diff options
author | Junio C Hamano <gitster@pobox.com> | 2021-01-21 09:52:50 +0300 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2021-01-21 09:52:50 +0300 |
commit | fe2f4d0031efea524163d63888c010fc6a8201e1 (patch) | |
tree | c314369e73e8d5a436cbd5d6b0fc9c03049e0026 /merge-ort.c | |
parent | 12aa5552a998c57cca471f82002d9f4ec03f5b83 (diff) | |
parent | 203c872c4f29e08867d572eca4f18cd1f39f9e4b (diff) |
Merge branch 'en/ort-directory-rename' into en/merge-ort-perf
* en/ort-directory-rename: (28 commits)
merge-ort: fix a directory rename detection bug
merge-ort: process_renames() now needs more defensiveness
merge-ort: implement apply_directory_rename_modifications()
merge-ort: add a new toplevel_dir field
merge-ort: implement handle_path_level_conflicts()
merge-ort: implement check_for_directory_rename()
merge-ort: implement apply_dir_rename() and check_dir_renamed()
merge-ort: implement compute_collisions()
merge-ort: modify collect_renames() for directory rename handling
merge-ort: implement handle_directory_level_conflicts()
merge-ort: implement compute_rename_counts()
merge-ort: copy get_renamed_dir_portion() from merge-recursive.c
merge-ort: add outline of get_provisional_directory_renames()
merge-ort: add outline for computing directory renames
merge-ort: collect which directories are removed in dirs_removed
merge-ort: initialize and free new directory rename data structures
merge-ort: add new data structures for directory rename detection
merge-ort: add implementation of type-changed rename handling
merge-ort: add implementation of normal rename handling
merge-ort: add implementation of rename collisions
...
Diffstat (limited to 'merge-ort.c')
-rw-r--r-- | merge-ort.c | 1250 |
1 files changed, 1228 insertions, 22 deletions
diff --git a/merge-ort.c b/merge-ort.c index ffe8a8c7e8..05c6b2e0dc 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -51,6 +51,53 @@ enum merge_side { MERGE_SIDE2 = 2 }; +struct rename_info { + /* + * All variables that are arrays of size 3 correspond to data tracked + * for the sides in enum merge_side. Index 0 is almost always unused + * because we often only need to track information for MERGE_SIDE1 and + * MERGE_SIDE2 (MERGE_BASE can't have rename information since renames + * are determined relative to what changed since the MERGE_BASE). + */ + + /* + * pairs: pairing of filenames from diffcore_rename() + */ + struct diff_queue_struct pairs[3]; + + /* + * dirs_removed: directories removed on a given side of history. + */ + struct strset dirs_removed[3]; + + /* + * dir_rename_count: tracking where parts of a directory were renamed to + * + * When files in a directory are renamed, they may not all go to the + * same location. Each strmap here tracks: + * old_dir => {new_dir => int} + * That is, dir_rename_count[side] is a strmap to a strintmap. + */ + struct strmap dir_rename_count[3]; + + /* + * dir_renames: computed directory renames + * + * This is a map of old_dir => new_dir and is derived in part from + * dir_rename_count. + */ + struct strmap dir_renames[3]; + + /* + * needed_limit: value needed for inexact rename detection to run + * + * If the current rename limit wasn't high enough for inexact + * rename detection to run, this records the limit needed. Otherwise, + * this value remains 0. + */ + int needed_limit; +}; + struct merge_options_internal { /* * paths: primary data structure in all of merge ort. @@ -119,12 +166,20 @@ struct merge_options_internal { struct strmap output; /* - * current_dir_name: temporary var used in collect_merge_info_callback() + * renames: various data relating to rename detection + */ + struct rename_info renames; + + /* + * current_dir_name, toplevel_dir: temporary vars * - * Used to set merged_info.directory_name; see documentation for that - * variable and the requirements placed on that field. + * These are used in collect_merge_info_callback(), and will set the + * various merged_info.directory_name for the various paths we get; + * see documentation for that variable and the requirements placed on + * that field. */ const char *current_dir_name; + const char *toplevel_dir; /* call_depth: recursion level counter for merging merge bases */ int call_depth; @@ -259,8 +314,12 @@ static void free_strmap_strings(struct strmap *map) static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, int reinitialize) { + struct rename_info *renames = &opti->renames; + int i; void (*strmap_func)(struct strmap *, int) = reinitialize ? strmap_partial_clear : strmap_clear; + void (*strset_func)(struct strset *) = + reinitialize ? strset_partial_clear : strset_clear; /* * We marked opti->paths with strdup_strings = 0, so that we @@ -290,6 +349,23 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti, string_list_clear(&opti->paths_to_free, 0); opti->paths_to_free.strdup_strings = 0; + /* Free memory used by various renames maps */ + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) { + struct hashmap_iter iter; + struct strmap_entry *entry; + + strset_func(&renames->dirs_removed[i]); + + strmap_for_each_entry(&renames->dir_rename_count[i], + &iter, entry) { + struct strintmap *counts = entry->value; + strintmap_clear(counts); + } + strmap_func(&renames->dir_rename_count[i], 1); + + strmap_func(&renames->dir_renames[i], 0); + } + if (!reinitialize) { struct hashmap_iter iter; struct strmap_entry *e; @@ -459,6 +535,27 @@ static void setup_path_info(struct merge_options *opt, result->util = mi; } +static void collect_rename_info(struct merge_options *opt, + struct name_entry *names, + const char *dirname, + const char *fullname, + unsigned filemask, + unsigned dirmask, + unsigned match_mask) +{ + struct rename_info *renames = &opt->priv->renames; + + /* Update dirs_removed, as needed */ + if (dirmask == 1 || dirmask == 3 || dirmask == 5) { + /* absent_mask = 0x07 - dirmask; sides = absent_mask/2 */ + unsigned sides = (0x07 - dirmask)/2; + if (sides & 1) + strset_add(&renames->dirs_removed[1], fullname); + if (sides & 2) + strset_add(&renames->dirs_removed[2], fullname); + } +} + static int collect_merge_info_callback(int n, unsigned long mask, unsigned long dirmask, @@ -560,6 +657,12 @@ static int collect_merge_info_callback(int n, } /* + * Gather additional information used in rename detection. + */ + collect_rename_info(opt, names, dirname, fullpath, + filemask, dirmask, match_mask); + + /* * Record information about the path so we can resolve later in * process_entries. */ @@ -634,10 +737,10 @@ static int collect_merge_info(struct merge_options *opt, int ret; struct tree_desc t[3]; struct traverse_info info; - const char *toplevel_dir_placeholder = ""; - opt->priv->current_dir_name = toplevel_dir_placeholder; - setup_traverse_info(&info, toplevel_dir_placeholder); + opt->priv->toplevel_dir = ""; + opt->priv->current_dir_name = opt->priv->toplevel_dir; + setup_traverse_info(&info, opt->priv->toplevel_dir); info.fn = collect_merge_info_callback; info.data = opt; info.show_all_errors = 1; @@ -1039,22 +1142,1098 @@ static int handle_content_merge(struct merge_options *opt, /*** Function Grouping: functions related to directory rename detection ***/ +struct collision_info { + struct string_list source_files; + unsigned reported_already:1; +}; + +/* + * Return a new string that replaces the beginning portion (which matches + * rename_info->key), with rename_info->util.new_dir. In perl-speak: + * new_path_name = (old_path =~ s/rename_info->key/rename_info->value/); + * NOTE: + * Caller must ensure that old_path starts with rename_info->key + '/'. + */ +static char *apply_dir_rename(struct strmap_entry *rename_info, + const char *old_path) +{ + struct strbuf new_path = STRBUF_INIT; + const char *old_dir = rename_info->key; + const char *new_dir = rename_info->value; + int oldlen, newlen, new_dir_len; + + oldlen = strlen(old_dir); + if (*new_dir == '\0') + /* + * If someone renamed/merged a subdirectory into the root + * directory (e.g. 'some/subdir' -> ''), then we want to + * avoid returning + * '' + '/filename' + * as the rename; we need to make old_path + oldlen advance + * past the '/' character. + */ + oldlen++; + new_dir_len = strlen(new_dir); + newlen = new_dir_len + (strlen(old_path) - oldlen) + 1; + strbuf_grow(&new_path, newlen); + strbuf_add(&new_path, new_dir, new_dir_len); + strbuf_addstr(&new_path, &old_path[oldlen]); + + return strbuf_detach(&new_path, NULL); +} + +static int path_in_way(struct strmap *paths, const char *path, unsigned side_mask) +{ + struct merged_info *mi = strmap_get(paths, path); + struct conflict_info *ci; + if (!mi) + return 0; + INITIALIZE_CI(ci, mi); + return mi->clean || (side_mask & (ci->filemask | ci->dirmask)); +} + +/* + * See if there is a directory rename for path, and if there are any file + * level conflicts on the given side for the renamed location. If there is + * a rename and there are no conflicts, return the new name. Otherwise, + * return NULL. + */ +static char *handle_path_level_conflicts(struct merge_options *opt, + const char *path, + unsigned side_index, + struct strmap_entry *rename_info, + struct strmap *collisions) +{ + char *new_path = NULL; + struct collision_info *c_info; + int clean = 1; + struct strbuf collision_paths = STRBUF_INIT; + + /* + * entry has the mapping of old directory name to new directory name + * that we want to apply to path. + */ + new_path = apply_dir_rename(rename_info, path); + if (!new_path) + BUG("Failed to apply directory rename!"); + + /* + * The caller needs to have ensured that it has pre-populated + * collisions with all paths that map to new_path. Do a quick check + * to ensure that's the case. + */ + c_info = strmap_get(collisions, new_path); + if (c_info == NULL) + BUG("c_info is NULL"); + + /* + * Check for one-sided add/add/.../add conflicts, i.e. + * where implicit renames from the other side doing + * directory rename(s) can affect this side of history + * to put multiple paths into the same location. Warn + * and bail on directory renames for such paths. + */ + if (c_info->reported_already) { + clean = 0; + } else if (path_in_way(&opt->priv->paths, new_path, 1 << side_index)) { + c_info->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &c_info->source_files); + path_msg(opt, new_path, 0, + _("CONFLICT (implicit dir rename): Existing file/dir " + "at %s in the way of implicit directory rename(s) " + "putting the following path(s) there: %s."), + new_path, collision_paths.buf); + clean = 0; + } else if (c_info->source_files.nr > 1) { + c_info->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &c_info->source_files); + path_msg(opt, new_path, 0, + _("CONFLICT (implicit dir rename): Cannot map more " + "than one path to %s; implicit directory renames " + "tried to put these paths there: %s"), + new_path, collision_paths.buf); + clean = 0; + } + + /* Free memory we no longer need */ + strbuf_release(&collision_paths); + if (!clean && new_path) { + free(new_path); + return NULL; + } + + return new_path; +} + +static void dirname_munge(char *filename) +{ + char *slash = strrchr(filename, '/'); + if (!slash) + slash = filename; + *slash = '\0'; +} + +static void increment_count(struct strmap *dir_rename_count, + 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(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(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 strmap *dir_rename_count, + 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; + + while (1) { + dirname_munge(old_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(dir_rename_count, 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 compute_rename_counts(struct diff_queue_struct *pairs, + struct strmap *dir_rename_count, + struct strset *dirs_removed) +{ + int i; + + for (i = 0; i < pairs->nr; ++i) { + struct diff_filepair *pair = pairs->queue[i]; + + /* File not part of directory rename if it wasn't renamed */ + if (pair->status != 'R') + continue; + + /* + * 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(dir_rename_count, dirs_removed, + pair->one->path, + pair->two->path); + } +} + +static void get_provisional_directory_renames(struct merge_options *opt, + unsigned side, + int *clean) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + struct rename_info *renames = &opt->priv->renames; + + compute_rename_counts(&renames->pairs[side], + &renames->dir_rename_count[side], + &renames->dirs_removed[side]); + /* + * Collapse + * dir_rename_count: old_directory -> {new_directory -> count} + * down to + * dir_renames: old_directory -> best_new_directory + * where best_new_directory is the one with the unique highest count. + */ + strmap_for_each_entry(&renames->dir_rename_count[side], &iter, entry) { + const char *source_dir = entry->key; + struct strintmap *counts = entry->value; + struct hashmap_iter count_iter; + struct strmap_entry *count_entry; + int max = 0; + int bad_max = 0; + const char *best = NULL; + + strintmap_for_each_entry(counts, &count_iter, count_entry) { + const char *target_dir = count_entry->key; + intptr_t count = (intptr_t)count_entry->value; + + if (count == max) + bad_max = max; + else if (count > max) { + max = count; + best = target_dir; + } + } + + if (bad_max == max) { + path_msg(opt, source_dir, 0, + _("CONFLICT (directory rename split): " + "Unclear where to rename %s to; it was " + "renamed to multiple other directories, with " + "no destination getting a majority of the " + "files."), + source_dir); + *clean = 0; + } else { + strmap_put(&renames->dir_renames[side], + source_dir, (void*)best); + } + } +} + +static void handle_directory_level_conflicts(struct merge_options *opt) +{ + struct hashmap_iter iter; + struct strmap_entry *entry; + struct string_list duplicated = STRING_LIST_INIT_NODUP; + struct rename_info *renames = &opt->priv->renames; + struct strmap *side1_dir_renames = &renames->dir_renames[MERGE_SIDE1]; + struct strmap *side2_dir_renames = &renames->dir_renames[MERGE_SIDE2]; + int i; + + strmap_for_each_entry(side1_dir_renames, &iter, entry) { + if (strmap_contains(side2_dir_renames, entry->key)) + string_list_append(&duplicated, entry->key); + } + + for (i = 0; i < duplicated.nr; i++) { + strmap_remove(side1_dir_renames, duplicated.items[i].string, 0); + strmap_remove(side2_dir_renames, duplicated.items[i].string, 0); + } + string_list_clear(&duplicated, 0); +} + +static struct strmap_entry *check_dir_renamed(const char *path, + struct strmap *dir_renames) +{ + char *temp = xstrdup(path); + char *end; + struct strmap_entry *e = NULL; + + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + e = strmap_get_entry(dir_renames, temp); + if (e) + break; + } + free(temp); + return e; +} + +static void compute_collisions(struct strmap *collisions, + struct strmap *dir_renames, + struct diff_queue_struct *pairs) +{ + int i; + + strmap_init_with_options(collisions, NULL, 0); + if (strmap_empty(dir_renames)) + return; + + /* + * Multiple files can be mapped to the same path due to directory + * renames done by the other side of history. Since that other + * side of history could have merged multiple directories into one, + * if our side of history added the same file basename to each of + * those directories, then all N of them would get implicitly + * renamed by the directory rename detection into the same path, + * and we'd get an add/add/.../add conflict, and all those adds + * from *this* side of history. This is not representable in the + * index, and users aren't going to easily be able to make sense of + * it. So we need to provide a good warning about what's + * happening, and fall back to no-directory-rename detection + * behavior for those paths. + * + * See testcases 9e and all of section 5 from t6043 for examples. + */ + for (i = 0; i < pairs->nr; ++i) { + struct strmap_entry *rename_info; + struct collision_info *collision_info; + char *new_path; + struct diff_filepair *pair = pairs->queue[i]; + + if (pair->status != 'A' && pair->status != 'R') + continue; + rename_info = check_dir_renamed(pair->two->path, dir_renames); + if (!rename_info) + continue; + + new_path = apply_dir_rename(rename_info, pair->two->path); + assert(new_path); + collision_info = strmap_get(collisions, new_path); + if (collision_info) { + free(new_path); + } else { + collision_info = xcalloc(1, + sizeof(struct collision_info)); + string_list_init(&collision_info->source_files, 0); + strmap_put(collisions, new_path, collision_info); + } + string_list_insert(&collision_info->source_files, + pair->two->path); + } +} + +static char *check_for_directory_rename(struct merge_options *opt, + const char *path, + unsigned side_index, + struct strmap *dir_renames, + struct strmap *dir_rename_exclusions, + struct strmap *collisions, + int *clean_merge) +{ + char *new_path = NULL; + struct strmap_entry *rename_info; + struct strmap_entry *otherinfo = NULL; + const char *new_dir; + + if (strmap_empty(dir_renames)) + return new_path; + rename_info = check_dir_renamed(path, dir_renames); + if (!rename_info) + return new_path; + /* old_dir = rename_info->key; */ + new_dir = rename_info->value; + + /* + * This next part is a little weird. We do not want to do an + * implicit rename into a directory we renamed on our side, because + * that will result in a spurious rename/rename(1to2) conflict. An + * example: + * Base commit: dumbdir/afile, otherdir/bfile + * Side 1: smrtdir/afile, otherdir/bfile + * Side 2: dumbdir/afile, dumbdir/bfile + * Here, while working on Side 1, we could notice that otherdir was + * renamed/merged to dumbdir, and change the diff_filepair for + * otherdir/bfile into a rename into dumbdir/bfile. However, Side + * 2 will notice the rename from dumbdir to smrtdir, and do the + * transitive rename to move it from dumbdir/bfile to + * smrtdir/bfile. That gives us bfile in dumbdir vs being in + * smrtdir, a rename/rename(1to2) conflict. We really just want + * the file to end up in smrtdir. And the way to achieve that is + * to not let Side1 do the rename to dumbdir, since we know that is + * the source of one of our directory renames. + * + * That's why otherinfo and dir_rename_exclusions is here. + * + * As it turns out, this also prevents N-way transient rename + * confusion; See testcases 9c and 9d of t6043. + */ + otherinfo = strmap_get_entry(dir_rename_exclusions, new_dir); + if (otherinfo) { + path_msg(opt, rename_info->key, 1, + _("WARNING: Avoiding applying %s -> %s rename " + "to %s, because %s itself was renamed."), + rename_info->key, new_dir, path, new_dir); + return NULL; + } + + new_path = handle_path_level_conflicts(opt, path, side_index, + rename_info, collisions); + *clean_merge &= (new_path != NULL); + + return new_path; +} + +static void apply_directory_rename_modifications(struct merge_options *opt, + struct diff_filepair *pair, + char *new_path) +{ + /* + * The basic idea is to get the conflict_info from opt->priv->paths + * at old path, and insert it into new_path; basically just this: + * ci = strmap_get(&opt->priv->paths, old_path); + * strmap_remove(&opt->priv->paths, old_path, 0); + * strmap_put(&opt->priv->paths, new_path, ci); + * However, there are some factors complicating this: + * - opt->priv->paths may already have an entry at new_path + * - Each ci tracks its containing directory, so we need to + * update that + * - If another ci has the same containing directory, then + * the two char*'s MUST point to the same location. See the + * comment in struct merged_info. strcmp equality is not + * enough; we need pointer equality. + * - opt->priv->paths must hold the parent directories of any + * entries that are added. So, if this directory rename + * causes entirely new directories, we must recursively add + * parent directories. + * - For each parent directory added to opt->priv->paths, we + * also need to get its parent directory stored in its + * conflict_info->merged.directory_name with all the same + * requirements about pointer equality. + */ + struct string_list dirs_to_insert = STRING_LIST_INIT_NODUP; + struct conflict_info *ci, *new_ci; + struct strmap_entry *entry; + const char *branch_with_new_path, *branch_with_dir_rename; + const char *old_path = pair->two->path; + const char *parent_name; + const char *cur_path; + int i, len; + + entry = strmap_get_entry(&opt->priv->paths, old_path); + old_path = entry->key; + ci = entry->value; + VERIFY_CI(ci); + + /* Find parent directories missing from opt->priv->paths */ + cur_path = new_path; + while (1) { + /* Find the parent directory of cur_path */ + char *last_slash = strrchr(cur_path, '/'); + if (last_slash) { + parent_name = xstrndup(cur_path, last_slash - cur_path); + } else { + parent_name = opt->priv->toplevel_dir; + break; + } + + /* Look it up in opt->priv->paths */ + entry = strmap_get_entry(&opt->priv->paths, parent_name); + if (entry) { + free((char*)parent_name); + parent_name = entry->key; /* reuse known pointer */ + break; + } + + /* Record this is one of the directories we need to insert */ + string_list_append(&dirs_to_insert, parent_name); + cur_path = parent_name; + } + + /* Traverse dirs_to_insert and insert them into opt->priv->paths */ + for (i = dirs_to_insert.nr-1; i >= 0; --i) { + struct conflict_info *dir_ci; + char *cur_dir = dirs_to_insert.items[i].string; + + dir_ci = xcalloc(1, sizeof(*dir_ci)); + + dir_ci->merged.directory_name = parent_name; + len = strlen(parent_name); + /* len+1 because of trailing '/' character */ + dir_ci->merged.basename_offset = (len > 0 ? len+1 : len); + dir_ci->dirmask = ci->filemask; + strmap_put(&opt->priv->paths, cur_dir, dir_ci); + + parent_name = cur_dir; + } + + /* + * We are removing old_path from opt->priv->paths. old_path also will + * eventually need to be freed, but it may still be used by e.g. + * ci->pathnames. So, store it in another string-list for now. + */ + string_list_append(&opt->priv->paths_to_free, old_path); + + assert(ci->filemask == 2 || ci->filemask == 4); + assert(ci->dirmask == 0); + strmap_remove(&opt->priv->paths, old_path, 0); + + branch_with_new_path = (ci->filemask == 2) ? opt->branch1 : opt->branch2; + branch_with_dir_rename = (ci->filemask == 2) ? opt->branch2 : opt->branch1; + + /* Now, finally update ci and stick it into opt->priv->paths */ + ci->merged.directory_name = parent_name; + len = strlen(parent_name); + ci->merged.basename_offset = (len > 0 ? len+1 : len); + new_ci = strmap_get(&opt->priv->paths, new_path); + if (!new_ci) { + /* Place ci back into opt->priv->paths, but at new_path */ + strmap_put(&opt->priv->paths, new_path, ci); + } else { + int index; + + /* A few sanity checks */ + VERIFY_CI(new_ci); + assert(ci->filemask == 2 || ci->filemask == 4); + assert((new_ci->filemask & ci->filemask) == 0); + assert(!new_ci->merged.clean); + + /* Copy stuff from ci into new_ci */ + new_ci->filemask |= ci->filemask; + if (new_ci->dirmask) + new_ci->df_conflict = 1; + index = (ci->filemask >> 1); + new_ci->pathnames[index] = ci->pathnames[index]; + new_ci->stages[index].mode = ci->stages[index].mode; + oidcpy(&new_ci->stages[index].oid, &ci->stages[index].oid); + + free(ci); + ci = new_ci; + } + + if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE) { + /* Notify user of updated path */ + if (pair->status == 'A') + path_msg(opt, new_path, 1, + _("Path updated: %s added in %s inside a " + "directory that was renamed in %s; moving " + "it to %s."), + old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + else + path_msg(opt, new_path, 1, + _("Path updated: %s renamed to %s in %s, " + "inside a directory that was renamed in %s; " + "moving it to %s."), + pair->one->path, old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + } else { + /* + * opt->detect_directory_renames has the value + * MERGE_DIRECTORY_RENAMES_CONFLICT, so mark these as conflicts. + */ + ci->path_conflict = 1; + if (pair->status == 'A') + path_msg(opt, new_path, 0, + _("CONFLICT (file location): %s added in %s " + "inside a directory that was renamed in %s, " + "suggesting it should perhaps be moved to " + "%s."), + old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + else + path_msg(opt, new_path, 0, + _("CONFLICT (file location): %s renamed to %s " + "in %s, inside a directory that was renamed " + "in %s, suggesting it should perhaps be " + "moved to %s."), + pair->one->path, old_path, branch_with_new_path, + branch_with_dir_rename, new_path); + } + + /* + * Finally, record the new location. + */ + pair->two->path = new_path; +} + /*** Function Grouping: functions related to regular rename detection ***/ +static int process_renames(struct merge_options *opt, + struct diff_queue_struct *renames) +{ + int clean_merge = 1, i; + + for (i = 0; i < renames->nr; ++i) { + const char *oldpath = NULL, *newpath; + struct diff_filepair *pair = renames->queue[i]; + struct conflict_info *oldinfo = NULL, *newinfo = NULL; + struct strmap_entry *old_ent, *new_ent; + unsigned int old_sidemask; + int target_index, other_source_index; + int source_deleted, collision, type_changed; + const char *rename_branch = NULL, *delete_branch = NULL; + + old_ent = strmap_get_entry(&opt->priv->paths, pair->one->path); + new_ent = strmap_get_entry(&opt->priv->paths, pair->two->path); + if (old_ent) { + oldpath = old_ent->key; + oldinfo = old_ent->value; + } + newpath = pair->two->path; + if (new_ent) { + newpath = new_ent->key; + newinfo = new_ent->value; + } + + /* + * If pair->one->path isn't in opt->priv->paths, that means + * that either directory rename detection removed that + * path, or a parent directory of oldpath was resolved and + * we don't even need the rename; in either case, we can + * skip it. If oldinfo->merged.clean, then the other side + * of history had no changes to oldpath and we don't need + * the rename and can skip it. + */ + if (!oldinfo || oldinfo->merged.clean) + continue; + + /* + * diff_filepairs have copies of pathnames, thus we have to + * use standard 'strcmp()' (negated) instead of '=='. + */ + if (i + 1 < renames->nr && + !strcmp(oldpath, renames->queue[i+1]->one->path)) { + /* Handle rename/rename(1to2) or rename/rename(1to1) */ + const char *pathnames[3]; + struct version_info merged; + struct conflict_info *base, *side1, *side2; + unsigned was_binary_blob = 0; + + pathnames[0] = oldpath; + pathnames[1] = newpath; + pathnames[2] = renames->queue[i+1]->two->path; + + base = strmap_get(&opt->priv->paths, pathnames[0]); + side1 = strmap_get(&opt->priv->paths, pathnames[1]); + side2 = strmap_get(&opt->priv->paths, pathnames[2]); + + VERIFY_CI(base); + VERIFY_CI(side1); + VERIFY_CI(side2); + + if (!strcmp(pathnames[1], pathnames[2])) { + /* Both sides renamed the same way */ + assert(side1 == side2); + memcpy(&side1->stages[0], &base->stages[0], + sizeof(merged)); + side1->filemask |= (1 << MERGE_BASE); + /* Mark base as resolved by removal */ + base->merged.is_null = 1; + base->merged.clean = 1; + + /* We handled both renames, i.e. i+1 handled */ + i++; + /* Move to next rename */ + continue; + } + + /* This is a rename/rename(1to2) */ + clean_merge = handle_content_merge(opt, + pair->one->path, + &base->stages[0], + &side1->stages[1], + &side2->stages[2], + pathnames, + 1 + 2 * opt->priv->call_depth, + &merged); + if (!clean_merge && + merged.mode == side1->stages[1].mode && + oideq(&merged.oid, &side1->stages[1].oid)) + was_binary_blob = 1; + memcpy(&side1->stages[1], &merged, sizeof(merged)); + if (was_binary_blob) { + /* + * Getting here means we were attempting to + * merge a binary blob. + * + * Since we can't merge binaries, + * handle_content_merge() just takes one + * side. But we don't want to copy the + * contents of one side to both paths. We + * used the contents of side1 above for + * side1->stages, let's use the contents of + * side2 for side2->stages below. + */ + oidcpy(&merged.oid, &side2->stages[2].oid); + merged.mode = side2->stages[2].mode; + } + memcpy(&side2->stages[2], &merged, sizeof(merged)); + + side1->path_conflict = 1; + side2->path_conflict = 1; + /* + * TODO: For renames we normally remove the path at the + * old name. It would thus seem consistent to do the + * same for rename/rename(1to2) cases, but we haven't + * done so traditionally and a number of the regression + * tests now encode an expectation that the file is + * left there at stage 1. If we ever decide to change + * this, add the following two lines here: + * base->merged.is_null = 1; + * base->merged.clean = 1; + * and remove the setting of base->path_conflict to 1. + */ + base->path_conflict = 1; + path_msg(opt, oldpath, 0, + _("CONFLICT (rename/rename): %s renamed to " + "%s in %s and to %s in %s."), + pathnames[0], + pathnames[1], opt->branch1, + pathnames[2], opt->branch2); + + i++; /* We handled both renames, i.e. i+1 handled */ + continue; + } + + VERIFY_CI(oldinfo); + VERIFY_CI(newinfo); + target_index = pair->score; /* from collect_renames() */ + assert(target_index == 1 || target_index == 2); + other_source_index = 3 - target_index; + old_sidemask = (1 << other_source_index); /* 2 or 4 */ + source_deleted = (oldinfo->filemask == 1); + collision = ((newinfo->filemask & old_sidemask) != 0); + type_changed = !source_deleted && + (S_ISREG(oldinfo->stages[other_source_index].mode) != + S_ISREG(newinfo->stages[target_index].mode)); + if (type_changed && collision) { + /* + * special handling so later blocks can handle this... + * + * if type_changed && collision are both true, then this + * was really a double rename, but one side wasn't + * detected due to lack of break detection. I.e. + * something like + * orig: has normal file 'foo' + * side1: renames 'foo' to 'bar', adds 'foo' symlink + * side2: renames 'foo' to 'bar' + * In this case, the foo->bar rename on side1 won't be + * detected because the new symlink named 'foo' is + * there and we don't do break detection. But we detect + * this here because we don't want to merge the content + * of the foo symlink with the foo->bar file, so we + * have some logic to handle this special case. The + * easiest way to do that is make 'bar' on side1 not + * be considered a colliding file but the other part + * of a normal rename. If the file is very different, + * well we're going to get content merge conflicts + * anyway so it doesn't hurt. And if the colliding + * file also has a different type, that'll be handled + * by the content merge logic in process_entry() too. + * + * See also t6430, 'rename vs. rename/symlink' + */ + collision = 0; + } + if (source_deleted) { + if (target_index == 1) { + rename_branch = opt->branch1; + delete_branch = opt->branch2; + } else { + rename_branch = opt->branch2; + delete_branch = opt->branch1; + } + } + + assert(source_deleted || oldinfo->filemask & old_sidemask); + + /* Need to check for special types of rename conflicts... */ + if (collision && !source_deleted) { + /* collision: rename/add or rename/rename(2to1) */ + const char *pathnames[3]; + struct version_info merged; + + struct conflict_info *base, *side1, *side2; + unsigned clean; + + pathnames[0] = oldpath; + pathnames[other_source_index] = oldpath; + pathnames[target_index] = newpath; + + base = strmap_get(&opt->priv->paths, pathnames[0]); + side1 = strmap_get(&opt->priv->paths, pathnames[1]); + side2 = strmap_get(&opt->priv->paths, pathnames[2]); + + VERIFY_CI(base); + VERIFY_CI(side1); + VERIFY_CI(side2); + + clean = handle_content_merge(opt, pair->one->path, + &base->stages[0], + &side1->stages[1], + &side2->stages[2], + pathnames, + 1 + 2 * opt->priv->call_depth, + &merged); + + memcpy(&newinfo->stages[target_index], &merged, + sizeof(merged)); + if (!clean) { + path_msg(opt, newpath, 0, + _("CONFLICT (rename involved in " + "collision): rename of %s -> %s has " + "content conflicts AND collides " + "with another path; this may result " + "in nested conflict markers."), + oldpath, newpath); + } + } else if (collision && source_deleted) { + /* + * rename/add/delete or rename/rename(2to1)/delete: + * since oldpath was deleted on the side that didn't + * do the rename, there's not much of a content merge + * we can do for the rename. oldinfo->merged.is_null + * was already set, so we just leave things as-is so + * they look like an add/add conflict. + */ + + newinfo->path_conflict = 1; + path_msg(opt, newpath, 0, + _("CONFLICT (rename/delete): %s renamed " + "to %s in %s, but deleted in %s."), + oldpath, newpath, rename_branch, delete_branch); + } else { + /* + * a few different cases...start by copying the + * existing stage(s) from oldinfo over the newinfo + * and update the pathname(s). + */ + memcpy(&newinfo->stages[0], &oldinfo->stages[0], + sizeof(newinfo->stages[0])); + newinfo->filemask |= (1 << MERGE_BASE); + newinfo->pathnames[0] = oldpath; + if (type_changed) { + /* rename vs. typechange */ + /* Mark the original as resolved by removal */ + memcpy(&oldinfo->stages[0].oid, &null_oid, + sizeof(oldinfo->stages[0].oid)); + oldinfo->stages[0].mode = 0; + oldinfo->filemask &= 0x06; + } else if (source_deleted) { + /* rename/delete */ + newinfo->path_conflict = 1; + path_msg(opt, newpath, 0, + _("CONFLICT (rename/delete): %s renamed" + " to %s in %s, but deleted in %s."), + oldpath, newpath, + rename_branch, delete_branch); + } else { + /* normal rename */ + memcpy(&newinfo->stages[other_source_index], + &oldinfo->stages[other_source_index], + sizeof(newinfo->stages[0])); + newinfo->filemask |= (1 << other_source_index); + newinfo->pathnames[other_source_index] = oldpath; + } + } + + if (!type_changed) { + /* Mark the original as resolved by removal */ + oldinfo->merged.is_null = 1; + oldinfo->merged.clean = 1; + } + + } + + return clean_merge; +} + +static int compare_pairs(const void *a_, const void *b_) +{ + const struct diff_filepair *a = *((const struct diff_filepair **)a_); + const struct diff_filepair *b = *((const struct diff_filepair **)b_); + + return strcmp(a->one->path, b->one->path); +} + +/* Call diffcore_rename() to compute which files have changed on given side */ +static void detect_regular_renames(struct merge_options *opt, + struct tree *merge_base, + struct tree *side, + unsigned side_index) +{ + struct diff_options diff_opts; + struct rename_info *renames = &opt->priv->renames; + + repo_diff_setup(opt->repo, &diff_opts); + diff_opts.flags.recursive = 1; + diff_opts.flags.rename_empty = 0; + diff_opts.detect_rename = DIFF_DETECT_RENAME; + diff_opts.rename_limit = opt->rename_limit; + if (opt->rename_limit <= 0) + diff_opts.rename_limit = 1000; + diff_opts.rename_score = opt->rename_score; + diff_opts.show_rename_progress = opt->show_rename_progress; + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_setup_done(&diff_opts); + diff_tree_oid(&merge_base->object.oid, &side->object.oid, "", + &diff_opts); + diffcore_std(&diff_opts); + + if (diff_opts.needed_rename_limit > renames->needed_limit) + renames->needed_limit = diff_opts.needed_rename_limit; + + renames->pairs[side_index] = diff_queued_diff; + + diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_queued_diff.queue = NULL; + diff_flush(&diff_opts); +} + +/* + * Get information of all renames which occurred in 'side_pairs', discarding + * non-renames. + */ +static int collect_renames(struct merge_options *opt, + struct diff_queue_struct *result, + unsigned side_index, + struct strmap *dir_renames_for_side, + struct strmap *rename_exclusions) +{ + int i, clean = 1; + struct strmap collisions; + struct diff_queue_struct *side_pairs; + struct hashmap_iter iter; + struct strmap_entry *entry; + struct rename_info *renames = &opt->priv->renames; + + side_pairs = &renames->pairs[side_index]; + compute_collisions(&collisions, dir_renames_for_side, side_pairs); + + for (i = 0; i < side_pairs->nr; ++i) { + struct diff_filepair *p = side_pairs->queue[i]; + char *new_path; /* non-NULL only with directory renames */ + + if (p->status != 'A' && p->status != 'R') { + diff_free_filepair(p); + continue; + } + + new_path = check_for_directory_rename(opt, p->two->path, + side_index, + dir_renames_for_side, + rename_exclusions, + &collisions, + &clean); + + if (p->status != 'R' && !new_path) { + diff_free_filepair(p); + continue; + } + + if (new_path) + apply_directory_rename_modifications(opt, p, new_path); + + /* + * p->score comes back from diffcore_rename_extended() with + * the similarity of the renamed file. The similarity is + * was used to determine that the two files were related + * and are a rename, which we have already used, but beyond + * that we have no use for the similarity. So p->score is + * now irrelevant. However, process_renames() will need to + * know which side of the merge this rename was associated + * with, so overwrite p->score with that value. + */ + p->score = side_index; + result->queue[result->nr++] = p; + } + + /* Free each value in the collisions map */ + strmap_for_each_entry(&collisions, &iter, entry) { + struct collision_info *info = entry->value; + string_list_clear(&info->source_files, 0); + } + /* + * In compute_collisions(), we set collisions.strdup_strings to 0 + * so that we wouldn't have to make another copy of the new_path + * allocated by apply_dir_rename(). But now that we've used them + * and have no other references to these strings, it is time to + * deallocate them. + */ + free_strmap_strings(&collisions); + strmap_clear(&collisions, 1); + return clean; +} + static int detect_and_process_renames(struct merge_options *opt, struct tree *merge_base, struct tree *side1, struct tree *side2) { - int clean = 1; + struct diff_queue_struct combined; + struct rename_info *renames = &opt->priv->renames; + int need_dir_renames, s, clean = 1; + + memset(&combined, 0, sizeof(combined)); + + detect_regular_renames(opt, merge_base, side1, MERGE_SIDE1); + detect_regular_renames(opt, merge_base, side2, MERGE_SIDE2); + + need_dir_renames = + !opt->priv->call_depth && + (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE || + opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT); + + if (need_dir_renames) { + get_provisional_directory_renames(opt, MERGE_SIDE1, &clean); + get_provisional_directory_renames(opt, MERGE_SIDE2, &clean); + handle_directory_level_conflicts(opt); + } + + ALLOC_GROW(combined.queue, + renames->pairs[1].nr + renames->pairs[2].nr, + combined.alloc); + clean &= collect_renames(opt, &combined, MERGE_SIDE1, + &renames->dir_renames[2], + &renames->dir_renames[1]); + clean &= collect_renames(opt, &combined, MERGE_SIDE2, + &renames->dir_renames[1], + &renames->dir_renames[2]); + QSORT(combined.queue, combined.nr, compare_pairs); + + clean &= process_renames(opt, &combined); + + /* Free memory for renames->pairs[] and combined */ + for (s = MERGE_SIDE1; s <= MERGE_SIDE2; s++) { + free(renames->pairs[s].queue); + DIFF_QUEUE_CLEAR(&renames->pairs[s]); + } + if (combined.nr) { + int i; + for (i = 0; i < combined.nr; i++) + diff_free_filepair(combined.queue[i]); + free(combined.queue); + } - /* - * Rename detection works by detecting file similarity. Here we use - * a really easy-to-implement scheme: files are similar IFF they have - * the same filename. Therefore, by this scheme, there are no renames. - * - * TODO: Actually implement a real rename detection scheme. - */ return clean; } @@ -1673,24 +2852,33 @@ static void process_entry(struct merge_options *opt, modify_branch = (side == 1) ? opt->branch1 : opt->branch2; delete_branch = (side == 1) ? opt->branch2 : opt->branch1; - path_msg(opt, path, 0, - _("CONFLICT (modify/delete): %s deleted in %s " - "and modified in %s. Version %s of %s left " - "in tree."), - path, delete_branch, modify_branch, - modify_branch, path); + if (ci->path_conflict && + oideq(&ci->stages[0].oid, &ci->stages[side].oid)) { + /* + * This came from a rename/delete; no action to take, + * but avoid printing "modify/delete" conflict notice + * since the contents were not modified. + */ + } else { + path_msg(opt, path, 0, + _("CONFLICT (modify/delete): %s deleted in %s " + "and modified in %s. Version %s of %s left " + "in tree."), + path, delete_branch, modify_branch, + modify_branch, path); + } } else if (ci->filemask == 2 || ci->filemask == 4) { /* Added on one side */ int side = (ci->filemask == 4) ? 2 : 1; ci->merged.result.mode = ci->stages[side].mode; oidcpy(&ci->merged.result.oid, &ci->stages[side].oid); - ci->merged.clean = !ci->df_conflict; + ci->merged.clean = !ci->df_conflict && !ci->path_conflict; } else if (ci->filemask == 1) { /* Deleted on both sides */ ci->merged.is_null = 1; ci->merged.result.mode = 0; oidcpy(&ci->merged.result.oid, &null_oid); - ci->merged.clean = 1; + ci->merged.clean = !ci->path_conflict; } /* @@ -1968,6 +3156,10 @@ void merge_switch_to_result(struct merge_options *opt, printf("%s", sb->buf); } string_list_clear(&olist, 0); + + /* Also include needed rename limit adjustment now */ + diff_warn_rename_limit("merge.renamelimit", + opti->renames.needed_limit, 0); } merge_finalize(opt, result); @@ -2005,6 +3197,9 @@ static struct commit *make_virtual_commit(struct repository *repo, static void merge_start(struct merge_options *opt, struct merge_result *result) { + struct rename_info *renames; + int i; + /* Sanity checks on opt */ assert(opt->repo); @@ -2039,6 +3234,17 @@ static void merge_start(struct merge_options *opt, struct merge_result *result) /* Initialization of opt->priv, our internal merge data */ opt->priv = xcalloc(1, sizeof(*opt->priv)); + /* Initialization of various renames fields */ + renames = &opt->priv->renames; + for (i = MERGE_SIDE1; i <= MERGE_SIDE2; i++) { + strset_init_with_options(&renames->dirs_removed[i], + NULL, 0); + strmap_init_with_options(&renames->dir_rename_count[i], + NULL, 1); + strmap_init_with_options(&renames->dir_renames[i], + NULL, 0); + } + /* * Although we initialize opt->priv->paths with strdup_strings=0, * that's just to avoid making yet another copy of an allocated |