diff -urNp coreutils-6.12-orig/src/sort.c coreutils-6.12/src/sort.c
--- coreutils-6.12-orig/src/sort.c 2009-02-26 16:01:04.000000000 +0100
+++ coreutils-6.12/src/sort.c 2009-02-26 16:24:27.000000000 +0100
@@ -1390,7 +1390,6 @@ begfield_uni (const struct line *line, c
char *ptr = line->text, *lim = ptr + line->length - 1;
size_t sword = key->sword;
size_t schar = key->schar;
- size_t remaining_bytes;
/* The leading field separator itself is included in a field when -t
is absent. */
@@ -1416,12 +1415,7 @@ begfield_uni (const struct line *line, c
while (ptr < lim && blanks[to_uchar (*ptr)])
++ptr;
- /* Advance PTR by SCHAR (if possible), but no further than LIM. */
- remaining_bytes = lim - ptr;
- if (schar < remaining_bytes)
- ptr += schar;
- else
- ptr = lim;
+ ptr = MIN (lim, ptr + schar);
return ptr;
}
@@ -1493,7 +1487,9 @@ limfield_uni (const struct line *line, c
{
char *ptr = line->text, *lim = ptr + line->length - 1;
size_t eword = key->eword, echar = key->echar;
- size_t remaining_bytes;
+
+ if (echar == 0)
+ eword++; /* Skip all of end field. */
/* Move PTR past EWORD fields or to one past the last byte on LINE,
whichever comes first. If there are more than EWORD fields, leave
@@ -1566,19 +1566,13 @@ limfield_uni (const struct line *line, c
}
#endif
- /* If we're ignoring leading blanks when computing the End
- of the field, don't start counting bytes until after skipping
- past any leading blanks. */
- if (key->skipeblanks)
- while (ptr < lim && blanks[to_uchar (*ptr)])
- ++ptr;
-
- /* Advance PTR by ECHAR (if possible), but no further than LIM. */
- remaining_bytes = lim - ptr;
- if (echar < remaining_bytes)
- ptr += echar;
- else
- ptr = lim;
+ if (echar != 0) /* We need to skip over a portion of the end field. */
+ {
+ if (key->skipeblanks) /* blanks not counted in echar. */
+ while (ptr < lim && blanks[to_uchar (*ptr)])
+ ++ptr;
+ ptr = MIN (lim, ptr + echar);
+ }
return ptr;
}
@@ -3582,12 +3579,9 @@ main (int argc, char **argv)
badfieldspec (optarg, N_("field number is zero"));
}
if (*s == '.')
- s = parse_field_count (s + 1, &key->echar,
- N_("invalid number after `.'"));
- else
{
- /* `-k 2,3' is equivalent to `+1 -3'. */
- key->eword++;
+ s = parse_field_count (s + 1, &key->echar,
+ N_("invalid number after `.'"));
}
s = set_ordering (s, key, bl_end);
}
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
@@ -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 $mb_locale = 'C';
+
# Since each test is run with a file name and with redirected stdin,
# the name in the diagnostic is either the file name or "-".
# Normalize each diagnostic to use '-'.
@@ -108,6 +114,8 @@ my @Tests =
["07b", '-k 2,3', {IN=>"a a b\nz a a\n"}, {OUT=>"z a a\na a b\n"}],
["07c", '-k 2,3', {IN=>"y k b\nz k a\n"}, {OUT=>"z k a\ny k b\n"}],
["07d", '+1 -3', {IN=>"y k b\nz k a\n"}, {OUT=>"z k a\ny k b\n"}],
+#ensure a character position of 0 includes whole field
+["07e", '-k 2,3.0', {IN=>"a a b\nz a a\n"}, {OUT=>"z a a\na a b\n"}],
#
# report an error for `.' without following char spec
["08a", '-k 2.,3', {EXIT=>2},
@@ -208,6 +216,15 @@ my @Tests =
# key start and key end.
["18e", '-nb -k1.1,1.2', {IN=>" 901\n100\n"}, {OUT=>"100\n 901\n"}],
+# When ignoring leading blanks for end position, ensure blanks from
+# next field are not included in the sort. I.E. order should not change here.
+["18f", '-k1,1b', {IN=>"a y\na z\n"}, {OUT=>"a y\na z\n"}],
+
+# When ignoring leading blanks for start position, ensure blanks from
+# next field are not included in the sort. I.E. order should not change here.
+# This was noticed as an issue on fedora 8 (only in multibyte locales).
+["18g", '-k1b,1', {IN=>"a y\na z\n"}, {OUT=>"a y\na z\n"},
+ {ENV => "LC_ALL=$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"}],