[PATCHv5 00/17] Diff machine: highlight moved lines.

Stefan Beller· May 24, 2017, 21:40 UTC · lore

v5:
* removed the color passing to the submodule to make the tests pass again.
* fixed an indentation issue that was introduced from v3 -> v4.
* I merged it with origin/next and tests pass here.

diff to v4:

diff --git a/diff.c b/diff.c
index 23e70d348e..1292d3c4ad 100644
--- a/diff.c
+++ b/diff.c
@@ -751,7 +751,7 @@ static void mark_color_as_moved(struct diff_options *o,
 }
 
 static void emit_diff_line(struct diff_options *o,
-				     struct diff_line *e)
+			   struct diff_line *e)
 {
 	const char *ws;
 	int has_trailing_newline, has_trailing_carriage_return;
@@ -804,7 +804,7 @@ static void emit_diff_line(struct diff_options *o,
 }
 
 static void append_diff_line(struct diff_options *o,
-				       struct diff_line *e)
+			     struct diff_line *e)
 {
 	struct diff_line *f;
 	ALLOC_GROW(o->line_buffer,
diff --git a/submodule.c b/submodule.c
index 428c996c97..19c63197fb 100644
--- a/submodule.c
+++ b/submodule.c
@@ -550,8 +550,6 @@ void show_submodule_inline_diff(struct diff_options *o, const char *path,
 
 	/* TODO: other options may need to be passed here. */
 	argv_array_push(&cp.args, "diff");
-	if (o->use_color)
-		argv_array_push(&cp.args, "--color=always");
 	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/",

v4:
* interdiff to v3 (what is currently origin/sb/diff-color-move) below.
* renamed the "buffered_patch_line" to "diff_line". Originally I planned
  to not carry the "line" part as it can be a piece of a line as well.
  But for the intended functionality it is best to keep the name.
  If we'd want to add more functionality to say have a move detection
  for words as well, we'd rename the struct to have a better name then.
  For now diff_line is the best. (Thanks Jonathan Nieder!)
* tests to demonstrate it doesn't mess with --color-words as well as
  submodules. (Thanks Jonathan Tan!)
* added in the statics (Thanks Ramsay!)
* smaller scope for the hashmaps (Thanks Jonathan Tan!)
* some commit messages were updated, prior patch 4-7 is squashed into one
  (Thanks Jonathan Tan!)
* the tests added revealed an actual fault: now that the submodule process
  is not attached to a dupe of our stdout, it would stop coloring the
  output. We need to pass on use-color explicitly.
* updated the NEEDSWORK comment in the second last patch.

Thanks for bearing,
Stefan

v3:
* see interdiff below.
* fixing one invalid computation (Thanks Junio!)
* I reasoned more about submodule and word diffing, see the commit message
  of the last patch:
  
    A note on the options '--submodule=diff' and '--color-words/--word-diff':
    In the conversion to use emit_line in the prior patches both submodules
    as well as word diff output carefully chose to call emit_line with sign=0.
    All output with sign=0 is ignored for move detection purposes in this
    patch, such that no weird looking output will be generated for these
    cases. This leads to another thought: We could pass on '--color-moved' to
    submodules such that they color up moved lines for themselves. If we'd do
    so only line moves within a repository boundary are marked up.

* better name for emit_line outside of diff.[ch]

v2:
* emit_line now takes an argument that indicates if we want it
  to emit the line prefix as well. This should allow for a more faithful
  refactoring in the beginning. (Thanks Jonathan!)
* fixed memleaks (Thanks Brandon!)
* "git -c color.moved=true log -p" works now! (Thanks Jeff)
* interdiff below, though it is large.
* less intrusive than v1 (Thanks Jonathan!)

v1:

For details on *why* see the commit message of the last commit.

The first five patches are slight refactorings to get into good
shape, the next patches are funneling all output through emit_line_*.

The second last patch introduces an option to buffer up all output
before printing, and then the last patch can color up moved lines
of code.

Any feedback welcome.

Thanks,
Stefan

Stefan Beller (17):
  diff: readability fix
  diff: move line ending check into emit_hunk_header
  diff.c: factor out diff_flush_patch_all_file_pairs
  diff: introduce more flexible emit function
  diff.c: convert fn_out_consume to use emit_line
  diff.c: convert builtin_diff to use emit_line_*
  diff.c: convert emit_rewrite_diff to use emit_line_*
  diff.c: convert emit_rewrite_lines to use emit_line_*
  submodule.c: convert show_submodule_summary to use emit_line_fmt
  diff.c: convert emit_binary_diff_body to use emit_line_*
  diff.c: convert show_stats to use emit_line_*
  diff.c: convert word diffing to use emit_line_*
  diff.c: convert diff_flush to use emit_line_*
  diff.c: convert diff_summary to use emit_line_*
  diff.c: emit_line includes whitespace highlighting
  diff: buffer all output if asked to
  diff.c: color moved lines differently

 Documentation/config.txt   |  14 +-
 diff.c                     | 858 +++++++++++++++++++++++++++++++++------------
 diff.h                     |  59 +++-
 submodule.c                |  87 ++---
 submodule.h                |   9 +-
 t/t4015-diff-whitespace.sh | 267 ++++++++++++++
 6 files changed, 1016 insertions(+), 278 deletions(-)

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 01/17] diff: readability fix

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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);

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 03/17] diff.c: factor out diff_flush_patch_all_file_pairs

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

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)

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 09/17] submodule.c: convert show_submodule_summary to use emit_line_fmt

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c      | 14 ++++++----
 diff.h      |  3 +++
 submodule.c | 87 ++++++++++++++++++++++++++++++++-----------------------------
 submodule.h |  9 +++----
 4 files changed, 61 insertions(+), 52 deletions(-)

diff --git a/diff.c b/diff.c
index ca6b48cf49..3357c0fca3 100644
--- a/diff.c
+++ b/diff.c
@@ -562,6 +562,12 @@ static void emit_line_fmt(struct diff_options *o,
 	strbuf_release(&sb);
 }
 
+void diff_emit_line(struct diff_options *o, const char *set, const char *reset,
+		    const char *line, int len)
+{
+	emit_line(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) &&
@@ -2384,8 +2390,7 @@ 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);
@@ -2395,11 +2400,10 @@ 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..9ad546361a 100644
--- a/diff.h
+++ b/diff.h
@@ -188,6 +188,9 @@ struct diff_options {
 	int diff_path_counter;
 };
 
+void diff_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..19c63197fb 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)
+			diff_emit_line(o, del, reset, sb.buf, sb.len);
+		else if (add)
+			diff_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,
@@ -425,12 +418,17 @@ static void show_submodule_header(FILE *f, const char *path,
 	struct strbuf sb = STRBUF_INIT;
 	int fast_forward = 0, fast_backward = 0;
 
-	if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED)
-		fprintf(f, "%sSubmodule %s contains untracked content\n",
-			line_prefix, path);
-	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED)
-		fprintf(f, "%sSubmodule %s contains modified content\n",
-			line_prefix, path);
+	if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED) {
+		strbuf_addf(&sb, "Submodule %s contains untracked content\n", path);
+		diff_emit_line(o, NULL, NULL, sb.buf, sb.len);
+		strbuf_reset(&sb);
+	}
+
+	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED) {
+		strbuf_addf(&sb, "Submodule %s contains modified content\n", path);
+		diff_emit_line(o, NULL, NULL, sb.buf, sb.len);
+		strbuf_reset(&sb);
+	}
 
 	if (is_null_oid(one))
 		message = "(new submodule)";
@@ -472,21 +470,20 @@ 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)" : "");
+	diff_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 +492,7 @@ 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 +505,12 @@ 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";
+		diff_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 +519,18 @@ 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 +543,14 @@ 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 +573,21 @@ 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";
+		diff_emit_line(o, NULL, NULL, error, strlen(error));
+	}
+
+	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
+		diff_emit_line(o, NULL, NULL, sb.buf, sb.len);
+
+	if (finish_command(&cp)) {
+		const char *error = "(diff failed)\n";
+		diff_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.*/

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 04/17] diff: introduce more flexible emit function

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 76 +++++++++++++++++++++++++++++-------------------------------------
 1 file changed, 33 insertions(+), 43 deletions(-)

diff --git a/diff.c b/diff.c
index 2f9722b382..3569857818 100644
--- a/diff.c
+++ b/diff.c
@@ -516,36 +516,30 @@ 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 first, 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;
-	int nofirst;
 	FILE *file = o->file;
 
-	fputs(diff_line_prefix(o), file);
+	if (add_line_prefix)
+		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) {
-		fputs(set, file);
-		if (!nofirst)
-			fputc(first, file);
+	if (len || sign) {
+		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);
@@ -553,12 +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, line[0], line+1, len-1);
-}
-
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
@@ -587,13 +575,13 @@ 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, 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(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(ecbdata->opt, set, reset, 1, sign, "", 0);
 		ws_check_emit(line, len, ecbdata->ws_rule,
 			      ecbdata->opt->file, set, reset, ws);
 	}
@@ -643,7 +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 @@ */
@@ -679,7 +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);
 }
 
@@ -742,8 +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, '\\',
-			    nneof, strlen(nneof));
+		emit_line(ecb->opt, context, reset, 1, '\\',
+			  nneof, strlen(nneof));
 	}
 }
 
@@ -1341,7 +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 {
 			/*
@@ -1353,7 +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;
 	}
@@ -1376,7 +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;
 	}
 }
@@ -2188,7 +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] == ' ') {
@@ -4833,9 +4821,11 @@ 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, 1, 0, term, !!term[0]);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);

-- 
2.13.0.18.g7d86cc8ba0

Re: [PATCHv5 04/17] diff: introduce more flexible emit function

> Currently, diff output is written either through the emit_line_0
> function or through the FILE * in struct diff_options directly. To
> make it easier to teach diff to buffer its output (which will be done
> in a subsequent commit), introduce a more flexible emit_line() function.
> In this commit, direct usages of emit_line_0() are replaced with
> emit_line(); subsequent commits will also replace usages of the
> FILE * with emit().

Check the names of the functions in this paragraph.

> diff --git a/diff.c b/diff.c
> index 2f9722b382..3569857818 100644
> --- a/diff.c
> +++ b/diff.c
> @@ -516,36 +516,30 @@ 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 first, 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)

Stefan Beller· Jun 13, 2017, 23:41 UTC · re: Jonathan Tan · lore

Re: [PATCHv5 04/17] diff: introduce more flexible emit function

On Tue, Jun 13, 2017 at 2:54 PM, Jonathan Tan <jonathantanmy@google.com> wrote:

> On Wed, 24 May 2017 14:40:23 -0700
> Stefan Beller <sbeller@google.com> wrote:
>
>> Currently, diff output is written either through the emit_line_0
>> function or through the FILE * in struct diff_options directly. To
>> make it easier to teach diff to buffer its output (which will be done
>> in a subsequent commit), introduce a more flexible emit_line() function.
>> In this commit, direct usages of emit_line_0() are replaced with
>> emit_line(); subsequent commits will also replace usages of the
>> FILE * with emit().
>
> Check the names of the functions in this paragraph.

Only the very last word needed replacement of /s/emit/emit_line/.

>
>> diff --git a/diff.c b/diff.c
>> index 2f9722b382..3569857818 100644
>> --- a/diff.c
>> +++ b/diff.c
>> @@ -516,36 +516,30 @@ 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 first, 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)
>
> In the future, this function is going to be used even to emit partial
> lines

Yes.

> - could this be called emit() instead?

After this patch

  $ git grep emit_line |wc -l
  16
  # not all are this function, there is
  emit_line_checked as well. But 16 is not too much.

But if renamed to emit():

  $ git grep emit -- diff.c |wc -l
  60

Re: [PATCHv5 04/17] diff: introduce more flexible emit function

> On Tue, Jun 13, 2017 at 2:54 PM, Jonathan Tan <jonathantanmy@google.com> wrote:
> > - could this be called emit() instead?
> 
> Despite having good IDEs available some (including me)
> very much like working with raw text, and then having a function
> named as a common string doesn't help.
> 
> After this patch
> 
>   $ git grep emit_line |wc -l
>   16
>   # not all are this function, there is
>   emit_line_checked as well. But 16 is not too much.
> 
> But if renamed to emit():
> 
>   $ git grep emit -- diff.c |wc -l
>   60
> 
> You could argue I'd just have to grep
> for "emit (" instead, but that then I would have
> rely on correct whitespacing or use a regex already.
> Complexity which I would not like.
> 
> So I am not sure if this is helping a reader. (Not the casual
> reader, but the one grepping for this function)
> 
> Maybe we can settle on a different name though,
> such as emit_string which is not a prefix of a dozen
> different other functions?

emit_string sounds good to me.

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 05/17] diff.c: convert fn_out_consume to use emit_line

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

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

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 02/17] diff: move line ending check into emit_hunk_header

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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;
 	}
 

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 07/17] diff.c: convert emit_rewrite_diff to use emit_line_*

This covers emit_rewrite_diff.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/diff.c b/diff.c
index 4fa976d43c..3dda9f3c8e 100644
--- a/diff.c
+++ b/diff.c
@@ -704,17 +704,17 @@ 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;
 	}
 }
@@ -768,7 +768,7 @@ 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;
@@ -806,20 +806,23 @@ 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, 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);
-	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, 1, 0, out.buf, out.len);
+	strbuf_release(&out);
+
 	if (lc_a && !o->irreversible_delete)
 		emit_rewrite_lines(&ecbdata, '-', data_one, size_one);
 	if (lc_b)

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 15/17] diff.c: emit_line includes whitespace highlighting

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 107 ++++++++++++++++++++++++++++++++++++++---------------------------
 diff.h |   2 ++
 2 files changed, 65 insertions(+), 44 deletions(-)

diff --git a/diff.c b/diff.c
index 76cafde4be..514c5facd7 100644
--- a/diff.c
+++ b/diff.c
@@ -516,15 +516,34 @@ 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)
+
+static 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--;
@@ -558,14 +577,14 @@ static 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);
 }
 
 void diff_emit_line(struct diff_options *o, const char *set, const char *reset,
 		    const char *line, int len)
 {
-	emit_line(o, set, reset, 1, 0, line, len);
+	emit_line(o, set, reset, 1, 0, 0, line, len);
 }
 
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
@@ -596,16 +615,15 @@ 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,
@@ -652,7 +670,7 @@ 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 @@ */
@@ -688,7 +706,7 @@ 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);
 }
 
@@ -759,7 +777,7 @@ 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);
 	}
@@ -835,7 +853,7 @@ 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)
@@ -908,7 +926,7 @@ 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 ?
@@ -917,14 +935,14 @@ 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;
@@ -1139,7 +1157,7 @@ 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
@@ -1298,7 +1316,7 @@ 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;
@@ -1351,8 +1369,8 @@ 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
@@ -1363,7 +1381,7 @@ 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;
 	}
@@ -1386,7 +1404,7 @@ 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;
 	}
 }
@@ -1575,7 +1593,7 @@ static 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;
 	}
 
@@ -1603,7 +1621,7 @@ static 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);
 }
 
@@ -1787,7 +1805,7 @@ 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;
 			}
@@ -1797,14 +1815,14 @@ 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;
 		}
@@ -1835,7 +1853,7 @@ 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);
 	}
 
@@ -1857,7 +1875,7 @@ 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;
 	}
@@ -2211,7 +2229,7 @@ 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] == ' ') {
@@ -2307,9 +2325,9 @@ 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);
 }
 
@@ -2318,7 +2336,7 @@ 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);
 }
@@ -2461,7 +2479,7 @@ 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);
@@ -2471,7 +2489,7 @@ 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) &&
@@ -2482,11 +2500,11 @@ 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",
@@ -2499,11 +2517,11 @@ 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))
@@ -2523,7 +2541,7 @@ 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);
 		}
 
@@ -2540,6 +2558,7 @@ 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;
@@ -4514,7 +4533,7 @@ 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);
 }
 
@@ -4566,7 +4585,7 @@ 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;
@@ -4873,10 +4892,10 @@ 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 56d8dd036e..85948ed65a 100644
--- a/diff.h
+++ b/diff.h
@@ -186,6 +186,8 @@ struct diff_options {
 	void *output_prefix_data;
 
 	int diff_path_counter;
+
+	unsigned ws_rule;
 };
 
 void diff_emit_line(struct diff_options *o, const char *set, const char *reset,

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 11/17] diff.c: convert show_stats to use emit_line_*

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 89 ++++++++++++++++++++++++++++++++++++++----------------------------
 diff.h |  4 +--
 2 files changed, 53 insertions(+), 40 deletions(-)

diff --git a/diff.c b/diff.c
index b5a5261a4e..a76abf5f69 100644
--- a/diff.c
+++ b/diff.c
@@ -1540,20 +1540,19 @@ 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)
@@ -1577,14 +1576,16 @@ 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)
+static 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,
@@ -1611,9 +1612,17 @@ 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)
@@ -1623,13 +1632,13 @@ 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);
@@ -1783,26 +1792,29 @@ 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;
 		}
 
@@ -1825,14 +1837,15 @@ 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++) {
@@ -1853,11 +1866,12 @@ 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)
@@ -1869,7 +1883,7 @@ 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))) {
@@ -1879,8 +1893,7 @@ 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 9ad546361a..56d8dd036e 100644
--- a/diff.h
+++ b/diff.h
@@ -392,8 +392,8 @@ 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 */

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 17/17] diff.c: color moved lines differently

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OM]  -        if (!is_authorized_user())
    [OM]  -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OM]  -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NM]  +        sensitive_stuff(spanning,
    [NM]  +                        multiple,
    [NM]  +                        lines);
    [NM]  +}

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OMA] -        if (!is_authorized_user())
    [OMA] -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OMA] -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NMA] +        sensitive_stuff(spanning,
    [NMA] +                        multiple,
    [NMA] +                        lines);
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NMA] +}

Helped-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

# Conflicts:
#	diff.c
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
---
 Documentation/config.txt   |  14 ++-
 diff.c                     | 275 +++++++++++++++++++++++++++++++++++++++++++--
 diff.h                     |   9 +-
 t/t4015-diff-whitespace.sh | 267 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 552 insertions(+), 13 deletions(-)

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 8e06206881..1292d3c4ad 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 diff_line *line;
+	struct moved_entry *next_line;
+};
+
+static void get_ws_cleaned_string(const struct diff_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 diff_line_cmp_no_ws(const struct diff_line *a,
+					 const struct diff_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 diff_line_cmp(const struct diff_line *a,
+				   const struct diff_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 diff_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 diff_line_cmp_no_ws(a->line, b->line, keydata);
+}
+
+static unsigned get_line_hash(struct diff_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 diff_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 +615,141 @@ 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 hashmap *add_lines,
+					struct hashmap *del_lines)
+{
+	struct moved_entry *prev_line = NULL;
+
+	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 = add_lines;
+			break;
+		case '-':
+			sign = '-';
+			hm = del_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 hashmap *add_lines,
+				struct hashmap *del_lines)
+{
+	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	int pmb_nr = 0, pmb_alloc = 0;
+	int use_alt_color = 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 diff_line *l = &o->line_buffer[n];
+		int i, lp, rp;
+
+		switch (l->sign) {
+		case '+':
+			hm = del_lines;
+			break;
+		case '-':
+			hm = add_lines;
+			break;
+		default:
+			use_alt_color = 0;
+			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 &&
+			    !diff_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 */
+			use_alt_color = (use_alt_color + 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 + use_alt_color);
+			break;
+		case '-':
+			l->set = diff_get_color_opt(o,
+				DIFF_FILE_OLD_MOVED + use_alt_color);
+			break;
+		default:
+			die("BUG: we should have continued earlier?");
+		}
+	}
+	free(pmb);
+}
+
 static void emit_diff_line(struct diff_options *o,
 			   struct diff_line *e)
 {
@@ -3518,6 +3752,8 @@ 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)
@@ -3627,6 +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)
@@ -4051,6 +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;
@@ -4856,16 +5099,9 @@ 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_diff_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)
+		o->use_buffer = 1;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
@@ -4874,6 +5110,24 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
+		if (o->color_moved) {
+			struct hashmap add_lines, del_lines;
+			unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+
+			hashmap_init(&del_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+			hashmap_init(&add_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+
+			add_lines_to_move_detection(o, &add_lines, &del_lines);
+			mark_color_as_moved(o, &add_lines, &del_lines);
+
+			hashmap_free(&add_lines, 0);
+			hashmap_free(&del_lines, 0);
+		}
+
 		for (i = 0; i < o->line_buffer_nr; i++)
 			emit_diff_line(o, &o->line_buffer[i]);
 
@@ -4962,6 +5216,7 @@ 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 fad1258556..445259ebf7 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;
@@ -228,6 +229,8 @@ struct diff_options {
 
 	struct diff_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
+
+	int color_moved;
 };
 
 /* Emit [line_prefix] [set] line [reset] */
@@ -243,7 +246,11 @@ 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..0e92bf94bf 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -972,4 +972,271 @@ 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_expect_success 'move detection does not mess up colored words' '
+	cat <<-\EOF >text.txt &&
+	Lorem Ipsum is simply dummy text of the printing and typesetting industry.
+	EOF
+	git add text.txt &&
+	git commit -a -m "clean state" &&
+	cat <<-\EOF >text.txt &&
+	simply Lorem Ipsum dummy is text of the typesetting and printing industry.
+	EOF
+	git diff --color-moved --word-diff >actual &&
+	git diff --word-diff >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'move detection with submodules' '
+	test_create_repo bananas &&
+	echo ripe >bananas/recipe &&
+	git -C bananas add recipe &&
+	test_commit fruit &&
+	test_commit -C bananas recipe &&
+	git submodule add ./bananas &&
+	git add bananas &&
+	git commit -a -m "bananas are like a heavy library?" &&
+	echo foul >bananas/recipe &&
+	echo ripe >fruit.t &&
+
+	git diff --submodule=diff --color-moved >actual &&
+
+	# no move detection as the moved line is across repository boundaries.
+	test_decode_color <actual >decoded_actual &&
+	! grep BGREEN decoded_actual &&
+	! grep BRED decoded_actual &&
+
+	# nor did we mess with it another way
+	git diff --submodule=diff | test_decode_color >expect &&
+	test_cmp expect decoded_actual
+'
+
 test_done

-- 
2.13.0.18.g7d86cc8ba0

Junio C Hamano· May 25, 2017, 02:27 UTC · re: Stefan Beller · lore

Re: [PATCHv5 17/17] diff.c: color moved lines differently

Stefan Beller <sbeller@google.com> writes:

> When a patch consists mostly of moving blocks of code around, it can
> be quite tedious to ensure that the blocks are moved verbatim, and not
> ...
> cases. This leads to another thought: We could pass on '--color-moved' to
> submodules such that they color up moved lines for themselves. If we'd do
> so only line moves within a repository boundary are marked up.
>
> Helped-by: Jonathan Tan <jonathantanmy@google.com>
> Signed-off-by: Stefan Beller <sbeller@google.com>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
>
> # Conflicts:
> #	diff.c
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> Signed-off-by: Stefan Beller <sbeller@google.com>
> ---

Hmph, what are these final lines about?

Stefan Beller· May 25, 2017, 05:39 UTC · re: Junio C Hamano · lore

Re: [PATCHv5 17/17] diff.c: color moved lines differently

On Wed, May 24, 2017 at 7:27 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>> When a patch consists mostly of moving blocks of code around, it can
>> be quite tedious to ensure that the blocks are moved verbatim, and not
>> ...
>> cases. This leads to another thought: We could pass on '--color-moved' to
>> submodules such that they color up moved lines for themselves. If we'd do
>> so only line moves within a repository boundary are marked up.
>>
>> Helped-by: Jonathan Tan <jonathantanmy@google.com>
>> Signed-off-by: Stefan Beller <sbeller@google.com>
>> Signed-off-by: Junio C Hamano <gitster@pobox.com>
>>
>> # Conflicts:
>> #     diff.c
>> Signed-off-by: Junio C Hamano <gitster@pobox.com>
>> Signed-off-by: Stefan Beller <sbeller@google.com>
>> ---
>
> Hmph, what are these final lines about?

Puzzeled, will fix in a reroll.

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 10/17] diff.c: convert emit_binary_diff_body to use emit_line_*

This covers emit_binary_diff_body.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/diff.c b/diff.c
index 3357c0fca3..b5a5261a4e 100644
--- a/diff.c
+++ b/diff.c
@@ -2244,8 +2244,8 @@ 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;
@@ -2274,13 +2274,12 @@ 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, 1, "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, 1, "literal %lu\n", two->size);
 		free(delta);
 		data = deflated;
 		data_size = deflate_size;
@@ -2289,8 +2288,9 @@ 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;
@@ -2298,20 +2298,25 @@ 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, 1, 0, line, len);
 	}
-	fprintf(file, "%s\n", prefix);
+	emit_line(o, NULL, NULL, 1, 0, "\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, 1, 0, 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)
@@ -2498,7 +2503,7 @@ 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, 1,
 				      "Binary files %s and %s differ\n",

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 08/17] diff.c: convert emit_rewrite_lines to use emit_line_*

This covers emit_rewrite_lines.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/diff.c b/diff.c
index 3dda9f3c8e..ca6b48cf49 100644
--- a/diff.c
+++ b/diff.c
@@ -722,15 +722,23 @@ 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 {
+			strbuf_add(&sb, data, size);
+			strbuf_addch(&sb, '\n');
+			size = 0; /* to exit the loop. */
+
+			data = sb.buf;
+			len = sb.len;
+		}
 		if (prefix != '+') {
 			ecb->lno_in_preimage++;
 			emit_del_line(reset, ecb, data, len);
@@ -741,12 +749,13 @@ 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);
 	}
 }
 

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 16/17] diff: buffer all output if asked to

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++---------------
 diff.h |  41 +++++++++++++++++
 2 files changed, 161 insertions(+), 35 deletions(-)

diff --git a/diff.c b/diff.c
index 514c5facd7..8e06206881 100644
--- a/diff.c
+++ b/diff.c
@@ -516,54 +516,85 @@ 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 markup_ws,
-		      int sign, const char *line, int len)
+static void emit_diff_line(struct diff_options *o,
+			   struct diff_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 DIFF_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 DIFF_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 DIFF_LINE_RELOAD_WS_RULE:
+		o->ws_rule = whitespace_rule(e->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_diff_line(struct diff_options *o,
+			     struct diff_line *e)
+{
+	struct diff_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 diff_line));
+	f->line = e->line ? xmemdupz(e->line, e->len) : NULL;
+}
+
+static 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 diff_line e = {set, reset, line,
+		len, sign, add_line_prefix,
+		markup_ws ? DIFF_LINE_WS : DIFF_LINE_ASIS};
+
+	if (o->use_buffer)
+		append_diff_line(o, &e);
+	else
+		emit_diff_line(o, &e);
 }
 
 static void emit_line_fmt(struct diff_options *o,
@@ -1172,6 +1203,18 @@ 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_diff_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)
@@ -1207,6 +1250,11 @@ 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)
@@ -1241,6 +1289,7 @@ 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);
@@ -2579,6 +2628,13 @@ 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 diff_line e = diff_line_INIT;
+			e.state = DIFF_LINE_RELOAD_WS_RULE;
+			e.line = name_b;
+			e.len = strlen(name_b);
+			append_diff_line(o, &e);
+		}
 		if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 				  &xpp, &xecfg))
 			die("unable to generate diff for %s", one->path);
@@ -3458,6 +3514,10 @@ 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)
@@ -4796,11 +4856,36 @@ 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_diff_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_diff_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 85948ed65a..fad1258556 100644
--- a/diff.h
+++ b/diff.h
@@ -115,6 +115,42 @@ 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
+ * enhance the state for emitting prefabricated lines, e.g. the similarity
+ * score line or hunk/file headers would only need to store a number or path
+ * and then the output can be constructed later on depending on state.
+ */
+struct diff_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.
+		 */
+		DIFF_LINE_WS,
+
+		/* Emits [lineprefix][set][sign] line [reset] */
+		DIFF_LINE_ASIS,
+
+		/* Reloads the ws_rule; line contains the file name */
+		DIFF_LINE_RELOAD_WS_RULE
+	} state;
+};
+#define diff_line_INIT {NULL, NULL, NULL, 0, 0, 0}
+
 struct diff_options {
 	const char *orderfile;
 	const char *pickaxe;
@@ -188,8 +224,13 @@ struct diff_options {
 	int diff_path_counter;
 
 	unsigned ws_rule;
+	int use_buffer;
+
+	struct diff_line *line_buffer;
+	int line_buffer_nr, line_buffer_alloc;
 };
 
+/* Emit [line_prefix] [set] line [reset] */
 void diff_emit_line(struct diff_options *o, const char *set, const char *reset,
 		    const char *line, int len);
 

-- 
2.13.0.18.g7d86cc8ba0

Junio C Hamano· May 25, 2017, 02:26 UTC · re: Stefan Beller · lore

Re: [PATCHv5 16/17] diff: buffer all output if asked to

Stefan Beller <sbeller@google.com> writes:

> Introduce a new option 'use_buffer' in the struct diff_options which
> controls whether all output is buffered up until all output is available.
> ...
> Unconditionally enable output via buffer in this patch as it yields
> a great opportunity for testing, i.e. all the diff tests from the
> test suite pass without having reordering issues (i.e. only parts
> of the output got buffered, and we forgot to buffer other parts).
> The test suite passes, which gives confidence that we converted all
> functions to use emit_line for output.
>
> Signed-off-by: Stefan Beller <sbeller@google.com>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Oh, did I?

> ---
>  diff.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++---------------
>  diff.h |  41 +++++++++++++++++
>  2 files changed, 161 insertions(+), 35 deletions(-)
>
> diff --git a/diff.c b/diff.c
> index 514c5facd7..8e06206881 100644
> --- a/diff.c
> +++ b/diff.c
> ...
> @@ -2579,6 +2628,13 @@ 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 diff_line e = diff_line_INIT;

This ...

> +			e.state = DIFF_LINE_RELOAD_WS_RULE;
> ...
> +#define diff_line_INIT {NULL, NULL, NULL, 0, 0, 0}

... and this should be in all caps.   We do not say

	struct strbuf buf = strbuf_INIT;

and we should do the same for this new thing.

Stefan Beller· May 25, 2017, 05:34 UTC · re: Junio C Hamano · lore

Re: [PATCHv5 16/17] diff: buffer all output if asked to

On Wed, May 24, 2017 at 7:26 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>> Introduce a new option 'use_buffer' in the struct diff_options which
>> controls whether all output is buffered up until all output is available.
>> ...
>> Unconditionally enable output via buffer in this patch as it yields
>> a great opportunity for testing, i.e. all the diff tests from the
>> test suite pass without having reordering issues (i.e. only parts
>> of the output got buffered, and we forgot to buffer other parts).
>> The test suite passes, which gives confidence that we converted all
>> functions to use emit_line for output.
>>
>> Signed-off-by: Stefan Beller <sbeller@google.com>
>> Signed-off-by: Junio C Hamano <gitster@pobox.com>
>
> Oh, did I?

Maybe I have to rethink that strategy.

>
>> ---
>>  diff.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++---------------
>>  diff.h |  41 +++++++++++++++++
>>  2 files changed, 161 insertions(+), 35 deletions(-)
>>
>> diff --git a/diff.c b/diff.c
>> index 514c5facd7..8e06206881 100644
>> --- a/diff.c
>> +++ b/diff.c
>> ...
>> @@ -2579,6 +2628,13 @@ 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 diff_line e = diff_line_INIT;
>
> This ...
>
>> +                     e.state = DIFF_LINE_RELOAD_WS_RULE;
>> ...
>> +#define diff_line_INIT {NULL, NULL, NULL, 0, 0, 0}
>
> ... and this should be in all caps.   We do not say
>
>         struct strbuf buf = strbuf_INIT;
>
> and we should do the same for this new thing.

Will fix again.

Stefan

Junio C Hamano· May 26, 2017, 01:09 UTC · re: Stefan Beller · lore

Re: [PATCHv5 16/17] diff: buffer all output if asked to

Stefan Beller <sbeller@google.com> writes:

> Yes, this is essentially the v4 with small indentation fixes, so I
> assumed your signoff is still valid.

Thanks.

Re: [PATCHv5 16/17] diff: buffer all output if asked to

> diff --git a/diff.h b/diff.h
> index 85948ed65a..fad1258556 100644
> --- a/diff.h
> +++ b/diff.h
> @@ -115,6 +115,42 @@ 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
> + * enhance the state for emitting prefabricated lines, e.g. the similarity
> + * score line or hunk/file headers would only need to store a number or path
> + * and then the output can be constructed later on depending on state.
> + */
> +struct diff_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.
> +		 */
> +		DIFF_LINE_WS,
> +
> +		/* Emits [lineprefix][set][sign] line [reset] */
> +		DIFF_LINE_ASIS,
> +
> +		/* Reloads the ws_rule; line contains the file name */
> +		DIFF_LINE_RELOAD_WS_RULE
> +	} state;
> +};
> +#define diff_line_INIT {NULL, NULL, NULL, 0, 0, 0}

Stefan Beller· Jun 14, 2017, 02:52 UTC · re: Jonathan Tan · lore

Re: [PATCHv5 16/17] diff: buffer all output if asked to

On Tue, Jun 13, 2017 at 3:07 PM, Jonathan Tan <jonathantanmy@google.com> wrote:

>> +struct diff_line {
>
> Probably should be called diff_emission (or just emission), since these
> may not be full lines.

I think emitted_string would do as well?

>
> Also, can this definition be in the .c file? Callers should use the
> diff_emit_line() below, and not need to know how it is implemented
> internally.

done

>> +#define diff_line_INIT {NULL, NULL, NULL, 0, 0, 0}
>
> Should be DIFF_LINE_INIT (capitalization), and {NULL} is sufficient, I
> think.

done.

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 12/17] diff.c: convert word diffing to use emit_line_*

This covers all code related to diffing words.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 73 +++++++++++++++++++++++++++++-------------------------------------
 1 file changed, 32 insertions(+), 41 deletions(-)

diff --git a/diff.c b/diff.c
index a76abf5f69..8317824963 100644
--- a/diff.c
+++ b/diff.c
@@ -897,37 +897,42 @@ 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)
+					  size_t count, const char *buf)
 {
 	int print = 0;
+	struct strbuf sb = STRBUF_INIT;
 
 	while (count) {
 		char *p = memchr(buf, '\n', count);
 		if (print)
-			fputs(line_prefix, fp);
+			emit_line(o, NULL, NULL, 1, 0, "", 0);
+
 		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;
+			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);
+			emit_line(o, st_el->color, reset,
+				  0, 0, sb.buf, sb.len);
+			strbuf_reset(&sb);
 		}
 		if (!p)
-			return 0;
-		if (fputs(newline, fp) < 0)
-			return -1;
+			goto out;
+
+		strbuf_addstr(&sb, newline);
+		emit_line(o, NULL, NULL, 0, 0, sb.buf, sb.len);
+		strbuf_reset(&sb);
 		count -= p + 1 - buf;
 		buf = p + 1;
 		print = 1;
 	}
+
+out:
+	strbuf_release(&sb);
 	return 0;
 }
 
@@ -981,14 +986,12 @@ 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) {
@@ -1005,28 +1008,21 @@ 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)) {
-		fputs(line_prefix, diff_words->opt->file);
-	}
 	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);
+				diff_words->current_plus);
 	}
 	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);
+				minus_end - minus_begin, minus_begin);
 	}
 	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);
+				plus_end - plus_begin, plus_begin);
 	}
 
 	diff_words->current_plus = plus_end;
@@ -1113,18 +1109,14 @@ 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) {
-		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);
+			diff_words->minus.text.ptr);
 		diff_words->minus.text.size = 0;
 		return;
 	}
@@ -1147,12 +1139,11 @@ 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))
-			fputs(line_prefix, diff_words->opt->file);
-		fn_out_diff_words_write_helper(diff_words->opt->file,
+			emit_line(diff_words->opt, NULL, NULL, 1, 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;
 }

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 14/17] diff.c: convert diff_summary to use emit_line_*

This covers diff_summary.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 64 ++++++++++++++++++++++++++++++++++------------------------------
 1 file changed, 34 insertions(+), 30 deletions(-)

diff --git a/diff.c b/diff.c
index 8ebe673331..76cafde4be 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, 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;
 	}
 }

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 13/17] diff.c: convert diff_flush to use emit_line_*

This covers diff_flush.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/diff.c b/diff.c
index 8317824963..8ebe673331 100644
--- a/diff.c
+++ b/diff.c
@@ -4872,7 +4872,9 @@ 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));
 			}
 		}
 

-- 
2.13.0.18.g7d86cc8ba0

Stefan Beller· May 24, 2017, 21:40 UTC · re: Stefan Beller · lore

[PATCHv5 06/17] diff.c: convert builtin_diff to use emit_line_*

This covers builtin_diff.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/diff.c b/diff.c
index 8186289734..4fa976d43c 100644
--- a/diff.c
+++ b/diff.c
@@ -1289,8 +1289,9 @@ 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, 0, 0,
+			  ecbdata->header->buf, ecbdata->header->len);
+		strbuf_release(ecbdata->header);
 		ecbdata->header = NULL;
 	}
 
@@ -2435,7 +2436,7 @@ 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, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
@@ -2445,7 +2446,7 @@ static void builtin_diff(const char *name_a,
 	}
 
 	if (o->irreversible_delete && lbl[1][0] == '/') {
-		fprintf(o->file, "%s", header.buf);
+		emit_line(o, NULL, NULL, 0, 0, header.buf, header.len);
 		strbuf_reset(&header);
 		goto free_ab_and_return;
 	} else if (!DIFF_OPT_TST(o, TEXT) &&
@@ -2456,12 +2457,15 @@ static void builtin_diff(const char *name_a,
 		    !DIFF_OPT_TST(o, BINARY)) {
 			if (!oidcmp(&one->oid, &two->oid)) {
 				if (must_show_header)
-					fprintf(o->file, "%s", header.buf);
+					emit_line(o, NULL, NULL, 0, 0,
+						  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]);
+			emit_line(o, NULL, NULL, 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;
 		}
 		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
@@ -2470,16 +2474,19 @@ static void builtin_diff(const char *name_a,
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
 			if (must_show_header)
-				fprintf(o->file, "%s", header.buf);
+				emit_line(o, NULL, NULL, 0, 0,
+					  header.buf, header.len);
 			goto free_ab_and_return;
 		}
-		fprintf(o->file, "%s", header.buf);
+		emit_line(o, NULL, NULL, 0, 0,
+			  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, 1,
+				      "Binary files %s and %s differ\n",
+				      lbl[0], lbl[1]);
 		o->found_changes = 1;
 	} else {
 		/* Crazy xdl interfaces.. */
@@ -2491,7 +2498,7 @@ static void builtin_diff(const char *name_a,
 		const struct userdiff_funcname *pe;
 
 		if (must_show_header) {
-			fprintf(o->file, "%s", header.buf);
+			emit_line(o, NULL, NULL, 0, 0, header.buf, header.len);
 			strbuf_reset(&header);
 		}
 

-- 
2.13.0.18.g7d86cc8ba0

Junio C Hamano· May 25, 2017, 06:44 UTC · re: Stefan Beller · lore

Re: [PATCHv5 00/17] Diff machine: highlight moved lines.

$ git -c color.moved diff js/blame-lib~6 js/blame-lib blame.c blame.h builtin/blame.c

Some random observations:

 * You do not seem to have any command line option yet.  I guess
   that is OK while the series is still in RFC state, but when we
   are ready to seriously start considering this for 'next', we'd
   need something like --color-moved that can be used across "diff",
   "log -p" and "show".

 * As configuration variable names go, "color.moved" is probably in
   a wrong section.  Perhaps "diff.colorMoved" or something?

 * The fact that I am using

     [diff "color"] 
	old = red reverse
	whitespace = blue reverse

   on a "black ink on white paper" terminal might have an effect on
   this, but lines printed in either bold green and on green
   background (i.e. not new ones but are the ones moved from
   elsewhere) stood out a lot more prominently than lines printed in
   green (i.e. truly new additions), and I felt that this is totally
   backwards from what I needed for this exercise.  That is, while
   reviewing a code moving change, I want to be able to concentrate
   primarily of three things:

   - What are the new lines that are *not* moved from elsewhere?
     Did the submitter try to sneak in unrelated changes?

   - What are the changes that are truly lost, not moved to
     elsewhere?

   - Do the lines moved from elsewhere form a coherent whole?  Where
     is the boundary between blocks of text that are copied?  Do
     adjacent two blocks of moved text come from the same old place
     next to each other?

   Using colors that stand out more prominently than for the regular
   new/old lines is counter-productive for all of these, especially
   for the first two purposes.  I may suggest using cyan (or any
   color that is very close to the background) so that the presense
   of moved lines are merely felt without being distracting.  IOW,
   while reviewing code moving patch, moved parts want to be dimmed,
   not highlighted.

Stefan Beller· May 25, 2017, 16:31 UTC · re: Junio C Hamano · lore

Re: [PATCHv5 00/17] Diff machine: highlight moved lines.

On Wed, May 24, 2017 at 11:44 PM, Junio C Hamano <gitster@pobox.com> wrote:

> I was trying to see how this is useful in code moving change, with
> this command line:
>
> $ git -c color.moved diff js/blame-lib~6 js/blame-lib blame.c blame.h builtin/blame.c
>
> Some random observations:
>
>  * You do not seem to have any command line option yet.  I guess
>    that is OK while the series is still in RFC state, but when we
>    are ready to seriously start considering this for 'next', we'd
>    need something like --color-moved that can be used across "diff",
>    "log -p" and "show".

>  * As configuration variable names go, "color.moved" is probably in
>    a wrong section.  Perhaps "diff.colorMoved" or something?

>
>  * The fact that I am using
>
>      [diff "color"]
>         old = red reverse
>         whitespace = blue reverse
>
>    on a "black ink on white paper" terminal might have an effect on
>    this,

Yes very much!

>    but lines printed in either bold green and on green
>    background (i.e. not new ones but are the ones moved from
>    elsewhere) stood out a lot more prominently than lines printed in
>    green (i.e. truly new additions), and I felt that this is totally
>    backwards from what I needed for this exercise.  That is, while
>    reviewing a code moving change, I want to be able to concentrate
>    primarily of three things:
>
>    - What are the new lines that are *not* moved from elsewhere?
>      Did the submitter try to sneak in unrelated changes?
>
>    - What are the changes that are truly lost, not moved to
>      elsewhere?
>
>    - Do the lines moved from elsewhere form a coherent whole?  Where
>      is the boundary between blocks of text that are copied?  Do
>      adjacent two blocks of moved text come from the same old place
>      next to each other?

Example of how it could look:
---8<---
    diff --git a/poetry.txt b/poetry.txt
    index 9d32b3b..cc50ca1 100644
    --- a/poetry.txt
    +++ b/poetry.txt
    @@ -1,12 +1,4 @@
[W] -A simple text is
[W] -written in paragraphs and
[W] -many more lines.
[R] -
[W]  A diff is smaller
[W]  than the pre or post image text form
[W]  used for review
[W]
[W] -In between focus
[W] -is hard to keep consistently
[W] -errors may occur
[W] -
    diff --git a/engineer.txt b/engineer.txt
    new file mode 100644
    index 0000000..8fbc0ce
    --- /dev/null
    +++ b/engineer.txt
    @@ -0,0 +1,7 @@
[W] +A simple text is
[W] +written in paragraphs and
[B] +many more lines.
[B] +In between focus
[W] +is hard to keep consistently
[W] +errors may occur
[W] +
---8<---

W -> simple White text (diff.color.context)
R -> Red text (diff.color.old)
B -> Boundary marker (Maybe just diff.color.{old/new}
      or a new color to configure)

>
>    Using colors that stand out more prominently than for the regular
>    new/old lines is counter-productive for all of these, especially
>    for the first two purposes.  I may suggest using cyan (or any
>    color that is very close to the background) so that the presense
>    of moved lines are merely felt without being distracting.  IOW,
>    while reviewing code moving patch, moved parts want to be dimmed,
>    not highlighted.

Junio C Hamano· May 26, 2017, 01:20 UTC · re: Stefan Beller · lore

Re: [PATCHv5 00/17] Diff machine: highlight moved lines.

Stefan Beller <sbeller@google.com> writes:

> As you turn on/off normal coloring via "color.diff" and this only extends
> the coloring scheme, I have the impression "color" is the right section.
> Maybe color.diffStyle=[normal/enhanced] and "enhanced" means this
> feature for now?

> The only option in the "diff" section related to color is diff.wsErrorHighlight
> which has a very similar purpose, so "diff.colorMoved" would fit in that
> scheme.

> So with these questions, I wonder if we want to color moved lines
> as "color.diff.context" (i.e. plain white text in the normal coloring scheme)
> This would serve the intended purpose of
> dimming the attention to moved lines.

Yes, but two points.

 (1) We want to do so while making it obvious where the boundary
     between two moved blocks of text whose destination (for
     moved-deleted lines) or source (for moved-added lines) is.

 (2) My message was an impression from using the code to review a
     patch that is meant to be "move without changing other things".
     For other purposes, there may be cases where moved ones may
     want to be highlighted, not dimmed.

> Regarding the last point of marking up adjacent blocks (which would
> indicate that there is a coherency issue or just moving from different
> places), we could highlight the last line of the previous block
> and first line of the next block in their "normal" colors (i.e.
> color.diff.old and color.diff.new).

Hmm.  That is an interesting thought.

Stefan Beller· May 26, 2017, 19:30 UTC · re: Junio C Hamano · lore

Re: [PATCHv5 00/17] Diff machine: highlight moved lines.

On Thu, May 25, 2017 at 6:20 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>> As you turn on/off normal coloring via "color.diff" and this only extends
>> the coloring scheme, I have the impression "color" is the right section.
>> Maybe color.diffStyle=[normal/enhanced] and "enhanced" means this
>> feature for now?
>
> Hmph, I thought the intent of color.diff is "is the diff command
> itself is colored?"  In other words, color.diff=false should give
> you monochrome if you say "diff --word-diff", etc.

And by that understanding color.diffStyle is just natural?

>> The only option in the "diff" section related to color is diff.wsErrorHighlight
>> which has a very similar purpose, so "diff.colorMoved" would fit in that
>> scheme.

Note: The average user may not aware that diff/show/log are tiny wrappers
around the same backend for the heavy lifting.

> I didn't have "should diff output highlight whitespace errors?" in
> mind when I wrote the message you are responding to, but yes, that
> is quite similar to "should diff output show lines moved and lines
> deleted/added differently?".
>
>> So with these questions, I wonder if we want to color moved lines
>> as "color.diff.context" (i.e. plain white text in the normal coloring scheme)
>> This would serve the intended purpose of
>> dimming the attention to moved lines.
>
> Yes, but two points.
>
>  (1) We want to do so while making it obvious where the boundary
>      between two moved blocks of text whose destination (for
>      moved-deleted lines) or source (for moved-added lines) is.

>  (2) My message was an impression from using the code to review a
>      patch that is meant to be "move without changing other things".

Ok, glad you found it somewhat useful already.

>      For other purposes, there may be cases where moved ones may
>      want to be highlighted, not dimmed.

>> Regarding the last point of marking up adjacent blocks (which would
>> indicate that there is a coherency issue or just moving from different
>> places), we could highlight the last line of the previous block
>> and first line of the next block in their "normal" colors (i.e.
>> color.diff.old and color.diff.new).
>
> Hmm.  That is an interesting thought.

I'll try the implementation for that and see if it looks good.

Stefan Beller· May 27, 2017, 00:18 UTC · re: Stefan Beller · lore

[PATCH 0/1] Diff machine: highlight moved lines.

This is a new version of the latest patch of sb/diff-color-move.

With more tests:
 * for each mode;
 * check that diff.colorMoved is respected
 
And it is documented as well.

Stefan Beller (1):
  diff.c: color moved lines differently

 Documentation/config.txt       |  10 +-
 Documentation/diff-options.txt |  32 ++++
 color.h                        |   2 +
 diff.c                         | 342 +++++++++++++++++++++++++++++++++++--
 diff.h                         |  15 +-
 t/t4015-diff-whitespace.sh     | 373 +++++++++++++++++++++++++++++++++++++++++
 6 files changed, 760 insertions(+), 14 deletions(-)

Interdiff to what Junio has queued:

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 902d017c3b..73511a4603 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1051,12 +1051,9 @@ 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.
+diff.colorMoved::
+	If set moved lines in a diff are colored differently,
+	for details see '--color-moved' in linkgit:git-diff[1].
 
 color.diff.<slot>::
 	Use customized color for diff colorization.  `<slot>` specifies
@@ -1065,10 +1062,9 @@ 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), `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)
+	(highlighting whitespace errors), `oldMoved`, `newMoved`,
+	`oldMovedAlternative` and `newMovedAlternative` (See the '<mode>'
+	setting of '--color-moved' in linkgit:git-diff[1] for details).
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 89cc0f48de..25259dbbc3 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -231,6 +231,38 @@ ifdef::git-diff[]
 endif::git-diff[]
 	It is the same as `--color=never`.
 
+--color-moved[=<mode>]::
+	Moved lines of code are colored differently.
+ifdef::git-diff[]
+	It can be changed by the `diff.colorMoved` configuration setting.
+endif::git-diff[]
+	The <mode> defaults to 'no' if the option is not given
+	and to 'adjacentbounds' if the option with no mode is given.
+	The mode must be one of:
++
+--
+no::
+	Moved lines are not highlighted.
+nobounds::
+	Any line that is added in on location and was removed
+	in another location will be colored with 'color.diff.newmoved'.
+	Any line that is removed in on location and was added
+	in another location will be colored with 'color.diff.oldmoved'.
+allbounds::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected and the first and last line of a block will be highlighted
+	using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+adjacentbounds::
+	The same as 'allbounds' except that highlighting is only performed
+	at adjacent block boundaries of blocks that have the same sign.
+alternate::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected. If moved blocks are adjacent mark one of them with the
+	alternative move color using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+--
+
 --word-diff[=<mode>]::
 	Show a word diff, using the <mode> to delimit changed words.
 	By default, words are delimited by whitespace; see
diff --git a/color.h b/color.h
index 90627650fc..04b3b87929 100644
--- a/color.h
+++ b/color.h
@@ -42,6 +42,8 @@ struct strbuf;
 #define GIT_COLOR_BG_BLUE	"\033[44m"
 #define GIT_COLOR_BG_MAGENTA	"\033[45m"
 #define GIT_COLOR_BG_CYAN	"\033[46m"
+#define GIT_COLOR_DI_IT_CYAN	"\033[2;3;36m"
+#define GIT_COLOR_DI_IT_MAGENTA	"\033[2;3;35m"
 
 /* A special value meaning "no color selected" */
 #define GIT_COLOR_NIL "NIL"
diff --git a/diff.c b/diff.c
index 40cccafb67..efd2530a89 100644
--- a/diff.c
+++ b/diff.c
@@ -56,10 +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 */
+	GIT_COLOR_DI_IT_MAGENTA,/* OLD_MOVED */
+	GIT_COLOR_BG_RED,	/* OLD_MOVED ALTERNATIVE */
+	GIT_COLOR_DI_IT_CYAN,	/* NEW_MOVED */
+	GIT_COLOR_BG_GREEN,	/* NEW_MOVED ALTERNATIVE */
 };
 
 static NORETURN void die_want_option(const char *option_name)
@@ -241,14 +241,33 @@ int git_diff_heuristic_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
+static int parse_color_moved(const char *arg)
+{
+	if (!strcmp(arg, "no"))
+		return MOVED_LINES_NO;
+	else if (!strcmp(arg, "nobounds"))
+		return MOVED_LINES_BOUNDARY_NO;
+	else if (!strcmp(arg, "allbounds"))
+		return MOVED_LINES_BOUNDARY_ALL;
+	else if (!strcmp(arg, "adjacentbounds"))
+		return MOVED_LINES_BOUNDARY_ADJACENT;
+	else if (!strcmp(arg, "alternate"))
+		return MOVED_LINES_ALTERNATE;
+	else
+		return -1;
+}
+
 int git_diff_ui_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
 		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);
+	if (!strcmp(var, "diff.colormoved")) {
+		int cm = parse_color_moved(value);
+		if (cm < 0)
+			return -1;
+		diff_color_moved_default = cm;
 		return 0;
 	}
 	if (!strcmp(var, "diff.context")) {
@@ -652,41 +671,69 @@ static void add_lines_to_move_detection(struct diff_options *o,
 	}
 }
 
+static void mark_color_as_moved_single_line(struct diff_options *o,
+					    struct diff_line *l, int alt_color)
+{
+	switch (l->sign) {
+	case '+':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_NEW_MOVED + alt_color);
+		break;
+	case '-':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_OLD_MOVED + alt_color);
+		break;
+	default:
+		die("BUG: we should have continued earlier?");
+	}
+}
+
 static void mark_color_as_moved(struct diff_options *o,
 				struct hashmap *add_lines,
 				struct hashmap *del_lines)
 {
 	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	struct diff_line *prev_line = NULL;
 	int pmb_nr = 0, pmb_alloc = 0;
-	int use_alt_color = 0;
-	int n;
+	int n, flipped_block = 0;
 
 	for (n = 0; n < o->line_buffer_nr; n++) {
 		struct hashmap *hm = NULL;
 		struct moved_entry *key;
 		struct moved_entry *match = NULL;
 		struct diff_line *l = &o->line_buffer[n];
-		int i, lp, rp;
+		int i, lp, rp, adjacent_blocks = 0;
 
+		/* Check for any match to color it as a move. */
 		switch (l->sign) {
 		case '+':
 			hm = del_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
 			break;
 		case '-':
 			hm = add_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
 			break;
-		default:
-			use_alt_color = 0;
-			pmb_nr = 0; /* no running sets */
+		default: ;
+		}
+
+		if (!match) {
+			pmb_nr = 0;
+			if (prev_line &&
+			    o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+				mark_color_as_moved_single_line(o, prev_line, 1);
+			prev_line = NULL;
 			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)
+		if (o->color_moved == MOVED_LINES_BOUNDARY_NO) {
+			mark_color_as_moved_single_line(o, l, 0);
 			continue;
+		}
 
 		/* Check any potential block runs, advance each or nullify */
 		for (i = 0; i < pmb_nr; i++) {
@@ -701,7 +748,7 @@ static void mark_color_as_moved(struct diff_options *o,
 			}
 		}
 
-		/* Shrink the set to the remaining runs */
+		/* Shrink the set of potential block to the remaining running */
 		for (lp = 0, rp = pmb_nr - 1; lp <= rp;) {
 			while (lp < pmb_nr && pmb[lp])
 				lp++;
@@ -719,34 +766,44 @@ static void mark_color_as_moved(struct diff_options *o,
 			}
 		}
 
-		if (rp > -1) {
-			/* Remember the number of running sets */
-			pmb_nr = rp + 1;
-		} else {
-			/* Toggle color */
-			use_alt_color = (use_alt_color + 1) % 2;
+		/* Remember the number of running sets */
+		pmb_nr = rp + 1;
 
-			/* Build up a new set */
-			pmb_nr = 0;
+		if (pmb_nr == 0) {
+			/*
+			 * This line is the start of a new block.
+			 * Setup the set of potential blocks.
+			 */
 			for (; match; match = hashmap_get_next(hm, match)) {
 				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
 				pmb[pmb_nr++] = match;
 			}
+
+			if (o->color_moved == MOVED_LINES_BOUNDARY_ALL) {
+				adjacent_blocks = 1;
+			} else {
+				/* Check if two blocks are adjacent */
+				adjacent_blocks = prev_line &&
+						  prev_line->sign == l->sign;
+			}
 		}
 
-		switch (l->sign) {
-		case '+':
-			l->set = diff_get_color_opt(o,
-				DIFF_FILE_NEW_MOVED + use_alt_color);
-			break;
-		case '-':
-			l->set = diff_get_color_opt(o,
-				DIFF_FILE_OLD_MOVED + use_alt_color);
-			break;
-		default:
-			die("BUG: we should have continued earlier?");
+		if (o->color_moved == MOVED_LINES_ALTERNATE) {
+			if (adjacent_blocks)
+				flipped_block = (flipped_block + 1) % 2;
+			mark_color_as_moved_single_line(o, l, flipped_block);
+		} else {
+			/* MOVED_LINES_BOUNDARY_{ADJACENT, ALL} */
+			mark_color_as_moved_single_line(o, l, adjacent_blocks);
+			if (adjacent_blocks && prev_line)
+				prev_line->set = l->set;
 		}
+
+		prev_line = l;
 	}
+	if (prev_line && o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+		mark_color_as_moved_single_line(o, prev_line, 1);
+
 	free(pmb);
 }
 
@@ -4291,10 +4348,18 @@ 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;
+		if (diff_color_moved_default)
+			options->color_moved = diff_color_moved_default;
+		else
+			options->color_moved = MOVED_LINES_BOUNDARY_ADJACENT;
 	else if (!strcmp(arg, "--no-color-moved"))
-		options->color_moved = 0;
-	else if (!strcmp(arg, "--color-words")) {
+		options->color_moved = MOVED_LINES_NO;
+	else if (skip_prefix(arg, "--color-moved=", &arg)) {
+		int cm = parse_color_moved(arg);
+		if (cm < 0)
+			die("bad --color-moved argument: %s", arg);
+		options->color_moved = cm;
+	} else if (!strcmp(arg, "--color-words")) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
 	}
diff --git a/diff.h b/diff.h
index c6d806c6b5..d9fbafd383 100644
--- a/diff.h
+++ b/diff.h
@@ -230,7 +230,13 @@ struct diff_options {
 	struct diff_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
 
-	int color_moved;
+	enum {
+		MOVED_LINES_NO = 0,
+		MOVED_LINES_BOUNDARY_NO = 1,
+		MOVED_LINES_BOUNDARY_ALL = 2,
+		MOVED_LINES_BOUNDARY_ADJACENT = 3,
+		MOVED_LINES_ALTERNATE = 4,
+	} color_moved;
 };
 
 /* Emit [line_prefix] [set] line [reset] */
diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh
index 0e92bf94bf..d4bd082af7 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -984,6 +984,8 @@ test_expect_success 'detect moved code, complete file' '
 	git add test.c &&
 	git commit -m "add main function" &&
 	git mv test.c main.c &&
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
 	git diff HEAD --color-moved --no-renames | test_decode_color >actual &&
 	cat >expected <<-\EOF &&
 	<BOLD>diff --git a/main.c b/main.c<RESET>
@@ -1081,6 +1083,10 @@ test_expect_success 'detect moved code, inside file' '
 			bar();
 		}
 	EOF
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
+	test_config color.diff.oldMovedAlternative "bold red" &&
+	test_config color.diff.newMovedAlternative "bold green" &&
 	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/main.c b/main.c<RESET>
@@ -1125,79 +1131,179 @@ test_expect_success 'detect moved code, inside file' '
 '
 
 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();
-		}
+	git reset --hard &&
+	cat <<-\EOF >lines.txt &&
+		line 1
+		line 2
+		line 3
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 10
+		line 11
+		line 12
+		line 13
+		line 14
+		line 15
+		line 16
 	EOF
-	cat <<-\EOF >test.c &&
-		#include<stdio.h>
-		int bar()
-		{
-			printf("Hello World, but different\n");
-		}
+	git add lines.txt &&
+	git commit -m "add poetry" &&
+	cat <<-\EOF >lines.txt &&
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 1
+		line 2
+		line 3
+		line 14
+		line 15
+		line 16
+		line 10
+		line 11
+		line 12
+		line 13
+	EOF
+	test_config color.diff.oldMoved "magenta" &&
+	test_config color.diff.newMoved "cyan" &&
+	test_config color.diff.oldMovedAlternative "blue" &&
+	test_config color.diff.newMovedAlternative "yellow" &&
 
-		int secure_foo(struct user *u)
-		{
-			foo(u);
-			if (!u->is_allowed_foo)
-				return;
-		}
 
-		int another_function()
-		{
-			bar();
-		}
+	git diff HEAD --no-renames --color-moved=nobounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+		<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+		<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+		<BOLD>--- a/lines.txt<RESET>
+		<BOLD>+++ b/lines.txt<RESET>
+		<CYAN>@@ -1,16 +1,16 @@<RESET>
+		<MAGENTA>-line 1<RESET>
+		<MAGENTA>-line 2<RESET>
+		<MAGENTA>-line 3<RESET>
+		 line 4<RESET>
+		 line 5<RESET>
+		 line 6<RESET>
+		 line 7<RESET>
+		 line 8<RESET>
+		 line 9<RESET>
+		<CYAN>+<RESET><CYAN>line 1<RESET>
+		<CYAN>+<RESET><CYAN>line 2<RESET>
+		<CYAN>+<RESET><CYAN>line 3<RESET>
+		<CYAN>+<RESET><CYAN>line 14<RESET>
+		<CYAN>+<RESET><CYAN>line 15<RESET>
+		<CYAN>+<RESET><CYAN>line 16<RESET>
+		 line 10<RESET>
+		 line 11<RESET>
+		 line 12<RESET>
+		 line 13<RESET>
+		<MAGENTA>-line 14<RESET>
+		<MAGENTA>-line 15<RESET>
+		<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	git diff HEAD --no-renames --color-moved=adjacentbounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<CYAN>+<RESET><CYAN>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<MAGENTA>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<MAGENTA>-line 16<RESET>
 	EOF
+	test_cmp expected actual &&
+
+	test_config diff.colorMoved alternate &&
 	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>
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<CYAN>+<RESET><CYAN>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<YELLOW>+<RESET><YELLOW>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<BLUE>-line 14<RESET>
+	<BLUE>-line 15<RESET>
+	<BLUE>-line 16<RESET>
 	EOF
+	test_cmp expected actual &&
 
+	test_config diff.colorMoved allbounds &&
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<BLUE>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<BLUE>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<YELLOW>+<RESET><YELLOW>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<BLUE>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<BLUE>-line 16<RESET>
+	EOF
 	test_cmp expected actual
 '
 

-- 
2.13.0.17.gab62347cd9

Stefan Beller· May 27, 2017, 00:18 UTC · re: Stefan Beller · lore

[PATCH 1/1] diff.c: color moved lines differently

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OM]  -        if (!is_authorized_user())
    [OM]  -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OM]  -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NM]  +        sensitive_stuff(spanning,
    [NM]  +                        multiple,
    [NM]  +                        lines);
    [NM]  +}

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OMA] -        if (!is_authorized_user())
    [OMA] -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OMA] -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NMA] +        sensitive_stuff(spanning,
    [NMA] +                        multiple,
    [NMA] +                        lines);
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NMA] +}

Helped-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/config.txt       |  10 +-
 Documentation/diff-options.txt |  32 ++++
 color.h                        |   2 +
 diff.c                         | 342 +++++++++++++++++++++++++++++++++++--
 diff.h                         |  15 +-
 t/t4015-diff-whitespace.sh     | 373 +++++++++++++++++++++++++++++++++++++++++
 6 files changed, 760 insertions(+), 14 deletions(-)

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 475e874d51..73511a4603 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1051,14 +1051,20 @@ 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.
 
+diff.colorMoved::
+	If set moved lines in a diff are colored differently,
+	for details see '--color-moved' in linkgit:git-diff[1].
+
 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`, `newMoved`,
+	`oldMovedAlternative` and `newMovedAlternative` (See the '<mode>'
+	setting of '--color-moved' in linkgit:git-diff[1] for details).
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 89cc0f48de..25259dbbc3 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -231,6 +231,38 @@ ifdef::git-diff[]
 endif::git-diff[]
 	It is the same as `--color=never`.
 
+--color-moved[=<mode>]::
+	Moved lines of code are colored differently.
+ifdef::git-diff[]
+	It can be changed by the `diff.colorMoved` configuration setting.
+endif::git-diff[]
+	The <mode> defaults to 'no' if the option is not given
+	and to 'adjacentbounds' if the option with no mode is given.
+	The mode must be one of:
++
+--
+no::
+	Moved lines are not highlighted.
+nobounds::
+	Any line that is added in on location and was removed
+	in another location will be colored with 'color.diff.newmoved'.
+	Any line that is removed in on location and was added
+	in another location will be colored with 'color.diff.oldmoved'.
+allbounds::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected and the first and last line of a block will be highlighted
+	using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+adjacentbounds::
+	The same as 'allbounds' except that highlighting is only performed
+	at adjacent block boundaries of blocks that have the same sign.
+alternate::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected. If moved blocks are adjacent mark one of them with the
+	alternative move color using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+--
+
 --word-diff[=<mode>]::
 	Show a word diff, using the <mode> to delimit changed words.
 	By default, words are delimited by whitespace; see
diff --git a/color.h b/color.h
index 90627650fc..04b3b87929 100644
--- a/color.h
+++ b/color.h
@@ -42,6 +42,8 @@ struct strbuf;
 #define GIT_COLOR_BG_BLUE	"\033[44m"
 #define GIT_COLOR_BG_MAGENTA	"\033[45m"
 #define GIT_COLOR_BG_CYAN	"\033[46m"
+#define GIT_COLOR_DI_IT_CYAN	"\033[2;3;36m"
+#define GIT_COLOR_DI_IT_MAGENTA	"\033[2;3;35m"
 
 /* A special value meaning "no color selected" */
 #define GIT_COLOR_NIL "NIL"
diff --git a/diff.c b/diff.c
index a3c16ef827..efd2530a89 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_DI_IT_MAGENTA,/* OLD_MOVED */
+	GIT_COLOR_BG_RED,	/* OLD_MOVED ALTERNATIVE */
+	GIT_COLOR_DI_IT_CYAN,	/* NEW_MOVED */
+	GIT_COLOR_BG_GREEN,	/* NEW_MOVED ALTERNATIVE */
 };
 
 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;
 }
 
@@ -228,12 +241,35 @@ int git_diff_heuristic_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
+static int parse_color_moved(const char *arg)
+{
+	if (!strcmp(arg, "no"))
+		return MOVED_LINES_NO;
+	else if (!strcmp(arg, "nobounds"))
+		return MOVED_LINES_BOUNDARY_NO;
+	else if (!strcmp(arg, "allbounds"))
+		return MOVED_LINES_BOUNDARY_ALL;
+	else if (!strcmp(arg, "adjacentbounds"))
+		return MOVED_LINES_BOUNDARY_ADJACENT;
+	else if (!strcmp(arg, "alternate"))
+		return MOVED_LINES_ALTERNATE;
+	else
+		return -1;
+}
+
 int git_diff_ui_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
 		diff_use_color_default = git_config_colorbool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.colormoved")) {
+		int cm = parse_color_moved(value);
+		if (cm < 0)
+			return -1;
+		diff_color_moved_default = cm;
+		return 0;
+	}
 	if (!strcmp(var, "diff.context")) {
 		diff_context_default = git_config_int(var, value);
 		if (diff_context_default < 0)
@@ -354,6 +390,88 @@ 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 diff_line *line;
+	struct moved_entry *next_line;
+};
+
+static void get_ws_cleaned_string(const struct diff_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 diff_line_cmp_no_ws(const struct diff_line *a,
+					 const struct diff_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 diff_line_cmp(const struct diff_line *a,
+				   const struct diff_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 diff_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 diff_line_cmp_no_ws(a->line, b->line, keydata);
+}
+
+static unsigned get_line_hash(struct diff_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 diff_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 +634,179 @@ 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 hashmap *add_lines,
+					struct hashmap *del_lines)
+{
+	struct moved_entry *prev_line = NULL;
+
+	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 = add_lines;
+			break;
+		case '-':
+			sign = '-';
+			hm = del_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_single_line(struct diff_options *o,
+					    struct diff_line *l, int alt_color)
+{
+	switch (l->sign) {
+	case '+':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_NEW_MOVED + alt_color);
+		break;
+	case '-':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_OLD_MOVED + alt_color);
+		break;
+	default:
+		die("BUG: we should have continued earlier?");
+	}
+}
+
+static void mark_color_as_moved(struct diff_options *o,
+				struct hashmap *add_lines,
+				struct hashmap *del_lines)
+{
+	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	struct diff_line *prev_line = NULL;
+	int pmb_nr = 0, pmb_alloc = 0;
+	int n, flipped_block = 0;
+
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		struct hashmap *hm = NULL;
+		struct moved_entry *key;
+		struct moved_entry *match = NULL;
+		struct diff_line *l = &o->line_buffer[n];
+		int i, lp, rp, adjacent_blocks = 0;
+
+		/* Check for any match to color it as a move. */
+		switch (l->sign) {
+		case '+':
+			hm = del_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
+			break;
+		case '-':
+			hm = add_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
+			break;
+		default: ;
+		}
+
+		if (!match) {
+			pmb_nr = 0;
+			if (prev_line &&
+			    o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+				mark_color_as_moved_single_line(o, prev_line, 1);
+			prev_line = NULL;
+			continue;
+		}
+
+		if (o->color_moved == MOVED_LINES_BOUNDARY_NO) {
+			mark_color_as_moved_single_line(o, l, 0);
+			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 &&
+			    !diff_line_cmp(pnext->line, l, o)) {
+				pmb[i] = p->next_line;
+			} else {
+				pmb[i] = NULL;
+			}
+		}
+
+		/* Shrink the set of potential block to the remaining running */
+		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++;
+			}
+		}
+
+		/* Remember the number of running sets */
+		pmb_nr = rp + 1;
+
+		if (pmb_nr == 0) {
+			/*
+			 * This line is the start of a new block.
+			 * Setup the set of potential blocks.
+			 */
+			for (; match; match = hashmap_get_next(hm, match)) {
+				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
+				pmb[pmb_nr++] = match;
+			}
+
+			if (o->color_moved == MOVED_LINES_BOUNDARY_ALL) {
+				adjacent_blocks = 1;
+			} else {
+				/* Check if two blocks are adjacent */
+				adjacent_blocks = prev_line &&
+						  prev_line->sign == l->sign;
+			}
+		}
+
+		if (o->color_moved == MOVED_LINES_ALTERNATE) {
+			if (adjacent_blocks)
+				flipped_block = (flipped_block + 1) % 2;
+			mark_color_as_moved_single_line(o, l, flipped_block);
+		} else {
+			/* MOVED_LINES_BOUNDARY_{ADJACENT, ALL} */
+			mark_color_as_moved_single_line(o, l, adjacent_blocks);
+			if (adjacent_blocks && prev_line)
+				prev_line->set = l->set;
+		}
+
+		prev_line = l;
+	}
+	if (prev_line && o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+		mark_color_as_moved_single_line(o, prev_line, 1);
+
+	free(pmb);
+}
+
 static void emit_diff_line(struct diff_options *o,
 			   struct diff_line *e)
 {
@@ -3518,6 +3809,8 @@ 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)
@@ -3627,6 +3920,9 @@ 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)
@@ -4051,7 +4347,19 @@ int diff_opt_parse(struct diff_options *options,
 	}
 	else if (!strcmp(arg, "--no-color"))
 		options->use_color = 0;
-	else if (!strcmp(arg, "--color-words")) {
+	else if (!strcmp(arg, "--color-moved"))
+		if (diff_color_moved_default)
+			options->color_moved = diff_color_moved_default;
+		else
+			options->color_moved = MOVED_LINES_BOUNDARY_ADJACENT;
+	else if (!strcmp(arg, "--no-color-moved"))
+		options->color_moved = MOVED_LINES_NO;
+	else if (skip_prefix(arg, "--color-moved=", &arg)) {
+		int cm = parse_color_moved(arg);
+		if (cm < 0)
+			die("bad --color-moved argument: %s", arg);
+		options->color_moved = cm;
+	} else if (!strcmp(arg, "--color-words")) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
 	}
@@ -4856,16 +5164,9 @@ 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_diff_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)
+		o->use_buffer = 1;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
@@ -4874,6 +5175,24 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
+		if (o->color_moved) {
+			struct hashmap add_lines, del_lines;
+			unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+
+			hashmap_init(&del_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+			hashmap_init(&add_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+
+			add_lines_to_move_detection(o, &add_lines, &del_lines);
+			mark_color_as_moved(o, &add_lines, &del_lines);
+
+			hashmap_free(&add_lines, 0);
+			hashmap_free(&del_lines, 0);
+		}
+
 		for (i = 0; i < o->line_buffer_nr; i++)
 			emit_diff_line(o, &o->line_buffer[i]);
 
@@ -4962,6 +5281,7 @@ 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 be51e8f867..d9fbafd383 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;
@@ -228,6 +229,14 @@ struct diff_options {
 
 	struct diff_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
+
+	enum {
+		MOVED_LINES_NO = 0,
+		MOVED_LINES_BOUNDARY_NO = 1,
+		MOVED_LINES_BOUNDARY_ALL = 2,
+		MOVED_LINES_BOUNDARY_ADJACENT = 3,
+		MOVED_LINES_ALTERNATE = 4,
+	} color_moved;
 };
 
 /* Emit [line_prefix] [set] line [reset] */
@@ -243,7 +252,11 @@ 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..d4bd082af7 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -972,4 +972,377 @@ 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 &&
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
+	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
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
+	test_config color.diff.oldMovedAlternative "bold red" &&
+	test_config color.diff.newMovedAlternative "bold green" &&
+	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' '
+	git reset --hard &&
+	cat <<-\EOF >lines.txt &&
+		line 1
+		line 2
+		line 3
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 10
+		line 11
+		line 12
+		line 13
+		line 14
+		line 15
+		line 16
+	EOF
+	git add lines.txt &&
+	git commit -m "add poetry" &&
+	cat <<-\EOF >lines.txt &&
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 1
+		line 2
+		line 3
+		line 14
+		line 15
+		line 16
+		line 10
+		line 11
+		line 12
+		line 13
+	EOF
+	test_config color.diff.oldMoved "magenta" &&
+	test_config color.diff.newMoved "cyan" &&
+	test_config color.diff.oldMovedAlternative "blue" &&
+	test_config color.diff.newMovedAlternative "yellow" &&
+
+
+	git diff HEAD --no-renames --color-moved=nobounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+		<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+		<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+		<BOLD>--- a/lines.txt<RESET>
+		<BOLD>+++ b/lines.txt<RESET>
+		<CYAN>@@ -1,16 +1,16 @@<RESET>
+		<MAGENTA>-line 1<RESET>
+		<MAGENTA>-line 2<RESET>
+		<MAGENTA>-line 3<RESET>
+		 line 4<RESET>
+		 line 5<RESET>
+		 line 6<RESET>
+		 line 7<RESET>
+		 line 8<RESET>
+		 line 9<RESET>
+		<CYAN>+<RESET><CYAN>line 1<RESET>
+		<CYAN>+<RESET><CYAN>line 2<RESET>
+		<CYAN>+<RESET><CYAN>line 3<RESET>
+		<CYAN>+<RESET><CYAN>line 14<RESET>
+		<CYAN>+<RESET><CYAN>line 15<RESET>
+		<CYAN>+<RESET><CYAN>line 16<RESET>
+		 line 10<RESET>
+		 line 11<RESET>
+		 line 12<RESET>
+		 line 13<RESET>
+		<MAGENTA>-line 14<RESET>
+		<MAGENTA>-line 15<RESET>
+		<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	git diff HEAD --no-renames --color-moved=adjacentbounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<CYAN>+<RESET><CYAN>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<MAGENTA>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	test_config diff.colorMoved alternate &&
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<CYAN>+<RESET><CYAN>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<YELLOW>+<RESET><YELLOW>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<BLUE>-line 14<RESET>
+	<BLUE>-line 15<RESET>
+	<BLUE>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	test_config diff.colorMoved allbounds &&
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<BLUE>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<BLUE>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<YELLOW>+<RESET><YELLOW>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<BLUE>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<BLUE>-line 16<RESET>
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'move detection does not mess up colored words' '
+	cat <<-\EOF >text.txt &&
+	Lorem Ipsum is simply dummy text of the printing and typesetting industry.
+	EOF
+	git add text.txt &&
+	git commit -a -m "clean state" &&
+	cat <<-\EOF >text.txt &&
+	simply Lorem Ipsum dummy is text of the typesetting and printing industry.
+	EOF
+	git diff --color-moved --word-diff >actual &&
+	git diff --word-diff >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'move detection with submodules' '
+	test_create_repo bananas &&
+	echo ripe >bananas/recipe &&
+	git -C bananas add recipe &&
+	test_commit fruit &&
+	test_commit -C bananas recipe &&
+	git submodule add ./bananas &&
+	git add bananas &&
+	git commit -a -m "bananas are like a heavy library?" &&
+	echo foul >bananas/recipe &&
+	echo ripe >fruit.t &&
+
+	git diff --submodule=diff --color-moved >actual &&
+
+	# no move detection as the moved line is across repository boundaries.
+	test_decode_color <actual >decoded_actual &&
+	! grep BGREEN decoded_actual &&
+	! grep BRED decoded_actual &&
+
+	# nor did we mess with it another way
+	git diff --submodule=diff | test_decode_color >expect &&
+	test_cmp expect decoded_actual
+'
+
 test_done

-- 
2.13.0.17.gab62347cd9

Philip Oakley· May 27, 2017, 07:05 UTC · re: Stefan Beller · lore

Re: [PATCH 1/1] diff.c: color moved lines differently

a couple of mispellings in the doc parts:
  s/on location/one location/
[code not checked]
----- Original Message ----- 
From: "Stefan Beller" <sbeller@google.com>
Subject: [PATCH 1/1] diff.c: color moved lines differently

> When a patch consists mostly of moving blocks of code around, it can
> be quite tedious to ensure that the blocks are moved verbatim, and not
> undesirably modified in the move. To that end, color blocks that are
> moved within the same patch differently. For example (OM, del, add,
> and NM are different colors):
>
>    [OM]  -void sensitive_stuff(void)
>    [OM]  -{
>    [OM]  -        if (!is_authorized_user())
>    [OM]  -                die("unauthorized");
>    [OM]  -        sensitive_stuff(spanning,
>    [OM]  -                        multiple,
>    [OM]  -                        lines);
>    [OM]  -}
>
>           void another_function()
>           {
>    [del] -        printf("foo");
>    [add] +        printf("bar");
>           }
>
>    [NM]  +void sensitive_stuff(void)
>    [NM]  +{
>    [NM]  +        if (!is_authorized_user())
>    [NM]  +                die("unauthorized");
>    [NM]  +        sensitive_stuff(spanning,
>    [NM]  +                        multiple,
>    [NM]  +                        lines);
>    [NM]  +}
>
> However adjacent blocks may be problematic. For example, in this
> potentially malicious patch, the swapping of blocks can be spotted:
>
>    [OM]  -void sensitive_stuff(void)
>    [OM]  -{
>    [OMA] -        if (!is_authorized_user())
>    [OMA] -                die("unauthorized");
>    [OM]  -        sensitive_stuff(spanning,
>    [OM]  -                        multiple,
>    [OM]  -                        lines);
>    [OMA] -}
>
>           void another_function()
>           {
>    [del] -        printf("foo");
>    [add] +        printf("bar");
>           }
>
>    [NM]  +void sensitive_stuff(void)
>    [NM]  +{
>    [NMA] +        sensitive_stuff(spanning,
>    [NMA] +                        multiple,
>    [NMA] +                        lines);
>    [NM]  +        if (!is_authorized_user())
>    [NM]  +                die("unauthorized");
>    [NMA] +}
>
> If the moved code is larger, it is easier to hide some permutation in the
> code, which is why some alternative coloring is needed.
>
> As the reviewers attention should be brought to the places, where the
> difference is introduced to the moved code, we cannot just have one new
> color for all of moved code.
>
> First I implemented an alternative design, which would try to fingerprint
> a line by its neighbors to detect if we are in a block or at the boundary.
> This idea iss error prone as it inspected each line and its neighboring
> lines to determine if the line was (a) moved and (b) if was deep inside
> a hunk by having matching neighboring lines. This is unreliable as the
> we can construct hunks which have equal neighbors that just exceed the
> number of lines inspected. (Think of 'AXYZBXYZCXYZD..' with each letter
> as a line, that is permutated to AXYZCXYZBXYZD..').
>
> Instead this provides a dynamic programming greedy algorithm that finds
> the largest moved hunk and then has several modes on highlighting bounds.
>
> A note on the options '--submodule=diff' and '--color-words/--word-diff':
> In the conversion to use emit_line in the prior patches both submodules
> as well as word diff output carefully chose to call emit_line with sign=0.
> All output with sign=0 is ignored for move detection purposes in this
> patch, such that no weird looking output will be generated for these
> cases. This leads to another thought: We could pass on '--color-moved' to
> submodules such that they color up moved lines for themselves. If we'd do
> so only line moves within a repository boundary are marked up.
>
> Helped-by: Jonathan Tan <jonathantanmy@google.com>
> Signed-off-by: Stefan Beller <sbeller@google.com>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> ---
> Documentation/config.txt       |  10 +-
> Documentation/diff-options.txt |  32 ++++
> color.h                        |   2 +
> diff.c                         | 342 +++++++++++++++++++++++++++++++++++--
> diff.h                         |  15 +-
> t/t4015-diff-whitespace.sh     | 373 
> +++++++++++++++++++++++++++++++++++++++++
> 6 files changed, 760 insertions(+), 14 deletions(-)
>
> diff --git a/Documentation/config.txt b/Documentation/config.txt
> index 475e874d51..73511a4603 100644
> --- a/Documentation/config.txt
> +++ b/Documentation/config.txt
> @@ -1051,14 +1051,20 @@ 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.
>
> +diff.colorMoved::
> + If set moved lines in a diff are colored differently,
> + for details see '--color-moved' in linkgit:git-diff[1].
> +
> 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`, `newMoved`,
> + `oldMovedAlternative` and `newMovedAlternative` (See the '<mode>'
> + setting of '--color-moved' in linkgit:git-diff[1] for details).
>
> color.decorate.<slot>::
>  Use customized color for 'git log --decorate' output.  `<slot>` is one
> diff --git a/Documentation/diff-options.txt 
> b/Documentation/diff-options.txt
> index 89cc0f48de..25259dbbc3 100644
> --- a/Documentation/diff-options.txt
> +++ b/Documentation/diff-options.txt
> @@ -231,6 +231,38 @@ ifdef::git-diff[]
> endif::git-diff[]
>  It is the same as `--color=never`.
>
> +--color-moved[=<mode>]::
> + Moved lines of code are colored differently.
> +ifdef::git-diff[]
> + It can be changed by the `diff.colorMoved` configuration setting.
> +endif::git-diff[]
> + The <mode> defaults to 'no' if the option is not given
> + and to 'adjacentbounds' if the option with no mode is given.
> + The mode must be one of:
> ++
> +--
> +no::
> + Moved lines are not highlighted.
> +nobounds::
> + Any line that is added in on location and was removed

s/on location/one location/

> + in another location will be colored with 'color.diff.newmoved'.
> + Any line that is removed in on location and was added

s/on location/one location/

> + in another location will be colored with 'color.diff.oldmoved'.
> +allbounds::
> + Based on 'nobounds'. Additionally blocks of moved code are
> + detected and the first and last line of a block will be highlighted
> + using 'color.diff.newMovedAlternate' or
> + 'color.diff.oldMovedAlternate'.
> +adjacentbounds::
> + The same as 'allbounds' except that highlighting is only performed
> + at adjacent block boundaries of blocks that have the same sign.
> +alternate::
> + Based on 'nobounds'. Additionally blocks of moved code are
> + detected. If moved blocks are adjacent mark one of them with the
> + alternative move color using 'color.diff.newMovedAlternate' or
> + 'color.diff.oldMovedAlternate'.
> +--
> +
> --word-diff[=<mode>]::
>  Show a word diff, using the <mode> to delimit changed words.
>  By default, words are delimited by whitespace; see

> diff --git a/color.h b/color.h
> index 90627650fc..04b3b87929 100644
> --- a/color.h
> +++ b/color.h
> @@ -42,6 +42,8 @@ struct strbuf;
> #define GIT_COLOR_BG_BLUE "\033[44m"
> #define GIT_COLOR_BG_MAGENTA "\033[45m"
> #define GIT_COLOR_BG_CYAN "\033[46m"
> +#define GIT_COLOR_DI_IT_CYAN "\033[2;3;36m"
> +#define GIT_COLOR_DI_IT_MAGENTA "\033[2;3;35m"
>
> /* A special value meaning "no color selected" */
> #define GIT_COLOR_NIL "NIL"
> diff --git a/diff.c b/diff.c
> index a3c16ef827..efd2530a89 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_DI_IT_MAGENTA,/* OLD_MOVED */
> + GIT_COLOR_BG_RED, /* OLD_MOVED ALTERNATIVE */
> + GIT_COLOR_DI_IT_CYAN, /* NEW_MOVED */
> + GIT_COLOR_BG_GREEN, /* NEW_MOVED ALTERNATIVE */
> };
>
> 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;
> }
>
> @@ -228,12 +241,35 @@ int git_diff_heuristic_config(const char *var, const 
> char *value, void *cb)
>  return 0;
> }
>
> +static int parse_color_moved(const char *arg)
> +{
> + if (!strcmp(arg, "no"))
> + return MOVED_LINES_NO;
> + else if (!strcmp(arg, "nobounds"))
> + return MOVED_LINES_BOUNDARY_NO;
> + else if (!strcmp(arg, "allbounds"))
> + return MOVED_LINES_BOUNDARY_ALL;
> + else if (!strcmp(arg, "adjacentbounds"))
> + return MOVED_LINES_BOUNDARY_ADJACENT;
> + else if (!strcmp(arg, "alternate"))
> + return MOVED_LINES_ALTERNATE;
> + else
> + return -1;
> +}
> +
> int git_diff_ui_config(const char *var, const char *value, void *cb)
> {
>  if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
>  diff_use_color_default = git_config_colorbool(var, value);
>  return 0;
>  }
> + if (!strcmp(var, "diff.colormoved")) {
> + int cm = parse_color_moved(value);
> + if (cm < 0)
> + return -1;
> + diff_color_moved_default = cm;
> + return 0;
> + }
>  if (!strcmp(var, "diff.context")) {
>  diff_context_default = git_config_int(var, value);
>  if (diff_context_default < 0)
> @@ -354,6 +390,88 @@ 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 diff_line *line;
> + struct moved_entry *next_line;
> +};
> +
> +static void get_ws_cleaned_string(const struct diff_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 diff_line_cmp_no_ws(const struct diff_line *a,
> + const struct diff_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 diff_line_cmp(const struct diff_line *a,
> +    const struct diff_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 diff_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 diff_line_cmp_no_ws(a->line, b->line, keydata);
> +}
> +
> +static unsigned get_line_hash(struct diff_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 diff_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 +634,179 @@ 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 hashmap *add_lines,
> + struct hashmap *del_lines)
> +{
> + struct moved_entry *prev_line = NULL;
> +
> + 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 = add_lines;
> + break;
> + case '-':
> + sign = '-';
> + hm = del_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_single_line(struct diff_options *o,
> +     struct diff_line *l, int alt_color)
> +{
> + switch (l->sign) {
> + case '+':
> + l->set = diff_get_color_opt(o,
> + DIFF_FILE_NEW_MOVED + alt_color);
> + break;
> + case '-':
> + l->set = diff_get_color_opt(o,
> + DIFF_FILE_OLD_MOVED + alt_color);
> + break;
> + default:
> + die("BUG: we should have continued earlier?");
> + }
> +}
> +
> +static void mark_color_as_moved(struct diff_options *o,
> + struct hashmap *add_lines,
> + struct hashmap *del_lines)
> +{
> + struct moved_entry **pmb = NULL; /* potentially moved blocks */
> + struct diff_line *prev_line = NULL;
> + int pmb_nr = 0, pmb_alloc = 0;
> + int n, flipped_block = 0;
> +
> + for (n = 0; n < o->line_buffer_nr; n++) {
> + struct hashmap *hm = NULL;
> + struct moved_entry *key;
> + struct moved_entry *match = NULL;
> + struct diff_line *l = &o->line_buffer[n];
> + int i, lp, rp, adjacent_blocks = 0;
> +
> + /* Check for any match to color it as a move. */
> + switch (l->sign) {
> + case '+':
> + hm = del_lines;
> + key = prepare_entry(o, n);
> + match = hashmap_get(hm, key, o);
> + free(key);
> + break;
> + case '-':
> + hm = add_lines;
> + key = prepare_entry(o, n);
> + match = hashmap_get(hm, key, o);
> + free(key);
> + break;
> + default: ;
> + }
> +
> + if (!match) {
> + pmb_nr = 0;
> + if (prev_line &&
> +     o->color_moved == MOVED_LINES_BOUNDARY_ALL)
> + mark_color_as_moved_single_line(o, prev_line, 1);
> + prev_line = NULL;
> + continue;
> + }
> +
> + if (o->color_moved == MOVED_LINES_BOUNDARY_NO) {
> + mark_color_as_moved_single_line(o, l, 0);
> + 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 &&
> +     !diff_line_cmp(pnext->line, l, o)) {
> + pmb[i] = p->next_line;
> + } else {
> + pmb[i] = NULL;
> + }
> + }
> +
> + /* Shrink the set of potential block to the remaining running */
> + 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++;
> + }
> + }
> +
> + /* Remember the number of running sets */
> + pmb_nr = rp + 1;
> +
> + if (pmb_nr == 0) {
> + /*
> + * This line is the start of a new block.
> + * Setup the set of potential blocks.
> + */
> + for (; match; match = hashmap_get_next(hm, match)) {
> + ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
> + pmb[pmb_nr++] = match;
> + }
> +
> + if (o->color_moved == MOVED_LINES_BOUNDARY_ALL) {
> + adjacent_blocks = 1;
> + } else {
> + /* Check if two blocks are adjacent */
> + adjacent_blocks = prev_line &&
> +   prev_line->sign == l->sign;
> + }
> + }
> +
> + if (o->color_moved == MOVED_LINES_ALTERNATE) {
> + if (adjacent_blocks)
> + flipped_block = (flipped_block + 1) % 2;
> + mark_color_as_moved_single_line(o, l, flipped_block);
> + } else {
> + /* MOVED_LINES_BOUNDARY_{ADJACENT, ALL} */
> + mark_color_as_moved_single_line(o, l, adjacent_blocks);
> + if (adjacent_blocks && prev_line)
> + prev_line->set = l->set;
> + }
> +
> + prev_line = l;
> + }
> + if (prev_line && o->color_moved == MOVED_LINES_BOUNDARY_ALL)
> + mark_color_as_moved_single_line(o, prev_line, 1);
> +
> + free(pmb);
> +}
> +
> static void emit_diff_line(struct diff_options *o,
>     struct diff_line *e)
> {
> @@ -3518,6 +3809,8 @@ 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)
> @@ -3627,6 +3920,9 @@ 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)
> @@ -4051,7 +4347,19 @@ int diff_opt_parse(struct diff_options *options,
>  }
>  else if (!strcmp(arg, "--no-color"))
>  options->use_color = 0;
> - else if (!strcmp(arg, "--color-words")) {
> + else if (!strcmp(arg, "--color-moved"))
> + if (diff_color_moved_default)
> + options->color_moved = diff_color_moved_default;
> + else
> + options->color_moved = MOVED_LINES_BOUNDARY_ADJACENT;
> + else if (!strcmp(arg, "--no-color-moved"))
> + options->color_moved = MOVED_LINES_NO;
> + else if (skip_prefix(arg, "--color-moved=", &arg)) {
> + int cm = parse_color_moved(arg);
> + if (cm < 0)
> + die("bad --color-moved argument: %s", arg);
> + options->color_moved = cm;
> + } else if (!strcmp(arg, "--color-words")) {
>  options->use_color = 1;
>  options->word_diff = DIFF_WORDS_COLOR;
>  }
> @@ -4856,16 +5164,9 @@ 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_diff_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)
> + o->use_buffer = 1;
>
>  for (i = 0; i < q->nr; i++) {
>  struct diff_filepair *p = q->queue[i];
> @@ -4874,6 +5175,24 @@ static void diff_flush_patch_all_file_pairs(struct 
> diff_options *o)
>  }
>
>  if (o->use_buffer) {
> + if (o->color_moved) {
> + struct hashmap add_lines, del_lines;
> + unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
> +
> + hashmap_init(&del_lines, ignore_ws ?
> + (hashmap_cmp_fn)moved_entry_cmp_no_ws :
> + (hashmap_cmp_fn)moved_entry_cmp, 0);
> + hashmap_init(&add_lines, ignore_ws ?
> + (hashmap_cmp_fn)moved_entry_cmp_no_ws :
> + (hashmap_cmp_fn)moved_entry_cmp, 0);
> +
> + add_lines_to_move_detection(o, &add_lines, &del_lines);
> + mark_color_as_moved(o, &add_lines, &del_lines);
> +
> + hashmap_free(&add_lines, 0);
> + hashmap_free(&del_lines, 0);
> + }
> +
>  for (i = 0; i < o->line_buffer_nr; i++)
>  emit_diff_line(o, &o->line_buffer[i]);
>
> @@ -4962,6 +5281,7 @@ 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 be51e8f867..d9fbafd383 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;
> @@ -228,6 +229,14 @@ struct diff_options {
>
>  struct diff_line *line_buffer;
>  int line_buffer_nr, line_buffer_alloc;
> +
> + enum {
> + MOVED_LINES_NO = 0,
> + MOVED_LINES_BOUNDARY_NO = 1,
> + MOVED_LINES_BOUNDARY_ALL = 2,
> + MOVED_LINES_BOUNDARY_ADJACENT = 3,
> + MOVED_LINES_ALTERNATE = 4,
> + } color_moved;
> };
>
> /* Emit [line_prefix] [set] line [reset] */
> @@ -243,7 +252,11 @@ 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..d4bd082af7 100755
> --- a/t/t4015-diff-whitespace.sh
> +++ b/t/t4015-diff-whitespace.sh
> @@ -972,4 +972,377 @@ 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 &&
> + test_config color.diff.oldMoved "normal red" &&
> + test_config color.diff.newMoved "normal green" &&
> + 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
> + test_config color.diff.oldMoved "normal red" &&
> + test_config color.diff.newMoved "normal green" &&
> + test_config color.diff.oldMovedAlternative "bold red" &&
> + test_config color.diff.newMovedAlternative "bold green" &&
> + 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' '
> + git reset --hard &&
> + cat <<-\EOF >lines.txt &&
> + line 1
> + line 2
> + line 3
> + line 4
> + line 5
> + line 6
> + line 7
> + line 8
> + line 9
> + line 10
> + line 11
> + line 12
> + line 13
> + line 14
> + line 15
> + line 16
> + EOF
> + git add lines.txt &&
> + git commit -m "add poetry" &&
> + cat <<-\EOF >lines.txt &&
> + line 4
> + line 5
> + line 6
> + line 7
> + line 8
> + line 9
> + line 1
> + line 2
> + line 3
> + line 14
> + line 15
> + line 16
> + line 10
> + line 11
> + line 12
> + line 13
> + EOF
> + test_config color.diff.oldMoved "magenta" &&
> + test_config color.diff.newMoved "cyan" &&
> + test_config color.diff.oldMovedAlternative "blue" &&
> + test_config color.diff.newMovedAlternative "yellow" &&
> +
> +
> + git diff HEAD --no-renames --color-moved=nobounds| test_decode_color 
>  >actual &&
> + cat <<-\EOF >expected &&
> + <BOLD>diff --git a/lines.txt b/lines.txt<RESET>
> + <BOLD>index 47ea9c3..ba96a38 100644<RESET>
> + <BOLD>--- a/lines.txt<RESET>
> + <BOLD>+++ b/lines.txt<RESET>
> + <CYAN>@@ -1,16 +1,16 @@<RESET>
> + <MAGENTA>-line 1<RESET>
> + <MAGENTA>-line 2<RESET>
> + <MAGENTA>-line 3<RESET>
> + line 4<RESET>
> + line 5<RESET>
> + line 6<RESET>
> + line 7<RESET>
> + line 8<RESET>
> + line 9<RESET>
> + <CYAN>+<RESET><CYAN>line 1<RESET>
> + <CYAN>+<RESET><CYAN>line 2<RESET>
> + <CYAN>+<RESET><CYAN>line 3<RESET>
> + <CYAN>+<RESET><CYAN>line 14<RESET>
> + <CYAN>+<RESET><CYAN>line 15<RESET>
> + <CYAN>+<RESET><CYAN>line 16<RESET>
> + line 10<RESET>
> + line 11<RESET>
> + line 12<RESET>
> + line 13<RESET>
> + <MAGENTA>-line 14<RESET>
> + <MAGENTA>-line 15<RESET>
> + <MAGENTA>-line 16<RESET>
> + EOF
> + test_cmp expected actual &&
> +
> + git diff HEAD --no-renames --color-moved=adjacentbounds| 
> test_decode_color >actual &&
> + cat <<-\EOF >expected &&
> + <BOLD>diff --git a/lines.txt b/lines.txt<RESET>
> + <BOLD>index 47ea9c3..ba96a38 100644<RESET>
> + <BOLD>--- a/lines.txt<RESET>
> + <BOLD>+++ b/lines.txt<RESET>
> + <CYAN>@@ -1,16 +1,16 @@<RESET>
> + <MAGENTA>-line 1<RESET>
> + <MAGENTA>-line 2<RESET>
> + <MAGENTA>-line 3<RESET>
> + line 4<RESET>
> + line 5<RESET>
> + line 6<RESET>
> + line 7<RESET>
> + line 8<RESET>
> + line 9<RESET>
> + <CYAN>+<RESET><CYAN>line 1<RESET>
> + <CYAN>+<RESET><CYAN>line 2<RESET>
> + <YELLOW>+<RESET><YELLOW>line 3<RESET>
> + <YELLOW>+<RESET><YELLOW>line 14<RESET>
> + <CYAN>+<RESET><CYAN>line 15<RESET>
> + <CYAN>+<RESET><CYAN>line 16<RESET>
> + line 10<RESET>
> + line 11<RESET>
> + line 12<RESET>
> + line 13<RESET>
> + <MAGENTA>-line 14<RESET>
> + <MAGENTA>-line 15<RESET>
> + <MAGENTA>-line 16<RESET>
> + EOF
> + test_cmp expected actual &&
> +
> + test_config diff.colorMoved alternate &&
> + git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
> + cat <<-\EOF >expected &&
> + <BOLD>diff --git a/lines.txt b/lines.txt<RESET>
> + <BOLD>index 47ea9c3..ba96a38 100644<RESET>
> + <BOLD>--- a/lines.txt<RESET>
> + <BOLD>+++ b/lines.txt<RESET>
> + <CYAN>@@ -1,16 +1,16 @@<RESET>
> + <MAGENTA>-line 1<RESET>
> + <MAGENTA>-line 2<RESET>
> + <MAGENTA>-line 3<RESET>
> + line 4<RESET>
> + line 5<RESET>
> + line 6<RESET>
> + line 7<RESET>
> + line 8<RESET>
> + line 9<RESET>
> + <CYAN>+<RESET><CYAN>line 1<RESET>
> + <CYAN>+<RESET><CYAN>line 2<RESET>
> + <CYAN>+<RESET><CYAN>line 3<RESET>
> + <YELLOW>+<RESET><YELLOW>line 14<RESET>
> + <YELLOW>+<RESET><YELLOW>line 15<RESET>
> + <YELLOW>+<RESET><YELLOW>line 16<RESET>
> + line 10<RESET>
> + line 11<RESET>
> + line 12<RESET>
> + line 13<RESET>
> + <BLUE>-line 14<RESET>
> + <BLUE>-line 15<RESET>
> + <BLUE>-line 16<RESET>
> + EOF
> + test_cmp expected actual &&
> +
> + test_config diff.colorMoved allbounds &&
> + git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
> + cat <<-\EOF >expected &&
> + <BOLD>diff --git a/lines.txt b/lines.txt<RESET>
> + <BOLD>index 47ea9c3..ba96a38 100644<RESET>
> + <BOLD>--- a/lines.txt<RESET>
> + <BOLD>+++ b/lines.txt<RESET>
> + <CYAN>@@ -1,16 +1,16 @@<RESET>
> + <BLUE>-line 1<RESET>
> + <MAGENTA>-line 2<RESET>
> + <BLUE>-line 3<RESET>
> + line 4<RESET>
> + line 5<RESET>
> + line 6<RESET>
> + line 7<RESET>
> + line 8<RESET>
> + line 9<RESET>
> + <YELLOW>+<RESET><YELLOW>line 1<RESET>
> + <CYAN>+<RESET><CYAN>line 2<RESET>
> + <YELLOW>+<RESET><YELLOW>line 3<RESET>
> + <YELLOW>+<RESET><YELLOW>line 14<RESET>
> + <CYAN>+<RESET><CYAN>line 15<RESET>
> + <YELLOW>+<RESET><YELLOW>line 16<RESET>
> + line 10<RESET>
> + line 11<RESET>
> + line 12<RESET>
> + line 13<RESET>
> + <BLUE>-line 14<RESET>
> + <MAGENTA>-line 15<RESET>
> + <BLUE>-line 16<RESET>
> + EOF
> + test_cmp expected actual
> +'
> +
> +test_expect_success 'move detection does not mess up colored words' '
> + cat <<-\EOF >text.txt &&
> + Lorem Ipsum is simply dummy text of the printing and typesetting 
> industry.
> + EOF
> + git add text.txt &&
> + git commit -a -m "clean state" &&
> + cat <<-\EOF >text.txt &&
> + simply Lorem Ipsum dummy is text of the typesetting and printing 
> industry.
> + EOF
> + git diff --color-moved --word-diff >actual &&
> + git diff --word-diff >expect &&
> + test_cmp expect actual
> +'
> +
> +test_expect_success 'move detection with submodules' '
> + test_create_repo bananas &&
> + echo ripe >bananas/recipe &&
> + git -C bananas add recipe &&
> + test_commit fruit &&
> + test_commit -C bananas recipe &&
> + git submodule add ./bananas &&
> + git add bananas &&
> + git commit -a -m "bananas are like a heavy library?" &&
> + echo foul >bananas/recipe &&
> + echo ripe >fruit.t &&
> +
> + git diff --submodule=diff --color-moved >actual &&
> +
> + # no move detection as the moved line is across repository boundaries.
> + test_decode_color <actual >decoded_actual &&
> + ! grep BGREEN decoded_actual &&
> + ! grep BRED decoded_actual &&
> +
> + # nor did we mess with it another way
> + git diff --submodule=diff | test_decode_color >expect &&
> + test_cmp expect decoded_actual
> +'
> +
> test_done
> -- 
> 2.13.0.17.gab62347cd9
> 

Stefan Beller· May 30, 2017, 21:33 UTC · re: Philip Oakley · lore

Re: [PATCH 1/1] diff.c: color moved lines differently

On Sat, May 27, 2017 at 12:05 AM, Philip Oakley <philipoakley@iee.org> wrote:

> a couple of mispellings in the doc parts:
>  s/on location/one location/
> [code not checked]

Thanks for proofreading the documentation!

>
> s/on location/one location/
>
>> + in another location will be colored with 'color.diff.newmoved'.
>> + Any line that is removed in on location and was added
>
> s/on location/one location/

    Similarly 'color.diff.oldmoved' will be used for removed lines
    that are added somewhere else in the diff.

Stefan Beller· Jun 1, 2017, 00:24 UTC · re: Stefan Beller · lore

[PATCH] diff.c: color moved lines differently

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OM]  -        if (!is_authorized_user())
    [OM]  -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OM]  -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NM]  +        sensitive_stuff(spanning,
    [NM]  +                        multiple,
    [NM]  +                        lines);
    [NM]  +}

    [OM]  -void sensitive_stuff(void)
    [OM]  -{
    [OMA] -        if (!is_authorized_user())
    [OMA] -                die("unauthorized");
    [OM]  -        sensitive_stuff(spanning,
    [OM]  -                        multiple,
    [OM]  -                        lines);
    [OMA] -}

           void another_function()
           {
    [del] -        printf("foo");
    [add] +        printf("bar");
           }

    [NM]  +void sensitive_stuff(void)
    [NM]  +{
    [NMA] +        sensitive_stuff(spanning,
    [NMA] +                        multiple,
    [NMA] +                        lines);
    [NM]  +        if (!is_authorized_user())
    [NM]  +                die("unauthorized");
    [NMA] +}

Helped-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
---

 Replacing the top commit in origin/sb/diff-color-move, 
 this has the spelling fixes by Philip.
 
 Also a minor fix for the 'alternate' mode, to go back to the default
 after empty lines. Thanks to Jacob.
 
 Thanks,
 Stefan

 Documentation/config.txt       |  10 +-
 Documentation/diff-options.txt |  32 ++++
 color.h                        |   2 +
 diff.c                         | 343 +++++++++++++++++++++++++++++++++++--
 diff.h                         |  15 +-
 t/t4015-diff-whitespace.sh     | 373 +++++++++++++++++++++++++++++++++++++++++
 6 files changed, 761 insertions(+), 14 deletions(-)

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 475e874d51..73511a4603 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1051,14 +1051,20 @@ 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.
 
+diff.colorMoved::
+	If set moved lines in a diff are colored differently,
+	for details see '--color-moved' in linkgit:git-diff[1].
+
 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`, `newMoved`,
+	`oldMovedAlternative` and `newMovedAlternative` (See the '<mode>'
+	setting of '--color-moved' in linkgit:git-diff[1] for details).
 
 color.decorate.<slot>::
 	Use customized color for 'git log --decorate' output.  `<slot>` is one
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 89cc0f48de..69bf061c5c 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -231,6 +231,38 @@ ifdef::git-diff[]
 endif::git-diff[]
 	It is the same as `--color=never`.
 
+--color-moved[=<mode>]::
+	Moved lines of code are colored differently.
+ifdef::git-diff[]
+	It can be changed by the `diff.colorMoved` configuration setting.
+endif::git-diff[]
+	The <mode> defaults to 'no' if the option is not given
+	and to 'adjacentbounds' if the option with no mode is given.
+	The mode must be one of:
++
+--
+no::
+	Moved lines are not highlighted.
+nobounds::
+	Any line that is added in one location and was removed
+	in another location will be colored with 'color.diff.newmoved'.
+	Similarly 'color.diff.oldmoved' will be used for removed lines
+	that are added somewhere else in the diff.
+allbounds::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected and the first and last line of a block will be highlighted
+	using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+adjacentbounds::
+	The same as 'allbounds' except that highlighting is only performed
+	at adjacent block boundaries of blocks that have the same sign.
+alternate::
+	Based on 'nobounds'. Additionally blocks of moved code are
+	detected. If moved blocks are adjacent mark one of them with the
+	alternative move color using 'color.diff.newMovedAlternate' or
+	'color.diff.oldMovedAlternate'.
+--
+
 --word-diff[=<mode>]::
 	Show a word diff, using the <mode> to delimit changed words.
 	By default, words are delimited by whitespace; see
diff --git a/color.h b/color.h
index 90627650fc..04b3b87929 100644
--- a/color.h
+++ b/color.h
@@ -42,6 +42,8 @@ struct strbuf;
 #define GIT_COLOR_BG_BLUE	"\033[44m"
 #define GIT_COLOR_BG_MAGENTA	"\033[45m"
 #define GIT_COLOR_BG_CYAN	"\033[46m"
+#define GIT_COLOR_DI_IT_CYAN	"\033[2;3;36m"
+#define GIT_COLOR_DI_IT_MAGENTA	"\033[2;3;35m"
 
 /* A special value meaning "no color selected" */
 #define GIT_COLOR_NIL "NIL"
diff --git a/diff.c b/diff.c
index a3c16ef827..a1f919ba57 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_DI_IT_MAGENTA,/* OLD_MOVED */
+	GIT_COLOR_BG_RED,	/* OLD_MOVED ALTERNATIVE */
+	GIT_COLOR_DI_IT_CYAN,	/* NEW_MOVED */
+	GIT_COLOR_BG_GREEN,	/* NEW_MOVED ALTERNATIVE */
 };
 
 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;
 }
 
@@ -228,12 +241,35 @@ int git_diff_heuristic_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
+static int parse_color_moved(const char *arg)
+{
+	if (!strcmp(arg, "no"))
+		return MOVED_LINES_NO;
+	else if (!strcmp(arg, "nobounds"))
+		return MOVED_LINES_BOUNDARY_NO;
+	else if (!strcmp(arg, "allbounds"))
+		return MOVED_LINES_BOUNDARY_ALL;
+	else if (!strcmp(arg, "adjacentbounds"))
+		return MOVED_LINES_BOUNDARY_ADJACENT;
+	else if (!strcmp(arg, "alternate"))
+		return MOVED_LINES_ALTERNATE;
+	else
+		return -1;
+}
+
 int git_diff_ui_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
 		diff_use_color_default = git_config_colorbool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.colormoved")) {
+		int cm = parse_color_moved(value);
+		if (cm < 0)
+			return -1;
+		diff_color_moved_default = cm;
+		return 0;
+	}
 	if (!strcmp(var, "diff.context")) {
 		diff_context_default = git_config_int(var, value);
 		if (diff_context_default < 0)
@@ -354,6 +390,88 @@ 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 diff_line *line;
+	struct moved_entry *next_line;
+};
+
+static void get_ws_cleaned_string(const struct diff_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 diff_line_cmp_no_ws(const struct diff_line *a,
+					 const struct diff_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 diff_line_cmp(const struct diff_line *a,
+				   const struct diff_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 diff_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 diff_line_cmp_no_ws(a->line, b->line, keydata);
+}
+
+static unsigned get_line_hash(struct diff_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 diff_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 +634,180 @@ 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 hashmap *add_lines,
+					struct hashmap *del_lines)
+{
+	struct moved_entry *prev_line = NULL;
+
+	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 = add_lines;
+			break;
+		case '-':
+			sign = '-';
+			hm = del_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_single_line(struct diff_options *o,
+					    struct diff_line *l, int alt_color)
+{
+	switch (l->sign) {
+	case '+':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_NEW_MOVED + alt_color);
+		break;
+	case '-':
+		l->set = diff_get_color_opt(o,
+			DIFF_FILE_OLD_MOVED + alt_color);
+		break;
+	default:
+		die("BUG: we should have continued earlier?");
+	}
+}
+
+static void mark_color_as_moved(struct diff_options *o,
+				struct hashmap *add_lines,
+				struct hashmap *del_lines)
+{
+	struct moved_entry **pmb = NULL; /* potentially moved blocks */
+	struct diff_line *prev_line = NULL;
+	int pmb_nr = 0, pmb_alloc = 0;
+	int n, flipped_block = 0;
+
+	for (n = 0; n < o->line_buffer_nr; n++) {
+		struct hashmap *hm = NULL;
+		struct moved_entry *key;
+		struct moved_entry *match = NULL;
+		struct diff_line *l = &o->line_buffer[n];
+		int i, lp, rp, adjacent_blocks = 0;
+
+		/* Check for any match to color it as a move. */
+		switch (l->sign) {
+		case '+':
+			hm = del_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
+			break;
+		case '-':
+			hm = add_lines;
+			key = prepare_entry(o, n);
+			match = hashmap_get(hm, key, o);
+			free(key);
+			break;
+		default: ;
+			flipped_block = 0;
+		}
+
+		if (!match) {
+			pmb_nr = 0;
+			if (prev_line &&
+			    o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+				mark_color_as_moved_single_line(o, prev_line, 1);
+			prev_line = NULL;
+			continue;
+		}
+
+		if (o->color_moved == MOVED_LINES_BOUNDARY_NO) {
+			mark_color_as_moved_single_line(o, l, 0);
+			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 &&
+			    !diff_line_cmp(pnext->line, l, o)) {
+				pmb[i] = p->next_line;
+			} else {
+				pmb[i] = NULL;
+			}
+		}
+
+		/* Shrink the set of potential block to the remaining running */
+		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++;
+			}
+		}
+
+		/* Remember the number of running sets */
+		pmb_nr = rp + 1;
+
+		if (pmb_nr == 0) {
+			/*
+			 * This line is the start of a new block.
+			 * Setup the set of potential blocks.
+			 */
+			for (; match; match = hashmap_get_next(hm, match)) {
+				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
+				pmb[pmb_nr++] = match;
+			}
+
+			if (o->color_moved == MOVED_LINES_BOUNDARY_ALL) {
+				adjacent_blocks = 1;
+			} else {
+				/* Check if two blocks are adjacent */
+				adjacent_blocks = prev_line &&
+						  prev_line->sign == l->sign;
+			}
+		}
+
+		if (o->color_moved == MOVED_LINES_ALTERNATE) {
+			if (adjacent_blocks)
+				flipped_block = (flipped_block + 1) % 2;
+			mark_color_as_moved_single_line(o, l, flipped_block);
+		} else {
+			/* MOVED_LINES_BOUNDARY_{ADJACENT, ALL} */
+			mark_color_as_moved_single_line(o, l, adjacent_blocks);
+			if (adjacent_blocks && prev_line)
+				prev_line->set = l->set;
+		}
+
+		prev_line = l;
+	}
+	if (prev_line && o->color_moved == MOVED_LINES_BOUNDARY_ALL)
+		mark_color_as_moved_single_line(o, prev_line, 1);
+
+	free(pmb);
+}
+
 static void emit_diff_line(struct diff_options *o,
 			   struct diff_line *e)
 {
@@ -3518,6 +3810,8 @@ 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)
@@ -3627,6 +3921,9 @@ 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)
@@ -4051,7 +4348,19 @@ int diff_opt_parse(struct diff_options *options,
 	}
 	else if (!strcmp(arg, "--no-color"))
 		options->use_color = 0;
-	else if (!strcmp(arg, "--color-words")) {
+	else if (!strcmp(arg, "--color-moved"))
+		if (diff_color_moved_default)
+			options->color_moved = diff_color_moved_default;
+		else
+			options->color_moved = MOVED_LINES_BOUNDARY_ADJACENT;
+	else if (!strcmp(arg, "--no-color-moved"))
+		options->color_moved = MOVED_LINES_NO;
+	else if (skip_prefix(arg, "--color-moved=", &arg)) {
+		int cm = parse_color_moved(arg);
+		if (cm < 0)
+			die("bad --color-moved argument: %s", arg);
+		options->color_moved = cm;
+	} else if (!strcmp(arg, "--color-words")) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
 	}
@@ -4856,16 +5165,9 @@ 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_diff_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)
+		o->use_buffer = 1;
 
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
@@ -4874,6 +5176,24 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	}
 
 	if (o->use_buffer) {
+		if (o->color_moved) {
+			struct hashmap add_lines, del_lines;
+			unsigned ignore_ws = DIFF_XDL_TST(o, IGNORE_WHITESPACE);
+
+			hashmap_init(&del_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+			hashmap_init(&add_lines, ignore_ws ?
+				(hashmap_cmp_fn)moved_entry_cmp_no_ws :
+				(hashmap_cmp_fn)moved_entry_cmp, 0);
+
+			add_lines_to_move_detection(o, &add_lines, &del_lines);
+			mark_color_as_moved(o, &add_lines, &del_lines);
+
+			hashmap_free(&add_lines, 0);
+			hashmap_free(&del_lines, 0);
+		}
+
 		for (i = 0; i < o->line_buffer_nr; i++)
 			emit_diff_line(o, &o->line_buffer[i]);
 
@@ -4962,6 +5282,7 @@ 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 be51e8f867..d9fbafd383 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;
@@ -228,6 +229,14 @@ struct diff_options {
 
 	struct diff_line *line_buffer;
 	int line_buffer_nr, line_buffer_alloc;
+
+	enum {
+		MOVED_LINES_NO = 0,
+		MOVED_LINES_BOUNDARY_NO = 1,
+		MOVED_LINES_BOUNDARY_ALL = 2,
+		MOVED_LINES_BOUNDARY_ADJACENT = 3,
+		MOVED_LINES_ALTERNATE = 4,
+	} color_moved;
 };
 
 /* Emit [line_prefix] [set] line [reset] */
@@ -243,7 +252,11 @@ 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..e7b821be0a 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -972,4 +972,377 @@ 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 &&
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
+	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
+	test_config color.diff.oldMoved "normal red" &&
+	test_config color.diff.newMoved "normal green" &&
+	test_config color.diff.oldMovedAlternative "bold red" &&
+	test_config color.diff.newMovedAlternative "bold green" &&
+	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' '
+	git reset --hard &&
+	cat <<-\EOF >lines.txt &&
+		line 1
+		line 2
+		line 3
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 10
+		line 11
+		line 12
+		line 13
+		line 14
+		line 15
+		line 16
+	EOF
+	git add lines.txt &&
+	git commit -m "add poetry" &&
+	cat <<-\EOF >lines.txt &&
+		line 4
+		line 5
+		line 6
+		line 7
+		line 8
+		line 9
+		line 1
+		line 2
+		line 3
+		line 14
+		line 15
+		line 16
+		line 10
+		line 11
+		line 12
+		line 13
+	EOF
+	test_config color.diff.oldMoved "magenta" &&
+	test_config color.diff.newMoved "cyan" &&
+	test_config color.diff.oldMovedAlternative "blue" &&
+	test_config color.diff.newMovedAlternative "yellow" &&
+
+
+	git diff HEAD --no-renames --color-moved=nobounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+		<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+		<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+		<BOLD>--- a/lines.txt<RESET>
+		<BOLD>+++ b/lines.txt<RESET>
+		<CYAN>@@ -1,16 +1,16 @@<RESET>
+		<MAGENTA>-line 1<RESET>
+		<MAGENTA>-line 2<RESET>
+		<MAGENTA>-line 3<RESET>
+		 line 4<RESET>
+		 line 5<RESET>
+		 line 6<RESET>
+		 line 7<RESET>
+		 line 8<RESET>
+		 line 9<RESET>
+		<CYAN>+<RESET><CYAN>line 1<RESET>
+		<CYAN>+<RESET><CYAN>line 2<RESET>
+		<CYAN>+<RESET><CYAN>line 3<RESET>
+		<CYAN>+<RESET><CYAN>line 14<RESET>
+		<CYAN>+<RESET><CYAN>line 15<RESET>
+		<CYAN>+<RESET><CYAN>line 16<RESET>
+		 line 10<RESET>
+		 line 11<RESET>
+		 line 12<RESET>
+		 line 13<RESET>
+		<MAGENTA>-line 14<RESET>
+		<MAGENTA>-line 15<RESET>
+		<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	git diff HEAD --no-renames --color-moved=adjacentbounds| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<CYAN>+<RESET><CYAN>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<MAGENTA>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	test_config diff.colorMoved alternate &&
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<MAGENTA>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<CYAN>+<RESET><CYAN>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<YELLOW>+<RESET><YELLOW>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<MAGENTA>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<MAGENTA>-line 16<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	test_config diff.colorMoved allbounds &&
+	git diff HEAD --no-renames --color-moved| test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>index 47ea9c3..ba96a38 100644<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<BLUE>-line 1<RESET>
+	<MAGENTA>-line 2<RESET>
+	<BLUE>-line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<YELLOW>+<RESET><YELLOW>line 1<RESET>
+	<CYAN>+<RESET><CYAN>line 2<RESET>
+	<YELLOW>+<RESET><YELLOW>line 3<RESET>
+	<YELLOW>+<RESET><YELLOW>line 14<RESET>
+	<CYAN>+<RESET><CYAN>line 15<RESET>
+	<YELLOW>+<RESET><YELLOW>line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<BLUE>-line 14<RESET>
+	<MAGENTA>-line 15<RESET>
+	<BLUE>-line 16<RESET>
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'move detection does not mess up colored words' '
+	cat <<-\EOF >text.txt &&
+	Lorem Ipsum is simply dummy text of the printing and typesetting industry.
+	EOF
+	git add text.txt &&
+	git commit -a -m "clean state" &&
+	cat <<-\EOF >text.txt &&
+	simply Lorem Ipsum dummy is text of the typesetting and printing industry.
+	EOF
+	git diff --color-moved --word-diff >actual &&
+	git diff --word-diff >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'move detection with submodules' '
+	test_create_repo bananas &&
+	echo ripe >bananas/recipe &&
+	git -C bananas add recipe &&
+	test_commit fruit &&
+	test_commit -C bananas recipe &&
+	git submodule add ./bananas &&
+	git add bananas &&
+	git commit -a -m "bananas are like a heavy library?" &&
+	echo foul >bananas/recipe &&
+	echo ripe >fruit.t &&
+
+	git diff --submodule=diff --color-moved >actual &&
+
+	# no move detection as the moved line is across repository boundaries.
+	test_decode_color <actual >decoded_actual &&
+	! grep BGREEN decoded_actual &&
+	! grep BRED decoded_actual &&
+
+	# nor did we mess with it another way
+	git diff --submodule=diff | test_decode_color >expect &&
+	test_cmp expect decoded_actual
+'
+
 test_done

-- 
2.13.0.17.gab62347cd9

Re: [PATCH] diff.c: color moved lines differently

> When a patch consists mostly of moving blocks of code around, it can
> be quite tedious to ensure that the blocks are moved verbatim, and not
> undesirably modified in the move. To that end, color blocks that are
> moved within the same patch differently. For example (OM, del, add,
> and NM are different colors):

[snip]

[1] https://public-inbox.org/git/CAGZ79kY2Z-fJYxczbzheu1hChLkKkdjEcDMwsP-hkN0TjUBotQ@mail.gmail.com/

> --- a/Documentation/diff-options.txt
> +++ b/Documentation/diff-options.txt
> @@ -231,6 +231,38 @@ ifdef::git-diff[]
>  endif::git-diff[]
>  	It is the same as `--color=never`.
>  
> +--color-moved[=<mode>]::
> +	Moved lines of code are colored differently.
> +ifdef::git-diff[]
> +	It can be changed by the `diff.colorMoved` configuration setting.
> +endif::git-diff[]
> +	The <mode> defaults to 'no' if the option is not given
> +	and to 'adjacentbounds' if the option with no mode is given.
> +	The mode must be one of:
> ++
> +--
> +no::
> +	Moved lines are not highlighted.
> +nobounds::
> +	Any line that is added in one location and was removed
> +	in another location will be colored with 'color.diff.newmoved'.
> +	Similarly 'color.diff.oldmoved' will be used for removed lines

Probably best to consistently capitalize newMoved and oldMoved.

> +static unsigned get_line_hash(struct diff_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);
> +	}
> +}

Can be written without the "else".

> +test_expect_success 'move detection does not mess up colored words' '

Stefan Beller· Jun 14, 2017, 18:55 UTC · re: Jonathan Tan · lore

Re: [PATCH] diff.c: color moved lines differently

On Tue, Jun 13, 2017 at 3:51 PM, Jonathan Tan <jonathantanmy@google.com> wrote:

> On Wed, 31 May 2017 17:24:29 -0700
> Stefan Beller <sbeller@google.com> wrote:
>
>> When a patch consists mostly of moving blocks of code around, it can
>> be quite tedious to ensure that the blocks are moved verbatim, and not
>> undesirably modified in the move. To that end, color blocks that are
>> moved within the same patch differently. For example (OM, del, add,
>> and NM are different colors):
>
> [snip]
>
> Junio asks "are we happy with these changes" [1] and my answer is, in
> general, yes - this seems like a very useful feature to have, and I'm OK
> with the current design.
>
> I do feel a bit of unease at how the emitted strings are collected
> without many guarantees as to their contents (e.g. whether they are full
> lines or even whether they originate from the text of a file), but this
> is already true for the existing code. The potential danger is that we
> are now relying more on the format of these strings, but we don't plan
> to do anything other than to color them, so this seems fine.

I will add comments into the code for that.

>
> I would also prefer if there was only one coloring method, to ease
> testing, but I can tolerate the current multiplicity of options.

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 00/26] reroll of sb/diff-color-moved

This is a complete rewrite of the series. Highlights:
* instead of buffering partial lines, we'll pretend all diff output
  follows a well defined grammar, and we emit symbols thereof.
  (The difference is mostly mental, though by this trick we reduce
  the memory footprint for storing one of these symbols from 7 variables
  (3 pointers, 3 ints, one state (also int) down to 4 variables
  (one pointer, 2 ints, one state).
* The algorithm for color painting was detangled:
  -> different functions for block detection and dimming
  -> The last patch (not to be applied) is an RFC that shows
     how we would approach non-colored, but machine parseable highlighting
     of moved lines.

Stefan Beller (26):
  diff.c: readability fix
  diff.c: move line ending check into emit_hunk_header
  diff.c: factor out diff_flush_patch_all_file_pairs
  diff.c: introduce emit_diff_symbol
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_CONTEXT_MARKER
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_CONTEXT_FRAGINFO
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_NO_LF_EOF
  diff.c: migrate emit_line_checked to use emit_diff_symbol
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_WORDS{_PORCELAIN}
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_CONTEXT_INCOMPLETE
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_FILEPAIR
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_HEADER
  diff.c: emit_diff_symbol learns about DIFF_SYMBOL_BINARY_FILES
  diff.c: emit_diff_symbol learns DIFF_SYMBOL_REWRITE_DIFF
  submodule.c: migrate diff output to use emit_diff_symbol
  diff.c: convert emit_binary_diff_body to use emit_diff_symbol
  diff.c: convert show_stats to use emit_diff_symbol
  diff.c: convert word diffing to use emit_diff_symbol
  diff.c: emit_diff_symbol learns about DIFF_SYMBOL_STAT_SEP
  diff.c: emit_diff_symbol learns about DIFF_SYMBOL_SUMMARY
  diff.c: buffer all output if asked to
  diff.c: color moved lines differently
  diff.c: color moved lines differently, plain mode
  diff.c: add dimming to moved line detection
  diff: document the new --color-moved setting
  WIP/RFC: diff.c: have a "machine parseable" move coloring

 Documentation/config.txt       |   12 +-
 Documentation/diff-options.txt |   27 +
 cache.h                        |    1 +
 color.h                        |    2 +
 diff.c                         | 1283 ++++++++++++++++++++++++++++++++--------
 diff.h                         |   39 +-
 submodule.c                    |   85 ++-
 submodule.h                    |   13 +-
 t/t4015-diff-whitespace.sh     |  369 ++++++++++++
 9 files changed, 1515 insertions(+), 316 deletions(-)

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 02/26] diff.c: move line ending check into emit_hunk_header

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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;
 	}
 

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 03/26] diff.c: factor out diff_flush_patch_all_file_pairs

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 diff.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

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)

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 06/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_CONTEXT_FRAGINFO

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/diff.c b/diff.c
index 3af07fa659..a1804a7785 100644
--- a/diff.c
+++ b/diff.c
@@ -562,6 +562,7 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
 enum diff_symbol {
 	DIFF_SYMBOL_SEPARATOR,
 	DIFF_SYMBOL_CONTEXT_MARKER,
+	DIFF_SYMBOL_CONTEXT_FRAGINFO,
 };
 
 static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
@@ -579,6 +580,9 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 		reset = diff_get_color_opt(o, DIFF_RESET);
 		emit_line(o, context, reset, line, len);
 		break;
+	case DIFF_SYMBOL_CONTEXT_FRAGINFO:
+		emit_line(o, "", "", line, len);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -704,8 +708,8 @@ 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);
+	emit_diff_symbol(ecbdata->opt,
+			 DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len);
 	strbuf_release(&msgbuf);
 }
 

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 07/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_NO_LF_EOF

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/diff.c b/diff.c
index a1804a7785..28be3226c2 100644
--- a/diff.c
+++ b/diff.c
@@ -563,11 +563,13 @@ enum diff_symbol {
 	DIFF_SYMBOL_SEPARATOR,
 	DIFF_SYMBOL_CONTEXT_MARKER,
 	DIFF_SYMBOL_CONTEXT_FRAGINFO,
+	DIFF_SYMBOL_NO_LF_EOF,
 };
 
 static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 			     const char *line, int len)
 {
+	static const char *nneof = " No newline at end of file\n";
 	const char *context, *reset;
 	switch (s) {
 	case DIFF_SYMBOL_SEPARATOR:
@@ -583,6 +585,13 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 	case DIFF_SYMBOL_CONTEXT_FRAGINFO:
 		emit_line(o, "", "", line, len);
 		break;
+	case DIFF_SYMBOL_NO_LF_EOF:
+		context = diff_get_color_opt(o, DIFF_CONTEXT);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		putc('\n', o->file);
+		emit_line_0(o, context, reset, '\\',
+			    nneof, strlen(nneof));
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -750,7 +759,6 @@ 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);
 
 	while (0 < size) {
@@ -768,13 +776,8 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		size -= len;
 		data += len;
 	}
-	if (!endp) {
-		const char *context = diff_get_color(ecb->color_diff,
-						     DIFF_CONTEXT);
-		putc('\n', ecb->opt->file);
-		emit_line_0(ecb->opt, context, reset, '\\',
-			    nneof, strlen(nneof));
-	}
+	if (!endp)
+		emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0);
 }
 
 static void emit_rewrite_diff(const char *name_a,

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 08/26] diff.c: migrate emit_line_checked to use emit_diff_symbol

Add a new flags field to emit_diff_symbol, that will be used by
context lines for:
* white space rules that are applicable (The first 12 bits)
* how the rules are evaluated (actually this double encodes the sign
  of the line, but the code is easier to keep this way, bits 13,14,15)
* if the line a blank line at EOF (bit 16)

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 cache.h |   1 +
 diff.c  | 112 ++++++++++++++++++++++++++++++++++++++++------------------------
 diff.h  |   6 ++--
 3 files changed, 75 insertions(+), 44 deletions(-)

diff --git a/cache.h b/cache.h
index e1f0e182ad..4d63c44f07 100644
--- a/cache.h
+++ b/cache.h
@@ -2168,6 +2168,7 @@ void shift_tree_by(const struct object_id *, const struct object_id *, struct ob
 #define WS_TRAILING_SPACE      (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF)
 #define WS_DEFAULT_RULE (WS_TRAILING_SPACE|WS_SPACE_BEFORE_TAB|8)
 #define WS_TAB_WIDTH_MASK        077
+#define WS_RULE_MASK           07777
 extern unsigned whitespace_rule_cfg;
 extern unsigned whitespace_rule(const char *);
 extern unsigned parse_whitespace_rule(const char *);
diff --git a/diff.c b/diff.c
index 28be3226c2..42c9f48dc2 100644
--- a/diff.c
+++ b/diff.c
@@ -564,13 +564,50 @@ enum diff_symbol {
 	DIFF_SYMBOL_CONTEXT_MARKER,
 	DIFF_SYMBOL_CONTEXT_FRAGINFO,
 	DIFF_SYMBOL_NO_LF_EOF,
+	DIFF_SYMBOL_CONTEXT,
+	DIFF_SYMBOL_PLUS,
+	DIFF_SYMBOL_MINUS,
 };
+/*
+ * Flags for content lines:
+ * 0..12 are whitespace rules
+ * 13-15 are WSEH_NEW | WSEH_OLD | WSEH_CONTEXT
+ * 16 is marking if the line is blank at EOF
+ */
+#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<16)
+#define DIFF_SYMBOL_CONTENT_WS_MASK (WSEH_NEW | WSEH_OLD | WSEH_CONTEXT | WS_RULE_MASK)
+
+static void emit_line_ws_markup(struct diff_options *o,
+				const char *set, const char *reset,
+				const char *line, int len, char sign,
+				unsigned ws_rule, int blank_at_eof)
+{
+	const char *ws = NULL;
+
+	if (o->ws_error_highlight & ws_rule) {
+		ws = diff_get_color_opt(o, DIFF_WHITESPACE);
+		if (!*ws)
+			ws = NULL;
+	}
+
+	if (!ws)
+		emit_line_0(o, set, reset, sign, line, len);
+	else if (blank_at_eof)
+		/* Blank line at EOF - paint '+' as well */
+		emit_line_0(o, ws, reset, sign, line, len);
+	else {
+		/* Emit just the prefix, then the rest. */
+		emit_line_0(o, set, reset, sign, "", 0);
+		ws_check_emit(line, len, ws_rule,
+			      o->file, set, reset, ws);
+	}
+}
 
 static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
-			     const char *line, int len)
+			     const char *line, int len, unsigned flags)
 {
 	static const char *nneof = " No newline at end of file\n";
-	const char *context, *reset;
+	const char *context, *reset, *set;
 	switch (s) {
 	case DIFF_SYMBOL_SEPARATOR:
 		fprintf(o->file, "%s%c",
@@ -592,6 +629,25 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 		emit_line_0(o, context, reset, '\\',
 			    nneof, strlen(nneof));
 		break;
+	case DIFF_SYMBOL_CONTEXT:
+		set = diff_get_color_opt(o, DIFF_CONTEXT);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		emit_line_ws_markup(o, set, reset, line, len, ' ',
+				    flags & (DIFF_SYMBOL_CONTENT_WS_MASK), 0);
+		break;
+	case DIFF_SYMBOL_PLUS:
+		set = diff_get_color_opt(o, DIFF_FILE_NEW);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		emit_line_ws_markup(o, set, reset, line, len, '+',
+				    flags & DIFF_SYMBOL_CONTENT_WS_MASK,
+				    flags & DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF);
+		break;
+	case DIFF_SYMBOL_MINUS:
+		set = diff_get_color_opt(o, DIFF_FILE_OLD);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		emit_line_ws_markup(o, set, reset, line, len, '-',
+				    flags & DIFF_SYMBOL_CONTENT_WS_MASK, 0);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -608,57 +664,31 @@ static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line
 	return ws_blank_line(line, len, ecbdata->ws_rule);
 }
 
-static void emit_line_checked(const char *reset,
-			      struct emit_callback *ecbdata,
-			      const char *line, int len,
-			      enum color_diff color,
-			      unsigned ws_error_highlight,
-			      char sign)
-{
-	const char *set = diff_get_color(ecbdata->color_diff, color);
-	const char *ws = NULL;
-
-	if (ecbdata->opt->ws_error_highlight & ws_error_highlight) {
-		ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE);
-		if (!*ws)
-			ws = NULL;
-	}
-
-	if (!ws)
-		emit_line_0(ecbdata->opt, set, reset, 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 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);
-	}
-}
-
 static void emit_add_line(const char *reset,
 			  struct emit_callback *ecbdata,
 			  const char *line, int len)
 {
-	emit_line_checked(reset, ecbdata, line, len,
-			  DIFF_FILE_NEW, WSEH_NEW, '+');
+	unsigned flags = WSEH_NEW | ecbdata->ws_rule;
+	if (new_blank_line_at_eof(ecbdata, line, len))
+		flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF;
+
+	emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags);
 }
 
 static void emit_del_line(const char *reset,
 			  struct emit_callback *ecbdata,
 			  const char *line, int len)
 {
-	emit_line_checked(reset, ecbdata, line, len,
-			  DIFF_FILE_OLD, WSEH_OLD, '-');
+	unsigned flags = WSEH_OLD | ecbdata->ws_rule;
+	emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_MINUS, line, len, flags);
 }
 
 static void emit_context_line(const char *reset,
 			      struct emit_callback *ecbdata,
 			      const char *line, int len)
 {
-	emit_line_checked(reset, ecbdata, line, len,
-			  DIFF_CONTEXT, WSEH_CONTEXT, ' ');
+	unsigned flags = WSEH_CONTEXT | ecbdata->ws_rule;
+	emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT, line, len, flags);
 }
 
 static void emit_hunk_header(struct emit_callback *ecbdata,
@@ -682,7 +712,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	    memcmp(line, atat, 2) ||
 	    !(ep = memmem(line + 2, len - 2, atat, 2))) {
 		emit_diff_symbol(ecbdata->opt,
-				 DIFF_SYMBOL_CONTEXT_MARKER, line, len);
+				 DIFF_SYMBOL_CONTEXT_MARKER, line, len, 0);
 		return;
 	}
 	ep += 2; /* skip over @@ */
@@ -718,7 +748,7 @@ static void emit_hunk_header(struct emit_callback *ecbdata,
 	strbuf_add(&msgbuf, line + len, org_len - len);
 	strbuf_complete_line(&msgbuf);
 	emit_diff_symbol(ecbdata->opt,
-			 DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len);
+			 DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len, 0);
 	strbuf_release(&msgbuf);
 }
 
@@ -777,7 +807,7 @@ static void emit_rewrite_lines(struct emit_callback *ecb,
 		data += len;
 	}
 	if (!endp)
-		emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0);
+		emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0, 0);
 }
 
 static void emit_rewrite_diff(const char *name_a,
@@ -4866,7 +4896,7 @@ void diff_flush(struct diff_options *options)
 
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
-			emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0);
+			emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0, 0);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);
diff --git a/diff.h b/diff.h
index 5be1ee77a7..8483ca0991 100644
--- a/diff.h
+++ b/diff.h
@@ -148,9 +148,9 @@ struct diff_options {
 	int abbrev;
 	int ita_invisible_in_index;
 /* white-space error highlighting */
-#define WSEH_NEW 1
-#define WSEH_CONTEXT 2
-#define WSEH_OLD 4
+#define WSEH_NEW (1<<12)
+#define WSEH_CONTEXT (1<<13)
+#define WSEH_OLD (1<<14)
 	unsigned ws_error_highlight;
 	const char *prefix;
 	int prefix_length;

-- 
2.12.2.575.gb14f27f917

Junio C Hamano· Jun 21, 2017, 20:05 UTC · re: Stefan Beller · lore

Re: [PATCH 08/26] diff.c: migrate emit_line_checked to use emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

>  static void emit_add_line(const char *reset,
>  			  struct emit_callback *ecbdata,
>  			  const char *line, int len)
>  {
> -	emit_line_checked(reset, ecbdata, line, len,
> -			  DIFF_FILE_NEW, WSEH_NEW, '+');
> +	unsigned flags = WSEH_NEW | ecbdata->ws_rule;
> +	if (new_blank_line_at_eof(ecbdata, line, len))
> +		flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF;
> +
> +	emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags);
>  }

> diff --git a/diff.h b/diff.h
> index 5be1ee77a7..8483ca0991 100644
> --- a/diff.h
> +++ b/diff.h
> @@ -148,9 +148,9 @@ struct diff_options {
>  	int abbrev;
>  	int ita_invisible_in_index;
>  /* white-space error highlighting */
> -#define WSEH_NEW 1
> -#define WSEH_CONTEXT 2
> -#define WSEH_OLD 4
> +#define WSEH_NEW (1<<12)
> +#define WSEH_CONTEXT (1<<13)
> +#define WSEH_OLD (1<<14)

Stefan Beller· Jun 22, 2017, 23:30 UTC · re: Junio C Hamano · lore

Re: [PATCH 08/26] diff.c: migrate emit_line_checked to use emit_diff_symbol

On Wed, Jun 21, 2017 at 1:05 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>>  static void emit_add_line(const char *reset,
>>                         struct emit_callback *ecbdata,
>>                         const char *line, int len)
>>  {
>> -     emit_line_checked(reset, ecbdata, line, len,
>> -                       DIFF_FILE_NEW, WSEH_NEW, '+');
>> +     unsigned flags = WSEH_NEW | ecbdata->ws_rule;
>> +     if (new_blank_line_at_eof(ecbdata, line, len))
>> +             flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF;
>> +
>> +     emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags);
>>  }
>
> This is a bit unsatisfactory that the original code didn't even have
> to make a call to new_blank_line_at_eof() at all when we know we are
> not checking for / coloring whitespace errors, but the function is
> called unconditionally in the new code.

>
>> diff --git a/diff.h b/diff.h
>> index 5be1ee77a7..8483ca0991 100644
>> --- a/diff.h
>> +++ b/diff.h
>> @@ -148,9 +148,9 @@ struct diff_options {
>>       int abbrev;
>>       int ita_invisible_in_index;
>>  /* white-space error highlighting */
>> -#define WSEH_NEW 1
>> -#define WSEH_CONTEXT 2
>> -#define WSEH_OLD 4
>> +#define WSEH_NEW (1<<12)
>> +#define WSEH_CONTEXT (1<<13)
>> +#define WSEH_OLD (1<<14)
>
> Hopefully this is a safe conversion, as everything should come from
> parse_ws_error_highlight() that uses these constants.

I reviewed the conversion again and I think it is safe, still.

>
> But this is brittle; there must be some hint to future readers of
> this code why these bits begin at 12th (it is linked to 07777 we saw
> earlier); otherwise when they change something that needs to widen
> that 07777, they will forget to shift these up, which would screw
> up everything that is carefully laid out here.

Stefan Beller· Jun 22, 2017, 23:37 UTC · re: Stefan Beller · lore

Re: [PATCH 08/26] diff.c: migrate emit_line_checked to use emit_diff_symbol

On Thu, Jun 22, 2017 at 4:30 PM, Stefan Beller <sbeller@google.com> wrote:

> On Wed, Jun 21, 2017 at 1:05 PM, Junio C Hamano <gitster@pobox.com> wrote:
>> Stefan Beller <sbeller@google.com> writes:
>>
>>>  static void emit_add_line(const char *reset,
>>>                         struct emit_callback *ecbdata,
>>>                         const char *line, int len)
>>>  {
>>> -     emit_line_checked(reset, ecbdata, line, len,
>>> -                       DIFF_FILE_NEW, WSEH_NEW, '+');
>>> +     unsigned flags = WSEH_NEW | ecbdata->ws_rule;
>>> +     if (new_blank_line_at_eof(ecbdata, line, len))
>>> +             flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF;
>>> +
>>> +     emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags);
>>>  }
>>
>> This is a bit unsatisfactory that the original code didn't even have
>> to make a call to new_blank_line_at_eof() at all when we know we are
>> not checking for / coloring whitespace errors, but the function is
>> called unconditionally in the new code.
>
> We could check if we do colored output here, I think'll just do that for now,
> but on the other hand this becomes a maintenance nightmare when we
> rely on these flags in the future e.g. for "machine parse-able coloring"
> and would markup according to the flags strictly. I guess we can fix it then.

Actually that function already has some quick return:

static int new_blank_line_at_eof(struct emit_callback *ecbdata, const
char *line, int len)
{
    if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
         ecbdata->blank_at_eof_in_preimage &&
         ecbdata->blank_at_eof_in_postimage &&
         ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage &&
         ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage))
                  return 0;
    return ws_blank_line(line, len, ecbdata->ws_rule);
}

Junio C Hamano· Jun 23, 2017, 04:56 UTC · re: Stefan Beller · lore

Re: [PATCH 08/26] diff.c: migrate emit_line_checked to use emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

> Actually that function already has some quick return:
>
> static int new_blank_line_at_eof(struct emit_callback *ecbdata, const
> char *line, int len)
> {
>     if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
>          ecbdata->blank_at_eof_in_preimage &&
>          ecbdata->blank_at_eof_in_postimage &&
>          ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage &&
>          ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage))
>                   return 0;
>     return ws_blank_line(line, len, ecbdata->ws_rule);
> }

Stefan Beller· Jun 20, 2017, 02:48 UTC · re: Stefan Beller · lore

[PATCH 11/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_FILEPAIR

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/diff.c b/diff.c
index e6029e8213..7c56150b56 100644
--- a/diff.c
+++ b/diff.c
@@ -570,6 +570,7 @@ enum diff_symbol {
 	DIFF_SYMBOL_MINUS,
 	DIFF_SYMBOL_WORDS_PORCELAIN,
 	DIFF_SYMBOL_WORDS,
+	DIFF_SYMBOL_FILEPAIR,
 };
 /*
  * Flags for content lines:
@@ -610,7 +611,7 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 			     const char *line, int len, unsigned flags)
 {
 	static const char *nneof = " No newline at end of file\n";
-	const char *context, *reset, *set;
+	const char *context, *reset, *set, *meta;
 	switch (s) {
 	case DIFF_SYMBOL_SEPARATOR:
 		fprintf(o->file, "%s%c",
@@ -676,6 +677,14 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 		}
 		emit_line(o, context, reset, line, len);
 		break;
+	case DIFF_SYMBOL_FILEPAIR:
+		meta = diff_get_color_opt(o, DIFF_METAINFO);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		fprintf(o->file, "%s%s%s%s%s%s\n", diff_line_prefix(o), meta,
+			flags ? "+++ " : "--- ",
+			line, reset,
+			strchr(line, ' ') ? "\t" : "");
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -847,8 +856,6 @@ static void emit_rewrite_diff(const char *name_a,
 			      struct diff_options *o)
 {
 	int lc_a, lc_b;
-	const char *name_a_tab, *name_b_tab;
-	const char *metainfo = diff_get_color(o->use_color, DIFF_METAINFO);
 	const char *fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO);
 	const char *reset = diff_get_color(o->use_color, DIFF_RESET);
 	static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT;
@@ -868,8 +875,6 @@ static void emit_rewrite_diff(const char *name_a,
 
 	name_a += (*name_a == '/');
 	name_b += (*name_b == '/');
-	name_a_tab = strchr(name_a, ' ') ? "\t" : "";
-	name_b_tab = strchr(name_b, ' ') ? "\t" : "";
 
 	strbuf_reset(&a_name);
 	strbuf_reset(&b_name);
@@ -896,11 +901,11 @@ static void emit_rewrite_diff(const char *name_a,
 
 	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);
+
+	emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR, a_name.buf, a_name.len, 0);
+	emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR, b_name.buf, b_name.len, 1);
+
+	fprintf(o->file, "%s%s@@ -", line_prefix, fraginfo);
 	if (!o->irreversible_delete)
 		print_line_count(o->file, lc_a);
 	else
@@ -1369,10 +1374,8 @@ static void find_lno(const char *line, struct emit_callback *ecbdata)
 static void fn_out_consume(void *priv, char *line, unsigned long len)
 {
 	struct emit_callback *ecbdata = priv;
-	const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO);
 	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;
 
@@ -1383,15 +1386,12 @@ 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_diff_symbol(o, DIFF_SYMBOL_FILEPAIR,
+				 ecbdata->label_path[0],
+				 strlen(ecbdata->label_path[0]), 0);
+		emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR,
+				 ecbdata->label_path[1],
+				 strlen(ecbdata->label_path[1]), 1);
 		ecbdata->label_path[0] = ecbdata->label_path[1] = NULL;
 	}
 

-- 
2.12.2.575.gb14f27f917

Re: [PATCH 11/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_FILEPAIR

> @@ -676,6 +677,14 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
>  		}
>  		emit_line(o, context, reset, line, len);
>  		break;
> +	case DIFF_SYMBOL_FILEPAIR:
> +		meta = diff_get_color_opt(o, DIFF_METAINFO);
> +		reset = diff_get_color_opt(o, DIFF_RESET);
> +		fprintf(o->file, "%s%s%s%s%s%s\n", diff_line_prefix(o), meta,
> +			flags ? "+++ " : "--- ",

> +			line, reset,
> +			strchr(line, ' ') ? "\t" : "");
> +		break;
>  	default:
>  		die("BUG: unknown diff symbol");
>  	}

Junio C Hamano· Jun 21, 2017, 20:09 UTC · re: Jonathan Tan · lore

Re: [PATCH 11/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_FILEPAIR

Jonathan Tan <jonathantanmy@google.com> writes:

> On Mon, 19 Jun 2017 19:48:01 -0700
> Stefan Beller <sbeller@google.com> wrote:
>
>> @@ -676,6 +677,14 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
>>  		}
>>  		emit_line(o, context, reset, line, len);
>>  		break;
>> +	case DIFF_SYMBOL_FILEPAIR:
>> +		meta = diff_get_color_opt(o, DIFF_METAINFO);
>> +		reset = diff_get_color_opt(o, DIFF_RESET);
>> +		fprintf(o->file, "%s%s%s%s%s%s\n", diff_line_prefix(o), meta,
>> +			flags ? "+++ " : "--- ",
>
> I think that a constant should be defined for this flag, just like for
> content lines. If not it is not immediately obvious that a flag should
> be set for the +++ lines.

True.

>> +			line, reset,
>> +			strchr(line, ' ') ? "\t" : "");
>> +		break;

Stefan Beller· Jun 22, 2017, 23:59 UTC · re: Junio C Hamano · lore

Re: [PATCH 11/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_FILEPAIR

On Wed, Jun 21, 2017 at 1:09 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Jonathan Tan <jonathantanmy@google.com> writes:
>
>> On Mon, 19 Jun 2017 19:48:01 -0700
>> Stefan Beller <sbeller@google.com> wrote:
>>
>>> @@ -676,6 +677,14 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
>>>              }
>>>              emit_line(o, context, reset, line, len);
>>>              break;
>>> +    case DIFF_SYMBOL_FILEPAIR:
>>> +            meta = diff_get_color_opt(o, DIFF_METAINFO);
>>> +            reset = diff_get_color_opt(o, DIFF_RESET);
>>> +            fprintf(o->file, "%s%s%s%s%s%s\n", diff_line_prefix(o), meta,
>>> +                    flags ? "+++ " : "--- ",
>>
>> I think that a constant should be defined for this flag, just like for
>> content lines. If not it is not immediately obvious that a flag should
>> be set for the +++ lines.
>
> True.
>
>>> +                    line, reset,
>>> +                    strchr(line, ' ') ? "\t" : "");
>>> +            break;
>
> Also this is somewhat misnamed in that a call to it only deals with
> one half of a filepair, iow, the caller must call it twice to show a
> single filepair.

Stefan Beller· Jun 20, 2017, 02:47 UTC · re: Stefan Beller · lore

[PATCH 04/26] diff.c: introduce emit_diff_symbol

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/diff.c b/diff.c
index 2f9722b382..89466018e5 100644
--- a/diff.c
+++ b/diff.c
@@ -559,6 +559,24 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
 	emit_line_0(o, set, reset, line[0], line+1, len-1);
 }
 
+enum diff_symbol {
+	DIFF_SYMBOL_SEPARATOR,
+};
+
+static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
+			     const char *line, int len)
+{
+	switch (s) {
+	case DIFF_SYMBOL_SEPARATOR:
+		fprintf(o->file, "%s%c",
+			diff_line_prefix(o),
+			o->line_termination);
+		break;
+	default:
+		die("BUG: unknown diff symbol");
+	}
+}
+
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
@@ -4833,9 +4851,7 @@ 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);
+			emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0);
 			if (options->stat_sep) {
 				/* attach patch instead of inline */
 				fputs(options->stat_sep, options->file);

-- 
2.12.2.575.gb14f27f917

Junio C Hamano· Jun 21, 2017, 19:36 UTC · re: Stefan Beller · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

> Signed-off-by: Stefan Beller <sbeller@google.com>
> ---
>  diff.c | 22 +++++++++++++++++++---
>  1 file changed, 19 insertions(+), 3 deletions(-)
>
> diff --git a/diff.c b/diff.c
> index 2f9722b382..89466018e5 100644
> --- a/diff.c
> +++ b/diff.c
> @@ -559,6 +559,24 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
>  	emit_line_0(o, set, reset, line[0], line+1, len-1);
>  }
>  
> +enum diff_symbol {
> +	DIFF_SYMBOL_SEPARATOR,

Drop the last comma from enum?

> +static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
> +			     const char *line, int len)
> +{
> +	switch (s) {
> +	case DIFF_SYMBOL_SEPARATOR:
> +		fprintf(o->file, "%s%c",
> +			diff_line_prefix(o),
> +			o->line_termination);
> +		break;

> +	default:
> +		die("BUG: unknown diff symbol");
> +	}
> +}
> +
>  static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
>  {
>  	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
> @@ -4833,9 +4851,7 @@ 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);
> +			emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0);
>  			if (options->stat_sep) {
>  				/* attach patch instead of inline */
>  				fputs(options->stat_sep, options->file);

Stefan Beller· Jun 21, 2017, 19:46 UTC · re: Junio C Hamano · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

On Wed, Jun 21, 2017 at 12:36 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>> Signed-off-by: Stefan Beller <sbeller@google.com>
>> ---
>>  diff.c | 22 +++++++++++++++++++---
>>  1 file changed, 19 insertions(+), 3 deletions(-)
>>
>> diff --git a/diff.c b/diff.c
>> index 2f9722b382..89466018e5 100644
>> --- a/diff.c
>> +++ b/diff.c
>> @@ -559,6 +559,24 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
>>       emit_line_0(o, set, reset, line[0], line+1, len-1);
>>  }
>>
>> +enum diff_symbol {
>> +     DIFF_SYMBOL_SEPARATOR,
>
> Drop the last comma from enum?

>
>> +static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
>> +                          const char *line, int len)
>> +{
>> +     switch (s) {
>> +     case DIFF_SYMBOL_SEPARATOR:
>> +             fprintf(o->file, "%s%c",
>> +                     diff_line_prefix(o),
>> +                     o->line_termination);
>> +             break;
>
> As the first patch in the "diff-symbol" subseries of this topic,
> this change must seriously be justified.  Why is it so important
> that a printing of an empty line must be moved to a helper function,
> which later will gain ability to show other kind of lines?

Junio C Hamano· Jun 21, 2017, 20:26 UTC · re: Stefan Beller · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

> This will be painful though as the next ~20 patches
> add more symbols mostly at the end.

> , maybe I need
> to restructure that such that the last symbol stays the same
> throughout the series. Thanks for that thought.

Junio C Hamano· Jun 21, 2017, 21:13 UTC · re: Stefan Beller · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

>>>
>>> +enum diff_symbol {
>>> +     DIFF_SYMBOL_SEPARATOR,
>>
>> Drop the last comma from enum?
>
> I looked through out code base and for enums this is
> actually strictly enforced, so I guess I have to play
> by the rules here as I do not want to be the first
> to deviate from an upheld standard.

Stefan Beller· Jun 21, 2017, 21:23 UTC · re: Junio C Hamano · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

On Wed, Jun 21, 2017 at 2:13 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>>>>
>>>> +enum diff_symbol {
>>>> +     DIFF_SYMBOL_SEPARATOR,
>>>
>>> Drop the last comma from enum?
>>
>> I looked through out code base and for enums this is
>> actually strictly enforced, so I guess I have to play
>> by the rules here as I do not want to be the first
>> to deviate from an upheld standard.
>
> You sound like you are trying to find an excuse "not to play by the
> rules".  Don't.
>

  C99 allows a trailing comma to follow the last enumeration
  constant initializer within an enumeration type declaration,
  similar to structure member initialization lists.
  C99: §6.7.2.2

  For struct member lists we already do that, e.g.
  builtin/help.c: struct common_guides[]
  builtin/repack.c: struct exts[]
  ...

Junio C Hamano· Jun 21, 2017, 21:43 UTC · re: Stefan Beller · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

Stefan Beller <sbeller@google.com> writes:

>>> I looked through out code base and for enums this is
>>> actually strictly enforced, so I guess I have to play
>>> by the rules here as I do not want to be the first
>>> to deviate from an upheld standard.
>>
>> You sound like you are trying to find an excuse "not to play by the
>> rules".  Don't.
>
> When the rules are not yielding best results, adapting the rules
> should be considered.

Stefan Beller· Jun 21, 2017, 21:51 UTC · re: Junio C Hamano · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

On Wed, Jun 21, 2017 at 2:43 PM, Junio C Hamano <gitster@pobox.com> wrote:

> Stefan Beller <sbeller@google.com> writes:
>
>>>> I looked through out code base and for enums this is
>>>> actually strictly enforced, so I guess I have to play
>>>> by the rules here as I do not want to be the first
>>>> to deviate from an upheld standard.
>>>
>>> You sound like you are trying to find an excuse "not to play by the
>>> rules".  Don't.
>>
>> When the rules are not yielding best results, adapting the rules
>> should be considered.
>
> I do not think anybody is saying that it is unreasonable to have a
> wish that it would be wonderful if we could use C99 features.
>
> Trailing comma at the end of enum is the least interesting addition
> (it is a fix for a previous editions' brown-paper-bag mistake).  I'd
> be delighted if we can drop support for older compilers and start
> using designated initializers, for example.
>
> Finding other's violation of the current coding guideline is *not*
> the right way to promote for that future, however.

In practice it is, though.

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

On 06/21, Stefan Beller wrote:

> On Wed, Jun 21, 2017 at 12:36 PM, Junio C Hamano <gitster@pobox.com> wrote:
> > Stefan Beller <sbeller@google.com> writes:
> >
> >> Signed-off-by: Stefan Beller <sbeller@google.com>
> >> ---
> >>  diff.c | 22 +++++++++++++++++++---
> >>  1 file changed, 19 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/diff.c b/diff.c
> >> index 2f9722b382..89466018e5 100644
> >> --- a/diff.c
> >> +++ b/diff.c
> >> @@ -559,6 +559,24 @@ static void emit_line(struct diff_options *o, const char *set, const char *reset
> >>       emit_line_0(o, set, reset, line[0], line+1, len-1);
> >>  }
> >>
> >> +enum diff_symbol {
> >> +     DIFF_SYMBOL_SEPARATOR,
> >
> > Drop the last comma from enum?
> 
> I looked through out code base and for enums this is
> actually strictly enforced, so I guess I have to play
> by the rules here as I do not want to be the first
> to deviate from an upheld standard.
> 
> This will be painful though as the next ~20 patches
> add more symbols mostly at the end, maybe I need
> to restructure that such that the last symbol stays the same
> throughout the series. Thanks for that thought.

> 
> >
> >> +static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
> >> +                          const char *line, int len)
> >> +{
> >> +     switch (s) {
> >> +     case DIFF_SYMBOL_SEPARATOR:
> >> +             fprintf(o->file, "%s%c",
> >> +                     diff_line_prefix(o),
> >> +                     o->line_termination);
> >> +             break;
> >
> > As the first patch in the "diff-symbol" subseries of this topic,
> > this change must seriously be justified.  Why is it so important
> > that a printing of an empty line must be moved to a helper function,
> > which later will gain ability to show other kind of lines?
> 
> Ah yes. This got lost in comparison to the currently queued series with
> diff_lines. The justification for the change was in the buffer patch,
> but now we need to have the justification here.
> 
> In the old series, I had copied the same text in all these
> refactoring patches, but thought to delete them in this series. The first
> refactoring patch makes sense though.
> 
> Thanks,
> Stefan

-- 
Brandon Williams

Junio C Hamano· Jun 21, 2017, 21:52 UTC · re: Brandon Williams · lore

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

Brandon Williams <bmwill@google.com> writes:

> I don't think this is strictly enforced.  If you look at grep.h:197 the
> enum 'grep_source_type' has a trailing comma.

Perhaps we should start pushing for C99 features?

Re: [PATCH 04/26] diff.c: introduce emit_diff_symbol

On 06/21, Junio C Hamano wrote:

> Brandon Williams <bmwill@google.com> writes:
> 
> > I don't think this is strictly enforced.  If you look at grep.h:197 the
> > enum 'grep_source_type' has a trailing comma.
> 
> OK, so we now know that at least since e1327023 ("grep: refactor the
> concept of "grep source" into an object", 2012-02-02) we haven't
> heard from anybody whose compiler fails to grok this.
> 
> Perhaps we should start pushing for C99 features?

And I'm all for moving to C99 :)

-- 
Brandon Williams

Stefan Beller· Jun 20, 2017, 02:48 UTC · re: Stefan Beller · lore

[PATCH 15/26] submodule.c: migrate diff output to use emit_diff_symbol

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c      | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++++---------
 diff.h      |  9 +++++++
 submodule.c | 85 ++++++++++++++++++++++++++--------------------------------
 submodule.h | 13 +++------
 4 files changed, 128 insertions(+), 68 deletions(-)

diff --git a/diff.c b/diff.c
index 96ce53c5cf..42a9020d95 100644
--- a/diff.c
+++ b/diff.c
@@ -574,6 +574,13 @@ enum diff_symbol {
 	DIFF_SYMBOL_HEADER,
 	DIFF_SYMBOL_BINARY_FILES,
 	DIFF_SYMBOL_REWRITE_DIFF,
+	DIFF_SYMBOL_SUBMODULE_ADD,
+	DIFF_SYMBOL_SUBMODULE_DEL,
+	DIFF_SYMBOL_SUBMODULE_UNTRACKED,
+	DIFF_SYMBOL_SUBMODULE_MODIFIED,
+	DIFF_SYMBOL_SUBMODULE_HEADER,
+	DIFF_SYMBOL_SUBMODULE_ERROR,
+	DIFF_SYMBOL_SUBMODULE_PIPETHROUGH,
 };
 /*
  * Flags for content lines:
@@ -700,11 +707,77 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 		reset = diff_get_color_opt(o, DIFF_RESET);
 		emit_line(o, fraginfo, reset, line, len);
 		break;
+	case DIFF_SYMBOL_SUBMODULE_ADD:
+		set = diff_get_color_opt(o, DIFF_FILE_NEW);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		emit_line(o, set, reset, line, len);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_DEL:
+		set = diff_get_color_opt(o, DIFF_FILE_OLD);
+		reset = diff_get_color_opt(o, DIFF_RESET);
+		emit_line(o, set, reset, line, len);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_UNTRACKED:
+		fprintf(o->file, "%sSubmodule %s contains untracked content\n",
+			diff_line_prefix(o), line);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_MODIFIED:
+		fprintf(o->file, "%sSubmodule %s contains modified content\n",
+			diff_line_prefix(o), line);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_HEADER:
+		fprintf(o->file, "%s%s", diff_line_prefix(o), line);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_ERROR:
+		emit_line(o, "", "", line, len);
+		break;
+	case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH:
+		emit_line(o, "", "", line, len);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
 }
 
+void diff_emit_submodule_del(struct diff_options *o, const char *line)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_DEL, line, strlen(line), 0);
+}
+
+void diff_emit_submodule_add(struct diff_options *o, const char *line)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ADD, line, strlen(line), 0);
+}
+
+void diff_emit_submodule_untracked(struct diff_options *o, const char *path)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_UNTRACKED,
+			 path, strlen(path), 0);
+}
+
+void diff_emit_submodule_modified(struct diff_options *o, const char *path)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_MODIFIED,
+			 path, strlen(path), 0);
+}
+
+void diff_emit_submodule_header(struct diff_options *o, const char *header)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_HEADER,
+			 header, strlen(header), 0);
+}
+
+void diff_emit_submodule_error(struct diff_options *o, const char *err)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ERROR, err, strlen(err), 0);
+}
+
+void diff_emit_submodule_pipethrough(struct diff_options *o,
+				     const char *line, int len)
+{
+	emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, line, len, 0);
+}
+
 static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len)
 {
 	if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) &&
@@ -2465,24 +2538,16 @@ static void builtin_diff(const char *name_a,
 	if (o->submodule_format == DIFF_SUBMODULE_LOG &&
 	    (!one->mode || S_ISGITLINK(one->mode)) &&
 	    (!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);
+				two->dirty_submodule);
 		return;
 	} else if (o->submodule_format == DIFF_SUBMODULE_INLINE_DIFF &&
 		   (!one->mode || S_ISGITLINK(one->mode)) &&
 		   (!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);
+				two->dirty_submodule);
 		return;
 	}
 
diff --git a/diff.h b/diff.h
index 8483ca0991..2ee0ef3908 100644
--- a/diff.h
+++ b/diff.h
@@ -188,6 +188,15 @@ struct diff_options {
 	int diff_path_counter;
 };
 
+void diff_emit_submodule_del(struct diff_options *o, const char *line);
+void diff_emit_submodule_add(struct diff_options *o, const char *line);
+void diff_emit_submodule_untracked(struct diff_options *o, const char *path);
+void diff_emit_submodule_modified(struct diff_options *o, const char *path);
+void diff_emit_submodule_header(struct diff_options *o, const char *header);
+void diff_emit_submodule_error(struct diff_options *o, const char *err);
+void diff_emit_submodule_pipethrough(struct diff_options *o,
+				     const char *line, int len);
+
 enum color_diff {
 	DIFF_RESET = 0,
 	DIFF_CONTEXT = 1,
diff --git a/submodule.c b/submodule.c
index d3299e29c0..71471f3241 100644
--- a/submodule.c
+++ b/submodule.c
@@ -362,9 +362,7 @@ 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,
-		const char *del, const char *add, const char *reset)
+static void print_submodule_summary(struct rev_info *rev, struct diff_options *o)
 {
 	static const char format[] = "  %m %s";
 	struct strbuf sb = STRBUF_INIT;
@@ -375,18 +373,12 @@ 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)
+			diff_emit_submodule_del(o, sb.buf);
+		else
+			diff_emit_submodule_add(o, sb.buf);
 	}
 	strbuf_release(&sb);
 }
@@ -413,11 +405,9 @@ 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,
+		unsigned dirty_submodule,
 		struct commit **left, struct commit **right,
 		struct commit_list **merge_bases)
 {
@@ -426,11 +416,10 @@ 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);
+		diff_emit_submodule_untracked(o, path);
+
 	if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED)
-		fprintf(f, "%sSubmodule %s contains modified content\n",
-			line_prefix, path);
+		diff_emit_submodule_modified(o, path);
 
 	if (is_null_oid(one))
 		message = "(new submodule)";
@@ -472,31 +461,29 @@ 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)" : "");
+	diff_emit_submodule_header(o, sb.buf);
 
 	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)
+		unsigned dirty_submodule)
 {
 	struct rev_info rev;
 	struct commit *left = NULL, *right = NULL;
 	struct commit_list *merge_bases = NULL;
 
-	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
-			      meta, reset, &left, &right, &merge_bases);
+	show_submodule_header(o, path, one, two, dirty_submodule,
+			      &left, &right, &merge_bases);
 
 	/*
 	 * If we don't have both a left and a right pointer, there is no
@@ -508,11 +495,11 @@ 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);
+		diff_emit_submodule_error(o, "(revision walker failed)\n");
 		goto out;
 	}
 
-	print_submodule_summary(&rev, f, line_prefix, del, add, reset);
+	print_submodule_summary(&rev, o);
 
 out:
 	if (merge_bases)
@@ -521,21 +508,18 @@ 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)
+		unsigned dirty_submodule)
 {
 	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,
-			      meta, reset, &left, &right, &merge_bases);
+	show_submodule_header(o, path, one, two, dirty_submodule,
+			      &left, &right, &merge_bases);
 
 	/* We need a valid left and right commit to display a difference */
 	if (!(left || is_null_oid(one)) ||
@@ -547,15 +531,16 @@ 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, "--color=%s", want_color(o->use_color) ?
+			 "always" : "never");
+
 	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
 		argv_array_pushf(&cp.args, "--src-prefix=%s%s/",
 				 o->b_prefix, path);
@@ -578,11 +563,17 @@ 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))
+		diff_emit_submodule_error(o, "(diff failed)\n");
+
+	while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF)
+		diff_emit_submodule_pipethrough(o, sb.buf, sb.len);
+
+	if (finish_command(&cp))
+		diff_emit_submodule_error(o, "(diff failed)\n");
 
 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..e7358863e9 100644
--- a/submodule.h
+++ b/submodule.h
@@ -53,17 +53,12 @@ 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,
+		unsigned dirty_submodule);
+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);
+		unsigned dirty_submodule);
 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.*/

-- 
2.12.2.575.gb14f27f917

Re: [PATCH 15/26] submodule.c: migrate diff output to use emit_diff_symbol

> As the submodule process is no longer attached to the same stdout as
> the superprojects process, we need to pass coloring explicitly.

> Remove the colors from the function signatures, as all the coloring
> decisions will be made either inside the child process or the final
> emit_diff_symbol.

    Create diff_emit_submodule_.* functions that make its own coloring
    decisions and migrate submodule.c to use them. This centralizes
    diff output, including coloring information, in one file.

or something like that.

Stefan Beller· Jun 20, 2017, 02:48 UTC · re: Stefan Beller · lore

[PATCH 19/26] diff.c: emit_diff_symbol learns about DIFF_SYMBOL_STAT_SEP

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/diff.c b/diff.c
index 5b46baa12a..18bfc4720b 100644
--- a/diff.c
+++ b/diff.c
@@ -591,6 +591,7 @@ enum diff_symbol {
 	DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES,
 	DIFF_SYMBOL_STATS_LINE,
 	DIFF_SYMBOL_WORD_DIFF,
+	DIFF_SYMBOL_STAT_SEP,
 };
 /*
  * Flags for content lines:
@@ -776,6 +777,9 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 	case DIFF_SYMBOL_WORD_DIFF:
 		fprintf(o->file, "%.*s", len, line);
 		break;
+	case DIFF_SYMBOL_STAT_SEP:
+		fputs(o->stat_sep, o->file);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -5085,10 +5089,10 @@ void diff_flush(struct diff_options *options)
 	if (output_format & DIFF_FORMAT_PATCH) {
 		if (separator) {
 			emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0, 0);
-			if (options->stat_sep) {
+			if (options->stat_sep)
 				/* attach patch instead of inline */
-				fputs(options->stat_sep, options->file);
-			}
+				emit_diff_symbol(options, DIFF_SYMBOL_STAT_SEP,
+						 NULL, 0, 0);
 		}
 
 		diff_flush_patch_all_file_pairs(options);

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:48 UTC · re: Stefan Beller · lore

[PATCH 12/26] diff.c: emit_diff_symbol learns DIFF_SYMBOL_HEADER

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/diff.c b/diff.c
index 7c56150b56..95f11ea86f 100644
--- a/diff.c
+++ b/diff.c
@@ -571,6 +571,7 @@ enum diff_symbol {
 	DIFF_SYMBOL_WORDS_PORCELAIN,
 	DIFF_SYMBOL_WORDS,
 	DIFF_SYMBOL_FILEPAIR,
+	DIFF_SYMBOL_HEADER,
 };
 /*
  * Flags for content lines:
@@ -685,6 +686,9 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 			line, reset,
 			strchr(line, ' ') ? "\t" : "");
 		break;
+	case DIFF_SYMBOL_HEADER:
+		fprintf(o->file, "%s", line);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
@@ -1380,7 +1384,8 @@ 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);
+		emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+				 ecbdata->header->buf, ecbdata->header->len, 0);
 		strbuf_reset(ecbdata->header);
 		ecbdata->header = NULL;
 	}
@@ -2514,7 +2519,8 @@ static void builtin_diff(const char *name_a,
 		if (complete_rewrite &&
 		    (textconv_one || !diff_filespec_is_binary(one)) &&
 		    (textconv_two || !diff_filespec_is_binary(two))) {
-			fprintf(o->file, "%s", header.buf);
+			emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+					 header.buf, header.len, 0);
 			strbuf_reset(&header);
 			emit_rewrite_diff(name_a, name_b, one, two,
 						textconv_one, textconv_two, o);
@@ -2524,7 +2530,8 @@ static void builtin_diff(const char *name_a,
 	}
 
 	if (o->irreversible_delete && lbl[1][0] == '/') {
-		fprintf(o->file, "%s", header.buf);
+		emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf,
+				 header.len, 0);
 		strbuf_reset(&header);
 		goto free_ab_and_return;
 	} else if (!DIFF_OPT_TST(o, TEXT) &&
@@ -2535,10 +2542,13 @@ static void builtin_diff(const char *name_a,
 		    !DIFF_OPT_TST(o, BINARY)) {
 			if (!oidcmp(&one->oid, &two->oid)) {
 				if (must_show_header)
-					fprintf(o->file, "%s", header.buf);
+					emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+							 header.buf, header.len,
+							 0);
 				goto free_ab_and_return;
 			}
-			fprintf(o->file, "%s", header.buf);
+			emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+					 header.buf, header.len, 0);
 			fprintf(o->file, "%sBinary files %s and %s differ\n",
 				line_prefix, lbl[0], lbl[1]);
 			goto free_ab_and_return;
@@ -2549,10 +2559,11 @@ static void builtin_diff(const char *name_a,
 		if (mf1.size == mf2.size &&
 		    !memcmp(mf1.ptr, mf2.ptr, mf1.size)) {
 			if (must_show_header)
-				fprintf(o->file, "%s", header.buf);
+				emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+						 header.buf, header.len, 0);
 			goto free_ab_and_return;
 		}
-		fprintf(o->file, "%s", header.buf);
+		emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf, header.len, 0);
 		strbuf_reset(&header);
 		if (DIFF_OPT_TST(o, BINARY))
 			emit_binary_diff(o->file, &mf1, &mf2, line_prefix);
@@ -2570,7 +2581,8 @@ static void builtin_diff(const char *name_a,
 		const struct userdiff_funcname *pe;
 
 		if (must_show_header) {
-			fprintf(o->file, "%s", header.buf);
+			emit_diff_symbol(o, DIFF_SYMBOL_HEADER,
+					 header.buf, header.len, 0);
 			strbuf_reset(&header);
 		}
 

-- 
2.12.2.575.gb14f27f917

Stefan Beller· Jun 20, 2017, 02:48 UTC · re: Stefan Beller · lore

[PATCH 17/26] diff.c: convert show_stats to use emit_diff_symbol

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 diff.c | 118 +++++++++++++++++++++++++++++++++++++++++------------------------
 diff.h |   4 +--
 2 files changed, 77 insertions(+), 45 deletions(-)

diff --git a/diff.c b/diff.c
index e6ade5fde0..0a5ff2500f 100644
--- a/diff.c
+++ b/diff.c
@@ -586,7 +586,10 @@ enum diff_symbol {
 	DIFF_SYMBOL_SUBMODULE_HEADER,
 	DIFF_SYMBOL_SUBMODULE_ERROR,
 	DIFF_SYMBOL_SUBMODULE_PIPETHROUGH,
-
+	DIFF_SYMBOL_STATS_SUMMARY_NO_FILES,
+	DIFF_SYMBOL_STATS_SUMMARY_ABBREV,
+	DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES,
+	DIFF_SYMBOL_STATS_LINE,
 };
 /*
  * Flags for content lines:
@@ -628,6 +631,7 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 {
 	static const char *nneof = " No newline at end of file\n";
 	const char *context, *reset, *set, *meta, *fraginfo;
+	struct strbuf sb = STRBUF_INIT;
 	switch (s) {
 	case DIFF_SYMBOL_SEPARATOR:
 		fprintf(o->file, "%s%c",
@@ -756,9 +760,22 @@ static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s,
 	case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH:
 		emit_line(o, "", "", line, len);
 		break;
+	case DIFF_SYMBOL_STATS_SUMMARY_NO_FILES:
+		fprintf(o->file, " 0 files changed\n");
+		break;
+	case DIFF_SYMBOL_STATS_SUMMARY_ABBREV:
+		emit_line(o, "", "", " ...\n", strlen(" ...\n"));
+		break;
+	case DIFF_SYMBOL_STATS_LINE:
+		emit_line(o, "", "", line, len);
+		break;
+	case DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES:
+		emit_line(o, "", "", line, len);
+		break;
 	default:
 		die("BUG: unknown diff symbol");
 	}
+	strbuf_release(&sb);
 }
 
 void diff_emit_submodule_del(struct diff_options *o, const char *line)
@@ -1712,20 +1729,14 @@ static int scale_linear(int it, int width, int max_change)
 	return 1 + (it * (width - 1) / max_change);
 }
 
-static void show_name(FILE *file,
-		      const char *prefix, const char *name, int len)
-{
-	fprintf(file, " %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)
@@ -1749,14 +1760,16 @@ 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)
+static void print_stat_summary_inserts_deletes(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");
+		emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_NO_FILES,
+				 NULL, 0, 0);
+		return;
 	}
 
 	strbuf_addf(&sb,
@@ -1783,9 +1796,19 @@ int print_stat_summary(FILE *fp, int files, int insertions, int deletions)
 			    deletions);
 	}
 	strbuf_addch(&sb, '\n');
-	ret = fputs(sb.buf, fp);
+	emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES,
+			 sb.buf, sb.len, 0);
 	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_inserts_deletes(&o, files, insertions, deletions);
 }
 
 static void show_stats(struct diffstat_t *data, struct diff_options *options)
@@ -1795,13 +1818,13 @@ 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);
@@ -1955,26 +1978,32 @@ 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");
+			strbuf_addf(&out, " %s%-*s |", prefix, len, name);
+			strbuf_addf(&out, " %*s", number_width, "Bin");
 			if (!added && !deleted) {
-				putc('\n', options->file);
+				strbuf_addch(&out, '\n');
+				emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
+						 out.buf, out.len, 0);
+				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_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
+					 out.buf, out.len, 0);
+			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");
+			strbuf_addf(&out, " %s%-*s |", prefix, len, name);
+			strbuf_addstr(&out, " Unmerged\n");
+			emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
+					 out.buf, out.len, 0);
+			strbuf_reset(&out);
 			continue;
 		}
 
@@ -1997,14 +2026,16 @@ 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",
+		strbuf_addf(&out, " %s%-*s |", prefix, len, name);
+		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_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
+				 out.buf, out.len, 0);
+		strbuf_reset(&out);
 	}
 
 	for (i = 0; i < data->nr; i++) {
@@ -2025,11 +2056,13 @@ 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_diff_symbol(options,
+					 DIFF_SYMBOL_STATS_SUMMARY_ABBREV,
+					 NULL, 0, 0);
 		extra_shown = 1;
 	}
-	fprintf(options->file, "%s", line_prefix);
-	print_stat_summary(options->file, total_files, adds, dels);
+
+	print_stat_summary_inserts_deletes(options, total_files, adds, dels);
 }
 
 static void show_shortstats(struct diffstat_t *data, struct diff_options *options)
@@ -2041,7 +2074,7 @@ 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))) {
@@ -2051,8 +2084,7 @@ 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_inserts_deletes(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 2ee0ef3908..b73f7a1e75 100644
--- a/diff.h
+++ b/diff.h
@@ -398,8 +398,8 @@ 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 */