1 files changed, 434 insertions, 212 deletions

diff --git a/diff.c b/diff.c
index 7e154265f7..732d4c2275 100644
--- a/diff.c
+++ b/diff.c
@@ -15,6 +15,7 @@
 #include "sigchain.h"
 #include "submodule.h"
 #include "ll-merge.h"
+#include "string-list.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -25,12 +26,14 @@
 static int diff_detect_rename_default;
 static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
-int diff_use_color_default = -1;
+static int diff_use_color_default = -1;
+static int diff_context_default = 3;
 static const char *diff_word_regex_cfg;
 static const char *external_diff_cmd_cfg;
 int diff_auto_refresh_index = 1;
 static int diff_mnemonic_prefix;
 static int diff_no_prefix;
+static int diff_stat_graph_width;
 static int diff_dirstat_permille_default = 30;
 static struct diff_options default_diff_options;
 
@@ -67,26 +70,30 @@ static int parse_diff_color_slot(const char *var, int ofs)
 	return -1;
 }
 
-static int parse_dirstat_params(struct diff_options *options, const char *params,
+static int parse_dirstat_params(struct diff_options *options, const char *params_string,
 				struct strbuf *errmsg)
 {
-	const char *p = params;
-	int p_len, ret = 0;
+	char *params_copy = xstrdup(params_string);
+	struct string_list params = STRING_LIST_INIT_NODUP;
+	int ret = 0;
+	int i;
 
-	while (*p) {
-		p_len = strchrnul(p, ',') - p;
-		if (!memcmp(p, "changes", p_len)) {
+	if (*params_copy)
+		string_list_split_in_place(&params, params_copy, ',', -1);
+	for (i = 0; i < params.nr; i++) {
+		const char *p = params.items[i].string;
+		if (!strcmp(p, "changes")) {
 			DIFF_OPT_CLR(options, DIRSTAT_BY_LINE);
 			DIFF_OPT_CLR(options, DIRSTAT_BY_FILE);
-		} else if (!memcmp(p, "lines", p_len)) {
+		} else if (!strcmp(p, "lines")) {
 			DIFF_OPT_SET(options, DIRSTAT_BY_LINE);
 			DIFF_OPT_CLR(options, DIRSTAT_BY_FILE);
-		} else if (!memcmp(p, "files", p_len)) {
+		} else if (!strcmp(p, "files")) {
 			DIFF_OPT_CLR(options, DIRSTAT_BY_LINE);
 			DIFF_OPT_SET(options, DIRSTAT_BY_FILE);
-		} else if (!memcmp(p, "noncumulative", p_len)) {
+		} else if (!strcmp(p, "noncumulative")) {
 			DIFF_OPT_CLR(options, DIRSTAT_CUMULATIVE);
-		} else if (!memcmp(p, "cumulative", p_len)) {
+		} else if (!strcmp(p, "cumulative")) {
 			DIFF_OPT_SET(options, DIRSTAT_CUMULATIVE);
 		} else if (isdigit(*p)) {
 			char *end;
@@ -98,27 +105,35 @@ static int parse_dirstat_params(struct diff_options *options, const char *params
 				while (isdigit(*++end))
 					; /* nothing */
 			}
-			if (end - p == p_len)
+			if (!*end)
 				options->dirstat_permille = permille;
 			else {
-				strbuf_addf(errmsg, _("  Failed to parse dirstat cut-off percentage '%.*s'\n"),
-					    p_len, p);
+				strbuf_addf(errmsg, _("  Failed to parse dirstat cut-off percentage '%s'\n"),
+					    p);
 				ret++;
 			}
 		} else {
-			strbuf_addf(errmsg, _("  Unknown dirstat parameter '%.*s'\n"),
-				    p_len, p);
+			strbuf_addf(errmsg, _("  Unknown dirstat parameter '%s'\n"), p);
 			ret++;
 		}
 
-		p += p_len;
-
-		if (*p)
-			p++; /* more parameters, swallow separator */
 	}
+	string_list_clear(&params, 0);
+	free(params_copy);
 	return ret;
 }
 
+static int parse_submodule_params(struct diff_options *options, const char *value)
+{
+	if (!strcmp(value, "log"))
+		DIFF_OPT_SET(options, SUBMODULE_LOG);
+	else if (!strcmp(value, "short"))
+		DIFF_OPT_CLR(options, SUBMODULE_LOG);
+	else
+		return -1;
+	return 0;
+}
+
 static int git_config_rename(const char *var, const char *value)
 {
 	if (!value)
@@ -140,6 +155,12 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		diff_use_color_default = git_config_colorbool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.context")) {
+		diff_context_default = git_config_int(var, value);
+		if (diff_context_default < 0)
+			return -1;
+		return 0;
+	}
 	if (!strcmp(var, "diff.renames")) {
 		diff_detect_rename_default = git_config_rename(var, value);
 		return 0;
@@ -156,6 +177,10 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		diff_no_prefix = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.statgraphwidth")) {
+		diff_stat_graph_width = git_config_int(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "diff.external"))
 		return git_config_string(&external_diff_cmd_cfg, var, value);
 	if (!strcmp(var, "diff.wordregex"))
@@ -164,6 +189,13 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 	if (!strcmp(var, "diff.ignoresubmodules"))
 		handle_ignore_submodules_arg(&default_diff_options, value);
 
+	if (!strcmp(var, "diff.submodule")) {
+		if (parse_submodule_params(&default_diff_options, value))
+			warning(_("Unknown value for 'diff.submodule' config variable: '%s'"),
+				value);
+		return 0;
+	}
+
 	if (git_color_config(var, value, cb) < 0)
 		return -1;
 
@@ -177,11 +209,8 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	switch (userdiff_config(var, value)) {
-		case 0: break;
-		case -1: return -1;
-		default: return 0;
-	}
+	if (userdiff_config(var, value) < 0)
+		return -1;
 
 	if (!prefixcmp(var, "diff.color.") || !prefixcmp(var, "color.diff.")) {
 		int slot = parse_diff_color_slot(var, 11);
@@ -572,6 +601,7 @@ 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));
 	}
@@ -987,10 +1017,74 @@ 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);
@@ -1233,6 +1327,7 @@ struct diffstat_t {
 		unsigned is_unmerged:1;
 		unsigned is_binary:1;
 		unsigned is_renamed:1;
+		unsigned is_interesting:1;
 		uintmax_t added, deleted;
 	} **files;
 };
@@ -1276,13 +1371,15 @@ const char mime_boundary_leader[] = "------------";
 
 static int scale_linear(int it, int width, int max_change)
 {
+	if (!it)
+		return 0;
 	/*
-	 * make sure that at least one '-' is printed if there were deletions,
-	 * and likewise for '+'.
+	 * make sure that at least one '-' or '+' is printed if
+	 * there is any change to this path. The easiest way is to
+	 * scale linearly as if the alloted width is one column shorter
+	 * than it is, and then add 1 to the result.
 	 */
-	if (max_change < 2)
-		return it;
-	return ((it - 1) * (width - 1) + max_change - 1) / (max_change - 1);
+	return 1 + (it * (width - 1) / max_change);
 }
 
 static void show_name(FILE *file,
@@ -1322,12 +1419,59 @@ static void fill_print_name(struct diffstat_file *file)
 	file->print_name = pname;
 }
 
+int print_stat_summary(FILE *fp, int files, int insertions, int deletions)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int ret;
+
+	if (!files) {
+		assert(insertions == 0 && deletions == 0);
+		return fprintf(fp, "%s\n", " 0 files changed");
+	}
+
+	strbuf_addf(&sb,
+		    (files == 1) ? " %d file changed" : " %d files changed",
+		    files);
+
+	/*
+	 * For binary diff, the caller may want to print "x files
+	 * changed" with insertions == 0 && deletions == 0.
+	 *
+	 * Not omitting "0 insertions(+), 0 deletions(-)" in this case
+	 * is probably less confusing (i.e skip over "2 files changed
+	 * but nothing about added/removed lines? Is this a bug in Git?").
+	 */
+	if (insertions || deletions == 0) {
+		/*
+		 * TRANSLATORS: "+" in (+) is a line addition marker;
+		 * do not translate it.
+		 */
+		strbuf_addf(&sb,
+			    (insertions == 1) ? ", %d insertion(+)" : ", %d insertions(+)",
+			    insertions);
+	}
+
+	if (deletions || insertions == 0) {
+		/*
+		 * TRANSLATORS: "-" in (-) is a line removal marker;
+		 * do not translate it.
+		 */
+		strbuf_addf(&sb,
+			    (deletions == 1) ? ", %d deletion(-)" : ", %d deletions(-)",
+			    deletions);
+	}
+	strbuf_addch(&sb, '\n');
+	ret = fputs(sb.buf, fp);
+	strbuf_release(&sb);
+	return ret;
+}
+
 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, 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;
@@ -1341,30 +1485,20 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		line_prefix = msg->buf;
 	}
 
-	width = options->stat_width ? options->stat_width : 80;
-	name_width = options->stat_name_width ? options->stat_name_width : 50;
 	count = options->stat_count ? options->stat_count : data->nr;
 
-	/* Sanity: give at least 5 columns to the graph,
-	 * but leave at least 10 columns for the name.
-	 */
-	if (width < 25)
-		width = 25;
-	if (name_width < 10)
-		name_width = 10;
-	else if (width < name_width + 15)
-		name_width = width - 15;
-
-	/* Find the longest filename and max number of changes */
 	reset = diff_get_color_opt(options, DIFF_RESET);
 	add_c = diff_get_color_opt(options, DIFF_FILE_NEW);
 	del_c = diff_get_color_opt(options, DIFF_FILE_OLD);
 
+	/*
+	 * Find the longest filename and max number of changes
+	 */
 	for (i = 0; (i < count) && (i < data->nr); i++) {
 		struct diffstat_file *file = data->files[i];
 		uintmax_t change = file->added + file->deleted;
-		if (!data->files[i]->is_renamed &&
-			 (change == 0)) {
+
+		if (!file->is_interesting && (change == 0)) {
 			count++; /* not shown == room for one more */
 			continue;
 		}
@@ -1373,38 +1507,121 @@ 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;
 	}
-	count = i; /* min(count, data->nr) */
+	count = i; /* where we can stop scanning in data->files[] */
 
-	/* Compute the width of the graph part;
-	 * 10 is for one blank at the beginning of the line plus
-	 * " | count " between the name and the graph.
+	/*
+	 * We have width = stat_width or term_columns() columns total.
+	 * We want a maximum of min(max_len, stat_name_width) for the name part.
+	 * We want a maximum of min(max_change, stat_graph_width) for the +- part.
+	 * We also need 1 for " " and 4 + decimal_width(max_change)
+	 * for " | NNNN " and one the empty column at the end, altogether
+	 * 6 + decimal_width(max_change).
+	 *
+	 * If there's not enough space, we will use the smaller of
+	 * stat_name_width (if set) and 5/8*width for the filename,
+	 * and the rest for constant elements + graph part, but no more
+	 * than stat_graph_width for the graph part.
+	 * (5/8 gives 50 for filename and 30 for the constant parts + graph
+	 * for the standard terminal size).
+	 *
+	 * In other words: stat_width limits the maximum width, and
+	 * stat_name_width fixes the maximum width of the filename,
+	 * and is also used to divide available columns if there
+	 * aren't enough.
 	 *
-	 * From here on, name_width is the width of the name area,
-	 * and width is the width of the graph area.
+	 * 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.
 	 */
-	name_width = (name_width < max_len) ? name_width : max_len;
-	if (width < (name_width + 10) + max_change)
-		width = width - (name_width + 10);
+
+	if (options->stat_width == -1)
+		width = term_columns() - options->output_prefix_length;
 	else
-		width = max_change;
+		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;
+
+	/*
+	 * Guarantee 3/8*16==6 for the graph part
+	 * and 5/8*16==10 for the filename part
+	 */
+	if (width < 16 + 6 + number_width)
+		width = 16 + 6 + number_width;
+
+	/*
+	 * 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 = 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;
+
+	/*
+	 * 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) {
+			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;
+		if (name_width > width - number_width - 6 - graph_width)
+			name_width = width - number_width - 6 - graph_width;
+		else
+			graph_width = width - number_width - 6 - name_width;
+	}
 
+	/*
+	 * From here name_width is the width of the name area,
+	 * and graph_width is the width of the graph area.
+	 * max_change is used to scale graph properly.
+	 */
 	for (i = 0; i < count; i++) {
 		const char *prefix = "";
-		char *name = data->files[i]->print_name;
-		uintmax_t added = data->files[i]->added;
-		uintmax_t deleted = data->files[i]->deleted;
+		struct diffstat_file *file = data->files[i];
+		char *name = file->print_name;
+		uintmax_t added = file->added;
+		uintmax_t deleted = file->deleted;
 		int name_len;
 
-		if (!data->files[i]->is_renamed &&
-			 (added + deleted == 0)) {
-			total_files--;
+		if (!file->is_interesting && (added + deleted == 0))
 			continue;
-		}
+
 		/*
 		 * "scale" the filename
 		 */
@@ -1420,11 +1637,15 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 				name = slash;
 		}
 
-		if (data->files[i]->is_binary) {
+		if (file->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",
@@ -1433,10 +1654,10 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 			fprintf(options->file, "\n");
 			continue;
 		}
-		else if (data->files[i]->is_unmerged) {
+		else if (file->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;
 		}
 
@@ -1445,39 +1666,55 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		 */
 		add = added;
 		del = deleted;
-		adds += add;
-		dels += del;
 
-		if (width <= max_change) {
-			add = scale_linear(add, width, max_change);
-			del = scale_linear(del, width, max_change);
+		if (graph_width <= max_change) {
+			int total = add + del;
+
+			total = scale_linear(add + del, graph_width, max_change);
+			if (total < 2 && add && del)
+				/* width >= 2 due to the sanity check */
+				total = 2;
+			if (add < del) {
+				add = scale_linear(add, graph_width, max_change);
+				del = total - add;
+			} else {
+				del = scale_linear(del, graph_width, max_change);
+				add = total - del;
+			}
 		}
 		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");
 	}
-	for (i = count; i < data->nr; i++) {
-		uintmax_t added = data->files[i]->added;
-		uintmax_t deleted = data->files[i]->deleted;
-		if (!data->files[i]->is_renamed &&
-			 (added + deleted == 0)) {
+
+	for (i = 0; i < data->nr; i++) {
+		struct diffstat_file *file = data->files[i];
+		uintmax_t added = file->added;
+		uintmax_t deleted = file->deleted;
+
+		if (file->is_unmerged ||
+		    (!file->is_interesting && (added + deleted == 0))) {
 			total_files--;
 			continue;
 		}
-		adds += added;
-		dels += deleted;
+
+		if (!file->is_binary) {
+			adds += added;
+			dels += deleted;
+		}
+		if (i < count)
+			continue;
 		if (!extra_shown)
 			fprintf(options->file, "%s ...\n", line_prefix);
 		extra_shown = 1;
 	}
 	fprintf(options->file, "%s", line_prefix);
-	fprintf(options->file,
-	       " %d files changed, %d insertions(+), %d deletions(-)\n",
-	       total_files, adds, dels);
+	print_stat_summary(options->file, total_files, adds, dels);
 }
 
 static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
@@ -1488,17 +1725,15 @@ 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 ||
+		    (!data->files[i]->is_interesting && (added + deleted == 0))) {
+			total_files--;
+		} else if (!data->files[i]->is_binary) { /* don't count bytes */
+			adds += added;
+			dels += deleted;
 		}
 	}
 	if (options->output_prefix) {
@@ -1507,8 +1742,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 				options->output_prefix_data);
 		fprintf(options->file, "%s", msg->buf);
 	}
-	fprintf(options->file, " %d files changed, %d insertions(+), %d deletions(-)\n",
-	       total_files, adds, dels);
+	print_stat_summary(options->file, total_files, adds, dels);
 }
 
 static void show_numstat(struct diffstat_t *data, struct diff_options *options)
@@ -1957,20 +2191,6 @@ 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) {
@@ -1996,12 +2216,6 @@ 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)
@@ -2031,7 +2245,7 @@ static void builtin_diff(const char *name_a,
 	mmfile_t mf1, mf2;
 	const char *lbl[2];
 	char *a_one, *b_two;
-	const char *set = diff_get_color_opt(o, DIFF_METAINFO);
+	const char *meta = diff_get_color_opt(o, DIFF_METAINFO);
 	const char *reset = diff_get_color_opt(o, DIFF_RESET);
 	const char *a_prefix, *b_prefix;
 	struct userdiff_driver *textconv_one = NULL;
@@ -2052,7 +2266,7 @@ static void builtin_diff(const char *name_a,
 		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
 		show_submodule_summary(o->file, one ? one->path : two->path,
 				one->sha1, two->sha1, two->dirty_submodule,
-				del, add, reset);
+				meta, del, add, reset);
 		return;
 	}
 
@@ -2078,24 +2292,24 @@ static void builtin_diff(const char *name_a,
 	b_two = quote_two(b_prefix, name_b + (*name_b == '/'));
 	lbl[0] = DIFF_FILE_VALID(one) ? a_one : "/dev/null";
 	lbl[1] = DIFF_FILE_VALID(two) ? b_two : "/dev/null";
-	strbuf_addf(&header, "%s%sdiff --git %s %s%s\n", line_prefix, set, a_one, b_two, reset);
+	strbuf_addf(&header, "%s%sdiff --git %s %s%s\n", line_prefix, meta, a_one, b_two, reset);
 	if (lbl[0][0] == '/') {
 		/* /dev/null */
-		strbuf_addf(&header, "%s%snew file mode %06o%s\n", line_prefix, set, two->mode, reset);
+		strbuf_addf(&header, "%s%snew file mode %06o%s\n", line_prefix, meta, two->mode, reset);
 		if (xfrm_msg)
 			strbuf_addstr(&header, xfrm_msg);
 		must_show_header = 1;
 	}
 	else if (lbl[1][0] == '/') {
-		strbuf_addf(&header, "%s%sdeleted file mode %06o%s\n", line_prefix, set, one->mode, reset);
+		strbuf_addf(&header, "%s%sdeleted file mode %06o%s\n", line_prefix, meta, one->mode, reset);
 		if (xfrm_msg)
 			strbuf_addstr(&header, xfrm_msg);
 		must_show_header = 1;
 	}
 	else {
 		if (one->mode != two->mode) {
-			strbuf_addf(&header, "%s%sold mode %06o%s\n", line_prefix, set, one->mode, reset);
-			strbuf_addf(&header, "%s%snew mode %06o%s\n", line_prefix, set, two->mode, reset);
+			strbuf_addf(&header, "%s%sold mode %06o%s\n", line_prefix, meta, one->mode, reset);
+			strbuf_addf(&header, "%s%snew mode %06o%s\n", line_prefix, meta, two->mode, reset);
 			must_show_header = 1;
 		}
 		if (xfrm_msg)
@@ -2151,7 +2365,7 @@ static void builtin_diff(const char *name_a,
 		struct emit_callback ecbdata;
 		const struct userdiff_funcname *pe;
 
-		if (!DIFF_XDL_TST(o, WHITESPACE_FLAGS) || must_show_header) {
+		if (must_show_header) {
 			fprintf(o->file, "%s", header.buf);
 			strbuf_reset(&header);
 		}
@@ -2188,42 +2402,8 @@ 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)
@@ -2249,22 +2429,37 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 			     struct diff_filespec *two,
 			     struct diffstat_t *diffstat,
 			     struct diff_options *o,
-			     int complete_rewrite)
+			     struct diff_filepair *p)
 {
 	mmfile_t mf1, mf2;
 	struct diffstat_file *data;
+	int same_contents;
+	int complete_rewrite = 0;
+
+	if (!DIFF_PAIR_UNMERGED(p)) {
+		if (p->status == DIFF_STATUS_MODIFIED && p->score)
+			complete_rewrite = 1;
+	}
 
 	data = diffstat_add(diffstat, name_a, name_b);
+	data->is_interesting = p->status != DIFF_STATUS_UNKNOWN;
 
 	if (!one || !two) {
 		data->is_unmerged = 1;
 		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) {
@@ -2274,7 +2469,7 @@ 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;
@@ -2384,12 +2579,12 @@ 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;
 	}
 }
 
@@ -2462,22 +2657,6 @@ 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;
@@ -2527,9 +2706,6 @@ 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:
@@ -2854,9 +3030,8 @@ 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;
@@ -2891,7 +3066,7 @@ 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;
 			}
@@ -2936,6 +3111,9 @@ 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);
@@ -2975,11 +3153,10 @@ static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
 {
 	const char *name;
 	const char *other;
-	int complete_rewrite = 0;
 
 	if (DIFF_PAIR_UNMERGED(p)) {
 		/* unmerged */
-		builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, o, 0);
+		builtin_diffstat(p->one->path, NULL, NULL, NULL, diffstat, o, p);
 		return;
 	}
 
@@ -2992,9 +3169,7 @@ static void run_diffstat(struct diff_filepair *p, struct diff_options *o,
 	diff_fill_sha1_info(p->one);
 	diff_fill_sha1_info(p->two);
 
-	if (p->status == DIFF_STATUS_MODIFIED && p->score)
-		complete_rewrite = 1;
-	builtin_diffstat(name, other, p->one, p->two, diffstat, o, complete_rewrite);
+	builtin_diffstat(name, other, p->one, p->two, diffstat, o, p);
 }
 
 static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
@@ -3031,7 +3206,8 @@ void diff_setup(struct diff_options *options)
 	options->break_opt = -1;
 	options->rename_limit = -1;
 	options->dirstat_permille = diff_dirstat_permille_default;
-	options->context = 3;
+	options->context = diff_context_default;
+	DIFF_OPT_SET(options, RENAME_EMPTY);
 
 	options->change = diff_change;
 	options->add_remove = diff_addremove;
@@ -3046,7 +3222,7 @@ 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;
 
@@ -3145,8 +3321,6 @@ 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)
@@ -3243,6 +3417,7 @@ static int stat_opt(struct diff_options *options, const char **av)
 	char *end;
 	int width = options->stat_width;
 	int name_width = options->stat_name_width;
+	int graph_width = options->stat_graph_width;
 	int count = options->stat_count;
 	int argcount = 1;
 
@@ -3271,6 +3446,16 @@ static int stat_opt(struct diff_options *options, const char **av)
 				name_width = strtoul(av[1], &end, 10);
 				argcount = 2;
 			}
+		} else if (!prefixcmp(arg, "-graph-width")) {
+			arg += strlen("-graph-width");
+			if (*arg == '=')
+				graph_width = strtoul(arg + 1, &end, 10);
+			else if (!*arg && !av[1])
+				die("Option '--stat-graph-width' requires a value");
+			else if (!*arg) {
+				graph_width = strtoul(av[1], &end, 10);
+				argcount = 2;
+			}
 		} else if (!prefixcmp(arg, "-count")) {
 			arg += strlen("-count");
 			if (*arg == '=')
@@ -3296,6 +3481,7 @@ static int stat_opt(struct diff_options *options, const char **av)
 		return 0;
 	options->output_format |= DIFF_FORMAT_DIFFSTAT;
 	options->stat_name_width = name_width;
+	options->stat_graph_width = graph_width;
 	options->stat_width = width;
 	options->stat_count = count;
 	return argcount;
@@ -3316,6 +3502,14 @@ static int parse_dirstat_opt(struct diff_options *options, const char *params)
 	return 1;
 }
 
+static int parse_submodule_opt(struct diff_options *options, const char *value)
+{
+	if (parse_submodule_params(options, value))
+		die(_("Failed to parse --submodule option parameter: '%s'"),
+			value);
+	return 1;
+}
+
 int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 {
 	const char *arg = av[0];
@@ -3390,6 +3584,10 @@ 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=")) {
@@ -3409,9 +3607,9 @@ 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")) {
@@ -3492,10 +3690,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		handle_ignore_submodules_arg(options, arg + 20);
 	} else if (!strcmp(arg, "--submodule"))
 		DIFF_OPT_SET(options, SUBMODULE_LOG);
-	else if (!prefixcmp(arg, "--submodule=")) {
-		if (!strcmp(arg + 12, "log"))
-			DIFF_OPT_SET(options, SUBMODULE_LOG);
-	}
+	else if (!prefixcmp(arg, "--submodule="))
+		return parse_submodule_opt(options, arg + 12);
 
 	/* misc options */
 	else if (!strcmp(arg, "-z"))
@@ -4283,6 +4479,12 @@ 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 */
@@ -4530,6 +4732,7 @@ 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;
@@ -4561,9 +4764,9 @@ 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;
 	}
 
@@ -4576,6 +4779,7 @@ 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)
 {
@@ -4590,6 +4794,8 @@ 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;
 	}
@@ -4600,8 +4806,8 @@ 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;
 
@@ -4707,3 +4913,19 @@ size_t fill_textconv(struct userdiff_driver *driver,
 
 	return size;
 }
+
+void setup_diff_pager(struct diff_options *opt)
+{
+	/*
+	 * If the user asked for our exit code, then either they want --quiet
+	 * or --exit-code. We should definitely not bother with a pager in the
+	 * former case, as we will generate no output. Since we still properly
+	 * report our exit code even when a pager is run, we _could_ run a
+	 * pager with --exit-code. But since we have not done so historically,
+	 * and because it is easy to find people oneline advising "git diff
+	 * --exit-code" in hooks and other scripts, we do not do so.
+	 */
+	if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
+	    check_pager_config("diff") != 0)
+		setup_pager();
+}