X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=blobdiff_plain;f=diff.c;h=494f5601e97e7395e647296bc7f8090331a47c43;hb=82c531b3b6d24040443ba739e150bc06ecc762ea;hp=0182237c2dab7fa3aa7e916f2eb8bc75865c0b9a;hpb=0974c117ff4e17e8b6300519cae0fbc67d34adaa;p=git.git

diff --git a/diff.c b/diff.c
index 0182237c2..494f5601e 100644
--- a/diff.c
+++ b/diff.c
@@ -14,6 +14,7 @@
 #include "userdiff.h"
 #include "sigchain.h"
 #include "submodule.h"
+#include "ll-merge.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -43,7 +44,8 @@ static char diff_colors[][COLOR_MAXLEN] = {
 };
 
 static void diff_filespec_load_driver(struct diff_filespec *one);
-static char *run_textconv(const char *, struct diff_filespec *, size_t *);
+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)
 {
@@ -194,6 +196,7 @@ struct emit_callback {
 	struct diff_words_data *diff_words;
 	int *found_changesp;
 	FILE *file;
+	struct strbuf *header;
 };
 
 static int count_lines(const char *data, int size)
@@ -464,8 +467,8 @@ static void emit_rewrite_diff(const char *name_a,
 			      const char *name_b,
 			      struct diff_filespec *one,
 			      struct diff_filespec *two,
-			      const char *textconv_one,
-			      const char *textconv_two,
+			      struct userdiff_driver *textconv_one,
+			      struct userdiff_driver *textconv_two,
 			      struct diff_options *o)
 {
 	int lc_a, lc_b;
@@ -476,7 +479,7 @@ static void emit_rewrite_diff(const char *name_a,
 	const char *reset = diff_get_color(color_diff, DIFF_RESET);
 	static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
 	const char *a_prefix, *b_prefix;
-	const char *data_one, *data_two;
+	char *data_one, *data_two;
 	size_t size_one, size_two;
 	struct emit_callback ecbdata;
 
@@ -498,26 +501,8 @@ static void emit_rewrite_diff(const char *name_a,
 	quote_two_c_style(&a_name, a_prefix, name_a, 0);
 	quote_two_c_style(&b_name, b_prefix, name_b, 0);
 
-	diff_populate_filespec(one, 0);
-	diff_populate_filespec(two, 0);
-	if (textconv_one) {
-		data_one = run_textconv(textconv_one, one, &size_one);
-		if (!data_one)
-			die("unable to read files to diff");
-	}
-	else {
-		data_one = one->data;
-		size_one = one->size;
-	}
-	if (textconv_two) {
-		data_two = run_textconv(textconv_two, two, &size_two);
-		if (!data_two)
-			die("unable to read files to diff");
-	}
-	else {
-		data_two = two->data;
-		size_two = two->size;
-	}
+	size_one = fill_textconv(textconv_one, one, &data_one);
+	size_two = fill_textconv(textconv_two, two, &data_two);
 
 	memset(&ecbdata, 0, sizeof(ecbdata));
 	ecbdata.color_diff = color_diff;
@@ -549,6 +534,10 @@ static void emit_rewrite_diff(const char *name_a,
 		emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
 	if (lc_b)
 		emit_rewrite_lines(&ecbdata, '+', data_two, size_two);
+	if (textconv_one)
+		free((char *)data_one);
+	if (textconv_two)
+		free((char *)data_two);
 }
 
 struct diff_words_buffer {
@@ -571,16 +560,68 @@ static void diff_words_append(char *line, unsigned long len,
 	buffer->text.ptr[buffer->text.size] = '\0';
 }
 
+struct diff_words_style_elem
+{
+	const char *prefix;
+	const char *suffix;
+	const char *color; /* NULL; filled in by the setup code if
+			    * color is enabled */
+};
+
+struct diff_words_style
+{
+	enum diff_words_type type;
+	struct diff_words_style_elem new, old, ctx;
+	const char *newline;
+};
+
+struct diff_words_style diff_words_styles[] = {
+	{ DIFF_WORDS_PORCELAIN, {"+", "\n"}, {"-", "\n"}, {" ", "\n"}, "~\n" },
+	{ DIFF_WORDS_PLAIN, {"{+", "+}"}, {"[-", "-]"}, {"", ""}, "\n" },
+	{ DIFF_WORDS_COLOR, {"", ""}, {"", ""}, {"", ""}, "\n" }
+};
+
 struct diff_words_data {
 	struct diff_words_buffer minus, plus;
 	const char *current_plus;
 	FILE *file;
 	regex_t *word_regex;
+	enum diff_words_type type;
+	struct diff_words_style *style;
 };
 
+static int fn_out_diff_words_write_helper(FILE *fp,
+					  struct diff_words_style_elem *st_el,
+					  const char *newline,
+					  size_t count, const char *buf)
+{
+	while (count) {
+		char *p = memchr(buf, '\n', count);
+		if (p != buf) {
+			if (st_el->color && fputs(st_el->color, fp) < 0)
+				return -1;
+			if (fputs(st_el->prefix, fp) < 0 ||
+			    fwrite(buf, p ? p - buf : count, 1, fp) != 1 ||
+			    fputs(st_el->suffix, fp) < 0)
+				return -1;
+			if (st_el->color && *st_el->color
+			    && fputs(GIT_COLOR_RESET, fp) < 0)
+				return -1;
+		}
+		if (!p)
+			return 0;
+		if (fputs(newline, fp) < 0)
+			return -1;
+		count -= p + 1 - buf;
+		buf = p + 1;
+	}
+	return 0;
+}
+
 static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 {
 	struct diff_words_data *diff_words = priv;
+	struct diff_words_style *style = diff_words->style;
 	int minus_first, minus_len, plus_first, plus_len;
 	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 
@@ -604,16 +645,17 @@ static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
 
 	if (diff_words->current_plus != plus_begin)
-		fwrite(diff_words->current_plus,
-				plus_begin - diff_words->current_plus, 1,
-				diff_words->file);
+		fn_out_diff_words_write_helper(diff_words->file,
+				&style->ctx, style->newline,
+				plus_begin - diff_words->current_plus,
+				diff_words->current_plus);
 	if (minus_begin != minus_end)
-		color_fwrite_lines(diff_words->file,
-				diff_get_color(1, DIFF_FILE_OLD),
+		fn_out_diff_words_write_helper(diff_words->file,
+				&style->old, style->newline,
 				minus_end - minus_begin, minus_begin);
 	if (plus_begin != plus_end)
-		color_fwrite_lines(diff_words->file,
-				diff_get_color(1, DIFF_FILE_NEW),
+		fn_out_diff_words_write_helper(diff_words->file,
+				&style->new, style->newline,
 				plus_end - plus_begin, plus_begin);
 
 	diff_words->current_plus = plus_end;
@@ -694,13 +736,13 @@ static void diff_words_show(struct diff_words_data *diff_words)
 {
 	xpparam_t xpp;
 	xdemitconf_t xecfg;
-	xdemitcb_t ecb;
 	mmfile_t minus, plus;
+	struct diff_words_style *style = diff_words->style;
 
 	/* special case: only removal */
 	if (!diff_words->plus.text.size) {
-		color_fwrite_lines(diff_words->file,
-			diff_get_color(1, DIFF_FILE_OLD),
+		fn_out_diff_words_write_helper(diff_words->file,
+			&style->old, style->newline,
 			diff_words->minus.text.size, diff_words->minus.text.ptr);
 		diff_words->minus.text.size = 0;
 		return;
@@ -716,15 +758,15 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	/* as only the hunk header will be parsed, we need a 0-context */
 	xecfg.ctxlen = 0;
 	xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
-		      &xpp, &xecfg, &ecb);
+		      &xpp, &xecfg);
 	free(minus.ptr);
 	free(plus.ptr);
 	if (diff_words->current_plus != diff_words->plus.text.ptr +
 			diff_words->plus.text.size)
-		fwrite(diff_words->current_plus,
+		fn_out_diff_words_write_helper(diff_words->file,
+			&style->ctx, style->newline,
 			diff_words->plus.text.ptr + diff_words->plus.text.size
-			- diff_words->current_plus, 1,
-			diff_words->file);
+			- diff_words->current_plus, diff_words->current_plus);
 	diff_words->minus.text.size = diff_words->plus.text.size = 0;
 }
 
@@ -797,6 +839,11 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	const char *plain = diff_get_color(ecbdata->color_diff, DIFF_PLAIN);
 	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
 
+	if (ecbdata->header) {
+		fprintf(ecbdata->file, "%s", ecbdata->header->buf);
+		strbuf_reset(ecbdata->header);
+		ecbdata->header = NULL;
+	}
 	*(ecbdata->found_changesp) = 1;
 
 	if (ecbdata->label_path[0]) {
@@ -831,6 +878,9 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 
 	if (len < 1) {
 		emit_line(ecbdata->file, reset, reset, line, len);
+		if (ecbdata->diff_words
+		    && ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN)
+			fputs("~\n", ecbdata->file);
 		return;
 	}
 
@@ -845,9 +895,13 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 			return;
 		}
 		diff_words_flush(ecbdata);
-		line++;
-		len--;
-		emit_line(ecbdata->file, plain, reset, line, len);
+		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
+			emit_line(ecbdata->file, plain, reset, line, len);
+			fputs("~\n", ecbdata->file);
+		} else {
+			/* don't print the prefix character */
+			emit_line(ecbdata->file, plain, reset, line+1, len-1);
+		}
 		return;
 	}
 
@@ -1367,37 +1421,32 @@ static void free_diffstat_info(struct diffstat_t *diffstat)
 struct checkdiff_t {
 	const char *filename;
 	int lineno;
+	int conflict_marker_size;
 	struct diff_options *o;
 	unsigned ws_rule;
 	unsigned status;
 };
 
-static int is_conflict_marker(const char *line, unsigned long len)
+static int is_conflict_marker(const char *line, int marker_size, unsigned long len)
 {
 	char firstchar;
 	int cnt;
 
-	if (len < 8)
+	if (len < marker_size + 1)
 		return 0;
 	firstchar = line[0];
 	switch (firstchar) {
-	case '=': case '>': case '<':
+	case '=': case '>': case '<': case '|':
 		break;
 	default:
 		return 0;
 	}
-	for (cnt = 1; cnt < 7; cnt++)
+	for (cnt = 1; cnt < marker_size; cnt++)
 		if (line[cnt] != firstchar)
 			return 0;
-	/* line[0] thru line[6] are same as firstchar */
-	if (firstchar == '=') {
-		/* divider between ours and theirs? */
-		if (len != 8 || line[7] != '\n')
-			return 0;
-	} else if (len < 8 || !isspace(line[7])) {
-		/* not divider before ours nor after theirs */
+	/* line[1] thru line[marker_size-1] are same as firstchar */
+	if (len < marker_size + 1 || !isspace(line[marker_size]))
 		return 0;
-	}
 	return 1;
 }
 
@@ -1405,6 +1454,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 {
 	struct checkdiff_t *data = priv;
 	int color_diff = DIFF_OPT_TST(data->o, COLOR_DIFF);
+	int marker_size = data->conflict_marker_size;
 	const char *ws = diff_get_color(color_diff, DIFF_WHITESPACE);
 	const char *reset = diff_get_color(color_diff, DIFF_RESET);
 	const char *set = diff_get_color(color_diff, DIFF_FILE_NEW);
@@ -1413,7 +1463,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 	if (line[0] == '+') {
 		unsigned bad;
 		data->lineno++;
-		if (is_conflict_marker(line + 1, len - 1)) {
+		if (is_conflict_marker(line + 1, marker_size, len - 1)) {
 			data->status |= 1;
 			fprintf(data->o->file,
 				"%s:%d: leftover conflict marker\n",
@@ -1579,14 +1629,26 @@ void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const
 		options->b_prefix = b;
 }
 
-static const char *get_textconv(struct diff_filespec *one)
+static struct userdiff_driver *get_textconv(struct diff_filespec *one)
 {
 	if (!DIFF_FILE_VALID(one))
 		return NULL;
 	if (!S_ISREG(one->mode))
 		return NULL;
 	diff_filespec_load_driver(one);
-	return one->driver->textconv;
+	if (!one->driver->textconv)
+		return NULL;
+
+	if (one->driver->textconv_want_cache && !one->driver->textconv_cache) {
+		struct notes_cache *c = xmalloc(sizeof(*c));
+		struct strbuf name = STRBUF_INIT;
+
+		strbuf_addf(&name, "textconv/%s", one->driver->name);
+		notes_cache_init(c, name.buf, one->driver->textconv);
+		one->driver->textconv_cache = c;
+	}
+
+	return one->driver;
 }
 
 static void builtin_diff(const char *name_a,
@@ -1603,7 +1665,9 @@ static void builtin_diff(const char *name_a,
 	const char *set = diff_get_color_opt(o, DIFF_METAINFO);
 	const char *reset = diff_get_color_opt(o, DIFF_RESET);
 	const char *a_prefix, *b_prefix;
-	const char *textconv_one = NULL, *textconv_two = NULL;
+	struct userdiff_driver *textconv_one = NULL;
+	struct userdiff_driver *textconv_two = NULL;
+	struct strbuf header = STRBUF_INIT;
 
 	if (DIFF_OPT_TST(o, SUBMODULE_LOG) &&
 			(!one->mode || S_ISGITLINK(one->mode)) &&
@@ -1611,7 +1675,7 @@ static void builtin_diff(const char *name_a,
 		const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
 		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,
+				one->sha1, two->sha1, two->dirty_submodule,
 				del, add, reset);
 		return;
 	}
@@ -1638,25 +1702,26 @@ 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";
-	fprintf(o->file, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
+	strbuf_addf(&header, "%sdiff --git %s %s%s\n", set, a_one, b_two, reset);
 	if (lbl[0][0] == '/') {
 		/* /dev/null */
-		fprintf(o->file, "%snew file mode %06o%s\n", set, two->mode, reset);
+		strbuf_addf(&header, "%snew file mode %06o%s\n", set, two->mode, reset);
 		if (xfrm_msg && xfrm_msg[0])
-			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
+			strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
 	}
 	else if (lbl[1][0] == '/') {
-		fprintf(o->file, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
+		strbuf_addf(&header, "%sdeleted file mode %06o%s\n", set, one->mode, reset);
 		if (xfrm_msg && xfrm_msg[0])
-			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
+			strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
 	}
 	else {
 		if (one->mode != two->mode) {
-			fprintf(o->file, "%sold mode %06o%s\n", set, one->mode, reset);
-			fprintf(o->file, "%snew mode %06o%s\n", set, two->mode, reset);
+			strbuf_addf(&header, "%sold mode %06o%s\n", set, one->mode, reset);
+			strbuf_addf(&header, "%snew mode %06o%s\n", set, two->mode, reset);
 		}
 		if (xfrm_msg && xfrm_msg[0])
-			fprintf(o->file, "%s%s%s\n", set, xfrm_msg, reset);
+			strbuf_addf(&header, "%s%s%s\n", set, xfrm_msg, reset);
+
 		/*
 		 * we do not run diff between different kind
 		 * of objects.
@@ -1666,6 +1731,8 @@ static void builtin_diff(const char *name_a,
 		if (complete_rewrite &&
 		    (textconv_one || !diff_filespec_is_binary(one)) &&
 		    (textconv_two || !diff_filespec_is_binary(two))) {
+			fprintf(o->file, "%s", header.buf);
+			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
 			o->found_changes = 1;
@@ -1673,16 +1740,17 @@ static void builtin_diff(const char *name_a,
 		}
 	}
 
-	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
-		die("unable to read files to diff");
-
 	if (!DIFF_OPT_TST(o, TEXT) &&
-	    ( (diff_filespec_is_binary(one) && !textconv_one) ||
-	      (diff_filespec_is_binary(two) && !textconv_two) )) {
+	    ( (!textconv_one && diff_filespec_is_binary(one)) ||
+	      (!textconv_two && diff_filespec_is_binary(two)) )) {
+		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
+			die("unable to read files to diff");
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size))
 			goto free_ab_and_return;
+		fprintf(o->file, "%s", header.buf);
+		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
 			emit_binary_diff(o->file, &mf1, &mf2);
 		else
@@ -1695,25 +1763,17 @@ static void builtin_diff(const char *name_a,
 		const char *diffopts = getenv("GIT_DIFF_OPTS");
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
-		xdemitcb_t ecb;
 		struct emit_callback ecbdata;
 		const struct userdiff_funcname *pe;
 
-		if (textconv_one) {
-			size_t size;
-			mf1.ptr = run_textconv(textconv_one, one, &size);
-			if (!mf1.ptr)
-				die("unable to read files to diff");
-			mf1.size = size;
-		}
-		if (textconv_two) {
-			size_t size;
-			mf2.ptr = run_textconv(textconv_two, two, &size);
-			if (!mf2.ptr)
-				die("unable to read files to diff");
-			mf2.size = size;
+		if (!DIFF_XDL_TST(o, WHITESPACE_FLAGS)) {
+			fprintf(o->file, "%s", header.buf);
+			strbuf_reset(&header);
 		}
 
+		mf1.size = fill_textconv(textconv_one, one, &mf1.ptr);
+		mf2.size = fill_textconv(textconv_two, two, &mf2.ptr);
+
 		pe = diff_funcname_pattern(one);
 		if (!pe)
 			pe = diff_funcname_pattern(two);
@@ -1728,6 +1788,7 @@ static void builtin_diff(const char *name_a,
 		if (ecbdata.ws_rule & WS_BLANK_AT_EOF)
 			check_blank_at_eof(&mf1, &mf2, &ecbdata);
 		ecbdata.file = o->file;
+		ecbdata.header = header.len ? &header : NULL;
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
 		xecfg.ctxlen = o->context;
 		xecfg.interhunkctxlen = o->interhunkcontext;
@@ -1740,10 +1801,13 @@ 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 (DIFF_OPT_TST(o, COLOR_DIFF_WORDS)) {
+		if (o->word_diff) {
+			int i;
+
 			ecbdata.diff_words =
 				xcalloc(1, sizeof(struct diff_words_data));
 			ecbdata.diff_words->file = o->file;
+			ecbdata.diff_words->type = o->word_diff;
 			if (!o->word_regex)
 				o->word_regex = userdiff_word_regex(one);
 			if (!o->word_regex)
@@ -1759,10 +1823,23 @@ static void builtin_diff(const char *name_a,
 					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 (DIFF_OPT_TST(o, COLOR_DIFF)) {
+				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);
+			}
 		}
 		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
-			      &xpp, &xecfg, &ecb);
-		if (DIFF_OPT_TST(o, COLOR_DIFF_WORDS))
+			      &xpp, &xecfg);
+		if (o->word_diff)
 			free_diff_words_data(&ecbdata);
 		if (textconv_one)
 			free(mf1.ptr);
@@ -1772,6 +1849,7 @@ static void builtin_diff(const char *name_a,
 	}
 
  free_ab_and_return:
+	strbuf_release(&header);
 	diff_free_filespec_data(one);
 	diff_free_filespec_data(two);
 	free(a_one);
@@ -1813,13 +1891,12 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		/* Crazy xdl interfaces.. */
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
-		xdemitcb_t ecb;
 
 		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
 		xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
-			      &xpp, &xecfg, &ecb);
+			      &xpp, &xecfg);
 	}
 
  free_and_return:
@@ -1844,6 +1921,7 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 	data.lineno = 0;
 	data.o = o;
 	data.ws_rule = whitespace_rule(attr_path);
+	data.conflict_marker_size = ll_merge_marker_size(attr_path);
 
 	if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
 		die("unable to read files to diff");
@@ -1860,14 +1938,13 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 		/* Crazy xdl interfaces.. */
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
-		xdemitcb_t ecb;
 
 		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xecfg.ctxlen = 1; /* at least one context line */
 		xpp.flags = XDF_NEED_MINIMAL;
 		xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
-			      &xpp, &xecfg, &ecb);
+			      &xpp, &xecfg);
 
 		if (data.ws_rule & WS_BLANK_AT_EOF) {
 			struct emit_callback ecbdata;
@@ -1981,7 +2058,7 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
 	 * If ce is marked as "assume unchanged", there is no
 	 * guarantee that work tree matches what we are looking for.
 	 */
-	if (ce->ce_flags & CE_VALID)
+	if ((ce->ce_flags & CE_VALID) || ce_skip_worktree(ce))
 		return 0;
 
 	/*
@@ -2013,9 +2090,14 @@ static int populate_from_stdin(struct diff_filespec *s)
 static int diff_populate_gitlink(struct diff_filespec *s, int size_only)
 {
 	int len;
-	char *data = xmalloc(100);
+	char *data = xmalloc(100), *dirty = "";
+
+	/* Are we looking at the work tree? */
+	if (s->dirty_submodule)
+		dirty = "-dirty";
+
 	len = snprintf(data, 100,
-		"Subproject commit %s\n", sha1_to_hex(s->sha1));
+		       "Subproject commit %s%s\n", sha1_to_hex(s->sha1), dirty);
 	s->data = data;
 	s->size = len;
 	s->should_free = 1;
@@ -2278,7 +2360,7 @@ static void run_external_diff(const char *pgm,
 	}
 	*arg = NULL;
 	fflush(NULL);
-	retval = run_command_v_opt(spawn_arg, 0);
+	retval = run_command_v_opt(spawn_arg, RUN_USING_SHELL);
 	remove_tempfile();
 	if (retval) {
 		fprintf(stderr, "external diff died, stopping at %s.\n", name);
@@ -2518,6 +2600,7 @@ static void run_checkdiff(struct diff_filepair *p, struct diff_options *o)
 void diff_setup(struct diff_options *options)
 {
 	memset(options, 0, sizeof(*options));
+	memset(&diff_queued_diff, 0, sizeof(diff_queued_diff));
 
 	options->file = stdout;
 
@@ -2554,6 +2637,20 @@ int diff_setup_done(struct diff_options *options)
 	if (count > 1)
 		die("--name-only, --name-status, --check and -s are mutually exclusive");
 
+	/*
+	 * Most of the time we can say "there are changes"
+	 * only by checking if there are changed paths, but
+	 * --ignore-whitespace* options force us to look
+	 * inside contents.
+	 */
+
+	if (DIFF_XDL_TST(options, IGNORE_WHITESPACE) ||
+	    DIFF_XDL_TST(options, IGNORE_WHITESPACE_CHANGE) ||
+	    DIFF_XDL_TST(options, IGNORE_WHITESPACE_AT_EOL))
+		DIFF_OPT_SET(options, DIFF_FROM_CONTENTS);
+	else
+		DIFF_OPT_CLR(options, DIFF_FROM_CONTENTS);
+
 	if (DIFF_OPT_TST(options, FIND_COPIES_HARDER))
 		options->detect_rename = DIFF_DETECT_COPY;
 
@@ -2593,6 +2690,12 @@ int diff_setup_done(struct diff_options *options)
 	 */
 	if (options->pickaxe)
 		DIFF_OPT_SET(options, RECURSIVE);
+	/*
+	 * When patches are generated, submodules diffed against the work tree
+	 * must be checked for dirtiness too so it can be shown in the output
+	 */
+	if (options->output_format & DIFF_FORMAT_PATCH)
+		DIFF_OPT_SET(options, DIRTY_SUBMODULES);
 
 	if (options->detect_rename && options->rename_limit < 0)
 		options->rename_limit = diff_rename_limit_default;
@@ -2614,7 +2717,7 @@ int diff_setup_done(struct diff_options *options)
 	 * to have found.  It does not make sense not to return with
 	 * exit code in such a case either.
 	 */
-	if (DIFF_OPT_TST(options, QUIET)) {
+	if (DIFF_OPT_TST(options, QUICK)) {
 		options->output_format = DIFF_FORMAT_NO_OUTPUT;
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	}
@@ -2676,7 +2779,7 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	const char *arg = av[0];
 
 	/* Output format options */
-	if (!strcmp(arg, "-p") || !strcmp(arg, "-u"))
+	if (!strcmp(arg, "-p") || !strcmp(arg, "-u") || !strcmp(arg, "--patch"))
 		options->output_format |= DIFF_FORMAT_PATCH;
 	else if (opt_arg(arg, 'U', "unified", &options->context))
 		options->output_format |= DIFF_FORMAT_PATCH;
@@ -2791,21 +2894,54 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_OPT_SET(options, FOLLOW_RENAMES);
 	else if (!strcmp(arg, "--color"))
 		DIFF_OPT_SET(options, COLOR_DIFF);
+	else if (!prefixcmp(arg, "--color=")) {
+		int value = git_config_colorbool(NULL, arg+8, -1);
+		if (value == 0)
+			DIFF_OPT_CLR(options, COLOR_DIFF);
+		else if (value > 0)
+			DIFF_OPT_SET(options, COLOR_DIFF);
+		else
+			return error("option `color' expects \"always\", \"auto\", or \"never\"");
+	}
 	else if (!strcmp(arg, "--no-color"))
 		DIFF_OPT_CLR(options, COLOR_DIFF);
 	else if (!strcmp(arg, "--color-words")) {
 		DIFF_OPT_SET(options, COLOR_DIFF);
-		DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+		options->word_diff = DIFF_WORDS_COLOR;
 	}
 	else if (!prefixcmp(arg, "--color-words=")) {
 		DIFF_OPT_SET(options, COLOR_DIFF);
-		DIFF_OPT_SET(options, COLOR_DIFF_WORDS);
+		options->word_diff = DIFF_WORDS_COLOR;
 		options->word_regex = arg + 14;
 	}
+	else if (!strcmp(arg, "--word-diff")) {
+		if (options->word_diff == DIFF_WORDS_NONE)
+			options->word_diff = DIFF_WORDS_PLAIN;
+	}
+	else if (!prefixcmp(arg, "--word-diff=")) {
+		const char *type = arg + 12;
+		if (!strcmp(type, "plain"))
+			options->word_diff = DIFF_WORDS_PLAIN;
+		else if (!strcmp(type, "color")) {
+			DIFF_OPT_SET(options, COLOR_DIFF);
+			options->word_diff = DIFF_WORDS_COLOR;
+		}
+		else if (!strcmp(type, "porcelain"))
+			options->word_diff = DIFF_WORDS_PORCELAIN;
+		else if (!strcmp(type, "none"))
+			options->word_diff = DIFF_WORDS_NONE;
+		else
+			die("bad --word-diff argument: %s", type);
+	}
+	else if (!prefixcmp(arg, "--word-diff-regex=")) {
+		if (options->word_diff == DIFF_WORDS_NONE)
+			options->word_diff = DIFF_WORDS_PLAIN;
+		options->word_regex = arg + 18;
+	}
 	else if (!strcmp(arg, "--exit-code"))
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	else if (!strcmp(arg, "--quiet"))
-		DIFF_OPT_SET(options, QUIET);
+		DIFF_OPT_SET(options, QUICK);
 	else if (!strcmp(arg, "--ext-diff"))
 		DIFF_OPT_SET(options, ALLOW_EXTERNAL);
 	else if (!strcmp(arg, "--no-ext-diff"))
@@ -2858,6 +2994,8 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		;
 	else if (!prefixcmp(arg, "--output=")) {
 		options->file = fopen(arg + strlen("--output="), "w");
+		if (!options->file)
+			die_errno("Could not open '%s'", arg + strlen("--output="));
 		options->close_file = 1;
 	} else
 		return 0;
@@ -3040,7 +3178,8 @@ int diff_unmodified_pair(struct diff_filepair *p)
 	 * dealing with a change.
 	 */
 	if (one->sha1_valid && two->sha1_valid &&
-	    !hashcmp(one->sha1, two->sha1))
+	    !hashcmp(one->sha1, two->sha1) &&
+	    !one->dirty_submodule && !two->dirty_submodule)
 		return 1; /* no change */
 	if (!one->sha1_valid && !two->sha1_valid)
 		return 1; /* both look at the same file on the filesystem. */
@@ -3175,6 +3314,8 @@ static void diff_resolve_rename_copy(void)
 		}
 		else if (hashcmp(p->one->sha1, p->two->sha1) ||
 			 p->one->mode != p->two->mode ||
+			 p->one->dirty_submodule ||
+			 p->two->dirty_submodule ||
 			 is_null_sha1(p->one->sha1))
 			p->status = DIFF_STATUS_MODIFIED;
 		else {
@@ -3323,7 +3464,6 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 	for (i = 0; i < q->nr; i++) {
 		xpparam_t xpp;
 		xdemitconf_t xecfg;
-		xdemitcb_t ecb;
 		mmfile_t mf1, mf2;
 		struct diff_filepair *p = q->queue[i];
 		int len1, len2;
@@ -3385,7 +3525,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 		xecfg.ctxlen = 3;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
 		xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data,
-			      &xpp, &xecfg, &ecb);
+			      &xpp, &xecfg);
 	}
 
 	git_SHA1_Final(sha1, &ctx);
@@ -3402,8 +3542,7 @@ int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
 		diff_free_filepair(q->queue[i]);
 
 	free(q->queue);
-	q->queue = NULL;
-	q->nr = q->alloc = 0;
+	DIFF_QUEUE_CLEAR(q);
 
 	return result;
 }
@@ -3485,6 +3624,29 @@ void diff_flush(struct diff_options *options)
 		separator++;
 	}
 
+	if (output_format & DIFF_FORMAT_NO_OUTPUT &&
+	    DIFF_OPT_TST(options, EXIT_WITH_STATUS) &&
+	    DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) {
+		/*
+		 * run diff_flush_patch for the exit status. setting
+		 * options->file to /dev/null should be safe, becaue we
+		 * aren't supposed to produce any output anyway.
+		 */
+		if (options->close_file)
+			fclose(options->file);
+		options->file = fopen("/dev/null", "w");
+		if (!options->file)
+			die_errno("Could not open /dev/null");
+		options->close_file = 1;
+		for (i = 0; i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			if (check_pair_status(p))
+				diff_flush_patch(p, options);
+			if (options->found_changes)
+				break;
+		}
+	}
+
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
 			putc(options->line_termination, options->file);
@@ -3508,10 +3670,21 @@ void diff_flush(struct diff_options *options)
 		diff_free_filepair(q->queue[i]);
 free_queue:
 	free(q->queue);
-	q->queue = NULL;
-	q->nr = q->alloc = 0;
+	DIFF_QUEUE_CLEAR(q);
 	if (options->close_file)
 		fclose(options->file);
+
+	/*
+	 * Report the content-level differences with HAS_CHANGES;
+	 * diff_addremove/diff_change does not set the bit when
+	 * DIFF_FROM_CONTENTS is in effect (e.g. with -w).
+	 */
+	if (DIFF_OPT_TST(options, DIFF_FROM_CONTENTS)) {
+		if (options->found_changes)
+			DIFF_OPT_SET(options, HAS_CHANGES);
+		else
+			DIFF_OPT_CLR(options, HAS_CHANGES);
+	}
 }
 
 static void diffcore_apply_filter(const char *filter)
@@ -3519,8 +3692,7 @@ static void diffcore_apply_filter(const char *filter)
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
 	struct diff_queue_struct outq;
-	outq.queue = NULL;
-	outq.nr = outq.alloc = 0;
+	DIFF_QUEUE_CLEAR(&outq);
 
 	if (!filter)
 		return;
@@ -3588,14 +3760,13 @@ static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
 	struct diff_queue_struct outq;
-	outq.queue = NULL;
-	outq.nr = outq.alloc = 0;
+	DIFF_QUEUE_CLEAR(&outq);
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 
 		/*
-		 * 1. Entries that come from stat info dirtyness
+		 * 1. Entries that come from stat info dirtiness
 		 *    always have both sides (iow, not create/delete),
 		 *    one side of the object name is unknown, with
 		 *    the same mode and size.  Keep the ones that
@@ -3631,8 +3802,31 @@ static void diffcore_skip_stat_unmatch(struct diff_options *diffopt)
 	*q = outq;
 }
 
+static int diffnamecmp(const void *a_, const void *b_)
+{
+	const struct diff_filepair *a = *((const struct diff_filepair **)a_);
+	const struct diff_filepair *b = *((const struct diff_filepair **)b_);
+	const char *name_a, *name_b;
+
+	name_a = a->one ? a->one->path : a->two->path;
+	name_b = b->one ? b->one->path : b->two->path;
+	return strcmp(name_a, name_b);
+}
+
+void diffcore_fix_diff_index(struct diff_options *options)
+{
+	struct diff_queue_struct *q = &diff_queued_diff;
+	qsort(q->queue, q->nr, sizeof(q->queue[0]), diffnamecmp);
+}
+
 void diffcore_std(struct diff_options *options)
 {
+	/* We never run this function more than one time, because the
+	 * rename/copy detection logic can only run once.
+	 */
+	if (diff_queued_diff.run)
+		return;
+
 	if (options->skip_stat_unmatch)
 		diffcore_skip_stat_unmatch(options);
 	if (options->break_opt != -1)
@@ -3648,10 +3842,12 @@ void diffcore_std(struct diff_options *options)
 	diff_resolve_rename_copy();
 	diffcore_apply_filter(options->filter);
 
-	if (diff_queued_diff.nr)
+	if (diff_queued_diff.nr && !DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
 		DIFF_OPT_SET(options, HAS_CHANGES);
 	else
 		DIFF_OPT_CLR(options, HAS_CHANGES);
+
+	diff_queued_diff.run = 1;
 }
 
 int diff_result_code(struct diff_options *opt, int status)
@@ -3672,7 +3868,7 @@ int diff_result_code(struct diff_options *opt, int status)
 void diff_addremove(struct diff_options *options,
 		    int addremove, unsigned mode,
 		    const unsigned char *sha1,
-		    const char *concatpath)
+		    const char *concatpath, unsigned dirty_submodule)
 {
 	struct diff_filespec *one, *two;
 
@@ -3704,18 +3900,22 @@ void diff_addremove(struct diff_options *options,
 
 	if (addremove != '+')
 		fill_filespec(one, sha1, mode);
-	if (addremove != '-')
+	if (addremove != '-') {
 		fill_filespec(two, sha1, mode);
+		two->dirty_submodule = dirty_submodule;
+	}
 
 	diff_queue(&diff_queued_diff, one, two);
-	DIFF_OPT_SET(options, HAS_CHANGES);
+	if (!DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
+		DIFF_OPT_SET(options, HAS_CHANGES);
 }
 
 void diff_change(struct diff_options *options,
 		 unsigned old_mode, unsigned new_mode,
 		 const unsigned char *old_sha1,
 		 const unsigned char *new_sha1,
-		 const char *concatpath)
+		 const char *concatpath,
+		 unsigned old_dirty_submodule, unsigned new_dirty_submodule)
 {
 	struct diff_filespec *one, *two;
 
@@ -3728,6 +3928,8 @@ 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_dirty_submodule; old_dirty_submodule = new_dirty_submodule;
+			new_dirty_submodule = tmp;
 	}
 
 	if (options->prefix &&
@@ -3738,9 +3940,12 @@ void diff_change(struct diff_options *options,
 	two = alloc_filespec(concatpath);
 	fill_filespec(one, old_sha1, old_mode);
 	fill_filespec(two, new_sha1, new_mode);
+	one->dirty_submodule = old_dirty_submodule;
+	two->dirty_submodule = new_dirty_submodule;
 
 	diff_queue(&diff_queued_diff, one, two);
-	DIFF_OPT_SET(options, HAS_CHANGES);
+	if (!DIFF_OPT_TST(options, DIFF_FROM_CONTENTS))
+		DIFF_OPT_SET(options, HAS_CHANGES);
 }
 
 void diff_unmerge(struct diff_options *options,
@@ -3767,6 +3972,7 @@ static char *run_textconv(const char *pgm, struct diff_filespec *spec,
 	const char **arg = argv;
 	struct child_process child;
 	struct strbuf buf = STRBUF_INIT;
+	int err = 0;
 
 	temp = prepare_temp_file(spec->path, spec);
 	*arg++ = pgm;
@@ -3774,17 +3980,68 @@ static char *run_textconv(const char *pgm, struct diff_filespec *spec,
 	*arg = NULL;
 
 	memset(&child, 0, sizeof(child));
+	child.use_shell = 1;
 	child.argv = argv;
 	child.out = -1;
-	if (start_command(&child) != 0 ||
-	    strbuf_read(&buf, child.out, 0) < 0 ||
-	    finish_command(&child) != 0) {
+	if (start_command(&child)) {
+		remove_tempfile();
+		return NULL;
+	}
+
+	if (strbuf_read(&buf, child.out, 0) < 0)
+		err = error("error reading from textconv command '%s'", pgm);
+	close(child.out);
+
+	if (finish_command(&child) || err) {
 		strbuf_release(&buf);
 		remove_tempfile();
-		error("error running textconv command '%s'", pgm);
 		return NULL;
 	}
 	remove_tempfile();
 
 	return strbuf_detach(&buf, outsize);
 }
+
+static size_t fill_textconv(struct userdiff_driver *driver,
+			    struct diff_filespec *df,
+			    char **outbuf)
+{
+	size_t size;
+
+	if (!driver || !driver->textconv) {
+		if (!DIFF_FILE_VALID(df)) {
+			*outbuf = "";
+			return 0;
+		}
+		if (diff_populate_filespec(df, 0))
+			die("unable to read files to diff");
+		*outbuf = df->data;
+		return df->size;
+	}
+
+	if (driver->textconv_cache) {
+		*outbuf = notes_cache_get(driver->textconv_cache, df->sha1,
+					  &size);
+		if (*outbuf)
+			return size;
+	}
+
+	*outbuf = run_textconv(driver->textconv, df, &size);
+	if (!*outbuf)
+		die("unable to read files to diff");
+
+	if (driver->textconv_cache) {
+		/* ignore errors, as we might be in a readonly repository */
+		notes_cache_put(driver->textconv_cache, df->sha1, *outbuf,
+				size);
+		/*
+		 * we could save up changes and flush them all at the end,
+		 * but we would need an extra call after all diffing is done.
+		 * Since generating a cache entry is the slow path anyway,
+		 * this extra overhead probably isn't a big deal.
+		 */
+		notes_cache_write(driver->textconv_cache);
+	}
+
+	return size;
+}