cut: do not print extraneous delimiters in some unusual cases

When printing output delimiters, and when a to-EOL range subsumes
at least one other range, cut would mistakenly print delimiters for
the subsumed range.  This bug was probably introduced via commit
v5.2.1-639-g847e066.
* src/cut.c (set_fields): Ignore any range that is subsumed by a
to-EOL range.  Also, move two declarations down.
* tests/misc/cut.pl: Add tests to exercise this.
* NEWS (Bug fixes): Mention it.
Reported by Marcel Böhme in http://bugs.gnu.org/12966

diff --git a/NEWS b/NEWS
index 63583c1..d4aebeb 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -18,6 +18,10 @@ GNU coreutils NEWS                                    -*- outline -*-
   interpret "-b2-,3-" like "-b3-".  Now it's treated like "-b2-".
   [This bug was present in "the beginning".]
 
+  cut no longer prints extraneous delimiters when a to-EOL range subsumes
+  another range.  Before, "echo 123|cut --output-delim=: -b2-,3" would print
+  "2:3".  Now it prints "23".  [bug introduced in 5.3.0]
+
   install -m M SOURCE DEST no longer has a race condition where DEST's
   permissions are temporarily derived from SOURCE instead of from M.
 

diff --git a/src/cut.c b/src/cut.c
index b464840..4219d24 100644 (file)
--- a/src/cut.c
+++ b/src/cut.c
@@ -514,17 +514,18 @@ set_fields (const char *fieldstr)
   /* Set the array entries corresponding to integers in the ranges of RP.  */
   for (i = 0; i < n_rp; i++)
     {
-      size_t j;
-      size_t rsi_candidate;
+      /* Ignore any range that is subsumed by the to-EOL range.  */
+      if (eol_range_start && eol_range_start <= rp[i].lo)
+        continue;
 
       /* Record the range-start indices, i.e., record each start
          index that is not part of any other (lo..hi] range.  */
-      rsi_candidate = complement ? rp[i].hi + 1 : rp[i].lo;
+      size_t rsi_candidate = complement ? rp[i].hi + 1 : rp[i].lo;
       if (output_delimiter_specified
           && !is_printable_field (rsi_candidate))
         mark_range_start (rsi_candidate);
 
-      for (j = rp[i].lo; j <= rp[i].hi; j++)
+      for (size_t j = rp[i].lo; j <= rp[i].hi; j++)
         mark_printable_field (j);
     }
 

diff --git a/tests/misc/cut.pl b/tests/misc/cut.pl
index cb4781a..27768ff 100755 (executable)
--- a/tests/misc/cut.pl
+++ b/tests/misc/cut.pl
@@ -166,6 +166,15 @@ my @Tests =
 
   ['overlapping-unbounded-1', '-b3-,2-', {IN=>"1234\n"}, {OUT=>"234\n"}],
   ['overlapping-unbounded-2', '-b2-,3-', {IN=>"1234\n"}, {OUT=>"234\n"}],
+
+  # When printing output delimiters, and with one or more ranges subsumed
+  # by a to-EOL range, cut 8.20 and earlier would print extraneous delimiters.
+  ['EOL-subsumed-1', '--output-d=: -b2-,3,4-4,5',
+                                         {IN=>"123456\n"}, {OUT=>"23456\n"}],
+  ['EOL-subsumed-2', '--output-d=: -b3,4-4,5,2-',
+                                         {IN=>"123456\n"}, {OUT=>"23456\n"}],
+  ['EOL-subsumed-3', '--complement -b3,4-4,5,2-',
+                                         {IN=>"123456\n"}, {OUT=>"1\n"}],
  );
 
 if ($mb_locale ne 'C')