fix sort bugs (including #485715) for multibyte locales
This commit is contained in:
Ondrej Vasik
parent
9a1c0e2727
commit
85ca01a1d9
3 changed files with 45 additions and 19 deletions
|
|
@ -79,7 +79,18 @@ diff -urNp coreutils-6.12-orig/src/sort.c coreutils-6.12/src/sort.c
|
|||
diff -urNp coreutils-6.12-orig/tests/misc/sort coreutils-6.12/tests/misc/sort
|
||||
--- coreutils-6.12-orig/tests/misc/sort 2008-05-17 08:41:12.000000000 +0200
|
||||
+++ coreutils-6.12/tests/misc/sort 2009-02-26 16:25:39.000000000 +0100
|
||||
@@ -108,6 +108,8 @@ my @Tests =
|
||||
@@ -24,6 +24,10 @@ my $prog = 'sort';
|
||||
# Turn off localization of executable's output.
|
||||
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
|
||||
|
||||
+my $mb_locale = $ENV{LOCALE_FR_UTF8};
|
||||
+! defined $mb_locale || $mb_locale eq 'none'
|
||||
+ and $mb_locale = 'C';
|
||||
+
|
||||
# Since each test is run with a file name and with redirected stdin,
|
||||
# the name in the diagnostic is either the file name or "-".
|
||||
# Normalize each diagnostic to use '-'.
|
||||
@@ -108,6 +114,8 @@ my @Tests =
|
||||
["07b", '-k 2,3', {IN=>"a a b\nz a a\n"}, {OUT=>"z a a\na a b\n"}],
|
||||
["07c", '-k 2,3', {IN=>"y k b\nz k a\n"}, {OUT=>"z k a\ny k b\n"}],
|
||||
["07d", '+1 -3', {IN=>"y k b\nz k a\n"}, {OUT=>"z k a\ny k b\n"}],
|
||||
|
|
@ -88,7 +99,7 @@ diff -urNp coreutils-6.12-orig/tests/misc/sort coreutils-6.12/tests/misc/sort
|
|||
#
|
||||
# report an error for `.' without following char spec
|
||||
["08a", '-k 2.,3', {EXIT=>2},
|
||||
@@ -208,6 +210,10 @@ my @Tests =
|
||||
@@ -208,6 +216,15 @@ my @Tests =
|
||||
# key start and key end.
|
||||
["18e", '-nb -k1.1,1.2', {IN=>" 901\n100\n"}, {OUT=>"100\n 901\n"}],
|
||||
|
||||
|
|
@ -96,6 +107,11 @@ diff -urNp coreutils-6.12-orig/tests/misc/sort coreutils-6.12/tests/misc/sort
|
|||
+# next field are not included in the sort. I.E. order should not change here.
|
||||
+["18f", '-k1,1b', {IN=>"a y\na z\n"}, {OUT=>"a y\na z\n"}],
|
||||
+
|
||||
+# When ignoring leading blanks for start position, ensure blanks from
|
||||
+# next field are not included in the sort. I.E. order should not change here.
|
||||
+# This was noticed as an issue on fedora 8 (only in multibyte locales).
|
||||
+["18g", '-k1b,1', {IN=>"a y\na z\n"}, {OUT=>"a y\na z\n"},
|
||||
+ {ENV => "LC_ALL=$mb_locale"}],
|
||||
# This looks odd, but works properly -- 2nd keyspec is never
|
||||
# used because all lines are different.
|
||||
["19a", '+0 +1nr', {IN=>"b 2\nb 1\nb 3\n"}, {OUT=>"b 1\nb 2\nb 3\n"}],
|
||||
|
|
|
|||
|
|
@ -1919,7 +1919,7 @@ diff -urNp coreutils-6.11-orig/src/join.c coreutils-6.11/src/join.c
|
|||
if (newlim)
|
||||
lim = newlim;
|
||||
}
|
||||
@@ -1384,6 +1570,107 @@
|
||||
@@ -1384,6 +1570,113 @@
|
||||
return ptr;
|
||||
}
|
||||
|
||||
|
|
@ -1931,7 +1931,10 @@ diff -urNp coreutils-6.11-orig/src/join.c coreutils-6.11/src/join.c
|
|||
+ size_t eword = key->eword, echar = key->echar;
|
||||
+ int i;
|
||||
+ size_t mblength;
|
||||
+
|
||||
+ mbstate_t state;
|
||||
+ if (echar == 0)
|
||||
+ eword++; /* skip all of end field. */
|
||||
+
|
||||
+ memset (&state, '\0', sizeof(mbstate_t));
|
||||
+
|
||||
|
|
@ -2001,24 +2004,27 @@ diff -urNp coreutils-6.11-orig/src/join.c coreutils-6.11/src/join.c
|
|||
+ }
|
||||
+# endif
|
||||
+
|
||||
+ /* If we're skipping leading blanks, don't start counting characters
|
||||
+ * until after skipping past any leading blanks. */
|
||||
+ if (key->skipsblanks)
|
||||
+ while (ptr < lim && ismbblank (ptr, lim - ptr, &mblength))
|
||||
+ ptr += mblength;
|
||||
+ if (echar != 0)
|
||||
+ {
|
||||
+ /* If we're skipping leading blanks, don't start counting characters
|
||||
+ * until after skipping past any leading blanks. */
|
||||
+ if (key->skipsblanks)
|
||||
+ while (ptr < lim && ismbblank (ptr, lim - ptr, &mblength))
|
||||
+ ptr += mblength;
|
||||
+
|
||||
+ memset (&state, '\0', sizeof(mbstate_t));
|
||||
+ memset (&state, '\0', sizeof(mbstate_t));
|
||||
+
|
||||
+ /* Advance PTR by ECHAR (if possible), but no further than LIM. */
|
||||
+ for (i = 0; i < echar; i++)
|
||||
+ {
|
||||
+ GET_BYTELEN_OF_CHAR (lim, ptr, mblength, state);
|
||||
+ /* Advance PTR by ECHAR (if possible), but no further than LIM. */
|
||||
+ for (i = 0; i < echar; i++)
|
||||
+ {
|
||||
+ GET_BYTELEN_OF_CHAR (lim, ptr, mblength, state);
|
||||
+
|
||||
+ if (ptr + mblength > lim)
|
||||
+ break;
|
||||
+ else
|
||||
+ ptr += mblength;
|
||||
+ }
|
||||
+ if (ptr + mblength > lim)
|
||||
+ break;
|
||||
+ else
|
||||
+ ptr += mblength;
|
||||
+ }
|
||||
+ }
|
||||
+
|
||||
+ return ptr;
|
||||
+}
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
Summary: The GNU core utilities: a set of tools commonly used in shell scripts
|
||||
Name: coreutils
|
||||
Version: 6.12
|
||||
Release: 19%{?dist}
|
||||
Release: 20%{?dist}
|
||||
License: GPLv3+
|
||||
Group: System Environment/Base
|
||||
Url: http://www.gnu.org/software/coreutils/
|
||||
|
|
@ -342,6 +342,10 @@ fi
|
|||
/sbin/runuser
|
||||
|
||||
%changelog
|
||||
* Mon Mar 02 2009 Ondrej Vasik <ovasik@redhat.com> - 6.12-20
|
||||
- fix sort bugs (including #485715) for multibyte locales
|
||||
as well
|
||||
|
||||
* Thu Feb 26 2009 Ondrej Vasik <ovasik@redhat.com> - 6.12-19
|
||||
- fix showing ACL's for ls -Z (#487374), fix automatic
|
||||
column width for it as well
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue