITH
+ * DIAERESIS and LATIN CAPITAL LETTER Y WITH
+ * DIAERESIS;
+ * 2) They are part of a multi-char fold with another
+ * latin1 character; only LATIN SMALL LETTER
+ * SHARP S => "ss" fits this;
+ * 3) They are part of a multi-char fold with a
+ * character outside of Latin1, such as various
+ * ligatures.
+ * We aren't dealing fully with multi-char folds, except
+ * we do deal with the pattern containing a character
+ * that has a multi-char fold (not so much the inverse).
+ * For types 1) and 3), the matches only happen when the
+ * target string is utf8; that's not true for 2), and we
+ * set a flag for it.
+ *
+ * The code below adds the single fold closures for 'j'
+ * to the inversion list. */
+ switch (j) {
+ case 'k':
+ case 'K':
+ /* KELVIN SIGN */
+ nonbitmap =
+ add_cp_to_invlist(nonbitmap, 0x212A);
+ break;
+ case 's':
+ case 'S':
+ /* LATIN SMALL LETTER LONG S */
+ nonbitmap =
+ add_cp_to_invlist(nonbitmap, 0x017F);
+ break;
+ case MICRO_SIGN:
+ nonbitmap = add_cp_to_invlist(nonbitmap,
+ GREEK_SMALL_LETTER_MU);
+ nonbitmap = add_cp_to_invlist(nonbitmap,
+ GREEK_CAPITAL_LETTER_MU);
+ break;
+ case LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE:
+ case LATIN_SMALL_LETTER_A_WITH_RING_ABOVE:
+ /* ANGSTROM SIGN */
+ nonbitmap =
+ add_cp_to_invlist(nonbitmap, 0x212B);
+ break;
+ case LATIN_SMALL_LETTER_Y_WITH_DIAERESIS:
+ nonbitmap = add_cp_to_invlist(nonbitmap,
+ LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS);
+ break;
+ case LATIN_SMALL_LETTER_SHARP_S:
+ nonbitmap = add_cp_to_invlist(nonbitmap,
+ LATIN_CAPITAL_LETTER_SHARP_S);
+
+ /* Under /a, /d, and /u, this can match the two
+ * chars "ss" */
+ if (! MORE_ASCII_RESTRICTED) {
+ add_alternate(&unicode_alternate,
+ (U8 *) "ss", 2);
+
+ /* And under /u or /a, it can match even if
+ * the target is not utf8 */
+ if (AT_LEAST_UNI_SEMANTICS) {
+ ANYOF_FLAGS(ret) |=
+ ANYOF_NONBITMAP_NON_UTF8;
+ }
+ }
+ break;
+ case 'F': case 'f':
+ case 'I': case 'i':
+ case 'L': case 'l':
+ case 'T': case 't':
+ case 'A': case 'a':
+ case 'H': case 'h':
+ case 'J': case 'j':
+ case 'N': case 'n':
+ case 'W': case 'w':
+ case 'Y': case 'y':
+ /* These all are targets of multi-character
+ * folds from code points that require UTF8 to
+ * express, so they can't match unless the
+ * target string is in UTF-8, so no action here
+ * is necessary, as regexec.c properly handles
+ * the general case for UTF-8 matching */
+ break;
+ default:
+ /* Use deprecated warning to increase the
+ * chances of this being output */
+ ckWARN2regdep(RExC_parse, "Perl folding rules are not up-to-date for 0x%"UVXf"; please use the perlbug utility to report;", j);
+ break;
+ }
+ }
+ continue;
+ }
+
+ /* Here is an above Latin1 character. We don't have the rules
+ * hard-coded for it. First, get its fold */
+ f = _to_uni_fold_flags(j, foldbuf, &foldlen,
+ ((allow_full_fold) ? FOLD_FLAGS_FULL : 0)
+ | ((LOC)
+ ? FOLD_FLAGS_LOCALE
+ : (MORE_ASCII_RESTRICTED)
+ ? FOLD_FLAGS_NOMIX_ASCII
+ : 0));
if (foldlen > (STRLEN)UNISKIP(f)) {
/* If any of the folded characters of this are in the
* Latin1 range, tell the regex engine that this can
- * match a non-utf8 target string. The only multi-byte
- * fold whose source is in the Latin1 range (U+00DF)
- * applies only when the target string is utf8, or
- * under unicode rules */
- if (j > 255 || AT_LEAST_UNI_SEMANTICS) {
- while (loc < e) {
-
- /* Can't mix ascii with non- under /aa */
- if (MORE_ASCII_RESTRICTED
- && (isASCII(*loc) != isASCII(j)))
- {
- goto end_multi_fold;
- }
- if (UTF8_IS_INVARIANT(*loc)
- || UTF8_IS_DOWNGRADEABLE_START(*loc))
- {
- /* Can't mix above and below 256 under LOC
- */
- if (LOC) {
- goto end_multi_fold;
- }
- ANYOF_FLAGS(ret)
- |= ANYOF_NONBITMAP_NON_UTF8;
- break;
- }
- loc += UTF8SKIP(loc);
- }
- }
+ * match a non-utf8 target string. */
+ while (loc < e) {
+ if (UTF8_IS_INVARIANT(*loc)
+ || UTF8_IS_DOWNGRADEABLE_START(*loc))
+ {
+ ANYOF_FLAGS(ret)
+ |= ANYOF_NONBITMAP_NON_UTF8;
+ break;
+ }
+ loc += UTF8SKIP(loc);
+ }
add_alternate(&unicode_alternate, foldbuf, foldlen);
- end_multi_fold: ;
- }
-
- /* This is special-cased, as it is the only letter which
- * has both a multi-fold and single-fold in Latin1. All
- * the other chars that have single and multi-folds are
- * always in utf8, and the utf8 folding algorithm catches
- * them */
- if (! LOC && j == LATIN_CAPITAL_LETTER_SHARP_S) {
- stored += set_regclass_bit(pRExC_state,
- ret,
- LATIN_SMALL_LETTER_SHARP_S,
- &l1_fold_invlist, &unicode_alternate);
}
}
- else {
- /* Single character fold. Add everything in its fold
- * closure to the list that this node should match */
+ else {
+ /* Single character fold of above Latin1. Add everything
+ * in its fold closure to the list that this node should
+ * match */
SV** listp;
/* The fold closures data structure is a hash with the keys
/* /aa doesn't allow folds between ASCII and non-;
* /l doesn't allow them between above and below
* 256 */
- if ((MORE_ASCII_RESTRICTED
- && (isASCII(c) != isASCII(j)))
- || (LOC && ((c < 256) != (j < 256))))
+ if ((MORE_ASCII_RESTRICTED && (isASCII(c) != isASCII(j)))
+ || (LOC && ((c < 256) != (j < 256))))
{
continue;
}
- if (c < 256 && AT_LEAST_UNI_SEMANTICS) {
- stored += set_regclass_bit(pRExC_state,
- ret,
- (U8) c,
- &l1_fold_invlist, &unicode_alternate);
- }
- /* It may be that the code point is already in
- * this range or already in the bitmap, in
- * which case we need do nothing */
- else if ((c < start || c > end)
- && (c > 255
- || ! ANYOF_BITMAP_TEST(ret, c)))
- {
+ /* Folds involving non-ascii Latin1 characters
+ * under /d are added to a separate list */
+ if (isASCII(c) || c > 255 || AT_LEAST_UNI_SEMANTICS)
+ {
nonbitmap = add_cp_to_invlist(nonbitmap, c);
+ }
+ else {
+ depends_list = add_cp_to_invlist(depends_list, c);
}
}
}
}
- }
+ }
}
SvREFCNT_dec(fold_intersection);
}
- /* Combine the two lists into one. */
- if (l1_fold_invlist) {
- if (nonbitmap) {
- _invlist_union(nonbitmap, l1_fold_invlist, &nonbitmap);
- SvREFCNT_dec(l1_fold_invlist);
- }
- else {
- nonbitmap = l1_fold_invlist;
- }
- }
-
/* And combine the result (if any) with any inversion list from properties.
* The lists are kept separate up to now because we don't want to fold the
* properties */
if (properties) {
- if (nonbitmap) {
- _invlist_union(nonbitmap, properties, &nonbitmap);
- SvREFCNT_dec(properties);
- }
- else {
- nonbitmap = properties;
- }
+ if (AT_LEAST_UNI_SEMANTICS) {
+ if (nonbitmap) {
+ _invlist_union(nonbitmap, properties, &nonbitmap);
+ SvREFCNT_dec(properties);
+ }
+ else {
+ nonbitmap = properties;
+ }
+ }
+ else {
+
+ /* Under /d, we put the things that match only when the target
+ * string is utf8, into a separate list */
+ SV* nonascii_but_latin1_properties = NULL;
+ _invlist_intersection(properties, PL_Latin1,
+ &nonascii_but_latin1_properties);
+ _invlist_subtract(nonascii_but_latin1_properties, PL_ASCII,
+ &nonascii_but_latin1_properties);
+ _invlist_subtract(properties, nonascii_but_latin1_properties,
+ &properties);
+ if (nonbitmap) {
+ _invlist_union(nonbitmap, properties, &nonbitmap);
+ SvREFCNT_dec(properties);
+ }
+ else {
+ nonbitmap = properties;
+ }
+
+ if (depends_list) {
+ _invlist_union(depends_list, nonascii_but_latin1_properties,
+ &depends_list);
+ SvREFCNT_dec(nonascii_but_latin1_properties);
+ }
+ else {
+ depends_list = nonascii_but_latin1_properties;
+ }
+ }
}
/* Here, <nonbitmap> contains all the code points we can determine at
- * compile time that we haven't put into the bitmap. Go through it, and
+ * compile time that match under all conditions. Go through it, and
* for things that belong in the bitmap, put them there, and delete from
* <nonbitmap> */
if (nonbitmap) {
- /* Above-ASCII code points in /d have to stay in <nonbitmap>, as they
- * possibly only should match when the target string is UTF-8 */
- UV max_cp_to_set = (DEPENDS_SEMANTICS) ? 127 : 255;
-
/* This gets set if we actually need to modify things */
bool change_invlist = FALSE;
int i;
/* Quit if are above what we should change */
- if (start > max_cp_to_set) {
+ if (start > 255) {
break;
}
change_invlist = TRUE;
/* Set all the bits in the range, up to the max that we are doing */
- high = (end < max_cp_to_set) ? end : max_cp_to_set;
+ high = (end < 255) ? end : 255;
for (i = start; i <= (int) high; i++) {
if (! ANYOF_BITMAP_TEST(ret, i)) {
ANYOF_BITMAP_SET(ret, i);
/* Done with loop; remove any code points that are in the bitmap from
* <nonbitmap> */
if (change_invlist) {
- _invlist_subtract(nonbitmap,
- (DEPENDS_SEMANTICS)
- ? PL_ASCII
- : PL_Latin1,
- &nonbitmap);
+ _invlist_subtract(nonbitmap, PL_Latin1, &nonbitmap);
}
/* If have completely emptied it, remove it completely */
}
}
+ /* Combine the two lists into one. */
+ if (depends_list) {
+ if (nonbitmap) {
+ _invlist_union(nonbitmap, depends_list, &nonbitmap);
+ SvREFCNT_dec(depends_list);
+ }
+ else {
+ nonbitmap = depends_list;
+ }
+ }
+
/* Here, we have calculated what code points should be in the character
* class. <nonbitmap> does not overlap the bitmap except possibly in the
* case of DEPENDS rules.
{
struct regexp *ret;
struct regexp *const r = (struct regexp *)SvANY(rx);
- register const I32 npar = r->nparens+1;
PERL_ARGS_ASSERT_REG_TEMP_COPY;
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->offs) {
+ const I32 npar = r->nparens+1;
+ Newx(ret->offs, npar, regexp_paren_pair);
+ Copy(r->offs, ret->offs, npar, regexp_paren_pair);
+ }
if (r->substrs) {
Newx(ret->substrs, 1, struct reg_substr_data);
StructCopy(r->substrs, ret->substrs, struct reg_substr_data);
https://perl5.git.perl.org / perl5.git / blobdiff