basenc: ensure partial padding with newlines induces an error

* src/basenc.c (has_padding): A more robust helper to
identify padding in the presence of trailing newlines.
(do_decode): Use has_padding() rather than just looking
at the last character.
* tests/basenc/base64.pl: Fully test commit v9.4-53-g378dc38f4
by ensuring partially padded data is diagnosed.
baddecode9 is the case fixed in this commit.
* NEWS: Mention the bug fix.

diff --git a/NEWS b/NEWS
index db9076c3423dc4644f7fcc4c48108f5d86cbf589..283d8046d527b396846f21c717a2b98bced63ce8 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -8,6 +8,10 @@ GNU coreutils NEWS                                    -*- outline -*-
   Previously it would have silently assumed 512 for any larger values.
   [bug introduced in coreutils-9.6]
 
+  'base32' and 'base64' when decoding will again diagnose partially
+  padded data that ends with a newline.
+  [bug introduced in coreutils-9.5]
+
   'basenc -d -i' will now strip '=' characters from the input
   in encodings where padding characters are not valid.
   [bug introduced with the basenc program in coreutils-8.31]

diff --git a/src/basenc.c b/src/basenc.c
index 84789e2de913ea83500b9d58c9ad1e89191fe59d..090404ee4b5026b016cadbd0294cf801c5285324 100644 (file)
--- a/src/basenc.c
+++ b/src/basenc.c
@@ -1446,6 +1446,22 @@ do_encode (FILE *in, char const *infile, FILE *out, idx_t wrap_column)
   finish_and_exit (in, infile);
 }
 
+/* Returns TRUE if BUF of length LEN
+   ends with a '=' character.
+   Trailing '\n' characters are ignored.  */
+ATTRIBUTE_PURE
+static bool
+has_padding (char const *buf, size_t len)
+{
+  while (len--)
+    {
+      if (buf[len] == '\n')
+        continue;
+      return buf[len] == '=';
+    }
+  return false;
+}
+
 static _Noreturn void
 do_decode (FILE *in, char const *infile, FILE *out, bool ignore_garbage)
 {
@@ -1504,7 +1520,7 @@ do_decode (FILE *in, char const *infile, FILE *out, bool ignore_garbage)
 
               /* auto pad input (at eof).  */
               idx_t auto_padding = REQUIRED_PADDING (ctx.i);
-              if (auto_padding && (sum == 0 || inbuf[sum - 1] != '='))
+              if (auto_padding && ! has_padding (inbuf, sum))
                 {
                   affirm (auto_padding <= sizeof (padbuf));
                   IF_LINT (free (inbuf));

diff --git a/tests/basenc/base64.pl b/tests/basenc/base64.pl
index 0aabc7b01b595e6a265178935e315f00674e52bf..9ba24cf47b6625169b81e04cbf28942a836d4cab 100755 (executable)
--- a/tests/basenc/base64.pl
+++ b/tests/basenc/base64.pl
@@ -122,10 +122,12 @@ sub gen_tests($)
   if ($prog eq "base64")
     {
         push @Tests, (
+          ['paddec1', '--decode', {IN=>'aQ'}, {OUT=>"i"}],
+          ['paddec2', '--decode', {IN=>'Zzw'}, {OUT=>"g<"}],
+          ['paddec3', '--decode', {IN=>'MTIzNA==MTIzNA'}, {OUT=>"12341234"}],
+          ['paddec4', '--decode', {IN=>"MTIzNA==\nMTIzNA"}, {OUT=>"12341234"}],
           ['baddecode', '--decode', {IN=>'a'}, {OUT=>""},
           {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}],
-          ['paddecode2', '--decode', {IN=>'aQ'}, {OUT=>"i"}],
-          ['paddecode3', '--decode', {IN=>'Zzw'}, {OUT=>"g<"}],
           ['baddecode4', '--decode', {IN=>'Zz='}, {OUT=>"g"},
           {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}],
           ['baddecode5', '--decode', {IN=>'Z==='}, {OUT=>""},
@@ -133,6 +135,10 @@ sub gen_tests($)
           ['baddecode6', '--decode', {IN=>'SB=='}, {OUT=>"H"},
           {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}],
           ['baddecode7', '--decode', {IN=>'SGVsbG9='}, {OUT=>"Hello"},
+          {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}],
+          ['baddecode8', '--decode', {IN=>'MTIzNA='}, {OUT=>"1234"},
+          {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}],
+          ['baddecode9', '--decode', {IN=>"MTIzNA=\n"}, {OUT=>"1234"},
           {ERR_SUBST => 's/.*: invalid input//'}, {ERR => "\n"}, {EXIT => 1}]
         );
     }