[PATCH] attr: support quoting pathname patterns in C style

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

Full pattern must be quoted. So 'pat"t"ern attr' will give exactly
'pat"t"ern', not 'pattern'.

If Git fails to unquote it, it warns users and takes the pattern
literally. This keeps existing patterns that begin with a double
quotation mark work until they get annoyed by the warnings and fix
their patterns.

Also clarify that leading whitespaces are not part of the pattern and
document comment syntax.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 On Fri, Nov 05, 2010 at 09:58:46AM -0700, Junio C Hamano wrote:
 > Nguyễn Thái Ngọc Duy <pclouds@gmail.com> writes:
 > 
 > > Full pattern must be quoted. So 'pat"t"ern attr' will give exactly
 > > 'pat"t"ern', not 'pattern'. Also clarify that leading whitespaces are
 > > not part of the pattern and document comment syntax.
 > >
 > > Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
 > > ---
 > >  Obvious regression: patterns that begin with double quote will
 > >  now work differently.
 > 
 > I'm really hesitant to pursue this route and break people's existing
 > setups

 How about this? No more breaking current setups.
  
 Documentation/gitattributes.txt |    8 +++++---
 attr.c                          |   32 ++++++++++++++++++++++++++++----
 t/t0003-attributes.sh           |   21 ++++++++++++++++++++-
 3 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index c80ca5d..f7954dd 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -21,9 +21,11 @@ Each line in `gitattributes` file is of form:
 	pattern	attr1 attr2 ...
 
 That is, a pattern followed by an attributes list,
-separated by whitespaces.  When the pattern matches the
-path in question, the attributes listed on the line are given to
-the path.
+separated by whitespaces. Leading and trailing whitespaces are
+ignored. Lines that begin with '#' are ignored. Patterns
+that begin with a double quotation mark are quoted in C style.
+When the pattern matches the path in question, the attributes
+listed on the line are given to the path.
 
 Each attribute can be in one of these states for a given path:
 
diff --git a/attr.c b/attr.c
index 6aff695..fdc4aae 100644
--- a/attr.c
+++ b/attr.c
@@ -2,6 +2,7 @@
 #include "cache.h"
 #include "exec_cmd.h"
 #include "attr.h"
+#include "quote.h"
 
 const char git_attr__true[] = "(builtin)true";
 const char git_attr__false[] = "\0(builtin)false";
@@ -181,21 +182,40 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 {
 	int namelen;
 	int num_attr;
-	const char *cp, *name;
+	const char *cp, *name, *ep;
 	struct match_attr *res = NULL;
 	int pass;
 	int is_macro;
+	struct strbuf pattern = STRBUF_INIT;
 
 	cp = line + strspn(line, blank);
 	if (!*cp || *cp == '#')
 		return NULL;
 	name = cp;
-	namelen = strcspn(name, blank);
+	if (*cp == '"') {
+		if (unquote_c_style(&pattern, name, &ep)) {
+			fprintf(stderr, "Misquoted pattern at %s:%d\n"
+				"Pattern is taken literally.\n",
+				src, lineno);
+			namelen = strcspn(name, blank);
+			ep = name + namelen;
+		}
+		else {
+			namelen = ep - name;
+			name = pattern.buf;
+		}
+	}
+	else {
+		namelen = strcspn(name, blank);
+		ep = name + namelen;
+	}
+
 	if (strlen(ATTRIBUTE_MACRO_PREFIX) < namelen &&
 	    !prefixcmp(name, ATTRIBUTE_MACRO_PREFIX)) {
 		if (!macro_ok) {
 			fprintf(stderr, "%s not allowed: %s:%d\n",
 				name, src, lineno);
+			strbuf_release(&pattern);
 			return NULL;
 		}
 		is_macro = 1;
@@ -206,6 +226,7 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 			fprintf(stderr,
 				"%.*s is not a valid attribute name: %s:%d\n",
 				namelen, name, src, lineno);
+			strbuf_release(&pattern);
 			return NULL;
 		}
 	}
@@ -215,12 +236,14 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 	for (pass = 0; pass < 2; pass++) {
 		/* pass 0 counts and allocates, pass 1 fills */
 		num_attr = 0;
-		cp = name + namelen;
+		cp = ep;
 		cp = cp + strspn(cp, blank);
 		while (*cp) {
 			cp = parse_attr(src, lineno, cp, &num_attr, res);
-			if (!cp)
+			if (!cp) {
+				strbuf_release(&pattern);
 				return NULL;
+			}
 		}
 		if (pass)
 			break;
@@ -238,6 +261,7 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 		res->is_macro = is_macro;
 		res->num_attr = num_attr;
 	}
+	strbuf_release(&pattern);
 	return res;
 }
 
diff --git a/t/t0003-attributes.sh b/t/t0003-attributes.sh
index 25205ac..7c55482 100755
--- a/t/t0003-attributes.sh
+++ b/t/t0003-attributes.sh
@@ -10,17 +10,32 @@ attr_check () {
 	expect="$2"
 
 	git check-attr test -- "$path" >actual &&
-	echo "$path: test: $2" >expect &&
+	echo "$path: test: $expect" >expect &&
 	test_cmp expect actual
 
 }
 
+attr_check_quote () {
+
+	path="$1"
+	quoted_path="$2"
+	expect="$3"
+
+	git check-attr test -- "$path" >actual &&
+	echo "\"$quoted_path\": test: $expect" >expect &&
+	test_cmp expect actual
+
+}
 
 test_expect_success 'setup' '
 
 	mkdir -p a/b/d a/c &&
 	(
 		echo "[attr]notest !test"
+		echo "\"c	test=c"
+		echo "\" d \"	test=d"
+		echo " e	test=e"
+		echo " e\"	test=e"
 		echo "f	test=f"
 		echo "a/i test=a/i"
 		echo "onoff test -test"
@@ -44,6 +59,10 @@ test_expect_success 'setup' '
 
 test_expect_success 'attribute test' '
 
+	attr_check_quote \"c \\\"c c &&
+	attr_check " d " d &&
+	attr_check e e &&
+	attr_check_quote e\" e\\\" e &&
 	attr_check f f &&
 	attr_check a/f f &&
 	attr_check a/c/f f &&
-- 
1.7.3.2.210.g045198