This function sets additional option bits for pcre2_compile() that are -housed in a compile context. It completely replaces all the bits. The extra +housed in a compile context. It completely replaces all the bits. The extra options are:
PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES Allow \x{df800} to \x{dfff} in UTF-8 and UTF-32 modes
+ PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL Treat all invalid escapes as a literal following character
There is a complete description of the PCRE2 native API in the
pcre2api
diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html
index 7df6d49..eaa5d8e 100644
--- a/doc/html/pcre2api.html
+++ b/doc/html/pcre2api.html
@@ -1706,6 +1706,24 @@ If the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set, surrogate code
point values in UTF-8 and UTF-32 patterns no longer provoke errors and are
incorporated in the compiled pattern. However, they can only match subject
characters if the matching function is called with PCRE2_NO_UTF_CHECK set.
++ PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL ++This is a dangerous option. Use with care. By default, an unrecognized escape +such as \j or a malformed one such as \x{2z} causes a compile-time error when +detected by pcre2_compile(). Perl is somewhat inconsistent in handling +such items: for example, \j is treated as a literal "j", and non-hexadecimal +digits in \x{} are just ignored, though warnings are given in both cases if +Perl's warning switch is enabled. However, a malformed octal number after \o{ +always causes an error in Perl. + +
+If the PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL extra option is passed to +pcre2_compile(), all unrecognized or erroneous escape sequences are +treated as single-character escapes. For example, \j is a literal "j" and +\x{2z} is treated as the literal string "x{2z}". Setting this option means +that typos in patterns may go undetected and have unexpected results. This is a +dangerous option. Use with care.
@@ -3471,7 +3489,7 @@ Cambridge, England.
-Last updated: 30 May 2017
+Last updated: 01 June 2017
Copyright © 1997-2017 University of Cambridge.
diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html
index a8d7d08..58312c0 100644
--- a/doc/html/pcre2test.html
+++ b/doc/html/pcre2test.html
@@ -577,6 +577,7 @@ for a description of the effects of these options.
alt_verbnames set PCRE2_ALT_VERBNAMES
anchored set PCRE2_ANCHORED
auto_callout set PCRE2_AUTO_CALLOUT
+ bad_escape_is_literal set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
/i caseless set PCRE2_CASELESS
dollar_endonly set PCRE2_DOLLAR_ENDONLY
/s dotall set PCRE2_DOTALL
@@ -1816,7 +1817,7 @@ Cambridge, England.
-Last updated: 26 May 2017
+Last updated: 01 June 2017
Copyright © 1997-2017 University of Cambridge.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt
index 477ad6f..4341a61 100644
--- a/doc/pcre2.txt
+++ b/doc/pcre2.txt
@@ -1688,6 +1688,24 @@ COMPILING A PATTERN
only match subject characters if the matching function is called with
PCRE2_NO_UTF_CHECK set.
+ PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
+
+ This is a dangerous option. Use with care. By default, an unrecognized
+ escape such as \j or a malformed one such as \x{2z} causes a compile-
+ time error when detected by pcre2_compile(). Perl is somewhat inconsis-
+ tent in handling such items: for example, \j is treated as a literal
+ "j", and non-hexadecimal digits in \x{} are just ignored, though warn-
+ ings are given in both cases if Perl's warning switch is enabled. How-
+ ever, a malformed octal number after \o{ always causes an error in
+ Perl.
+
+ If the PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL extra option is passed to
+ pcre2_compile(), all unrecognized or erroneous escape sequences are
+ treated as single-character escapes. For example, \j is a literal "j"
+ and \x{2z} is treated as the literal string "x{2z}". Setting this
+ option means that typos in patterns may go undetected and have unex-
+ pected results. This is a dangerous option. Use with care.
+
COMPILATION ERROR CODES
@@ -3350,7 +3368,7 @@ AUTHOR
REVISION
- Last updated: 30 May 2017
+ Last updated: 01 June 2017
Copyright (c) 1997-2017 University of Cambridge.
------------------------------------------------------------------------------
diff --git a/doc/pcre2_set_compile_extra_options.3 b/doc/pcre2_set_compile_extra_options.3
index efd6970..3a081d5 100644
--- a/doc/pcre2_set_compile_extra_options.3
+++ b/doc/pcre2_set_compile_extra_options.3
@@ -1,4 +1,4 @@
-.TH PCRE2_SET_MAX_PATTERN_LENGTH 3 "17 May 2017" "PCRE2 10.30"
+.TH PCRE2_SET_MAX_PATTERN_LENGTH 3 "01 June 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
@@ -15,12 +15,15 @@ PCRE2 - Perl-compatible regular expressions (revised API)
.rs
.sp
This function sets additional option bits for \fBpcre2_compile()\fP that are
-housed in a compile context. It completely replaces all the bits. The extra
+housed in a compile context. It completely replaces all the bits. The extra
options are:
.sp
.\" JOIN
PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES Allow \ex{df800} to \ex{dfff}
in UTF-8 and UTF-32 modes
+.\" JOIN
+ PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL Treat all invalid escapes as
+ a literal following character
.sp
There is a complete description of the PCRE2 native API in the
.\" HREF
diff --git a/doc/pcre2api.3 b/doc/pcre2api.3
index 34c9f37..aeaf36a 100644
--- a/doc/pcre2api.3
+++ b/doc/pcre2api.3
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "30 May 2017" "PCRE2 10.30"
+.TH PCRE2API 3 "01 June 2017" "PCRE2 10.30"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.sp
@@ -1661,6 +1661,23 @@ If the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set, surrogate code
point values in UTF-8 and UTF-32 patterns no longer provoke errors and are
incorporated in the compiled pattern. However, they can only match subject
characters if the matching function is called with PCRE2_NO_UTF_CHECK set.
+.sp
+ PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
+.sp
+This is a dangerous option. Use with care. By default, an unrecognized escape
+such as \ej or a malformed one such as \ex{2z} causes a compile-time error when
+detected by \fBpcre2_compile()\fP. Perl is somewhat inconsistent in handling
+such items: for example, \ej is treated as a literal "j", and non-hexadecimal
+digits in \ex{} are just ignored, though warnings are given in both cases if
+Perl's warning switch is enabled. However, a malformed octal number after \eo{
+always causes an error in Perl.
+.P
+If the PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL extra option is passed to
+\fBpcre2_compile()\fP, all unrecognized or erroneous escape sequences are
+treated as single-character escapes. For example, \ej is a literal "j" and
+\ex{2z} is treated as the literal string "x{2z}". Setting this option means
+that typos in patterns may go undetected and have unexpected results. This is a
+dangerous option. Use with care.
.
.
.SH "COMPILATION ERROR CODES"
@@ -3491,6 +3508,6 @@ Cambridge, England.
.rs
.sp
.nf
-Last updated: 30 May 2017
+Last updated: 01 June 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
diff --git a/doc/pcre2test.1 b/doc/pcre2test.1
index 7ce0520..26d395f 100644
--- a/doc/pcre2test.1
+++ b/doc/pcre2test.1
@@ -1,4 +1,4 @@
-.TH PCRE2TEST 1 "26 May 2017" "PCRE 10.30"
+.TH PCRE2TEST 1 "01 June 2017" "PCRE 10.30"
.SH NAME
pcre2test - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS
@@ -539,6 +539,7 @@ for a description of the effects of these options.
alt_verbnames set PCRE2_ALT_VERBNAMES
anchored set PCRE2_ANCHORED
auto_callout set PCRE2_AUTO_CALLOUT
+ bad_escape_is_literal set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
/i caseless set PCRE2_CASELESS
dollar_endonly set PCRE2_DOLLAR_ENDONLY
/s dotall set PCRE2_DOTALL
@@ -1792,6 +1793,6 @@ Cambridge, England.
.rs
.sp
.nf
-Last updated: 26 May 2017
+Last updated: 01 June 2017
Copyright (c) 1997-2017 University of Cambridge.
.fi
diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt
index e6164f9..685c3d9 100644
--- a/doc/pcre2test.txt
+++ b/doc/pcre2test.txt
@@ -521,6 +521,7 @@ PATTERN MODIFIERS
alt_verbnames set PCRE2_ALT_VERBNAMES
anchored set PCRE2_ANCHORED
auto_callout set PCRE2_AUTO_CALLOUT
+ bad_escape_is_literal set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
/i caseless set PCRE2_CASELESS
dollar_endonly set PCRE2_DOLLAR_ENDONLY
/s dotall set PCRE2_DOTALL
@@ -1650,5 +1651,5 @@ AUTHOR
REVISION
- Last updated: 26 May 2017
+ Last updated: 01 June 2017
Copyright (c) 1997-2017 University of Cambridge.
diff --git a/src/pcre2.h b/src/pcre2.h
index 590803c..cc2a642 100644
--- a/src/pcre2.h
+++ b/src/pcre2.h
@@ -142,6 +142,7 @@ D is inspected during pcre2_dfa_match() execution
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
+#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
/* These are for pcre2_jit_compile(). */
diff --git a/src/pcre2.h.in b/src/pcre2.h.in
index bed10f4..b6fd9d9 100644
--- a/src/pcre2.h.in
+++ b/src/pcre2.h.in
@@ -142,6 +142,7 @@ D is inspected during pcre2_dfa_match() execution
/* An additional compile options word is available in the compile context. */
#define PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES 0x00000001u /* C */
+#define PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL 0x00000002u /* C */
/* These are for pcre2_jit_compile(). */
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index f592831..c97f3fb 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -2591,11 +2591,23 @@ while (ptr < ptrend)
/* ---- Escape sequence ---- */
case CHAR_BACKSLASH:
+ tempptr = ptr;
escape = PRIV(check_escape)(&ptr, ptrend, &c, &errorcode, options,
FALSE, cb);
- if (errorcode != 0) goto FAILED;
+ 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
+ {
+ GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
+ }
+ escape = 0; /* Treat as literal character */
+ }
- /* The escape was a data character. */
+ /* The escape was a data escape or literal character. */
if (escape == 0)
{
@@ -2647,12 +2659,12 @@ while (ptr < ptrend)
case ESC_C:
#ifdef NEVER_BACKSLASH_C
errorcode = ERR85;
- goto FAILED;
+ goto ESCAPE_FAILED;
#else
if ((options & PCRE2_NEVER_BACKSLASH_C) != 0)
{
errorcode = ERR83;
- goto FAILED;
+ goto ESCAPE_FAILED;
}
#endif
okquantifier = TRUE;
@@ -2662,7 +2674,7 @@ while (ptr < ptrend)
case ESC_X:
#ifndef SUPPORT_UNICODE
errorcode = ERR45; /* Supported only with Unicode support */
- goto FAILED;
+ goto ESCAPE_FAILED;
#endif
case ESC_H:
case ESC_h:
@@ -2727,7 +2739,7 @@ while (ptr < ptrend)
BOOL negated;
uint16_t ptype = 0, pdata = 0;
if (!get_ucp(&ptr, &negated, &ptype, &pdata, &errorcode, cb))
- goto FAILED;
+ goto ESCAPE_FAILED;
if (negated) escape = (escape == ESC_P)? ESC_p : ESC_P;
*parsed_pattern++ = META_ESCAPE + escape;
*parsed_pattern++ = (ptype << 16) | pdata;
@@ -2735,7 +2747,7 @@ while (ptr < ptrend)
}
#else
errorcode = ERR45;
- goto FAILED;
+ goto ESCAPE_FAILED;
#endif
break; /* End \P and \p */
@@ -2751,7 +2763,7 @@ while (ptr < ptrend)
*ptr != CHAR_LESS_THAN_SIGN && *ptr != CHAR_APOSTROPHE))
{
errorcode = (escape == ESC_g)? ERR57 : ERR69;
- goto FAILED;
+ goto ESCAPE_FAILED;
}
terminator = (*ptr == CHAR_LESS_THAN_SIGN)?
CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)?
@@ -2769,18 +2781,18 @@ while (ptr < ptrend)
if (p >= ptrend || *p != terminator)
{
errorcode = ERR57;
- goto FAILED;
+ goto ESCAPE_FAILED;
}
ptr = p;
goto SET_RECURSION;
}
- if (errorcode != 0) goto FAILED;
+ if (errorcode != 0) goto ESCAPE_FAILED;
}
/* Not a numerical recursion */
if (!read_name(&ptr, ptrend, terminator, &offset, &name, &namelen,
- &errorcode, cb)) goto FAILED;
+ &errorcode, cb)) goto ESCAPE_FAILED;
/* \k and \g when used with braces are back references, whereas \g used
with quotes or angle brackets is a recursion */
@@ -2792,7 +2804,7 @@ while (ptr < ptrend)
PUTOFFSET(offset, parsed_pattern);
okquantifier = TRUE;
- break;
+ break; /* End special escape processing */
}
break; /* End escape sequence processing */
@@ -3139,10 +3151,23 @@ while (ptr < ptrend)
else
{
+ tempptr = ptr;
escape = PRIV(check_escape)(&ptr, ptrend, &c, &errorcode,
options, TRUE, cb);
-
- if (errorcode != 0) goto FAILED;
+
+ 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
+ {
+ GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
+ }
+ escape = 0; /* Treat as literal character */
+ }
+
if (escape == 0) /* Escaped character code point is in c */
{
char_is_literal = FALSE;
@@ -3176,7 +3201,7 @@ while (ptr < ptrend)
if (class_range_state == RANGE_STARTED)
{
errorcode = ERR50;
- goto FAILED;
+ goto CLASS_ESCAPE_FAILED;
}
/* Of the remaining escapes, only those that define characters are
@@ -3187,7 +3212,7 @@ while (ptr < ptrend)
{
case ESC_N:
errorcode = ERR71; /* Not supported in a class */
- goto FAILED;
+ goto CLASS_ESCAPE_FAILED;
case ESC_H:
case ESC_h:
@@ -3250,13 +3275,14 @@ while (ptr < ptrend)
}
#else
errorcode = ERR45;
- goto FAILED;
+ goto CLASS_ESCAPE_FAILED;
#endif
break; /* End \P and \p */
default: /* All others are not allowed in a class */
errorcode = ERR7;
- goto FAILED_BACK;
+ ptr--;
+ goto CLASS_ESCAPE_FAILED;
}
}
diff --git a/src/pcre2test.c b/src/pcre2test.c
index 08d3669..8eafadf 100644
--- a/src/pcre2test.c
+++ b/src/pcre2test.c
@@ -402,9 +402,9 @@ typedef struct convertstruct {
static convertstruct convertlist[] = {
{ "glob", PCRE2_CONVERT_GLOB },
{ "glob_basic", PCRE2_CONVERT_GLOB_BASIC },
- { "glob_ignore_dot_start", PCRE2_CONVERT_GLOB_IGNORE_DOT_START },
- { "glob_no_starstar", PCRE2_CONVERT_GLOB_NO_STARSTAR },
- { "glob_no_wild_separator", PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR },
+ { "glob_ignore_dot_start", PCRE2_CONVERT_GLOB_IGNORE_DOT_START },
+ { "glob_no_starstar", PCRE2_CONVERT_GLOB_NO_STARSTAR },
+ { "glob_no_wild_separator", PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR },
{ "posix_basic", PCRE2_CONVERT_POSIX_BASIC },
{ "posix_extended", PCRE2_CONVERT_POSIX_EXTENDED },
{ "unset", CONVERT_UNSET }};
@@ -590,6 +590,7 @@ static modstruct modlist[] = {
{ "altglobal", MOD_PND, MOD_CTL, CTL_ALTGLOBAL, PO(control) },
{ "anchored", MOD_PD, MOD_OPT, PCRE2_ANCHORED, PD(options) },
{ "auto_callout", MOD_PAT, MOD_OPT, PCRE2_AUTO_CALLOUT, PO(options) },
+ { "bad_escape_is_literal", MOD_CTC, MOD_OPT, PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL, CO(extra_options) },
{ "bincode", MOD_PAT, MOD_CTL, CTL_BINCODE, PO(control) },
{ "bsr", MOD_CTC, MOD_BSR, 0, CO(bsr_convention) },
{ "callout_capture", MOD_DAT, MOD_CTL, CTL_CALLOUT_CAPTURE, DO(control) },
@@ -692,8 +693,8 @@ static modstruct modlist[] = {
#define POSIX_SUPPORTED_COMPILE_OPTIONS ( \
PCRE2_CASELESS|PCRE2_DOTALL|PCRE2_MULTILINE|PCRE2_UCP|PCRE2_UTF| \
PCRE2_UNGREEDY)
-
-#define POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS (0)
+
+#define POSIX_SUPPORTED_COMPILE_EXTRA_OPTIONS (0)
#define POSIX_SUPPORTED_COMPILE_CONTROLS ( \
CTL_AFTERTEXT|CTL_ALLAFTERTEXT|CTL_EXPAND|CTL_POSIX|CTL_POSIX_NOSUB)
@@ -3701,7 +3702,7 @@ for (;;)
case MOD_CON: /* A convert type/options list */
for (;; pp++)
- {
+ {
uint8_t *colon = (uint8_t *)strchr((const char *)pp, ':');
len = ((colon != NULL && colon < ep)? colon:ep) - pp;
for (i = 0; i < convertlistcount; i++)
@@ -4073,13 +4074,14 @@ Returns: nothing
*/
static void
-show_compile_extra_options(uint32_t options, const char *before,
- const char *after)
-{
+show_compile_extra_options(uint32_t options, const char *before,
+ const char *after)
+{
if (options == 0) fprintf(outfile, "%s