return renames;
}
+struct dir_rename_info {
+ struct strintmap idx_map;
+ struct strmap dir_rename_guess;
+ struct strmap *dir_rename_count;
+ struct strset *relevant_source_dirs;
+ unsigned setup;
+};
+
+static char *get_dirname(const char *filename)
+{
+ char *slash = strrchr(filename, '/');
+ return slash ? xstrndup(filename, slash - filename) : xstrdup("");
+}
+
+static void dirname_munge(char *filename)
+{
+ char *slash = strrchr(filename, '/');
+ if (!slash)
+ slash = filename;
+ *slash = '\0';
+}
+
+static const char *get_highest_rename_path(struct strintmap *counts)
+{
+ int highest_count = 0;
+ const char *highest_destination_dir = NULL;
+ struct hashmap_iter iter;
+ struct strmap_entry *entry;
+
+ strintmap_for_each_entry(counts, &iter, entry) {
+ const char *destination_dir = entry->key;
+ intptr_t count = (intptr_t)entry->value;
+ if (count > highest_count) {
+ highest_count = count;
+ highest_destination_dir = destination_dir;
+ }
+ }
+ return highest_destination_dir;
+}
+
+static void increment_count(struct dir_rename_info *info,
+ char *old_dir,
+ char *new_dir)
+{
+ struct strintmap *counts;
+ struct strmap_entry *e;
+
+ /* Get the {new_dirs -> counts} mapping using old_dir */
+ e = strmap_get_entry(info->dir_rename_count, old_dir);
+ if (e) {
+ counts = e->value;
+ } else {
+ counts = xmalloc(sizeof(*counts));
+ strintmap_init_with_options(counts, 0, NULL, 1);
+ strmap_put(info->dir_rename_count, old_dir, counts);
+ }
+
+ /* Increment the count for new_dir */
+ strintmap_incr(counts, new_dir, 1);
+}
+
+static void update_dir_rename_counts(struct dir_rename_info *info,
+ struct strset *dirs_removed,
+ const char *oldname,
+ const char *newname)
+{
+ char *old_dir = xstrdup(oldname);
+ char *new_dir = xstrdup(newname);
+ char new_dir_first_char = new_dir[0];
+ int first_time_in_loop = 1;
+
+ if (!info->setup)
+ /*
+ * info->setup is 0 here in two cases: (1) all auxiliary
+ * vars (like dirs_removed) were NULL so
+ * initialize_dir_rename_info() returned early, or (2)
+ * either break detection or copy detection are active so
+ * that we never called initialize_dir_rename_info(). In
+ * the former case, we don't have enough info to know if
+ * directories were renamed (because dirs_removed lets us
+ * know about a necessary prerequisite, namely if they were
+ * removed), and in the latter, we don't care about
+ * directory renames or find_basename_matches.
+ *
+ * This matters because both basename and inexact matching
+ * will also call update_dir_rename_counts(). In either of
+ * the above two cases info->dir_rename_counts will not
+ * have been properly initialized which prevents us from
+ * updating it, but in these two cases we don't care about
+ * dir_rename_counts anyway, so we can just exit early.
+ */
+ return;
+
+ while (1) {
+ /* Get old_dir, skip if its directory isn't relevant. */
+ dirname_munge(old_dir);
+ if (info->relevant_source_dirs &&
+ !strset_contains(info->relevant_source_dirs, old_dir))
+ break;
+
+ /* Get new_dir */
+ dirname_munge(new_dir);
+
+ /*
+ * When renaming
+ * "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
+ * then this suggests that both
+ * a/b/c/d/e/ => a/b/some/thing/else/e/
+ * a/b/c/d/ => a/b/some/thing/else/
+ * so we want to increment counters for both. We do NOT,
+ * however, also want to suggest that there was the following
+ * rename:
+ * a/b/c/ => a/b/some/thing/
+ * so we need to quit at that point.
+ *
+ * Note the when first_time_in_loop, we only strip off the
+ * basename, and we don't care if that's different.
+ */
+ if (!first_time_in_loop) {
+ char *old_sub_dir = strchr(old_dir, '\0')+1;
+ char *new_sub_dir = strchr(new_dir, '\0')+1;
+ if (!*new_dir) {
+ /*
+ * Special case when renaming to root directory,
+ * i.e. when new_dir == "". In this case, we had
+ * something like
+ * a/b/subdir => subdir
+ * and so dirname_munge() sets things up so that
+ * old_dir = "a/b\0subdir\0"
+ * new_dir = "\0ubdir\0"
+ * We didn't have a '/' to overwrite a '\0' onto
+ * in new_dir, so we have to compare differently.
+ */
+ if (new_dir_first_char != old_sub_dir[0] ||
+ strcmp(old_sub_dir+1, new_sub_dir))
+ break;
+ } else {
+ if (strcmp(old_sub_dir, new_sub_dir))
+ break;
+ }
+ }
+
+ if (strset_contains(dirs_removed, old_dir))
+ increment_count(info, old_dir, new_dir);
+ else
+ break;
+
+ /* If we hit toplevel directory ("") for old or new dir, quit */
+ if (!*old_dir || !*new_dir)
+ break;
+
+ first_time_in_loop = 0;
+ }
+
+ /* Free resources we don't need anymore */
+ free(old_dir);
+ free(new_dir);
+}
+
+static void initialize_dir_rename_info(struct dir_rename_info *info,
+ struct strset *dirs_removed,
+ struct strmap *dir_rename_count)
+{
+ struct hashmap_iter iter;
+ struct strmap_entry *entry;
+ int i;
+
+ if (!dirs_removed) {
+ info->setup = 0;
+ return;
+ }
+ info->setup = 1;
+
+ info->dir_rename_count = dir_rename_count;
+ if (!info->dir_rename_count) {
+ info->dir_rename_count = xmalloc(sizeof(*dir_rename_count));
+ strmap_init(info->dir_rename_count);
+ }
+ strintmap_init_with_options(&info->idx_map, -1, NULL, 0);
+ strmap_init_with_options(&info->dir_rename_guess, NULL, 0);
+
+ /* Setup info->relevant_source_dirs */
+ info->relevant_source_dirs = dirs_removed;
+
+ /*
+ * Loop setting up both info->idx_map, and doing setup of
+ * info->dir_rename_count.
+ */
+ for (i = 0; i < rename_dst_nr; ++i) {
+ /*
+ * For non-renamed files, make idx_map contain mapping of
+ * filename -> index (index within rename_dst, that is)
+ */
+ if (!rename_dst[i].is_rename) {
+ char *filename = rename_dst[i].p->two->path;
+ strintmap_set(&info->idx_map, filename, i);
+ continue;
+ }
+
+ /*
+ * For everything else (i.e. renamed files), make
+ * dir_rename_count contain a map of a map:
+ * old_directory -> {new_directory -> count}
+ * In other words, for every pair look at the directories for
+ * the old filename and the new filename and count how many
+ * times that pairing occurs.
+ */
+ update_dir_rename_counts(info, dirs_removed,
+ rename_dst[i].p->one->path,
+ rename_dst[i].p->two->path);
+ }
+
+ /*
+ * Now we collapse
+ * dir_rename_count: old_directory -> {new_directory -> count}
+ * down to
+ * dir_rename_guess: old_directory -> best_new_directory
+ * where best_new_directory is the one with the highest count.
+ */
+ strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
+ /* entry->key is source_dir */
+ struct strintmap *counts = entry->value;
+ char *best_newdir;
+
+ best_newdir = xstrdup(get_highest_rename_path(counts));
+ strmap_put(&info->dir_rename_guess, entry->key,
+ best_newdir);
+ }
+}
+
+void partial_clear_dir_rename_count(struct strmap *dir_rename_count)
+{
+ struct hashmap_iter iter;
+ struct strmap_entry *entry;
+
+ strmap_for_each_entry(dir_rename_count, &iter, entry) {
+ struct strintmap *counts = entry->value;
+ strintmap_clear(counts);
+ }
+ strmap_partial_clear(dir_rename_count, 1);
+}
+
+static void cleanup_dir_rename_info(struct dir_rename_info *info,
+ struct strset *dirs_removed,
+ int keep_dir_rename_count)
+{
+ struct hashmap_iter iter;
+ struct strmap_entry *entry;
+ struct string_list to_remove = STRING_LIST_INIT_NODUP;
+ int i;
+
+ if (!info->setup)
+ return;
+
+ /* idx_map */
+ strintmap_clear(&info->idx_map);
+
+ /* dir_rename_guess */
+ strmap_clear(&info->dir_rename_guess, 1);
+
+ /* dir_rename_count */
+ if (!keep_dir_rename_count) {
+ partial_clear_dir_rename_count(info->dir_rename_count);
+ strmap_clear(info->dir_rename_count, 1);
+ FREE_AND_NULL(info->dir_rename_count);
+ return;
+ }
+
+ /*
+ * Although dir_rename_count was passed in
+ * diffcore_rename_extended() and we want to keep it around and
+ * return it to that caller, we first want to remove any data
+ * associated with directories that weren't renamed.
+ */
+ strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
+ const char *source_dir = entry->key;
+ struct strintmap *counts = entry->value;
+
+ if (!strset_contains(dirs_removed, source_dir)) {
+ string_list_append(&to_remove, source_dir);
+ strintmap_clear(counts);
+ continue;
+ }
+ }
+ for (i = 0; i < to_remove.nr; ++i)
+ strmap_remove(info->dir_rename_count,
+ to_remove.items[i].string, 1);
+ string_list_clear(&to_remove, 0);
+}
+
+static const char *get_basename(const char *filename)
+{
+ /*
+ * gitbasename() has to worry about special drives, multiple
+ * directory separator characters, trailing slashes, NULL or
+ * empty strings, etc. We only work on filenames as stored in
+ * git, and thus get to ignore all those complications.
+ */
+ const char *base = strrchr(filename, '/');
+ return base ? base + 1 : filename;
+}
+
+static int idx_possible_rename(char *filename, struct dir_rename_info *info)
+{
+ /*
+ * Our comparison of files with the same basename (see
+ * find_basename_matches() below), is only helpful when after exact
+ * rename detection we have exactly one file with a given basename
+ * among the rename sources and also only exactly one file with
+ * that basename among the rename destinations. When we have
+ * multiple files with the same basename in either set, we do not
+ * know which to compare against. However, there are some
+ * filenames that occur in large numbers (particularly
+ * build-related filenames such as 'Makefile', '.gitignore', or
+ * 'build.gradle' that potentially exist within every single
+ * subdirectory), and for performance we want to be able to quickly
+ * find renames for these files too.
+ *
+ * The reason basename comparisons are a useful heuristic was that it
+ * is common for people to move files across directories while keeping
+ * their filename the same. If we had a way of determining or even
+ * making a good educated guess about which directory these non-unique
+ * basename files had moved the file to, we could check it.
+ * Luckily...
+ *
+ * When an entire directory is in fact renamed, we have two factors
+ * helping us out:
+ * (a) the original directory disappeared giving us a hint
+ * about when we can apply an extra heuristic.
+ * (a) we often have several files within that directory and
+ * subdirectories that are renamed without changes
+ * So, rules for a heuristic:
+ * (0) If there basename matches are non-unique (the condition under
+ * which this function is called) AND
+ * (1) the directory in which the file was found has disappeared
+ * (i.e. dirs_removed is non-NULL and has a relevant entry) THEN
+ * (2) use exact renames of files within the directory to determine
+ * where the directory is likely to have been renamed to. IF
+ * there is at least one exact rename from within that
+ * directory, we can proceed.
+ * (3) If there are multiple places the directory could have been
+ * renamed to based on exact renames, ignore all but one of them.
+ * Just use the destination with the most renames going to it.
+ * (4) Check if applying that directory rename to the original file
+ * would result in a destination filename that is in the
+ * potential rename set. If so, return the index of the
+ * destination file (the index within rename_dst).
+ * (5) Compare the original file and returned destination for
+ * similarity, and if they are sufficiently similar, record the
+ * rename.
+ *
+ * This function, idx_possible_rename(), is only responsible for (4).
+ * The conditions/steps in (1)-(3) are handled via setting up
+ * dir_rename_count and dir_rename_guess in
+ * initialize_dir_rename_info(). Steps (0) and (5) are handled by
+ * the caller of this function.
+ */
+ char *old_dir, *new_dir;
+ struct strbuf new_path = STRBUF_INIT;
+ int idx;
+
+ if (!info->setup)
+ return -1;
+
+ old_dir = get_dirname(filename);
+ new_dir = strmap_get(&info->dir_rename_guess, old_dir);
+ free(old_dir);
+ if (!new_dir)
+ return -1;
+
+ strbuf_addstr(&new_path, new_dir);
+ strbuf_addch(&new_path, '/');
+ strbuf_addstr(&new_path, get_basename(filename));
+
+ idx = strintmap_get(&info->idx_map, new_path.buf);
+ strbuf_release(&new_path);
+ return idx;
+}
+
+static int find_basename_matches(struct diff_options *options,
+ int minimum_score,
+ struct dir_rename_info *info,
+ struct strset *dirs_removed)
+{
+ /*
+ * When I checked in early 2020, over 76% of file renames in linux
+ * just moved files to a different directory but kept the same
+ * basename. gcc did that with over 64% of renames, gecko did it
+ * with over 79%, and WebKit did it with over 89%.
+ *
+ * Therefore we can bypass the normal exhaustive NxM matrix
+ * comparison of similarities between all potential rename sources
+ * and destinations by instead using file basename as a hint (i.e.
+ * the portion of the filename after the last '/'), checking for
+ * similarity between files with the same basename, and if we find
+ * a pair that are sufficiently similar, record the rename pair and
+ * exclude those two from the NxM matrix.
+ *
+ * This *might* cause us to find a less than optimal pairing (if
+ * there is another file that we are even more similar to but has a
+ * different basename). Given the huge performance advantage
+ * basename matching provides, and given the frequency with which
+ * people use the same basename in real world projects, that's a
+ * trade-off we are willing to accept when doing just rename
+ * detection.
+ *
+ * If someone wants copy detection that implies they are willing to
+ * spend more cycles to find similarities between files, so it may
+ * be less likely that this heuristic is wanted. If someone is
+ * doing break detection, that means they do not want filename
+ * similarity to imply any form of content similiarity, and thus
+ * this heuristic would definitely be incompatible.
+ */
+
+ int i, renames = 0;
+ struct strintmap sources;
+ struct strintmap dests;
+
+ /*
+ * The prefeteching stuff wants to know if it can skip prefetching
+ * blobs that are unmodified...and will then do a little extra work
+ * to verify that the oids are indeed different before prefetching.
+ * Unmodified blobs are only relevant when doing copy detection;
+ * when limiting to rename detection, diffcore_rename[_extended]()
+ * will never be called with unmodified source paths fed to us, so
+ * the extra work necessary to check if rename_src entries are
+ * unmodified would be a small waste.
+ */
+ int skip_unmodified = 0;
+
+ /*
+ * Create maps of basename -> fullname(s) for remaining sources and
+ * dests.
+ */
+ strintmap_init_with_options(&sources, -1, NULL, 0);
+ strintmap_init_with_options(&dests, -1, NULL, 0);
+ for (i = 0; i < rename_src_nr; ++i) {
+ char *filename = rename_src[i].p->one->path;
+ const char *base;
+
+ /* exact renames removed in remove_unneeded_paths_from_src() */
+ assert(!rename_src[i].p->one->rename_used);
+
+ /* Record index within rename_src (i) if basename is unique */
+ base = get_basename(filename);
+ if (strintmap_contains(&sources, base))
+ strintmap_set(&sources, base, -1);
+ else
+ strintmap_set(&sources, base, i);
+ }
+ for (i = 0; i < rename_dst_nr; ++i) {
+ char *filename = rename_dst[i].p->two->path;
+ const char *base;
+
+ if (rename_dst[i].is_rename)
+ continue; /* involved in exact match already. */
+
+ /* Record index within rename_dst (i) if basename is unique */
+ base = get_basename(filename);
+ if (strintmap_contains(&dests, base))
+ strintmap_set(&dests, base, -1);
+ else
+ strintmap_set(&dests, base, i);
+ }
+
+ /* Now look for basename matchups and do similarity estimation */
+ for (i = 0; i < rename_src_nr; ++i) {
+ char *filename = rename_src[i].p->one->path;
+ const char *base = NULL;
+ intptr_t src_index;
+ intptr_t dst_index;
+
+ /*
+ * If the basename is unique among remaining sources, then
+ * src_index will equal 'i' and we can attempt to match it
+ * to a unique basename in the destinations. Otherwise,
+ * use directory rename heuristics, if possible.
+ */
+ base = get_basename(filename);
+ src_index = strintmap_get(&sources, base);
+ assert(src_index == -1 || src_index == i);
+
+ if (strintmap_contains(&dests, base)) {
+ struct diff_filespec *one, *two;
+ int score;
+
+ /* Find a matching destination, if possible */
+ dst_index = strintmap_get(&dests, base);
+ if (src_index == -1 || dst_index == -1) {
+ src_index = i;
+ dst_index = idx_possible_rename(filename, info);
+ }
+ if (dst_index == -1)
+ continue;
+
+ /* Ignore this dest if already used in a rename */
+ if (rename_dst[dst_index].is_rename)
+ continue; /* already used previously */
+
+ /* Estimate the similarity */
+ one = rename_src[src_index].p->one;
+ two = rename_dst[dst_index].p->two;
+ score = estimate_similarity(options->repo, one, two,
+ minimum_score, skip_unmodified);
+
+ /* If sufficiently similar, record as rename pair */
+ if (score < minimum_score)
+ continue;
+ record_rename_pair(dst_index, src_index, score);
+ renames++;
+ update_dir_rename_counts(info, dirs_removed,
+ one->path, two->path);
+
+ /*
+ * Found a rename so don't need text anymore; if we
+ * didn't find a rename, the filespec_blob would get
+ * re-used when doing the matrix of comparisons.
+ */
+ diff_free_filespec_blob(one);
+ diff_free_filespec_blob(two);
+ }
+ }
+
+ strintmap_clear(&sources);
+ strintmap_clear(&dests);
+
+ return renames;
+}
+
#define NUM_CANDIDATE_PER_DST 4
static void record_if_better(struct diff_score m[], struct diff_score *o)
{
return 1;
}
-static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, int copies)
+static int find_renames(struct diff_score *mx,
+ int dst_cnt,
+ int minimum_score,
+ int copies,
+ struct dir_rename_info *info,
+ struct strset *dirs_removed)
{
int count = 0, i;
continue;
record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
count++;
+ update_dir_rename_counts(info, dirs_removed,
+ rename_src[mx[i].src].p->one->path,
+ rename_dst[mx[i].dst].p->two->path);
}
return count;
}
-void diffcore_rename(struct diff_options *options)
+static void remove_unneeded_paths_from_src(int detecting_copies)
+{
+ int i, new_num_src;
+
+ if (detecting_copies)
+ return; /* nothing to remove */
+ if (break_idx)
+ return; /* culling incompatible with break detection */
+
+ /*
+ * Note on reasons why we cull unneeded sources but not destinations:
+ * 1) Pairings are stored in rename_dst (not rename_src), which we
+ * need to keep around. So, we just can't cull rename_dst even
+ * if we wanted to. But doing so wouldn't help because...
+ *
+ * 2) There is a matrix pairwise comparison that follows the
+ * "Performing inexact rename detection" progress message.
+ * Iterating over the destinations is done in the outer loop,
+ * hence we only iterate over each of those once and we can
+ * easily skip the outer loop early if the destination isn't
+ * relevant. That's only one check per destination path to
+ * skip.
+ *
+ * By contrast, the sources are iterated in the inner loop; if
+ * we check whether a source can be skipped, then we'll be
+ * checking it N separate times, once for each destination.
+ * We don't want to have to iterate over known-not-needed
+ * sources N times each, so avoid that by removing the sources
+ * from rename_src here.
+ */
+ for (i = 0, new_num_src = 0; i < rename_src_nr; i++) {
+ /*
+ * renames are stored in rename_dst, so if a rename has
+ * already been detected using this source, we can just
+ * remove the source knowing rename_dst has its info.
+ */
+ if (rename_src[i].p->one->rename_used)
+ continue;
+
+ if (new_num_src < i)
+ memcpy(&rename_src[new_num_src], &rename_src[i],
+ sizeof(struct diff_rename_src));
+ new_num_src++;
+ }
+
+ rename_src_nr = new_num_src;
+}
+
+void diffcore_rename_extended(struct diff_options *options,
+ struct strset *dirs_removed,
+ struct strmap *dir_rename_count)
{
int detect_rename = options->detect_rename;
int minimum_score = options->rename_score;
struct diff_score *mx;
int i, j, rename_count, skip_unmodified = 0;
int num_destinations, dst_cnt;
+ int num_sources, want_copies;
struct progress *progress = NULL;
+ struct dir_rename_info info;
trace2_region_enter("diff", "setup", options->repo);
+ info.setup = 0;
+ assert(!dir_rename_count || strmap_empty(dir_rename_count));
+ want_copies = (detect_rename == DIFF_DETECT_COPY);
+ if (dirs_removed && (break_idx || want_copies))
+ BUG("dirs_removed incompatible with break/copy detection");
if (!minimum_score)
minimum_score = DEFAULT_RENAME_SCORE;
p->one->rename_used++;
register_rename_src(p);
}
- else if (detect_rename == DIFF_DETECT_COPY) {
+ else if (want_copies) {
/*
* Increment the "rename_used" score by
* one, to indicate ourselves as a user.
if (minimum_score == MAX_SCORE)
goto cleanup;
- /*
- * Calculate how many renames are left (but all the source
- * files still remain as options for rename/copies!)
- */
+ num_sources = rename_src_nr;
+
+ if (want_copies || break_idx) {
+ /*
+ * Cull sources:
+ * - remove ones corresponding to exact renames
+ */
+ trace2_region_enter("diff", "cull after exact", options->repo);
+ remove_unneeded_paths_from_src(want_copies);
+ trace2_region_leave("diff", "cull after exact", options->repo);
+ } else {
+ /* Determine minimum score to match basenames */
+ double factor = 0.5;
+ char *basename_factor = getenv("GIT_BASENAME_FACTOR");
+ int min_basename_score;
+
+ if (basename_factor)
+ factor = strtol(basename_factor, NULL, 10)/100.0;
+ assert(factor >= 0.0 && factor <= 1.0);
+ min_basename_score = minimum_score +
+ (int)(factor * (MAX_SCORE - minimum_score));
+
+ /*
+ * Cull sources:
+ * - remove ones involved in renames (found via exact match)
+ */
+ trace2_region_enter("diff", "cull after exact", options->repo);
+ remove_unneeded_paths_from_src(want_copies);
+ trace2_region_leave("diff", "cull after exact", options->repo);
+
+ /* Preparation for basename-driven matching. */
+ trace2_region_enter("diff", "dir rename setup", options->repo);
+ initialize_dir_rename_info(&info,
+ dirs_removed, dir_rename_count);
+ trace2_region_leave("diff", "dir rename setup", options->repo);
+
+ /* Utilize file basenames to quickly find renames. */
+ trace2_region_enter("diff", "basename matches", options->repo);
+ rename_count += find_basename_matches(options,
+ min_basename_score,
+ &info, dirs_removed);
+ trace2_region_leave("diff", "basename matches", options->repo);
+
+ /*
+ * Cull sources, again:
+ * - remove ones involved in renames (found via basenames)
+ */
+ trace2_region_enter("diff", "cull basename", options->repo);
+ remove_unneeded_paths_from_src(want_copies);
+ trace2_region_leave("diff", "cull basename", options->repo);
+ }
+
+ /* Calculate how many rename destinations are left */
num_destinations = (rename_dst_nr - rename_count);
+ num_sources = rename_src_nr; /* rename_src_nr reflects lower number */
/* All done? */
- if (!num_destinations)
+ if (!num_destinations || !num_sources)
goto cleanup;
- switch (too_many_rename_candidates(num_destinations, rename_src_nr,
+ switch (too_many_rename_candidates(num_destinations, num_sources,
options)) {
case 1:
goto cleanup;
if (options->show_rename_progress) {
progress = start_delayed_progress(
_("Performing inexact rename detection"),
- (uint64_t)num_destinations * (uint64_t)rename_src_nr);
+ (uint64_t)num_destinations * (uint64_t)num_sources);
}
- mx = xcalloc(st_mult(NUM_CANDIDATE_PER_DST, num_destinations),
- sizeof(*mx));
+ CALLOC_ARRAY(mx, st_mult(NUM_CANDIDATE_PER_DST, num_destinations));
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
struct diff_filespec *two = rename_dst[i].p->two;
struct diff_score *m;
if (rename_dst[i].is_rename)
- continue; /* dealt with exact match already. */
+ continue; /* exact or basename match already handled */
m = &mx[dst_cnt * NUM_CANDIDATE_PER_DST];
for (j = 0; j < NUM_CANDIDATE_PER_DST; j++)
struct diff_filespec *one = rename_src[j].p->one;
struct diff_score this_src;
+ assert(!one->rename_used || want_copies || break_idx);
+
if (skip_unmodified &&
diff_unmodified_pair(rename_src[j].p))
continue;
}
dst_cnt++;
display_progress(progress,
- (uint64_t)dst_cnt * (uint64_t)rename_src_nr);
+ (uint64_t)dst_cnt * (uint64_t)num_sources);
}
stop_progress(&progress);
/* cost matrix sorted by most to least similar pair */
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)
- rename_count += find_renames(mx, dst_cnt, minimum_score, 1);
+ rename_count += find_renames(mx, dst_cnt, minimum_score, 0,
+ &info, dirs_removed);
+ if (want_copies)
+ rename_count += find_renames(mx, dst_cnt, minimum_score, 1,
+ &info, dirs_removed);
free(mx);
trace2_region_leave("diff", "inexact renames", options->repo);
if (rename_dst[i].filespec_to_free)
free_filespec(rename_dst[i].filespec_to_free);
+ cleanup_dir_rename_info(&info, dirs_removed, dir_rename_count != NULL);
FREE_AND_NULL(rename_dst);
rename_dst_nr = rename_dst_alloc = 0;
FREE_AND_NULL(rename_src);
trace2_region_leave("diff", "write back to queue", options->repo);
return;
}
+
+void diffcore_rename(struct diff_options *options)
+{
+ diffcore_rename_extended(options, NULL, NULL);
+}