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.
Helped-by: Junio C Hamano <gits...@pobox.com>
Signed-off-by: Stefan Beller <sbel...@google.com>
---
> That would be true _only_ when "find next escape and copy up to that
> byte" aka "scanning once with optimized strchr(), and copying once
> with optimized memmove()" is faster than "scanning once and copying"
> loop.
Oh right. that would work for larger strings that don't fit into a cache
very well, but in our expected case this will do.
> I was merely reacting to your use of memmove() in a very different
> loop, where if you unescape "a\b\c\defghijk", your memmove() would
> move "efghijk" many times.
Right, at the time of writing I didn't like it, but was ok with it as
we only have a few escapes.
> Also the handling of the terminating NUL may need to be
> updated.
I don't think so.
> That is why I did not say "replace yours with this", but
> merely "along the lines of this" ;-)
This is pretty much your code modulo nits (xmalloz, semicolons) now,
and I am convinced it works by the test.
However if we add a value restriction here, we need to be as strict in the
.gitattributes parsing as well and put a warning there (similar to
invalid_attr_name_message) I would think.
Thanks,
Stefan
pathspec.c | 52 +++++++++++++++++++++++++++++++++++++----
t/t6134-pathspec-with-labels.sh | 10 ++++++++
2 files changed, 58 insertions(+), 4 deletions(-)
diff --git a/pathspec.c b/pathspec.c
index 326863a..fe53ddf 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -89,6 +89,51 @@ 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 *stop)
+{
+ const char *i;
+
+ for (i = s; *i; i++) {
+ /* skip the escaped character */
+ if (i[0] == '\\' && i[1]) {
+ i++;
+ continue;
+ }
+
+ if (strchr(stop, *i))
+ break;
+ }
+ return i - s;
+}
+
+static inline int invalid_value_char(const char ch)
+{
+ if (isalnum(ch) || strchr(",-_", ch))
+ return 0;
+ return -1;
+}
+
+static char *attr_value_unescape(const char *value)
+{
+ const char *src;
+ char *dst, *ret;
+
+ ret = xmallocz(strlen(value));
+ for (src = value, dst = ret; *src; src++, dst++) {
+ if (*src == '\\') {
+ if (!src[1])
+ die(_("Escape character '\\' not allowed as "
+ "last character in attr value"));
+ src++;
+ }
+ if (*src && invalid_value_char(*src))
+ die("cannot use '%c' for value matching", *src);
+ *dst = *src;
+ }
+ *dst = '\0';
+ return ret;
+}
+
static void parse_pathspec_attr_match(struct pathspec_item *item, const char
*value)
{
struct string_list_item *si;
@@ -131,10 +176,9 @@ 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 +210,7 @@ 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..f1e355f 100755
--- a/t/t6134-pathspec-with-labels.sh
+++ b/t/t6134-pathspec-with-labels.sh
@@ -163,4 +163,14 @@ 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_done
--
2.8.2.126.g9068a9d.dirty
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
