Merge branch 'di/fast-import-ident'

* di/fast-import-ident: fsck: improve committer/author check fsck: add a few committer name tests fast-import: check committer name more strictly fast-import: don't fail on omitted committer name fast-import: add input format tests
2024-08-27 03:29:21 +00:00 · 2011-08-28 21:18:47 -07:00 · 2011-08-28 21:18:47 -07:00 · 0b98954975
parent d39753c238 53f53cff24
commit 0b98954975
5 changed files with 164 additions and 18 deletions
--- a/Documentation/git-fast-import.txt
+++ b/Documentation/git-fast-import.txt
@ -425,8 +425,8 @@ Here `<name>` is the person's display name (for example
 (``cm@example.com'').  `LT` and `GT` are the literal less-than (\x3c)
 and greater-than (\x3e) symbols.  These are required to delimit
 the email address from the other fields in the line.  Note that
-`<name>` is free-form and may contain any sequence of bytes, except
-`LT` and `LF`.  It is typically UTF-8 encoded.
+`<name>` and `<email>` are free-form and may contain any sequence
+of bytes, except `LT`, `GT` and `LF`.  `<name>` is typically UTF-8 encoded.

 The time of the change is specified by `<when>` using the date format
 that was selected by the \--date-format=<fmt> command line option.
--- a/fast-import.c
+++ b/fast-import.c
@ -1969,32 +1969,41 @@ static int validate_raw_date(const char *src, char *result, int maxlen)

 static char *parse_ident(const char *buf)
 {
-	const char *gt;
+	const char *ltgt;
 	size_t name_len;
 	char *ident;

-	gt = strrchr(buf, '>');
-	if (!gt)
+	/* ensure there is a space delimiter even if there is no name */
+	if (*buf == '<')
+		--buf;
+
+	ltgt = buf + strcspn(buf, "<>");
+	if (*ltgt != '<')
+		die("Missing < in ident string: %s", buf);
+	if (ltgt != buf && ltgt[-1] != ' ')
+		die("Missing space before < in ident string: %s", buf);
+	ltgt = ltgt + 1 + strcspn(ltgt + 1, "<>");
+	if (*ltgt != '>')
 		die("Missing > in ident string: %s", buf);
-	gt++;
-	if (*gt != ' ')
+	ltgt++;
+	if (*ltgt != ' ')
 		die("Missing space after > in ident string: %s", buf);
-	gt++;
-	name_len = gt - buf;
+	ltgt++;
+	name_len = ltgt - buf;
 	ident = xmalloc(name_len + 24);
 	strncpy(ident, buf, name_len);

 	switch (whenspec) {
 	case WHENSPEC_RAW:
-		if (validate_raw_date(gt, ident + name_len, 24) < 0)
-			die("Invalid raw date \"%s\" in ident: %s", gt, buf);
+		if (validate_raw_date(ltgt, ident + name_len, 24) < 0)
+			die("Invalid raw date \"%s\" in ident: %s", ltgt, buf);
 		break;
 	case WHENSPEC_RFC2822:
-		if (parse_date(gt, ident + name_len, 24) < 0)
-			die("Invalid rfc2822 date \"%s\" in ident: %s", gt, buf);
+		if (parse_date(ltgt, ident + name_len, 24) < 0)
+			die("Invalid rfc2822 date \"%s\" in ident: %s", ltgt, buf);
 		break;
 	case WHENSPEC_NOW:
-		if (strcmp("now", gt))
+		if (strcmp("now", ltgt))
 			die("Date in ident must be 'now': %s", buf);
 		datestamp(ident + name_len, 24);
 		break;
--- a/fsck.c
+++ b/fsck.c
@ -224,13 +224,15 @@ static int fsck_tree(struct tree *item, int strict, fsck_error error_func)

 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] != ' ')
+	if (**ident == '<')
 		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
+	*ident += strcspn(*ident, "<>\n");
+	if (**ident == '>')
+		return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad name");
 	if (**ident != '<')
 		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing email");
+	if ((*ident)[-1] != ' ')
+		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
 	(*ident)++;
 	*ident += strcspn(*ident, "<>\n");
 	if (**ident != '>')
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@ -110,6 +110,42 @@ test_expect_success 'email with embedded > is not okay' '
 	grep "error in commit $new" out
 '

+test_expect_success 'missing < email delimiter is reported nicely' '
+	git cat-file commit HEAD >basis &&
+	sed "s/<//" basis >bad-email-2 &&
+	new=$(git hash-object -t commit -w --stdin <bad-email-2) &&
+	test_when_finished "remove_object $new" &&
+	git update-ref refs/heads/bogus "$new" &&
+	test_when_finished "git update-ref -d refs/heads/bogus" &&
+	git fsck 2>out &&
+	cat out &&
+	grep "error in commit $new.* - bad name" out
+'
+
+test_expect_success 'missing email is reported nicely' '
+	git cat-file commit HEAD >basis &&
+	sed "s/[a-z]* <[^>]*>//" basis >bad-email-3 &&
+	new=$(git hash-object -t commit -w --stdin <bad-email-3) &&
+	test_when_finished "remove_object $new" &&
+	git update-ref refs/heads/bogus "$new" &&
+	test_when_finished "git update-ref -d refs/heads/bogus" &&
+	git fsck 2>out &&
+	cat out &&
+	grep "error in commit $new.* - missing email" out
+'
+
+test_expect_success '> in name is reported' '
+	git cat-file commit HEAD >basis &&
+	sed "s/ </> </" basis >bad-email-4 &&
+	new=$(git hash-object -t commit -w --stdin <bad-email-4) &&
+	test_when_finished "remove_object $new" &&
+	git update-ref refs/heads/bogus "$new" &&
+	test_when_finished "git update-ref -d refs/heads/bogus" &&
+	git fsck 2>out &&
+	cat out &&
+	grep "error in commit $new" out
+'
+
 test_expect_success 'tag pointing to nonexistent' '
 	cat >invalid-tag <<-\EOF &&
 	object ffffffffffffffffffffffffffffffffffffffff
--- a/t/t9300-fast-import.sh
+++ b/t/t9300-fast-import.sh
@ -324,6 +324,105 @@ test_expect_success \
 	 test `git rev-parse master` = `git rev-parse TEMP_TAG^`'
 rm -f .git/TEMP_TAG

+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/empty-committer-1
+committer  <> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: accept empty committer' '
+	git fast-import <input &&
+	out=$(git fsck) &&
+	echo "$out" &&
+	test -z "$out"
+'
+git update-ref -d refs/heads/empty-committer-1 || true
+
+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/empty-committer-2
+committer <a@b.com> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: accept and fixup committer with no name' '
+	git fast-import <input &&
+	out=$(git fsck) &&
+	echo "$out" &&
+	test -z "$out"
+'
+git update-ref -d refs/heads/empty-committer-2 || true
+
+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name email> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (1)' '
+	test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <e<mail> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (2)' '
+	test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <email>> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (3)' '
+	test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <email $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (4)' '
+	test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name<email> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (5)' '
+	test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
 ###
 ### series C
 ###