fsck: check ident lines in commit objects

Check that email addresses do not contain <, >, or newline so they can
be quickly scanned without trouble.  The copy() function in ident.c
already ensures that ordinary git commands will not write email
addresses without this property.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/fsck.c b/fsck.c
index 89278c1459d36a3e2b718661ca71483522f587fd..ae9ae1abee8e406e838fc32802aeb2c50ba4ca7d 100644 (file)
--- a/fsck.c
+++ b/fsck.c
@@ -222,12 +222,47 @@ static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
        return retval;
 }
 
+static int fsck_ident(char **ident, struct object *obj, fsck_error error_func)
+{
+       if (**ident == '<' || **ident == '\n')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
+       *ident += strcspn(*ident, "<\n");
+       if ((*ident)[-1] != ' ')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
+       if (**ident != '<')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing email");
+       (*ident)++;
+       *ident += strcspn(*ident, "<>\n");
+       if (**ident != '>')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad email");
+       (*ident)++;
+       if (**ident != ' ')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before date");
+       (*ident)++;
+       if (**ident == '0' && (*ident)[1] != ' ')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - zero-padded date");
+       *ident += strspn(*ident, "0123456789");
+       if (**ident != ' ')
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad date");
+       (*ident)++;
+       if ((**ident != '+' && **ident != '-') ||
+           !isdigit((*ident)[1]) ||
+           !isdigit((*ident)[2]) ||
+           !isdigit((*ident)[3]) ||
+           !isdigit((*ident)[4]) ||
+           ((*ident)[5] != '\n'))
+               return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad time zone");
+       (*ident) += 6;
+       return 0;
+}
+
 static int fsck_commit(struct commit *commit, fsck_error error_func)
 {
        char *buffer = commit->buffer;
        unsigned char tree_sha1[20], sha1[20];
        struct commit_graft *graft;
        int parents = 0;
+       int err;
 
        if (commit->date == ULONG_MAX)
                return error_func(&commit->object, FSCK_ERROR, "invalid author/committer line");
@@ -266,6 +301,18 @@ static int fsck_commit(struct commit *commit, fsck_error error_func)
        }
        if (memcmp(buffer, "author ", 7))
                return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'author' line");
+       buffer += 7;
+       err = fsck_ident(&buffer, &commit->object, error_func);
+       if (err)
+               return err;
+       if (memcmp(buffer, "committer ", strlen("committer ")))
+               return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'committer' line");
+       buffer += strlen("committer ");
+       err = fsck_ident(&buffer, &commit->object, error_func);
+       if (err)
+               return err;
+       if (*buffer != '\n')
+               return error_func(&commit->object, FSCK_ERROR, "invalid format - expected blank line");
        if (!commit->tree)
                return error_func(&commit->object, FSCK_ERROR, "could not load commit's tree %s", sha1_to_hex(tree_sha1));
 

diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh
index 49cae3ed524d70ae39114b35a95e7070f1a4e575..22a80c8268b368963d58fd26fffde5cc8d084ee6 100755 (executable)
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@@ -57,6 +57,34 @@ test_expect_success 'branch pointing to non-commit' '
        git update-ref -d refs/heads/invalid
 '
 
+new=nothing
+test_expect_success 'email without @ is okay' '
+       git cat-file commit HEAD >basis &&
+       sed "s/@/AT/" basis >okay &&
+       new=$(git hash-object -t commit -w --stdin <okay) &&
+       echo "$new" &&
+       git update-ref refs/heads/bogus "$new" &&
+       git fsck 2>out &&
+       cat out &&
+       ! grep "error in commit $new" out
+'
+git update-ref -d refs/heads/bogus
+rm -f ".git/objects/$new"
+
+new=nothing
+test_expect_success 'email with embedded > is not okay' '
+       git cat-file commit HEAD >basis &&
+       sed "s/@[a-z]/&>/" basis >bad-email &&
+       new=$(git hash-object -t commit -w --stdin <bad-email) &&
+       echo "$new" &&
+       git update-ref refs/heads/bogus "$new" &&
+       git fsck 2>out &&
+       cat out &&
+       grep "error in commit $new" out
+'
+git update-ref -d refs/heads/bogus
+rm -f ".git/objects/$new"
+
 cat > invalid-tag <<EOF
 object ffffffffffffffffffffffffffffffffffffffff
 type commit