aboutsummaryrefslogtreecommitdiffstats
path: root/diffcore-rename.c
diff options
context:
space:
mode:
Diffstat (limited to 'diffcore-rename.c')
-rw-r--r--diffcore-rename.c110
1 files changed, 84 insertions, 26 deletions
diff --git a/diffcore-rename.c b/diffcore-rename.c
index d775183c2f..99e63e90f8 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -1,4 +1,5 @@
/*
+ *
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
@@ -7,6 +8,7 @@
#include "object-store.h"
#include "hashmap.h"
#include "progress.h"
+#include "promisor-remote.h"
/* Table of rename/copy destinations */
@@ -23,7 +25,7 @@ static int find_rename_dst(struct diff_filespec *two)
first = 0;
last = rename_dst_nr;
while (last > first) {
- int next = (last + first) >> 1;
+ int next = first + ((last - first) >> 1);
struct diff_rename_dst *dst = &(rename_dst[next]);
int cmp = strcmp(two->path, dst->two->path);
if (!cmp)
@@ -83,7 +85,7 @@ static struct diff_rename_src *register_rename_src(struct diff_filepair *p)
first = 0;
last = rename_src_nr;
while (last > first) {
- int next = (last + first) >> 1;
+ int next = first + ((last - first) >> 1);
struct diff_rename_src *src = &(rename_src[next]);
int cmp = strcmp(one->path, src->p->one->path);
if (!cmp)
@@ -128,9 +130,46 @@ struct diff_score {
short name_score;
};
-static int estimate_similarity(struct diff_filespec *src,
+struct prefetch_options {
+ struct repository *repo;
+ int skip_unmodified;
+};
+static void prefetch(void *prefetch_options)
+{
+ struct prefetch_options *options = prefetch_options;
+ int i;
+ struct oid_array to_fetch = OID_ARRAY_INIT;
+
+ for (i = 0; i < rename_dst_nr; i++) {
+ if (rename_dst[i].pair)
+ /*
+ * The loop in diffcore_rename() will not need these
+ * blobs, so skip prefetching.
+ */
+ continue; /* already found exact match */
+ diff_add_if_missing(options->repo, &to_fetch,
+ rename_dst[i].two);
+ }
+ for (i = 0; i < rename_src_nr; i++) {
+ if (options->skip_unmodified &&
+ diff_unmodified_pair(rename_src[i].p))
+ /*
+ * The loop in diffcore_rename() will not need these
+ * blobs, so skip prefetching.
+ */
+ continue;
+ diff_add_if_missing(options->repo, &to_fetch,
+ rename_src[i].p->one);
+ }
+ promisor_remote_get_direct(options->repo, to_fetch.oid, to_fetch.nr);
+ oid_array_clear(&to_fetch);
+}
+
+static int estimate_similarity(struct repository *r,
+ struct diff_filespec *src,
struct diff_filespec *dst,
- int minimum_score)
+ int minimum_score,
+ int skip_unmodified)
{
/* src points at a file that existed in the original tree (or
* optionally a file in the destination tree) and dst points
@@ -147,6 +186,15 @@ static int estimate_similarity(struct diff_filespec *src,
*/
unsigned long max_size, delta_size, base_size, src_copied, literal_added;
int score;
+ struct diff_populate_filespec_options dpf_options = {
+ .check_size_only = 1
+ };
+ struct prefetch_options prefetch_options = {r, skip_unmodified};
+
+ if (r == the_repository && has_promisor_remote()) {
+ dpf_options.missing_object_cb = prefetch;
+ dpf_options.missing_object_data = &prefetch_options;
+ }
/* We deal only with regular files. Symlink renames are handled
* only when they are exact matches --- in other words, no edits
@@ -165,10 +213,10 @@ static int estimate_similarity(struct diff_filespec *src,
* say whether the size is valid or not!)
*/
if (!src->cnt_data &&
- diff_populate_filespec(src, CHECK_SIZE_ONLY))
+ diff_populate_filespec(r, src, &dpf_options))
return 0;
if (!dst->cnt_data &&
- diff_populate_filespec(dst, CHECK_SIZE_ONLY))
+ diff_populate_filespec(r, dst, &dpf_options))
return 0;
max_size = ((src->size > dst->size) ? src->size : dst->size);
@@ -186,12 +234,14 @@ static int estimate_similarity(struct diff_filespec *src,
if (max_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
- if (!src->cnt_data && diff_populate_filespec(src, 0))
+ dpf_options.check_size_only = 0;
+
+ if (!src->cnt_data && diff_populate_filespec(r, src, &dpf_options))
return 0;
- if (!dst->cnt_data && diff_populate_filespec(dst, 0))
+ if (!dst->cnt_data && diff_populate_filespec(r, dst, &dpf_options))
return 0;
- if (diffcore_count_changes(src, dst,
+ if (diffcore_count_changes(r, src, dst,
&src->cnt_data, &dst->cnt_data,
&src_copied, &literal_added))
return 0;
@@ -256,15 +306,16 @@ struct file_similarity {
struct diff_filespec *filespec;
};
-static unsigned int hash_filespec(struct diff_filespec *filespec)
+static unsigned int hash_filespec(struct repository *r,
+ struct diff_filespec *filespec)
{
if (!filespec->oid_valid) {
- if (diff_populate_filespec(filespec, 0))
+ if (diff_populate_filespec(r, filespec, NULL))
return 0;
- hash_object_file(filespec->data, filespec->size, "blob",
- &filespec->oid);
+ hash_object_file(r->hash_algo, filespec->data, filespec->size,
+ "blob", &filespec->oid);
}
- return sha1hash(filespec->oid.hash);
+ return oidhash(&filespec->oid);
}
static int find_identical_files(struct hashmap *srcs,
@@ -272,21 +323,22 @@ static int find_identical_files(struct hashmap *srcs,
struct diff_options *options)
{
int renames = 0;
-
struct diff_filespec *target = rename_dst[dst_index].two;
struct file_similarity *p, *best = NULL;
int i = 100, best_score = -1;
+ unsigned int hash = hash_filespec(options->repo, target);
/*
* Find the best source match for specified destination.
*/
- p = hashmap_get_from_hash(srcs, hash_filespec(target), NULL);
- for (; p; p = hashmap_get_next(srcs, p)) {
+ p = hashmap_get_entry_from_hash(srcs, hash, NULL,
+ struct file_similarity, entry);
+ hashmap_for_each_entry_from(srcs, p, entry) {
int score;
struct diff_filespec *source = p->filespec;
/* False hash collision? */
- if (oidcmp(&source->oid, &target->oid))
+ if (!oideq(&source->oid, &target->oid))
continue;
/* Non-regular files? If so, the modes must match! */
if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
@@ -316,15 +368,17 @@ static int find_identical_files(struct hashmap *srcs,
return renames;
}
-static void insert_file_table(struct hashmap *table, int index, struct diff_filespec *filespec)
+static void insert_file_table(struct repository *r,
+ struct hashmap *table, int index,
+ struct diff_filespec *filespec)
{
struct file_similarity *entry = xmalloc(sizeof(*entry));
entry->index = index;
entry->filespec = filespec;
- hashmap_entry_init(entry, hash_filespec(filespec));
- hashmap_add(table, entry);
+ hashmap_entry_init(&entry->entry, hash_filespec(r, filespec));
+ hashmap_add(table, &entry->entry);
}
/*
@@ -344,14 +398,16 @@ static int find_exact_renames(struct diff_options *options)
*/
hashmap_init(&file_table, NULL, NULL, rename_src_nr);
for (i = rename_src_nr-1; i >= 0; i--)
- insert_file_table(&file_table, i, rename_src[i].p->one);
+ insert_file_table(options->repo,
+ &file_table, i,
+ rename_src[i].p->one);
/* Walk the destinations and find best source match */
for (i = 0; i < rename_dst_nr; i++)
renames += find_identical_files(&file_table, i, options);
/* Free the hash data structure and entries */
- hashmap_free(&file_table, 1);
+ hashmap_free_entries(&file_table, struct file_similarity, entry);
return renames;
}
@@ -557,8 +613,10 @@ void diffcore_rename(struct diff_options *options)
diff_unmodified_pair(rename_src[j].p))
continue;
- this_src.score = estimate_similarity(one, two,
- minimum_score);
+ this_src.score = estimate_similarity(options->repo,
+ one, two,
+ minimum_score,
+ skip_unmodified);
this_src.name_score = basename_same(one, two);
this_src.dst = i;
this_src.src = j;
@@ -576,7 +634,7 @@ void diffcore_rename(struct diff_options *options)
stop_progress(&progress);
/* cost matrix sorted by most to least similar pair */
- QSORT(mx, dst_cnt * NUM_CANDIDATE_PER_DST, score_compare);
+ STABLE_QSORT(mx, dst_cnt * NUM_CANDIDATE_PER_DST, score_compare);
rename_count += find_renames(mx, dst_cnt, minimum_score, 0);
if (detect_rename == DIFF_DETECT_COPY)
generated by cgit v1.2.3 (git 2.39.1) at 2025-12-15 13:53:05 +0000