convert filter: supply path to external driver

Filtering to support keyword expansion may need the name of
the file being filtered.  In particular, to support p4 keywords
like

    $File: //depot/product/dir/script.sh $

the smudge filter needs to know the name of the file it is
smudging.

Allow "%f" in the custom filter command line specified in the
configuration.  This will be substituted by the filename
inside a single-quote pair to be passed to the shell.

Signed-off-by: Pete Wyckoff <pw@padd.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 74 insertions, 1 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 5a7f936429..22b85825ab 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -335,6 +335,16 @@ input that is already correctly indented.  In this case, the lack of a
 smudge filter means that the clean filter _must_ accept its own output
 without modifying it.
 
+Sequence "%f" on the filter command line is replaced with the name of
+the file the filter is working on.  A filter might use this in keyword
+substitution.  For example:
+
+------------------------
+[filter "p4"]
+	clean = git-p4-filter --clean %f
+	smudge = git-p4-filter --smudge %f
+------------------------
+
 
 Interaction between checkin/checkout attributes
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/convert.c b/convert.c
index 01de9a84c2..d5aebed48d 100644
--- a/convert.c
+++ b/convert.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "attr.h"
 #include "run-command.h"
+#include "quote.h"
 
 /*
  * convert.c - convert a file when checking it out and checking it in.
@@ -318,6 +319,7 @@ struct filter_params {
 	const char *src;
 	unsigned long size;
 	const char *cmd;
+	const char *path;
 };
 
 static int filter_buffer(int in, int out, void *data)
@@ -330,7 +332,23 @@ static int filter_buffer(int in, int out, void *data)
 	int write_err, status;
 	const char *argv[] = { NULL, NULL };
 
-	argv[0] = params->cmd;
+	/* apply % substitution to cmd */
+	struct strbuf cmd = STRBUF_INIT;
+	struct strbuf path = STRBUF_INIT;
+	struct strbuf_expand_dict_entry dict[] = {
+		{ "f", NULL, },
+		{ NULL, NULL, },
+	};
+
+	/* quote the path to preserve spaces, etc. */
+	sq_quote_buf(&path, params->path);
+	dict[0].value = path.buf;
+
+	/* expand all %f with the quoted path */
+	strbuf_expand(&cmd, params->cmd, strbuf_expand_dict_cb, &dict);
+	strbuf_release(&path);
+
+	argv[0] = cmd.buf;
 
 	memset(&child_process, 0, sizeof(child_process));
 	child_process.argv = argv;
@@ -350,6 +368,8 @@ static int filter_buffer(int in, int out, void *data)
 	status = finish_command(&child_process);
 	if (status)
 		error("external filter %s failed %d", params->cmd, status);
+
+	strbuf_release(&cmd);
 	return (write_err || status);
 }
 
@@ -377,6 +397,7 @@ static int apply_filter(const char *path, const char *src, size_t len,
 	params.src = src;
 	params.size = len;
 	params.cmd = cmd;
+	params.path = path;
 
 	fflush(NULL);
 	if (start_async(&async))
diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh
index 828e35baf7..aacfd004b1 100755
--- a/t/t0021-conversion.sh
+++ b/t/t0021-conversion.sh
@@ -93,4 +93,46 @@ test_expect_success expanded_in_repo '
 	cmp expanded-keywords expected-output
 '
 
+# The use of %f in a filter definition is expanded to the path to
+# the filename being smudged or cleaned.  It must be shell escaped.
+# First, set up some interesting file names and pet them in
+# .gitattributes.
+test_expect_success 'filter shell-escaped filenames' '
+	cat >argc.sh <<-EOF &&
+	#!$SHELL_PATH
+	echo argc: \$# "\$@"
+	EOF
+	normal=name-no-magic &&
+	special="name  with '\''sq'\'' and \$x" &&
+	echo some test text >"$normal" &&
+	echo some test text >"$special" &&
+	git add "$normal" "$special" &&
+	git commit -q -m "add files" &&
+	echo "name* filter=argc" >.gitattributes &&
+
+	# delete the files and check them out again, using a smudge filter
+	# that will count the args and echo the command-line back to us
+	git config filter.argc.smudge "sh ./argc.sh %f" &&
+	rm "$normal" "$special" &&
+	git checkout -- "$normal" "$special" &&
+
+	# make sure argc.sh counted the right number of args
+	echo "argc: 1 $normal" >expect &&
+	test_cmp expect "$normal" &&
+	echo "argc: 1 $special" >expect &&
+	test_cmp expect "$special" &&
+
+	# do the same thing, but with more args in the filter expression
+	git config filter.argc.smudge "sh ./argc.sh %f --my-extra-arg" &&
+	rm "$normal" "$special" &&
+	git checkout -- "$normal" "$special" &&
+
+	# make sure argc.sh counted the right number of args
+	echo "argc: 2 $normal --my-extra-arg" >expect &&
+	test_cmp expect "$normal" &&
+	echo "argc: 2 $special --my-extra-arg" >expect &&
+	test_cmp expect "$special" &&
+	:
+'
+
 test_done