Revision: 384
http://www.exim.org/viewvc/pcre2?view=rev&revision=384
Author: ph10
Date: 2015-10-09 17:06:53 +0100 (Fri, 09 Oct 2015)
Log Message:
-----------
Fix compiler bug for classes such as [\W\p{Any}].
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/src/pcre2_compile.c
code/trunk/testdata/testinput5
code/trunk/testdata/testoutput5
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2015-10-07 17:40:22 UTC (rev 383)
+++ code/trunk/ChangeLog 2015-10-09 16:06:53 UTC (rev 384)
@@ -194,7 +194,11 @@
55. Implemented PCRE2_SUBSTITUTE_EXTENDED.
+56. In a character class such as [\W\p{Any}] where both a negative-type escape
+("not a word character") and a property escape were present, the property
+escape was being ignored.
+
Version 10.20 30-June-2015
--------------------------
Modified: code/trunk/src/pcre2_compile.c
===================================================================
--- code/trunk/src/pcre2_compile.c 2015-10-07 17:40:22 UTC (rev 383)
+++ code/trunk/src/pcre2_compile.c 2015-10-09 16:06:53 UTC (rev 384)
@@ -1645,11 +1645,11 @@
/* If backslash is at the end of the pattern, it's an error. */
-if (ptr >= ptrend)
+if (ptr >= ptrend)
{
*errorcodeptr = ERR1;
return 0;
- }
+ }
GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */
ptr--; /* Set pointer back to the last code unit */
@@ -1671,8 +1671,8 @@
}
}
-/* Escapes that need further processing, including those that are unknown.
-When called from pcre2_substitute(), only \c, \o, and \x are recognized (and \u
+/* Escapes that need further processing, including those that are unknown.
+When called from pcre2_substitute(), only \c, \o, and \x are recognized (and \u
when BSUX is set). */
else
@@ -1680,7 +1680,7 @@
PCRE2_SPTR oldptr;
BOOL braced, negated, overflow;
unsigned int s;
-
+
/* Filter calls from pcre2_substitute(). */
if (cb == NULL && c != CHAR_c && c != CHAR_o && c != CHAR_x &&
@@ -1688,7 +1688,7 @@
{
*errorcodeptr = ERR3;
return 0;
- }
+ }
switch (c)
{
@@ -4645,19 +4645,21 @@
zeroreqcu = reqcu;
zeroreqcuflags = reqcuflags;
- /* If there are characters with values > 255, we have to compile an
- extended class, with its own opcode, unless there was a negated special
- such as \S in the class, and PCRE2_UCP is not set, because in that case all
+ /* 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
characters > 255 are in the class, so any that were explicitly given as
- well can be ignored. If (when there are explicit characters > 255 that must
- be listed) there are no characters < 256, we can omit the bitmap in the
- actual compiled code. */
+ well can be ignored. If (when there are explicit characters > 255 or
+ property settings that must be listed) there are no characters < 256, we
+ can omit the bitmap in the actual compiled code. */
#ifdef SUPPORT_WIDE_CHARS
#ifdef SUPPORT_UNICODE
- if (xclass && (!should_flip_negation || (options & PCRE2_UCP) != 0))
+ if (xclass && (xclass_has_prop || !should_flip_negation ||
+ (options & PCRE2_UCP) != 0))
#elif PCRE2_CODE_UNIT_WIDTH != 8
- if (xclass && !should_flip_negation)
+ if (xclass && (xclass_has_prop || !should_flip_negation))
#endif
{
*class_uchardata++ = XCL_END; /* Marks the end of extra data */
Modified: code/trunk/testdata/testinput5
===================================================================
--- code/trunk/testdata/testinput5 2015-10-07 17:40:22 UTC (rev 383)
+++ code/trunk/testdata/testinput5 2015-10-09 16:06:53 UTC (rev 384)
@@ -1693,4 +1693,13 @@
/((?<digit>\d)|(?<letter>\p{L}))/g,substitute_extended,replace=<${digit:+digit; :not digit; }${letter:+letter:not a letter}>
ab12cde
+/[\W\p{Any}]/B
+ abc
+ 123
+
+/[\W\pL]/B
+ abc
+\= Expect no match
+ 123
+
# End of testinput5
Modified: code/trunk/testdata/testoutput5
===================================================================
--- code/trunk/testdata/testoutput5 2015-10-07 17:40:22 UTC (rev 383)
+++ code/trunk/testdata/testoutput5 2015-10-09 16:06:53 UTC (rev 384)
@@ -4046,4 +4046,29 @@
ab12cde
7: <not digit; letter><not digit; letter><digit; not a letter><digit; not a letter><not digit; letter><not digit; letter><not digit; letter>
+/[\W\p{Any}]/B
+------------------------------------------------------------------
+ Bra
+ [\x00-/:-@[-^`{-\xff\p{Any}]
+ Ket
+ End
+------------------------------------------------------------------
+ abc
+ 0: a
+ 123
+ 0: 1
+
+/[\W\pL]/B
+------------------------------------------------------------------
+ Bra
+ [\x00-/:-@[-^`{-\xff\p{L}]
+ Ket
+ End
+------------------------------------------------------------------
+ abc
+ 0: a
+\= Expect no match
+ 123
+No match
+
# End of testinput5
