RFC patch, 19 partsDiff machine: highlight moved lines.

diff --git a/diff.c b/diff.c
index 74283d9001..3f5bf8b5a4 100644
--- a/diff.c
+++ b/diff.c
@@ -3283,8 +3283,8 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 	const char *other;
 	const char *attr_path;
 
-	name  = p->one->path;
-	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+	name  = one->path;
+	other = (strcmp(name, two->path) ? two->path : NULL);
 	attr_path = name;
 	if (o->prefix_length)
 		strip_prefix(o->prefix_length, &name, &other);

diff --git a/diff.c b/diff.c
index 3f5bf8b5a4..c2ed605cd0 100644
--- a/diff.c
+++ b/diff.c
@@ -677,6 +677,8 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	}
 
 	strbuf_add(&msgbuf, line + len, org_len - len);
+	strbuf_complete_line(&msgbuf);
+
 	emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
@@ -1315,8 +1317,6 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		len = sane_truncate_line(ecbdata, line, len);
 		find_lno(line, ecbdata);
 		emit_hunk_header(ecbdata, line, len);
-		if (line[len-1] != '\n')
-			putc('\n', o->file);
 		return;
 	}
 

diff --git a/diff.c b/diff.c
index 48f0fb98dc..aef159a919 100644
--- a/diff.c
+++ b/diff.c
@@ -552,6 +552,20 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
 	emit_line_0(o, set, reset, 0, line, len);
 }
 
+static void emit_line_fmt(struct diff_options *o,
+			  const char *set, const char *reset,
+			  const char *fmt, ...)
+{
+	struct strbuf sb = STRBUF_INIT;
+	va_list ap;
+	va_start(ap, fmt);
+	strbuf_vaddf(&sb, fmt, ap);
+	va_end(ap);
+
+	emit_line(o, set, reset, sb.buf, sb.len);
+	strbuf_release(&sb);
+}
+
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&

diff --git a/diff.c b/diff.c
index c2ed605cd0..4269b8dccf 100644
--- a/diff.c
+++ b/diff.c
@@ -517,33 +517,24 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 }
 
 static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
-			int first, const char *line, int len)
+			int sign, const char *line, int len)
 {
 	int has_trailing_newline, has_trailing_carriage_return;
-	int nofirst;
 	FILE *file = o->file;
 
 	fputs(diff_line_prefix(o), file);
 
-	if (len == 0) {
-		has_trailing_newline = (first == '\n');
-		has_trailing_carriage_return = (!has_trailing_newline &&
-						(first == '\r'));
-		nofirst = has_trailing_newline || has_trailing_carriage_return;
-	} else {
-		has_trailing_newline = (len > 0 && line[len-1] == '\n');
-		if (has_trailing_newline)
-			len--;
-		has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
-		if (has_trailing_carriage_return)
-			len--;
-		nofirst = 0;
-	}
+	has_trailing_newline = (len > 0 && line[len-1] == '\n');
+	if (has_trailing_newline)
+		len--;
+	has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
+	if (has_trailing_carriage_return)
+		len--;
 
-	if (len || !nofirst) {
+	if (len || sign) {
 		fputs(set, file);
-		if (!nofirst)
-			fputc(first, file);
+		if (sign)
+			fputc(sign, file);
 		fwrite(line, len, 1, file);
 		fputs(reset, file);
 	}
@@ -556,7 +547,7 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 static void emit_line(struct diff_options *o, const char *set, const char *reset,
 		      const char *line, int len)
 {
-	emit_line_0(o, set, reset, line[0], line+1, len-1);
+	emit_line_0(o, set, reset, 0, line, len);
 }
 
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
@@ -4822,9 +4813,12 @@ void diff_flush(struct diff_options *options)
 
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
-			fprintf(options->file, "%s%c",
-				diff_line_prefix(options),
-				options->line_termination);
+			char term[2];
+			term[0] = options->line_termination;
+			term[1] = '\0';
+
+			emit_line(options, NULL, NULL,
+				  term, 1);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);

diff --git a/diff.c b/diff.c
index 93343a9ccc..8e00010bf4 100644
--- a/diff.c
+++ b/diff.c
@@ -1293,8 +1293,9 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	o->found_changes = 1;
 
 	if (ecbdata->header) {
-		fprintf(o->file, "%s", ecbdata->header->buf);
-		strbuf_reset(ecbdata->header);
+		emit_line(o, NULL, NULL,
+			  ecbdata->header->buf, ecbdata->header->len);
+		strbuf_release(ecbdata->header);
 		ecbdata->header = NULL;
 	}
 
@@ -2407,7 +2408,7 @@ 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, meta, a_one, b_two, reset);
+	strbuf_addf(&header, "%sdiff --git %s %s%s\n", meta, a_one, b_two, reset);
 	if (lbl[0][0] == '/') {
 		/* /dev/null */
 		strbuf_addf(&header, "%s%snew file mode %06o%s\n", line_prefix, meta, two->mode, reset);
@@ -2439,7 +2440,7 @@ 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);
+			emit_line(o, NULL, NULL, header.buf, header.len);
 			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
@@ -2449,7 +2450,8 @@ static void builtin_diff(const char *name_a,
 	}
 
 	if (o->irreversible_delete && lbl[1][0] == '/') {
-		fprintf(o->file, "%s", header.buf);
+		if (header.len)
+			emit_line(o, NULL, NULL, header.buf, header.len);
 		strbuf_reset(&header);
 		goto free_ab_and_return;
 	} else if (!DIFF_OPT_TST(o, TEXT) &&
@@ -2459,13 +2461,16 @@ static void builtin_diff(const char *name_a,
 		    S_ISREG(one->mode) && S_ISREG(two->mode) &&
 		    !DIFF_OPT_TST(o, BINARY)) {
 			if (!oidcmp(&one->oid, &two->oid)) {
-				if (must_show_header)
-					fprintf(o->file, "%s", header.buf);
+				if (must_show_header && header.len)
+					emit_line(o, NULL, NULL,
+						  header.buf, header.len);
 				goto free_ab_and_return;
 			}
-			fprintf(o->file, "%s", header.buf);
-			fprintf(o->file, "%sBinary files %s and %s differ\n",
-				line_prefix, lbl[0], lbl[1]);
+			if (header.len)
+				emit_line(o, NULL, NULL,
+					  header.buf, header.len);
+			emit_line_fmt(o, 0, 0, "Binary files %s and %s differ\n",
+				      lbl[0], lbl[1]);
 			goto free_ab_and_return;
 		}
 		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
@@ -2473,17 +2478,21 @@ static void builtin_diff(const char *name_a,
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
-			if (must_show_header)
-				fprintf(o->file, "%s", header.buf);
+			if (must_show_header && header.len)
+				emit_line(o, NULL, NULL,
+					  header.buf, header.len);
 			goto free_ab_and_return;
 		}
-		fprintf(o->file, "%s", header.buf);
+		if (header.len)
+			emit_line(o, NULL, NULL,
+				  header.buf, header.len);
 		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
 			emit_binary_diff(o->file, &mf1, &mf2, line_prefix);
 		else
-			fprintf(o->file, "%sBinary files %s and %s differ\n",
-				line_prefix, lbl[0], lbl[1]);
+			emit_line_fmt(o, NULL, NULL,
+				      "Binary files %s and %s differ\n",
+				      lbl[0], lbl[1]);
 		o->found_changes = 1;
 	} else {
 		/* Crazy xdl interfaces.. */
@@ -2494,8 +2503,8 @@ static void builtin_diff(const char *name_a,
 		struct emit_callback ecbdata;
 		const struct userdiff_funcname *pe;
 
-		if (must_show_header) {
-			fprintf(o->file, "%s", header.buf);
+		if (must_show_header && header.len) {
+			emit_line(o, NULL, NULL, header.buf, header.len);
 			strbuf_reset(&header);
 		}
 

diff --git a/diff.c b/diff.c
index e4b46fee4f..369c804f03 100644
--- a/diff.c
+++ b/diff.c
@@ -748,7 +748,7 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 	if (!endp) {
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
-		putc('\n', ecb->opt->file);
+		emit_line(ecb->opt, NULL, NULL, "\n", 1);
 		emit_line_0(ecb->opt, context, reset, '\\',
 			    nneof, strlen(nneof));
 	}

diff --git a/diff.c b/diff.c
index 0f10736ee6..f46e52135d 100644
--- a/diff.c
+++ b/diff.c
@@ -1011,15 +1011,27 @@ static void add_line_count(struct strbuf *out,
int count)
 static void emit_rewrite_lines(struct emit_callback *ecb,
                               int prefix, const char *data, int size)
 {
-       const char *endp = NULL;
-       static const char *nneof = " No newline at end of file\n";
+       static const char *nneof = "\\ No newline at end of file\n";
        const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET);
+       struct strbuf sb = STRBUF_INIT;

        while (0 < size) {
                int len;

                endp = memchr(data, '\n', size);
-               len = endp ? (endp - data + 1) : size;
+               if (endp)
+                       len = endp - data + 1;
+               else {
+                       /* last line has no \n */
+                       while (0 < size) {
+                               strbuf_addch(&sb, *data);
+                               size -= len;
+                               data += len;
+                       }
+                       strbuf_addch(&sb, '\n');
+                       data = sb.buf;
+                       len = sb.len;
+               }
                if (prefix != '+') {
                        ecb->lno_in_preimage++;
                        emit_del_line(reset, ecb, data, len);
@@ -1030,12 +1042,12 @@ static void emit_rewrite_lines(struct
emit_callback *ecb,
                size -= len;
                data += len;
        }
-       if (!endp) {
+       if (sb.len) {
                const char *context = diff_get_color(ecb->color_diff,
                                                     DIFF_CONTEXT);
-               emit_line(ecb->opt, NULL, NULL, "\n", 1);
-               emit_line_0(ecb->opt, context, reset, '\\',
+               emit_line(ecb->opt, context, reset,
                            nneof, strlen(nneof));
+               strbuf_release(&sb);
        }
 }

diff --git a/diff.c b/diff.c
index aef159a919..93343a9ccc 100644
--- a/diff.c
+++ b/diff.c
@@ -1289,7 +1289,6 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT);
 	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
 	struct diff_options *o = ecbdata->opt;
-	const char *line_prefix = diff_line_prefix(o);
 
 	o->found_changes = 1;
 
@@ -1301,14 +1300,12 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 
 	if (ecbdata->label_path[0]) {
 		const char *name_a_tab, *name_b_tab;
-
 		name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
 		name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";
-
-		fprintf(o->file, "%s%s--- %s%s%s\n",
-			line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab);
-		fprintf(o->file, "%s%s+++ %s%s%s\n",
-			line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab);
+		emit_line_fmt(o, meta, reset, "--- %s%s\n",
+			      ecbdata->label_path[0], name_a_tab);
+		emit_line_fmt(o, meta, reset, "+++ %s%s\n",
+			      ecbdata->label_path[1], name_b_tab);
 		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
 	}
 
@@ -1349,7 +1346,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		diff_words_flush(ecbdata);
 		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
 			emit_line(o, context, reset, line, len);
-			fputs("~\n", o->file);
+			emit_line(o, NULL, NULL, "~\n", 2);
 		} else {
 			/*
 			 * Skip the prefix character, if any.  With

diff.c, diff.h, submodule.c, submodule.h

diff --git a/diff.c b/diff.c
index 369c804f03..45ec311828 100644
--- a/diff.c
+++ b/diff.c
@@ -546,15 +546,15 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 		fputc('\n', file);
 }
 
-static void emit_line(struct diff_options *o, const char *set, const char *reset,
-		      const char *line, int len)
+void emit_line(struct diff_options *o, const char *set, const char *reset,
+	       const char *line, int len)
 {
 	emit_line_0(o, set, reset, 0, line, len);
 }
 
-static void emit_line_fmt(struct diff_options *o,
-			  const char *set, const char *reset,
-			  const char *fmt, ...)
+void emit_line_fmt(struct diff_options *o,
+		   const char *set, const char *reset,
+		   const char *fmt, ...)
 {
 	struct strbuf sb = STRBUF_INIT;
 	va_list ap;
@@ -2379,8 +2379,7 @@ static void builtin_diff(const char *name_a,
 	    (!two->mode || S_ISGITLINK(two->mode))) {
 		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->path ? one->path : two->path,
-				line_prefix,
+		show_submodule_summary(o, one->path ? one->path : two->path,
 				&one->oid, &two->oid,
 				two->dirty_submodule,
 				meta, del, add, reset);
@@ -2390,11 +2389,10 @@ static void builtin_diff(const char *name_a,
 		   (!two->mode || S_ISGITLINK(two->mode))) {
 		const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
 		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
-		show_submodule_inline_diff(o->file, one->path ? one->path : two->path,
-				line_prefix,
+		show_submodule_inline_diff(o, one->path ? one->path : two->path,
 				&one->oid, &two->oid,
 				two->dirty_submodule,
-				meta, del, add, reset, o);
+				meta, del, add, reset);
 		return;
 	}
 
diff --git a/diff.h b/diff.h
index 5be1ee77a7..addebd5a0f 100644
--- a/diff.h
+++ b/diff.h
@@ -188,6 +188,11 @@ struct diff_options {
 	int diff_path_counter;
 };
 
+void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
+		   const char *fmt, ...);
+void emit_line(struct diff_options *o, const char *set, const char *reset,
+	       const char *line, int len);
+
 enum color_diff {
 	DIFF_RESET = 0,
 	DIFF_CONTEXT = 1,
diff --git a/submodule.c b/submodule.c
index d3299e29c0..cfad469a2f 100644
--- a/submodule.c
+++ b/submodule.c
@@ -362,8 +362,8 @@ static int prepare_submodule_summary(struct rev_info *rev, const char *path,
 	return prepare_revision_walk(rev);
 }
 
-static void print_submodule_summary(struct rev_info *rev, FILE *f,
-		const char *line_prefix,
+static void print_submodule_summary(struct rev_info *rev,
+		struct diff_options *o,
 		const char *del, const char *add, const char *reset)
 {
 	static const char format[] = "  %m %s";
@@ -375,18 +375,12 @@ static void print_submodule_summary(struct rev_info *rev, FILE *f,
 		ctx.date_mode = rev->date_mode;
 		ctx.output_encoding = get_log_output_encoding();
 		strbuf_setlen(&sb, 0);
-		strbuf_addstr(&sb, line_prefix);
-		if (commit->object.flags & SYMMETRIC_LEFT) {
-			if (del)
-				strbuf_addstr(&sb, del);
-		}
-		else if (add)
-			strbuf_addstr(&sb, add);
 		format_commit_message(commit, format, &sb, &ctx);
-		if (reset)
-			strbuf_addstr(&sb, reset);
 		strbuf_addch(&sb, '\n');
-		fprintf(f, "%s", sb.buf);
+		if (commit->object.flags & SYMMETRIC_LEFT)
+			emit_line(o, del, reset, sb.buf, sb.len);
+		else if (add)
+			emit_line(o, add, reset, sb.buf, sb.len);
 	}
 	strbuf_release(&sb);
 }
@@ -413,8 +407,7 @@ void prepare_submodule_repo_env(struct argv_array *out)
  * attempt to lookup both the left and right commits and put them into the
  * left and right pointers.
  */
-static void show_submodule_header(FILE *f, const char *path,
-		const char *line_prefix,
+static void show_submodule_header(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *reset,
@@ -426,11 +419,11 @@ static void show_submodule_header(FILE *f, const char *path,
 	int fast_forward = 0, fast_backward = 0;
 
 	if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED)
-		fprintf(f, "%sSubmodule %s contains untracked content\n",
-			line_prefix, path);
+		emit_line_fmt(o, NULL, NULL,
+			      "Submodule %s contains untracked content\n", path);
 	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED)
-		fprintf(f, "%sSubmodule %s contains modified content\n",
-			line_prefix, path);
+		emit_line_fmt(o, NULL, NULL,
+			      "Submodule %s contains modified content\n", path);
 
 	if (is_null_oid(one))
 		message = "(new submodule)";
@@ -472,21 +465,20 @@ static void show_submodule_header(FILE *f, const char *path,
 	}
 
 output_header:
-	strbuf_addf(&sb, "%s%sSubmodule %s ", line_prefix, meta, path);
+	strbuf_addf(&sb, "Submodule %s ", path);
 	strbuf_add_unique_abbrev(&sb, one->hash, DEFAULT_ABBREV);
 	strbuf_addstr(&sb, (fast_backward || fast_forward) ? ".." : "...");
 	strbuf_add_unique_abbrev(&sb, two->hash, DEFAULT_ABBREV);
 	if (message)
-		strbuf_addf(&sb, " %s%s\n", message, reset);
+		strbuf_addf(&sb, " %s\n", message);
 	else
-		strbuf_addf(&sb, "%s:%s\n", fast_backward ? " (rewind)" : "", reset);
-	fwrite(sb.buf, sb.len, 1, f);
+		strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : "");
+	emit_line(o, meta, reset, sb.buf, sb.len);
 
 	strbuf_release(&sb);
 }
 
-void show_submodule_summary(FILE *f, const char *path,
-		const char *line_prefix,
+void show_submodule_summary(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *del, const char *add, const char *reset)
@@ -495,7 +487,7 @@ void show_submodule_summary(FILE *f, const char *path,
 	struct commit *left = NULL, *right = NULL;
 	struct commit_list *merge_bases = NULL;
 
-	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
+	show_submodule_header(o, path, one, two, dirty_submodule,
 			      meta, reset, &left, &right, &merge_bases);
 
 	/*
@@ -508,11 +500,12 @@ void show_submodule_summary(FILE *f, const char *path,
 
 	/* Treat revision walker failure the same as missing commits */
 	if (prepare_submodule_summary(&rev, path, left, right, merge_bases)) {
-		fprintf(f, "%s(revision walker failed)\n", line_prefix);
+		const char *error = "(revision walker failed)\n";
+		emit_line(o, NULL, NULL, error, strlen(error));
 		goto out;
 	}
 
-	print_submodule_summary(&rev, f, line_prefix, del, add, reset);
+	print_submodule_summary(&rev, o, del, add, reset);
 
 out:
 	if (merge_bases)
@@ -521,20 +514,18 @@ void show_submodule_summary(FILE *f, const char *path,
 	clear_commit_marks(right, ~0);
 }
 
-void show_submodule_inline_diff(FILE *f, const char *path,
-		const char *line_prefix,
+void show_submodule_inline_diff(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
-		const char *del, const char *add, const char *reset,
-		const struct diff_options *o)
+		const char *del, const char *add, const char *reset)
 {
 	const struct object_id *old = &empty_tree_oid, *new = &empty_tree_oid;
 	struct commit *left = NULL, *right = NULL;
 	struct commit_list *merge_bases = NULL;
-	struct strbuf submodule_dir = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
+	struct strbuf sb = STRBUF_INIT;
 
-	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
+	show_submodule_header(o, path, one, two, dirty_submodule,
 			      meta, reset, &left, &right, &merge_bases);
 
 	/* We need a valid left and right commit to display a difference */
@@ -547,15 +538,14 @@ void show_submodule_inline_diff(FILE *f, const char *path,
 	if (right)
 		new = two;
 
-	fflush(f);
 	cp.git_cmd = 1;
 	cp.dir = path;
-	cp.out = dup(fileno(f));
+	cp.out = -1;
 	cp.no_stdin = 1;
 
 	/* TODO: other options may need to be passed here. */
 	argv_array_push(&cp.args, "diff");
-	argv_array_pushf(&cp.args, "--line-prefix=%s", line_prefix);
+	argv_array_pushf(&cp.args, "--line-prefix=%s", diff_line_prefix(o));
 	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
 		argv_array_pushf(&cp.args, "--src-prefix=%s%s/",
 				 o->b_prefix, path);
@@ -578,11 +568,21 @@ void show_submodule_inline_diff(FILE *f, const char *path,
 		argv_array_push(&cp.args, oid_to_hex(new));
 
 	prepare_submodule_repo_env(&cp.env_array);
-	if (run_command(&cp))
-		fprintf(f, "(diff failed)\n");
+	if (start_command(&cp)) {
+		const char *error = "(diff failed)\n";
+		emit_line(o, NULL, NULL, error, strlen(error));
+	}
+
+	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
+		emit_line(o, NULL, NULL, sb.buf, sb.len);
+
+	if (finish_command(&cp)) {
+		const char *error = "(diff failed)\n";
+		emit_line(o, NULL, NULL, error, strlen(error));
+	}
 
 done:
-	strbuf_release(&submodule_dir);
+	strbuf_release(&sb);
 	if (merge_bases)
 		free_commit_list(merge_bases);
 	if (left)
diff --git a/submodule.h b/submodule.h
index 1277480add..9df0a3aea2 100644
--- a/submodule.h
+++ b/submodule.h
@@ -53,17 +53,14 @@ extern int parse_submodule_update_strategy(const char *value,
 		struct submodule_update_strategy *dst);
 extern const char *submodule_strategy_to_string(const struct submodule_update_strategy *s);
 extern void handle_ignore_submodules_arg(struct diff_options *, const char *);
-extern void show_submodule_summary(FILE *f, const char *path,
-		const char *line_prefix,
+extern void show_submodule_summary(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *del, const char *add, const char *reset);
-extern void show_submodule_inline_diff(FILE *f, const char *path,
-		const char *line_prefix,
+extern void show_submodule_inline_diff(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
-		const char *del, const char *add, const char *reset,
-		const struct diff_options *opt);
+		const char *del, const char *add, const char *reset);
 extern void set_config_fetch_recurse_submodules(int value);
 extern void set_config_update_recurse_submodules(int value);
 /* Check if we want to update any submodule.*/

diff --git a/diff.c b/diff.c
index 899dc69dff..08dcc56bb9 100644
--- a/diff.c
+++ b/diff.c
@@ -552,6 +552,16 @@ void emit_line(struct diff_options *o, const char *set, const char *reset,
 	emit_line_0(o, set, reset, 0, line, len);
 }
 
+static void emit_line_ws(struct diff_options *o,
+			 const char *set, const char *reset, int sign,
+			 const char *line, int len,
+			 const char *ws, unsigned ws_rule)
+{
+	emit_line_0(o, set, reset, sign, "", 0);
+	ws_check_emit(line, len, ws_rule,
+		      o->file, set, reset, ws);
+}
+
 void emit_line_fmt(struct diff_options *o,
 		   const char *set, const char *reset,
 		   const char *fmt, ...)
@@ -598,12 +608,10 @@ static void emit_line_checked(const char *reset,
 	else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len))
 		/* Blank line at EOF - paint '+' as well */
 		emit_line_0(ecbdata->opt, ws, reset, sign, line, len);
-	else {
+	else
 		/* Emit just the prefix, then the rest. */
-		emit_line_0(ecbdata->opt, set, reset, sign, "", 0);
-		ws_check_emit(line, len, ecbdata->ws_rule,
-			      ecbdata->opt->file, set, reset, ws);
-	}
+		emit_line_ws(ecbdata->opt, set, reset, sign, line, len,
+			     ws, ecbdata->ws_rule);
 }
 
 static void emit_add_line(const char *reset,

diff --git a/diff.c b/diff.c
index 91dc045a45..07041a35ad 100644
--- a/diff.c
+++ b/diff.c
@@ -886,37 +886,38 @@ struct diff_words_data {
 	struct diff_words_style *style;
 };
 
-static int fn_out_diff_words_write_helper(FILE *fp,
+static int fn_out_diff_words_write_helper(struct diff_options *o,
 					  struct diff_words_style_elem *st_el,
 					  const char *newline,
 					  size_t count, const char *buf,
 					  const char *line_prefix)
 {
-	int print = 0;
+	struct strbuf sb = STRBUF_INIT;
 
 	while (count) {
 		char *p = memchr(buf, '\n', count);
-		if (print)
-			fputs(line_prefix, fp);
+
 		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 (st_el->color)
+				strbuf_addstr(&sb, st_el->color);
+			strbuf_addstr(&sb, st_el->prefix);
+			strbuf_add(&sb, buf, p ? p - buf : count);
+			strbuf_addstr(&sb, st_el->suffix);
+			if (st_el->color && *st_el->color)
+			    strbuf_addstr(&sb, GIT_COLOR_RESET);
 		}
 		if (!p)
-			return 0;
-		if (fputs(newline, fp) < 0)
-			return -1;
+			goto out;
+		strbuf_addstr(&sb, newline);
+		emit_line(o, NULL, NULL, sb.buf, sb.len);
+		strbuf_reset(&sb);
 		count -= p + 1 - buf;
 		buf = p + 1;
-		print = 1;
 	}
+out:
+	if (sb.len)
+		emit_line(o, NULL, NULL, sb.buf, sb.len);
+	strbuf_release(&sb);
 	return 0;
 }
 
@@ -994,25 +995,25 @@ static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 	} else
 		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
 
-	if (color_words_output_graph_prefix(diff_words)) {
-		fputs(line_prefix, diff_words->opt->file);
-	}
+	if (color_words_output_graph_prefix(diff_words))
+		emit_line(diff_words->opt, NULL, NULL, "", 0);
+
 	if (diff_words->current_plus != plus_begin) {
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->ctx, style->newline,
 				plus_begin - diff_words->current_plus,
 				diff_words->current_plus, line_prefix);
 		if (*(plus_begin - 1) == '\n')
-			fputs(line_prefix, diff_words->opt->file);
+			emit_line(diff_words->opt, NULL, NULL, "", 0);
 	}
 	if (minus_begin != minus_end) {
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->old, style->newline,
 				minus_end - minus_begin, minus_begin,
 				line_prefix);
 	}
 	if (plus_begin != plus_end) {
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->new, style->newline,
 				plus_end - plus_begin, plus_begin,
 				line_prefix);
@@ -1109,8 +1110,7 @@ static void diff_words_show(struct diff_words_data *diff_words)
 
 	/* special case: only removal */
 	if (!diff_words->plus.text.size) {
-		fputs(line_prefix, diff_words->opt->file);
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+		fn_out_diff_words_write_helper(diff_words->opt,
 			&style->old, style->newline,
 			diff_words->minus.text.size,
 			diff_words->minus.text.ptr, line_prefix);
@@ -1136,8 +1136,8 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	if (diff_words->current_plus != diff_words->plus.text.ptr +
 			diff_words->plus.text.size) {
 		if (color_words_output_graph_prefix(diff_words))
-			fputs(line_prefix, diff_words->opt->file);
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+			emit_line(diff_words->opt, NULL, NULL, "", 0);
+		fn_out_diff_words_write_helper(diff_words->opt,
 			&style->ctx, style->newline,
 			diff_words->plus.text.ptr + diff_words->plus.text.size
 			- diff_words->current_plus, diff_words->current_plus,

diff.c, diff.h

diff --git a/diff.c b/diff.c
index 08dcc56bb9..dbab7fb44e 100644
--- a/diff.c
+++ b/diff.c
@@ -516,29 +516,29 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
-			int sign, const char *line, int len)
+static void emit_buffered_patch_line(struct diff_options *o,
+				     struct buffered_patch_line *e)
 {
-	int has_trailing_newline, has_trailing_carriage_return;
+	int has_trailing_newline, has_trailing_carriage_return, len = e->len;
 	FILE *file = o->file;
 
 	fputs(diff_line_prefix(o), file);
 
-	has_trailing_newline = (len > 0 && line[len-1] == '\n');
+	has_trailing_newline = (len > 0 && e->line[len-1] == '\n');
 	if (has_trailing_newline)
 		len--;
-	has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
+	has_trailing_carriage_return = (len > 0 && e->line[len-1] == '\r');
 	if (has_trailing_carriage_return)
 		len--;
 
-	if (len || sign) {
-		if (set)
-			fputs(set, file);
-		if (sign)
-			fputc(sign, file);
-		fwrite(line, len, 1, file);
-		if (reset)
-			fputs(reset, file);
+	if (len || e->sign) {
+		if (e->set)
+			fputs(e->set, file);
+		if (e->sign)
+			fputc(e->sign, file);
+		fwrite(e->line, len, 1, file);
+		if (e->reset)
+			fputs(e->reset, file);
 	}
 	if (has_trailing_carriage_return)
 		fputc('\r', file);
@@ -546,6 +546,65 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 		fputc('\n', file);
 }
 
+static void emit_buffered_patch_line_ws(struct diff_options *o,
+					struct buffered_patch_line *e,
+					const char *ws, unsigned ws_rule)
+{
+	struct buffered_patch_line s = {e->set, e->reset, "", 0, e->sign};
+
+	emit_buffered_patch_line(o, &s);
+	ws_check_emit(e->line, e->len, ws_rule,
+		      o->file, e->set, e->reset, ws);
+}
+
+static void process_next_buffered_patch_line(struct diff_options *o, int line_no)
+{
+	struct buffered_patch_line *e = &o->line_buffer[line_no];
+
+	const char *ws = o->current_filepair->ws;
+	unsigned ws_rule = o->current_filepair->ws_rule;
+
+	switch (e->state) {
+		case BPL_EMIT_LINE_ASIS:
+			emit_buffered_patch_line(o, e);
+			break;
+		case BPL_EMIT_LINE_WS:
+			emit_buffered_patch_line_ws(o, e, ws, ws_rule);
+			break;
+		case BPL_HANDOVER:
+			o->current_filepair++;
+			break;
+		default:
+			die("BUG: malformatted buffered patch line: '%d'", e->state);
+	}
+}
+
+static void append_buffered_patch_line(struct diff_options *o,
+				       struct buffered_patch_line *e)
+{
+	struct buffered_patch_line *f;
+	ALLOC_GROW(o->line_buffer,
+		   o->line_buffer_nr + 1,
+		   o->line_buffer_alloc);
+	f = &o->line_buffer[o->line_buffer_nr];
+	o->line_buffer_nr++;
+
+	memcpy(f, e, sizeof(struct buffered_patch_line));
+	f->line = e->line ? xmemdupz(e->line, e->len) : NULL;
+}
+
+static void emit_line_0(struct diff_options *o,
+			const char *set, const char *reset,
+			int sign, const char *line, int len)
+{
+	struct buffered_patch_line e = {set, reset, line, len, sign, BPL_EMIT_LINE_ASIS};
+
+	if (o->use_buffer)
+		append_buffered_patch_line(o, &e);
+	else
+		emit_buffered_patch_line(o, &e);
+}
+
 void emit_line(struct diff_options *o, const char *set, const char *reset,
 	       const char *line, int len)
 {
@@ -557,9 +616,12 @@ static void emit_line_ws(struct diff_options *o,
 			 const char *line, int len,
 			 const char *ws, unsigned ws_rule)
 {
-	emit_line_0(o, set, reset, sign, "", 0);
-	ws_check_emit(line, len, ws_rule,
-		      o->file, set, reset, ws);
+	struct buffered_patch_line e = {set, reset, line, len, sign, BPL_EMIT_LINE_WS};
+
+	if (o->use_buffer)
+		append_buffered_patch_line(o, &e);
+	else
+		emit_buffered_patch_line_ws(o, &e, ws, ws_rule);
 }
 
 void emit_line_fmt(struct diff_options *o,
@@ -1160,6 +1222,16 @@ static void diff_words_flush(struct emit_callback *ecbdata)
 	if (ecbdata->diff_words->minus.text.size ||
 	    ecbdata->diff_words->plus.text.size)
 		diff_words_show(ecbdata->diff_words);
+
+	if (ecbdata->diff_words->opt->line_buffer_nr) {
+		int i;
+		for (i = 0; i < ecbdata->diff_words->opt->line_buffer_nr; i++)
+			append_buffered_patch_line(ecbdata->opt,
+				&ecbdata->diff_words->opt->line_buffer[i]);
+
+		ecbdata->diff_words->opt->line_buffer_nr = 0;
+		/* TODO: free memory as well */
+	}
 }
 
 static void diff_filespec_load_driver(struct diff_filespec *one)
@@ -1195,6 +1267,11 @@ static void init_diff_words_data(struct emit_callback *ecbdata,
 		xcalloc(1, sizeof(struct diff_words_data));
 	ecbdata->diff_words->type = o->word_diff;
 	ecbdata->diff_words->opt = o;
+
+	o->line_buffer = NULL;
+	o->line_buffer_nr = 0;
+	o->line_buffer_alloc = 0;
+
 	if (!o->word_regex)
 		o->word_regex = userdiff_word_regex(one);
 	if (!o->word_regex)
@@ -2568,9 +2645,25 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(v, NULL, 10);
 		if (o->word_diff)
 			init_diff_words_data(&ecbdata, o, one, two);
+		if (o->use_buffer) {
+			ALLOC_GROW(o->filepair_buffer,
+				   o->filepair_buffer_nr + 1,
+				   o->filepair_buffer_alloc);
+			o->current_filepair =
+				&o->filepair_buffer[o->filepair_buffer_nr++];
+
+			o->current_filepair->ws_rule = ecbdata.ws_rule;
+			o->current_filepair->ws =
+				diff_get_color(ecbdata.color_diff, DIFF_WHITESPACE);
+		}
 		if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 				  &xpp, &xecfg))
 			die("unable to generate diff for %s", one->path);
+		if (o->use_buffer) {
+			struct buffered_patch_line e = BUFFERED_PATCH_LINE_INIT;
+			e.state = BPL_HANDOVER; /* handover to next file pair */
+			append_buffered_patch_line(o, &e);
+		}
 		if (o->word_diff)
 			free_diff_words_data(&ecbdata);
 		if (textconv_one)
@@ -4785,11 +4878,44 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 {
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
+	/*
+	 * For testing purposes we want to make sure the diff machinery
+	 * works completely with the buffer. If there is anything emitted
+	 * outside the emit_buffered_patch_line, then the order is screwed
+	 * up and the tests will fail.
+	 *
+	 * TODO (later in this series):
+	 * We'll unset this flag in a later patch.
+	 */
+	o->use_buffer = 1;
+
+	if (o->use_buffer) {
+		ALLOC_GROW(o->filepair_buffer,
+			   o->filepair_buffer_nr + 1,
+			   o->filepair_buffer_alloc);
+		o->current_filepair = &o->filepair_buffer[o->filepair_buffer_nr];
+	}
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		if (check_pair_status(p))
 			diff_flush_patch(p, o);
 	}
+
+	if (o->use_buffer) {
+		o->current_filepair = &o->filepair_buffer[0];
+		for (i = 0; i < o->line_buffer_nr; i++)
+			process_next_buffered_patch_line(o, i);
+
+		for (i = 0; i < o->line_buffer_nr; i++);
+			free((void*)o->line_buffer[i].line);
+
+		o->line_buffer = NULL;
+		o->line_buffer_nr = 0;
+		free(o->line_buffer);
+		o->filepair_buffer = NULL;
+		o->filepair_buffer_nr = 0;
+		free(o->filepair_buffer);
+	}
 }
 
 void diff_flush(struct diff_options *options)
diff --git a/diff.h b/diff.h
index 5e89481769..c334aac02e 100644
--- a/diff.h
+++ b/diff.h
@@ -115,6 +115,36 @@ enum diff_submodule_format {
 	DIFF_SUBMODULE_INLINE_DIFF
 };
 
+/*
+ * This struct is used when we need to buffer the output of the diff output.
+ *
+ * NEEDSWORK: Instead of storing a copy of the line, add an offset pointer
+ * into the pre/post image file. This pointer could be a union with the
+ * line pointer. By storing an offset into the file instead of the literal line,
+ * we can decrease the memory footprint for the buffered output. At first we
+ * may want to only have indirection for the content lines, but we could
+ * also have an enum (based on sign?) that stores prefabricated lines, e.g.
+ * the similarity score line or hunk/file headers.
+ */
+struct buffered_patch_line {
+	const char *set;
+	const char *reset;
+	const char *line;
+	int len;
+	int sign;
+	enum {
+		BPL_EMIT_LINE_WS,
+		BPL_EMIT_LINE_ASIS,
+		BPL_HANDOVER
+	} state;
+};
+#define BUFFERED_PATCH_LINE_INIT {NULL, NULL, NULL, 0, 0, 0}
+
+struct buffered_filepair {
+	const char *ws;
+	unsigned ws_rule;
+};
+
 struct diff_options {
 	const char *orderfile;
 	const char *pickaxe;
@@ -186,6 +216,15 @@ struct diff_options {
 	void *output_prefix_data;
 
 	int diff_path_counter;
+
+	int use_buffer;
+
+	struct buffered_patch_line *line_buffer;
+	int line_buffer_nr, line_buffer_alloc;
+
+	struct buffered_filepair *filepair_buffer;
+	int filepair_buffer_nr, filepair_buffer_alloc;
+	struct buffered_filepair *current_filepair;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,

@@ -557,9 +616,12 @@ static void emit_line_ws(struct diff_options *o,
                         const char *line, int len,
                         const char *ws, unsigned ws_rule)
 {
-       emit_line_0(o, set, reset, sign, "", 0);
-       ws_check_emit(line, len, ws_rule,
-                     o->file, set, reset, ws);
+       struct buffered_patch_line e = {set, reset, line, len, sign,
BPL_EMIT_LINE_WS};
+
+       if (o->use_buffer)
+               append_buffered_patch_line(o, &e);
+       else
+               emit_buffered_patch_line_ws(o, &e, ws, ws_rule);
 }

>> +       switch (e->state) {
>> +               case BPL_EMIT_LINE_ASIS:
>> +                       emit_buffered_patch_line(o, e);
>> +                       break;
>> +               case BPL_EMIT_LINE_WS:
>> +                       emit_buffered_patch_line_ws(o, e, ws, ws_rule);
>> +                       break;
>> +               case BPL_HANDOVER:
>> +                       o->current_filepair++;
>
> If we're just buffering the diff output, do we need to store
> per-file-pair metadata? (I assume that's why you need a special
> handover constant.) Clients can already read what they need from the
> diff output.

Currently we keep only whitespace settings per-file separate as they are
defined per path (via attributes).

So I read this comment as if you consider the per-file buffer unneeded and
we could just detect the next file via the line

    <line-prefix>diff --git a/<file> b/<file>

and then re-read the attributes and remember only the current files settings in
the output pass. I'll look into that.

>> +        *
>> +        * TODO (later in this series):
>> +        * We'll unset this flag in a later patch.
>> +        */
>> +       o->use_buffer = 1;
>
> What I would do is to add a demonstration patch at the end of the
> patch series (which is not supposed to be queued) to avoid such churn
> in history, but I'm not sure how the Git project prefers to do this.

ok, I can omit this part in a reroll.

>> + *
>> + * NEEDSWORK: Instead of storing a copy of the line, add an offset pointer
>> + * into the pre/post image file. This pointer could be a union with the
>> + * line pointer. By storing an offset into the file instead of the literal line,
>> + * we can decrease the memory footprint for the buffered output. At first we
>> + * may want to only have indirection for the content lines, but we could
>> + * also have an enum (based on sign?) that stores prefabricated lines, e.g.
>> + * the similarity score line or hunk/file headers.
>
> This would be nice, but come to think of it, might not be possible.
> When requesting --word-diff, control characters (or others) might
> appear in the output, right?

That is why we'd have even more states. ;)
Or duplicate word diff still, but lines left intact are referenced via offsets.
It's a hard problem to get right, so I defer it via this comment.

>
>> + */
>> +struct buffered_patch_line {
>> +       const char *set;
>> +       const char *reset;
>> +       const char *line;
>> +       int len;
>> +       int sign;
>> +       enum {
>> +               BPL_EMIT_LINE_WS,
>> +               BPL_EMIT_LINE_ASIS,
>> +               BPL_HANDOVER
>> +       } state;
>
> It might be better, for simplicity, just to have one big buffer
> including everything (if we decide that we really can't add pointers
> to input later).

What do you mean here? (Drop the other structs such as the file pair?)

Thanks for the review!
Stefan

Documentation/config.txt, diff.c, diff.h, t/t4015-diff-whitespace.sh

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 475e874d51..90403c06e3 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1051,14 +1051,22 @@ This does not affect linkgit:git-format-patch[1] or the
 'git-diff-{asterisk}' plumbing commands.  Can be overridden on the
 command line with the `--color[=<when>]` option.
 
+color.moved::
+	A boolean value, whether a diff should color moved lines
+	differently. The moved lines are searched for in the diff only.
+	Duplicated lines from somewhere in the project that are not
+	part of the diff are not colored as moved.
+	Defaults to false.
+
 color.diff.<slot>::
 	Use customized color for diff colorization.  `<slot>` specifies
 	which part of the patch to use the specified color, and is one
 	of `context` (context text - `plain` is a historical synonym),
 	`meta` (metainformation), `frag`
 	(hunk header), 'func' (function in hunk header), `old` (removed lines),
-	`new` (added lines), `commit` (commit headers), or `whitespace`
-	(highlighting whitespace errors).
+	`new` (added lines), `commit` (commit headers), `whitespace`
+	(highlighting whitespace errors), `movedFrom` (removed lines that
+	reappear), `movedTo` (added lines that were removed elsewhere).
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/diff.c b/diff.c
index dbab7fb44e..6372e0eb25 100644
--- a/diff.c
+++ b/diff.c
@@ -31,6 +31,7 @@ static int diff_indent_heuristic; /* experimental */
 static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
 static int diff_use_color_default = -1;
+static int diff_color_moved_default;
 static int diff_context_default = 3;
 static int diff_interhunk_context_default;
 static const char *diff_word_regex_cfg;
@@ -55,6 +56,10 @@ static char diff_colors[][COLOR_MAXLEN] = {
 	GIT_COLOR_YELLOW,	/* COMMIT */
 	GIT_COLOR_BG_RED,	/* WHITESPACE */
 	GIT_COLOR_NORMAL,	/* FUNCINFO */
+	GIT_COLOR_BOLD_RED,	/* OLD_MOVED_A */
+	GIT_COLOR_BG_RED,	/* OLD_MOVED_B */
+	GIT_COLOR_BOLD_GREEN,	/* NEW_MOVED_A */
+	GIT_COLOR_BG_GREEN,	/* NEW_MOVED_B */
 };
 
 static NORETURN void die_want_option(const char *option_name)
@@ -80,6 +85,14 @@ static int parse_diff_color_slot(const char *var)
 		return DIFF_WHITESPACE;
 	if (!strcasecmp(var, "func"))
 		return DIFF_FUNCINFO;
+	if (!strcasecmp(var, "oldmoved"))
+		return DIFF_FILE_OLD_MOVED;
+	if (!strcasecmp(var, "oldmovedalternative"))
+		return DIFF_FILE_OLD_MOVED_ALT;
+	if (!strcasecmp(var, "newmoved"))
+		return DIFF_FILE_NEW_MOVED;
+	if (!strcasecmp(var, "newmovedalternative"))
+		return DIFF_FILE_NEW_MOVED_ALT;
 	return -1;
 }
 
@@ -234,6 +247,10 @@ 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, "color.moved")) {
+		diff_color_moved_default = git_config_bool(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "diff.context")) {
 		diff_context_default = git_config_int(var, value);
 		if (diff_context_default < 0)
@@ -354,6 +371,81 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 	return git_default_config(var, value, cb);
 }
 
+struct moved_entry {
+	struct hashmap_entry ent;
+	const struct buffered_patch_line *line;
+	struct moved_entry *next_line;
+};
+
+static void get_ws_cleaned_string(const struct buffered_patch_line *l,
+				  struct strbuf *out)
+{
+	int i;
+	for (i = 0; i < l->len; i++) {
+		if (isspace(l->line[i]))
+			continue;
+		strbuf_addch(out, l->line[i]);
+	}
+}
+
+static int buffered_patch_line_cmp_no_ws(const struct buffered_patch_line *a,
+					 const struct buffered_patch_line *b,
+					 const void *keydata)
+{
+	struct strbuf sba = STRBUF_INIT;
+	struct strbuf sbb = STRBUF_INIT;
+	get_ws_cleaned_string(a, &sba);
+	get_ws_cleaned_string(b, &sbb);
+	return sba.len != sbb.len || strncmp(sba.buf, sbb.buf, sba.len);
+}
+
+static int buffered_patch_line_cmp(const struct buffered_patch_line *a,
+				   const struct buffered_patch_line *b,
+				   const void *keydata)
+{
+	return a->len != b->len || strncmp(a->line, b->line, a->len);
+}
+
+static int moved_entry_cmp(const struct moved_entry *a,
+			   const struct moved_entry *b,
+			   const void *keydata)
+{
+	return buffered_patch_line_cmp(a->line, b->line, keydata);
+}
+
+static int moved_entry_cmp_no_ws(const struct moved_entry *a,
+				 const struct moved_entry *b,
+				 const void *keydata)
+{
+	return buffered_patch_line_cmp_no_ws(a->line, b->line, keydata);
+}
+
+static unsigned get_line_hash(struct buffered_patch_line *line, unsigned ignore_ws)
+{
+	static struct strbuf sb = STRBUF_INIT;
+
+	if (ignore_ws) {
+		strbuf_reset(&sb);
+		get_ws_cleaned_string(line, &sb);
+		return memhash(sb.buf, sb.len);
+	} else
+		return memhash(line->line, line->len);
+}
+
+static struct moved_entry *prepare_entry(struct diff_options *o,
+					 int line_no)
+{
+	struct moved_entry *ret = xmalloc(sizeof(*ret));
+	unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+	struct buffered_patch_line *l = &o->line_buffer[line_no];
+
+	ret->ent.hash = get_line_hash(l, ignore_ws);
+	ret->line = l;
+	ret->next_line = NULL;
+
+	return ret;
+}
+
 static char *quote_two(const char *one, const char *two)
 {
 	int need_one = quote_c_style(one, NULL, NULL, 1);
@@ -516,8 +608,98 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
+static void mark_color_as_moved(struct diff_options *o, int line_no)
+{
+	struct hashmap *hm = NULL;
+	struct moved_entry *key = prepare_entry(o, line_no);
+	struct moved_entry *match = NULL;
+	struct buffered_patch_line *l = &o->line_buffer[line_no];
+	int alt_flag;
+	int i, lp, rp;
+
+	switch (l->sign) {
+	case '+':
+		hm = o->deleted_lines;
+		break;
+	case '-':
+		hm = o->added_lines;
+		break;
+	default:
+		/* reset to standard, on-alt move color */
+		o->color_moved = 1;
+		break;
+	}
+
+	/* Check for any match to color it as a move. */
+	if (!hm)
+		return;
+	match = hashmap_get(hm, key, o);
+	free(key);
+	if (!match)
+		return;
+
+	/* Check any potential block runs, advance each or nullify */
+	for (i = 0; i < o->pmb_nr; i++) {
+		struct moved_entry *p = o->pmb[i];
+		if (p && p->next_line &&
+		    !buffered_patch_line_cmp(p->next_line->line, l, o)) {
+			o->pmb[i] = p->next_line;
+		} else {
+			o->pmb[i] = NULL;
+		}
+	}
+
+	/* Shrink the set to the remaining runs */
+	for (lp = 0, rp = o->pmb_nr - 1; lp <= rp;) {
+		while (lp < o->pmb_nr && o->pmb[lp])
+			lp ++;
+		/* lp points at the first NULL now */
+
+		while (rp > -1 && !o->pmb[rp])
+			rp--;
+		/* rp points at the last non-NULL */
+
+		if (lp < o->pmb_nr && rp > -1 && lp < rp) {
+			o->pmb[lp] = o->pmb[rp];
+			o->pmb[rp] = NULL;
+			rp--;
+			lp++;
+		}
+	}
+
+	if (rp > -1) {
+		/* Remember the number of running sets */
+		o->pmb_nr = rp + 1;
+	} else {
+		/* Toggle color */
+		o->color_moved = o->color_moved == 2 ? 1 : 2;
+
+		/* Build up a new set */
+		i = 0;
+		for (; match; match = hashmap_get_next(hm, match)) {
+			ALLOC_GROW(o->pmb, i + 1, o->pmb_alloc);
+			o->pmb[i] = match;
+			i++;
+		}
+		o->pmb_nr = i;
+	}
+
+	alt_flag = o->color_moved - 1;
+	switch (l->sign) {
+	case '+':
+		l->set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED + alt_flag);
+		break;
+	case '-':
+		l->set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED + alt_flag);
+		break;
+	default:
+		; /* nothing */
+	}
+}
+
 static void emit_buffered_patch_line(struct diff_options *o,
-				     struct buffered_patch_line *e)
+				     struct buffered_patch_line *e,
+				     int pass)
 {
 	int has_trailing_newline, has_trailing_carriage_return, len = e->len;
 	FILE *file = o->file;
@@ -548,11 +730,11 @@ static void emit_buffered_patch_line(struct diff_options *o,
 
 static void emit_buffered_patch_line_ws(struct diff_options *o,
 					struct buffered_patch_line *e,
-					const char *ws, unsigned ws_rule)
+					const char *ws, unsigned ws_rule,
+					int pass)
 {
 	struct buffered_patch_line s = {e->set, e->reset, "", 0, e->sign};
-
-	emit_buffered_patch_line(o, &s);
+	emit_buffered_patch_line(o, &s, 0);
 	ws_check_emit(e->line, e->len, ws_rule,
 		      o->file, e->set, e->reset, ws);
 }
@@ -564,12 +746,14 @@ static void process_next_buffered_patch_line(struct diff_options *o, int line_no
 	const char *ws = o->current_filepair->ws;
 	unsigned ws_rule = o->current_filepair->ws_rule;
 
+	mark_color_as_moved(o, line_no);
+
 	switch (e->state) {
 		case BPL_EMIT_LINE_ASIS:
-			emit_buffered_patch_line(o, e);
+			emit_buffered_patch_line(o, e, 1);
 			break;
 		case BPL_EMIT_LINE_WS:
-			emit_buffered_patch_line_ws(o, e, ws, ws_rule);
+			emit_buffered_patch_line_ws(o, e, ws, ws_rule, 1);
 			break;
 		case BPL_HANDOVER:
 			o->current_filepair++;
@@ -602,7 +786,7 @@ static void emit_line_0(struct diff_options *o,
 	if (o->use_buffer)
 		append_buffered_patch_line(o, &e);
 	else
-		emit_buffered_patch_line(o, &e);
+		emit_buffered_patch_line(o, &e, 0);
 }
 
 void emit_line(struct diff_options *o, const char *set, const char *reset,
@@ -621,7 +805,7 @@ static void emit_line_ws(struct diff_options *o,
 	if (o->use_buffer)
 		append_buffered_patch_line(o, &e);
 	else
-		emit_buffered_patch_line_ws(o, &e, ws, ws_rule);
+		emit_buffered_patch_line_ws(o, &e, ws, ws_rule, 0);
 }
 
 void emit_line_fmt(struct diff_options *o,
@@ -676,6 +860,36 @@ static void emit_line_checked(const char *reset,
 			     ws, ecbdata->ws_rule);
 }
 
+static void add_line_to_move_detection(struct diff_options *o, int line_idx)
+{
+	int sign = 0;
+	struct hashmap *hm;
+	struct moved_entry *key;
+
+	switch (o->line_buffer[line_idx].sign) {
+	case '+':
+		sign = '+';
+		hm = o->added_lines;
+		break;
+	case '-':
+		sign = '-';
+		hm = o->deleted_lines;
+		break;
+	case ' ':
+	default:
+		o->prev_line = NULL;
+		return;
+	}
+
+	key = prepare_entry(o, line_idx);
+	if (o->prev_line &&
+	    o->prev_line->line->sign == sign)
+		o->prev_line->next_line = key;
+
+	hashmap_add(hm, key);
+	o->prev_line = key;
+}
+
 static void emit_add_line(const char *reset,
 			  struct emit_callback *ecbdata,
 			  const char *line, int len)
@@ -3649,6 +3863,9 @@ void diff_setup_done(struct diff_options *options)
 
 	if (DIFF_OPT_TST(options, FOLLOW_RENAMES) && options->pathspec.nr != 1)
 		die(_("--follow requires exactly one pathspec"));
+
+	if (!options->use_color || external_diff())
+		options->color_moved = 0;
 }
 
 static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
@@ -4073,6 +4290,10 @@ int diff_opt_parse(struct diff_options *options,
 	}
 	else if (!strcmp(arg, "--no-color"))
 		options->use_color = 0;
+	else if (!strcmp(arg, "--color-moved"))
+		options->color_moved = 1;
+	else if (!strcmp(arg, "--no-color-moved"))
+		options->color_moved = 0;
 	else if (!strcmp(arg, "--color-words")) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
@@ -4878,16 +5099,19 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 {
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
-	/*
-	 * For testing purposes we want to make sure the diff machinery
-	 * works completely with the buffer. If there is anything emitted
-	 * outside the emit_buffered_patch_line, then the order is screwed
-	 * up and the tests will fail.
-	 *
-	 * TODO (later in this series):
-	 * We'll unset this flag in a later patch.
-	 */
-	o->use_buffer = 1;
+
+	if (o->color_moved) {
+		unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+		o->use_buffer = 1;
+		o->deleted_lines = xmallocz(sizeof(*o->deleted_lines));
+		o->added_lines = xmallocz(sizeof(*o->added_lines));
+		hashmap_init(o->deleted_lines, ignore_ws ?
+			(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+			(hashmap_cmp_fn)moved_entry_cmp, 0);
+		hashmap_init(o->added_lines, ignore_ws ?
+			(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+			(hashmap_cmp_fn)moved_entry_cmp, 0);
+	}
 
 	if (o->use_buffer) {
 		ALLOC_GROW(o->filepair_buffer,
@@ -4902,6 +5126,10 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
+		o->current_filepair = &o->filepair_buffer[0];
+		for (i = 0; i < o->line_buffer_nr; i++)
+			add_line_to_move_detection(o, i);
+
 		o->current_filepair = &o->filepair_buffer[0];
 		for (i = 0; i < o->line_buffer_nr; i++)
 			process_next_buffered_patch_line(o, i);
@@ -4992,6 +5220,7 @@ void diff_flush(struct diff_options *options)
 		if (!options->file)
 			die_errno("Could not open /dev/null");
 		options->close_file = 1;
+		options->color_moved = 0;
 		for (i = 0; i < q->nr; i++) {
 			struct diff_filepair *p = q->queue[i];
 			if (check_pair_status(p))
diff --git a/diff.h b/diff.h
index c334aac02e..b83d6fefcc 100644
--- a/diff.h
+++ b/diff.h
@@ -7,6 +7,7 @@
 #include "tree-walk.h"
 #include "pathspec.h"
 #include "object.h"
+#include "hashmap.h"
 
 struct rev_info;
 struct diff_options;
@@ -145,6 +146,8 @@ struct buffered_filepair {
 	unsigned ws_rule;
 };
 
+struct moved_entry;
+
 struct diff_options {
 	const char *orderfile;
 	const char *pickaxe;
@@ -217,6 +220,8 @@ struct diff_options {
 
 	int diff_path_counter;
 
+	/* Determines color moved code. Flipped between 1, 2 for alt. color. */
+	int color_moved;
 	int use_buffer;
 
 	struct buffered_patch_line *line_buffer;
@@ -225,6 +230,16 @@ struct diff_options {
 	struct buffered_filepair *filepair_buffer;
 	int filepair_buffer_nr, filepair_buffer_alloc;
 	struct buffered_filepair *current_filepair;
+
+	/* built up in the first pass: */
+	struct hashmap *deleted_lines;
+	struct hashmap *added_lines;
+	/* needed for building up */
+	struct moved_entry *prev_line;
+
+	/* state in the second pass */
+	struct moved_entry **pmb; /* potentially moved blocks */
+	int pmb_nr, pmb_alloc;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
@@ -241,7 +256,11 @@ enum color_diff {
 	DIFF_FILE_NEW = 5,
 	DIFF_COMMIT = 6,
 	DIFF_WHITESPACE = 7,
-	DIFF_FUNCINFO = 8
+	DIFF_FUNCINFO = 8,
+	DIFF_FILE_OLD_MOVED = 9,
+	DIFF_FILE_OLD_MOVED_ALT = 10,
+	DIFF_FILE_NEW_MOVED = 11,
+	DIFF_FILE_NEW_MOVED_ALT = 12
 };
 const char *diff_get_color(int diff_use_color, enum color_diff ix);
 #define diff_get_color_opt(o, ix) \
diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh
index 289806d0c7..232d9ad55e 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -972,4 +972,233 @@ test_expect_success 'option overrides diff.wsErrorHighlight' '
 
 '
 
+test_expect_success 'detect moved code, complete file' '
+	git reset --hard &&
+	cat <<-\EOF >test.c &&
+	#include<stdio.h>
+	main()
+	{
+	printf("Hello World");
+	}
+	EOF
+	git add test.c &&
+	git commit -m "add main function" &&
+	git mv test.c main.c &&
+	git diff HEAD --color-moved --no-renames | test_decode_color >actual &&
+	cat >expected <<-\EOF &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>new file mode 100644<RESET>
+	<BOLD>index 0000000..a986c57<RESET>
+	<BOLD>--- /dev/null<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -0,0 +1,5 @@<RESET>
+	<BGREEN>+<RESET><BGREEN>#include<stdio.h><RESET>
+	<BGREEN>+<RESET><BGREEN>main()<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BGREEN>+<RESET><BGREEN>printf("Hello World");<RESET>
+	<BGREEN>+<RESET><BGREEN>}<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>deleted file mode 100644<RESET>
+	<BOLD>index a986c57..0000000<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ /dev/null<RESET>
+	<CYAN>@@ -1,5 +0,0 @@<RESET>
+	<BRED>-#include<stdio.h><RESET>
+	<BRED>-main()<RESET>
+	<BRED>-{<RESET>
+	<BRED>-printf("Hello World");<RESET>
+	<BRED>-}<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
+test_expect_success 'detect moved code, inside file' '
+	git reset --hard &&
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			if (!u->is_allowed_foo)
+				return;
+			foo(u);
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git add main.c test.c &&
+	git commit -m "add main and test file" &&
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			if (!u->is_allowed_foo)
+				return;
+			foo(u);
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>index 27a619c..7cf9336 100644<RESET>
+	<BOLD>--- a/main.c<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET>
+	 printf("World\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BRED>-int secure_foo(struct user *u)<RESET>
+	<BRED>-{<RESET>
+	<BRED>-if (!u->is_allowed_foo)<RESET>
+	<BRED>-return;<RESET>
+	<BRED>-foo(u);<RESET>
+	<BRED>-}<RESET>
+	<BRED>-<RESET>
+	 int main()<RESET>
+	 {<RESET>
+	 foo();<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>index 1dc1d85..e34eb69 100644<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ b/test.c<RESET>
+	<CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET>
+	 printf("Hello World, but different\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET>
+	<BGREEN>+<RESET><BGREEN>return;<RESET>
+	<BGREEN>+<RESET><BGREEN>foo(u);<RESET>
+	<BGREEN>+<RESET><BGREEN>}<RESET>
+	<BGREEN>+<RESET>
+	 int another_function()<RESET>
+	 {<RESET>
+	 bar();<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
+test_expect_success 'detect permutations inside moved code, ' '
+	# reusing the move example from last test:
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			foo(u);
+			if (!u->is_allowed_foo)
+				return;
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>index 27a619c..7cf9336 100644<RESET>
+	<BOLD>--- a/main.c<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET>
+	 printf("World\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BRED>-int secure_foo(struct user *u)<RESET>
+	<BRED>-{<RESET>
+	<BOLD;RED>-if (!u->is_allowed_foo)<RESET>
+	<BOLD;RED>-return;<RESET>
+	<BRED>-foo(u);<RESET>
+	<BOLD;RED>-}<RESET>
+	<BOLD;RED>-<RESET>
+	 int main()<RESET>
+	 {<RESET>
+	 foo();<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>index 1dc1d85..2bedec9 100644<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ b/test.c<RESET>
+	<CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET>
+	 printf("Hello World, but different\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BOLD;GREEN>+<RESET><BOLD;GREEN>foo(u);<RESET>
+	<BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET>
+	<BGREEN>+<RESET><BGREEN>return;<RESET>
+	<BOLD;GREEN>+<RESET><BOLD;GREEN>}<RESET>
+	<BOLD;GREEN>+<RESET>
+	 int another_function()<RESET>
+	 {<RESET>
+	 bar();<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
 test_done

diff --git a/diff.c b/diff.c
index 45ec311828..ffdb728810 100644
--- a/diff.c
+++ b/diff.c
@@ -2233,8 +2233,8 @@ static unsigned char *deflate_it(char *data,
 	return deflated;
 }
 
-static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two,
-				  const char *prefix)
+static void emit_binary_diff_body(struct diff_options *o,
+				  mmfile_t *one, mmfile_t *two)
 {
 	void *cp;
 	void *delta;
@@ -2263,13 +2263,12 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two,
 	}
 
 	if (delta && delta_size < deflate_size) {
-		fprintf(file, "%sdelta %lu\n", prefix, orig_size);
+		emit_line_fmt(o, NULL, NULL, "delta %lu\n", orig_size);
 		free(deflated);
 		data = delta;
 		data_size = delta_size;
-	}
-	else {
-		fprintf(file, "%sliteral %lu\n", prefix, two->size);
+	} else {
+		emit_line_fmt(o, NULL, NULL, "literal %lu\n", two->size);
 		free(delta);
 		data = deflated;
 		data_size = deflate_size;
@@ -2278,8 +2277,9 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two,
 	/* emit data encoded in base85 */
 	cp = data;
 	while (data_size) {
+		int len;
 		int bytes = (52 < data_size) ? 52 : data_size;
-		char line[70];
+		char line[71];
 		data_size -= bytes;
 		if (bytes <= 26)
 			line[0] = bytes + 'A' - 1;
@@ -2287,20 +2287,25 @@ static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two,
 			line[0] = bytes - 26 + 'a' - 1;
 		encode_85(line + 1, cp, bytes);
 		cp = (char *) cp + bytes;
-		fprintf(file, "%s", prefix);
-		fputs(line, file);
-		fputc('\n', file);
+
+		len = strlen(line);
+		line[len++] = '\n';
+		line[len] = '\0';
+
+		emit_line(o, NULL, NULL, line, len);
 	}
-	fprintf(file, "%s\n", prefix);
+	emit_line(o, NULL, NULL, "\n", 1);
 	free(data);
 }
 
-static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two,
-			     const char *prefix)
+static void emit_binary_diff(struct diff_options *o,
+			     mmfile_t *one, mmfile_t *two)
 {
-	fprintf(file, "%sGIT binary patch\n", prefix);
-	emit_binary_diff_body(file, one, two, prefix);
-	emit_binary_diff_body(file, two, one, prefix);
+	const char *s = "GIT binary patch\n";
+	const int len = strlen(s);
+	emit_line(o, NULL, NULL, s, len);
+	emit_binary_diff_body(o, one, two);
+	emit_binary_diff_body(o, two, one);
 }
 
 int diff_filespec_is_binary(struct diff_filespec *one)
@@ -2489,7 +2494,7 @@ static void builtin_diff(const char *name_a,
 				  header.buf, header.len);
 		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
-			emit_binary_diff(o->file, &mf1, &mf2, line_prefix);
+			emit_binary_diff(o, &mf1, &mf2);
 		else
 			emit_line_fmt(o, NULL, NULL,
 				      "Binary files %s and %s differ\n",

diff --git a/diff.c b/diff.c
index 386b28cf47..899dc69dff 100644
--- a/diff.c
+++ b/diff.c
@@ -4504,67 +4504,71 @@ static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt)
 	}
 }
 
-static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs)
+static void show_file_mode_name(struct diff_options *opt, const char *newdelete, struct diff_filespec *fs)
 {
+	struct strbuf sb = STRBUF_INIT;
 	if (fs->mode)
-		fprintf(file, " %s mode %06o ", newdelete, fs->mode);
+		strbuf_addf(&sb, " %s mode %06o ", newdelete, fs->mode);
 	else
-		fprintf(file, " %s ", newdelete);
-	write_name_quoted(fs->path, file, '\n');
+		strbuf_addf(&sb, " %s ", newdelete);
+
+	quote_c_style(fs->path, &sb, NULL, 0);
+	strbuf_addch(&sb, '\n');
+	emit_line(opt, NULL, NULL, sb.buf, sb.len);
+	strbuf_release(&sb);
 }
 
 
-static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name,
-		const char *line_prefix)
+static void show_mode_change(struct diff_options *opt, struct diff_filepair *p,
+		int show_name)
 {
 	if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
-		fprintf(file, "%s mode change %06o => %06o%c", line_prefix, p->one->mode,
-			p->two->mode, show_name ? ' ' : '\n');
+		struct strbuf sb = STRBUF_INIT;
 		if (show_name) {
-			write_name_quoted(p->two->path, file, '\n');
+			strbuf_addch(&sb, ' ');
+			quote_c_style(p->two->path, &sb, NULL, 0);
 		}
+		emit_line_fmt(opt, NULL, NULL,
+			      " mode change %06o => %06o%s\n",
+			      p->one->mode, p->two->mode,
+			      show_name ? sb.buf : "");
+		strbuf_release(&sb);
 	}
 }
 
-static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p,
-			const char *line_prefix)
+static void show_rename_copy(struct diff_options *opt, const char *renamecopy,
+		struct diff_filepair *p)
 {
 	char *names = pprint_rename(p->one->path, p->two->path);
-
-	fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
+	emit_line_fmt(opt, NULL, NULL, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
 	free(names);
-	show_mode_change(file, p, 0, line_prefix);
+	show_mode_change(opt, p, 0);
 }
 
 static void diff_summary(struct diff_options *opt, struct diff_filepair *p)
 {
-	FILE *file = opt->file;
-	const char *line_prefix = diff_line_prefix(opt);
-
 	switch(p->status) {
 	case DIFF_STATUS_DELETED:
-		fputs(line_prefix, file);
-		show_file_mode_name(file, "delete", p->one);
+		show_file_mode_name(opt, "delete", p->one);
 		break;
 	case DIFF_STATUS_ADDED:
-		fputs(line_prefix, file);
-		show_file_mode_name(file, "create", p->two);
+		show_file_mode_name(opt, "create", p->two);
 		break;
 	case DIFF_STATUS_COPIED:
-		fputs(line_prefix, file);
-		show_rename_copy(file, "copy", p, line_prefix);
+		show_rename_copy(opt, "copy", p);
 		break;
 	case DIFF_STATUS_RENAMED:
-		fputs(line_prefix, file);
-		show_rename_copy(file, "rename", p, line_prefix);
+		show_rename_copy(opt, "rename", p);
 		break;
 	default:
 		if (p->score) {
-			fprintf(file, "%s rewrite ", line_prefix);
-			write_name_quoted(p->two->path, file, ' ');
-			fprintf(file, "(%d%%)\n", similarity_index(p));
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addstr(&sb, " rewrite ");
+			quote_c_style(p->two->path, &sb, NULL, 0);
+			strbuf_addf(&sb, " (%d%%)\n", similarity_index(p));
+			emit_line(opt, NULL, NULL, sb.buf, sb.len);
 		}
-		show_mode_change(file, p, !p->score, line_prefix);
+		show_mode_change(opt, p, !p->score);
 		break;
 	}
 }

diff.c, diff.h

diff --git a/diff.c b/diff.c
index ffdb728810..91dc045a45 100644
--- a/diff.c
+++ b/diff.c
@@ -1529,20 +1529,19 @@ static int scale_linear(int it, int width, int max_change)
 	return 1 + (it * (width - 1) / max_change);
 }
 
-static void show_name(FILE *file,
+static void show_name(struct strbuf *out,
 		      const char *prefix, const char *name, int len)
 {
-	fprintf(file, " %s%-*s |", prefix, len, name);
+	strbuf_addf(out, " %s%-*s |", prefix, len, name);
 }
 
-static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
+static void show_graph(struct strbuf *out, char ch, int cnt, const char *set, const char *reset)
 {
 	if (cnt <= 0)
 		return;
-	fprintf(file, "%s", set);
-	while (cnt--)
-		putc(ch, file);
-	fprintf(file, "%s", reset);
+	strbuf_addstr(out, set);
+	strbuf_addchars(out, ch, cnt);
+	strbuf_addstr(out, reset);
 }
 
 static void fill_print_name(struct diffstat_file *file)
@@ -1566,14 +1565,16 @@ 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)
+void print_stat_summary_0(struct diff_options *options, 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_addstr(&sb, " 0 files changed");
+		emit_line(options, NULL, NULL, sb.buf, sb.len);
+		return;
 	}
 
 	strbuf_addf(&sb,
@@ -1600,9 +1601,17 @@ int print_stat_summary(FILE *fp, int files, int insertions, int deletions)
 			    deletions);
 	}
 	strbuf_addch(&sb, '\n');
-	ret = fputs(sb.buf, fp);
+	emit_line(options, NULL, NULL, sb.buf, sb.len);
 	strbuf_release(&sb);
-	return ret;
+}
+
+void print_stat_summary(FILE *fp, int files,
+			int insertions, int deletions)
+{
+	struct diff_options o;
+	memset(&o, 0, sizeof(o));
+	o.file = fp;
+	print_stat_summary_0(&o, files, insertions, deletions);
 }
 
 static void show_stats(struct diffstat_t *data, struct diff_options *options)
@@ -1612,13 +1621,13 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 	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;
+	const char *line_prefix = diff_line_prefix(options);
+	struct strbuf out = STRBUF_INIT;
 
 	if (data->nr == 0)
 		return;
 
-	line_prefix = diff_line_prefix(options);
 	count = options->stat_count ? options->stat_count : data->nr;
 
 	reset = diff_get_color_opt(options, DIFF_RESET);
@@ -1772,26 +1781,29 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		}
 
 		if (file->is_binary) {
-			fprintf(options->file, "%s", line_prefix);
-			show_name(options->file, prefix, name, len);
-			fprintf(options->file, " %*s", number_width, "Bin");
+			show_name(&out, prefix, name, len);
+			strbuf_addf(&out, " %*s", number_width, "Bin");
 			if (!added && !deleted) {
-				putc('\n', options->file);
+				strbuf_addch(&out, '\n');
+				emit_line(options, NULL, NULL, out.buf, out.len);
+				strbuf_reset(&out);
 				continue;
 			}
-			fprintf(options->file, " %s%"PRIuMAX"%s",
+			strbuf_addf(&out, " %s%"PRIuMAX"%s",
 				del_c, deleted, reset);
-			fprintf(options->file, " -> ");
-			fprintf(options->file, "%s%"PRIuMAX"%s",
+			strbuf_addstr(&out, " -> ");
+			strbuf_addf(&out, "%s%"PRIuMAX"%s",
 				add_c, added, reset);
-			fprintf(options->file, " bytes");
-			fprintf(options->file, "\n");
+			strbuf_addstr(&out, " bytes\n");
+			emit_line(options, NULL, NULL, out.buf, out.len);
+			strbuf_reset(&out);
 			continue;
 		}
 		else if (file->is_unmerged) {
-			fprintf(options->file, "%s", line_prefix);
-			show_name(options->file, prefix, name, len);
-			fprintf(options->file, " Unmerged\n");
+			show_name(&out, prefix, name, len);
+			strbuf_addstr(&out, " Unmerged\n");
+			emit_line(options, NULL, NULL, out.buf, out.len);
+			strbuf_reset(&out);
 			continue;
 		}
 
@@ -1814,14 +1826,15 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 				add = total - del;
 			}
 		}
-		fprintf(options->file, "%s", line_prefix);
-		show_name(options->file, prefix, name, len);
-		fprintf(options->file, " %*"PRIuMAX"%s",
+		show_name(&out, prefix, name, len);
+		strbuf_addf(&out, " %*"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");
+		show_graph(&out, '+', add, add_c, reset);
+		show_graph(&out, '-', del, del_c, reset);
+		strbuf_addch(&out, '\n');
+		emit_line(options, NULL, NULL, out.buf, out.len);
+		strbuf_reset(&out);
 	}
 
 	for (i = 0; i < data->nr; i++) {
@@ -1842,11 +1855,12 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (i < count)
 			continue;
 		if (!extra_shown)
-			fprintf(options->file, "%s ...\n", line_prefix);
+			emit_line(options, NULL, NULL,
+				  " ...\n", strlen(" ...\n"));
 		extra_shown = 1;
 	}
-	fprintf(options->file, "%s", line_prefix);
-	print_stat_summary(options->file, total_files, adds, dels);
+
+	print_stat_summary_0(options, total_files, adds, dels);
 }
 
 static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
@@ -1858,7 +1872,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 
 	for (i = 0; i < data->nr; i++) {
 		int added = data->files[i]->added;
-		int deleted= data->files[i]->deleted;
+		int deleted = data->files[i]->deleted;
 
 		if (data->files[i]->is_unmerged ||
 		    (!data->files[i]->is_interesting && (added + deleted == 0))) {
@@ -1868,8 +1882,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 			dels += deleted;
 		}
 	}
-	fprintf(options->file, "%s", diff_line_prefix(options));
-	print_stat_summary(options->file, total_files, adds, dels);
+	print_stat_summary_0(options, total_files, adds, dels);
 }
 
 static void show_numstat(struct diffstat_t *data, struct diff_options *options)
diff --git a/diff.h b/diff.h
index addebd5a0f..5e89481769 100644
--- a/diff.h
+++ b/diff.h
@@ -394,8 +394,8 @@ extern int parse_rename_score(const char **cp_p);
 
 extern long parse_algorithm_value(const char *value);
 
-extern int print_stat_summary(FILE *fp, int files,
-			      int insertions, int deletions);
+extern void print_stat_summary(FILE *fp, int files,
+			       int insertions, int deletions);
 extern void setup_diff_pager(struct diff_options *);
 
 #endif /* DIFF_H */

diff --git a/diff.c b/diff.c
index 8e00010bf4..e4b46fee4f 100644
--- a/diff.c
+++ b/diff.c
@@ -708,17 +708,17 @@ static void remove_tempfile(void)
 	}
 }
 
-static void print_line_count(FILE *file, int count)
+static void add_line_count(struct strbuf *out, int count)
 {
 	switch (count) {
 	case 0:
-		fprintf(file, "0,0");
+		strbuf_addstr(out, "0,0");
 		break;
 	case 1:
-		fprintf(file, "1");
+		strbuf_addstr(out, "1");
 		break;
 	default:
-		fprintf(file, "1,%d", count);
+		strbuf_addf(out, "1,%d", count);
 		break;
 	}
 }
@@ -772,7 +772,7 @@ static void emit_rewrite_diff(const char *name_a,
 	char *data_one, *data_two;
 	size_t size_one, size_two;
 	struct emit_callback ecbdata;
-	const char *line_prefix = diff_line_prefix(o);
+	struct strbuf out = STRBUF_INIT;
 
 	if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) {
 		a_prefix = o->b_prefix;
@@ -810,20 +810,23 @@ static void emit_rewrite_diff(const char *name_a,
 	ecbdata.lno_in_preimage = 1;
 	ecbdata.lno_in_postimage = 1;
 
+	emit_line_fmt(o, metainfo, reset, "--- %s%s\n", a_name.buf, name_a_tab);
+	emit_line_fmt(o, metainfo, reset, "+++ %s%s\n", b_name.buf, name_b_tab);
+
 	lc_a = count_lines(data_one, size_one);
 	lc_b = count_lines(data_two, size_two);
-	fprintf(o->file,
-		"%s%s--- %s%s%s\n%s%s+++ %s%s%s\n%s%s@@ -",
-		line_prefix, metainfo, a_name.buf, name_a_tab, reset,
-		line_prefix, metainfo, b_name.buf, name_b_tab, reset,
-		line_prefix, fraginfo);
+
+	strbuf_addstr(&out, "@@ -");
 	if (!o->irreversible_delete)
-		print_line_count(o->file, lc_a);
+		add_line_count(&out, lc_a);
 	else
-		fprintf(o->file, "?,?");
-	fprintf(o->file, " +");
-	print_line_count(o->file, lc_b);
-	fprintf(o->file, " @@%s\n", reset);
+		strbuf_addstr(&out, "?,?");
+	strbuf_addstr(&out, " +");
+	add_line_count(&out, lc_b);
+	strbuf_addstr(&out, " @@\n");
+	emit_line(o, fraginfo, reset, out.buf, out.len);
+	strbuf_release(&out);
+
 	if (lc_a && !o->irreversible_delete)
 		emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
 	if (lc_b)

diff --git a/diff.c b/diff.c
index 07041a35ad..386b28cf47 100644
--- a/diff.c
+++ b/diff.c
@@ -4873,7 +4873,9 @@ void diff_flush(struct diff_options *options)
 				  term, 1);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
-				fputs(options->stat_sep, options->file);
+				emit_line(options, NULL, NULL,
+					  options->stat_sep,
+					  strlen(options->stat_sep));
 			}
 		}
 

diff --git a/diff.c b/diff.c
index 4269b8dccf..381b572d76 100644
--- a/diff.c
+++ b/diff.c
@@ -4728,6 +4728,17 @@ void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc)
 		warning(_(rename_limit_advice), varname, needed);
 }
 
+static void diff_flush_patch_all_file_pairs(struct diff_options *o)
+{
+	int i;
+	struct diff_queue_struct *q = &diff_queued_diff;
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		if (check_pair_status(p))
+			diff_flush_patch(p, o);
+	}
+}
+
 void diff_flush(struct diff_options *options)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -4825,11 +4836,7 @@ void diff_flush(struct diff_options *options)
 			}
 		}
 
-		for (i = 0; i < q->nr; i++) {
-			struct diff_filepair *p = q->queue[i];
-			if (check_pair_status(p))
-				diff_flush_patch(p, options);
-		}
+		diff_flush_patch_all_file_pairs(options);
 	}
 
 	if (output_format & DIFF_FORMAT_CALLBACK)

diff --git a/diff.c b/diff.c
index 381b572d76..48f0fb98dc 100644
--- a/diff.c
+++ b/diff.c
@@ -532,11 +532,13 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 		len--;
 
 	if (len || sign) {
-		fputs(set, file);
+		if (set)
+			fputs(set, file);
 		if (sign)
 			fputc(sign, file);
 		fwrite(line, len, 1, file);
-		fputs(reset, file);
+		if (reset)
+			fputs(reset, file);
 	}
 	if (has_trailing_carriage_return)
 		fputc('\r', file);

Documentation/config.txt, diff.c, diff.h, submodule.c

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 90403c06e3..902d017c3b 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1065,8 +1065,10 @@ color.diff.<slot>::
 	`meta` (metainformation), `frag`
 	(hunk header), 'func' (function in hunk header), `old` (removed lines),
 	`new` (added lines), `commit` (commit headers), `whitespace`
-	(highlighting whitespace errors), `movedFrom` (removed lines that
-	reappear), `movedTo` (added lines that were removed elsewhere).
+	(highlighting whitespace errors), `oldMoved` (removed lines that
+	reappear), `newMoved` (added lines that were removed elsewhere),
+	`oldMovedAlternative` and `newMovedAlternative` (as a fallback to
+	cover adjacent blocks of moved code)
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/diff.c b/diff.c
index 5dfd582084..15cf322b50 100644
--- a/diff.c
+++ b/diff.c
@@ -392,11 +392,17 @@ static int buffered_patch_line_cmp_no_ws(const struct buffered_patch_line *a,
 					 const struct buffered_patch_line *b,
 					 const void *keydata)
 {
+	int ret;
 	struct strbuf sba = STRBUF_INIT;
 	struct strbuf sbb = STRBUF_INIT;
+
 	get_ws_cleaned_string(a, &sba);
 	get_ws_cleaned_string(b, &sbb);
-	return sba.len != sbb.len || strncmp(sba.buf, sbb.buf, sba.len);
+	ret = sba.len != sbb.len || strncmp(sba.buf, sbb.buf, sba.len);
+
+	strbuf_release(&sba);
+	strbuf_release(&sbb);
+	return ret;
 }
 
 static int buffered_patch_line_cmp(const struct buffered_patch_line *a,
@@ -428,8 +434,9 @@ static unsigned get_line_hash(struct buffered_patch_line *line, unsigned ignore_
 		strbuf_reset(&sb);
 		get_ws_cleaned_string(line, &sb);
 		return memhash(sb.buf, sb.len);
-	} else
+	} else {
 		return memhash(line->line, line->len);
+	}
 }
 
 static struct moved_entry *prepare_entry(struct diff_options *o,
@@ -608,159 +615,185 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-static void mark_color_as_moved(struct diff_options *o, int line_no)
+static void add_lines_to_move_detection(struct diff_options *o)
 {
-	struct hashmap *hm = NULL;
-	struct moved_entry *key = prepare_entry(o, line_no);
-	struct moved_entry *match = NULL;
-	struct buffered_patch_line *l = &o->line_buffer[line_no];
-	int alt_flag;
-	int i, lp, rp;
+	struct moved_entry *prev_line;
 
-	switch (l->sign) {
-	case '+':
-		hm = o->deleted_lines;
-		break;
-	case '-':
-		hm = o->added_lines;
-		break;
-	default:
-		/* reset to standard, on-alt move color */
-		o->color_moved = 1;
-		break;
+	int n;
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		int sign = 0;
+		struct hashmap *hm;
+		struct moved_entry *key;
+
+		switch (o->line_buffer[n].sign) {
+		case '+':
+			sign = '+';
+			hm = o->added_lines;
+			break;
+		case '-':
+			sign = '-';
+			hm = o->deleted_lines;
+			break;
+		case ' ':
+		default:
+			prev_line = NULL;
+			continue;
+		}
+
+		key = prepare_entry(o, n);
+		if (prev_line &&
+		    prev_line->line->sign == sign)
+			prev_line->next_line = key;
+
+		hashmap_add(hm, key);
+		prev_line = key;
 	}
+}
 
-	/* Check for any match to color it as a move. */
-	if (!hm)
-		return;
-	match = hashmap_get(hm, key, o);
-	free(key);
-	if (!match)
-		return;
+static void mark_color_as_moved(struct diff_options *o)
+{
+	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	int pmb_nr = 0, pmb_alloc = 0;
+	int alt_flag = 0;
+	int n;
 
-	/* Check any potential block runs, advance each or nullify */
-	for (i = 0; i < o->pmb_nr; i++) {
-		struct moved_entry *p = o->pmb[i];
-		if (p && p->next_line &&
-		    !buffered_patch_line_cmp(p->next_line->line, l, o)) {
-			o->pmb[i] = p->next_line;
-		} else {
-			o->pmb[i] = NULL;
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		struct hashmap *hm = NULL;
+		struct moved_entry *key;
+		struct moved_entry *match = NULL;
+		struct buffered_patch_line *l = &o->line_buffer[n];
+		int i, lp, rp;
+
+		switch (l->sign) {
+		case '+':
+			hm = o->deleted_lines;
+			break;
+		case '-':
+			hm = o->added_lines;
+			break;
+		default:
+			alt_flag = 0; /* reset to standard, no-alt move color */
+			pmb_nr = 0; /* no running sets */
+			continue;
 		}
-	}
 
-	/* Shrink the set to the remaining runs */
-	for (lp = 0, rp = o->pmb_nr - 1; lp <= rp;) {
-		while (lp < o->pmb_nr && o->pmb[lp])
-			lp ++;
-		/* lp points at the first NULL now */
+		/* Check for any match to color it as a move. */
+		key = prepare_entry(o, n);
+		match = hashmap_get(hm, key, o);
+		free(key);
+		if (!match)
+			continue;
 
-		while (rp > -1 && !o->pmb[rp])
-			rp--;
-		/* rp points at the last non-NULL */
+		/* Check any potential block runs, advance each or nullify */
+		for (i = 0; i < pmb_nr; i++) {
+			struct moved_entry *p = pmb[i];
+			struct moved_entry *pnext = (p && p->next_line) ?
+					p->next_line : NULL;
+			if (pnext &&
+			    !buffered_patch_line_cmp(pnext->line, l, o)) {
+				pmb[i] = p->next_line;
+			} else {
+				pmb[i] = NULL;
+			}
+		}
 
-		if (lp < o->pmb_nr && rp > -1 && lp < rp) {
-			o->pmb[lp] = o->pmb[rp];
-			o->pmb[rp] = NULL;
-			rp--;
-			lp++;
+		/* Shrink the set to the remaining runs */
+		for (lp = 0, rp = pmb_nr - 1; lp <= rp;) {
+			while (lp < pmb_nr && pmb[lp])
+				lp ++;
+			/* lp points at the first NULL now */
+
+			while (rp > -1 && !pmb[rp])
+				rp--;
+			/* rp points at the last non-NULL */
+
+			if (lp < pmb_nr && rp > -1 && lp < rp) {
+				pmb[lp] = pmb[rp];
+				pmb[rp] = NULL;
+				rp--;
+				lp++;
+			}
 		}
-	}
 
-	if (rp > -1) {
-		/* Remember the number of running sets */
-		o->pmb_nr = rp + 1;
-	} else {
-		/* Toggle color */
-		o->color_moved = o->color_moved == 2 ? 1 : 2;
-
-		/* Build up a new set */
-		i = 0;
-		for (; match; match = hashmap_get_next(hm, match)) {
-			ALLOC_GROW(o->pmb, i + 1, o->pmb_alloc);
-			o->pmb[i] = match;
-			i++;
+		if (rp > -1) {
+			/* Remember the number of running sets */
+			pmb_nr = rp + 1;
+		} else {
+			/* Toggle color */
+			alt_flag = (alt_flag + 1) % 2;
+
+			/* Build up a new set */
+			pmb_nr = 0;
+			for (; match; match = hashmap_get_next(hm, match)) {
+				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
+				pmb[pmb_nr++] = match;
+			}
 		}
-		o->pmb_nr = i;
-	}
 
-	alt_flag = o->color_moved - 1;
-	switch (l->sign) {
-	case '+':
-		l->set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED + alt_flag);
-		break;
-	case '-':
-		l->set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED + alt_flag);
-		break;
-	default:
-		/* reset to standard, on-alt move color */
-		o->color_moved = 1;
+		switch (l->sign) {
+		case '+':
+			l->set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED + alt_flag);
+			break;
+		case '-':
+			l->set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED + alt_flag);
+			break;
+		default:
+			die("BUG: we should have continued earlier?");
+		}
 	}
+	free(pmb);
 }
 
 static void emit_buffered_patch_line(struct diff_options *o,
-				     struct buffered_patch_line *e,
-				     int pass)
+				     struct buffered_patch_line *e)
 {
-	int has_trailing_newline, has_trailing_carriage_return, len = e->len;
+	const char *ws;
+	int has_trailing_newline, has_trailing_carriage_return;
+	int len = e->len;
 	FILE *file = o->file;
 
-	fputs(diff_line_prefix(o), file);
-
-	has_trailing_newline = (len > 0 && e->line[len-1] == '\n');
-	if (has_trailing_newline)
-		len--;
-	has_trailing_carriage_return = (len > 0 && e->line[len-1] == '\r');
-	if (has_trailing_carriage_return)
-		len--;
+	if (e->add_line_prefix)
+		fputs(diff_line_prefix(o), file);
 
-	if (len || e->sign) {
+	switch (e->state) {
+	case BPL_EMIT_LINE_WS:
+		ws = diff_get_color(o->use_color, DIFF_WHITESPACE);
 		if (e->set)
 			fputs(e->set, file);
 		if (e->sign)
 			fputc(e->sign, file);
-		fwrite(e->line, len, 1, file);
 		if (e->reset)
 			fputs(e->reset, file);
-	}
-	if (has_trailing_carriage_return)
-		fputc('\r', file);
-	if (has_trailing_newline)
-		fputc('\n', file);
-}
-
-static void emit_buffered_patch_line_ws(struct diff_options *o,
-					struct buffered_patch_line *e,
-					const char *ws, unsigned ws_rule,
-					int pass)
-{
-	struct buffered_patch_line s = {e->set, e->reset, "", 0, e->sign};
-	emit_buffered_patch_line(o, &s, 0);
-	ws_check_emit(e->line, e->len, ws_rule,
-		      o->file, e->set, e->reset, ws);
-}
-
-static void process_next_buffered_patch_line(struct diff_options *o, int line_no)
-{
-	struct buffered_patch_line *e = &o->line_buffer[line_no];
-
-	const char *ws = o->current_filepair->ws;
-	unsigned ws_rule = o->current_filepair->ws_rule;
-
-	mark_color_as_moved(o, line_no);
+		ws_check_emit(e->line, e->len, o->ws_rule,
+			      file, e->set, e->reset, ws);
+		return;
+	case BPL_EMIT_LINE_ASIS:
+		has_trailing_newline = (len > 0 && e->line[len-1] == '\n');
+		if (has_trailing_newline)
+			len--;
+		has_trailing_carriage_return = (len > 0 && e->line[len-1] == '\r');
+		if (has_trailing_carriage_return)
+			len--;
 
-	switch (e->state) {
-		case BPL_EMIT_LINE_ASIS:
-			emit_buffered_patch_line(o, e, 1);
-			break;
-		case BPL_EMIT_LINE_WS:
-			emit_buffered_patch_line_ws(o, e, ws, ws_rule, 1);
-			break;
-		case BPL_HANDOVER:
-			o->current_filepair++;
-			break;
-		default:
-			die("BUG: malformatted buffered patch line: '%d'", e->state);
+		if (len || e->sign) {
+			if (e->set)
+				fputs(e->set, file);
+			if (e->sign)
+				fputc(e->sign, file);
+			fwrite(e->line, len, 1, file);
+			if (e->reset)
+				fputs(e->reset, file);
+		}
+		if (has_trailing_carriage_return)
+			fputc('\r', file);
+		if (has_trailing_newline)
+			fputc('\n', file);
+		return;
+	case BPL_HANDOVER:
+		o->ws_rule = whitespace_rule(e->line); /*read from file, stored in line?*/
+		return;
+	default:
+		die("BUG: malformatted buffered patch line: '%d'", e->state);
 	}
 }
 
@@ -771,46 +804,30 @@ static void append_buffered_patch_line(struct diff_options *o,
 	ALLOC_GROW(o->line_buffer,
 		   o->line_buffer_nr + 1,
 		   o->line_buffer_alloc);
-	f = &o->line_buffer[o->line_buffer_nr];
-	o->line_buffer_nr++;
+	f = &o->line_buffer[o->line_buffer_nr++];
 
 	memcpy(f, e, sizeof(struct buffered_patch_line));
 	f->line = e->line ? xmemdupz(e->line, e->len) : NULL;
 }
 
-static void emit_line_0(struct diff_options *o,
-			const char *set, const char *reset,
-			int sign, const char *line, int len)
+void emit_line(struct diff_options *o,
+	       const char *set, const char *reset,
+	       int add_line_prefix, int markup_ws,
+	       int sign, const char *line, int len)
 {
-	struct buffered_patch_line e = {set, reset, line, len, sign, BPL_EMIT_LINE_ASIS};
+	struct buffered_patch_line e = {set, reset, line,
+		len, sign, add_line_prefix,
+		markup_ws ? BPL_EMIT_LINE_WS : BPL_EMIT_LINE_ASIS};
 
 	if (o->use_buffer)
 		append_buffered_patch_line(o, &e);
 	else
-		emit_buffered_patch_line(o, &e, 0);
-}
-
-void emit_line(struct diff_options *o, const char *set, const char *reset,
-	       const char *line, int len)
-{
-	emit_line_0(o, set, reset, 0, line, len);
-}
-
-static void emit_line_ws(struct diff_options *o,
-			 const char *set, const char *reset, int sign,
-			 const char *line, int len,
-			 const char *ws, unsigned ws_rule)
-{
-	struct buffered_patch_line e = {set, reset, line, len, sign, BPL_EMIT_LINE_WS};
-
-	if (o->use_buffer)
-		append_buffered_patch_line(o, &e);
-	else
-		emit_buffered_patch_line_ws(o, &e, ws, ws_rule, 0);
+		emit_buffered_patch_line(o, &e);
 }
 
 void emit_line_fmt(struct diff_options *o,
 		   const char *set, const char *reset,
+		   int add_line_prefix,
 		   const char *fmt, ...)
 {
 	struct strbuf sb = STRBUF_INIT;
@@ -819,7 +836,7 @@ void emit_line_fmt(struct diff_options *o,
 	strbuf_vaddf(&sb, fmt, ap);
 	va_end(ap);
 
-	emit_line(o, set, reset, sb.buf, sb.len);
+	emit_line(o, set, reset, add_line_prefix, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
@@ -851,44 +868,15 @@ static void emit_line_checked(const char *reset,
 	}
 
 	if (!ws)
-		emit_line_0(ecbdata->opt, set, reset, sign, line, len);
+		emit_line(ecbdata->opt, set, reset, 1, 0, sign, line, len);
 	else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len))
 		/* Blank line at EOF - paint '+' as well */
-		emit_line_0(ecbdata->opt, ws, reset, sign, line, len);
-	else
+		emit_line(ecbdata->opt, ws, reset, 1, 1, sign, line, len);
+	else {
 		/* Emit just the prefix, then the rest. */
-		emit_line_ws(ecbdata->opt, set, reset, sign, line, len,
-			     ws, ecbdata->ws_rule);
-}
-
-static void add_line_to_move_detection(struct diff_options *o, int line_idx)
-{
-	int sign = 0;
-	struct hashmap *hm;
-	struct moved_entry *key;
-
-	switch (o->line_buffer[line_idx].sign) {
-	case '+':
-		sign = '+';
-		hm = o->added_lines;
-		break;
-	case '-':
-		sign = '-';
-		hm = o->deleted_lines;
-		break;
-	case ' ':
-	default:
-		o->prev_line = NULL;
-		return;
+		emit_line(ecbdata->opt, set, reset, 1, 1, sign, line, len);
 	}
 
-	key = prepare_entry(o, line_idx);
-	if (o->prev_line &&
-	    o->prev_line->line->sign == sign)
-		o->prev_line->next_line = key;
-
-	hashmap_add(hm, key);
-	o->prev_line = key;
 }
 
 static void emit_add_line(const char *reset,
@@ -935,7 +923,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	if (len < 10 ||
 	    memcmp(line, atat, 2) ||
 	    !(ep = memmem(line + 2, len - 2, atat, 2))) {
-		emit_line(ecbdata->opt, context, reset, line, len);
+		emit_line(ecbdata->opt, context, reset, 1, 0, 0, line, len);
 		return;
 	}
 	ep += 2; /* skip over @@ */
@@ -971,7 +959,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	strbuf_add(&msgbuf, line + len, org_len - len);
 	strbuf_complete_line(&msgbuf);
 
-	emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len);
+	emit_line(ecbdata->opt, "", "", 1, 0, 0, msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
 
@@ -1011,15 +999,25 @@ static void add_line_count(struct strbuf *out, int count)
 static void emit_rewrite_lines(struct emit_callback *ecb,
 			       int prefix, const char *data, int size)
 {
-	const char *endp = NULL;
-	static const char *nneof = " No newline at end of file\n";
 	const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET);
+	struct strbuf sb = STRBUF_INIT;
 
 	while (0 < size) {
 		int len;
 
-		endp = memchr(data, '\n', size);
-		len = endp ? (endp - data + 1) : size;
+		const char *endp = memchr(data, '\n', size);
+		if (endp)
+			len = endp - data + 1;
+		else {
+			while (0 < size) {
+				strbuf_addch(&sb, *data);
+				size -= len;
+				data += len;
+			}
+			strbuf_addch(&sb, '\n');
+			data = sb.buf;
+			len = sb.len;
+		}
 		if (prefix != '+') {
 			ecb->lno_in_preimage++;
 			emit_del_line(reset, ecb, data, len);
@@ -1030,12 +1028,13 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		size -= len;
 		data += len;
 	}
-	if (!endp) {
+	if (sb.len) {
+		static const char *nneof = "\\ No newline at end of file\n";
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
-		emit_line(ecb->opt, NULL, NULL, "\n", 1);
-		emit_line_0(ecb->opt, context, reset, '\\',
+		emit_line(ecb->opt, context, reset, 1, 0, 0,
 			    nneof, strlen(nneof));
+		strbuf_release(&sb);
 	}
 }
 
@@ -1095,8 +1094,8 @@ static void emit_rewrite_diff(const char *name_a,
 	ecbdata.lno_in_preimage = 1;
 	ecbdata.lno_in_postimage = 1;
 
-	emit_line_fmt(o, metainfo, reset, "--- %s%s\n", a_name.buf, name_a_tab);
-	emit_line_fmt(o, metainfo, reset, "+++ %s%s\n", b_name.buf, name_b_tab);
+	emit_line_fmt(o, metainfo, reset, 1, "--- %s%s\n", a_name.buf, name_a_tab);
+	emit_line_fmt(o, metainfo, reset, 1, "+++ %s%s\n", b_name.buf, name_b_tab);
 
 	lc_a = count_lines(data_one, size_one);
 	lc_b = count_lines(data_two, size_two);
@@ -1109,7 +1108,7 @@ static void emit_rewrite_diff(const char *name_a,
 	strbuf_addstr(&out, " +");
 	add_line_count(&out, lc_b);
 	strbuf_addstr(&out, " @@\n");
-	emit_line(o, fraginfo, reset, out.buf, out.len);
+	emit_line(o, fraginfo, reset, 1, 0, 0, out.buf, out.len);
 	strbuf_release(&out);
 
 	if (lc_a && !o->irreversible_delete)
@@ -1174,34 +1173,38 @@ struct diff_words_data {
 static int fn_out_diff_words_write_helper(struct diff_options *o,
 					  struct diff_words_style_elem *st_el,
 					  const char *newline,
-					  size_t count, const char *buf,
-					  const char *line_prefix)
+					  size_t count, const char *buf)
 {
+	int print = 0;
 	struct strbuf sb = STRBUF_INIT;
 
 	while (count) {
 		char *p = memchr(buf, '\n', count);
+		if (print)
+			emit_line(o, NULL, NULL, 1, 0, 0, "", 0);
 
 		if (p != buf) {
-			if (st_el->color)
-				strbuf_addstr(&sb, st_el->color);
+			const char *reset = st_el->color && *st_el->color ?
+					    GIT_COLOR_RESET : NULL;
 			strbuf_addstr(&sb, st_el->prefix);
 			strbuf_add(&sb, buf, p ? p - buf : count);
 			strbuf_addstr(&sb, st_el->suffix);
-			if (st_el->color && *st_el->color)
-			    strbuf_addstr(&sb, GIT_COLOR_RESET);
+			emit_line(o, st_el->color, reset,
+				  0, 0, 0, sb.buf, sb.len);
+			strbuf_reset(&sb);
 		}
 		if (!p)
 			goto out;
+
 		strbuf_addstr(&sb, newline);
-		emit_line(o, NULL, NULL, sb.buf, sb.len);
+		emit_line(o, NULL, NULL, 0, 0, 0, sb.buf, sb.len);
 		strbuf_reset(&sb);
 		count -= p + 1 - buf;
 		buf = p + 1;
+		print = 1;
 	}
+
 out:
-	if (sb.len)
-		emit_line(o, NULL, NULL, sb.buf, sb.len);
 	strbuf_release(&sb);
 	return 0;
 }
@@ -1256,14 +1259,12 @@ static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 	int minus_first, minus_len, plus_first, plus_len;
 	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 	struct diff_options *opt = diff_words->opt;
-	const char *line_prefix;
 
 	if (line[0] != '@' || parse_hunk_header(line, len,
 			&minus_first, &minus_len, &plus_first, &plus_len))
 		return;
 
 	assert(opt);
-	line_prefix = diff_line_prefix(opt);
 
 	/* POSIX requires that first be decremented by one if len == 0... */
 	if (minus_len) {
@@ -1280,28 +1281,21 @@ static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 	} else
 		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
 
-	if (color_words_output_graph_prefix(diff_words))
-		emit_line(diff_words->opt, NULL, NULL, "", 0);
-
 	if (diff_words->current_plus != plus_begin) {
 		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->ctx, style->newline,
 				plus_begin - diff_words->current_plus,
-				diff_words->current_plus, line_prefix);
-		if (*(plus_begin - 1) == '\n')
-			emit_line(diff_words->opt, NULL, NULL, "", 0);
+				diff_words->current_plus);
 	}
 	if (minus_begin != minus_end) {
 		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->old, style->newline,
-				minus_end - minus_begin, minus_begin,
-				line_prefix);
+				minus_end - minus_begin, minus_begin);
 	}
 	if (plus_begin != plus_end) {
 		fn_out_diff_words_write_helper(diff_words->opt,
 				&style->new, style->newline,
-				plus_end - plus_begin, plus_begin,
-				line_prefix);
+				plus_end - plus_begin, plus_begin);
 	}
 
 	diff_words->current_plus = plus_end;
@@ -1388,17 +1382,14 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	struct diff_words_style *style = diff_words->style;
 
 	struct diff_options *opt = diff_words->opt;
-	const char *line_prefix;
-
 	assert(opt);
-	line_prefix = diff_line_prefix(opt);
 
 	/* special case: only removal */
 	if (!diff_words->plus.text.size) {
 		fn_out_diff_words_write_helper(diff_words->opt,
 			&style->old, style->newline,
 			diff_words->minus.text.size,
-			diff_words->minus.text.ptr, line_prefix);
+			diff_words->minus.text.ptr);
 		diff_words->minus.text.size = 0;
 		return;
 	}
@@ -1421,12 +1412,11 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	if (diff_words->current_plus != diff_words->plus.text.ptr +
 			diff_words->plus.text.size) {
 		if (color_words_output_graph_prefix(diff_words))
-			emit_line(diff_words->opt, NULL, NULL, "", 0);
+			emit_line(diff_words->opt, NULL, NULL, 1, 0, 0, "", 0);
 		fn_out_diff_words_write_helper(diff_words->opt,
 			&style->ctx, style->newline,
 			diff_words->plus.text.ptr + diff_words->plus.text.size
-			- diff_words->current_plus, diff_words->current_plus,
-			line_prefix);
+			- diff_words->current_plus, diff_words->current_plus);
 	}
 	diff_words->minus.text.size = diff_words->plus.text.size = 0;
 }
@@ -1444,8 +1434,10 @@ static void diff_words_flush(struct emit_callback *ecbdata)
 			append_buffered_patch_line(ecbdata->opt,
 				&ecbdata->diff_words->opt->line_buffer[i]);
 
+		for (i = 0; i < ecbdata->diff_words->opt->line_buffer_nr; i++)
+			free((void*) ecbdata->diff_words->opt->line_buffer[i].line);
+
 		ecbdata->diff_words->opt->line_buffer_nr = 0;
-		/* TODO: free memory as well */
 	}
 }
 
@@ -1521,6 +1513,7 @@ static void free_diff_words_data(struct emit_callback *ecbdata)
 {
 	if (ecbdata->diff_words) {
 		diff_words_flush(ecbdata);
+		free (ecbdata->diff_words->opt->line_buffer);
 		free (ecbdata->diff_words->opt);
 		free (ecbdata->diff_words->minus.text.ptr);
 		free (ecbdata->diff_words->minus.orig);
@@ -1596,7 +1589,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	o->found_changes = 1;
 
 	if (ecbdata->header) {
-		emit_line(o, NULL, NULL,
+		emit_line(o, NULL, NULL, 0, 0, 0,
 			  ecbdata->header->buf, ecbdata->header->len);
 		strbuf_release(ecbdata->header);
 		ecbdata->header = NULL;
@@ -1606,9 +1599,9 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		const char *name_a_tab, *name_b_tab;
 		name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
 		name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";
-		emit_line_fmt(o, meta, reset, "--- %s%s\n",
+		emit_line_fmt(o, meta, reset, 1, "--- %s%s\n",
 			      ecbdata->label_path[0], name_a_tab);
-		emit_line_fmt(o, meta, reset, "+++ %s%s\n",
+		emit_line_fmt(o, meta, reset, 1, "+++ %s%s\n",
 			      ecbdata->label_path[1], name_b_tab);
 		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
 	}
@@ -1649,8 +1642,8 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		}
 		diff_words_flush(ecbdata);
 		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
-			emit_line(o, context, reset, line, len);
-			emit_line(o, NULL, NULL, "~\n", 2);
+			emit_line(o, context, reset, 1, 0, 0, line, len);
+			emit_line(o, NULL, NULL, 0, 0, 0, "~\n", 2);
 		} else {
 			/*
 			 * Skip the prefix character, if any.  With
@@ -1661,7 +1654,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 			      line++;
 			      len--;
 			}
-			emit_line(o, context, reset, line, len);
+			emit_line(o, context, reset, 1, 0, 0, line, len);
 		}
 		return;
 	}
@@ -1684,7 +1677,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		/* incomplete line at the end */
 		ecbdata->lno_in_preimage++;
 		emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT),
-			  reset, line, len);
+			  reset, 1, 0, 0, line, len);
 		break;
 	}
 }
@@ -1873,7 +1866,7 @@ void print_stat_summary_0(struct diff_options *options, int files,
 	if (!files) {
 		assert(insertions == 0 && deletions == 0);
 		strbuf_addstr(&sb, " 0 files changed");
-		emit_line(options, NULL, NULL, sb.buf, sb.len);
+		emit_line(options, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 		return;
 	}
 
@@ -1901,7 +1894,7 @@ void print_stat_summary_0(struct diff_options *options, int files,
 			    deletions);
 	}
 	strbuf_addch(&sb, '\n');
-	emit_line(options, NULL, NULL, sb.buf, sb.len);
+	emit_line(options, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
@@ -2085,7 +2078,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 			strbuf_addf(&out, " %*s", number_width, "Bin");
 			if (!added && !deleted) {
 				strbuf_addch(&out, '\n');
-				emit_line(options, NULL, NULL, out.buf, out.len);
+				emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 				strbuf_reset(&out);
 				continue;
 			}
@@ -2095,14 +2088,14 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 			strbuf_addf(&out, "%s%"PRIuMAX"%s",
 				add_c, added, reset);
 			strbuf_addstr(&out, " bytes\n");
-			emit_line(options, NULL, NULL, out.buf, out.len);
+			emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 			strbuf_reset(&out);
 			continue;
 		}
 		else if (file->is_unmerged) {
 			show_name(&out, prefix, name, len);
 			strbuf_addstr(&out, " Unmerged\n");
-			emit_line(options, NULL, NULL, out.buf, out.len);
+			emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 			strbuf_reset(&out);
 			continue;
 		}
@@ -2133,7 +2126,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		show_graph(&out, '+', add, add_c, reset);
 		show_graph(&out, '-', del, del_c, reset);
 		strbuf_addch(&out, '\n');
-		emit_line(options, NULL, NULL, out.buf, out.len);
+		emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 		strbuf_reset(&out);
 	}
 
@@ -2155,7 +2148,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (i < count)
 			continue;
 		if (!extra_shown)
-			emit_line(options, NULL, NULL,
+			emit_line(options, NULL, NULL, 1, 0, 0,
 				  " ...\n", strlen(" ...\n"));
 		extra_shown = 1;
 	}
@@ -2509,7 +2502,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 		fprintf(data->o->file, "%s%s:%d: %s.\n",
 			line_prefix, data->filename, data->lineno, err);
 		free(err);
-		emit_line(data->o, set, reset, line, 1);
+		emit_line(data->o, set, reset, 1, 0, 0, line, 1);
 		ws_check_emit(line + 1, len - 1, data->ws_rule,
 			      data->o->file, set, reset, ws);
 	} else if (line[0] == ' ') {
@@ -2576,12 +2569,12 @@ static void emit_binary_diff_body(struct diff_options *o,
 	}
 
 	if (delta && delta_size < deflate_size) {
-		emit_line_fmt(o, NULL, NULL, "delta %lu\n", orig_size);
+		emit_line_fmt(o, NULL, NULL, 1, "delta %lu\n", orig_size);
 		free(deflated);
 		data = delta;
 		data_size = delta_size;
 	} else {
-		emit_line_fmt(o, NULL, NULL, "literal %lu\n", two->size);
+		emit_line_fmt(o, NULL, NULL, 1, "literal %lu\n", two->size);
 		free(delta);
 		data = deflated;
 		data_size = deflate_size;
@@ -2605,9 +2598,9 @@ static void emit_binary_diff_body(struct diff_options *o,
 		line[len++] = '\n';
 		line[len] = '\0';
 
-		emit_line(o, NULL, NULL, line, len);
+		emit_line(o, NULL, NULL, 1, 0, 0, line, len);
 	}
-	emit_line(o, NULL, NULL, "\n", 1);
+	emit_line(o, NULL, NULL, 1, 0, 0, "\n", 1);
 	free(data);
 }
 
@@ -2616,7 +2609,7 @@ static void emit_binary_diff(struct diff_options *o,
 {
 	const char *s = "GIT binary patch\n";
 	const int len = strlen(s);
-	emit_line(o, NULL, NULL, s, len);
+	emit_line(o, NULL, NULL, 1, 0, 0, s, len);
 	emit_binary_diff_body(o, one, two);
 	emit_binary_diff_body(o, two, one);
 }
@@ -2727,7 +2720,7 @@ 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, "%sdiff --git %s %s%s\n", meta, 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, meta, two->mode, reset);
@@ -2759,7 +2752,7 @@ 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))) {
-			emit_line(o, NULL, NULL, header.buf, header.len);
+			emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
@@ -2769,8 +2762,7 @@ static void builtin_diff(const char *name_a,
 	}
 
 	if (o->irreversible_delete && lbl[1][0] == '/') {
-		if (header.len)
-			emit_line(o, NULL, NULL, header.buf, header.len);
+		emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 		strbuf_reset(&header);
 		goto free_ab_and_return;
 	} else if (!DIFF_OPT_TST(o, TEXT) &&
@@ -2780,15 +2772,15 @@ static void builtin_diff(const char *name_a,
 		    S_ISREG(one->mode) && S_ISREG(two->mode) &&
 		    !DIFF_OPT_TST(o, BINARY)) {
 			if (!oidcmp(&one->oid, &two->oid)) {
-				if (must_show_header && header.len)
-					emit_line(o, NULL, NULL,
+				if (must_show_header)
+					emit_line(o, NULL, NULL, 0, 0, 0,
 						  header.buf, header.len);
 				goto free_ab_and_return;
 			}
-			if (header.len)
-				emit_line(o, NULL, NULL,
-					  header.buf, header.len);
-			emit_line_fmt(o, 0, 0, "Binary files %s and %s differ\n",
+			emit_line(o, NULL, NULL, 0, 0, 0,
+				  header.buf, header.len);
+			emit_line_fmt(o, NULL, NULL, 1,
+				      "Binary files %s and %s differ\n",
 				      lbl[0], lbl[1]);
 			goto free_ab_and_return;
 		}
@@ -2797,19 +2789,18 @@ static void builtin_diff(const char *name_a,
 		/* Quite common confusing case */
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
-			if (must_show_header && header.len)
-				emit_line(o, NULL, NULL,
+			if (must_show_header)
+				emit_line(o, NULL, NULL, 0, 0, 0,
 					  header.buf, header.len);
 			goto free_ab_and_return;
 		}
-		if (header.len)
-			emit_line(o, NULL, NULL,
-				  header.buf, header.len);
+		emit_line(o, NULL, NULL, 0, 0, 0,
+			  header.buf, header.len);
 		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
 			emit_binary_diff(o, &mf1, &mf2);
 		else
-			emit_line_fmt(o, NULL, NULL,
+			emit_line_fmt(o, NULL, NULL, 1,
 				      "Binary files %s and %s differ\n",
 				      lbl[0], lbl[1]);
 		o->found_changes = 1;
@@ -2822,8 +2813,8 @@ static void builtin_diff(const char *name_a,
 		struct emit_callback ecbdata;
 		const struct userdiff_funcname *pe;
 
-		if (must_show_header && header.len) {
-			emit_line(o, NULL, NULL, header.buf, header.len);
+		if (must_show_header) {
+			emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 		}
 
@@ -2840,6 +2831,7 @@ static void builtin_diff(const char *name_a,
 		ecbdata.label_path = lbl;
 		ecbdata.color_diff = want_color(o->use_color);
 		ecbdata.ws_rule = whitespace_rule(name_b);
+		o->ws_rule = ecbdata.ws_rule;
 		if (ecbdata.ws_rule & WS_BLANK_AT_EOF)
 			check_blank_at_eof(&mf1, &mf2, &ecbdata);
 		ecbdata.opt = o;
@@ -2861,24 +2853,15 @@ static void builtin_diff(const char *name_a,
 		if (o->word_diff)
 			init_diff_words_data(&ecbdata, o, one, two);
 		if (o->use_buffer) {
-			ALLOC_GROW(o->filepair_buffer,
-				   o->filepair_buffer_nr + 1,
-				   o->filepair_buffer_alloc);
-			o->current_filepair =
-				&o->filepair_buffer[o->filepair_buffer_nr++];
-
-			o->current_filepair->ws_rule = ecbdata.ws_rule;
-			o->current_filepair->ws =
-				diff_get_color(ecbdata.color_diff, DIFF_WHITESPACE);
+			struct buffered_patch_line e = BUFFERED_PATCH_LINE_INIT;
+			e.state = BPL_HANDOVER;
+			e.line = name_b;
+			e.len = strlen(name_b);
+			append_buffered_patch_line(o, &e);
 		}
 		if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 				  &xpp, &xecfg))
 			die("unable to generate diff for %s", one->path);
-		if (o->use_buffer) {
-			struct buffered_patch_line e = BUFFERED_PATCH_LINE_INIT;
-			e.state = BPL_HANDOVER; /* handover to next file pair */
-			append_buffered_patch_line(o, &e);
-		}
 		if (o->word_diff)
 			free_diff_words_data(&ecbdata);
 		if (textconv_one)
@@ -3755,6 +3738,12 @@ void diff_setup(struct diff_options *options)
 		options->a_prefix = "a/";
 		options->b_prefix = "b/";
 	}
+
+	options->line_buffer = NULL;
+	options->line_buffer_nr = 0;
+	options->line_buffer_alloc = 0;
+
+	options->color_moved = diff_color_moved_default;
 }
 
 void diff_setup_done(struct diff_options *options)
@@ -4837,11 +4826,10 @@ static void show_file_mode_name(struct diff_options *opt, const char *newdelete,
 
 	quote_c_style(fs->path, &sb, NULL, 0);
 	strbuf_addch(&sb, '\n');
-	emit_line(opt, NULL, NULL, sb.buf, sb.len);
+	emit_line(opt, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
-
 static void show_mode_change(struct diff_options *opt, struct diff_filepair *p,
 		int show_name)
 {
@@ -4851,7 +4839,7 @@ static void show_mode_change(struct diff_options *opt, struct diff_filepair *p,
 			strbuf_addch(&sb, ' ');
 			quote_c_style(p->two->path, &sb, NULL, 0);
 		}
-		emit_line_fmt(opt, NULL, NULL,
+		emit_line_fmt(opt, NULL, NULL, 1,
 			      " mode change %06o => %06o%s\n",
 			      p->one->mode, p->two->mode,
 			      show_name ? sb.buf : "");
@@ -4863,7 +4851,8 @@ static void show_rename_copy(struct diff_options *opt, const char *renamecopy,
 		struct diff_filepair *p)
 {
 	char *names = pprint_rename(p->one->path, p->two->path);
-	emit_line_fmt(opt, NULL, NULL, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
+	emit_line_fmt(opt, NULL, NULL, 1, " %s %s (%d%%)\n",
+		      renamecopy, names, similarity_index(p));
 	free(names);
 	show_mode_change(opt, p, 0);
 }
@@ -4889,7 +4878,7 @@ static void diff_summary(struct diff_options *opt, struct diff_filepair *p)
 			strbuf_addstr(&sb, " rewrite ");
 			quote_c_style(p->two->path, &sb, NULL, 0);
 			strbuf_addf(&sb, " (%d%%)\n", similarity_index(p));
-			emit_line(opt, NULL, NULL, sb.buf, sb.len);
+			emit_line(opt, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 		}
 		show_mode_change(opt, p, !p->score);
 		break;
@@ -5114,12 +5103,6 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 			(hashmap_cmp_fn)moved_entry_cmp, 0);
 	}
 
-	if (o->use_buffer) {
-		ALLOC_GROW(o->filepair_buffer,
-			   o->filepair_buffer_nr + 1,
-			   o->filepair_buffer_alloc);
-		o->current_filepair = &o->filepair_buffer[o->filepair_buffer_nr];
-	}
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		if (check_pair_status(p))
@@ -5127,23 +5110,22 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
-		o->current_filepair = &o->filepair_buffer[0];
-		for (i = 0; i < o->line_buffer_nr; i++)
-			add_line_to_move_detection(o, i);
+		if (o->color_moved) {
+			add_lines_to_move_detection(o);
+			mark_color_as_moved(o);
+		}
 
-		o->current_filepair = &o->filepair_buffer[0];
 		for (i = 0; i < o->line_buffer_nr; i++)
-			process_next_buffered_patch_line(o, i);
+			emit_buffered_patch_line(o, &o->line_buffer[i]);
 
-		for (i = 0; i < o->line_buffer_nr; i++);
+		for (i = 0; i < o->line_buffer_nr; i++)
 			free((void*)o->line_buffer[i].line);
 
+		free(o->line_buffer);
+
 		o->line_buffer = NULL;
 		o->line_buffer_nr = 0;
-		free(o->line_buffer);
-		o->filepair_buffer = NULL;
-		o->filepair_buffer_nr = 0;
-		free(o->filepair_buffer);
+		o->line_buffer_alloc = 0;
 	}
 }
 
@@ -5237,11 +5219,10 @@ void diff_flush(struct diff_options *options)
 			term[0] = options->line_termination;
 			term[1] = '\0';
 
-			emit_line(options, NULL, NULL,
-				  term, 1);
+			emit_line(options, NULL, NULL, 1, 0, 0, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
-				emit_line(options, NULL, NULL,
+				emit_line(options, NULL, NULL, 0, 0, 0,
 					  options->stat_sep,
 					  strlen(options->stat_sep));
 			}
diff --git a/diff.h b/diff.h
index b83d6fefcc..b8b2a33ccc 100644
--- a/diff.h
+++ b/diff.h
@@ -133,21 +133,24 @@ struct buffered_patch_line {
 	const char *line;
 	int len;
 	int sign;
+	int add_line_prefix;
 	enum {
+		/*
+		 * Emits [lineprefix][set][sign][reset] and then calls
+		 * ws_check_emit which will output "line", marked up
+		 * according to ws_rule.
+		 */
 		BPL_EMIT_LINE_WS,
+
+		/* Emits [lineprefix][set][sign] line [reset] */
 		BPL_EMIT_LINE_ASIS,
+
+		/* Reloads the ws_rule; line contains the file name */
 		BPL_HANDOVER
 	} state;
 };
 #define BUFFERED_PATCH_LINE_INIT {NULL, NULL, NULL, 0, 0, 0}
 
-struct buffered_filepair {
-	const char *ws;
-	unsigned ws_rule;
-};
-
-struct moved_entry;
-
 struct diff_options {
 	const char *orderfile;
 	const char *pickaxe;
@@ -220,32 +223,21 @@ struct diff_options {
 
 	int diff_path_counter;
 
-	/* Determines color moved code. Flipped between 1, 2 for alt. color. */
-	int color_moved;
+	unsigned ws_rule;
 	int use_buffer;
 
 	struct buffered_patch_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
 
-	struct buffered_filepair *filepair_buffer;
-	int filepair_buffer_nr, filepair_buffer_alloc;
-	struct buffered_filepair *current_filepair;
-
-	/* built up in the first pass: */
+	int color_moved;
 	struct hashmap *deleted_lines;
 	struct hashmap *added_lines;
-	/* needed for building up */
-	struct moved_entry *prev_line;
-
-	/* state in the second pass */
-	struct moved_entry **pmb; /* potentially moved blocks */
-	int pmb_nr, pmb_alloc;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
-		   const char *fmt, ...);
+		   int add_line_prefix, const char *fmt, ...);
 void emit_line(struct diff_options *o, const char *set, const char *reset,
-	       const char *line, int len);
+	       int add_line_prefix, int markup_ws, int sign, const char *line, int len);
 
 enum color_diff {
 	DIFF_RESET = 0,
diff --git a/submodule.c b/submodule.c
index cfad469a2f..868f913971 100644
--- a/submodule.c
+++ b/submodule.c
@@ -378,9 +378,9 @@ static void print_submodule_summary(struct rev_info *rev,
 		format_commit_message(commit, format, &sb, &ctx);
 		strbuf_addch(&sb, '\n');
 		if (commit->object.flags & SYMMETRIC_LEFT)
-			emit_line(o, del, reset, sb.buf, sb.len);
+			emit_line(o, del, reset, 1, 0, 0, sb.buf, sb.len);
 		else if (add)
-			emit_line(o, add, reset, sb.buf, sb.len);
+			emit_line(o, add, reset, 1, 0, 0, sb.buf, sb.len);
 	}
 	strbuf_release(&sb);
 }
@@ -419,10 +419,10 @@ static void show_submodule_header(struct diff_options *o, const char *path,
 	int fast_forward = 0, fast_backward = 0;
 
 	if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED)
-		emit_line_fmt(o, NULL, NULL,
+		emit_line_fmt(o, NULL, NULL, 1,
 			      "Submodule %s contains untracked content\n", path);
 	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED)
-		emit_line_fmt(o, NULL, NULL,
+		emit_line_fmt(o, NULL, NULL, 1,
 			      "Submodule %s contains modified content\n", path);
 
 	if (is_null_oid(one))
@@ -473,7 +473,7 @@ static void show_submodule_header(struct diff_options *o, const char *path,
 		strbuf_addf(&sb, " %s\n", message);
 	else
 		strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : "");
-	emit_line(o, meta, reset, sb.buf, sb.len);
+	emit_line(o, meta, reset, 1, 0, 0, sb.buf, sb.len);
 
 	strbuf_release(&sb);
 }
@@ -501,7 +501,7 @@ void show_submodule_summary(struct diff_options *o, const char *path,
 	/* Treat revision walker failure the same as missing commits */
 	if (prepare_submodule_summary(&rev, path, left, right, merge_bases)) {
 		const char *error = "(revision walker failed)\n";
-		emit_line(o, NULL, NULL, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 		goto out;
 	}
 
@@ -570,15 +570,15 @@ void show_submodule_inline_diff(struct diff_options *o, const char *path,
 	prepare_submodule_repo_env(&cp.env_array);
 	if (start_command(&cp)) {
 		const char *error = "(diff failed)\n";
-		emit_line(o, NULL, NULL, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 	}
 
 	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
-		emit_line(o, NULL, NULL, sb.buf, sb.len);
+		emit_line(o, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 
 	if (finish_command(&cp)) {
 		const char *error = "(diff failed)\n";
-		emit_line(o, NULL, NULL, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 	}
 
 done:

diff --git a/diff.c b/diff.c
index 74283d9001..3f5bf8b5a4 100644
--- a/diff.c
+++ b/diff.c
@@ -3283,8 +3283,8 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o)
 	const char *other;
 	const char *attr_path;
 
-	name  = p->one->path;
-	other = (strcmp(name, p->two->path) ? p->two->path : NULL);
+	name  = one->path;
+	other = (strcmp(name, two->path) ? two->path : NULL);
 	attr_path = name;
 	if (o->prefix_length)
 		strip_prefix(o->prefix_length, &name, &other);

diff --git a/diff.c b/diff.c
index 3f5bf8b5a4..c2ed605cd0 100644
--- a/diff.c
+++ b/diff.c
@@ -677,6 +677,8 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	}
 
 	strbuf_add(&msgbuf, line + len, org_len - len);
+	strbuf_complete_line(&msgbuf);
+
 	emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
@@ -1315,8 +1317,6 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		len = sane_truncate_line(ecbdata, line, len);
 		find_lno(line, ecbdata);
 		emit_hunk_header(ecbdata, line, len);
-		if (line[len-1] != '\n')
-			putc('\n', o->file);
 		return;
 	}
 

diff --git a/diff.c b/diff.c
index c2ed605cd0..2f9722b382 100644
--- a/diff.c
+++ b/diff.c
@@ -4737,6 +4737,17 @@ void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc)
 		warning(_(rename_limit_advice), varname, needed);
 }
 
+static void diff_flush_patch_all_file_pairs(struct diff_options *o)
+{
+	int i;
+	struct diff_queue_struct *q = &diff_queued_diff;
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		if (check_pair_status(p))
+			diff_flush_patch(p, o);
+	}
+}
+
 void diff_flush(struct diff_options *options)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -4831,11 +4842,7 @@ void diff_flush(struct diff_options *options)
 			}
 		}
 
-		for (i = 0; i < q->nr; i++) {
-			struct diff_filepair *p = q->queue[i];
-			if (check_pair_status(p))
-				diff_flush_patch(p, options);
-		}
+		diff_flush_patch_all_file_pairs(options);
 	}
 
 	if (output_format & DIFF_FORMAT_CALLBACK)

diff --git a/diff.c b/diff.c
index 2f9722b382..73e55b0c10 100644
--- a/diff.c
+++ b/diff.c
@@ -517,33 +517,24 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 }
 
 static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
-			int first, const char *line, int len)
+			int sign, const char *line, int len)
 {
 	int has_trailing_newline, has_trailing_carriage_return;
-	int nofirst;
 	FILE *file = o->file;
 
 	fputs(diff_line_prefix(o), file);
 
-	if (len == 0) {
-		has_trailing_newline = (first == '\n');
-		has_trailing_carriage_return = (!has_trailing_newline &&
-						(first == '\r'));
-		nofirst = has_trailing_newline || has_trailing_carriage_return;
-	} else {
-		has_trailing_newline = (len > 0 && line[len-1] == '\n');
-		if (has_trailing_newline)
-			len--;
-		has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
-		if (has_trailing_carriage_return)
-			len--;
-		nofirst = 0;
-	}
+	has_trailing_newline = (len > 0 && line[len-1] == '\n');
+	if (has_trailing_newline)
+		len--;
+	has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
+	if (has_trailing_carriage_return)
+		len--;
 
-	if (len || !nofirst) {
+	if (len || sign) {
 		fputs(set, file);
-		if (!nofirst)
-			fputc(first, file);
+		if (sign)
+			fputc(sign, file);
 		fwrite(line, len, 1, file);
 		fputs(reset, file);
 	}
@@ -556,7 +547,7 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 static void emit_line(struct diff_options *o, const char *set, const char *reset,
 		      const char *line, int len)
 {
-	emit_line_0(o, set, reset, line[0], line+1, len-1);
+	emit_line_0(o, set, reset, 0, line, len);
 }
 
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
@@ -4833,9 +4824,11 @@ void diff_flush(struct diff_options *options)
 
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
-			fprintf(options->file, "%s%c",
-				diff_line_prefix(options),
-				options->line_termination);
+			char term[2];
+			term[0] = options->line_termination;
+			term[1] = '\0';
+
+			emit_line(options, NULL, NULL, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);

diff --git a/diff.c b/diff.c
index 25735f03d2..3569857818 100644
--- a/diff.c
+++ b/diff.c
@@ -516,8 +516,8 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
-			int add_line_prefix, int sign, const char *line, int len)
+static void emit_line(struct diff_options *o, const char *set, const char *reset,
+		      int add_line_prefix, int sign, const char *line, int len)
 {
 	int has_trailing_newline, has_trailing_carriage_return;
 	FILE *file = o->file;
@@ -547,12 +547,6 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 		fputc('\n', file);
 }
 
-static void emit_line(struct diff_options *o, const char *set, const char *reset,
-		      const char *line, int len)
-{
-	emit_line_0(o, set, reset, 1, 0, line, len);
-}
-
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
@@ -581,13 +575,13 @@ static void emit_line_checked(const char *reset,
 	}
 
 	if (!ws)
-		emit_line_0(ecbdata->opt, set, reset, 1, sign, line, len);
+		emit_line(ecbdata->opt, set, reset, 1, sign, line, len);
 	else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len))
 		/* Blank line at EOF - paint '+' as well */
-		emit_line_0(ecbdata->opt, ws, reset, 1, sign, line, len);
+		emit_line(ecbdata->opt, ws, reset, 1, sign, line, len);
 	else {
 		/* Emit just the prefix, then the rest. */
-		emit_line_0(ecbdata->opt, set, reset, 1, sign, "", 0);
+		emit_line(ecbdata->opt, set, reset, 1, sign, "", 0);
 		ws_check_emit(line, len, ecbdata->ws_rule,
 			      ecbdata->opt->file, set, reset, ws);
 	}
@@ -637,7 +631,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	if (len < 10 ||
 	    memcmp(line, atat, 2) ||
 	    !(ep = memmem(line + 2, len - 2, atat, 2))) {
-		emit_line(ecbdata->opt, context, reset, line, len);
+		emit_line(ecbdata->opt, context, reset, 1, 0, line, len);
 		return;
 	}
 	ep += 2; /* skip over @@ */
@@ -673,7 +667,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	strbuf_add(&msgbuf, line + len, org_len - len);
 	strbuf_complete_line(&msgbuf);
 
-	emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len);
+	emit_line(ecbdata->opt, "", "", 1, 0, msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
 
@@ -736,8 +730,8 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
 		putc('\n', ecb->opt->file);
-		emit_line_0(ecb->opt, context, reset, 1, '\\',
-			    nneof, strlen(nneof));
+		emit_line(ecb->opt, context, reset, 1, '\\',
+			  nneof, strlen(nneof));
 	}
 }
 
@@ -1335,7 +1329,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		}
 		diff_words_flush(ecbdata);
 		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
-			emit_line(o, context, reset, line, len);
+			emit_line(o, context, reset, 1, 0, line, len);
 			fputs("~\n", o->file);
 		} else {
 			/*
@@ -1347,7 +1341,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 			      line++;
 			      len--;
 			}
-			emit_line(o, context, reset, line, len);
+			emit_line(o, context, reset, 1, 0, line, len);
 		}
 		return;
 	}
@@ -1370,7 +1364,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		/* incomplete line at the end */
 		ecbdata->lno_in_preimage++;
 		emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT),
-			  reset, line, len);
+			  reset, 1, 0, line, len);
 		break;
 	}
 }
@@ -2182,7 +2176,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 		fprintf(data->o->file, "%s%s:%d: %s.\n",
 			line_prefix, data->filename, data->lineno, err);
 		free(err);
-		emit_line(data->o, set, reset, line, 1);
+		emit_line(data->o, set, reset, 1, 0, line, 1);
 		ws_check_emit(line + 1, len - 1, data->ws_rule,
 			      data->o->file, set, reset, ws);
 	} else if (line[0] == ' ') {
@@ -4831,7 +4825,7 @@ void diff_flush(struct diff_options *options)
 			term[0] = options->line_termination;
 			term[1] = '\0';
 
-			emit_line(options, NULL, NULL, term, !!term[0]);
+			emit_line(options, NULL, NULL, 1, 0, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);

diff --git a/diff.c b/diff.c
index 3dda9f3c8e..690794aeb8 100644
--- a/diff.c
+++ b/diff.c
@@ -722,15 +722,25 @@ static void add_line_count(struct strbuf *out, int count)
 static void emit_rewrite_lines(struct emit_callback *ecb,
 			       int prefix, const char *data, int size)
 {
-	const char *endp = NULL;
-	static const char *nneof = " No newline at end of file\n";
 	const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET);
+	struct strbuf sb = STRBUF_INIT;
 
 	while (0 < size) {
 		int len;
 
-		endp = memchr(data, '\n', size);
-		len = endp ? (endp - data + 1) : size;
+		const char *endp = memchr(data, '\n', size);
+		if (endp)
+			len = endp - data + 1;
+		else {
+			while (0 < size) {
+				strbuf_addch(&sb, *data);
+				size -= len;
+				data += len;
+			}
+			strbuf_addch(&sb, '\n');
+			data = sb.buf;
+			len = sb.len;
+		}
 		if (prefix != '+') {
 			ecb->lno_in_preimage++;
 			emit_del_line(reset, ecb, data, len);
@@ -741,12 +751,13 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		size -= len;
 		data += len;
 	}
-	if (!endp) {
+	if (sb.len) {
+		static const char *nneof = "\\ No newline at end of file\n";
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
-		putc('\n', ecb->opt->file);
-		emit_line(ecb->opt, context, reset, 1, '\\',
-			  nneof, strlen(nneof));
+		emit_line(ecb->opt, context, reset, 1, 0,
+			    nneof, strlen(nneof));
+		strbuf_release(&sb);
 	}
 }
 

diff.c, diff.h

diff --git a/diff.c b/diff.c
index 2dd10fa16a..ccd28953d7 100644
--- a/diff.c
+++ b/diff.c
@@ -1536,20 +1536,19 @@ static int scale_linear(int it, int width, int max_change)
 	return 1 + (it * (width - 1) / max_change);
 }
 
-static void show_name(FILE *file,
+static void show_name(struct strbuf *out,
 		      const char *prefix, const char *name, int len)
 {
-	fprintf(file, " %s%-*s |", prefix, len, name);
+	strbuf_addf(out, " %s%-*s |", prefix, len, name);
 }
 
-static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset)
+static void show_graph(struct strbuf *out, char ch, int cnt, const char *set, const char *reset)
 {
 	if (cnt <= 0)
 		return;
-	fprintf(file, "%s", set);
-	while (cnt--)
-		putc(ch, file);
-	fprintf(file, "%s", reset);
+	strbuf_addstr(out, set);
+	strbuf_addchars(out, ch, cnt);
+	strbuf_addstr(out, reset);
 }
 
 static void fill_print_name(struct diffstat_file *file)
@@ -1573,14 +1572,16 @@ 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)
+void print_stat_summary_0(struct diff_options *options, 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_addstr(&sb, " 0 files changed");
+		emit_line(options, NULL, NULL, 1, 0, sb.buf, sb.len);
+		return;
 	}
 
 	strbuf_addf(&sb,
@@ -1607,9 +1608,17 @@ int print_stat_summary(FILE *fp, int files, int insertions, int deletions)
 			    deletions);
 	}
 	strbuf_addch(&sb, '\n');
-	ret = fputs(sb.buf, fp);
+	emit_line(options, NULL, NULL, 1, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
-	return ret;
+}
+
+void print_stat_summary(FILE *fp, int files,
+			int insertions, int deletions)
+{
+	struct diff_options o;
+	memset(&o, 0, sizeof(o));
+	o.file = fp;
+	print_stat_summary_0(&o, files, insertions, deletions);
 }
 
 static void show_stats(struct diffstat_t *data, struct diff_options *options)
@@ -1619,13 +1628,13 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 	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;
+	const char *line_prefix = diff_line_prefix(options);
+	struct strbuf out = STRBUF_INIT;
 
 	if (data->nr == 0)
 		return;
 
-	line_prefix = diff_line_prefix(options);
 	count = options->stat_count ? options->stat_count : data->nr;
 
 	reset = diff_get_color_opt(options, DIFF_RESET);
@@ -1779,26 +1788,29 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		}
 
 		if (file->is_binary) {
-			fprintf(options->file, "%s", line_prefix);
-			show_name(options->file, prefix, name, len);
-			fprintf(options->file, " %*s", number_width, "Bin");
+			show_name(&out, prefix, name, len);
+			strbuf_addf(&out, " %*s", number_width, "Bin");
 			if (!added && !deleted) {
-				putc('\n', options->file);
+				strbuf_addch(&out, '\n');
+				emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+				strbuf_reset(&out);
 				continue;
 			}
-			fprintf(options->file, " %s%"PRIuMAX"%s",
+			strbuf_addf(&out, " %s%"PRIuMAX"%s",
 				del_c, deleted, reset);
-			fprintf(options->file, " -> ");
-			fprintf(options->file, "%s%"PRIuMAX"%s",
+			strbuf_addstr(&out, " -> ");
+			strbuf_addf(&out, "%s%"PRIuMAX"%s",
 				add_c, added, reset);
-			fprintf(options->file, " bytes");
-			fprintf(options->file, "\n");
+			strbuf_addstr(&out, " bytes\n");
+			emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+			strbuf_reset(&out);
 			continue;
 		}
 		else if (file->is_unmerged) {
-			fprintf(options->file, "%s", line_prefix);
-			show_name(options->file, prefix, name, len);
-			fprintf(options->file, " Unmerged\n");
+			show_name(&out, prefix, name, len);
+			strbuf_addstr(&out, " Unmerged\n");
+			emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+			strbuf_reset(&out);
 			continue;
 		}
 
@@ -1821,14 +1833,15 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 				add = total - del;
 			}
 		}
-		fprintf(options->file, "%s", line_prefix);
-		show_name(options->file, prefix, name, len);
-		fprintf(options->file, " %*"PRIuMAX"%s",
+		show_name(&out, prefix, name, len);
+		strbuf_addf(&out, " %*"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");
+		show_graph(&out, '+', add, add_c, reset);
+		show_graph(&out, '-', del, del_c, reset);
+		strbuf_addch(&out, '\n');
+		emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+		strbuf_reset(&out);
 	}
 
 	for (i = 0; i < data->nr; i++) {
@@ -1849,11 +1862,12 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (i < count)
 			continue;
 		if (!extra_shown)
-			fprintf(options->file, "%s ...\n", line_prefix);
+			emit_line(options, NULL, NULL, 1, 0,
+				  " ...\n", strlen(" ...\n"));
 		extra_shown = 1;
 	}
-	fprintf(options->file, "%s", line_prefix);
-	print_stat_summary(options->file, total_files, adds, dels);
+
+	print_stat_summary_0(options, total_files, adds, dels);
 }
 
 static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
@@ -1865,7 +1879,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 
 	for (i = 0; i < data->nr; i++) {
 		int added = data->files[i]->added;
-		int deleted= data->files[i]->deleted;
+		int deleted = data->files[i]->deleted;
 
 		if (data->files[i]->is_unmerged ||
 		    (!data->files[i]->is_interesting && (added + deleted == 0))) {
@@ -1875,8 +1889,7 @@ static void show_shortstats(struct diffstat_t *data, struct diff_options *option
 			dels += deleted;
 		}
 	}
-	fprintf(options->file, "%s", diff_line_prefix(options));
-	print_stat_summary(options->file, total_files, adds, dels);
+	print_stat_summary_0(options, total_files, adds, dels);
 }
 
 static void show_numstat(struct diffstat_t *data, struct diff_options *options)
diff --git a/diff.h b/diff.h
index 6e14100102..b75b0d7283 100644
--- a/diff.h
+++ b/diff.h
@@ -394,8 +394,8 @@ extern int parse_rename_score(const char **cp_p);
 
 extern long parse_algorithm_value(const char *value);
 
-extern int print_stat_summary(FILE *fp, int files,
-			      int insertions, int deletions);
+extern void print_stat_summary(FILE *fp, int files,
+			       int insertions, int deletions);
 extern void setup_diff_pager(struct diff_options *);
 
 #endif /* DIFF_H */

diff --git a/diff.c b/diff.c
index 6c1886d495..25735f03d2 100644
--- a/diff.c
+++ b/diff.c
@@ -517,12 +517,13 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 }
 
 static void emit_line_0(struct diff_options *o, const char *set, const char *reset,
-			int sign, const char *line, int len)
+			int add_line_prefix, int sign, const char *line, int len)
 {
 	int has_trailing_newline, has_trailing_carriage_return;
 	FILE *file = o->file;
 
-	fputs(diff_line_prefix(o), file);
+	if (add_line_prefix)
+		fputs(diff_line_prefix(o), file);
 
 	has_trailing_newline = (len > 0 && line[len-1] == '\n');
 	if (has_trailing_newline)
@@ -549,7 +550,7 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 static void emit_line(struct diff_options *o, const char *set, const char *reset,
 		      const char *line, int len)
 {
-	emit_line_0(o, set, reset, 0, line, len);
+	emit_line_0(o, set, reset, 1, 0, line, len);
 }
 
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
@@ -580,13 +581,13 @@ static void emit_line_checked(const char *reset,
 	}
 
 	if (!ws)
-		emit_line_0(ecbdata->opt, set, reset, sign, line, len);
+		emit_line_0(ecbdata->opt, set, reset, 1, sign, line, len);
 	else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len))
 		/* Blank line at EOF - paint '+' as well */
-		emit_line_0(ecbdata->opt, ws, reset, sign, line, len);
+		emit_line_0(ecbdata->opt, ws, reset, 1, sign, line, len);
 	else {
 		/* Emit just the prefix, then the rest. */
-		emit_line_0(ecbdata->opt, set, reset, sign, "", 0);
+		emit_line_0(ecbdata->opt, set, reset, 1, sign, "", 0);
 		ws_check_emit(line, len, ecbdata->ws_rule,
 			      ecbdata->opt->file, set, reset, ws);
 	}
@@ -735,7 +736,7 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
 		putc('\n', ecb->opt->file);
-		emit_line_0(ecb->opt, context, reset, '\\',
+		emit_line_0(ecb->opt, context, reset, 1, '\\',
 			    nneof, strlen(nneof));
 	}
 }

diff --git a/diff.c b/diff.c
index 3569857818..8186289734 100644
--- a/diff.c
+++ b/diff.c
@@ -547,6 +547,21 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
 		fputc('\n', file);
 }
 
+static void emit_line_fmt(struct diff_options *o,
+			  const char *set, const char *reset,
+			  int add_line_prefix,
+			  const char *fmt, ...)
+{
+	struct strbuf sb = STRBUF_INIT;
+	va_list ap;
+	va_start(ap, fmt);
+	strbuf_vaddf(&sb, fmt, ap);
+	va_end(ap);
+
+	emit_line(o, set, reset, add_line_prefix, 0, sb.buf, sb.len);
+	strbuf_release(&sb);
+}
+
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
@@ -1270,7 +1285,6 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT);
 	const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET);
 	struct diff_options *o = ecbdata->opt;
-	const char *line_prefix = diff_line_prefix(o);
 
 	o->found_changes = 1;
 
@@ -1282,14 +1296,12 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 
 	if (ecbdata->label_path[0]) {
 		const char *name_a_tab, *name_b_tab;
-
 		name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : "";
 		name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : "";
-
-		fprintf(o->file, "%s%s--- %s%s%s\n",
-			line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab);
-		fprintf(o->file, "%s%s+++ %s%s%s\n",
-			line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab);
+		emit_line_fmt(o, meta, reset, 1, "--- %s%s\n",
+			      ecbdata->label_path[0], name_a_tab);
+		emit_line_fmt(o, meta, reset, 1, "+++ %s%s\n",
+			      ecbdata->label_path[1], name_b_tab);
 		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
 	}
 
@@ -1330,7 +1342,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		diff_words_flush(ecbdata);
 		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
 			emit_line(o, context, reset, 1, 0, line, len);
-			fputs("~\n", o->file);
+			emit_line(o, NULL, NULL, 0, 0, "~\n", 2);
 		} else {
 			/*
 			 * Skip the prefix character, if any.  With

diff --git a/diff.c b/diff.c
index 4cd1b3c520..964b5cb5a7 100644
--- a/diff.c
+++ b/diff.c
@@ -4500,67 +4500,71 @@ static void flush_one_pair(struct diff_filepair *p, struct diff_options *opt)
 	}
 }
 
-static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs)
+static void show_file_mode_name(struct diff_options *opt, const char *newdelete, struct diff_filespec *fs)
 {
+	struct strbuf sb = STRBUF_INIT;
 	if (fs->mode)
-		fprintf(file, " %s mode %06o ", newdelete, fs->mode);
+		strbuf_addf(&sb, " %s mode %06o ", newdelete, fs->mode);
 	else
-		fprintf(file, " %s ", newdelete);
-	write_name_quoted(fs->path, file, '\n');
-}
+		strbuf_addf(&sb, " %s ", newdelete);
 
+	quote_c_style(fs->path, &sb, NULL, 0);
+	strbuf_addch(&sb, '\n');
+	emit_line(opt, NULL, NULL, 1, 0, sb.buf, sb.len);
+	strbuf_release(&sb);
+}
 
-static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name,
-		const char *line_prefix)
+static void show_mode_change(struct diff_options *opt, struct diff_filepair *p,
+		int show_name)
 {
 	if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) {
-		fprintf(file, "%s mode change %06o => %06o%c", line_prefix, p->one->mode,
-			p->two->mode, show_name ? ' ' : '\n');
+		struct strbuf sb = STRBUF_INIT;
 		if (show_name) {
-			write_name_quoted(p->two->path, file, '\n');
+			strbuf_addch(&sb, ' ');
+			quote_c_style(p->two->path, &sb, NULL, 0);
 		}
+		emit_line_fmt(opt, NULL, NULL, 1,
+			      " mode change %06o => %06o%s\n",
+			      p->one->mode, p->two->mode,
+			      show_name ? sb.buf : "");
+		strbuf_release(&sb);
 	}
 }
 
-static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p,
-			const char *line_prefix)
+static void show_rename_copy(struct diff_options *opt, const char *renamecopy,
+		struct diff_filepair *p)
 {
 	char *names = pprint_rename(p->one->path, p->two->path);
-
-	fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p));
+	emit_line_fmt(opt, NULL, NULL, 1, " %s %s (%d%%)\n",
+		      renamecopy, names, similarity_index(p));
 	free(names);
-	show_mode_change(file, p, 0, line_prefix);
+	show_mode_change(opt, p, 0);
 }
 
 static void diff_summary(struct diff_options *opt, struct diff_filepair *p)
 {
-	FILE *file = opt->file;
-	const char *line_prefix = diff_line_prefix(opt);
-
 	switch(p->status) {
 	case DIFF_STATUS_DELETED:
-		fputs(line_prefix, file);
-		show_file_mode_name(file, "delete", p->one);
+		show_file_mode_name(opt, "delete", p->one);
 		break;
 	case DIFF_STATUS_ADDED:
-		fputs(line_prefix, file);
-		show_file_mode_name(file, "create", p->two);
+		show_file_mode_name(opt, "create", p->two);
 		break;
 	case DIFF_STATUS_COPIED:
-		fputs(line_prefix, file);
-		show_rename_copy(file, "copy", p, line_prefix);
+		show_rename_copy(opt, "copy", p);
 		break;
 	case DIFF_STATUS_RENAMED:
-		fputs(line_prefix, file);
-		show_rename_copy(file, "rename", p, line_prefix);
+		show_rename_copy(opt, "rename", p);
 		break;
 	default:
 		if (p->score) {
-			fprintf(file, "%s rewrite ", line_prefix);
-			write_name_quoted(p->two->path, file, ' ');
-			fprintf(file, "(%d%%)\n", similarity_index(p));
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addstr(&sb, " rewrite ");
+			quote_c_style(p->two->path, &sb, NULL, 0);
+			strbuf_addf(&sb, " (%d%%)\n", similarity_index(p));
+			emit_line(opt, NULL, NULL, 1, 0, sb.buf, sb.len);
 		}
-		show_mode_change(file, p, !p->score, line_prefix);
+		show_mode_change(opt, p, !p->score);
 		break;
 	}
 }

diff --git a/diff.c b/diff.c
index f1cb0b7799..4cd1b3c520 100644
--- a/diff.c
+++ b/diff.c
@@ -4868,7 +4868,9 @@ void diff_flush(struct diff_options *options)
 			emit_line(options, NULL, NULL, 1, 0, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
-				fputs(options->stat_sep, options->file);
+				emit_line(options, NULL, NULL, 0, 0,
+					  options->stat_sep,
+					  strlen(options->stat_sep));
 			}
 		}
 

Documentation/config.txt, diff.c, diff.h, t/t4015-diff-whitespace.sh

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 475e874d51..902d017c3b 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1051,14 +1051,24 @@ This does not affect linkgit:git-format-patch[1] or the
 'git-diff-{asterisk}' plumbing commands.  Can be overridden on the
 command line with the `--color[=<when>]` option.
 
+color.moved::
+	A boolean value, whether a diff should color moved lines
+	differently. The moved lines are searched for in the diff only.
+	Duplicated lines from somewhere in the project that are not
+	part of the diff are not colored as moved.
+	Defaults to false.
+
 color.diff.<slot>::
 	Use customized color for diff colorization.  `<slot>` specifies
 	which part of the patch to use the specified color, and is one
 	of `context` (context text - `plain` is a historical synonym),
 	`meta` (metainformation), `frag`
 	(hunk header), 'func' (function in hunk header), `old` (removed lines),
-	`new` (added lines), `commit` (commit headers), or `whitespace`
-	(highlighting whitespace errors).
+	`new` (added lines), `commit` (commit headers), `whitespace`
+	(highlighting whitespace errors), `oldMoved` (removed lines that
+	reappear), `newMoved` (added lines that were removed elsewhere),
+	`oldMovedAlternative` and `newMovedAlternative` (as a fallback to
+	cover adjacent blocks of moved code)
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/diff.c b/diff.c
index 1d8d1786fd..15cf322b50 100644
--- a/diff.c
+++ b/diff.c
@@ -31,6 +31,7 @@ static int diff_indent_heuristic; /* experimental */
 static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
 static int diff_use_color_default = -1;
+static int diff_color_moved_default;
 static int diff_context_default = 3;
 static int diff_interhunk_context_default;
 static const char *diff_word_regex_cfg;
@@ -55,6 +56,10 @@ static char diff_colors[][COLOR_MAXLEN] = {
 	GIT_COLOR_YELLOW,	/* COMMIT */
 	GIT_COLOR_BG_RED,	/* WHITESPACE */
 	GIT_COLOR_NORMAL,	/* FUNCINFO */
+	GIT_COLOR_BOLD_RED,	/* OLD_MOVED_A */
+	GIT_COLOR_BG_RED,	/* OLD_MOVED_B */
+	GIT_COLOR_BOLD_GREEN,	/* NEW_MOVED_A */
+	GIT_COLOR_BG_GREEN,	/* NEW_MOVED_B */
 };
 
 static NORETURN void die_want_option(const char *option_name)
@@ -80,6 +85,14 @@ static int parse_diff_color_slot(const char *var)
 		return DIFF_WHITESPACE;
 	if (!strcasecmp(var, "func"))
 		return DIFF_FUNCINFO;
+	if (!strcasecmp(var, "oldmoved"))
+		return DIFF_FILE_OLD_MOVED;
+	if (!strcasecmp(var, "oldmovedalternative"))
+		return DIFF_FILE_OLD_MOVED_ALT;
+	if (!strcasecmp(var, "newmoved"))
+		return DIFF_FILE_NEW_MOVED;
+	if (!strcasecmp(var, "newmovedalternative"))
+		return DIFF_FILE_NEW_MOVED_ALT;
 	return -1;
 }
 
@@ -234,6 +247,10 @@ 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, "color.moved")) {
+		diff_color_moved_default = git_config_bool(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "diff.context")) {
 		diff_context_default = git_config_int(var, value);
 		if (diff_context_default < 0)
@@ -354,6 +371,88 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 	return git_default_config(var, value, cb);
 }
 
+struct moved_entry {
+	struct hashmap_entry ent;
+	const struct buffered_patch_line *line;
+	struct moved_entry *next_line;
+};
+
+static void get_ws_cleaned_string(const struct buffered_patch_line *l,
+				  struct strbuf *out)
+{
+	int i;
+	for (i = 0; i < l->len; i++) {
+		if (isspace(l->line[i]))
+			continue;
+		strbuf_addch(out, l->line[i]);
+	}
+}
+
+static int buffered_patch_line_cmp_no_ws(const struct buffered_patch_line *a,
+					 const struct buffered_patch_line *b,
+					 const void *keydata)
+{
+	int ret;
+	struct strbuf sba = STRBUF_INIT;
+	struct strbuf sbb = STRBUF_INIT;
+
+	get_ws_cleaned_string(a, &sba);
+	get_ws_cleaned_string(b, &sbb);
+	ret = sba.len != sbb.len || strncmp(sba.buf, sbb.buf, sba.len);
+
+	strbuf_release(&sba);
+	strbuf_release(&sbb);
+	return ret;
+}
+
+static int buffered_patch_line_cmp(const struct buffered_patch_line *a,
+				   const struct buffered_patch_line *b,
+				   const void *keydata)
+{
+	return a->len != b->len || strncmp(a->line, b->line, a->len);
+}
+
+static int moved_entry_cmp(const struct moved_entry *a,
+			   const struct moved_entry *b,
+			   const void *keydata)
+{
+	return buffered_patch_line_cmp(a->line, b->line, keydata);
+}
+
+static int moved_entry_cmp_no_ws(const struct moved_entry *a,
+				 const struct moved_entry *b,
+				 const void *keydata)
+{
+	return buffered_patch_line_cmp_no_ws(a->line, b->line, keydata);
+}
+
+static unsigned get_line_hash(struct buffered_patch_line *line, unsigned ignore_ws)
+{
+	static struct strbuf sb = STRBUF_INIT;
+
+	if (ignore_ws) {
+		strbuf_reset(&sb);
+		get_ws_cleaned_string(line, &sb);
+		return memhash(sb.buf, sb.len);
+	} else {
+		return memhash(line->line, line->len);
+	}
+}
+
+static struct moved_entry *prepare_entry(struct diff_options *o,
+					 int line_no)
+{
+	struct moved_entry *ret = xmalloc(sizeof(*ret));
+	unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+	struct buffered_patch_line *l = &o->line_buffer[line_no];
+
+	ret->ent.hash = get_line_hash(l, ignore_ws);
+	ret->line = l;
+	ret->next_line = NULL;
+
+	return ret;
+}
+
 static char *quote_two(const char *one, const char *two)
 {
 	int need_one = quote_c_style(one, NULL, NULL, 1);
@@ -516,6 +615,135 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
+static void add_lines_to_move_detection(struct diff_options *o)
+{
+	struct moved_entry *prev_line;
+
+	int n;
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		int sign = 0;
+		struct hashmap *hm;
+		struct moved_entry *key;
+
+		switch (o->line_buffer[n].sign) {
+		case '+':
+			sign = '+';
+			hm = o->added_lines;
+			break;
+		case '-':
+			sign = '-';
+			hm = o->deleted_lines;
+			break;
+		case ' ':
+		default:
+			prev_line = NULL;
+			continue;
+		}
+
+		key = prepare_entry(o, n);
+		if (prev_line &&
+		    prev_line->line->sign == sign)
+			prev_line->next_line = key;
+
+		hashmap_add(hm, key);
+		prev_line = key;
+	}
+}
+
+static void mark_color_as_moved(struct diff_options *o)
+{
+	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	int pmb_nr = 0, pmb_alloc = 0;
+	int alt_flag = 0;
+	int n;
+
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		struct hashmap *hm = NULL;
+		struct moved_entry *key;
+		struct moved_entry *match = NULL;
+		struct buffered_patch_line *l = &o->line_buffer[n];
+		int i, lp, rp;
+
+		switch (l->sign) {
+		case '+':
+			hm = o->deleted_lines;
+			break;
+		case '-':
+			hm = o->added_lines;
+			break;
+		default:
+			alt_flag = 0; /* reset to standard, no-alt move color */
+			pmb_nr = 0; /* no running sets */
+			continue;
+		}
+
+		/* Check for any match to color it as a move. */
+		key = prepare_entry(o, n);
+		match = hashmap_get(hm, key, o);
+		free(key);
+		if (!match)
+			continue;
+
+		/* Check any potential block runs, advance each or nullify */
+		for (i = 0; i < pmb_nr; i++) {
+			struct moved_entry *p = pmb[i];
+			struct moved_entry *pnext = (p && p->next_line) ?
+					p->next_line : NULL;
+			if (pnext &&
+			    !buffered_patch_line_cmp(pnext->line, l, o)) {
+				pmb[i] = p->next_line;
+			} else {
+				pmb[i] = NULL;
+			}
+		}
+
+		/* Shrink the set to the remaining runs */
+		for (lp = 0, rp = pmb_nr - 1; lp <= rp;) {
+			while (lp < pmb_nr && pmb[lp])
+				lp ++;
+			/* lp points at the first NULL now */
+
+			while (rp > -1 && !pmb[rp])
+				rp--;
+			/* rp points at the last non-NULL */
+
+			if (lp < pmb_nr && rp > -1 && lp < rp) {
+				pmb[lp] = pmb[rp];
+				pmb[rp] = NULL;
+				rp--;
+				lp++;
+			}
+		}
+
+		if (rp > -1) {
+			/* Remember the number of running sets */
+			pmb_nr = rp + 1;
+		} else {
+			/* Toggle color */
+			alt_flag = (alt_flag + 1) % 2;
+
+			/* Build up a new set */
+			pmb_nr = 0;
+			for (; match; match = hashmap_get_next(hm, match)) {
+				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
+				pmb[pmb_nr++] = match;
+			}
+		}
+
+		switch (l->sign) {
+		case '+':
+			l->set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED + alt_flag);
+			break;
+		case '-':
+			l->set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED + alt_flag);
+			break;
+		default:
+			die("BUG: we should have continued earlier?");
+		}
+	}
+	free(pmb);
+}
+
 static void emit_buffered_patch_line(struct diff_options *o,
 				     struct buffered_patch_line *e)
 {
@@ -3514,6 +3742,8 @@ void diff_setup(struct diff_options *options)
 	options->line_buffer = NULL;
 	options->line_buffer_nr = 0;
 	options->line_buffer_alloc = 0;
+
+	options->color_moved = diff_color_moved_default;
 }
 
 void diff_setup_done(struct diff_options *options)
@@ -3623,6 +3853,9 @@ void diff_setup_done(struct diff_options *options)
 
 	if (DIFF_OPT_TST(options, FOLLOW_RENAMES) && options->pathspec.nr != 1)
 		die(_("--follow requires exactly one pathspec"));
+
+	if (!options->use_color || external_diff())
+		options->color_moved = 0;
 }
 
 static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val)
@@ -4047,6 +4280,10 @@ int diff_opt_parse(struct diff_options *options,
 	}
 	else if (!strcmp(arg, "--no-color"))
 		options->use_color = 0;
+	else if (!strcmp(arg, "--color-moved"))
+		options->color_moved = 1;
+	else if (!strcmp(arg, "--no-color-moved"))
+		options->color_moved = 0;
 	else if (!strcmp(arg, "--color-words")) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
@@ -4852,16 +5089,19 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 {
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
-	/*
-	 * For testing purposes we want to make sure the diff machinery
-	 * works completely with the buffer. If there is anything emitted
-	 * outside the emit_buffered_patch_line, then the order is screwed
-	 * up and the tests will fail.
-	 *
-	 * TODO (later in this series):
-	 * We'll unset this flag in a later patch.
-	 */
-	o->use_buffer = 1;
+
+	if (o->color_moved) {
+		unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+		o->use_buffer = 1;
+		o->deleted_lines = xmallocz(sizeof(*o->deleted_lines));
+		o->added_lines = xmallocz(sizeof(*o->added_lines));
+		hashmap_init(o->deleted_lines, ignore_ws ?
+			(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+			(hashmap_cmp_fn)moved_entry_cmp, 0);
+		hashmap_init(o->added_lines, ignore_ws ?
+			(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+			(hashmap_cmp_fn)moved_entry_cmp, 0);
+	}
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
@@ -4870,6 +5110,11 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
+		if (o->color_moved) {
+			add_lines_to_move_detection(o);
+			mark_color_as_moved(o);
+		}
+
 		for (i = 0; i < o->line_buffer_nr; i++)
 			emit_buffered_patch_line(o, &o->line_buffer[i]);
 
@@ -4958,6 +5203,7 @@ void diff_flush(struct diff_options *options)
 		if (!options->file)
 			die_errno("Could not open /dev/null");
 		options->close_file = 1;
+		options->color_moved = 0;
 		for (i = 0; i < q->nr; i++) {
 			struct diff_filepair *p = q->queue[i];
 			if (check_pair_status(p))
diff --git a/diff.h b/diff.h
index 64bc9bcd8c..b8b2a33ccc 100644
--- a/diff.h
+++ b/diff.h
@@ -7,6 +7,7 @@
 #include "tree-walk.h"
 #include "pathspec.h"
 #include "object.h"
+#include "hashmap.h"
 
 struct rev_info;
 struct diff_options;
@@ -227,6 +228,10 @@ struct diff_options {
 
 	struct buffered_patch_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
+
+	int color_moved;
+	struct hashmap *deleted_lines;
+	struct hashmap *added_lines;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
@@ -243,7 +248,11 @@ enum color_diff {
 	DIFF_FILE_NEW = 5,
 	DIFF_COMMIT = 6,
 	DIFF_WHITESPACE = 7,
-	DIFF_FUNCINFO = 8
+	DIFF_FUNCINFO = 8,
+	DIFF_FILE_OLD_MOVED = 9,
+	DIFF_FILE_OLD_MOVED_ALT = 10,
+	DIFF_FILE_NEW_MOVED = 11,
+	DIFF_FILE_NEW_MOVED_ALT = 12
 };
 const char *diff_get_color(int diff_use_color, enum color_diff ix);
 #define diff_get_color_opt(o, ix) \
diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh
index 289806d0c7..232d9ad55e 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -972,4 +972,233 @@ test_expect_success 'option overrides diff.wsErrorHighlight' '
 
 '
 
+test_expect_success 'detect moved code, complete file' '
+	git reset --hard &&
+	cat <<-\EOF >test.c &&
+	#include<stdio.h>
+	main()
+	{
+	printf("Hello World");
+	}
+	EOF
+	git add test.c &&
+	git commit -m "add main function" &&
+	git mv test.c main.c &&
+	git diff HEAD --color-moved --no-renames | test_decode_color >actual &&
+	cat >expected <<-\EOF &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>new file mode 100644<RESET>
+	<BOLD>index 0000000..a986c57<RESET>
+	<BOLD>--- /dev/null<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -0,0 +1,5 @@<RESET>
+	<BGREEN>+<RESET><BGREEN>#include<stdio.h><RESET>
+	<BGREEN>+<RESET><BGREEN>main()<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BGREEN>+<RESET><BGREEN>printf("Hello World");<RESET>
+	<BGREEN>+<RESET><BGREEN>}<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>deleted file mode 100644<RESET>
+	<BOLD>index a986c57..0000000<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ /dev/null<RESET>
+	<CYAN>@@ -1,5 +0,0 @@<RESET>
+	<BRED>-#include<stdio.h><RESET>
+	<BRED>-main()<RESET>
+	<BRED>-{<RESET>
+	<BRED>-printf("Hello World");<RESET>
+	<BRED>-}<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
+test_expect_success 'detect moved code, inside file' '
+	git reset --hard &&
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			if (!u->is_allowed_foo)
+				return;
+			foo(u);
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git add main.c test.c &&
+	git commit -m "add main and test file" &&
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			if (!u->is_allowed_foo)
+				return;
+			foo(u);
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>index 27a619c..7cf9336 100644<RESET>
+	<BOLD>--- a/main.c<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET>
+	 printf("World\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BRED>-int secure_foo(struct user *u)<RESET>
+	<BRED>-{<RESET>
+	<BRED>-if (!u->is_allowed_foo)<RESET>
+	<BRED>-return;<RESET>
+	<BRED>-foo(u);<RESET>
+	<BRED>-}<RESET>
+	<BRED>-<RESET>
+	 int main()<RESET>
+	 {<RESET>
+	 foo();<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>index 1dc1d85..e34eb69 100644<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ b/test.c<RESET>
+	<CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET>
+	 printf("Hello World, but different\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET>
+	<BGREEN>+<RESET><BGREEN>return;<RESET>
+	<BGREEN>+<RESET><BGREEN>foo(u);<RESET>
+	<BGREEN>+<RESET><BGREEN>}<RESET>
+	<BGREEN>+<RESET>
+	 int another_function()<RESET>
+	 {<RESET>
+	 bar();<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
+test_expect_success 'detect permutations inside moved code, ' '
+	# reusing the move example from last test:
+	cat <<-\EOF >main.c &&
+		#include<stdio.h>
+		int stuff()
+		{
+			printf("Hello ");
+			printf("World\n");
+		}
+
+		int main()
+		{
+			foo();
+		}
+	EOF
+	cat <<-\EOF >test.c &&
+		#include<stdio.h>
+		int bar()
+		{
+			printf("Hello World, but different\n");
+		}
+
+		int secure_foo(struct user *u)
+		{
+			foo(u);
+			if (!u->is_allowed_foo)
+				return;
+		}
+
+		int another_function()
+		{
+			bar();
+		}
+	EOF
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/main.c b/main.c<RESET>
+	<BOLD>index 27a619c..7cf9336 100644<RESET>
+	<BOLD>--- a/main.c<RESET>
+	<BOLD>+++ b/main.c<RESET>
+	<CYAN>@@ -5,13 +5,6 @@<RESET> <RESET>printf("Hello ");<RESET>
+	 printf("World\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BRED>-int secure_foo(struct user *u)<RESET>
+	<BRED>-{<RESET>
+	<BOLD;RED>-if (!u->is_allowed_foo)<RESET>
+	<BOLD;RED>-return;<RESET>
+	<BRED>-foo(u);<RESET>
+	<BOLD;RED>-}<RESET>
+	<BOLD;RED>-<RESET>
+	 int main()<RESET>
+	 {<RESET>
+	 foo();<RESET>
+	<BOLD>diff --git a/test.c b/test.c<RESET>
+	<BOLD>index 1dc1d85..2bedec9 100644<RESET>
+	<BOLD>--- a/test.c<RESET>
+	<BOLD>+++ b/test.c<RESET>
+	<CYAN>@@ -4,6 +4,13 @@<RESET> <RESET>int bar()<RESET>
+	 printf("Hello World, but different\n");<RESET>
+	 }<RESET>
+	 <RESET>
+	<BGREEN>+<RESET><BGREEN>int secure_foo(struct user *u)<RESET>
+	<BGREEN>+<RESET><BGREEN>{<RESET>
+	<BOLD;GREEN>+<RESET><BOLD;GREEN>foo(u);<RESET>
+	<BGREEN>+<RESET><BGREEN>if (!u->is_allowed_foo)<RESET>
+	<BGREEN>+<RESET><BGREEN>return;<RESET>
+	<BOLD;GREEN>+<RESET><BOLD;GREEN>}<RESET>
+	<BOLD;GREEN>+<RESET>
+	 int another_function()<RESET>
+	 {<RESET>
+	 bar();<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
 test_done

diff.c, diff.h, submodule.c, submodule.h

diff --git a/diff.c b/diff.c
index 690794aeb8..7c8d6a5d12 100644
--- a/diff.c
+++ b/diff.c
@@ -516,8 +516,8 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-static void emit_line(struct diff_options *o, const char *set, const char *reset,
-		      int add_line_prefix, int sign, const char *line, int len)
+void emit_line(struct diff_options *o, const char *set, const char *reset,
+	       int add_line_prefix, int sign, const char *line, int len)
 {
 	int has_trailing_newline, has_trailing_carriage_return;
 	FILE *file = o->file;
@@ -547,10 +547,10 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
 		fputc('\n', file);
 }
 
-static void emit_line_fmt(struct diff_options *o,
-			  const char *set, const char *reset,
-			  int add_line_prefix,
-			  const char *fmt, ...)
+void emit_line_fmt(struct diff_options *o,
+		   const char *set, const char *reset,
+		   int add_line_prefix,
+		   const char *fmt, ...)
 {
 	struct strbuf sb = STRBUF_INIT;
 	va_list ap;
@@ -2386,8 +2386,7 @@ static void builtin_diff(const char *name_a,
 	    (!two->mode || S_ISGITLINK(two->mode))) {
 		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->path ? one->path : two->path,
-				line_prefix,
+		show_submodule_summary(o, one->path ? one->path : two->path,
 				&one->oid, &two->oid,
 				two->dirty_submodule,
 				meta, del, add, reset);
@@ -2397,11 +2396,10 @@ static void builtin_diff(const char *name_a,
 		   (!two->mode || S_ISGITLINK(two->mode))) {
 		const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
 		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
-		show_submodule_inline_diff(o->file, one->path ? one->path : two->path,
-				line_prefix,
+		show_submodule_inline_diff(o, one->path ? one->path : two->path,
 				&one->oid, &two->oid,
 				two->dirty_submodule,
-				meta, del, add, reset, o);
+				meta, del, add, reset);
 		return;
 	}
 
diff --git a/diff.h b/diff.h
index 5be1ee77a7..6e14100102 100644
--- a/diff.h
+++ b/diff.h
@@ -188,6 +188,11 @@ struct diff_options {
 	int diff_path_counter;
 };
 
+void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
+		   int add_line_prefix, const char *fmt, ...);
+void emit_line(struct diff_options *o, const char *set, const char *reset,
+	       int add_line_prefix, int sign, const char *line, int len);
+
 enum color_diff {
 	DIFF_RESET = 0,
 	DIFF_CONTEXT = 1,
diff --git a/submodule.c b/submodule.c
index d3299e29c0..5996ebca44 100644
--- a/submodule.c
+++ b/submodule.c
@@ -362,8 +362,8 @@ static int prepare_submodule_summary(struct rev_info *rev, const char *path,
 	return prepare_revision_walk(rev);
 }
 
-static void print_submodule_summary(struct rev_info *rev, FILE *f,
-		const char *line_prefix,
+static void print_submodule_summary(struct rev_info *rev,
+		struct diff_options *o,
 		const char *del, const char *add, const char *reset)
 {
 	static const char format[] = "  %m %s";
@@ -375,18 +375,12 @@ static void print_submodule_summary(struct rev_info *rev, FILE *f,
 		ctx.date_mode = rev->date_mode;
 		ctx.output_encoding = get_log_output_encoding();
 		strbuf_setlen(&sb, 0);
-		strbuf_addstr(&sb, line_prefix);
-		if (commit->object.flags & SYMMETRIC_LEFT) {
-			if (del)
-				strbuf_addstr(&sb, del);
-		}
-		else if (add)
-			strbuf_addstr(&sb, add);
 		format_commit_message(commit, format, &sb, &ctx);
-		if (reset)
-			strbuf_addstr(&sb, reset);
 		strbuf_addch(&sb, '\n');
-		fprintf(f, "%s", sb.buf);
+		if (commit->object.flags & SYMMETRIC_LEFT)
+			emit_line(o, del, reset, 1, 0, sb.buf, sb.len);
+		else if (add)
+			emit_line(o, add, reset, 1, 0, sb.buf, sb.len);
 	}
 	strbuf_release(&sb);
 }
@@ -413,8 +407,7 @@ void prepare_submodule_repo_env(struct argv_array *out)
  * attempt to lookup both the left and right commits and put them into the
  * left and right pointers.
  */
-static void show_submodule_header(FILE *f, const char *path,
-		const char *line_prefix,
+static void show_submodule_header(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *reset,
@@ -426,11 +419,11 @@ static void show_submodule_header(FILE *f, const char *path,
 	int fast_forward = 0, fast_backward = 0;
 
 	if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED)
-		fprintf(f, "%sSubmodule %s contains untracked content\n",
-			line_prefix, path);
+		emit_line_fmt(o, NULL, NULL, 1,
+			      "Submodule %s contains untracked content\n", path);
 	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED)
-		fprintf(f, "%sSubmodule %s contains modified content\n",
-			line_prefix, path);
+		emit_line_fmt(o, NULL, NULL, 1,
+			      "Submodule %s contains modified content\n", path);
 
 	if (is_null_oid(one))
 		message = "(new submodule)";
@@ -472,21 +465,20 @@ static void show_submodule_header(FILE *f, const char *path,
 	}
 
 output_header:
-	strbuf_addf(&sb, "%s%sSubmodule %s ", line_prefix, meta, path);
+	strbuf_addf(&sb, "Submodule %s ", path);
 	strbuf_add_unique_abbrev(&sb, one->hash, DEFAULT_ABBREV);
 	strbuf_addstr(&sb, (fast_backward || fast_forward) ? ".." : "...");
 	strbuf_add_unique_abbrev(&sb, two->hash, DEFAULT_ABBREV);
 	if (message)
-		strbuf_addf(&sb, " %s%s\n", message, reset);
+		strbuf_addf(&sb, " %s\n", message);
 	else
-		strbuf_addf(&sb, "%s:%s\n", fast_backward ? " (rewind)" : "", reset);
-	fwrite(sb.buf, sb.len, 1, f);
+		strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : "");
+	emit_line(o, meta, reset, 1, 0,  sb.buf, sb.len);
 
 	strbuf_release(&sb);
 }
 
-void show_submodule_summary(FILE *f, const char *path,
-		const char *line_prefix,
+void show_submodule_summary(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *del, const char *add, const char *reset)
@@ -495,7 +487,7 @@ void show_submodule_summary(FILE *f, const char *path,
 	struct commit *left = NULL, *right = NULL;
 	struct commit_list *merge_bases = NULL;
 
-	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
+	show_submodule_header(o, path, one, two, dirty_submodule,
 			      meta, reset, &left, &right, &merge_bases);
 
 	/*
@@ -508,11 +500,12 @@ void show_submodule_summary(FILE *f, const char *path,
 
 	/* Treat revision walker failure the same as missing commits */
 	if (prepare_submodule_summary(&rev, path, left, right, merge_bases)) {
-		fprintf(f, "%s(revision walker failed)\n", line_prefix);
+		const char *error = "(revision walker failed)\n";
+		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
 		goto out;
 	}
 
-	print_submodule_summary(&rev, f, line_prefix, del, add, reset);
+	print_submodule_summary(&rev, o, del, add, reset);
 
 out:
 	if (merge_bases)
@@ -521,20 +514,18 @@ void show_submodule_summary(FILE *f, const char *path,
 	clear_commit_marks(right, ~0);
 }
 
-void show_submodule_inline_diff(FILE *f, const char *path,
-		const char *line_prefix,
+void show_submodule_inline_diff(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
-		const char *del, const char *add, const char *reset,
-		const struct diff_options *o)
+		const char *del, const char *add, const char *reset)
 {
 	const struct object_id *old = &empty_tree_oid, *new = &empty_tree_oid;
 	struct commit *left = NULL, *right = NULL;
 	struct commit_list *merge_bases = NULL;
-	struct strbuf submodule_dir = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
+	struct strbuf sb = STRBUF_INIT;
 
-	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
+	show_submodule_header(o, path, one, two, dirty_submodule,
 			      meta, reset, &left, &right, &merge_bases);
 
 	/* We need a valid left and right commit to display a difference */
@@ -547,15 +538,14 @@ void show_submodule_inline_diff(FILE *f, const char *path,
 	if (right)
 		new = two;
 
-	fflush(f);
 	cp.git_cmd = 1;
 	cp.dir = path;
-	cp.out = dup(fileno(f));
+	cp.out = -1;
 	cp.no_stdin = 1;
 
 	/* TODO: other options may need to be passed here. */
 	argv_array_push(&cp.args, "diff");
-	argv_array_pushf(&cp.args, "--line-prefix=%s", line_prefix);
+	argv_array_pushf(&cp.args, "--line-prefix=%s", diff_line_prefix(o));
 	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
 		argv_array_pushf(&cp.args, "--src-prefix=%s%s/",
 				 o->b_prefix, path);
@@ -578,11 +568,21 @@ void show_submodule_inline_diff(FILE *f, const char *path,
 		argv_array_push(&cp.args, oid_to_hex(new));
 
 	prepare_submodule_repo_env(&cp.env_array);
-	if (run_command(&cp))
-		fprintf(f, "(diff failed)\n");
+	if (start_command(&cp)) {
+		const char *error = "(diff failed)\n";
+		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
+	}
+
+	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
+		emit_line(o, NULL, NULL, 1, 0, sb.buf, sb.len);
+
+	if (finish_command(&cp)) {
+		const char *error = "(diff failed)\n";
+		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
+	}
 
 done:
-	strbuf_release(&submodule_dir);
+	strbuf_release(&sb);
 	if (merge_bases)
 		free_commit_list(merge_bases);
 	if (left)
diff --git a/submodule.h b/submodule.h
index 1277480add..9df0a3aea2 100644
--- a/submodule.h
+++ b/submodule.h
@@ -53,17 +53,14 @@ extern int parse_submodule_update_strategy(const char *value,
 		struct submodule_update_strategy *dst);
 extern const char *submodule_strategy_to_string(const struct submodule_update_strategy *s);
 extern void handle_ignore_submodules_arg(struct diff_options *, const char *);
-extern void show_submodule_summary(FILE *f, const char *path,
-		const char *line_prefix,
+extern void show_submodule_summary(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *del, const char *add, const char *reset);
-extern void show_submodule_inline_diff(FILE *f, const char *path,
-		const char *line_prefix,
+extern void show_submodule_inline_diff(struct diff_options *o, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
-		const char *del, const char *add, const char *reset,
-		const struct diff_options *opt);
+		const char *del, const char *add, const char *reset);
 extern void set_config_fetch_recurse_submodules(int value);
 extern void set_config_update_recurse_submodules(int value);
 /* Check if we want to update any submodule.*/

diff.c, diff.h, submodule.c

diff --git a/diff.c b/diff.c
index 964b5cb5a7..34482a6a09 100644
--- a/diff.c
+++ b/diff.c
@@ -516,15 +516,33 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-void emit_line(struct diff_options *o, const char *set, const char *reset,
-	       int add_line_prefix, int sign, const char *line, int len)
+void emit_line(struct diff_options *o,
+	       const char *set, const char *reset,
+	       int add_line_prefix, int markup_ws,
+	       int sign, const char *line, int len)
 {
+	const char *ws;
 	int has_trailing_newline, has_trailing_carriage_return;
 	FILE *file = o->file;
 
 	if (add_line_prefix)
 		fputs(diff_line_prefix(o), file);
 
+	if (markup_ws) {
+		ws = diff_get_color(o->use_color, DIFF_WHITESPACE);
+
+		if (set)
+			fputs(set, file);
+		if (sign)
+			fputc(sign, file);
+		if (reset)
+			fputs(reset, file);
+		ws = diff_get_color(o->use_color, DIFF_WHITESPACE);
+		ws_check_emit(line, len, o->ws_rule,
+			      file, set, reset, ws);
+		return;
+	}
+
 	has_trailing_newline = (len > 0 && line[len-1] == '\n');
 	if (has_trailing_newline)
 		len--;
@@ -558,7 +576,7 @@ void emit_line_fmt(struct diff_options *o,
 	strbuf_vaddf(&sb, fmt, ap);
 	va_end(ap);
 
-	emit_line(o, set, reset, add_line_prefix, 0, sb.buf, sb.len);
+	emit_line(o, set, reset, add_line_prefix, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
@@ -590,16 +608,15 @@ static void emit_line_checked(const char *reset,
 	}
 
 	if (!ws)
-		emit_line(ecbdata->opt, set, reset, 1, sign, line, len);
+		emit_line(ecbdata->opt, set, reset, 1, 0, sign, line, len);
 	else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len))
 		/* Blank line at EOF - paint '+' as well */
-		emit_line(ecbdata->opt, ws, reset, 1, sign, line, len);
+		emit_line(ecbdata->opt, ws, reset, 1, 1, sign, line, len);
 	else {
 		/* Emit just the prefix, then the rest. */
-		emit_line(ecbdata->opt, set, reset, 1, sign, "", 0);
-		ws_check_emit(line, len, ecbdata->ws_rule,
-			      ecbdata->opt->file, set, reset, ws);
+		emit_line(ecbdata->opt, set, reset, 1, 1, sign, line, len);
 	}
+
 }
 
 static void emit_add_line(const char *reset,
@@ -646,7 +663,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	if (len < 10 ||
 	    memcmp(line, atat, 2) ||
 	    !(ep = memmem(line + 2, len - 2, atat, 2))) {
-		emit_line(ecbdata->opt, context, reset, 1, 0, line, len);
+		emit_line(ecbdata->opt, context, reset, 1, 0, 0, line, len);
 		return;
 	}
 	ep += 2; /* skip over @@ */
@@ -682,7 +699,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	strbuf_add(&msgbuf, line + len, org_len - len);
 	strbuf_complete_line(&msgbuf);
 
-	emit_line(ecbdata->opt, "", "", 1, 0, msgbuf.buf, msgbuf.len);
+	emit_line(ecbdata->opt, "", "", 1, 0, 0, msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
 
@@ -755,7 +772,7 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		static const char *nneof = "\\ No newline at end of file\n";
 		const char *context = diff_get_color(ecb->color_diff,
 						     DIFF_CONTEXT);
-		emit_line(ecb->opt, context, reset, 1, 0,
+		emit_line(ecb->opt, context, reset, 1, 0, 0,
 			    nneof, strlen(nneof));
 		strbuf_release(&sb);
 	}
@@ -831,7 +848,7 @@ static void emit_rewrite_diff(const char *name_a,
 	strbuf_addstr(&out, " +");
 	add_line_count(&out, lc_b);
 	strbuf_addstr(&out, " @@\n");
-	emit_line(o, fraginfo, reset, 1, 0, out.buf, out.len);
+	emit_line(o, fraginfo, reset, 1, 0, 0, out.buf, out.len);
 	strbuf_release(&out);
 
 	if (lc_a && !o->irreversible_delete)
@@ -904,7 +921,7 @@ static int fn_out_diff_words_write_helper(struct diff_options *o,
 	while (count) {
 		char *p = memchr(buf, '\n', count);
 		if (print)
-			emit_line(o, NULL, NULL, 1, 0, "", 0);
+			emit_line(o, NULL, NULL, 1, 0, 0, "", 0);
 
 		if (p != buf) {
 			const char *reset = st_el->color && *st_el->color ?
@@ -913,14 +930,14 @@ static int fn_out_diff_words_write_helper(struct diff_options *o,
 			strbuf_add(&sb, buf, p ? p - buf : count);
 			strbuf_addstr(&sb, st_el->suffix);
 			emit_line(o, st_el->color, reset,
-				  0, 0, sb.buf, sb.len);
+				  0, 0, 0, sb.buf, sb.len);
 			strbuf_reset(&sb);
 		}
 		if (!p)
 			goto out;
 
 		strbuf_addstr(&sb, newline);
-		emit_line(o, NULL, NULL, 0, 0, sb.buf, sb.len);
+		emit_line(o, NULL, NULL, 0, 0, 0, sb.buf, sb.len);
 		strbuf_reset(&sb);
 		count -= p + 1 - buf;
 		buf = p + 1;
@@ -1135,7 +1152,7 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	if (diff_words->current_plus != diff_words->plus.text.ptr +
 			diff_words->plus.text.size) {
 		if (color_words_output_graph_prefix(diff_words))
-			emit_line(diff_words->opt, NULL, NULL, 1, 0, "", 0);
+			emit_line(diff_words->opt, NULL, NULL, 1, 0, 0, "", 0);
 		fn_out_diff_words_write_helper(diff_words->opt,
 			&style->ctx, style->newline,
 			diff_words->plus.text.ptr + diff_words->plus.text.size
@@ -1294,7 +1311,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 	o->found_changes = 1;
 
 	if (ecbdata->header) {
-		emit_line(o, NULL, NULL, 0, 0,
+		emit_line(o, NULL, NULL, 0, 0, 0,
 			  ecbdata->header->buf, ecbdata->header->len);
 		strbuf_release(ecbdata->header);
 		ecbdata->header = NULL;
@@ -1347,8 +1364,8 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		}
 		diff_words_flush(ecbdata);
 		if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) {
-			emit_line(o, context, reset, 1, 0, line, len);
-			emit_line(o, NULL, NULL, 0, 0, "~\n", 2);
+			emit_line(o, context, reset, 1, 0, 0, line, len);
+			emit_line(o, NULL, NULL, 0, 0, 0, "~\n", 2);
 		} else {
 			/*
 			 * Skip the prefix character, if any.  With
@@ -1359,7 +1376,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 			      line++;
 			      len--;
 			}
-			emit_line(o, context, reset, 1, 0, line, len);
+			emit_line(o, context, reset, 1, 0, 0, line, len);
 		}
 		return;
 	}
@@ -1382,7 +1399,7 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		/* incomplete line at the end */
 		ecbdata->lno_in_preimage++;
 		emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT),
-			  reset, 1, 0, line, len);
+			  reset, 1, 0, 0, line, len);
 		break;
 	}
 }
@@ -1571,7 +1588,7 @@ void print_stat_summary_0(struct diff_options *options, int files,
 	if (!files) {
 		assert(insertions == 0 && deletions == 0);
 		strbuf_addstr(&sb, " 0 files changed");
-		emit_line(options, NULL, NULL, 1, 0, sb.buf, sb.len);
+		emit_line(options, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 		return;
 	}
 
@@ -1599,7 +1616,7 @@ void print_stat_summary_0(struct diff_options *options, int files,
 			    deletions);
 	}
 	strbuf_addch(&sb, '\n');
-	emit_line(options, NULL, NULL, 1, 0, sb.buf, sb.len);
+	emit_line(options, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
@@ -1783,7 +1800,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 			strbuf_addf(&out, " %*s", number_width, "Bin");
 			if (!added && !deleted) {
 				strbuf_addch(&out, '\n');
-				emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+				emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 				strbuf_reset(&out);
 				continue;
 			}
@@ -1793,14 +1810,14 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 			strbuf_addf(&out, "%s%"PRIuMAX"%s",
 				add_c, added, reset);
 			strbuf_addstr(&out, " bytes\n");
-			emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+			emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 			strbuf_reset(&out);
 			continue;
 		}
 		else if (file->is_unmerged) {
 			show_name(&out, prefix, name, len);
 			strbuf_addstr(&out, " Unmerged\n");
-			emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+			emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 			strbuf_reset(&out);
 			continue;
 		}
@@ -1831,7 +1848,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		show_graph(&out, '+', add, add_c, reset);
 		show_graph(&out, '-', del, del_c, reset);
 		strbuf_addch(&out, '\n');
-		emit_line(options, NULL, NULL, 1, 0, out.buf, out.len);
+		emit_line(options, NULL, NULL, 1, 0, 0, out.buf, out.len);
 		strbuf_reset(&out);
 	}
 
@@ -1853,7 +1870,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
 		if (i < count)
 			continue;
 		if (!extra_shown)
-			emit_line(options, NULL, NULL, 1, 0,
+			emit_line(options, NULL, NULL, 1, 0, 0,
 				  " ...\n", strlen(" ...\n"));
 		extra_shown = 1;
 	}
@@ -2207,7 +2224,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 		fprintf(data->o->file, "%s%s:%d: %s.\n",
 			line_prefix, data->filename, data->lineno, err);
 		free(err);
-		emit_line(data->o, set, reset, 1, 0, line, 1);
+		emit_line(data->o, set, reset, 1, 0, 0, line, 1);
 		ws_check_emit(line + 1, len - 1, data->ws_rule,
 			      data->o->file, set, reset, ws);
 	} else if (line[0] == ' ') {
@@ -2303,9 +2320,9 @@ static void emit_binary_diff_body(struct diff_options *o,
 		line[len++] = '\n';
 		line[len] = '\0';
 
-		emit_line(o, NULL, NULL, 1, 0, line, len);
+		emit_line(o, NULL, NULL, 1, 0, 0, line, len);
 	}
-	emit_line(o, NULL, NULL, 1, 0, "\n", 1);
+	emit_line(o, NULL, NULL, 1, 0, 0, "\n", 1);
 	free(data);
 }
 
@@ -2314,7 +2331,7 @@ static void emit_binary_diff(struct diff_options *o,
 {
 	const char *s = "GIT binary patch\n";
 	const int len = strlen(s);
-	emit_line(o, NULL, NULL, 1, 0, s, len);
+	emit_line(o, NULL, NULL, 1, 0, 0, s, len);
 	emit_binary_diff_body(o, one, two);
 	emit_binary_diff_body(o, two, one);
 }
@@ -2457,7 +2474,7 @@ 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))) {
-			emit_line(o, NULL, NULL, 0, 0, header.buf, header.len);
+			emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
@@ -2467,7 +2484,7 @@ static void builtin_diff(const char *name_a,
 	}
 
 	if (o->irreversible_delete && lbl[1][0] == '/') {
-		emit_line(o, NULL, NULL, 0, 0, header.buf, header.len);
+		emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 		strbuf_reset(&header);
 		goto free_ab_and_return;
 	} else if (!DIFF_OPT_TST(o, TEXT) &&
@@ -2478,11 +2495,11 @@ static void builtin_diff(const char *name_a,
 		    !DIFF_OPT_TST(o, BINARY)) {
 			if (!oidcmp(&one->oid, &two->oid)) {
 				if (must_show_header)
-					emit_line(o, NULL, NULL, 0, 0,
+					emit_line(o, NULL, NULL, 0, 0, 0,
 						  header.buf, header.len);
 				goto free_ab_and_return;
 			}
-			emit_line(o, NULL, NULL, 0, 0,
+			emit_line(o, NULL, NULL, 0, 0, 0,
 				  header.buf, header.len);
 			emit_line_fmt(o, NULL, NULL, 1,
 				      "Binary files %s and %s differ\n",
@@ -2495,11 +2512,11 @@ static void builtin_diff(const char *name_a,
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
 			if (must_show_header)
-				emit_line(o, NULL, NULL, 0, 0,
+				emit_line(o, NULL, NULL, 0, 0, 0,
 					  header.buf, header.len);
 			goto free_ab_and_return;
 		}
-		emit_line(o, NULL, NULL, 0, 0,
+		emit_line(o, NULL, NULL, 0, 0, 0,
 			  header.buf, header.len);
 		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
@@ -2519,7 +2536,7 @@ static void builtin_diff(const char *name_a,
 		const struct userdiff_funcname *pe;
 
 		if (must_show_header) {
-			emit_line(o, NULL, NULL, 0, 0, header.buf, header.len);
+			emit_line(o, NULL, NULL, 0, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 		}
 
@@ -2536,6 +2553,7 @@ static void builtin_diff(const char *name_a,
 		ecbdata.label_path = lbl;
 		ecbdata.color_diff = want_color(o->use_color);
 		ecbdata.ws_rule = whitespace_rule(name_b);
+		o->ws_rule = ecbdata.ws_rule;
 		if (ecbdata.ws_rule & WS_BLANK_AT_EOF)
 			check_blank_at_eof(&mf1, &mf2, &ecbdata);
 		ecbdata.opt = o;
@@ -4510,7 +4528,7 @@ static void show_file_mode_name(struct diff_options *opt, const char *newdelete,
 
 	quote_c_style(fs->path, &sb, NULL, 0);
 	strbuf_addch(&sb, '\n');
-	emit_line(opt, NULL, NULL, 1, 0, sb.buf, sb.len);
+	emit_line(opt, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 	strbuf_release(&sb);
 }
 
@@ -4562,7 +4580,7 @@ static void diff_summary(struct diff_options *opt, struct diff_filepair *p)
 			strbuf_addstr(&sb, " rewrite ");
 			quote_c_style(p->two->path, &sb, NULL, 0);
 			strbuf_addf(&sb, " (%d%%)\n", similarity_index(p));
-			emit_line(opt, NULL, NULL, 1, 0, sb.buf, sb.len);
+			emit_line(opt, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 		}
 		show_mode_change(opt, p, !p->score);
 		break;
@@ -4869,10 +4887,10 @@ void diff_flush(struct diff_options *options)
 			term[0] = options->line_termination;
 			term[1] = '\0';
 
-			emit_line(options, NULL, NULL, 1, 0, term, !!term[0]);
+			emit_line(options, NULL, NULL, 1, 0, 0, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
-				emit_line(options, NULL, NULL, 0, 0,
+				emit_line(options, NULL, NULL, 0, 0, 0,
 					  options->stat_sep,
 					  strlen(options->stat_sep));
 			}
diff --git a/diff.h b/diff.h
index b75b0d7283..267acf1980 100644
--- a/diff.h
+++ b/diff.h
@@ -186,12 +186,14 @@ struct diff_options {
 	void *output_prefix_data;
 
 	int diff_path_counter;
+
+	unsigned ws_rule;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,
 		   int add_line_prefix, const char *fmt, ...);
 void emit_line(struct diff_options *o, const char *set, const char *reset,
-	       int add_line_prefix, int sign, const char *line, int len);
+	       int add_line_prefix, int markup_ws, int sign, const char *line, int len);
 
 enum color_diff {
 	DIFF_RESET = 0,
diff --git a/submodule.c b/submodule.c
index 5996ebca44..868f913971 100644
--- a/submodule.c
+++ b/submodule.c
@@ -378,9 +378,9 @@ static void print_submodule_summary(struct rev_info *rev,
 		format_commit_message(commit, format, &sb, &ctx);
 		strbuf_addch(&sb, '\n');
 		if (commit->object.flags & SYMMETRIC_LEFT)
-			emit_line(o, del, reset, 1, 0, sb.buf, sb.len);
+			emit_line(o, del, reset, 1, 0, 0, sb.buf, sb.len);
 		else if (add)
-			emit_line(o, add, reset, 1, 0, sb.buf, sb.len);
+			emit_line(o, add, reset, 1, 0, 0, sb.buf, sb.len);
 	}
 	strbuf_release(&sb);
 }
@@ -473,7 +473,7 @@ static void show_submodule_header(struct diff_options *o, const char *path,
 		strbuf_addf(&sb, " %s\n", message);
 	else
 		strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : "");
-	emit_line(o, meta, reset, 1, 0,  sb.buf, sb.len);
+	emit_line(o, meta, reset, 1, 0, 0, sb.buf, sb.len);
 
 	strbuf_release(&sb);
 }
@@ -501,7 +501,7 @@ void show_submodule_summary(struct diff_options *o, const char *path,
 	/* Treat revision walker failure the same as missing commits */
 	if (prepare_submodule_summary(&rev, path, left, right, merge_bases)) {
 		const char *error = "(revision walker failed)\n";
-		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 		goto out;
 	}
 
@@ -570,15 +570,15 @@ void show_submodule_inline_diff(struct diff_options *o, const char *path,
 	prepare_submodule_repo_env(&cp.env_array);
 	if (start_command(&cp)) {
 		const char *error = "(diff failed)\n";
-		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 	}
 
 	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
-		emit_line(o, NULL, NULL, 1, 0, sb.buf, sb.len);
+		emit_line(o, NULL, NULL, 1, 0, 0, sb.buf, sb.len);
 
 	if (finish_command(&cp)) {
 		const char *error = "(diff failed)\n";
-		emit_line(o, NULL, NULL, 1, 0, error, strlen(error));
+		emit_line(o, NULL, NULL, 1, 0, 0, error, strlen(error));
 	}
 
 done:

diff --git a/diff.c b/diff.c
index 73e55b0c10..6c1886d495 100644
--- a/diff.c
+++ b/diff.c
@@ -532,11 +532,13 @@ static void emit_line_0(struct diff_options *o, const char *set, const char *res
 		len--;
 
 	if (len || sign) {
-		fputs(set, file);
+		if (set)
+			fputs(set, file);
 		if (sign)
 			fputc(sign, file);
 		fwrite(line, len, 1, file);
-		fputs(reset, file);
+		if (reset)
+			fputs(reset, file);
 	}
 	if (has_trailing_carriage_return)
 		fputc('\r', file);

diff.c, diff.h

diff --git a/diff.c b/diff.c
index 34482a6a09..1d8d1786fd 100644
--- a/diff.c
+++ b/diff.c
@@ -516,53 +516,85 @@ static void check_blank_at_eof(mmfile_t *mf1, mmfile_t *mf2,
 	ecbdata->blank_at_eof_in_postimage = (at - l2) + 1;
 }
 
-void emit_line(struct diff_options *o,
-	       const char *set, const char *reset,
-	       int add_line_prefix, int markup_ws,
-	       int sign, const char *line, int len)
+static void emit_buffered_patch_line(struct diff_options *o,
+				     struct buffered_patch_line *e)
 {
 	const char *ws;
 	int has_trailing_newline, has_trailing_carriage_return;
+	int len = e->len;
 	FILE *file = o->file;
 
-	if (add_line_prefix)
+	if (e->add_line_prefix)
 		fputs(diff_line_prefix(o), file);
 
-	if (markup_ws) {
+	switch (e->state) {
+	case BPL_EMIT_LINE_WS:
 		ws = diff_get_color(o->use_color, DIFF_WHITESPACE);
+		if (e->set)
+			fputs(e->set, file);
+		if (e->sign)
+			fputc(e->sign, file);
+		if (e->reset)
+			fputs(e->reset, file);
+		ws_check_emit(e->line, e->len, o->ws_rule,
+			      file, e->set, e->reset, ws);
+		return;
+	case BPL_EMIT_LINE_ASIS:
+		has_trailing_newline = (len > 0 && e->line[len-1] == '\n');
+		if (has_trailing_newline)
+			len--;
+		has_trailing_carriage_return = (len > 0 && e->line[len-1] == '\r');
+		if (has_trailing_carriage_return)
+			len--;
 
-		if (set)
-			fputs(set, file);
-		if (sign)
-			fputc(sign, file);
-		if (reset)
-			fputs(reset, file);
-		ws = diff_get_color(o->use_color, DIFF_WHITESPACE);
-		ws_check_emit(line, len, o->ws_rule,
-			      file, set, reset, ws);
+		if (len || e->sign) {
+			if (e->set)
+				fputs(e->set, file);
+			if (e->sign)
+				fputc(e->sign, file);
+			fwrite(e->line, len, 1, file);
+			if (e->reset)
+				fputs(e->reset, file);
+		}
+		if (has_trailing_carriage_return)
+			fputc('\r', file);
+		if (has_trailing_newline)
+			fputc('\n', file);
+		return;
+	case BPL_HANDOVER:
+		o->ws_rule = whitespace_rule(e->line); /*read from file, stored in line?*/
 		return;
+	default:
+		die("BUG: malformatted buffered patch line: '%d'", e->state);
 	}
+}
 
-	has_trailing_newline = (len > 0 && line[len-1] == '\n');
-	if (has_trailing_newline)
-		len--;
-	has_trailing_carriage_return = (len > 0 && line[len-1] == '\r');
-	if (has_trailing_carriage_return)
-		len--;
+static void append_buffered_patch_line(struct diff_options *o,
+				       struct buffered_patch_line *e)
+{
+	struct buffered_patch_line *f;
+	ALLOC_GROW(o->line_buffer,
+		   o->line_buffer_nr + 1,
+		   o->line_buffer_alloc);
+	f = &o->line_buffer[o->line_buffer_nr++];
 
-	if (len || sign) {
-		if (set)
-			fputs(set, file);
-		if (sign)
-			fputc(sign, file);
-		fwrite(line, len, 1, file);
-		if (reset)
-			fputs(reset, file);
-	}
-	if (has_trailing_carriage_return)
-		fputc('\r', file);
-	if (has_trailing_newline)
-		fputc('\n', file);
+	memcpy(f, e, sizeof(struct buffered_patch_line));
+	f->line = e->line ? xmemdupz(e->line, e->len) : NULL;
+}
+
+void emit_line(struct diff_options *o,
+	       const char *set, const char *reset,
+	       int add_line_prefix, int markup_ws,
+	       int sign, const char *line, int len)
+{
+	struct buffered_patch_line e = {set, reset, line,
+		len, sign, add_line_prefix,
+		markup_ws ? BPL_EMIT_LINE_WS : BPL_EMIT_LINE_ASIS};
+
+	if (o->use_buffer)
+		append_buffered_patch_line(o, &e);
+	else
+		emit_buffered_patch_line(o, &e);
 }
 
 void emit_line_fmt(struct diff_options *o,
@@ -1167,6 +1199,18 @@ static void diff_words_flush(struct emit_callback *ecbdata)
 	if (ecbdata->diff_words->minus.text.size ||
 	    ecbdata->diff_words->plus.text.size)
 		diff_words_show(ecbdata->diff_words);
+
+	if (ecbdata->diff_words->opt->line_buffer_nr) {
+		int i;
+		for (i = 0; i < ecbdata->diff_words->opt->line_buffer_nr; i++)
+			append_buffered_patch_line(ecbdata->opt,
+				&ecbdata->diff_words->opt->line_buffer[i]);
+
+		for (i = 0; i < ecbdata->diff_words->opt->line_buffer_nr; i++)
+			free((void*) ecbdata->diff_words->opt->line_buffer[i].line);
+
+		ecbdata->diff_words->opt->line_buffer_nr = 0;
+	}
 }
 
 static void diff_filespec_load_driver(struct diff_filespec *one)
@@ -1202,6 +1246,11 @@ static void init_diff_words_data(struct emit_callback *ecbdata,
 		xcalloc(1, sizeof(struct diff_words_data));
 	ecbdata->diff_words->type = o->word_diff;
 	ecbdata->diff_words->opt = o;
+
+	o->line_buffer = NULL;
+	o->line_buffer_nr = 0;
+	o->line_buffer_alloc = 0;
+
 	if (!o->word_regex)
 		o->word_regex = userdiff_word_regex(one);
 	if (!o->word_regex)
@@ -1236,6 +1285,7 @@ static void free_diff_words_data(struct emit_callback *ecbdata)
 {
 	if (ecbdata->diff_words) {
 		diff_words_flush(ecbdata);
+		free (ecbdata->diff_words->opt->line_buffer);
 		free (ecbdata->diff_words->opt);
 		free (ecbdata->diff_words->minus.text.ptr);
 		free (ecbdata->diff_words->minus.orig);
@@ -2574,6 +2624,13 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(v, NULL, 10);
 		if (o->word_diff)
 			init_diff_words_data(&ecbdata, o, one, two);
+		if (o->use_buffer) {
+			struct buffered_patch_line e = BUFFERED_PATCH_LINE_INIT;
+			e.state = BPL_HANDOVER;
+			e.line = name_b;
+			e.len = strlen(name_b);
+			append_buffered_patch_line(o, &e);
+		}
 		if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 				  &xpp, &xecfg))
 			die("unable to generate diff for %s", one->path);
@@ -3453,6 +3510,10 @@ void diff_setup(struct diff_options *options)
 		options->a_prefix = "a/";
 		options->b_prefix = "b/";
 	}
+
+	options->line_buffer = NULL;
+	options->line_buffer_nr = 0;
+	options->line_buffer_alloc = 0;
 }
 
 void diff_setup_done(struct diff_options *options)
@@ -4791,11 +4852,36 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 {
 	int i;
 	struct diff_queue_struct *q = &diff_queued_diff;
+	/*
+	 * For testing purposes we want to make sure the diff machinery
+	 * works completely with the buffer. If there is anything emitted
+	 * outside the emit_buffered_patch_line, then the order is screwed
+	 * up and the tests will fail.
+	 *
+	 * TODO (later in this series):
+	 * We'll unset this flag in a later patch.
+	 */
+	o->use_buffer = 1;
+
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		if (check_pair_status(p))
 			diff_flush_patch(p, o);
 	}
+
+	if (o->use_buffer) {
+		for (i = 0; i < o->line_buffer_nr; i++)
+			emit_buffered_patch_line(o, &o->line_buffer[i]);
+
+		for (i = 0; i < o->line_buffer_nr; i++)
+			free((void*)o->line_buffer[i].line);
+
+		free(o->line_buffer);
+
+		o->line_buffer = NULL;
+		o->line_buffer_nr = 0;
+		o->line_buffer_alloc = 0;
+	}
 }
 
 void diff_flush(struct diff_options *options)
diff --git a/diff.h b/diff.h
index 267acf1980..64bc9bcd8c 100644
--- a/diff.h
+++ b/diff.h
@@ -115,6 +115,41 @@ enum diff_submodule_format {
 	DIFF_SUBMODULE_INLINE_DIFF
 };
 
+/*
+ * This struct is used when we need to buffer the output of the diff output.
+ *
+ * NEEDSWORK: Instead of storing a copy of the line, add an offset pointer
+ * into the pre/post image file. This pointer could be a union with the
+ * line pointer. By storing an offset into the file instead of the literal line,
+ * we can decrease the memory footprint for the buffered output. At first we
+ * may want to only have indirection for the content lines, but we could
+ * also have an enum (based on sign?) that stores prefabricated lines, e.g.
+ * the similarity score line or hunk/file headers.
+ */
+struct buffered_patch_line {
+	const char *set;
+	const char *reset;
+	const char *line;
+	int len;
+	int sign;
+	int add_line_prefix;
+	enum {
+		/*
+		 * Emits [lineprefix][set][sign][reset] and then calls
+		 * ws_check_emit which will output "line", marked up
+		 * according to ws_rule.
+		 */
+		BPL_EMIT_LINE_WS,
+
+		/* Emits [lineprefix][set][sign] line [reset] */
+		BPL_EMIT_LINE_ASIS,
+
+		/* Reloads the ws_rule; line contains the file name */
+		BPL_HANDOVER
+	} state;
+};
+#define BUFFERED_PATCH_LINE_INIT {NULL, NULL, NULL, 0, 0, 0}
+
 struct diff_options {
 	const char *orderfile;
 	const char *pickaxe;
@@ -188,6 +223,10 @@ struct diff_options {
 	int diff_path_counter;
 
 	unsigned ws_rule;
+	int use_buffer;
+
+	struct buffered_patch_line *line_buffer;
+	int line_buffer_nr, line_buffer_alloc;
 };
 
 void emit_line_fmt(struct diff_options *o, const char *set, const char *reset,