/*
* Returns a grammar object or NULL in case of an error.
*
* Warning: this function could write to stderr in case the re_keywords could
* not be compiled.
*/
cleri_grammar_t * cleri_grammar(cleri_t * start, const char * re_keywords)
{
const char * re_kw = (re_keywords == NULL) ?
CLERI_DEFAULT_RE_KEYWORDS : re_keywords;
/* re_keywords should start with a ^ */
assert (re_kw[0] == '^');
if (start == NULL)
{
return NULL;
}
cleri_grammar_t * grammar = cleri__malloc(cleri_grammar_t);
if (grammar == NULL)
{
return NULL;
}
int pcre_error_num;
PCRE2_SIZE pcre_error_offset;
grammar->re_keywords = pcre2_compile(
(PCRE2_SPTR8) re_kw,
PCRE2_ZERO_TERMINATED,
0,
&pcre_error_num,
&pcre_error_offset,
NULL);
if(grammar->re_keywords == NULL)
{
PCRE2_UCHAR buffer[256];
pcre2_get_error_message(pcre_error_num, buffer, sizeof(buffer));
/* this is critical and unexpected, memory is not cleaned */
fprintf(stderr,
"error: cannot compile '%s' (%s)\n",
re_kw,
buffer);
free(grammar);
return NULL;
}
grammar->match_data = \
pcre2_match_data_create_from_pattern(grammar->re_keywords, NULL);
if (grammar->match_data == NULL)
{
pcre2_code_free(grammar->re_keywords);
fprintf(stderr, "error: cannot create matsch data\n");
free(grammar);
return NULL;
}
/* bind root element and increment the reference counter */
grammar->start = start;
cleri_incref(start);
return grammar;
}
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;
}
pcre2_code *compile(char *pattern) {
PCRE2_SPTR pcre2_pattern = (PCRE2_SPTR)pattern;
pcre2_code *re;
int errornumber;
PCRE2_SIZE erroroffset;
re = pcre2_compile(
pcre2_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 */
pcre2_jit_compile(re, PCRE2_JIT_COMPLETE);
if (re == NULL) {
PCRE2_UCHAR buffer[256];
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
printf("PCRE2 compilation failed at offset %d: %s\n for pattern: %s", (int)erroroffset,
buffer, pattern);
exit(1);
}
return re;
}
int cli_pcre_compile(struct cli_pcre_data *pd, long long unsigned match_limit, long long unsigned match_limit_recursion, unsigned int options, int opt_override)
{
int errornum, erroffset;
pcre2_general_context *gctx;
pcre2_compile_context *cctx;
if (!pd || !pd->expression) {
cli_errmsg("cli_pcre_compile: NULL pd or NULL pd->expression\n");
return CL_ENULLARG;
}
gctx = pcre2_general_context_create(cli_pcre_malloc, cli_pcre_free, NULL);
if (!gctx) {
cli_errmsg("cli_pcre_compile: Unable to allocate memory for general context\n");
return CL_EMEM;
}
cctx = pcre2_compile_context_create(gctx);
if (!cctx) {
cli_errmsg("cli_pcre_compile: Unable to allocate memory for compile context\n");
pcre2_general_context_free(gctx);
return CL_EMEM;
}
/* compile the pcre2 regex last arg is charset, allow for options override */
if (opt_override)
pd->re = pcre2_compile(pd->expression, PCRE2_ZERO_TERMINATED, options, &errornum, &erroffset, cctx); /* pd->re handled by pcre2 -> call pcre_free() -> calls free() */
else
pd->re = pcre2_compile(pd->expression, PCRE2_ZERO_TERMINATED, pd->options, &errornum, &erroffset, cctx); /* pd->re handled by pcre2 -> call pcre_free() -> calls free() */
if (pd->re == NULL) {
PCRE2_UCHAR errmsg[256];
pcre2_get_error_message(errornum, errmsg, sizeof(errmsg));
cli_errmsg("cli_pcre_compile: PCRE2 compilation failed at offset %d: %s\n", erroffset, errmsg);
pcre2_compile_context_free(cctx);
pcre2_general_context_free(gctx);
return CL_EMALFDB;
}
/* setup matching context and set the match limits */
pd->mctx = pcre2_match_context_create(gctx);
if (!pd->mctx) {
cli_errmsg("cli_pcre_compile: Unable to allocate memory for match context\n");
pcre2_compile_context_free(cctx);
pcre2_general_context_free(gctx);
return CL_EMEM;
}
pcre2_set_match_limit(pd->mctx, match_limit);
pcre2_set_recursion_limit(pd->mctx, match_limit_recursion);
/* non-dynamic allocated fields set by caller */
pcre2_compile_context_free(cctx);
pcre2_general_context_free(gctx);
return CL_SUCCESS;
}
static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
{
int error;
PCRE2_UCHAR errbuf[256];
PCRE2_SIZE erroffset;
int options = PCRE2_MULTILINE;
const uint8_t *character_tables = NULL;
int jitret;
assert(opt->pcre2);
p->pcre2_compile_context = NULL;
if (opt->ignore_case) {
if (has_non_ascii(p->pattern)) {
character_tables = pcre2_maketables(NULL);
p->pcre2_compile_context = pcre2_compile_context_create(NULL);
pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
}
options |= PCRE2_CASELESS;
}
if (is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE2_UTF;
p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
p->patternlen, options, &error, &erroffset,
p->pcre2_compile_context);
if (p->pcre2_pattern) {
p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL);
if (!p->pcre2_match_data)
die("Couldn't allocate PCRE2 match data");
} else {
pcre2_get_error_message(error, errbuf, sizeof(errbuf));
compile_regexp_failed(p, (const char *)&errbuf);
}
pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
if (p->pcre2_jit_on == 1) {
jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE);
if (jitret)
die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret);
p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
if (!p->pcre2_jit_stack)
die("Couldn't allocate PCRE2 JIT stack");
p->pcre2_match_context = pcre2_match_context_create(NULL);
if (!p->pcre2_match_context)
die("Couldn't allocate PCRE2 match context");
pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack);
} else if (p->pcre2_jit_on != 0) {
die("BUG: The pcre2_jit_on variable should be 0 or 1, not %d",
p->pcre1_jit_on);
}
}
static void prt_regerror(const char *msg, const Regex_node *re, int rc,
int erroffset)
{
#if HAVE_PCRE2_H
PCRE2_UCHAR errbuf[ERRBUFFLEN];
pcre2_get_error_message(rc, errbuf, ERRBUFFLEN);
#else
char errbuf[ERRBUFFLEN];
regerror(rc, re->re, errbuf, ERRBUFFLEN);
#endif /* HAVE_PCRE2_H */
prt_error("Error: %s: \"%s\" (%s", msg, re->pattern, re->name);
if (-1 != erroffset) prt_error(" at %d", erroffset);
prt_error("): %s (%d)\n", errbuf, rc);
}
pcre2_code *ftw_pcre_compile(ConstLStrH regex, uint32_t options, LStrHandle err_string,
int32 *err_offset_in_regex)
{
MgErr lv_err;
pcre2_code *compiled_regex;
PCRE2_SIZE err_offset;
char buf[1024] = {0};
int err_code;
int rc;
compiled_regex = pcre2_compile(LHStrBuf(regex), LHStrLen(regex), options, &err_code, &err_offset, NULL);
if (compiled_regex)
return compiled_regex;
*err_offset_in_regex = (int32)err_offset;
rc = pcre2_get_error_message(err_code, buf, sizeof(buf));
ftw_assert (rc == StrLen(buf));
lv_err = ftw_support_CStr_to_LStrHandle(&err_string, buf, sizeof(buf));
return NULL;
}
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;
}
/*
* 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.
}
}
}
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;
}
int LLVMFuzzerTestOneInput(const unsigned char *data, size_t size)
{
uint32_t compile_options;
uint32_t match_options;
pcre2_match_data *match_data = NULL;
pcre2_match_context *match_context = NULL;
size_t match_size;
int dfa_workspace[DFA_WORKSPACE_COUNT];
int r1, r2;
int i;
if (size < 1) return 0;
/* Limiting the length of the subject for matching stops fruitless searches
in large trees taking too much time. */
match_size = (size > MAX_MATCH_SIZE)? MAX_MATCH_SIZE : size;
/* Figure out some options to use. Initialize the random number to ensure
repeatability. Ensure that we get a 32-bit unsigned random number for testing
options. (RAND_MAX is required to be at least 32767, but is commonly
2147483647, which excludes the top bit.) */
srand((unsigned int)(data[size/2]));
r1 = rand();
r2 = rand();
/* Ensure that all undefined option bits are zero (waste of time trying them)
and also that PCRE2_NO_UTF_CHECK is unset, as there is no guarantee that the
input is UTF-8. Also unset PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as there is no
reason to disallow UTF and UCP. Force PCRE2_NEVER_BACKSLASH_C to be set because
\C in random patterns is highly likely to cause a crash. */
compile_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_COMPILE_OPTIONS) |
PCRE2_NEVER_BACKSLASH_C;
match_options =
((((uint32_t)r1 << 16) | ((uint32_t)r2 & 0xffff)) & ALLOWED_MATCH_OPTIONS);
/* Discard partial matching if PCRE2_ENDANCHORED is set, because they are not
allowed together and just give an immediate error return. */
if (((compile_options|match_options) & PCRE2_ENDANCHORED) != 0)
match_options &= ~(PCRE2_PARTIAL_HARD|PCRE2_PARTIAL_SOFT);
/* Do the compile with and without the options, and after a successful compile,
likewise do the match with and without the options. */
for (i = 0; i < 2; i++)
{
uint32_t callout_count;
int errorcode;
PCRE2_SIZE erroroffset;
pcre2_code *code;
#ifdef STANDALONE
printf("Compile options %.8x never_backslash_c", compile_options);
printf("%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
((compile_options & PCRE2_ALT_BSUX) != 0)? ",alt_bsux" : "",
((compile_options & PCRE2_ALT_CIRCUMFLEX) != 0)? ",alt_circumflex" : "",
((compile_options & PCRE2_ALT_VERBNAMES) != 0)? ",alt_verbnames" : "",
((compile_options & PCRE2_ALLOW_EMPTY_CLASS) != 0)? ",allow_empty_class" : "",
((compile_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((compile_options & PCRE2_AUTO_CALLOUT) != 0)? ",auto_callout" : "",
((compile_options & PCRE2_CASELESS) != 0)? ",caseless" : "",
((compile_options & PCRE2_DOLLAR_ENDONLY) != 0)? ",dollar_endonly" : "",
((compile_options & PCRE2_DOTALL) != 0)? ",dotall" : "",
((compile_options & PCRE2_DUPNAMES) != 0)? ",dupnames" : "",
((compile_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((compile_options & PCRE2_EXTENDED) != 0)? ",extended" : "",
((compile_options & PCRE2_FIRSTLINE) != 0)? ",firstline" : "",
((compile_options & PCRE2_MATCH_UNSET_BACKREF) != 0)? ",match_unset_backref" : "",
((compile_options & PCRE2_MULTILINE) != 0)? ",multiline" : "",
((compile_options & PCRE2_NEVER_UCP) != 0)? ",never_ucp" : "",
((compile_options & PCRE2_NEVER_UTF) != 0)? ",never_utf" : "",
((compile_options & PCRE2_NO_AUTO_CAPTURE) != 0)? ",no_auto_capture" : "",
((compile_options & PCRE2_NO_AUTO_POSSESS) != 0)? ",no_auto_possess" : "",
((compile_options & PCRE2_NO_DOTSTAR_ANCHOR) != 0)? ",no_dotstar_anchor" : "",
((compile_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((compile_options & PCRE2_NO_START_OPTIMIZE) != 0)? ",no_start_optimize" : "",
((compile_options & PCRE2_UCP) != 0)? ",ucp" : "",
((compile_options & PCRE2_UNGREEDY) != 0)? ",ungreedy" : "",
((compile_options & PCRE2_USE_OFFSET_LIMIT) != 0)? ",use_offset_limit" : "",
((compile_options & PCRE2_UTF) != 0)? ",utf" : "");
#endif
code = pcre2_compile((PCRE2_SPTR)data, (PCRE2_SIZE)size, compile_options,
&errorcode, &erroroffset, NULL);
/* Compilation succeeded */
if (code != NULL)
{
int j;
uint32_t save_match_options = match_options;
/* Create match data and context blocks only when we first need them. Set
low match and depth limits to avoid wasting too much searching large
pattern trees. Almost all matches are going to fail. */
if (match_data == NULL)
{
match_data = pcre2_match_data_create(32, NULL);
if (match_data == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match data block\n");
#endif
return 0;
}
}
if (match_context == NULL)
{
match_context = pcre2_match_context_create(NULL);
if (match_context == NULL)
{
#ifdef STANDALONE
printf("** Failed to create match context block\n");
#endif
return 0;
}
(void)pcre2_set_match_limit(match_context, 100);
(void)pcre2_set_depth_limit(match_context, 100);
(void)pcre2_set_callout(match_context, callout_function, &callout_count);
}
/* Match twice, with and without options. */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("Match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_JIT) != 0)? ",no_jit" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_match(code, (PCRE2_SPTR)data, (PCRE2_SIZE)match_size, 0,
match_options, match_data, match_context);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
/* Match with DFA twice, with and without options. */
match_options = save_match_options & ~PCRE2_NO_JIT; /* Not valid for DFA */
for (j = 0; j < 2; j++)
{
#ifdef STANDALONE
printf("DFA match options %.8x", match_options);
printf("%s%s%s%s%s%s%s%s%s\n",
((match_options & PCRE2_ANCHORED) != 0)? ",anchored" : "",
((match_options & PCRE2_ENDANCHORED) != 0)? ",endanchored" : "",
((match_options & PCRE2_NO_UTF_CHECK) != 0)? ",no_utf_check" : "",
((match_options & PCRE2_NOTBOL) != 0)? ",notbol" : "",
((match_options & PCRE2_NOTEMPTY) != 0)? ",notempty" : "",
((match_options & PCRE2_NOTEMPTY_ATSTART) != 0)? ",notempty_atstart" : "",
((match_options & PCRE2_NOTEOL) != 0)? ",noteol" : "",
((match_options & PCRE2_PARTIAL_HARD) != 0)? ",partial_hard" : "",
((match_options & PCRE2_PARTIAL_SOFT) != 0)? ",partial_soft" : "");
#endif
callout_count = 0;
errorcode = pcre2_dfa_match(code, (PCRE2_SPTR)data,
(PCRE2_SIZE)match_size, 0, match_options, match_data, match_context,
dfa_workspace, DFA_WORKSPACE_COUNT);
#ifdef STANDALONE
if (errorcode >= 0) printf("Match returned %d\n", errorcode); else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
printf("Match failed: error %d: %s\n", errorcode, buffer);
}
#endif
match_options = 0; /* For second time */
}
match_options = save_match_options; /* Reset for the second compile */
pcre2_code_free(code);
}
/* Compilation failed */
else
{
unsigned char buffer[256];
pcre2_get_error_message(errorcode, buffer, 256);
#ifdef STANDALONE
printf("Error %d at offset %lu: %s\n", errorcode, erroroffset, buffer);
#else
if (strstr((const char *)buffer, "internal error") != NULL) abort();
#endif
}
compile_options = PCRE2_NEVER_BACKSLASH_C; /* For second time */
}
if (match_data != NULL) pcre2_match_data_free(match_data);
if (match_context != NULL) pcre2_match_context_free(match_context);
return 0;
}
static wcstring pcre2_strerror(int err_code) {
wchar_t buf[128];
pcre2_get_error_message(err_code, (PCRE2_UCHAR *)buf, sizeof(buf) / sizeof(wchar_t));
return buf;
}
int regex_compile(tvh_regex_t *regex, const char *re_str, int flags, int subsys)
{
#if ENABLE_PCRE || ENABLE_PCRE2
regex->is_posix = 0;
if (flags & TVHREGEX_POSIX) {
regex->is_posix = 1;
#endif
int options = REG_EXTENDED;
if (flags & TVHREGEX_CASELESS)
options |= REG_ICASE;
if (!regcomp(®ex->re_posix_code, re_str, options))
return 0;
tvherror(subsys, "Unable to compile regex '%s'", re_str);
return -1;
#if ENABLE_PCRE || ENABLE_PCRE2
} else {
#if ENABLE_PCRE
const char *estr;
int eoff;
int options = PCRE_UTF8;
if (flags & TVHREGEX_CASELESS)
options |= PCRE_CASELESS;
#if PCRE_STUDY_JIT_COMPILE
regex->re_jit_stack = NULL;
#endif
regex->re_extra = NULL;
regex->re_code = pcre_compile(re_str, options, &estr, &eoff, NULL);
if (regex->re_code == NULL) {
tvherror(subsys, "Unable to compile PCRE '%s': %s", re_str, estr);
} else {
regex->re_extra = pcre_study(regex->re_code,
PCRE_STUDY_JIT_COMPILE, &estr);
if (regex->re_extra == NULL && estr)
tvherror(subsys, "Unable to study PCRE '%s': %s", re_str, estr);
else {
#if PCRE_STUDY_JIT_COMPILE
regex->re_jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024);
if (regex->re_jit_stack)
pcre_assign_jit_stack(regex->re_extra, NULL, regex->re_jit_stack);
#endif
return 0;
}
}
return -1;
#elif ENABLE_PCRE2
PCRE2_UCHAR8 ebuf[128];
int ecode;
PCRE2_SIZE eoff;
size_t jsz;
uint32_t options;
assert(regex->re_jit_stack == NULL);
regex->re_jit_stack = NULL;
regex->re_match = NULL;
regex->re_mcontext = pcre2_match_context_create(NULL);
options = PCRE2_UTF;
if (flags & TVHREGEX_CASELESS)
options |= PCRE2_CASELESS;
regex->re_code = pcre2_compile((PCRE2_SPTR8)re_str, -1, options,
&ecode, &eoff, NULL);
if (regex->re_code == NULL) {
(void)pcre2_get_error_message(ecode, ebuf, 120);
tvherror(subsys, "Unable to compile PCRE2 '%s': %s", re_str, ebuf);
} else {
regex->re_match = pcre2_match_data_create(TVHREGEX_MAX_MATCHES, NULL);
if (re_str[0] && pcre2_jit_compile(regex->re_code, PCRE2_JIT_COMPLETE) >= 0) {
jsz = 0;
if (pcre2_pattern_info(regex->re_code, PCRE2_INFO_JITSIZE, &jsz) >= 0 && jsz > 0) {
regex->re_jit_stack = pcre2_jit_stack_create(32 * 1024, 512 * 1024, NULL);
if (regex->re_jit_stack)
pcre2_jit_stack_assign(regex->re_mcontext, NULL, regex->re_jit_stack);
}
}
return 0;
}
return -1;
#endif
}
#endif
}
void regex_format_error(struct regex_error_data const *error_data, char *buffer,
size_t buf_size)
{
unsigned the_end_length = buf_size > 4 ? 4 : buf_size;
char *ptr = &buffer[buf_size - the_end_length];
int rc = 0;
size_t pos = 0;
if (!buffer || !buf_size)
return;
rc = snprintf(buffer, buf_size, "REGEX back-end error: ");
if (rc < 0)
/*
* If snprintf fails it constitutes a logical error that needs
* fixing.
*/
abort();
pos += rc;
if (pos >= buf_size)
goto truncated;
if (error_data->error_offset > 0) {
#ifdef USE_PCRE2
rc = snprintf(buffer + pos, buf_size - pos, "At offset %zu: ",
error_data->error_offset);
#else
rc = snprintf(buffer + pos, buf_size - pos, "At offset %d: ",
error_data->error_offset);
#endif
if (rc < 0)
abort();
}
pos += rc;
if (pos >= buf_size)
goto truncated;
#ifdef USE_PCRE2
rc = pcre2_get_error_message(error_data->error_code,
(PCRE2_UCHAR *)(buffer + pos),
buf_size - pos);
if (rc == PCRE2_ERROR_NOMEMORY)
goto truncated;
#else
rc = snprintf(buffer + pos, buf_size - pos, "%s",
error_data->error_buffer);
if (rc < 0)
abort();
if ((size_t)rc < strlen(error_data->error_buffer))
goto truncated;
#endif
return;
truncated:
/* replace end of string with "..." to indicate that it was truncated */
switch (the_end_length) {
/* no break statements, fall-through is intended */
case 4:
*ptr++ = '.';
/* FALLTHRU */
case 3:
*ptr++ = '.';
/* FALLTHRU */
case 2:
*ptr++ = '.';
/* FALLTHRU */
case 1:
*ptr++ = '\0';
/* FALLTHRU */
default:
break;
}
return;
}
tb_char_t const* tb_regex_replace(tb_regex_ref_t self, tb_char_t const* cstr, tb_size_t size, tb_size_t start, tb_char_t const* replace_cstr, tb_size_t replace_size, tb_size_t* plength)
{
// check
tb_regex_t* regex = (tb_regex_t*)self;
tb_assert_and_check_return_val(regex && regex->code && cstr && replace_cstr, tb_null);
// done
tb_char_t const* result = tb_null;
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
if (regex->mode & TB_REGEX_MODE_GLOBAL) options |= PCRE2_SUBSTITUTE_GLOBAL;
// init buffer
if (!regex->buffer_data)
{
regex->buffer_maxn = tb_max(size + replace_size + 64, 256);
regex->buffer_data = (PCRE2_UCHAR*)tb_malloc_bytes(regex->buffer_maxn);
}
tb_assert_and_check_break(regex->buffer_data);
// done
tb_long_t ok = -1;
PCRE2_SIZE length = 0;
while (1)
{
// replace it
length = (PCRE2_SIZE)regex->buffer_maxn;
ok = pcre2_substitute(regex->code, (PCRE2_SPTR)cstr, (PCRE2_SIZE)size, (PCRE2_SIZE)start, options, tb_null, tb_null, (PCRE2_SPTR)replace_cstr, (PCRE2_SIZE)replace_size, regex->buffer_data, &length);
// no space?
if (ok == PCRE2_ERROR_NOMEMORY)
{
// grow buffer
regex->buffer_maxn <<= 1;
regex->buffer_data = (PCRE2_UCHAR*)tb_ralloc_bytes(regex->buffer_data, regex->buffer_maxn);
tb_assert_and_check_break(regex->buffer_data);
}
// failed
else if (ok < 0)
{
#if defined(__tb_debug__) && !defined(TB_CONFIG_OS_WINDOWS)
// get error info
PCRE2_UCHAR info[256];
pcre2_get_error_message(ok, info, sizeof(info));
// trace
tb_trace_d("replace failed at offset %lu: error: %ld, %s\n", start, ok, info);
#endif
// end
break;
}
else break;
}
// check
tb_check_break(ok > 0);
tb_assert_and_check_break(length < regex->buffer_maxn);
// end
regex->buffer_data[length] = '\0';
// trace
tb_trace_d(" replace: [%lu]: %s", length, regex->buffer_data);
// save length
if (plength) *plength = (tb_size_t)length;
// ok
result = (tb_char_t const*)regex->buffer_data;
} while (0);
// ok?
return result;
}
/* //////////////////////////////////////////////////////////////////////////////////////
* implementation
*/
tb_regex_ref_t tb_regex_init(tb_char_t const* pattern, tb_size_t mode)
{
// check
tb_assert_and_check_return_val(pattern, tb_null);
// done
tb_bool_t ok = tb_false;
tb_regex_t* regex = tb_null;
do
{
// make regex
regex = (tb_regex_t*)tb_malloc0_type(tb_regex_t);
tb_assert_and_check_break(regex);
// init options
tb_uint32_t options = PCRE2_UTF;
if (mode & TB_REGEX_MODE_CASELESS) options |= PCRE2_CASELESS;
if (mode & TB_REGEX_MODE_MULTILINE) options |= PCRE2_MULTILINE;
#ifndef __tb_debug__
options |= PCRE2_NO_UTF_CHECK;
#endif
// init code
tb_int_t errornumber;
PCRE2_SIZE erroroffset;
regex->code = pcre2_compile((PCRE2_SPTR)pattern, PCRE2_ZERO_TERMINATED, options, &errornumber, &erroroffset, tb_null);
if (!regex->code)
{
#if defined(__tb_debug__) && !defined(TB_CONFIG_OS_WINDOWS) // FIXME: _sprintf undefined link error for vs2015 on windows
// get error info
PCRE2_UCHAR info[256];
pcre2_get_error_message(errornumber, info, sizeof(info));
// trace
tb_trace_d("compile failed at offset %ld: %s\n", (tb_long_t)erroroffset, info);
#endif
// end
break;
}
// init match data
regex->match_data = pcre2_match_data_create_from_pattern(regex->code, tb_null);
tb_assert_and_check_break(regex->match_data);
// save mode
regex->mode = mode;
// ok
ok = tb_true;
} while (0);
// failed?
if (!ok)
{
// exit it
if (regex) tb_regex_exit((tb_regex_ref_t)regex);
regex = tb_null;
}
// ok?
return (tb_regex_ref_t)regex;
}
rspamd_regexp_t*
rspamd_regexp_new (const gchar *pattern, const gchar *flags,
GError **err)
{
const gchar *start = pattern, *end, *flags_str = NULL;
gchar *err_str;
rspamd_regexp_t *res;
PCRE_T *r;
gchar sep = 0, *real_pattern;
#ifndef WITH_PCRE2
gint err_off;
#else
gsize err_off;
#endif
gint regexp_flags = 0, rspamd_flags = 0, err_code, ncaptures;
gboolean strict_flags = FALSE;
rspamd_regexp_library_init (NULL);
if (flags == NULL) {
/* We need to parse pattern and detect flags set */
if (*start == '/') {
sep = '/';
}
else if (*start == 'm') {
start ++;
sep = *start;
/* Paired braces */
if (sep == '{') {
sep = '}';
}
rspamd_flags |= RSPAMD_REGEXP_FLAG_FULL_MATCH;
}
if (sep == '\0' || g_ascii_isalnum (sep)) {
/* We have no flags, no separators and just use all line as expr */
start = pattern;
end = start + strlen (pattern);
rspamd_flags &= ~RSPAMD_REGEXP_FLAG_FULL_MATCH;
}
else {
end = strrchr (pattern, sep);
if (end == NULL || end <= start) {
g_set_error (err, rspamd_regexp_quark(), EINVAL,
"pattern is not enclosed with %c: %s",
sep, pattern);
return NULL;
}
flags_str = end + 1;
start ++;
}
}
else {
/* Strictly check all flags */
strict_flags = TRUE;
start = pattern;
end = pattern + strlen (pattern);
flags_str = flags;
}
rspamd_flags |= RSPAMD_REGEXP_FLAG_RAW;
#ifndef WITH_PCRE2
regexp_flags &= ~PCRE_FLAG(UTF8);
regexp_flags |= PCRE_FLAG(NEWLINE_ANYCRLF);
#else
regexp_flags &= ~PCRE_FLAG(UTF);
#endif
if (flags_str != NULL) {
while (*flags_str) {
switch (*flags_str) {
case 'i':
regexp_flags |= PCRE_FLAG(CASELESS);
break;
case 'm':
regexp_flags |= PCRE_FLAG(MULTILINE);
break;
case 's':
regexp_flags |= PCRE_FLAG(DOTALL);
break;
case 'x':
regexp_flags |= PCRE_FLAG(EXTENDED);
break;
case 'u':
rspamd_flags &= ~RSPAMD_REGEXP_FLAG_RAW;
#ifndef WITH_PCRE2
regexp_flags |= PCRE_FLAG(UTF8);
#else
regexp_flags |= PCRE_FLAG(UTF);
#endif
break;
case 'O':
/* We optimize all regexps by default */
rspamd_flags |= RSPAMD_REGEXP_FLAG_NOOPT;
break;
case 'r':
rspamd_flags |= RSPAMD_REGEXP_FLAG_RAW;
#ifndef WITH_PCRE2
regexp_flags &= ~PCRE_FLAG(UTF8);
#else
regexp_flags &= ~PCRE_FLAG(UTF);
#endif
break;
default:
if (strict_flags) {
g_set_error (err, rspamd_regexp_quark(), EINVAL,
"invalid regexp flag: %c in pattern %s",
*flags_str, pattern);
return NULL;
}
msg_warn ("invalid flag '%c' in pattern %s", *flags_str, pattern);
goto fin;
break;
}
flags_str++;
}
}
fin:
real_pattern = g_malloc (end - start + 1);
rspamd_strlcpy (real_pattern, start, end - start + 1);
#ifndef WITH_PCRE2
r = pcre_compile (real_pattern, regexp_flags,
(const char **)&err_str, &err_off, NULL);
(void)err_code;
#else
r = pcre2_compile (real_pattern, PCRE2_ZERO_TERMINATED,
regexp_flags,
&err_code, &err_off, pcre2_ctx);
if (r == NULL) {
err_str = g_alloca (1024);
memset (err_str, 0, 1024);
pcre2_get_error_message (err_code, err_str, 1024);
}
#endif
if (r == NULL) {
g_set_error (err, rspamd_regexp_quark(), EINVAL,
"regexp parsing error: '%s' at position %d",
err_str, (gint)err_off);
g_free (real_pattern);
return NULL;
}
/* Now allocate the target structure */
res = g_malloc0 (sizeof (*res));
REF_INIT_RETAIN (res, rspamd_regexp_dtor);
res->flags = rspamd_flags;
res->pattern = real_pattern;
res->cache_id = RSPAMD_INVALID_ID;
res->pcre_flags = regexp_flags;
res->max_hits = 0;
res->re = r;
if (rspamd_flags & RSPAMD_REGEXP_FLAG_RAW) {
res->raw_re = r;
}
else {
#ifndef WITH_PCRE2
res->raw_re = pcre_compile (real_pattern, regexp_flags & ~PCRE_FLAG(UTF8),
(const char **)&err_str, &err_off, NULL);
(void)err_code;
#else
res->raw_re = pcre2_compile (real_pattern, PCRE2_ZERO_TERMINATED,
regexp_flags & ~PCRE_FLAG(UTF),
&err_code, &err_off, pcre2_ctx);
if (res->raw_re == NULL) {
err_str = g_alloca (1024);
memset (err_str, 0, 1024);
pcre2_get_error_message (err_code, err_str, 1024);
}
#endif
if (res->raw_re == NULL) {
msg_warn ("raw regexp parsing error: '%s': '%s' at position %d",
err_str, real_pattern, (gint)err_off);
}
}
rspamd_regexp_post_process (res);
rspamd_regexp_generate_id (pattern, flags, res->id);
#ifndef WITH_PCRE2
/* Check number of captures */
if (pcre_fullinfo (res->raw_re, res->extra, PCRE_INFO_CAPTURECOUNT,
&ncaptures) == 0) {
res->ncaptures = ncaptures;
}
/* Check number of backrefs */
if (pcre_fullinfo (res->raw_re, res->extra, PCRE_INFO_BACKREFMAX,
&ncaptures) == 0) {
res->nbackref = ncaptures;
}
#else
/* Check number of captures */
if (pcre2_pattern_info (res->raw_re, PCRE2_INFO_CAPTURECOUNT,
&ncaptures) == 0) {
res->ncaptures = ncaptures;
}
/* Check number of backrefs */
if (pcre2_pattern_info (res->raw_re, PCRE2_INFO_BACKREFMAX,
&ncaptures) == 0) {
res->nbackref = ncaptures;
}
#endif
return res;
}