sort: fix parsing of end field in obsolescent key formats

This regression was introduced in commit 224a69b5, 2009-02-24,
"sort: Fix two bugs with determining the end of field".
The specific regression being that we include 1 field too many when
an end field is specified using obsolescent key syntax (+POS -POS).

* src/sort.c (struct keyfield): Clarify the description of the eword
member, as suggested by Alan Curry.
(main): When processing obsolescent format key specifications,
normalize eword to a zero based count when no specific end char is given
for an end field. This matches what's done when keys are specified with -k.
* tests/misc/sort: Add a few more tests for the obsolescent key formats,
with test 07i being the particular failure addressed by this change.
* THANKS: Add Alan Curry who precisely identified the issue.
* NEWS: Mention the fix.
Reported by Santiago Rodríguez

diff --git a/NEWS b/NEWS
index 867589c..32ea392 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -14,6 +14,10 @@ GNU coreutils NEWS                                    -*- outline -*-
   handled correctly, including multi byte locales with the caveat
   that multi byte characters are matched case sensitively.
 
+  sort again handles obsolescent key formats (+POS -POS) correctly.
+  Previously if -POS was specified, 1 field too many was used in the sort.
+  [bug introduced in coreutils-7.2]
+
 ** New features
 
   join now accepts the --header option, to treat the first line of each

diff --git a/THANKS b/THANKS
index fad308a..2ea6801 100644 (file)
--- a/THANKS
+++ b/THANKS
@@ -17,6 +17,7 @@ Adrian Bunk                         bunk@stusta.de
 AIDA Shinra                         shinra@j10n.org
 Akim Demaille                       demaille@inf.enst.fr
 Alain Magloire                      alain@qnx.com
+Alan Curry                          pacman@kosh.dhis.org
 Alan Iwi                            iwi@atm.ox.ac.uk
 Albert Chin-A-Young                 china@thewrittenword.com
 Albert Hopkins                      ahopkins@dynacare.com

diff --git a/src/sort.c b/src/sort.c
index d619c60..6d47b79 100644 (file)
--- a/src/sort.c
+++ b/src/sort.c
@@ -167,7 +167,7 @@ struct keyfield
 {
   size_t sword;                        /* Zero-origin 'word' to start at. */
   size_t schar;                        /* Additional characters to skip. */
-  size_t eword;                        /* Zero-origin first word after field. */
+  size_t eword;                        /* Zero-origin last 'word' of key. */
   size_t echar;                        /* Additional characters in field. */
   bool const *ignore;          /* Boolean array of characters to ignore. */
   char const *translate;       /* Translation applied to characters. */
@@ -3389,6 +3389,16 @@ main (int argc, char **argv)
                           if (*s == '.')
                             s = parse_field_count (s + 1, &key->echar,
                                                N_("invalid number after `.'"));
+                          if (!key->echar && key->eword)
+                            {
+                              /* obsolescent syntax +A.x -B.y is equivalent to:
+                                   -k A+1.x+1,B.y   (when y = 0)
+                                   -k A+1.x+1,B+1.y (when y > 0)
+                                 So eword is decremented as in the -k case
+                                 only when the end field (B) is specified and
+                                 echar (y) is 0.  */
+                              key->eword--;
+                            }
                           if (*set_ordering (s, key, bl_end))
                             badfieldspec (optarg1,
                                       N_("stray character in field spec"));

diff --git a/tests/misc/sort b/tests/misc/sort
index e5d18d0..4ca52fe 100755 (executable)
--- a/tests/misc/sort
+++ b/tests/misc/sort
@@ -142,6 +142,12 @@ my @Tests =
 ["07f", '-n -k1.3,1.1', {IN=>"a 2\nb 1\n"}, {OUT=>"a 2\nb 1\n"}],
 ["07g", '-n -k2.2,1.2', {IN=>"aa 2\nbb 1\n"}, {OUT=>"aa 2\nbb 1\n"}],
 ["07h", '-k1.3nb,1.3', {IN=>"  a 2\n  b 1\n"}, {OUT=>"  a 2\n  b 1\n"}],
+# ensure obsolescent key limits are handled correctly
+["07i", '-s +0 -1', {IN=>"a c\na b\n"}, {OUT=>"a c\na b\n"}],
+["07j", '-s +0 -1.0', {IN=>"a c\na b\n"}, {OUT=>"a c\na b\n"}],
+["07k", '-s +0 -1.1', {IN=>"a c\na b\n"}, {OUT=>"a c\na b\n"}],
+["07l", '-s +0 -1.2', {IN=>"a c\na b\n"}, {OUT=>"a b\na c\n"}],
+["07m", '-s +0 -1.1b', {IN=>"a c\na b\n"}, {OUT=>"a b\na c\n"}],
 #
 # report an error for `.' without following char spec
 ["08a", '-k 2.,3', {EXIT=>2},