static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
int ret, flags = 0;
PCRE2_SIZE *ovector;
PCRE2_UCHAR errbuf[256];
if (eflags & REG_NOTBOL)
flags |= PCRE2_NOTBOL;
if (p->pcre2_jit_on)
ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line,
eol - line, 0, flags, p->pcre2_match_data,
NULL);
else
ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line,
eol - line, 0, flags, p->pcre2_match_data,
NULL);
if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) {
pcre2_get_error_message(ret, errbuf, sizeof(errbuf));
die("%s failed with error code %d: %s",
(p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret,
errbuf);
}
if (ret > 0) {
ovector = pcre2_get_ovector_pointer(p->pcre2_match_data);
ret = 0;
match->rm_so = (int)ovector[0];
match->rm_eo = (int)ovector[1];
}
return ret;
}
bool report_matches(const wchar_t *arg) {
// A return value of true means all is well (even if no matches were found), false indicates
// an unrecoverable error.
if (regex.code == 0) {
// pcre2_compile() failed.
return false;
}
int matched = 0;
// See pcre2demo.c for an explanation of this logic.
PCRE2_SIZE arglen = wcslen(arg);
int rc = report_match(
arg, pcre2_match(regex.code, PCRE2_SPTR(arg), arglen, 0, 0, regex.match, 0));
if (rc < 0) { // pcre2 match error.
return false;
} else if (rc == 0) { // no match
return true;
}
matched++;
total_matched++;
if (opts.invert_match) {
return true;
}
// Report any additional matches.
PCRE2_SIZE *ovector = pcre2_get_ovector_pointer(regex.match);
while (opts.all || matched == 0) {
uint32_t options = 0;
PCRE2_SIZE offset = ovector[1]; // start at end of previous match
if (ovector[0] == ovector[1]) {
if (ovector[0] == arglen) {
break;
}
options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
}
rc = report_match(arg, pcre2_match(regex.code, PCRE2_SPTR(arg), arglen, offset, options,
regex.match, 0));
if (rc < 0) {
return false;
}
if (rc == 0) {
if (options == 0) { // all matches found
break;
}
ovector[1] = offset + 1;
continue;
}
matched++;
total_matched++;
}
return true;
}
int report_match(const wchar_t *arg, int pcre2_rc) {
// Return values: -1 = error, 0 = no match, 1 = match.
if (pcre2_rc == PCRE2_ERROR_NOMATCH) {
if (opts.invert_match && !opts.quiet) {
if (opts.index) {
streams.out.append_format(L"1 %lu\n", wcslen(arg));
} else {
streams.out.append(arg);
streams.out.push_back(L'\n');
}
}
return opts.invert_match ? 1 : 0;
} else if (pcre2_rc < 0) {
string_error(streams, _(L"%ls: Regular expression match error: %ls\n"), argv0,
pcre2_strerror(pcre2_rc).c_str());
return -1;
} else if (pcre2_rc == 0) {
// The output vector wasn't big enough. Should not happen.
string_error(streams, _(L"%ls: Regular expression internal error\n"), argv0);
return -1;
} else if (opts.invert_match) {
return 0;
}
if (opts.entire) {
streams.out.append(arg);
streams.out.push_back(L'\n');
}
PCRE2_SIZE *ovector = pcre2_get_ovector_pointer(regex.match);
for (int j = (opts.entire ? 1 : 0); j < pcre2_rc; j++) {
PCRE2_SIZE begin = ovector[2 * j];
PCRE2_SIZE end = ovector[2 * j + 1];
if (begin != PCRE2_UNSET && end != PCRE2_UNSET && !opts.quiet) {
if (opts.index) {
streams.out.append_format(L"%lu %lu", (unsigned long)(begin + 1),
(unsigned long)(end - begin));
} else if (end > begin) {
// May have end < begin if \K is used.
streams.out.append(wcstring(&arg[begin], end - begin));
}
streams.out.push_back(L'\n');
}
}
return opts.invert_match ? 0 : 1;
}
int preg_match(char *pattern, char *subject, char *matches[]) {
int rc;
//int count;
PCRE2_SIZE *ovector;
pcre2_code *compiled_re = get_compiled_re(pattern);
PCRE2_SPTR pcre2_subject = (PCRE2_SPTR)subject;
size_t subject_length = strlen((char *)subject);
pcre2_match_data *match_data;
match_data = pcre2_match_data_create_from_pattern(compiled_re, NULL);
rc = pcre2_match(
compiled_re,
pcre2_subject,
subject_length,
0,
0,
match_data,
NULL);
if (rc < 1) {
pcre2_match_data_free(match_data); /* Release memory used for the match */
pcre2_code_free(compiled_re); /* data and the compiled pattern. */
return 0;
}
ovector = pcre2_get_ovector_pointer(match_data);
matches = malloc(rc * sizeof(char*));
for (int i = 0; i < rc; i++)
{
PCRE2_SPTR substring_start = pcre2_subject + ovector[2*i];
size_t substring_length = ovector[2*i+1] - ovector[2*i];
//printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
matches[i] = strndup((char *)substring_start, (int)substring_length);
}
return rc;
}
tb_long_t tb_regex_match(tb_regex_ref_t self, tb_char_t const* cstr, tb_size_t size, tb_size_t start, tb_size_t* plength, tb_vector_ref_t* presults)
{
// check
tb_regex_t* regex = (tb_regex_t*)self;
tb_assert_and_check_return_val(regex && regex->code && regex->match_data && cstr, -1);
// done
tb_long_t ok = -1;
do
{
// clear length first
if (plength) *plength = 0;
// end?
tb_check_break(start < size);
// init options
#ifdef __tb_debug__
tb_uint32_t options = 0;
#else
tb_uint32_t options = PCRE2_NO_UTF_CHECK;
#endif
// match it
tb_long_t count = pcre2_match(regex->code, (PCRE2_SPTR)cstr, (PCRE2_SIZE)size, (PCRE2_SIZE)start, options, regex->match_data, tb_null);
if (count < 0)
{
// no match?
tb_check_break(count != PCRE2_ERROR_NOMATCH);
#if defined(__tb_debug__) && !defined(TB_CONFIG_OS_WINDOWS)
// get error info
PCRE2_UCHAR info[256];
pcre2_get_error_message(count, info, sizeof(info));
// trace
tb_trace_d("match failed at offset %lu: error: %ld, %s\n", start, count, info);
#endif
// end
break;
}
// check
tb_assertf_and_check_break(count, "ovector has not enough space!");
// get output vector
PCRE2_SIZE* ovector = pcre2_get_ovector_pointer(regex->match_data);
tb_assert_and_check_break(ovector);
// get the match offset and length
tb_size_t offset = (tb_size_t)ovector[0];
tb_size_t length = (tb_size_t)ovector[1] - ovector[0];
tb_assert_and_check_break(offset + length <= size);
// trace
tb_trace_d("matched count: %lu, offset: %lu, length: %lu", count, offset, length);
// save results
if (presults)
{
// init results if not exists
tb_vector_ref_t results = *presults;
if (!results)
{
// init it
if (!regex->results) regex->results = tb_vector_init(16, tb_element_mem(sizeof(tb_regex_match_t), tb_regex_match_exit, tb_null));
// save it
*presults = results = regex->results;
}
tb_assert_and_check_break(results);
// clear it first
tb_vector_clear(results);
// done
tb_long_t i = 0;
tb_regex_match_t entry;
for (i = 0; i < count; i++)
{
// get substring offset and length
tb_size_t substr_offset = ovector[i << 1];
tb_size_t substr_length = ovector[(i << 1) + 1] - ovector[i << 1];
tb_assert_and_check_break(substr_offset + substr_length <= size);
// make match entry
entry.cstr = tb_strndup(cstr + substr_offset, substr_length);
entry.size = substr_length;
entry.start = substr_offset;
tb_assert_and_check_break(entry.cstr);
// trace
tb_trace_d(" matched: [%lu, %lu]: %s", entry.start, entry.size, entry.cstr);
// append it
tb_vector_insert_tail(results, &entry);
}
tb_assert_and_check_break(i == count);
}
// save length
if (plength) *plength = length;
// ok
ok = offset;
} while (0);
// ok?
return ok;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length,
PCRE2_SIZE start_offset, uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext, PCRE2_SPTR replacement, PCRE2_SIZE rlength,
PCRE2_UCHAR *buffer, PCRE2_SIZE *blength)
{
int rc;
int subs;
int forcecase = 0;
int forcecasereset = 0;
uint32_t ovector_count;
uint32_t goptions = 0;
uint32_t suboptions;
BOOL match_data_created = FALSE;
BOOL literal = FALSE;
BOOL overflowed = FALSE;
#ifdef SUPPORT_UNICODE
BOOL utf = (code->overall_options & PCRE2_UTF) != 0;
#endif
PCRE2_UCHAR temp[6];
PCRE2_SPTR ptr;
PCRE2_SPTR repend;
PCRE2_SIZE extra_needed = 0;
PCRE2_SIZE buff_offset, buff_length, lengthleft, fraglength;
PCRE2_SIZE *ovector;
buff_offset = 0;
lengthleft = buff_length = *blength;
*blength = PCRE2_UNSET;
/* Partial matching is not valid. */
if ((options & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) != 0)
return PCRE2_ERROR_BADOPTION;
/* If no match data block is provided, create one. */
if (match_data == NULL)
{
pcre2_general_context *gcontext = (mcontext == NULL)?
(pcre2_general_context *)code :
(pcre2_general_context *)mcontext;
match_data = pcre2_match_data_create_from_pattern(code, gcontext);
if (match_data == NULL) return PCRE2_ERROR_NOMEMORY;
match_data_created = TRUE;
}
ovector = pcre2_get_ovector_pointer(match_data);
ovector_count = pcre2_get_ovector_count(match_data);
/* Find lengths of zero-terminated strings and the end of the replacement. */
if (length == PCRE2_ZERO_TERMINATED) length = PRIV(strlen)(subject);
if (rlength == PCRE2_ZERO_TERMINATED) rlength = PRIV(strlen)(replacement);
repend = replacement + rlength;
/* Check UTF replacement string if necessary. */
#ifdef SUPPORT_UNICODE
if (utf && (options & PCRE2_NO_UTF_CHECK) == 0)
{
rc = PRIV(valid_utf)(replacement, rlength, &(match_data->rightchar));
if (rc != 0)
{
match_data->leftchar = 0;
goto EXIT;
}
}
#endif /* SUPPORT_UNICODE */
/* Save the substitute options and remove them from the match options. */
suboptions = options & SUBSTITUTE_OPTIONS;
options &= ~SUBSTITUTE_OPTIONS;
/* Copy up to the start offset */
if (start_offset > length)
{
match_data->leftchar = 0;
rc = PCRE2_ERROR_BADOFFSET;
goto EXIT;
}
CHECKMEMCPY(subject, start_offset);
/* Loop for global substituting. */
subs = 0;
do
{
PCRE2_SPTR ptrstack[PTR_STACK_SIZE];
uint32_t ptrstackptr = 0;
rc = pcre2_match(code, subject, length, start_offset, options|goptions,
match_data, mcontext);
#ifdef SUPPORT_UNICODE
if (utf) options |= PCRE2_NO_UTF_CHECK; /* Only need to check once */
#endif
/* Any error other than no match returns the error code. No match when not
doing the special after-empty-match global rematch, or when at the end of the
subject, breaks the global loop. Otherwise, advance the starting point by one
character, copying it to the output, and try again. */
if (rc < 0)
{
PCRE2_SIZE save_start;
if (rc != PCRE2_ERROR_NOMATCH) goto EXIT;
if (goptions == 0 || start_offset >= length) break;
/* Advance by one code point. Then, if CRLF is a valid newline sequence and
we have advanced into the middle of it, advance one more code point. In
other words, do not start in the middle of CRLF, even if CR and LF on their
own are valid newlines. */
save_start = start_offset++;
if (subject[start_offset-1] == CHAR_CR &&
code->newline_convention != PCRE2_NEWLINE_CR &&
code->newline_convention != PCRE2_NEWLINE_LF &&
start_offset < length &&
subject[start_offset] == CHAR_LF)
start_offset++;
/* Otherwise, in UTF mode, advance past any secondary code points. */
else if ((code->overall_options & PCRE2_UTF) != 0)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
while (start_offset < length && (subject[start_offset] & 0xc0) == 0x80)
start_offset++;
#elif PCRE2_CODE_UNIT_WIDTH == 16
while (start_offset < length &&
(subject[start_offset] & 0xfc00) == 0xdc00)
start_offset++;
#endif
}
/* Copy what we have advanced past, reset the special global options, and
continue to the next match. */
fraglength = start_offset - save_start;
CHECKMEMCPY(subject + save_start, fraglength);
goptions = 0;
continue;
}
/* Handle a successful match. Matches that use \K to end before they start
are not supported. */
if (ovector[1] < ovector[0])
{
rc = PCRE2_ERROR_BADSUBSPATTERN;
goto EXIT;
}
/* Count substitutions with a paranoid check for integer overflow; surely no
real call to this function would ever hit this! */
if (subs == INT_MAX)
{
rc = PCRE2_ERROR_TOOMANYREPLACE;
goto EXIT;
}
subs++;
/* Copy the text leading up to the match. */
if (rc == 0) rc = ovector_count;
fraglength = ovector[0] - start_offset;
CHECKMEMCPY(subject + start_offset, fraglength);
/* Process the replacement string. Literal mode is set by \Q, but only in
extended mode when backslashes are being interpreted. In extended mode we
must handle nested substrings that are to be reprocessed. */
ptr = replacement;
for (;;)
{
uint32_t ch;
unsigned int chlen;
/* If at the end of a nested substring, pop the stack. */
if (ptr >= repend)
{
if (ptrstackptr <= 0) break; /* End of replacement string */
repend = ptrstack[--ptrstackptr];
ptr = ptrstack[--ptrstackptr];
continue;
}
/* Handle the next character */
if (literal)
{
if (ptr[0] == CHAR_BACKSLASH && ptr < repend - 1 && ptr[1] == CHAR_E)
{
literal = FALSE;
ptr += 2;
continue;
}
goto LOADLITERAL;
}
/* Not in literal mode. */
if (*ptr == CHAR_DOLLAR_SIGN)
{
int group, n;
uint32_t special = 0;
BOOL inparens;
BOOL star;
PCRE2_SIZE sublength;
PCRE2_SPTR text1_start = NULL;
PCRE2_SPTR text1_end = NULL;
PCRE2_SPTR text2_start = NULL;
PCRE2_SPTR text2_end = NULL;
PCRE2_UCHAR next;
PCRE2_UCHAR name[33];
if (++ptr >= repend) goto BAD;
if ((next = *ptr) == CHAR_DOLLAR_SIGN) goto LOADLITERAL;
group = -1;
n = 0;
inparens = FALSE;
star = FALSE;
if (next == CHAR_LEFT_CURLY_BRACKET)
{
if (++ptr >= repend) goto BAD;
next = *ptr;
inparens = TRUE;
}
if (next == CHAR_ASTERISK)
{
if (++ptr >= repend) goto BAD;
next = *ptr;
star = TRUE;
}
if (!star && next >= CHAR_0 && next <= CHAR_9)
{
group = next - CHAR_0;
while (++ptr < repend)
{
next = *ptr;
if (next < CHAR_0 || next > CHAR_9) break;
group = group * 10 + next - CHAR_0;
/* A check for a number greater than the hightest captured group
is sufficient here; no need for a separate overflow check. If unknown
groups are to be treated as unset, just skip over any remaining
digits and carry on. */
if (group > code->top_bracket)
{
if ((suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
while (++ptr < repend && *ptr >= CHAR_0 && *ptr <= CHAR_9);
break;
}
else
{
rc = PCRE2_ERROR_NOSUBSTRING;
goto PTREXIT;
}
}
}
}
else
{
const uint8_t *ctypes = code->tables + ctypes_offset;
while (MAX_255(next) && (ctypes[next] & ctype_word) != 0)
{
name[n++] = next;
if (n > 32) goto BAD;
if (++ptr >= repend) break;
next = *ptr;
}
if (n == 0) goto BAD;
name[n] = 0;
}
/* In extended mode we recognize ${name:+set text:unset text} and
${name:-default text}. */
if (inparens)
{
if ((suboptions & PCRE2_SUBSTITUTE_EXTENDED) != 0 &&
!star && ptr < repend - 2 && next == CHAR_COLON)
{
special = *(++ptr);
if (special != CHAR_PLUS && special != CHAR_MINUS)
{
rc = PCRE2_ERROR_BADSUBSTITUTION;
goto PTREXIT;
}
text1_start = ++ptr;
rc = find_text_end(code, &ptr, repend, special == CHAR_MINUS);
if (rc != 0) goto PTREXIT;
text1_end = ptr;
if (special == CHAR_PLUS && *ptr == CHAR_COLON)
{
text2_start = ++ptr;
rc = find_text_end(code, &ptr, repend, TRUE);
if (rc != 0) goto PTREXIT;
text2_end = ptr;
}
}
else
{
if (ptr >= repend || *ptr != CHAR_RIGHT_CURLY_BRACKET)
{
rc = PCRE2_ERROR_REPMISSINGBRACE;
goto PTREXIT;
}
}
ptr++;
}
/* Have found a syntactically correct group number or name, or *name.
Only *MARK is currently recognized. */
if (star)
{
if (PRIV(strcmp_c8)(name, STRING_MARK) == 0)
{
PCRE2_SPTR mark = pcre2_get_mark(match_data);
if (mark != NULL)
{
PCRE2_SPTR mark_start = mark;
while (*mark != 0) mark++;
fraglength = mark - mark_start;
CHECKMEMCPY(mark_start, fraglength);
}
}
else goto BAD;
}
/* Substitute the contents of a group. We don't use substring_copy
functions any more, in order to support case forcing. */
else
{
PCRE2_SPTR subptr, subptrend;
/* Find a number for a named group. In case there are duplicate names,
search for the first one that is set. If the name is not found when
PCRE2_SUBSTITUTE_UNKNOWN_EMPTY is set, set the group number to a
non-existent group. */
if (group < 0)
{
PCRE2_SPTR first, last, entry;
rc = pcre2_substring_nametable_scan(code, name, &first, &last);
if (rc == PCRE2_ERROR_NOSUBSTRING &&
(suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
group = code->top_bracket + 1;
}
else
{
if (rc < 0) goto PTREXIT;
for (entry = first; entry <= last; entry += rc)
{
uint32_t ng = GET2(entry, 0);
if (ng < ovector_count)
{
if (group < 0) group = ng; /* First in ovector */
if (ovector[ng*2] != PCRE2_UNSET)
{
group = ng; /* First that is set */
break;
}
}
}
/* If group is still negative, it means we did not find a group
that is in the ovector. Just set the first group. */
if (group < 0) group = GET2(first, 0);
}
}
/* We now have a group that is identified by number. Find the length of
the captured string. If a group in a non-special substitution is unset
when PCRE2_SUBSTITUTE_UNSET_EMPTY is set, substitute nothing. */
rc = pcre2_substring_length_bynumber(match_data, group, &sublength);
if (rc < 0)
{
if (rc == PCRE2_ERROR_NOSUBSTRING &&
(suboptions & PCRE2_SUBSTITUTE_UNKNOWN_UNSET) != 0)
{
rc = PCRE2_ERROR_UNSET;
}
if (rc != PCRE2_ERROR_UNSET) goto PTREXIT; /* Non-unset errors */
if (special == 0) /* Plain substitution */
{
if ((suboptions & PCRE2_SUBSTITUTE_UNSET_EMPTY) != 0) continue;
goto PTREXIT; /* Else error */
}
}
/* If special is '+' we have a 'set' and possibly an 'unset' text,
both of which are reprocessed when used. If special is '-' we have a
default text for when the group is unset; it must be reprocessed. */
if (special != 0)
{
if (special == CHAR_MINUS)
{
if (rc == 0) goto LITERAL_SUBSTITUTE;
text2_start = text1_start;
text2_end = text1_end;
}
if (ptrstackptr >= PTR_STACK_SIZE) goto BAD;
ptrstack[ptrstackptr++] = ptr;
ptrstack[ptrstackptr++] = repend;
if (rc == 0)
{
ptr = text1_start;
repend = text1_end;
}
else
{
ptr = text2_start;
repend = text2_end;
}
continue;
}
/* Otherwise we have a literal substitution of a group's contents. */
LITERAL_SUBSTITUTE:
subptr = subject + ovector[group*2];
subptrend = subject + ovector[group*2 + 1];
/* Substitute a literal string, possibly forcing alphabetic case. */
while (subptr < subptrend)
{
GETCHARINCTEST(ch, subptr);
if (forcecase != 0)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
uint32_t type = UCD_CHARTYPE(ch);
if (PRIV(ucp_gentype)[type] == ucp_L &&
type != ((forcecase > 0)? ucp_Lu : ucp_Ll))
ch = UCD_OTHERCASE(ch);
}
else
#endif
{
if (((code->tables + cbits_offset +
((forcecase > 0)? cbit_upper:cbit_lower)
)[ch/8] & (1 << (ch%8))) == 0)
ch = (code->tables + fcc_offset)[ch];
}
forcecase = forcecasereset;
}
#ifdef SUPPORT_UNICODE
if (utf) chlen = PRIV(ord2utf)(ch, temp); else
#endif
{
temp[0] = ch;
chlen = 1;
}
CHECKMEMCPY(temp, chlen);
}
}
}
/* Handle an escape sequence in extended mode. We can use check_escape()
to process \Q, \E, \c, \o, \x and \ followed by non-alphanumerics, but
the case-forcing escapes are not supported in pcre2_compile() so must be
recognized here. */
else if ((suboptions & PCRE2_SUBSTITUTE_EXTENDED) != 0 &&
*ptr == CHAR_BACKSLASH)
{
int errorcode;
if (ptr < repend - 1) switch (ptr[1])
{
case CHAR_L:
forcecase = forcecasereset = -1;
ptr += 2;
continue;
case CHAR_l:
forcecase = -1;
forcecasereset = 0;
ptr += 2;
continue;
case CHAR_U:
forcecase = forcecasereset = 1;
ptr += 2;
continue;
case CHAR_u:
forcecase = 1;
forcecasereset = 0;
ptr += 2;
continue;
default:
break;
}
ptr++; /* Point after \ */
rc = PRIV(check_escape)(&ptr, repend, &ch, &errorcode,
code->overall_options, FALSE, NULL);
if (errorcode != 0) goto BADESCAPE;
switch(rc)
{
case ESC_E:
forcecase = forcecasereset = 0;
continue;
case ESC_Q:
literal = TRUE;
continue;
case 0: /* Data character */
goto LITERAL;
default:
goto BADESCAPE;
}
}
/* Handle a literal code unit */
else
{
LOADLITERAL:
GETCHARINCTEST(ch, ptr); /* Get character value, increment pointer */
LITERAL:
if (forcecase != 0)
{
#ifdef SUPPORT_UNICODE
if (utf)
{
uint32_t type = UCD_CHARTYPE(ch);
if (PRIV(ucp_gentype)[type] == ucp_L &&
type != ((forcecase > 0)? ucp_Lu : ucp_Ll))
ch = UCD_OTHERCASE(ch);
}
else
#endif
{
if (((code->tables + cbits_offset +
((forcecase > 0)? cbit_upper:cbit_lower)
)[ch/8] & (1 << (ch%8))) == 0)
ch = (code->tables + fcc_offset)[ch];
}
forcecase = forcecasereset;
}
#ifdef SUPPORT_UNICODE
if (utf) chlen = PRIV(ord2utf)(ch, temp); else
#endif
{
temp[0] = ch;
chlen = 1;
}
CHECKMEMCPY(temp, chlen);
} /* End handling a literal code unit */
} /* End of loop for scanning the replacement. */
/* The replacement has been copied to the output. Update the start offset to
point to the rest of the subject string. If we matched an empty string,
do the magic for global matches. */
start_offset = ovector[1];
goptions = (ovector[0] != ovector[1])? 0 :
PCRE2_ANCHORED|PCRE2_NOTEMPTY_ATSTART;
} while ((suboptions & PCRE2_SUBSTITUTE_GLOBAL) != 0); /* Repeat "do" loop */
/* Copy the rest of the subject. */
fraglength = length - start_offset;
CHECKMEMCPY(subject + start_offset, fraglength);
temp[0] = 0;
CHECKMEMCPY(temp , 1);
/* If overflowed is set it means the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set,
and matching has carried on after a full buffer, in order to compute the length
needed. Otherwise, an overflow generates an immediate error return. */
if (overflowed)
{
rc = PCRE2_ERROR_NOMEMORY;
*blength = buff_length + extra_needed;
}
/* After a successful execution, return the number of substitutions and set the
length of buffer used, excluding the trailing zero. */
else
{
rc = subs;
*blength = buff_offset - 1;
}
EXIT:
if (match_data_created) pcre2_match_data_free(match_data);
else match_data->rc = rc;
return rc;
NOROOM:
rc = PCRE2_ERROR_NOMEMORY;
goto EXIT;
BAD:
rc = PCRE2_ERROR_BADREPLACEMENT;
goto PTREXIT;
BADESCAPE:
rc = PCRE2_ERROR_BADREPESCAPE;
PTREXIT:
*blength = (PCRE2_SIZE)(ptr - replacement);
goto EXIT;
}
/*
* return 1: success
* return 0: error;
* */
int8_t pecl_regx_match(PCRE2_SPTR subject, PCRE2_SPTR pattern, int *match_offset, int *match_str_lenght) {
pcre2_code *re;
PCRE2_SPTR name_table;
int crlf_is_newline;
int errornumber;
int i;
int namecount;
int name_entry_size;
int rc;
int utf8;
uint32_t option_bits;
uint32_t newline;
PCRE2_SIZE erroroffset;
PCRE2_SIZE *ovector;
size_t subject_length;
pcre2_match_data *match_data;
//char * _pattern = "[2-9]";
char *_pattern = "[^\u4e00-\u9fa5]++";
subject_length = strlen((char *) subject);
re = pcre2_compile(
pattern, /* the pattern */
PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
0, /* default options */
&errornumber, /* for error number */
&erroroffset, /* for error offset */
NULL); /* use default compile context */
if (re == NULL) {
PCRE2_UCHAR buffer[256];
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
printf("PCRE2 compilation failed at offset %d: %s\n", (int) erroroffset,
buffer);
return 0;
}
match_data = pcre2_match_data_create_from_pattern(re, NULL);
rc = pcre2_match(
re, /* the compiled pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
0, /* start at offset 0 in the subject */
0, /* default options */
match_data, /* block for storing the result */
NULL); /* use default match context */
if (rc < 0) {
switch (rc) {
case PCRE2_ERROR_NOMATCH:
break;
/*
Handle other special cases if you like
*/
default:
printf("Matching error %d\n", rc);
break;
}
pcre2_match_data_free(match_data); /* Release memory used for the match */
pcre2_code_free(re); /* data and the compiled pattern. */
return 0;
}
ovector = pcre2_get_ovector_pointer(match_data);
*match_offset = (int) ovector[0];
if (rc == 0) {
printf("ovector was not big enough for all the captured substrings\n");
}
for (i = 0; i < rc; i++) {
size_t substring_length = ovector[2 * i + 1] - ovector[2 * i];
*match_str_lenght = (int) substring_length;
PCRE2_SPTR substring_start = subject + ovector[2 * i];
if (i > 1) {
//wrong. i can't large than one.todo.
}
}
}
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
regexec(const regex_t *preg, const char *string, size_t nmatch,
regmatch_t pmatch[], int eflags)
{
int rc, so, eo;
int options = 0;
pcre2_match_data *md = (pcre2_match_data *)preg->re_match_data;
if ((eflags & REG_NOTBOL) != 0) options |= PCRE2_NOTBOL;
if ((eflags & REG_NOTEOL) != 0) options |= PCRE2_NOTEOL;
if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE2_NOTEMPTY;
((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */
/* When REG_NOSUB was specified, or if no vector has been passed in which to
put captured strings, ensure that nmatch is zero. This will stop any attempt to
write to pmatch. */
if ((preg->re_cflags & REG_NOSUB) != 0 || pmatch == NULL) nmatch = 0;
/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings.
The man page from OS X says "REG_STARTEND affects only the location of the
string, not how it is matched". That is why the "so" value is used to bump the
start location rather than being passed as a PCRE2 "starting offset". */
if ((eflags & REG_STARTEND) != 0)
{
if (pmatch == NULL) return REG_INVARG;
so = pmatch[0].rm_so;
eo = pmatch[0].rm_eo;
}
else
{
so = 0;
eo = (int)strlen(string);
}
rc = pcre2_match((const pcre2_code *)preg->re_pcre2_code,
(PCRE2_SPTR)string + so, (eo - so), 0, options, md, NULL);
/* Successful match */
if (rc >= 0)
{
size_t i;
PCRE2_SIZE *ovector = pcre2_get_ovector_pointer(md);
if ((size_t)rc > nmatch) rc = (int)nmatch;
for (i = 0; i < (size_t)rc; i++)
{
pmatch[i].rm_so = ovector[i*2] + so;
pmatch[i].rm_eo = ovector[i*2+1] + so;
}
for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1;
return 0;
}
/* Unsuccessful match */
if (rc <= PCRE2_ERROR_UTF8_ERR1 && rc >= PCRE2_ERROR_UTF8_ERR21)
return REG_INVARG;
switch(rc)
{
default: return REG_ASSERT;
case PCRE2_ERROR_BADMODE: return REG_INVARG;
case PCRE2_ERROR_BADMAGIC: return REG_INVARG;
case PCRE2_ERROR_BADOPTION: return REG_INVARG;
case PCRE2_ERROR_BADUTFOFFSET: return REG_INVARG;
case PCRE2_ERROR_MATCHLIMIT: return REG_ESPACE;
case PCRE2_ERROR_NOMATCH: return REG_NOMATCH;
case PCRE2_ERROR_NOMEMORY: return REG_ESPACE;
case PCRE2_ERROR_NULL: return REG_INVARG;
}
}
/* TODO: audit this function */
void cli_pcre_report(const struct cli_pcre_data *pd, const unsigned char *buffer, uint32_t buflen, int rc, struct cli_pcre_results *results)
{
int i, j, length, trunc;
const char *start;
char outstr[2*MATCH_MAXLEN+1];
#if USING_PCRE2
PCRE2_SIZE *ovector;
ovector = pcre2_get_ovector_pointer(results->match_data);
#else
int *ovector = results->ovector;
#endif
/* print out additional diagnostics if cli_debug_flag is set */
if (!DISABLE_PCRE_REPORT) {
cli_dbgmsg("\n");
#if USING_PCRE2
cli_dbgmsg("cli_pcre_report: PCRE2 Execution Report:\n");
#else
cli_dbgmsg("cli_pcre_report: PCRE Execution Report:\n");
#endif
cli_dbgmsg("cli_pcre_report: running regex /%s/ returns %d\n", pd->expression, rc);
if (rc > 0) {
/* print out full-match and capture groups */
for (i = 0; i < rc; ++i) {
start = buffer + ovector[2*i];
length = ovector[2*i+1] - ovector[2*i];
if (ovector[2*i+1] > buflen) {
cli_warnmsg("cli_pcre_report: reported match goes outside buffer\n");
continue;
}
trunc = 0;
if (length > MATCH_MAXLEN) {
trunc = 1;
length = MATCH_MAXLEN;
}
for (j = 0; j < length; ++j)
snprintf(outstr+(2*j), sizeof(outstr)-(2*j), "%02x", (unsigned int)*(start+j));
cli_dbgmsg("cli_pcre_report: %d: %s%s\n", i, outstr, trunc ? " (trunc)":"");
//cli_dbgmsg("cli_pcre_report: %d: %.*s%s\n", i, length, start, trunc ? " (trunc)":"");
}
named_substr_print(pd, buffer, ovector);
}
#if USING_PCRE2
else if (rc == 0 || rc == PCRE2_ERROR_NOMATCH) {
#else
else if (rc == 0 || rc == PCRE_ERROR_NOMATCH) {
#endif
cli_dbgmsg("cli_pcre_report: no match found\n");
}
else {
cli_dbgmsg("cli_pcre_report: error occurred in pcre_match: %d\n", rc);
/* error handled by caller */
}
cli_dbgmsg("cli_pcre_report: PCRE Execution Report End\n");
cli_dbgmsg("\n");
}
}
int cli_pcre_match(struct cli_pcre_data *pd, const unsigned char *buffer, uint32_t buflen, int override_offset, int options, struct cli_pcre_results *results)
{
int rc, startoffset;
#if USING_PCRE2
pcre2_general_context *pc2ctx;
PCRE2_SIZE *ovector;
#endif
/* set the startoffset, override if a value is specified */
startoffset = pd->search_offset;
if (override_offset >= 0)
startoffset = override_offset;
/* execute the pcre and return */
#if USING_PCRE2
rc = pcre2_match(pd->re, buffer, buflen, startoffset, options, results->match_data, pd->mctx);
if (rc < 0 && rc != PCRE2_ERROR_NOMATCH) {
switch (rc) {
case PCRE2_ERROR_CALLOUT:
break;
case PCRE2_ERROR_NOMEMORY:
cli_errmsg("cli_pcre_match: pcre_exec: out of memory\n");
results->err = CL_EMEM;
break;
case PCRE2_ERROR_MATCHLIMIT:
cli_dbgmsg("cli_pcre_match: pcre_exec: match limit exceeded\n");
break;
case PCRE2_ERROR_RECURSIONLIMIT:
cli_dbgmsg("cli_pcre_match: pcre_exec: recursive limit exceeded\n");
break;
default:
cli_errmsg("cli_pcre_match: pcre_exec: returned error %d\n", rc);
results->err = CL_BREAK;
}
} else if (rc > 0) {
ovector = pcre2_get_ovector_pointer(results->match_data);
results->match[0] = ovector[0];
results->match[1] = ovector[1];
} else {
results->match[0] = results->match[1] = 0;
}
#else
rc = pcre_exec(pd->re, pd->ex, buffer, buflen, startoffset, options, results->ovector, OVECCOUNT);
if (rc < 0 && rc != PCRE_ERROR_NOMATCH) {
switch (rc) {
case PCRE_ERROR_CALLOUT:
break;
case PCRE_ERROR_NOMEMORY:
cli_errmsg("cli_pcre_match: pcre_exec: out of memory\n");
results->err = CL_EMEM;
break;
case PCRE_ERROR_MATCHLIMIT:
cli_dbgmsg("cli_pcre_match: pcre_exec: match limit exceeded\n");
break;
case PCRE_ERROR_RECURSIONLIMIT:
cli_dbgmsg("cli_pcre_match: pcre_exec: recursive limit exceeded\n");
break;
default:
cli_errmsg("cli_pcre_match: pcre_exec: returned error %d\n", rc);
results->err = CL_BREAK;
}
} else if (rc > 0) {
results->match[0] = results->ovector[0];
results->match[1] = results->ovector[1];
} else {
results->match[0] = results->match[1] = 0;
}
#endif
return rc;
}
int main(int argc, char **argv)
{
pcre2_code *re;
PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */
PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */
PCRE2_SPTR name_table;
int crlf_is_newline;
int errornumber;
int find_all;
int i;
int namecount;
int name_entry_size;
int rc;
int utf8;
uint32_t option_bits;
uint32_t newline;
PCRE2_SIZE erroroffset;
PCRE2_SIZE *ovector;
size_t subject_length;
pcre2_match_data *match_data;
/**************************************************************************
* First, sort out the command line. There is only one possible option at *
* the moment, "-g" to request repeated matching to find all occurrences, *
* like Perl's /g option. We set the variable find_all to a non-zero value *
* if the -g option is present. Apart from that, there must be exactly two *
* arguments. *
**************************************************************************/
find_all = 0;
for (i = 1; i < argc; i++)
{
if (strcmp(argv[i], "-g") == 0) find_all = 1;
else break;
}
/* After the options, we require exactly two arguments, which are the pattern,
and the subject string. */
if (argc - i != 2)
{
printf("Two arguments required: a regex and a subject string\n");
return 1;
}
/* As pattern and subject are char arguments, they can be straightforwardly
cast to PCRE2_SPTR as we are working in 8-bit code units. */
pattern = (PCRE2_SPTR)argv[i];
subject = (PCRE2_SPTR)argv[i+1];
subject_length = strlen((char *)subject);
/*************************************************************************
* Now we are going to compile the regular expression pattern, and handle *
* any errors that are detected. *
*************************************************************************/
re = pcre2_compile(
pattern, /* the pattern */
PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
0, /* default options */
&errornumber, /* for error number */
&erroroffset, /* for error offset */
NULL); /* use default compile context */
/* Compilation failed: print the error message and exit. */
if (re == NULL)
{
PCRE2_UCHAR buffer[256];
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,
buffer);
return 1;
}
/*************************************************************************
* If the compilation succeeded, we call PCRE again, in order to do a *
* pattern match against the subject string. This does just ONE match. If *
* further matching is needed, it will be done below. Before running the *
* match we must set up a match_data block for holding the result. *
*************************************************************************/
/* Using this function ensures that the block is exactly the right size for
the number of capturing parentheses in the pattern. */
match_data = pcre2_match_data_create_from_pattern(re, NULL);
rc = pcre2_match(
re, /* the compiled pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
0, /* start at offset 0 in the subject */
0, /* default options */
match_data, /* block for storing the result */
NULL); /* use default match context */
/* Matching failed: handle error cases */
if (rc < 0)
{
switch(rc)
{
case PCRE2_ERROR_NOMATCH: printf("No match\n"); break;
/*
Handle other special cases if you like
*/
default: printf("Matching error %d\n", rc); break;
}
pcre2_match_data_free(match_data); /* Release memory used for the match */
pcre2_code_free(re); /* data and the compiled pattern. */
return 1;
}
/* Match succeded. Get a pointer to the output vector, where string offsets are
stored. */
ovector = pcre2_get_ovector_pointer(match_data);
printf("\nMatch succeeded at offset %d\n", (int)ovector[0]);
/*************************************************************************
* We have found the first match within the subject string. If the output *
* vector wasn't big enough, say so. Then output any substrings that were *
* captured. *
*************************************************************************/
/* The output vector wasn't big enough. This should not happen, because we used
pcre2_match_data_create_from_pattern() above. */
if (rc == 0)
printf("ovector was not big enough for all the captured substrings\n");
/* Show substrings stored in the output vector by number. Obviously, in a real
application you might want to do things other than print them. */
for (i = 0; i < rc; i++)
{
PCRE2_SPTR substring_start = subject + ovector[2*i];
size_t substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
}
/**************************************************************************
* That concludes the basic part of this demonstration program. We have *
* compiled a pattern, and performed a single match. The code that follows *
* shows first how to access named substrings, and then how to code for *
* repeated matches on the same subject. *
**************************************************************************/
/* See if there are any named substrings, and if so, show them by name. First
we have to extract the count of named parentheses from the pattern. */
(void)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
&namecount); /* where to put the answer */
if (namecount <= 0) printf("No named substrings\n"); else
{
PCRE2_SPTR tabptr;
printf("Named substrings\n");
/* Before we can access the substrings, we must extract the table for
translating names to numbers, and the size of each entry in the table. */
(void)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMETABLE, /* address of the table */
&name_table); /* where to put the answer */
(void)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
&name_entry_size); /* where to put the answer */
/* Now we can scan the table and, for each entry, print the number, the name,
and the substring itself. In the 8-bit library the number is held in two
bytes, most significant first. */
tabptr = name_table;
for (i = 0; i < namecount; i++)
{
int n = (tabptr[0] << 8) | tabptr[1];
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
tabptr += name_entry_size;
}
}
/*************************************************************************
* If the "-g" option was given on the command line, we want to continue *
* to search for additional matches in the subject string, in a similar *
* way to the /g option in Perl. This turns out to be trickier than you *
* might think because of the possibility of matching an empty string. *
* What happens is as follows: *
* *
* If the previous match was NOT for an empty string, we can just start *
* the next match at the end of the previous one. *
* *
* If the previous match WAS for an empty string, we can't do that, as it *
* would lead to an infinite loop. Instead, a call of pcre2_match() is *
* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
* first of these tells PCRE2 that an empty string at the start of the *
* subject is not a valid match; other possibilities must be tried. The *
* second flag restricts PCRE2 to one match attempt at the initial string *
* position. If this match succeeds, an alternative to the empty string *
* match has been found, and we can print it and proceed round the loop, *
* advancing by the length of whatever was found. If this match does not *
* succeed, we still stay in the loop, advancing by just one character. *
* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be *
* more than one byte. *
* *
* However, there is a complication concerned with newlines. When the *
* newline convention is such that CRLF is a valid newline, we must *
* advance by two characters rather than one. The newline convention can *
* be set in the regex by (*CR), etc.; if not, we must find the default. *
*************************************************************************/
if (!find_all) /* Check for -g */
{
pcre2_match_data_free(match_data); /* Release the memory that was used */
pcre2_code_free(re); /* for the match data and the pattern. */
return 0; /* Exit the program. */
}
/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
sequence. First, find the options with which the regex was compiled and extract
the UTF state. */
(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits);
utf8 = (option_bits & PCRE2_UTF) != 0;
/* Now find the newline convention and see whether CRLF is a valid newline
sequence. */
(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline);
crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
newline == PCRE2_NEWLINE_CRLF ||
newline == PCRE2_NEWLINE_ANYCRLF;
/* Loop for second and subsequent matches */
for (;;)
{
uint32_t options = 0; /* Normally no options */
PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */
/* If the previous match was for an empty string, we are finished if we are
at the end of the subject. Otherwise, arrange to run another match at the
same point to see if a non-empty match can be found. */
if (ovector[0] == ovector[1])
{
if (ovector[0] == subject_length) break;
options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
}
/* Run the next matching operation */
rc = pcre2_match(
re, /* the compiled pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
start_offset, /* starting offset in the subject */
options, /* options */
match_data, /* block for storing the result */
NULL); /* use default match context */
/* This time, a result of NOMATCH isn't an error. If the value in "options"
is zero, it just means we have found all possible matches, so the loop ends.
Otherwise, it means we have failed to find a non-empty-string match at a
point where there was a previous empty-string match. In this case, we do what
Perl does: advance the matching position by one character, and continue. We
do this by setting the "end of previous match" offset, because that is picked
up at the top of the loop as the point at which to start again.
There are two complications: (a) When CRLF is a valid newline sequence, and
the current position is just before it, advance by an extra byte. (b)
Otherwise we must ensure that we skip an entire UTF character if we are in
UTF mode. */
if (rc == PCRE2_ERROR_NOMATCH)
{
if (options == 0) break; /* All matches found */
ovector[1] = start_offset + 1; /* Advance one code unit */
if (crlf_is_newline && /* If CRLF is newline & */
start_offset < subject_length - 1 && /* we are at CRLF, */
subject[start_offset] == '\r' &&
subject[start_offset + 1] == '\n')
ovector[1] += 1; /* Advance by one more. */
else if (utf8) /* Otherwise, ensure we */
{ /* advance a whole UTF-8 */
while (ovector[1] < subject_length) /* character. */
{
if ((subject[ovector[1]] & 0xc0) != 0x80) break;
ovector[1] += 1;
}
}
continue; /* Go round the loop again */
}
/* Other matching errors are not recoverable. */
if (rc < 0)
{
printf("Matching error %d\n", rc);
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return 1;
}
/* Match succeded */
printf("\nMatch succeeded again at offset %d\n", (int)ovector[0]);
/* The match succeeded, but the output vector wasn't big enough. This
should not happen. */
if (rc == 0)
printf("ovector was not big enough for all the captured substrings\n");
/* As before, show substrings stored in the output vector by number, and then
also any named substrings. */
for (i = 0; i < rc; i++)
{
PCRE2_SPTR substring_start = subject + ovector[2*i];
size_t substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
}
if (namecount <= 0) printf("No named substrings\n"); else
{
PCRE2_SPTR tabptr = name_table;
printf("Named substrings\n");
for (i = 0; i < namecount; i++)
{
int n = (tabptr[0] << 8) | tabptr[1];
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
(int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]);
tabptr += name_entry_size;
}
}
} /* End of loop to find second and subsequent matches */
printf("\n");
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return 0;
}
int32 ftw_pcre_match(const pcre2_code *compiled_regex, ConstLStrH subject,
int32 startoffset, int32 *match_begin, int32 *match_end,
int32Array **submatches, CalloutAccumulator **callout)
{
struct ftw_callout_args arg;
pcre2_match_context *ctx;
pcre2_match_data *match_data;
PCRE2_SIZE subj_len;
PCRE2_SPTR subj_ptr;
PCRE2_SIZE *ovector;
uint32_t ovec_count;
int num_submatches;
MgErr lv_err;
int32 rc;
int i;
ctx = pcre2_match_context_create(NULL);
if (ctx == NULL)
return PCRE2_ERROR_INTERNAL;
/* Adjust these numbers to change characteristics of memory management. */
arg.grow_size = 100;
arg.accumulator = callout;
arg.index = 0;
rc = pcre2_set_callout(ctx, ftw_pcre_callout, &arg);
if (rc) {
pcre2_match_context_free(ctx);
return rc;
}
subj_len = LHStrLen(subject);
subj_ptr = LHStrBuf(subject);
match_data = pcre2_match_data_create_from_pattern(compiled_regex, NULL);
if (match_data == NULL) {
pcre2_match_context_free(ctx);
return PCRE2_ERROR_INTERNAL;
}
rc = pcre2_match(compiled_regex, subj_ptr, subj_len, (PCRE2_SIZE)startoffset, 0, match_data, ctx);
/* Sanity check array size. */
ftw_assert(arg.index >= 0 && (*arg.accumulator)->dimsize >= 0);
/* This should always be a trim operation, and never an increase. */
ftw_assert(arg.index <= (*arg.accumulator)->dimsize);
/* Trim callout buffer. */
lv_err = resize_CalloutAccumulator(&callout, arg.index);
if (lv_err) {
rc = PCRE2_ERROR_INTERNAL;
goto MATCH_DONE;
}
if (rc < 0) {
/* No match was found, or an error encountered. */
*match_begin = PCRE2_ERROR_NOMATCH;
*match_end = PCRE2_ERROR_NOMATCH;
goto MATCH_DONE;
}
/* Retrieve match data. */
ovec_count = pcre2_get_ovector_count(match_data);
ftw_assert(ovec_count > 0);
ovector = pcre2_get_ovector_pointer(match_data);
ftw_assert(ovector);
/* A whole match was found, but no submatches. */
*match_begin = (int32)ovector[0];
*match_end = (int32)ovector[1];
/* Resize the submatch buffer, accounting for the first ovec as the whole match. */
num_submatches = (int)ovec_count - 1;
if (num_submatches == 0)
goto MATCH_DONE;
lv_err = ftw_support_expand_int32Array(&submatches, num_submatches * 2);
if (lv_err) {
rc = PCRE2_ERROR_INTERNAL;
goto MATCH_DONE;
}
for (i = 0; i < num_submatches; i++) {
/* Advance to next submatch pair. */
ovector += 2;
(*submatches)->element[2 * i] = ovector[0];
(*submatches)->element[2 * i + 1] = ovector[1];
}
MATCH_DONE:
pcre2_match_data_free(match_data);
pcre2_match_context_free(ctx);
return rc;
}
PCRE2_EXP_DEFN int PCRE2_CALL_CONVENTION
pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length,
PCRE2_SIZE start_offset, uint32_t options, pcre2_match_data *match_data,
pcre2_match_context *mcontext, PCRE2_SPTR replacement, PCRE2_SIZE rlength,
PCRE2_UCHAR *buffer, PCRE2_SIZE *blength)
{
int rc;
int subs;
uint32_t ovector_count;
uint32_t goptions = 0;
BOOL match_data_created = FALSE;
BOOL global = FALSE;
PCRE2_SIZE buff_offset, lengthleft, fraglength;
PCRE2_SIZE *ovector;
/* Partial matching is not valid. */
if ((options & (PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT)) != 0)
return PCRE2_ERROR_BADOPTION;
/* If no match data block is provided, create one. */
if (match_data == NULL)
{
pcre2_general_context *gcontext = (mcontext == NULL)?
(pcre2_general_context *)code :
(pcre2_general_context *)mcontext;
match_data = pcre2_match_data_create_from_pattern(code, gcontext);
if (match_data == NULL) return PCRE2_ERROR_NOMEMORY;
match_data_created = TRUE;
}
ovector = pcre2_get_ovector_pointer(match_data);
ovector_count = pcre2_get_ovector_count(match_data);
/* Check UTF replacement string if necessary. */
#ifdef SUPPORT_UNICODE
if ((code->overall_options & PCRE2_UTF) != 0 &&
(options & PCRE2_NO_UTF_CHECK) == 0)
{
rc = PRIV(valid_utf)(replacement, rlength, &(match_data->rightchar));
if (rc != 0)
{
match_data->leftchar = 0;
goto EXIT;
}
}
#endif /* SUPPORT_UNICODE */
/* Notice the global option and remove it from the options that are passed to
pcre2_match(). */
if ((options & PCRE2_SUBSTITUTE_GLOBAL) != 0)
{
options &= ~PCRE2_SUBSTITUTE_GLOBAL;
global = TRUE;
}
/* Find lengths of zero-terminated strings. */
if (length == PCRE2_ZERO_TERMINATED) length = PRIV(strlen)(subject);
if (rlength == PCRE2_ZERO_TERMINATED) rlength = PRIV(strlen)(replacement);
/* Copy up to the start offset */
if (start_offset > *blength) goto NOROOM;
memcpy(buffer, subject, start_offset * (PCRE2_CODE_UNIT_WIDTH/8));
buff_offset = start_offset;
lengthleft = *blength - start_offset;
/* Loop for global substituting. */
subs = 0;
do
{
PCRE2_SIZE i;
rc = pcre2_match(code, subject, length, start_offset, options|goptions,
match_data, mcontext);
/* Any error other than no match returns the error code. No match when not
doing the special after-empty-match global rematch, or when at the end of the
subject, breaks the global loop. Otherwise, advance the starting point by one
character, copying it to the output, and try again. */
if (rc < 0)
{
PCRE2_SIZE save_start;
if (rc != PCRE2_ERROR_NOMATCH) goto EXIT;
if (goptions == 0 || start_offset >= length) break;
save_start = start_offset++;
if ((code->overall_options & PCRE2_UTF) != 0)
{
#if PCRE2_CODE_UNIT_WIDTH == 8
while (start_offset < length && (subject[start_offset] & 0xc0) == 0x80)
start_offset++;
#elif PCRE2_CODE_UNIT_WIDTH == 16
while (start_offset < length &&
(subject[start_offset] & 0xfc00) == 0xdc00)
start_offset++;
#endif
}
fraglength = start_offset - save_start;
if (lengthleft < fraglength) goto NOROOM;
memcpy(buffer + buff_offset, subject + save_start,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
lengthleft -= fraglength;
goptions = 0;
continue;
}
/* Handle a successful match. */
subs++;
if (rc == 0) rc = ovector_count;
fraglength = ovector[0] - start_offset;
if (fraglength >= lengthleft) goto NOROOM;
memcpy(buffer + buff_offset, subject + start_offset,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
lengthleft -= fraglength;
for (i = 0; i < rlength; i++)
{
if (replacement[i] == CHAR_DOLLAR_SIGN)
{
int group, n;
BOOL inparens;
PCRE2_SIZE sublength;
PCRE2_UCHAR next;
PCRE2_UCHAR name[33];
if (++i == rlength) goto BAD;
if ((next = replacement[i]) == CHAR_DOLLAR_SIGN) goto LITERAL;
group = -1;
n = 0;
inparens = FALSE;
if (next == CHAR_LEFT_CURLY_BRACKET)
{
if (++i == rlength) goto BAD;
next = replacement[i];
inparens = TRUE;
}
if (next >= CHAR_0 && next <= CHAR_9)
{
group = next - CHAR_0;
while (i < rlength - 1)
{
next = replacement[++i];
if (next < CHAR_0 || next > CHAR_9) break;
group = group * 10 + next - CHAR_0;
}
}
else
{
const uint8_t *ctypes = code->tables + ctypes_offset;
while (MAX_255(next) && (ctypes[next] & ctype_word) != 0)
{
name[n++] = next;
if (n > 32) goto BAD;
if (i == rlength) break;
next = replacement[++i];
}
if (n == 0) goto BAD;
name[n] = 0;
}
if (inparens)
{
if (i == rlength || next != CHAR_RIGHT_CURLY_BRACKET) goto BAD;
}
else i--; /* Last code unit of name/number */
/* Have found a syntactically correct group number or name. */
sublength = lengthleft;
if (group < 0)
rc = pcre2_substring_copy_byname(match_data, name,
buffer + buff_offset, &sublength);
else
rc = pcre2_substring_copy_bynumber(match_data, group,
buffer + buff_offset, &sublength);
if (rc < 0) goto EXIT;
buff_offset += sublength;
lengthleft -= sublength;
}
/* Handle a literal code unit */
else
{
LITERAL:
if (lengthleft-- < 1) goto NOROOM;
buffer[buff_offset++] = replacement[i];
}
}
/* The replacement has been copied to the output. Update the start offset to
point to the rest of the subject string. If we matched an empty string,
do the magic for global matches. */
start_offset = ovector[1];
goptions = (ovector[0] != ovector[1])? 0 :
PCRE2_ANCHORED|PCRE2_NOTEMPTY_ATSTART;
} while (global); /* Repeat "do" loop */
/* Copy the rest of the subject and return the number of substitutions. */
rc = subs;
fraglength = length - start_offset;
if (fraglength + 1 > lengthleft) goto NOROOM;
memcpy(buffer + buff_offset, subject + start_offset,
fraglength*(PCRE2_CODE_UNIT_WIDTH/8));
buff_offset += fraglength;
buffer[buff_offset] = 0;
*blength = buff_offset;
EXIT:
if (match_data_created) pcre2_match_data_free(match_data);
else match_data->rc = rc;
return rc;
NOROOM:
rc = PCRE2_ERROR_NOMEMORY;
goto EXIT;
BAD:
rc = PCRE2_ERROR_BADREPLACEMENT;
goto EXIT;
}
/* PCRE 2 version */
gboolean
rspamd_regexp_search (rspamd_regexp_t *re, const gchar *text, gsize len,
const gchar **start, const gchar **end, gboolean raw,
GArray *captures)
{
pcre2_match_data *match_data;
pcre2_match_context *mcontext;
PCRE_T *r;
const gchar *mt;
gsize remain = 0, *ovec;
gint rc, match_flags, novec, i;
gboolean ret = FALSE;
g_assert (re != NULL);
g_assert (text != NULL);
if (len == 0) {
len = strlen (text);
}
if (end != NULL && *end != NULL) {
/* Incremental search */
mt = (*end);
if ((gint)len > (mt - text)) {
remain = len - (mt - text);
}
}
else {
mt = text;
remain = len;
}
if (remain == 0) {
return FALSE;
}
match_flags = 0;
if (raw || re->re == re->raw_re) {
r = re->raw_re;
mcontext = re->raw_mcontext;
}
else {
r = re->re;
mcontext = re->mcontext;
}
match_data = pcre2_match_data_create (re->ncaptures + 1, NULL);
#ifdef HAVE_PCRE_JIT
if (!(re->flags & RSPAMD_REGEXP_FLAG_DISABLE_JIT) && can_jit) {
if (re->re != re->raw_re && !g_utf8_validate (mt, remain, NULL)) {
msg_err ("bad utf8 input for JIT re");
return FALSE;
}
rc = pcre2_jit_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
}
else {
rc = pcre2_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
}
#else
rc = pcre2_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
#endif
if (rc >= 0) {
novec = pcre2_get_ovector_count (match_data);
ovec = pcre2_get_ovector_pointer (match_data);
if (start) {
*start = mt + ovec[0];
}
if (end) {
*end = mt + ovec[1];
}
if (captures != NULL && novec > 1) {
struct rspamd_re_capture *elt;
g_assert (g_array_get_element_size (captures) ==
sizeof (struct rspamd_re_capture));
g_array_set_size (captures, novec);
for (i = 0; i < novec; i ++) {
elt = &g_array_index (captures, struct rspamd_re_capture, i);
elt->p = mt + ovec[i * 2];
elt->len = (mt + ovec[i * 2 + 1]) - elt->p;
}
}
ret = TRUE;
if (re->flags & RSPAMD_REGEXP_FLAG_FULL_MATCH) {
/* We also ensure that the match is full */
if (ovec[0] != 0 || (guint)ovec[1] < len) {
ret = FALSE;
}
}
}
