Merge branch 'ab/blame-textconv'

* ab/blame-textconv:
  t/t8006: test textconv support for blame
  textconv: support for blame
  textconv: make the API public

Conflicts:
	diff.h

builtin/blame.c

@@ -20,6 +20,7 @@
 #include "mailmap.h"
 #include "parse-options.h"
 #include "utf8.h"
+#include "userdiff.h"
 
 static char blame_usage[] = "git blame [options] [rev-opts] [rev] [--] file";
 
@@ -85,17 +86,51 @@ struct origin {
 	char path[FLEX_ARRAY];
 };
 
+/*
+ * Prepare diff_filespec and convert it using diff textconv API
+ * 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)
+{
+	struct diff_filespec *df;
+	struct userdiff_driver *textconv;
+
+	df = alloc_filespec(path);
+	fill_filespec(df, sha1, S_IFREG | 0664);
+	textconv = get_textconv(df);
+	if (!textconv) {
+		free_filespec(df);
+		return 0;
+	}
+
+	*buf_size = fill_textconv(textconv, df, buf);
+	free_filespec(df);
+	return 1;
+}
+
 /*
  * Given an origin, prepare mmfile_t structure to be used by the
  * diff machinery
  */
-static void fill_origin_blob(struct origin *o, mmfile_t *file)
+static void fill_origin_blob(struct diff_options *opt,
+			     struct origin *o, mmfile_t *file)
 {
 	if (!o->file.ptr) {
 		enum object_type type;
+		unsigned long file_size;
+
 		num_read_blob++;
-		file->ptr = read_sha1_file(o->blob_sha1, &type,
-					   (unsigned long *)(&(file->size)));
+		if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) &&
+		    textconv_object(o->path, o->blob_sha1, &file->ptr, &file_size))
+			;
+		else
+			file->ptr = read_sha1_file(o->blob_sha1, &type, &file_size);
+		file->size = file_size;
+
 		if (!file->ptr)
 			die("Cannot read blob %s for path %s",
 			    sha1_to_hex(o->blob_sha1),
@@ -282,7 +317,6 @@ static struct origin *get_origin(struct scoreboard *sb,
 static int fill_blob_sha1(struct origin *origin)
 {
 	unsigned mode;
-
 	if (!is_null_sha1(origin->blob_sha1))
 		return 0;
 	if (get_tree_entry(origin->commit->object.sha1,
@@ -742,8 +776,8 @@ static int pass_blame_to_parent(struct scoreboard *sb,
 	if (last_in_target < 0)
 		return 1; /* nothing remains for this target */
 
-	fill_origin_blob(parent, &file_p);
-	fill_origin_blob(target, &file_o);
+	fill_origin_blob(&sb->revs->diffopt, parent, &file_p);
+	fill_origin_blob(&sb->revs->diffopt, target, &file_o);
 	num_get_patch++;
 
 	memset(&xpp, 0, sizeof(xpp));
@@ -924,7 +958,7 @@ static int find_move_in_parent(struct scoreboard *sb,
 	if (last_in_target < 0)
 		return 1; /* nothing remains for this target */
 
-	fill_origin_blob(parent, &file_p);
+	fill_origin_blob(&sb->revs->diffopt, parent, &file_p);
 	if (!file_p.ptr)
 		return 0;
 
@@ -1065,7 +1099,7 @@ static int find_copy_in_parent(struct scoreboard *sb,
 
 			norigin = get_origin(sb, parent, p->one->path);
 			hashcpy(norigin->blob_sha1, p->one->sha1);
-			fill_origin_blob(norigin, &file_p);
+			fill_origin_blob(&sb->revs->diffopt, norigin, &file_p);
 			if (!file_p.ptr)
 				continue;
 
@@ -1985,6 +2019,16 @@ static int git_blame_config(const char *var, const char *value, void *cb)
 		blame_date_mode = parse_date_format(value);
 		return 0;
 	}
+
+	switch (userdiff_config(var, value)) {
+	case 0:
+		break;
+	case -1:
+		return -1;
+	default:
+		return 0;
+	}
+
 	return git_default_config(var, value, cb);
 }
 
@@ -1992,7 +2036,9 @@ static int git_blame_config(const char *var, const char *value, void *cb)
  * Prepare a dummy commit that represents the work tree (or staged) item.
  * Note that annotating work tree item never works in the reverse.
  */
-static struct commit *fake_working_tree_commit(const char *path, const char *contents_from)
+static struct commit *fake_working_tree_commit(struct diff_options *opt,
+					       const char *path,
+					       const char *contents_from)
 {
 	struct commit *commit;
 	struct origin *origin;
@@ -2020,6 +2066,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
 	if (!contents_from || strcmp("-", contents_from)) {
 		struct stat st;
 		const char *read_from;
+		unsigned long buf_len;
 
 		if (contents_from) {
 			if (stat(contents_from, &st) < 0)
@@ -2032,9 +2079,13 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
 			read_from = path;
 		}
 		mode = canon_mode(st.st_mode);
+
 		switch (st.st_mode & S_IFMT) {
 		case S_IFREG:
-			if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
+			if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) &&
+			    textconv_object(read_from, null_sha1, &buf.buf, &buf_len))
+				buf.len = buf_len;
+			else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
 				die_errno("cannot open or read '%s'", read_from);
 			break;
 		case S_IFLNK:
@@ -2250,6 +2301,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 	git_config(git_blame_config, NULL);
 	init_revisions(&revs, NULL);
 	revs.date_mode = blame_date_mode;
+	DIFF_OPT_SET(&revs.diffopt, ALLOW_TEXTCONV);
 
 	save_commit_buffer = 0;
 	dashdash_pos = 0;
@@ -2386,7 +2438,8 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		 * or "--contents".
 		 */
 		setup_work_tree();
-		sb.final = fake_working_tree_commit(path, contents_from);
+		sb.final = fake_working_tree_commit(&sb.revs->diffopt,
+						    path, contents_from);
 		add_pending_object(&revs, &(sb.final->object), ":");
 	}
 	else if (contents_from)
@@ -2413,8 +2466,14 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		if (fill_blob_sha1(o))
 			die("no such path %s in %s", path, final_commit_name);
 
-		sb.final_buf = read_sha1_file(o->blob_sha1, &type,
-					      &sb.final_buf_size);
+		if (DIFF_OPT_TST(&sb.revs->diffopt, ALLOW_TEXTCONV) &&
+		    textconv_object(path, o->blob_sha1, (char **) &sb.final_buf,
+				    &sb.final_buf_size))
+			;
+		else
+			sb.final_buf = read_sha1_file(o->blob_sha1, &type,
+						      &sb.final_buf_size);
+
 		if (!sb.final_buf)
 			die("Cannot read blob %s for path %s",
 			    sha1_to_hex(o->blob_sha1),

diff.c

@@ -44,10 +44,6 @@ static char diff_colors[][COLOR_MAXLEN] = {
 	GIT_COLOR_NORMAL,	/* FUNCINFO */
 };
 
-static void diff_filespec_load_driver(struct diff_filespec *one);
-static size_t fill_textconv(struct userdiff_driver *driver,
-			    struct diff_filespec *df, char **outbuf);
-
 static int parse_diff_color_slot(const char *var, int ofs)
 {
 	if (!strcasecmp(var+ofs, "plain"))
@@ -1810,7 +1806,7 @@ void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const
 		options->b_prefix = b;
 }
 
-static struct userdiff_driver *get_textconv(struct diff_filespec *one)
+struct userdiff_driver *get_textconv(struct diff_filespec *one)
 {
 	if (!DIFF_FILE_VALID(one))
 		return NULL;
@@ -4243,9 +4239,9 @@ static char *run_textconv(const char *pgm, struct diff_filespec *spec,
 	return strbuf_detach(&buf, outsize);
 }
 
-static size_t fill_textconv(struct userdiff_driver *driver,
-			    struct diff_filespec *df,
-			    char **outbuf)
+size_t fill_textconv(struct userdiff_driver *driver,
+		     struct diff_filespec *df,
+		     char **outbuf)
 {
 	size_t size;
 

diff.h

@@ -10,6 +10,8 @@ struct rev_info;
 struct diff_options;
 struct diff_queue_struct;
 struct strbuf;
+struct diff_filespec;
+struct userdiff_driver;
 
 typedef void (*change_fn_t)(struct diff_options *options,
 		 unsigned old_mode, unsigned new_mode,
@@ -74,6 +76,7 @@ typedef struct strbuf *(*diff_prefix_fn_t)(struct diff_options *opt, void *data)
 #define DIFF_OPT_SUBMODULE_LOG       (1 << 23)
 #define DIFF_OPT_DIRTY_SUBMODULES    (1 << 24)
 #define DIFF_OPT_IGNORE_UNTRACKED_IN_SUBMODULES (1 << 25)
+#define DIFF_OPT_IGNORE_DIRTY_SUBMODULES (1 << 26)
 
 #define DIFF_OPT_TST(opts, flag)    ((opts)->flags & DIFF_OPT_##flag)
 #define DIFF_OPT_SET(opts, flag)    ((opts)->flags |= DIFF_OPT_##flag)
@@ -292,4 +295,10 @@ extern void diff_no_index(struct rev_info *, int, const char **, int, const char
 
 extern int index_differs_from(const char *def, int diff_flags);
 
+extern size_t fill_textconv(struct userdiff_driver *driver,
+			    struct diff_filespec *df,
+			    char **outbuf);
+
+extern struct userdiff_driver *get_textconv(struct diff_filespec *one);
+
 #endif /* DIFF_H */

t/t8006-blame-textconv.sh

@@ -0,0 +1,80 @@
+#!/bin/sh
+
+test_description='git blame textconv support'
+. ./test-lib.sh
+
+find_blame() {
+	sed -e 's/^[^(]*//'
+}
+
+cat >helper <<'EOF'
+#!/bin/sh
+sed 's/^/converted: /' "$@"
+EOF
+chmod +x helper
+
+test_expect_success 'setup ' '
+	echo test 1 >one.bin &&
+	echo test number 2 >two.bin &&
+	git add . &&
+	GIT_AUTHOR_NAME=Number1 git commit -a -m First --date="2010-01-01 18:00:00" &&
+	echo test 1 version 2 >one.bin &&
+	echo test number 2 version 2 >>two.bin &&
+	GIT_AUTHOR_NAME=Number2 git commit -a -m Second --date="2010-01-01 20:00:00"
+'
+
+cat >expected <<EOF
+(Number2 2010-01-01 20:00:00 +0000 1) test 1 version 2
+EOF
+
+test_expect_success 'no filter specified' '
+	git blame one.bin >blame &&
+	find_blame Number2 <blame >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
+'
+
+test_expect_success 'blame with --no-textconv' '
+	git blame --no-textconv one.bin >blame &&
+	find_blame <blame> result &&
+	test_cmp expected result
+'
+
+cat >expected <<EOF
+(Number2 2010-01-01 20:00:00 +0000 1) converted: test 1 version 2
+EOF
+
+test_expect_success 'basic blame on last commit' '
+	git blame one.bin >blame &&
+	find_blame  <blame >result &&
+	test_cmp expected result
+'
+
+cat >expected <<EOF
+(Number1 2010-01-01 18:00:00 +0000 1) converted: test number 2
+(Number2 2010-01-01 20:00:00 +0000 2) converted: test number 2 version 2
+EOF
+
+test_expect_success 'blame --textconv going through revisions' '
+	git blame --textconv two.bin >blame &&
+	find_blame <blame >result &&
+	test_cmp expected result
+'
+
+test_expect_success 'make a new commit' '
+	echo "test number 2 version 3" >>two.bin &&
+	GIT_AUTHOR_NAME=Number3 git commit -a -m Third --date="2010-01-01 22:00:00"
+'
+
+test_expect_success 'blame from previous revision' '
+	git blame HEAD^ two.bin >blame &&
+	find_blame <blame >result &&
+	test_cmp expected result
+'
+
+test_done