In perl.git, the branch blead has been updated
<http://perl5.git.perl.org/perl.git/commitdiff/0399b2152e23eb6ce1f09562d53b87be7fe30924?hp=b2adfa9b5e1682df8c4a2cbe81aa36113f397b1d>
- Log -----------------------------------------------------------------
commit 0399b2152e23eb6ce1f09562d53b87be7fe30924
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 16:55:42 2010 -0600
regcomp.c: No longer need _C_C_T_ and variant macro
Now, all calls have been converted to the more general case; can remove
the old one, and rename the new one to have the same name as the old one
M regcomp.c
commit 9b7c43baf09d4c57d5cd6c9a052ce398d1626a6a
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 16:48:55 2010 -0600
[:posix:] now works under /u
This patch is part of fixing the Unicode bug. The /u regex modifier now
applies to posix character classes. This resolves [perl #18281].
The Todo tests in reg_posicc.t have all been made not todo.
M pod/perldelta.pod
M pod/perlunicode.pod
M regcomp.c
M t/re/reg_posixcc.t
commit aedd44b501ab1196eeb3ebe56ef7647debb77eab
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 15:33:34 2010 -0600
l1_char_class_tab.h: Wrong for ALNUMC
The generated table was wrong in the Latin1 range for characters with
the ALNUMC property
M Porting/mk_PL_charclass.pl
M l1_char_class_tab.h
commit e486b3ccda3754fd159530607148c92cbfcbddf8
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 15:23:11 2010 -0600
Nits in re pods
M pod/perlrebackslash.pod
M pod/perlrecharclass.pod
commit d35dd6c678badc24d545f8b7b7a3ebdf0fb0b355
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 15:20:24 2010 -0600
DOCs: Clarify that \w matches marks and \Pc
The previous documentation really didn't specify what \w is. It matches
the underscore, but also all other connector punctuation, plus any
marks, such as diacritical accents that occur within a word.
M lib/unicore/mktables
M pod/perlre.pod
M pod/perlrebackslash.pod
M pod/perlrecharclass.pod
M pod/perlreref.pod
commit cbc24f92709e23449028ec3036bda16c0af294fb
Author: Karl Williamson <pub...@khwilliamson.com>
Date: Sat Oct 30 10:13:48 2010 -0600
Add consistent synonyms for \p{PosxFOO}
This patch adds a set of synonyms \p{XPosixFOO} for the full extended
Unicode version of \p{PosixFOO}, so only one rule need be remembered.
Similarly, \p{XPerlSpace} is added to preserve the rule for the one
similar class that doesn't have Posix in its name.
Prior to this patch there was no exact equivalent to \p{PosixPunct}
extended beyond ASCII.
M lib/unicore/mktables
M pod/perlrecharclass.pod
M pod/perlreref.pod
commit 0721d74039598968722031f4192aa5133e1659c9
Author: Father Chrysostomos <spr...@cpan.org>
Date: Sun Oct 31 10:23:39 2010 -0700
Revert "Add consistent synonyms for \p{PosxFOO}"
This reverts commit d5944336d74c819152158dabfd806d49ad0ecb21.
M lib/unicore/mktables
M pod/perlrecharclass.pod
-----------------------------------------------------------------------
Summary of changes:
Porting/mk_PL_charclass.pl | 2 +-
l1_char_class_tab.h | 130 ++++++++++++++++++++++----------------------
lib/unicore/mktables | 3 +-
pod/perldelta.pod | 20 +++++++
pod/perlre.pod | 4 +-
pod/perlrebackslash.pod | 12 +++--
pod/perlrecharclass.pod | 25 ++++++---
pod/perlreref.pod | 70 +++++++++++-------------
pod/perlunicode.pod | 5 +-
regcomp.c | 59 ++++++--------------
t/re/reg_posixcc.t | 29 ++++-------
11 files changed, 177 insertions(+), 182 deletions(-)
diff --git a/Porting/mk_PL_charclass.pl b/Porting/mk_PL_charclass.pl
index a23d611..64599e0 100644
--- a/Porting/mk_PL_charclass.pl
+++ b/Porting/mk_PL_charclass.pl
@@ -90,7 +90,7 @@ for my $ord (0..255) {
$re = qr/\w/;
} elsif ($name eq 'ALNUMC') {
# Like \w, but no underscore
- $re = qr/[^_\W]/;
+ $re = qr/\p{Alnum}/;
} elsif ($name eq 'OCTAL') {
$re = qr/[0-7]/;
} else { # The remainder have the same name and values as Unicode
diff --git a/l1_char_class_tab.h b/l1_char_class_tab.h
index f5c8870..f50b8d2 100644
--- a/l1_char_class_tab.h
+++ b/l1_char_class_tab.h
@@ -209,7 +209,7 @@ EXTCONST U32 PL_charclass[] = {
/* U+A7 SECTION SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+A8 DIAERESIS */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+A9 COPYRIGHT SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+AA FEMININE ORDINAL INDICATOR */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+AA FEMININE ORDINAL INDICATOR */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
/* U+AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK */
_CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
/* U+AC NOT SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+AD SOFT HYPHEN */ _CC_GRAPH_L1|_CC_PRINT_L1,
@@ -220,81 +220,81 @@ EXTCONST U32 PL_charclass[] = {
/* U+B2 SUPERSCRIPT TWO */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+B3 SUPERSCRIPT THREE */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+B4 ACUTE ACCENT */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+B5 MICRO SIGN */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+B5 MICRO SIGN */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
/* U+B6 PILCROW SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+B7 MIDDLE DOT */ _CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
/* U+B8 CEDILLA */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+B9 SUPERSCRIPT ONE */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+BA MASCULINE ORDINAL INDICATOR */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+BA MASCULINE ORDINAL INDICATOR */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
/* U+BB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK */
_CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
/* U+BC VULGAR FRACTION ONE QUARTER */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+BD VULGAR FRACTION ONE HALF */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+BE VULGAR FRACTION THREE QUARTERS */ _CC_GRAPH_L1|_CC_PRINT_L1,
/* U+BF INVERTED QUESTION MARK */ _CC_GRAPH_L1|_CC_PRINT_L1|_CC_PUNCT_L1,
-/* U+C0 A WITH GRAVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C1 A WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C2 A WITH CIRCUMFLEX */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C3 A WITH TILDE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C4 A WITH DIAERESIS */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C5 A WITH RING ABOVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C6 AE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C7 C WITH CEDILLA */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C8 E WITH GRAVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+C9 E WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CA E WITH CIRCUMFLEX */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CB E WITH DIAERESIS */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CC I WITH GRAVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CD I WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CE I WITH CIRCUMFLEX */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+CF I WITH DIAERESIS */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D0 ETH */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D1 N WITH TILDE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D2 O WITH GRAVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D3 O WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D4 O WITH CIRCUMFLEX */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D5 O WITH TILDE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D6 O WITH DIAERESIS */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C0 A WITH GRAVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C1 A WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C2 A WITH CIRCUMFLEX */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C3 A WITH TILDE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C4 A WITH DIAERESIS */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C5 A WITH RING ABOVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C6 AE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C7 C WITH CEDILLA */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C8 E WITH GRAVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+C9 E WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CA E WITH CIRCUMFLEX */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CB E WITH DIAERESIS */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CC I WITH GRAVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CD I WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CE I WITH CIRCUMFLEX */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+CF I WITH DIAERESIS */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D0 ETH */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D1 N WITH TILDE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D2 O WITH GRAVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D3 O WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D4 O WITH CIRCUMFLEX */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D5 O WITH TILDE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D6 O WITH DIAERESIS */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
/* U+D7 MULTIPLICATION SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+D8 O WITH STROKE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+D9 U WITH GRAVE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DA U WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DB U WITH CIRCUMFLEX */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DC U WITH DIAERESIS */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DD Y WITH ACUTE */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DE THORN */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
-/* U+DF sharp s */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E0 a with grave */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E1 a with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E2 a with circumflex */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E3 a with tilde */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E4 a with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E5 a with ring above */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E6 ae */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E7 c with cedilla */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E8 e with grave */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+E9 e with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+EA e with circumflex */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+EB e with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+EC i with grave */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+ED i with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+EE i with circumflex */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+EF i with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F0 eth */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F1 n with tilde */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F2 o with grave */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F3 o with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F4 o with circumflex */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F5 o with tilde */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F6 o with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+D8 O WITH STROKE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+D9 U WITH GRAVE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DA U WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DB U WITH CIRCUMFLEX */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DC U WITH DIAERESIS */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DD Y WITH ACUTE */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DE THORN */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1,
+/* U+DF sharp s */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E0 a with grave */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E1 a with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E2 a with circumflex */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E3 a with tilde */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E4 a with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E5 a with ring above */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E6 ae */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E7 c with cedilla */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E8 e with grave */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+E9 e with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+EA e with circumflex */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+EB e with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+EC i with grave */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+ED i with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+EE i with circumflex */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+EF i with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F0 eth */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F1 n with tilde */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F2 o with grave */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F3 o with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F4 o with circumflex */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F5 o with tilde */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F6 o with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
/* U+F7 DIVISION SIGN */ _CC_GRAPH_L1|_CC_PRINT_L1,
-/* U+F8 o with stroke */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+F9 u with grave */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FA u with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FB u with circumflex */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FC u with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FD y with acute */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FE thorn */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
-/* U+FF y with diaeresis */
_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F8 o with stroke */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+F9 u with grave */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FA u with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FB u with circumflex */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FC u with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FD y with acute */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FE thorn */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
+/* U+FF y with diaeresis */
_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1,
};
#else /* ! DOINIT */
diff --git a/lib/unicore/mktables b/lib/unicore/mktables
index 8a5c89a..73dea61 100644
--- a/lib/unicore/mktables
+++ b/lib/unicore/mktables
@@ -11323,7 +11323,8 @@ sub compile_perl() {
);
my $Word = $perl->add_match_table('Word',
- Description => '\w, including beyond ASCII',
+ Description => '\w, including beyond ASCII;'
+ . ' = \p{Alnum} + \pM + \p{Pc}',
Initialize => $Alnum + $gc->table('Mark'),
);
$Word->add_alias('XPosixWord');
diff --git a/pod/perldelta.pod b/pod/perldelta.pod
index 162ce85..203260c 100644
--- a/pod/perldelta.pod
+++ b/pod/perldelta.pod
@@ -65,6 +65,18 @@ See L<re/'/flags' mode> for details.
Statement labels can now occur before any type of statement or declaration,
such as C<package>.
+=head2 C<use feature "unicode_strings"> now applies to more regex matching
+
+Another chunk of the L<perlunicode/The "Unicode Bug"> is fixed in this
+release. Now, regular expressions compiled within the scope of the
+"unicode_strings" feature (or under the "u" regex modifier (specifiable
+currently only with infix notation C<(?u:...)> or via C<use re '/u'>)
+will match the same whether or not the target string is encoded in utf8,
+with regard to C<[[:posix:]]> character classes
+
+Work is underway to add the case sensitive matching to the control of
+this feature, but was not complete in time for this dot release.
+
=head1 Security
XXX Any security-related notices go here. In particular, any security
@@ -626,6 +638,14 @@ L<[perl
#77498]|http://rt.perl.org/rt3/Public/Bug/Display.html?id=77498>.
C<sprintf> was ignoring locales when called with constant arguments
L<[perl #78632]|http://rt.perl.org/rt3/Public/Bug/Display.html?id=78632>.
+=item *
+
+A non-ASCII character in the Latin-1 range could match both a Posix
+class, such as C<[[:alnum:]]>, and its inverse C<[[:^alnum:]]>. This is
+now fixed for regular expressions compiled under the C<"u"> modifier.
+See L</C<use feature "unicode_strings"> now applies to more regex matching>.
+L<[perl #18281]|http://rt.perl.org/rt3/Public/Bug/Display.html?id=18281>.
+
=back
=head1 Known Problems
diff --git a/pod/perlre.pod b/pod/perlre.pod
index d4e6599..acc1ad5 100644
--- a/pod/perlre.pod
+++ b/pod/perlre.pod
@@ -256,7 +256,9 @@ X<\g> X<\k> X<\K> X<backreference>
character class "..." within the outer bracketed
character class. Example: [[:upper:]] matches any
uppercase character.
- \w [3] Match a "word" character (alphanumeric plus "_")
+ \w [3] Match a "word" character (alphanumeric plus "_", plus
+ other connector punctuation chars plus Unicode
+ marks
\W [3] Match a non-"word" character
\s [3] Match a whitespace character
\S [3] Match a non-whitespace character
diff --git a/pod/perlrebackslash.pod b/pod/perlrebackslash.pod
index b75c1e4..9bab138 100644
--- a/pod/perlrebackslash.pod
+++ b/pod/perlrebackslash.pod
@@ -359,15 +359,17 @@ the character classes are written as a backslash
sequence. We will briefly
discuss those here; full details of character classes can be found in
L<perlrecharclass>.
-C<\w> is a character class that matches any single I<word> character (letters,
-digits, underscore). C<\d> is a character class that matches any decimal digit,
-while the character class C<\s> matches any whitespace character.
+C<\w> is a character class that matches any single I<word> character
+(letters, digits, Unicode marks, and connector punctuation (like the
+underscore)). C<\d> is a character class that matches any decimal
+digit, while the character class C<\s> matches any whitespace character.
New in perl 5.10.0 are the classes C<\h> and C<\v> which match horizontal
and vertical whitespace characters.
The uppercase variants (C<\W>, C<\D>, C<\S>, C<\H>, and C<\V>) are
-character classes that match any character that isn't a word character,
-digit, whitespace, horizontal whitespace nor vertical whitespace.
+character classes that match, respectively, any character that isn't a
+word character, digit, whitespace, horizontal whitespace, or vertical
+whitespace.
Mnemonics: I<w>ord, I<d>igit, I<s>pace, I<h>orizontal, I<v>ertical.
diff --git a/pod/perlrecharclass.pod b/pod/perlrecharclass.pod
index 7f96b4b..3329d60 100644
--- a/pod/perlrecharclass.pod
+++ b/pod/perlrecharclass.pod
@@ -113,14 +113,19 @@ Any character that isn't matched by C<\d> will be matched
by C<\D>.
=head3 Word characters
A C<\w> matches a single alphanumeric character (an alphabetic character, or a
-decimal digit) or an underscore (C<_>), not a whole word. To match a whole
+decimal digit) or a connecting punctuation character, such as an
+underscore ("_"). It does not match a whole word. To match a whole
word, use C<\w+>. This isn't the same thing as matching an English word, but
-is the same as a string of Perl-identifier characters. What is considered a
+in the ASCII range is the same as a string of Perl-identifier
+characters. What is considered a
word character depends on several factors, detailed below in L</Locale,
EBCDIC, Unicode and UTF-8>. If those factors indicate a Unicode
interpretation, C<\w> matches the characters that are considered word
characters in the Unicode database. That is, it not only matches ASCII letters,
-but also Thai letters, Greek letters, etc. If a Unicode interpretation
+but also Thai letters, Greek letters, etc. This includes connector
+punctuation (like the underscore) which connect two words together, or
+marks, such as a C<COMBINING TILDE>, which are generally used to add
+diacritical marks to letters. If a Unicode interpretation
is not indicated, C<\w> matches those characters that are considered
word characters by the current locale or EBCDIC code page. Without a
locale or EBCDIC code page, C<\w> matches the ASCII letters, digits and
@@ -229,7 +234,7 @@ UTF-8 format, or the locale or EBCDIC code page that is in
effect includes them.
=back
It is worth noting that C<\d>, C<\w>, etc, match single characters, not
-complete numbers or words. To match a number (that consists of integers),
+complete numbers or words. To match a number (that consists of digits),
use C<\d+>; to match a word, use C<\w+>.
=head3 \N
@@ -534,8 +539,8 @@ and any C<\p> property name can be prefixed with "Is" such
as C<\p{IsAlpha}>.)
Both the C<\p> forms are unaffected by any locale that is in effect, or whether
the string is in UTF-8 format or not, or whether the platform is EBCDIC or not.
In contrast, the POSIX character classes are affected. If the source string is
-in UTF-8 format, the POSIX classes (with the exception of C<[[:punct:]]>, see
-Note [5] below) behave like their "Full-range" Unicode counterparts. If the
+in UTF-8 format, the POSIX classes behave like their "Full-range"
+Unicode counterparts. If the
source string is not in UTF-8 format, and no locale is in effect, and the
platform is not EBCDIC, all the POSIX classes behave like their ASCII-range
counterparts. Otherwise, they behave based on the rules of the locale or
@@ -603,13 +608,15 @@ non-controls, non-alphanumeric, non-space characters:
C<[-!"#$%&'()*+,./:;<=E<gt>?...@[\\\]^_`{|}~]> (although if a locale is in
effect,
it could alter the behavior of C<[[:punct:]]>).
-C<\p{Punct}> matches a somewhat different set in the ASCII range, namely
+The similarly named property, C<\p{Punct}>, matches a somewhat different
+set in the ASCII range, namely
C<[-!"#%&'()*,./:;?...@[\\\]_{}]>. That is, it is missing
C<[$+E<lt>=E<gt>^`|~]>.
This is because Unicode splits what POSIX considers to be punctuation into two
categories, Punctuation and Symbols.
-When the matching string is in UTF-8 format, C<[[:punct:]]> matches what it
-matches in the ASCII range, plus what C<\p{Punct}> matches. This is different
+C<\p{PosixPunct>, and when the matching string is in UTF-8 format,
+C<[[:punct:]]>, match what they match in the ASCII range, plus what
+C<\p{Punct}> matches. This is different
than strictly matching according to C<\p{Punct}>. Another way to say it is
that
for a UTF-8 string, C<[[:punct:]]> matches all the characters that Unicode
considers to be punctuation, plus all the ASCII-range characters that Unicode
diff --git a/pod/perlreref.pod b/pod/perlreref.pod
index 6e028ee..5247a63 100644
--- a/pod/perlreref.pod
+++ b/pod/perlreref.pod
@@ -145,44 +145,40 @@ and L<perlunicode> for details.
POSIX character classes and their Unicode and Perl equivalents:
- ASCII- Full-
- range range backslash
- POSIX \p{...} \p{} sequence Description
+ ASCII- Full-
+ POSIX range range backslash
+ [[:...:]] \p{...} \p{...} sequence Description
+
-----------------------------------------------------------------------
- alnum PosixAlnum Alnum Alpha plus Digit
- alpha PosixAlpha Alpha Alphabetic characters
- ascii ASCII Any ASCII character
- blank PosixBlank Blank \h Horizontal whitespace;
- full-range also written
- as \p{HorizSpace} (GNU
- extension)
- cntrl PosixCntrl Cntrl Control characters
- digit PosixDigit Digit \d Decimal digits
- graph PosixGraph Graph Alnum plus Punct
- lower PosixLower Lower Lowercase characters
- print PosixPrint Print Graph plus Print, but not
- any Cntrls
- punct PosixPunct Punct These aren't precisely
- equivalent. See NOTE,
- below.
- space PosixSpace Space [\s\cK] Whitespace
- PerlSpace SpacePerl \s Perl's whitespace
- definition
- upper PosixUpper Upper Uppercase characters
- word PerlWord Word \w Alnum plus '_' (Perl
- extension)
- xdigit ASCII_Hex_Digit XDigit Hexadecimal digit,
- ASCII-range is
- [0-9A-Fa-f]
-
-NOTE on C<[[:punct:]]>, C<\p{PosixPunct}> and C<\p{Punct}>:
-In the ASCII range, C<[[:punct:]]> and C<\p{PosixPunct}> match
-C<[-!"#$%&'()*+,./:;<=E<gt>?...@[\\\]^_`{|}~]> (although if a locale is in
-effect, it could alter the behavior of C<[[:punct:]]>); and C<\p{Punct}>
-matches C<[-!"#%&'()*,./:;?...@[\\\]_{}]>. When matching a UTF-8 string,
-C<[[:punct:]]> matches what it does in the ASCII range, plus what
-C<\p{Punct}> matches. C<\p{Punct}> matches, anything that isn't a
-control, an alphanumeric, a space, nor a symbol.
+ alnum PosixAlnum XPosixAlnum Alpha plus Digit
+ alpha PosixAlpha XPosixAlpha Alphabetic characters
+ ascii ASCII Any ASCII character
+ blank PosixBlank XPosixBlank \h Horizontal whitespace;
+ full-range also
+ written as
+ \p{HorizSpace} (GNU
+ extension)
+ cntrl PosixCntrl XPosixCntrl Control characters
+ digit PosixDigit XPosixDigit \d Decimal digits
+ graph PosixGraph XPosixGraph Alnum plus Punct
+ lower PosixLower XPosixLower Lowercase characters
+ print PosixPrint XPosixPrint Graph plus Print, but
+ not any Cntrls
+ punct PosixPunct XPosixPunct Punctuation and Symbols
+ in ASCII-range; just
+ punct outside it
+ space PosixSpace XPosixSpace [\s\cK] Whitespace
+ PerlSpace XPerlSpace \s Perl's whitespace def'n
+ upper PosixUpper XPosixUpper Uppercase characters
+ word PerlWord XPosixWord \w Alnum + Unicode marks +
+ connectors, like '_'
+ (Perl extension)
+ xdigit ASCII_Hex_Digit XPosixDigit Hexadecimal digit,
+ ASCII-range is
+ [0-9A-Fa-f]
+
+Also, various synonyms like C<\p{Alpha}> for C<\p{XPosixAlpha}>; all listed
+in L<perluniprops/Properties accessible through \p{} and \P{}>
Within a character class:
diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod
index 8ff5bb0..dfd6d42 100644
--- a/pod/perlunicode.pod
+++ b/pod/perlunicode.pod
@@ -1510,8 +1510,9 @@ support seamlessly. The result wasn't seamless: these
characters were
orphaned.
Work is being done to correct this, but only some of it is complete.
-What has been finished is the matching of C<\b>, C<\s>, C<\w> and their
-complements in regular expressions, and the important part of the case
+What has been finished is the matching of C<\b>, C<\s>, C<\w> and the Posix
+character classes and their complements in regular expressions, and the
+important part of the case
changing component. Due to concerns, and some evidence, that older code might
have come to rely on the existing behavior, the new behavior must be explicitly
enabled by the feature C<unicode_strings> in the L<feature> pragma, even though
diff --git a/regcomp.c b/regcomp.c
index 0d469c1..cbba23d 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -8056,32 +8056,7 @@ S_checkposixcc(pTHX_ RExC_state_t *pRExC_state)
}
}
-
-#define _C_C_T_(NAME,TEST,WORD) \
-ANYOF_##NAME: \
- if (LOC) \
- ANYOF_CLASS_SET(ret, ANYOF_##NAME); \
- else { \
- for (value = 0; value < 256; value++) \
- if (TEST) \
- ANYOF_BITMAP_SET(ret, value); \
- } \
- yesno = '+'; \
- what = WORD; \
- break; \
-case ANYOF_N##NAME: \
- if (LOC) \
- ANYOF_CLASS_SET(ret, ANYOF_N##NAME); \
- else { \
- for (value = 0; value < 256; value++) \
- if (!TEST) \
- ANYOF_BITMAP_SET(ret, value); \
- } \
- yesno = '!'; \
- what = WORD; \
- break
-
-/* Like above, but no locale test */
+/* No locale test */
#define _C_C_T_NOLOC_(NAME,TEST,WORD) \
ANYOF_##NAME: \
for (value = 0; value < 256; value++) \
@@ -8102,7 +8077,7 @@ case ANYOF_N##NAME: \
* there are two tests passed in, to use depending on that. There aren't any
* cases where the label is different from the name, so no need for that
* parameter */
-#define _C_C_T_UNI_8_BIT(NAME,TEST_8,TEST_7,WORD) \
+#define _C_C_T_(NAME,TEST_8,TEST_7,WORD) \
ANYOF_##NAME: \
if (LOC) ANYOF_CLASS_SET(ret, ANYOF_##NAME); \
else if (UNI_SEMANTICS) { \
@@ -8471,26 +8446,26 @@ parseit:
* --jhi */
switch ((I32)namedclass) {
- case _C_C_T_(ALNUMC, isALNUMC(value),
POSIX_CC_UNI_NAME("Alnum"));
- case _C_C_T_(ALPHA, isALPHA(value), POSIX_CC_UNI_NAME("Alpha"));
- case _C_C_T_(BLANK, isBLANK(value), POSIX_CC_UNI_NAME("Blank"));
- case _C_C_T_(CNTRL, isCNTRL(value), POSIX_CC_UNI_NAME("Cntrl"));
- case _C_C_T_(GRAPH, isGRAPH(value), POSIX_CC_UNI_NAME("Graph"));
- case _C_C_T_(LOWER, isLOWER(value), POSIX_CC_UNI_NAME("Lower"));
- case _C_C_T_(PRINT, isPRINT(value), POSIX_CC_UNI_NAME("Print"));
- case _C_C_T_(PSXSPC, isPSXSPC(value),
POSIX_CC_UNI_NAME("Space"));
- case _C_C_T_(PUNCT, isPUNCT(value), POSIX_CC_UNI_NAME("Punct"));
- case _C_C_T_(UPPER, isUPPER(value), POSIX_CC_UNI_NAME("Upper"));
+ case _C_C_T_(ALNUMC, isALNUMC_L1(value), isALNUMC(value),
"XPosixAlnum");
+ case _C_C_T_(ALPHA, isALPHA_L1(value), isALPHA(value),
"XPosixAlpha");
+ case _C_C_T_(BLANK, isBLANK_L1(value), isBLANK(value),
"XPosixBlank");
+ case _C_C_T_(CNTRL, isCNTRL_L1(value), isCNTRL(value),
"XPosixCntrl");
+ case _C_C_T_(GRAPH, isGRAPH_L1(value), isGRAPH(value),
"XPosixGraph");
+ case _C_C_T_(LOWER, isLOWER_L1(value), isLOWER(value),
"XPosixLower");
+ case _C_C_T_(PRINT, isPRINT_L1(value), isPRINT(value),
"XPosixPrint");
+ case _C_C_T_(PSXSPC, isPSXSPC_L1(value), isPSXSPC(value),
"XPosixSpace");
+ case _C_C_T_(PUNCT, isPUNCT_L1(value), isPUNCT(value),
"XPosixPunct");
+ case _C_C_T_(UPPER, isUPPER_L1(value), isUPPER(value),
"XPosixUpper");
#ifdef BROKEN_UNICODE_CHARCLASS_MAPPINGS
/* \s, \w match all unicode if utf8. */
- case _C_C_T_UNI_8_BIT(SPACE, isSPACE_L1(value),
isSPACE(value), "SpacePerl");
- case _C_C_T_UNI_8_BIT(ALNUM, isWORDCHAR_L1(value),
isALNUM(value), "Word");
+ case _C_C_T_(SPACE, isSPACE_L1(value), isSPACE(value),
"SpacePerl");
+ case _C_C_T_(ALNUM, isWORDCHAR_L1(value), isALNUM(value),
"Word");
#else
/* \s, \w match ascii and locale only */
- case _C_C_T_UNI_8_BIT(SPACE, isSPACE_L1(value),
isSPACE(value), "PerlSpace");
- case _C_C_T_UNI_8_BIT(ALNUM, isWORDCHAR_L1(value),
isALNUM(value), "PerlWord");
+ case _C_C_T_(SPACE, isSPACE_L1(value), isSPACE(value),
"PerlSpace");
+ case _C_C_T_(ALNUM, isWORDCHAR_L1(value), isALNUM(value),
"PerlWord");
#endif
- case _C_C_T_(XDIGIT, isXDIGIT(value), "XDigit");
+ case _C_C_T_(XDIGIT, isXDIGIT_L1(value), isXDIGIT(value),
"XPosixXDigit");
case _C_C_T_NOLOC_(VERTWS, is_VERTWS_latin1(&value),
"VertSpace");
case _C_C_T_NOLOC_(HORIZWS, is_HORIZWS_latin1(&value),
"HorizSpace");
case ANYOF_ASCII:
diff --git a/t/re/reg_posixcc.t b/t/re/reg_posixcc.t
index cd3890c..aa7f445 100644
--- a/t/re/reg_posixcc.t
+++ b/t/re/reg_posixcc.t
@@ -41,9 +41,6 @@ my @pats=(
"[:^space:]",
"[:blank:]",
"[:^blank:]" );
-if (1 or $ENV{PERL_TEST_LEGACY_POSIX_CC}) {
- $::TODO = "Only works under PERL_LEGACY_UNICODE_CHARCLASS_MAPPINGS = 0";
-}
sub rangify {
my $ary= shift;
@@ -72,6 +69,9 @@ sub rangify {
return $ret;
}
+# The bug is only fixed for /u
+use feature 'unicode_strings';
+
my $description = "";
while (@pats) {
my ($yes,$no)= splice @pats,0,2;
@@ -81,6 +81,7 @@ while (@pats) {
my %complements;
foreach my $b (0..255) {
my %got;
+ my $display_b = sprintf("\\x%02X", $b);
for my $type ('unicode','not-unicode') {
my $str=chr($b).chr($b);
if ($type eq 'unicode') {
@@ -88,10 +89,8 @@ while (@pats) {
chop $str;
}
if ($str=~/[$yes][$no]/){
- TODO: {
- unlike($str,qr/[$yes][$no]/,
- "chr($b)=~/[$yes][$no]/ should not match under $type");
- }
+ unlike($str,qr/[$yes][$no]/,
+ "chr($display_b) X 2 =~/[$yes][$no]/ should not match
under $type");
push @{$err_by_type{$type}},$b;
}
$got{"[$yes]"}{$type} = $str=~/[$yes]/ ? 1 : 0;
@@ -101,20 +100,16 @@ while (@pats) {
}
foreach my $which ("[$yes]","[$no]","[^$yes]","[^$no]") {
if ($got{$which}{'unicode'} != $got{$which}{'not-unicode'}){
- TODO: {
- is($got{$which}{'unicode'},$got{$which}{'not-unicode'},
- "chr($b)=~/$which/ should have the same results
regardless of internal string encoding");
- }
+ is($got{$which}{'unicode'},$got{$which}{'not-unicode'},
+ "chr($display_b) X 2=~ /$which/ should have the same
results regardless of internal string encoding");
push @{$singles{$which}},$b;
}
}
foreach my $which ($yes,$no) {
foreach my $strtype ('unicode','not-unicode') {
if ($got{"[$which]"}{$strtype} == $got{"[^$which]"}{$strtype})
{
- TODO: {
-
isnt($got{"[$which]"}{$strtype},$got{"[^$which]"}{$strtype},
- "chr($b)=~/[$which]/ should not have the same
result as chr($b)=~/[^$which]/");
- }
+
isnt($got{"[$which]"}{$strtype},$got{"[^$which]"}{$strtype},
+ "chr($display_b) X 2 =~ /[$which]/ should not have the
same result as chr($display_b)=~/[^$which]/");
push @{$complements{$which}{$strtype}},$b;
}
}
@@ -153,8 +148,4 @@ while (@pats) {
}
}
}
-TODO: {
- is( $description, "", "POSIX and perl charclasses should not depend on
string type");
-}
-
__DATA__
--
Perl5 Master Repository
