[PATCH v5 3/6] blame: optionally track the line starts during fill_blame_origin()

[Barret Rhoden <brho@google.com>]

The line_starts array is an index of line number to file offset, so that
we can quickly find where a particular line begins in a file.  Prior to
this commit, we only tracked this information for the final file image,
i.e. the current version of the file.

This commit adds the ability to track this information for any version
of the file throughout the file's history.  In particular, we track this
info when we load the file's image into memory: fill_blame_origin().

This feature will be used when we attempt to pass blame entries to
parents when we "ignore" a commit.  Most uses of fill_blame_origin()
will not require this feature, hence the flag parameter.  Multiple calls
to fill_blame_origin() are idempotent, and any of them can request the
creation of the line_starts array.

Suggested-by: Michael Platings <michael@platin.gs>
Signed-off-by: Barret Rhoden <brho@google.com>
---
 blame.c | 76 ++++++++++++++++++++++++++++++++++-----------------------
 blame.h |  2 ++
 2 files changed, 48 insertions(+), 30 deletions(-)

diff --git a/blame.c b/blame.c
index 31e05c1458d8..cb5806f955a6 100644
--- a/blame.c
+++ b/blame.c
@@ -310,12 +310,42 @@ static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b,
 	return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb);
 }
 
+static const char *get_next_line(const char *start, const char *end)
+{
+	const char *nl = memchr(start, '\n', end - start);
+
+	return nl ? nl + 1 : end;
+}
+
+static int find_line_starts(int **line_starts, const char *buf,
+			    unsigned long len)
+{
+	const char *end = buf + len;
+	const char *p;
+	int *lineno;
+	int num = 0;
+
+	for (p = buf; p < end; p = get_next_line(p, end))
+		num++;
+
+	ALLOC_ARRAY(*line_starts, num + 1);
+	lineno = *line_starts;
+
+	for (p = buf; p < end; p = get_next_line(p, end))
+		*lineno++ = p - buf;
+
+	*lineno = len;
+
+	return num;
+}
+
 /*
  * Given an origin, prepare mmfile_t structure to be used by the
  * diff machinery
  */
 static void fill_origin_blob(struct diff_options *opt,
-			     struct blame_origin *o, mmfile_t *file, int *num_read_blob)
+			     struct blame_origin *o, mmfile_t *file,
+			     int *num_read_blob, int fill_line_starts)
 {
 	if (!o->file.ptr) {
 		enum object_type type;
@@ -339,11 +369,16 @@ static void fill_origin_blob(struct diff_options *opt,
 	}
 	else
 		*file = o->file;
+	if (fill_line_starts && !o->line_starts)
+		o->num_lines = find_line_starts(&o->line_starts, o->file.ptr,
+						o->file.size);
 }
 
 static void drop_origin_blob(struct blame_origin *o)
 {
 	FREE_AND_NULL(o->file.ptr);
+	FREE_AND_NULL(o->line_starts);
+	o->num_lines = 0;
 }
 
 /*
@@ -992,8 +1027,10 @@ static void pass_blame_to_parent(struct blame_scoreboard *sb,
 	d.offset = 0;
 	d.dstq = &newdest; d.srcq = &target->suspects;
 
-	fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob);
-	fill_origin_blob(&sb->revs->diffopt, target, &file_o, &sb->num_read_blob);
+	fill_origin_blob(&sb->revs->diffopt, parent, &file_p,
+			 &sb->num_read_blob, 0);
+	fill_origin_blob(&sb->revs->diffopt, target, &file_o,
+			 &sb->num_read_blob, 0);
 	sb->num_get_patch++;
 
 	if (diff_hunks(&file_p, &file_o, blame_chunk_cb, &d, sb->xdl_opts))
@@ -1199,7 +1236,8 @@ static void find_move_in_parent(struct blame_scoreboard *sb,
 	if (!unblamed)
 		return; /* nothing remains for this target */
 
-	fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob);
+	fill_origin_blob(&sb->revs->diffopt, parent, &file_p,
+			 &sb->num_read_blob, 0);
 	if (!file_p.ptr)
 		return;
 
@@ -1328,7 +1366,8 @@ static void find_copy_in_parent(struct blame_scoreboard *sb,
 			norigin = get_origin(parent, p->one->path);
 			oidcpy(&norigin->blob_oid, &p->one->oid);
 			norigin->mode = p->one->mode;
-			fill_origin_blob(&sb->revs->diffopt, norigin, &file_p, &sb->num_read_blob);
+			fill_origin_blob(&sb->revs->diffopt, norigin, &file_p,
+					 &sb->num_read_blob, 0);
 			if (!file_p.ptr)
 				continue;
 
@@ -1650,37 +1689,14 @@ void assign_blame(struct blame_scoreboard *sb, int opt)
 	}
 }
 
-static const char *get_next_line(const char *start, const char *end)
-{
-	const char *nl = memchr(start, '\n', end - start);
-	return nl ? nl + 1 : end;
-}
-
 /*
  * To allow quick access to the contents of nth line in the
  * final image, prepare an index in the scoreboard.
  */
 static int prepare_lines(struct blame_scoreboard *sb)
 {
-	const char *buf = sb->final_buf;
-	unsigned long len = sb->final_buf_size;
-	const char *end = buf + len;
-	const char *p;
-	int *lineno;
-	int num = 0;
-
-	for (p = buf; p < end; p = get_next_line(p, end))
-		num++;
-
-	ALLOC_ARRAY(sb->lineno, num + 1);
-	lineno = sb->lineno;
-
-	for (p = buf; p < end; p = get_next_line(p, end))
-		*lineno++ = p - buf;
-
-	*lineno = len;
-
-	sb->num_lines = num;
+	sb->num_lines = find_line_starts(&sb->lineno, sb->final_buf,
+					 sb->final_buf_size);
 	return sb->num_lines;
 }
 
diff --git a/blame.h b/blame.h
index be3a895043e0..b418bd2e480d 100644
--- a/blame.h
+++ b/blame.h
@@ -51,6 +51,8 @@ struct blame_origin {
 	 */
 	struct blame_entry *suspects;
 	mmfile_t file;
+	int num_lines;
+	int *line_starts;
 	struct object_id blob_oid;
 	unsigned mode;
 	/* guilty gets set when shipping any suspects to the final
-- 
2.21.0.392.gf8f6787159e-goog