Merge branch 'cp/textconv-cat-file'

* cp/textconv-cat-file:
  git-cat-file.txt: Document --textconv
  t/t8007: test textconv support for cat-file
  textconv: support for cat_file
  sha1_name: add get_sha1_with_context()

7 files changed, 155 insertions, 15 deletions

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 58c8d65772..9ebbe9402b 100644
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -9,14 +9,15 @@ git-cat-file - Provide content or type and size information for repository objec
 SYNOPSIS
 --------
 [verse]
-'git cat-file' (-t | -s | -e | -p | <type>) <object>
+'git cat-file' (-t | -s | -e | -p | <type> | --textconv ) <object>
 'git cat-file' (--batch | --batch-check) < <list-of-objects>
 
 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.
+object type, or '-s' is used to find the object size, or '--textconv' is used
+(which implies type "blob").
 
 In the second form, a list of objects (separated by linefeeds) is provided on
 stdin, and the SHA1, type, and size of each object is printed on stdout.
@@ -51,6 +52,11 @@ OPTIONS
 	or to ask for a "blob" with <object> being a tag object that
 	points at it.
 
+--textconv::
+	Show the content as transformed by a textconv filter. In this case,
+	<object> has be of the form <treeish>:<path>, or :<path> in order
+	to apply the filter to the content recorded in the index at <path>.
+
 --batch::
 	Print the SHA1, type, size, and contents of each object provided on
 	stdin. May not be combined with any other options or arguments.
diff --git a/builtin.h b/builtin.h
index 1054c6e295..ed6ee26933 100644
--- a/builtin.h
+++ b/builtin.h
@@ -37,6 +37,8 @@ void finish_copy_notes_for_rewrite(struct notes_rewrite_cfg *c);
 
 extern int check_pager_config(const char *cmd);
 
+extern int textconv_object(const char *path, const unsigned char *sha1, char **buf, unsigned long *buf_size);
+
 extern int cmd_add(int argc, const char **argv, const char *prefix);
 extern int cmd_annotate(int argc, const char **argv, const char *prefix);
 extern int cmd_apply(int argc, const char **argv, const char *prefix);
diff --git a/builtin/blame.c b/builtin/blame.c
index 9b88ce9256..01e62fdeb0 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -91,10 +91,10 @@ struct origin {
  * if the textconv driver exists.
  * Return 1 if the conversion succeeds, 0 otherwise.
  */
-static int textconv_object(const char *path,
-			   const unsigned char *sha1,
-			   char **buf,
-			   unsigned long *buf_size)
+int textconv_object(const char *path,
+		    const unsigned char *sha1,
+		    char **buf,
+		    unsigned long *buf_size)
 {
 	struct diff_filespec *df;
 	struct userdiff_driver *textconv;
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index e5118c57da..76ec3fec92 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -9,6 +9,8 @@
 #include "tree.h"
 #include "builtin.h"
 #include "parse-options.h"
+#include "diff.h"
+#include "userdiff.h"
 
 #define BATCH 1
 #define BATCH_CHECK 2
@@ -84,10 +86,11 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 {
 	unsigned char sha1[20];
 	enum object_type type;
-	void *buf;
+	char *buf;
 	unsigned long size;
+	struct object_context obj_context;
 
-	if (get_sha1(obj_name, sha1))
+	if (get_sha1_with_context(obj_name, sha1, &obj_context))
 		die("Not a valid object name %s", obj_name);
 
 	buf = NULL;
@@ -134,6 +137,17 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 
 		/* otherwise just spit out the data */
 		break;
+
+	case 'c':
+		if (!obj_context.path[0])
+			die("git cat-file --textconv %s: <object> must be <sha1:path>",
+			    obj_name);
+
+		if (!textconv_object(obj_context.path, sha1, &buf, &size))
+			die("git cat-file --textconv: unable to run textconv on %s",
+			    obj_name);
+		break;
+
 	case 0:
 		buf = read_object_with_reference(sha1, exp_type, &size, NULL);
 		break;
@@ -203,11 +217,25 @@ static int batch_objects(int print_contents)
 }
 
 static const char * const cat_file_usage[] = {
-	"git cat-file (-t|-s|-e|-p|<type>) <object>",
+	"git cat-file (-t|-s|-e|-p|<type>|--textconv) <object>",
 	"git cat-file (--batch|--batch-check) < <list_of_objects>",
 	NULL
 };
 
+static int git_cat_file_config(const char *var, const char *value, void *cb)
+{
+	switch (userdiff_config(var, value)) {
+	case 0:
+		break;
+	case -1:
+		return -1;
+	default:
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
+
 int cmd_cat_file(int argc, const char **argv, const char *prefix)
 {
 	int opt = 0, batch = 0;
@@ -220,6 +248,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_SET_INT('e', NULL, &opt,
 			    "exit with zero when there's no error", 'e'),
 		OPT_SET_INT('p', NULL, &opt, "pretty-print object's content", 'p'),
+		OPT_SET_INT(0, "textconv", &opt,
+			    "for blob objects, run textconv on object's content", 'c'),
 		OPT_SET_INT(0, "batch", &batch,
 			    "show info and content of objects fed from the standard input",
 			    BATCH),
@@ -229,7 +259,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_END()
 	};
 
-	git_config(git_default_config, NULL);
+	git_config(git_cat_file_config, NULL);
 
 	if (argc != 3 && argc != 2)
 		usage_with_options(cat_file_usage, options);
diff --git a/cache.h b/cache.h
index ff4a7c26d3..c9fa3df7f5 100644
--- a/cache.h
+++ b/cache.h
@@ -750,12 +750,23 @@ static inline unsigned int hexval(unsigned char c)
 #define MINIMUM_ABBREV 4
 #define DEFAULT_ABBREV 7
 
+struct object_context {
+	unsigned char tree[20];
+	char path[PATH_MAX];
+	unsigned mode;
+};
+
 extern int get_sha1(const char *str, unsigned char *sha1);
 extern int get_sha1_with_mode_1(const char *str, unsigned char *sha1, unsigned *mode, int gently, const char *prefix);
 static inline int get_sha1_with_mode(const char *str, unsigned char *sha1, unsigned *mode)
 {
 	return get_sha1_with_mode_1(str, sha1, mode, 1, NULL);
 }
+extern int get_sha1_with_context_1(const char *name, unsigned char *sha1, struct object_context *orc, int gently, const char *prefix);
+static inline int get_sha1_with_context(const char *str, unsigned char *sha1, struct object_context *orc)
+{
+	return get_sha1_with_context_1(str, sha1, orc, 1, NULL);
+}
 extern int get_sha1_hex(const char *hex, unsigned char *sha1);
 extern char *sha1_to_hex(const unsigned char *sha1);	/* static buffer result! */
 extern int read_ref(const char *filename, unsigned char *sha1);
diff --git a/sha1_name.c b/sha1_name.c
index 8cf635af54..4f2af8da93 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -939,8 +939,8 @@ int interpret_branch_name(const char *name, struct strbuf *buf)
  */
 int get_sha1(const char *name, unsigned char *sha1)
 {
-	unsigned unused;
-	return get_sha1_with_mode(name, sha1, &unused);
+	struct object_context unused;
+	return get_sha1_with_context(name, sha1, &unused);
 }
 
 /* Must be called only when object_name:filename doesn't exist. */
@@ -1038,11 +1038,23 @@ static void diagnose_invalid_index_path(int stage,
 
 int get_sha1_with_mode_1(const char *name, unsigned char *sha1, unsigned *mode, int gently, const char *prefix)
 {
+	struct object_context oc;
+	int ret;
+	ret = get_sha1_with_context_1(name, sha1, &oc, gently, prefix);
+	*mode = oc.mode;
+	return ret;
+}
+
+int get_sha1_with_context_1(const char *name, unsigned char *sha1,
+			    struct object_context *oc,
+			    int gently, const char *prefix)
+{
 	int ret, bracket_depth;
 	int namelen = strlen(name);
 	const char *cp;
 
-	*mode = S_IFINVALID;
+	memset(oc, 0, sizeof(*oc));
+	oc->mode = S_IFINVALID;
 	ret = get_sha1_1(name, namelen, sha1);
 	if (!ret)
 		return ret;
@@ -1065,6 +1077,11 @@ int get_sha1_with_mode_1(const char *name, unsigned char *sha1, unsigned *mode,
 			cp = name + 3;
 		}
 		namelen = namelen - (cp - name);
+
+		strncpy(oc->path, cp,
+			sizeof(oc->path));
+		oc->path[sizeof(oc->path)-1] = '\0';
+
 		if (!active_cache)
 			read_cache();
 		pos = cache_name_pos(cp, namelen);
@@ -1077,7 +1094,6 @@ int get_sha1_with_mode_1(const char *name, unsigned char *sha1, unsigned *mode,
 				break;
 			if (ce_stage(ce) == stage) {
 				hashcpy(sha1, ce->sha1);
-				*mode = ce->ce_mode;
 				return 0;
 			}
 			pos++;
@@ -1104,12 +1120,17 @@ int get_sha1_with_mode_1(const char *name, unsigned char *sha1, unsigned *mode,
 		}
 		if (!get_sha1_1(name, cp-name, tree_sha1)) {
 			const char *filename = cp+1;
-			ret = get_tree_entry(tree_sha1, filename, sha1, mode);
+			ret = get_tree_entry(tree_sha1, filename, sha1, &oc->mode);
 			if (!gently) {
 				diagnose_invalid_sha1_path(prefix, filename,
 							   tree_sha1, object_name);
 				free(object_name);
 			}
+			hashcpy(oc->tree, tree_sha1);
+			strncpy(oc->path, filename,
+				sizeof(oc->path));
+			oc->path[sizeof(oc->path)-1] = '\0';
+
 			return ret;
 		} else {
 			if (!gently)
diff --git a/t/t8007-cat-file-textconv.sh b/t/t8007-cat-file-textconv.sh
new file mode 100755
index 0000000000..38ac05e4a0
--- /dev/null
+++ b/t/t8007-cat-file-textconv.sh
@@ -0,0 +1,70 @@
+#!/bin/sh
+
+test_description='git cat-file textconv support'
+. ./test-lib.sh
+
+cat >helper <<'EOF'
+#!/bin/sh
+sed 's/^/converted: /' "$@"
+EOF
+chmod +x helper
+
+test_expect_success 'setup ' '
+	echo test >one.bin &&
+	git add . &&
+	GIT_AUTHOR_NAME=Number1 git commit -a -m First --date="2010-01-01 18:00:00" &&
+	echo test version 2 >one.bin &&
+	GIT_AUTHOR_NAME=Number2 git commit -a -m Second --date="2010-01-01 20:00:00"
+'
+
+cat >expected <<EOF
+fatal: git cat-file --textconv: unable to run textconv on :one.bin
+EOF
+
+test_expect_success 'no filter specified' '
+	git cat-file --textconv :one.bin 2>result
+	test_cmp expected result
+'
+
+test_expect_success 'setup textconv filters' '
+	echo "*.bin diff=test" >.gitattributes &&
+	git config diff.test.textconv ./helper &&
+	git config diff.test.cachetextconv false
+'
+
+cat >expected <<EOF
+test version 2
+EOF
+
+test_expect_success 'cat-file without --textconv' '
+	git cat-file blob :one.bin >result &&
+	test_cmp expected result
+'
+
+cat >expected <<EOF
+test
+EOF
+
+test_expect_success 'cat-file without --textconv on previous commit' '
+	git cat-file -p HEAD^:one.bin >result &&
+	test_cmp expected result
+'
+
+cat >expected <<EOF
+converted: test version 2
+EOF
+
+test_expect_success 'cat-file --textconv on last commit' '
+	git cat-file --textconv :one.bin >result &&
+	test_cmp expected result
+'
+
+cat >expected <<EOF
+converted: test
+EOF
+
+test_expect_success 'cat-file --textconv on previous commit' '
+	git cat-file --textconv HEAD^:one.bin >result &&
+	test_cmp expected result
+'
+test_done