git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 4/4] Add 'filter' attribute and external filter driver definition.

From
Junio C Hamano <junkio@cox.net>
Date
Apr 21, 2007, 10:40 UTC
Message-ID
<11771520591703-git-send-email-junkio@cox.net>
In-Reply-To
<11771520591529-git-send-email-junkio@cox.net>
The interface is similar to the custom low-level merge drivers.

First you configure your filter driver by defining 'filter.<name>.*' variables in the configuration.

	filter.<name>.clean	filter command to run upon checkin
	filter.<name>.smudge	filter command to run upon checkout

Then you assign filter attribute to each path, whose name matches the custom filter driver's name.

Example:
	(in .gitattributes)
	*.c	filter=indent
	(in config)
	[filter "indent"]
		clean = indent
		smudge = cat
Signed-off-by: Junio C Hamano <junkio@cox.net>
---
 convert.c         |  253 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 t/t0021-filter.sh |   35 ++++++++
 2 files changed, 279 insertions(+), 9 deletions(-)
 create mode 100755 t/t0021-filter.sh
diff --git a/convert.c b/convert.c
index 37239ac..62d8cee 100644
--- a/convert.c
+++ b/convert.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "attr.h"
+#include "run-command.h"
 
 /*
  * convert.c - convert a file when checking it out and checking it in.
@@ -200,18 +201,208 @@ static char *crlf_to_worktree(const char *path, const char *src, unsigned long *
 	return buffer;
 }
 
+static int filter_buffer(const char *path, const char *src,
+			 unsigned long size, const char *cmd)
+{
+	/*
+	 * Spawn cmd and feed the buffer contents through its stdin.
+	 */
+	struct child_process child_process;
+	int pipe_feed[2];
+	int write_err, status;
+
+	memset(&child_process, 0, sizeof(child_process));
+
+	if (pipe(pipe_feed) < 0) {
+		error("cannot create pipe to run external filter %s", cmd);
+		return 1;
+	}
+
+	child_process.pid = fork();
+	if (child_process.pid < 0) {
+		error("cannot fork to run external filter %s", cmd);
+		close(pipe_feed[0]);
+		close(pipe_feed[1]);
+		return 1;
+	}
+	if (!child_process.pid) {
+		dup2(pipe_feed[0], 0);
+		close(pipe_feed[0]);
+		close(pipe_feed[1]);
+		execlp(cmd, cmd, NULL);
+		return 1;
+	}
+	close(pipe_feed[0]);
+
+	write_err = (write_in_full(pipe_feed[1], src, size) < 0);
+	if (close(pipe_feed[1]))
+		write_err = 1;
+	if (write_err)
+		error("cannot feed the input to external filter %s", cmd);
+
+	status = finish_command(&child_process);
+	if (status)
+		error("external filter %s failed %d", cmd, -status);
+	return (write_err || status);
+}
+
+static char *apply_filter(const char *path, const char *src,
+			  unsigned long *sizep, const char *cmd)
+{
+	/*
+	 * Create a pipeline to have the command filter the buffer's
+	 * contents.
+	 *
+	 * (child --> cmd) --> us
+	 */
+	const int SLOP = 4096;
+	int pipe_feed[2];
+	int status;
+	char *dst;
+	unsigned long dstsize, dstalloc;
+	struct child_process child_process;
+
+	if (!cmd)
+		return NULL;
+
+	memset(&child_process, 0, sizeof(child_process));
+
+	if (pipe(pipe_feed) < 0) {
+		error("cannot create pipe to run external filter %s", cmd);
+		return NULL;
+	}
+
+	child_process.pid = fork();
+	if (child_process.pid < 0) {
+		error("cannot fork to run external filter %s", cmd);
+		close(pipe_feed[0]);
+		close(pipe_feed[1]);
+		return NULL;
+	}
+	if (!child_process.pid) {
+		dup2(pipe_feed[1], 1);
+		close(pipe_feed[0]);
+		close(pipe_feed[1]);
+		exit(filter_buffer(path, src, *sizep, cmd));
+	}
+	close(pipe_feed[1]);
+
+	dstalloc = *sizep;
+	dst = xmalloc(dstalloc);
+	dstsize = 0;
+
+	while (1) {
+		ssize_t numread = xread(pipe_feed[0], dst + dstsize,
+					dstalloc - dstsize);
+
+		if (numread <= 0) {
+			if (!numread)
+				break;
+			error("read from external filter %s failed", cmd);
+			free(dst);
+			dst = NULL;
+			break;
+		}
+		dstsize += numread;
+		if (dstalloc <= dstsize + SLOP) {
+			dstalloc = dstsize + SLOP;
+			dst = xrealloc(dst, dstalloc);
+		}
+	}
+
+	status = finish_command(&child_process);
+	if (status) {
+		error("external filter %s failed %d", cmd, -status);
+		free(dst);
+		dst = NULL;
+	}
+
+	if (dst)
+		*sizep = dstsize;
+	return dst;
+}
+
+static struct convert_driver {
+	const char *name;
+	struct convert_driver *next;
+	char *smudge;
+	char *clean;
+} *user_convert, **user_convert_tail;
+
+static int read_convert_config(const char *var, const char *value)
+{
+	const char *ep, *name;
+	int namelen;
+	struct convert_driver *drv;
+
+	/*
+	 * External conversion drivers are configured using
+	 * "filter.<name>.variable".
+	 */
+	if (prefixcmp(var, "filter.") || (ep = strrchr(var, '.')) == var + 6)
+		return 0;
+	name = var + 7;
+	namelen = ep - name;
+	for (drv = user_convert; drv; drv = drv->next)
+		if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
+			break;
+	if (!drv) {
+		char *namebuf;
+		drv = xcalloc(1, sizeof(struct convert_driver));
+		namebuf = xmalloc(namelen + 1);
+		memcpy(namebuf, name, namelen);
+		namebuf[namelen] = 0;
+		drv->name = namebuf;
+		drv->next = NULL;
+		*user_convert_tail = drv;
+		user_convert_tail = &(drv->next);
+	}
+
+	ep++;
+
+	/*
+	 * filter.<name>.smudge and filter.<name>.clean specifies
+	 * the command line:
+	 *
+	 *	command-line
+	 *
+	 * The command-line will not be interpolated in any way.
+	 */
+
+	if (!strcmp("smudge", ep)) {
+		if (!value)
+			return error("%s: lacks value", var);
+		drv->smudge = strdup(value);
+		return 0;
+	}
+
+	if (!strcmp("clean", ep)) {
+		if (!value)
+			return error("%s: lacks value", var);
+		drv->clean = strdup(value);
+		return 0;
+	}
+	return 0;
+}
+
 static void setup_convert_check(struct git_attr_check *check)
 {
 	static struct git_attr *attr_crlf;
+	static struct git_attr *attr_filter;
 
-	if (!attr_crlf)
+	if (!attr_crlf) {
 		attr_crlf = git_attr("crlf", 4);
-	check->attr = attr_crlf;
+		attr_filter = git_attr("filter", 6);
+		user_convert_tail = &user_convert;
+		git_config(read_convert_config);
+	}
+	check[0].attr = attr_crlf;
+	check[1].attr = attr_filter;
 }
 
 static int git_path_check_crlf(const char *path, struct git_attr_check *check)
 {
-	const char *value = check->value;
+	const char *value = check[0].value;
 
 	if (ATTR_TRUE(value))
 		return CRLF_TEXT;
@@ -224,26 +415,70 @@ static int git_path_check_crlf(const char *path, struct git_attr_check *check)
 	return CRLF_GUESS;
 }
 
+static struct convert_driver *git_path_check_convert(const char *path,
+					     struct git_attr_check *check)
+{
+	const char *value = check[1].value;
+	struct convert_driver *drv;
+
+	if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
+		return NULL;
+	for (drv = user_convert; drv; drv = drv->next)
+		if (!strcmp(value, drv->name))
+			return drv;
+	return NULL;
+}
+
 char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
 {
-	struct git_attr_check check[1];
+	struct git_attr_check check[2];
 	int crlf = CRLF_GUESS;
+	char *filter = NULL;
+	char *buf, *buf2;
 
 	setup_convert_check(check);
-	if (!git_checkattr(path, 1, check)) {
+	if (!git_checkattr(path, 2, check)) {
+		struct convert_driver *drv;
 		crlf = git_path_check_crlf(path, check);
+		drv = git_path_check_convert(path, check);
+		if (drv && drv->clean)
+			filter = drv->clean;
 	}
-	return crlf_to_git(path, src, sizep, crlf);
+
+	buf = apply_filter(path, src, sizep, filter);
+
+	buf2 = crlf_to_git(path, buf ? buf : src, sizep, crlf);
+	if (buf2) {
+		free(buf);
+		buf = buf2;
+	}
+
+	return buf;
 }
 
 char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep)
 {
-	struct git_attr_check check[1];
+	struct git_attr_check check[2];
 	int crlf = CRLF_GUESS;
+	char *filter = NULL;
+	char *buf, *buf2;
 
 	setup_convert_check(check);
-	if (!git_checkattr(path, 1, check)) {
+	if (!git_checkattr(path, 2, check)) {
+		struct convert_driver *drv;
 		crlf = git_path_check_crlf(path, check);
+		drv = git_path_check_convert(path, check);
+		if (drv && drv->smudge)
+			filter = drv->smudge;
 	}
-	return crlf_to_worktree(path, src, sizep, crlf);
+
+	buf = crlf_to_worktree(path, src, sizep, crlf);
+
+	buf2 = apply_filter(path, buf ? buf : src, sizep, filter);
+	if (buf2) {
+		free(buf);
+		buf = buf2;
+	}
+
+	return buf;
 }
diff --git a/t/t0021-filter.sh b/t/t0021-filter.sh
new file mode 100755
index 0000000..0f4cd05
--- /dev/null
+++ b/t/t0021-filter.sh
@@ -0,0 +1,35 @@
+#!/bin/sh
+
+test_description='external filter conversion'
+
+. ./test-lib.sh
+
+cat <<\EOF >rot13.sh
+tr '[a-zA-Z]' '[n-za-mN-ZA-M]'
+EOF
+chmod +x rot13.sh
+
+test_expect_success setup '
+	git config filter.rot13.smudge ./rot13.sh &&
+	git config filter.rot13.clean ./rot13.sh &&
+
+	echo "*.t filter=rot13" >.gitattributes &&
+
+	{
+	    echo a b c d e f g h i j k l m
+	    echo n o p q r s t u v w x y z
+	} >test &&
+	cat test >test.t &&
+	cat test >test.o &&
+	git add test test.t &&
+	git checkout -- test test.t
+'
+
+test_expect_success check '
+
+	cmp test.o test &&
+	cmp test.o test.t
+
+'
+
+test_done
-- 
1.5.1.1.948.g9f6f
Previous: Junio C HamanoNext: Shawn O. Pearce
Message 5 of 22 in “External 'filter' attributes and drivers”
  1. 0/4 External 'filter' attributes and driversJunio C Hamano, Apr 21, 2007
  2. 1/4 Simplify calling of CR/LF conversion routinesJunio C Hamano, Apr 21, 2007
  3. 2/4 convert.c: restructure the attribute checking part.Junio C Hamano, Apr 21, 2007
  4. 3/4 lockfile: record the primary process.Junio C Hamano, Apr 21, 2007
  5. 4/4 Add 'filter' attribute and external filter driver definition.Junio C Hamano, Apr 21, 2007
  6. Shawn O. PearceApr 22, 2007
  7. Junio C HamanoApr 22, 2007
  8. Shawn O. PearceApr 22, 2007
  9. David LangApr 22, 2007
  10. Junio C HamanoApr 22, 2007
  11. David LangApr 22, 2007
  12. David LangApr 22, 2007
  13. Junio C HamanoApr 22, 2007
  14. David LangApr 22, 2007
  15. Nicolas PitreApr 22, 2007
  16. David LangApr 22, 2007
  17. Linus TorvaldsApr 22, 2007
  18. Junio C HamanoApr 22, 2007
  19. Alex RiesenApr 21, 2007
  20. David LangApr 22, 2007
  21. Shawn O. PearceApr 22, 2007
  22. David LangApr 22, 2007

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.