merge-ort, diffcore-rename: tweak dirs_removed and relevant_source type
As noted in the previous commit, we want to be able to take advantage of the "majority rules" portion of directory rename detection to avoid detecting more renames than necessary. However, for diffcore-rename to take advantage of that, it needs to know whether a rename source file was needed for just directory rename detection reasons, or if it is wanted for potential three-way content merging. Modify relevant_sources from a strset to a strintmap, so we can encode additional information. We also modify dirs_removed from a strset to a strintmap at the same time because trying to determine what files are needed for directory rename detection will require us tracking a bit more information for each directory. This commit only changes the types of the two variables from strset to strintmap; it does not actually store any special values yet and for now only checks for presence of entries in the strintmap. Thus, the code is functionally identical to how it behaved before. Future commits will start associating values with each key for these two maps. Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Elijah Newren committed
Mar 13, 2021 at 22:22 UTC
a49b55d52e7dcfd628b6328c9098d734ebe7a97d
3 files changed
+41
-40
diffcore-rename.c
+24
-23
@@ -371,7 +371,7 @@ struct dir_rename_info {
371
struct strintmap idx_map;
372
struct strmap dir_rename_guess;
373
struct strmap *dir_rename_count;
374
- struct strset *relevant_source_dirs;
374
+ struct strintmap *relevant_source_dirs;
375
unsigned setup;
376
};
377
@@ -429,7 +429,7 @@ static void increment_count(struct dir_rename_info *info,
429
}
430
431
static void update_dir_rename_counts(struct dir_rename_info *info,
432
- struct strset *dirs_removed,
432
+ struct strintmap *dirs_removed,
433
const char *oldname,
434
const char *newname)
435
{
@@ -464,7 +464,7 @@ static void update_dir_rename_counts(struct dir_rename_info *info,
464
/* Get old_dir, skip if its directory isn't relevant. */
465
dirname_munge(old_dir);
466
if (info->relevant_source_dirs &&
467
- !strset_contains(info->relevant_source_dirs, old_dir))
467
+ !strintmap_contains(info->relevant_source_dirs, old_dir))
468
break;
469
470
/* Get new_dir */
@@ -509,7 +509,7 @@ static void update_dir_rename_counts(struct dir_rename_info *info,
509
}
510
}
511
512
- if (strset_contains(dirs_removed, old_dir))
512
+ if (strintmap_contains(dirs_removed, old_dir))
513
increment_count(info, old_dir, new_dir);
514
else
515
break;
@@ -527,8 +527,8 @@ static void update_dir_rename_counts(struct dir_rename_info *info,
527
}
528
529
static void initialize_dir_rename_info(struct dir_rename_info *info,
530
- struct strset *relevant_sources,
531
- struct strset *dirs_removed,
530
+ struct strintmap *relevant_sources,
531
+ struct strintmap *dirs_removed,
532
struct strmap *dir_rename_count)
533
{
534
struct hashmap_iter iter;
@@ -555,12 +555,13 @@ static void initialize_dir_rename_info(struct dir_rename_info *info,
555
info->relevant_source_dirs = dirs_removed; /* might be NULL */
556
} else {
557
info->relevant_source_dirs = xmalloc(sizeof(struct strintmap));
558
- strset_init(info->relevant_source_dirs);
559
- strset_for_each_entry(relevant_sources, &iter, entry) {
558
+ strintmap_init(info->relevant_source_dirs, 0 /* unused */);
559
+ strintmap_for_each_entry(relevant_sources, &iter, entry) {
560
char *dirname = get_dirname(entry->key);
561
if (!dirs_removed ||
562
- strset_contains(dirs_removed, dirname))
563
- strset_add(info->relevant_source_dirs, dirname);
562
+ strintmap_contains(dirs_removed, dirname))
563
+ strintmap_set(info->relevant_source_dirs,
564
+ dirname, 0 /* value irrelevant */);
565
free(dirname);
566
}
567
}
@@ -624,7 +625,7 @@ void partial_clear_dir_rename_count(struct strmap *dir_rename_count)
625
}
626
627
static void cleanup_dir_rename_info(struct dir_rename_info *info,
627
- struct strset *dirs_removed,
628
+ struct strintmap *dirs_removed,
629
int keep_dir_rename_count)
630
{
631
struct hashmap_iter iter;
@@ -644,7 +645,7 @@ static void cleanup_dir_rename_info(struct dir_rename_info *info,
645
/* relevant_source_dirs */
646
if (info->relevant_source_dirs &&
647
info->relevant_source_dirs != dirs_removed) {
647
- strset_clear(info->relevant_source_dirs);
648
+ strintmap_clear(info->relevant_source_dirs);
649
FREE_AND_NULL(info->relevant_source_dirs);
650
}
651
@@ -666,7 +667,7 @@ static void cleanup_dir_rename_info(struct dir_rename_info *info,
667
const char *source_dir = entry->key;
668
struct strintmap *counts = entry->value;
669
669
- if (!strset_contains(dirs_removed, source_dir)) {
670
+ if (!strintmap_contains(dirs_removed, source_dir)) {
671
string_list_append(&to_remove, source_dir);
672
strintmap_clear(counts);
673
continue;
@@ -770,8 +771,8 @@ static int idx_possible_rename(char *filename, struct dir_rename_info *info)
771
static int find_basename_matches(struct diff_options *options,
772
int minimum_score,
773
struct dir_rename_info *info,
773
- struct strset *relevant_sources,
774
- struct strset *dirs_removed)
774
+ struct strintmap *relevant_sources,
775
+ struct strintmap *dirs_removed)
776
{
777
/*
778
* When I checked in early 2020, over 76% of file renames in linux
@@ -863,7 +864,7 @@ static int find_basename_matches(struct diff_options *options,
864
865
/* Skip irrelevant sources */
866
if (relevant_sources &&
866
- !strset_contains(relevant_sources, filename))
867
+ !strintmap_contains(relevant_sources, filename))
868
continue;
869
870
/*
@@ -994,7 +995,7 @@ static int find_renames(struct diff_score *mx,
995
int minimum_score,
996
int copies,
997
struct dir_rename_info *info,
997
- struct strset *dirs_removed)
998
+ struct strintmap *dirs_removed)
999
{
1000
int count = 0, i;
1001
@@ -1019,7 +1020,7 @@ static int find_renames(struct diff_score *mx,
1020
}
1021
1022
static void remove_unneeded_paths_from_src(int detecting_copies,
1022
- struct strset *interesting)
1023
+ struct strintmap *interesting)
1024
{
1025
int i, new_num_src;
1026
@@ -1061,7 +1062,7 @@ static void remove_unneeded_paths_from_src(int detecting_copies,
1062
continue;
1063
1064
/* If we don't care about the source path, skip it */
1064
- if (interesting && !strset_contains(interesting, one->path))
1065
+ if (interesting && !strintmap_contains(interesting, one->path))
1066
continue;
1067
1068
if (new_num_src < i)
@@ -1074,8 +1075,8 @@ static void remove_unneeded_paths_from_src(int detecting_copies,
1075
}
1076
1077
static void handle_early_known_dir_renames(struct dir_rename_info *info,
1077
- struct strset *relevant_sources,
1078
- struct strset *dirs_removed)
1078
+ struct strintmap *relevant_sources,
1079
+ struct strintmap *dirs_removed)
1080
{
1081
/*
1082
* Not yet implemented; directory renames are determined via an
@@ -1092,8 +1093,8 @@ static void handle_early_known_dir_renames(struct dir_rename_info *info,
1093
}
1094
1095
void diffcore_rename_extended(struct diff_options *options,
1095
- struct strset *relevant_sources,
1096
- struct strset *dirs_removed,
1096
+ struct strintmap *relevant_sources,
1097
+ struct strintmap *dirs_removed,
1098
struct strmap *dir_rename_count)
1099
{
1100
int detect_rename = options->detect_rename;
diffcore.h
+3
-3
@@ -8,8 +8,8 @@
8
9
struct diff_options;
10
struct repository;
11
+struct strintmap;
12
struct strmap;
12
-struct strset;
13
struct userdiff_driver;
14
15
/* This header file is internal between diff.c and its diff transformers
@@ -166,8 +166,8 @@ void partial_clear_dir_rename_count(struct strmap *dir_rename_count);
166
void diffcore_break(struct repository *, int);
167
void diffcore_rename(struct diff_options *);
168
void diffcore_rename_extended(struct diff_options *options,
169
- struct strset *relevant_sources,
170
- struct strset *dirs_removed,
169
+ struct strintmap *relevant_sources,
170
+ struct strintmap *dirs_removed,
171
struct strmap *dir_rename_count);
172
void diffcore_merge_broken(void);
173
void diffcore_pickaxe(struct diff_options *);
merge-ort.c
+14
-14
@@ -74,7 +74,7 @@ struct rename_info {
74
/*
75
* dirs_removed: directories removed on a given side of history.
76
*/
77
- struct strset dirs_removed[3];
77
+ struct strintmap dirs_removed[3];
78
79
/*
80
* dir_rename_count: tracking where parts of a directory were renamed to
@@ -106,7 +106,7 @@ struct rename_info {
106
* If neither of those are true, we can skip rename detection for
107
* that path.
108
*/
109
- struct strset relevant_sources[3];
109
+ struct strintmap relevant_sources[3];
110
111
/*
112
* dir_rename_mask:
@@ -362,8 +362,8 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
362
int i;
363
void (*strmap_func)(struct strmap *, int) =
364
reinitialize ? strmap_partial_clear : strmap_clear;
365
- void (*strset_func)(struct strset *) =
366
- reinitialize ? strset_partial_clear : strset_clear;
365
+ void (*strintmap_func)(struct strintmap *) =
366
+ reinitialize ? strintmap_partial_clear : strintmap_clear;
367
368
/*
369
* We marked opti->paths with strdup_strings = 0, so that we
@@ -395,7 +395,7 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
395
396
/* Free memory used by various renames maps */
397
for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) {
398
- strset_func(&renames->dirs_removed[i]);
398
+ strintmap_func(&renames->dirs_removed[i]);
399
400
partial_clear_dir_rename_count(&renames->dir_rename_count[i]);
401
if (!reinitialize)
@@ -403,7 +403,7 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
403
404
strmap_func(&renames->dir_renames[i], 0);
405
406
- strset_func(&renames->relevant_sources[i]);
406
+ strintmap_func(&renames->relevant_sources[i]);
407
}
408
409
if (!reinitialize) {
@@ -674,7 +674,7 @@ static void add_pair(struct merge_options *opt,
674
unsigned location_relevant = (dir_rename_mask == 0x07);
675
676
if (content_relevant || location_relevant)
677
- strset_add(&renames->relevant_sources[side], pathname);
677
+ strintmap_set(&renames->relevant_sources[side], pathname, 1);
678
}
679
680
one = alloc_filespec(pathname);
@@ -730,9 +730,9 @@ static void collect_rename_info(struct merge_options *opt,
730
/* absent_mask = 0x07 - dirmask; sides = absent_mask/2 */
731
unsigned sides = (0x07 - dirmask)/2;
732
if (sides & 1)
733
- strset_add(&renames->dirs_removed[1], fullname);
733
+ strintmap_set(&renames->dirs_removed[1], fullname, 1);
734
if (sides & 2)
735
- strset_add(&renames->dirs_removed[2], fullname);
735
+ strintmap_set(&renames->dirs_removed[2], fullname, 1);
736
}
737
738
if (filemask == 0 || filemask == 7)
@@ -2161,7 +2161,7 @@ static inline int possible_side_renames(struct rename_info *renames,
2161
unsigned side_index)
2162
{
2163
return renames->pairs[side_index].nr > 0 &&
2164
- !strset_empty(&renames->relevant_sources[side_index]);
2164
+ !strintmap_empty(&renames->relevant_sources[side_index]);
2165
}
2166
2167
static inline int possible_renames(struct rename_info *renames)
@@ -3445,14 +3445,14 @@ static void merge_start(struct merge_options *opt, struct merge_result *result)
3445
/* Initialization of various renames fields */
3446
renames = &opt->priv->renames;
3447
for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) {
3448
- strset_init_with_options(&renames->dirs_removed[i],
3449
- NULL, 0);
3448
+ strintmap_init_with_options(&renames->dirs_removed[i],
3449
+ 0, NULL, 0);
3450
strmap_init_with_options(&renames->dir_rename_count[i],
3451
NULL, 1);
3452
strmap_init_with_options(&renames->dir_renames[i],
3453
NULL, 0);
3454
- strset_init_with_options(&renames->relevant_sources[i],
3455
- NULL, 0);
3454
+ strintmap_init_with_options(&renames->relevant_sources[i],
3455
+ 0, NULL, 0);
3456
}
3457
3458
/*