fold: fix handling of invalid multi-byte characters

* src/fold.c (fold_file): Continue the loop when we have buffered bytes
but nothing left to read from the file.
(adjust_column): Don't assume that the character is printable.
* tests/fold/fold-characters.sh: Add a new test case.
(bad_unicode): New function.

diff --git a/src/fold.c b/src/fold.c
index 343ee62c30c89e7a21ae0f2552cd4ea999ab78ed..5f71d5c5530c938e483530ec92847fd2b8fd5106 100644 (file)
--- a/src/fold.c
+++ b/src/fold.c
@@ -115,10 +115,16 @@ adjust_column (size_t column, mcel_t g)
         column = 0;
       else if (g.ch == '\t')
         column += TAB_WIDTH - column % TAB_WIDTH;
-      else /* if (c32isprint (g.ch)) */
+      else
         {
-          last_character_width = (counting_mode == COUNT_CHARACTERS
-                                  ? 1 : c32width (g.ch));
+          if (counting_mode == COUNT_CHARACTERS)
+            last_character_width = 1;
+          else
+            {
+              int width = c32width (g.ch);
+              /* Default to a width of 1 if there is an invalid character.  */
+              last_character_width = width < 0 ? 1 : width;
+            }
           column += last_character_width;
         }
     }
@@ -160,7 +166,8 @@ fold_file (char const *filename, size_t width)
   fadvise (istream, FADVISE_SEQUENTIAL);
 
   while (0 < (length_in = fread (line_in + offset_in, 1,
-                                 sizeof line_in - offset_in, istream)))
+                                 sizeof line_in - offset_in, istream))
+         || 0 < offset_in)
     {
       char *p = line_in;
       char *lim = p + length_in + offset_in;
@@ -172,7 +179,7 @@ fold_file (char const *filename, size_t width)
             {
               /* Replace the character with the byte if it cannot be a
                  truncated multibyte sequence.  */
-              if (!(lim - p <= MCEL_LEN_MAX))
+              if (!(lim - p <= MCEL_LEN_MAX) || length_in == 0)
                 g.ch = p[0];
               else
                 {

diff --git a/tests/fold/fold-characters.sh b/tests/fold/fold-characters.sh
index 7de718450cbae139622866cbbfe9cd4eb622e5f1..c29b4bdd6ddda0f1ceff2f72770b17a8e54cd447 100755 (executable)
--- a/tests/fold/fold-characters.sh
+++ b/tests/fold/fold-characters.sh
@@ -80,6 +80,17 @@ env printf '\naaaa\n' >> exp3 || framework_failure_
 fold --characters input3 | tail -n 4 > out3 || fail=1
 compare exp3 out3 || fail=1
 
+# Sequence derived from <https://datatracker.ietf.org/doc/rfc9839>.
+bad_unicode ()
+{
+  # invalid UTF8|unpaired surrogate|NUL|C1 control|noncharacter
+  env printf '\xC3|\xED\xBA\xAD|\u0000|\u0089|\xED\xA6\xBF\xED\xBF\xBF\n'
+}
+bad_unicode > /dev/null || framework_failure_
+test $({ bad_unicode | fold; bad_unicode; } | uniq | wc -l) = 1 || fail=1
+# Check bad character at EOF
+test $(env printf '\xC3' | fold | wc -c) = 1 || fail=1
+
 # Ensure bounded memory operation
 vm=$(get_min_ulimit_v_ fold /dev/null) && {
   yes | tr -d '\n' | (ulimit -v $(($vm+8000)) && fold 2>err) | head || fail=1