/* TODO: audit this function */
static void named_substr_print(const struct cli_pcre_data *pd, const unsigned char *buffer, int *ovector)
{
int i, j, length, namecount, trunc;
unsigned char *tabptr;
int name_entry_size;
unsigned char *name_table;
const char *start;
char outstr[2*MATCH_MAXLEN+1];
/* determine if there are named substrings */
#if USING_PCRE2
(void)pcre2_pattern_info(pd->re, PCRE2_INFO_NAMECOUNT, &namecount);
#else
(void)pcre_fullinfo(pd->re, pd->ex, PCRE_INFO_NAMECOUNT, &namecount);
#endif
if (namecount <= 0) {
cli_dbgmsg("cli_pcre_report: no named substrings\n");
}
else {
cli_dbgmsg("cli_pcre_report: named substrings\n");
/* extract named substring translation table */
#if USING_PCRE2
(void)pcre2_pattern_info(pd->re, PCRE2_INFO_NAMETABLE, &name_table);
(void)pcre2_pattern_info(pd->re, PCRE2_INFO_NAMEENTRYSIZE, &name_entry_size);
#else
(void)pcre_fullinfo(pd->re, pd->ex, PCRE_INFO_NAMETABLE, &name_table);
(void)pcre_fullinfo(pd->re, pd->ex, PCRE_INFO_NAMEENTRYSIZE, &name_entry_size);
#endif
/* print named substring information */
tabptr = name_table;
for (i = 0; i < namecount; i++) {
int n = (tabptr[0] << 8) | tabptr[1];
start = buffer + ovector[2*n];
length = ovector[2*n+1] - ovector[2*n];
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%s\n", n, name_entry_size - 3, tabptr + 2,
outstr, trunc ? " (trunc)":"");
/*
cli_dbgmsg("named_substr: (%d) %*s: %.*s%s\n", n, name_entry_size - 3, tabptr + 2,
length, start, trunc ? " (trunc)":"");
*/
tabptr += name_entry_size;
}
}
}
/*
* TODO Replace this compare function with something that actually compares the
* regular expressions.
* This compare function basically just compares the binary representations of
* the automatons, and because this representation contains pointers and
* metadata, it can only return a match if regex1 == regex2.
* Preferably, this function would be replaced with an algorithm that computes
* the equivalence of the automatons systematically.
*/
int regex_cmp(struct regex_data *regex1, struct regex_data *regex2)
{
int rc;
size_t len1, len2;
rc = pcre2_pattern_info(regex1->regex, PCRE2_INFO_SIZE, &len1);
assert(rc == 0);
rc = pcre2_pattern_info(regex2->regex, PCRE2_INFO_SIZE, &len2);
assert(rc == 0);
if (len1 != len2 || memcmp(regex1->regex, regex2->regex, len1))
return SELABEL_INCOMPARABLE;
return SELABEL_EQUAL;
}
int32 ftw_pcre_capture_groups(const pcre2_code *compiled_regex, LStrHandleArray **named_capturing_groups)
{
int rc;
uint32_t i;
uint32_t num_submatches;
uint32_t namecount;
uint32_t namesize;
uint32_t entrysize;
uChar *nametable;
const uChar *offset;
MgErr lv_err;
uInt16 submatch_index;
rc = pcre2_pattern_info(compiled_regex, PCRE2_INFO_NAMECOUNT, &namecount);
if (rc)
return rc;
rc = pcre2_pattern_info(compiled_regex, PCRE2_INFO_NAMEENTRYSIZE, &entrysize);
if (rc)
return rc;
rc = pcre2_pattern_info(compiled_regex, PCRE2_INFO_NAMETABLE, &nametable);
if (rc)
return rc;
rc = pcre2_pattern_info(compiled_regex, PCRE2_INFO_CAPTURECOUNT, &num_submatches);
if (rc)
return rc;
lv_err = ftw_support_expand_LStrHandleArray(&named_capturing_groups, num_submatches);
if (lv_err)
return lv_err;
namesize = entrysize - sizeof(submatch_index);
offset = nametable;
for (i = 0; i < namecount; i++) {
offset = nametable + i * entrysize;
submatch_index = Word(offset[0], offset[1]) - 1;
offset += sizeof(submatch_index);
lv_err = ftw_support_CStr_to_LStrHandle(&((*named_capturing_groups)->element)[submatch_index], offset, namesize);
if (lv_err)
break;
}
return lv_err;
}
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
regcomp(regex_t *preg, const char *pattern, int cflags)
{
PCRE2_SIZE erroffset;
PCRE2_SIZE patlen;
int errorcode;
int options = 0;
int re_nsub = 0;
patlen = ((cflags & REG_PEND) != 0)? (PCRE2_SIZE)(preg->re_endp - pattern) :
PCRE2_ZERO_TERMINATED;
if ((cflags & REG_ICASE) != 0) options |= PCRE2_CASELESS;
if ((cflags & REG_NEWLINE) != 0) options |= PCRE2_MULTILINE;
if ((cflags & REG_DOTALL) != 0) options |= PCRE2_DOTALL;
if ((cflags & REG_NOSPEC) != 0) options |= PCRE2_LITERAL;
if ((cflags & REG_UTF) != 0) options |= PCRE2_UTF;
if ((cflags & REG_UCP) != 0) options |= PCRE2_UCP;
if ((cflags & REG_UNGREEDY) != 0) options |= PCRE2_UNGREEDY;
preg->re_cflags = cflags;
preg->re_pcre2_code = pcre2_compile((PCRE2_SPTR)pattern, patlen, options,
&errorcode, &erroffset, NULL);
preg->re_erroffset = erroffset;
if (preg->re_pcre2_code == NULL)
{
unsigned int i;
/* A negative value is a UTF error; otherwise all error codes are greater
than COMPILE_ERROR_BASE, but check, just in case. */
if (errorcode < COMPILE_ERROR_BASE) return REG_BADPAT;
errorcode -= COMPILE_ERROR_BASE;
if (errorcode < (int)(sizeof(eint1)/sizeof(const int)))
return eint1[errorcode];
for (i = 0; i < sizeof(eint2)/sizeof(const int); i += 2)
if (errorcode == eint2[i]) return eint2[i+1];
return REG_BADPAT;
}
(void)pcre2_pattern_info((const pcre2_code *)preg->re_pcre2_code,
PCRE2_INFO_CAPTURECOUNT, &re_nsub);
preg->re_nsub = (size_t)re_nsub;
preg->re_match_data = pcre2_match_data_create(re_nsub + 1, NULL);
if (preg->re_match_data == NULL)
{
pcre2_code_free(preg->re_pcre2_code);
return REG_ESPACE;
}
return 0;
}
PCRE2POSIX_EXP_DEFN int PCRE2_CALL_CONVENTION
regcomp(regex_t *preg, const char *pattern, int cflags)
{
PCRE2_SIZE erroffset;
int errorcode;
int options = 0;
int re_nsub = 0;
if ((cflags & REG_ICASE) != 0) options |= PCRE2_CASELESS;
if ((cflags & REG_NEWLINE) != 0) options |= PCRE2_MULTILINE;
if ((cflags & REG_DOTALL) != 0) options |= PCRE2_DOTALL;
if ((cflags & REG_NOSUB) != 0) options |= PCRE2_NO_AUTO_CAPTURE;
if ((cflags & REG_UTF) != 0) options |= PCRE2_UTF;
if ((cflags & REG_UCP) != 0) options |= PCRE2_UCP;
if ((cflags & REG_UNGREEDY) != 0) options |= PCRE2_UNGREEDY;
preg->re_pcre2_code = pcre2_compile((PCRE2_SPTR)pattern, PCRE2_ZERO_TERMINATED,
options, &errorcode, &erroffset, NULL);
preg->re_erroffset = erroffset;
if (preg->re_pcre2_code == NULL)
{
unsigned int i;
if (errorcode < 0) return REG_BADPAT; /* UTF error */
errorcode -= COMPILE_ERROR_BASE;
if (errorcode < (int)(sizeof(eint1)/sizeof(const int)))
return eint1[errorcode];
for (i = 0; i < sizeof(eint2)/(2*sizeof(const int)); i += 2)
if (errorcode == eint2[i]) return eint2[i+1];
return REG_BADPAT;
}
(void)pcre2_pattern_info((const pcre2_code *)preg->re_pcre2_code,
PCRE2_INFO_CAPTURECOUNT, &re_nsub);
preg->re_nsub = (size_t)re_nsub;
if ((options & PCRE2_NO_AUTO_CAPTURE) != 0) re_nsub = -1;
preg->re_match_data = pcre2_match_data_create(re_nsub + 1, NULL);
return 0;
}
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 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
}
/* Compile a regular expression to be used later
* Allowed flags are:
* - OS_CASE_SENSITIVE
* - OS_RETURN_SUBSTRING
* Returns 1 on success or 0 on error
* The error code is set on reg->error
*/
int OSRegex_Compile(const char *pattern, OSRegex *reg, int flags)
{
char *pattern_pcre2 = NULL;
int flags_compile = 0;
int error = 0;
PCRE2_SIZE erroroffset = 0;
size_t pattern_len = 0UL;
char first_char, last_char;
uint32_t count, i;
/* Check for references not initialized */
if (reg == NULL) {
return (0);
}
/* Initialize OSRegex structure */
reg->error = 0;
reg->sub_strings = NULL;
reg->regex = NULL;
reg->match_data = NULL;
reg->pattern_len = 0UL;
reg->pattern = NULL;
reg->exec_function = NULL;
/* The pattern can't be null */
if (pattern == NULL) {
reg->error = OS_REGEX_PATTERN_NULL;
goto compile_error;
}
/* Maximum size of the pattern */
pattern_len = strlen(pattern);
if (pattern_len > OS_PATTERN_MAXSIZE) {
reg->error = OS_REGEX_MAXSIZE;
goto compile_error;
}
if (OSRegex_CouldBeOptimized(pattern)) {
first_char = pattern[0];
last_char = pattern[pattern_len - 1];
if (first_char == '^') {
if (last_char == '$') {
reg->pattern = strdup(&pattern[1]);
reg->pattern_len = pattern_len - 2;
reg->pattern[reg->pattern_len] = '\0';
if (flags & OS_CASE_SENSITIVE) {
reg->exec_function = OSRegex_Execute_strcmp;
} else {
reg->exec_function = OSRegex_Execute_strcasecmp;
}
return (1);
} else {
reg->pattern = strdup(&pattern[1]);
reg->pattern_len = pattern_len - 1;
if (flags & OS_CASE_SENSITIVE) {
reg->exec_function = OSRegex_Execute_strncmp;
} else {
reg->exec_function = OSRegex_Execute_strncasecmp;
}
return (1);
}
} else {
if (last_char == '$') {
reg->pattern = strdup(pattern);
reg->pattern_len = pattern_len - 1;
reg->pattern[reg->pattern_len] = '\0';
if (flags & OS_CASE_SENSITIVE) {
reg->exec_function = OSRegex_Execute_strrcmp;
} else {
reg->exec_function = OSRegex_Execute_strrcasecmp;
}
return (1);
}
}
}
reg->exec_function = OSRegex_Execute_pcre2_match;
/* Ossec pattern conversion */
if (OSRegex_Convert(pattern, &pattern_pcre2, OS_CONVERT_REGEX) == 0) {
reg->error = OS_REGEX_BADREGEX;
goto compile_error;
}
flags_compile |= PCRE2_UTF;
flags_compile |= PCRE2_NO_UTF_CHECK;
flags_compile |= (flags & OS_CASE_SENSITIVE) ? 0 : PCRE2_CASELESS;
reg->regex = pcre2_compile((PCRE2_SPTR)pattern_pcre2, PCRE2_ZERO_TERMINATED, flags_compile,
&error, &erroroffset, NULL);
if (reg->regex == NULL) {
reg->error = OS_REGEX_BADREGEX;
goto compile_error;
}
reg->match_data = pcre2_match_data_create_from_pattern(reg->regex, NULL);
if (reg->match_data == NULL) {
reg->error = OS_REGEX_OUTOFMEMORY;
goto compile_error;
}
#ifdef USE_PCRE2_JIT
/* Just In Time compilation for faster execution */
if (pcre2_jit_compile(reg->regex, PCRE2_JIT_COMPLETE) != 0) {
reg->error = OS_REGEX_NO_JIT;
goto compile_error;
}
#endif
if (flags & OS_RETURN_SUBSTRING) {
pcre2_pattern_info(reg->regex, PCRE2_INFO_CAPTURECOUNT, (void *)&count);
count++; // to store NULL pointer at the end
reg->sub_strings = calloc(count, sizeof(char *));
if (reg->sub_strings == NULL) {
reg->error = OS_REGEX_OUTOFMEMORY;
goto compile_error;
}
for (i = 0; i < count; i++) {
reg->sub_strings[i] = NULL;
}
}
free(pattern_pcre2);
return (1);
compile_error:
/* Error handling */
if (pattern_pcre2) {
free(pattern_pcre2);
}
OSRegex_FreePattern(reg);
return (0);
}
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;
}
static void
rspamd_regexp_post_process (rspamd_regexp_t *r)
{
if (global_re_cache == NULL) {
rspamd_regexp_library_init (NULL);
}
#if defined(WITH_PCRE2)
gsize jsz;
guint jit_flags = PCRE2_JIT_COMPLETE;
/* Create match context */
r->mcontext = pcre2_match_context_create (NULL);
if (r->re != r->raw_re) {
r->raw_mcontext = pcre2_match_context_create (NULL);
}
else {
r->raw_mcontext = r->mcontext;
}
#ifdef HAVE_PCRE_JIT
if (pcre2_jit_compile (r->re, jit_flags) < 0) {
msg_err ("jit compilation of %s is not supported: %d", r->pattern, jit_flags);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
else {
if (!(pcre2_pattern_info (r->re, PCRE2_INFO_JITSIZE, &jsz) >= 0 && jsz > 0)) {
msg_err ("jit compilation of %s is not supported", r->pattern);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
}
if (!(r->flags & RSPAMD_REGEXP_FLAG_DISABLE_JIT)) {
pcre2_jit_stack_assign (r->mcontext, NULL, global_re_cache->jstack);
}
if (r->re != r->raw_re) {
if (pcre2_jit_compile (r->raw_re, jit_flags) < 0) {
msg_debug ("jit compilation of %s is not supported", r->pattern);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
if (!(pcre2_pattern_info (r->raw_re, PCRE2_INFO_JITSIZE, &jsz) >= 0 && jsz > 0)) {
msg_debug ("jit compilation of raw %s is not supported", r->pattern);
}
else if (!(r->flags & RSPAMD_REGEXP_FLAG_DISABLE_JIT)) {
pcre2_jit_stack_assign (r->raw_mcontext, NULL, global_re_cache->jstack);
}
}
#endif
#else
const gchar *err_str = "unknown";
gboolean try_jit = TRUE, try_raw_jit = TRUE;
gint study_flags = 0;
#if defined(HAVE_PCRE_JIT)
study_flags |= PCRE_STUDY_JIT_COMPILE;
#endif
/* Pcre 1 needs study */
if (r->re) {
r->extra = pcre_study (r->re, study_flags, &err_str);
if (r->extra == NULL) {
msg_debug ("cannot optimize regexp pattern: '%s': %s",
r->pattern, err_str);
try_jit = FALSE;
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
}
else {
g_assert_not_reached ();
}
if (r->raw_re && r->raw_re != r->re) {
r->raw_extra = pcre_study (r->re, study_flags, &err_str);
}
else if (r->raw_re == r->re) {
r->raw_extra = r->extra;
}
if (r->raw_extra == NULL) {
msg_debug ("cannot optimize raw regexp pattern: '%s': %s",
r->pattern, err_str);
try_raw_jit = FALSE;
}
/* JIT path */
if (try_jit) {
#ifdef HAVE_PCRE_JIT
gint jit, n;
if (can_jit) {
jit = 0;
n = pcre_fullinfo (r->re, r->extra,
PCRE_INFO_JIT, &jit);
if (n != 0 || jit != 1) {
msg_debug ("jit compilation of %s is not supported", r->pattern);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
else {
pcre_assign_jit_stack (r->extra, NULL, global_re_cache->jstack);
}
}
#endif
}
else {
msg_debug ("cannot optimize regexp pattern: '%s': %s",
r->pattern, err_str);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
if (try_raw_jit) {
#ifdef HAVE_PCRE_JIT
gint jit, n;
if (can_jit) {
if (r->raw_re != r->re) {
jit = 0;
n = pcre_fullinfo (r->raw_re, r->raw_extra,
PCRE_INFO_JIT, &jit);
if (n != 0 || jit != 1) {
msg_debug ("jit compilation of %s is not supported", r->pattern);
r->flags |= RSPAMD_REGEXP_FLAG_DISABLE_JIT;
}
else {
pcre_assign_jit_stack (r->raw_extra, NULL,
global_re_cache->jstack);
}
}
}
#endif
}
#endif /* WITH_PCRE2 */
}
