1 files changed, 168 insertions, 118 deletions

diff --git a/diff.c b/diff.c
index 377ec1ea4c..e6846ca750 100644
--- a/diff.c
+++ b/diff.c
@@ -574,6 +574,7 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 	if (!endp) {
 		const char *plain = diff_get_color(ecb->color_diff,
 						   DIFF_PLAIN);
+		putc('\n', ecb->opt->file);
 		emit_line_0(ecb->opt, plain, reset, '\\',
 			    nneof, strlen(nneof));
 	}
@@ -989,10 +990,74 @@ static void diff_words_flush(struct emit_callback *ecbdata)
 		diff_words_show(ecbdata->diff_words);
 }
 
+static void diff_filespec_load_driver(struct diff_filespec *one)
+{
+	/* Use already-loaded driver */
+	if (one->driver)
+		return;
+
+	if (S_ISREG(one->mode))
+		one->driver = userdiff_find_by_path(one->path);
+
+	/* Fallback to default settings */
+	if (!one->driver)
+		one->driver = userdiff_find_by_name("default");
+}
+
+static const char *userdiff_word_regex(struct diff_filespec *one)
+{
+	diff_filespec_load_driver(one);
+	return one->driver->word_regex;
+}
+
+static void init_diff_words_data(struct emit_callback *ecbdata,
+				 struct diff_options *orig_opts,
+				 struct diff_filespec *one,
+				 struct diff_filespec *two)
+{
+	int i;
+	struct diff_options *o = xmalloc(sizeof(struct diff_options));
+	memcpy(o, orig_opts, sizeof(struct diff_options));
+
+	ecbdata->diff_words =
+		xcalloc(1, sizeof(struct diff_words_data));
+	ecbdata->diff_words->type = o->word_diff;
+	ecbdata->diff_words->opt = o;
+	if (!o->word_regex)
+		o->word_regex = userdiff_word_regex(one);
+	if (!o->word_regex)
+		o->word_regex = userdiff_word_regex(two);
+	if (!o->word_regex)
+		o->word_regex = diff_word_regex_cfg;
+	if (o->word_regex) {
+		ecbdata->diff_words->word_regex = (regex_t *)
+			xmalloc(sizeof(regex_t));
+		if (regcomp(ecbdata->diff_words->word_regex,
+			    o->word_regex,
+			    REG_EXTENDED | REG_NEWLINE))
+			die ("Invalid regular expression: %s",
+			     o->word_regex);
+	}
+	for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
+		if (o->word_diff == diff_words_styles[i].type) {
+			ecbdata->diff_words->style =
+				&diff_words_styles[i];
+			break;
+		}
+	}
+	if (want_color(o->use_color)) {
+		struct diff_words_style *st = ecbdata->diff_words->style;
+		st->old.color = diff_get_color_opt(o, DIFF_FILE_OLD);
+		st->new.color = diff_get_color_opt(o, DIFF_FILE_NEW);
+		st->ctx.color = diff_get_color_opt(o, DIFF_PLAIN);
+	}
+}
+
 static void free_diff_words_data(struct emit_callback *ecbdata)
 {
 	if (ecbdata->diff_words) {
 		diff_words_flush(ecbdata);
+		free (ecbdata->diff_words->opt);
 		free (ecbdata->diff_words->minus.text.ptr);
 		free (ecbdata->diff_words->minus.orig);
 		free (ecbdata->diff_words->plus.text.ptr);
@@ -1333,7 +1398,7 @@ int print_stat_summary(FILE *fp, int files, int insertions, int deletions)
 
 	if (!files) {
 		assert(insertions == 0 && deletions == 0);
-		return fputs(_(" 0 files changed\n"), fp);
+		return fprintf(fp, "%s\n", _(" 0 files changed"));
 	}
 
 	strbuf_addf(&sb,
@@ -1379,8 +1444,8 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 {
 	int i, len, add, del, adds = 0, dels = 0;
 	uintmax_t max_change = 0, max_len = 0;
-	int total_files = data->nr;
-	int width, name_width, graph_width, number_width = 4, count;
+	int total_files = data->nr, count;
+	int width, name_width, graph_width, number_width = 0, bin_width = 0;
 	const char *reset, *add_c, *del_c;
 	const char *line_prefix = "";
 	int extra_shown = 0;
@@ -1416,8 +1481,21 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (max_len < len)
 			max_len = len;
 
-		if (file->is_binary || file->is_unmerged)
+		if (file->is_unmerged) {
+			/* "Unmerged" is 8 characters */
+			bin_width = bin_width < 8 ? 8 : bin_width;
 			continue;
+		}
+		if (file->is_binary) {
+			/* "Bin XXX -> YYY bytes" */
+			int w = 14 + decimal_width(file->added)
+				+ decimal_width(file->deleted);
+			bin_width = bin_width < w ? w : bin_width;
+			/* Display change counts aligned with "Bin" */
+			number_width = 3;
+			continue;
+		}
+
 		if (max_change < change)
 			max_change = change;
 	}
@@ -1442,12 +1520,22 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 	 * stat_name_width fixes the maximum width of the filename,
 	 * and is also used to divide available columns if there
 	 * aren't enough.
+	 *
+	 * Binary files are displayed with "Bin XXX -> YYY bytes"
+	 * instead of the change count and graph. This part is treated
+	 * similarly to the graph part, except that it is not
+	 * "scaled". If total width is too small to accomodate the
+	 * guaranteed minimum width of the filename part and the
+	 * separators and this message, this message will "overflow"
+	 * making the line longer than the maximum width.
 	 */
 
 	if (options->stat_width == -1)
-		width = term_columns();
+		width = term_columns() - options->output_prefix_length;
 	else
 		width = options->stat_width ? options->stat_width : 80;
+	number_width = decimal_width(max_change) > number_width ?
+		decimal_width(max_change) : number_width;
 
 	if (options->stat_graph_width == -1)
 		options->stat_graph_width = diff_stat_graph_width;
@@ -1461,10 +1549,14 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 
 	/*
 	 * First assign sizes that are wanted, ignoring available width.
+	 * strlen("Bin XXX -> YYY bytes") == bin_width, and the part
+	 * starting from "XXX" should fit in graph_width.
 	 */
-	graph_width = (options->stat_graph_width &&
-		       options->stat_graph_width < max_change) ?
-		options->stat_graph_width : max_change;
+	graph_width = max_change + 4 > bin_width ? max_change : bin_width - 4;
+	if (options->stat_graph_width &&
+	    options->stat_graph_width < graph_width)
+		graph_width = options->stat_graph_width;
+
 	name_width = (options->stat_name_width > 0 &&
 		      options->stat_name_width < max_len) ?
 		options->stat_name_width : max_len;
@@ -1473,8 +1565,12 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 	 * Adjust adjustable widths not to exceed maximum width
 	 */
 	if (name_width + number_width + 6 + graph_width > width) {
-		if (graph_width > width * 3/8 - number_width - 6)
+		if (graph_width > width * 3/8 - number_width - 6) {
 			graph_width = width * 3/8 - number_width - 6;
+			if (graph_width < 6)
+				graph_width = 6;
+		}
+
 		if (options->stat_graph_width &&
 		    graph_width > options->stat_graph_width)
 			graph_width = options->stat_graph_width;
@@ -1519,8 +1615,12 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (data->files[i]->is_binary) {
 			fprintf(options->file, "%s", line_prefix);
 			show_name(options->file, prefix, name, len);
-			fprintf(options->file, "  Bin ");
-			fprintf(options->file, "%s%"PRIuMAX"%s",
+			fprintf(options->file, " %*s", number_width, "Bin");
+			if (!added && !deleted) {
+				putc('\n', options->file);
+				continue;
+			}
+			fprintf(options->file, " %s%"PRIuMAX"%s",
 				del_c, deleted, reset);
 			fprintf(options->file, " -> ");
 			fprintf(options->file, "%s%"PRIuMAX"%s",
@@ -1532,7 +1632,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		else if (data->files[i]->is_unmerged) {
 			fprintf(options->file, "%s", line_prefix);
 			show_name(options->file, prefix, name, len);
-			fprintf(options->file, "  Unmerged\n");
+			fprintf(options->file, " Unmerged\n");
 			continue;
 		}
 
@@ -1561,8 +1661,9 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		}
 		fprintf(options->file, "%s", line_prefix);
 		show_name(options->file, prefix, name, len);
-		fprintf(options->file, "%5"PRIuMAX"%s", added + deleted,
-				added + deleted ? " " : "");
+		fprintf(options->file, " %*"PRIuMAX"%s",
+			number_width, added + deleted,
+			added + deleted ? " " : "");
 		show_graph(options->file, '+', add, add_c, reset);
 		show_graph(options->file, '-', del, del_c, reset);
 		fprintf(options->file, "\n");
@@ -1593,17 +1694,16 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 		return;
 
 	for (i = 0; i < data->nr; i++) {
-		if (!data->files[i]->is_binary &&
-		    !data->files[i]->is_unmerged) {
-			int added = data->files[i]->added;
-			int deleted= data->files[i]->deleted;
-			if (!data->files[i]->is_renamed &&
-			    (added + deleted == 0)) {
-				total_files--;
-			} else {
-				adds += added;
-				dels += deleted;
-			}
+		int added = data->files[i]->added;
+		int deleted= data->files[i]->deleted;
+
+		if (data->files[i]->is_unmerged)
+			continue;
+		if (!data->files[i]->is_renamed && (added + deleted == 0)) {
+			total_files--;
+		} else if (!data->files[i]->is_binary) { /* don't count bytes */
+			adds += added;
+			dels += deleted;
 		}
 	}
 	if (options->output_prefix) {
@@ -2061,20 +2161,6 @@ static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, char *pre
 	emit_binary_diff_body(file, two, one, prefix);
 }
 
-static void diff_filespec_load_driver(struct diff_filespec *one)
-{
-	/* Use already-loaded driver */
-	if (one->driver)
-		return;
-
-	if (S_ISREG(one->mode))
-		one->driver = userdiff_find_by_path(one->path);
-
-	/* Fallback to default settings */
-	if (!one->driver)
-		one->driver = userdiff_find_by_name("default");
-}
-
 int diff_filespec_is_binary(struct diff_filespec *one)
 {
 	if (one->is_binary == -1) {
@@ -2100,12 +2186,6 @@ static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespe
 	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
 }
 
-static const char *userdiff_word_regex(struct diff_filespec *one)
-{
-	diff_filespec_load_driver(one);
-	return one->driver->word_regex;
-}
-
 void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
 {
 	if (!options->a_prefix)
@@ -2292,42 +2372,8 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
 		else if (!prefixcmp(diffopts, "-u"))
 			xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
-		if (o->word_diff) {
-			int i;
-
-			ecbdata.diff_words =
-				xcalloc(1, sizeof(struct diff_words_data));
-			ecbdata.diff_words->type = o->word_diff;
-			ecbdata.diff_words->opt = o;
-			if (!o->word_regex)
-				o->word_regex = userdiff_word_regex(one);
-			if (!o->word_regex)
-				o->word_regex = userdiff_word_regex(two);
-			if (!o->word_regex)
-				o->word_regex = diff_word_regex_cfg;
-			if (o->word_regex) {
-				ecbdata.diff_words->word_regex = (regex_t *)
-					xmalloc(sizeof(regex_t));
-				if (regcomp(ecbdata.diff_words->word_regex,
-						o->word_regex,
-						REG_EXTENDED | REG_NEWLINE))
-					die ("Invalid regular expression: %s",
-							o->word_regex);
-			}
-			for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
-				if (o->word_diff == diff_words_styles[i].type) {
-					ecbdata.diff_words->style =
-						&diff_words_styles[i];
-					break;
-				}
-			}
-			if (want_color(o->use_color)) {
-				struct diff_words_style *st = ecbdata.diff_words->style;
-				st->old.color = diff_get_color_opt(o, DIFF_FILE_OLD);
-				st->new.color = diff_get_color_opt(o, DIFF_FILE_NEW);
-				st->ctx.color = diff_get_color_opt(o, DIFF_PLAIN);
-			}
-		}
+		if (o->word_diff)
+			init_diff_words_data(&ecbdata, o, one, two);
 		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 			      &xpp, &xecfg);
 		if (o->word_diff)
@@ -2357,6 +2403,7 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 {
 	mmfile_t mf1, mf2;
 	struct diffstat_file *data;
+	int same_contents;
 
 	data = diffstat_add(diffstat, name_a, name_b);
 
@@ -2365,10 +2412,17 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		return;
 	}
 
+	same_contents = !hashcmp(one->sha1, two->sha1);
+
 	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
 		data->is_binary = 1;
-		data->added = diff_filespec_size(two);
-		data->deleted = diff_filespec_size(one);
+		if (same_contents) {
+			data->added = 0;
+			data->deleted = 0;
+		} else {
+			data->added = diff_filespec_size(two);
+			data->deleted = diff_filespec_size(one);
+		}
 	}
 
 	else if (complete_rewrite) {
@@ -2378,7 +2432,7 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		data->added = count_lines(two->data, two->size);
 	}
 
-	else {
+	else if (!same_contents) {
 		/* Crazy xdl interfaces.. */
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
@@ -2488,12 +2542,12 @@ void free_filespec(struct diff_filespec *spec)
 }
 
 void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
-		   unsigned short mode)
+		   int sha1_valid, unsigned short mode)
 {
 	if (mode) {
 		spec->mode = canon_mode(mode);
 		hashcpy(spec->sha1, sha1);
-		spec->sha1_valid = !is_null_sha1(sha1);
+		spec->sha1_valid = sha1_valid;
 	}
 }
 
@@ -2566,22 +2620,6 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	return 0;
 }
 
-static int populate_from_stdin(struct diff_filespec *s)
-{
-	struct strbuf buf = STRBUF_INIT;
-	size_t size = 0;
-
-	if (strbuf_read(&buf, 0, 0) < 0)
-		return error("error while reading from stdin %s",
-				     strerror(errno));
-
-	s->should_munmap = 0;
-	s->data = strbuf_detach(&buf, &size);
-	s->size = size;
-	s->should_free = 1;
-	return 0;
-}
-
 static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
 {
 	int len;
@@ -2631,9 +2669,6 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only)
 		struct stat st;
 		int fd;
 
-		if (!strcmp(s->path, "-"))
-			return populate_from_stdin(s);
-
 		if (lstat(s->path, &st) < 0) {
 			if (errno == ENOENT) {
 			err_empty:
@@ -2958,9 +2993,8 @@ static void run_diff_cmd(const char *pgm,
 	int complete_rewrite = (p->status == DIFF_STATUS_MODIFIED) && p->score;
 	int must_show_header = 0;
 
-	if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
-		pgm = NULL;
-	else {
+
+	if (DIFF_OPT_TST(o, ALLOW_EXTERNAL)) {
 		struct userdiff_driver *drv = userdiff_find_by_path(attr_path);
 		if (drv && drv->external)
 			pgm = drv->external;
@@ -2995,7 +3029,7 @@ static void diff_fill_sha1_info(struct diff_filespec *one)
 	if (DIFF_FILE_VALID(one)) {
 		if (!one->sha1_valid) {
 			struct stat st;
-			if (!strcmp(one->path, "-")) {
+			if (one->is_stdin) {
 				hashcpy(one->sha1, null_sha1);
 				return;
 			}
@@ -3040,6 +3074,9 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 	if (o->prefix_length)
 		strip_prefix(o->prefix_length, &name, &other);
 
+	if (!DIFF_OPT_TST(o, ALLOW_EXTERNAL))
+		pgm = NULL;
+
 	if (DIFF_PAIR_UNMERGED(p)) {
 		run_diff_cmd(pgm, name, NULL, attr_path,
 			     NULL, NULL, NULL, o, p);
@@ -3136,6 +3173,7 @@ void diff_setup(struct diff_options *options)
 	options->rename_limit = -1;
 	options->dirstat_permille = diff_dirstat_permille_default;
 	options->context = 3;
+	DIFF_OPT_SET(options, RENAME_EMPTY);
 
 	options->change = diff_change;
 	options->add_remove = diff_addremove;
@@ -3150,7 +3188,7 @@ void diff_setup(struct diff_options *options)
 	}
 }
 
-int diff_setup_done(struct diff_options *options)
+void diff_setup_done(struct diff_options *options)
 {
 	int count = 0;
 
@@ -3249,8 +3287,6 @@ int diff_setup_done(struct diff_options *options)
 		options->output_format = DIFF_FORMAT_NO_OUTPUT;
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	}
-
-	return 0;
 }
 
 static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
@@ -3506,6 +3542,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 	else if (!strcmp(arg, "--no-renames"))
 		options->detect_rename = 0;
+	else if (!strcmp(arg, "--rename-empty"))
+		DIFF_OPT_SET(options, RENAME_EMPTY);
+	else if (!strcmp(arg, "--no-rename-empty"))
+		DIFF_OPT_CLR(options, RENAME_EMPTY);
 	else if (!strcmp(arg, "--relative"))
 		DIFF_OPT_SET(options, RELATIVE_NAME);
 	else if (!prefixcmp(arg, "--relative=")) {
@@ -3525,9 +3565,9 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	else if (!strcmp(arg, "--ignore-space-at-eol"))
 		DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
 	else if (!strcmp(arg, "--patience"))
-		DIFF_XDL_SET(options, PATIENCE_DIFF);
+		options->xdl_opts = DIFF_WITH_ALG(options, PATIENCE_DIFF);
 	else if (!strcmp(arg, "--histogram"))
-		DIFF_XDL_SET(options, HISTOGRAM_DIFF);
+		options->xdl_opts = DIFF_WITH_ALG(options, HISTOGRAM_DIFF);
 
 	/* flags options */
 	else if (!strcmp(arg, "--binary")) {
@@ -4399,6 +4439,12 @@ void diff_flush(struct diff_options *options)
 
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
+			if (options->output_prefix) {
+				struct strbuf *msg = NULL;
+				msg = options->output_prefix(options,
+					options->output_prefix_data);
+				fwrite(msg->buf, msg->len, 1, stdout);
+			}
 			putc(options->line_termination, options->file);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
@@ -4646,6 +4692,7 @@ static int is_submodule_ignored(const char *path, struct diff_options *options)
 void diff_addremove(struct diff_options *options,
 		    int addremove, unsigned mode,
 		    const unsigned char *sha1,
+		    int sha1_valid,
 		    const char *concatpath, unsigned dirty_submodule)
 {
 	struct diff_filespec *one, *two;
@@ -4677,9 +4724,9 @@ void diff_addremove(struct diff_options *options,
 	two = alloc_filespec(concatpath);
 
 	if (addremove != '+')
-		fill_filespec(one, sha1, mode);
+		fill_filespec(one, sha1, sha1_valid, mode);
 	if (addremove != '-') {
-		fill_filespec(two, sha1, mode);
+		fill_filespec(two, sha1, sha1_valid, mode);
 		two->dirty_submodule = dirty_submodule;
 	}
 
@@ -4692,6 +4739,7 @@ void diff_change(struct diff_options *options,
 		 unsigned old_mode, unsigned new_mode,
 		 const unsigned char *old_sha1,
 		 const unsigned char *new_sha1,
+		 int old_sha1_valid, int new_sha1_valid,
 		 const char *concatpath,
 		 unsigned old_dirty_submodule, unsigned new_dirty_submodule)
 {
@@ -4706,6 +4754,8 @@ void diff_change(struct diff_options *options,
 		const unsigned char *tmp_c;
 		tmp = old_mode; old_mode = new_mode; new_mode = tmp;
 		tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
+		tmp = old_sha1_valid; old_sha1_valid = new_sha1_valid;
+			new_sha1_valid = tmp;
 		tmp = old_dirty_submodule; old_dirty_submodule = new_dirty_submodule;
 			new_dirty_submodule = tmp;
 	}
@@ -4716,8 +4766,8 @@ void diff_change(struct diff_options *options,
 
 	one = alloc_filespec(concatpath);
 	two = alloc_filespec(concatpath);
-	fill_filespec(one, old_sha1, old_mode);
-	fill_filespec(two, new_sha1, new_mode);
+	fill_filespec(one, old_sha1, old_sha1_valid, old_mode);
+	fill_filespec(two, new_sha1, new_sha1_valid, new_mode);
 	one->dirty_submodule = old_dirty_submodule;
 	two->dirty_submodule = new_dirty_submodule;