blame: optionally track line fingerprints during fill_blame_origin()
fill_blame_origin() is a convenient place to store data that we will use throughout the lifetime of a blame_origin. Some heuristics for ignoring commits during a blame session can make use of this storage. In particular, we will calculate a fingerprint for each line of a file for blame_origins involved in an ignored commit. In this commit, we only calculate the line_starts, reusing the existing code from the scoreboard's line_starts. In an upcoming commit, we will actually compute the fingerprints. 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 fingerprints structure. Suggested-by: Michael Platings <michael@platin.gs> Signed-off-by: Barret Rhoden <brho@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Barret Rhoden committed
May 15, 2019 at 17:45 UTC
1fc73384bac289b4907f0adba2a25d0644affa73
2 files changed
+62
-30
blame.c
+60
-30
@@ -310,12 +310,58 @@ static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b,
310
return xdi_diff(file_a, file_b, &xpp, &xecfg, &ecb);
311
}
312
313
+static const char *get_next_line(const char *start, const char *end)
314
+{
315
+ const char *nl = memchr(start, '\n', end - start);
316
+
317
+ return nl ? nl + 1 : end;
318
+}
319
+
320
+static int find_line_starts(int **line_starts, const char *buf,
321
+ unsigned long len)
322
+{
323
+ const char *end = buf + len;
324
+ const char *p;
325
+ int *lineno;
326
+ int num = 0;
327
+
328
+ for (p = buf; p < end; p = get_next_line(p, end))
329
+ num++;
330
+
331
+ ALLOC_ARRAY(*line_starts, num + 1);
332
+ lineno = *line_starts;
333
+
334
+ for (p = buf; p < end; p = get_next_line(p, end))
335
+ *lineno++ = p - buf;
336
+
337
+ *lineno = len;
338
+
339
+ return num;
340
+}
341
+
342
+static void fill_origin_fingerprints(struct blame_origin *o, mmfile_t *file)
343
+{
344
+ int *line_starts;
345
+
346
+ if (o->fingerprints)
347
+ return;
348
+ o->num_lines = find_line_starts(&line_starts, o->file.ptr,
349
+ o->file.size);
350
+ /* TODO: Will fill in fingerprints in a future commit */
351
+ free(line_starts);
352
+}
353
+
354
+static void drop_origin_fingerprints(struct blame_origin *o)
355
+{
356
+}
357
+
358
/*
359
* Given an origin, prepare mmfile_t structure to be used by the
360
* diff machinery
361
*/
362
static void fill_origin_blob(struct diff_options *opt,
318
- struct blame_origin *o, mmfile_t *file, int *num_read_blob)
363
+ struct blame_origin *o, mmfile_t *file,
364
+ int *num_read_blob, int fill_fingerprints)
365
{
366
if (!o->file.ptr) {
367
enum object_type type;
@@ -339,11 +385,14 @@ static void fill_origin_blob(struct diff_options *opt,
385
}
386
else
387
*file = o->file;
388
+ if (fill_fingerprints)
389
+ fill_origin_fingerprints(o, file);
390
}
391
392
static void drop_origin_blob(struct blame_origin *o)
393
{
394
FREE_AND_NULL(o->file.ptr);
395
+ drop_origin_fingerprints(o);
396
}
397
398
/*
@@ -1140,8 +1189,10 @@ static void pass_blame_to_parent(struct blame_scoreboard *sb,
1189
d.ignore_diffs = ignore_diffs;
1190
d.dstq = &newdest; d.srcq = &target->suspects;
1191
1143
- fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob);
1144
- fill_origin_blob(&sb->revs->diffopt, target, &file_o, &sb->num_read_blob);
1192
+ fill_origin_blob(&sb->revs->diffopt, parent, &file_p,
1193
+ &sb->num_read_blob, ignore_diffs);
1194
+ fill_origin_blob(&sb->revs->diffopt, target, &file_o,
1195
+ &sb->num_read_blob, ignore_diffs);
1196
sb->num_get_patch++;
1197
1198
if (diff_hunks(&file_p, &file_o, blame_chunk_cb, &d, sb->xdl_opts))
@@ -1352,7 +1403,8 @@ static void find_move_in_parent(struct blame_scoreboard *sb,
1403
if (!unblamed)
1404
return; /* nothing remains for this target */
1405
1355
- fill_origin_blob(&sb->revs->diffopt, parent, &file_p, &sb->num_read_blob);
1406
+ fill_origin_blob(&sb->revs->diffopt, parent, &file_p,
1407
+ &sb->num_read_blob, 0);
1408
if (!file_p.ptr)
1409
return;
1410
@@ -1481,7 +1533,8 @@ static void find_copy_in_parent(struct blame_scoreboard *sb,
1533
norigin = get_origin(parent, p->one->path);
1534
oidcpy(&norigin->blob_oid, &p->one->oid);
1535
norigin->mode = p->one->mode;
1484
- fill_origin_blob(&sb->revs->diffopt, norigin, &file_p, &sb->num_read_blob);
1536
+ fill_origin_blob(&sb->revs->diffopt, norigin, &file_p,
1537
+ &sb->num_read_blob, 0);
1538
if (!file_p.ptr)
1539
continue;
1540
@@ -1820,37 +1873,14 @@ void assign_blame(struct blame_scoreboard *sb, int opt)
1873
}
1874
}
1875
1823
-static const char *get_next_line(const char *start, const char *end)
1824
-{
1825
- const char *nl = memchr(start, '\n', end - start);
1826
- return nl ? nl + 1 : end;
1827
-}
1828
-
1876
/*
1877
* To allow quick access to the contents of nth line in the
1878
* final image, prepare an index in the scoreboard.
1879
*/
1880
static int prepare_lines(struct blame_scoreboard *sb)
1881
{
1835
- const char *buf = sb->final_buf;
1836
- unsigned long len = sb->final_buf_size;
1837
- const char *end = buf + len;
1838
- const char *p;
1839
- int *lineno;
1840
- int num = 0;
1841
-
1842
- for (p = buf; p < end; p = get_next_line(p, end))
1843
- num++;
1844
-
1845
- ALLOC_ARRAY(sb->lineno, num + 1);
1846
- lineno = sb->lineno;
1847
-
1848
- for (p = buf; p < end; p = get_next_line(p, end))
1849
- *lineno++ = p - buf;
1850
-
1851
- *lineno = len;
1852
-
1853
- sb->num_lines = num;
1882
+ sb->num_lines = find_line_starts(&sb->lineno, sb->final_buf,
1883
+ sb->final_buf_size);
1884
return sb->num_lines;
1885
}
1886
blame.h
+2
@@ -51,6 +51,8 @@ struct blame_origin {
51
*/
52
struct blame_entry *suspects;
53
mmfile_t file;
54
+ int num_lines;
55
+ void *fingerprints;
56
struct object_id blob_oid;
57
unsigned mode;
58
/* guilty gets set when shipping any suspects to the final