From bfff2133f5df6a92053347be42d78bdcae69327f Mon Sep 17 00:00:00 2001
From: Ondrej Vasik <ovasik@fedoraproject.org>
Date: Mon, 2 Mar 2009 12:42:55 +0000
Subject: [PATCH] fix sort bugs (including #485715) for multibyte locales

---
 coreutils-7.1-sort-endoffields.patch | 20 +++++++++++++--
 coreutils-i18n.patch                 | 38 ++++++++++++++++------------
 coreutils.spec                       |  5 +++-
 3 files changed, 44 insertions(+), 19 deletions(-)

diff --git a/coreutils-7.1-sort-endoffields.patch b/coreutils-7.1-sort-endoffields.patch
index 22e336f..190c4a1 100644
--- a/coreutils-7.1-sort-endoffields.patch
+++ b/coreutils-7.1-sort-endoffields.patch
@@ -64,7 +64,18 @@ diff -urNp coreutils-7.1-orig/src/sort.c coreutils-7.1/src/sort.c
 diff -urNp coreutils-7.1-orig/tests/misc/sort coreutils-7.1/tests/misc/sort
 --- coreutils-7.1-orig/tests/misc/sort	2009-01-27 22:11:25.000000000 +0100
 +++ coreutils-7.1/tests/misc/sort	2009-02-25 16:21:48.000000000 +0100
-@@ -110,6 +110,8 @@ 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 '-'.
+@@ -110,6 +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"}],
@@ -73,7 +84,7 @@ diff -urNp coreutils-7.1-orig/tests/misc/sort coreutils-7.1/tests/misc/sort
  #
  # report an error for `.' without following char spec
  ["08a", '-k 2.,3', {EXIT=>2},
-@@ -210,6 +212,10 @@ my @Tests =
+@@ -210,6 +216,15 @@ my @Tests =
  # key start and key end.
  ["18e", '-nb -k1.1,1.2', {IN=>" 901\n100\n"}, {OUT=>"100\n 901\n"}],
  
@@ -81,6 +92,11 @@ diff -urNp coreutils-7.1-orig/tests/misc/sort coreutils-7.1/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"}],
diff --git a/coreutils-i18n.patch b/coreutils-i18n.patch
index cd5852a..5e6facd 100644
--- a/coreutils-i18n.patch
+++ b/coreutils-i18n.patch
@@ -1938,7 +1938,7 @@ 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;
  }
  
@@ -1952,6 +1952,9 @@ diff -urNp coreutils-6.11-orig/src/join.c coreutils-6.11/src/join.c
 +  size_t mblength;
 +  mbstate_t state;
 +
++  if (echar == 0)
++    eword++; /* skip all of end field. */
++
 +  memset (&state, '\0', sizeof(mbstate_t));
 +
 +  if (tab_length)
@@ -2020,24 +2023,27 @@ 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;
 +}
diff --git a/coreutils.spec b/coreutils.spec
index bfa4a3a..24f093e 100644
--- a/coreutils.spec
+++ b/coreutils.spec
@@ -1,7 +1,7 @@
 Summary: A set of basic GNU tools commonly used in shell scripts
 Name:    coreutils
 Version: 7.1
-Release: 5%{?dist}
+Release: 6%{?dist}
 License: GPLv3+
 Group:   System Environment/Base
 Url:     http://www.gnu.org/software/coreutils/
@@ -313,6 +313,9 @@ fi
 /sbin/runuser
 
 %changelog
+* Mon Mar 02 2009 Ondrej Vasik <ovasik@redhat.com> 7.1-6
+- fix sort bugs (including #485715) for multibyte locales
+  as well
 * Fri Feb 27 2009 Ondrej Vasik <ovasik@redhat.com> 7.1-5
 - fix infinite loop in recursive cp (upstream, introduced
   by 7.1)