2014-03-07 18:28:52 +01:00
|
|
|
/*************************************************
|
|
|
|
* Perl-Compatible Regular Expressions *
|
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
/* PCRE is a library of functions to support regular expressions whose syntax
|
|
|
|
and semantics are as close as possible to those of the Perl 5 language.
|
|
|
|
|
|
|
|
Written by Philip Hazel
|
|
|
|
Original API code Copyright (c) 1997-2012 University of Cambridge
|
2018-07-21 16:34:51 +02:00
|
|
|
New API code Copyright (c) 2016-2018 University of Cambridge
|
2014-03-07 18:28:52 +01:00
|
|
|
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
|
|
modification, are permitted provided that the following conditions are met:
|
|
|
|
|
|
|
|
* Redistributions of source code must retain the above copyright notice,
|
|
|
|
this list of conditions and the following disclaimer.
|
|
|
|
|
|
|
|
* Redistributions in binary form must reproduce the above copyright
|
|
|
|
notice, this list of conditions and the following disclaimer in the
|
|
|
|
documentation and/or other materials provided with the distribution.
|
|
|
|
|
|
|
|
* Neither the name of the University of Cambridge nor the names of its
|
|
|
|
contributors may be used to endorse or promote products derived from
|
|
|
|
this software without specific prior written permission.
|
|
|
|
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
|
|
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
|
|
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
|
|
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
|
|
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
|
|
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
|
|
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
|
|
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
|
|
POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
#ifdef HAVE_CONFIG_H
|
|
|
|
#include "config.h"
|
|
|
|
#endif
|
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
#define NLBLOCK cb /* Block containing newline information */
|
2014-06-14 20:29:51 +02:00
|
|
|
#define PSSTART start_pattern /* Field containing processed string start */
|
|
|
|
#define PSEND end_pattern /* Field containing processed string end */
|
|
|
|
|
2014-03-07 18:28:52 +01:00
|
|
|
#include "pcre2_internal.h"
|
|
|
|
|
2015-05-06 18:51:25 +02:00
|
|
|
/* In rare error cases debugging might require calling pcre2_printint(). */
|
|
|
|
|
|
|
|
#if 0
|
|
|
|
#ifdef EBCDIC
|
|
|
|
#define PRINTABLE(c) ((c) >= 64 && (c) < 255)
|
|
|
|
#else
|
|
|
|
#define PRINTABLE(c) ((c) >= 32 && (c) < 127)
|
|
|
|
#endif
|
|
|
|
#include "pcre2_printint.c"
|
2016-10-02 18:01:01 +02:00
|
|
|
#define DEBUG_CALL_PRINTINT
|
2015-05-06 18:51:25 +02:00
|
|
|
#endif
|
2014-03-07 18:28:52 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Other debugging code can be enabled by these defines. */
|
|
|
|
|
2018-06-20 19:05:31 +02:00
|
|
|
/* #define DEBUG_SHOW_CAPTURES */
|
|
|
|
/* #define DEBUG_SHOW_PARSED */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* There are a few things that vary with different code unit sizes. Handle them
|
|
|
|
by defining macros in order to minimize #if usage. */
|
|
|
|
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
2014-08-03 19:50:08 +02:00
|
|
|
#define STRING_UTFn_RIGHTPAR STRING_UTF8_RIGHTPAR, 5
|
|
|
|
#define XDIGIT(c) xdigitab[c]
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
#else /* Either 16-bit or 32-bit */
|
2014-08-03 19:50:08 +02:00
|
|
|
#define XDIGIT(c) (MAX_255(c)? xdigitab[c] : 0xff)
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 16
|
2014-08-03 19:50:08 +02:00
|
|
|
#define STRING_UTFn_RIGHTPAR STRING_UTF16_RIGHTPAR, 6
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-08-10 18:09:24 +02:00
|
|
|
#else /* 32-bit */
|
2014-08-03 19:50:08 +02:00
|
|
|
#define STRING_UTFn_RIGHTPAR STRING_UTF32_RIGHTPAR, 6
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
|
|
|
#endif
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Macros to store and retrieve a PCRE2_SIZE value in the parsed pattern, which
|
|
|
|
consists of uint32_t elements. Assume that if uint32_t can't hold it, two of
|
|
|
|
them will be able to (i.e. assume a 64-bit world). */
|
|
|
|
|
|
|
|
#if PCRE2_SIZE_MAX <= UINT32_MAX
|
|
|
|
#define PUTOFFSET(s,p) *p++ = s
|
|
|
|
#define GETOFFSET(s,p) s = *p++
|
|
|
|
#define GETPLUSOFFSET(s,p) s = *(++p)
|
|
|
|
#define READPLUSOFFSET(s,p) s = p[1]
|
|
|
|
#define SKIPOFFSET(p) p++
|
|
|
|
#define SIZEOFFSET 1
|
|
|
|
#else
|
|
|
|
#define PUTOFFSET(s,p) \
|
|
|
|
{ *p++ = (uint32_t)(s >> 32); *p++ = (uint32_t)(s & 0xffffffff); }
|
|
|
|
#define GETOFFSET(s,p) \
|
|
|
|
{ s = ((PCRE2_SIZE)p[0] << 32) | (PCRE2_SIZE)p[1]; p += 2; }
|
|
|
|
#define GETPLUSOFFSET(s,p) \
|
|
|
|
{ s = ((PCRE2_SIZE)p[1] << 32) | (PCRE2_SIZE)p[2]; p += 2; }
|
|
|
|
#define READPLUSOFFSET(s,p) \
|
|
|
|
{ s = ((PCRE2_SIZE)p[1] << 32) | (PCRE2_SIZE)p[2]; }
|
|
|
|
#define SKIPOFFSET(p) p += 2
|
|
|
|
#define SIZEOFFSET 2
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Macros for manipulating elements of the parsed pattern vector. */
|
|
|
|
|
|
|
|
#define META_CODE(x) (x & 0xffff0000u)
|
|
|
|
#define META_DATA(x) (x & 0x0000ffffu)
|
|
|
|
#define META_DIFF(x,y) ((x-y)>>16)
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Function definitions to allow mutual recursion */
|
|
|
|
|
2017-01-16 18:40:47 +01:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-02-16 11:23:06 +01:00
|
|
|
static unsigned int
|
2017-01-16 18:40:47 +01:00
|
|
|
add_list_to_class_internal(uint8_t *, PCRE2_UCHAR **, uint32_t,
|
|
|
|
compile_block *, const uint32_t *, unsigned int);
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
static int
|
2016-10-02 18:01:01 +02:00
|
|
|
compile_regex(uint32_t, PCRE2_UCHAR **, uint32_t **, int *, uint32_t,
|
|
|
|
uint32_t *, int32_t *, uint32_t *, int32_t *, branch_chain *,
|
|
|
|
compile_block *, PCRE2_SIZE *);
|
|
|
|
|
|
|
|
static int
|
|
|
|
get_branchlength(uint32_t **, int *, int *, parsed_recurse_check *,
|
|
|
|
compile_block *);
|
|
|
|
|
|
|
|
static BOOL
|
|
|
|
set_lookbehind_lengths(uint32_t **, int *, int *, parsed_recurse_check *,
|
|
|
|
compile_block *);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
|
|
|
* Code parameters and static tables *
|
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#define MAX_GROUP_NUMBER 65535u
|
|
|
|
#define MAX_REPEAT_COUNT 65535u
|
|
|
|
#define REPEAT_UNLIMITED (MAX_REPEAT_COUNT+1)
|
|
|
|
|
|
|
|
/* COMPILE_WORK_SIZE specifies the size of stack workspace, which is used in
|
|
|
|
different ways in the different pattern scans. The parsing and group-
|
|
|
|
identifying pre-scan uses it to handle nesting, and needs it to be 16-bit
|
|
|
|
aligned for this. Having defined the size in code units, we set up
|
|
|
|
C16_WORK_SIZE as the number of elements in the 16-bit vector.
|
2015-11-08 15:41:34 +01:00
|
|
|
|
|
|
|
During the first compiling phase, when determining how much memory is required,
|
|
|
|
the regex is partly compiled into this space, but the compiled parts are
|
|
|
|
discarded as soon as they can be, so that hopefully there will never be an
|
|
|
|
overrun. The code does, however, check for an overrun, which can occur for
|
|
|
|
pathological patterns. The size of the workspace depends on LINK_SIZE because
|
|
|
|
the length of compiled items varies with this.
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
In the real compile phase, this workspace is not currently used. */
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2017-04-18 14:32:52 +02:00
|
|
|
#define COMPILE_WORK_SIZE (3000*LINK_SIZE) /* Size in code units */
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#define C16_WORK_SIZE \
|
|
|
|
((COMPILE_WORK_SIZE * sizeof(PCRE2_UCHAR))/sizeof(uint16_t))
|
|
|
|
|
|
|
|
/* A uint32_t vector is used for caching information about the size of
|
|
|
|
capturing groups, to improve performance. A default is created on the stack of
|
|
|
|
this size. */
|
|
|
|
|
|
|
|
#define GROUPINFO_DEFAULT_SIZE 256
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* The overrun tests check for a slightly smaller size so that they detect the
|
|
|
|
overrun before it actually does run off the end of the data block. */
|
|
|
|
|
|
|
|
#define WORK_SIZE_SAFETY_MARGIN (100)
|
|
|
|
|
|
|
|
/* This value determines the size of the initial vector that is used for
|
|
|
|
remembering named groups during the pre-compile. It is allocated on the stack,
|
|
|
|
but if it is too small, it is expanded, in a similar way to the workspace. The
|
|
|
|
value is the number of slots in the list. */
|
|
|
|
|
|
|
|
#define NAMED_GROUP_LIST_SIZE 20
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The pre-compiling pass over the pattern creates a parsed pattern in a vector
|
|
|
|
of uint32_t. For short patterns this lives on the stack, with this size. Heap
|
|
|
|
memory is used for longer patterns. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#define PARSED_PATTERN_DEFAULT_SIZE 1024
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Maximum length value to check against when making sure that the variable
|
|
|
|
that holds the compiled pattern length does not overflow. We make it a bit less
|
2016-10-02 18:01:01 +02:00
|
|
|
than INT_MAX to allow for adding in group terminating code units, so that we
|
|
|
|
don't have to check them every time. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
#define OFLOW_MAX (INT_MAX - 20)
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Code values for parsed patterns, which are stored in a vector of 32-bit
|
|
|
|
unsigned ints. Values less than META_END are literal data values. The coding
|
|
|
|
for identifying the item is in the top 16-bits, leaving 16 bits for the
|
|
|
|
additional data that some of them need. The META_CODE, META_DATA, and META_DIFF
|
2016-11-23 18:17:57 +01:00
|
|
|
macros are used to manipulate parsed pattern elements.
|
|
|
|
|
|
|
|
NOTE: When these definitions are changed, the table of extra lengths for each
|
|
|
|
code (meta_extra_lengths, just below) must be updated to remain in step. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
#define META_END 0x80000000u /* End of pattern */
|
|
|
|
|
|
|
|
#define META_ALT 0x80010000u /* alternation */
|
|
|
|
#define META_ATOMIC 0x80020000u /* atomic group */
|
|
|
|
#define META_BACKREF 0x80030000u /* Back ref */
|
|
|
|
#define META_BACKREF_BYNAME 0x80040000u /* \k'name' */
|
|
|
|
#define META_BIGVALUE 0x80050000u /* Next is a literal > META_END */
|
|
|
|
#define META_CALLOUT_NUMBER 0x80060000u /* (?C with numerical argument */
|
|
|
|
#define META_CALLOUT_STRING 0x80070000u /* (?C with string argument */
|
|
|
|
#define META_CAPTURE 0x80080000u /* Capturing parenthesis */
|
|
|
|
#define META_CIRCUMFLEX 0x80090000u /* ^ metacharacter */
|
|
|
|
#define META_CLASS 0x800a0000u /* start non-empty class */
|
|
|
|
#define META_CLASS_EMPTY 0x800b0000u /* empty class */
|
|
|
|
#define META_CLASS_EMPTY_NOT 0x800c0000u /* negative empty class */
|
|
|
|
#define META_CLASS_END 0x800d0000u /* end of non-empty class */
|
|
|
|
#define META_CLASS_NOT 0x800e0000u /* start non-empty negative class */
|
|
|
|
#define META_COND_ASSERT 0x800f0000u /* (?(?assertion)... */
|
|
|
|
#define META_COND_DEFINE 0x80100000u /* (?(DEFINE)... */
|
|
|
|
#define META_COND_NAME 0x80110000u /* (?(<name>)... */
|
|
|
|
#define META_COND_NUMBER 0x80120000u /* (?(digits)... */
|
|
|
|
#define META_COND_RNAME 0x80130000u /* (?(R&name)... */
|
|
|
|
#define META_COND_RNUMBER 0x80140000u /* (?(Rdigits)... */
|
|
|
|
#define META_COND_VERSION 0x80150000u /* (?(VERSION<op>x.y)... */
|
|
|
|
#define META_DOLLAR 0x80160000u /* $ metacharacter */
|
|
|
|
#define META_DOT 0x80170000u /* . metacharacter */
|
|
|
|
#define META_ESCAPE 0x80180000u /* \d and friends */
|
|
|
|
#define META_KET 0x80190000u /* closing parenthesis */
|
|
|
|
#define META_NOCAPTURE 0x801a0000u /* no capture parens */
|
|
|
|
#define META_OPTIONS 0x801b0000u /* (?i) and friends */
|
|
|
|
#define META_POSIX 0x801c0000u /* POSIX class item */
|
|
|
|
#define META_POSIX_NEG 0x801d0000u /* negative POSIX class item */
|
|
|
|
#define META_RANGE_ESCAPED 0x801e0000u /* range with at least one escape */
|
|
|
|
#define META_RANGE_LITERAL 0x801f0000u /* range defined literally */
|
|
|
|
#define META_RECURSE 0x80200000u /* Recursion */
|
|
|
|
#define META_RECURSE_BYNAME 0x80210000u /* (?&name) */
|
|
|
|
|
|
|
|
/* These must be kept together to make it easy to check that an assertion
|
|
|
|
is present where expected in a conditional group. */
|
|
|
|
|
|
|
|
#define META_LOOKAHEAD 0x80220000u /* (?= */
|
|
|
|
#define META_LOOKAHEADNOT 0x80230000u /* (?! */
|
|
|
|
#define META_LOOKBEHIND 0x80240000u /* (?<= */
|
|
|
|
#define META_LOOKBEHINDNOT 0x80250000u /* (?<! */
|
|
|
|
|
|
|
|
/* These must be kept in this order, with consecutive values, and the _ARG
|
2018-07-21 16:34:51 +02:00
|
|
|
versions of COMMIT, PRUNE, SKIP, and THEN immediately after their non-argument
|
2016-10-02 18:01:01 +02:00
|
|
|
versions. */
|
|
|
|
|
|
|
|
#define META_MARK 0x80260000u /* (*MARK) */
|
|
|
|
#define META_ACCEPT 0x80270000u /* (*ACCEPT) */
|
2018-07-21 16:34:51 +02:00
|
|
|
#define META_FAIL 0x80280000u /* (*FAIL) */
|
|
|
|
#define META_COMMIT 0x80290000u /* These */
|
|
|
|
#define META_COMMIT_ARG 0x802a0000u /* pairs */
|
|
|
|
#define META_PRUNE 0x802b0000u /* must */
|
|
|
|
#define META_PRUNE_ARG 0x802c0000u /* be */
|
|
|
|
#define META_SKIP 0x802d0000u /* kept */
|
|
|
|
#define META_SKIP_ARG 0x802e0000u /* in */
|
|
|
|
#define META_THEN 0x802f0000u /* this */
|
2018-07-28 18:23:24 +02:00
|
|
|
#define META_THEN_ARG 0x80300000u /* order */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* These must be kept in groups of adjacent 3 values, and all together. */
|
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
#define META_ASTERISK 0x80310000u /* * */
|
|
|
|
#define META_ASTERISK_PLUS 0x80320000u /* *+ */
|
|
|
|
#define META_ASTERISK_QUERY 0x80330000u /* *? */
|
|
|
|
#define META_PLUS 0x80340000u /* + */
|
|
|
|
#define META_PLUS_PLUS 0x80350000u /* ++ */
|
|
|
|
#define META_PLUS_QUERY 0x80360000u /* +? */
|
|
|
|
#define META_QUERY 0x80370000u /* ? */
|
|
|
|
#define META_QUERY_PLUS 0x80380000u /* ?+ */
|
|
|
|
#define META_QUERY_QUERY 0x80390000u /* ?? */
|
|
|
|
#define META_MINMAX 0x803a0000u /* {n,m} repeat */
|
|
|
|
#define META_MINMAX_PLUS 0x803b0000u /* {n,m}+ repeat */
|
|
|
|
#define META_MINMAX_QUERY 0x803c0000u /* {n,m}? repeat */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
#define META_FIRST_QUANTIFIER META_ASTERISK
|
|
|
|
#define META_LAST_QUANTIFIER META_MINMAX_QUERY
|
|
|
|
|
2016-11-23 18:17:57 +01:00
|
|
|
/* Table of extra lengths for each of the meta codes. Must be kept in step with
|
|
|
|
the definitions above. For some items these values are a basic length to which
|
|
|
|
a variable amount has to be added. */
|
|
|
|
|
|
|
|
static unsigned char meta_extra_lengths[] = {
|
|
|
|
0, /* META_END */
|
|
|
|
0, /* META_ALT */
|
|
|
|
0, /* META_ATOMIC */
|
|
|
|
0, /* META_BACKREF - more if group is >= 10 */
|
|
|
|
1+SIZEOFFSET, /* META_BACKREF_BYNAME */
|
|
|
|
1, /* META_BIGVALUE */
|
|
|
|
3, /* META_CALLOUT_NUMBER */
|
|
|
|
3+SIZEOFFSET, /* META_CALLOUT_STRING */
|
|
|
|
0, /* META_CAPTURE */
|
|
|
|
0, /* META_CIRCUMFLEX */
|
|
|
|
0, /* META_CLASS */
|
|
|
|
0, /* META_CLASS_EMPTY */
|
|
|
|
0, /* META_CLASS_EMPTY_NOT */
|
|
|
|
0, /* META_CLASS_END */
|
|
|
|
0, /* META_CLASS_NOT */
|
|
|
|
0, /* META_COND_ASSERT */
|
|
|
|
SIZEOFFSET, /* META_COND_DEFINE */
|
|
|
|
1+SIZEOFFSET, /* META_COND_NAME */
|
|
|
|
1+SIZEOFFSET, /* META_COND_NUMBER */
|
|
|
|
1+SIZEOFFSET, /* META_COND_RNAME */
|
|
|
|
1+SIZEOFFSET, /* META_COND_RNUMBER */
|
|
|
|
3, /* META_COND_VERSION */
|
|
|
|
0, /* META_DOLLAR */
|
|
|
|
0, /* META_DOT */
|
|
|
|
0, /* META_ESCAPE - more for ESC_P, ESC_p, ESC_g, ESC_k */
|
|
|
|
0, /* META_KET */
|
|
|
|
0, /* META_NOCAPTURE */
|
|
|
|
1, /* META_OPTIONS */
|
|
|
|
1, /* META_POSIX */
|
|
|
|
1, /* META_POSIX_NEG */
|
|
|
|
0, /* META_RANGE_ESCAPED */
|
|
|
|
0, /* META_RANGE_LITERAL */
|
|
|
|
SIZEOFFSET, /* META_RECURSE */
|
|
|
|
1+SIZEOFFSET, /* META_RECURSE_BYNAME */
|
|
|
|
0, /* META_LOOKAHEAD */
|
|
|
|
0, /* META_LOOKAHEADNOT */
|
|
|
|
SIZEOFFSET, /* META_LOOKBEHIND */
|
|
|
|
SIZEOFFSET, /* META_LOOKBEHINDNOT */
|
|
|
|
1, /* META_MARK - plus the string length */
|
|
|
|
0, /* META_ACCEPT */
|
|
|
|
0, /* META_FAIL */
|
2018-07-21 16:34:51 +02:00
|
|
|
0, /* META_COMMIT */
|
2018-07-28 18:23:24 +02:00
|
|
|
1, /* META_COMMIT_ARG - plus the string length */
|
2016-11-23 18:17:57 +01:00
|
|
|
0, /* META_PRUNE */
|
|
|
|
1, /* META_PRUNE_ARG - plus the string length */
|
|
|
|
0, /* META_SKIP */
|
|
|
|
1, /* META_SKIP_ARG - plus the string length */
|
|
|
|
0, /* META_THEN */
|
|
|
|
1, /* META_THEN_ARG - plus the string length */
|
|
|
|
0, /* META_ASTERISK */
|
|
|
|
0, /* META_ASTERISK_PLUS */
|
|
|
|
0, /* META_ASTERISK_QUERY */
|
|
|
|
0, /* META_PLUS */
|
|
|
|
0, /* META_PLUS_PLUS */
|
|
|
|
0, /* META_PLUS_QUERY */
|
|
|
|
0, /* META_QUERY */
|
|
|
|
0, /* META_QUERY_PLUS */
|
|
|
|
0, /* META_QUERY_QUERY */
|
|
|
|
2, /* META_MINMAX */
|
|
|
|
2, /* META_MINMAX_PLUS */
|
|
|
|
2 /* META_MINMAX_QUERY */
|
|
|
|
};
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Types for skipping parts of a parsed pattern. */
|
|
|
|
|
|
|
|
enum { PSKIP_ALT, PSKIP_CLASS, PSKIP_KET };
|
|
|
|
|
2016-06-29 18:52:05 +02:00
|
|
|
/* Macro for setting individual bits in class bitmaps. It took some
|
|
|
|
experimenting to figure out how to stop gcc 5.3.0 from warning with
|
2016-02-16 11:23:06 +01:00
|
|
|
-Wconversion. This version gets a warning:
|
|
|
|
|
2016-06-29 18:52:05 +02:00
|
|
|
#define SETBIT(a,b) a[(b)/8] |= (uint8_t)(1 << ((b)&7))
|
|
|
|
|
|
|
|
Let's hope the apparently less efficient version isn't actually so bad if the
|
2016-02-16 11:23:06 +01:00
|
|
|
compiler is clever with identical subexpressions. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-02-16 11:23:06 +01:00
|
|
|
#define SETBIT(a,b) a[(b)/8] = (uint8_t)(a[(b)/8] | (1 << ((b)&7)))
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Private flags added to firstcu and reqcu. */
|
|
|
|
|
|
|
|
#define REQ_CASELESS (1 << 0) /* Indicates caselessness */
|
|
|
|
#define REQ_VARY (1 << 1) /* reqcu followed non-literal item */
|
|
|
|
/* Negative values for the firstcu and reqcu flags */
|
2014-06-21 14:39:48 +02:00
|
|
|
#define REQ_UNSET (-2) /* Not yet found anything */
|
|
|
|
#define REQ_NONE (-1) /* Found not fixed char */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-11-08 15:20:09 +01:00
|
|
|
/* These flags are used in the groupinfo vector. */
|
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
#define GI_SET_FIXED_LENGTH 0x80000000u
|
|
|
|
#define GI_NOT_FIXED_LENGTH 0x40000000u
|
2015-11-08 15:20:09 +01:00
|
|
|
#define GI_FIXED_LENGTH_MASK 0x0000ffffu
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* This simple test for a decimal digit works for both ASCII/Unicode and EBCDIC
|
|
|
|
and is fast (a good compiler can turn it into a subtraction and unsigned
|
|
|
|
comparison). */
|
|
|
|
|
|
|
|
#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9)
|
|
|
|
|
|
|
|
/* Table to identify hex digits. The tables in chartables are dependent on the
|
|
|
|
locale, and may mark arbitrary characters as digits. We want to recognize only
|
|
|
|
0-9, a-z, and A-Z as hex digits, which is why we have a private table here. It
|
|
|
|
costs 256 bytes, but it is a lot faster than doing character value tests (at
|
2016-11-23 18:17:57 +01:00
|
|
|
least in some simple cases I timed), and in some applications one wants PCRE2
|
|
|
|
to compile efficiently as well as match efficiently. The value in the table is
|
2014-06-14 20:29:51 +02:00
|
|
|
the binary hex digit value, or 0xff for non-hex digits. */
|
|
|
|
|
|
|
|
/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in
|
|
|
|
UTF-8 mode. */
|
|
|
|
|
|
|
|
#ifndef EBCDIC
|
|
|
|
static const uint8_t xdigitab[] =
|
|
|
|
{
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 0- 7 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 8- 15 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 16- 23 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 24- 31 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* - ' */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* ( - / */
|
|
|
|
0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07, /* 0 - 7 */
|
|
|
|
0x08,0x09,0xff,0xff,0xff,0xff,0xff,0xff, /* 8 - ? */
|
|
|
|
0xff,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0xff, /* @ - G */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* H - O */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* P - W */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* X - _ */
|
|
|
|
0xff,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0xff, /* ` - g */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* h - o */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* p - w */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* x -127 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 128-135 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 136-143 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 144-151 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 152-159 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 160-167 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 168-175 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 176-183 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 184-191 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 192-199 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 2ff-207 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 208-215 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 216-223 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 224-231 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 232-239 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 240-247 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff};/* 248-255 */
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */
|
|
|
|
|
|
|
|
static const uint8_t xdigitab[] =
|
|
|
|
{
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 0- 7 0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 8- 15 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 16- 23 10 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 24- 31 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 32- 39 20 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 40- 47 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 48- 55 30 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 56- 63 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* - 71 40 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 72- | */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* & - 87 50 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 88- 95 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* - -103 60 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 104- ? */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 112-119 70 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 120- " */
|
|
|
|
0xff,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0xff, /* 128- g 80 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* h -143 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 144- p 90 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* q -159 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 160- x A0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* y -175 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* ^ -183 B0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* 184-191 */
|
|
|
|
0xff,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,0xff, /* { - G C0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* H -207 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* } - P D0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* Q -223 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* \ - X E0 */
|
|
|
|
0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff, /* Y -239 */
|
|
|
|
0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07, /* 0 - 7 F0 */
|
|
|
|
0x08,0x09,0xff,0xff,0xff,0xff,0xff,0xff};/* 8 -255 */
|
|
|
|
#endif /* EBCDIC */
|
|
|
|
|
|
|
|
|
|
|
|
/* Table for handling alphanumeric escaped characters. Positive returns are
|
|
|
|
simple data values; negative values are for special things like \d and so on.
|
|
|
|
Zero means further processing is needed (for things like \x), or the escape is
|
|
|
|
invalid. */
|
|
|
|
|
|
|
|
/* This is the "normal" table for ASCII systems or for EBCDIC systems running
|
|
|
|
in UTF-8 mode. It runs from '0' to 'z'. */
|
|
|
|
|
|
|
|
#ifndef EBCDIC
|
2015-06-13 18:10:14 +02:00
|
|
|
#define ESCAPES_FIRST CHAR_0
|
|
|
|
#define ESCAPES_LAST CHAR_z
|
2015-07-24 15:30:50 +02:00
|
|
|
#define UPPER_CASE(c) (c-32)
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
static const short int escapes[] = {
|
|
|
|
0, 0,
|
|
|
|
0, 0,
|
|
|
|
0, 0,
|
|
|
|
0, 0,
|
|
|
|
0, 0,
|
|
|
|
CHAR_COLON, CHAR_SEMICOLON,
|
|
|
|
CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN,
|
|
|
|
CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK,
|
|
|
|
CHAR_COMMERCIAL_AT, -ESC_A,
|
|
|
|
-ESC_B, -ESC_C,
|
|
|
|
-ESC_D, -ESC_E,
|
|
|
|
0, -ESC_G,
|
|
|
|
-ESC_H, 0,
|
|
|
|
0, -ESC_K,
|
|
|
|
0, 0,
|
|
|
|
-ESC_N, 0,
|
|
|
|
-ESC_P, -ESC_Q,
|
|
|
|
-ESC_R, -ESC_S,
|
|
|
|
0, 0,
|
|
|
|
-ESC_V, -ESC_W,
|
|
|
|
-ESC_X, 0,
|
|
|
|
-ESC_Z, CHAR_LEFT_SQUARE_BRACKET,
|
|
|
|
CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET,
|
|
|
|
CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE,
|
2018-08-19 18:54:41 +02:00
|
|
|
CHAR_GRAVE_ACCENT, CHAR_BEL,
|
2014-06-14 20:29:51 +02:00
|
|
|
-ESC_b, 0,
|
2018-08-19 18:54:41 +02:00
|
|
|
-ESC_d, CHAR_ESC,
|
|
|
|
CHAR_FF, 0,
|
2014-06-14 20:29:51 +02:00
|
|
|
-ESC_h, 0,
|
|
|
|
0, -ESC_k,
|
|
|
|
0, 0,
|
2018-08-19 18:54:41 +02:00
|
|
|
CHAR_LF, 0,
|
2014-06-14 20:29:51 +02:00
|
|
|
-ESC_p, 0,
|
2018-08-19 18:54:41 +02:00
|
|
|
CHAR_CR, -ESC_s,
|
|
|
|
CHAR_HT, 0,
|
2014-06-14 20:29:51 +02:00
|
|
|
-ESC_v, -ESC_w,
|
|
|
|
0, 0,
|
|
|
|
-ESC_z
|
|
|
|
};
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
/* This is the "abnormal" table for EBCDIC systems without UTF-8 support.
|
2014-11-03 18:13:00 +01:00
|
|
|
It runs from 'a' to '9'. For some minimal testing of EBCDIC features, the code
|
|
|
|
is sometimes compiled on an ASCII system. In this case, we must not use CHAR_a
|
2014-10-26 19:00:19 +01:00
|
|
|
because it is defined as 'a', which of course picks up the ASCII value. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-06-13 18:10:14 +02:00
|
|
|
#if 'a' == 0x81 /* Check for a real EBCDIC environment */
|
|
|
|
#define ESCAPES_FIRST CHAR_a
|
|
|
|
#define ESCAPES_LAST CHAR_9
|
2015-07-24 15:30:50 +02:00
|
|
|
#define UPPER_CASE(c) (c+64)
|
2015-06-13 18:10:14 +02:00
|
|
|
#else /* Testing in an ASCII environment */
|
2014-10-26 19:00:19 +01:00
|
|
|
#define ESCAPES_FIRST ((unsigned char)'\x81') /* EBCDIC 'a' */
|
|
|
|
#define ESCAPES_LAST ((unsigned char)'\xf9') /* EBCDIC '9' */
|
2015-07-24 15:30:50 +02:00
|
|
|
#define UPPER_CASE(c) (c-32)
|
2014-10-26 19:00:19 +01:00
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
static const short int escapes[] = {
|
2018-08-19 18:54:41 +02:00
|
|
|
/* 80 */ CHAR_BEL, -ESC_b, 0, -ESC_d, CHAR_ESC, CHAR_FF, 0,
|
|
|
|
/* 88 */ -ESC_h, 0, 0, '{', 0, 0, 0, 0,
|
|
|
|
/* 90 */ 0, 0, -ESC_k, 0, 0, CHAR_LF, 0, -ESC_p,
|
|
|
|
/* 98 */ 0, CHAR_CR, 0, '}', 0, 0, 0, 0,
|
|
|
|
/* A0 */ 0, '~', -ESC_s, CHAR_HT, 0, -ESC_v, -ESC_w, 0,
|
|
|
|
/* A8 */ 0, -ESC_z, 0, 0, 0, '[', 0, 0,
|
|
|
|
/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0,
|
|
|
|
/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-',
|
|
|
|
/* C0 */ '{', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G,
|
|
|
|
/* C8 */ -ESC_H, 0, 0, 0, 0, 0, 0, 0,
|
|
|
|
/* D0 */ '}', 0, -ESC_K, 0, 0, -ESC_N, 0, -ESC_P,
|
|
|
|
/* D8 */ -ESC_Q, -ESC_R, 0, 0, 0, 0, 0, 0,
|
|
|
|
/* E0 */ '\\', 0, -ESC_S, 0, 0, -ESC_V, -ESC_W, -ESC_X,
|
|
|
|
/* E8 */ 0, -ESC_Z, 0, 0, 0, 0, 0, 0,
|
|
|
|
/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0,
|
|
|
|
/* F8 */ 0, 0
|
2014-06-14 20:29:51 +02:00
|
|
|
};
|
|
|
|
|
2015-06-13 18:10:14 +02:00
|
|
|
/* We also need a table of characters that may follow \c in an EBCDIC
|
|
|
|
environment for characters 0-31. */
|
|
|
|
|
|
|
|
static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
|
|
|
|
|
2014-10-26 19:00:19 +01:00
|
|
|
#endif /* EBCDIC */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
|
|
|
|
searched linearly. Put all the names into a single string, in order to reduce
|
|
|
|
the number of relocations when a shared library is dynamically linked. The
|
|
|
|
string is built from string macros so that it works in UTF-8 mode on EBCDIC
|
|
|
|
platforms. */
|
|
|
|
|
|
|
|
typedef struct verbitem {
|
2016-10-02 18:01:01 +02:00
|
|
|
unsigned int len; /* Length of verb name */
|
|
|
|
uint32_t meta; /* Base META_ code */
|
|
|
|
int has_arg; /* Argument requirement */
|
2014-06-14 20:29:51 +02:00
|
|
|
} verbitem;
|
|
|
|
|
|
|
|
static const char verbnames[] =
|
|
|
|
"\0" /* Empty name is a shorthand for MARK */
|
|
|
|
STRING_MARK0
|
|
|
|
STRING_ACCEPT0
|
|
|
|
STRING_F0
|
|
|
|
STRING_FAIL0
|
2018-07-21 16:34:51 +02:00
|
|
|
STRING_COMMIT0
|
2014-06-14 20:29:51 +02:00
|
|
|
STRING_PRUNE0
|
|
|
|
STRING_SKIP0
|
|
|
|
STRING_THEN;
|
|
|
|
|
|
|
|
static const verbitem verbs[] = {
|
2016-10-02 18:01:01 +02:00
|
|
|
{ 0, META_MARK, +1 }, /* > 0 => must have an argument */
|
|
|
|
{ 4, META_MARK, +1 },
|
2018-07-21 16:34:51 +02:00
|
|
|
{ 6, META_ACCEPT, -1 }, /* < 0 => Optional argument, convert to pre-MARK */
|
2016-10-02 18:01:01 +02:00
|
|
|
{ 1, META_FAIL, -1 },
|
|
|
|
{ 4, META_FAIL, -1 },
|
2018-07-21 16:34:51 +02:00
|
|
|
{ 6, META_COMMIT, 0 },
|
|
|
|
{ 5, META_PRUNE, 0 }, /* Optional argument; bump META code if found */
|
2016-10-02 18:01:01 +02:00
|
|
|
{ 4, META_SKIP, 0 },
|
|
|
|
{ 4, META_THEN, 0 }
|
2014-06-14 20:29:51 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
static const int verbcount = sizeof(verbs)/sizeof(verbitem);
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Verb opcodes, indexed by their META code offset from META_MARK. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static const uint32_t verbops[] = {
|
2018-07-28 18:23:24 +02:00
|
|
|
OP_MARK, OP_ACCEPT, OP_FAIL, OP_COMMIT, OP_COMMIT_ARG, OP_PRUNE,
|
2018-07-21 16:34:51 +02:00
|
|
|
OP_PRUNE_ARG, OP_SKIP, OP_SKIP_ARG, OP_THEN, OP_THEN_ARG };
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* Table of "alpha assertions" like (*pla:...), similar to the (*VERB) table. */
|
|
|
|
|
|
|
|
typedef struct alasitem {
|
|
|
|
unsigned int len; /* Length of name */
|
|
|
|
uint32_t meta; /* Base META_ code */
|
|
|
|
} alasitem;
|
|
|
|
|
|
|
|
static const char alasnames[] =
|
|
|
|
STRING_pla0
|
|
|
|
STRING_plb0
|
|
|
|
STRING_nla0
|
|
|
|
STRING_nlb0
|
|
|
|
STRING_positive_lookahead0
|
|
|
|
STRING_positive_lookbehind0
|
|
|
|
STRING_negative_lookahead0
|
|
|
|
STRING_negative_lookbehind0
|
|
|
|
STRING_atomic0
|
|
|
|
STRING_sr0
|
|
|
|
STRING_asr0
|
|
|
|
STRING_script_run0
|
|
|
|
STRING_atomic_script_run;
|
|
|
|
|
|
|
|
static const alasitem alasmeta[] = {
|
|
|
|
{ 3, META_LOOKAHEAD },
|
|
|
|
{ 3, META_LOOKBEHIND },
|
|
|
|
{ 3, META_LOOKAHEADNOT },
|
|
|
|
{ 3, META_LOOKBEHINDNOT },
|
|
|
|
{ 18, META_LOOKAHEAD },
|
|
|
|
{ 19, META_LOOKBEHIND },
|
|
|
|
{ 18, META_LOOKAHEADNOT },
|
|
|
|
{ 19, META_LOOKBEHINDNOT },
|
|
|
|
{ 6, META_ATOMIC },
|
|
|
|
{ 2, 0 }, /* sr = script run */
|
|
|
|
{ 3, 0 }, /* asr = atomic script run */
|
|
|
|
{ 10, 0 }, /* script run */
|
|
|
|
{ 17, 0 } /* atomic script run */
|
|
|
|
};
|
|
|
|
|
|
|
|
static const int alascount = sizeof(alasmeta)/sizeof(alasitem);
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Offsets from OP_STAR for case-independent and negative repeat opcodes. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static uint32_t chartypeoffset[] = {
|
|
|
|
OP_STAR - OP_STAR, OP_STARI - OP_STAR,
|
|
|
|
OP_NOTSTAR - OP_STAR, OP_NOTSTARI - OP_STAR };
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Tables of names of POSIX character classes and their lengths. The names are
|
|
|
|
now all in a single string, to reduce the number of relocations when a shared
|
|
|
|
library is dynamically loaded. The list of lengths is terminated by a zero
|
|
|
|
length entry. The first three must be alpha, lower, upper, as this is assumed
|
|
|
|
for handling case independence. The indices for graph, print, and punct are
|
|
|
|
needed, so identify them. */
|
|
|
|
|
|
|
|
static const char posix_names[] =
|
|
|
|
STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0
|
|
|
|
STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0
|
|
|
|
STRING_graph0 STRING_print0 STRING_punct0 STRING_space0
|
|
|
|
STRING_word0 STRING_xdigit;
|
|
|
|
|
|
|
|
static const uint8_t posix_name_lengths[] = {
|
|
|
|
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
|
|
|
|
|
|
|
|
#define PC_GRAPH 8
|
|
|
|
#define PC_PRINT 9
|
|
|
|
#define PC_PUNCT 10
|
|
|
|
|
|
|
|
/* Table of class bit maps for each POSIX class. Each class is formed from a
|
|
|
|
base map, with an optional addition or removal of another map. Then, for some
|
|
|
|
classes, there is some additional tweaking: for [:blank:] the vertical space
|
|
|
|
characters are removed, and for [:alpha:] and [:alnum:] the underscore
|
|
|
|
character is removed. The triples in the table consist of the base map offset,
|
|
|
|
second map offset or -1 if no second map, and a non-negative value for map
|
|
|
|
addition or a negative value for map subtraction (if there are two maps). The
|
|
|
|
absolute value of the third field has these meanings: 0 => no tweaking, 1 =>
|
|
|
|
remove vertical space characters, 2 => remove underscore. */
|
|
|
|
|
|
|
|
static const int posix_class_maps[] = {
|
|
|
|
cbit_word, cbit_digit, -2, /* alpha */
|
|
|
|
cbit_lower, -1, 0, /* lower */
|
|
|
|
cbit_upper, -1, 0, /* upper */
|
|
|
|
cbit_word, -1, 2, /* alnum - word without underscore */
|
|
|
|
cbit_print, cbit_cntrl, 0, /* ascii */
|
|
|
|
cbit_space, -1, 1, /* blank - a GNU extension */
|
|
|
|
cbit_cntrl, -1, 0, /* cntrl */
|
|
|
|
cbit_digit, -1, 0, /* digit */
|
|
|
|
cbit_graph, -1, 0, /* graph */
|
|
|
|
cbit_print, -1, 0, /* print */
|
|
|
|
cbit_punct, -1, 0, /* punct */
|
|
|
|
cbit_space, -1, 0, /* space */
|
|
|
|
cbit_word, -1, 0, /* word - a Perl extension */
|
|
|
|
cbit_xdigit,-1, 0 /* xdigit */
|
|
|
|
};
|
|
|
|
|
2014-09-19 09:43:39 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The POSIX class Unicode property substitutes that are used in UCP mode must
|
|
|
|
be in the order of the POSIX class names, defined above. */
|
|
|
|
|
|
|
|
static int posix_substitutes[] = {
|
|
|
|
PT_GC, ucp_L, /* alpha */
|
|
|
|
PT_PC, ucp_Ll, /* lower */
|
|
|
|
PT_PC, ucp_Lu, /* upper */
|
|
|
|
PT_ALNUM, 0, /* alnum */
|
|
|
|
-1, 0, /* ascii, treat as non-UCP */
|
|
|
|
-1, 1, /* blank, treat as \h */
|
|
|
|
PT_PC, ucp_Cc, /* cntrl */
|
|
|
|
PT_PC, ucp_Nd, /* digit */
|
|
|
|
PT_PXGRAPH, 0, /* graph */
|
|
|
|
PT_PXPRINT, 0, /* print */
|
|
|
|
PT_PXPUNCT, 0, /* punct */
|
|
|
|
PT_PXSPACE, 0, /* space */ /* Xps is POSIX space, but from 8.34 */
|
|
|
|
PT_WORD, 0, /* word */ /* Perl and POSIX space are the same */
|
|
|
|
-1, 0 /* xdigit, treat as non-UCP */
|
2014-06-14 20:29:51 +02:00
|
|
|
};
|
2016-10-02 18:01:01 +02:00
|
|
|
#define POSIX_SUBSIZE (sizeof(posix_substitutes) / (2*sizeof(uint32_t)))
|
2014-09-19 09:43:39 +02:00
|
|
|
#endif /* SUPPORT_UNICODE */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
/* Masks for checking option settings. When PCRE2_LITERAL is set, only a subset
|
|
|
|
are allowed. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
#define PUBLIC_LITERAL_COMPILE_OPTIONS \
|
|
|
|
(PCRE2_ANCHORED|PCRE2_AUTO_CALLOUT|PCRE2_CASELESS|PCRE2_ENDANCHORED| \
|
|
|
|
PCRE2_FIRSTLINE|PCRE2_LITERAL|PCRE2_NO_START_OPTIMIZE| \
|
|
|
|
PCRE2_NO_UTF_CHECK|PCRE2_USE_OFFSET_LIMIT|PCRE2_UTF)
|
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
#define PUBLIC_COMPILE_OPTIONS \
|
|
|
|
(PUBLIC_LITERAL_COMPILE_OPTIONS| \
|
|
|
|
PCRE2_ALLOW_EMPTY_CLASS|PCRE2_ALT_BSUX|PCRE2_ALT_CIRCUMFLEX| \
|
|
|
|
PCRE2_ALT_VERBNAMES|PCRE2_DOLLAR_ENDONLY|PCRE2_DOTALL|PCRE2_DUPNAMES| \
|
|
|
|
PCRE2_EXTENDED|PCRE2_EXTENDED_MORE|PCRE2_MATCH_UNSET_BACKREF| \
|
|
|
|
PCRE2_MULTILINE|PCRE2_NEVER_BACKSLASH_C|PCRE2_NEVER_UCP| \
|
|
|
|
PCRE2_NEVER_UTF|PCRE2_NO_AUTO_CAPTURE|PCRE2_NO_AUTO_POSSESS| \
|
|
|
|
PCRE2_NO_DOTSTAR_ANCHOR|PCRE2_UCP|PCRE2_UNGREEDY)
|
|
|
|
|
|
|
|
#define PUBLIC_LITERAL_COMPILE_EXTRA_OPTIONS \
|
|
|
|
(PCRE2_EXTRA_MATCH_LINE|PCRE2_EXTRA_MATCH_WORD)
|
|
|
|
|
|
|
|
#define PUBLIC_COMPILE_EXTRA_OPTIONS \
|
|
|
|
(PUBLIC_LITERAL_COMPILE_EXTRA_OPTIONS| \
|
2018-09-21 18:59:48 +02:00
|
|
|
PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES|PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL| \
|
|
|
|
PCRE2_EXTRA_ESCAPED_CR_IS_LF)
|
2017-06-16 19:51:13 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Compile time error code numbers. They are given names so that they can more
|
2014-08-08 17:36:18 +02:00
|
|
|
easily be tracked. When a new number is added, the tables called eint1 and
|
2015-11-03 11:39:27 +01:00
|
|
|
eint2 in pcre2posix.c may need to be updated, and a new error text must be
|
|
|
|
added to compile_error_texts in pcre2_error.c. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
enum { ERR0 = COMPILE_ERROR_BASE,
|
|
|
|
ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR10,
|
|
|
|
ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, ERR20,
|
|
|
|
ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30,
|
|
|
|
ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40,
|
|
|
|
ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, ERR50,
|
|
|
|
ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, ERR60,
|
|
|
|
ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69, ERR70,
|
2015-03-11 18:44:16 +01:00
|
|
|
ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79, ERR80,
|
2017-05-17 19:55:11 +02:00
|
|
|
ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERR87, ERR88, ERR89, ERR90,
|
2018-09-24 18:23:53 +02:00
|
|
|
ERR91, ERR92, ERR93, ERR94, ERR95 };
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* This is a table of start-of-pattern options such as (*UTF) and settings such
|
|
|
|
as (*LIMIT_MATCH=nnnn) and (*CRLF). For completeness and backward
|
|
|
|
compatibility, (*UTFn) is supported in the relevant libraries, but (*UTF) is
|
|
|
|
generic and always supported. */
|
|
|
|
|
|
|
|
enum { PSO_OPT, /* Value is an option bit */
|
2014-08-26 13:46:21 +02:00
|
|
|
PSO_FLG, /* Value is a flag bit */
|
2014-06-14 20:29:51 +02:00
|
|
|
PSO_NL, /* Value is a newline type */
|
|
|
|
PSO_BSR, /* Value is a \R type */
|
2017-05-17 19:55:11 +02:00
|
|
|
PSO_LIMH, /* Read integer value for heap limit */
|
2014-06-14 20:29:51 +02:00
|
|
|
PSO_LIMM, /* Read integer value for match limit */
|
2017-03-12 14:47:01 +01:00
|
|
|
PSO_LIMD }; /* Read integer value for depth limit */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
typedef struct pso {
|
|
|
|
const uint8_t *name;
|
|
|
|
uint16_t length;
|
|
|
|
uint16_t type;
|
|
|
|
uint32_t value;
|
|
|
|
} pso;
|
|
|
|
|
|
|
|
/* NB: STRING_UTFn_RIGHTPAR contains the length as well */
|
|
|
|
|
|
|
|
static pso pso_list[] = {
|
2015-01-02 18:09:16 +01:00
|
|
|
{ (uint8_t *)STRING_UTFn_RIGHTPAR, PSO_OPT, PCRE2_UTF },
|
|
|
|
{ (uint8_t *)STRING_UTF_RIGHTPAR, 4, PSO_OPT, PCRE2_UTF },
|
|
|
|
{ (uint8_t *)STRING_UCP_RIGHTPAR, 4, PSO_OPT, PCRE2_UCP },
|
|
|
|
{ (uint8_t *)STRING_NOTEMPTY_RIGHTPAR, 9, PSO_FLG, PCRE2_NOTEMPTY_SET },
|
|
|
|
{ (uint8_t *)STRING_NOTEMPTY_ATSTART_RIGHTPAR, 17, PSO_FLG, PCRE2_NE_ATST_SET },
|
|
|
|
{ (uint8_t *)STRING_NO_AUTO_POSSESS_RIGHTPAR, 16, PSO_OPT, PCRE2_NO_AUTO_POSSESS },
|
|
|
|
{ (uint8_t *)STRING_NO_DOTSTAR_ANCHOR_RIGHTPAR, 18, PSO_OPT, PCRE2_NO_DOTSTAR_ANCHOR },
|
2015-01-26 15:57:27 +01:00
|
|
|
{ (uint8_t *)STRING_NO_JIT_RIGHTPAR, 7, PSO_FLG, PCRE2_NOJIT },
|
2015-01-02 18:09:16 +01:00
|
|
|
{ (uint8_t *)STRING_NO_START_OPT_RIGHTPAR, 13, PSO_OPT, PCRE2_NO_START_OPTIMIZE },
|
2017-04-11 13:47:25 +02:00
|
|
|
{ (uint8_t *)STRING_LIMIT_HEAP_EQ, 11, PSO_LIMH, 0 },
|
2015-01-02 18:09:16 +01:00
|
|
|
{ (uint8_t *)STRING_LIMIT_MATCH_EQ, 12, PSO_LIMM, 0 },
|
2017-03-12 14:47:01 +01:00
|
|
|
{ (uint8_t *)STRING_LIMIT_DEPTH_EQ, 12, PSO_LIMD, 0 },
|
|
|
|
{ (uint8_t *)STRING_LIMIT_RECURSION_EQ, 16, PSO_LIMD, 0 },
|
2015-01-02 18:09:16 +01:00
|
|
|
{ (uint8_t *)STRING_CR_RIGHTPAR, 3, PSO_NL, PCRE2_NEWLINE_CR },
|
|
|
|
{ (uint8_t *)STRING_LF_RIGHTPAR, 3, PSO_NL, PCRE2_NEWLINE_LF },
|
|
|
|
{ (uint8_t *)STRING_CRLF_RIGHTPAR, 5, PSO_NL, PCRE2_NEWLINE_CRLF },
|
|
|
|
{ (uint8_t *)STRING_ANY_RIGHTPAR, 4, PSO_NL, PCRE2_NEWLINE_ANY },
|
2017-05-26 19:14:36 +02:00
|
|
|
{ (uint8_t *)STRING_NUL_RIGHTPAR, 4, PSO_NL, PCRE2_NEWLINE_NUL },
|
2015-01-02 18:09:16 +01:00
|
|
|
{ (uint8_t *)STRING_ANYCRLF_RIGHTPAR, 8, PSO_NL, PCRE2_NEWLINE_ANYCRLF },
|
|
|
|
{ (uint8_t *)STRING_BSR_ANYCRLF_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_ANYCRLF },
|
|
|
|
{ (uint8_t *)STRING_BSR_UNICODE_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_UNICODE }
|
2014-06-14 20:29:51 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/* This table is used when converting repeating opcodes into possessified
|
|
|
|
versions as a result of an explicit possessive quantifier such as ++. A zero
|
|
|
|
value means there is no possessified version - in those cases the item in
|
|
|
|
question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT
|
|
|
|
because all relevant opcodes are less than that. */
|
|
|
|
|
|
|
|
static const uint8_t opcode_possessify[] = {
|
|
|
|
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */
|
|
|
|
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */
|
|
|
|
|
|
|
|
0, /* NOTI */
|
|
|
|
OP_POSSTAR, 0, /* STAR, MINSTAR */
|
|
|
|
OP_POSPLUS, 0, /* PLUS, MINPLUS */
|
|
|
|
OP_POSQUERY, 0, /* QUERY, MINQUERY */
|
|
|
|
OP_POSUPTO, 0, /* UPTO, MINUPTO */
|
|
|
|
0, /* EXACT */
|
|
|
|
0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */
|
|
|
|
|
|
|
|
OP_POSSTARI, 0, /* STARI, MINSTARI */
|
|
|
|
OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */
|
|
|
|
OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */
|
|
|
|
OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */
|
|
|
|
0, /* EXACTI */
|
|
|
|
0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */
|
|
|
|
|
|
|
|
OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */
|
|
|
|
OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */
|
|
|
|
OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */
|
|
|
|
OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */
|
|
|
|
0, /* NOTEXACT */
|
|
|
|
0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */
|
|
|
|
|
|
|
|
OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */
|
|
|
|
OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */
|
|
|
|
OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */
|
|
|
|
OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */
|
|
|
|
0, /* NOTEXACTI */
|
|
|
|
0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */
|
|
|
|
|
|
|
|
OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */
|
|
|
|
OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */
|
|
|
|
OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */
|
|
|
|
OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */
|
|
|
|
0, /* TYPEEXACT */
|
|
|
|
0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */
|
|
|
|
|
|
|
|
OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */
|
|
|
|
OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */
|
|
|
|
OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */
|
|
|
|
OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */
|
|
|
|
0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */
|
|
|
|
|
|
|
|
0, 0, 0, /* CLASS, NCLASS, XCLASS */
|
|
|
|
0, 0, /* REF, REFI */
|
|
|
|
0, 0, /* DNREF, DNREFI */
|
|
|
|
0, 0 /* RECURSE, CALLOUT */
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef DEBUG_SHOW_PARSED
|
|
|
|
/*************************************************
|
|
|
|
* Show the parsed pattern for debugging *
|
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
/* For debugging the pre-scan, this code, which outputs the parsed data vector,
|
|
|
|
can be enabled. */
|
|
|
|
|
|
|
|
static void show_parsed(compile_block *cb)
|
|
|
|
{
|
|
|
|
uint32_t *pptr = cb->parsed_pattern;
|
|
|
|
|
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
int max, min;
|
|
|
|
PCRE2_SIZE offset;
|
|
|
|
uint32_t i;
|
|
|
|
uint32_t length;
|
|
|
|
uint32_t meta_arg = META_DATA(*pptr);
|
|
|
|
|
|
|
|
fprintf(stderr, "+++ %02d %.8x ", (int)(pptr - cb->parsed_pattern), *pptr);
|
|
|
|
|
|
|
|
if (*pptr < META_END)
|
|
|
|
{
|
|
|
|
if (*pptr > 32 && *pptr < 128) fprintf(stderr, "%c", *pptr);
|
|
|
|
pptr++;
|
|
|
|
}
|
|
|
|
|
|
|
|
else switch (META_CODE(*pptr++))
|
|
|
|
{
|
|
|
|
default:
|
|
|
|
fprintf(stderr, "**** OOPS - unknown META value - giving up ****\n");
|
|
|
|
return;
|
|
|
|
|
|
|
|
case META_END:
|
|
|
|
fprintf(stderr, "META_END\n");
|
|
|
|
return;
|
|
|
|
|
|
|
|
case META_CAPTURE:
|
|
|
|
fprintf(stderr, "META_CAPTURE %d", meta_arg);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_RECURSE:
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "META_RECURSE %d %zd", meta_arg, offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_BACKREF:
|
|
|
|
if (meta_arg < 10)
|
|
|
|
offset = cb->small_ref_offset[meta_arg];
|
|
|
|
else
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "META_BACKREF %d %zd", meta_arg, offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_ESCAPE:
|
|
|
|
if (meta_arg == ESC_P || meta_arg == ESC_p)
|
|
|
|
{
|
|
|
|
uint32_t ptype = *pptr >> 16;
|
|
|
|
uint32_t pvalue = *pptr++ & 0xffff;
|
|
|
|
fprintf(stderr, "META \\%c %d %d", (meta_arg == ESC_P)? 'P':'p',
|
|
|
|
ptype, pvalue);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
uint32_t cc;
|
|
|
|
/* There's just one escape we might have here that isn't negated in the
|
|
|
|
escapes table. */
|
|
|
|
if (meta_arg == ESC_g) cc = CHAR_g;
|
|
|
|
else for (cc = ESCAPES_FIRST; cc <= ESCAPES_LAST; cc++)
|
|
|
|
{
|
|
|
|
if (meta_arg == (uint32_t)(-escapes[cc - ESCAPES_FIRST])) break;
|
|
|
|
}
|
|
|
|
if (cc > ESCAPES_LAST) cc = CHAR_QUESTION_MARK;
|
|
|
|
fprintf(stderr, "META \\%c", cc);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MINMAX:
|
|
|
|
min = *pptr++;
|
|
|
|
max = *pptr++;
|
|
|
|
if (max != REPEAT_UNLIMITED)
|
|
|
|
fprintf(stderr, "META {%d,%d}", min, max);
|
|
|
|
else
|
|
|
|
fprintf(stderr, "META {%d,}", min);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
min = *pptr++;
|
|
|
|
max = *pptr++;
|
|
|
|
if (max != REPEAT_UNLIMITED)
|
|
|
|
fprintf(stderr, "META {%d,%d}?", min, max);
|
|
|
|
else
|
|
|
|
fprintf(stderr, "META {%d,}?", min);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
min = *pptr++;
|
|
|
|
max = *pptr++;
|
|
|
|
if (max != REPEAT_UNLIMITED)
|
|
|
|
fprintf(stderr, "META {%d,%d}+", min, max);
|
|
|
|
else
|
|
|
|
fprintf(stderr, "META {%d,}+", min);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_BIGVALUE: fprintf(stderr, "META_BIGVALUE %.8x", *pptr++); break;
|
|
|
|
case META_CIRCUMFLEX: fprintf(stderr, "META_CIRCUMFLEX"); break;
|
2016-11-18 19:59:37 +01:00
|
|
|
case META_COND_ASSERT: fprintf(stderr, "META_COND_ASSERT"); break;
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_DOLLAR: fprintf(stderr, "META_DOLLAR"); break;
|
|
|
|
case META_DOT: fprintf(stderr, "META_DOT"); break;
|
|
|
|
case META_ASTERISK: fprintf(stderr, "META *"); break;
|
|
|
|
case META_ASTERISK_QUERY: fprintf(stderr, "META *?"); break;
|
|
|
|
case META_ASTERISK_PLUS: fprintf(stderr, "META *+"); break;
|
|
|
|
case META_PLUS: fprintf(stderr, "META +"); break;
|
|
|
|
case META_PLUS_QUERY: fprintf(stderr, "META +?"); break;
|
|
|
|
case META_PLUS_PLUS: fprintf(stderr, "META ++"); break;
|
|
|
|
case META_QUERY: fprintf(stderr, "META ?"); break;
|
|
|
|
case META_QUERY_QUERY: fprintf(stderr, "META ??"); break;
|
|
|
|
case META_QUERY_PLUS: fprintf(stderr, "META ?+"); break;
|
|
|
|
|
|
|
|
case META_ATOMIC: fprintf(stderr, "META (?>"); break;
|
|
|
|
case META_NOCAPTURE: fprintf(stderr, "META (?:"); break;
|
|
|
|
case META_LOOKAHEAD: fprintf(stderr, "META (?="); break;
|
|
|
|
case META_LOOKAHEADNOT: fprintf(stderr, "META (?!"); break;
|
|
|
|
case META_KET: fprintf(stderr, "META )"); break;
|
|
|
|
case META_ALT: fprintf(stderr, "META | %d", meta_arg); break;
|
|
|
|
|
|
|
|
case META_CLASS: fprintf(stderr, "META ["); break;
|
|
|
|
case META_CLASS_NOT: fprintf(stderr, "META [^"); break;
|
|
|
|
case META_CLASS_END: fprintf(stderr, "META ]"); break;
|
|
|
|
case META_CLASS_EMPTY: fprintf(stderr, "META []"); break;
|
|
|
|
case META_CLASS_EMPTY_NOT: fprintf(stderr, "META [^]"); break;
|
|
|
|
|
|
|
|
case META_RANGE_LITERAL: fprintf(stderr, "META - (literal)"); break;
|
|
|
|
case META_RANGE_ESCAPED: fprintf(stderr, "META - (escaped)"); break;
|
|
|
|
|
|
|
|
case META_POSIX: fprintf(stderr, "META_POSIX %d", *pptr++); break;
|
|
|
|
case META_POSIX_NEG: fprintf(stderr, "META_POSIX_NEG %d", *pptr++); break;
|
|
|
|
|
|
|
|
case META_ACCEPT: fprintf(stderr, "META (*ACCEPT)"); break;
|
|
|
|
case META_FAIL: fprintf(stderr, "META (*FAIL)"); break;
|
2018-07-21 16:34:51 +02:00
|
|
|
case META_COMMIT: fprintf(stderr, "META (*COMMIT)"); break;
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE: fprintf(stderr, "META (*PRUNE)"); break;
|
|
|
|
case META_SKIP: fprintf(stderr, "META (*SKIP)"); break;
|
|
|
|
case META_THEN: fprintf(stderr, "META (*THEN)"); break;
|
|
|
|
|
|
|
|
case META_OPTIONS: fprintf(stderr, "META_OPTIONS 0x%02x", *pptr++); break;
|
|
|
|
|
|
|
|
case META_LOOKBEHIND:
|
|
|
|
fprintf(stderr, "META (?<= %d offset=", meta_arg);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
fprintf(stderr, "META (?<! %d offset=", meta_arg);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_CALLOUT_NUMBER:
|
|
|
|
fprintf(stderr, "META (?C%d) next=%d/%d", pptr[2], pptr[0],
|
|
|
|
pptr[1]);
|
|
|
|
pptr += 3;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_CALLOUT_STRING:
|
|
|
|
{
|
|
|
|
uint32_t patoffset = *pptr++; /* Offset of next pattern item */
|
|
|
|
uint32_t patlength = *pptr++; /* Length of next pattern item */
|
|
|
|
fprintf(stderr, "META (?Cstring) length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd next=%d/%d", offset, patoffset, patlength);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_RECURSE_BYNAME:
|
|
|
|
fprintf(stderr, "META (?(&name) length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_BACKREF_BYNAME:
|
|
|
|
fprintf(stderr, "META_BACKREF_BYNAME length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_COND_NUMBER:
|
|
|
|
fprintf(stderr, "META_COND_NUMBER %d offset=", pptr[SIZEOFFSET]);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
pptr++;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_COND_DEFINE:
|
|
|
|
fprintf(stderr, "META (?(DEFINE) offset=");
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_COND_VERSION:
|
|
|
|
fprintf(stderr, "META (?(VERSION%s", (*pptr++ == 0)? "=" : ">=");
|
|
|
|
fprintf(stderr, "%d.", *pptr++);
|
|
|
|
fprintf(stderr, "%d)", *pptr++);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_COND_NAME:
|
|
|
|
fprintf(stderr, "META (?(<name>) length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_COND_RNAME:
|
|
|
|
fprintf(stderr, "META (?(R&name) length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* This is kept as a name, because it might be. */
|
|
|
|
|
|
|
|
case META_COND_RNUMBER:
|
|
|
|
fprintf(stderr, "META (?(Rnumber) length=%d offset=", *pptr++);
|
|
|
|
GETOFFSET(offset, pptr);
|
|
|
|
fprintf(stderr, "%zd", offset);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MARK:
|
|
|
|
fprintf(stderr, "META (*MARK:");
|
|
|
|
goto SHOWARG;
|
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
case META_COMMIT_ARG:
|
|
|
|
fprintf(stderr, "META (*COMMIT:");
|
|
|
|
goto SHOWARG;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE_ARG:
|
|
|
|
fprintf(stderr, "META (*PRUNE:");
|
|
|
|
goto SHOWARG;
|
|
|
|
|
|
|
|
case META_SKIP_ARG:
|
|
|
|
fprintf(stderr, "META (*SKIP:");
|
|
|
|
goto SHOWARG;
|
|
|
|
|
|
|
|
case META_THEN_ARG:
|
|
|
|
fprintf(stderr, "META (*THEN:");
|
|
|
|
SHOWARG:
|
|
|
|
length = *pptr++;
|
|
|
|
for (i = 0; i < length; i++)
|
|
|
|
{
|
|
|
|
uint32_t cc = *pptr++;
|
|
|
|
if (cc > 32 && cc < 128) fprintf(stderr, "%c", cc);
|
|
|
|
else fprintf(stderr, "\\x{%x}", cc);
|
|
|
|
}
|
|
|
|
fprintf(stderr, ") length=%u", length);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
fprintf(stderr, "\n");
|
|
|
|
}
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
#endif /* DEBUG_SHOW_PARSED */
|
|
|
|
|
|
|
|
|
2015-04-01 17:37:54 +02:00
|
|
|
|
2016-02-26 19:26:17 +01:00
|
|
|
/*************************************************
|
|
|
|
* Copy compiled code *
|
|
|
|
*************************************************/
|
|
|
|
|
2016-06-29 18:52:05 +02:00
|
|
|
/* Compiled JIT code cannot be copied, so the new compiled block has no
|
2016-02-26 19:26:17 +01:00
|
|
|
associated JIT data. */
|
|
|
|
|
|
|
|
PCRE2_EXP_DEFN pcre2_code * PCRE2_CALL_CONVENTION
|
|
|
|
pcre2_code_copy(const pcre2_code *code)
|
|
|
|
{
|
|
|
|
PCRE2_SIZE* ref_count;
|
|
|
|
pcre2_code *newcode;
|
|
|
|
|
|
|
|
if (code == NULL) return NULL;
|
|
|
|
newcode = code->memctl.malloc(code->blocksize, code->memctl.memory_data);
|
|
|
|
if (newcode == NULL) return NULL;
|
|
|
|
memcpy(newcode, code, code->blocksize);
|
|
|
|
newcode->executable_jit = NULL;
|
|
|
|
|
2016-06-29 18:52:05 +02:00
|
|
|
/* If the code is one that has been deserialized, increment the reference count
|
2016-02-26 19:26:17 +01:00
|
|
|
in the decoded tables. */
|
|
|
|
|
|
|
|
if ((code->flags & PCRE2_DEREF_TABLES) != 0)
|
|
|
|
{
|
|
|
|
ref_count = (PCRE2_SIZE *)(code->tables + tables_length);
|
|
|
|
(*ref_count)++;
|
2016-06-29 18:52:05 +02:00
|
|
|
}
|
2016-11-23 18:17:57 +01:00
|
|
|
|
2016-11-22 16:37:02 +01:00
|
|
|
return newcode;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
|
|
|
* Copy compiled code and character tables *
|
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
/* Compiled JIT code cannot be copied, so the new compiled block has no
|
|
|
|
associated JIT data. This version of code_copy also makes a separate copy of
|
|
|
|
the character tables. */
|
|
|
|
|
|
|
|
PCRE2_EXP_DEFN pcre2_code * PCRE2_CALL_CONVENTION
|
|
|
|
pcre2_code_copy_with_tables(const pcre2_code *code)
|
|
|
|
{
|
|
|
|
PCRE2_SIZE* ref_count;
|
|
|
|
pcre2_code *newcode;
|
|
|
|
uint8_t *newtables;
|
2016-02-26 19:26:17 +01:00
|
|
|
|
2016-11-22 16:37:02 +01:00
|
|
|
if (code == NULL) return NULL;
|
|
|
|
newcode = code->memctl.malloc(code->blocksize, code->memctl.memory_data);
|
|
|
|
if (newcode == NULL) return NULL;
|
|
|
|
memcpy(newcode, code, code->blocksize);
|
|
|
|
newcode->executable_jit = NULL;
|
|
|
|
|
|
|
|
newtables = code->memctl.malloc(tables_length + sizeof(PCRE2_SIZE),
|
|
|
|
code->memctl.memory_data);
|
|
|
|
if (newtables == NULL)
|
|
|
|
{
|
|
|
|
code->memctl.free((void *)newcode, code->memctl.memory_data);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
memcpy(newtables, code->tables, tables_length);
|
|
|
|
ref_count = (PCRE2_SIZE *)(newtables + tables_length);
|
|
|
|
*ref_count = 1;
|
|
|
|
|
|
|
|
newcode->tables = newtables;
|
|
|
|
newcode->flags |= PCRE2_DEREF_TABLES;
|
2016-02-26 19:26:17 +01:00
|
|
|
return newcode;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/*************************************************
|
|
|
|
* Free compiled code *
|
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
|
|
|
|
pcre2_code_free(pcre2_code *code)
|
|
|
|
{
|
2015-01-23 17:51:47 +01:00
|
|
|
PCRE2_SIZE* ref_count;
|
|
|
|
|
2014-10-20 19:28:49 +02:00
|
|
|
if (code != NULL)
|
2014-10-07 15:07:20 +02:00
|
|
|
{
|
2014-10-09 12:06:19 +02:00
|
|
|
if (code->executable_jit != NULL)
|
|
|
|
PRIV(jit_free)(code->executable_jit, &code->memctl);
|
2015-01-23 17:51:47 +01:00
|
|
|
|
|
|
|
if ((code->flags & PCRE2_DEREF_TABLES) != 0)
|
|
|
|
{
|
|
|
|
/* Decoded tables belong to the codes after deserialization, and they must
|
|
|
|
be freed when there are no more reference to them. The *ref_count should
|
|
|
|
always be > 0. */
|
|
|
|
|
|
|
|
ref_count = (PCRE2_SIZE *)(code->tables + tables_length);
|
|
|
|
if (*ref_count > 0)
|
|
|
|
{
|
|
|
|
(*ref_count)--;
|
|
|
|
if (*ref_count == 0)
|
|
|
|
code->memctl.free((void *)code->tables, code->memctl.memory_data);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-10-07 15:07:20 +02:00
|
|
|
code->memctl.free(code, code->memctl.memory_data);
|
2014-10-20 19:28:49 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Read a number, possibly signed *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is used to read numbers in the pattern. The initial pointer
|
|
|
|
must be the sign or first digit of the number. When relative values (introduced
|
|
|
|
by + or -) are allowed, they are relative group numbers, and the result must be
|
|
|
|
greater than zero.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
ptrptr points to the character pointer variable
|
|
|
|
ptrend points to the end of the input string
|
|
|
|
allow_sign if < 0, sign not allowed; if >= 0, sign is relative to this
|
|
|
|
max_value the largest number allowed
|
|
|
|
max_error the error to give for an over-large number
|
|
|
|
intptr where to put the result
|
|
|
|
errcodeptr where to put an error code
|
|
|
|
|
|
|
|
Returns: TRUE - a number was read
|
|
|
|
FALSE - errorcode == 0 => no number was found
|
|
|
|
errorcode != 0 => an error occurred
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
read_number(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, int32_t allow_sign,
|
|
|
|
uint32_t max_value, uint32_t max_error, int *intptr, int *errorcodeptr)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
int sign = 0;
|
|
|
|
uint32_t n = 0;
|
|
|
|
PCRE2_SPTR ptr = *ptrptr;
|
|
|
|
BOOL yield = FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-01-31 18:15:30 +01:00
|
|
|
if (allow_sign >= 0 && ptr < ptrend)
|
|
|
|
{
|
|
|
|
if (*ptr == CHAR_PLUS)
|
|
|
|
{
|
|
|
|
sign = +1;
|
|
|
|
max_value -= allow_sign;
|
2017-02-14 11:40:33 +01:00
|
|
|
ptr++;
|
2017-01-31 18:15:30 +01:00
|
|
|
}
|
|
|
|
else if (*ptr == CHAR_MINUS)
|
2017-02-14 11:40:33 +01:00
|
|
|
{
|
|
|
|
sign = -1;
|
|
|
|
ptr++;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend || !IS_DIGIT(*ptr)) return FALSE;
|
|
|
|
while (ptr < ptrend && IS_DIGIT(*ptr))
|
|
|
|
{
|
|
|
|
n = n * 10 + *ptr++ - CHAR_0;
|
|
|
|
if (n > max_value)
|
|
|
|
{
|
|
|
|
*errorcodeptr = max_error;
|
|
|
|
goto EXIT;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (allow_sign >= 0 && sign != 0)
|
|
|
|
{
|
|
|
|
if (n == 0)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR26; /* +0 and -0 are not allowed */
|
|
|
|
goto EXIT;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (sign > 0) n += allow_sign;
|
|
|
|
else if ((int)n > allow_sign)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR15; /* Non-existent subpattern */
|
|
|
|
goto EXIT;
|
|
|
|
}
|
|
|
|
else n = allow_sign + 1 - n;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
yield = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
EXIT:
|
|
|
|
*intptr = n;
|
|
|
|
*ptrptr = ptr;
|
|
|
|
return yield;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Read repeat counts *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Read an item of the form {n,m} and return the values if non-NULL pointers
|
|
|
|
are supplied. Repeat counts must be less than 65536 (MAX_REPEAT_COUNT); a
|
|
|
|
larger value is used for "unlimited". We have to use signed arguments for
|
|
|
|
read_number() because it is capable of returning a signed value.
|
2015-11-03 11:39:27 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
ptrptr points to pointer to character after'{'
|
|
|
|
ptrend pointer to end of input
|
|
|
|
minp if not NULL, pointer to int for min
|
|
|
|
maxp if not NULL, pointer to int for max (-1 if no max)
|
|
|
|
returned as -1 if no max
|
|
|
|
errorcodeptr points to error code variable
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: FALSE if not a repeat quantifier, errorcode set zero
|
|
|
|
FALSE on error, with errorcode set non-zero
|
|
|
|
TRUE on success, with pointer updated to point after '}'
|
|
|
|
*/
|
2015-11-03 11:39:27 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
read_repeat_counts(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t *minp,
|
|
|
|
uint32_t *maxp, int *errorcodeptr)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SPTR p = *ptrptr;
|
|
|
|
BOOL yield = FALSE;
|
|
|
|
int32_t min = 0;
|
2016-11-01 13:12:45 +01:00
|
|
|
int32_t max = REPEAT_UNLIMITED; /* This value is larger than MAX_REPEAT_COUNT */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* NB read_number() initializes the error code to zero. The only error is for a
|
|
|
|
number that is too big. */
|
|
|
|
|
|
|
|
if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &min, errorcodeptr))
|
|
|
|
goto EXIT;
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (p >= ptrend) goto EXIT;
|
|
|
|
|
|
|
|
if (*p == CHAR_RIGHT_CURLY_BRACKET)
|
2015-11-08 15:20:09 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
p++;
|
|
|
|
max = min;
|
|
|
|
}
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (*p++ != CHAR_COMMA || p >= ptrend) goto EXIT;
|
|
|
|
if (*p != CHAR_RIGHT_CURLY_BRACKET)
|
2015-11-10 15:33:28 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!read_number(&p, ptrend, -1, MAX_REPEAT_COUNT, ERR5, &max,
|
2016-11-01 13:12:45 +01:00
|
|
|
errorcodeptr) || p >= ptrend || *p != CHAR_RIGHT_CURLY_BRACKET)
|
2016-10-02 18:01:01 +02:00
|
|
|
goto EXIT;
|
|
|
|
if (max < min)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR4;
|
|
|
|
goto EXIT;
|
|
|
|
}
|
2015-11-10 15:33:28 +01:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
p++;
|
2015-11-08 15:20:09 +01:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
yield = TRUE;
|
|
|
|
if (minp != NULL) *minp = (uint32_t)min;
|
|
|
|
if (maxp != NULL) *maxp = (uint32_t)max;
|
2015-11-10 15:33:28 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Update the pattern pointer on success, or after an error, but not when
|
|
|
|
the result is "not a repeat quantifier". */
|
2015-11-10 15:33:28 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
EXIT:
|
|
|
|
if (yield || *errorcodeptr != 0) *ptrptr = p;
|
|
|
|
return yield;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-11-03 20:14:31 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Handle escapes *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called when a \ has been encountered. It either returns a
|
|
|
|
positive value for a simple escape such as \d, or 0 for a data character, which
|
|
|
|
is placed in chptr. A backreference to group n is returned as negative n. On
|
|
|
|
entry, ptr is pointing at the character after \. On exit, it points after the
|
|
|
|
final code unit of the escape sequence.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
This function is also called from pcre2_substitute() to handle escape sequences
|
2016-12-11 17:42:29 +01:00
|
|
|
in replacement strings. In this case, the cb argument is NULL, and in the case
|
2016-12-09 17:57:51 +01:00
|
|
|
of escapes that have further processing, only sequences that define a data
|
|
|
|
character are recognised. The isclass argument is not relevant; the options
|
|
|
|
argument is the final value of the compiled pattern's options.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
ptrptr points to the input position pointer
|
|
|
|
ptrend points to the end of the input
|
|
|
|
chptr points to a returned data character
|
|
|
|
errorcodeptr points to the errorcode variable (containing zero)
|
|
|
|
options the current options bits
|
|
|
|
isclass TRUE if inside a character class
|
2018-09-21 18:59:48 +02:00
|
|
|
cb compile data block or NULL when called from pcre2_substitute()
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: zero => a data character
|
|
|
|
positive => a special escape sequence
|
|
|
|
negative => a numerical back reference
|
|
|
|
on error, errorcodeptr is set non-zero
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
int
|
|
|
|
PRIV(check_escape)(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t *chptr,
|
|
|
|
int *errorcodeptr, uint32_t options, BOOL isclass, compile_block *cb)
|
|
|
|
{
|
|
|
|
BOOL utf = (options & PCRE2_UTF) != 0;
|
|
|
|
PCRE2_SPTR ptr = *ptrptr;
|
|
|
|
uint32_t c, cc;
|
|
|
|
int escape = 0;
|
|
|
|
int i;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If backslash is at the end of the string, it's an error. */
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR1;
|
|
|
|
return 0;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
|
|
|
|
*errorcodeptr = 0; /* Be optimistic */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Non-alphanumerics are literals, so we just leave the value in c. An initial
|
|
|
|
value test saves a memory lookup for code points outside the alphanumeric
|
2018-09-21 18:59:48 +02:00
|
|
|
range. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c < ESCAPES_FIRST || c > ESCAPES_LAST) {} /* Definitely literal */
|
|
|
|
|
2018-09-21 18:59:48 +02:00
|
|
|
/* Otherwise, do a table lookup. Non-zero values need little processing here. A
|
|
|
|
positive value is a literal value for something like \n. A negative value is
|
|
|
|
the negation of one of the ESC_ macros that is passed back for handling by the
|
|
|
|
calling function. Some extra checking is needed for \N because only \N{U+dddd}
|
|
|
|
is supported. If the value is zero, further processing is handled below. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if ((i = escapes[c - ESCAPES_FIRST]) != 0)
|
|
|
|
{
|
2018-09-21 18:59:48 +02:00
|
|
|
if (i > 0)
|
|
|
|
{
|
|
|
|
c = (uint32_t)i;
|
|
|
|
if (cb != NULL && c == CHAR_CR &&
|
|
|
|
(cb->cx->extra_options & PCRE2_EXTRA_ESCAPED_CR_IS_LF) != 0)
|
2018-09-24 18:23:53 +02:00
|
|
|
c = CHAR_LF;
|
2018-09-21 18:59:48 +02:00
|
|
|
}
|
2018-09-24 18:23:53 +02:00
|
|
|
else /* Negative table entry */
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
escape = -i; /* Else return a special escape */
|
2016-12-09 17:57:51 +01:00
|
|
|
if (cb != NULL && (escape == ESC_P || escape == ESC_p || escape == ESC_X))
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->external_flags |= PCRE2_HASBKPORX; /* Note \P, \p, or \X */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-27 18:30:40 +02:00
|
|
|
/* Perl supports \N{name} for character names and \N{U+dddd} for numerical
|
|
|
|
Unicode code points, as well as plain \N for "not newline". PCRE does not
|
2018-07-28 18:23:24 +02:00
|
|
|
support \N{name}. However, it does support quantification such as \N{2,3},
|
2018-07-27 18:30:40 +02:00
|
|
|
so if \N{ is not followed by U+dddd we check for a quantifier. */
|
|
|
|
|
|
|
|
if (escape == ESC_N && ptr < ptrend && *ptr == CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
PCRE2_SPTR p = ptr + 1;
|
2018-07-28 18:23:24 +02:00
|
|
|
|
|
|
|
/* \N{U+ can be handled by the \x{ code. However, this construction is
|
|
|
|
not valid in EBCDIC environments because it specifies a Unicode
|
|
|
|
character, not a codepoint in the local code. For example \N{U+0041}
|
2018-09-02 18:53:29 +02:00
|
|
|
must be "A" in all environments. Also, in Perl, \N{U+ forces Unicode
|
|
|
|
casing semantics for the entire pattern, so allow it only in UTF (i.e.
|
2018-09-02 18:03:27 +02:00
|
|
|
Unicode) mode. */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-27 18:30:40 +02:00
|
|
|
if (ptrend - p > 1 && *p == CHAR_U && p[1] == CHAR_PLUS)
|
|
|
|
{
|
|
|
|
#ifdef EBCDIC
|
|
|
|
*errorcodeptr = ERR93;
|
2018-07-28 18:23:24 +02:00
|
|
|
#else
|
2018-09-02 18:03:27 +02:00
|
|
|
if (utf)
|
2018-09-02 18:53:29 +02:00
|
|
|
{
|
2018-09-02 18:03:27 +02:00
|
|
|
ptr = p + 1;
|
|
|
|
escape = 0; /* Not a fancy escape after all */
|
|
|
|
goto COME_FROM_NU;
|
|
|
|
}
|
2018-09-02 18:53:29 +02:00
|
|
|
else *errorcodeptr = ERR93;
|
2018-07-28 18:23:24 +02:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Give an error if what follows is not a quantifier, but don't override
|
2018-07-27 18:30:40 +02:00
|
|
|
an error set by the quantifier reader (e.g. number overflow). */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-27 18:30:40 +02:00
|
|
|
else
|
2018-07-28 18:23:24 +02:00
|
|
|
{
|
2018-07-27 18:30:40 +02:00
|
|
|
if (!read_repeat_counts(&p, ptrend, NULL, NULL, errorcodeptr) &&
|
|
|
|
*errorcodeptr == 0)
|
|
|
|
*errorcodeptr = ERR37;
|
2018-07-28 18:23:24 +02:00
|
|
|
}
|
2018-07-27 18:30:40 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* Escapes that need further processing, including those that are unknown, have
|
2018-09-21 18:59:48 +02:00
|
|
|
a zero entry in the lookup table. When called from pcre2_substitute(), only \c,
|
|
|
|
\o, and \x are recognized (and \u when BSUX is set). */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
PCRE2_SPTR oldptr;
|
|
|
|
BOOL overflow;
|
|
|
|
int s;
|
|
|
|
|
|
|
|
/* Filter calls from pcre2_substitute(). */
|
|
|
|
|
|
|
|
if (cb == NULL && c != CHAR_c && c != CHAR_o && c != CHAR_x &&
|
|
|
|
(c != CHAR_u || (options & PCRE2_ALT_BSUX) != 0))
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR3;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (c)
|
|
|
|
{
|
|
|
|
/* A number of Perl escapes are not handled by PCRE. We give an explicit
|
|
|
|
error. */
|
|
|
|
|
2018-07-27 18:55:52 +02:00
|
|
|
case CHAR_F:
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_l:
|
|
|
|
case CHAR_L:
|
|
|
|
*errorcodeptr = ERR37;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* \u is unrecognized when PCRE2_ALT_BSUX is not set. When it is treated
|
|
|
|
specially, \u must be followed by four hex digits. Otherwise it is a
|
|
|
|
lowercase u letter. */
|
|
|
|
|
|
|
|
case CHAR_u:
|
|
|
|
if ((options & PCRE2_ALT_BSUX) == 0) *errorcodeptr = ERR37; else
|
|
|
|
{
|
|
|
|
uint32_t xc;
|
|
|
|
if (ptrend - ptr < 4) break; /* Less than 4 chars */
|
|
|
|
if ((cc = XDIGIT(ptr[0])) == 0xff) break; /* Not a hex digit */
|
|
|
|
if ((xc = XDIGIT(ptr[1])) == 0xff) break; /* Not a hex digit */
|
|
|
|
cc = (cc << 4) | xc;
|
|
|
|
if ((xc = XDIGIT(ptr[2])) == 0xff) break; /* Not a hex digit */
|
|
|
|
cc = (cc << 4) | xc;
|
|
|
|
if ((xc = XDIGIT(ptr[3])) == 0xff) break; /* Not a hex digit */
|
|
|
|
c = (cc << 4) | xc;
|
|
|
|
ptr += 4;
|
|
|
|
if (utf)
|
|
|
|
{
|
|
|
|
if (c > 0x10ffffU) *errorcodeptr = ERR77;
|
2017-05-17 19:55:11 +02:00
|
|
|
else
|
|
|
|
if (c >= 0xd800 && c <= 0xdfff &&
|
|
|
|
(cb->cx->extra_options & PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES) == 0)
|
|
|
|
*errorcodeptr = ERR73;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
else if (c > MAX_NON_UTF_CHAR) *errorcodeptr = ERR77;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* \U is unrecognized unless PCRE2_ALT_BSUX is set, in which case it is an
|
|
|
|
upper case letter. */
|
|
|
|
|
|
|
|
case CHAR_U:
|
|
|
|
if ((options & PCRE2_ALT_BSUX) == 0) *errorcodeptr = ERR37;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In a character class, \g is just a literal "g". Outside a character
|
|
|
|
class, \g must be followed by one of a number of specific things:
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
(1) A number, either plain or braced. If positive, it is an absolute
|
|
|
|
backreference. If negative, it is a relative backreference. This is a Perl
|
|
|
|
5.10 feature.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
(2) Perl 5.10 also supports \g{name} as a reference to a named group. This
|
|
|
|
is part of Perl's movement towards a unified syntax for back references. As
|
|
|
|
this is synonymous with \k{name}, we fudge it up by pretending it really
|
|
|
|
was \k{name}.
|
|
|
|
|
|
|
|
(3) For Oniguruma compatibility we also support \g followed by a name or a
|
|
|
|
number either in angle brackets or in single quotes. However, these are
|
|
|
|
(possibly recursive) subroutine calls, _not_ backreferences. We return
|
|
|
|
the ESC_g code.
|
|
|
|
|
|
|
|
Summary: Return a negative number for a numerical back reference, ESC_k for
|
|
|
|
a named back reference, and ESC_g for a named or numbered subroutine call.
|
|
|
|
*/
|
|
|
|
|
|
|
|
case CHAR_g:
|
|
|
|
if (isclass) break;
|
|
|
|
|
|
|
|
if (ptr >= ptrend)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR57;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (*ptr == CHAR_LESS_THAN_SIGN || *ptr == CHAR_APOSTROPHE)
|
|
|
|
{
|
|
|
|
escape = ESC_g;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If there is a brace delimiter, try to read a numerical reference. If
|
|
|
|
there isn't one, assume we have a name and treat it as \k. */
|
|
|
|
|
|
|
|
if (*ptr == CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
PCRE2_SPTR p = ptr + 1;
|
|
|
|
if (!read_number(&p, ptrend, cb->bracount, MAX_GROUP_NUMBER, ERR61, &s,
|
|
|
|
errorcodeptr))
|
|
|
|
{
|
|
|
|
if (*errorcodeptr == 0) escape = ESC_k; /* No number found */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (p >= ptrend || *p != CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR57;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
ptr = p + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Read an undelimited number */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (!read_number(&ptr, ptrend, cb->bracount, MAX_GROUP_NUMBER, ERR61, &s,
|
|
|
|
errorcodeptr))
|
|
|
|
{
|
|
|
|
if (*errorcodeptr == 0) *errorcodeptr = ERR57; /* No number found */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s <= 0)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR15;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
escape = -s;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The handling of escape sequences consisting of a string of digits
|
|
|
|
starting with one that is not zero is not straightforward. Perl has changed
|
|
|
|
over the years. Nowadays \g{} for backreferences and \o{} for octal are
|
|
|
|
recommended to avoid the ambiguities in the old syntax.
|
|
|
|
|
|
|
|
Outside a character class, the digits are read as a decimal number. If the
|
|
|
|
number is less than 10, or if there are that many previous extracting left
|
|
|
|
brackets, it is a back reference. Otherwise, up to three octal digits are
|
|
|
|
read to form an escaped character code. Thus \123 is likely to be octal 123
|
|
|
|
(cf \0123, which is octal 012 followed by the literal 3).
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Inside a character class, \ followed by a digit is always either a literal
|
|
|
|
8 or 9 or an octal number. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5:
|
|
|
|
case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9:
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!isclass)
|
|
|
|
{
|
|
|
|
oldptr = ptr;
|
|
|
|
ptr--; /* Back to the digit */
|
|
|
|
if (!read_number(&ptr, ptrend, -1, INT_MAX/10 - 1, ERR61, &s,
|
|
|
|
errorcodeptr))
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* \1 to \9 are always back references. \8x and \9x are too; \1x to \7x
|
|
|
|
are octal escapes if there are not that many previous captures. */
|
|
|
|
|
|
|
|
if (s < 10 || oldptr[-1] >= CHAR_8 || s <= (int)cb->bracount)
|
|
|
|
{
|
|
|
|
if (s > (int)MAX_GROUP_NUMBER) *errorcodeptr = ERR61;
|
|
|
|
else escape = -s; /* Indicates a back reference */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
ptr = oldptr; /* Put the pointer back and fall through */
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Handle a digit following \ when the number is not a back reference, or
|
|
|
|
we are within a character class. If the first digit is 8 or 9, Perl used to
|
|
|
|
generate a binary zero and then treat the digit as a following literal. At
|
|
|
|
least by Perl 5.18 this changed so as not to insert the binary zero. */
|
|
|
|
|
|
|
|
if (c >= CHAR_8) break;
|
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
/* Fall through */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* \0 always starts an octal number, but we may drop through to here with a
|
|
|
|
larger first octal digit. The original code used just to take the least
|
|
|
|
significant 8 bits of octal numbers (I think this is what early Perls used
|
|
|
|
to do). Nowadays we allow for larger numbers in UTF-8 mode and 16-bit mode,
|
|
|
|
but no more than 3 octal digits. */
|
|
|
|
|
|
|
|
case CHAR_0:
|
|
|
|
c -= CHAR_0;
|
|
|
|
while(i++ < 2 && ptr < ptrend && *ptr >= CHAR_0 && *ptr <= CHAR_7)
|
|
|
|
c = c * 8 + *ptr++ - CHAR_0;
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
|
|
|
if (!utf && c > 0xff) *errorcodeptr = ERR51;
|
|
|
|
#endif
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* \o is a relatively new Perl feature, supporting a more general way of
|
|
|
|
specifying character codes in octal. The only supported form is \o{ddd}. */
|
|
|
|
|
|
|
|
case CHAR_o:
|
|
|
|
if (ptr >= ptrend || *ptr++ != CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
*errorcodeptr = ERR55;
|
|
|
|
}
|
|
|
|
else if (ptr >= ptrend || *ptr == CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
*errorcodeptr = ERR78;
|
2014-06-14 20:29:51 +02:00
|
|
|
else
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
c = 0;
|
|
|
|
overflow = FALSE;
|
|
|
|
while (ptr < ptrend && *ptr >= CHAR_0 && *ptr <= CHAR_7)
|
|
|
|
{
|
|
|
|
cc = *ptr++;
|
|
|
|
if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
if (c >= 0x20000000l) { overflow = TRUE; break; }
|
|
|
|
#endif
|
|
|
|
c = (c << 3) + (cc - CHAR_0);
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
|
|
|
if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; }
|
|
|
|
#elif PCRE2_CODE_UNIT_WIDTH == 16
|
|
|
|
if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; }
|
|
|
|
#elif PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
if (utf && c > 0x10ffffU) { overflow = TRUE; break; }
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
if (overflow)
|
|
|
|
{
|
|
|
|
while (ptr < ptrend && *ptr >= CHAR_0 && *ptr <= CHAR_7) ptr++;
|
|
|
|
*errorcodeptr = ERR34;
|
|
|
|
}
|
|
|
|
else if (ptr < ptrend && *ptr++ == CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
{
|
2017-05-23 18:47:29 +02:00
|
|
|
if (utf && c >= 0xd800 && c <= 0xdfff && (cb == NULL ||
|
|
|
|
(cb->cx->extra_options & PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES) == 0))
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
*errorcodeptr = ERR73;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
*errorcodeptr = ERR64;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* \x is complicated. When PCRE2_ALT_BSUX is set, \x must be followed by
|
|
|
|
two hexadecimal digits. Otherwise it is a lowercase x letter. */
|
|
|
|
|
|
|
|
case CHAR_x:
|
|
|
|
if ((options & PCRE2_ALT_BSUX) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t xc;
|
|
|
|
if (ptrend - ptr < 2) break; /* Less than 2 characters */
|
|
|
|
if ((cc = XDIGIT(ptr[0])) == 0xff) break; /* Not a hex digit */
|
|
|
|
if ((xc = XDIGIT(ptr[1])) == 0xff) break; /* Not a hex digit */
|
|
|
|
c = (cc << 4) | xc;
|
|
|
|
ptr += 2;
|
|
|
|
} /* End PCRE2_ALT_BSUX handling */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle \x in Perl's style. \x{ddd} is a character number which can be
|
|
|
|
greater than 0xff in UTF-8 or non-8bit mode, but only if the ddd are hex
|
|
|
|
digits. If not, { used to be treated as a data character. However, Perl
|
|
|
|
seems to read hex digits up to the first non-such, and ignore the rest, so
|
|
|
|
that, for example \x{zz} matches a binary zero. This seems crazy, so PCRE
|
|
|
|
now gives an error. */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (ptr < ptrend && *ptr == CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
{
|
2018-07-28 18:23:24 +02:00
|
|
|
#ifndef EBCDIC
|
|
|
|
COME_FROM_NU:
|
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
if (++ptr >= ptrend || *ptr == CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR78;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
c = 0;
|
|
|
|
overflow = FALSE;
|
|
|
|
|
|
|
|
while (ptr < ptrend && (cc = XDIGIT(*ptr)) != 0xff)
|
|
|
|
{
|
|
|
|
ptr++;
|
|
|
|
if (c == 0 && cc == 0) continue; /* Leading zeroes */
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
if (c >= 0x10000000l) { overflow = TRUE; break; }
|
|
|
|
#endif
|
|
|
|
c = (c << 4) | cc;
|
|
|
|
if ((utf && c > 0x10ffffU) || (!utf && c > MAX_NON_UTF_CHAR))
|
|
|
|
{
|
|
|
|
overflow = TRUE;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (overflow)
|
|
|
|
{
|
|
|
|
while (ptr < ptrend && XDIGIT(*ptr) != 0xff) ptr++;
|
|
|
|
*errorcodeptr = ERR34;
|
|
|
|
}
|
|
|
|
else if (ptr < ptrend && *ptr++ == CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
{
|
2017-05-23 18:47:29 +02:00
|
|
|
if (utf && c >= 0xd800 && c <= 0xdfff && (cb == NULL ||
|
|
|
|
(cb->cx->extra_options & PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES) == 0))
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
*errorcodeptr = ERR73;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If the sequence of hex digits does not end with '}', give an error.
|
|
|
|
We used just to recognize this construct and fall through to the normal
|
|
|
|
\x handling, but nowadays Perl gives an error, which seems much more
|
|
|
|
sensible, so we do too. */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
*errorcodeptr = ERR67;
|
|
|
|
}
|
|
|
|
} /* End of \x{} processing */
|
|
|
|
|
|
|
|
/* Read a up to two hex digits after \x */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
c = 0;
|
|
|
|
if (ptr >= ptrend || (cc = XDIGIT(*ptr)) == 0xff) break; /* Not a hex digit */
|
|
|
|
ptr++;
|
|
|
|
c = cc;
|
|
|
|
if (ptr >= ptrend || (cc = XDIGIT(*ptr)) == 0xff) break; /* Not a hex digit */
|
|
|
|
ptr++;
|
|
|
|
c = (c << 4) | cc;
|
|
|
|
} /* End of \xdd handling */
|
|
|
|
} /* End of Perl-style \x handling */
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* The handling of \c is different in ASCII and EBCDIC environments. In an
|
|
|
|
ASCII (or Unicode) environment, an error is given if the character
|
|
|
|
following \c is not a printable ASCII character. Otherwise, the following
|
|
|
|
character is upper-cased if it is a letter, and after that the 0x40 bit is
|
|
|
|
flipped. The result is the value of the escape.
|
|
|
|
|
|
|
|
In an EBCDIC environment the handling of \c is compatible with the
|
|
|
|
specification in the perlebcdic document. The following character must be
|
|
|
|
a letter or one of small number of special characters. These provide a
|
|
|
|
means of defining the character values 0-31.
|
|
|
|
|
|
|
|
For testing the EBCDIC handling of \c in an ASCII environment, recognize
|
|
|
|
the EBCDIC value of 'c' explicitly. */
|
|
|
|
|
|
|
|
#if defined EBCDIC && 'a' != 0x81
|
|
|
|
case 0x83:
|
|
|
|
#else
|
|
|
|
case CHAR_c:
|
|
|
|
#endif
|
|
|
|
if (ptr >= ptrend)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR2;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
c = *ptr;
|
|
|
|
if (c >= CHAR_a && c <= CHAR_z) c = UPPER_CASE(c);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle \c in an ASCII/Unicode environment. */
|
|
|
|
|
|
|
|
#ifndef EBCDIC /* ASCII/UTF-8 coding */
|
|
|
|
if (c < 32 || c > 126) /* Excludes all non-printable ASCII */
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR68;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
c ^= 0x40;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle \c in an EBCDIC environment. The special case \c? is converted to
|
|
|
|
255 (0xff) or 95 (0x5f) if other character suggest we are using th POSIX-BC
|
|
|
|
encoding. (This is the way Perl indicates that it handles \c?.) The other
|
|
|
|
valid sequences correspond to a list of specific characters. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#else
|
|
|
|
if (c == CHAR_QUESTION_MARK)
|
|
|
|
c = ('\\' == 188 && '`' == 74)? 0x5f : 0xff;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
for (i = 0; i < 32; i++)
|
|
|
|
{
|
|
|
|
if (c == ebcdic_escape_c[i]) break;
|
|
|
|
}
|
|
|
|
if (i < 32) c = i; else *errorcodeptr = ERR68;
|
|
|
|
}
|
|
|
|
#endif /* EBCDIC */
|
|
|
|
|
|
|
|
ptr++;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Any other alphanumeric following \ is an error. Perl gives an error only
|
|
|
|
if in warning mode, but PCRE doesn't have a warning mode. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
default:
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR3;
|
|
|
|
*ptrptr = ptr - 1; /* Point to the character at fault */
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Set the pointer to the next character before returning. */
|
|
|
|
|
|
|
|
*ptrptr = ptr;
|
|
|
|
*chptr = c;
|
|
|
|
return escape;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
/*************************************************
|
|
|
|
* Handle \P and \p *
|
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
/* This function is called after \P or \p has been encountered, provided that
|
|
|
|
PCRE2 is compiled with support for UTF and Unicode properties. On entry, the
|
|
|
|
contents of ptrptr are pointing after the P or p. On exit, it is left pointing
|
|
|
|
after the final code unit of the escape sequence.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
ptrptr the pattern position pointer
|
|
|
|
negptr a boolean that is set TRUE for negation else FALSE
|
|
|
|
ptypeptr an unsigned int that is set to the type value
|
|
|
|
pdataptr an unsigned int that is set to the detailed property value
|
|
|
|
errorcodeptr the error code variable
|
|
|
|
cb the compile data
|
|
|
|
|
|
|
|
Returns: TRUE if the type value was found, or FALSE for an invalid type
|
|
|
|
*/
|
|
|
|
|
|
|
|
static BOOL
|
|
|
|
get_ucp(PCRE2_SPTR *ptrptr, BOOL *negptr, uint16_t *ptypeptr,
|
|
|
|
uint16_t *pdataptr, int *errorcodeptr, compile_block *cb)
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR c;
|
|
|
|
PCRE2_SIZE i, bot, top;
|
|
|
|
PCRE2_SPTR ptr = *ptrptr;
|
|
|
|
PCRE2_UCHAR name[32];
|
|
|
|
|
|
|
|
if (ptr >= cb->end_pattern) goto ERROR_RETURN;
|
|
|
|
c = *ptr++;
|
|
|
|
*negptr = FALSE;
|
|
|
|
|
|
|
|
/* \P or \p can be followed by a name in {}, optionally preceded by ^ for
|
|
|
|
negation. */
|
|
|
|
|
|
|
|
if (c == CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
if (ptr >= cb->end_pattern) goto ERROR_RETURN;
|
|
|
|
if (*ptr == CHAR_CIRCUMFLEX_ACCENT)
|
|
|
|
{
|
|
|
|
*negptr = TRUE;
|
|
|
|
ptr++;
|
|
|
|
}
|
|
|
|
for (i = 0; i < (int)(sizeof(name) / sizeof(PCRE2_UCHAR)) - 1; i++)
|
|
|
|
{
|
|
|
|
if (ptr >= cb->end_pattern) goto ERROR_RETURN;
|
|
|
|
c = *ptr++;
|
2017-05-26 19:14:36 +02:00
|
|
|
if (c == CHAR_NUL) goto ERROR_RETURN;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_RIGHT_CURLY_BRACKET) break;
|
|
|
|
name[i] = c;
|
|
|
|
}
|
|
|
|
if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN;
|
|
|
|
name[i] = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Otherwise there is just one following character, which must be an ASCII
|
|
|
|
letter. */
|
|
|
|
|
|
|
|
else if (MAX_255(c) && (cb->ctypes[c] & ctype_letter) != 0)
|
|
|
|
{
|
|
|
|
name[0] = c;
|
|
|
|
name[1] = 0;
|
|
|
|
}
|
|
|
|
else goto ERROR_RETURN;
|
|
|
|
|
|
|
|
*ptrptr = ptr;
|
|
|
|
|
|
|
|
/* Search for a recognized property name using binary chop. */
|
|
|
|
|
|
|
|
bot = 0;
|
|
|
|
top = PRIV(utt_size);
|
|
|
|
|
|
|
|
while (bot < top)
|
|
|
|
{
|
|
|
|
int r;
|
|
|
|
i = (bot + top) >> 1;
|
|
|
|
r = PRIV(strcmp_c8)(name, PRIV(utt_names) + PRIV(utt)[i].name_offset);
|
|
|
|
if (r == 0)
|
|
|
|
{
|
|
|
|
*ptypeptr = PRIV(utt)[i].type;
|
|
|
|
*pdataptr = PRIV(utt)[i].value;
|
|
|
|
return TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
if (r > 0) bot = i + 1; else top = i;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR47; /* Unrecognized name */
|
|
|
|
return FALSE;
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
ERROR_RETURN: /* Malformed \P or \p */
|
|
|
|
*errorcodeptr = ERR46;
|
|
|
|
*ptrptr = ptr;
|
|
|
|
return FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Check for POSIX class syntax *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called when the sequence "[:" or "[." or "[=" is
|
|
|
|
encountered in a character class. It checks whether this is followed by a
|
|
|
|
sequence of characters terminated by a matching ":]" or ".]" or "=]". If we
|
|
|
|
reach an unescaped ']' without the special preceding character, return FALSE.
|
|
|
|
|
|
|
|
Originally, this function only recognized a sequence of letters between the
|
|
|
|
terminators, but it seems that Perl recognizes any sequence of characters,
|
|
|
|
though of course unknown POSIX names are subsequently rejected. Perl gives an
|
|
|
|
"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE
|
|
|
|
didn't consider this to be a POSIX class. Likewise for [:1234:].
|
|
|
|
|
|
|
|
The problem in trying to be exactly like Perl is in the handling of escapes. We
|
|
|
|
have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX
|
|
|
|
class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code
|
|
|
|
below handles the special cases \\ and \], but does not try to do any other
|
|
|
|
escape processing. This makes it different from Perl for cases such as
|
|
|
|
[:l\ower:] where Perl recognizes it as the POSIX class "lower" but PCRE does
|
|
|
|
not recognize "l\ower". This is a lesser evil than not diagnosing bad classes
|
|
|
|
when Perl does, I think.
|
|
|
|
|
|
|
|
A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not.
|
|
|
|
It seems that the appearance of a nested POSIX class supersedes an apparent
|
|
|
|
external class. For example, [:a[:digit:]b:] matches "a", "b", ":", or
|
|
|
|
a digit. This is handled by returning FALSE if the start of a new group with
|
|
|
|
the same terminator is encountered, since the next closing sequence must close
|
|
|
|
the nested group, not the outer one.
|
|
|
|
|
|
|
|
In Perl, unescaped square brackets may also appear as part of class names. For
|
|
|
|
example, [:a[:abc]b:] gives unknown POSIX class "[:abc]b:]". However, for
|
|
|
|
[:a[:abc]b][b:] it gives unknown POSIX class "[:abc]b][b:]", which does not
|
|
|
|
seem right at all. PCRE does not allow closing square brackets in POSIX class
|
|
|
|
names.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
ptr pointer to the character after the initial [ (colon, dot, equals)
|
|
|
|
ptrend pointer to the end of the pattern
|
|
|
|
endptr where to return a pointer to the terminating ':', '.', or '='
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: TRUE or FALSE
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
check_posix_syntax(PCRE2_SPTR ptr, PCRE2_SPTR ptrend, PCRE2_SPTR *endptr)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_UCHAR terminator; /* Don't combine these lines; the Solaris cc */
|
|
|
|
terminator = *ptr++; /* compiler warns about "non-constant" initializer. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (; ptrend - ptr >= 2; ptr++)
|
|
|
|
{
|
|
|
|
if (*ptr == CHAR_BACKSLASH &&
|
|
|
|
(ptr[1] == CHAR_RIGHT_SQUARE_BRACKET || ptr[1] == CHAR_BACKSLASH))
|
|
|
|
ptr++;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if ((*ptr == CHAR_LEFT_SQUARE_BRACKET && ptr[1] == terminator) ||
|
|
|
|
*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE;
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET)
|
|
|
|
{
|
|
|
|
*endptr = ptr;
|
|
|
|
return TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
return FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Check POSIX class name *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called to check the name given in a POSIX-style class entry
|
|
|
|
such as [:alnum:].
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
ptr points to the first letter
|
|
|
|
len the length of the name
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: a value representing the name, or -1 if unknown
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2015-11-10 15:33:28 +01:00
|
|
|
static int
|
2016-10-02 18:01:01 +02:00
|
|
|
check_posix_name(PCRE2_SPTR ptr, int len)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
const char *pn = posix_names;
|
|
|
|
int yield = 0;
|
|
|
|
while (posix_name_lengths[yield] != 0)
|
2015-11-08 15:20:09 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (len == posix_name_lengths[yield] &&
|
|
|
|
PRIV(strncmp_c8)(ptr, pn, (unsigned int)len) == 0) return yield;
|
|
|
|
pn += posix_name_lengths[yield] + 1;
|
|
|
|
yield++;
|
2015-11-08 15:20:09 +01:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
return -1;
|
|
|
|
}
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Read a subpattern or VERB name *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called from parse_regex() below whenever it needs to read
|
2018-09-24 18:23:53 +02:00
|
|
|
the name of a subpattern or a (*VERB) or an (*alpha_assertion). The initial
|
|
|
|
pointer must be to the character before the name. If that character is '*' we
|
|
|
|
are reading a verb or alpha assertion name. The pointer is updated to point
|
|
|
|
after the name, for a VERB or alpha assertion name, or after tha name's
|
2016-10-02 18:01:01 +02:00
|
|
|
terminator for a subpattern name. Returning both the offset and the name
|
|
|
|
pointer is redundant information, but some callers use one and some the other,
|
|
|
|
so it is simplest just to return both.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
ptrptr points to the character pointer variable
|
|
|
|
ptrend points to the end of the input string
|
|
|
|
terminator the terminator of a subpattern name must be this
|
|
|
|
offsetptr where to put the offset from the start of the pattern
|
|
|
|
nameptr where to put a pointer to the name in the input
|
|
|
|
namelenptr where to put the length of the name
|
|
|
|
errcodeptr where to put an error code
|
|
|
|
cb pointer to the compile data block
|
|
|
|
|
|
|
|
Returns: TRUE if a name was read
|
|
|
|
FALSE otherwise, with error code set
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
read_name(PCRE2_SPTR *ptrptr, PCRE2_SPTR ptrend, uint32_t terminator,
|
|
|
|
PCRE2_SIZE *offsetptr, PCRE2_SPTR *nameptr, uint32_t *namelenptr,
|
|
|
|
int *errorcodeptr, compile_block *cb)
|
|
|
|
{
|
|
|
|
PCRE2_SPTR ptr = *ptrptr;
|
2018-09-24 18:23:53 +02:00
|
|
|
BOOL is_group = (*ptr != CHAR_ASTERISK);
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t namelen = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
if (++ptr >= ptrend) /* No characters in name */
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2018-09-24 18:23:53 +02:00
|
|
|
*errorcodeptr = is_group? ERR62: /* Subpattern name expected */
|
|
|
|
ERR60; /* Verb not recognized or malformed */
|
2016-10-02 18:01:01 +02:00
|
|
|
goto FAILED;
|
|
|
|
}
|
2018-09-24 18:23:53 +02:00
|
|
|
|
|
|
|
/* A group name must not start with a digit. If either of the others start with
|
|
|
|
a digit it just won't be recognized. */
|
|
|
|
|
|
|
|
if (is_group && IS_DIGIT(*ptr))
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR44;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*nameptr = ptr;
|
|
|
|
*offsetptr = (PCRE2_SIZE)(ptr - cb->start_pattern);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
while (ptr < ptrend && MAX_255(*ptr) && (cb->ctypes[*ptr] & ctype_word) != 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
ptr++;
|
|
|
|
namelen++;
|
|
|
|
if (namelen > MAX_NAME_SIZE)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR48;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Subpattern names must not be empty, and their terminator is checked here.
|
2018-09-24 18:23:53 +02:00
|
|
|
(What follows a verb or alpha assertion name is checked separately.) */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
if (is_group)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
if (namelen == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR62; /* Subpattern name expected */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
if (ptr >= ptrend || *ptr != (PCRE2_UCHAR)terminator)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR42;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
ptr++;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*namelenptr = namelen;
|
|
|
|
*ptrptr = ptr;
|
|
|
|
return TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
FAILED:
|
|
|
|
*ptrptr = ptr;
|
|
|
|
return FALSE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Manage callouts at start of cycle *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* At the start of a new item in parse_regex() we are able to record the
|
|
|
|
details of the previous item in a prior callout, and also to set up an
|
|
|
|
automatic callout if enabled. Avoid having two adjacent automatic callouts,
|
|
|
|
which would otherwise happen for items such as \Q that contribute nothing to
|
|
|
|
the parsed pattern.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
ptr current pattern pointer
|
|
|
|
pcalloutptr points to a pointer to previous callout, or NULL
|
2017-06-15 18:41:44 +02:00
|
|
|
auto_callout TRUE if auto_callouts are enabled
|
2016-10-02 18:01:01 +02:00
|
|
|
parsed_pattern the parsed pattern pointer
|
|
|
|
cb compile block
|
|
|
|
|
|
|
|
Returns: possibly updated parsed_pattern pointer.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static uint32_t *
|
2017-06-15 18:41:44 +02:00
|
|
|
manage_callouts(PCRE2_SPTR ptr, uint32_t **pcalloutptr, BOOL auto_callout,
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t *parsed_pattern, compile_block *cb)
|
|
|
|
{
|
|
|
|
uint32_t *previous_callout = *pcalloutptr;
|
|
|
|
|
2017-10-29 17:58:38 +01:00
|
|
|
if (previous_callout != NULL) previous_callout[2] = (uint32_t)(ptr -
|
2017-09-26 19:01:23 +02:00
|
|
|
cb->start_pattern - (PCRE2_SIZE)previous_callout[1]);
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
if (!auto_callout) previous_callout = NULL; else
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
if (previous_callout == NULL ||
|
|
|
|
previous_callout != parsed_pattern - 4 ||
|
|
|
|
previous_callout[3] != 255)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
previous_callout = parsed_pattern; /* Set up new automatic callout */
|
|
|
|
parsed_pattern += 4;
|
|
|
|
previous_callout[0] = META_CALLOUT_NUMBER;
|
|
|
|
previous_callout[2] = 0;
|
|
|
|
previous_callout[3] = 255;
|
|
|
|
}
|
|
|
|
previous_callout[1] = (uint32_t)(ptr - cb->start_pattern);
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*pcalloutptr = previous_callout;
|
|
|
|
return parsed_pattern;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Parse regex and identify named groups *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called first of all. It scans the pattern and does two
|
|
|
|
things: (1) It identifies capturing groups and makes a table of named capturing
|
|
|
|
groups so that information about them is fully available to both the compiling
|
|
|
|
scans. (2) It writes a parsed version of the pattern with comments omitted and
|
|
|
|
escapes processed into the parsed_pattern vector.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
ptr points to the start of the pattern
|
|
|
|
options compiling dynamic options (may change during the scan)
|
|
|
|
has_lookbehind points to a boolean, set TRUE if a lookbehind is found
|
|
|
|
cb pointer to the compile data block
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: zero on success or a non-zero error code, with the
|
|
|
|
error offset placed in the cb field
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A structure and some flags for dealing with nested groups. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
typedef struct nest_save {
|
|
|
|
uint16_t nest_depth;
|
|
|
|
uint16_t reset_group;
|
|
|
|
uint16_t max_group;
|
|
|
|
uint16_t flags;
|
2017-05-17 19:55:11 +02:00
|
|
|
uint32_t options;
|
2016-10-02 18:01:01 +02:00
|
|
|
} nest_save;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-04-18 14:32:52 +02:00
|
|
|
#define NSF_RESET 0x0001u
|
|
|
|
#define NSF_CONDASSERT 0x0002u
|
|
|
|
|
2018-08-04 10:20:18 +02:00
|
|
|
/* Options that are changeable within the pattern must be tracked during
|
|
|
|
parsing. Some (e.g. PCRE2_EXTENDED) are implemented entirely during parsing,
|
|
|
|
but all must be tracked so that META_OPTIONS items set the correct values for
|
|
|
|
the main compiling phase. */
|
2017-04-18 14:32:52 +02:00
|
|
|
|
2018-08-04 10:20:18 +02:00
|
|
|
#define PARSE_TRACKED_OPTIONS (PCRE2_CASELESS|PCRE2_DOTALL|PCRE2_DUPNAMES| \
|
|
|
|
PCRE2_EXTENDED|PCRE2_EXTENDED_MORE|PCRE2_MULTILINE|PCRE2_NO_AUTO_CAPTURE| \
|
|
|
|
PCRE2_UNGREEDY)
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* States used for analyzing ranges in character classes. The two OK values
|
|
|
|
must be last. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
enum { RANGE_NO, RANGE_STARTED, RANGE_OK_ESCAPED, RANGE_OK_LITERAL };
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Only in 32-bit mode can there be literals > META_END. A macros encapsulates
|
|
|
|
the storing of literal values in the parsed pattern. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
#define PARSED_LITERAL(c, p) \
|
|
|
|
{ \
|
|
|
|
if (c >= META_END) *p++ = META_BIGVALUE; \
|
|
|
|
*p++ = c; \
|
|
|
|
okquantifier = TRUE; \
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
#define PARSED_LITERAL(c, p) *p++ = c; okquantifier = TRUE;
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Here's the actual function. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static int parse_regex(PCRE2_SPTR ptr, uint32_t options, BOOL *has_lookbehind,
|
|
|
|
compile_block *cb)
|
|
|
|
{
|
|
|
|
uint32_t c;
|
|
|
|
uint32_t delimiter;
|
|
|
|
uint32_t namelen;
|
|
|
|
uint32_t class_range_state;
|
|
|
|
uint32_t *verblengthptr = NULL; /* Value avoids compiler warning */
|
|
|
|
uint32_t *previous_callout = NULL;
|
|
|
|
uint32_t *parsed_pattern = cb->parsed_pattern;
|
2016-11-04 17:35:47 +01:00
|
|
|
uint32_t *parsed_pattern_end = cb->parsed_pattern_end;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t meta_quantifier = 0;
|
2018-07-21 16:34:51 +02:00
|
|
|
uint32_t add_after_mark = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint16_t nest_depth = 0;
|
|
|
|
int after_manual_callout = 0;
|
|
|
|
int expect_cond_assert = 0;
|
|
|
|
int errorcode = 0;
|
|
|
|
int escape;
|
|
|
|
int i;
|
|
|
|
BOOL inescq = FALSE;
|
|
|
|
BOOL inverbname = FALSE;
|
|
|
|
BOOL utf = (options & PCRE2_UTF) != 0;
|
2017-06-15 18:41:44 +02:00
|
|
|
BOOL auto_callout = (options & PCRE2_AUTO_CALLOUT) != 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
BOOL isdupname;
|
|
|
|
BOOL negate_class;
|
|
|
|
BOOL okquantifier = FALSE;
|
2017-06-15 18:41:44 +02:00
|
|
|
PCRE2_SPTR thisptr;
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SPTR name;
|
|
|
|
PCRE2_SPTR ptrend = cb->end_pattern;
|
2016-10-26 18:59:22 +02:00
|
|
|
PCRE2_SPTR verbnamestart = NULL; /* Value avoids compiler warning */
|
2016-10-02 18:01:01 +02:00
|
|
|
named_group *ng;
|
2017-06-15 18:41:44 +02:00
|
|
|
nest_save *top_nest, *end_nests;
|
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
/* Insert leading items for word and line matching (features provided for the
|
|
|
|
benefit of pcre2grep). */
|
|
|
|
|
|
|
|
if ((cb->cx->extra_options & PCRE2_EXTRA_MATCH_LINE) != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_CIRCUMFLEX;
|
|
|
|
*parsed_pattern++ = META_NOCAPTURE;
|
|
|
|
}
|
|
|
|
else if ((cb->cx->extra_options & PCRE2_EXTRA_MATCH_WORD) != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + ESC_b;
|
|
|
|
*parsed_pattern++ = META_NOCAPTURE;
|
|
|
|
}
|
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
/* If the pattern is actually a literal string, process it separately to avoid
|
|
|
|
cluttering up the main loop. */
|
|
|
|
|
|
|
|
if ((options & PCRE2_LITERAL) != 0)
|
|
|
|
{
|
|
|
|
while (ptr < ptrend)
|
|
|
|
{
|
|
|
|
if (parsed_pattern >= parsed_pattern_end)
|
|
|
|
{
|
|
|
|
errorcode = ERR63; /* Internal error (parsed pattern overflow) */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
thisptr = ptr;
|
|
|
|
GETCHARINCTEST(c, ptr);
|
|
|
|
if (auto_callout)
|
|
|
|
parsed_pattern = manage_callouts(thisptr, &previous_callout,
|
|
|
|
auto_callout, parsed_pattern, cb);
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
}
|
2017-06-16 19:51:13 +02:00
|
|
|
goto PARSED_END;
|
2017-06-15 18:41:44 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Process a real regex which may contain meta-characters. */
|
|
|
|
|
|
|
|
top_nest = NULL;
|
|
|
|
end_nests = (nest_save *)(cb->start_workspace + cb->workspace_size);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The size of the nest_save structure might not be a factor of the size of the
|
|
|
|
workspace. Therefore we must round down end_nests so as to correctly avoid
|
|
|
|
creating a nest_save that spans the end of the workspace. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
end_nests = (nest_save *)((char *)end_nests -
|
|
|
|
((cb->workspace_size * sizeof(PCRE2_UCHAR)) % sizeof(nest_save)));
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-04-18 14:32:52 +02:00
|
|
|
/* PCRE2_EXTENDED_MORE implies PCRE2_EXTENDED */
|
|
|
|
|
2017-05-17 19:55:11 +02:00
|
|
|
if ((options & PCRE2_EXTENDED_MORE) != 0) options |= PCRE2_EXTENDED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now scan the pattern */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
while (ptr < ptrend)
|
|
|
|
{
|
|
|
|
int prev_expect_cond_assert;
|
|
|
|
uint32_t min_repeat, max_repeat;
|
|
|
|
uint32_t set, unset, *optset;
|
|
|
|
uint32_t terminator;
|
|
|
|
uint32_t prev_meta_quantifier;
|
|
|
|
BOOL prev_okquantifier;
|
|
|
|
PCRE2_SPTR tempptr;
|
|
|
|
PCRE2_SIZE offset;
|
2016-11-18 19:59:37 +01:00
|
|
|
|
2016-11-04 17:35:47 +01:00
|
|
|
if (parsed_pattern >= parsed_pattern_end)
|
|
|
|
{
|
|
|
|
errorcode = ERR63; /* Internal error (parsed pattern overflow) */
|
2016-11-18 19:59:37 +01:00
|
|
|
goto FAILED;
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (nest_depth > cb->cx->parens_nest_limit)
|
|
|
|
{
|
|
|
|
errorcode = ERR19;
|
2017-06-15 18:41:44 +02:00
|
|
|
goto FAILED; /* Parentheses too deeply nested */
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Get next input character, save its position for callout handling. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
thisptr = ptr;
|
|
|
|
GETCHARINCTEST(c, ptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Copy quoted literals until \E, allowing for the possibility of automatic
|
2016-11-27 17:14:33 +01:00
|
|
|
callouts, except when processing a (*VERB) "name". */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (inescq)
|
|
|
|
{
|
|
|
|
if (c == CHAR_BACKSLASH && ptr < ptrend && *ptr == CHAR_E)
|
|
|
|
{
|
|
|
|
inescq = FALSE;
|
|
|
|
ptr++; /* Skip E */
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2016-12-28 13:26:12 +01:00
|
|
|
if (expect_cond_assert > 0) /* A literal is not allowed if we are */
|
|
|
|
{ /* expecting a conditional assertion, */
|
|
|
|
ptr--; /* but an empty \Q\E sequence is OK. */
|
|
|
|
errorcode = ERR28;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2016-11-27 17:14:33 +01:00
|
|
|
if (!inverbname && after_manual_callout-- <= 0)
|
2017-06-15 18:41:44 +02:00
|
|
|
parsed_pattern = manage_callouts(thisptr, &previous_callout,
|
|
|
|
auto_callout, parsed_pattern, cb);
|
2016-10-02 18:01:01 +02:00
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
2016-12-23 19:34:10 +01:00
|
|
|
meta_quantifier = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
continue; /* Next character */
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If we are processing the "name" part of a (*VERB:NAME) item, all
|
|
|
|
characters up to the closing parenthesis are literals except when
|
|
|
|
PCRE2_ALT_VERBNAMES is set. That causes backslash interpretation, but only \Q
|
|
|
|
and \E and escaped characters are allowed (no character types such as \d). If
|
|
|
|
PCRE2_EXTENDED is also set, we must ignore white space and # comments. Do
|
|
|
|
this by not entering the special (*VERB:NAME) processing - they are then
|
2016-10-27 19:42:14 +02:00
|
|
|
picked up below. Note that c is a character, not a code unit, so we must not
|
|
|
|
use MAX_255 to test its size because MAX_255 tests code units and is assumed
|
|
|
|
TRUE in 8-bit mode. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (inverbname &&
|
|
|
|
(
|
|
|
|
/* EITHER: not both options set */
|
|
|
|
((options & (PCRE2_EXTENDED | PCRE2_ALT_VERBNAMES)) !=
|
|
|
|
(PCRE2_EXTENDED | PCRE2_ALT_VERBNAMES)) ||
|
2018-08-04 10:20:18 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2018-08-03 11:38:36 +02:00
|
|
|
/* OR: character > 255 AND not Unicode Pattern White Space */
|
|
|
|
(c > 255 && (c|1) != 0x200f && (c|1) != 0x2029) ||
|
2018-08-04 10:20:18 +02:00
|
|
|
#endif
|
2018-08-03 11:38:36 +02:00
|
|
|
/* OR: not a # comment or isspace() white space */
|
|
|
|
(c < 256 && c != CHAR_NUMBER_SIGN && (cb->ctypes[c] & ctype_space) == 0
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
/* and not CHAR_NEL when Unicode is supported */
|
|
|
|
&& c != CHAR_NEL
|
2018-08-04 10:20:18 +02:00
|
|
|
#endif
|
2018-08-03 11:38:36 +02:00
|
|
|
)))
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
PCRE2_SIZE verbnamelength;
|
|
|
|
|
|
|
|
switch(c)
|
|
|
|
{
|
|
|
|
default:
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
break;
|
|
|
|
|
|
|
|
case CHAR_RIGHT_PARENTHESIS:
|
|
|
|
inverbname = FALSE;
|
2016-12-11 17:42:29 +01:00
|
|
|
okquantifier = FALSE; /* Was probably set by literals */
|
2016-10-26 18:59:22 +02:00
|
|
|
/* This is the length in characters */
|
2016-10-02 18:01:01 +02:00
|
|
|
verbnamelength = (PCRE2_SIZE)(parsed_pattern - verblengthptr - 1);
|
2016-10-26 18:59:22 +02:00
|
|
|
/* But the limit on the length is in code units */
|
2017-02-14 11:40:33 +01:00
|
|
|
if (ptr - verbnamestart - 1 > (int)MAX_MARK)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
ptr--;
|
|
|
|
errorcode = ERR76;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
*verblengthptr = (uint32_t)verbnamelength;
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
/* If this name was on a verb such as (*ACCEPT) which does not continue,
|
2018-07-28 18:23:24 +02:00
|
|
|
a (*MARK) was generated for the name. We now add the original verb as the
|
|
|
|
next item. */
|
2018-07-21 16:34:51 +02:00
|
|
|
|
|
|
|
if (add_after_mark != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = add_after_mark;
|
2018-07-28 18:23:24 +02:00
|
|
|
add_after_mark = 0;
|
2018-07-21 16:34:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case CHAR_BACKSLASH:
|
|
|
|
if ((options & PCRE2_ALT_VERBNAMES) != 0)
|
|
|
|
{
|
|
|
|
escape = PRIV(check_escape)(&ptr, ptrend, &c, &errorcode, options,
|
|
|
|
FALSE, cb);
|
|
|
|
if (errorcode != 0) goto FAILED;
|
|
|
|
}
|
|
|
|
else escape = 0; /* Treat all as literal */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(escape)
|
|
|
|
{
|
|
|
|
case 0:
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_Q:
|
|
|
|
inescq = TRUE;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_E: /* Ignore */
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
errorcode = ERR40; /* Invalid in verb name */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
continue; /* Next character in pattern */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-11 17:42:29 +01:00
|
|
|
/* Not a verb name character. At this point we must process everything that
|
|
|
|
must not change the quantification state. This is mainly comments, but we
|
|
|
|
handle \Q and \E here as well, so that an item such as A\Q\E+ is treated as
|
|
|
|
A+, as in Perl. An isolated \E is ignored. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_BACKSLASH && ptr < ptrend)
|
|
|
|
{
|
|
|
|
if (*ptr == CHAR_Q || *ptr == CHAR_E)
|
|
|
|
{
|
|
|
|
inescq = *ptr == CHAR_Q;
|
|
|
|
ptr++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-27 19:42:14 +02:00
|
|
|
/* Skip over whitespace and # comments in extended mode. Note that c is a
|
|
|
|
character, not a code unit, so we must not use MAX_255 to test its size
|
2018-08-03 11:38:36 +02:00
|
|
|
because MAX_255 tests code units and is assumed TRUE in 8-bit mode. The
|
|
|
|
whitespace characters are those designated as "Pattern White Space" by
|
2018-08-04 10:20:18 +02:00
|
|
|
Unicode, which are the isspace() characters plus CHAR_NEL (newline), which is
|
|
|
|
U+0085 in Unicode, plus U+200E, U+200F, U+2028, and U+2029. These are a
|
2018-08-03 11:38:36 +02:00
|
|
|
subset of space characters that match \h and \v. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((options & PCRE2_EXTENDED) != 0)
|
|
|
|
{
|
2016-10-27 19:42:14 +02:00
|
|
|
if (c < 256 && (cb->ctypes[c] & ctype_space) != 0) continue;
|
2018-08-04 10:20:18 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2018-08-03 11:38:36 +02:00
|
|
|
if (c == CHAR_NEL || (c|1) == 0x200f || (c|1) == 0x2029) continue;
|
2018-08-04 10:20:18 +02:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_NUMBER_SIGN)
|
|
|
|
{
|
|
|
|
while (ptr < ptrend)
|
|
|
|
{
|
|
|
|
if (IS_NEWLINE(ptr)) /* For non-fixed-length newline cases, */
|
|
|
|
{ /* IS_NEWLINE sets cb->nllen. */
|
|
|
|
ptr += cb->nllen;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
ptr++;
|
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-10-31 18:46:56 +01:00
|
|
|
if (utf) FORWARDCHARTEST(ptr, ptrend);
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
continue; /* Next character in pattern */
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Skip over bracketed comments */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_LEFT_PARENTHESIS && ptrend - ptr >= 2 &&
|
|
|
|
ptr[0] == CHAR_QUESTION_MARK && ptr[1] == CHAR_NUMBER_SIGN)
|
|
|
|
{
|
|
|
|
while (++ptr < ptrend && *ptr != CHAR_RIGHT_PARENTHESIS);
|
|
|
|
if (ptr >= ptrend)
|
|
|
|
{
|
|
|
|
errorcode = ERR18; /* A special error for missing ) in a comment */
|
|
|
|
goto FAILED; /* to make it easier to debug. */
|
|
|
|
}
|
|
|
|
ptr++;
|
|
|
|
continue; /* Next character in pattern */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the next item is not a quantifier, fill in length of any previous
|
|
|
|
callout and create an auto callout if required. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c != CHAR_ASTERISK && c != CHAR_PLUS && c != CHAR_QUESTION_MARK &&
|
|
|
|
(c != CHAR_LEFT_CURLY_BRACKET ||
|
|
|
|
(tempptr = ptr,
|
|
|
|
!read_repeat_counts(&tempptr, ptrend, NULL, NULL, &errorcode))))
|
|
|
|
{
|
|
|
|
if (after_manual_callout-- <= 0)
|
2017-06-15 18:41:44 +02:00
|
|
|
parsed_pattern = manage_callouts(thisptr, &previous_callout, auto_callout,
|
2016-10-02 18:01:01 +02:00
|
|
|
parsed_pattern, cb);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-11-18 19:59:37 +01:00
|
|
|
/* If expect_cond_assert is 2, we have just passed (?( and are expecting an
|
|
|
|
assertion, possibly preceded by a callout. If the value is 1, we have just
|
|
|
|
had the callout and expect an assertion. There must be at least 3 more
|
2016-12-23 19:34:10 +01:00
|
|
|
characters in all cases. When expect_cond_assert is 2, we know that the
|
|
|
|
current character is an opening parenthesis, as otherwise we wouldn't be
|
|
|
|
here. However, when it is 1, we need to check, and it's easiest just to check
|
|
|
|
always. Note that expect_cond_assert may be negative, since all callouts just
|
|
|
|
decrement it. */
|
2016-11-18 19:59:37 +01:00
|
|
|
|
|
|
|
if (expect_cond_assert > 0)
|
|
|
|
{
|
2016-12-23 19:34:10 +01:00
|
|
|
BOOL ok = c == CHAR_LEFT_PARENTHESIS && ptrend - ptr >= 3 &&
|
2018-09-24 18:23:53 +02:00
|
|
|
(ptr[0] == CHAR_QUESTION_MARK || ptr[0] == CHAR_ASTERISK);
|
|
|
|
if (ok)
|
2016-11-18 19:59:37 +01:00
|
|
|
{
|
2018-09-24 18:23:53 +02:00
|
|
|
if (ptr[0] == CHAR_ASTERISK) /* New alpha assertion format, possibly */
|
|
|
|
{
|
|
|
|
ok = MAX_255(ptr[1]) && (cb->ctypes[ptr[1]] & ctype_lcletter) != 0;
|
|
|
|
}
|
|
|
|
else switch(ptr[1]) /* Traditional symbolic format */
|
|
|
|
{
|
|
|
|
case CHAR_C:
|
|
|
|
ok = expect_cond_assert == 2;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case CHAR_EQUALS_SIGN:
|
|
|
|
case CHAR_EXCLAMATION_MARK:
|
|
|
|
break;
|
|
|
|
|
|
|
|
case CHAR_LESS_THAN_SIGN:
|
|
|
|
ok = ptr[2] == CHAR_EQUALS_SIGN || ptr[2] == CHAR_EXCLAMATION_MARK;
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
ok = FALSE;
|
|
|
|
}
|
|
|
|
}
|
2016-11-18 19:59:37 +01:00
|
|
|
|
|
|
|
if (!ok)
|
|
|
|
{
|
2016-11-22 16:37:02 +01:00
|
|
|
ptr--; /* Adjust error offset */
|
2016-11-18 19:59:37 +01:00
|
|
|
errorcode = ERR28;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember whether we are expecting a conditional assertion, and set the
|
|
|
|
default for this item. */
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
prev_expect_cond_assert = expect_cond_assert;
|
|
|
|
expect_cond_assert = 0;
|
2015-11-08 15:20:09 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember quantification status for the previous significant item, then set
|
|
|
|
default for this item. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
prev_okquantifier = okquantifier;
|
|
|
|
prev_meta_quantifier = meta_quantifier;
|
|
|
|
okquantifier = FALSE;
|
|
|
|
meta_quantifier = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the previous significant item was a quantifier, adjust the parsed code
|
|
|
|
if there is a following modifier. The base meta value is always followed by
|
|
|
|
the PLUS and QUERY values, in that order. We do this here rather than after
|
|
|
|
reading a quantifier so that intervening comments and /x whitespace can be
|
|
|
|
ignored without having to replicate code. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (prev_meta_quantifier != 0 && (c == CHAR_QUESTION_MARK || c == CHAR_PLUS))
|
|
|
|
{
|
|
|
|
parsed_pattern[(prev_meta_quantifier == META_MINMAX)? -3 : -1] =
|
|
|
|
prev_meta_quantifier + ((c == CHAR_QUESTION_MARK)?
|
|
|
|
0x00020000u : 0x00010000u);
|
|
|
|
continue; /* Next character in pattern */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process the next item in the main part of a pattern. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(c)
|
|
|
|
{
|
|
|
|
default: /* Non-special character */
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Escape sequence ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_BACKSLASH:
|
2017-06-01 20:10:15 +02:00
|
|
|
tempptr = ptr;
|
2016-10-02 18:01:01 +02:00
|
|
|
escape = PRIV(check_escape)(&ptr, ptrend, &c, &errorcode, options,
|
|
|
|
FALSE, cb);
|
2017-06-01 20:10:15 +02:00
|
|
|
if (errorcode != 0)
|
|
|
|
{
|
|
|
|
ESCAPE_FAILED:
|
|
|
|
if ((cb->cx->extra_options & PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL) == 0)
|
|
|
|
goto FAILED;
|
|
|
|
ptr = tempptr;
|
|
|
|
if (ptr >= ptrend) c = CHAR_BACKSLASH; else
|
2017-06-15 18:41:44 +02:00
|
|
|
{
|
2017-06-01 20:10:15 +02:00
|
|
|
GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
|
2017-06-15 18:41:44 +02:00
|
|
|
}
|
2017-06-01 20:10:15 +02:00
|
|
|
escape = 0; /* Treat as literal character */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-01 20:10:15 +02:00
|
|
|
/* The escape was a data escape or literal character. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (escape == 0)
|
|
|
|
{
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The escape was a back (or forward) reference. We keep the offset in
|
|
|
|
order to give a more useful diagnostic for a bad forward reference. For
|
|
|
|
references to groups numbered less than 10 we can't use more than two items
|
|
|
|
in parsed_pattern because they may be just two characters in the input (and
|
|
|
|
in a 64-bit world an offset may need two elements). So for them, the offset
|
|
|
|
of the first occurrent is held in a special vector. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (escape < 0)
|
|
|
|
{
|
|
|
|
offset = (PCRE2_SIZE)(ptr - cb->start_pattern - 1);
|
|
|
|
escape = -escape;
|
|
|
|
*parsed_pattern++ = META_BACKREF | (uint32_t)escape;
|
|
|
|
if (escape < 10)
|
|
|
|
{
|
|
|
|
if (cb->small_ref_offset[escape] == PCRE2_UNSET)
|
|
|
|
cb->small_ref_offset[escape] = offset;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
}
|
|
|
|
okquantifier = TRUE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The escape was a character class such as \d etc. or other special
|
|
|
|
escape indicator such as \A or \X. Most of them generate just a single
|
|
|
|
parsed item, but \P and \p are followed by a 16-bit type and a 16-bit
|
|
|
|
value. They are supported only when Unicode is available. The type and
|
|
|
|
value are packed into a single 32-bit value so that the whole sequences
|
|
|
|
uses only two elements in the parsed_vector. This is because the same
|
|
|
|
coding is used if \d (for example) is turned into \p{Nd} when PCRE2_UCP is
|
|
|
|
set.
|
|
|
|
|
|
|
|
There are also some cases where the escape sequence is followed by a name:
|
|
|
|
\k{name}, \k<name>, and \k'name' are backreferences by name, and \g<name>
|
|
|
|
and \g'name' are subroutine calls by name; \g{name} is a synonym for
|
|
|
|
\k{name}. Note that \g<number> and \g'number' are handled by check_escape()
|
|
|
|
and returned as a negative value (handled above). A name is coded as an
|
|
|
|
offset into the pattern and a length. */
|
|
|
|
|
|
|
|
else switch (escape)
|
|
|
|
{
|
|
|
|
case ESC_C:
|
|
|
|
#ifdef NEVER_BACKSLASH_C
|
|
|
|
errorcode = ERR85;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
#else
|
|
|
|
if ((options & PCRE2_NEVER_BACKSLASH_C) != 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR83;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
okquantifier = TRUE;
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
break;
|
2015-10-07 19:32:48 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_X:
|
|
|
|
#ifndef SUPPORT_UNICODE
|
|
|
|
errorcode = ERR45; /* Supported only with Unicode support */
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
|
|
|
case ESC_H:
|
|
|
|
case ESC_h:
|
|
|
|
case ESC_N:
|
|
|
|
case ESC_R:
|
|
|
|
case ESC_V:
|
|
|
|
case ESC_v:
|
|
|
|
okquantifier = TRUE;
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
break;
|
2015-10-21 13:29:07 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default: /* \A, \B, \b, \G, \K, \Z, \z cannot be quantified. */
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Escapes that change in UCP mode. Note that PCRE2_UCP will never be set
|
|
|
|
without Unicode support because it is checked when pcre2_compile() is
|
|
|
|
called. */
|
|
|
|
|
|
|
|
case ESC_d:
|
|
|
|
case ESC_D:
|
|
|
|
case ESC_s:
|
|
|
|
case ESC_S:
|
|
|
|
case ESC_w:
|
|
|
|
case ESC_W:
|
|
|
|
okquantifier = TRUE;
|
|
|
|
if ((options & PCRE2_UCP) == 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE +
|
|
|
|
((escape == ESC_d || escape == ESC_s || escape == ESC_w)?
|
|
|
|
ESC_p : ESC_P);
|
|
|
|
switch(escape)
|
|
|
|
{
|
|
|
|
case ESC_d:
|
|
|
|
case ESC_D:
|
|
|
|
*parsed_pattern++ = (PT_PC << 16) | ucp_Nd;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_s:
|
|
|
|
case ESC_S:
|
|
|
|
*parsed_pattern++ = PT_SPACE << 16;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_w:
|
|
|
|
case ESC_W:
|
|
|
|
*parsed_pattern++ = PT_WORD << 16;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
2015-10-21 13:29:07 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Unicode property matching */
|
2015-10-21 13:29:07 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_P:
|
|
|
|
case ESC_p:
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
{
|
|
|
|
BOOL negated;
|
|
|
|
uint16_t ptype = 0, pdata = 0;
|
|
|
|
if (!get_ucp(&ptr, &negated, &ptype, &pdata, &errorcode, cb))
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (negated) escape = (escape == ESC_P)? ESC_p : ESC_P;
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
*parsed_pattern++ = (ptype << 16) | pdata;
|
|
|
|
okquantifier = TRUE;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
errorcode = ERR45;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
|
|
|
break; /* End \P and \p */
|
|
|
|
|
|
|
|
/* When \g is used with quotes or angle brackets as delimiters, it is a
|
|
|
|
numerical or named subroutine call, and control comes here. When used
|
|
|
|
with brace delimiters it is a numberical back reference and does not come
|
|
|
|
here because check_escape() returns it directly as a reference. \k is
|
|
|
|
always a named back reference. */
|
|
|
|
|
|
|
|
case ESC_g:
|
|
|
|
case ESC_k:
|
|
|
|
if (ptr >= ptrend || (*ptr != CHAR_LEFT_CURLY_BRACKET &&
|
|
|
|
*ptr != CHAR_LESS_THAN_SIGN && *ptr != CHAR_APOSTROPHE))
|
|
|
|
{
|
|
|
|
errorcode = (escape == ESC_g)? ERR57 : ERR69;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
terminator = (*ptr == CHAR_LESS_THAN_SIGN)?
|
|
|
|
CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)?
|
|
|
|
CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For a non-braced \g, check for a numerical recursion. */
|
2015-10-07 19:32:48 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (escape == ESC_g && terminator != CHAR_RIGHT_CURLY_BRACKET)
|
|
|
|
{
|
|
|
|
PCRE2_SPTR p = ptr + 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (read_number(&p, ptrend, cb->bracount, MAX_GROUP_NUMBER, ERR61, &i,
|
|
|
|
&errorcode))
|
|
|
|
{
|
2016-11-04 12:05:21 +01:00
|
|
|
if (p >= ptrend || *p != terminator)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
errorcode = ERR57;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
ptr = p;
|
|
|
|
goto SET_RECURSION;
|
|
|
|
}
|
2017-06-01 20:10:15 +02:00
|
|
|
if (errorcode != 0) goto ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Not a numerical recursion */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
|
2017-06-01 20:10:15 +02:00
|
|
|
&errorcode, cb)) goto ESCAPE_FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* \k and \g when used with braces are back references, whereas \g used
|
|
|
|
with quotes or angle brackets is a recursion */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ =
|
|
|
|
(escape == ESC_k || terminator == CHAR_RIGHT_CURLY_BRACKET)?
|
|
|
|
META_BACKREF_BYNAME : META_RECURSE_BYNAME;
|
|
|
|
*parsed_pattern++ = namelen;
|
2015-10-09 18:06:53 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
okquantifier = TRUE;
|
2017-06-01 20:10:15 +02:00
|
|
|
break; /* End special escape processing */
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
break; /* End escape sequence processing */
|
2015-10-07 19:32:48 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Single-character special items ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_CIRCUMFLEX_ACCENT:
|
|
|
|
*parsed_pattern++ = META_CIRCUMFLEX;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_DOLLAR_SIGN:
|
|
|
|
*parsed_pattern++ = META_DOLLAR;
|
|
|
|
break;
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_DOT:
|
|
|
|
*parsed_pattern++ = META_DOT;
|
|
|
|
okquantifier = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Single-character quantifiers ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_ASTERISK:
|
|
|
|
meta_quantifier = META_ASTERISK;
|
|
|
|
goto CHECK_QUANTIFIER;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_PLUS:
|
|
|
|
meta_quantifier = META_PLUS;
|
|
|
|
goto CHECK_QUANTIFIER;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_QUESTION_MARK:
|
|
|
|
meta_quantifier = META_QUERY;
|
|
|
|
goto CHECK_QUANTIFIER;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* ---- Potential {n,m} quantifier ---- */
|
|
|
|
|
|
|
|
case CHAR_LEFT_CURLY_BRACKET:
|
|
|
|
if (!read_repeat_counts(&ptr, ptrend, &min_repeat, &max_repeat,
|
|
|
|
&errorcode))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (errorcode != 0) goto FAILED; /* Error in quantifier. */
|
|
|
|
PARSED_LITERAL(c, parsed_pattern); /* Not a quantifier */
|
|
|
|
break; /* No more quantifier processing */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
meta_quantifier = META_MINMAX;
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
|
|
|
|
/* ---- Quantifier post-processing ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check that a quantifier is allowed after the previous item. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
CHECK_QUANTIFIER:
|
|
|
|
if (!prev_okquantifier)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = ERR9;
|
|
|
|
goto FAILED_BACK;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now we can put the quantifier into the parsed pattern vector. At this
|
|
|
|
stage, we have only the basic quantifier. The check for a following + or ?
|
|
|
|
modifier happens at the top of the loop, after any intervening comments
|
|
|
|
have been removed. */
|
|
|
|
|
|
|
|
*parsed_pattern++ = meta_quantifier;
|
|
|
|
if (c == CHAR_LEFT_CURLY_BRACKET)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = min_repeat;
|
|
|
|
*parsed_pattern++ = max_repeat;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
|
|
/* ---- Character class ---- */
|
|
|
|
|
|
|
|
case CHAR_LEFT_SQUARE_BRACKET:
|
|
|
|
okquantifier = TRUE;
|
|
|
|
|
|
|
|
/* In another (POSIX) regex library, the ugly syntax [[:<:]] and [[:>:]] is
|
|
|
|
used for "start of word" and "end of word". As these are otherwise illegal
|
|
|
|
sequences, we don't break anything by recognizing them. They are replaced
|
|
|
|
by \b(?=\w) and \b(?<=\w) respectively. Sequences like [a[:<:]] are
|
|
|
|
erroneous and are handled by the normal code below. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptrend - ptr >= 6 &&
|
|
|
|
(PRIV(strncmp_c8)(ptr, STRING_WEIRD_STARTWORD, 6) == 0 ||
|
|
|
|
PRIV(strncmp_c8)(ptr, STRING_WEIRD_ENDWORD, 6) == 0))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_ESCAPE + ESC_b;
|
|
|
|
|
|
|
|
if (ptr[2] == CHAR_LESS_THAN_SIGN)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_LOOKAHEAD;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_LOOKBEHIND;
|
|
|
|
*has_lookbehind = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The offset is used only for the "non-fixed length" error; this won't
|
|
|
|
occur here, so just store zero. */
|
|
|
|
|
|
|
|
PUTOFFSET((PCRE2_SIZE)0, parsed_pattern);
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((options & PCRE2_UCP) == 0)
|
|
|
|
*parsed_pattern++ = META_ESCAPE + ESC_w;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + ESC_p;
|
|
|
|
*parsed_pattern++ = PT_WORD << 16;
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = META_KET;
|
|
|
|
ptr += 6;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* PCRE supports POSIX class stuff inside a class. Perl gives an error if
|
|
|
|
they are encountered at the top level, so we'll do that too. */
|
|
|
|
|
|
|
|
if (ptr < ptrend && (*ptr == CHAR_COLON || *ptr == CHAR_DOT ||
|
|
|
|
*ptr == CHAR_EQUALS_SIGN) &&
|
|
|
|
check_posix_syntax(ptr, ptrend, &tempptr))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = (*ptr-- == CHAR_COLON)? ERR12 : ERR13;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process a regular character class. If the first character is '^', set
|
|
|
|
the negation flag. If the first few characters (either before or after ^)
|
2017-04-18 14:32:52 +02:00
|
|
|
are \Q\E or \E or space or tab in extended-more mode, we skip them too.
|
|
|
|
This makes for compatibility with Perl. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
negate_class = FALSE;
|
|
|
|
while (ptr < ptrend)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
GETCHARINCTEST(c, ptr);
|
|
|
|
if (c == CHAR_BACKSLASH)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr < ptrend && *ptr == CHAR_E) ptr++;
|
|
|
|
else if (ptrend - ptr >= 3 &&
|
|
|
|
PRIV(strncmp_c8)(ptr, STR_Q STR_BACKSLASH STR_E, 3) == 0)
|
|
|
|
ptr += 3;
|
|
|
|
else
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2017-04-18 14:32:52 +02:00
|
|
|
else if ((options & PCRE2_EXTENDED_MORE) != 0 &&
|
|
|
|
(c == CHAR_SPACE || c == CHAR_HT)) /* Note: just these two */
|
|
|
|
continue;
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT)
|
|
|
|
negate_class = TRUE;
|
|
|
|
else break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now the real contents of the class; c has the first "real" character.
|
|
|
|
Empty classes are permitted only if the option is set. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_RIGHT_SQUARE_BRACKET &&
|
|
|
|
(cb->external_options & PCRE2_ALLOW_EMPTY_CLASS) != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = negate_class? META_CLASS_EMPTY_NOT : META_CLASS_EMPTY;
|
|
|
|
break; /* End of class processing */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process a non-empty class. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = negate_class? META_CLASS_NOT : META_CLASS;
|
|
|
|
class_range_state = RANGE_NO;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In an EBCDIC environment, Perl treats alphabetic ranges specially
|
|
|
|
because there are holes in the encoding, and simply using the range A-Z
|
|
|
|
(for example) would include the characters in the holes. This applies only
|
|
|
|
to ranges where both values are literal; [\xC1-\xE9] is different to [A-Z]
|
|
|
|
in this respect. In order to accommodate this, we keep track of whether
|
|
|
|
character values are literal or not, and a state variable for handling
|
|
|
|
ranges. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Loop for the contents of the class */
|
|
|
|
|
|
|
|
for (;;)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
BOOL char_is_literal = TRUE;
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Inside \Q...\E everything is literal except \E */
|
|
|
|
|
|
|
|
if (inescq)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == CHAR_BACKSLASH && ptr < ptrend && *ptr == CHAR_E)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
inescq = FALSE; /* Reset literal state */
|
|
|
|
ptr++; /* Skip the 'E' */
|
|
|
|
goto CLASS_CONTINUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
goto CLASS_LITERAL;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-04-18 14:32:52 +02:00
|
|
|
/* Skip over space and tab (only) in extended-more mode. */
|
2017-05-17 19:55:11 +02:00
|
|
|
|
|
|
|
if ((options & PCRE2_EXTENDED_MORE) != 0 &&
|
|
|
|
(c == CHAR_SPACE || c == CHAR_HT))
|
2017-04-18 14:32:52 +02:00
|
|
|
goto CLASS_CONTINUE;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Handle POSIX class names. Perl allows a negation extension of the
|
|
|
|
form [:^name:]. A square bracket that doesn't match the syntax is
|
|
|
|
treated as a literal. We also recognize the POSIX constructions
|
|
|
|
[.ch.] and [=ch=] ("collating elements") and fault them, as Perl
|
|
|
|
5.6 and 5.8 do. */
|
|
|
|
|
|
|
|
if (c == CHAR_LEFT_SQUARE_BRACKET &&
|
|
|
|
ptrend - ptr >= 3 &&
|
|
|
|
(*ptr == CHAR_COLON || *ptr == CHAR_DOT ||
|
|
|
|
*ptr == CHAR_EQUALS_SIGN) &&
|
|
|
|
check_posix_syntax(ptr, ptrend, &tempptr))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
BOOL posix_negate = FALSE;
|
|
|
|
int posix_class;
|
|
|
|
|
|
|
|
/* Perl treats a hyphen before a POSIX class as a literal, not the
|
|
|
|
start of a range. However, it gives a warning in its warning mode. PCRE
|
|
|
|
does not have a warning mode, so we give an error, because this is
|
|
|
|
likely an error on the user's part. */
|
|
|
|
|
|
|
|
if (class_range_state == RANGE_STARTED)
|
|
|
|
{
|
|
|
|
errorcode = ERR50;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (*ptr != CHAR_COLON)
|
|
|
|
{
|
|
|
|
errorcode = ERR13;
|
|
|
|
goto FAILED_BACK;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (*(++ptr) == CHAR_CIRCUMFLEX_ACCENT)
|
|
|
|
{
|
|
|
|
posix_negate = TRUE;
|
|
|
|
ptr++;
|
|
|
|
}
|
|
|
|
|
|
|
|
posix_class = check_posix_name(ptr, (int)(tempptr - ptr));
|
|
|
|
if (posix_class < 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR30;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
ptr = tempptr + 2;
|
2016-12-28 13:26:12 +01:00
|
|
|
|
2016-12-27 12:50:28 +01:00
|
|
|
/* Perl treats a hyphen after a POSIX class as a literal, not the
|
2017-07-29 17:54:04 +02:00
|
|
|
start of a range. However, it gives a warning in its warning mode
|
|
|
|
unless the hyphen is the last character in the class. PCRE does not
|
|
|
|
have a warning mode, so we give an error, because this is likely an
|
|
|
|
error on the user's part. */
|
2016-12-28 13:26:12 +01:00
|
|
|
|
2017-07-29 17:54:04 +02:00
|
|
|
if (ptr < ptrend - 1 && *ptr == CHAR_MINUS &&
|
|
|
|
ptr[1] != CHAR_RIGHT_SQUARE_BRACKET)
|
2016-12-27 12:50:28 +01:00
|
|
|
{
|
|
|
|
errorcode = ERR50;
|
|
|
|
goto FAILED;
|
2016-12-28 13:26:12 +01:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2017-07-29 17:54:04 +02:00
|
|
|
/* Set "a hyphen is not the start of a range" for the -] case, and also
|
|
|
|
in case the POSIX class is followed by \E or \Q\E (possibly repeated -
|
|
|
|
fuzzers do that kind of thing) and *then* a hyphen. This causes that
|
|
|
|
hyphen to be treated as a literal. I don't think it's worth setting up
|
|
|
|
special apparatus to do otherwise. */
|
2017-01-11 17:40:35 +01:00
|
|
|
|
|
|
|
class_range_state = RANGE_NO;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* When PCRE2_UCP is set, some of the POSIX classes are converted to
|
|
|
|
use Unicode properties \p or \P or, in one case, \h or \H. The
|
|
|
|
substitutes table has two values per class, containing the type and
|
|
|
|
value of a \p or \P item. The special cases are specified with a
|
|
|
|
negative type: a non-zero value causes \h or \H to be used, and a zero
|
|
|
|
value falls through to behave like a non-UCP POSIX class. */
|
|
|
|
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if ((options & PCRE2_UCP) != 0)
|
|
|
|
{
|
|
|
|
int ptype = posix_substitutes[2*posix_class];
|
|
|
|
int pvalue = posix_substitutes[2*posix_class + 1];
|
|
|
|
if (ptype >= 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + (posix_negate? ESC_P : ESC_p);
|
|
|
|
*parsed_pattern++ = (ptype << 16) | pvalue;
|
|
|
|
goto CLASS_CONTINUE;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (pvalue != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + (posix_negate? ESC_H : ESC_h);
|
|
|
|
goto CLASS_CONTINUE;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Fall through */
|
|
|
|
}
|
|
|
|
#endif /* SUPPORT_UNICODE */
|
|
|
|
|
|
|
|
/* Non-UCP POSIX class */
|
|
|
|
|
|
|
|
*parsed_pattern++ = posix_negate? META_POSIX_NEG : META_POSIX;
|
|
|
|
*parsed_pattern++ = posix_class;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2015-05-06 18:51:25 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle potential start of range */
|
2015-05-06 18:51:25 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (c == CHAR_MINUS && class_range_state >= RANGE_OK_ESCAPED)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = (class_range_state == RANGE_OK_LITERAL)?
|
|
|
|
META_RANGE_LITERAL : META_RANGE_ESCAPED;
|
|
|
|
class_range_state = RANGE_STARTED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a literal character */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (c != CHAR_BACKSLASH)
|
|
|
|
{
|
|
|
|
CLASS_LITERAL:
|
|
|
|
if (class_range_state == RANGE_STARTED)
|
|
|
|
{
|
|
|
|
if (c == parsed_pattern[-2]) /* Optimize one-char range */
|
|
|
|
parsed_pattern--;
|
|
|
|
else if (parsed_pattern[-2] > c) /* Check range is in order */
|
|
|
|
{
|
|
|
|
errorcode = ERR8;
|
|
|
|
goto FAILED_BACK;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (!char_is_literal && parsed_pattern[-1] == META_RANGE_LITERAL)
|
|
|
|
parsed_pattern[-1] = META_RANGE_ESCAPED;
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
}
|
|
|
|
class_range_state = RANGE_NO;
|
|
|
|
}
|
|
|
|
else /* Potential start of range */
|
|
|
|
{
|
|
|
|
class_range_state = char_is_literal?
|
|
|
|
RANGE_OK_LITERAL : RANGE_OK_ESCAPED;
|
|
|
|
PARSED_LITERAL(c, parsed_pattern);
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle escapes in a class */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
2017-06-15 18:41:44 +02:00
|
|
|
tempptr = ptr;
|
2016-10-02 18:01:01 +02:00
|
|
|
escape = PRIV(check_escape)(&ptr, ptrend, &c, &errorcode,
|
|
|
|
options, TRUE, cb);
|
2017-06-01 20:10:15 +02:00
|
|
|
if (errorcode != 0)
|
|
|
|
{
|
|
|
|
CLASS_ESCAPE_FAILED:
|
|
|
|
if ((cb->cx->extra_options & PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL) == 0)
|
|
|
|
goto FAILED;
|
|
|
|
ptr = tempptr;
|
|
|
|
if (ptr >= ptrend) c = CHAR_BACKSLASH; else
|
2017-06-15 18:41:44 +02:00
|
|
|
{
|
2017-06-01 20:10:15 +02:00
|
|
|
GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
|
2017-06-15 18:41:44 +02:00
|
|
|
}
|
2017-06-01 20:10:15 +02:00
|
|
|
escape = 0; /* Treat as literal character */
|
|
|
|
}
|
2017-06-15 18:41:44 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (escape == 0) /* Escaped character code point is in c */
|
|
|
|
{
|
|
|
|
char_is_literal = FALSE;
|
|
|
|
goto CLASS_LITERAL;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* These three escapes do not alter the class range state. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (escape == ESC_b)
|
|
|
|
{
|
|
|
|
c = CHAR_BS; /* \b is backspace in a class */
|
|
|
|
char_is_literal = FALSE;
|
|
|
|
goto CLASS_LITERAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (escape == ESC_Q)
|
|
|
|
{
|
|
|
|
inescq = TRUE; /* Enter literal mode */
|
|
|
|
goto CLASS_CONTINUE;
|
|
|
|
}
|
|
|
|
|
|
|
|
else if (escape == ESC_E) /* Ignore orphan \E */
|
|
|
|
goto CLASS_CONTINUE;
|
|
|
|
|
|
|
|
/* The second part of a range can be a single-character escape
|
|
|
|
sequence (detected above), but not any of the other escapes. Perl
|
|
|
|
treats a hyphen as a literal in such circumstances. However, in Perl's
|
|
|
|
warning mode, a warning is given, so PCRE now faults it, as it is
|
|
|
|
almost certainly a mistake on the user's part. */
|
|
|
|
|
|
|
|
if (class_range_state == RANGE_STARTED)
|
|
|
|
{
|
|
|
|
errorcode = ERR50;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto CLASS_ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Of the remaining escapes, only those that define characters are
|
|
|
|
allowed in a class. None may start a range. */
|
|
|
|
|
|
|
|
class_range_state = RANGE_NO;
|
|
|
|
switch(escape)
|
|
|
|
{
|
|
|
|
case ESC_N:
|
|
|
|
errorcode = ERR71; /* Not supported in a class */
|
2017-06-01 20:10:15 +02:00
|
|
|
goto CLASS_ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
case ESC_H:
|
|
|
|
case ESC_h:
|
|
|
|
case ESC_V:
|
|
|
|
case ESC_v:
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* These escapes are converted to Unicode property tests when
|
|
|
|
PCRE2_UCP is set. */
|
|
|
|
|
|
|
|
case ESC_d:
|
|
|
|
case ESC_D:
|
|
|
|
case ESC_s:
|
|
|
|
case ESC_S:
|
|
|
|
case ESC_w:
|
|
|
|
case ESC_W:
|
|
|
|
if ((options & PCRE2_UCP) == 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_ESCAPE +
|
|
|
|
((escape == ESC_d || escape == ESC_s || escape == ESC_w)?
|
|
|
|
ESC_p : ESC_P);
|
|
|
|
switch(escape)
|
|
|
|
{
|
|
|
|
case ESC_d:
|
|
|
|
case ESC_D:
|
|
|
|
*parsed_pattern++ = (PT_PC << 16) | ucp_Nd;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case ESC_s:
|
|
|
|
case ESC_S:
|
|
|
|
*parsed_pattern++ = PT_SPACE << 16;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case ESC_w:
|
|
|
|
case ESC_W:
|
|
|
|
*parsed_pattern++ = PT_WORD << 16;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* Explicit Unicode property matching */
|
|
|
|
|
|
|
|
case ESC_P:
|
|
|
|
case ESC_p:
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
{
|
|
|
|
BOOL negated;
|
|
|
|
uint16_t ptype = 0, pdata = 0;
|
|
|
|
if (!get_ucp(&ptr, &negated, &ptype, &pdata, &errorcode, cb))
|
|
|
|
goto FAILED;
|
|
|
|
if (negated) escape = (escape == ESC_P)? ESC_p : ESC_P;
|
|
|
|
*parsed_pattern++ = META_ESCAPE + escape;
|
|
|
|
*parsed_pattern++ = (ptype << 16) | pdata;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
errorcode = ERR45;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto CLASS_ESCAPE_FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
break; /* End \P and \p */
|
|
|
|
|
|
|
|
default: /* All others are not allowed in a class */
|
|
|
|
errorcode = ERR7;
|
2017-06-15 18:41:44 +02:00
|
|
|
ptr--;
|
2017-06-01 20:10:15 +02:00
|
|
|
goto CLASS_ESCAPE_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2017-07-29 17:54:04 +02:00
|
|
|
|
|
|
|
/* Perl gives a warning unless a following hyphen is the last character
|
|
|
|
in the class. PCRE throws an error. */
|
|
|
|
|
|
|
|
if (ptr < ptrend - 1 && *ptr == CHAR_MINUS &&
|
|
|
|
ptr[1] != CHAR_RIGHT_SQUARE_BRACKET)
|
|
|
|
{
|
|
|
|
errorcode = ERR50;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Proceed to next thing in the class. */
|
|
|
|
|
|
|
|
CLASS_CONTINUE:
|
|
|
|
if (ptr >= ptrend)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = ERR6; /* Missing terminating ']' */
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
GETCHARINCTEST(c, ptr);
|
|
|
|
if (c == CHAR_RIGHT_SQUARE_BRACKET && !inescq) break;
|
|
|
|
} /* End of class-processing loop */
|
|
|
|
|
|
|
|
if (class_range_state == RANGE_STARTED)
|
|
|
|
{
|
|
|
|
parsed_pattern[-1] = CHAR_MINUS;
|
|
|
|
class_range_state = RANGE_NO;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_CLASS_END;
|
|
|
|
break; /* End of character class */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Opening parenthesis ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_LEFT_PARENTHESIS:
|
|
|
|
if (ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* If ( is not followed by ? it is either a capture or a special verb or an
|
|
|
|
alpha assertion. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (*ptr != CHAR_QUESTION_MARK)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
const char *vn;
|
|
|
|
|
|
|
|
/* Handle capturing brackets (or non-capturing if auto-capture is turned
|
|
|
|
off). */
|
|
|
|
|
|
|
|
if (*ptr != CHAR_ASTERISK)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
nest_depth++;
|
|
|
|
if ((options & PCRE2_NO_AUTO_CAPTURE) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->bracount++;
|
|
|
|
*parsed_pattern++ = META_CAPTURE | cb->bracount;
|
2014-08-08 17:36:18 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
else *parsed_pattern++ = META_NOCAPTURE;
|
|
|
|
}
|
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* Do nothing for (* followed by end of pattern or ) so it gives a "bad
|
|
|
|
quantifier" error rather than "(*MARK) must have an argument". */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
else if (ptrend - ptr <= 1 || (c = ptr[1]) == CHAR_RIGHT_PARENTHESIS)
|
|
|
|
break;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* Handle "alpha assertions" such as (*pla:...). Most of these are
|
|
|
|
synonyms for the historical symbolic assertions, but the script run ones
|
|
|
|
are new. They are distinguished by starting with a lower case letter.
|
|
|
|
Checking both ends of the alphabet makes this work in all character
|
|
|
|
codes. */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
else if (CHMAX_255(c) && (cb->ctypes[c] & ctype_lcletter) != 0)
|
|
|
|
{
|
|
|
|
uint32_t meta;
|
|
|
|
|
|
|
|
vn = alasnames;
|
|
|
|
if (!read_name(&ptr, ptrend, 0, &offset, &name, &namelen, &errorcode,
|
|
|
|
cb)) goto FAILED;
|
|
|
|
if (ptr >= ptrend || *ptr != CHAR_COLON)
|
|
|
|
{
|
|
|
|
errorcode = ERR95; /* Malformed */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Scan the table of alpha assertion names */
|
|
|
|
|
|
|
|
for (i = 0; i < alascount; i++)
|
|
|
|
{
|
|
|
|
if (namelen == alasmeta[i].len &&
|
|
|
|
PRIV(strncmp_c8)(name, vn, namelen) == 0)
|
|
|
|
break;
|
|
|
|
vn += alasmeta[i].len + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (i >= alascount)
|
|
|
|
{
|
|
|
|
errorcode = ERR95; /* Alpha assertion not recognized */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Check for expecting an assertion condition. If so, only lookaround
|
|
|
|
assertions are valid. */
|
|
|
|
|
|
|
|
meta = alasmeta[i].meta;
|
|
|
|
if (prev_expect_cond_assert > 0 &&
|
|
|
|
(meta < META_LOOKAHEAD || meta > META_LOOKBEHINDNOT))
|
|
|
|
{
|
|
|
|
errorcode = ERR28; /* Assertion expected */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch(meta)
|
|
|
|
{
|
|
|
|
case META_ATOMIC:
|
|
|
|
goto ATOMIC_GROUP;
|
|
|
|
|
|
|
|
case META_LOOKAHEAD:
|
|
|
|
goto POSITIVE_LOOK_AHEAD;
|
|
|
|
|
|
|
|
case META_LOOKAHEADNOT:
|
|
|
|
goto NEGATIVE_LOOK_AHEAD;
|
|
|
|
|
|
|
|
case META_LOOKBEHIND:
|
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
*parsed_pattern++ = meta;
|
|
|
|
ptr--;
|
|
|
|
goto LOOKBEHIND;
|
|
|
|
|
|
|
|
/* FIXME: Script Run stuff ... */
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* ---- Handle (*VERB) and (*VERB:NAME) ---- */
|
|
|
|
|
|
|
|
else
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
vn = verbnames;
|
|
|
|
if (!read_name(&ptr, ptrend, 0, &offset, &name, &namelen, &errorcode,
|
|
|
|
cb)) goto FAILED;
|
|
|
|
if (ptr >= ptrend || (*ptr != CHAR_COLON &&
|
|
|
|
*ptr != CHAR_RIGHT_PARENTHESIS))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = ERR60; /* Malformed */
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Scan the table of verb names */
|
|
|
|
|
|
|
|
for (i = 0; i < verbcount; i++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (namelen == verbs[i].len &&
|
|
|
|
PRIV(strncmp_c8)(name, vn, namelen) == 0)
|
|
|
|
break;
|
|
|
|
vn += verbs[i].len + 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (i >= verbcount)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = ERR60; /* Verb not recognized */
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* An empty argument is treated as no argument. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr == CHAR_COLON && ptr + 1 < ptrend &&
|
|
|
|
ptr[1] == CHAR_RIGHT_PARENTHESIS)
|
|
|
|
ptr++; /* Advance to the closing parens */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check for mandatory non-empty argument; this is (*MARK) */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (verbs[i].has_arg > 0 && *ptr != CHAR_COLON)
|
|
|
|
{
|
|
|
|
errorcode = ERR66;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* It appears that Perl allows any characters whatsoever, other than a
|
|
|
|
closing parenthesis, to appear in arguments ("names"), so we no longer
|
|
|
|
insist on letters, digits, and underscores. Perl does not, however, do
|
|
|
|
any interpretation within arguments, and has no means of including a
|
|
|
|
closing parenthesis. PCRE supports escape processing but only when it
|
|
|
|
is requested by an option. We set inverbname TRUE here, and let the
|
|
|
|
main loop take care of this so that escape and \x processing is done by
|
|
|
|
the main code above. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr++ == CHAR_COLON) /* Skip past : or ) */
|
|
|
|
{
|
2018-07-21 16:34:51 +02:00
|
|
|
/* Some optional arguments can be treated as a preceding (*MARK) */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
if (verbs[i].has_arg < 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2018-07-21 16:34:51 +02:00
|
|
|
add_after_mark = verbs[i].meta;
|
2018-07-28 18:23:24 +02:00
|
|
|
*parsed_pattern++ = META_MARK;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
/* The remaining verbs with arguments (except *MARK) need a different
|
|
|
|
opcode. */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
else
|
2018-07-28 18:23:24 +02:00
|
|
|
{
|
2018-07-21 16:34:51 +02:00
|
|
|
*parsed_pattern++ = verbs[i].meta +
|
|
|
|
((verbs[i].meta != META_MARK)? 0x00010000u:0);
|
2018-07-28 18:23:24 +02:00
|
|
|
}
|
|
|
|
|
2018-07-21 16:34:51 +02:00
|
|
|
/* Set up for reading the name in the main loop. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
verblengthptr = parsed_pattern++;
|
2016-10-26 18:59:22 +02:00
|
|
|
verbnamestart = ptr;
|
2016-10-02 18:01:01 +02:00
|
|
|
inverbname = TRUE;
|
|
|
|
}
|
|
|
|
else /* No verb "name" argument */
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = verbs[i].meta;
|
|
|
|
}
|
|
|
|
} /* End of (*VERB) handling */
|
|
|
|
break; /* Done with this parenthesis */
|
|
|
|
} /* End of groups that don't start with (? */
|
2015-06-13 18:10:14 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Items starting (? ---- */
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The type of item is determined by what follows (?. Handle (?| and option
|
|
|
|
changes under "default" because both need a new block on the nest stack.
|
|
|
|
Comments starting with (?# are handled above. Note that there is some
|
|
|
|
ambiguity about the sequence (?- because if a digit follows it's a relative
|
|
|
|
recursion or subroutine call whereas otherwise it's an option unsetting. */
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (++ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(*ptr)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
if (*ptr == CHAR_MINUS && ptrend - ptr > 1 && IS_DIGIT(ptr[1]))
|
|
|
|
goto RECURSION_BYNUMBER; /* The + case is handled by CHAR_PLUS */
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* We now have either (?| or a (possibly empty) option setting,
|
|
|
|
optionally followed by a non-capturing group. */
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
nest_depth++;
|
|
|
|
if (top_nest == NULL) top_nest = (nest_save *)(cb->start_workspace);
|
|
|
|
else if (++top_nest >= end_nests)
|
2015-06-13 18:10:14 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
errorcode = ERR84;
|
|
|
|
goto FAILED;
|
2015-06-13 18:10:14 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
top_nest->nest_depth = nest_depth;
|
|
|
|
top_nest->flags = 0;
|
2017-04-18 14:32:52 +02:00
|
|
|
top_nest->options = options & PARSE_TRACKED_OPTIONS;
|
2015-06-13 18:10:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Start of non-capturing group that resets the capture count for each
|
|
|
|
branch. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr == CHAR_VERTICAL_LINE)
|
|
|
|
{
|
|
|
|
top_nest->reset_group = (uint16_t)cb->bracount;
|
|
|
|
top_nest->max_group = (uint16_t)cb->bracount;
|
|
|
|
top_nest->flags |= NSF_RESET;
|
|
|
|
cb->external_flags |= PCRE2_DUPCAPUSED;
|
|
|
|
*parsed_pattern++ = META_NOCAPTURE;
|
|
|
|
ptr++;
|
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-04-18 18:21:50 +02:00
|
|
|
/* Scan for options imnsxJU to be set or unset. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
2018-07-28 18:23:24 +02:00
|
|
|
BOOL hyphenok = TRUE;
|
2018-08-13 13:57:09 +02:00
|
|
|
uint32_t oldoptions = options;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
top_nest->reset_group = 0;
|
|
|
|
top_nest->max_group = 0;
|
|
|
|
set = unset = 0;
|
|
|
|
optset = &set;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-07-28 18:23:24 +02:00
|
|
|
/* ^ at the start unsets imnsx and disables the subsequent use of - */
|
|
|
|
|
|
|
|
if (ptr < ptrend && *ptr == CHAR_CIRCUMFLEX_ACCENT)
|
|
|
|
{
|
|
|
|
options &= ~(PCRE2_CASELESS|PCRE2_MULTILINE|PCRE2_NO_AUTO_CAPTURE|
|
|
|
|
PCRE2_DOTALL|PCRE2_EXTENDED|PCRE2_EXTENDED_MORE);
|
|
|
|
hyphenok = FALSE;
|
2018-08-04 10:20:18 +02:00
|
|
|
ptr++;
|
2018-07-28 18:23:24 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
while (ptr < ptrend && *ptr != CHAR_RIGHT_PARENTHESIS &&
|
|
|
|
*ptr != CHAR_COLON)
|
|
|
|
{
|
|
|
|
switch (*ptr++)
|
|
|
|
{
|
2018-07-28 18:23:24 +02:00
|
|
|
case CHAR_MINUS:
|
|
|
|
if (!hyphenok)
|
|
|
|
{
|
|
|
|
errorcode = ERR94;
|
|
|
|
ptr--; /* Correct the offset */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
optset = &unset;
|
2018-08-04 10:20:18 +02:00
|
|
|
hyphenok = FALSE;
|
2018-07-28 18:23:24 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_J: /* Record that it changed in the external options */
|
|
|
|
*optset |= PCRE2_DUPNAMES;
|
|
|
|
cb->external_flags |= PCRE2_JCHANGED;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_i: *optset |= PCRE2_CASELESS; break;
|
|
|
|
case CHAR_m: *optset |= PCRE2_MULTILINE; break;
|
2017-04-18 18:21:50 +02:00
|
|
|
case CHAR_n: *optset |= PCRE2_NO_AUTO_CAPTURE; break;
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_s: *optset |= PCRE2_DOTALL; break;
|
|
|
|
case CHAR_U: *optset |= PCRE2_UNGREEDY; break;
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-04-18 14:32:52 +02:00
|
|
|
/* If x appears twice it sets the extended extended option. */
|
2017-05-17 19:55:11 +02:00
|
|
|
|
|
|
|
case CHAR_x:
|
2017-07-25 17:27:30 +02:00
|
|
|
*optset |= PCRE2_EXTENDED;
|
|
|
|
if (ptr < ptrend && *ptr == CHAR_x)
|
|
|
|
{
|
|
|
|
*optset |= PCRE2_EXTENDED_MORE;
|
|
|
|
ptr++;
|
|
|
|
}
|
2017-04-18 14:32:52 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
errorcode = ERR11;
|
|
|
|
ptr--; /* Correct the offset */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
}
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-07-25 17:27:30 +02:00
|
|
|
/* If we are setting extended without extended-more, ensure that any
|
|
|
|
existing extended-more gets unset. Also, unsetting extended must also
|
|
|
|
unset extended-more. */
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-07-25 17:27:30 +02:00
|
|
|
if ((set & (PCRE2_EXTENDED|PCRE2_EXTENDED_MORE)) == PCRE2_EXTENDED ||
|
|
|
|
(unset & PCRE2_EXTENDED) != 0)
|
|
|
|
unset |= PCRE2_EXTENDED_MORE;
|
|
|
|
|
|
|
|
options = (options | set) & (~unset);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the options ended with ')' this is not the start of a nested
|
|
|
|
group with option changes, so the options change at this level.
|
|
|
|
In this case, if the previous level set up a nest block, discard the
|
|
|
|
one we have just created. Otherwise adjust it for the previous level.
|
|
|
|
If the options ended with ':' we are starting a non-capturing group,
|
|
|
|
possibly with an options setting. */
|
|
|
|
|
|
|
|
if (ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
|
|
|
if (*ptr++ == CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
nest_depth--; /* This is not a nested group after all. */
|
|
|
|
if (top_nest > (nest_save *)(cb->start_workspace) &&
|
|
|
|
(top_nest-1)->nest_depth == nest_depth) top_nest--;
|
|
|
|
else top_nest->nest_depth = nest_depth;
|
|
|
|
}
|
|
|
|
else *parsed_pattern++ = META_NOCAPTURE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-08-04 10:20:18 +02:00
|
|
|
/* If nothing changed, no need to record. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-08-04 10:20:18 +02:00
|
|
|
if (options != oldoptions)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_OPTIONS;
|
|
|
|
*parsed_pattern++ = options;
|
|
|
|
}
|
|
|
|
} /* End options processing */
|
|
|
|
break; /* End default case after (? */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Python syntax support ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_P:
|
|
|
|
if (++ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* (?P<name> is the same as (?<name>, which defines a named group. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr == CHAR_LESS_THAN_SIGN)
|
|
|
|
{
|
|
|
|
terminator = CHAR_GREATER_THAN_SIGN;
|
|
|
|
goto DEFINE_NAME;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* (?P>name) is the same as (?&name), which is a recursion or subroutine
|
|
|
|
call. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr == CHAR_GREATER_THAN_SIGN) goto RECURSE_BY_NAME;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* (?P=name) is the same as \k<name>, a back reference by name. Anything
|
|
|
|
else after (?P is an error. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr != CHAR_EQUALS_SIGN)
|
|
|
|
{
|
|
|
|
errorcode = ERR41;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
if (!read_name(&ptr, ptrend, CHAR_RIGHT_PARENTHESIS, &offset, &name,
|
|
|
|
&namelen, &errorcode, cb)) goto FAILED;
|
|
|
|
*parsed_pattern++ = META_BACKREF_BYNAME;
|
|
|
|
*parsed_pattern++ = namelen;
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
okquantifier = TRUE;
|
|
|
|
break; /* End of (?P processing */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Recursion/subroutine calls by number ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_R:
|
|
|
|
i = 0; /* (?R) == (?R0) */
|
|
|
|
ptr++;
|
|
|
|
if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
errorcode = ERR58;
|
2016-10-18 13:22:40 +02:00
|
|
|
goto FAILED;
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
goto SET_RECURSION;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* An item starting (?- followed by a digit comes here via the "default"
|
|
|
|
case because (?- followed by a non-digit is an options setting. */
|
|
|
|
|
|
|
|
case CHAR_PLUS:
|
|
|
|
if (ptrend - ptr < 2 || !IS_DIGIT(ptr[1]))
|
|
|
|
{
|
|
|
|
errorcode = ERR29; /* Missing number */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4:
|
|
|
|
case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9:
|
|
|
|
RECURSION_BYNUMBER:
|
|
|
|
if (!read_number(&ptr, ptrend,
|
|
|
|
(IS_DIGIT(*ptr))? -1:(int)(cb->bracount), /* + and - are relative */
|
|
|
|
MAX_GROUP_NUMBER, ERR61,
|
|
|
|
&i, &errorcode)) goto FAILED;
|
|
|
|
if (i < 0) /* NB (?0) is permitted */
|
|
|
|
{
|
|
|
|
errorcode = ERR15; /* Unknown group */
|
|
|
|
goto FAILED_BACK;
|
|
|
|
}
|
|
|
|
if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
goto UNCLOSED_PARENTHESIS;
|
|
|
|
|
|
|
|
SET_RECURSION:
|
|
|
|
*parsed_pattern++ = META_RECURSE | (uint32_t)i;
|
|
|
|
offset = (PCRE2_SIZE)(ptr - cb->start_pattern);
|
|
|
|
ptr++;
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
okquantifier = TRUE;
|
|
|
|
break; /* End of recursive call by number handling */
|
|
|
|
|
|
|
|
|
|
|
|
/* ---- Recursion/subroutine calls by name ---- */
|
|
|
|
|
|
|
|
case CHAR_AMPERSAND:
|
|
|
|
RECURSE_BY_NAME:
|
|
|
|
if (!read_name(&ptr, ptrend, CHAR_RIGHT_PARENTHESIS, &offset, &name,
|
|
|
|
&namelen, &errorcode, cb)) goto FAILED;
|
|
|
|
*parsed_pattern++ = META_RECURSE_BYNAME;
|
|
|
|
*parsed_pattern++ = namelen;
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
okquantifier = TRUE;
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* ---- Callout with numerical or string argument ---- */
|
|
|
|
|
|
|
|
case CHAR_C:
|
|
|
|
if (++ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
|
|
|
|
|
|
|
/* If the previous item was a condition starting (?(? an assertion,
|
|
|
|
optionally preceded by a callout, is expected. This is checked later on,
|
|
|
|
during actual compilation. However we need to identify this kind of
|
|
|
|
assertion in this pass because it must not be qualified. The value of
|
|
|
|
expect_cond_assert is set to 2 after (?(? is processed. We decrement it
|
|
|
|
for a callout - still leaving a positive value that identifies the
|
|
|
|
assertion. Multiple callouts or any other items will make it zero or
|
|
|
|
less, which doesn't matter because they will cause an error later. */
|
|
|
|
|
|
|
|
expect_cond_assert = prev_expect_cond_assert - 1;
|
|
|
|
|
|
|
|
/* If previous_callout is not NULL, it means this follows a previous
|
|
|
|
callout. If it was a manual callout, do nothing; this means its "length
|
|
|
|
of next pattern item" field will remain zero. If it was an automatic
|
|
|
|
callout, abolish it. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (previous_callout != NULL && (options & PCRE2_AUTO_CALLOUT) != 0 &&
|
|
|
|
previous_callout == parsed_pattern - 4 &&
|
|
|
|
parsed_pattern[-1] == 255)
|
|
|
|
parsed_pattern = previous_callout;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Save for updating next pattern item length, and skip one item before
|
|
|
|
completing. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
previous_callout = parsed_pattern;
|
|
|
|
after_manual_callout = 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a string argument; specific delimiter is required. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr != CHAR_RIGHT_PARENTHESIS && !IS_DIGIT(*ptr))
|
|
|
|
{
|
|
|
|
PCRE2_SIZE calloutlength;
|
|
|
|
PCRE2_SPTR startptr = ptr;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
delimiter = 0;
|
|
|
|
for (i = 0; PRIV(callout_start_delims)[i] != 0; i++)
|
|
|
|
{
|
|
|
|
if (*ptr == PRIV(callout_start_delims)[i])
|
|
|
|
{
|
|
|
|
delimiter = PRIV(callout_end_delims)[i];
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (delimiter == 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR82;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern = META_CALLOUT_STRING;
|
|
|
|
parsed_pattern += 3; /* Skip pattern info */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
if (++ptr >= ptrend)
|
|
|
|
{
|
|
|
|
errorcode = ERR81;
|
|
|
|
ptr = startptr; /* To give a more useful message */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2016-11-18 19:59:37 +01:00
|
|
|
if (*ptr == delimiter && (++ptr >= ptrend || *ptr != delimiter))
|
2016-11-01 18:45:54 +01:00
|
|
|
break;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
calloutlength = (PCRE2_SIZE)(ptr - startptr);
|
|
|
|
if (calloutlength > UINT32_MAX)
|
|
|
|
{
|
|
|
|
errorcode = ERR72;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = (uint32_t)calloutlength;
|
|
|
|
offset = (PCRE2_SIZE)(startptr - cb->start_pattern);
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a callout with an optional numerical argument, which must be
|
|
|
|
less than or equal to 255. A missing argument gives 0. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
int n = 0;
|
|
|
|
*parsed_pattern = META_CALLOUT_NUMBER; /* Numerical callout */
|
|
|
|
parsed_pattern += 3; /* Skip pattern info */
|
|
|
|
while (ptr < ptrend && IS_DIGIT(*ptr))
|
|
|
|
{
|
|
|
|
n = n * 10 + *ptr++ - CHAR_0;
|
|
|
|
if (n > 255)
|
|
|
|
{
|
|
|
|
errorcode = ERR38;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = n;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Both formats must have a closing parenthesis */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
errorcode = ERR39;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
ptr++;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember the offset to the next item in the pattern, and set a default
|
|
|
|
length. This should get updated after the next item is read. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-09-26 19:01:23 +02:00
|
|
|
previous_callout[1] = (uint32_t)(ptr - cb->start_pattern);
|
2016-10-02 18:01:01 +02:00
|
|
|
previous_callout[2] = 0;
|
|
|
|
break; /* End callout */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Conditional group ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A condition can be an assertion, a number (referring to a numbered
|
|
|
|
group's having been set), a name (referring to a named group), or 'R',
|
|
|
|
referring to overall recursion. R<digits> and R&name are also permitted
|
|
|
|
for recursion state tests. Numbers may be preceded by + or - to specify a
|
|
|
|
relative group number.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
There are several syntaxes for testing a named group: (?(name)) is used
|
|
|
|
by Python; Perl 5.10 onwards uses (?(<name>) or (?('name')).
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
There are two unfortunate ambiguities. 'R' can be the recursive thing or
|
|
|
|
the name 'R' (and similarly for 'R' followed by digits). 'DEFINE' can be
|
|
|
|
the Perl DEFINE feature or the Python named test. We look for a name
|
|
|
|
first; if not found, we try the other case.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
For compatibility with auto-callouts, we allow a callout to be specified
|
|
|
|
before a condition that is an assertion. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_LEFT_PARENTHESIS:
|
|
|
|
if (++ptr >= ptrend) goto UNCLOSED_PARENTHESIS;
|
|
|
|
nest_depth++;
|
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
/* If the next character is ? or * there must be an assertion next
|
|
|
|
(optionally preceded by a callout). We do not check this here, but
|
|
|
|
instead we set expect_cond_assert to 2. If this is still greater than
|
|
|
|
zero (callouts decrement it) when the next assertion is read, it will be
|
|
|
|
marked as a condition that must not be repeated. A value greater than
|
|
|
|
zero also causes checking that an assertion (possibly with callout)
|
|
|
|
follows. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2018-09-24 18:23:53 +02:00
|
|
|
if (*ptr == CHAR_QUESTION_MARK || *ptr == CHAR_ASTERISK)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_COND_ASSERT;
|
2016-11-22 16:37:02 +01:00
|
|
|
ptr--; /* Pull pointer back to the opening parenthesis. */
|
2016-10-02 18:01:01 +02:00
|
|
|
expect_cond_assert = 2;
|
|
|
|
break; /* End of conditional */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle (?([+-]number)... */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (read_number(&ptr, ptrend, cb->bracount, MAX_GROUP_NUMBER, ERR61, &i,
|
|
|
|
&errorcode))
|
|
|
|
{
|
|
|
|
if (i <= 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR15;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = META_COND_NUMBER;
|
|
|
|
offset = (PCRE2_SIZE)(ptr - cb->start_pattern - 2);
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
*parsed_pattern++ = i;
|
|
|
|
}
|
|
|
|
else if (errorcode != 0) goto FAILED; /* Number too big */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* No number found. Handle the special case (?(VERSION[>]=n.m)... */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (ptrend - ptr >= 10 &&
|
|
|
|
PRIV(strncmp_c8)(ptr, STRING_VERSION, 7) == 0 &&
|
|
|
|
ptr[7] != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
uint32_t ge = 0;
|
|
|
|
int major = 0;
|
|
|
|
int minor = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
ptr += 7;
|
|
|
|
if (*ptr == CHAR_GREATER_THAN_SIGN)
|
|
|
|
{
|
|
|
|
ge = 1;
|
|
|
|
ptr++;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* NOTE: cannot write IS_DIGIT(*(++ptr)) here because IS_DIGIT
|
|
|
|
references its argument twice. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr != CHAR_EQUALS_SIGN || (ptr++, !IS_DIGIT(*ptr)))
|
|
|
|
goto BAD_VERSION_CONDITION;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!read_number(&ptr, ptrend, -1, 1000, ERR79, &major, &errorcode))
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend) goto BAD_VERSION_CONDITION;
|
|
|
|
if (*ptr == CHAR_DOT)
|
|
|
|
{
|
|
|
|
if (++ptr >= ptrend || !IS_DIGIT(*ptr)) goto BAD_VERSION_CONDITION;
|
2018-07-02 14:26:04 +02:00
|
|
|
minor = (*ptr++ - CHAR_0) * 10;
|
2018-07-28 18:23:24 +02:00
|
|
|
if (IS_DIGIT(*ptr)) minor += *ptr++ - CHAR_0;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
goto BAD_VERSION_CONDITION;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_COND_VERSION;
|
|
|
|
*parsed_pattern++ = ge;
|
|
|
|
*parsed_pattern++ = major;
|
|
|
|
*parsed_pattern++ = minor;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* All the remaining cases now require us to read a name. We cannot at
|
|
|
|
this stage distinguish ambiguous cases such as (?(R12) which might be a
|
|
|
|
recursion test by number or a name, because the named groups have not yet
|
|
|
|
all been identified. Those cases are treated as names, but given a
|
|
|
|
different META code. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
BOOL was_r_ampersand = FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*ptr == CHAR_R && ptrend - ptr > 1 && ptr[1] == CHAR_AMPERSAND)
|
|
|
|
{
|
|
|
|
terminator = CHAR_RIGHT_PARENTHESIS;
|
|
|
|
was_r_ampersand = TRUE;
|
|
|
|
ptr++;
|
|
|
|
}
|
|
|
|
else if (*ptr == CHAR_LESS_THAN_SIGN)
|
|
|
|
terminator = CHAR_GREATER_THAN_SIGN;
|
|
|
|
else if (*ptr == CHAR_APOSTROPHE)
|
|
|
|
terminator = CHAR_APOSTROPHE;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
terminator = CHAR_RIGHT_PARENTHESIS;
|
|
|
|
ptr--; /* Point to char before name */
|
|
|
|
}
|
|
|
|
if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
|
|
|
|
&errorcode, cb)) goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle (?(R&name) */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (was_r_ampersand)
|
|
|
|
{
|
|
|
|
*parsed_pattern = META_COND_RNAME;
|
|
|
|
ptr--; /* Back to closing parens */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle (?(name). If the name is "DEFINE" we identify it with a
|
|
|
|
special code. Likewise if the name consists of R followed only by
|
|
|
|
digits. Otherwise, handle it like a quoted name. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (terminator == CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
if (namelen == 6 && PRIV(strncmp_c8)(name, STRING_DEFINE, 6) == 0)
|
|
|
|
*parsed_pattern = META_COND_DEFINE;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
for (i = 1; i < (int)namelen; i++)
|
|
|
|
if (!IS_DIGIT(name[i])) break;
|
|
|
|
*parsed_pattern = (*name == CHAR_R && i >= (int)namelen)?
|
|
|
|
META_COND_RNUMBER : META_COND_NAME;
|
|
|
|
}
|
|
|
|
ptr--; /* Back to closing parens */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle (?('name') or (?(<name>) */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else *parsed_pattern = META_COND_NAME;
|
2015-07-21 15:42:14 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* All these cases except DEFINE end with the name length and offset;
|
|
|
|
DEFINE just has an offset (for the "too many branches" error). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*parsed_pattern++ != META_COND_DEFINE) *parsed_pattern++ = namelen;
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
} /* End cases that read a name */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check the closing parenthesis of the condition */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (ptr >= ptrend || *ptr != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
errorcode = ERR24;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
ptr++;
|
|
|
|
break; /* End of condition processing */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Atomic group ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_GREATER_THAN_SIGN:
|
2018-09-24 18:23:53 +02:00
|
|
|
ATOMIC_GROUP: /* Come from (*atomic: */
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_ATOMIC;
|
|
|
|
nest_depth++;
|
|
|
|
ptr++;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Lookahead assertions ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_EQUALS_SIGN:
|
2018-09-24 18:23:53 +02:00
|
|
|
POSITIVE_LOOK_AHEAD: /* Come from (*pla: */
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_LOOKAHEAD;
|
|
|
|
ptr++;
|
|
|
|
goto POST_ASSERTION;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_EXCLAMATION_MARK:
|
2018-09-24 18:23:53 +02:00
|
|
|
NEGATIVE_LOOK_AHEAD: /* Come from (*nla: */
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern++ = META_LOOKAHEADNOT;
|
|
|
|
ptr++;
|
|
|
|
goto POST_ASSERTION;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Lookbehind assertions ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* (?< followed by = or ! is a lookbehind assertion. Otherwise (?< is the
|
|
|
|
start of the name of a capturing group. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_LESS_THAN_SIGN:
|
|
|
|
if (ptrend - ptr <= 1 ||
|
|
|
|
(ptr[1] != CHAR_EQUALS_SIGN && ptr[1] != CHAR_EXCLAMATION_MARK))
|
|
|
|
{
|
|
|
|
terminator = CHAR_GREATER_THAN_SIGN;
|
|
|
|
goto DEFINE_NAME;
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = (ptr[1] == CHAR_EQUALS_SIGN)?
|
|
|
|
META_LOOKBEHIND : META_LOOKBEHINDNOT;
|
2018-09-24 18:23:53 +02:00
|
|
|
|
|
|
|
LOOKBEHIND: /* Come from (*plb: and (*nlb: */
|
2016-10-02 18:01:01 +02:00
|
|
|
*has_lookbehind = TRUE;
|
|
|
|
offset = (PCRE2_SIZE)(ptr - cb->start_pattern - 2);
|
|
|
|
PUTOFFSET(offset, parsed_pattern);
|
|
|
|
ptr += 2;
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
/* If the previous item was a condition starting (?(? an assertion,
|
|
|
|
optionally preceded by a callout, is expected. This is checked later on,
|
|
|
|
during actual compilation. However we need to identify this kind of
|
|
|
|
assertion in this pass because it must not be qualified. The value of
|
|
|
|
expect_cond_assert is set to 2 after (?(? is processed. We decrement it
|
|
|
|
for a callout - still leaving a positive value that identifies the
|
|
|
|
assertion. Multiple callouts or any other items will make it zero or
|
|
|
|
less, which doesn't matter because they will cause an error later. */
|
|
|
|
|
|
|
|
POST_ASSERTION:
|
|
|
|
nest_depth++;
|
|
|
|
if (prev_expect_cond_assert > 0)
|
|
|
|
{
|
|
|
|
if (top_nest == NULL) top_nest = (nest_save *)(cb->start_workspace);
|
|
|
|
else if (++top_nest >= end_nests)
|
|
|
|
{
|
|
|
|
errorcode = ERR84;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
top_nest->nest_depth = nest_depth;
|
|
|
|
top_nest->flags = NSF_CONDASSERT;
|
2017-04-18 14:32:52 +02:00
|
|
|
top_nest->options = options & PARSE_TRACKED_OPTIONS;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Define a named group ---- */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A named group may be defined as (?'name') or (?<name>). In the latter
|
|
|
|
case we jump to DEFINE_NAME from the disambiguation of (?< above with the
|
|
|
|
terminator set to '>'. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_APOSTROPHE:
|
|
|
|
terminator = CHAR_APOSTROPHE; /* Terminator */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
DEFINE_NAME:
|
|
|
|
if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
|
|
|
|
&errorcode, cb)) goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* We have a name for this capturing group. It is also assigned a number,
|
|
|
|
which is its primary means of identification. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->bracount++;
|
|
|
|
*parsed_pattern++ = META_CAPTURE | cb->bracount;
|
|
|
|
nest_depth++;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check not too many names */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cb->names_found >= MAX_NAME_COUNT)
|
|
|
|
{
|
|
|
|
errorcode = ERR49;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Adjust the entry size to accommodate the longest name found. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (namelen + IMM2_SIZE + 1 > cb->name_entry_size)
|
|
|
|
cb->name_entry_size = (uint16_t)(namelen + IMM2_SIZE + 1);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Scan the list to check for duplicates. For duplicate names, if the
|
|
|
|
number is the same, break the loop, which causes the name to be
|
|
|
|
discarded; otherwise, if DUPNAMES is not set, give an error.
|
|
|
|
If it is set, allow the name with a different number, but continue
|
|
|
|
scanning in case this is a duplicate with the same number. For
|
|
|
|
non-duplicate names, give an error if the number is duplicated. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
isdupname = FALSE;
|
|
|
|
ng = cb->named_groups;
|
|
|
|
for (i = 0; i < cb->names_found; i++, ng++)
|
|
|
|
{
|
|
|
|
if (namelen == ng->length &&
|
|
|
|
PRIV(strncmp)(name, ng->name, (PCRE2_SIZE)namelen) == 0)
|
|
|
|
{
|
|
|
|
if (ng->number == cb->bracount) break;
|
|
|
|
if ((options & PCRE2_DUPNAMES) == 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR43;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
isdupname = ng->isdup = TRUE; /* Mark as a duplicate */
|
|
|
|
cb->dupnames = TRUE; /* Duplicate names exist */
|
|
|
|
}
|
|
|
|
else if (ng->number == cb->bracount)
|
|
|
|
{
|
|
|
|
errorcode = ERR65;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (i < cb->names_found) break; /* Ignore duplicate with same number */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Increase the list size if necessary */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cb->names_found >= cb->named_group_list_size)
|
|
|
|
{
|
|
|
|
uint32_t newsize = cb->named_group_list_size * 2;
|
|
|
|
named_group *newspace =
|
|
|
|
cb->cx->memctl.malloc(newsize * sizeof(named_group),
|
|
|
|
cb->cx->memctl.memory_data);
|
|
|
|
if (newspace == NULL)
|
|
|
|
{
|
|
|
|
errorcode = ERR21;
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
memcpy(newspace, cb->named_groups,
|
|
|
|
cb->named_group_list_size * sizeof(named_group));
|
|
|
|
if (cb->named_group_list_size > NAMED_GROUP_LIST_SIZE)
|
|
|
|
cb->cx->memctl.free((void *)cb->named_groups,
|
|
|
|
cb->cx->memctl.memory_data);
|
|
|
|
cb->named_groups = newspace;
|
|
|
|
cb->named_group_list_size = newsize;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Add this name to the list */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->named_groups[cb->names_found].name = name;
|
|
|
|
cb->named_groups[cb->names_found].length = (uint16_t)namelen;
|
|
|
|
cb->named_groups[cb->names_found].number = cb->bracount;
|
|
|
|
cb->named_groups[cb->names_found].isdup = (uint16_t)isdupname;
|
|
|
|
cb->names_found++;
|
|
|
|
break;
|
|
|
|
} /* End of (? switch */
|
|
|
|
break; /* End of ( handling */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ---- Branch terminators ---- */
|
|
|
|
|
|
|
|
/* Alternation: reset the capture count if we are in a (?| group. */
|
|
|
|
|
|
|
|
case CHAR_VERTICAL_LINE:
|
|
|
|
if (top_nest != NULL && top_nest->nest_depth == nest_depth &&
|
|
|
|
(top_nest->flags & NSF_RESET) != 0)
|
|
|
|
{
|
|
|
|
if (cb->bracount > top_nest->max_group)
|
|
|
|
top_nest->max_group = (uint16_t)cb->bracount;
|
|
|
|
cb->bracount = top_nest->reset_group;
|
|
|
|
}
|
|
|
|
*parsed_pattern++ = META_ALT;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* End of group; reset the capture count to the maximum if we are in a (?|
|
2017-04-18 14:32:52 +02:00
|
|
|
group and/or reset the options that are tracked during parsing. Disallow
|
|
|
|
quantifier for a condition that is an assertion. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case CHAR_RIGHT_PARENTHESIS:
|
|
|
|
okquantifier = TRUE;
|
|
|
|
if (top_nest != NULL && top_nest->nest_depth == nest_depth)
|
|
|
|
{
|
2017-04-18 14:32:52 +02:00
|
|
|
options = (options & ~PARSE_TRACKED_OPTIONS) | top_nest->options;
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((top_nest->flags & NSF_RESET) != 0 &&
|
|
|
|
top_nest->max_group > cb->bracount)
|
|
|
|
cb->bracount = top_nest->max_group;
|
|
|
|
if ((top_nest->flags & NSF_CONDASSERT) != 0)
|
|
|
|
okquantifier = FALSE;
|
|
|
|
if (top_nest == (nest_save *)(cb->start_workspace)) top_nest = NULL;
|
|
|
|
else top_nest--;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
if (nest_depth == 0) /* Unmatched closing parenthesis */
|
|
|
|
{
|
|
|
|
errorcode = ERR22;
|
|
|
|
goto FAILED_BACK;
|
|
|
|
}
|
|
|
|
nest_depth--;
|
|
|
|
*parsed_pattern++ = META_KET;
|
|
|
|
break;
|
|
|
|
} /* End of switch on pattern character */
|
|
|
|
} /* End of main character scan loop */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* End of pattern reached. Check for missing ) at the end of a verb name. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (inverbname && ptr >= ptrend)
|
|
|
|
{
|
|
|
|
errorcode = ERR60;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Manage callout for the final item */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
PARSED_END:
|
2017-06-15 18:41:44 +02:00
|
|
|
parsed_pattern = manage_callouts(ptr, &previous_callout, auto_callout,
|
2016-10-02 18:01:01 +02:00
|
|
|
parsed_pattern, cb);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
/* Insert trailing items for word and line matching (features provided for the
|
|
|
|
benefit of pcre2grep). */
|
|
|
|
|
|
|
|
if ((cb->cx->extra_options & PCRE2_EXTRA_MATCH_LINE) != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_KET;
|
|
|
|
*parsed_pattern++ = META_DOLLAR;
|
|
|
|
}
|
|
|
|
else if ((cb->cx->extra_options & PCRE2_EXTRA_MATCH_WORD) != 0)
|
|
|
|
{
|
|
|
|
*parsed_pattern++ = META_KET;
|
|
|
|
*parsed_pattern++ = META_ESCAPE + ESC_b;
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Terminate the parsed pattern, then return success if all groups are closed.
|
|
|
|
Otherwise we have unclosed parentheses. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-18 19:59:37 +01:00
|
|
|
if (parsed_pattern >= parsed_pattern_end)
|
|
|
|
{
|
|
|
|
errorcode = ERR63; /* Internal error (parsed pattern overflow) */
|
|
|
|
goto FAILED;
|
|
|
|
}
|
2017-06-16 19:51:13 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*parsed_pattern = META_END;
|
|
|
|
if (nest_depth == 0) return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
UNCLOSED_PARENTHESIS:
|
|
|
|
errorcode = ERR14;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Come here for all failures. */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
FAILED:
|
|
|
|
cb->erroroffset = (PCRE2_SIZE)(ptr - cb->start_pattern);
|
|
|
|
return errorcode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Some errors need to indicate the previous character. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
FAILED_BACK:
|
|
|
|
ptr--;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This failure happens several times. */
|
|
|
|
|
|
|
|
BAD_VERSION_CONDITION:
|
|
|
|
errorcode = ERR79;
|
|
|
|
goto FAILED;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2018-06-17 16:13:28 +02:00
|
|
|
* Find first significant opcode *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This is called by several functions that scan a compiled expression looking
|
2018-06-17 16:13:28 +02:00
|
|
|
for a fixed first character, or an anchoring opcode etc. It skips over things
|
2016-10-02 18:01:01 +02:00
|
|
|
that do not influence this. For some calls, it makes sense to skip negative
|
|
|
|
forward and all backward assertions, and also the \b assertion; for others it
|
|
|
|
does not.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
code pointer to the start of the group
|
|
|
|
skipassert TRUE if certain assertions are to be skipped
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: pointer to the first significant opcode
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static const PCRE2_UCHAR*
|
|
|
|
first_significant_code(PCRE2_SPTR code, BOOL skipassert)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;;)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
switch ((int)*code)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_ASSERT_NOT:
|
|
|
|
case OP_ASSERTBACK:
|
|
|
|
case OP_ASSERTBACK_NOT:
|
|
|
|
if (!skipassert) return code;
|
|
|
|
do code += GET(code, 1); while (*code == OP_ALT);
|
|
|
|
code += PRIV(OP_lengths)[*code];
|
|
|
|
break;
|
|
|
|
|
|
|
|
case OP_WORD_BOUNDARY:
|
|
|
|
case OP_NOT_WORD_BOUNDARY:
|
|
|
|
if (!skipassert) return code;
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
case OP_CALLOUT:
|
|
|
|
case OP_CREF:
|
|
|
|
case OP_DNCREF:
|
|
|
|
case OP_RREF:
|
|
|
|
case OP_DNRREF:
|
|
|
|
case OP_FALSE:
|
|
|
|
case OP_TRUE:
|
|
|
|
code += PRIV(OP_lengths)[*code];
|
|
|
|
break;
|
|
|
|
|
|
|
|
case OP_CALLOUT_STR:
|
|
|
|
code += GET(code, 1 + 2*LINK_SIZE);
|
|
|
|
break;
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-04-07 10:46:29 +02:00
|
|
|
case OP_SKIPZERO:
|
|
|
|
code += 2 + GET(code, 2) + LINK_SIZE;
|
2017-05-17 19:55:11 +02:00
|
|
|
break;
|
|
|
|
|
2017-04-07 10:46:29 +02:00
|
|
|
case OP_COND:
|
|
|
|
case OP_SCOND:
|
|
|
|
if (code[1+LINK_SIZE] != OP_FALSE || /* Not DEFINE */
|
|
|
|
code[GET(code, 1)] != OP_KET) /* More than one branch */
|
|
|
|
return code;
|
|
|
|
code += GET(code, 1) + 1 + LINK_SIZE;
|
2017-05-17 19:55:11 +02:00
|
|
|
break;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
default:
|
|
|
|
return code;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Control never reaches here */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
/*************************************************
|
|
|
|
* Get othercase range *
|
|
|
|
*************************************************/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is passed the start and end of a class range in UCP mode. It
|
|
|
|
searches up the characters, looking for ranges of characters in the "other"
|
|
|
|
case. Each call returns the next one, updating the start address. A character
|
|
|
|
with multiple other cases is returned on its own with a special return value.
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
cptr points to starting character value; updated
|
|
|
|
d end value
|
|
|
|
ocptr where to put start of othercase range
|
|
|
|
odptr where to put end of othercase range
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Yield: -1 when no more
|
|
|
|
0 when a range is returned
|
|
|
|
>0 the CASESET offset for char with multiple other cases
|
|
|
|
in this case, ocptr contains the original
|
|
|
|
*/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static int
|
|
|
|
get_othercase_range(uint32_t *cptr, uint32_t d, uint32_t *ocptr,
|
|
|
|
uint32_t *odptr)
|
|
|
|
{
|
|
|
|
uint32_t c, othercase, next;
|
|
|
|
unsigned int co;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Find the first character that has an other case. If it has multiple other
|
|
|
|
cases, return its case offset value. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (c = *cptr; c <= d; c++)
|
|
|
|
{
|
|
|
|
if ((co = UCD_CASESET(c)) != 0)
|
|
|
|
{
|
|
|
|
*ocptr = c++; /* Character that has the set */
|
|
|
|
*cptr = c; /* Rest of input range */
|
|
|
|
return (int)co;
|
|
|
|
}
|
|
|
|
if ((othercase = UCD_OTHERCASE(c)) != c) break;
|
|
|
|
}
|
2015-12-03 19:36:36 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c > d) return -1; /* Reached end of range */
|
2015-12-03 19:36:36 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Found a character that has a single other case. Search for the end of the
|
|
|
|
range, which is either the end of the input range, or a character that has zero
|
|
|
|
or more than one other cases. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*ocptr = othercase;
|
|
|
|
next = othercase + 1;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (++c; c <= d; c++)
|
|
|
|
{
|
|
|
|
if ((co = UCD_CASESET(c)) != 0 || UCD_OTHERCASE(c) != next) break;
|
|
|
|
next++;
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*odptr = next - 1; /* End of othercase range */
|
|
|
|
*cptr = c; /* Rest of input range */
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* SUPPORT_UNICODE */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
2017-01-03 19:17:31 +01:00
|
|
|
* Add a character or range to a class (internal) *
|
2016-10-02 18:01:01 +02:00
|
|
|
*************************************************/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function packages up the logic of adding a character or range of
|
|
|
|
characters to a class. The character values in the arguments will be within the
|
2017-01-11 17:40:35 +01:00
|
|
|
valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is
|
|
|
|
called only from within the "add to class" group of functions, some of which
|
|
|
|
are recursive and mutually recursive. The external entry point is
|
|
|
|
add_to_class().
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
classbits the bit map for characters < 256
|
|
|
|
uchardptr points to the pointer for extra data
|
|
|
|
options the options word
|
|
|
|
cb compile data
|
|
|
|
start start of range character
|
|
|
|
end end of range character
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the number of < 256 characters added
|
|
|
|
the pointer to extra data is updated
|
|
|
|
*/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static unsigned int
|
2017-01-11 17:40:35 +01:00
|
|
|
add_to_class_internal(uint8_t *classbits, PCRE2_UCHAR **uchardptr,
|
2017-01-03 19:17:31 +01:00
|
|
|
uint32_t options, compile_block *cb, uint32_t start, uint32_t end)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
uint32_t c;
|
|
|
|
uint32_t classbits_end = (end <= 0xff ? end : 0xff);
|
|
|
|
unsigned int n8 = 0;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If caseless matching is required, scan the range and process alternate
|
|
|
|
cases. In Unicode, there are 8-bit characters that have alternate cases that
|
|
|
|
are greater than 255 and vice-versa. Sometimes we can just extend the original
|
|
|
|
range. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((options & PCRE2_CASELESS) != 0)
|
|
|
|
{
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if ((options & PCRE2_UTF) != 0)
|
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
uint32_t oc, od;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
options &= ~PCRE2_CASELESS; /* Remove for recursive calls */
|
|
|
|
c = start;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
while ((rc = get_othercase_range(&c, end, &oc, &od)) >= 0)
|
|
|
|
{
|
|
|
|
/* Handle a single character that has more than one other case. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2017-01-03 19:17:31 +01:00
|
|
|
if (rc > 0) n8 += add_list_to_class_internal(classbits, uchardptr, options, cb,
|
2016-10-02 18:01:01 +02:00
|
|
|
PRIV(ucd_caseless_sets) + rc, oc);
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Do nothing if the other case range is within the original range. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2017-01-03 19:17:31 +01:00
|
|
|
else if (oc >= cb->class_range_start && od <= cb->class_range_end) continue;
|
2015-07-17 15:41:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Extend the original range if there is overlap, noting that if oc < c, we
|
|
|
|
can't have od > end because a subrange is always shorter than the basic
|
|
|
|
range. Otherwise, use a recursive call to add the additional range. */
|
2015-07-17 15:41:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */
|
|
|
|
else if (od > end && oc <= end + 1)
|
2015-07-16 19:47:20 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
end = od; /* Extend upwards */
|
|
|
|
if (end > classbits_end) classbits_end = (end <= 0xff ? end : 0xff);
|
2015-07-17 15:41:09 +02:00
|
|
|
}
|
2017-01-03 19:17:31 +01:00
|
|
|
else n8 += add_to_class_internal(classbits, uchardptr, options, cb, oc, od);
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
#endif /* SUPPORT_UNICODE */
|
2015-07-16 19:47:20 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Not UTF mode */
|
2015-07-17 15:41:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (c = start; c <= classbits_end; c++)
|
|
|
|
{
|
|
|
|
SETBIT(classbits, cb->fcc[c]);
|
|
|
|
n8++;
|
|
|
|
}
|
|
|
|
}
|
2015-07-22 11:29:09 +02:00
|
|
|
|
2017-01-03 19:17:31 +01:00
|
|
|
/* Now handle the originally supplied range. Adjust the final value according
|
|
|
|
to the bit length - this means that the same lists of (e.g.) horizontal spaces
|
|
|
|
can be used in all cases. */
|
2015-07-22 11:29:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((options & PCRE2_UTF) == 0 && end > MAX_NON_UTF_CHAR)
|
|
|
|
end = MAX_NON_UTF_CHAR;
|
2017-01-11 17:40:35 +01:00
|
|
|
|
2017-01-03 19:17:31 +01:00
|
|
|
if (start > cb->class_range_start && end < cb->class_range_end) return n8;
|
2015-07-22 11:29:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Use the bitmap for characters < 256. Otherwise use extra data.*/
|
2015-07-21 16:03:08 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (c = start; c <= classbits_end; c++)
|
|
|
|
{
|
|
|
|
/* Regardless of start, c will always be <= 255. */
|
|
|
|
SETBIT(classbits, c);
|
|
|
|
n8++;
|
|
|
|
}
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
if (start <= 0xff) start = 0xff + 1;
|
2015-07-17 15:41:09 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (end >= start)
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR *uchardata = *uchardptr;
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if ((options & PCRE2_UTF) != 0)
|
|
|
|
{
|
|
|
|
if (start < end)
|
|
|
|
{
|
|
|
|
*uchardata++ = XCL_RANGE;
|
|
|
|
uchardata += PRIV(ord2utf)(start, uchardata);
|
|
|
|
uchardata += PRIV(ord2utf)(end, uchardata);
|
|
|
|
}
|
|
|
|
else if (start == end)
|
|
|
|
{
|
|
|
|
*uchardata++ = XCL_SINGLE;
|
|
|
|
uchardata += PRIV(ord2utf)(start, uchardata);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
#endif /* SUPPORT_UNICODE */
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Without UTF support, character values are constrained by the bit length,
|
|
|
|
and can only be > 256 for 16-bit and 32-bit libraries. */
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
|
|
|
{}
|
|
|
|
#else
|
|
|
|
if (start < end)
|
|
|
|
{
|
|
|
|
*uchardata++ = XCL_RANGE;
|
|
|
|
*uchardata++ = start;
|
|
|
|
*uchardata++ = end;
|
|
|
|
}
|
|
|
|
else if (start == end)
|
|
|
|
{
|
|
|
|
*uchardata++ = XCL_SINGLE;
|
|
|
|
*uchardata++ = start;
|
|
|
|
}
|
2017-01-03 19:17:31 +01:00
|
|
|
#endif /* PCRE2_CODE_UNIT_WIDTH == 8 */
|
2016-10-02 18:01:01 +02:00
|
|
|
*uchardptr = uchardata; /* Updata extra data pointer */
|
|
|
|
}
|
2017-01-03 19:17:31 +01:00
|
|
|
#else /* SUPPORT_WIDE_CHARS */
|
2016-10-02 18:01:01 +02:00
|
|
|
(void)uchardptr; /* Avoid compiler warning */
|
|
|
|
#endif /* SUPPORT_WIDE_CHARS */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
return n8; /* Number of 8-bit characters */
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2017-01-16 18:40:47 +01:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
2017-01-03 19:17:31 +01:00
|
|
|
* Add a list of characters to a class (internal) *
|
2016-10-02 18:01:01 +02:00
|
|
|
*************************************************/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is used for adding a list of case-equivalent characters to a
|
2017-01-16 18:40:47 +01:00
|
|
|
class when in UTF mode. This function is called only from within
|
|
|
|
add_to_class_internal(), with which it is mutually recursive.
|
2017-01-03 19:17:31 +01:00
|
|
|
|
|
|
|
Arguments:
|
|
|
|
classbits the bit map for characters < 256
|
|
|
|
uchardptr points to the pointer for extra data
|
|
|
|
options the options word
|
|
|
|
cb contains pointers to tables etc.
|
|
|
|
p points to row of 32-bit values, terminated by NOTACHAR
|
|
|
|
except character to omit; this is used when adding lists of
|
|
|
|
case-equivalent characters to avoid including the one we
|
|
|
|
already know about
|
|
|
|
|
|
|
|
Returns: the number of < 256 characters added
|
|
|
|
the pointer to extra data is updated
|
|
|
|
*/
|
|
|
|
|
|
|
|
static unsigned int
|
2017-01-11 17:40:35 +01:00
|
|
|
add_list_to_class_internal(uint8_t *classbits, PCRE2_UCHAR **uchardptr,
|
2017-01-03 19:17:31 +01:00
|
|
|
uint32_t options, compile_block *cb, const uint32_t *p, unsigned int except)
|
|
|
|
{
|
|
|
|
unsigned int n8 = 0;
|
|
|
|
while (p[0] < NOTACHAR)
|
|
|
|
{
|
|
|
|
unsigned int n = 0;
|
|
|
|
if (p[0] != except)
|
|
|
|
{
|
|
|
|
while(p[n+1] == p[0] + n + 1) n++;
|
|
|
|
n8 += add_to_class_internal(classbits, uchardptr, options, cb, p[0], p[n]);
|
|
|
|
}
|
|
|
|
p += n + 1;
|
|
|
|
}
|
|
|
|
return n8;
|
|
|
|
}
|
2017-01-16 18:40:47 +01:00
|
|
|
#endif
|
2017-01-03 19:17:31 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
|
|
|
* External entry point for add range to class *
|
|
|
|
*************************************************/
|
|
|
|
|
2017-01-11 17:40:35 +01:00
|
|
|
/* This function sets the overall range so that the internal functions can try
|
2017-01-03 19:17:31 +01:00
|
|
|
to avoid duplication when handling case-independence.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
classbits the bit map for characters < 256
|
|
|
|
uchardptr points to the pointer for extra data
|
|
|
|
options the options word
|
|
|
|
cb compile data
|
|
|
|
start start of range character
|
|
|
|
end end of range character
|
|
|
|
|
|
|
|
Returns: the number of < 256 characters added
|
|
|
|
the pointer to extra data is updated
|
|
|
|
*/
|
|
|
|
|
|
|
|
static unsigned int
|
|
|
|
add_to_class(uint8_t *classbits, PCRE2_UCHAR **uchardptr, uint32_t options,
|
|
|
|
compile_block *cb, uint32_t start, uint32_t end)
|
|
|
|
{
|
|
|
|
cb->class_range_start = start;
|
|
|
|
cb->class_range_end = end;
|
|
|
|
return add_to_class_internal(classbits, uchardptr, options, cb, start, end);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
|
|
|
* External entry point for add list to class *
|
|
|
|
*************************************************/
|
|
|
|
|
2017-01-16 18:40:47 +01:00
|
|
|
/* This function is used for adding a list of horizontal or vertical whitespace
|
|
|
|
characters to a class. The list must be in order so that ranges of characters
|
|
|
|
can be detected and handled appropriately. This function sets the overall range
|
|
|
|
so that the internal functions can try to avoid duplication when handling
|
|
|
|
case-independence.
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
classbits the bit map for characters < 256
|
|
|
|
uchardptr points to the pointer for extra data
|
|
|
|
options the options word
|
|
|
|
cb contains pointers to tables etc.
|
|
|
|
p points to row of 32-bit values, terminated by NOTACHAR
|
|
|
|
except character to omit; this is used when adding lists of
|
|
|
|
case-equivalent characters to avoid including the one we
|
|
|
|
already know about
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the number of < 256 characters added
|
|
|
|
the pointer to extra data is updated
|
|
|
|
*/
|
|
|
|
|
|
|
|
static unsigned int
|
|
|
|
add_list_to_class(uint8_t *classbits, PCRE2_UCHAR **uchardptr, uint32_t options,
|
|
|
|
compile_block *cb, const uint32_t *p, unsigned int except)
|
|
|
|
{
|
|
|
|
unsigned int n8 = 0;
|
|
|
|
while (p[0] < NOTACHAR)
|
|
|
|
{
|
|
|
|
unsigned int n = 0;
|
|
|
|
if (p[0] != except)
|
|
|
|
{
|
|
|
|
while(p[n+1] == p[0] + n + 1) n++;
|
2017-01-03 19:17:31 +01:00
|
|
|
cb->class_range_start = p[0];
|
2017-01-11 17:40:35 +01:00
|
|
|
cb->class_range_end = p[n];
|
2017-01-03 19:17:31 +01:00
|
|
|
n8 += add_to_class_internal(classbits, uchardptr, options, cb, p[0], p[n]);
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
p += n + 1;
|
|
|
|
}
|
|
|
|
return n8;
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Add characters not in a list to a class *
|
|
|
|
*************************************************/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is used for adding the complement of a list of horizontal or
|
|
|
|
vertical whitespace to a class. The list must be in order.
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
classbits the bit map for characters < 256
|
|
|
|
uchardptr points to the pointer for extra data
|
|
|
|
options the options word
|
|
|
|
cb contains pointers to tables etc.
|
|
|
|
p points to row of 32-bit values, terminated by NOTACHAR
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the number of < 256 characters added
|
|
|
|
the pointer to extra data is updated
|
|
|
|
*/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static unsigned int
|
|
|
|
add_not_list_to_class(uint8_t *classbits, PCRE2_UCHAR **uchardptr,
|
|
|
|
uint32_t options, compile_block *cb, const uint32_t *p)
|
|
|
|
{
|
|
|
|
BOOL utf = (options & PCRE2_UTF) != 0;
|
|
|
|
unsigned int n8 = 0;
|
|
|
|
if (p[0] > 0)
|
|
|
|
n8 += add_to_class(classbits, uchardptr, options, cb, 0, p[0] - 1);
|
|
|
|
while (p[0] < NOTACHAR)
|
|
|
|
{
|
|
|
|
while (p[1] == p[0] + 1) p++;
|
|
|
|
n8 += add_to_class(classbits, uchardptr, options, cb, p[0] + 1,
|
|
|
|
(p[1] == NOTACHAR) ? (utf ? 0x10ffffu : 0xffffffffu) : p[1] - 1);
|
|
|
|
p++;
|
|
|
|
}
|
|
|
|
return n8;
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Find details of duplicate group names *
|
|
|
|
*************************************************/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This is called from compile_branch() when it needs to know the index and
|
|
|
|
count of duplicates in the names table when processing named backreferences,
|
|
|
|
either directly, or as conditions.
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
name points to the name
|
|
|
|
length the length of the name
|
|
|
|
indexptr where to put the index
|
|
|
|
countptr where to put the count of duplicates
|
|
|
|
errorcodeptr where to put an error code
|
|
|
|
cb the compile block
|
|
|
|
|
|
|
|
Returns: TRUE if OK, FALSE if not, error code set
|
|
|
|
*/
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
find_dupname_details(PCRE2_SPTR name, uint32_t length, int *indexptr,
|
|
|
|
int *countptr, int *errorcodeptr, compile_block *cb)
|
|
|
|
{
|
|
|
|
uint32_t i, groupnumber;
|
|
|
|
int count;
|
|
|
|
PCRE2_UCHAR *slot = cb->name_table;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Find the first entry in the table */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < cb->names_found; i++)
|
|
|
|
{
|
|
|
|
if (PRIV(strncmp)(name, slot+IMM2_SIZE, length) == 0 &&
|
|
|
|
slot[IMM2_SIZE+length] == 0) break;
|
|
|
|
slot += cb->name_entry_size;
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This should not occur, because this function is called only when we know we
|
|
|
|
have duplicate names. Give an internal error. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (i >= cb->names_found)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR53;
|
|
|
|
cb->erroroffset = name - cb->start_pattern;
|
|
|
|
return FALSE;
|
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Record the index and then see how many duplicates there are, updating the
|
|
|
|
backref map and maximum back reference as we do. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*indexptr = i;
|
|
|
|
count = 0;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;;)
|
2016-02-13 16:30:29 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
count++;
|
|
|
|
groupnumber = GET2(slot,0);
|
|
|
|
cb->backref_map |= (groupnumber < 32)? (1u << groupnumber) : 1;
|
|
|
|
if (groupnumber > cb->top_backref) cb->top_backref = groupnumber;
|
|
|
|
if (++i >= cb->names_found) break;
|
|
|
|
slot += cb->name_entry_size;
|
|
|
|
if (PRIV(strncmp)(name, slot+IMM2_SIZE, length) != 0 ||
|
|
|
|
(slot+IMM2_SIZE)[length] != 0) break;
|
2016-02-13 16:30:29 +01:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*countptr = count;
|
|
|
|
return TRUE;
|
2015-06-03 18:27:47 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/*************************************************
|
|
|
|
* Compile one branch *
|
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Scan the parsed pattern, compiling it into the a vector of PCRE2_UCHAR. If
|
|
|
|
the options are changed during the branch, the pointer is used to change the
|
|
|
|
external options bits. This function is used during the pre-compile phase when
|
|
|
|
we are trying to find out the amount of memory needed, as well as during the
|
|
|
|
real compile phase. The value of lengthptr distinguishes the two phases.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
|
|
|
optionsptr pointer to the option bits
|
|
|
|
codeptr points to the pointer to the current code point
|
2016-10-02 18:01:01 +02:00
|
|
|
pptrptr points to the current parsed pattern pointer
|
2014-06-14 20:29:51 +02:00
|
|
|
errorcodeptr points to error code variable
|
|
|
|
firstcuptr place to put the first required code unit
|
|
|
|
firstcuflagsptr place to put the first code unit flags, or a negative number
|
|
|
|
reqcuptr place to put the last required code unit
|
|
|
|
reqcuflagsptr place to put the last required code unit flags, or a negative number
|
|
|
|
bcptr points to current branch chain
|
2014-06-28 16:23:18 +02:00
|
|
|
cb contains pointers to tables etc.
|
2014-06-14 20:29:51 +02:00
|
|
|
lengthptr NULL during the real compile phase
|
|
|
|
points to length accumulator during pre-compile phase
|
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
Returns: 0 There's been an error, *errorcodeptr is non-zero
|
|
|
|
+1 Success, this branch must match at least one character
|
2016-12-23 19:34:10 +01:00
|
|
|
-1 Success, this branch may match an empty string
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
static int
|
2016-10-02 18:01:01 +02:00
|
|
|
compile_branch(uint32_t *optionsptr, PCRE2_UCHAR **codeptr, uint32_t **pptrptr,
|
|
|
|
int *errorcodeptr, uint32_t *firstcuptr, int32_t *firstcuflagsptr,
|
|
|
|
uint32_t *reqcuptr, int32_t *reqcuflagsptr, branch_chain *bcptr,
|
|
|
|
compile_block *cb, PCRE2_SIZE *lengthptr)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
int bravalue = 0;
|
2016-12-23 18:09:37 +01:00
|
|
|
int okreturn = -1;
|
2016-12-23 19:34:10 +01:00
|
|
|
int group_return = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t repeat_min = 0, repeat_max = 0; /* To please picky compilers */
|
2015-03-31 18:10:01 +02:00
|
|
|
uint32_t greedy_default, greedy_non_default;
|
|
|
|
uint32_t repeat_type, op_type;
|
|
|
|
uint32_t options = *optionsptr; /* May change dynamically */
|
2014-06-14 20:29:51 +02:00
|
|
|
uint32_t firstcu, reqcu;
|
|
|
|
uint32_t zeroreqcu, zerofirstcu;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t escape;
|
|
|
|
uint32_t *pptr = *pptrptr;
|
|
|
|
uint32_t meta, meta_arg;
|
|
|
|
int32_t firstcuflags, reqcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
int32_t zeroreqcuflags, zerofirstcuflags;
|
|
|
|
int32_t req_caseopt, reqvary, tempreqvary;
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SIZE offset = 0;
|
|
|
|
PCRE2_SIZE length_prevgroup = 0;
|
|
|
|
PCRE2_UCHAR *code = *codeptr;
|
2014-06-14 20:29:51 +02:00
|
|
|
PCRE2_UCHAR *last_code = code;
|
|
|
|
PCRE2_UCHAR *orig_code = code;
|
|
|
|
PCRE2_UCHAR *tempcode;
|
|
|
|
PCRE2_UCHAR *previous = NULL;
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_UCHAR op_previous;
|
|
|
|
BOOL groupsetfirstcu = FALSE;
|
2016-12-23 18:09:37 +01:00
|
|
|
BOOL matched_char = FALSE;
|
|
|
|
BOOL previous_matched_char = FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
const uint8_t *cbits = cb->cbits;
|
2014-06-14 20:29:51 +02:00
|
|
|
uint8_t classbits[32];
|
|
|
|
|
|
|
|
/* We can fish out the UTF setting once and for all into a BOOL, but we must
|
|
|
|
not do this for other options (e.g. PCRE2_EXTENDED) because they may change
|
|
|
|
dynamically as we process the pattern. */
|
|
|
|
|
2014-09-19 09:43:39 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2014-06-14 20:29:51 +02:00
|
|
|
BOOL utf = (options & PCRE2_UTF) != 0;
|
|
|
|
#else /* No UTF support */
|
|
|
|
BOOL utf = FALSE;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Helper variables for OP_XCLASS opcode (for characters > 255). We define
|
|
|
|
class_uchardata always so that it can be passed to add_to_class() always,
|
|
|
|
though it will not be used in non-UTF 8-bit cases. This avoids having to supply
|
|
|
|
alternative calls for the different cases. */
|
|
|
|
|
|
|
|
PCRE2_UCHAR *class_uchardata;
|
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
BOOL xclass;
|
|
|
|
PCRE2_UCHAR *class_uchardata_base;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Set up the default and non-default settings for greediness */
|
|
|
|
|
|
|
|
greedy_default = ((options & PCRE2_UNGREEDY) != 0);
|
|
|
|
greedy_non_default = greedy_default ^ 1;
|
|
|
|
|
|
|
|
/* Initialize no first unit, no required unit. REQ_UNSET means "no char
|
|
|
|
matching encountered yet". It gets changed to REQ_NONE if we hit something that
|
|
|
|
matches a non-fixed first unit; reqcu just remains unset if we never find one.
|
|
|
|
|
|
|
|
When we hit a repeat whose minimum is zero, we may have to adjust these values
|
|
|
|
to take the zero repeat into account. This is implemented by setting them to
|
|
|
|
zerofirstcu and zeroreqcu when such a repeat is encountered. The individual
|
|
|
|
item types that can be repeated set these backoff variables appropriately. */
|
|
|
|
|
|
|
|
firstcu = reqcu = zerofirstcu = zeroreqcu = 0;
|
|
|
|
firstcuflags = reqcuflags = zerofirstcuflags = zeroreqcuflags = REQ_UNSET;
|
|
|
|
|
|
|
|
/* The variable req_caseopt contains either the REQ_CASELESS value or zero,
|
|
|
|
according to the current setting of the caseless flag. The REQ_CASELESS value
|
|
|
|
leaves the lower 28 bit empty. It is added into the firstcu or reqcu variables
|
|
|
|
to record the case status of the value. This is used only for ASCII characters.
|
|
|
|
*/
|
|
|
|
|
|
|
|
req_caseopt = ((options & PCRE2_CASELESS) != 0)? REQ_CASELESS:0;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Switch on next META item until the end of the branch */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;; pptr++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
BOOL xclass_has_prop;
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
BOOL negate_class;
|
|
|
|
BOOL should_flip_negation;
|
2015-11-27 18:03:58 +01:00
|
|
|
BOOL match_all_or_no_wide_chars;
|
2014-06-14 20:29:51 +02:00
|
|
|
BOOL possessive_quantifier;
|
2016-12-23 19:34:10 +01:00
|
|
|
BOOL note_group_empty;
|
2014-06-14 20:29:51 +02:00
|
|
|
int class_has_8bitchar;
|
2016-10-02 18:01:01 +02:00
|
|
|
int i;
|
|
|
|
uint32_t mclength;
|
2015-03-31 18:10:01 +02:00
|
|
|
uint32_t skipunits;
|
2015-03-31 17:01:25 +02:00
|
|
|
uint32_t subreqcu, subfirstcu;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t groupnumber;
|
|
|
|
uint32_t verbarglen, verbculen;
|
2015-03-31 17:01:25 +02:00
|
|
|
int32_t subreqcuflags, subfirstcuflags; /* Must be signed */
|
2016-10-02 18:01:01 +02:00
|
|
|
open_capitem *oc;
|
2014-06-14 20:29:51 +02:00
|
|
|
PCRE2_UCHAR mcbuffer[8];
|
2016-06-29 18:52:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Get next META item in the pattern and its potential argument. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
meta = META_CODE(*pptr);
|
|
|
|
meta_arg = META_DATA(*pptr);
|
2017-01-11 17:40:35 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* If we are in the pre-compile phase, accumulate the length used for the
|
2016-10-02 18:01:01 +02:00
|
|
|
previous cycle of this loop, unless the next item is a quantifier. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
2014-06-28 16:23:18 +02:00
|
|
|
if (code > cb->start_workspace + cb->workspace_size -
|
2014-06-14 20:29:51 +02:00
|
|
|
WORK_SIZE_SAFETY_MARGIN) /* Check for overrun */
|
|
|
|
{
|
2015-11-01 17:28:13 +01:00
|
|
|
*errorcodeptr = (code >= cb->start_workspace + cb->workspace_size)?
|
2015-10-28 10:59:53 +01:00
|
|
|
ERR52 : ERR86;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* There is at least one situation where code goes backwards: this is the
|
2016-10-02 18:01:01 +02:00
|
|
|
case of a zero quantifier after a class (e.g. [ab]{0}). When the quantifier
|
|
|
|
is processed, the whole class is eliminated. However, it is created first,
|
|
|
|
so we have to allow memory for it. Therefore, don't ever reduce the length
|
|
|
|
at this point. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
if (code < last_code) code = last_code;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the next thing is not a quantifier, we add the length of the previous
|
|
|
|
item into the total, and reset the code pointer to the start of the
|
|
|
|
workspace. Otherwise leave the previous item available to be quantified. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta < META_ASTERISK || meta > META_MINMAX_QUERY)
|
2015-11-25 19:46:35 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (OFLOW_MAX - *lengthptr < (PCRE2_SIZE)(code - orig_code))
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20; /* Integer overflow */
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
*lengthptr += (PCRE2_SIZE)(code - orig_code);
|
2017-01-03 12:35:26 +01:00
|
|
|
if (*lengthptr > MAX_PATTERN_SIZE)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20; /* Pattern is too large */
|
|
|
|
return 0;
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
code = orig_code;
|
2015-11-25 19:46:35 +01:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember where this code item starts so we can catch the "backwards"
|
|
|
|
case above next time round. */
|
|
|
|
|
|
|
|
last_code = code;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process the next parsed pattern item. If it is not a quantifier, remember
|
|
|
|
where it starts so that it can be quantified when a quantifier follows.
|
|
|
|
Checking for the legality of quantifiers happens in parse_regex(), except for
|
|
|
|
a quantifier after an assertion that is a condition. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 19:34:10 +01:00
|
|
|
if (meta < META_ASTERISK || meta > META_MINMAX_QUERY)
|
2016-12-23 18:09:37 +01:00
|
|
|
{
|
|
|
|
previous = code;
|
|
|
|
if (matched_char) okreturn = 1;
|
2016-12-23 19:34:10 +01:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
previous_matched_char = matched_char;
|
|
|
|
matched_char = FALSE;
|
2016-12-23 19:34:10 +01:00
|
|
|
note_group_empty = FALSE;
|
2016-12-23 18:09:37 +01:00
|
|
|
skipunits = 0; /* Default value for most subgroups */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
switch(meta)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
/* ===================================================================*/
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The branch terminates at pattern end or | or ) */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_END:
|
|
|
|
case META_ALT:
|
|
|
|
case META_KET:
|
2014-06-14 20:29:51 +02:00
|
|
|
*firstcuptr = firstcu;
|
|
|
|
*firstcuflagsptr = firstcuflags;
|
|
|
|
*reqcuptr = reqcu;
|
|
|
|
*reqcuflagsptr = reqcuflags;
|
|
|
|
*codeptr = code;
|
2016-10-02 18:01:01 +02:00
|
|
|
*pptrptr = pptr;
|
2016-12-23 18:09:37 +01:00
|
|
|
return okreturn;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle single-character metacharacters. In multiline mode, ^ disables
|
|
|
|
the setting of any following char as a first character. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CIRCUMFLEX:
|
2014-06-14 20:29:51 +02:00
|
|
|
if ((options & PCRE2_MULTILINE) != 0)
|
|
|
|
{
|
2014-08-08 17:36:18 +02:00
|
|
|
if (firstcuflags == REQ_UNSET)
|
2014-06-21 14:39:48 +02:00
|
|
|
zerofirstcuflags = firstcuflags = REQ_NONE;
|
2014-06-14 20:29:51 +02:00
|
|
|
*code++ = OP_CIRCM;
|
|
|
|
}
|
|
|
|
else *code++ = OP_CIRC;
|
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_DOLLAR:
|
2014-06-14 20:29:51 +02:00
|
|
|
*code++ = ((options & PCRE2_MULTILINE) != 0)? OP_DOLLM : OP_DOLL;
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* There can never be a first char if '.' is first, whatever happens about
|
|
|
|
repeats. The value of reqcu doesn't change either. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_DOT:
|
2016-12-23 19:34:10 +01:00
|
|
|
matched_char = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
|
|
|
*code++ = ((options & PCRE2_DOTALL) != 0)? OP_ALLANY: OP_ANY;
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Empty character classes are allowed if PCRE2_ALLOW_EMPTY_CLASS is set.
|
|
|
|
Otherwise, an initial ']' is taken as a data character. When empty classes
|
|
|
|
are allowed, [] must always fail, so generate OP_FAIL, whereas [^] must
|
|
|
|
match any character, so generate OP_ALLANY. */
|
|
|
|
|
|
|
|
case META_CLASS_EMPTY:
|
|
|
|
case META_CLASS_EMPTY_NOT:
|
2016-12-23 19:34:10 +01:00
|
|
|
matched_char = TRUE;
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = (meta == META_CLASS_EMPTY_NOT)? OP_ALLANY : OP_FAIL;
|
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
|
|
|
/* Non-empty character class. If the included characters are all < 256, we
|
|
|
|
build a 32-byte bitmap of the permitted characters, except in the special
|
|
|
|
case where there is only one such character. For negated classes, we build
|
|
|
|
the map as usual, then invert it at the end. However, we use a different
|
|
|
|
opcode so that data characters > 255 can be handled correctly.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
If the class contains characters outside the 0-255 range, a different
|
|
|
|
opcode is compiled. It may optionally have a bit map for characters < 256,
|
2016-10-02 18:01:01 +02:00
|
|
|
but those above are are explicitly listed afterwards. A flag code unit
|
|
|
|
tells whether the bitmap is present, and whether this is a negated class or
|
|
|
|
not. */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CLASS_NOT:
|
|
|
|
case META_CLASS:
|
2016-12-23 19:34:10 +01:00
|
|
|
matched_char = TRUE;
|
2016-10-02 18:01:01 +02:00
|
|
|
negate_class = meta == META_CLASS_NOT;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* We can optimize the case of a single character in a class by generating
|
|
|
|
OP_CHAR or OP_CHARI if it's positive, or OP_NOT or OP_NOTI if it's
|
|
|
|
negative. In the negative case there can be no first char if this item is
|
|
|
|
first, whatever repeat count may follow. In the case of reqcu, save the
|
|
|
|
previous value for reinstating. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* NOTE: at present this optimization is not effective if the only
|
|
|
|
character in a class in 32-bit, non-UCP mode has its top bit set. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (pptr[1] < META_END && pptr[2] == META_CLASS_END)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
uint32_t d;
|
|
|
|
#endif
|
|
|
|
uint32_t c = pptr[1];
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
pptr += 2; /* Move on to class end */
|
|
|
|
if (meta == META_CLASS) /* A positive one-char class can be */
|
|
|
|
{ /* handled as a normal literal character. */
|
|
|
|
meta = c; /* Set up the character */
|
|
|
|
goto NORMAL_CHAR_SET;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a negative one-character class */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For caseless UTF mode, check whether this character has more than
|
|
|
|
one other case. If so, generate a special OP_NOTPROP item instead of
|
|
|
|
OP_NOTI. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (utf && (options & PCRE2_CASELESS) != 0 &&
|
|
|
|
(d = UCD_CASESET(c)) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = OP_NOTPROP;
|
|
|
|
*code++ = PT_CLIST;
|
|
|
|
*code++ = d;
|
|
|
|
break; /* We are finished with this class */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
|
|
|
/* Char has only one other case, or UCP not available */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = ((options & PCRE2_CASELESS) != 0)? OP_NOTI: OP_NOT;
|
|
|
|
code += PUTCHAR(c, code);
|
|
|
|
break; /* We are finished with this class */
|
|
|
|
} /* End of 1-char optimization */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle character classes that contain more than just one literal
|
|
|
|
character. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-11-20 17:55:36 +01:00
|
|
|
/* If a non-extended class contains a negative special such as \S, we need
|
|
|
|
to flip the negation flag at the end, so that support for characters > 255
|
|
|
|
works correctly (they are all included in the class). An extended class may
|
2015-11-27 18:03:58 +01:00
|
|
|
need to insert specific matching or non-matching code for wide characters.
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-11-27 18:03:58 +01:00
|
|
|
should_flip_negation = match_all_or_no_wide_chars = FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Extended class (xclass) will be used when characters > 255
|
|
|
|
might match. */
|
|
|
|
|
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
xclass = FALSE;
|
|
|
|
class_uchardata = code + LINK_SIZE + 2; /* For XCLASS items */
|
|
|
|
class_uchardata_base = class_uchardata; /* Save the start */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* For optimization purposes, we track some properties of the class:
|
2016-10-02 18:01:01 +02:00
|
|
|
class_has_8bitchar will be non-zero if the class contains at least one
|
|
|
|
character with a code point less than 256; xclass_has_prop will be TRUE if
|
|
|
|
Unicode property checks are present in the class. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
class_has_8bitchar = 0;
|
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
xclass_has_prop = FALSE;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Initialize the 256-bit (32-byte) bit map to all zeros. We build the map
|
|
|
|
in a temporary bit of memory, in case the class contains fewer than two
|
|
|
|
8-bit characters because in that case the compiled code doesn't use the bit
|
|
|
|
map. */
|
|
|
|
|
|
|
|
memset(classbits, 0, 32 * sizeof(uint8_t));
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process items until META_CLASS_END is reached. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
while ((meta = *(++pptr)) != META_CLASS_END)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle POSIX classes such as [:alpha:] etc. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta == META_POSIX || meta == META_POSIX_NEG)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
BOOL local_negate = (meta == META_POSIX_NEG);
|
|
|
|
int posix_class = *(++pptr);
|
|
|
|
int taboffset, tabopt;
|
2014-06-14 20:29:51 +02:00
|
|
|
uint8_t pbits[32];
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
should_flip_negation = local_negate; /* Note negative special */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If matching is caseless, upper and lower are converted to alpha.
|
|
|
|
This relies on the fact that the class table starts with alpha,
|
|
|
|
lower, upper as the first 3 entries. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
if ((options & PCRE2_CASELESS) != 0 && posix_class <= 2)
|
|
|
|
posix_class = 0;
|
|
|
|
|
|
|
|
/* When PCRE2_UCP is set, some of the POSIX classes are converted to
|
2016-10-02 18:01:01 +02:00
|
|
|
different escape sequences that use Unicode properties \p or \P.
|
|
|
|
Others that are not available via \p or \P have to generate
|
|
|
|
XCL_PROP/XCL_NOTPROP directly, which is done here. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-09-19 09:43:39 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((options & PCRE2_UCP) != 0) switch(posix_class)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
case PC_GRAPH:
|
|
|
|
case PC_PRINT:
|
|
|
|
case PC_PUNCT:
|
|
|
|
*class_uchardata++ = local_negate? XCL_NOTPROP : XCL_PROP;
|
|
|
|
*class_uchardata++ = (PCRE2_UCHAR)
|
|
|
|
((posix_class == PC_GRAPH)? PT_PXGRAPH :
|
|
|
|
(posix_class == PC_PRINT)? PT_PXPRINT : PT_PXPUNCT);
|
|
|
|
*class_uchardata++ = 0;
|
|
|
|
xclass_has_prop = TRUE;
|
|
|
|
goto CONTINUE_CLASS;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For the other POSIX classes (ascii, xdigit) we are going to
|
|
|
|
fall through to the non-UCP case and build a bit map for
|
|
|
|
characters with code points less than 256. However, if we are in
|
|
|
|
a negated POSIX class, characters with code points greater than
|
|
|
|
255 must either all match or all not match, depending on whether
|
|
|
|
the whole class is not or is negated. For example, for
|
|
|
|
[[:^ascii:]... they must all match, whereas for [^[:^xdigit:]...
|
|
|
|
they must not.
|
|
|
|
|
|
|
|
In the special case where there are no xclass items, this is
|
|
|
|
automatically handled by the use of OP_CLASS or OP_NCLASS, but an
|
|
|
|
explicit range is needed for OP_XCLASS. Setting a flag here
|
|
|
|
causes the range to be generated later when it is known that
|
2016-12-28 13:26:12 +01:00
|
|
|
OP_XCLASS is required. In the 8-bit library this is relevant only in
|
2016-12-26 18:11:18 +01:00
|
|
|
utf mode, since no wide characters can exist otherwise. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
2016-12-26 18:11:18 +01:00
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
|
|
|
if (utf)
|
2016-12-28 13:26:12 +01:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
match_all_or_no_wide_chars |= local_negate;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-09-19 09:43:39 +02:00
|
|
|
#endif /* SUPPORT_UNICODE */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* In the non-UCP case, or when UCP makes no difference, we build the
|
2016-10-02 18:01:01 +02:00
|
|
|
bit map for the POSIX class in a chunk of local store because we may
|
|
|
|
be adding and subtracting from it, and we don't want to subtract bits
|
|
|
|
that may be in the main map already. At the end we or the result into
|
|
|
|
the bit map that is being built. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
posix_class *= 3;
|
|
|
|
|
|
|
|
/* Copy in the first table (always present) */
|
|
|
|
|
|
|
|
memcpy(pbits, cbits + posix_class_maps[posix_class],
|
|
|
|
32 * sizeof(uint8_t));
|
|
|
|
|
|
|
|
/* If there is a second table, add or remove it as required. */
|
|
|
|
|
|
|
|
taboffset = posix_class_maps[posix_class + 1];
|
|
|
|
tabopt = posix_class_maps[posix_class + 2];
|
|
|
|
|
|
|
|
if (taboffset >= 0)
|
|
|
|
{
|
|
|
|
if (tabopt >= 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) pbits[i] |= cbits[(int)i + taboffset];
|
2014-06-14 20:29:51 +02:00
|
|
|
else
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) pbits[i] &= ~cbits[(int)i + taboffset];
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Now see if we need to remove any special characters. An option
|
|
|
|
value of 1 removes vertical space and 2 removes underscore. */
|
|
|
|
|
|
|
|
if (tabopt < 0) tabopt = -tabopt;
|
|
|
|
if (tabopt == 1) pbits[1] &= ~0x3c;
|
|
|
|
else if (tabopt == 2) pbits[11] &= 0x7f;
|
|
|
|
|
|
|
|
/* Add the POSIX table or its complement into the main table that is
|
|
|
|
being built and we are done. */
|
|
|
|
|
|
|
|
if (local_negate)
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= ~pbits[i];
|
2014-06-14 20:29:51 +02:00
|
|
|
else
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= pbits[i];
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Every class contains at least one < 256 character. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
class_has_8bitchar = 1;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto CONTINUE_CLASS; /* End of POSIX handling */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Other than POSIX classes, the only items we should encounter are
|
|
|
|
\d-type escapes and literal characters (possibly as ranges). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta == META_BIGVALUE)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
meta = *(++pptr);
|
|
|
|
goto CLASS_LITERAL;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Any other non-literal must be an escape */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-23 18:17:57 +01:00
|
|
|
if (meta >= META_END)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (META_CODE(meta) != META_ESCAPE)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef DEBUG_SHOW_PARSED
|
|
|
|
fprintf(stderr, "** Unrecognized parsed pattern item 0x%.8x "
|
2016-12-27 12:50:28 +01:00
|
|
|
"in character class\n", meta);
|
2016-10-02 18:01:01 +02:00
|
|
|
#endif
|
|
|
|
*errorcodeptr = ERR89; /* Internal error - unrecognized. */
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
escape = META_DATA(meta);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Every class contains at least one < 256 character. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
class_has_8bitchar++;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(escape)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_d:
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_digit];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_D:
|
|
|
|
should_flip_negation = TRUE;
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_digit];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_w:
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_word];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_W:
|
|
|
|
should_flip_negation = TRUE;
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_word];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Perl 5.004 onwards omitted VT from \s, but restored it at Perl
|
|
|
|
5.18. Before PCRE 8.34, we had to preserve the VT bit if it was
|
|
|
|
previously set by something earlier in the character class.
|
|
|
|
Luckily, the value of CHAR_VT is 0x0b in both ASCII and EBCDIC, so
|
|
|
|
we could just adjust the appropriate bit. From PCRE 8.34 we no
|
|
|
|
longer treat \s and \S specially. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_s:
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= cbits[i+cbit_space];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_S:
|
|
|
|
should_flip_negation = TRUE;
|
|
|
|
for (i = 0; i < 32; i++) classbits[i] |= ~cbits[i+cbit_space];
|
|
|
|
break;
|
2017-01-11 17:40:35 +01:00
|
|
|
|
|
|
|
/* When adding the horizontal or vertical space lists to a class, or
|
|
|
|
their complements, disable PCRE2_CASELESS, because it justs wastes
|
|
|
|
time, and in the "not-x" UTF cases can create unwanted duplicates in
|
|
|
|
the XCLASS list (provoked by characters that have more than one other
|
2017-01-03 19:17:31 +01:00
|
|
|
case and by both cases being in the same "not-x" sublist). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_h:
|
2017-01-11 17:40:35 +01:00
|
|
|
(void)add_list_to_class(classbits, &class_uchardata,
|
2017-01-03 19:17:31 +01:00
|
|
|
options & ~PCRE2_CASELESS, cb, PRIV(hspace_list), NOTACHAR);
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_H:
|
2017-01-11 17:40:35 +01:00
|
|
|
(void)add_not_list_to_class(classbits, &class_uchardata,
|
2017-01-03 19:17:31 +01:00
|
|
|
options & ~PCRE2_CASELESS, cb, PRIV(hspace_list));
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_v:
|
2017-01-11 17:40:35 +01:00
|
|
|
(void)add_list_to_class(classbits, &class_uchardata,
|
2017-01-03 19:17:31 +01:00
|
|
|
options & ~PCRE2_CASELESS, cb, PRIV(vspace_list), NOTACHAR);
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_V:
|
2017-01-11 17:40:35 +01:00
|
|
|
(void)add_not_list_to_class(classbits, &class_uchardata,
|
2017-01-03 19:17:31 +01:00
|
|
|
options & ~PCRE2_CASELESS, cb, PRIV(vspace_list));
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2017-08-12 18:22:52 +02:00
|
|
|
/* If Unicode is not supported, \P and \p are not allowed and are
|
|
|
|
faulted at parse time, so will never appear here. */
|
|
|
|
|
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-10-02 18:01:01 +02:00
|
|
|
case ESC_p:
|
|
|
|
case ESC_P:
|
2015-07-24 20:18:05 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t ptype = *(++pptr) >> 16;
|
|
|
|
uint32_t pdata = *pptr & 0xffff;
|
|
|
|
*class_uchardata++ = (escape == ESC_p)? XCL_PROP : XCL_NOTPROP;
|
|
|
|
*class_uchardata++ = ptype;
|
|
|
|
*class_uchardata++ = pdata;
|
|
|
|
xclass_has_prop = TRUE;
|
|
|
|
class_has_8bitchar--; /* Undo! */
|
2015-07-24 20:18:05 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2017-08-12 18:22:52 +02:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
goto CONTINUE_CLASS;
|
|
|
|
} /* End handling \d-type escapes */
|
2015-07-24 20:18:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A literal character may be followed by a range meta. At parse time
|
|
|
|
there are checks for out-of-order characters, for ranges where the two
|
|
|
|
characters are equal, and for hyphens that cannot indicate a range. At
|
|
|
|
this point, therefore, no checking is needed. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t c, d;
|
|
|
|
|
|
|
|
CLASS_LITERAL:
|
|
|
|
c = d = meta;
|
|
|
|
|
|
|
|
/* Remember if \r or \n were explicitly used */
|
|
|
|
|
|
|
|
if (c == CHAR_CR || c == CHAR_NL) cb->external_flags |= PCRE2_HASCRORLF;
|
|
|
|
|
|
|
|
/* Process a character range */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (pptr[1] == META_RANGE_LITERAL || pptr[1] == META_RANGE_ESCAPED)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef EBCDIC
|
|
|
|
BOOL range_is_literal = (pptr[1] == META_RANGE_LITERAL);
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
pptr += 2;
|
|
|
|
d = *pptr;
|
|
|
|
if (d == META_BIGVALUE) d = *(++pptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember an explicit \r or \n, and add the range to the class. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (d == CHAR_CR || d == CHAR_NL) cb->external_flags |= PCRE2_HASCRORLF;
|
|
|
|
|
|
|
|
/* In an EBCDIC environment, Perl treats alphabetic ranges specially
|
|
|
|
because there are holes in the encoding, and simply using the range
|
|
|
|
A-Z (for example) would include the characters in the holes. This
|
|
|
|
applies only to literal ranges; [\xC1-\xE9] is different to [A-Z]. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef EBCDIC
|
|
|
|
if (range_is_literal &&
|
|
|
|
(cb->ctypes[c] & ctype_letter) != 0 &&
|
|
|
|
(cb->ctypes[d] & ctype_letter) != 0 &&
|
|
|
|
(d <= CHAR_z) == (d <= CHAR_z))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t uc = (d <= CHAR_z)? 0 : 64;
|
|
|
|
uint32_t C = d - uc;
|
|
|
|
uint32_t D = d - uc;
|
|
|
|
|
|
|
|
if (C <= CHAR_i)
|
|
|
|
{
|
|
|
|
class_has_8bitchar +=
|
|
|
|
add_to_class(classbits, &class_uchardata, options, cb, C + uc,
|
|
|
|
((D < CHAR_i)? D : CHAR_i) + uc);
|
|
|
|
C = CHAR_j;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (C <= D && C <= CHAR_r)
|
|
|
|
{
|
|
|
|
class_has_8bitchar +=
|
|
|
|
add_to_class(classbits, &class_uchardata, options, cb, C + uc,
|
|
|
|
((D < CHAR_r)? D : CHAR_r) + uc);
|
|
|
|
C = CHAR_s;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (C <= D)
|
|
|
|
{
|
|
|
|
class_has_8bitchar +=
|
|
|
|
add_to_class(classbits, &class_uchardata, options, cb, C + uc,
|
|
|
|
D + uc);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
#endif
|
|
|
|
/* Not an EBCDIC special range */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
class_has_8bitchar +=
|
|
|
|
add_to_class(classbits, &class_uchardata, options, cb, c, d);
|
|
|
|
goto CONTINUE_CLASS; /* Go get the next char in the class */
|
|
|
|
} /* End of range handling */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a single character. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
class_has_8bitchar +=
|
|
|
|
add_to_class(classbits, &class_uchardata, options, cb, meta, meta);
|
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Continue to the next item in the class. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
CONTINUE_CLASS:
|
|
|
|
|
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
2016-08-03 19:22:59 +02:00
|
|
|
/* If any wide characters or Unicode properties have been encountered,
|
|
|
|
set xclass = TRUE. Then, in the pre-compile phase, accumulate the length
|
2016-10-02 18:01:01 +02:00
|
|
|
of the extra data and reset the pointer. This is so that very large
|
|
|
|
classes that contain a zillion wide characters or Unicode property tests
|
2018-06-17 16:13:28 +02:00
|
|
|
do not overwrite the workspace (which is on the stack). */
|
2015-03-25 20:26:27 +01:00
|
|
|
|
|
|
|
if (class_uchardata > class_uchardata_base)
|
|
|
|
{
|
|
|
|
xclass = TRUE;
|
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
|
|
|
*lengthptr += class_uchardata - class_uchardata_base;
|
|
|
|
class_uchardata = class_uchardata_base;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2015-03-25 20:26:27 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
continue; /* Needed to avoid error when not supporting wide chars */
|
2015-03-25 20:26:27 +01:00
|
|
|
} /* End of main class-processing loop */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If this class is the first thing in the branch, there can be no first
|
|
|
|
char setting, whatever the repeat count. Any reqcu setting must remain
|
2014-06-14 20:29:51 +02:00
|
|
|
unchanged after any kind of repeat. */
|
|
|
|
|
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
|
|
|
|
2015-10-09 18:06:53 +02:00
|
|
|
/* If there are characters with values > 255, or Unicode property settings
|
|
|
|
(\p or \P), we have to compile an extended class, with its own opcode,
|
|
|
|
unless there were no property settings and there was a negated special such
|
|
|
|
as \S in the class, and PCRE2_UCP is not set, because in that case all
|
2015-11-27 18:03:58 +01:00
|
|
|
characters > 255 are in or not in the class, so any that were explicitly
|
|
|
|
given as well can be ignored.
|
2015-11-20 17:55:36 +01:00
|
|
|
|
|
|
|
In the UCP case, if certain negated POSIX classes ([:^ascii:] or
|
2015-11-27 18:03:58 +01:00
|
|
|
[^:xdigit:]) were present in a class, we either have to match or not match
|
|
|
|
all wide characters (depending on whether the whole class is or is not
|
|
|
|
negated). This requirement is indicated by match_all_or_no_wide_chars being
|
|
|
|
true. We do this by including an explicit range, which works in both cases.
|
2016-12-26 18:11:18 +01:00
|
|
|
This applies only in UTF and 16-bit and 32-bit non-UTF modes, since there
|
|
|
|
cannot be any wide characters in 8-bit non-UTF mode.
|
2015-11-20 17:55:36 +01:00
|
|
|
|
2016-08-03 19:22:59 +02:00
|
|
|
When there *are* properties in a positive UTF-8 or any 16-bit or 32_bit
|
|
|
|
class where \S etc is present without PCRE2_UCP, causing an extended class
|
|
|
|
to be compiled, we make sure that all characters > 255 are included by
|
|
|
|
forcing match_all_or_no_wide_chars to be true.
|
|
|
|
|
2015-11-20 17:55:36 +01:00
|
|
|
If, when generating an xclass, there are no characters < 256, we can omit
|
|
|
|
the bitmap in the actual compiled code. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-08-03 19:22:59 +02:00
|
|
|
#ifdef SUPPORT_WIDE_CHARS /* Defined for 16/32 bits, or 8-bit with Unicode */
|
|
|
|
if (xclass && (
|
2014-09-19 09:43:39 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
2016-08-03 19:22:59 +02:00
|
|
|
(options & PCRE2_UCP) != 0 ||
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2016-08-03 19:22:59 +02:00
|
|
|
xclass_has_prop || !should_flip_negation))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-08-03 19:22:59 +02:00
|
|
|
if (match_all_or_no_wide_chars || (
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 8
|
|
|
|
utf &&
|
|
|
|
#endif
|
|
|
|
should_flip_negation && !negate_class && (options & PCRE2_UCP) == 0))
|
2015-11-20 17:55:36 +01:00
|
|
|
{
|
|
|
|
*class_uchardata++ = XCL_RANGE;
|
2016-08-03 19:22:59 +02:00
|
|
|
if (utf) /* Will always be utf in the 8-bit library */
|
|
|
|
{
|
|
|
|
class_uchardata += PRIV(ord2utf)(0x100, class_uchardata);
|
|
|
|
class_uchardata += PRIV(ord2utf)(MAX_UTF_CODE_POINT, class_uchardata);
|
|
|
|
}
|
|
|
|
else /* Can only happen for the 16-bit & 32-bit libraries */
|
|
|
|
{
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 16
|
|
|
|
*class_uchardata++ = 0x100;
|
|
|
|
*class_uchardata++ = 0xffffu;
|
|
|
|
#elif PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
*class_uchardata++ = 0x100;
|
|
|
|
*class_uchardata++ = 0xffffffffu;
|
|
|
|
#endif
|
|
|
|
}
|
2015-11-20 17:55:36 +01:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
*class_uchardata++ = XCL_END; /* Marks the end of extra data */
|
|
|
|
*code++ = OP_XCLASS;
|
|
|
|
code += LINK_SIZE;
|
|
|
|
*code = negate_class? XCL_NOT:0;
|
|
|
|
if (xclass_has_prop) *code |= XCL_HASPROP;
|
|
|
|
|
|
|
|
/* If the map is required, move up the extra data to make room for it;
|
|
|
|
otherwise just move the code pointer to the end of the extra data. */
|
|
|
|
|
|
|
|
if (class_has_8bitchar > 0)
|
|
|
|
{
|
|
|
|
*code++ |= XCL_MAP;
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(code + (32 / sizeof(PCRE2_UCHAR)), code,
|
2014-06-14 20:29:51 +02:00
|
|
|
CU2BYTES(class_uchardata - code));
|
|
|
|
if (negate_class && !xclass_has_prop)
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) classbits[i] = ~classbits[i];
|
2014-06-14 20:29:51 +02:00
|
|
|
memcpy(code, classbits, 32);
|
|
|
|
code = class_uchardata + (32 / sizeof(PCRE2_UCHAR));
|
|
|
|
}
|
|
|
|
else code = class_uchardata;
|
|
|
|
|
|
|
|
/* Now fill in the complete length of the item */
|
|
|
|
|
|
|
|
PUT(previous, 1, (int)(code - previous));
|
|
|
|
break; /* End of class handling */
|
|
|
|
}
|
2016-08-03 19:22:59 +02:00
|
|
|
#endif /* SUPPORT_WIDE_CHARS */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* If there are no characters > 255, or they are all to be included or
|
|
|
|
excluded, set the opcode to OP_CLASS or OP_NCLASS, depending on whether the
|
|
|
|
whole class was negated and whether there were negative specials such as \S
|
|
|
|
(non-UCP) in the class. Then copy the 32-byte map into the code vector,
|
|
|
|
negating it if necessary. */
|
|
|
|
|
|
|
|
*code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS;
|
|
|
|
if (lengthptr == NULL) /* Save time in the pre-compile phase */
|
|
|
|
{
|
|
|
|
if (negate_class)
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < 32; i++) classbits[i] = ~classbits[i];
|
2014-06-14 20:29:51 +02:00
|
|
|
memcpy(code, classbits, 32);
|
|
|
|
}
|
|
|
|
code += 32 / sizeof(PCRE2_UCHAR);
|
2016-10-02 18:01:01 +02:00
|
|
|
break; /* End of class processing */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Deal with (*VERB)s. */
|
2015-07-17 15:41:09 +02:00
|
|
|
|
2017-10-29 17:58:38 +01:00
|
|
|
/* Check for open captures before ACCEPT and close those that are within
|
|
|
|
the same assertion level, also converting ACCEPT to ASSERT_ACCEPT in an
|
|
|
|
assertion. In the first pass, just accumulate the length required;
|
2016-10-02 18:01:01 +02:00
|
|
|
otherwise hitting (*ACCEPT) inside many nested parentheses can cause
|
|
|
|
workspace overflow. Do not set firstcu after *ACCEPT. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ACCEPT:
|
|
|
|
cb->had_accept = TRUE;
|
2017-10-29 17:58:38 +01:00
|
|
|
for (oc = cb->open_caps;
|
|
|
|
oc != NULL && oc->assert_depth >= cb->assert_depth;
|
|
|
|
oc = oc->next)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (lengthptr != NULL)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*lengthptr += CU2BYTES(1) + IMM2_SIZE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = OP_CLOSE;
|
|
|
|
PUT2INC(code, 0, oc->number);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = (cb->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT;
|
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE:
|
|
|
|
case META_SKIP:
|
|
|
|
cb->had_pruneorskip = TRUE;
|
|
|
|
/* Fall through */
|
|
|
|
case META_COMMIT:
|
|
|
|
case META_FAIL:
|
|
|
|
*code++ = verbops[(meta - META_MARK) >> 16];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_THEN:
|
|
|
|
cb->external_flags |= PCRE2_HASTHEN;
|
|
|
|
*code++ = OP_THEN;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle verbs with arguments. Arguments can be very long, especially in
|
|
|
|
16- and 32-bit modes, and can overflow the workspace in the first pass.
|
|
|
|
However, the argument length is constrained to be small enough to fit in
|
|
|
|
one code unit. This check happens in parse_regex(). In the first pass,
|
|
|
|
instead of putting the argument into memory, we just update the length
|
|
|
|
counter and set up an empty argument. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_THEN_ARG:
|
|
|
|
cb->external_flags |= PCRE2_HASTHEN;
|
|
|
|
goto VERB_ARG;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE_ARG:
|
|
|
|
case META_SKIP_ARG:
|
|
|
|
cb->had_pruneorskip = TRUE;
|
|
|
|
/* Fall through */
|
|
|
|
case META_MARK:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_COMMIT_ARG:
|
2016-10-02 18:01:01 +02:00
|
|
|
VERB_ARG:
|
|
|
|
*code++ = verbops[(meta - META_MARK) >> 16];
|
|
|
|
/* The length is in characters. */
|
|
|
|
verbarglen = *(++pptr);
|
|
|
|
verbculen = 0;
|
|
|
|
tempcode = code++;
|
|
|
|
for (i = 0; i < (int)verbarglen; i++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
meta = *(++pptr);
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (utf) mclength = PRIV(ord2utf)(meta, mcbuffer); else
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
mclength = 1;
|
|
|
|
mcbuffer[0] = meta;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
if (lengthptr != NULL) *lengthptr += mclength; else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
memcpy(code, mcbuffer, CU2BYTES(mclength));
|
|
|
|
code += mclength;
|
|
|
|
verbculen += mclength;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*tempcode = verbculen; /* Fill in the code unit length */
|
|
|
|
*code++ = 0; /* Terminating zero */
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle options change. The new setting must be passed back for use in
|
|
|
|
subsequent branches. Reset the greedy defaults and the case value for
|
|
|
|
firstcu and reqcu. */
|
|
|
|
|
|
|
|
case META_OPTIONS:
|
|
|
|
*optionsptr = options = *(++pptr);
|
|
|
|
greedy_default = ((options & PCRE2_UNGREEDY) != 0);
|
|
|
|
greedy_non_default = greedy_default ^ 1;
|
|
|
|
req_caseopt = ((options & PCRE2_CASELESS) != 0)? REQ_CASELESS : 0;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle conditional subpatterns. The case of (?(Rdigits) is ambiguous
|
|
|
|
because it could be a numerical check on recursion, or a name check on a
|
|
|
|
group's being set. The pre-pass sets up META_COND_RNUMBER as a name so that
|
|
|
|
we can handle it either way. We first try for a name; if not found, process
|
|
|
|
the number. */
|
|
|
|
|
|
|
|
case META_COND_RNUMBER: /* (?(Rdigits) */
|
|
|
|
case META_COND_NAME: /* (?(name) or (?'name') or ?(<name>) */
|
|
|
|
case META_COND_RNAME: /* (?(R&name) - test for recursion */
|
|
|
|
bravalue = OP_COND;
|
|
|
|
{
|
|
|
|
int count, index;
|
|
|
|
PCRE2_SPTR name;
|
|
|
|
named_group *ng = cb->named_groups;
|
|
|
|
uint32_t length = *(++pptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
name = cb->start_pattern + offset;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the first pass, the names generated in the pre-pass are available,
|
|
|
|
but the main name table has not yet been created. Scan the list of names
|
|
|
|
generated in the pre-pass in order to get a number and whether or not
|
|
|
|
this name is duplicated. If it is not duplicated, we can handle it as a
|
|
|
|
numerical group. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < cb->names_found; i++, ng++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (length == ng->length &&
|
|
|
|
PRIV(strncmp)(name, ng->name, length) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!ng->isdup)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
code[1+LINK_SIZE] = (meta == META_COND_RNAME)? OP_RREF : OP_CREF;
|
|
|
|
PUT2(code, 2+LINK_SIZE, ng->number);
|
|
|
|
if (ng->number > cb->top_backref) cb->top_backref = ng->number;
|
|
|
|
skipunits = 1+IMM2_SIZE;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
break; /* Found a duplicated name */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the name was not found we have a bad reference, unless we are
|
|
|
|
dealing with R<digits>, which is treated as a recursion test by number.
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (i >= cb->names_found)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
groupnumber = 0;
|
|
|
|
if (meta == META_COND_RNUMBER)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 1; i < (int)length; i++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
groupnumber = groupnumber * 10 + name[i] - CHAR_0;
|
|
|
|
if (groupnumber > MAX_GROUP_NUMBER)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR61;
|
|
|
|
cb->erroroffset = offset + i;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta != META_COND_RNUMBER || groupnumber > cb->bracount)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR15;
|
|
|
|
cb->erroroffset = offset;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* (?Rdigits) treated as a recursion reference by number. A value of
|
|
|
|
zero (which is the result of both (?R) and (?R0)) means "any", and is
|
|
|
|
translated into RREF_ANY (which is 0xffff). */
|
|
|
|
|
|
|
|
if (groupnumber == 0) groupnumber = RREF_ANY;
|
|
|
|
code[1+LINK_SIZE] = OP_RREF;
|
|
|
|
PUT2(code, 2+LINK_SIZE, groupnumber);
|
|
|
|
skipunits = 1+IMM2_SIZE;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A duplicated name was found. Note that if an R<digits> name is found
|
|
|
|
(META_COND_RNUMBER), it is a reference test, not a recursion test. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code[1+LINK_SIZE] = (meta == META_COND_RNAME)? OP_RREF : OP_CREF;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* We have a duplicated name. In the compile pass we have to search the
|
|
|
|
main table in order to get the index and count values. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
count = 0; /* Values for first pass (avoids compiler warning) */
|
|
|
|
index = 0;
|
|
|
|
if (lengthptr == NULL && !find_dupname_details(name, length, &index,
|
2016-12-23 18:09:37 +01:00
|
|
|
&count, errorcodeptr, cb)) return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Add one to the opcode to change CREF/RREF into DNCREF/DNRREF and
|
|
|
|
insert appropriate data values. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code[1+LINK_SIZE]++;
|
|
|
|
skipunits = 1+2*IMM2_SIZE;
|
|
|
|
PUT2(code, 2+LINK_SIZE, index);
|
|
|
|
PUT2(code, 2+LINK_SIZE+IMM2_SIZE, count);
|
|
|
|
}
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
/* The DEFINE condition is always false. It's internal groups may never
|
2016-12-23 19:34:10 +01:00
|
|
|
be called, so matched_char must remain false, hence the jump to
|
2016-12-23 18:09:37 +01:00
|
|
|
GROUP_PROCESS rather than GROUP_PROCESS_NOTE_EMPTY. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_COND_DEFINE:
|
|
|
|
bravalue = OP_COND;
|
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
code[1+LINK_SIZE] = OP_DEFINE;
|
|
|
|
skipunits = 1;
|
|
|
|
goto GROUP_PROCESS;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Conditional test of a group's being set. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_COND_NUMBER:
|
|
|
|
bravalue = OP_COND;
|
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
groupnumber = *(++pptr);
|
|
|
|
if (groupnumber > cb->bracount)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR15;
|
|
|
|
cb->erroroffset = offset;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
if (groupnumber > cb->top_backref) cb->top_backref = groupnumber;
|
|
|
|
offset -= 2; /* Point at initial ( for too many branches error */
|
|
|
|
code[1+LINK_SIZE] = OP_CREF;
|
|
|
|
skipunits = 1+IMM2_SIZE;
|
|
|
|
PUT2(code, 2+LINK_SIZE, groupnumber);
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Test for the PCRE2 version. */
|
|
|
|
|
|
|
|
case META_COND_VERSION:
|
|
|
|
bravalue = OP_COND;
|
|
|
|
if (pptr[1] > 0)
|
|
|
|
code[1+LINK_SIZE] = ((PCRE2_MAJOR > pptr[2]) ||
|
|
|
|
(PCRE2_MAJOR == pptr[2] && PCRE2_MINOR >= pptr[3]))?
|
|
|
|
OP_TRUE : OP_FALSE;
|
|
|
|
else
|
|
|
|
code[1+LINK_SIZE] = (PCRE2_MAJOR == pptr[2] && PCRE2_MINOR == pptr[3])?
|
|
|
|
OP_TRUE : OP_FALSE;
|
|
|
|
skipunits = 1;
|
|
|
|
pptr += 3;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2016-11-18 19:59:37 +01:00
|
|
|
/* The condition is an assertion, possibly preceded by a callout. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
case META_COND_ASSERT:
|
|
|
|
bravalue = OP_COND;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle all kinds of nested bracketed groups. The non-capturing,
|
|
|
|
non-conditional cases are here; others come to GROUP_PROCESS via goto. */
|
|
|
|
|
|
|
|
case META_LOOKAHEAD:
|
|
|
|
bravalue = OP_ASSERT;
|
|
|
|
cb->assert_depth += 1;
|
|
|
|
goto GROUP_PROCESS;
|
|
|
|
|
|
|
|
/* Optimize (?!) to (*FAIL) unless it is quantified - which is a weird
|
|
|
|
thing to do, but Perl allows all assertions to be quantified, and when
|
|
|
|
they contain capturing parentheses there may be a potential use for
|
|
|
|
this feature. Not that that applies to a quantified (?!) but we allow
|
|
|
|
it for uniformity. */
|
|
|
|
|
|
|
|
case META_LOOKAHEADNOT:
|
|
|
|
if (pptr[1] == META_KET &&
|
|
|
|
(pptr[2] < META_ASTERISK || pptr[2] > META_MINMAX_QUERY))
|
|
|
|
{
|
|
|
|
*code++ = OP_FAIL;
|
|
|
|
pptr++;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
bravalue = OP_ASSERT_NOT;
|
|
|
|
cb->assert_depth += 1;
|
|
|
|
goto GROUP_PROCESS;
|
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_LOOKBEHIND:
|
|
|
|
bravalue = OP_ASSERTBACK;
|
|
|
|
cb->assert_depth += 1;
|
|
|
|
goto GROUP_PROCESS;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
bravalue = OP_ASSERTBACK_NOT;
|
|
|
|
cb->assert_depth += 1;
|
|
|
|
goto GROUP_PROCESS;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ATOMIC:
|
|
|
|
bravalue = OP_ONCE;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_NOCAPTURE:
|
|
|
|
bravalue = OP_BRA;
|
|
|
|
/* Fall through */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Process nested bracketed regex. The nesting depth is maintained for the
|
|
|
|
benefit of the stackguard function. The test for too deep nesting is now
|
2016-12-23 19:34:10 +01:00
|
|
|
done in parse_regex(). Assertion and DEFINE groups come to GROUP_PROCESS;
|
|
|
|
others come to GROUP_PROCESS_NOTE_EMPTY, to indicate that we need to take
|
2016-12-23 18:09:37 +01:00
|
|
|
note of whether or not they may match an empty string. */
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
GROUP_PROCESS_NOTE_EMPTY:
|
2016-12-23 19:34:10 +01:00
|
|
|
note_group_empty = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
GROUP_PROCESS:
|
|
|
|
cb->parens_depth += 1;
|
|
|
|
*code = bravalue;
|
|
|
|
pptr++;
|
|
|
|
tempcode = code;
|
|
|
|
tempreqvary = cb->req_varyopt; /* Save value before group */
|
|
|
|
length_prevgroup = 0; /* Initialize for pre-compile phase */
|
2015-07-22 11:29:09 +02:00
|
|
|
|
2016-12-23 19:34:10 +01:00
|
|
|
if ((group_return =
|
2016-12-23 18:09:37 +01:00
|
|
|
compile_regex(
|
2016-10-02 18:01:01 +02:00
|
|
|
options, /* The option state */
|
|
|
|
&tempcode, /* Where to put code (updated) */
|
|
|
|
&pptr, /* Input pointer (updated) */
|
|
|
|
errorcodeptr, /* Where to put an error message */
|
|
|
|
skipunits, /* Skip over bracket number */
|
|
|
|
&subfirstcu, /* For possible first char */
|
|
|
|
&subfirstcuflags,
|
|
|
|
&subreqcu, /* For possible last char */
|
|
|
|
&subreqcuflags,
|
|
|
|
bcptr, /* Current branch chain */
|
|
|
|
cb, /* Compile data block */
|
|
|
|
(lengthptr == NULL)? NULL : /* Actual compile phase */
|
|
|
|
&length_prevgroup /* Pre-compile phase */
|
2016-12-23 18:09:37 +01:00
|
|
|
)) == 0)
|
|
|
|
return 0; /* Error */
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->parens_depth -= 1;
|
2015-07-22 11:01:50 +02:00
|
|
|
|
2016-12-23 19:34:10 +01:00
|
|
|
/* If that was a non-conditional significant group (not an assertion, not a
|
2016-12-23 18:09:37 +01:00
|
|
|
DEFINE) that matches at least one character, then the current item matches
|
|
|
|
a character. Conditionals are handled below. */
|
|
|
|
|
2016-12-23 19:34:10 +01:00
|
|
|
if (note_group_empty && bravalue != OP_COND && group_return > 0)
|
2016-12-23 18:09:37 +01:00
|
|
|
matched_char = TRUE;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If we've just compiled an assertion, pop the assert depth. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT)
|
|
|
|
cb->assert_depth -= 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* At the end of compiling, code is still pointing to the start of the
|
|
|
|
group, while tempcode has been updated to point past the end of the group.
|
|
|
|
The parsed pattern pointer (pptr) is on the closing META_KET.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
If this is a conditional bracket, check that there are no more than
|
|
|
|
two branches in the group, or just one if it's a DEFINE group. We do this
|
|
|
|
in the real compile phase, not in the pre-pass, where the whole group may
|
|
|
|
not be available. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (bravalue == OP_COND && lengthptr == NULL)
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR *tc = code;
|
|
|
|
int condcount = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
do {
|
|
|
|
condcount++;
|
|
|
|
tc += GET(tc,1);
|
|
|
|
}
|
|
|
|
while (*tc != OP_KET);
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A DEFINE group is never obeyed inline (the "condition" is always
|
|
|
|
false). It must have only one branch. Having checked this, change the
|
|
|
|
opcode to OP_FALSE. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (code[LINK_SIZE+1] == OP_DEFINE)
|
|
|
|
{
|
|
|
|
if (condcount > 1)
|
|
|
|
{
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
*errorcodeptr = ERR54;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
code[LINK_SIZE+1] = OP_FALSE;
|
|
|
|
bravalue = OP_DEFINE; /* A flag to suppress char handling below */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A "normal" conditional group. If there is just one branch, we must not
|
|
|
|
make use of its firstcu or reqcu, because this is equivalent to an
|
2016-12-23 19:34:10 +01:00
|
|
|
empty second branch. Also, it may match an empty string. If there are two
|
2016-12-23 18:09:37 +01:00
|
|
|
branches, this item must match a character if the group must. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
if (condcount > 2)
|
|
|
|
{
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
*errorcodeptr = ERR27;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
if (condcount == 1) subfirstcuflags = subreqcuflags = REQ_NONE;
|
2016-12-23 18:09:37 +01:00
|
|
|
else if (group_return > 0) matched_char = TRUE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the pre-compile phase, update the length by the length of the group,
|
|
|
|
less the brackets at either end. Then reduce the compiled code to just a
|
|
|
|
set of non-capturing brackets so that it doesn't use much memory if it is
|
|
|
|
duplicated by a quantifier.*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (lengthptr != NULL)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
*lengthptr += length_prevgroup - 2 - 2*LINK_SIZE;
|
|
|
|
code++; /* This already contains bravalue */
|
|
|
|
PUTINC(code, 0, 1 + LINK_SIZE);
|
|
|
|
*code++ = OP_KET;
|
|
|
|
PUTINC(code, 0, 1 + LINK_SIZE);
|
|
|
|
break; /* No need to waste time with special character handling */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Otherwise update the main code pointer to the end of the group. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code = tempcode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For a DEFINE group, required and first character settings are not
|
|
|
|
relevant. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (bravalue == OP_DEFINE) break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle updating of the required and first code units for other types of
|
|
|
|
group. Update for normal brackets of all kinds, and conditions with two
|
|
|
|
branches (see code above). If the bracket is followed by a quantifier with
|
|
|
|
zero repeat, we have to back off. Hence the definition of zeroreqcu and
|
|
|
|
zerofirstcu outside the main loop so that they can be accessed for the back
|
|
|
|
off. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
groupsetfirstcu = FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-18 13:22:40 +02:00
|
|
|
if (bravalue >= OP_ONCE) /* Not an assertion */
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
/* If we have not yet set a firstcu in this branch, take it from the
|
|
|
|
subpattern, remembering that it was set here so that a repeat of more
|
|
|
|
than one can replicate it as reqcu if necessary. If the subpattern has
|
|
|
|
no firstcu, set "none" for the whole branch. In both cases, a zero
|
|
|
|
repeat forces firstcu to "none". */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (firstcuflags == REQ_UNSET && subfirstcuflags != REQ_UNSET)
|
|
|
|
{
|
|
|
|
if (subfirstcuflags >= 0)
|
|
|
|
{
|
|
|
|
firstcu = subfirstcu;
|
|
|
|
firstcuflags = subfirstcuflags;
|
|
|
|
groupsetfirstcu = TRUE;
|
|
|
|
}
|
|
|
|
else firstcuflags = REQ_NONE;
|
|
|
|
zerofirstcuflags = REQ_NONE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If firstcu was previously set, convert the subpattern's firstcu
|
|
|
|
into reqcu if there wasn't one, using the vary flag that was in
|
|
|
|
existence beforehand. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (subfirstcuflags >= 0 && subreqcuflags < 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
subreqcu = subfirstcu;
|
|
|
|
subreqcuflags = subfirstcuflags | tempreqvary;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the subpattern set a required code unit (or set a first code unit
|
|
|
|
that isn't really the first code unit - see above), set it. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (subreqcuflags >= 0)
|
|
|
|
{
|
|
|
|
reqcu = subreqcu;
|
|
|
|
reqcuflags = subreqcuflags;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-18 13:22:40 +02:00
|
|
|
/* For a forward assertion, we take the reqcu, if set, provided that the
|
|
|
|
group has also set a firstcu. This can be helpful if the pattern that
|
|
|
|
follows the assertion doesn't set a different char. For example, it's
|
|
|
|
useful for /(?=abcde).+/. We can't set firstcu for an assertion, however
|
|
|
|
because it leads to incorrect effect for patterns such as /(?=a)a.+/ when
|
|
|
|
the "real" "a" would then become a reqcu instead of a firstcu. This is
|
|
|
|
overcome by a scan at the end if there's no firstcu, looking for an
|
|
|
|
asserted first char. A similar effect for patterns like /(?=.*X)X$/ means
|
|
|
|
we must only take the reqcu when the group also set a firstcu. Otherwise,
|
|
|
|
in that example, 'X' ends up set for both. */
|
|
|
|
|
|
|
|
else if (bravalue == OP_ASSERT && subreqcuflags >= 0 &&
|
|
|
|
subfirstcuflags >= 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
reqcu = subreqcu;
|
|
|
|
reqcuflags = subreqcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
break; /* End of nested group handling */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle named backreferences and recursions. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BACKREF_BYNAME:
|
|
|
|
case META_RECURSE_BYNAME:
|
|
|
|
{
|
|
|
|
int count, index;
|
|
|
|
PCRE2_SPTR name;
|
|
|
|
BOOL is_dupname = FALSE;
|
|
|
|
named_group *ng = cb->named_groups;
|
|
|
|
uint32_t length = *(++pptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
name = cb->start_pattern + offset;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the first pass, the names generated in the pre-pass are available,
|
|
|
|
but the main name table has not yet been created. Scan the list of names
|
|
|
|
generated in the pre-pass in order to get a number and whether or not
|
|
|
|
this name is duplicated. */
|
|
|
|
|
|
|
|
groupnumber = 0;
|
|
|
|
for (i = 0; i < cb->names_found; i++, ng++)
|
|
|
|
{
|
|
|
|
if (length == ng->length &&
|
|
|
|
PRIV(strncmp)(name, ng->name, length) == 0)
|
|
|
|
{
|
|
|
|
is_dupname = ng->isdup;
|
|
|
|
groupnumber = ng->number;
|
2015-11-03 21:04:23 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For a recursion, that's all that is needed. We can now go to
|
|
|
|
the code above that handles numerical recursion, applying it to
|
|
|
|
the first group with the given name. */
|
2015-11-03 21:04:23 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta == META_RECURSE_BYNAME)
|
|
|
|
{
|
|
|
|
meta_arg = groupnumber;
|
|
|
|
goto HANDLE_NUMERICAL_RECURSION;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For a back reference, update the back reference map and the
|
|
|
|
maximum back reference. Then, for each group, we must check to
|
|
|
|
see if it is recursive, that is, it is inside the group that it
|
|
|
|
references. A flag is set so that the group can be made atomic.
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->backref_map |= (groupnumber < 32)? (1u << groupnumber) : 1;
|
|
|
|
if (groupnumber > cb->top_backref)
|
|
|
|
cb->top_backref = groupnumber;
|
2015-08-30 19:47:36 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (oc = cb->open_caps; oc != NULL; oc = oc->next)
|
2015-11-03 20:14:31 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (oc->number == groupnumber)
|
2015-11-03 20:14:31 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
oc->flag = TRUE;
|
|
|
|
break;
|
2015-11-03 20:14:31 +01:00
|
|
|
}
|
|
|
|
}
|
2015-08-30 19:47:36 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the name was not found we have a bad reference. */
|
|
|
|
|
|
|
|
if (groupnumber == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorcodeptr = ERR15;
|
|
|
|
cb->erroroffset = offset;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If a back reference name is not duplicated, we can handle it as
|
|
|
|
a numerical reference. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (!is_dupname)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
meta_arg = groupnumber;
|
|
|
|
goto HANDLE_SINGLE_REFERENCE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If a back reference name is duplicated, we generate a different
|
|
|
|
opcode to a numerical back reference. In the second pass we must
|
|
|
|
search for the index and count in the final name table. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
count = 0; /* Values for first pass (avoids compiler warning) */
|
|
|
|
index = 0;
|
|
|
|
if (lengthptr == NULL && !find_dupname_details(name, length, &index,
|
2016-12-23 18:09:37 +01:00
|
|
|
&count, errorcodeptr, cb)) return 0;
|
2016-02-13 16:30:29 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
*code++ = ((options & PCRE2_CASELESS) != 0)? OP_DNREFI : OP_DNREF;
|
|
|
|
PUT2INC(code, 0, index);
|
|
|
|
PUT2INC(code, 0, count);
|
|
|
|
}
|
|
|
|
break;
|
2016-02-13 16:30:29 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle a numerical callout. */
|
|
|
|
|
|
|
|
case META_CALLOUT_NUMBER:
|
|
|
|
code[0] = OP_CALLOUT;
|
|
|
|
PUT(code, 1, pptr[1]); /* Offset to next pattern item */
|
|
|
|
PUT(code, 1 + LINK_SIZE, pptr[2]); /* Length of next pattern item */
|
|
|
|
code[1 + 2*LINK_SIZE] = pptr[3];
|
|
|
|
pptr += 3;
|
|
|
|
code += PRIV(OP_lengths)[OP_CALLOUT];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle a callout with a string argument. In the pre-pass we just compute
|
|
|
|
the length without generating anything. The length in pptr[3] includes both
|
|
|
|
delimiters; in the actual compile only the first one is copied, but a
|
|
|
|
terminating zero is added. Any doubled delimiters within the string make
|
|
|
|
this an overestimate, but it is not worth bothering about. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CALLOUT_STRING:
|
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
|
|
|
*lengthptr += pptr[3] + (1 + 4*LINK_SIZE);
|
|
|
|
pptr += 3;
|
|
|
|
SKIPOFFSET(pptr);
|
|
|
|
}
|
2015-10-28 10:25:31 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the real compile we can copy the string. The starting delimiter is
|
|
|
|
included so that the client can discover it if they want. We also pass the
|
|
|
|
start offset to help a script language give better error messages. */
|
2015-10-28 10:25:31 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
PCRE2_SPTR pp;
|
|
|
|
uint32_t delimiter;
|
|
|
|
uint32_t length = pptr[3];
|
|
|
|
PCRE2_UCHAR *callout_string = code + (1 + 4*LINK_SIZE);
|
|
|
|
|
|
|
|
code[0] = OP_CALLOUT_STR;
|
|
|
|
PUT(code, 1, pptr[1]); /* Offset to next pattern item */
|
|
|
|
PUT(code, 1 + LINK_SIZE, pptr[2]); /* Length of next pattern item */
|
|
|
|
|
|
|
|
pptr += 3;
|
|
|
|
GETPLUSOFFSET(offset, pptr); /* Offset to string in pattern */
|
|
|
|
pp = cb->start_pattern + offset;
|
|
|
|
delimiter = *callout_string++ = *pp++;
|
|
|
|
if (delimiter == CHAR_LEFT_CURLY_BRACKET)
|
|
|
|
delimiter = CHAR_RIGHT_CURLY_BRACKET;
|
|
|
|
PUT(code, 1 + 3*LINK_SIZE, (int)(offset + 1)); /* One after delimiter */
|
|
|
|
|
|
|
|
/* The syntax of the pattern was checked in the parsing scan. The length
|
|
|
|
includes both delimiters, but we have passed the opening one just above,
|
|
|
|
so we reduce length before testing it. The test is for > 1 because we do
|
|
|
|
not want to copy the final delimiter. This also ensures that pp[1] is
|
|
|
|
accessible. */
|
|
|
|
|
|
|
|
while (--length > 1)
|
|
|
|
{
|
|
|
|
if (*pp == delimiter && pp[1] == delimiter)
|
|
|
|
{
|
|
|
|
*callout_string++ = delimiter;
|
|
|
|
pp += 2;
|
|
|
|
length--;
|
|
|
|
}
|
|
|
|
else *callout_string++ = *pp++;
|
|
|
|
}
|
2017-05-26 19:14:36 +02:00
|
|
|
*callout_string++ = CHAR_NUL;
|
2015-08-30 19:47:36 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Set the length of the entire item, the advance to its end. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
PUT(code, 1 + 2*LINK_SIZE, (int)(callout_string - code));
|
|
|
|
code = callout_string;
|
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle repetition. The different types are all sorted out in the parsing
|
|
|
|
pass. */
|
|
|
|
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
case META_MINMAX:
|
|
|
|
repeat_min = *(++pptr);
|
|
|
|
repeat_max = *(++pptr);
|
|
|
|
goto REPEAT;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ASTERISK:
|
|
|
|
case META_ASTERISK_PLUS:
|
|
|
|
case META_ASTERISK_QUERY:
|
|
|
|
repeat_min = 0;
|
|
|
|
repeat_max = REPEAT_UNLIMITED;
|
|
|
|
goto REPEAT;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PLUS:
|
|
|
|
case META_PLUS_PLUS:
|
|
|
|
case META_PLUS_QUERY:
|
|
|
|
repeat_min = 1;
|
|
|
|
repeat_max = REPEAT_UNLIMITED;
|
|
|
|
goto REPEAT;
|
2015-03-29 19:34:04 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_QUERY:
|
|
|
|
case META_QUERY_PLUS:
|
|
|
|
case META_QUERY_QUERY:
|
|
|
|
repeat_min = 0;
|
|
|
|
repeat_max = 1;
|
2015-03-29 13:15:32 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
REPEAT:
|
2016-12-23 19:34:10 +01:00
|
|
|
if (previous_matched_char && repeat_min > 0) matched_char = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember whether this is a variable length repeat, and default to
|
|
|
|
single-char opcodes. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY;
|
|
|
|
op_type = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the repeat is {1} we can ignore it. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max == 1 && repeat_min == 1) goto END_REPEAT;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Adjust first and required code units for a zero repeat. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min == 0)
|
|
|
|
{
|
|
|
|
firstcu = zerofirstcu;
|
|
|
|
firstcuflags = zerofirstcuflags;
|
|
|
|
reqcu = zeroreqcu;
|
|
|
|
reqcuflags = zeroreqcuflags;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Note the greediness and possessiveness. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch (meta)
|
|
|
|
{
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
case META_ASTERISK_PLUS:
|
|
|
|
case META_PLUS_PLUS:
|
|
|
|
case META_QUERY_PLUS:
|
|
|
|
repeat_type = 0; /* Force greedy */
|
|
|
|
possessive_quantifier = TRUE;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
case META_ASTERISK_QUERY:
|
|
|
|
case META_PLUS_QUERY:
|
|
|
|
case META_QUERY_QUERY:
|
|
|
|
repeat_type = greedy_non_default;
|
|
|
|
possessive_quantifier = FALSE;
|
|
|
|
break;
|
2015-03-20 13:37:28 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
repeat_type = greedy_default;
|
|
|
|
possessive_quantifier = FALSE;
|
|
|
|
break;
|
|
|
|
}
|
2015-03-20 13:37:28 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Save start of previous item, in case we have to move it up in order to
|
|
|
|
insert something before it, and remember what it was. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
tempcode = previous;
|
|
|
|
op_previous = *previous;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now handle repetition for the different types of item. */
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch (op_previous)
|
|
|
|
{
|
|
|
|
/* If previous was a character or negated character match, abolish the
|
|
|
|
item and generate a repeat item instead. If a char item has a minimum of
|
|
|
|
more than one, ensure that it is set in reqcu - it might not be if a
|
|
|
|
sequence such as x{3} is the first thing in a branch because the x will
|
|
|
|
have gone into firstcu instead. */
|
|
|
|
|
|
|
|
case OP_CHAR:
|
|
|
|
case OP_CHARI:
|
|
|
|
case OP_NOT:
|
|
|
|
case OP_NOTI:
|
|
|
|
op_type = chartypeoffset[op_previous - OP_CHAR];
|
2014-08-26 13:46:21 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Deal with UTF characters that take up more than one code unit. */
|
|
|
|
|
|
|
|
#ifdef MAYBE_UTF_MULTI
|
|
|
|
if (utf && NOT_FIRSTCU(code[-1]))
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR *lastchar = code - 1;
|
|
|
|
BACKCHAR(lastchar);
|
|
|
|
mclength = (uint32_t)(code - lastchar); /* Length of UTF character */
|
|
|
|
memcpy(mcbuffer, lastchar, CU2BYTES(mclength)); /* Save the char */
|
|
|
|
}
|
|
|
|
else
|
|
|
|
#endif /* MAYBE_UTF_MULTI */
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle the case of a single code unit - either with no UTF support, or
|
|
|
|
with UTF disabled, or for a single-code-unit UTF character. */
|
|
|
|
{
|
|
|
|
mcbuffer[0] = code[-1];
|
|
|
|
mclength = 1;
|
|
|
|
if (op_previous <= OP_CHARI && repeat_min > 1)
|
2014-08-26 13:46:21 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
reqcu = mcbuffer[0];
|
|
|
|
reqcuflags = req_caseopt | cb->req_varyopt;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If previous was a character class or a back reference, we put the
|
|
|
|
repeat stuff after it, but just skip the item if the repeat was {0,0}. */
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
case OP_XCLASS:
|
|
|
|
#endif
|
|
|
|
case OP_CLASS:
|
|
|
|
case OP_NCLASS:
|
|
|
|
case OP_REF:
|
|
|
|
case OP_REFI:
|
|
|
|
case OP_DNREF:
|
|
|
|
case OP_DNREFI:
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max == 0)
|
|
|
|
{
|
|
|
|
code = previous;
|
|
|
|
goto END_REPEAT;
|
|
|
|
}
|
2014-08-26 13:46:21 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min == 0 && repeat_max == REPEAT_UNLIMITED)
|
|
|
|
*code++ = OP_CRSTAR + repeat_type;
|
|
|
|
else if (repeat_min == 1 && repeat_max == REPEAT_UNLIMITED)
|
|
|
|
*code++ = OP_CRPLUS + repeat_type;
|
|
|
|
else if (repeat_min == 0 && repeat_max == 1)
|
|
|
|
*code++ = OP_CRQUERY + repeat_type;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*code++ = OP_CRRANGE + repeat_type;
|
|
|
|
PUT2INC(code, 0, repeat_min);
|
|
|
|
if (repeat_max == REPEAT_UNLIMITED) repeat_max = 0; /* 2-byte encoding for max */
|
|
|
|
PUT2INC(code, 0, repeat_max);
|
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If previous is OP_FAIL, it was generated by an empty class []
|
|
|
|
(PCRE2_ALLOW_EMPTY_CLASS is set). The other ways in which OP_FAIL can be
|
|
|
|
generated, that is by (*FAIL) or (?!), disallow a quantifier at parse
|
|
|
|
time. We can just ignore this repeat. */
|
|
|
|
|
|
|
|
case OP_FAIL:
|
|
|
|
goto END_REPEAT;
|
|
|
|
|
2017-03-09 17:23:28 +01:00
|
|
|
/* Prior to 10.30, repeated recursions were wrapped in OP_ONCE brackets
|
|
|
|
because pcre2_match() could not handle backtracking into recursively
|
|
|
|
called groups. Now that this backtracking is available, we no longer need
|
|
|
|
to do this. However, we still need to replicate recursions as we do for
|
|
|
|
groups so as to have independent backtracking points. We can replicate
|
|
|
|
for the minimum number of repeats directly. For optional repeats we now
|
|
|
|
wrap the recursion in OP_BRA brackets and make use of the bracket
|
|
|
|
repetition. */
|
|
|
|
|
|
|
|
case OP_RECURSE:
|
|
|
|
|
|
|
|
/* Generate unwrapped repeats for a non-zero minimum, except when the
|
|
|
|
minimum is 1 and the maximum unlimited, because that can be handled with
|
|
|
|
OP_BRA terminated by OP_KETRMAX/MIN. When the maximum is equal to the
|
|
|
|
minimum, we just need to generate the appropriate additional copies.
|
|
|
|
Otherwise we need to generate one more, to simulate the situation when
|
|
|
|
the minimum is zero. */
|
|
|
|
|
|
|
|
if (repeat_min > 0 && (repeat_min != 1 || repeat_max != REPEAT_UNLIMITED))
|
|
|
|
{
|
|
|
|
int replicate = repeat_min;
|
|
|
|
if (repeat_min == repeat_max) replicate--;
|
|
|
|
|
|
|
|
/* In the pre-compile phase, we don't actually do the replication. We
|
|
|
|
just adjust the length as if we had. Do some paranoid checks for
|
|
|
|
potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit
|
|
|
|
integer type when available, otherwise double. */
|
|
|
|
|
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
|
|
|
PCRE2_SIZE delta = replicate*(1 + LINK_SIZE);
|
|
|
|
if ((INT64_OR_DOUBLE)replicate*
|
|
|
|
(INT64_OR_DOUBLE)(1 + LINK_SIZE) >
|
|
|
|
(INT64_OR_DOUBLE)INT_MAX ||
|
|
|
|
OFLOW_MAX - *lengthptr < delta)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
*lengthptr += delta;
|
|
|
|
}
|
|
|
|
|
|
|
|
else for (i = 0; i < replicate; i++)
|
|
|
|
{
|
|
|
|
memcpy(code, previous, CU2BYTES(1 + LINK_SIZE));
|
|
|
|
previous = code;
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If the number of repeats is fixed, we are done. Otherwise, adjust
|
|
|
|
the counts and fall through. */
|
|
|
|
|
|
|
|
if (repeat_min == repeat_max) break;
|
|
|
|
if (repeat_max != REPEAT_UNLIMITED) repeat_max -= repeat_min;
|
|
|
|
repeat_min = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Wrap the recursion call in OP_BRA brackets. */
|
|
|
|
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(previous + 1 + LINK_SIZE, previous, CU2BYTES(1 + LINK_SIZE));
|
2017-03-09 17:23:28 +01:00
|
|
|
op_previous = *previous = OP_BRA;
|
|
|
|
PUT(previous, 1, 2 + 2*LINK_SIZE);
|
|
|
|
previous[2 + 2*LINK_SIZE] = OP_KET;
|
|
|
|
PUT(previous, 3 + 2*LINK_SIZE, 2 + 2*LINK_SIZE);
|
|
|
|
code += 2 + 2 * LINK_SIZE;
|
|
|
|
length_prevgroup = 3 + 3*LINK_SIZE;
|
|
|
|
group_return = -1; /* Set "may match empty string" */
|
|
|
|
|
2017-06-03 19:50:03 +02:00
|
|
|
/* Now treat as a repeated OP_BRA. */
|
2017-06-15 18:41:44 +02:00
|
|
|
/* Fall through */
|
2017-03-09 17:23:28 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If previous was a bracket group, we may have to replicate it in
|
|
|
|
certain cases. Note that at this point we can encounter only the "basic"
|
|
|
|
bracket opcodes such as BRA and CBRA, as this is the place where they get
|
|
|
|
converted into the more special varieties such as BRAPOS and SBRA.
|
|
|
|
Originally, PCRE did not allow repetition of assertions, but now it does,
|
|
|
|
for Perl compatibility. */
|
|
|
|
|
|
|
|
case OP_ASSERT:
|
|
|
|
case OP_ASSERT_NOT:
|
|
|
|
case OP_ASSERTBACK:
|
|
|
|
case OP_ASSERTBACK_NOT:
|
|
|
|
case OP_ONCE:
|
|
|
|
case OP_BRA:
|
|
|
|
case OP_CBRA:
|
|
|
|
case OP_COND:
|
|
|
|
{
|
|
|
|
int len = (int)(code - previous);
|
|
|
|
PCRE2_UCHAR *bralink = NULL;
|
|
|
|
PCRE2_UCHAR *brazeroptr = NULL;
|
2014-08-26 13:46:21 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Repeating a DEFINE group (or any group where the condition is always
|
|
|
|
FALSE and there is only one branch) is pointless, but Perl allows the
|
|
|
|
syntax, so we just ignore the repeat. */
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op_previous == OP_COND && previous[LINK_SIZE+1] == OP_FALSE &&
|
|
|
|
previous[GET(previous, 1)] != OP_ALT)
|
|
|
|
goto END_REPEAT;
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2017-03-09 17:23:28 +01:00
|
|
|
/* There is no sense in actually repeating assertions. The only
|
|
|
|
potential use of repetition is in cases when the assertion is optional.
|
|
|
|
Therefore, if the minimum is greater than zero, just ignore the repeat.
|
|
|
|
If the maximum is not zero or one, set it to 1. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op_previous < OP_ONCE) /* Assertion */
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min > 0) goto END_REPEAT;
|
|
|
|
if (repeat_max > 1) repeat_max = 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The case of a zero minimum is special because of the need to stick
|
|
|
|
OP_BRAZERO in front of it, and because the group appears once in the
|
|
|
|
data, whereas in other cases it appears the minimum number of times. For
|
|
|
|
this reason, it is simplest to treat this case separately, as otherwise
|
|
|
|
the code gets far too messy. There are several special subcases when the
|
|
|
|
minimum is zero. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the maximum is also zero, we used to just omit the group from
|
|
|
|
the output altogether, like this:
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
** if (repeat_max == 0)
|
|
|
|
** {
|
|
|
|
** code = previous;
|
|
|
|
** goto END_REPEAT;
|
|
|
|
** }
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
However, that fails when a group or a subgroup within it is
|
|
|
|
referenced as a subroutine from elsewhere in the pattern, so now we
|
|
|
|
stick in OP_SKIPZERO in front of it so that it is skipped on
|
|
|
|
execution. As we don't have a list of which groups are referenced, we
|
|
|
|
cannot do this selectively.
|
|
|
|
|
|
|
|
If the maximum is 1 or unlimited, we just have to stick in the
|
|
|
|
BRAZERO and do no more at this point. */
|
|
|
|
|
|
|
|
if (repeat_max <= 1 || repeat_max == REPEAT_UNLIMITED)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(previous + 1, previous, CU2BYTES(len));
|
2016-10-02 18:01:01 +02:00
|
|
|
code++;
|
|
|
|
if (repeat_max == 0)
|
2015-08-04 11:13:11 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*previous++ = OP_SKIPZERO;
|
|
|
|
goto END_REPEAT;
|
2015-08-09 18:29:35 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
brazeroptr = previous; /* Save for possessive optimizing */
|
|
|
|
*previous++ = OP_BRAZERO + repeat_type;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If the maximum is greater than 1 and limited, we have to replicate
|
|
|
|
in a nested fashion, sticking OP_BRAZERO before each set of brackets.
|
|
|
|
The first one has to be handled carefully because it's the original
|
|
|
|
copy, which has to be moved up. The remainder can be handled by code
|
|
|
|
that is common with the non-zero minimum case below. We have to
|
|
|
|
adjust the value or repeat_max, since one less copy is required. */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
int linkoffset;
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(previous + 2 + LINK_SIZE, previous, CU2BYTES(len));
|
2016-10-02 18:01:01 +02:00
|
|
|
code += 2 + LINK_SIZE;
|
|
|
|
*previous++ = OP_BRAZERO + repeat_type;
|
|
|
|
*previous++ = OP_BRA;
|
|
|
|
|
|
|
|
/* We chain together the bracket link offset fields that have to be
|
|
|
|
filled in later when the ends of the brackets are reached. */
|
|
|
|
|
|
|
|
linkoffset = (bralink == NULL)? 0 : (int)(previous - bralink);
|
|
|
|
bralink = previous;
|
|
|
|
PUTINC(previous, 0, linkoffset);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (repeat_max != REPEAT_UNLIMITED) repeat_max--;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the minimum is greater than zero, replicate the group as many
|
|
|
|
times as necessary, and adjust the maximum to the number of subsequent
|
|
|
|
copies that we need. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
else
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min > 1)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the pre-compile phase, we don't actually do the replication.
|
|
|
|
We just adjust the length as if we had. Do some paranoid checks for
|
|
|
|
potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit
|
|
|
|
integer type when available, otherwise double. */
|
|
|
|
|
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
|
|
|
PCRE2_SIZE delta = (repeat_min - 1)*length_prevgroup;
|
|
|
|
if ((INT64_OR_DOUBLE)(repeat_min - 1)*
|
|
|
|
(INT64_OR_DOUBLE)length_prevgroup >
|
|
|
|
(INT64_OR_DOUBLE)INT_MAX ||
|
|
|
|
OFLOW_MAX - *lengthptr < delta)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
*lengthptr += delta;
|
|
|
|
}
|
|
|
|
|
2016-10-18 13:22:40 +02:00
|
|
|
/* This is compiling for real. If there is a set first code unit
|
|
|
|
for the group, and we have not yet set a "required code unit", set
|
|
|
|
it. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (groupsetfirstcu && reqcuflags < 0)
|
|
|
|
{
|
|
|
|
reqcu = firstcu;
|
|
|
|
reqcuflags = firstcuflags;
|
|
|
|
}
|
|
|
|
for (i = 1; (uint32_t)i < repeat_min; i++)
|
|
|
|
{
|
|
|
|
memcpy(code, previous, CU2BYTES(len));
|
|
|
|
code += len;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max != REPEAT_UNLIMITED) repeat_max -= repeat_min;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This code is common to both the zero and non-zero minimum cases. If
|
|
|
|
the maximum is limited, it replicates the group in a nested fashion,
|
|
|
|
remembering the bracket starts on a stack. In the case of a zero
|
|
|
|
minimum, the first one was set up above. In all cases the repeat_max
|
|
|
|
now specifies the number of additional copies needed. Again, we must
|
|
|
|
remember to replicate entries on the forward reference list. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max != REPEAT_UNLIMITED)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In the pre-compile phase, we don't actually do the replication. We
|
|
|
|
just adjust the length as if we had. For each repetition we must add
|
|
|
|
1 to the length for BRAZERO and for all but the last repetition we
|
|
|
|
must add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some
|
|
|
|
paranoid checks to avoid integer overflow. The INT64_OR_DOUBLE type
|
|
|
|
is a 64-bit integer type when available, otherwise double. */
|
|
|
|
|
|
|
|
if (lengthptr != NULL && repeat_max > 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SIZE delta = repeat_max*(length_prevgroup + 1 + 2 + 2*LINK_SIZE) -
|
|
|
|
2 - 2*LINK_SIZE; /* Last one doesn't nest */
|
|
|
|
if ((INT64_OR_DOUBLE)repeat_max *
|
|
|
|
(INT64_OR_DOUBLE)(length_prevgroup + 1 + 2 + 2*LINK_SIZE)
|
|
|
|
> (INT64_OR_DOUBLE)INT_MAX ||
|
|
|
|
OFLOW_MAX - *lengthptr < delta)
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
*lengthptr += delta;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This is compiling for real */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else for (i = repeat_max - 1; i >= 0; i--)
|
|
|
|
{
|
|
|
|
*code++ = OP_BRAZERO + repeat_type;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* All but the final copy start a new nesting, maintaining the
|
|
|
|
chain of brackets outstanding. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (i != 0)
|
|
|
|
{
|
|
|
|
int linkoffset;
|
|
|
|
*code++ = OP_BRA;
|
|
|
|
linkoffset = (bralink == NULL)? 0 : (int)(code - bralink);
|
|
|
|
bralink = code;
|
|
|
|
PUTINC(code, 0, linkoffset);
|
|
|
|
}
|
2015-01-23 17:51:47 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
memcpy(code, previous, CU2BYTES(len));
|
|
|
|
code += len;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now chain through the pending brackets, and fill in their length
|
|
|
|
fields (which are holding the chain links pro tem). */
|
|
|
|
|
|
|
|
while (bralink != NULL)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
int oldlinkoffset;
|
|
|
|
int linkoffset = (int)(code - bralink + 1);
|
|
|
|
PCRE2_UCHAR *bra = code - linkoffset;
|
|
|
|
oldlinkoffset = GET(bra, 1);
|
|
|
|
bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset;
|
|
|
|
*code++ = OP_KET;
|
|
|
|
PUTINC(code, 0, linkoffset);
|
|
|
|
PUT(bra, 1, linkoffset);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the maximum is unlimited, set a repeater in the final copy. For
|
|
|
|
ONCE brackets, that's all we need to do. However, possessively repeated
|
|
|
|
ONCE brackets can be converted into non-capturing brackets, as the
|
|
|
|
behaviour of (?:xx)++ is the same as (?>xx)++ and this saves having to
|
|
|
|
deal with possessive ONCEs specially.
|
|
|
|
|
|
|
|
Otherwise, when we are doing the actual compile phase, check to see
|
|
|
|
whether this group is one that could match an empty string. If so,
|
|
|
|
convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so
|
|
|
|
that runtime checking can be done. [This check is also applied to ONCE
|
|
|
|
groups at runtime, but in a different way.]
|
|
|
|
|
|
|
|
Then, if the quantifier was possessive and the bracket is not a
|
|
|
|
conditional, we convert the BRA code to the POS form, and the KET code to
|
|
|
|
KETRPOS. (It turns out to be convenient at runtime to detect this kind of
|
|
|
|
subpattern at both the start and at the end.) The use of special opcodes
|
|
|
|
makes it possible to reduce greatly the stack usage in pcre2_match(). If
|
|
|
|
the group is preceded by OP_BRAZERO, convert this to OP_BRAPOSZERO.
|
|
|
|
|
|
|
|
Then, if the minimum number of matches is 1 or 0, cancel the possessive
|
|
|
|
flag so that the default action below, of wrapping everything inside
|
|
|
|
atomic brackets, does not happen. When the minimum is greater than 1,
|
|
|
|
there will be earlier copies of the group, and so we still have to wrap
|
|
|
|
the whole thing. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_UCHAR *ketcode = code - 1 - LINK_SIZE;
|
|
|
|
PCRE2_UCHAR *bracode = ketcode - GET(ketcode, 1);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Convert possessive ONCE brackets to non-capturing */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-11 18:59:23 +01:00
|
|
|
if (*bracode == OP_ONCE && possessive_quantifier) *bracode = OP_BRA;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* For non-possessive ONCE brackets, all we need to do is to
|
|
|
|
set the KET. */
|
|
|
|
|
2017-03-11 18:59:23 +01:00
|
|
|
if (*bracode == OP_ONCE) *ketcode = OP_KETRMAX + repeat_type;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Handle non-ONCE brackets and possessive ONCEs (which have been
|
|
|
|
converted to non-capturing above). */
|
|
|
|
|
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-12-23 19:34:10 +01:00
|
|
|
/* In the compile phase, adjust the opcode if the group can match
|
2016-12-23 18:09:37 +01:00
|
|
|
an empty string. For a conditional group with only one branch, the
|
2016-12-23 19:34:10 +01:00
|
|
|
value of group_return will not show "could be empty", so we must
|
2016-12-23 18:09:37 +01:00
|
|
|
check that separately. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (lengthptr == NULL)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-12-23 18:09:37 +01:00
|
|
|
if (group_return < 0) *bracode += OP_SBRA - OP_BRA;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*bracode == OP_COND && bracode[GET(bracode,1)] != OP_ALT)
|
|
|
|
*bracode = OP_SCOND;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Handle possessive quantifiers. */
|
|
|
|
|
|
|
|
if (possessive_quantifier)
|
2015-08-04 11:13:11 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For COND brackets, we wrap the whole thing in a possessively
|
|
|
|
repeated non-capturing bracket, because we have not invented POS
|
|
|
|
versions of the COND opcodes. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*bracode == OP_COND || *bracode == OP_SCOND)
|
|
|
|
{
|
|
|
|
int nlen = (int)(code - bracode);
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(bracode + 1 + LINK_SIZE, bracode, CU2BYTES(nlen));
|
2016-10-02 18:01:01 +02:00
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
nlen += 1 + LINK_SIZE;
|
|
|
|
*bracode = (*bracode == OP_COND)? OP_BRAPOS : OP_SBRAPOS;
|
|
|
|
*code++ = OP_KETRPOS;
|
|
|
|
PUTINC(code, 0, nlen);
|
|
|
|
PUT(bracode, 1, nlen);
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For non-COND brackets, we modify the BRA code and use KETRPOS. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
*bracode += 1; /* Switch to xxxPOS opcodes */
|
|
|
|
*ketcode = OP_KETRPOS;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the minimum is zero, mark it as possessive, then unset the
|
|
|
|
possessive flag when the minimum is 0 or 1. */
|
|
|
|
|
|
|
|
if (brazeroptr != NULL) *brazeroptr = OP_BRAPOSZERO;
|
|
|
|
if (repeat_min < 2) possessive_quantifier = FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Non-possessive quantifier */
|
|
|
|
|
|
|
|
else *ketcode = OP_KETRMAX + repeat_type;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If previous was a character type match (\d or similar), abolish it and
|
|
|
|
create a suitable repeat item. The code is shared with single-character
|
|
|
|
repeats by setting op_type to add a suitable offset into repeat_type.
|
|
|
|
Note the the Unicode property types will be present only when
|
|
|
|
SUPPORT_UNICODE is defined, but we don't wrap the little bits of code
|
|
|
|
here because it just makes it horribly messy. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
if (op_previous >= OP_EODN) /* Not a character type - internal error */
|
|
|
|
{
|
|
|
|
*errorcodeptr = ERR10;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
int prop_type, prop_value;
|
|
|
|
PCRE2_UCHAR *oldcode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */
|
|
|
|
mclength = 0; /* Not a character */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op_previous == OP_PROP || op_previous == OP_NOTPROP)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
prop_type = previous[1];
|
|
|
|
prop_value = previous[2];
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Come here from just above with a character in mcbuffer/mclength. */
|
|
|
|
OUTPUT_SINGLE_REPEAT:
|
|
|
|
prop_type = prop_value = -1;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* At this point, if prop_type == prop_value == -1 we either have a
|
|
|
|
character in mcbuffer when mclength is greater than zero, or we have
|
|
|
|
mclength zero, in which case there is a non-property character type in
|
|
|
|
op_previous. If prop_type/value are not negative, we have a property
|
|
|
|
character type in op_previous. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
oldcode = code; /* Save where we were */
|
|
|
|
code = previous; /* Usually overwrite previous item */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the maximum is zero then the minimum must also be zero; Perl allows
|
|
|
|
this case, so we do too - by simply omitting the item altogether. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max == 0) goto END_REPEAT;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Combine the op_type with the repeat_type */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
repeat_type += op_type;
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A minimum of zero is handled either as the special case * or ?, or as
|
|
|
|
an UPTO, with the maximum given. */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_min == 0)
|
2015-03-12 18:00:18 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max == REPEAT_UNLIMITED) *code++ = OP_STAR + repeat_type;
|
|
|
|
else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type;
|
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = OP_UPTO + repeat_type;
|
|
|
|
PUT2INC(code, 0, repeat_max);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A repeat minimum of 1 is optimized into some special cases. If the
|
|
|
|
maximum is unlimited, we use OP_PLUS. Otherwise, the original item is
|
|
|
|
left in place and, if the maximum is greater than 1, we use OP_UPTO with
|
|
|
|
one less than the maximum. */
|
|
|
|
|
|
|
|
else if (repeat_min == 1)
|
|
|
|
{
|
|
|
|
if (repeat_max == REPEAT_UNLIMITED)
|
|
|
|
*code++ = OP_PLUS + repeat_type;
|
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
code = oldcode; /* Leave previous item in place */
|
|
|
|
if (repeat_max == 1) goto END_REPEAT;
|
|
|
|
*code++ = OP_UPTO + repeat_type;
|
|
|
|
PUT2INC(code, 0, repeat_max - 1);
|
2015-03-12 18:00:18 +01:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* The case {n,n} is just an EXACT, while the general case {n,m} is
|
|
|
|
handled as an EXACT followed by an UPTO or STAR or QUERY. */
|
|
|
|
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */
|
|
|
|
PUT2INC(code, 0, repeat_min);
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Unless repeat_max equals repeat_min, fill in the data for EXACT,
|
|
|
|
and then generate the second opcode. For a repeated Unicode property
|
|
|
|
match, there are two extra values that define the required property,
|
|
|
|
and mclength is set zero to indicate this. */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max != repeat_min)
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (mclength > 0)
|
|
|
|
{
|
|
|
|
memcpy(code, mcbuffer, CU2BYTES(mclength));
|
|
|
|
code += mclength;
|
|
|
|
}
|
|
|
|
else
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = op_previous;
|
|
|
|
if (prop_type >= 0)
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = prop_type;
|
|
|
|
*code++ = prop_value;
|
2015-03-11 18:44:16 +01:00
|
|
|
}
|
|
|
|
}
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now set up the following opcode */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repeat_max == REPEAT_UNLIMITED)
|
|
|
|
*code++ = OP_STAR + repeat_type;
|
|
|
|
else
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
repeat_max -= repeat_min;
|
|
|
|
if (repeat_max == 1)
|
|
|
|
{
|
|
|
|
*code++ = OP_QUERY + repeat_type;
|
|
|
|
}
|
|
|
|
else
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = OP_UPTO + repeat_type;
|
|
|
|
PUT2INC(code, 0, repeat_max);
|
2015-03-12 18:00:18 +01:00
|
|
|
}
|
2015-03-11 18:44:16 +01:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Fill in the character or character type for the final opcode. */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (mclength > 0)
|
|
|
|
{
|
|
|
|
memcpy(code, mcbuffer, CU2BYTES(mclength));
|
|
|
|
code += mclength;
|
|
|
|
}
|
2015-03-11 18:44:16 +01:00
|
|
|
else
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = op_previous;
|
|
|
|
if (prop_type >= 0)
|
2015-03-11 18:44:16 +01:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = prop_type;
|
|
|
|
*code++ = prop_value;
|
2015-03-11 18:44:16 +01:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
} /* End of switch on different op_previous values */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the character following a repeat is '+', possessive_quantifier is
|
|
|
|
TRUE. For some opcodes, there are special alternative opcodes for this
|
|
|
|
case. For anything else, we wrap the entire repeated item inside OP_ONCE
|
|
|
|
brackets. Logically, the '+' notation is just syntactic sugar, taken from
|
|
|
|
Sun's Java package, but the special opcodes can optimize it.
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Some (but not all) possessively repeated subpatterns have already been
|
|
|
|
completely handled in the code just above. For them, possessive_quantifier
|
|
|
|
is always FALSE at this stage. Note that the repeated item starts at
|
|
|
|
tempcode, not at previous, which might be the first part of a string whose
|
|
|
|
(former) last char we repeated. */
|
2015-03-12 18:00:18 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (possessive_quantifier)
|
|
|
|
{
|
|
|
|
int len;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Possessifying an EXACT quantifier has no effect, so we can ignore it.
|
|
|
|
However, QUERY, STAR, or UPTO may follow (for quantifiers such as {5,6},
|
|
|
|
{5,}, or {5,10}). We skip over an EXACT item; if the length of what
|
|
|
|
remains is greater than zero, there's a further opcode that can be
|
|
|
|
handled. If not, do nothing, leaving the EXACT alone. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(*tempcode)
|
|
|
|
{
|
|
|
|
case OP_TYPEEXACT:
|
|
|
|
tempcode += PRIV(OP_lengths)[*tempcode] +
|
|
|
|
((tempcode[1 + IMM2_SIZE] == OP_PROP
|
|
|
|
|| tempcode[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0);
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* CHAR opcodes are used for exacts whose count is 1. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_CHAR:
|
|
|
|
case OP_CHARI:
|
|
|
|
case OP_NOT:
|
|
|
|
case OP_NOTI:
|
|
|
|
case OP_EXACT:
|
|
|
|
case OP_EXACTI:
|
|
|
|
case OP_NOTEXACT:
|
|
|
|
case OP_NOTEXACTI:
|
|
|
|
tempcode += PRIV(OP_lengths)[*tempcode];
|
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (utf && HAS_EXTRALEN(tempcode[-1]))
|
|
|
|
tempcode += GET_EXTRALEN(tempcode[-1]);
|
|
|
|
#endif
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For the class opcodes, the repeat operator appears at the end;
|
|
|
|
adjust tempcode to point to it. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_CLASS:
|
|
|
|
case OP_NCLASS:
|
|
|
|
tempcode += 1 + 32/sizeof(PCRE2_UCHAR);
|
|
|
|
break;
|
2015-05-19 18:48:57 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_WIDE_CHARS
|
|
|
|
case OP_XCLASS:
|
|
|
|
tempcode += GET(tempcode, 1);
|
|
|
|
break;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
/* If tempcode is equal to code (which points to the end of the repeated
|
|
|
|
item), it means we have skipped an EXACT item but there is no following
|
|
|
|
QUERY, STAR, or UPTO; the value of len will be 0, and we do nothing. In
|
|
|
|
all other cases, tempcode will be pointing to the repeat opcode, and will
|
|
|
|
be less than code, so the value of len will be greater than 0. */
|
|
|
|
|
|
|
|
len = (int)(code - tempcode);
|
|
|
|
if (len > 0)
|
|
|
|
{
|
|
|
|
unsigned int repcode = *tempcode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* There is a table for possessifying opcodes, all of which are less
|
|
|
|
than OP_CALLOUT. A zero entry means there is no possessified version.
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (repcode < OP_CALLOUT && opcode_possessify[repcode] > 0)
|
|
|
|
*tempcode = opcode_possessify[repcode];
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For opcode without a special possessified version, wrap the item in
|
|
|
|
ONCE brackets. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(tempcode + 1 + LINK_SIZE, tempcode, CU2BYTES(len));
|
2016-10-02 18:01:01 +02:00
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
len += 1 + LINK_SIZE;
|
|
|
|
tempcode[0] = OP_ONCE;
|
|
|
|
*code++ = OP_KET;
|
|
|
|
PUTINC(code, 0, len);
|
|
|
|
PUT(tempcode, 1, len);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We set the "follows varying string" flag for subsequently encountered
|
|
|
|
reqcus if it isn't already set and we have just passed a varying length
|
|
|
|
item. */
|
|
|
|
|
|
|
|
END_REPEAT:
|
|
|
|
cb->req_varyopt |= reqvary;
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle a 32-bit data character with a value greater than META_END. */
|
|
|
|
|
|
|
|
case META_BIGVALUE:
|
|
|
|
pptr++;
|
|
|
|
goto NORMAL_CHAR;
|
|
|
|
|
|
|
|
|
|
|
|
/* ===============================================================*/
|
|
|
|
/* Handle a back reference by number, which is the meta argument. The
|
|
|
|
pattern offsets for back references to group numbers less than 10 are held
|
|
|
|
in a special vector, to avoid using more than two parsed pattern elements
|
|
|
|
in 64-bit environments. We only need the offset to the first occurrence,
|
|
|
|
because if that doesn't fail, subsequent ones will also be OK. */
|
|
|
|
|
|
|
|
case META_BACKREF:
|
|
|
|
if (meta_arg < 10) offset = cb->small_ref_offset[meta_arg];
|
|
|
|
else GETPLUSOFFSET(offset, pptr);
|
|
|
|
|
|
|
|
if (meta_arg > cb->bracount)
|
|
|
|
{
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
*errorcodeptr = ERR15; /* Non-existent subpattern */
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Come here from named backref handling when the reference is to a
|
|
|
|
single group (that is, not to a duplicated name). The back reference
|
|
|
|
data will have already been updated. We must disable firstcu if not
|
|
|
|
set, to cope with cases like (?=(\w+))\1: which would otherwise set ':'
|
|
|
|
later. */
|
|
|
|
|
|
|
|
HANDLE_SINGLE_REFERENCE:
|
2017-12-12 16:01:51 +01:00
|
|
|
if (firstcuflags == REQ_UNSET) zerofirstcuflags = firstcuflags = REQ_NONE;
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = ((options & PCRE2_CASELESS) != 0)? OP_REFI : OP_REF;
|
|
|
|
PUT2INC(code, 0, meta_arg);
|
|
|
|
|
|
|
|
/* Update the map of back references, and keep the highest one. We
|
|
|
|
could do this in parse_regex() for numerical back references, but not
|
|
|
|
for named back references, because we don't know the numbers to which
|
|
|
|
named back references refer. So we do it all in this function. */
|
|
|
|
|
|
|
|
cb->backref_map |= (meta_arg < 32)? (1u << meta_arg) : 1;
|
|
|
|
if (meta_arg > cb->top_backref) cb->top_backref = meta_arg;
|
|
|
|
|
|
|
|
/* Check to see if this back reference is recursive, that it, it
|
|
|
|
is inside the group that it references. A flag is set so that the
|
|
|
|
group can be made atomic. */
|
|
|
|
|
|
|
|
for (oc = cb->open_caps; oc != NULL; oc = oc->next)
|
|
|
|
{
|
|
|
|
if (oc->number == meta_arg)
|
|
|
|
{
|
|
|
|
oc->flag = TRUE;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===============================================================*/
|
|
|
|
/* Handle recursion by inserting the number of the called group (which is
|
|
|
|
the meta argument) after OP_RECURSE. At the end of compiling the pattern is
|
|
|
|
scanned and these numbers are replaced by offsets within the pattern. It is
|
|
|
|
done like this to avoid problems with forward references and adjusting
|
|
|
|
offsets when groups are duplicated and moved (as discovered in previous
|
|
|
|
implementations). Note that a recursion does not have a set first character
|
|
|
|
(relevant if it is repeated, because it will then be wrapped with ONCE
|
|
|
|
brackets). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_RECURSE:
|
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
if (meta_arg > cb->bracount)
|
|
|
|
{
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
*errorcodeptr = ERR15; /* Non-existent subpattern */
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
HANDLE_NUMERICAL_RECURSION:
|
|
|
|
*code = OP_RECURSE;
|
|
|
|
PUT(code, 1, meta_arg);
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
groupsetfirstcu = FALSE;
|
|
|
|
cb->had_recurse = TRUE;
|
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===============================================================*/
|
|
|
|
/* Handle capturing parentheses; the number is the meta argument. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CAPTURE:
|
|
|
|
bravalue = OP_CBRA;
|
|
|
|
skipunits = IMM2_SIZE;
|
|
|
|
PUT2(code, 1+LINK_SIZE, meta_arg);
|
|
|
|
cb->lastcapture = meta_arg;
|
2016-12-23 18:09:37 +01:00
|
|
|
goto GROUP_PROCESS_NOTE_EMPTY;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===============================================================*/
|
|
|
|
/* Handle escape sequence items. For ones like \d, the ESC_values are
|
|
|
|
arranged to be the same as the corresponding OP_values in the default case
|
|
|
|
when PCRE2_UCP is not set (which is the only case in which they will appear
|
|
|
|
here).
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Note: \Q and \E are never seen here, as they were dealt with in
|
|
|
|
parse_pattern(). Neither are numerical back references or recursions, which
|
|
|
|
were turned into META_BACKREF or META_RECURSE items, respectively. \k and
|
|
|
|
\g, when followed by names, are turned into META_BACKREF_BYNAME or
|
|
|
|
META_RECURSE_BYNAME. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ESCAPE:
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* We can test for escape sequences that consume a character because their
|
2016-12-23 18:09:37 +01:00
|
|
|
values lie between ESC_b and ESC_Z; this may have to change if any new ones
|
|
|
|
are ever created. For these sequences, we disable the setting of a first
|
|
|
|
character if it hasn't already been set. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
if (meta_arg > ESC_b && meta_arg < ESC_Z)
|
2016-12-23 19:34:10 +01:00
|
|
|
{
|
|
|
|
matched_char = TRUE;
|
2016-12-23 18:09:37 +01:00
|
|
|
if (firstcuflags == REQ_UNSET) firstcuflags = REQ_NONE;
|
2016-12-23 19:34:10 +01:00
|
|
|
}
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Set values to reset to if this is followed by a zero repeat. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If Unicode is not supported, \P and \p are not allowed and are
|
|
|
|
faulted at parse time, so will never appear here. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (meta_arg == ESC_P || meta_arg == ESC_p)
|
|
|
|
{
|
|
|
|
uint32_t ptype = *(++pptr) >> 16;
|
|
|
|
uint32_t pdata = *pptr & 0xffff;
|
|
|
|
*code++ = (meta_arg == ESC_p)? OP_PROP : OP_NOTPROP;
|
|
|
|
*code++ = ptype;
|
|
|
|
*code++ = pdata;
|
|
|
|
break; /* End META_ESCAPE */
|
|
|
|
}
|
|
|
|
#endif
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For the rest (including \X when Unicode is supported - if not it's
|
|
|
|
faulted at parse time), the OP value is the escape value when PCRE2_UCP is
|
|
|
|
not set; if it is set, these escapes do not show up here because they are
|
|
|
|
converted into Unicode property tests in parse_regex(). Note that \b and \B
|
|
|
|
do a one-character lookbehind, and \A also behaves as if it does. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta_arg == ESC_C) cb->external_flags |= PCRE2_HASBKC; /* Record */
|
|
|
|
if ((meta_arg == ESC_b || meta_arg == ESC_B || meta_arg == ESC_A) &&
|
|
|
|
cb->max_lookbehind == 0)
|
|
|
|
cb->max_lookbehind = 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* In non-UTF mode, and for both 32-bit modes, we turn \C into OP_ALLANY
|
|
|
|
instead of OP_ANYBYTE so that it works in DFA mode and in lookbehinds. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
*code++ = (meta_arg == ESC_C)? OP_ALLANY : meta_arg;
|
|
|
|
#else
|
|
|
|
*code++ = (!utf && meta_arg == ESC_C)? OP_ALLANY : meta_arg;
|
|
|
|
#endif
|
|
|
|
break; /* End META_ESCAPE */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* ===================================================================*/
|
|
|
|
/* Handle an unrecognized meta value. A parsed pattern value less than
|
|
|
|
META_END is a literal. Otherwise we have a problem. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
if (meta >= META_END)
|
|
|
|
{
|
|
|
|
#ifdef DEBUG_SHOW_PARSED
|
|
|
|
fprintf(stderr, "** Unrecognized parsed pattern item 0x%.8x\n", *pptr);
|
|
|
|
#endif
|
|
|
|
*errorcodeptr = ERR89; /* Internal error - unrecognized. */
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle a literal character. We come here by goto in the case of a
|
|
|
|
32-bit, non-UTF character whose value is greater than META_END. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
NORMAL_CHAR:
|
|
|
|
meta = *pptr; /* Get the full 32 bits */
|
|
|
|
NORMAL_CHAR_SET: /* Character is already in meta */
|
2016-12-23 19:34:10 +01:00
|
|
|
matched_char = TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* For caseless UTF mode, check whether this character has more than one
|
|
|
|
other case. If so, generate a special OP_PROP item instead of OP_CHARI. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (utf && (options & PCRE2_CASELESS) != 0)
|
|
|
|
{
|
|
|
|
uint32_t caseset = UCD_CASESET(meta);
|
|
|
|
if (caseset != 0)
|
|
|
|
{
|
|
|
|
*code++ = OP_PROP;
|
|
|
|
*code++ = PT_CLIST;
|
|
|
|
*code++ = caseset;
|
|
|
|
if (firstcuflags == REQ_UNSET)
|
|
|
|
firstcuflags = zerofirstcuflags = REQ_NONE;
|
|
|
|
break; /* End handling this meta item */
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Caseful matches, or not one of the multicase characters. Get the
|
|
|
|
character's code units into mcbuffer, with the length in mclength. When not
|
|
|
|
in UTF mode, the length is always 1. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef SUPPORT_UNICODE
|
|
|
|
if (utf) mclength = PRIV(ord2utf)(meta, mcbuffer); else
|
|
|
|
#endif
|
|
|
|
{
|
|
|
|
mclength = 1;
|
|
|
|
mcbuffer[0] = meta;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Generate the appropriate code */
|
2015-08-30 19:47:36 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*code++ = ((options & PCRE2_CASELESS) != 0)? OP_CHARI : OP_CHAR;
|
|
|
|
memcpy(code, mcbuffer, CU2BYTES(mclength));
|
|
|
|
code += mclength;
|
2015-08-09 18:29:35 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember if \r or \n were seen */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL)
|
|
|
|
cb->external_flags |= PCRE2_HASCRORLF;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Set the first and required code units appropriately. If no previous
|
|
|
|
first code unit, set it from this character, but revert to none on a zero
|
|
|
|
repeat. Otherwise, leave the firstcu value alone, and don't change it on
|
|
|
|
a zero repeat. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (firstcuflags == REQ_UNSET)
|
|
|
|
{
|
|
|
|
zerofirstcuflags = REQ_NONE;
|
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If the character is more than one code unit long, we can set firstcu
|
|
|
|
only if it is not to be matched caselessly. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (mclength == 1 || req_caseopt == 0)
|
|
|
|
{
|
|
|
|
firstcu = mcbuffer[0];
|
|
|
|
firstcuflags = req_caseopt;
|
|
|
|
if (mclength != 1)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
reqcu = code[-1];
|
|
|
|
reqcuflags = cb->req_varyopt;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else firstcuflags = reqcuflags = REQ_NONE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* firstcu was previously set; we can set reqcu only if the length is
|
|
|
|
1 or the matching is caseful. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
zerofirstcu = firstcu;
|
|
|
|
zerofirstcuflags = firstcuflags;
|
|
|
|
zeroreqcu = reqcu;
|
|
|
|
zeroreqcuflags = reqcuflags;
|
|
|
|
if (mclength == 1 || req_caseopt == 0)
|
|
|
|
{
|
|
|
|
reqcu = code[-1];
|
|
|
|
reqcuflags = req_caseopt | cb->req_varyopt;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break; /* End default meta handling */
|
|
|
|
} /* End of big switch */
|
|
|
|
} /* End of big loop */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Control never reaches here. */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Compile regex: a sequence of alternatives *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* On entry, pptr is pointing past the bracket meta, but on return it points to
|
|
|
|
the closing bracket or META_END. The code variable is pointing at the code unit
|
|
|
|
into which the BRA operator has been stored. This function is used during the
|
|
|
|
pre-compile phase when we are trying to find out the amount of memory needed,
|
|
|
|
as well as during the real compile phase. The value of lengthptr distinguishes
|
|
|
|
the two phases.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
options option bits, including any changes for this subpattern
|
|
|
|
codeptr -> the address of the current code pointer
|
|
|
|
pptrptr -> the address of the current parsed pattern pointer
|
|
|
|
errorcodeptr -> pointer to error code variable
|
|
|
|
skipunits skip this many code units at start (for brackets and OP_COND)
|
|
|
|
firstcuptr place to put the first required code unit
|
|
|
|
firstcuflagsptr place to put the first code unit flags, or a negative number
|
|
|
|
reqcuptr place to put the last required code unit
|
|
|
|
reqcuflagsptr place to put the last required code unit flags, or a negative number
|
|
|
|
bcptr pointer to the chain of currently open branches
|
|
|
|
cb points to the data block with tables pointers etc.
|
|
|
|
lengthptr NULL during the real compile phase
|
|
|
|
points to length accumulator during pre-compile phase
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
Returns: 0 There has been an error
|
|
|
|
+1 Success, this group must match at least one character
|
|
|
|
-1 Success, this group may match an empty string
|
2016-12-23 19:34:10 +01:00
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
static int
|
2016-10-02 18:01:01 +02:00
|
|
|
compile_regex(uint32_t options, PCRE2_UCHAR **codeptr, uint32_t **pptrptr,
|
|
|
|
int *errorcodeptr, uint32_t skipunits, uint32_t *firstcuptr,
|
|
|
|
int32_t *firstcuflagsptr, uint32_t *reqcuptr,int32_t *reqcuflagsptr,
|
|
|
|
branch_chain *bcptr, compile_block *cb, PCRE2_SIZE *lengthptr)
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR *code = *codeptr;
|
|
|
|
PCRE2_UCHAR *last_branch = code;
|
|
|
|
PCRE2_UCHAR *start_bracket = code;
|
|
|
|
BOOL lookbehind;
|
|
|
|
open_capitem capitem;
|
|
|
|
int capnumber = 0;
|
2016-12-23 18:09:37 +01:00
|
|
|
int okreturn = 1;
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t *pptr = *pptrptr;
|
|
|
|
uint32_t firstcu, reqcu;
|
|
|
|
uint32_t lookbehindlength;
|
|
|
|
int32_t firstcuflags, reqcuflags;
|
|
|
|
uint32_t branchfirstcu, branchreqcu;
|
|
|
|
int32_t branchfirstcuflags, branchreqcuflags;
|
|
|
|
PCRE2_SIZE length;
|
|
|
|
branch_chain bc;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If set, call the external function that checks for stack availability. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cb->cx->stack_guard != NULL &&
|
|
|
|
cb->cx->stack_guard(cb->parens_depth, cb->cx->stack_guard_data))
|
|
|
|
{
|
|
|
|
*errorcodeptr= ERR33;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Miscellaneous initialization */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
bc.outer = bcptr;
|
|
|
|
bc.current_branch = code;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
firstcu = reqcu = 0;
|
|
|
|
firstcuflags = reqcuflags = REQ_UNSET;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Accumulate the length for use in the pre-compile phase. Start with the
|
|
|
|
length of the BRA and KET and any extra code units that are required at the
|
|
|
|
beginning. We accumulate in a local variable to save frequent testing of
|
|
|
|
lengthptr for NULL. We cannot do this by looking at the value of 'code' at the
|
|
|
|
start and end of each alternative, because compiled items are discarded during
|
2018-06-17 16:13:28 +02:00
|
|
|
the pre-compile phase so that the workspace is not exceeded. */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
length = 2 + 2*LINK_SIZE + skipunits;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Remember if this is a lookbehind assertion, and if it is, save its length
|
|
|
|
and skip over the pattern offset. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
lookbehind = *code == OP_ASSERTBACK || *code == OP_ASSERTBACK_NOT;
|
|
|
|
if (lookbehind)
|
|
|
|
{
|
|
|
|
lookbehindlength = META_DATA(pptr[-1]);
|
|
|
|
pptr += SIZEOFFSET;
|
|
|
|
}
|
|
|
|
else lookbehindlength = 0;
|
2015-02-20 12:20:40 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If this is a capturing subpattern, add to the chain of open capturing items
|
|
|
|
so that we can detect them if (*ACCEPT) is encountered. Note that only OP_CBRA
|
|
|
|
need be tested here; changing this opcode to one of its variants, e.g.
|
|
|
|
OP_SCBRAPOS, happens later, after the group has been compiled. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*code == OP_CBRA)
|
|
|
|
{
|
|
|
|
capnumber = GET2(code, 1 + LINK_SIZE);
|
|
|
|
capitem.number = capnumber;
|
|
|
|
capitem.next = cb->open_caps;
|
|
|
|
capitem.flag = FALSE;
|
2017-10-29 17:58:38 +01:00
|
|
|
capitem.assert_depth = cb->assert_depth;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->open_caps = &capitem;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Offset is set zero to mark that this bracket is still open */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
PUT(code, 1, 0);
|
|
|
|
code += 1 + LINK_SIZE + skipunits;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Loop for each alternative branch */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;;)
|
|
|
|
{
|
2016-12-23 18:09:37 +01:00
|
|
|
int branch_return;
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Insert OP_REVERSE if this is as lookbehind assertion. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (lookbehind && lookbehindlength > 0)
|
|
|
|
{
|
|
|
|
*code++ = OP_REVERSE;
|
|
|
|
PUTINC(code, 0, lookbehindlength);
|
|
|
|
length += 1 + LINK_SIZE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Now compile the branch; in the pre-compile phase its length gets added
|
|
|
|
into the length. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-12-23 19:34:10 +01:00
|
|
|
if ((branch_return =
|
2016-12-23 18:09:37 +01:00
|
|
|
compile_branch(&options, &code, &pptr, errorcodeptr, &branchfirstcu,
|
|
|
|
&branchfirstcuflags, &branchreqcu, &branchreqcuflags, &bc,
|
|
|
|
cb, (lengthptr == NULL)? NULL : &length)) == 0)
|
|
|
|
return 0;
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
/* If a branch can match an empty string, so can the whole group. */
|
2016-12-23 19:34:10 +01:00
|
|
|
|
2016-12-23 18:09:37 +01:00
|
|
|
if (branch_return < 0) okreturn = -1;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* In the real compile phase, there is some post-processing to be done. */
|
|
|
|
|
|
|
|
if (lengthptr == NULL)
|
|
|
|
{
|
|
|
|
/* If this is the first branch, the firstcu and reqcu values for the
|
|
|
|
branch become the values for the regex. */
|
|
|
|
|
|
|
|
if (*last_branch != OP_ALT)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
firstcu = branchfirstcu;
|
|
|
|
firstcuflags = branchfirstcuflags;
|
|
|
|
reqcu = branchreqcu;
|
|
|
|
reqcuflags = branchreqcuflags;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If this is not the first branch, the first char and reqcu have to
|
|
|
|
match the values from all the previous branches, except that if the
|
|
|
|
previous value for reqcu didn't have REQ_VARY set, it can still match,
|
|
|
|
and we set REQ_VARY for the regex. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
/* If we previously had a firstcu, but it doesn't match the new branch,
|
|
|
|
we have to abandon the firstcu for the regex, but if there was
|
|
|
|
previously no reqcu, it takes on the value of the old firstcu. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (firstcuflags != branchfirstcuflags || firstcu != branchfirstcu)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (firstcuflags >= 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (reqcuflags < 0)
|
|
|
|
{
|
|
|
|
reqcu = firstcu;
|
|
|
|
reqcuflags = firstcuflags;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
firstcuflags = REQ_NONE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If we (now or from before) have no firstcu, a firstcu from the
|
|
|
|
branch becomes a reqcu if there isn't a branch reqcu. */
|
|
|
|
|
|
|
|
if (firstcuflags < 0 && branchfirstcuflags >= 0 &&
|
|
|
|
branchreqcuflags < 0)
|
|
|
|
{
|
|
|
|
branchreqcu = branchfirstcu;
|
|
|
|
branchreqcuflags = branchfirstcuflags;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Now ensure that the reqcus match */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (((reqcuflags & ~REQ_VARY) != (branchreqcuflags & ~REQ_VARY)) ||
|
|
|
|
reqcu != branchreqcu)
|
|
|
|
reqcuflags = REQ_NONE;
|
2014-06-14 20:29:51 +02:00
|
|
|
else
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
reqcu = branchreqcu;
|
|
|
|
reqcuflags |= branchreqcuflags; /* To "or" REQ_VARY */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Handle reaching the end of the expression, either ')' or end of pattern.
|
|
|
|
In the real compile phase, go back through the alternative branches and
|
|
|
|
reverse the chain of offsets, with the field in the BRA item now becoming an
|
|
|
|
offset to the first alternative. If there are no alternatives, it points to
|
|
|
|
the end of the group. The length in the terminating ket is always the length
|
|
|
|
of the whole bracketed item. Return leaving the pointer at the terminating
|
|
|
|
char. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (META_CODE(*pptr) != META_ALT)
|
|
|
|
{
|
|
|
|
if (lengthptr == NULL)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SIZE branch_length = code - last_branch;
|
|
|
|
do
|
|
|
|
{
|
|
|
|
PCRE2_SIZE prev_length = GET(last_branch, 1);
|
|
|
|
PUT(last_branch, 1, branch_length);
|
|
|
|
branch_length = prev_length;
|
|
|
|
last_branch -= branch_length;
|
|
|
|
}
|
|
|
|
while (branch_length > 0);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Fill in the ket */
|
|
|
|
|
|
|
|
*code = OP_KET;
|
|
|
|
PUT(code, 1, (int)(code - start_bracket));
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
|
|
|
|
/* If it was a capturing subpattern, check to see if it contained any
|
|
|
|
recursive back references. If so, we must wrap it in atomic brackets. In
|
|
|
|
any event, remove the block from the chain. */
|
|
|
|
|
|
|
|
if (capnumber > 0)
|
|
|
|
{
|
|
|
|
if (cb->open_caps->flag)
|
|
|
|
{
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(start_bracket + 1 + LINK_SIZE, start_bracket,
|
2016-10-02 18:01:01 +02:00
|
|
|
CU2BYTES(code - start_bracket));
|
|
|
|
*start_bracket = OP_ONCE;
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
PUT(start_bracket, 1, (int)(code - start_bracket));
|
|
|
|
*code = OP_KET;
|
|
|
|
PUT(code, 1, (int)(code - start_bracket));
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
length += 2 + 2*LINK_SIZE;
|
|
|
|
}
|
|
|
|
cb->open_caps = cb->open_caps->next;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Set values to pass back */
|
|
|
|
|
|
|
|
*codeptr = code;
|
|
|
|
*pptrptr = pptr;
|
|
|
|
*firstcuptr = firstcu;
|
|
|
|
*firstcuflagsptr = firstcuflags;
|
|
|
|
*reqcuptr = reqcu;
|
|
|
|
*reqcuflagsptr = reqcuflags;
|
2014-06-14 20:29:51 +02:00
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (OFLOW_MAX - *lengthptr < length)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
*errorcodeptr = ERR20;
|
2016-12-23 18:09:37 +01:00
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
*lengthptr += length;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-12-23 18:09:37 +01:00
|
|
|
return okreturn;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Another branch follows. In the pre-compile phase, we can move the code
|
|
|
|
pointer back to where it was for the start of the first branch. (That is,
|
|
|
|
pretend that each branch is the only one.)
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
In the real compile phase, insert an ALT node. Its length field points back
|
|
|
|
to the previous branch while the bracket remains open. At the end the chain
|
|
|
|
is reversed. It's done like this so that the start of the bracket has a
|
|
|
|
zero offset until it is closed, making it possible to detect recursion. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (lengthptr != NULL)
|
|
|
|
{
|
|
|
|
code = *codeptr + 1 + LINK_SIZE + skipunits;
|
|
|
|
length += 1 + LINK_SIZE;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
*code = OP_ALT;
|
|
|
|
PUT(code, 1, (int)(code - last_branch));
|
|
|
|
bc.current_branch = last_branch = code;
|
|
|
|
code += 1 + LINK_SIZE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-28 18:09:08 +02:00
|
|
|
/* Set the lookbehind length (if not in a lookbehind the value will be zero)
|
|
|
|
and then advance past the vertical bar. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-28 18:09:08 +02:00
|
|
|
lookbehindlength = META_DATA(*pptr);
|
2016-10-02 18:01:01 +02:00
|
|
|
pptr++;
|
|
|
|
}
|
|
|
|
/* Control never reaches here */
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Check for anchored pattern *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Try to find out if this is an anchored regular expression. Consider each
|
|
|
|
alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket
|
|
|
|
all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then
|
|
|
|
it's anchored. However, if this is a multiline pattern, then only OP_SOD will
|
|
|
|
be found, because ^ generates OP_CIRCM in that mode.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
We can also consider a regex to be anchored if OP_SOM starts all its branches.
|
|
|
|
This is the code for \G, which means "match at start of match position, taking
|
|
|
|
into account the match offset".
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
A branch is also implicitly anchored if it starts with .* and DOTALL is set,
|
|
|
|
because that will try the rest of the pattern at all possible matching points,
|
|
|
|
so there is no point trying again.... er ....
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
.... except when the .* appears inside capturing parentheses, and there is a
|
|
|
|
subsequent back reference to those parentheses. We haven't enough information
|
|
|
|
to catch that case precisely.
|
|
|
|
|
|
|
|
At first, the best we could do was to detect when .* was in capturing brackets
|
|
|
|
and the highest back reference was greater than or equal to that level.
|
|
|
|
However, by keeping a bitmap of the first 31 back references, we can catch some
|
|
|
|
of the more common cases more precisely.
|
|
|
|
|
|
|
|
... A second exception is when the .* appears inside an atomic group, because
|
|
|
|
this prevents the number of characters it matches from being adjusted.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
code points to start of the compiled pattern
|
|
|
|
bracket_map a bitmap of which brackets we are inside while testing; this
|
|
|
|
handles up to substring 31; after that we just have to take
|
|
|
|
the less precise approach
|
|
|
|
cb points to the compile data block
|
|
|
|
atomcount atomic group level
|
2016-11-01 16:58:28 +01:00
|
|
|
inassert TRUE if in an assertion
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: TRUE or FALSE
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
is_anchored(PCRE2_SPTR code, unsigned int bracket_map, compile_block *cb,
|
2016-11-01 16:58:28 +01:00
|
|
|
int atomcount, BOOL inassert)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
do {
|
|
|
|
PCRE2_SPTR scode = first_significant_code(
|
|
|
|
code + PRIV(OP_lengths)[*code], FALSE);
|
|
|
|
int op = *scode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Non-capturing brackets */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op == OP_BRA || op == OP_BRAPOS ||
|
|
|
|
op == OP_SBRA || op == OP_SBRAPOS)
|
|
|
|
{
|
2016-11-01 18:45:54 +01:00
|
|
|
if (!is_anchored(scode, bracket_map, cb, atomcount, inassert))
|
2016-11-01 16:58:28 +01:00
|
|
|
return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2015-11-30 18:31:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Capturing brackets */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op == OP_CBRA || op == OP_CBRAPOS ||
|
|
|
|
op == OP_SCBRA || op == OP_SCBRAPOS)
|
|
|
|
{
|
|
|
|
int n = GET2(scode, 1+LINK_SIZE);
|
|
|
|
int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
|
2016-11-01 16:58:28 +01:00
|
|
|
if (!is_anchored(scode, new_map, cb, atomcount, inassert)) return FALSE;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Positive forward assertion */
|
|
|
|
|
|
|
|
else if (op == OP_ASSERT)
|
|
|
|
{
|
|
|
|
if (!is_anchored(scode, bracket_map, cb, atomcount, TRUE)) return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-02 18:53:29 +02:00
|
|
|
/* Condition. If there is no second branch, it can't be anchored. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2018-09-03 17:20:40 +02:00
|
|
|
else if (op == OP_COND || op == OP_SCOND)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2018-09-02 18:53:29 +02:00
|
|
|
if (scode[GET(scode,1)] != OP_ALT) return FALSE;
|
2016-11-01 18:45:54 +01:00
|
|
|
if (!is_anchored(scode, bracket_map, cb, atomcount, inassert))
|
2016-11-01 16:58:28 +01:00
|
|
|
return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Atomic groups */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-11 18:59:23 +01:00
|
|
|
else if (op == OP_ONCE)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2016-11-01 16:58:28 +01:00
|
|
|
if (!is_anchored(scode, bracket_map, cb, atomcount + 1, inassert))
|
2016-10-02 18:01:01 +02:00
|
|
|
return FALSE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and
|
|
|
|
it isn't in brackets that are or may be referenced or inside an atomic
|
2016-11-01 16:58:28 +01:00
|
|
|
group or an assertion. Also the pattern must not contain *PRUNE or *SKIP,
|
|
|
|
because these break the feature. Consider, for example, /(?s).*?(*PRUNE)b/
|
|
|
|
with the subject "aab", which matches "b", i.e. not at the start of a line.
|
|
|
|
There is also an option that disables auto-anchoring. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR ||
|
|
|
|
op == OP_TYPEPOSSTAR))
|
|
|
|
{
|
|
|
|
if (scode[1] != OP_ALLANY || (bracket_map & cb->backref_map) != 0 ||
|
2016-11-01 16:58:28 +01:00
|
|
|
atomcount > 0 || cb->had_pruneorskip || inassert ||
|
2016-10-02 18:01:01 +02:00
|
|
|
(cb->external_options & PCRE2_NO_DOTSTAR_ANCHOR) != 0)
|
|
|
|
return FALSE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check for explicit anchoring */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op != OP_SOD && op != OP_SOM && op != OP_CIRC) return FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code += GET(code, 1);
|
|
|
|
}
|
|
|
|
while (*code == OP_ALT); /* Loop for each alternative */
|
|
|
|
return TRUE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Check for starting with ^ or .* *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This is called to find out if every branch starts with ^ or .* so that
|
|
|
|
"first char" processing can be done to speed things up in multiline
|
|
|
|
matching and for non-DOTALL patterns that start with .* (which must start at
|
|
|
|
the beginning or after \n). As in the case of is_anchored() (see above), we
|
|
|
|
have to take account of back references to capturing brackets that contain .*
|
|
|
|
because in that case we can't make the assumption. Also, the appearance of .*
|
2016-10-18 13:22:40 +02:00
|
|
|
inside atomic brackets or in an assertion, or in a pattern that contains *PRUNE
|
|
|
|
or *SKIP does not count, because once again the assumption no longer holds.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
code points to start of the compiled pattern or a group
|
|
|
|
bracket_map a bitmap of which brackets we are inside while testing; this
|
|
|
|
handles up to substring 31; after that we just have to take
|
|
|
|
the less precise approach
|
|
|
|
cb points to the compile data
|
|
|
|
atomcount atomic group level
|
2016-10-18 13:22:40 +02:00
|
|
|
inassert TRUE if in an assertion
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: TRUE or FALSE
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
is_startline(PCRE2_SPTR code, unsigned int bracket_map, compile_block *cb,
|
2016-10-18 13:22:40 +02:00
|
|
|
int atomcount, BOOL inassert)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
do {
|
|
|
|
PCRE2_SPTR scode = first_significant_code(
|
|
|
|
code + PRIV(OP_lengths)[*code], FALSE);
|
|
|
|
int op = *scode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* If we are at the start of a conditional assertion group, *both* the
|
|
|
|
conditional assertion *and* what follows the condition must satisfy the test
|
|
|
|
for start of line. Other kinds of condition fail. Note that there may be an
|
|
|
|
auto-callout at the start of a condition. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op == OP_COND)
|
|
|
|
{
|
|
|
|
scode += 1 + LINK_SIZE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*scode == OP_CALLOUT) scode += PRIV(OP_lengths)[OP_CALLOUT];
|
|
|
|
else if (*scode == OP_CALLOUT_STR) scode += GET(scode, 1 + 2*LINK_SIZE);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch (*scode)
|
|
|
|
{
|
|
|
|
case OP_CREF:
|
|
|
|
case OP_DNCREF:
|
|
|
|
case OP_RREF:
|
|
|
|
case OP_DNRREF:
|
|
|
|
case OP_FAIL:
|
|
|
|
case OP_FALSE:
|
|
|
|
case OP_TRUE:
|
|
|
|
return FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default: /* Assertion */
|
2016-10-18 13:22:40 +02:00
|
|
|
if (!is_startline(scode, bracket_map, cb, atomcount, TRUE)) return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
do scode += GET(scode, 1); while (*scode == OP_ALT);
|
|
|
|
scode += 1 + LINK_SIZE;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
scode = first_significant_code(scode, FALSE);
|
|
|
|
op = *scode;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Non-capturing brackets */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (op == OP_BRA || op == OP_BRAPOS ||
|
|
|
|
op == OP_SBRA || op == OP_SBRAPOS)
|
|
|
|
{
|
2016-10-18 13:22:40 +02:00
|
|
|
if (!is_startline(scode, bracket_map, cb, atomcount, inassert))
|
|
|
|
return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Capturing brackets */
|
2015-10-25 18:35:34 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op == OP_CBRA || op == OP_CBRAPOS ||
|
|
|
|
op == OP_SCBRA || op == OP_SCBRAPOS)
|
|
|
|
{
|
|
|
|
int n = GET2(scode, 1+LINK_SIZE);
|
|
|
|
int new_map = bracket_map | ((n < 32)? (1u << n) : 1);
|
2016-10-18 13:22:40 +02:00
|
|
|
if (!is_startline(scode, new_map, cb, atomcount, inassert)) return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2015-04-13 19:29:05 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Positive forward assertions */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op == OP_ASSERT)
|
|
|
|
{
|
2016-10-18 13:22:40 +02:00
|
|
|
if (!is_startline(scode, bracket_map, cb, atomcount, TRUE))
|
|
|
|
return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Atomic brackets */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-11 18:59:23 +01:00
|
|
|
else if (op == OP_ONCE)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2016-10-18 13:22:40 +02:00
|
|
|
if (!is_startline(scode, bracket_map, cb, atomcount + 1, inassert))
|
|
|
|
return FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* .* means "start at start or after \n" if it isn't in atomic brackets or
|
2016-10-18 13:22:40 +02:00
|
|
|
brackets that may be referenced or an assertion, and as long as the pattern
|
|
|
|
does not contain *PRUNE or *SKIP, because these break the feature. Consider,
|
|
|
|
for example, /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab",
|
|
|
|
i.e. not at the start of a line. There is also an option that disables this
|
|
|
|
optimization. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR)
|
|
|
|
{
|
|
|
|
if (scode[1] != OP_ANY || (bracket_map & cb->backref_map) != 0 ||
|
2016-10-18 13:22:40 +02:00
|
|
|
atomcount > 0 || cb->had_pruneorskip || inassert ||
|
2016-10-02 18:01:01 +02:00
|
|
|
(cb->external_options & PCRE2_NO_DOTSTAR_ANCHOR) != 0)
|
|
|
|
return FALSE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check for explicit circumflex; anything else gives a FALSE result. Note
|
2017-03-11 18:59:23 +01:00
|
|
|
in particular that this includes atomic brackets OP_ONCE because the number
|
|
|
|
of characters matched by .* cannot be adjusted inside them. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else if (op != OP_CIRC && op != OP_CIRCM) return FALSE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Move on to the next alternative */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code += GET(code, 1);
|
|
|
|
}
|
|
|
|
while (*code == OP_ALT); /* Loop for each alternative */
|
|
|
|
return TRUE;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Scan compiled regex for recursion reference *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function scans through a compiled pattern until it finds an instance of
|
|
|
|
OP_RECURSE.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
code points to start of expression
|
|
|
|
utf TRUE in UTF mode
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: pointer to the opcode for OP_RECURSE, or NULL if not found
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static PCRE2_SPTR
|
|
|
|
find_recurse(PCRE2_SPTR code, BOOL utf)
|
|
|
|
{
|
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
PCRE2_UCHAR c = *code;
|
|
|
|
if (c == OP_END) return NULL;
|
|
|
|
if (c == OP_RECURSE) return code;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* XCLASS is used for classes that cannot be represented just by a bit map.
|
|
|
|
This includes negated single high-valued characters. CALLOUT_STR is used for
|
|
|
|
callouts with string arguments. In both cases the length in the table is
|
|
|
|
zero; the actual length is stored in the compiled code. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (c == OP_XCLASS) code += GET(code, 1);
|
|
|
|
else if (c == OP_CALLOUT_STR) code += GET(code, 1 + 2*LINK_SIZE);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Otherwise, we can get the item's length from the table, except that for
|
|
|
|
repeated character types, we have to test for \p and \P, which have an extra
|
|
|
|
two code units of parameters, and for MARK/PRUNE/SKIP/THEN with an argument,
|
|
|
|
we must add in its length. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else
|
|
|
|
{
|
|
|
|
switch(c)
|
|
|
|
{
|
|
|
|
case OP_TYPESTAR:
|
|
|
|
case OP_TYPEMINSTAR:
|
|
|
|
case OP_TYPEPLUS:
|
|
|
|
case OP_TYPEMINPLUS:
|
|
|
|
case OP_TYPEQUERY:
|
|
|
|
case OP_TYPEMINQUERY:
|
|
|
|
case OP_TYPEPOSSTAR:
|
|
|
|
case OP_TYPEPOSPLUS:
|
|
|
|
case OP_TYPEPOSQUERY:
|
|
|
|
if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_TYPEPOSUPTO:
|
|
|
|
case OP_TYPEUPTO:
|
|
|
|
case OP_TYPEMINUPTO:
|
|
|
|
case OP_TYPEEXACT:
|
|
|
|
if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP)
|
|
|
|
code += 2;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case OP_MARK:
|
2018-07-28 18:23:24 +02:00
|
|
|
case OP_COMMIT_ARG:
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_PRUNE_ARG:
|
|
|
|
case OP_SKIP_ARG:
|
|
|
|
case OP_THEN_ARG:
|
|
|
|
code += code[1];
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Add in the fixed length from the table */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code += PRIV(OP_lengths)[c];
|
|
|
|
|
|
|
|
/* In UTF-8 and UTF-16 modes, opcodes that are followed by a character may
|
|
|
|
be followed by a multi-unit character. The length in the table is a
|
|
|
|
minimum, so we have to arrange to skip the extra units. */
|
|
|
|
|
|
|
|
#ifdef MAYBE_UTF_MULTI
|
|
|
|
if (utf) switch(c)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_CHAR:
|
|
|
|
case OP_CHARI:
|
|
|
|
case OP_NOT:
|
|
|
|
case OP_NOTI:
|
|
|
|
case OP_EXACT:
|
|
|
|
case OP_EXACTI:
|
|
|
|
case OP_NOTEXACT:
|
|
|
|
case OP_NOTEXACTI:
|
|
|
|
case OP_UPTO:
|
|
|
|
case OP_UPTOI:
|
|
|
|
case OP_NOTUPTO:
|
|
|
|
case OP_NOTUPTOI:
|
|
|
|
case OP_MINUPTO:
|
|
|
|
case OP_MINUPTOI:
|
|
|
|
case OP_NOTMINUPTO:
|
|
|
|
case OP_NOTMINUPTOI:
|
|
|
|
case OP_POSUPTO:
|
|
|
|
case OP_POSUPTOI:
|
|
|
|
case OP_NOTPOSUPTO:
|
|
|
|
case OP_NOTPOSUPTOI:
|
|
|
|
case OP_STAR:
|
|
|
|
case OP_STARI:
|
|
|
|
case OP_NOTSTAR:
|
|
|
|
case OP_NOTSTARI:
|
|
|
|
case OP_MINSTAR:
|
|
|
|
case OP_MINSTARI:
|
|
|
|
case OP_NOTMINSTAR:
|
|
|
|
case OP_NOTMINSTARI:
|
|
|
|
case OP_POSSTAR:
|
|
|
|
case OP_POSSTARI:
|
|
|
|
case OP_NOTPOSSTAR:
|
|
|
|
case OP_NOTPOSSTARI:
|
|
|
|
case OP_PLUS:
|
|
|
|
case OP_PLUSI:
|
|
|
|
case OP_NOTPLUS:
|
|
|
|
case OP_NOTPLUSI:
|
|
|
|
case OP_MINPLUS:
|
|
|
|
case OP_MINPLUSI:
|
|
|
|
case OP_NOTMINPLUS:
|
|
|
|
case OP_NOTMINPLUSI:
|
|
|
|
case OP_POSPLUS:
|
|
|
|
case OP_POSPLUSI:
|
|
|
|
case OP_NOTPOSPLUS:
|
|
|
|
case OP_NOTPOSPLUSI:
|
|
|
|
case OP_QUERY:
|
|
|
|
case OP_QUERYI:
|
|
|
|
case OP_NOTQUERY:
|
|
|
|
case OP_NOTQUERYI:
|
|
|
|
case OP_MINQUERY:
|
|
|
|
case OP_MINQUERYI:
|
|
|
|
case OP_NOTMINQUERY:
|
|
|
|
case OP_NOTMINQUERYI:
|
|
|
|
case OP_POSQUERY:
|
|
|
|
case OP_POSQUERYI:
|
|
|
|
case OP_NOTPOSQUERY:
|
|
|
|
case OP_NOTPOSQUERYI:
|
|
|
|
if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
#else
|
|
|
|
(void)(utf); /* Keep compiler happy by referencing function argument */
|
|
|
|
#endif /* MAYBE_UTF_MULTI */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Check for asserted fixed first code unit *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* During compilation, the "first code unit" settings from forward assertions
|
|
|
|
are discarded, because they can cause conflicts with actual literals that
|
|
|
|
follow. However, if we end up without a first code unit setting for an
|
|
|
|
unanchored pattern, it is worth scanning the regex to see if there is an
|
|
|
|
initial asserted first code unit. If all branches start with the same asserted
|
|
|
|
code unit, or with a non-conditional bracket all of whose alternatives start
|
|
|
|
with the same asserted code unit (recurse ad lib), then we return that code
|
|
|
|
unit, with the flags set to zero or REQ_CASELESS; otherwise return zero with
|
|
|
|
REQ_NONE in the flags.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
code points to start of compiled pattern
|
|
|
|
flags points to the first code unit flags
|
2017-12-12 17:23:01 +01:00
|
|
|
inassert non-zero if in an assertion
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the fixed first code unit, or 0 with REQ_NONE in flags
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static uint32_t
|
2017-12-12 17:23:01 +01:00
|
|
|
find_firstassertedcu(PCRE2_SPTR code, int32_t *flags, uint32_t inassert)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t c = 0;
|
|
|
|
int cflags = REQ_NONE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*flags = REQ_NONE;
|
|
|
|
do {
|
|
|
|
uint32_t d;
|
|
|
|
int dflags;
|
|
|
|
int xl = (*code == OP_CBRA || *code == OP_SCBRA ||
|
|
|
|
*code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0;
|
|
|
|
PCRE2_SPTR scode = first_significant_code(code + 1+LINK_SIZE + xl, TRUE);
|
|
|
|
PCRE2_UCHAR op = *scode;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch(op)
|
|
|
|
{
|
|
|
|
default:
|
|
|
|
return 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_BRA:
|
|
|
|
case OP_BRAPOS:
|
|
|
|
case OP_CBRA:
|
|
|
|
case OP_SCBRA:
|
|
|
|
case OP_CBRAPOS:
|
|
|
|
case OP_SCBRAPOS:
|
|
|
|
case OP_ASSERT:
|
|
|
|
case OP_ONCE:
|
2017-12-12 17:23:01 +01:00
|
|
|
d = find_firstassertedcu(scode, &dflags, inassert + ((op==OP_ASSERT)?1:0));
|
2016-10-02 18:01:01 +02:00
|
|
|
if (dflags < 0)
|
|
|
|
return 0;
|
|
|
|
if (cflags < 0) { c = d; cflags = dflags; }
|
|
|
|
else if (c != d || cflags != dflags) return 0;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case OP_EXACT:
|
|
|
|
scode += IMM2_SIZE;
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
case OP_CHAR:
|
|
|
|
case OP_PLUS:
|
|
|
|
case OP_MINPLUS:
|
|
|
|
case OP_POSPLUS:
|
2017-12-12 17:23:01 +01:00
|
|
|
if (inassert == 0) return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cflags < 0) { c = scode[1]; cflags = 0; }
|
|
|
|
else if (c != scode[1]) return 0;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_EXACTI:
|
|
|
|
scode += IMM2_SIZE;
|
|
|
|
/* Fall through */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case OP_CHARI:
|
|
|
|
case OP_PLUSI:
|
|
|
|
case OP_MINPLUSI:
|
|
|
|
case OP_POSPLUSI:
|
2017-12-12 17:23:01 +01:00
|
|
|
if (inassert == 0) return 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; }
|
|
|
|
else if (c != scode[1]) return 0;
|
|
|
|
break;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
code += GET(code, 1);
|
|
|
|
}
|
|
|
|
while (*code == OP_ALT);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
*flags = cflags;
|
|
|
|
return c;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Add an entry to the name/number table *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called between compiling passes to add an entry to the
|
|
|
|
name/number table, maintaining alphabetical order. Checking for permitted
|
|
|
|
and forbidden duplicates has already been done.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
cb the compile data block
|
|
|
|
name the name to add
|
|
|
|
length the length of the name
|
|
|
|
groupno the group number
|
|
|
|
tablecount the count of names in the table so far
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: nothing
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static void
|
|
|
|
add_name_to_table(compile_block *cb, PCRE2_SPTR name, int length,
|
|
|
|
unsigned int groupno, uint32_t tablecount)
|
|
|
|
{
|
|
|
|
uint32_t i;
|
|
|
|
PCRE2_UCHAR *slot = cb->name_table;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < tablecount; i++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
int crc = memcmp(name, slot+IMM2_SIZE, CU2BYTES(length));
|
|
|
|
if (crc == 0 && slot[IMM2_SIZE+length] != 0)
|
|
|
|
crc = -1; /* Current name is a substring */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Make space in the table and break the loop for an earlier name. For a
|
|
|
|
duplicate or later name, carry on. We do this for duplicates so that in the
|
|
|
|
simple case (when ?(| is not used) they are in order of their numbers. In all
|
|
|
|
cases they are in the order in which they appear in the pattern. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (crc < 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2018-08-10 18:27:44 +02:00
|
|
|
(void)memmove(slot + cb->name_entry_size, slot,
|
2016-12-21 18:09:11 +01:00
|
|
|
CU2BYTES((tablecount - i) * cb->name_entry_size));
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Continue the loop for a later or duplicate name */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
slot += cb->name_entry_size;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
PUT2(slot, 0, groupno);
|
|
|
|
memcpy(slot + IMM2_SIZE, name, CU2BYTES(length));
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Add a terminating zero and fill the rest of the slot with zeroes so that
|
|
|
|
the memory is all initialized. Otherwise valgrind moans about uninitialized
|
|
|
|
memory when saving serialized compiled patterns. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
memset(slot + IMM2_SIZE + length, 0,
|
|
|
|
CU2BYTES(cb->name_entry_size - length - IMM2_SIZE));
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Skip in parsed pattern *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called to skip parts of the parsed pattern when finding the
|
|
|
|
length of a lookbehind branch. It is called after (*ACCEPT) and (*FAIL) to find
|
|
|
|
the end of the branch, it is called to skip over an internal lookaround, and it
|
|
|
|
is also called to skip to the end of a class, during which it will never
|
|
|
|
encounter nested groups (but there's no need to have special code for that).
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-16 18:17:47 +01:00
|
|
|
When called to find the end of a branch or group, pptr must point to the first
|
|
|
|
meta code inside the branch, not the branch-starting code. In other cases it
|
|
|
|
can point to the item that causes the function to be called.
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
pptr current pointer to skip from
|
|
|
|
skiptype PSKIP_CLASS when skipping to end of class
|
|
|
|
PSKIP_ALT when META_ALT ends the skip
|
|
|
|
PSKIP_KET when only META_KET ends the skip
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: new value of pptr
|
2016-11-23 18:17:57 +01:00
|
|
|
NULL if META_END is reached - should never occur
|
2016-12-28 13:26:12 +01:00
|
|
|
or for an unknown meta value - likewise
|
2016-10-02 18:01:01 +02:00
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static uint32_t *
|
|
|
|
parsed_skip(uint32_t *pptr, uint32_t skiptype)
|
|
|
|
{
|
|
|
|
uint32_t nestlevel = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-16 18:17:47 +01:00
|
|
|
for (;; pptr++)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2016-11-23 18:17:57 +01:00
|
|
|
uint32_t meta = META_CODE(*pptr);
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2016-11-23 18:17:57 +01:00
|
|
|
switch(meta)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
2016-11-23 18:17:57 +01:00
|
|
|
default: /* Just skip over most items */
|
2016-12-24 17:25:11 +01:00
|
|
|
if (meta < META_END) continue; /* Literal */
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-23 18:17:57 +01:00
|
|
|
/* This should never occur. */
|
|
|
|
|
|
|
|
case META_END:
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
/* The data for these items is variable in length. */
|
|
|
|
|
|
|
|
case META_BACKREF: /* Offset is present only if group >= 10 */
|
|
|
|
if (META_DATA(*pptr) >= 10) pptr += SIZEOFFSET;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_ESCAPE: /* A few escapes are followed by data items. */
|
|
|
|
switch (META_DATA(*pptr))
|
|
|
|
{
|
|
|
|
case ESC_P:
|
|
|
|
case ESC_p:
|
|
|
|
pptr += 1;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case ESC_g:
|
|
|
|
case ESC_k:
|
|
|
|
pptr += 1 + SIZEOFFSET;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MARK: /* Add the length of the name. */
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_COMMIT_ARG:
|
2016-11-23 18:17:57 +01:00
|
|
|
case META_PRUNE_ARG:
|
|
|
|
case META_SKIP_ARG:
|
|
|
|
case META_THEN_ARG:
|
|
|
|
pptr += pptr[1];
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* These are the "active" items in this loop. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CLASS_END:
|
|
|
|
if (skiptype == PSKIP_CLASS) return pptr;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ATOMIC:
|
|
|
|
case META_CAPTURE:
|
|
|
|
case META_COND_ASSERT:
|
|
|
|
case META_COND_DEFINE:
|
|
|
|
case META_COND_NAME:
|
|
|
|
case META_COND_NUMBER:
|
|
|
|
case META_COND_RNAME:
|
|
|
|
case META_COND_RNUMBER:
|
|
|
|
case META_COND_VERSION:
|
|
|
|
case META_LOOKAHEAD:
|
|
|
|
case META_LOOKAHEADNOT:
|
|
|
|
case META_LOOKBEHIND:
|
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
case META_NOCAPTURE:
|
|
|
|
nestlevel++;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ALT:
|
|
|
|
if (nestlevel == 0 && skiptype == PSKIP_ALT) return pptr;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_KET:
|
|
|
|
if (nestlevel == 0) return pptr;
|
|
|
|
nestlevel--;
|
|
|
|
break;
|
|
|
|
}
|
2016-11-23 18:17:57 +01:00
|
|
|
|
|
|
|
/* The extra data item length for each meta is in a table. */
|
|
|
|
|
2016-12-24 17:25:11 +01:00
|
|
|
meta = (meta >> 16) & 0x7fff;
|
2016-11-23 18:17:57 +01:00
|
|
|
if (meta >= sizeof(meta_extra_lengths)) return NULL;
|
|
|
|
pptr += meta_extra_lengths[meta];
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
|
|
|
/* Control never reaches here */
|
|
|
|
return pptr;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/*************************************************
|
|
|
|
* Find length of a parsed group *
|
|
|
|
*************************************************/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This is called for nested groups within a branch of a lookbehind whose
|
|
|
|
length is being computed. If all the branches in the nested group have the same
|
|
|
|
length, that is OK. On entry, the pointer must be at the first element after
|
2017-03-16 18:17:47 +01:00
|
|
|
the group initializing code. On exit it points to OP_KET. Caching is used to
|
|
|
|
improve processing speed when the same capturing group occurs many times.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
pptrptr pointer to pointer in the parsed pattern
|
2017-03-16 18:17:47 +01:00
|
|
|
isinline FALSE if a reference or recursion; TRUE for inline group
|
2016-10-02 18:01:01 +02:00
|
|
|
errcodeptr pointer to the errorcode
|
|
|
|
lcptr pointer to the loop counter
|
|
|
|
group number of captured group or -1 for a non-capturing group
|
|
|
|
recurses chain of recurse_check to catch mutual recursion
|
|
|
|
cb pointer to the compile data
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the group length or a negative number
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static int
|
2017-03-16 18:17:47 +01:00
|
|
|
get_grouplength(uint32_t **pptrptr, BOOL isinline, int *errcodeptr, int *lcptr,
|
2016-10-02 18:01:01 +02:00
|
|
|
int group, parsed_recurse_check *recurses, compile_block *cb)
|
|
|
|
{
|
|
|
|
int branchlength;
|
|
|
|
int grouplength = -1;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The cache can be used only if there is no possibility of there being two
|
2017-05-17 19:55:11 +02:00
|
|
|
groups with the same number. We do not need to set the end pointer for a group
|
|
|
|
that is being processed as a back reference or recursion, but we must do so for
|
2017-03-16 18:17:47 +01:00
|
|
|
an inline group. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-03-16 18:17:47 +01:00
|
|
|
if (group > 0 && (cb->external_flags & PCRE2_DUPCAPUSED) == 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
uint32_t groupinfo = cb->groupinfo[group];
|
2017-03-16 18:17:47 +01:00
|
|
|
if ((groupinfo & GI_NOT_FIXED_LENGTH) != 0) return -1;
|
|
|
|
if ((groupinfo & GI_SET_FIXED_LENGTH) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-03-16 18:17:47 +01:00
|
|
|
if (isinline) *pptrptr = parsed_skip(*pptrptr, PSKIP_KET);
|
|
|
|
return groupinfo & GI_FIXED_LENGTH_MASK;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-03-16 18:17:47 +01:00
|
|
|
/* Scan the group. In this case we find the end pointer of necessity. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for(;;)
|
|
|
|
{
|
|
|
|
branchlength = get_branchlength(pptrptr, errcodeptr, lcptr, recurses, cb);
|
|
|
|
if (branchlength < 0) goto ISNOTFIXED;
|
|
|
|
if (grouplength == -1) grouplength = branchlength;
|
|
|
|
else if (grouplength != branchlength) goto ISNOTFIXED;
|
|
|
|
if (**pptrptr == META_KET) break;
|
|
|
|
*pptrptr += 1; /* Skip META_ALT */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (group > 0)
|
|
|
|
cb->groupinfo[group] |= (uint32_t)(GI_SET_FIXED_LENGTH | grouplength);
|
|
|
|
return grouplength;
|
|
|
|
|
|
|
|
ISNOTFIXED:
|
|
|
|
if (group > 0) cb->groupinfo[group] |= GI_NOT_FIXED_LENGTH;
|
|
|
|
return -1;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2014-03-07 18:28:52 +01:00
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Find length of a parsed branch *
|
2014-03-07 18:28:52 +01:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Return a fixed length for a branch in a lookbehind, giving an error if the
|
|
|
|
length is not fixed. If any lookbehinds are encountered on the way, they get
|
|
|
|
their length set. On entry, *pptrptr points to the first element inside the
|
|
|
|
branch. On exit it is set to point to the ALT or KET.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments:
|
|
|
|
pptrptr pointer to pointer in the parsed pattern
|
|
|
|
errcodeptr pointer to error code
|
|
|
|
lcptr pointer to loop counter
|
|
|
|
recurses chain of recurse_check to catch mutual recursion
|
|
|
|
cb pointer to compile block
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: the length, or a negative value on error
|
|
|
|
*/
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static int
|
|
|
|
get_branchlength(uint32_t **pptrptr, int *errcodeptr, int *lcptr,
|
|
|
|
parsed_recurse_check *recurses, compile_block *cb)
|
|
|
|
{
|
|
|
|
int branchlength = 0;
|
|
|
|
int grouplength;
|
|
|
|
uint32_t lastitemlength = 0;
|
|
|
|
uint32_t *pptr = *pptrptr;
|
|
|
|
PCRE2_SIZE offset;
|
|
|
|
parsed_recurse_check this_recurse;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A large and/or complex regex can take too long to process. This can happen
|
|
|
|
more often when (?| groups are present in the pattern because their length
|
|
|
|
cannot be cached. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((*lcptr)++ > 2000)
|
|
|
|
{
|
|
|
|
*errcodeptr = ERR35; /* Lookbehind is too complicated */
|
|
|
|
return -1;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Scan the branch, accumulating the length. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (;; pptr++)
|
|
|
|
{
|
|
|
|
parsed_recurse_check *r;
|
|
|
|
uint32_t *gptr, *gptrend;
|
|
|
|
uint32_t escape;
|
|
|
|
uint32_t group = 0;
|
|
|
|
uint32_t itemlength = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (*pptr < META_END)
|
|
|
|
{
|
|
|
|
itemlength = 1;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
else switch (META_CODE(*pptr))
|
|
|
|
{
|
|
|
|
case META_KET:
|
|
|
|
case META_ALT:
|
|
|
|
goto EXIT;
|
|
|
|
|
|
|
|
/* (*ACCEPT) and (*FAIL) terminate the branch, but we must skip to the
|
|
|
|
actual termination. */
|
|
|
|
|
|
|
|
case META_ACCEPT:
|
|
|
|
case META_FAIL:
|
|
|
|
pptr = parsed_skip(pptr, PSKIP_ALT);
|
2016-11-23 18:17:57 +01:00
|
|
|
if (pptr == NULL) goto PARSED_SKIP_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto EXIT;
|
|
|
|
|
|
|
|
case META_MARK:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_COMMIT_ARG:
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE_ARG:
|
|
|
|
case META_SKIP_ARG:
|
|
|
|
case META_THEN_ARG:
|
|
|
|
pptr += pptr[1] + 1;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CIRCUMFLEX:
|
|
|
|
case META_COMMIT:
|
|
|
|
case META_DOLLAR:
|
|
|
|
case META_PRUNE:
|
|
|
|
case META_SKIP:
|
|
|
|
case META_THEN:
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_OPTIONS:
|
|
|
|
pptr += 1;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BIGVALUE:
|
|
|
|
itemlength = 1;
|
|
|
|
pptr += 1;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CLASS:
|
|
|
|
case META_CLASS_NOT:
|
|
|
|
itemlength = 1;
|
|
|
|
pptr = parsed_skip(pptr, PSKIP_CLASS);
|
2016-11-23 18:17:57 +01:00
|
|
|
if (pptr == NULL) goto PARSED_SKIP_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CLASS_EMPTY_NOT:
|
|
|
|
case META_DOT:
|
|
|
|
itemlength = 1;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CALLOUT_NUMBER:
|
|
|
|
pptr += 3;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CALLOUT_STRING:
|
|
|
|
pptr += 3 + SIZEOFFSET;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Only some escapes consume a character. Of those, \R and \X are never
|
|
|
|
allowed because they might match more than character. \C is allowed only in
|
|
|
|
32-bit and non-UTF 8/16-bit modes. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ESCAPE:
|
|
|
|
escape = META_DATA(*pptr);
|
|
|
|
if (escape == ESC_R || escape == ESC_X) return -1;
|
|
|
|
if (escape > ESC_b && escape < ESC_Z)
|
|
|
|
{
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH != 32
|
|
|
|
if ((cb->external_options & PCRE2_UTF) != 0 && escape == ESC_C)
|
|
|
|
{
|
|
|
|
*errcodeptr = ERR36;
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
itemlength = 1;
|
|
|
|
if (escape == ESC_p || escape == ESC_P) pptr++; /* Skip prop data */
|
|
|
|
}
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-05-17 19:55:11 +02:00
|
|
|
/* Lookaheads can be ignored, but we must start the skip inside the group
|
2017-03-16 18:17:47 +01:00
|
|
|
so that it isn't treated as a group within the branch. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_LOOKAHEAD:
|
|
|
|
case META_LOOKAHEADNOT:
|
2017-03-16 18:17:47 +01:00
|
|
|
pptr = parsed_skip(pptr + 1, PSKIP_KET);
|
2016-11-23 18:17:57 +01:00
|
|
|
if (pptr == NULL) goto PARSED_SKIP_FAILED;
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-02 13:23:45 +02:00
|
|
|
/* Also ignore any qualifiers that follow a lookahead assertion. */
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-02 13:23:45 +02:00
|
|
|
switch (pptr[1])
|
|
|
|
{
|
|
|
|
case META_ASTERISK:
|
|
|
|
case META_ASTERISK_PLUS:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_ASTERISK_QUERY:
|
2018-07-02 13:23:45 +02:00
|
|
|
case META_PLUS:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_PLUS_PLUS:
|
2018-07-02 13:23:45 +02:00
|
|
|
case META_PLUS_QUERY:
|
|
|
|
case META_QUERY:
|
|
|
|
case META_QUERY_PLUS:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_QUERY_QUERY:
|
2018-07-02 13:23:45 +02:00
|
|
|
pptr++;
|
|
|
|
break;
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-02 13:23:45 +02:00
|
|
|
case META_MINMAX:
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
pptr += 3;
|
|
|
|
break;
|
2018-07-28 18:23:24 +02:00
|
|
|
|
2018-07-02 13:23:45 +02:00
|
|
|
default:
|
2018-07-28 18:23:24 +02:00
|
|
|
break;
|
2018-07-02 13:23:45 +02:00
|
|
|
}
|
2016-10-02 18:01:01 +02:00
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Lookbehinds can be ignored, but must themselves be checked. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_LOOKBEHIND:
|
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
if (!set_lookbehind_lengths(&pptr, errcodeptr, lcptr, recurses, cb))
|
|
|
|
return -1;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Back references and recursions are handled by very similar code. At this
|
|
|
|
stage, the names generated in the parsing pass are available, but the main
|
|
|
|
name table has not yet been created. So for the named varieties, scan the
|
|
|
|
list of names in order to get the number of the first one in the pattern,
|
|
|
|
and whether or not this name is duplicated. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BACKREF_BYNAME:
|
|
|
|
if ((cb->external_options & PCRE2_MATCH_UNSET_BACKREF) != 0)
|
|
|
|
goto ISNOTFIXED;
|
2017-05-17 19:55:11 +02:00
|
|
|
/* Fall through */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_RECURSE_BYNAME:
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
PCRE2_SPTR name;
|
|
|
|
BOOL is_dupname = FALSE;
|
|
|
|
named_group *ng = cb->named_groups;
|
|
|
|
uint32_t meta_code = META_CODE(*pptr);
|
|
|
|
uint32_t length = *(++pptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
GETPLUSOFFSET(offset, pptr);
|
|
|
|
name = cb->start_pattern + offset;
|
|
|
|
for (i = 0; i < cb->names_found; i++, ng++)
|
|
|
|
{
|
|
|
|
if (length == ng->length && PRIV(strncmp)(name, ng->name, length) == 0)
|
|
|
|
{
|
|
|
|
group = ng->number;
|
|
|
|
is_dupname = ng->isdup;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (group == 0)
|
|
|
|
{
|
|
|
|
*errcodeptr = ERR15; /* Non-existent subpattern */
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
return -1;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A numerical back reference can be fixed length if duplicate capturing
|
|
|
|
groups are not being used. A non-duplicate named back reference can also
|
|
|
|
be handled. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (meta_code == META_RECURSE_BYNAME ||
|
|
|
|
(!is_dupname && (cb->external_flags & PCRE2_DUPCAPUSED) == 0))
|
|
|
|
goto RECURSE_OR_BACKREF_LENGTH; /* Handle as a numbered version. */
|
|
|
|
}
|
|
|
|
goto ISNOTFIXED; /* Duplicate name or number */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* The offset values for back references < 10 are in a separate vector
|
|
|
|
because otherwise they would use more than two parsed pattern elements on
|
|
|
|
64-bit systems. */
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BACKREF:
|
|
|
|
if ((cb->external_options & PCRE2_MATCH_UNSET_BACKREF) != 0 ||
|
|
|
|
(cb->external_flags & PCRE2_DUPCAPUSED) != 0)
|
|
|
|
goto ISNOTFIXED;
|
|
|
|
group = META_DATA(*pptr);
|
|
|
|
if (group < 10)
|
|
|
|
{
|
|
|
|
offset = cb->small_ref_offset[group];
|
|
|
|
goto RECURSE_OR_BACKREF_LENGTH;
|
|
|
|
}
|
2015-03-11 18:44:16 +01:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
/* Fall through */
|
2017-06-03 19:50:03 +02:00
|
|
|
/* For groups >= 10 - picking up group twice does no harm. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* A true recursion implies not fixed length, but a subroutine call may
|
|
|
|
be OK. Back reference "recursions" are also failed. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_RECURSE:
|
|
|
|
group = META_DATA(*pptr);
|
|
|
|
GETPLUSOFFSET(offset, pptr);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
RECURSE_OR_BACKREF_LENGTH:
|
|
|
|
if (group > cb->bracount)
|
|
|
|
{
|
|
|
|
cb->erroroffset = offset;
|
|
|
|
*errcodeptr = ERR15; /* Non-existent subpattern */
|
|
|
|
return -1;
|
|
|
|
}
|
2016-10-23 19:05:09 +02:00
|
|
|
if (group == 0) goto ISNOTFIXED; /* Local recursion */
|
2016-10-02 18:01:01 +02:00
|
|
|
for (gptr = cb->parsed_pattern; *gptr != META_END; gptr++)
|
|
|
|
{
|
|
|
|
if (META_CODE(*gptr) == META_BIGVALUE) gptr++;
|
|
|
|
else if (*gptr == (META_CAPTURE | group)) break;
|
|
|
|
}
|
2016-10-26 18:59:22 +02:00
|
|
|
|
2017-05-17 19:55:11 +02:00
|
|
|
/* We must start the search for the end of the group at the first meta code
|
2017-03-16 18:17:47 +01:00
|
|
|
inside the group. Otherwise it will be treated as an enclosed group. */
|
|
|
|
|
|
|
|
gptrend = parsed_skip(gptr + 1, PSKIP_KET);
|
2016-11-23 18:17:57 +01:00
|
|
|
if (gptrend == NULL) goto PARSED_SKIP_FAILED;
|
2016-10-02 18:01:01 +02:00
|
|
|
if (pptr > gptr && pptr < gptrend) goto ISNOTFIXED; /* Local recursion */
|
|
|
|
for (r = recurses; r != NULL; r = r->prev) if (r->groupptr == gptr) break;
|
|
|
|
if (r != NULL) goto ISNOTFIXED; /* Mutual recursion */
|
|
|
|
this_recurse.prev = recurses;
|
|
|
|
this_recurse.groupptr = gptr;
|
2017-05-17 19:55:11 +02:00
|
|
|
|
2017-03-16 18:17:47 +01:00
|
|
|
/* We do not need to know the position of the end of the group, that is,
|
2017-05-17 19:55:11 +02:00
|
|
|
gptr is not used after the call to get_grouplength(). Setting the second
|
|
|
|
argument FALSE stops it scanning for the end when the length can be found
|
|
|
|
in the cache. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
gptr++;
|
2017-03-16 18:17:47 +01:00
|
|
|
grouplength = get_grouplength(&gptr, FALSE, errcodeptr, lcptr, group,
|
2016-10-02 18:01:01 +02:00
|
|
|
&this_recurse, cb);
|
|
|
|
if (grouplength < 0)
|
|
|
|
{
|
|
|
|
if (*errcodeptr == 0) goto ISNOTFIXED;
|
|
|
|
return -1; /* Error already set */
|
|
|
|
}
|
|
|
|
itemlength = grouplength;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Check nested groups - advance past the initial data for each type and
|
|
|
|
then seek a fixed length with get_grouplength(). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_COND_NAME:
|
|
|
|
case META_COND_NUMBER:
|
|
|
|
case META_COND_RNAME:
|
|
|
|
case META_COND_RNUMBER:
|
|
|
|
case META_COND_DEFINE:
|
|
|
|
pptr += 2 + SIZEOFFSET;
|
|
|
|
goto CHECK_GROUP;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_COND_ASSERT:
|
2016-11-18 19:59:37 +01:00
|
|
|
pptr += 1;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto CHECK_GROUP;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_COND_VERSION:
|
|
|
|
pptr += 4;
|
|
|
|
goto CHECK_GROUP;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CAPTURE:
|
|
|
|
group = META_DATA(*pptr);
|
|
|
|
/* Fall through */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ATOMIC:
|
|
|
|
case META_NOCAPTURE:
|
|
|
|
pptr++;
|
|
|
|
CHECK_GROUP:
|
2017-05-17 19:55:11 +02:00
|
|
|
grouplength = get_grouplength(&pptr, TRUE, errcodeptr, lcptr, group,
|
2017-03-16 18:17:47 +01:00
|
|
|
recurses, cb);
|
2016-10-02 18:01:01 +02:00
|
|
|
if (grouplength < 0) return -1;
|
|
|
|
itemlength = grouplength;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Exact repetition is OK; variable repetition is not. A repetition of zero
|
|
|
|
must subtract the length that has already been added. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_MINMAX:
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
if (pptr[1] == pptr[2])
|
|
|
|
{
|
|
|
|
if (pptr[1] == 0) branchlength -= lastitemlength;
|
|
|
|
else itemlength = (pptr[1] - 1) * lastitemlength;
|
|
|
|
pptr += 2;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* Fall through */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Any other item means this branch does not have a fixed length. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
ISNOTFIXED:
|
|
|
|
*errcodeptr = ERR25; /* Not fixed length */
|
|
|
|
return -1;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Add the item length to the branchlength, and save it for use if the next
|
|
|
|
thing is a quantifier. */
|
|
|
|
|
|
|
|
branchlength += itemlength;
|
|
|
|
lastitemlength = itemlength;
|
|
|
|
|
|
|
|
/* Ensure that the length does not overflow the limit. */
|
|
|
|
|
|
|
|
if (branchlength > LOOKBEHIND_MAX)
|
|
|
|
{
|
|
|
|
*errcodeptr = ERR87;
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
EXIT:
|
|
|
|
*pptrptr = pptr;
|
|
|
|
if (branchlength > cb->max_lookbehind) cb->max_lookbehind = branchlength;
|
|
|
|
return branchlength;
|
2016-11-23 18:17:57 +01:00
|
|
|
|
|
|
|
PARSED_SKIP_FAILED:
|
|
|
|
*errcodeptr = ERR90;
|
|
|
|
return -1;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Set lengths in a lookbehind *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called for each lookbehind, to set the lengths in its
|
|
|
|
branches. An error occurs if any branch does not have a fixed length that is
|
|
|
|
less than the maximum (65535). On exit, the pointer must be left on the final
|
|
|
|
ket.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
Arguments:
|
2016-10-02 18:01:01 +02:00
|
|
|
pptrptr pointer to pointer in the parsed pattern
|
|
|
|
errcodeptr pointer to error code
|
|
|
|
lcptr pointer to loop counter
|
|
|
|
recurses chain of recurse_check to catch mutual recursion
|
|
|
|
cb pointer to compile block
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Returns: TRUE if all is well
|
|
|
|
FALSE otherwise, with error code and offset set
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static BOOL
|
|
|
|
set_lookbehind_lengths(uint32_t **pptrptr, int *errcodeptr, int *lcptr,
|
|
|
|
parsed_recurse_check *recurses, compile_block *cb)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_SIZE offset;
|
|
|
|
int branchlength;
|
|
|
|
uint32_t *bptr = *pptrptr;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
READPLUSOFFSET(offset, bptr); /* Offset for error messages */
|
|
|
|
*pptrptr += SIZEOFFSET;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
do
|
|
|
|
{
|
|
|
|
*pptrptr += 1;
|
|
|
|
branchlength = get_branchlength(pptrptr, errcodeptr, lcptr, recurses, cb);
|
|
|
|
if (branchlength < 0)
|
|
|
|
{
|
|
|
|
/* The errorcode and offset may already be set from a nested lookbehind. */
|
|
|
|
if (*errcodeptr == 0) *errcodeptr = ERR25;
|
|
|
|
if (cb->erroroffset == PCRE2_UNSET) cb->erroroffset = offset;
|
|
|
|
return FALSE;
|
|
|
|
}
|
|
|
|
*bptr |= branchlength; /* branchlength never more than 65535 */
|
|
|
|
bptr = *pptrptr;
|
|
|
|
}
|
|
|
|
while (*bptr == META_ALT);
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
return TRUE;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2016-10-02 18:01:01 +02:00
|
|
|
* Check parsed pattern lookbehinds *
|
2014-06-14 20:29:51 +02:00
|
|
|
*************************************************/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* This function is called at the end of parsing a pattern if any lookbehinds
|
|
|
|
were encountered. It scans the parsed pattern for them, calling
|
|
|
|
set_lookbehind_lengths() for each one. At the start, the errorcode is zero and
|
|
|
|
the error offset is marked unset. The enables the functions above not to
|
|
|
|
override settings from deeper nestings.
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
Arguments cb points to the compile block
|
|
|
|
Returns: 0 on success, or an errorcode (cb->erroroffset will be set)
|
2014-06-14 20:29:51 +02:00
|
|
|
*/
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
static int
|
|
|
|
check_lookbehinds(compile_block *cb)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t *pptr;
|
|
|
|
int errorcode = 0;
|
|
|
|
int loopcount = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb->erroroffset = PCRE2_UNSET;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
for (pptr = cb->parsed_pattern; *pptr != META_END; pptr++)
|
|
|
|
{
|
|
|
|
if (*pptr < META_END) continue; /* Literal */
|
2016-12-28 13:26:12 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
switch (META_CODE(*pptr))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
default:
|
|
|
|
return ERR70; /* Unrecognized meta code */
|
|
|
|
|
|
|
|
case META_ESCAPE:
|
|
|
|
if (*pptr - META_ESCAPE == ESC_P || *pptr - META_ESCAPE == ESC_p)
|
|
|
|
pptr += 1;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_ACCEPT:
|
|
|
|
case META_ALT:
|
|
|
|
case META_ASTERISK:
|
|
|
|
case META_ASTERISK_PLUS:
|
|
|
|
case META_ASTERISK_QUERY:
|
|
|
|
case META_ATOMIC:
|
|
|
|
case META_BACKREF:
|
|
|
|
case META_CAPTURE:
|
|
|
|
case META_CIRCUMFLEX:
|
|
|
|
case META_CLASS:
|
|
|
|
case META_CLASS_EMPTY:
|
|
|
|
case META_CLASS_EMPTY_NOT:
|
|
|
|
case META_CLASS_END:
|
|
|
|
case META_CLASS_NOT:
|
|
|
|
case META_COMMIT:
|
2016-11-18 19:59:37 +01:00
|
|
|
case META_COND_ASSERT:
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_DOLLAR:
|
|
|
|
case META_DOT:
|
|
|
|
case META_FAIL:
|
|
|
|
case META_KET:
|
|
|
|
case META_LOOKAHEAD:
|
|
|
|
case META_LOOKAHEADNOT:
|
|
|
|
case META_NOCAPTURE:
|
|
|
|
case META_PLUS:
|
|
|
|
case META_PLUS_PLUS:
|
|
|
|
case META_PLUS_QUERY:
|
|
|
|
case META_PRUNE:
|
|
|
|
case META_QUERY:
|
|
|
|
case META_QUERY_PLUS:
|
|
|
|
case META_QUERY_QUERY:
|
|
|
|
case META_RANGE_ESCAPED:
|
|
|
|
case META_RANGE_LITERAL:
|
|
|
|
case META_SKIP:
|
|
|
|
case META_THEN:
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_RECURSE:
|
|
|
|
pptr += SIZEOFFSET;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BACKREF_BYNAME:
|
|
|
|
case META_COND_DEFINE:
|
|
|
|
case META_COND_NAME:
|
|
|
|
case META_COND_NUMBER:
|
|
|
|
case META_COND_RNAME:
|
|
|
|
case META_COND_RNUMBER:
|
|
|
|
case META_RECURSE_BYNAME:
|
|
|
|
pptr += 1 + SIZEOFFSET;
|
|
|
|
break;
|
2015-01-23 17:51:47 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_CALLOUT_STRING:
|
|
|
|
pptr += 3 + SIZEOFFSET;
|
|
|
|
break;
|
2015-01-23 17:51:47 +01:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_BIGVALUE:
|
|
|
|
case META_OPTIONS:
|
|
|
|
case META_POSIX:
|
|
|
|
case META_POSIX_NEG:
|
|
|
|
pptr += 1;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MINMAX:
|
|
|
|
case META_MINMAX_QUERY:
|
|
|
|
case META_MINMAX_PLUS:
|
|
|
|
pptr += 2;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_CALLOUT_NUMBER:
|
|
|
|
case META_COND_VERSION:
|
|
|
|
pptr += 3;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_MARK:
|
2018-07-28 18:23:24 +02:00
|
|
|
case META_COMMIT_ARG:
|
2016-10-02 18:01:01 +02:00
|
|
|
case META_PRUNE_ARG:
|
|
|
|
case META_SKIP_ARG:
|
|
|
|
case META_THEN_ARG:
|
|
|
|
pptr += 1 + pptr[1];
|
|
|
|
break;
|
|
|
|
|
|
|
|
case META_LOOKBEHIND:
|
|
|
|
case META_LOOKBEHINDNOT:
|
|
|
|
if (!set_lookbehind_lengths(&pptr, &errorcode, &loopcount, NULL, cb))
|
|
|
|
return errorcode;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2014-03-07 18:28:52 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*************************************************
|
2014-06-14 20:29:51 +02:00
|
|
|
* External function to compile a pattern *
|
2014-03-07 18:28:52 +01:00
|
|
|
*************************************************/
|
|
|
|
|
|
|
|
/* This function reads a regular expression in the form of a string and returns
|
|
|
|
a pointer to a block of store holding a compiled version of the expression.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
pattern the regular expression
|
2015-11-09 18:09:00 +01:00
|
|
|
patlen the length of the pattern, or PCRE2_ZERO_TERMINATED
|
2014-03-07 18:28:52 +01:00
|
|
|
options option bits
|
2014-06-14 20:29:51 +02:00
|
|
|
errorptr pointer to errorcode
|
2014-08-08 17:36:18 +02:00
|
|
|
erroroffset pointer to error offset
|
2014-04-18 17:37:56 +02:00
|
|
|
ccontext points to a compile context or is NULL
|
2014-03-07 18:28:52 +01:00
|
|
|
|
|
|
|
Returns: pointer to compiled data block, or NULL on error,
|
|
|
|
with errorcode and erroroffset set
|
|
|
|
*/
|
|
|
|
|
|
|
|
PCRE2_EXP_DEFN pcre2_code * PCRE2_CALL_CONVENTION
|
2014-08-16 11:46:58 +02:00
|
|
|
pcre2_compile(PCRE2_SPTR pattern, PCRE2_SIZE patlen, uint32_t options,
|
|
|
|
int *errorptr, PCRE2_SIZE *erroroffset, pcre2_compile_context *ccontext)
|
2014-03-07 18:28:52 +01:00
|
|
|
{
|
2016-11-01 18:45:54 +01:00
|
|
|
BOOL utf; /* Set TRUE for UTF mode */
|
2017-06-15 18:41:44 +02:00
|
|
|
BOOL has_lookbehind = FALSE; /* Set TRUE if a lookbehind is found */
|
2016-11-01 18:45:54 +01:00
|
|
|
BOOL zero_terminated; /* Set TRUE for zero-terminated pattern */
|
|
|
|
pcre2_real_code *re = NULL; /* What we will return */
|
|
|
|
compile_block cb; /* "Static" compile-time data */
|
|
|
|
const uint8_t *tables; /* Char tables base pointer */
|
|
|
|
|
|
|
|
PCRE2_UCHAR *code; /* Current pointer in compiled code */
|
|
|
|
PCRE2_SPTR codestart; /* Start of compiled code */
|
|
|
|
PCRE2_SPTR ptr; /* Current pointer in pattern */
|
|
|
|
uint32_t *pptr; /* Current pointer in parsed pattern */
|
|
|
|
|
|
|
|
PCRE2_SIZE length = 1; /* Allow for final END opcode */
|
|
|
|
PCRE2_SIZE usedlength; /* Actual length used */
|
|
|
|
PCRE2_SIZE re_blocksize; /* Size of memory block */
|
|
|
|
PCRE2_SIZE big32count = 0; /* 32-bit literals >= 0x80000000 */
|
|
|
|
PCRE2_SIZE parsed_size_needed; /* Needed for parsed pattern */
|
|
|
|
|
|
|
|
int32_t firstcuflags, reqcuflags; /* Type of first/req code unit */
|
|
|
|
uint32_t firstcu, reqcu; /* Value of first/req code unit */
|
|
|
|
uint32_t setflags = 0; /* NL and BSR set flags */
|
|
|
|
|
|
|
|
uint32_t skipatstart; /* When checking (*UTF) etc */
|
2017-04-11 13:47:25 +02:00
|
|
|
uint32_t limit_heap = UINT32_MAX;
|
2016-11-01 18:45:54 +01:00
|
|
|
uint32_t limit_match = UINT32_MAX; /* Unset match limits */
|
2017-03-12 14:47:01 +01:00
|
|
|
uint32_t limit_depth = UINT32_MAX;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-01 18:45:54 +01:00
|
|
|
int newline = 0; /* Unset; can be set by the pattern */
|
|
|
|
int bsr = 0; /* Unset; can be set by the pattern */
|
|
|
|
int errorcode = 0; /* Initialize to avoid compiler warn */
|
2016-12-23 18:09:37 +01:00
|
|
|
int regexrc; /* Return from compile */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-01 18:45:54 +01:00
|
|
|
uint32_t i; /* Local loop counter */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Comments at the head of this file explain about these variables. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t stack_groupinfo[GROUPINFO_DEFAULT_SIZE];
|
|
|
|
uint32_t stack_parsed_pattern[PARSED_PATTERN_DEFAULT_SIZE];
|
2014-06-14 20:29:51 +02:00
|
|
|
named_group named_groups[NAMED_GROUP_LIST_SIZE];
|
|
|
|
|
2015-06-03 18:27:47 +02:00
|
|
|
/* The workspace is used in different ways in the different compiling phases.
|
2016-10-02 18:01:01 +02:00
|
|
|
It needs to be 16-bit aligned for the preliminary parsing scan. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
uint32_t c16workspace[C16_WORK_SIZE];
|
|
|
|
PCRE2_UCHAR *cworkspace = (PCRE2_UCHAR *)c16workspace;
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* -------------- Check arguments and set up the pattern ----------------- */
|
|
|
|
|
|
|
|
/* There must be error code and offset pointers. */
|
|
|
|
|
|
|
|
if (errorptr == NULL || erroroffset == NULL) return NULL;
|
|
|
|
*errorptr = ERR0;
|
|
|
|
*erroroffset = 0;
|
|
|
|
|
|
|
|
/* There must be a pattern! */
|
|
|
|
|
|
|
|
if (pattern == NULL)
|
|
|
|
{
|
|
|
|
*errorptr = ERR16;
|
|
|
|
return NULL;
|
|
|
|
}
|
2016-10-27 19:42:14 +02:00
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
/* A NULL compile context means "use a default context" */
|
|
|
|
|
|
|
|
if (ccontext == NULL)
|
|
|
|
ccontext = (pcre2_compile_context *)(&PRIV(default_compile_context));
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Check that all undefined public option bits are zero. */
|
2014-04-18 17:37:56 +02:00
|
|
|
|
2017-06-16 19:51:13 +02:00
|
|
|
if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0 ||
|
|
|
|
(ccontext->extra_options & ~PUBLIC_COMPILE_EXTRA_OPTIONS) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
*errorptr = ERR17;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
if ((options & PCRE2_LITERAL) != 0 &&
|
2017-06-16 19:51:13 +02:00
|
|
|
((options & ~PUBLIC_LITERAL_COMPILE_OPTIONS) != 0 ||
|
|
|
|
(ccontext->extra_options & ~PUBLIC_LITERAL_COMPILE_EXTRA_OPTIONS) != 0))
|
2017-06-15 18:41:44 +02:00
|
|
|
{
|
|
|
|
*errorptr = ERR92;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2014-10-20 19:28:49 +02:00
|
|
|
/* A zero-terminated pattern is indicated by the special length value
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_ZERO_TERMINATED. Check for an overlong pattern. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-11-01 18:45:54 +01:00
|
|
|
if ((zero_terminated = (patlen == PCRE2_ZERO_TERMINATED)))
|
|
|
|
patlen = PRIV(strlen)(pattern);
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (patlen > ccontext->max_pattern_length)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
*errorptr = ERR88;
|
|
|
|
return NULL;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-11-01 18:45:54 +01:00
|
|
|
/* From here on, all returns from this function should end up going via the
|
|
|
|
EXIT label. */
|
|
|
|
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* ------------ Initialize the "static" compile data -------------- */
|
|
|
|
|
|
|
|
tables = (ccontext->tables != NULL)? ccontext->tables : PRIV(default_tables);
|
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.lcc = tables + lcc_offset; /* Individual */
|
|
|
|
cb.fcc = tables + fcc_offset; /* character */
|
|
|
|
cb.cbits = tables + cbits_offset; /* tables */
|
|
|
|
cb.ctypes = tables + ctypes_offset;
|
|
|
|
|
|
|
|
cb.assert_depth = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.bracount = 0;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.cx = ccontext;
|
|
|
|
cb.dupnames = FALSE;
|
|
|
|
cb.end_pattern = pattern + patlen;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.erroroffset = 0;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.external_flags = 0;
|
|
|
|
cb.external_options = options;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.groupinfo = stack_groupinfo;
|
2015-08-09 18:29:35 +02:00
|
|
|
cb.had_recurse = FALSE;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.lastcapture = 0;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.max_lookbehind = 0;
|
|
|
|
cb.name_entry_size = 0;
|
|
|
|
cb.name_table = NULL;
|
|
|
|
cb.named_groups = named_groups;
|
|
|
|
cb.named_group_list_size = NAMED_GROUP_LIST_SIZE;
|
|
|
|
cb.names_found = 0;
|
|
|
|
cb.open_caps = NULL;
|
|
|
|
cb.parens_depth = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.parsed_pattern = stack_parsed_pattern;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.req_varyopt = 0;
|
|
|
|
cb.start_code = cworkspace;
|
|
|
|
cb.start_pattern = pattern;
|
|
|
|
cb.start_workspace = cworkspace;
|
|
|
|
cb.workspace_size = COMPILE_WORK_SIZE;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Maximum back reference and backref bitmap. The bitmap records up to 31 back
|
|
|
|
references to help in deciding whether (.*) can be treated as anchored or not.
|
|
|
|
*/
|
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.top_backref = 0;
|
|
|
|
cb.backref_map = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Escape sequences \1 to \9 are always back references, but as they are only
|
|
|
|
two characters long, only two elements can be used in the parsed_pattern
|
|
|
|
vector. The first contains the reference, and we'd like to use the second to
|
|
|
|
record the offset in the pattern, so that forward references to non-existent
|
|
|
|
groups can be diagnosed later with an offset. However, on 64-bit systems,
|
|
|
|
PCRE2_SIZE won't fit. Instead, we have a vector of offsets for the first
|
|
|
|
occurrence of \1 to \9, indexed by the second parsed_pattern value. All other
|
|
|
|
references have enough space for the offset to be put into the parsed pattern.
|
|
|
|
*/
|
|
|
|
|
|
|
|
for (i = 0; i < 10; i++) cb.small_ref_offset[i] = PCRE2_UNSET;
|
|
|
|
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* --------------- Start looking at the pattern --------------- */
|
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
/* Unless PCRE2_LITERAL is set, check for global one-time option settings at
|
|
|
|
the start of the pattern, and remember the offset to the actual regex. With
|
|
|
|
valgrind support, make the terminator of a zero-terminated pattern
|
|
|
|
inaccessible. This catches bugs that would otherwise only show up for
|
|
|
|
non-zero-terminated patterns. */
|
2016-11-01 18:45:54 +01:00
|
|
|
|
|
|
|
#ifdef SUPPORT_VALGRIND
|
|
|
|
if (zero_terminated) VALGRIND_MAKE_MEM_NOACCESS(pattern + patlen, CU2BYTES(1));
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
ptr = pattern;
|
|
|
|
skipatstart = 0;
|
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
if ((options & PCRE2_LITERAL) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-06-15 18:41:44 +02:00
|
|
|
while (patlen - skipatstart >= 2 &&
|
|
|
|
ptr[skipatstart] == CHAR_LEFT_PARENTHESIS &&
|
|
|
|
ptr[skipatstart+1] == CHAR_ASTERISK)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-06-15 18:41:44 +02:00
|
|
|
for (i = 0; i < sizeof(pso_list)/sizeof(pso); i++)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
uint32_t c, pp;
|
2017-06-15 18:41:44 +02:00
|
|
|
pso *p = pso_list + i;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
if (patlen - skipatstart - 2 >= p->length &&
|
|
|
|
PRIV(strncmp_c8)(ptr + skipatstart + 2, (char *)(p->name),
|
|
|
|
p->length) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-06-15 18:41:44 +02:00
|
|
|
skipatstart += p->length + 2;
|
|
|
|
switch(p->type)
|
|
|
|
{
|
|
|
|
case PSO_OPT:
|
|
|
|
cb.external_options |= p->value;
|
|
|
|
break;
|
2014-10-20 19:28:49 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
case PSO_FLG:
|
|
|
|
setflags |= p->value;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
case PSO_NL:
|
|
|
|
newline = p->value;
|
|
|
|
setflags |= PCRE2_NL_SET;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
case PSO_BSR:
|
|
|
|
bsr = p->value;
|
|
|
|
setflags |= PCRE2_BSR_SET;
|
|
|
|
break;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-15 18:41:44 +02:00
|
|
|
case PSO_LIMM:
|
|
|
|
case PSO_LIMD:
|
|
|
|
case PSO_LIMH:
|
|
|
|
c = 0;
|
|
|
|
pp = skipatstart;
|
|
|
|
if (!IS_DIGIT(ptr[pp]))
|
|
|
|
{
|
|
|
|
errorcode = ERR60;
|
|
|
|
ptr += pp;
|
|
|
|
goto HAD_EARLY_ERROR;
|
|
|
|
}
|
|
|
|
while (IS_DIGIT(ptr[pp]))
|
|
|
|
{
|
|
|
|
if (c > UINT32_MAX / 10 - 1) break; /* Integer overflow */
|
|
|
|
c = c*10 + (ptr[pp++] - CHAR_0);
|
|
|
|
}
|
|
|
|
if (ptr[pp++] != CHAR_RIGHT_PARENTHESIS)
|
|
|
|
{
|
|
|
|
errorcode = ERR60;
|
|
|
|
ptr += pp;
|
|
|
|
goto HAD_EARLY_ERROR;
|
|
|
|
}
|
|
|
|
if (p->type == PSO_LIMH) limit_heap = c;
|
|
|
|
else if (p->type == PSO_LIMM) limit_match = c;
|
|
|
|
else limit_depth = c;
|
|
|
|
skipatstart += pp - skipatstart;
|
|
|
|
break;
|
2014-08-08 17:36:18 +02:00
|
|
|
}
|
2017-06-15 18:41:44 +02:00
|
|
|
break; /* Out of the table scan loop */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2017-06-15 18:41:44 +02:00
|
|
|
if (i >= sizeof(pso_list)/sizeof(pso)) break; /* Out of pso loop */
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* End of pattern-start options; advance to start of real regex. */
|
|
|
|
|
|
|
|
ptr += skipatstart;
|
|
|
|
|
|
|
|
/* Can't support UTF or UCP unless PCRE2 has been compiled with UTF support. */
|
|
|
|
|
2014-09-19 09:43:39 +02:00
|
|
|
#ifndef SUPPORT_UNICODE
|
2014-08-10 18:09:24 +02:00
|
|
|
if ((cb.external_options & (PCRE2_UTF|PCRE2_UCP)) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
errorcode = ERR32;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_EARLY_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Check UTF. We have the original options in 'options', with that value as
|
2017-05-17 19:55:11 +02:00
|
|
|
modified by (*UTF) etc in cb->external_options. The extra option
|
|
|
|
PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is not permitted in UTF-16 mode because the
|
|
|
|
surrogate code points cannot be represented in UTF-16. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
utf = (cb.external_options & PCRE2_UTF) != 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
if (utf)
|
|
|
|
{
|
|
|
|
if ((options & PCRE2_NEVER_UTF) != 0)
|
|
|
|
{
|
2014-06-21 14:39:48 +02:00
|
|
|
errorcode = ERR74;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_EARLY_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
if ((options & PCRE2_NO_UTF_CHECK) == 0 &&
|
2014-08-16 11:46:58 +02:00
|
|
|
(errorcode = PRIV(valid_utf)(pattern, patlen, erroroffset)) != 0)
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_ERROR; /* Offset was set by valid_utf() */
|
2017-05-17 19:55:11 +02:00
|
|
|
|
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 16
|
|
|
|
if ((ccontext->extra_options & PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES) != 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR91;
|
|
|
|
goto HAD_EARLY_ERROR;
|
|
|
|
}
|
|
|
|
#endif
|
2014-08-08 17:36:18 +02:00
|
|
|
}
|
|
|
|
|
2014-07-24 18:32:38 +02:00
|
|
|
/* Check UCP lockout. */
|
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
if ((cb.external_options & (PCRE2_UCP|PCRE2_NEVER_UCP)) ==
|
2014-07-24 18:32:38 +02:00
|
|
|
(PCRE2_UCP|PCRE2_NEVER_UCP))
|
|
|
|
{
|
|
|
|
errorcode = ERR75;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_EARLY_ERROR;
|
2014-08-08 17:36:18 +02:00
|
|
|
}
|
2014-04-18 17:37:56 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Process the BSR setting. */
|
2014-03-07 18:28:52 +01:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
if (bsr == 0) bsr = ccontext->bsr_convention;
|
|
|
|
|
|
|
|
/* Process the newline setting. */
|
2014-04-18 17:37:56 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
if (newline == 0) newline = ccontext->newline_convention;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nltype = NLTYPE_FIXED;
|
2014-06-14 20:29:51 +02:00
|
|
|
switch(newline)
|
|
|
|
{
|
|
|
|
case PCRE2_NEWLINE_CR:
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nllen = 1;
|
|
|
|
cb.nl[0] = CHAR_CR;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case PCRE2_NEWLINE_LF:
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nllen = 1;
|
|
|
|
cb.nl[0] = CHAR_NL;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
2017-05-26 19:14:36 +02:00
|
|
|
case PCRE2_NEWLINE_NUL:
|
|
|
|
cb.nllen = 1;
|
|
|
|
cb.nl[0] = CHAR_NUL;
|
|
|
|
break;
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
case PCRE2_NEWLINE_CRLF:
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nllen = 2;
|
|
|
|
cb.nl[0] = CHAR_CR;
|
|
|
|
cb.nl[1] = CHAR_NL;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case PCRE2_NEWLINE_ANY:
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nltype = NLTYPE_ANY;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
case PCRE2_NEWLINE_ANYCRLF:
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.nltype = NLTYPE_ANYCRLF;
|
2014-06-14 20:29:51 +02:00
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
errorcode = ERR56;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_EARLY_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Pre-scan the pattern to do two things: (1) Discover the named groups and
|
|
|
|
their numerical equivalents, so that this information is always available for
|
|
|
|
the remaining processing. (2) At the same time, parse the pattern and put a
|
|
|
|
processed version into the parsed_pattern vector. This has escapes interpreted
|
|
|
|
and comments removed (amongst other things).
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
In all but one case, when PCRE2_AUTO_CALLOUT is not set, the number of unsigned
|
|
|
|
32-bit ints in the parsed pattern is bounded by the length of the pattern plus
|
2017-06-16 19:51:13 +02:00
|
|
|
one (for the terminator) plus four if PCRE2_EXTRA_WORD or PCRE2_EXTRA_LINE is
|
|
|
|
set. The exceptional case is when running in 32-bit, non-UTF mode, when literal
|
|
|
|
characters greater than META_END (0x80000000) have to be coded as two units. In
|
|
|
|
this case, therefore, we scan the pattern to check for such values. */
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#if PCRE2_CODE_UNIT_WIDTH == 32
|
|
|
|
if (!utf)
|
|
|
|
{
|
|
|
|
PCRE2_SPTR p;
|
|
|
|
for (p = ptr; p < cb.end_pattern; p++) if (*p >= META_END) big32count++;
|
|
|
|
}
|
|
|
|
#endif
|
2015-06-03 18:27:47 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Ensure that the parsed pattern buffer is big enough. When PCRE2_AUTO_CALLOUT
|
|
|
|
is set we have to assume a numerical callout (4 elements) for each character
|
|
|
|
plus one at the end. This is overkill, but memory is plentiful these days. For
|
|
|
|
many smaller patterns the vector on the stack (which was set up above) can be
|
|
|
|
used. */
|
|
|
|
|
|
|
|
parsed_size_needed = patlen - skipatstart + big32count;
|
2017-06-16 19:51:13 +02:00
|
|
|
|
|
|
|
if ((ccontext->extra_options &
|
|
|
|
(PCRE2_EXTRA_MATCH_WORD|PCRE2_EXTRA_MATCH_LINE)) != 0)
|
|
|
|
parsed_size_needed += 4;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if ((options & PCRE2_AUTO_CALLOUT) != 0)
|
2016-11-04 17:35:47 +01:00
|
|
|
parsed_size_needed = (parsed_size_needed + 1) * 5;
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
if (parsed_size_needed >= PARSED_PATTERN_DEFAULT_SIZE)
|
|
|
|
{
|
2016-11-01 18:45:54 +01:00
|
|
|
uint32_t *heap_parsed_pattern = ccontext->memctl.malloc(
|
|
|
|
(parsed_size_needed + 1) * sizeof(uint32_t), ccontext->memctl.memory_data);
|
|
|
|
if (heap_parsed_pattern == NULL)
|
2016-10-02 18:01:01 +02:00
|
|
|
{
|
|
|
|
*errorptr = ERR21;
|
2016-11-01 18:45:54 +01:00
|
|
|
goto EXIT;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2016-11-01 18:45:54 +01:00
|
|
|
cb.parsed_pattern = heap_parsed_pattern;
|
2016-10-02 18:01:01 +02:00
|
|
|
}
|
2016-11-18 19:59:37 +01:00
|
|
|
cb.parsed_pattern_end = cb.parsed_pattern + parsed_size_needed + 1;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Do the parsing scan. */
|
|
|
|
|
|
|
|
errorcode = parse_regex(ptr, cb.external_options, &has_lookbehind, &cb);
|
|
|
|
if (errorcode != 0) goto HAD_CB_ERROR;
|
|
|
|
|
|
|
|
/* Workspace is needed to remember information about numbered groups: whether a
|
|
|
|
group can match an empty string and what its fixed length is. This is done to
|
|
|
|
avoid the possibility of recursive references causing very long compile times
|
|
|
|
when checking these features. Unnumbered groups do not have this exposure since
|
|
|
|
they cannot be referenced. We use an indexed vector for this purpose. If there
|
|
|
|
are sufficiently few groups, the default vector on the stack, as set up above,
|
|
|
|
can be used. Otherwise we have to get/free a special vector. The vector must be
|
|
|
|
initialized to zero. */
|
|
|
|
|
|
|
|
if (cb.bracount >= GROUPINFO_DEFAULT_SIZE)
|
|
|
|
{
|
|
|
|
cb.groupinfo = ccontext->memctl.malloc(
|
|
|
|
(cb.bracount + 1)*sizeof(uint32_t), ccontext->memctl.memory_data);
|
|
|
|
if (cb.groupinfo == NULL)
|
|
|
|
{
|
|
|
|
errorcode = ERR21;
|
|
|
|
cb.erroroffset = 0;
|
|
|
|
goto HAD_CB_ERROR;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
memset(cb.groupinfo, 0, (cb.bracount + 1) * sizeof(uint32_t));
|
|
|
|
|
|
|
|
/* If there were any lookbehinds, scan the parsed pattern to figure out their
|
|
|
|
lengths. */
|
|
|
|
|
|
|
|
if (has_lookbehind)
|
|
|
|
{
|
|
|
|
errorcode = check_lookbehinds(&cb);
|
|
|
|
if (errorcode != 0) goto HAD_CB_ERROR;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* For debugging, there is a function that shows the parsed data vector. */
|
|
|
|
|
|
|
|
#ifdef DEBUG_SHOW_PARSED
|
|
|
|
fprintf(stderr, "+++ Pre-scan complete:\n");
|
|
|
|
show_parsed(&cb);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* For debugging capturing information this code can be enabled. */
|
|
|
|
|
|
|
|
#ifdef DEBUG_SHOW_CAPTURES
|
2015-06-03 18:27:47 +02:00
|
|
|
{
|
|
|
|
named_group *ng = cb.named_groups;
|
2016-10-02 18:01:01 +02:00
|
|
|
fprintf(stderr, "+++Captures: %d\n", cb.bracount);
|
2015-06-03 18:27:47 +02:00
|
|
|
for (i = 0; i < cb.names_found; i++, ng++)
|
|
|
|
{
|
|
|
|
fprintf(stderr, "+++%3d %.*s\n", ng->number, ng->length, ng->name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Pretend to compile the pattern while actually just accumulating the amount
|
|
|
|
of memory required in the 'length' variable. This behaviour is triggered by
|
|
|
|
passing a non-NULL final argument to compile_regex(). We pass a block of
|
|
|
|
workspace (cworkspace) for it to compile parts of the pattern into; the
|
|
|
|
compiled code is discarded when it is no longer needed, so hopefully this
|
|
|
|
workspace will never overflow, though there is a test for its doing so.
|
|
|
|
|
|
|
|
On error, errorcode will be set non-zero, so we don't need to look at the
|
2016-10-02 18:01:01 +02:00
|
|
|
result of the function. The initial options have been put into the cb block,
|
|
|
|
but we still have to pass a separate options variable (the first argument)
|
|
|
|
because the options may change as the pattern is processed. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.erroroffset = patlen; /* For any subsequent errors that do not set it */
|
|
|
|
pptr = cb.parsed_pattern;
|
2014-06-14 20:29:51 +02:00
|
|
|
code = cworkspace;
|
|
|
|
*code = OP_BRA;
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
(void)compile_regex(cb.external_options, &code, &pptr, &errorcode, 0, &firstcu,
|
|
|
|
&firstcuflags, &reqcu, &reqcuflags, NULL, &cb, &length);
|
|
|
|
|
|
|
|
if (errorcode != 0) goto HAD_CB_ERROR; /* Offset is in cb.erroroffset */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-01-03 12:35:26 +01:00
|
|
|
/* This should be caught in compile_regex(), but just in case... */
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
if (length > MAX_PATTERN_SIZE)
|
|
|
|
{
|
|
|
|
errorcode = ERR20;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_CB_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Compute the size of, and then get and initialize, the data block for storing
|
|
|
|
the compiled pattern and names table. Integer overflow should no longer be
|
2014-06-28 16:23:18 +02:00
|
|
|
possible because nowadays we limit the maximum value of cb.names_found and
|
|
|
|
cb.name_entry_size. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
re_blocksize = sizeof(pcre2_real_code) +
|
2017-05-17 19:55:11 +02:00
|
|
|
CU2BYTES(length +
|
2017-04-16 18:49:11 +02:00
|
|
|
(PCRE2_SIZE)cb.names_found * (PCRE2_SIZE)cb.name_entry_size);
|
2014-06-14 20:29:51 +02:00
|
|
|
re = (pcre2_real_code *)
|
|
|
|
ccontext->memctl.malloc(re_blocksize, ccontext->memctl.memory_data);
|
|
|
|
if (re == NULL)
|
|
|
|
{
|
|
|
|
errorcode = ERR21;
|
2016-10-02 18:01:01 +02:00
|
|
|
goto HAD_CB_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2017-05-17 19:55:11 +02:00
|
|
|
|
|
|
|
/* The compiler may put padding at the end of the pcre2_real_code structure in
|
|
|
|
order to round it up to a multiple of 4 or 8 bytes. This means that when a
|
|
|
|
compiled pattern is copied (for example, when serialized) undefined bytes are
|
|
|
|
read, and this annoys debuggers such as valgrind. To avoid this, we explicitly
|
2017-04-12 15:48:11 +02:00
|
|
|
write to the last 8 bytes of the structure before setting the fields. */
|
2015-02-20 12:20:40 +01:00
|
|
|
|
2017-04-12 15:48:11 +02:00
|
|
|
memset((char *)re + sizeof(pcre2_real_code) - 8, 0, 8);
|
2014-06-14 20:29:51 +02:00
|
|
|
re->memctl = ccontext->memctl;
|
|
|
|
re->tables = tables;
|
|
|
|
re->executable_jit = NULL;
|
2014-06-21 14:39:48 +02:00
|
|
|
memset(re->start_bitmap, 0, 32 * sizeof(uint8_t));
|
2014-06-14 20:29:51 +02:00
|
|
|
re->blocksize = re_blocksize;
|
|
|
|
re->magic_number = MAGIC_NUMBER;
|
|
|
|
re->compile_options = options;
|
2014-06-28 16:23:18 +02:00
|
|
|
re->overall_options = cb.external_options;
|
2017-12-16 18:49:26 +01:00
|
|
|
re->extra_options = ccontext->extra_options;
|
2014-08-10 18:09:24 +02:00
|
|
|
re->flags = PCRE2_CODE_UNIT_WIDTH/8 | cb.external_flags | setflags;
|
2017-04-11 13:47:25 +02:00
|
|
|
re->limit_heap = limit_heap;
|
2014-06-14 20:29:51 +02:00
|
|
|
re->limit_match = limit_match;
|
2017-03-12 14:47:01 +01:00
|
|
|
re->limit_depth = limit_depth;
|
2014-06-14 20:29:51 +02:00
|
|
|
re->first_codeunit = 0;
|
|
|
|
re->last_codeunit = 0;
|
|
|
|
re->bsr_convention = bsr;
|
|
|
|
re->newline_convention = newline;
|
2015-11-01 18:31:48 +01:00
|
|
|
re->max_lookbehind = 0;
|
2014-06-14 20:29:51 +02:00
|
|
|
re->minlength = 0;
|
|
|
|
re->top_bracket = 0;
|
|
|
|
re->top_backref = 0;
|
2014-06-28 16:23:18 +02:00
|
|
|
re->name_entry_size = cb.name_entry_size;
|
|
|
|
re->name_count = cb.names_found;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
/* The basic block is immediately followed by the name table, and the compiled
|
2014-06-14 20:29:51 +02:00
|
|
|
code follows after that. */
|
|
|
|
|
2014-08-08 17:36:18 +02:00
|
|
|
codestart = (PCRE2_SPTR)((uint8_t *)re + sizeof(pcre2_real_code)) +
|
2014-06-14 20:29:51 +02:00
|
|
|
re->name_entry_size * re->name_count;
|
|
|
|
|
|
|
|
/* Update the compile data block for the actual compile. The starting points of
|
|
|
|
the name/number translation table and of the code are passed around in the
|
|
|
|
compile data block. The start/end pattern and initial options are already set
|
2016-10-02 18:01:01 +02:00
|
|
|
from the pre-compile phase, as is the name_entry_size field. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.parens_depth = 0;
|
|
|
|
cb.assert_depth = 0;
|
2016-10-02 18:01:01 +02:00
|
|
|
cb.lastcapture = 0;
|
2014-06-28 16:23:18 +02:00
|
|
|
cb.name_table = (PCRE2_UCHAR *)((uint8_t *)re + sizeof(pcre2_real_code));
|
|
|
|
cb.start_code = codestart;
|
|
|
|
cb.req_varyopt = 0;
|
|
|
|
cb.had_accept = FALSE;
|
|
|
|
cb.had_pruneorskip = FALSE;
|
|
|
|
cb.open_caps = NULL;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* If any named groups were found, create the name/number table from the list
|
2015-06-03 18:27:47 +02:00
|
|
|
created in the pre-pass. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
if (cb.names_found > 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2014-06-28 16:23:18 +02:00
|
|
|
named_group *ng = cb.named_groups;
|
2016-10-02 18:01:01 +02:00
|
|
|
for (i = 0; i < cb.names_found; i++, ng++)
|
|
|
|
add_name_to_table(&cb, ng->name, ng->length, ng->number, i);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Set up a starting, non-extracting bracket, then compile the expression. On
|
|
|
|
error, errorcode will be set non-zero, so we don't need to look at the result
|
|
|
|
of the function here. */
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
pptr = cb.parsed_pattern;
|
2014-06-14 20:29:51 +02:00
|
|
|
code = (PCRE2_UCHAR *)codestart;
|
|
|
|
*code = OP_BRA;
|
2016-12-23 19:34:10 +01:00
|
|
|
regexrc = compile_regex(re->overall_options, &code, &pptr, &errorcode, 0,
|
2016-12-23 18:09:37 +01:00
|
|
|
&firstcu, &firstcuflags, &reqcu, &reqcuflags, NULL, &cb, NULL);
|
|
|
|
if (regexrc < 0) re->flags |= PCRE2_MATCH_EMPTY;
|
2014-06-28 16:23:18 +02:00
|
|
|
re->top_bracket = cb.bracount;
|
|
|
|
re->top_backref = cb.top_backref;
|
|
|
|
re->max_lookbehind = cb.max_lookbehind;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-06-28 16:23:18 +02:00
|
|
|
if (cb.had_accept)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
|
|
|
reqcu = 0; /* Must disable after (*ACCEPT) */
|
|
|
|
reqcuflags = REQ_NONE;
|
|
|
|
}
|
|
|
|
|
2016-02-02 18:22:55 +01:00
|
|
|
/* Fill in the final opcode and check for disastrous overflow. If no overflow,
|
|
|
|
but the estimated length exceeds the really used length, adjust the value of
|
|
|
|
re->blocksize, and if valgrind support is configured, mark the extra allocated
|
|
|
|
memory as unaddressable, so that any out-of-bound reads can be detected. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
*code++ = OP_END;
|
2015-01-23 17:51:47 +01:00
|
|
|
usedlength = code - codestart;
|
2015-01-27 18:21:32 +01:00
|
|
|
if (usedlength > length) errorcode = ERR23; else
|
|
|
|
{
|
|
|
|
re->blocksize -= CU2BYTES(length - usedlength);
|
2014-06-14 20:29:51 +02:00
|
|
|
#ifdef SUPPORT_VALGRIND
|
2015-01-27 18:21:32 +01:00
|
|
|
VALGRIND_MAKE_MEM_NOACCESS(code, CU2BYTES(length - usedlength));
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2015-01-27 18:21:32 +01:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2015-08-09 18:29:35 +02:00
|
|
|
/* Scan the pattern for recursion/subroutine calls and convert the group
|
|
|
|
numbers into offsets. Maintain a small cache so that repeated groups containing
|
|
|
|
recursions are efficiently handled. */
|
2015-05-06 18:51:25 +02:00
|
|
|
|
2015-08-09 18:29:35 +02:00
|
|
|
#define RSCAN_CACHE_SIZE 8
|
2015-05-06 18:51:25 +02:00
|
|
|
|
2015-08-09 18:29:35 +02:00
|
|
|
if (errorcode == 0 && cb.had_recurse)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2015-08-09 18:29:35 +02:00
|
|
|
PCRE2_UCHAR *rcode;
|
|
|
|
PCRE2_SPTR rgroup;
|
2016-10-02 18:01:01 +02:00
|
|
|
unsigned int ccount = 0;
|
2015-08-09 18:29:35 +02:00
|
|
|
int start = RSCAN_CACHE_SIZE;
|
|
|
|
recurse_cache rc[RSCAN_CACHE_SIZE];
|
|
|
|
|
|
|
|
for (rcode = (PCRE2_UCHAR *)find_recurse(codestart, utf);
|
|
|
|
rcode != NULL;
|
|
|
|
rcode = (PCRE2_UCHAR *)find_recurse(rcode + 1 + LINK_SIZE, utf))
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
int p, groupnumber;
|
2015-08-09 18:29:35 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
groupnumber = (int)GET(rcode, 1);
|
|
|
|
if (groupnumber == 0) rgroup = codestart; else
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2015-08-30 19:47:36 +02:00
|
|
|
PCRE2_SPTR search_from = codestart;
|
2015-08-09 18:29:35 +02:00
|
|
|
rgroup = NULL;
|
|
|
|
for (i = 0, p = start; i < ccount; i++, p = (p + 1) & 7)
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
if (groupnumber == rc[p].groupnumber)
|
2015-08-09 18:29:35 +02:00
|
|
|
{
|
|
|
|
rgroup = rc[p].group;
|
|
|
|
break;
|
|
|
|
}
|
2015-08-30 19:47:36 +02:00
|
|
|
|
|
|
|
/* Group n+1 must always start to the right of group n, so we can save
|
|
|
|
search time below when the new group number is greater than any of the
|
2015-08-09 18:29:35 +02:00
|
|
|
previously found groups. */
|
2015-08-30 19:47:36 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (groupnumber > rc[p].groupnumber) search_from = rc[p].group;
|
2015-08-09 18:29:35 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (rgroup == NULL)
|
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
rgroup = PRIV(find_bracket)(search_from, utf, groupnumber);
|
2015-08-09 18:29:35 +02:00
|
|
|
if (rgroup == NULL)
|
|
|
|
{
|
|
|
|
errorcode = ERR53;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (--start < 0) start = RSCAN_CACHE_SIZE - 1;
|
2016-10-02 18:01:01 +02:00
|
|
|
rc[start].groupnumber = groupnumber;
|
2015-08-09 18:29:35 +02:00
|
|
|
rc[start].group = rgroup;
|
|
|
|
if (ccount < RSCAN_CACHE_SIZE) ccount++;
|
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2015-08-09 18:29:35 +02:00
|
|
|
|
|
|
|
PUT(rcode, 1, rgroup - codestart);
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-08-09 18:29:35 +02:00
|
|
|
/* In rare debugging situations we sometimes need to look at the compiled code
|
|
|
|
at this stage. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
#ifdef DEBUG_CALL_PRINTINT
|
2015-08-09 18:29:35 +02:00
|
|
|
pcre2_printint(re, stderr, TRUE);
|
|
|
|
fprintf(stderr, "Length=%lu Used=%lu\n", length, usedlength);
|
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Unless disabled, check whether any single character iterators can be
|
|
|
|
auto-possessified. The function overwrites the appropriate opcode values, so
|
|
|
|
the type of the pointer must be cast. NOTE: the intermediate variable "temp" is
|
|
|
|
used in this code because at least one compiler gives a warning about loss of
|
|
|
|
"const" attribute if the cast (PCRE2_UCHAR *)codestart is used directly in the
|
|
|
|
function call. */
|
2014-05-13 13:20:03 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (errorcode == 0 && (re->overall_options & PCRE2_NO_AUTO_POSSESS) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2016-10-02 18:01:01 +02:00
|
|
|
PCRE2_UCHAR *temp = (PCRE2_UCHAR *)codestart;
|
|
|
|
if (PRIV(auto_possessify)(temp, utf, &cb) != 0) errorcode = ERR80;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
/* Failed to compile, or error while post-processing. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2016-10-02 18:01:01 +02:00
|
|
|
if (errorcode != 0) goto HAD_CB_ERROR;
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
/* Successful compile. If the anchored option was not passed, set it if
|
|
|
|
we can determine that the pattern is anchored by virtue of ^ characters or \A
|
|
|
|
or anything else, such as starting with non-atomic .* when DOTALL is set and
|
2015-01-02 18:09:16 +01:00
|
|
|
there are no occurrences of *PRUNE or *SKIP (though there is an option to
|
|
|
|
disable this case). */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2014-06-24 17:47:33 +02:00
|
|
|
if ((re->overall_options & PCRE2_ANCHORED) == 0 &&
|
2016-11-01 16:58:28 +01:00
|
|
|
is_anchored(codestart, 0, &cb, 0, FALSE))
|
2014-06-24 17:47:33 +02:00
|
|
|
re->overall_options |= PCRE2_ANCHORED;
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
/* Set up the first code unit or startline flag, the required code unit, and
|
|
|
|
then study the pattern. This code need not be obeyed if PCRE2_NO_START_OPTIMIZE
|
|
|
|
is set, as the data it would create will not be used. Note that a first code
|
|
|
|
unit (but not the startline flag) is useful for anchored patterns because it
|
|
|
|
can still give a quick "no match" and also avoid searching for a last code
|
|
|
|
unit. */
|
|
|
|
|
|
|
|
if ((re->overall_options & PCRE2_NO_START_OPTIMIZE) == 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-06-30 18:00:33 +02:00
|
|
|
/* If we do not have a first code unit, see if there is one that is asserted
|
|
|
|
(these are not saved during the compile because they can cause conflicts with
|
|
|
|
actual literals that follow). */
|
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
if (firstcuflags < 0)
|
2017-12-12 17:23:01 +01:00
|
|
|
firstcu = find_firstassertedcu(codestart, &firstcuflags, 0);
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Save the data for a first code unit. */
|
|
|
|
|
|
|
|
if (firstcuflags >= 0)
|
|
|
|
{
|
|
|
|
re->first_codeunit = firstcu;
|
|
|
|
re->flags |= PCRE2_FIRSTSET;
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
/* Handle caseless first code units. */
|
2014-05-13 13:20:03 +02:00
|
|
|
|
2014-06-14 20:29:51 +02:00
|
|
|
if ((firstcuflags & REQ_CASELESS) != 0)
|
|
|
|
{
|
|
|
|
if (firstcu < 128 || (!utf && firstcu < 255))
|
|
|
|
{
|
2014-06-28 16:23:18 +02:00
|
|
|
if (cb.fcc[firstcu] != firstcu) re->flags |= PCRE2_FIRSTCASELESS;
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
|
|
|
/* The first code unit is > 128 in UTF mode, or > 255 otherwise. In
|
|
|
|
8-bit UTF mode, codepoints in the range 128-255 are introductory code
|
|
|
|
points and cannot have another case. In 16-bit and 32-bit modes, we can
|
2014-06-14 20:29:51 +02:00
|
|
|
check wide characters when UTF (and therefore UCP) is supported. */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2014-09-19 09:43:39 +02:00
|
|
|
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH != 8
|
2014-08-08 17:36:18 +02:00
|
|
|
else if (firstcu <= MAX_UTF_CODE_POINT &&
|
2014-08-05 18:51:32 +02:00
|
|
|
UCD_OTHERCASE(firstcu) != firstcu)
|
2014-06-14 20:29:51 +02:00
|
|
|
re->flags |= PCRE2_FIRSTCASELESS;
|
2014-08-08 17:36:18 +02:00
|
|
|
#endif
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
|
|
|
}
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
/* When there is no first code unit, for non-anchored patterns, see if we can
|
|
|
|
set the PCRE2_STARTLINE flag. This is helpful for multiline matches when all
|
|
|
|
branches start with ^ and also when all branches start with non-atomic .* for
|
|
|
|
non-DOTALL matches when *PRUNE and SKIP are not present. (There is an option
|
|
|
|
that disables this case.) */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
else if ((re->overall_options & PCRE2_ANCHORED) == 0 &&
|
|
|
|
is_startline(codestart, 0, &cb, 0, FALSE))
|
2016-10-18 13:22:40 +02:00
|
|
|
re->flags |= PCRE2_STARTLINE;
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
/* Handle the "required code unit", if one is set. In the case of an anchored
|
|
|
|
pattern, do this only if it follows a variable length item in the pattern. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
if (reqcuflags >= 0 &&
|
|
|
|
((re->overall_options & PCRE2_ANCHORED) == 0 ||
|
|
|
|
(reqcuflags & REQ_VARY) != 0))
|
|
|
|
{
|
|
|
|
re->last_codeunit = reqcu;
|
|
|
|
re->flags |= PCRE2_LASTSET;
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
/* Handle caseless required code units as for first code units (above). */
|
2014-08-08 17:36:18 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
if ((reqcuflags & REQ_CASELESS) != 0)
|
2014-06-14 20:29:51 +02:00
|
|
|
{
|
2017-06-30 18:00:33 +02:00
|
|
|
if (reqcu < 128 || (!utf && reqcu < 255))
|
|
|
|
{
|
|
|
|
if (cb.fcc[reqcu] != reqcu) re->flags |= PCRE2_LASTCASELESS;
|
|
|
|
}
|
2014-09-19 09:43:39 +02:00
|
|
|
#if defined SUPPORT_UNICODE && PCRE2_CODE_UNIT_WIDTH != 8
|
2017-06-30 18:00:33 +02:00
|
|
|
else if (reqcu <= MAX_UTF_CODE_POINT && UCD_OTHERCASE(reqcu) != reqcu)
|
|
|
|
re->flags |= PCRE2_LASTCASELESS;
|
2014-06-14 20:29:51 +02:00
|
|
|
#endif
|
2017-06-30 18:00:33 +02:00
|
|
|
}
|
2014-06-14 20:29:51 +02:00
|
|
|
}
|
2014-05-13 13:20:03 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
/* Finally, study the compiled pattern to set up information such as a bitmap
|
|
|
|
of starting code units and a minimum matching length. */
|
2014-06-21 14:39:48 +02:00
|
|
|
|
2017-06-30 18:00:33 +02:00
|
|
|
if (PRIV(study)(re) != 0)
|
|
|
|
{
|
|
|
|
errorcode = ERR31;
|
|
|
|
goto HAD_CB_ERROR;
|
|
|
|
}
|
|
|
|
} /* End of start-of-match optimizations. */
|
2014-06-21 14:39:48 +02:00
|
|
|
|
2016-11-18 19:59:37 +01:00
|
|
|
/* Control ends up here in all cases. When running under valgrind, make a
|
2016-11-01 18:45:54 +01:00
|
|
|
pattern's terminating zero defined again. If memory was obtained for the parsed
|
2016-10-02 18:01:01 +02:00
|
|
|
version of the pattern, free it before returning. Also free the list of named
|
|
|
|
groups if a larger one had to be obtained, and likewise the group information
|
|
|
|
vector. */
|
2014-06-14 20:29:51 +02:00
|
|
|
|
|
|
|
EXIT:
|
2016-11-01 18:45:54 +01:00
|
|
|
#ifdef SUPPORT_VALGRIND
|
|
|
|
if (zero_terminated) VALGRIND_MAKE_MEM_DEFINED(pattern + patlen, CU2BYTES(1));
|
|
|
|
#endif
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cb.parsed_pattern != stack_parsed_pattern)
|
|
|
|
ccontext->memctl.free(cb.parsed_pattern, ccontext->memctl.memory_data);
|
2015-06-03 18:27:47 +02:00
|
|
|
if (cb.named_group_list_size > NAMED_GROUP_LIST_SIZE)
|
|
|
|
ccontext->memctl.free((void *)cb.named_groups, ccontext->memctl.memory_data);
|
2016-10-02 18:01:01 +02:00
|
|
|
if (cb.groupinfo != stack_groupinfo)
|
2015-11-08 15:20:09 +01:00
|
|
|
ccontext->memctl.free((void *)cb.groupinfo, ccontext->memctl.memory_data);
|
2014-06-14 20:29:51 +02:00
|
|
|
return re; /* Will be NULL after an error */
|
2016-10-02 18:01:01 +02:00
|
|
|
|
|
|
|
/* Errors discovered in parse_regex() set the offset value in the compile
|
|
|
|
block. Errors discovered before it is called must compute it from the ptr
|
|
|
|
value. After parse_regex() is called, the offset in the compile block is set to
|
|
|
|
the end of the pattern, but certain errors in compile_regex() may reset it if
|
|
|
|
an offset is available in the parsed pattern. */
|
|
|
|
|
|
|
|
HAD_CB_ERROR:
|
|
|
|
ptr = pattern + cb.erroroffset;
|
|
|
|
|
|
|
|
HAD_EARLY_ERROR:
|
|
|
|
*erroroffset = ptr - pattern;
|
|
|
|
|
|
|
|
HAD_ERROR:
|
|
|
|
*errorptr = errorcode;
|
|
|
|
pcre2_code_free(re);
|
|
|
|
re = NULL;
|
|
|
|
goto EXIT;
|
2014-03-07 18:28:52 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
/* End of pcre2_compile.c */
|