mirror/git
1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-09-28 11:11:18 +02:00
Code

diffcore-rename: check if we have enough renames for directories early on

Browse Source 
As noted in the past few commits, if we can determine that a directory
already has enough renames to determine how directory rename detection
will be decided for that directory, then we can mark that directory as
no longer needing any more renames detected for files underneath it.
For such directories, we change the value in the dirs_removed map from
RELEVANT_TO_SELF to RELEVANT_FOR_ANCESTOR.

A subsequent patch will use this information while iterating over the
remaining potential rename sources to mark ones that were only
location_relevant as unneeded if no containing directory is still marked
as RELEVANT_TO_SELF.

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Elijah Newren 2021-03-13 22:22:05 +00:00 committed by Junio C Hamano
parent e54385b97a
commit 0491d39297
1 changed files with 63 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
diffcore-rename.c
View File

@ -407,6 +407,28 @@ static const char *get_highest_rename_path(struct strintmap *counts)
return highest_destination_dir;
}
static char *UNKNOWN_DIR = "/"; /* placeholder -- short, illegal directory */
static int dir_rename_already_determinable(struct strintmap *counts)
{
struct hashmap_iter iter;
struct strmap_entry *entry;
int first = 0, second = 0, unknown = 0;
strintmap_for_each_entry(counts, &iter, entry) {
const char *destination_dir = entry->key;
intptr_t count = (intptr_t)entry->value;
if (!strcmp(destination_dir, UNKNOWN_DIR)) {
unknown = count;
} else if (count >= first) {
second = first;
first = count;
} else if (count >= second) {
second = count;
}
}
return first > second + unknown;
}
static void increment_count(struct dir_rename_info *info,
char *old_dir,
char *new_dir)
@ -1096,17 +1118,48 @@ static void handle_early_known_dir_renames(struct dir_rename_info *info,
struct strintmap *dirs_removed)
{
/*
* Not yet implemented; directory renames are determined via an
* aggregate of all renames under them and using a "majority wins"
* rule. The fact that "majority wins", though, means we don't need
* all the renames under the given directory, we only need enough to
* ensure we have a majority.
*
* For now, we don't have enough information to know if we have a
* majority after exact renames and basename-guided rename detection,
* so just return early without doing any extra filtering.
* Directory renames are determined via an aggregate of all renames
* under them and using a "majority wins" rule. The fact that
* "majority wins", though, means we don't need all the renames
* under the given directory, we only need enough to ensure we have
* a majority.
*/
return;
struct hashmap_iter iter;
struct strmap_entry *entry;
if (!dirs_removed || !relevant_sources)
return; /* nothing to cull */
if (break_idx)
return; /* culling incompatbile with break detection */
/*
* FIXME: Supplement dir_rename_count with number of potential
* renames, marking all potential rename sources as mapping to
* UNKNOWN_DIR.
*/
/*
* For any directory which we need a potential rename detected for
* (i.e. those marked as RELEVANT_FOR_SELF in dirs_removed), check
* whether we have enough renames to satisfy the "majority rules"
* requirement such that detecting any more renames of files under
* it won't change the result. For any such directory, mark that
* we no longer need to detect a rename for it. However, since we
* might need to still detect renames for an ancestor of that
* directory, use RELEVANT_FOR_ANCESTOR.
*/
strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
/* entry->key is source_dir */
struct strintmap *counts = entry->value;
if (strintmap_get(dirs_removed, entry->key) ==
RELEVANT_FOR_SELF &&
dir_rename_already_determinable(counts)) {
strintmap_set(dirs_removed, entry->key,
RELEVANT_FOR_ANCESTOR);
}
}
}
void diffcore_rename_extended(struct diff_options *options,