1 files changed, 116 insertions, 206 deletions

diff --git a/builtin/blame.c b/builtin/blame.c
index 77707819af..e5b5d71bad 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -21,6 +21,8 @@
 #include "parse-options.h"
 #include "utf8.h"
 #include "userdiff.h"
+#include "line-range.h"
+#include "line-log.h"
 
 static char blame_usage[] = N_("git blame [options] [rev-opts] [rev] [--] file");
 
@@ -195,7 +197,6 @@ static void drop_origin_blob(struct origin *o)
  * scoreboard structure, sorted by the target line number.
  */
 struct blame_entry {
-	struct blame_entry *prev;
 	struct blame_entry *next;
 
 	/* the first line of this group in the final image;
@@ -254,15 +255,6 @@ struct scoreboard {
 	int *lineno;
 };
 
-static inline int same_suspect(struct origin *a, struct origin *b)
-{
-	if (a == b)
-		return 1;
-	if (a->commit != b->commit)
-		return 0;
-	return !strcmp(a->path, b->path);
-}
-
 static void sanity_check_refcnt(struct scoreboard *);
 
 /*
@@ -275,13 +267,11 @@ static void coalesce(struct scoreboard *sb)
 	struct blame_entry *ent, *next;
 
 	for (ent = sb->ent; ent && (next = ent->next); ent = next) {
-		if (same_suspect(ent->suspect, next->suspect) &&
+		if (ent->suspect == next->suspect &&
 		    ent->guilty == next->guilty &&
 		    ent->s_lno + ent->num_lines == next->s_lno) {
 			ent->num_lines += next->num_lines;
 			ent->next = next->next;
-			if (ent->next)
-				ent->next->prev = ent;
 			origin_decref(next->suspect);
 			free(next);
 			ent->score = 0;
@@ -407,7 +397,9 @@ static struct origin *find_origin(struct scoreboard *sb,
 	paths[0] = origin->path;
 	paths[1] = NULL;
 
-	diff_tree_setup_paths(paths, &diff_opts);
+	parse_pathspec(&diff_opts.pathspec,
+		       PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
+		       PATHSPEC_LITERAL_PATH, "", paths);
 	diff_setup_done(&diff_opts);
 
 	if (is_null_sha1(origin->commit->object.sha1))
@@ -457,7 +449,7 @@ static struct origin *find_origin(struct scoreboard *sb,
 		}
 	}
 	diff_flush(&diff_opts);
-	diff_tree_release_paths(&diff_opts);
+	free_pathspec(&diff_opts.pathspec);
 	if (porigin) {
 		/*
 		 * Create a freestanding copy that is not part of
@@ -485,15 +477,12 @@ static struct origin *find_rename(struct scoreboard *sb,
 	struct origin *porigin = NULL;
 	struct diff_options diff_opts;
 	int i;
-	const char *paths[2];
 
 	diff_setup(&diff_opts);
 	DIFF_OPT_SET(&diff_opts, RECURSIVE);
 	diff_opts.detect_rename = DIFF_DETECT_RENAME;
 	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
 	diff_opts.single_follow = origin->path;
-	paths[0] = NULL;
-	diff_tree_setup_paths(paths, &diff_opts);
 	diff_setup_done(&diff_opts);
 
 	if (is_null_sha1(origin->commit->object.sha1))
@@ -515,7 +504,7 @@ static struct origin *find_rename(struct scoreboard *sb,
 		}
 	}
 	diff_flush(&diff_opts);
-	diff_tree_release_paths(&diff_opts);
+	free_pathspec(&diff_opts.pathspec);
 	return porigin;
 }
 
@@ -533,7 +522,7 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e)
 		prev = ent;
 
 	/* prev, if not NULL, is the last one that is below e */
-	e->prev = prev;
+
 	if (prev) {
 		e->next = prev->next;
 		prev->next = e;
@@ -542,8 +531,6 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e)
 		e->next = sb->ent;
 		sb->ent = e;
 	}
-	if (e->next)
-		e->next->prev = e;
 }
 
 /*
@@ -554,23 +541,26 @@ static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e)
  */
 static void dup_entry(struct blame_entry *dst, struct blame_entry *src)
 {
-	struct blame_entry *p, *n;
+	struct blame_entry *n;
 
-	p = dst->prev;
 	n = dst->next;
 	origin_incref(src->suspect);
 	origin_decref(dst->suspect);
 	memcpy(dst, src, sizeof(*src));
-	dst->prev = p;
 	dst->next = n;
 	dst->score = 0;
 }
 
-static const char *nth_line(struct scoreboard *sb, int lno)
+static const char *nth_line(struct scoreboard *sb, long lno)
 {
 	return sb->final_buf + sb->lineno[lno];
 }
 
+static const char *nth_line_cb(void *data, long lno)
+{
+	return nth_line((struct scoreboard *)data, lno);
+}
+
 /*
  * It is known that lines between tlno to same came from parent, and e
  * has an overlap with that range.  it also is known that parent's
@@ -736,7 +726,7 @@ static int find_last_in_target(struct scoreboard *sb, struct origin *target)
 	int last_in_target = -1;
 
 	for (e = sb->ent; e; e = e->next) {
-		if (e->guilty || !same_suspect(e->suspect, target))
+		if (e->guilty || e->suspect != target)
 			continue;
 		if (last_in_target < e->s_lno + e->num_lines)
 			last_in_target = e->s_lno + e->num_lines;
@@ -756,7 +746,7 @@ static void blame_chunk(struct scoreboard *sb,
 	struct blame_entry *e;
 
 	for (e = sb->ent; e; e = e->next) {
-		if (e->guilty || !same_suspect(e->suspect, target))
+		if (e->guilty || e->suspect != target)
 			continue;
 		if (same <= e->s_lno)
 			continue;
@@ -933,7 +923,6 @@ static void find_copy_in_blob(struct scoreboard *sb,
 			      mmfile_t *file_p)
 {
 	const char *cp;
-	int cnt;
 	mmfile_t file_o;
 	struct handle_split_cb_data d;
 
@@ -944,13 +933,7 @@ static void find_copy_in_blob(struct scoreboard *sb,
 	 */
 	cp = nth_line(sb, ent->lno);
 	file_o.ptr = (char *) cp;
-	cnt = ent->num_lines;
-
-	while (cnt && cp < sb->final_buf + sb->final_buf_size) {
-		if (*cp++ == '\n')
-			cnt--;
-	}
-	file_o.size = cp - file_o.ptr;
+	file_o.size = nth_line(sb, ent->lno + ent->num_lines) - cp;
 
 	/*
 	 * file_o is a part of final image we are annotating.
@@ -986,7 +969,7 @@ static int find_move_in_parent(struct scoreboard *sb,
 	while (made_progress) {
 		made_progress = 0;
 		for (e = sb->ent; e; e = e->next) {
-			if (e->guilty || !same_suspect(e->suspect, target) ||
+			if (e->guilty || e->suspect != target ||
 			    ent_score(sb, e) < blame_move_score)
 				continue;
 			find_copy_in_blob(sb, e, parent, split, &file_p);
@@ -1021,14 +1004,14 @@ static struct blame_list *setup_blame_list(struct scoreboard *sb,
 
 	for (e = sb->ent, num_ents = 0; e; e = e->next)
 		if (!e->scanned && !e->guilty &&
-		    same_suspect(e->suspect, target) &&
+		    e->suspect == target &&
 		    min_score < ent_score(sb, e))
 			num_ents++;
 	if (num_ents) {
 		blame_list = xcalloc(num_ents, sizeof(struct blame_list));
 		for (e = sb->ent, i = 0; e; e = e->next)
 			if (!e->scanned && !e->guilty &&
-			    same_suspect(e->suspect, target) &&
+			    e->suspect == target &&
 			    min_score < ent_score(sb, e))
 				blame_list[i++].ent = e;
 	}
@@ -1058,7 +1041,6 @@ static int find_copy_in_parent(struct scoreboard *sb,
 			       int opt)
 {
 	struct diff_options diff_opts;
-	const char *paths[1];
 	int i, j;
 	int retval;
 	struct blame_list *blame_list;
@@ -1072,8 +1054,6 @@ static int find_copy_in_parent(struct scoreboard *sb,
 	DIFF_OPT_SET(&diff_opts, RECURSIVE);
 	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
 
-	paths[0] = NULL;
-	diff_tree_setup_paths(paths, &diff_opts);
 	diff_setup_done(&diff_opts);
 
 	/* Try "find copies harder" on new path if requested;
@@ -1156,7 +1136,7 @@ static int find_copy_in_parent(struct scoreboard *sb,
 	}
 	reset_scanned_flag(sb);
 	diff_flush(&diff_opts);
-	diff_tree_release_paths(&diff_opts);
+	free_pathspec(&diff_opts.pathspec);
 	return retval;
 }
 
@@ -1175,7 +1155,7 @@ static void pass_whole_blame(struct scoreboard *sb,
 		origin->file.ptr = NULL;
 	}
 	for (e = sb->ent; e; e = e->next) {
-		if (!same_suspect(e->suspect, origin))
+		if (e->suspect != origin)
 			continue;
 		origin_incref(porigin);
 		origin_decref(e->suspect);
@@ -1430,7 +1410,7 @@ static void get_commit_info(struct commit *commit,
 	commit_info_init(ret);
 
 	encoding = get_log_output_encoding();
-	message = logmsg_reencode(commit, encoding);
+	message = logmsg_reencode(commit, NULL, encoding);
 	get_ac_line(message, "\nauthor ",
 		    &ret->author, &ret->author_mail,
 		    &ret->author_time, &ret->author_tz);
@@ -1548,8 +1528,7 @@ static void assign_blame(struct scoreboard *sb, int opt)
 		 */
 		origin_incref(suspect);
 		commit = suspect->commit;
-		if (!commit->object.parsed)
-			parse_commit(commit);
+		parse_commit(commit);
 		if (reverse ||
 		    (!(commit->object.flags & UNINTERESTING) &&
 		     !(revs->max_age != -1 && commit->date < revs->max_age)))
@@ -1565,7 +1544,7 @@ static void assign_blame(struct scoreboard *sb, int opt)
 
 		/* Take responsibility for the remaining entries */
 		for (ent = sb->ent; ent; ent = ent->next)
-			if (same_suspect(ent->suspect, suspect))
+			if (ent->suspect == suspect)
 				found_guilty_entry(ent);
 		origin_decref(suspect);
 
@@ -1578,14 +1557,14 @@ static const char *format_time(unsigned long time, const char *tz_str,
 			       int show_raw_time)
 {
 	static char time_buf[128];
-	const char *time_str;
-	int time_len;
-	int tz;
 
 	if (show_raw_time) {
 		snprintf(time_buf, sizeof(time_buf), "%lu %s", time, tz_str);
 	}
 	else {
+		const char *time_str;
+		int time_len;
+		int tz;
 		tz = atoi(tz_str);
 		time_str = show_date(time, tz, blame_date_mode);
 		time_len = strlen(time_str);
@@ -1770,25 +1749,41 @@ static int prepare_lines(struct scoreboard *sb)
 {
 	const char *buf = sb->final_buf;
 	unsigned long len = sb->final_buf_size;
-	int num = 0, incomplete = 0, bol = 1;
+	const char *end = buf + len;
+	const char *p;
+	int *lineno;
+	int num = 0, incomplete = 0;
 
-	if (len && buf[len-1] != '\n')
-		incomplete++; /* incomplete line at the end */
-	while (len--) {
-		if (bol) {
-			sb->lineno = xrealloc(sb->lineno,
-					      sizeof(int *) * (num + 1));
-			sb->lineno[num] = buf - sb->final_buf;
-			bol = 0;
-		}
-		if (*buf++ == '\n') {
+	for (p = buf;;) {
+		p = memchr(p, '\n', end - p);
+		if (p) {
+			p++;
 			num++;
-			bol = 1;
+			continue;
 		}
+		break;
+	}
+
+	if (len && end[-1] != '\n')
+		incomplete++; /* incomplete line at the end */
+
+	sb->lineno = xmalloc(sizeof(*sb->lineno) * (num + incomplete + 1));
+	lineno = sb->lineno;
+
+	*lineno++ = 0;
+	for (p = buf;;) {
+		p = memchr(p, '\n', end - p);
+		if (p) {
+			p++;
+			*lineno++ = p - buf;
+			continue;
+		}
+		break;
 	}
-	sb->lineno = xrealloc(sb->lineno,
-			      sizeof(int *) * (num + incomplete + 1));
-	sb->lineno[num + incomplete] = buf - sb->final_buf;
+
+	if (incomplete)
+		*lineno++ = len;
+
 	sb->num_lines = num + incomplete;
 	return sb->num_lines;
 }
@@ -1801,17 +1796,17 @@ static int prepare_lines(struct scoreboard *sb)
 static int read_ancestry(const char *graft_file)
 {
 	FILE *fp = fopen(graft_file, "r");
-	char buf[1024];
+	struct strbuf buf = STRBUF_INIT;
 	if (!fp)
 		return -1;
-	while (fgets(buf, sizeof(buf), fp)) {
+	while (!strbuf_getwholeline(&buf, fp, '\n')) {
 		/* The format is just "Commit Parent1 Parent2 ...\n" */
-		int len = strlen(buf);
-		struct commit_graft *graft = read_graft_line(buf, len);
+		struct commit_graft *graft = read_graft_line(buf.buf, buf.len);
 		if (graft)
 			register_commit_graft(graft, 0);
 	}
 	fclose(fp);
+	strbuf_release(&buf);
 	return 0;
 }
 
@@ -1931,103 +1926,6 @@ static const char *add_prefix(const char *prefix, const char *path)
 	return prefix_path(prefix, prefix ? strlen(prefix) : 0, path);
 }
 
-/*
- * Parsing of (comma separated) one item in the -L option
- */
-static const char *parse_loc(const char *spec,
-			     struct scoreboard *sb, long lno,
-			     long begin, long *ret)
-{
-	char *term;
-	const char *line;
-	long num;
-	int reg_error;
-	regex_t regexp;
-	regmatch_t match[1];
-
-	/* Allow "-L <something>,+20" to mean starting at <something>
-	 * for 20 lines, or "-L <something>,-5" for 5 lines ending at
-	 * <something>.
-	 */
-	if (1 < begin && (spec[0] == '+' || spec[0] == '-')) {
-		num = strtol(spec + 1, &term, 10);
-		if (term != spec + 1) {
-			if (spec[0] == '-')
-				num = 0 - num;
-			if (0 < num)
-				*ret = begin + num - 2;
-			else if (!num)
-				*ret = begin;
-			else
-				*ret = begin + num;
-			return term;
-		}
-		return spec;
-	}
-	num = strtol(spec, &term, 10);
-	if (term != spec) {
-		*ret = num;
-		return term;
-	}
-	if (spec[0] != '/')
-		return spec;
-
-	/* it could be a regexp of form /.../ */
-	for (term = (char *) spec + 1; *term && *term != '/'; term++) {
-		if (*term == '\\')
-			term++;
-	}
-	if (*term != '/')
-		return spec;
-
-	/* try [spec+1 .. term-1] as regexp */
-	*term = 0;
-	begin--; /* input is in human terms */
-	line = nth_line(sb, begin);
-
-	if (!(reg_error = regcomp(&regexp, spec + 1, REG_NEWLINE)) &&
-	    !(reg_error = regexec(&regexp, line, 1, match, 0))) {
-		const char *cp = line + match[0].rm_so;
-		const char *nline;
-
-		while (begin++ < lno) {
-			nline = nth_line(sb, begin);
-			if (line <= cp && cp < nline)
-				break;
-			line = nline;
-		}
-		*ret = begin;
-		regfree(&regexp);
-		*term++ = '/';
-		return term;
-	}
-	else {
-		char errbuf[1024];
-		regerror(reg_error, &regexp, errbuf, 1024);
-		die("-L parameter '%s': %s", spec + 1, errbuf);
-	}
-}
-
-/*
- * Parsing of -L option
- */
-static void prepare_blame_range(struct scoreboard *sb,
-				const char *bottomtop,
-				long lno,
-				long *bottom, long *top)
-{
-	const char *term;
-
-	term = parse_loc(bottomtop, sb, lno, 1, bottom);
-	if (*term == ',') {
-		term = parse_loc(term + 1, sb, lno, *bottom + 1, top);
-		if (*term)
-			usage(blame_usage);
-	}
-	if (*term)
-		usage(blame_usage);
-}
-
 static int git_blame_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "blame.showroot")) {
@@ -2324,38 +2222,27 @@ static int blame_move_callback(const struct option *option, const char *arg, int
 	return 0;
 }
 
-static int blame_bottomtop_callback(const struct option *option, const char *arg, int unset)
-{
-	const char **bottomtop = option->value;
-	if (!arg)
-		return -1;
-	if (*bottomtop)
-		die("More than one '-L n,m' option given");
-	*bottomtop = arg;
-	return 0;
-}
-
 int cmd_blame(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
 	const char *path;
 	struct scoreboard sb;
 	struct origin *o;
-	struct blame_entry *ent;
-	long dashdash_pos, bottom, top, lno;
+	struct blame_entry *ent = NULL;
+	long dashdash_pos, lno;
 	const char *final_commit_name = NULL;
 	enum object_type type;
 
-	static const char *bottomtop = NULL;
+	static struct string_list range_list;
 	static int output_option = 0, opt = 0;
 	static int show_stats = 0;
 	static const char *revs_file = NULL;
 	static const char *contents_from = NULL;
 	static const struct option options[] = {
-		OPT_BOOLEAN(0, "incremental", &incremental, N_("Show blame entries as we find them, incrementally")),
-		OPT_BOOLEAN('b', NULL, &blank_boundary, N_("Show blank SHA-1 for boundary commits (Default: off)")),
-		OPT_BOOLEAN(0, "root", &show_root, N_("Do not treat root commits as boundaries (Default: off)")),
-		OPT_BOOLEAN(0, "show-stats", &show_stats, N_("Show work cost statistics")),
+		OPT_BOOL(0, "incremental", &incremental, N_("Show blame entries as we find them, incrementally")),
+		OPT_BOOL('b', NULL, &blank_boundary, N_("Show blank SHA-1 for boundary commits (Default: off)")),
+		OPT_BOOL(0, "root", &show_root, N_("Do not treat root commits as boundaries (Default: off)")),
+		OPT_BOOL(0, "show-stats", &show_stats, N_("Show work cost statistics")),
 		OPT_BIT(0, "score-debug", &output_option, N_("Show output score for blame entries"), OUTPUT_SHOW_SCORE),
 		OPT_BIT('f', "show-name", &output_option, N_("Show original filename (Default: auto)"), OUTPUT_SHOW_NAME),
 		OPT_BIT('n', "show-number", &output_option, N_("Show original linenumber (Default: off)"), OUTPUT_SHOW_NUMBER),
@@ -2372,13 +2259,16 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		OPT_STRING(0, "contents", &contents_from, N_("file"), N_("Use <file>'s contents as the final image")),
 		{ OPTION_CALLBACK, 'C', NULL, &opt, N_("score"), N_("Find line copies within and across files"), PARSE_OPT_OPTARG, blame_copy_callback },
 		{ OPTION_CALLBACK, 'M', NULL, &opt, N_("score"), N_("Find line movements within and across files"), PARSE_OPT_OPTARG, blame_move_callback },
-		OPT_CALLBACK('L', NULL, &bottomtop, N_("n,m"), N_("Process only line range n,m, counting from 1"), blame_bottomtop_callback),
+		OPT_STRING_LIST('L', NULL, &range_list, N_("n,m"), N_("Process only line range n,m, counting from 1")),
 		OPT__ABBREV(&abbrev),
 		OPT_END()
 	};
 
 	struct parse_opt_ctx_t ctx;
 	int cmd_is_annotate = !strcmp(argv[0], "annotate");
+	struct range_set ranges;
+	unsigned int range_i;
+	long anchor;
 
 	git_config(git_blame_config, NULL);
 	init_revisions(&revs, NULL);
@@ -2571,26 +2461,46 @@ parse_done:
 	num_read_blob++;
 	lno = prepare_lines(&sb);
 
-	bottom = top = 0;
-	if (bottomtop)
-		prepare_blame_range(&sb, bottomtop, lno, &bottom, &top);
-	if (bottom && top && top < bottom) {
-		long tmp;
-		tmp = top; top = bottom; bottom = tmp;
-	}
-	if (bottom < 1)
-		bottom = 1;
-	if (top < 1)
-		top = lno;
-	bottom--;
-	if (lno < top || lno < bottom)
-		die("file %s has only %lu lines", path, lno);
-
-	ent = xcalloc(1, sizeof(*ent));
-	ent->lno = bottom;
-	ent->num_lines = top - bottom;
-	ent->suspect = o;
-	ent->s_lno = bottom;
+	if (lno && !range_list.nr)
+		string_list_append(&range_list, xstrdup("1"));
+
+	anchor = 1;
+	range_set_init(&ranges, range_list.nr);
+	for (range_i = 0; range_i < range_list.nr; ++range_i) {
+		long bottom, top;
+		if (parse_range_arg(range_list.items[range_i].string,
+				    nth_line_cb, &sb, lno, anchor,
+				    &bottom, &top, sb.path))
+			usage(blame_usage);
+		if (lno < top || ((lno || bottom) && lno < bottom))
+			die("file %s has only %lu lines", path, lno);
+		if (bottom < 1)
+			bottom = 1;
+		if (top < 1)
+			top = lno;
+		bottom--;
+		range_set_append_unsafe(&ranges, bottom, top);
+		anchor = top + 1;
+	}
+	sort_and_merge_range_set(&ranges);
+
+	for (range_i = ranges.nr; range_i > 0; --range_i) {
+		const struct range *r = &ranges.ranges[range_i - 1];
+		long bottom = r->start;
+		long top = r->end;
+		struct blame_entry *next = ent;
+		ent = xcalloc(1, sizeof(*ent));
+		ent->lno = bottom;
+		ent->num_lines = top - bottom;
+		ent->suspect = o;
+		ent->s_lno = bottom;
+		ent->next = next;
+		origin_incref(o);
+	}
+	origin_decref(o);
+
+	range_set_release(&ranges);
+	string_list_clear(&range_list, 0);
 
 	sb.ent = ent;
 	sb.path = path;