Merge branch 'br/blame-ignore' into pu

"git blame" learned to "ignore" commits in the history, whose
effects (as well as their presence) get ignored.

* br/blame-ignore:
  SQUASH???
  blame: add tests for ignoring revisions
  blame: add a config option to mark ignored lines
  blame: add the ability to ignore commits and their changes
  blame: use a helper function in blame_chunk()
  Move init_skiplist() outside of fsck

Author: gitster

Documentation/blame-options.txt

@@ -110,5 +110,21 @@ commit. And the default value is 40. If there are more than one
 `-C` options given, the <num> argument of the last `-C` will
 take effect.
 
+--ignore-rev <rev>::
+	Ignore changes made by the revision when assigning blame, as if the
+	change never happened.  Lines that were changed or added by an ignored
+	commit will be blamed on the previous commit that changed that line or
+	nearby lines.  This option may be specified multiple times to ignore
+	more than one revision.  If the `blame.markIgnoredLines` config option
+	is set, then lines that were changed by an ignored commit will be
+	marked with a `*` in the blame output.
+
+--ignore-revs-file <file>::
+	Ignore revisions listed in `file`, one unabbreviated object name per line.
+	Whitespace and comments beginning with `#` are ignored.  This option may be
+	repeated, and these files will be processed after any files specified with
+	the `blame.ignoreRevsFile` config option.  An empty file name, `""`, will
+	clear the list of revs from previously processed files.
+
 -h::
 	Show help message.

Documentation/config/blame.txt

@@ -19,3 +19,14 @@ blame.showEmail::
 blame.showRoot::
 	Do not treat root commits as boundaries in linkgit:git-blame[1].
 	This option defaults to false.
+
+blame.ignoreRevsFile::
+	Ignore revisions listed in the file, one unabbreviated object name per
+	line, in linkgit:git-blame[1].  Whitespace and comments beginning with
+	`#` are ignored.  This option may be repeated multiple times.  Empty
+	file names will reset the list of ignored revisions.  This option will
+	be handled before the command line option `--ignore-revs-file`.
+
+blame.markIgnoredLines::
+	Mark lines that were changed by an ignored revision with a '*' in the
+	output of linkgit:git-blame[1].

Documentation/git-blame.txt

@@ -10,6 +10,7 @@ SYNOPSIS
 [verse]
 'git blame' [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-e] [-p] [-w] [--incremental]
 	    [-L <range>] [-S <revs-file>] [-M] [-C] [-C] [-C] [--since=<date>]
+	    [--ignore-rev <rev>] [--ignore-revs-file <file>]
 	    [--progress] [--abbrev=<n>] [<rev> | --contents <file> | --reverse <rev>..<rev>]
 	    [--] <file>
 

blame.c

@@ -480,7 +480,9 @@ void blame_coalesce(struct blame_scoreboard *sb)
 
 	for (ent = sb->ent; ent && (next = ent->next); ent = next) {
 		if (ent->suspect == next->suspect &&
-		    ent->s_lno + ent->num_lines == next->s_lno) {
+		    ent->s_lno + ent->num_lines == next->s_lno &&
+		    ent->ignored == next->ignored &&
+		    ent->unblamable == next->unblamable) {
 			ent->num_lines += next->num_lines;
 			ent->next = next->next;
 			blame_origin_decref(next->suspect);
@@ -732,6 +734,11 @@ static void split_overlap(struct blame_entry *split,
 	int chunk_end_lno;
 	memset(split, 0, sizeof(struct blame_entry [3]));
 
+	split[0].ignored = split[1].ignored = split[2].ignored = e->ignored;
+	split[0].unblamable = e->unblamable;
+	split[1].unblamable = e->unblamable;
+	split[2].unblamable = e->unblamable;
+
 	if (e->s_lno < tlno) {
 		/* there is a pre-chunk part not blamed on parent */
 		split[0].suspect = blame_origin_incref(e->suspect);
@@ -839,6 +846,27 @@ static struct blame_entry *reverse_blame(struct blame_entry *head,
 	return tail;
 }
 
+/* Splits a blame entry into two entries at 'len' lines.  The original 'e'
+ * consists of len lines, i.e. [e->lno, e->lno + len), and the second part,
+ * which is returned, consists of the remainder: [e->lno + len, e->lno +
+ * e->num_lines).  The caller needs to sort out the reference counting for the
+ * new entry's suspect. */
+static struct blame_entry *split_blame_at(struct blame_entry *e, int len,
+					  struct blame_origin *new_suspect)
+{
+	struct blame_entry *n = xcalloc(1, sizeof(struct blame_entry));
+
+	n->suspect = new_suspect;
+	n->ignored = e->ignored;
+	n->unblamable = e->unblamable;
+	n->lno = e->lno + len;
+	n->s_lno = e->s_lno + len;
+	n->num_lines = e->num_lines - len;
+	e->num_lines = len;
+	e->score = 0;
+	return n;
+}
+
 /*
  * Process one hunk from the patch between the current suspect for
  * blame_entry e and its parent.  This first blames any unfinished
@@ -851,10 +879,10 @@ static struct blame_entry *reverse_blame(struct blame_entry *head,
  */
 static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq,
 			int tlno, int offset, int same,
-			struct blame_origin *parent)
+			struct blame_origin *parent, int ignore_diffs, int delta)
 {
 	struct blame_entry *e = **srcq;
-	struct blame_entry *samep = NULL, *diffp = NULL;
+	struct blame_entry *samep = NULL, *diffp = NULL, *ignoredp = NULL;
 
 	while (e && e->s_lno < tlno) {
 		struct blame_entry *next = e->next;
@@ -865,14 +893,9 @@ static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq,
 		 */
 		if (e->s_lno + e->num_lines > tlno) {
 			/* Move second half to a new record */
-			int len = tlno - e->s_lno;
-			struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry));
-			n->suspect = e->suspect;
-			n->lno = e->lno + len;
-			n->s_lno = e->s_lno + len;
-			n->num_lines = e->num_lines - len;
-			e->num_lines = len;
-			e->score = 0;
+			struct blame_entry *n;
+
+			n = split_blame_at(e, tlno - e->s_lno, e->suspect);
 			/* Push new record to diffp */
 			n->next = diffp;
 			diffp = n;
@@ -919,22 +942,45 @@ static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq,
 			 * Move second half to a new record to be
 			 * processed by later chunks
 			 */
-			int len = same - e->s_lno;
-			struct blame_entry *n = xcalloc(1, sizeof (struct blame_entry));
-			n->suspect = blame_origin_incref(e->suspect);
-			n->lno = e->lno + len;
-			n->s_lno = e->s_lno + len;
-			n->num_lines = e->num_lines - len;
-			e->num_lines = len;
-			e->score = 0;
+			struct blame_entry *n;
+
+			n = split_blame_at(e, same - e->s_lno,
+					   blame_origin_incref(e->suspect));
 			/* Push new record to samep */
 			n->next = samep;
 			samep = n;
 		}
-		e->next = diffp;
-		diffp = e;
+		if (ignore_diffs) {
+			/* These go to the parent, like the ones before tlno. */
+			blame_origin_decref(e->suspect);
+			e->suspect = blame_origin_incref(parent);
+			e->s_lno += offset;
+			e->ignored = 1;
+			/* The top part of any ignored diff will not exist in
+			 * the parent, and we will never be able to accurately
+			 * blame it.  We'll keep it on the blame list for the
+			 * target and mark it during the output. */
+			if (delta > 0) {
+				struct blame_entry *n;
+
+				n = split_blame_at(e, e->num_lines - delta,
+					blame_origin_incref(e->suspect));
+				n->unblamable = 1;
+				n->next = diffp;
+				diffp = n;
+			}
+			e->next = ignoredp;
+			ignoredp = e;
+		} else {
+			e->next = diffp;
+			diffp = e;
+		}
 		e = next;
 	}
+	if (ignoredp) {
+		**dstq = reverse_blame(ignoredp, **dstq);
+		*dstq = &ignoredp->next;
+	}
 	**srcq = reverse_blame(diffp, reverse_blame(samep, e));
 	/* Move across elements that are in the unblamable portion */
 	if (diffp)
@@ -944,6 +990,7 @@ static void blame_chunk(struct blame_entry ***dstq, struct blame_entry ***srcq,
 struct blame_chunk_cb_data {
 	struct blame_origin *parent;
 	long offset;
+	int ignore_diffs;
 	struct blame_entry **dstq;
 	struct blame_entry **srcq;
 };
@@ -956,7 +1003,7 @@ static int blame_chunk_cb(long start_a, long count_a,
 	if (start_a - start_b != d->offset)
 		die("internal error in blame::blame_chunk_cb");
 	blame_chunk(&d->dstq, &d->srcq, start_b, start_a - start_b,
-		    start_b + count_b, d->parent);
+		    start_b + count_b, d->parent, d->ignore_diffs, count_b - count_a);
 	d->offset = start_a + count_a - (start_b + count_b);
 	return 0;
 }
@@ -968,7 +1015,7 @@ static int blame_chunk_cb(long start_a, long count_a,
  */
 static void pass_blame_to_parent(struct blame_scoreboard *sb,
 				 struct blame_origin *target,
-				 struct blame_origin *parent)
+				 struct blame_origin *parent, int ignore_diffs)
 {
 	mmfile_t file_p, file_o;
 	struct blame_chunk_cb_data d;
@@ -979,6 +1026,7 @@ static void pass_blame_to_parent(struct blame_scoreboard *sb,
 
 	d.parent = parent;
 	d.offset = 0;
+	d.ignore_diffs = ignore_diffs;
 	d.dstq = &newdest; d.srcq = &target->suspects;
 
 	fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob);
@@ -990,7 +1038,7 @@ static void pass_blame_to_parent(struct blame_scoreboard *sb,
 		    oid_to_hex(&parent->commit->object.oid),
 		    oid_to_hex(&target->commit->object.oid));
 	/* The rest are the same as the parent */
-	blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent);
+	blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent, 0, 0);
 	*d.dstq = NULL;
 	queue_blames(sb, parent, newdest);
 
@@ -1495,11 +1543,28 @@ static void pass_blame(struct blame_scoreboard *sb, struct blame_origin *origin,
 			blame_origin_incref(porigin);
 			origin->previous = porigin;
 		}
-		pass_blame_to_parent(sb, origin, porigin);
+		pass_blame_to_parent(sb, origin, porigin, 0);
 		if (!origin->suspects)
 			goto finish;
 	}
 
+	/*
+	 * Pass remaining suspects for ignored commits to their parents.
+	 */
+	if (oidset_contains(&sb->ignore_list, &commit->object.oid)) {
+		for (i = 0, sg = first_scapegoat(revs, commit, sb->reverse);
+		     i < num_sg && sg;
+		     sg = sg->next, i++) {
+			struct blame_origin *porigin = sg_origin[i];
+
+			if (!porigin)
+				continue;
+			pass_blame_to_parent(sb, origin, porigin, 1);
+			if (!origin->suspects)
+				goto finish;
+		}
+	}
+
 	/*
 	 * Optionally find moves in parents' files.
 	 */

blame.h

@@ -92,6 +92,8 @@ struct blame_entry {
 	 * scanning the lines over and over.
 	 */
 	unsigned score;
+	int ignored;
+	int unblamable;
 };
 
 /*
@@ -117,6 +119,8 @@ struct blame_scoreboard {
 	/* linked list of blames */
 	struct blame_entry *ent;
 
+	struct oidset ignore_list;
+
 	/* look-up a line in the final buffer */
 	int num_lines;
 	int *lineno;

builtin/blame.c

@@ -52,6 +52,8 @@ static int no_whole_file_rename;
 static int show_progress;
 static char repeated_meta_color[COLOR_MAXLEN];
 static int coloring_mode;
+static struct string_list ignore_revs_file_list = STRING_LIST_INIT_NODUP;
+static int mark_ignored_lines;
 
 static struct date_mode blame_date_mode = { DATE_ISO8601 };
 static size_t blame_date_width;
@@ -346,6 +348,8 @@ static void emit_porcelain(struct blame_scoreboard *sb, struct blame_entry *ent,
 	char hex[GIT_MAX_HEXSZ + 1];
 
 	oid_to_hex_r(hex, &suspect->commit->object.oid);
+	if (ent->unblamable)
+		memset(hex, '0', strlen(hex));
 	printf("%s %d %d %d\n",
 	       hex,
 	       ent->s_lno + 1,
@@ -479,6 +483,12 @@ static void emit_other(struct blame_scoreboard *sb, struct blame_entry *ent, int
 			}
 		}
 
+		if (mark_ignored_lines && ent->ignored) {
+			length--;
+			putchar('*');
+		}
+		if (ent->unblamable)
+			memset(hex, '0', length);
 		printf("%.*s", length, hex);
 		if (opt & OUTPUT_ANNOTATE_COMPAT) {
 			const char *name;
@@ -695,6 +705,20 @@ static int git_blame_config(const char *var, const char *value, void *cb)
 		parse_date_format(value, &blame_date_mode);
 		return 0;
 	}
+	if (!strcmp(var, "blame.ignorerevsfile")) {
+		const char *str;
+		int ret;
+
+		ret = git_config_pathname(&str, var, value);
+		if (ret)
+			return ret;
+		string_list_insert(&ignore_revs_file_list, str);
+		return 0;
+	}
+	if (!strcmp(var, "blame.markignoredlines")) {
+		mark_ignored_lines = git_config_bool(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "color.blame.repeatedlines")) {
 		if (color_parse_mem(value, strlen(value), repeated_meta_color))
 			warning(_("invalid color '%s' in color.blame.repeatedLines"),
@@ -774,6 +798,27 @@ static int is_a_rev(const char *name)
 	return OBJ_NONE < oid_object_info(the_repository, &oid, NULL);
 }
 
+static void build_ignorelist(struct blame_scoreboard *sb,
+			     struct string_list *ignore_revs_file_list,
+			     struct string_list *ignore_rev_list)
+{
+	struct string_list_item *i;
+	struct object_id oid;
+
+	oidset_init(&sb->ignore_list, 0);
+	for_each_string_list_item(i, ignore_revs_file_list) {
+		if (!strcmp(i->string, ""))
+			oidset_clear(&sb->ignore_list);
+		else
+			oidset_parse_file(&sb->ignore_list, i->string);
+	}
+	for_each_string_list_item(i, ignore_rev_list) {
+		if (get_oid_committish(i->string, &oid))
+			die(_("Cannot find revision %s to ignore"), i->string);
+		oidset_insert(&sb->ignore_list, &oid);
+	}
+}
+
 int cmd_blame(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
@@ -785,6 +830,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 	struct progress_info pi = { NULL, 0 };
 
 	struct string_list range_list = STRING_LIST_INIT_NODUP;
+	struct string_list ignore_rev_list = STRING_LIST_INIT_NODUP;
 	int output_option = 0, opt = 0;
 	int show_stats = 0;
 	const char *revs_file = NULL;
@@ -806,6 +852,8 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		OPT_BIT('s', NULL, &output_option, N_("Suppress author name and timestamp (Default: off)"), OUTPUT_NO_AUTHOR),
 		OPT_BIT('e', "show-email", &output_option, N_("Show author email instead of name (Default: off)"), OUTPUT_SHOW_EMAIL),
 		OPT_BIT('w', NULL, &xdl_opts, N_("Ignore whitespace differences"), XDF_IGNORE_WHITESPACE),
+		OPT_STRING_LIST(0, "ignore-rev", &ignore_rev_list, N_("rev"), N_("Ignore <rev> when blaming")),
+		OPT_STRING_LIST(0, "ignore-revs-file", &ignore_revs_file_list, N_("file"), N_("Ignore revisions from <file>")),
 		OPT_BIT(0, "color-lines", &output_option, N_("color redundant metadata from previous line differently"), OUTPUT_COLOR_LINE),
 		OPT_BIT(0, "color-by-age", &output_option, N_("color lines by age"), OUTPUT_SHOW_AGE_WITH_COLOR),
 
@@ -999,6 +1047,9 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 	sb.contents_from = contents_from;
 	sb.reverse = reverse;
 	sb.repo = the_repository;
+	build_ignorelist(&sb, &ignore_revs_file_list, &ignore_rev_list);
+	string_list_clear(&ignore_revs_file_list, 0);
+	string_list_clear(&ignore_rev_list, 0);
 	setup_scoreboard(&sb, path, &o);
 	lno = sb.num_lines;