commit: reject invalid UTF-8 codepoints

The commit code already contains code for validating UTF-8, but it does not
check for invalid values, such as guaranteed non-characters and surrogates.  Fix
this by explicitly checking for and rejecting such characters.

Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/commit.c b/commit.c
index 888e02ae2f65ab566555465e5d88d02bbe52420f..b140af7e449c0dfce54733bd66747a7e7acc784a 100644 (file)
--- a/commit.c
+++ b/commit.c
@@ -1244,6 +1244,7 @@ static int find_invalid_utf8(const char *buf, int len)
        while (len) {
                unsigned char c = *buf++;
                int bytes, bad_offset;
        while (len) {
                unsigned char c = *buf++;
                int bytes, bad_offset;

+               unsigned int codepoint;

 
                len--;
                offset++;
 
                len--;
                offset++;


@@ -1264,24 +1265,40 @@ static int find_invalid_utf8(const char *buf, int len)
                        bytes++;
                }
 
                        bytes++;
                }
 

-               /* Must be between 1 and 5 more bytes */
-               if (bytes < 1 || bytes > 5)
+               /*
+                * Must be between 1 and 3 more bytes.  Longer sequences result in
+                * codepoints beyond U+10FFFF, which are guaranteed never to exist.
+                */
+               if (bytes < 1 || 3 < bytes)

                        return bad_offset;
 
                /* Do we *have* that many bytes? */
                if (len < bytes)
                        return bad_offset;
 
                        return bad_offset;
 
                /* Do we *have* that many bytes? */
                if (len < bytes)
                        return bad_offset;
 

+               /* Place the encoded bits at the bottom of the value. */
+               codepoint = (c & 0x7f) >> bytes;
+

                offset += bytes;
                len -= bytes;
 
                /* And verify that they are good continuation bytes */
                do {
                offset += bytes;
                len -= bytes;
 
                /* And verify that they are good continuation bytes */
                do {

+                       codepoint <<= 6;
+                       codepoint |= *buf & 0x3f;

                        if ((*buf++ & 0xc0) != 0x80)
                                return bad_offset;
                } while (--bytes);
 
                        if ((*buf++ & 0xc0) != 0x80)
                                return bad_offset;
                } while (--bytes);
 

-               /* We could/should check the value and length here too */
+               /* No codepoints can ever be allocated beyond U+10FFFF. */
+               if (codepoint > 0x10ffff)
+                       return bad_offset;
+               /* Surrogates are only for UTF-16 and cannot be encoded in UTF-8. */
+               if ((codepoint & 0x1ff800) == 0xd800)
+                       return bad_offset;
+               /* U+FFFE and U+FFFF are guaranteed non-characters. */
+               if ((codepoint & 0x1ffffe) == 0xfffe)
+                       return bad_offset;

        }
        return -1;
 }
        }
        return -1;
 }


@@ -1292,8 +1309,8 @@ static int find_invalid_utf8(const char *buf, int len)
  * If it isn't, it assumes any non-utf8 characters are Latin1,
  * and does the conversion.
  *
  * If it isn't, it assumes any non-utf8 characters are Latin1,
  * and does the conversion.
  *

- * Fixme: we should probably also disallow overlong forms and
- * invalid characters. But we don't do that currently.
+ * Fixme: we should probably also disallow overlong forms.
+ * But we don't do that currently.

  */
 static int verify_utf8(struct strbuf *buf)
 {
  */
 static int verify_utf8(struct strbuf *buf)
 {

diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh
index 37ddabba2d60956a4d8da63585bec5a622e12a5d..687669f28d930cb217f54b6f207f41a1835e17b7 100755 (executable)
--- a/t/t3900-i18n-commit.sh
+++ b/t/t3900-i18n-commit.sh
@@ -39,6 +39,14 @@ test_expect_failure 'UTF-16 refused because of NULs' '
        git commit -a -F "$TEST_DIRECTORY"/t3900/UTF-16.txt
 '
 
        git commit -a -F "$TEST_DIRECTORY"/t3900/UTF-16.txt
 '
 

+test_expect_success 'UTF-8 invalid characters refused' '
+       test_when_finished "rm -f $HOME/stderr $HOME/invalid" &&
+       echo "UTF-8 characters" >F &&
+       printf "Commit message\n\nInvalid surrogate:\355\240\200\n" \
+               >"$HOME/invalid" &&
+       git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr &&
+       grep "did not conform" "$HOME"/stderr
+'

 
 for H in ISO8859-1 eucJP ISO-2022-JP
 do
 
 for H in ISO8859-1 eucJP ISO-2022-JP
 do