Merge branch 'jc/attr'

* jc/attr:
  Add 'filter' attribute and external filter driver definition.
  Add 'ident' conversion.

3 files changed, 531 insertions, 12 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 857d55a409..87723105d1 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -78,12 +78,17 @@ are attributes-aware.
 Checking-out and checking-in
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The attribute `crlf` affects how the contents stored in the
+These attributes affect how the contents stored in the
 repository are copied to the working tree files when commands
-such as `git checkout` and `git merge` run.  It also affects how
+such as `git checkout` and `git merge` run.  They also affect how
 git stores the contents you prepare in the working tree in the
 repository upon `git add` and `git commit`.
 
+`crlf`
+^^^^^^
+
+This attribute controls the line-ending convention.
+
 Set::
 
 	Setting the `crlf` attribute on a path is meant to mark
@@ -129,6 +134,67 @@ converted to LF upon checkin, but there is no conversion done
 upon checkout.
 
 
+`ident`
+^^^^^^^
+
+When the attribute `ident` is set to a path, git replaces
+`$ident$` in the blob object with `$ident:`, followed by
+40-character hexadecimal blob object name, followed by a dollar
+sign `$` upon checkout.  Any byte sequence that begins with
+`$ident:` and ends with `$` in the worktree file is replaced
+with `$ident$` upon check-in.
+
+
+Interaction between checkin/checkout attributes
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In the check-in codepath, the worktree file is first converted
+with `ident` (if specified), and then with `crlf` (again, if
+specified and applicable).
+
+In the check-out codepath, the blob content is first converted
+with `crlf`, and then `ident`.
+
+
+`filter`
+^^^^^^^^
+
+A `filter` attribute can be set to a string value.  This names
+filter driver specified in the configuration.
+
+A filter driver consists of `clean` command and `smudge`
+command, either of which can be left unspecified.  Upon
+checkout, when `smudge` command is specified, the command is fed
+the blob object from its standard input, and its standard output
+is used to update the worktree file.  Similarly, `clean` command
+is used to convert the contents of worktree file upon checkin.
+
+Missing filter driver definition in the config is not an error
+but makes the filter a no-op passthru.
+
+The content filtering is done to massage the content into a
+shape that is more convenient for the platform, filesystem, and
+the user to use.  The keyword here is "more convenient" and not
+"turning something unusable into usable".  In other words, it is
+"hanging yourself because we gave you a long rope" if your
+project uses filtering mechanism in such a way that it makes
+your project unusable unless the checkout is done with a
+specific filter in effect.
+
+
+Interaction between checkin/checkout attributes
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In the check-in codepath, the worktree file is first converted
+with `filter` driver (if specified and corresponding driver
+defined), then the result is processed with `ident` (if
+specified), and then finally with `crlf` (again, if specified
+and applicable).
+
+In the check-out codepath, the blob content is first converted
+with `crlf`, and then `ident` and fed to `filter`.
+
+
 Generating diff text
 ~~~~~~~~~~~~~~~~~~~~
 
diff --git a/convert.c b/convert.c
index ad106ef35f..9ee31b0ee0 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.
@@ -200,13 +201,350 @@ 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("sh", "sh", "-c", 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;
+	}
+
+	fflush(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);
+		}
+	}
+	if (close(pipe_feed[0])) {
+		error("read from external filter %s failed", cmd);
+		free(dst);
+		dst = NULL;
+	}
+
+	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_ident;
+	static struct git_attr *attr_filter;
 
-	if (!attr_crlf)
+	if (!attr_crlf) {
 		attr_crlf = git_attr("crlf", 4);
-	check->attr = attr_crlf;
+		attr_ident = git_attr("ident", 5);
+		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_ident;
+	check[2].attr = attr_filter;
+}
+
+static int count_ident(const char *cp, unsigned long size)
+{
+	/*
+	 * "$ident: 0000000000000000000000000000000000000000 $" <=> "$ident$"
+	 */
+	int cnt = 0;
+	char ch;
+
+	while (size) {
+		ch = *cp++;
+		size--;
+		if (ch != '$')
+			continue;
+		if (size < 6)
+			break;
+		if (memcmp("ident", cp, 5))
+			continue;
+		ch = cp[5];
+		cp += 6;
+		size -= 6;
+		if (ch == '$')
+			cnt++; /* $ident$ */
+		if (ch != ':')
+			continue;
+
+		/*
+		 * "$ident: ... "; scan up to the closing dollar sign and discard.
+		 */
+		while (size) {
+			ch = *cp++;
+			size--;
+			if (ch == '$') {
+				cnt++;
+				break;
+			}
+		}
+	}
+	return cnt;
+}
+
+static char *ident_to_git(const char *path, const char *src, unsigned long *sizep, int ident)
+{
+	int cnt;
+	unsigned long size;
+	char *dst, *buf;
+
+	if (!ident)
+		return NULL;
+	size = *sizep;
+	cnt = count_ident(src, size);
+	if (!cnt)
+		return NULL;
+	buf = xmalloc(size);
+
+	for (dst = buf; size; size--) {
+		char ch = *src++;
+		*dst++ = ch;
+		if ((ch == '$') && (6 <= size) &&
+		    !memcmp("ident:", src, 6)) {
+			unsigned long rem = size - 6;
+			const char *cp = src + 6;
+			do {
+				ch = *cp++;
+				if (ch == '$')
+					break;
+				rem--;
+			} while (rem);
+			if (!rem)
+				continue;
+			memcpy(dst, "ident$", 6);
+			dst += 6;
+			size -= (cp - src);
+			src = cp;
+		}
+	}
+
+	*sizep = dst - buf;
+	return buf;
+}
+
+static char *ident_to_worktree(const char *path, const char *src, unsigned long *sizep, int ident)
+{
+	int cnt;
+	unsigned long size;
+	char *dst, *buf;
+	unsigned char sha1[20];
+
+	if (!ident)
+		return NULL;
+
+	size = *sizep;
+	cnt = count_ident(src, size);
+	if (!cnt)
+		return NULL;
+
+	hash_sha1_file(src, size, "blob", sha1);
+	buf = xmalloc(size + cnt * 43);
+
+	for (dst = buf; size; size--) {
+		const char *cp;
+		char ch = *src++;
+		*dst++ = ch;
+		if ((ch != '$') || (size < 6) || memcmp("ident", src, 5))
+			continue;
+
+		if (src[5] == ':') {
+			/* discard up to but not including the closing $ */
+			unsigned long rem = size - 6;
+			cp = src + 6;
+			do {
+				ch = *cp++;
+				if (ch == '$')
+					break;
+				rem--;
+			} while (rem);
+			if (!rem)
+				continue;
+			size -= (cp - src);
+		} else if (src[5] == '$')
+			cp = src + 5;
+		else
+			continue;
+
+		memcpy(dst, "ident: ", 7);
+		dst += 7;
+		memcpy(dst, sha1_to_hex(sha1), 40);
+		dst += 40;
+		*dst++ = ' ';
+		size -= (cp - src);
+		src = cp;
+		*dst++ = *src++;
+		size--;
+	}
+
+	*sizep = dst - buf;
+	return buf;
 }
 
 static int git_path_check_crlf(const char *path, struct git_attr_check *check)
@@ -224,26 +562,93 @@ 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->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;
+}
+
+static int git_path_check_ident(const char *path, struct git_attr_check *check)
+{
+	const char *value = check->value;
+
+	return !!ATTR_TRUE(value);
+}
+
 char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
 {
-	struct git_attr_check check[1];
+	struct git_attr_check check[3];
 	int crlf = CRLF_GUESS;
+	int ident = 0;
+	char *filter = NULL;
+	char *buf, *buf2;
 
 	setup_convert_check(check);
-	if (!git_checkattr(path, 1, check)) {
-		crlf = git_path_check_crlf(path, check);
+	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
+		struct convert_driver *drv;
+		crlf = git_path_check_crlf(path, check + 0);
+		ident = git_path_check_ident(path, check + 1);
+		drv = git_path_check_convert(path, check + 2);
+		if (drv && drv->clean)
+			filter = drv->clean;
+	}
+
+	buf = apply_filter(path, src, sizep, filter);
+
+	buf2 = crlf_to_git(path, buf ? buf : src, sizep, crlf);
+	if (buf2) {
+		free(buf);
+		buf = buf2;
+	}
+
+	buf2 = ident_to_git(path, buf ? buf : src, sizep, ident);
+	if (buf2) {
+		free(buf);
+		buf = buf2;
 	}
-	return crlf_to_git(path, src, sizep, crlf);
+
+	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[3];
 	int crlf = CRLF_GUESS;
+	int ident = 0;
+	char *filter = NULL;
+	char *buf, *buf2;
 
 	setup_convert_check(check);
-	if (!git_checkattr(path, 1, check)) {
-		crlf = git_path_check_crlf(path, check);
+	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
+		struct convert_driver *drv;
+		crlf = git_path_check_crlf(path, check + 0);
+		ident = git_path_check_ident(path, check + 1);
+		drv = git_path_check_convert(path, check + 2);
+		if (drv && drv->smudge)
+			filter = drv->smudge;
+	}
+
+	buf = ident_to_worktree(path, src, sizep, ident);
+
+	buf2 = crlf_to_worktree(path, buf ? buf : src, sizep, crlf);
+	if (buf2) {
+		free(buf);
+		buf = buf2;
 	}
-	return 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-conversion.sh b/t/t0021-conversion.sh
new file mode 100755
index 0000000000..bab9ecc34e
--- /dev/null
+++ b/t/t0021-conversion.sh
@@ -0,0 +1,48 @@
+#!/bin/sh
+
+test_description='blob conversion via gitattributes'
+
+. ./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"
+	    echo "*.i ident"
+	} >.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
+	    echo '\''$ident$'\''
+	} >test &&
+	cat test >test.t &&
+	cat test >test.o &&
+	cat test >test.i &&
+	git add test test.t test.i &&
+	rm -f test test.t test.i &&
+	git checkout -- test test.t test.i
+'
+
+script='s/^\$ident: \([0-9a-f]*\) \$/\1/p'
+
+test_expect_success check '
+
+	cmp test.o test &&
+	cmp test.o test.t &&
+
+	# ident should be stripped in the repository
+	git diff --raw --exit-code :test :test.i &&
+	id=$(git rev-parse --verify :test) &&
+	embedded=$(sed -ne "$script" test.i) &&
+	test "z$id" = "z$embedded"
+'
+
+test_done