# include "regcomp.h"
#endif
+#include "dquote_static.c"
+
#ifdef op
#undef op
#endif /* op */
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)
*/
#define WORST 0 /* Worst case. */
#define HASWIDTH 0x01 /* Known to match non-null strings. */
-#define SIMPLE 0x02 /* Simple enough to be STAR/PLUS operand. */
+
+/* Simple enough to be STAR/PLUS operand, in an EXACT node must be a single
+ * character, and if utf8, must be invariant. */
+#define SIMPLE 0x02
#define SPSTART 0x04 /* Starts with * or +. */
#define TRYAGAIN 0x08 /* Weeded out a declaration. */
#define POSTPONED 0x10 /* (?1),(?&name), (??{...}) or similar */
#define PAREN_SET(u8str,paren) PBYTE(u8str,paren) |= PBITVAL(paren)
#define PAREN_UNSET(u8str,paren) PBYTE(u8str,paren) &= (~PBITVAL(paren))
+/* If not already in utf8, do a longjmp back to the beginning */
+#define UTF8_LONGJMP 42 /* Choose a value not likely to ever conflict */
+#define REQUIRE_UTF8 STMT_START { \
+ if (! UTF) JMPENV_JUMP(UTF8_LONGJMP); \
+ } STMT_END
/* About scan_data_t.
#define SCF_TRIE_RESTUDY 0x4000 /* Do restudy? */
#define SCF_SEEN_ACCEPT 0x8000
-#define UTF (RExC_utf8 != 0)
-#define LOC ((RExC_flags & RXf_PMf_LOCALE) != 0)
-#define FOLD ((RExC_flags & RXf_PMf_FOLD) != 0)
+#define UTF cBOOL(RExC_utf8)
+#define LOC cBOOL(RExC_flags & RXf_PMf_LOCALE)
+#define UNI_SEMANTICS cBOOL(RExC_flags & RXf_PMf_UNICODE)
+#define FOLD cBOOL(RExC_flags & RXf_PMf_FOLD)
#define OOB_UNICODE 12345678
#define OOB_NAMEDCLASS -1
U32 state;
SV *sv=sv_newmortal();
int colwidth= widecharmap ? 6 : 4;
+ U16 word;
GET_RE_DEBUG_FLAGS_DECL;
PERL_ARGS_ASSERT_DUMP_TRIE;
}
PerlIO_printf( Perl_debug_log, "\n" );
}
+ PerlIO_printf(Perl_debug_log, "%*sword_info N:(prev,len)=", (int)depth*2, "");
+ for (word=1; word <= trie->wordcount; word++) {
+ PerlIO_printf(Perl_debug_log, " %d:(%d,%d)",
+ (int)word, (int)(trie->wordinfo[word].prev),
+ (int)(trie->wordinfo[word].len));
+ }
+ PerlIO_printf(Perl_debug_log, "\n" );
}
/*
Dumps a fully constructed but uncompressed trie in list form.
#endif
+
/* make_trie(startbranch,first,last,tail,word_count,flags,depth)
startbranch: the first branch in the whole branch sequence
first : start branch of sequence of branch-exact nodes.
U16 dupe= trie->states[ state ].wordnum; \
regnode * const noper_next = regnext( noper ); \
\
- if (trie->wordlen) \
- trie->wordlen[ curword ] = wordlen; \
DEBUG_r({ \
/* store the word for dumping */ \
SV* tmp; \
}); \
\
curword++; \
+ trie->wordinfo[curword].prev = 0; \
+ trie->wordinfo[curword].len = wordlen; \
+ trie->wordinfo[curword].accept = state; \
\
if ( noper_next < tail ) { \
if (!trie->jump) \
} \
\
if ( dupe ) { \
- /* So it's a dupe. This means we need to maintain a */\
- /* linked-list from the first to the next. */\
- /* we only allocate the nextword buffer when there */\
- /* a dupe, so first time we have to do the allocation */\
- if (!trie->nextword) \
- trie->nextword = (U16 *) \
- PerlMemShared_calloc( word_count + 1, sizeof(U16)); \
- while ( trie->nextword[dupe] ) \
- dupe= trie->nextword[dupe]; \
- trie->nextword[dupe]= curword; \
+ /* It's a dupe. Pre-insert into the wordinfo[].prev */\
+ /* chain, so that when the bits of chain are later */\
+ /* linked together, the dups appear in the chain */\
+ trie->wordinfo[curword].prev = trie->wordinfo[dupe].prev; \
+ trie->wordinfo[dupe].prev = curword; \
} else { \
/* we haven't inserted this word yet. */ \
trie->states[ state ].wordnum = curword; \
regnode *jumper = NULL;
regnode *nextbranch = NULL;
regnode *convert = NULL;
+ U32 *prev_states; /* temp array mapping each state to previous one */
/* we just use folder as a flag in utf8 */
const U8 * const folder = ( flags == EXACTF
? PL_fold
trie->charmap = (U16 *) PerlMemShared_calloc( 256, sizeof(U16) );
if (!(UTF && folder))
trie->bitmap = (char *) PerlMemShared_calloc( ANYOF_BITMAP_SIZE, 1 );
+ trie->wordinfo = (reg_trie_wordinfo *) PerlMemShared_calloc(
+ trie->wordcount+1, sizeof(reg_trie_wordinfo));
+
DEBUG_r({
trie_words = newAV();
});
(int)TRIE_CHARCOUNT(trie), trie->uniquecharcount,
(int)trie->minlen, (int)trie->maxlen )
);
- trie->wordlen = (U32 *) PerlMemShared_calloc( word_count, sizeof(U32) );
/*
We now know what we are dealing with in terms of unique chars and
*/
+ Newx(prev_states, TRIE_CHARCOUNT(trie) + 2, U32);
+ prev_states[1] = 0;
+
if ( (IV)( ( TRIE_CHARCOUNT(trie) + 1 ) * trie->uniquecharcount + 1) > SvIV(re_trie_maxbuff) ) {
/*
Second Pass -- Array Of Lists Representation
}
if ( ! newstate ) {
newstate = next_alloc++;
+ prev_states[newstate] = state;
TRIE_LIST_PUSH( state, charid, newstate );
transcount++;
}
if ( !trie->trans[ state + charid ].next ) {
trie->trans[ state + charid ].next = next_alloc;
trie->trans[ state ].check++;
+ prev_states[TRIE_NODENUM(next_alloc)]
+ = TRIE_NODENUM(state);
next_alloc += trie->uniquecharcount;
}
state = trie->trans[ state + charid ].next;
PerlMemShared_realloc( trie->trans, trie->lasttrans
* sizeof(reg_trie_trans) );
- /* and now dump out the compressed format */
- DEBUG_TRIE_COMPILE_r(dump_trie(trie, widecharmap, revcharmap, depth+1));
-
{ /* Modify the program and insert the new TRIE node*/
U8 nodetype =(U8)(flags & 0xFF);
char *str=NULL;
break;
}
}
+ trie->prefixlen = (state-1);
if (str) {
regnode *n = convert+NODE_SZ_STR(convert);
NEXT_OFF(convert) = NODE_SZ_STR(convert);
Set_Node_Offset_Length(convert,mjd_offset,mjd_nodelen);
});
} /* end node insert */
+
+ /* Finish populating the prev field of the wordinfo array. Walk back
+ * from each accept state until we find another accept state, and if
+ * so, point the first word's .prev field at the second word. If the
+ * second already has a .prev field set, stop now. This will be the
+ * case either if we've already processed that word's accept state,
+ * or that that state had multiple words, and the overspill words
+ * were already linked up earlier.
+ */
+ {
+ U16 word;
+ U32 state;
+ U16 prev;
+
+ for (word=1; word <= trie->wordcount; word++) {
+ prev = 0;
+ if (trie->wordinfo[word].prev)
+ continue;
+ state = trie->wordinfo[word].accept;
+ while (state) {
+ state = prev_states[state];
+ if (!state)
+ break;
+ prev = trie->states[state].wordnum;
+ if (prev)
+ break;
+ }
+ trie->wordinfo[word].prev = prev;
+ }
+ Safefree(prev_states);
+ }
+
+
+ /* and now dump out the compressed format */
+ DEBUG_TRIE_COMPILE_r(dump_trie(trie, widecharmap, revcharmap, depth+1));
+
RExC_rxi->data->data[ data_slot + 1 ] = (void*)widecharmap;
#ifdef DEBUGGING
RExC_rxi->data->data[ data_slot + TRIE_WORDS_OFFSET ] = (void*)trie_words;
}
flags &= ~SCF_DO_STCLASS;
}
- else if (strchr((const char*)PL_varies,OP(scan))) {
+ else if (REGNODE_VARIES(OP(scan))) {
I32 mincount, maxcount, minnext, deltanext, fl = 0;
I32 f = flags, pos_before = 0;
regnode * const oscan = scan;
/* Skip open. */
nxt = regnext(nxt);
- if (!strchr((const char*)PL_simple,OP(nxt))
+ if (!REGNODE_SIMPLE(OP(nxt))
&& !(PL_regkind[OP(nxt)] == EXACT
&& STR_LEN(nxt) == 1))
goto nogo;
#ifdef DEBUGGING
OP(nxt1 + 1) = OPTIMIZED; /* was count. */
- NEXT_OFF(nxt1+ 1) = 0; /* just for consistancy. */
- NEXT_OFF(nxt2) = 0; /* just for consistancy with CURLY. */
+ NEXT_OFF(nxt1+ 1) = 0; /* just for consistency. */
+ NEXT_OFF(nxt2) = 0; /* just for consistency with CURLY. */
OP(nxt) = OPTIMIZED; /* was CLOSE. */
OP(nxt + 1) = OPTIMIZED; /* was count. */
- NEXT_OFF(nxt+ 1) = 0; /* just for consistancy. */
+ NEXT_OFF(nxt+ 1) = 0; /* just for consistency. */
#endif
}
nogo:
nxt = nxt2;
OP(nxt2) = SUCCEED; /* Whas WHILEM */
/* Need to optimize away parenths. */
- if (data->flags & SF_IN_PAR) {
+ if ((data->flags & SF_IN_PAR) && OP(nxt) == CLOSE) {
/* Set the parenth number. */
regnode *nxt1 = NEXTOPER(oscan) + EXTRA_STEP_2ARGS; /* OPEN*/
- if (OP(nxt) != CLOSE)
- FAIL("Panic opt close");
oscan->flags = (U8)ARG(nxt);
if (RExC_open_parens) {
RExC_open_parens[ARG(nxt1)-1]=oscan; /*open->CURLYM*/
data->longest = &(data->longest_float);
}
}
- else if (strchr((const char*)PL_simple,OP(scan))) {
+ else if (REGNODE_SIMPLE(OP(scan))) {
int value = 0;
if (flags & SCF_DO_SUBSTR) {
I32 minlen = 0;
I32 sawplus = 0;
I32 sawopen = 0;
+ U8 jump_ret = 0;
+ dJMPENV;
scan_data_t data;
RExC_state_t RExC_state;
RExC_state_t * const pRExC_state = &RExC_state;
PL_colors[4],PL_colors[5],s);
});
-redo_first_pass:
+ /* Longjmp back to here if have to switch in midstream to utf8 */
+ if (! RExC_orig_utf8) {
+ JMPENV_PUSH(jump_ret);
+ }
+
+ if (jump_ret != 0) {
+ STRLEN len = plen;
+
+ /* Here, we longjmped back. If the cause was other than changing to
+ * utf8, pop our own setjmp, and longjmp to the correct handler */
+ if (jump_ret != UTF8_LONGJMP) {
+ JMPENV_POP;
+ JMPENV_JUMP(jump_ret);
+ }
+
+ GET_RE_DEBUG_FLAGS;
+
+ /* It's possible to write a regexp in ascii that represents Unicode
+ codepoints outside of the byte range, such as via \x{100}. If we
+ detect such a sequence we have to convert the entire pattern to utf8
+ and then recompile, as our sizing calculation will have been based
+ on 1 byte == 1 character, but we will need to use utf8 to encode
+ at least some part of the pattern, and therefore must convert the whole
+ thing.
+ -- dmq */
+ DEBUG_PARSE_r(PerlIO_printf(Perl_debug_log,
+ "UTF8 mismatch! Converting to utf8 for resizing and compile\n"));
+ exp = (char*)Perl_bytes_to_utf8(aTHX_ (U8*)SvPV(pattern, plen), &len);
+ xend = exp + len;
+ RExC_orig_utf8 = RExC_utf8 = 1;
+ SAVEFREEPV(exp);
+ }
+
RExC_precomp = exp;
RExC_flags = pm_flags;
RExC_sawback = 0;
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;
RExC_precomp = NULL;
return(NULL);
}
- if (RExC_utf8 && !RExC_orig_utf8) {
- /* It's possible to write a regexp in ascii that represents Unicode
- codepoints outside of the byte range, such as via \x{100}. If we
- detect such a sequence we have to convert the entire pattern to utf8
- and then recompile, as our sizing calculation will have been based
- on 1 byte == 1 character, but we will need to use utf8 to encode
- at least some part of the pattern, and therefore must convert the whole
- thing.
- XXX: somehow figure out how to make this less expensive...
- -- dmq */
- STRLEN len = plen;
- DEBUG_PARSE_r(PerlIO_printf(Perl_debug_log,
- "UTF8 mismatch! Converting to utf8 for resizing and compile\n"));
- exp = (char*)Perl_bytes_to_utf8(aTHX_ (U8*)exp, &len);
- xend = exp + len;
- RExC_orig_utf8 = RExC_utf8;
- SAVEFREEPV(exp);
- goto redo_first_pass;
+
+ /* Here, finished first pass. Get rid of our setjmp, which we added for
+ * efficiency only if the passed-in string wasn't in utf8, as shown by
+ * RExC_orig_utf8. But if the first pass was redone, that variable will be
+ * 1 here even though the original string wasn't utf8, but in this case
+ * there will have been a long jump */
+ if (jump_ret == UTF8_LONGJMP || ! RExC_orig_utf8) {
+ JMPENV_POP;
}
DEBUG_PARSE_r({
PerlIO_printf(Perl_debug_log,
>> RXf_PMf_STD_PMMOD_SHIFT);
const char *fptr = STD_PAT_MODS; /*"msix"*/
char *p;
- const STRLEN wraplen = plen + has_minus + has_p + has_runon
+ /* Allocate for the worst case, which is all the std flags are turned
+ * on, but this means no caret. We never output a minus, as all those
+ * are defaults, so are covered by the caret */
+ const STRLEN wraplen = plen + has_p + has_runon
+ (sizeof(STD_PAT_MODS) - 1)
+ (sizeof("(?:)") - 1);
p = sv_grow(MUTABLE_SV(rx), wraplen + 1);
- SvCUR_set(rx, wraplen);
SvPOK_on(rx);
SvFLAGS(rx) |= SvUTF8(pattern);
*p++='('; *p++='?';
+
+ /* If a default, cover it using the caret */
+ if (has_minus || (r->extflags & ~(RXf_PMf_LOCALE|RXf_PMf_UNICODE))) {
+ *p++= DEFAULT_PAT_MOD;
+ }
+ if (r->extflags & RXf_PMf_LOCALE) {
+ *p++ = LOCALE_PAT_MOD;
+ }
+ else if (r->extflags & RXf_PMf_UNICODE) {
+ *p++ = UNICODE_PAT_MOD;
+ }
if (has_p)
*p++ = KEEPCOPY_PAT_MOD; /*'p'*/
{
- char *r = p + (sizeof(STD_PAT_MODS) - 1) + has_minus - 1;
- char *colon = r + 1;
char ch;
-
while((ch = *fptr++)) {
if(reganch & 1)
*p++ = ch;
- else
- *r-- = ch;
reganch >>= 1;
}
- if(has_minus) {
- *r = '-';
- p = colon;
- }
}
*p++ = ':';
*p++ = '\n';
*p++ = ')';
*p = 0;
+ SvCUR_set(rx, p - SvPVX_const(rx));
}
r->intflags = 0;
ri->regstclass = trie_op;
}
#endif
- else if (strchr((const char*)PL_simple,OP(first)))
+ else if (REGNODE_SIMPLE(OP(first)))
ri->regstclass = first;
else if (PL_regkind[OP(first)] == BOUND ||
PL_regkind[OP(first)] == NBOUND)
#endif
#ifdef DEBUGGING
if (RExC_paren_names) {
- ri->name_list_idx = add_data( pRExC_state, 1, "p" );
+ ri->name_list_idx = add_data( pRExC_state, 1, "a" );
ri->data->data[ri->name_list_idx] = (void*)SvREFCNT_inc(RExC_paren_name_list);
} else
#endif
if (flags & RXapif_FETCH) {
return reg_named_buff_fetch(rx, key, flags);
} else if (flags & (RXapif_STORE | RXapif_DELETE | RXapif_CLEAR)) {
- Perl_croak(aTHX_ "%s", PL_no_modify);
+ Perl_croak_no_modify(aTHX);
return NULL;
} else if (flags & RXapif_EXISTS) {
return reg_named_buff_exists(rx, key, flags)
PERL_UNUSED_ARG(value);
if (!PL_localizing)
- Perl_croak(aTHX_ "%s", PL_no_modify);
+ Perl_croak_no_modify(aTHX);
}
I32
if (*RExC_parse == '?') { /* (?...) */
bool is_logical = 0;
const char * const seqstart = RExC_parse;
+ bool has_use_defaults = FALSE;
RExC_parse++;
paren = *RExC_parse++;
RExC_parse++;
case '=': /* (?=...) */
RExC_seen_zerolen++;
- break;
+ break;
case '!': /* (?!...) */
RExC_seen_zerolen++;
if (*RExC_parse == ')') {
RExC_parse--; /* for vFAIL to print correctly */
vFAIL("Sequence (? incomplete");
break;
+ case DEFAULT_PAT_MOD: /* Use default flags with the exceptions
+ that follow */
+ has_use_defaults = TRUE;
+ STD_PMMOD_FLAGS_CLEAR(&RExC_flags);
+ RExC_flags &= ~(RXf_PMf_LOCALE|RXf_PMf_UNICODE);
+ goto parse_flags;
default:
--RExC_parse;
parse_flags: /* (?i) */
{
U32 posflags = 0, negflags = 0;
U32 *flagsp = &posflags;
+ bool has_charset_modifier = 0;
while (*RExC_parse) {
/* && strchr("iogcmsx", *RExC_parse) */
and must be globally applied -- japhy */
switch (*RExC_parse) {
CASE_STD_PMMOD_FLAGS_PARSE_SET(flagsp);
+ case LOCALE_PAT_MOD:
+ if (has_charset_modifier || flagsp == &negflags) {
+ goto fail_modifiers;
+ }
+ *flagsp &= ~RXf_PMf_UNICODE;
+ *flagsp |= RXf_PMf_LOCALE;
+ has_charset_modifier = 1;
+ break;
+ case UNICODE_PAT_MOD:
+ if (has_charset_modifier || flagsp == &negflags) {
+ goto fail_modifiers;
+ }
+ *flagsp &= ~RXf_PMf_LOCALE;
+ *flagsp |= RXf_PMf_UNICODE;
+ has_charset_modifier = 1;
+ break;
+ case DUAL_PAT_MOD:
+ if (has_use_defaults
+ || has_charset_modifier
+ || flagsp == &negflags)
+ {
+ goto fail_modifiers;
+ }
+ *flagsp &= ~(RXf_PMf_LOCALE|RXf_PMf_UNICODE);
+ has_charset_modifier = 1;
+ break;
case ONCE_PAT_MOD: /* 'o' */
case GLOBAL_PAT_MOD: /* 'g' */
if (SIZE_ONLY && ckWARN(WARN_REGEXP)) {
}
break;
case '-':
- if (flagsp == &negflags) {
+ /* A flag is a default iff it is following a minus, so
+ * if there is a minus, it means will be trying to
+ * re-specify a default which is an error */
+ if (has_use_defaults || flagsp == &negflags) {
+ fail_modifiers:
RExC_parse++;
vFAIL3("Sequence (%.*s...) not recognized", RExC_parse-seqstart, seqstart);
/*NOTREACHED*/
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 valuep 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, 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;
- if (*RExC_parse != '{' ||
- (*RExC_parse == '{' && RExC_parse[1]
- && strchr("0123456789", RExC_parse[1])))
- {
- GET_RE_DEBUG_FLAGS_DECL;
- if (valuep)
+ /* 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("Missing braces on \\N{}");
- GET_RE_DEBUG_FLAGS;
+ 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;
Set_Node_Length(ret, 1); /* MJD */
return ret;
}
- 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;
- len = (STRLEN)(endbrace - name - 2);
- cp = grok_hex(name + 2, &len, &fl, NULL);
- if ( len != (STRLEN)(endbrace - name - 2) ) {
- cp = 0xFFFD;
- }
- if ( valuep ) {
- if (cp > 0xff) RExC_utf8 = 1;
- *valuep = cp;
- return NULL;
- }
- /* Need to convert to utf8 if either: won't fit into a byte, or the re
- * is going to be in utf8 and the representation changes under utf8. */
- if (cp > 0xff || (RExC_utf8 && ! UNI_IS_INVARIANT(cp))) {
- U8 string[UTF8_MAXBYTES+1];
- U8 *tmps;
- RExC_utf8 = 1;
- tmps = uvuni_to_utf8(string, cp);
- sv_str = newSVpvn_utf8((char*)string, tmps - string, TRUE);
- } else { /* Otherwise, no need for utf8, can skip that step */
- char string;
- string = (char)cp;
- sv_str= newSVpvn(&string, 1);
+ /* 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{}");
+ }
+
+ 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 (endbrace == RExC_parse) { /* empty: \N{} */
+ if (! valuep) {
+ RExC_parse = endbrace + 1;
+ return reg_node(pRExC_state,NOTHING);
}
- } 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{%" SVf "}) unknown: "
- "(possibly a missing \"use charnames ...\")",
- SVfARG(sv_name));
- }
- if (!cvp || !SvOK(*cvp)) { /* when $^H{charnames} = undef; */
- vFAIL2("Constant(\\N{%" SVf "}): "
- "$^H{charnames} is not defined", SVfARG(sv_name));
- }
-
-
-
- if (!RExC_charnames) {
- /* make sure our cache is allocated */
- RExC_charnames = newHV();
- sv_2mortal(MUTABLE_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);
- SPAGAIN ;
-
- if (count == 1) { /* XXXX is this right? dmq */
- sv_str = POPs;
- SvREFCNT_inc_simple_void(sv_str);
- }
-
- PUTBACK ;
- FREETMPS ;
- LEAVE ;
-
- if ( !sv_str || !SvOK(sv_str) ) {
- vFAIL2("Constant(\\N{%" SVf "}): Call to &{$^H{charnames}} "
- "did not return a defined value", SVfARG(sv_name));
- }
- if (hv_store_ent( RExC_charnames, sv_name, sv_str, 0))
- cached = 1;
- }
+ 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 (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) {
- ckWARN2reg(RExC_parse,
- "Ignoring excess chars from \\N{%" SVf "} in character class",
- SVfARG(sv_name)
- );
- }
- } else if (SIZE_ONLY) {
- ckWARN2reg(RExC_parse,
- "Ignoring zero length \\N{%" SVf "} in character class",
- SVfARG(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 { /* zero length */
- ret = reg_node(pRExC_state,NOTHING);
+
+ REQUIRE_UTF8; /* 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 = RExC_parse + strcspn(RExC_parse, ".}");
+ if (endchar < endbrace) {
+ ckWARNreg(endchar, "Using just the first character returned by \\N{} in character class");
+ }
+
+ 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 */
}
- SvREFCNT_dec(sv_name);
- if (!cached)
- SvREFCNT_dec(sv_str);
- return ret;
+ else { /* Not a char class */
+ char *s; /* String to put in generated EXACT node */
+ STRLEN len = 0; /* Its current byte 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 exceed 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 = RExC_parse + strcspn(RExC_parse, ".}");
+
+ /* 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;
}
ender = ASCII_TO_NATIVE('\007');
p++;
break;
+ case 'o':
+ {
+ STRLEN brace_len = len;
+ UV result;
+ const char* error_msg;
+
+ bool valid = grok_bslash_o(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
+ {
+ ender = result;
+ }
+ if (PL_encoding && ender < 0x100) {
+ goto recode_encoding;
+ }
+ if (ender > 0xff) {
+ REQUIRE_UTF8;
+ }
+ break;
+ }
case 'x':
if (*++p == '{') {
char* const e = strchr(p, '}');
STRLEN numlen = e - p - 1;
ender = grok_hex(p + 1, &numlen, &flags, NULL);
if (ender > 0xff)
- RExC_utf8 = 1;
+ REQUIRE_UTF8;
p = e + 1;
}
}
break;
case 'c':
p++;
- ender = UCHARAT(p++);
- ender = toCTRL(ender);
+ ender = grok_bslash_c(*p++, SIZE_ONLY);
break;
case '0': case '1': case '2': case '3':case '4':
case '5': case '6': case '7': case '8':case '9':
if (*p == '0' ||
- (isDIGIT(p[1]) && atoi(p) >= RExC_npar) ) {
- I32 flags = 0;
+ (isOCTAL(p[1]) && atoi(p) >= RExC_npar))
+ {
+ I32 flags = PERL_SCAN_SILENT_ILLDIGIT;
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");
+ if (ender > 0xff) {
+ REQUIRE_UTF8;
}
p += numlen;
}
ender = reg_recode((const char)(U8)ender, &enc);
if (!enc && SIZE_ONLY)
ckWARNreg(p, "Invalid escape in the specified encoding");
- RExC_utf8 = 1;
+ REQUIRE_UTF8;
}
break;
case '\0':
case 'b': value = '\b'; break;
case 'e': value = ASCII_TO_NATIVE('\033');break;
case 'a': value = ASCII_TO_NATIVE('\007');break;
+ case 'o':
+ RExC_parse--; /* function expects to be pointed at the 'o' */
+ {
+ const char* error_msg;
+ bool valid = grok_bslash_o(RExC_parse,
+ &value,
+ &numlen,
+ &error_msg,
+ SIZE_ONLY);
+ RExC_parse += numlen;
+ if (! valid) {
+ vFAIL(error_msg);
+ }
+ }
+ if (PL_encoding && value < 0x100) {
+ goto recode_encoding;
+ }
+ break;
case 'x':
if (*RExC_parse == '{') {
I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
goto recode_encoding;
break;
case 'c':
- value = UCHARAT(RExC_parse++);
- value = toCTRL(value);
+ value = grok_bslash_c(*RExC_parse++, 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':
{
- I32 flags = 0;
+ /* Take 1-3 octal digits */
+ I32 flags = PERL_SCAN_SILENT_ILLDIGIT;
numlen = 3;
value = grok_oct(--RExC_parse, &numlen, &flags, NULL);
RExC_parse += numlen;
break;
}
default:
- if (!SIZE_ONLY && isALPHA(value))
+ /* Allow \_ to not give an error */
+ if (!SIZE_ONLY && isALNUM(value) && value != '_') {
ckWARN2reg(RExC_parse,
"Unrecognized escape \\%c in character class passed through",
(int)value);
+ }
break;
}
} /* end of \blah */
#endif
/*
- - regcurly - a little FSA that accepts {\d+,?\d*}
- */
-STATIC I32
-S_regcurly(register const char *s)
-{
- PERL_ARGS_ASSERT_REGCURLY;
-
- if (*s++ != '{')
- return FALSE;
- if (!isDIGIT(*s))
- return FALSE;
- while (isDIGIT(*s))
- s++;
- if (*s == ',')
- s++;
- while (isDIGIT(*s))
- s++;
- if (*s != '}')
- return FALSE;
- return TRUE;
-}
-
-
-/*
- regdump - dump a regexp onto Perl_debug_log in vaguely comprehensible form
*/
#ifdef DEBUGGING
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) {
while (--n >= 0) {
/* If you add a ->what type here, update the comment in regcomp.h */
switch (ri->data->what[n]) {
+ case 'a':
case 's':
case 'S':
case 'u':
PerlMemShared_free(trie->trans);
if (trie->bitmap)
PerlMemShared_free(trie->bitmap);
- if (trie->wordlen)
- PerlMemShared_free(trie->wordlen);
if (trie->jump)
PerlMemShared_free(trie->jump);
- if (trie->nextword)
- PerlMemShared_free(trie->nextword);
+ PerlMemShared_free(trie->wordinfo);
/* do this last!!!! */
PerlMemShared_free(ri->data->data[n]);
}
Safefree(ri);
}
-#define sv_dup_inc(s,t) SvREFCNT_inc(sv_dup(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 av_dup_inc(s,t) MUTABLE_AV(sv_dup_inc((const SV *)s,t))
+#define hv_dup_inc(s,t) MUTABLE_HV(sv_dup_inc((const SV *)s,t))
#define SAVEPVN(p,n) ((p) ? savepvn(p,n) : NULL)
/*
for (i = 0; i < count; i++) {
d->what[i] = ri->data->what[i];
switch (d->what[i]) {
- /* legal options are one of: sSfpontTu
+ /* legal options are one of: sSfpontTua
see also regcomp.h and pregfree() */
+ case 'a': /* actually an AV, but the dup function is identical. */
case 's':
case 'S':
case 'p': /* actually an AV, but the dup function is identical. */
if (!p)
return(NULL);
+ if (OP(p) > REGNODE_MAX) { /* regnode.type is unsigned */
+ Perl_croak(aTHX_ "Corrupted regexp opcode %d > %d", (int)OP(p), (int)REGNODE_MAX);
+ }
+
offset = (reg_off_by_arg[OP(p)] ? ARG(p) : NEXT_OFF(p));
if (offset == 0)
return(NULL);
state = (struct re_save_state *)(PL_savestack + PL_savestack_ix);
PL_savestack_ix += SAVESTACK_ALLOC_FOR_RE_SAVE_STATE;
- SSPUSHINT(SAVEt_RE_STATE);
+ SSPUSHUV(SAVEt_RE_STATE);
Copy(&PL_reg_state, state, 1, struct re_save_state);
https://perl5.git.perl.org / perl5.git / blobdiff