cut: fix NUL termination of multi-byte field delimiter

* src/cut.c (delim_bytes): Add a spare byte so a maximum-length
multi-byte delimiter stays NUL terminated for the strstr needle in
find_field_delim.  Note in 9.11 this buffer was larger (16 bytes)
and so didn't not have a buffer over-read issue.
(main): Ensure DELIM_BYTES is NUL terminated after each --delimeter.
Also explicitly writing the NUL allows for better testing by
triggering overflow issues in default builds, if the buffer
is not sized correctly.
* NEWS: Mention the bug fix.
* tests/cut/cut.pl: Add test cases.
Reported at https://github.com/coreutils/coreutils/pull/286

diff --git a/NEWS b/NEWS
index b822ae46ae32e25d722aa5ce968835940bbab98a..ac6a0d5ca191e093666fadb9eac1ee90f37671f9 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -8,6 +8,10 @@ GNU coreutils NEWS                                    -*- outline -*-
   mistakenly exit with a nonzero status.
   [This bug was present in "the beginning".]
 
+  'cut -d' with multiple multi-byte delimiter options specified
+  will correctly match the last delimiter specified.
+  [bug introduced with multi-byte support in coreutils-9.11]
+
   'head' and 'tail' now quote names in file headers when needed.
   [This bug was present in "the beginning".]
 

diff --git a/src/cut.c b/src/cut.c
index 3ec406586e563d715ccc7cd7f6d015bb2c56e7b8..83f24244dad6eacca12fdf4256cbd234593b80eb 100644 (file)
--- a/src/cut.c
+++ b/src/cut.c
@@ -89,8 +89,9 @@ static bool complement;
 /* The delimiter character for multibyte field mode.  */
 static mcel_t delim_mcel;
 
-/* The delimiter bytes.  */
-static char delim_bytes[MCEL_LEN_MAX];
+/* The delimiter bytes
+   (to be NUL terminated for strstr() optimization).  */
+static char delim_bytes[MCEL_LEN_MAX + 1];
 
 /* The delimiter for each line/record.  */
 static unsigned char line_delim = '\n';
@@ -1323,7 +1324,8 @@ main (int argc, char **argv)
             mcel_t g = delim_mcel = mcel_scanz (optarg);
             if (optarg[0] && optarg[g.len])
               FATAL_ERROR (_("the delimiter must be a single character"));
-            copy_bytes (delim_bytes, optarg, g.len);
+            /* Note NUL is copied for use with strstr.  */
+            copy_bytes (delim_bytes, optarg, g.len + 1);
             delim_specified = true;
             break;
           }

diff --git a/tests/cut/cut.pl b/tests/cut/cut.pl
index 33d6388b9b232cb86e8d2a3513788693c79c8023..6f589a9b594415ee952995a13070e3056188de2f 100755 (executable)
--- a/tests/cut/cut.pl
+++ b/tests/cut/cut.pl
@@ -360,6 +360,9 @@ if ($mb_locale ne 'C')
       ['mb-delim-10', '-s', '-d', "\xc3\xa9", '-f2',
        {IN=>"a\0b\0"}, {OUT=>""},
        {ENV => "LC_ALL=$mb_locale"}],
+      ['mb-delim-11', '-f1', '-d', "\xF0\x9F\x98\x80",  # MCEL_LEN_MAX
+       {IN=>"a\xF0\x9F\x98\x80b\n"}, {OUT=>"a\n"},
+       {ENV => "LC_ALL=$mb_locale"}],
       ['mb-w-delim-1', '-w', '-f2', {IN=>"a\xe2\x80\x83b\n"}, {OUT=>"b\n"},
        {ENV => "LC_ALL=$mb_locale"}],
       ['mb-w-delim-2', '-sw', '-f2', {IN=>"a\xc2\xa0b\n"}, {OUT=>""},
@@ -438,6 +441,11 @@ if ($mb_locale ne 'C')
       # -F in multi-byte locale
       ['mb-F-1', '-F', '2', {IN=>"\xc3\xa9\t\xc3\xbc\n"},
        {OUT=>"\xc3\xbc\n"},
+       {ENV => "LC_ALL=$mb_locale"}],
+
+      # In coreutils-9.11 this corrupted the delimiter "string"
+      ['mb-mismatch', '-f1', '-d', "\xF0\x9F\x98\x80", '-d', "\xEF\xBC\x8C",
+       {IN=>"a\xEF\xBC\x8Cb\n"}, {OUT=>"a\n"},
        {ENV => "LC_ALL=$mb_locale"}];
   }