Merge branch 'jk/blame-line-porcelain'

* jk/blame-line-porcelain:
  blame: add --line-porcelain output format
  blame: refactor porcelain output
  add tests for various blame formats

4 files changed, 131 insertions, 10 deletions

diff --git a/Documentation/blame-options.txt b/Documentation/blame-options.txt
index 16e3c68576..e76195ac97 100644
--- a/Documentation/blame-options.txt
+++ b/Documentation/blame-options.txt
@@ -52,6 +52,11 @@ of lines before or after the line given by <start>.
 --porcelain::
 	Show in a format designed for machine consumption.
 
+--line-porcelain::
+	Show the porcelain format, but output commit information for
+	each line, not just the first time a commit is referenced.
+	Implies --porcelain.
+
 --incremental::
 	Show the result incrementally in a format designed for
 	machine consumption.
diff --git a/Documentation/git-blame.txt b/Documentation/git-blame.txt
index bb8edb4abc..9516914236 100644
--- a/Documentation/git-blame.txt
+++ b/Documentation/git-blame.txt
@@ -105,6 +105,19 @@ The contents of the actual line is output after the above
 header, prefixed by a TAB. This is to allow adding more
 header elements later.
 
+The porcelain format generally suppresses commit information that has
+already been seen. For example, two lines that are blamed to the same
+commit will both be shown, but the details for that commit will be shown
+only once. This is more efficient, but may require more state be kept by
+the reader. The `--line-porcelain` option can be used to output full
+commit information for each line, allowing simpler (but less efficient)
+usage like:
+
+	# count the number of lines attributed to each author
+	git blame --line-porcelain file |
+	sed -n 's/^author //p' |
+	sort | uniq -c | sort -rn
+
 
 SPECIFYING RANGES
 -----------------
diff --git a/builtin/blame.c b/builtin/blame.c
index 4242e4b513..26a5d424b8 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1484,13 +1484,14 @@ static void write_filename_info(const char *path)
 /*
  * Porcelain/Incremental format wants to show a lot of details per
  * commit.  Instead of repeating this every line, emit it only once,
- * the first time each commit appears in the output.
+ * the first time each commit appears in the output (unless the
+ * user has specifically asked for us to repeat).
  */
-static int emit_one_suspect_detail(struct origin *suspect)
+static int emit_one_suspect_detail(struct origin *suspect, int repeat)
 {
 	struct commit_info ci;
 
-	if (suspect->commit->object.flags & METAINFO_SHOWN)
+	if (!repeat && (suspect->commit->object.flags & METAINFO_SHOWN))
 		return 0;
 
 	suspect->commit->object.flags |= METAINFO_SHOWN;
@@ -1529,7 +1530,7 @@ static void found_guilty_entry(struct blame_entry *ent)
 		printf("%s %d %d %d\n",
 		       sha1_to_hex(suspect->commit->object.sha1),
 		       ent->s_lno + 1, ent->lno + 1, ent->num_lines);
-		emit_one_suspect_detail(suspect);
+		emit_one_suspect_detail(suspect, 0);
 		write_filename_info(suspect->path);
 		maybe_flush_or_die(stdout, "stdout");
 	}
@@ -1618,9 +1619,19 @@ static const char *format_time(unsigned long time, const char *tz_str,
 #define OUTPUT_SHOW_SCORE      0100
 #define OUTPUT_NO_AUTHOR       0200
 #define OUTPUT_SHOW_EMAIL	0400
+#define OUTPUT_LINE_PORCELAIN 01000
 
-static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent)
+static void emit_porcelain_details(struct origin *suspect, int repeat)
 {
+	if (emit_one_suspect_detail(suspect, repeat) ||
+	    (suspect->commit->object.flags & MORE_THAN_ONE_PATH))
+		write_filename_info(suspect->path);
+}
+
+static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent,
+			   int opt)
+{
+	int repeat = opt & OUTPUT_LINE_PORCELAIN;
 	int cnt;
 	const char *cp;
 	struct origin *suspect = ent->suspect;
@@ -1633,17 +1644,18 @@ static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent)
 	       ent->s_lno + 1,
 	       ent->lno + 1,
 	       ent->num_lines);
-	if (emit_one_suspect_detail(suspect) ||
-	    (suspect->commit->object.flags & MORE_THAN_ONE_PATH))
-		write_filename_info(suspect->path);
+	emit_porcelain_details(suspect, repeat);
 
 	cp = nth_line(sb, ent->lno);
 	for (cnt = 0; cnt < ent->num_lines; cnt++) {
 		char ch;
-		if (cnt)
+		if (cnt) {
 			printf("%s %d %d\n", hex,
 			       ent->s_lno + 1 + cnt,
 			       ent->lno + 1 + cnt);
+			if (repeat)
+				emit_porcelain_details(suspect, 1);
+		}
 		putchar('\t');
 		do {
 			ch = *cp++;
@@ -1756,7 +1768,7 @@ static void output(struct scoreboard *sb, int option)
 
 	for (ent = sb->ent; ent; ent = ent->next) {
 		if (option & OUTPUT_PORCELAIN)
-			emit_porcelain(sb, ent);
+			emit_porcelain(sb, ent, option);
 		else {
 			emit_other(sb, ent, option);
 		}
@@ -2300,6 +2312,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		OPT_BIT('f', "show-name", &output_option, "Show original filename (Default: auto)", OUTPUT_SHOW_NAME),
 		OPT_BIT('n', "show-number", &output_option, "Show original linenumber (Default: off)", OUTPUT_SHOW_NUMBER),
 		OPT_BIT('p', "porcelain", &output_option, "Show in a format designed for machine consumption", OUTPUT_PORCELAIN),
+		OPT_BIT(0, "line-porcelain", &output_option, "Show porcelain format with per-line commit information", OUTPUT_PORCELAIN|OUTPUT_LINE_PORCELAIN),
 		OPT_BIT('c', NULL, &output_option, "Use the same output mode as git-annotate (Default: off)", OUTPUT_ANNOTATE_COMPAT),
 		OPT_BIT('t', NULL, &output_option, "Show raw timestamp (Default: off)", OUTPUT_RAW_TIMESTAMP),
 		OPT_BIT('l', NULL, &output_option, "Show long commit SHA1 (Default: off)", OUTPUT_LONG_OBJECT_NAME),
diff --git a/t/t8008-blame-formats.sh b/t/t8008-blame-formats.sh
new file mode 100755
index 0000000000..d15f8b3d47
--- /dev/null
+++ b/t/t8008-blame-formats.sh
@@ -0,0 +1,90 @@
+#!/bin/sh
+
+test_description='blame output in various formats on a simple case'
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	echo a >file &&
+	git add file
+	test_tick &&
+	git commit -m one &&
+	echo b >>file &&
+	echo c >>file &&
+	echo d >>file &&
+	test_tick &&
+	git commit -a -m two
+'
+
+cat >expect <<'EOF'
+^baf5e0b (A U Thor 2005-04-07 15:13:13 -0700 1) a
+8825379d (A U Thor 2005-04-07 15:14:13 -0700 2) b
+8825379d (A U Thor 2005-04-07 15:14:13 -0700 3) c
+8825379d (A U Thor 2005-04-07 15:14:13 -0700 4) d
+EOF
+test_expect_success 'normal blame output' '
+	git blame file >actual &&
+	test_cmp expect actual
+'
+
+ID1=baf5e0b3869e0b2b2beb395a3720c7b51eac94fc
+COMMIT1='author A U Thor
+author-mail <author@example.com>
+author-time 1112911993
+author-tz -0700
+committer C O Mitter
+committer-mail <committer@example.com>
+committer-time 1112911993
+committer-tz -0700
+summary one
+boundary
+filename file'
+ID2=8825379dfb8a1267b58e8e5bcf69eec838f685ec
+COMMIT2='author A U Thor
+author-mail <author@example.com>
+author-time 1112912053
+author-tz -0700
+committer C O Mitter
+committer-mail <committer@example.com>
+committer-time 1112912053
+committer-tz -0700
+summary two
+previous baf5e0b3869e0b2b2beb395a3720c7b51eac94fc file
+filename file'
+
+cat >expect <<EOF
+$ID1 1 1 1
+$COMMIT1
+	a
+$ID2 2 2 3
+$COMMIT2
+	b
+$ID2 3 3
+	c
+$ID2 4 4
+	d
+EOF
+test_expect_success 'blame --porcelain output' '
+	git blame --porcelain file >actual &&
+	test_cmp expect actual
+'
+
+cat >expect <<EOF
+$ID1 1 1 1
+$COMMIT1
+	a
+$ID2 2 2 3
+$COMMIT2
+	b
+$ID2 3 3
+$COMMIT2
+	c
+$ID2 4 4
+$COMMIT2
+	d
+EOF
+test_expect_success 'blame --line-porcelain output' '
+	git blame --line-porcelain file >actual &&
+	test_cmp expect actual
+'
+
+test_done