Merge branch 'br/blame-ignore'

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

* br/blame-ignore:
  t8014: remove unnecessary braces
  blame: drop some unused function parameters
  blame: add a test to cover blame_coalesce()
  blame: use the fingerprint heuristic to match ignored lines
  blame: add a fingerprint heuristic to match ignored lines
  blame: optionally track line fingerprints during fill_blame_origin()
  blame: add config options for the output of ignored or unblamable lines
  blame: add the ability to ignore commits and their changes
  blame: use a helper function in blame_chunk()
  Move oidset_parse_file() to oidset.c
  fsck: rename and touch up init_skiplist()

Documentation/blame-options.txt

@@ -110,5 +110,24 @@ 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 and attributed to
+	another commit will be marked with a `?` in the blame output.  If the
+	`blame.markUnblamableLines` config option is set, then those lines touched
+	by an ignored commit that we could not attribute to another revision are
+	marked with a '*'.
+
+--ignore-revs-file <file>::
+	Ignore revisions listed in `file`, which must be in the same format as an
+	`fsck.skipList`.  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 +19,19 @@ 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.markUnblamables::
+	Mark lines that were changed by an ignored revision that we could not
+	attribute to another commit with a '*' in the output of
+	linkgit:git-blame[1].
+
+blame.markIgnoredLines::
+	Mark lines that were changed by an ignored revision that we attributed to
+	another commit 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.h

@@ -51,6 +51,8 @@ struct blame_origin {
 	 */
 	struct blame_entry *suspects;
 	mmfile_t file;
+	int num_lines;
+	void *fingerprints;
 	struct object_id blob_oid;
 	unsigned short mode;
 	/* guilty gets set when shipping any suspects to the final
@@ -92,6 +94,8 @@ struct blame_entry {
 	 * scanning the lines over and over.
 	 */
 	unsigned score;
+	int ignored;
+	int unblamable;
 };
 
 /*
@@ -117,6 +121,8 @@ 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

@@ -53,6 +53,9 @@ 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_unblamable_lines;
+static int mark_ignored_lines;
 
 static struct date_mode blame_date_mode = { DATE_ISO8601 };
 static size_t blame_date_width;
@@ -480,6 +483,14 @@ static void emit_other(struct blame_scoreboard *sb, struct blame_entry *ent, int
 			}
 		}
 
+		if (mark_unblamable_lines && ent->unblamable) {
+			length--;
+			putchar('*');
+		}
+		if (mark_ignored_lines && ent->ignored) {
+			length--;
+			putchar('?');
+		}
 		printf("%.*s", length, hex);
 		if (opt & OUTPUT_ANNOTATE_COMPAT) {
 			const char *name;
@@ -696,6 +707,24 @@ 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.markunblamablelines")) {
+		mark_unblamable_lines = git_config_bool(var, value);
+		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"),
@@ -775,6 +804,27 @@ 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;
@@ -786,6 +836,7 @@ 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;
@@ -807,6 +858,8 @@ 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),
 
@@ -1012,6 +1065,9 @@ 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;
 

fsck.c

@@ -181,41 +181,6 @@ static int fsck_msg_type(enum fsck_msg_id msg_id,
 	return msg_type;
 }
 
-static void init_skiplist(struct fsck_options *options, const char *path)
-{
-	FILE *fp;
-	struct strbuf sb = STRBUF_INIT;
-	struct object_id oid;
-
-	fp = fopen(path, "r");
-	if (!fp)
-		die("Could not open skip list: %s", path);
-	while (!strbuf_getline(&sb, fp)) {
-		const char *p;
-		const char *hash;
-
-		/*
-		 * Allow trailing comments, leading whitespace
-		 * (including before commits), and empty or whitespace
-		 * only lines.
-		 */
-		hash = strchr(sb.buf, '#');
-		if (hash)
-			strbuf_setlen(&sb, hash - sb.buf);
-		strbuf_trim(&sb);
-		if (!sb.len)
-			continue;
-
-		if (parse_oid_hex(sb.buf, &oid, &p) || *p != '\0')
-			die("Invalid SHA-1: %s", sb.buf);
-		oidset_insert(&options->skiplist, &oid);
-	}
-	if (ferror(fp))
-		die_errno("Could not read '%s'", path);
-	fclose(fp);
-	strbuf_release(&sb);
-}
-
 static int parse_msg_type(const char *str)
 {
 	if (!strcmp(str, "error"))
@@ -284,7 +249,7 @@ void fsck_set_msg_types(struct fsck_options *options, const char *values)
 		if (!strcmp(buf, "skiplist")) {
 			if (equal == len)
 				die("skiplist requires a path");
-			init_skiplist(options, buf + equal + 1);
+			oidset_parse_file(&options->skiplist, buf + equal + 1);
 			buf += len + 1;
 			continue;
 		}

oidset.c

@@ -35,3 +35,38 @@ void oidset_clear(struct oidset *set)
 	kh_release_oid_set(&set->set);
 	oidset_init(set, 0);
 }
+
+void oidset_parse_file(struct oidset *set, const char *path)
+{
+	FILE *fp;
+	struct strbuf sb = STRBUF_INIT;
+	struct object_id oid;
+
+	fp = fopen(path, "r");
+	if (!fp)
+		die("could not open object name list: %s", path);
+	while (!strbuf_getline(&sb, fp)) {
+		const char *p;
+		const char *name;
+
+		/*
+		 * Allow trailing comments, leading whitespace
+		 * (including before commits), and empty or whitespace
+		 * only lines.
+		 */
+		name = strchr(sb.buf, '#');
+		if (name)
+			strbuf_setlen(&sb, name - sb.buf);
+		strbuf_trim(&sb);
+		if (!sb.len)
+			continue;
+
+		if (parse_oid_hex(sb.buf, &oid, &p) || *p != '\0')
+			die("invalid object name: %s", sb.buf);
+		oidset_insert(set, &oid);
+	}
+	if (ferror(fp))
+		die_errno("Could not read '%s'", path);
+	fclose(fp);
+	strbuf_release(&sb);
+}

oidset.h

@@ -61,6 +61,14 @@ int oidset_remove(struct oidset *set, const struct object_id *oid);
  */
 void oidset_clear(struct oidset *set);
 
+/**
+ * Add the contents of the file 'path' to an initialized oidset.  Each line is
+ * an unabbreviated object name.  Comments begin with '#', and trailing comments
+ * are allowed.  Leading whitespace and empty or white-space only lines are
+ * ignored.
+ */
+void oidset_parse_file(struct oidset *set, const char *path);
+
 struct oidset_iter {
 	kh_oid_set_t *set;
 	khiter_t iter;

t/t5504-fetch-receive-strict.sh

@@ -164,9 +164,9 @@ test_expect_success 'fsck with unsorted skipList' '
 test_expect_success 'fsck with invalid or bogus skipList input' '
 	git -c fsck.skipList=/dev/null -c fsck.missingEmail=ignore fsck &&
 	test_must_fail git -c fsck.skipList=does-not-exist -c fsck.missingEmail=ignore fsck 2>err &&
-	test_i18ngrep "Could not open skip list: does-not-exist" err &&
+	test_i18ngrep "could not open.*: does-not-exist" err &&
 	test_must_fail git -c fsck.skipList=.git/config -c fsck.missingEmail=ignore fsck 2>err &&
-	test_i18ngrep "Invalid SHA-1: \[core\]" err
+	test_i18ngrep "invalid object name: \[core\]" err
 '
 
 test_expect_success 'fsck with other accepted skipList input (comments & empty lines)' '
@@ -193,7 +193,7 @@ test_expect_success 'fsck no garbage output from comments & empty lines errors'
 test_expect_success 'fsck with invalid abbreviated skipList input' '
 	echo $commit | test_copy_bytes 20 >SKIP.abbreviated &&
 	test_must_fail git -c fsck.skipList=SKIP.abbreviated fsck 2>err-abbreviated &&
-	test_i18ngrep "^fatal: Invalid SHA-1: " err-abbreviated
+	test_i18ngrep "^fatal: invalid object name: " err-abbreviated
 '
 
 test_expect_success 'fsck with exhaustive accepted skipList input (various types of comments etc.)' '
@@ -226,10 +226,10 @@ test_expect_success 'push with receive.fsck.skipList' '
 	test_must_fail git push --porcelain dst bogus &&
 	git --git-dir=dst/.git config receive.fsck.skipList does-not-exist &&
 	test_must_fail git push --porcelain dst bogus 2>err &&
-	test_i18ngrep "Could not open skip list: does-not-exist" err &&
+	test_i18ngrep "could not open.*: does-not-exist" err &&
 	git --git-dir=dst/.git config receive.fsck.skipList config &&
 	test_must_fail git push --porcelain dst bogus 2>err &&
-	test_i18ngrep "Invalid SHA-1: \[core\]" err &&
+	test_i18ngrep "invalid object name: \[core\]" err &&
 
 	git --git-dir=dst/.git config receive.fsck.skipList SKIP &&
 	git push --porcelain dst bogus
@@ -255,10 +255,10 @@ test_expect_success 'fetch with fetch.fsck.skipList' '
 	test_must_fail git --git-dir=dst/.git fetch "file://$(pwd)" $refspec &&
 	git --git-dir=dst/.git config fetch.fsck.skipList does-not-exist &&
 	test_must_fail git --git-dir=dst/.git fetch "file://$(pwd)" $refspec 2>err &&
-	test_i18ngrep "Could not open skip list: does-not-exist" err &&
+	test_i18ngrep "could not open.*: does-not-exist" err &&
 	git --git-dir=dst/.git config fetch.fsck.skipList dst/.git/config &&
 	test_must_fail git --git-dir=dst/.git fetch "file://$(pwd)" $refspec 2>err &&
-	test_i18ngrep "Invalid SHA-1: \[core\]" err &&
+	test_i18ngrep "invalid object name: \[core\]" err &&
 
 	git --git-dir=dst/.git config fetch.fsck.skipList dst/.git/SKIP &&
 	git --git-dir=dst/.git fetch "file://$(pwd)" $refspec

t/t8003-blame-corner-cases.sh

@@ -275,4 +275,40 @@ test_expect_success 'blame file with CRLF core.autocrlf=true' '
 	grep "A U Thor" actual
 '
 
+# Tests the splitting and merging of blame entries in blame_coalesce().
+# The output of blame is the same, regardless of whether blame_coalesce() runs
+# or not, so we'd likely only notice a problem if blame crashes or assigned
+# blame to the "splitting" commit ('SPLIT' below).
+test_expect_success 'blame coalesce' '
+	cat >giraffe <<-\EOF &&
+	ABC
+	DEF
+	EOF
+	git add giraffe &&
+	git commit -m "original file" &&
+	oid=$(git rev-parse HEAD) &&
+
+	cat >giraffe <<-\EOF &&
+	ABC
+	SPLIT
+	DEF
+	EOF
+	git add giraffe &&
+	git commit -m "interior SPLIT line" &&
+
+	cat >giraffe <<-\EOF &&
+	ABC
+	DEF
+	EOF
+	git add giraffe &&
+	git commit -m "same contents as original" &&
+
+	cat >expect <<-EOF &&
+	$oid 1) ABC
+	$oid 2) DEF
+	EOF
+	git -c core.abbrev=40 blame -s giraffe >actual &&
+	test_cmp expect actual
+'
+
 test_done

t/t8013-blame-ignore-revs.sh

@@ -0,0 +1,274 @@
+#!/bin/sh
+
+test_description='ignore revisions when blaming'
+. ./test-lib.sh
+
+# Creates:
+# 	A--B--X
+# A added line 1 and B added line 2.  X makes changes to those lines.  Sanity
+# check that X is blamed for both lines.
+test_expect_success setup '
+	test_commit A file line1 &&
+
+	echo line2 >>file &&
+	git add file &&
+	test_tick &&
+	git commit -m B &&
+	git tag B &&
+
+	test_write_lines line-one line-two >file &&
+	git add file &&
+	test_tick &&
+	git commit -m X &&
+	git tag X &&
+
+	git blame --line-porcelain file >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse X >expect &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 2" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse X >expect &&
+	test_cmp expect actual
+	'
+
+# Ignore X, make sure A is blamed for line 1 and B for line 2.
+test_expect_success ignore_rev_changing_lines '
+	git blame --line-porcelain --ignore-rev X file >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse A >expect &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 2" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse B >expect &&
+	test_cmp expect actual
+	'
+
+# For ignored revs that have added 'unblamable' lines, attribute those to the
+# ignored commit.
+# 	A--B--X--Y
+# Where Y changes lines 1 and 2, and adds lines 3 and 4.  The added lines ought
+# to have nothing in common with "line-one" or "line-two", to keep any
+# heuristics from matching them with any lines in the parent.
+test_expect_success ignore_rev_adding_unblamable_lines '
+	test_write_lines line-one-change line-two-changed y3 y4 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m Y &&
+	git tag Y &&
+
+	git rev-parse Y >expect &&
+	git blame --line-porcelain file --ignore-rev Y >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 3" blame_raw | sed -e "s/ .*//" >actual &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 4" blame_raw | sed -e "s/ .*//" >actual &&
+	test_cmp expect actual
+	'
+
+# Ignore X and Y, both in separate files.  Lines 1 == A, 2 == B.
+test_expect_success ignore_revs_from_files '
+	git rev-parse X >ignore_x &&
+	git rev-parse Y >ignore_y &&
+	git blame --line-porcelain file --ignore-revs-file ignore_x --ignore-revs-file ignore_y >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse A >expect &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 2" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse B >expect &&
+	test_cmp expect actual
+	'
+
+# Ignore X from the config option, Y from a file.
+test_expect_success ignore_revs_from_configs_and_files '
+	git config --add blame.ignoreRevsFile ignore_x &&
+	git blame --line-porcelain file --ignore-revs-file ignore_y >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse A >expect &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 2" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse B >expect &&
+	test_cmp expect actual
+	'
+
+# Override blame.ignoreRevsFile (ignore_x) with an empty string.  X should be
+# blamed now for lines 1 and 2, since we are no longer ignoring X.
+test_expect_success override_ignore_revs_file '
+	git blame --line-porcelain file --ignore-revs-file "" --ignore-revs-file ignore_y >blame_raw &&
+	git rev-parse X >expect &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 2" blame_raw | sed -e "s/ .*//" >actual &&
+	test_cmp expect actual
+	'
+test_expect_success bad_files_and_revs '
+	test_must_fail git blame file --ignore-rev NOREV 2>err &&
+	test_i18ngrep "cannot find revision NOREV to ignore" err &&
+
+	test_must_fail git blame file --ignore-revs-file NOFILE 2>err &&
+	test_i18ngrep "could not open.*: NOFILE" err &&
+
+	echo NOREV >ignore_norev &&
+	test_must_fail git blame file --ignore-revs-file ignore_norev 2>err &&
+	test_i18ngrep "invalid object name: NOREV" err
+	'
+
+# For ignored revs that have added 'unblamable' lines, mark those lines with a
+# '*'
+# 	A--B--X--Y
+# Lines 3 and 4 are from Y and unblamable.  This was set up in
+# ignore_rev_adding_unblamable_lines.
+test_expect_success mark_unblamable_lines '
+	git config --add blame.markUnblamableLines true &&
+
+	git blame --ignore-rev Y file >blame_raw &&
+	echo "*" >expect &&
+
+	sed -n "3p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual &&
+
+	sed -n "4p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual
+	'
+
+# Commit Z will touch the first two lines.  Y touched all four.
+# 	A--B--X--Y--Z
+# The blame output when ignoring Z should be:
+# ?Y ... 1)
+# ?Y ... 2)
+# Y  ... 3)
+# Y  ... 4)
+# We're checking only the first character
+test_expect_success mark_ignored_lines '
+	git config --add blame.markIgnoredLines true &&
+
+	test_write_lines line-one-Z line-two-Z y3 y4 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m Z &&
+	git tag Z &&
+
+	git blame --ignore-rev Z file >blame_raw &&
+	echo "?" >expect &&
+
+	sed -n "1p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual &&
+
+	sed -n "2p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual &&
+
+	sed -n "3p" blame_raw | cut -c1 >actual &&
+	! test_cmp expect actual &&
+
+	sed -n "4p" blame_raw | cut -c1 >actual &&
+	! test_cmp expect actual
+	'
+
+# For ignored revs that added 'unblamable' lines and more recent commits changed
+# the blamable lines, mark the unblamable lines with a
+# '*'
+# 	A--B--X--Y--Z
+# Lines 3 and 4 are from Y and unblamable, as set up in
+# ignore_rev_adding_unblamable_lines.  Z changed lines 1 and 2.
+test_expect_success mark_unblamable_lines_intermediate '
+	git config --add blame.markUnblamableLines true &&
+
+	git blame --ignore-rev Y file >blame_raw 2>stderr &&
+	echo "*" >expect &&
+
+	sed -n "3p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual &&
+
+	sed -n "4p" blame_raw | cut -c1 >actual &&
+	test_cmp expect actual
+	'
+
+# The heuristic called by guess_line_blames() tries to find the size of a
+# blame_entry 'e' in the parent's address space.  Those calculations need to
+# check for negative or zero values for when a blame entry is completely outside
+# the window of the parent's version of a file.
+#
+# This happens when one commit adds several lines (commit B below).  A later
+# commit (C) changes one line in the middle of B's change.  Commit C gets blamed
+# for its change, and that breaks up B's change into multiple blame entries.
+# When processing B, one of the blame_entries is outside A's window (which was
+# zero - it had no lines added on its side of the diff).
+#
+# A--B--C, ignore B to test the ignore heuristic's boundary checks.
+test_expect_success ignored_chunk_negative_parent_size '
+	rm -rf .git/ &&
+	git init &&
+
+	test_write_lines L1 L2 L7 L8 L9 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m A &&
+	git tag A &&
+
+	test_write_lines L1 L2 L3 L4 L5 L6 L7 L8 L9 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m B &&
+	git tag B &&
+
+	test_write_lines L1 L2 L3 L4 xxx L6 L7 L8 L9 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m C &&
+	git tag C &&
+
+	git blame file --ignore-rev B >blame_raw
+	'
+
+# Resetting the repo and creating:
+#
+# A--B--M
+#  \   /
+#   C-+
+#
+# 'A' creates a file.  B changes line 1, and C changes line 9.  M merges.
+test_expect_success ignore_merge '
+	rm -rf .git/ &&
+	git init &&
+
+	test_write_lines L1 L2 L3 L4 L5 L6 L7 L8 L9 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m A &&
+	git tag A &&
+
+	test_write_lines BB L2 L3 L4 L5 L6 L7 L8 L9 >file &&
+	git add file &&
+	test_tick &&
+	git commit -m B &&
+	git tag B &&
+
+	git reset --hard A &&
+	test_write_lines L1 L2 L3 L4 L5 L6 L7 L8 CC >file &&
+	git add file &&
+	test_tick &&
+	git commit -m C &&
+	git tag C &&
+
+	test_merge M B &&
+	git blame --line-porcelain file --ignore-rev M >blame_raw &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 1" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse B >expect &&
+	test_cmp expect actual &&
+
+	grep -E "^[0-9a-f]+ [0-9]+ 9" blame_raw | sed -e "s/ .*//" >actual &&
+	git rev-parse C >expect &&
+	test_cmp expect actual
+	'
+
+test_done

t/t8014-blame-ignore-fuzzy.sh

@@ -0,0 +1,437 @@
+#!/bin/sh
+
+test_description='git blame ignore fuzzy heuristic'
+. ./test-lib.sh
+
+pick_author='s/^[0-9a-f^]* *(\([^ ]*\) .*/\1/'
+
+# Each test is composed of 4 variables:
+# titleN - the test name
+# aN - the initial content
+# bN - the final content
+# expectedN - the line numbers from aN that we expect git blame
+#             on bN to identify, or "Final" if bN itself should
+#             be identified as the origin of that line.
+
+# We start at test 2 because setup will show as test 1
+title2="Regression test for partially overlapping search ranges"
+cat <<EOF >a2
+1
+2
+3
+abcdef
+5
+6
+7
+ijkl
+9
+10
+11
+pqrs
+13
+14
+15
+wxyz
+17
+18
+19
+EOF
+cat <<EOF >b2
+abcde
+ijk
+pqr
+wxy
+EOF
+cat <<EOF >expected2
+4
+8
+12
+16
+EOF
+
+title3="Combine 3 lines into 2"
+cat <<EOF >a3
+if ((maxgrow==0) ||
+	( single_line_field && (field->dcols < maxgrow)) ||
+	(!single_line_field && (field->drows < maxgrow)))
+EOF
+cat <<EOF >b3
+if ((maxgrow == 0) || (single_line_field && (field->dcols < maxgrow)) ||
+	(!single_line_field && (field->drows < maxgrow))) {
+EOF
+cat <<EOF >expected3
+2
+3
+EOF
+
+title4="Add curly brackets"
+cat <<EOF >a4
+	if (rows) *rows = field->rows;
+	if (cols) *cols = field->cols;
+	if (frow) *frow = field->frow;
+	if (fcol) *fcol = field->fcol;
+EOF
+cat <<EOF >b4
+	if (rows) {
+		*rows = field->rows;
+	}
+	if (cols) {
+		*cols = field->cols;
+	}
+	if (frow) {
+		*frow = field->frow;
+	}
+	if (fcol) {
+		*fcol = field->fcol;
+	}
+EOF
+cat <<EOF >expected4
+1
+1
+Final
+2
+2
+Final
+3
+3
+Final
+4
+4
+Final
+EOF
+
+
+title5="Combine many lines and change case"
+cat <<EOF >a5
+for(row=0,pBuffer=field->buf;
+	row<height;
+	row++,pBuffer+=width )
+{
+	if ((len = (int)( After_End_Of_Data( pBuffer, width ) - pBuffer )) > 0)
+	{
+		wmove( win, row, 0 );
+		waddnstr( win, pBuffer, len );
+EOF
+cat <<EOF >b5
+for (Row = 0, PBuffer = field->buf; Row < Height; Row++, PBuffer += Width) {
+	if ((Len = (int)(afterEndOfData(PBuffer, Width) - PBuffer)) > 0) {
+		wmove(win, Row, 0);
+		waddnstr(win, PBuffer, Len);
+EOF
+cat <<EOF >expected5
+1
+5
+7
+8
+EOF
+
+title6="Rename and combine lines"
+cat <<EOF >a6
+bool need_visual_update = ((form != (FORM *)0)      &&
+	(form->status & _POSTED) &&
+	(form->current==field));
+
+if (need_visual_update)
+	Synchronize_Buffer(form);
+
+if (single_line_field)
+{
+	growth = field->cols * amount;
+	if (field->maxgrow)
+		growth = Minimum(field->maxgrow - field->dcols,growth);
+	field->dcols += growth;
+	if (field->dcols == field->maxgrow)
+EOF
+cat <<EOF >b6
+bool NeedVisualUpdate = ((Form != (FORM *)0) && (Form->status & _POSTED) &&
+	(Form->current == field));
+
+if (NeedVisualUpdate) {
+	synchronizeBuffer(Form);
+}
+
+if (SingleLineField) {
+	Growth = field->cols * amount;
+	if (field->maxgrow) {
+		Growth = Minimum(field->maxgrow - field->dcols, Growth);
+	}
+	field->dcols += Growth;
+	if (field->dcols == field->maxgrow) {
+EOF
+cat <<EOF >expected6
+1
+3
+4
+5
+6
+Final
+7
+8
+10
+11
+12
+Final
+13
+14
+EOF
+
+# Both lines match identically so position must be used to tie-break.
+title7="Same line twice"
+cat <<EOF >a7
+abc
+abc
+EOF
+cat <<EOF >b7
+abcd
+abcd
+EOF
+cat <<EOF >expected7
+1
+2
+EOF
+
+title8="Enforce line order"
+cat <<EOF >a8
+abcdef
+ghijkl
+ab
+EOF
+cat <<EOF >b8
+ghijk
+abcd
+EOF
+cat <<EOF >expected8
+2
+3
+EOF
+
+title9="Expand lines and rename variables"
+cat <<EOF >a9
+int myFunction(int ArgumentOne, Thing *ArgTwo, Blah XuglyBug) {
+	Squiggle FabulousResult = squargle(ArgumentOne, *ArgTwo,
+		XuglyBug) + EwwwGlobalWithAReallyLongNameYepTooLong;
+	return FabulousResult * 42;
+}
+EOF
+cat <<EOF >b9
+int myFunction(int argument_one, Thing *arg_asdfgh,
+	Blah xugly_bug) {
+	Squiggle fabulous_result = squargle(argument_one,
+		*arg_asdfgh, xugly_bug)
+		+ g_ewww_global_with_a_really_long_name_yep_too_long;
+	return fabulous_result * 42;
+}
+EOF
+cat <<EOF >expected9
+1
+1
+2
+3
+3
+4
+5
+EOF
+
+title10="Two close matches versus one less close match"
+cat <<EOF >a10
+abcdef
+abcdef
+ghijkl
+EOF
+cat <<EOF >b10
+gh
+abcdefx
+EOF
+cat <<EOF >expected10
+Final
+2
+EOF
+
+# The first line of b matches best with the last line of a, but the overall
+# match is better if we match it with the the first line of a.
+title11="Piggy in the middle"
+cat <<EOF >a11
+abcdefg
+ijklmn
+abcdefgh
+EOF
+cat <<EOF >b11
+abcdefghx
+ijklm
+EOF
+cat <<EOF >expected11
+1
+2
+EOF
+
+title12="No trailing newline"
+printf "abc\ndef" >a12
+printf "abx\nstu" >b12
+cat <<EOF >expected12
+1
+Final
+EOF
+
+title13="Reorder includes"
+cat <<EOF >a13
+#include "c.h"
+#include "b.h"
+#include "a.h"
+#include "e.h"
+#include "d.h"
+EOF
+cat <<EOF >b13
+#include "a.h"
+#include "b.h"
+#include "c.h"
+#include "d.h"
+#include "e.h"
+EOF
+cat <<EOF >expected13
+3
+2
+1
+5
+4
+EOF
+
+last_test=13
+
+test_expect_success setup '
+	for i in $(test_seq 2 $last_test)
+	do
+		# Append each line in a separate commit to make it easy to
+		# check which original line the blame output relates to.
+
+		line_count=0 &&
+		while IFS= read line
+		do
+			line_count=$((line_count+1)) &&
+			echo "$line" >>"$i" &&
+			git add "$i" &&
+			test_tick &&
+			GIT_AUTHOR_NAME="$line_count" git commit -m "$line_count"
+		done <"a$i"
+	done &&
+
+	for i in $(test_seq 2 $last_test)
+	do
+		# Overwrite the files with the final content.
+		cp b$i $i &&
+		git add $i
+	done &&
+	test_tick &&
+
+	# Commit the final content all at once so it can all be
+	# referred to with the same commit ID.
+	GIT_AUTHOR_NAME=Final git commit -m Final &&
+
+	IGNOREME=$(git rev-parse HEAD)
+'
+
+for i in $(test_seq 2 $last_test); do
+	eval title="\$title$i"
+	test_expect_success "$title" \
+	"git blame -M9 --ignore-rev $IGNOREME $i >output &&
+	sed -e \"$pick_author\" output >actual &&
+	test_cmp expected$i actual"
+done
+
+# This invoked a null pointer dereference when the chunk callback was called
+# with a zero length parent chunk and there were no more suspects.
+test_expect_success 'Diff chunks with no suspects' '
+	test_write_lines xy1 A B C xy1 >file &&
+	git add file &&
+	test_tick &&
+	GIT_AUTHOR_NAME=1 git commit -m 1 &&
+
+	test_write_lines xy2 A B xy2 C xy2 >file &&
+	git add file &&
+	test_tick &&
+	GIT_AUTHOR_NAME=2 git commit -m 2 &&
+	REV_2=$(git rev-parse HEAD) &&
+
+	test_write_lines xy3 A >file &&
+	git add file &&
+	test_tick &&
+	GIT_AUTHOR_NAME=3 git commit -m 3 &&
+	REV_3=$(git rev-parse HEAD) &&
+
+	test_write_lines 1 1 >expected &&
+
+	git blame --ignore-rev $REV_2 --ignore-rev $REV_3 file >output &&
+	sed -e "$pick_author" output >actual &&
+
+	test_cmp expected actual
+	'
+
+test_expect_success 'position matching' '
+	test_write_lines abc def >file2 &&
+	git add file2 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=1 git commit -m 1 &&
+
+	test_write_lines abc def abc def >file2 &&
+	git add file2 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=2 git commit -m 2 &&
+
+	test_write_lines abcx defx abcx defx >file2 &&
+	git add file2 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=3 git commit -m 3 &&
+	REV_3=$(git rev-parse HEAD) &&
+
+	test_write_lines abcy defy abcx defx >file2 &&
+	git add file2 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=4 git commit -m 4 &&
+	REV_4=$(git rev-parse HEAD) &&
+
+	test_write_lines 1 1 2 2 >expected &&
+
+	git blame --ignore-rev $REV_3 --ignore-rev $REV_4 file2 >output &&
+	sed -e "$pick_author" output >actual &&
+
+	test_cmp expected actual
+	'
+
+# This fails if each blame entry is processed independently instead of
+# processing each diff change in full.
+test_expect_success 'preserve order' '
+	test_write_lines bcde >file3 &&
+	git add file3 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=1 git commit -m 1 &&
+
+	test_write_lines bcde fghij >file3 &&
+	git add file3 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=2 git commit -m 2 &&
+
+	test_write_lines bcde fghij abcd >file3 &&
+	git add file3 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=3 git commit -m 3 &&
+
+	test_write_lines abcdx fghijx bcdex >file3 &&
+	git add file3 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=4 git commit -m 4 &&
+	REV_4=$(git rev-parse HEAD) &&
+
+	test_write_lines abcdx fghijy bcdex >file3 &&
+	git add file3 &&
+	test_tick &&
+	GIT_AUTHOR_NAME=5 git commit -m 5 &&
+	REV_5=$(git rev-parse HEAD) &&
+
+	test_write_lines 1 2 3 >expected &&
+
+	git blame --ignore-rev $REV_4 --ignore-rev $REV_5 file3 >output &&
+	sed -e "$pick_author" output >actual &&
+
+	test_cmp expected actual
+	'
+
+test_done