Merge branch 'js/cat-file-filters'

Even though "git hash-objects", which is a tool to take an
on-filesystem data stream and put it into the Git object store,
allowed to perform the "outside-world-to-Git" conversions (e.g.
end-of-line conversions and application of the clean-filter), and
it had the feature on by default from very early days, its reverse
operation "git cat-file", which takes an object from the Git object
store and externalize for the consumption by the outside world,
lacked an equivalent mechanism to run the "Git-to-outside-world"
conversion.  The command learned the "--filters" option to do so.

* js/cat-file-filters:
  cat-file: support --textconv/--filters in batch mode
  cat-file --textconv/--filters: allow specifying the path separately
  cat-file: introduce the --filters option
  cat-file: fix a grammo in the man page

3 files changed, 190 insertions, 18 deletions

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 18d03d8e8..204541c69 100644
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -9,18 +9,22 @@ git-cat-file - Provide content or type and size information for repository objec
 SYNOPSIS
 --------
 [verse]
-'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv ) <object>
-'git cat-file' (--batch | --batch-check) [--follow-symlinks]
+'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv | --filters ) [--path=<path>] <object>
+'git cat-file' (--batch | --batch-check) [ --textconv | --filters ] [--follow-symlinks]
 
 DESCRIPTION
 -----------
 In its first form, the command provides the content or the type of an object in
 the repository. The type is required unless `-t` or `-p` is used to find the
-object type, or `-s` is used to find the object size, or `--textconv` is used
-(which implies type "blob").
+object type, or `-s` is used to find the object size, or `--textconv` or
+`--filters` is used (which imply type "blob").
 
 In the second form, a list of objects (separated by linefeeds) is provided on
-stdin, and the SHA-1, type, and size of each object is printed on stdout.
+stdin, and the SHA-1, type, and size of each object is printed on stdout. The
+output format can be overridden using the optional `<format>` argument. If
+either `--textconv` or `--filters` was specified, the input is expected to
+list the object names followed by the path name, separated by a single white
+space, so that the appropriate drivers can be determined.
 
 OPTIONS
 -------
@@ -54,19 +58,35 @@ OPTIONS
 
 --textconv::
 	Show the content as transformed by a textconv filter. In this case,
-	<object> has be of the form <tree-ish>:<path>, or :<path> in order
-	to apply the filter to the content recorded in the index at <path>.
+	<object> has to be of the form <tree-ish>:<path>, or :<path> in
+	order to apply the filter to the content recorded in the index at
+	<path>.
+
+--filters::
+	Show the content as converted by the filters configured in
+	the current working tree for the given <path> (i.e. smudge filters,
+	end-of-line conversion, etc). In this case, <object> has to be of
+	the form <tree-ish>:<path>, or :<path>.
+
+--path=<path>::
+	For use with --textconv or --filters, to allow specifying an object
+	name and a path separately, e.g. when it is difficult to figure out
+	the revision from which the blob came.
 
 --batch::
 --batch=<format>::
 	Print object information and contents for each object provided
-	on stdin.  May not be combined with any other options or arguments.
-	See the section `BATCH OUTPUT` below for details.
+	on stdin.  May not be combined with any other options or arguments
+	except `--textconv` or `--filters`, in which case the input lines
+	also need to specify the path, separated by white space.  See the
+	section `BATCH OUTPUT` below for details.
 
 --batch-check::
 --batch-check=<format>::
 	Print object information for each object provided on stdin.  May
-	not be combined with any other options or arguments.  See the
+	not be combined with any other options or arguments except
+	`--textconv` or `--filters`, in which case the input lines also
+	need to specify the path, separated by white space.  See the
 	section `BATCH OUTPUT` below for details.
 
 --batch-all-objects::
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 3ee9bc9ad..94e67ebb7 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -17,9 +17,34 @@ struct batch_options {
 	int print_contents;
 	int buffer_output;
 	int all_objects;
+	int cmdmode; /* may be 'w' or 'c' for --filters or --textconv */
 	const char *format;
 };
 
+static const char *force_path;
+
+static int filter_object(const char *path, unsigned mode,
+			 const struct object_id *oid,
+			 char **buf, unsigned long *size)
+{
+	enum object_type type;
+
+	*buf = read_sha1_file(oid->hash, &type, size);
+	if (!*buf)
+		return error(_("cannot read object %s '%s'"),
+			     oid_to_hex(oid), path);
+	if ((type == OBJ_BLOB) && S_ISREG(mode)) {
+		struct strbuf strbuf = STRBUF_INIT;
+		if (convert_to_working_tree(path, *buf, *size, &strbuf)) {
+			free(*buf);
+			*size = strbuf.len;
+			*buf = strbuf_detach(&strbuf, NULL);
+		}
+	}
+
+	return 0;
+}
+
 static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 			int unknown_type)
 {
@@ -31,6 +56,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	struct object_info oi = {NULL};
 	struct strbuf sb = STRBUF_INIT;
 	unsigned flags = LOOKUP_REPLACE_OBJECT;
+	const char *path = force_path;
 
 	if (unknown_type)
 		flags |= LOOKUP_UNKNOWN_OBJECT;
@@ -38,6 +64,11 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	if (get_sha1_with_context(obj_name, 0, oid.hash, &obj_context))
 		die("Not a valid object name %s", obj_name);
 
+	if (!path)
+		path = obj_context.path;
+	if (obj_context.mode == S_IFINVALID)
+		obj_context.mode = 0100644;
+
 	buf = NULL;
 	switch (opt) {
 	case 't':
@@ -61,12 +92,22 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	case 'e':
 		return !has_object_file(&oid);
 
+	case 'w':
+		if (!path[0])
+			die("git cat-file --filters %s: <object> must be "
+			    "<sha1:path>", obj_name);
+
+		if (filter_object(path, obj_context.mode,
+				  &oid, &buf, &size))
+			return -1;
+		break;
+
 	case 'c':
-		if (!obj_context.path[0])
+		if (!path[0])
 			die("git cat-file --textconv %s: <object> must be <sha1:path>",
 			    obj_name);
 
-		if (textconv_object(obj_context.path, obj_context.mode, &oid, 1, &buf, &size))
+		if (textconv_object(path, obj_context.mode, &oid, 1, &buf, &size))
 			break;
 
 	case 'p':
@@ -240,7 +281,32 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 	if (data->type == OBJ_BLOB) {
 		if (opt->buffer_output)
 			fflush(stdout);
-		if (stream_blob_to_fd(1, oid, NULL, 0) < 0)
+		if (opt->cmdmode) {
+			char *contents;
+			unsigned long size;
+
+			if (!data->rest)
+				die("missing path for '%s'", oid_to_hex(oid));
+
+			if (opt->cmdmode == 'w') {
+				if (filter_object(data->rest, 0100644, oid,
+						  &contents, &size))
+					die("could not convert '%s' %s",
+					    oid_to_hex(oid), data->rest);
+			} else if (opt->cmdmode == 'c') {
+				enum object_type type;
+				if (!textconv_object(data->rest, 0100644, oid,
+						     1, &contents, &size))
+					contents = read_sha1_file(oid->hash, &type,
+								  &size);
+				if (!contents)
+					die("could not convert '%s' %s",
+					    oid_to_hex(oid), data->rest);
+			} else
+				die("BUG: invalid cmdmode: %c", opt->cmdmode);
+			batch_write(opt, contents, size);
+			free(contents);
+		} else if (stream_blob_to_fd(1, oid, NULL, 0) < 0)
 			die("unable to stream %s to stdout", oid_to_hex(oid));
 	}
 	else {
@@ -378,6 +444,8 @@ static int batch_objects(struct batch_options *opt)
 	data.mark_query = 1;
 	strbuf_expand(&buf, opt->format, expand_format, &data);
 	data.mark_query = 0;
+	if (opt->cmdmode)
+		data.split_on_whitespace = 1;
 
 	if (opt->all_objects) {
 		struct object_info empty;
@@ -442,8 +510,8 @@ static int batch_objects(struct batch_options *opt)
 }
 
 static const char * const cat_file_usage[] = {
-	N_("git cat-file (-t [--allow-unknown-type] | -s [--allow-unknown-type] | -e | -p | <type> | --textconv) <object>"),
-	N_("git cat-file (--batch | --batch-check) [--follow-symlinks]"),
+	N_("git cat-file (-t [--allow-unknown-type] | -s [--allow-unknown-type] | -e | -p | <type> | --textconv | --filters) [--path=<path>] <object>"),
+	N_("git cat-file (--batch | --batch-check) [--follow-symlinks] [--textconv | --filters]"),
 	NULL
 };
 
@@ -488,6 +556,10 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
 		OPT_CMDMODE(0, "textconv", &opt,
 			    N_("for blob objects, run textconv on object's content"), 'c'),
+		OPT_CMDMODE(0, "filters", &opt,
+			    N_("for blob objects, run filters on object's content"), 'w'),
+		OPT_STRING(0, "path", &force_path, N_("blob"),
+			   N_("use a specific path for --textconv/--filters")),
 		OPT_BOOL(0, "allow-unknown-type", &unknown_type,
 			  N_("allow -s and -t to work with broken/corrupt objects")),
 		OPT_BOOL(0, "buffer", &batch.buffer_output, N_("buffer --batch output")),
@@ -510,7 +582,9 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
 
 	if (opt) {
-		if (argc == 1)
+		if (batch.enabled && (opt == 'c' || opt == 'w'))
+			batch.cmdmode = opt;
+		else if (argc == 1)
 			obj_name = argv[0];
 		else
 			usage_with_options(cat_file_usage, options);
@@ -522,14 +596,28 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		} else
 			usage_with_options(cat_file_usage, options);
 	}
-	if (batch.enabled && (opt || argc)) {
-		usage_with_options(cat_file_usage, options);
+	if (batch.enabled) {
+		if (batch.cmdmode != opt || argc)
+			usage_with_options(cat_file_usage, options);
+		if (batch.cmdmode && batch.all_objects)
+			die("--batch-all-objects cannot be combined with "
+			    "--textconv nor with --filters");
 	}
 
 	if ((batch.follow_symlinks || batch.all_objects) && !batch.enabled) {
 		usage_with_options(cat_file_usage, options);
 	}
 
+	if (force_path && opt != 'c' && opt != 'w') {
+		error("--path=<path> needs --textconv or --filters");
+		usage_with_options(cat_file_usage, options);
+	}
+
+	if (force_path && batch.enabled) {
+		error("--path=<path> incompatible with --batch");
+		usage_with_options(cat_file_usage, options);
+	}
+
 	if (batch.buffer_output < 0)
 		batch.buffer_output = batch.all_objects;
 
diff --git a/t/t8010-cat-file-filters.sh b/t/t8010-cat-file-filters.sh
new file mode 100755
index 000000000..d8242e467
--- /dev/null
+++ b/t/t8010-cat-file-filters.sh
@@ -0,0 +1,64 @@
+#!/bin/sh
+
+test_description='git cat-file filters support'
+. ./test-lib.sh
+
+test_expect_success 'setup ' '
+	echo "*.txt eol=crlf diff=txt" >.gitattributes &&
+	echo "hello" | append_cr >world.txt &&
+	git add .gitattributes world.txt &&
+	test_tick &&
+	git commit -m "Initial commit"
+'
+
+has_cr () {
+	tr '\015' Q <"$1" | grep Q >/dev/null
+}
+
+test_expect_success 'no filters with `git show`' '
+	git show HEAD:world.txt >actual &&
+	! has_cr actual
+
+'
+
+test_expect_success 'no filters with cat-file' '
+	git cat-file blob HEAD:world.txt >actual &&
+	! has_cr actual
+'
+
+test_expect_success 'cat-file --filters converts to worktree version' '
+	git cat-file --filters HEAD:world.txt >actual &&
+	has_cr actual
+'
+
+test_expect_success 'cat-file --filters --path=<path> works' '
+	sha1=$(git rev-parse -q --verify HEAD:world.txt) &&
+	git cat-file --filters --path=world.txt $sha1 >actual &&
+	has_cr actual
+'
+
+test_expect_success 'cat-file --textconv --path=<path> works' '
+	sha1=$(git rev-parse -q --verify HEAD:world.txt) &&
+	test_config diff.txt.textconv "tr A-Za-z N-ZA-Mn-za-m <" &&
+	git cat-file --textconv --path=hello.txt $sha1 >rot13 &&
+	test uryyb = "$(cat rot13 | remove_cr)"
+'
+
+test_expect_success '--path=<path> complains without --textconv/--filters' '
+	sha1=$(git rev-parse -q --verify HEAD:world.txt) &&
+	test_must_fail git cat-file --path=hello.txt blob $sha1 >actual 2>err &&
+	test ! -s actual &&
+	grep "path.*needs.*filters" err
+'
+
+test_expect_success 'cat-file --textconv --batch works' '
+	sha1=$(git rev-parse -q --verify HEAD:world.txt) &&
+	test_config diff.txt.textconv "tr A-Za-z N-ZA-Mn-za-m <" &&
+	printf "%s hello.txt\n%s hello\n" $sha1 $sha1 |
+	git cat-file --textconv --batch >actual &&
+	printf "%s blob 6\nuryyb\r\n\n%s blob 6\nhello\n\n" \
+		$sha1 $sha1 >expect &&
+	test_cmp expect actual
+'
+
+test_done