[PATCHv2] pathspec: allow escaped query values

From: Stefan Beller <sbeller@google.com>
Date: Jun 2, 2016, 21:30 UTC
Message-ID: <20160602213015.21712-1-sbeller@google.com>

In our own .gitattributes file we have attributes such as:

    *.[ch] whitespace=indent,trail,space

When querying for attributes we want to be able to ask for the exact value, i.e.

    git ls-files :(attr:whitespace=indent,trail,space)

should work, but the commas are used in the attr magic to introduce the next attr, such that this query currently fails with

fatal: Invalid pathspec magic 'trail' in ':(attr:whitespace=indent,trail,space)'

This change allows escaping characters by a backslash, such that the query

    git ls-files :(attr:whitespace=indent\,trail\,space)

will match all path that have the value "indent,trail,space" for the whitespace attribute. To accomplish this, we need to modify two places. First `eat_long_magic` needs to not stop early upon seeing a comma or closing paren that is escaped. As a second step we need to remove any escaping from the attr value.

Signed-off-by: Stefan Beller <sbeller@google.com>
---

So here is the "escaping only, but escaping done right" version. (It goes on top of sb/pathspec-label)

Thanks, Stefan

 pathspec.c                      | 44 +++++++++++++++++++++++++++++++++++++----
 t/t6134-pathspec-with-labels.sh | 23 +++++++++++++++++++++
 2 files changed, 63 insertions(+), 4 deletions(-)

diff --git a/pathspec.c b/pathspec.c
index 326863a..45bd775 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -89,6 +89,43 @@ static void prefix_short_magic(struct strbuf *sb, int prefixlen,
 	strbuf_addf(sb, ",prefix:%d)", prefixlen);
 }
 
+static size_t strcspn_escaped(const char *s, const char *reject)
+{
+	const char *i, *j;
+
+	for (i = s; *i; i++) {
+		/* skip escaped the character */
+		if (i[0] == '\\' && i[1]) {
+			i++;
+			continue;
+		}
+		/* see if any of the chars matches the current character */
+		for (j = reject; *j; j++)
+			if (!*i || *i == *j)
+				return i - s;
+	}
+	return i - s;
+}
+
+static char *attr_value_unescape(const char *value)
+{
+	char *i, *ret = xstrdup(value);
+
+	for (i = ret; *i; i++) {
+		if (i[0] == '\\') {
+			if (!i[1])
+				die(_("Escape character '\\' not allowed as "
+				      "last character in attr value"));
+
+			/* remove the backslash */
+			memmove(i, i + 1, strlen(i));
+			/* and ignore the character after that */
+			i++;
+		}
+	}
+	return ret;
+}
+
 static void parse_pathspec_attr_match(struct pathspec_item *item, const char *value)
 {
 	struct string_list_item *si;
@@ -131,10 +168,9 @@ static void parse_pathspec_attr_match(struct pathspec_item *item, const char *va
 			if (attr[attr_len] != '=')
 				am->match_mode = MATCH_SET;
 			else {
+				const char *v = &attr[attr_len + 1];
 				am->match_mode = MATCH_VALUE;
-				am->value = xstrdup(&attr[attr_len + 1]);
-				if (strchr(am->value, '\\'))
-					die(_("attr spec values must not contain backslashes"));
+				am->value = attr_value_unescape(v);
 			}
 			break;
 		}
@@ -166,7 +202,7 @@ static void eat_long_magic(struct pathspec_item *item, const char *elt,
 	for (copyfrom = elt + 2;
 	     *copyfrom && *copyfrom != ')';
 	     copyfrom = nextat) {
-		size_t len = strcspn(copyfrom, ",)");
+		size_t len = strcspn_escaped(copyfrom, ",)");
 		if (copyfrom[len] == ',')
 			nextat = copyfrom + len + 1;
 		else
diff --git a/t/t6134-pathspec-with-labels.sh b/t/t6134-pathspec-with-labels.sh
index a5c9632..cbea858 100755
--- a/t/t6134-pathspec-with-labels.sh
+++ b/t/t6134-pathspec-with-labels.sh
@@ -163,4 +163,27 @@ test_expect_success 'abort on asking for wrong magic' '
 	test_must_fail git ls-files . ":(attr:!label=foo)"
 '
 
+test_expect_success 'check attribute list' '
+	cat <<-EOF >>.gitattributes &&
+	* whitespace=indent,trail,space
+	EOF
+	cat .gitattributes &&
+	git ls-files ":(attr:whitespace=indent\,trail\,space)" >actual &&
+	git ls-files >expect &&
+	test_cmp expect actual
+'
+test_expect_success 'wrong escaping caught' '
+	# Pass one backslash to git to fail with a missing closing paren
+	test_must_fail git ls-files ":(attr:marked-with-backslash=\\)" 2>actual &&
+	test_i18ngrep Missing actual
+'
+test_expect_success 'check escaped backslash' '
+	cat <<-EOF >>.gitattributes &&
+	/sub/* marked-with-backslash=\\
+	EOF
+	git ls-files ":(attr:marked-with-backslash=\\\\)" >actual &&
+	git ls-files sub/ >expect &&
+	test_cmp expect actual
+'
+
 test_done

-- 
2.8.2.126.gaa5c87d.dirty