cat-file --textconv/--filters: allow specifying the path separately

dscho · gitster · commit 7bcf34145357 · 2016-09-11T14:48:15.000-07:00
There are circumstances when it is relatively easy to figure out the object name for a given path, but not the name of the containing tree. For example, when looking at a diff generated by Git, the object names are recorded, but not the revision. As a matter of fact, the revisions from which the diff was generated may not even exist locally. In such a case, the user would have to generate a fake revision just to be able to use --textconv or --filters. Let's simplify this dramatically, because we do not really need that revision at all: all we care about is that we know the path. In the scenario described above, we do know the path, and we just want to specify it separately from the object name. Example usage: git cat-file --textconv --path=main.c 0f1937f Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
@@ -9,7 +9,7 @@ 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 | --filters ) <object>
+'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) [--follow-symlinks]
 
 DESCRIPTION
@@ -64,6 +64,11 @@ OPTIONS
 	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
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
@@ -20,6 +20,8 @@ struct batch_options {
 	const char *format;
 };
 
+static const char *force_path;
+
 static int filter_object(const char *path, unsigned mode,
 			 const unsigned char *sha1,
 			 char **buf, unsigned long *size)
@@ -53,13 +55,19 @@ 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;
 
 	if (get_sha1_with_context(obj_name, 0, sha1, &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':
@@ -84,21 +92,22 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 		return !has_sha1_file(sha1);
 
 	case 'w':
-		if (!obj_context.path[0])
+		if (!path[0])
 			die("git cat-file --filters %s: <object> must be "
 			    "<sha1:path>", obj_name);
 
-		if (filter_object(obj_context.path, obj_context.mode,
+		if (filter_object(path, obj_context.mode,
 				  sha1, &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, sha1, 1, &buf, &size))
+		if (textconv_object(path, obj_context.mode,
+				    sha1, 1, &buf, &size))
 			break;
 
 	case 'p':
@@ -472,7 +481,7 @@ 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|--filters) <object>"),
+	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]"),
 	NULL
 };
@@ -520,6 +529,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 			    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")),
@@ -562,6 +573,11 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		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 (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
@@ -31,4 +31,24 @@ test_expect_success 'cat-file --filters converts to worktree version' '
 	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_done
