[v6,0/3] builtin/ls-files.c:add git ls-file --dedup option

Message

Linus Arver via GitGitGadget Jan. 23, 2021, 10:20 a.m. UTC

I am reading the source code of git ls-files and learned that git ls-files
may have duplicate files name when there are unmerged path in a branch merge
or when different options are used at the same time. Users may fell confuse
when they see these duplicate file names.

As Junio C Hamano said ,it have odd behaviour.

Therefore, we can provide an additional option to git ls-files to delete
those repeated information.

This fixes https://github.com/gitgitgadget/git/issues/198

Thanks!

ZheNing Hu (3):
  ls_files.c: bugfix for --deleted and --modified
  ls_files.c: consolidate two for loops into one
  ls-files.c: add --deduplicate option

 Documentation/git-ls-files.txt |  5 ++
 builtin/ls-files.c             | 85 ++++++++++++++++++++--------------
 t/t3012-ls-files-dedup.sh      | 66 ++++++++++++++++++++++++++
 3 files changed, 121 insertions(+), 35 deletions(-)
 create mode 100755 t/t3012-ls-files-dedup.sh


base-commit: 6d3ef5b467eccd2769f1aa1c555d317d3c8dc707
Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-832%2Fadlternative%2Fls-files-dedup-v6
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-832/adlternative/ls-files-dedup-v6
Pull-Request: https://github.com/gitgitgadget/git/pull/832

Range-diff vs v5:

 1:  ec9464f6094 ! 1:  fbc38ce9075 ls_files.c: bugfix for --deleted and --modified
     @@ Commit message
      
       ## builtin/ls-files.c ##
      @@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     + 		for (i = 0; i < repo->index->cache_nr; i++) {
     + 			const struct cache_entry *ce = repo->index->cache[i];
     + 			struct stat st;
     +-			int err;
     ++			int stat_err;
     + 
     + 			construct_fullname(&fullname, repo, ce);
     + 
     +@@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     + 				continue;
       			if (ce_skip_worktree(ce))
       				continue;
     - 			err = lstat(fullname.buf, &st);
     +-			err = lstat(fullname.buf, &st);
      -			if (show_deleted && err)
     --				show_ce(repo, dir, ce, fullname.buf, tag_removed);
     ++			stat_err = lstat(fullname.buf, &st);
     ++			if (stat_err && (errno != ENOENT && errno != ENOTDIR))
     ++				error_errno("cannot lstat '%s'", fullname.buf);
     ++			if (stat_err && show_deleted)
     + 				show_ce(repo, dir, ce, fullname.buf, tag_removed);
      -			if (show_modified && ie_modified(repo->index, ce, &st, 0))
     -+			if (err) {
     -+				if (errno != ENOENT && errno != ENOTDIR)
     -+				    error_errno("cannot lstat '%s'", fullname.buf);
     -+				if (show_deleted)
     -+					show_ce(repo, dir, ce, fullname.buf, tag_removed);
     -+				if (show_modified)
     +-				show_ce(repo, dir, ce, fullname.buf, tag_modified);
     ++			if (show_modified &&
     ++				(stat_err || ie_modified(repo->index, ce, &st, 0)))
      +					show_ce(repo, dir, ce, fullname.buf, tag_modified);
     -+			} else if (show_modified && ie_modified(repo->index, ce, &st, 0))
     - 				show_ce(repo, dir, ce, fullname.buf, tag_modified);
       		}
       	}
     + 
 2:  802ff802be8 ! 2:  3997d390883 ls_files.c: consolidate two for loops into one
     @@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_s
      -	if (show_cached || show_stage) {
      -		for (i = 0; i < repo->index->cache_nr; i++) {
      -			const struct cache_entry *ce = repo->index->cache[i];
     -+	if (! (show_cached || show_stage || show_deleted || show_modified))
     -+		return;
     -+	for (i = 0; i < repo->index->cache_nr; i++) {
     -+		const struct cache_entry *ce = repo->index->cache[i];
     -+		struct stat st;
     -+		int err;
     - 
     +-
      -			construct_fullname(&fullname, repo, ce);
     -+		construct_fullname(&fullname, repo, ce);
     - 
     +-
      -			if ((dir->flags & DIR_SHOW_IGNORED) &&
      -			    !ce_excluded(dir, repo->index, fullname.buf, ce))
      -				continue;
     @@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_s
      -				ce_stage(ce) ? tag_unmerged :
      -				(ce_skip_worktree(ce) ? tag_skip_worktree :
      -				 tag_cached));
     -+		if ((dir->flags & DIR_SHOW_IGNORED) &&
     -+			!ce_excluded(dir, repo->index, fullname.buf, ce))
     -+			continue;
     -+		if (ce->ce_flags & CE_UPDATE)
     -+			continue;
     -+		if (show_cached || show_stage) {
     -+			if (!show_unmerged || ce_stage(ce))
     -+				show_ce(repo, dir, ce, fullname.buf,
     -+					ce_stage(ce) ? tag_unmerged :
     -+					(ce_skip_worktree(ce) ? tag_skip_worktree :
     -+						tag_cached));
     - 		}
     +-		}
      -	}
      -	if (show_deleted || show_modified) {
      -		for (i = 0; i < repo->index->cache_nr; i++) {
      -			const struct cache_entry *ce = repo->index->cache[i];
      -			struct stat st;
     --			int err;
     --
     +-			int stat_err;
     ++	if (! (show_cached || show_stage || show_deleted || show_modified))
     ++		return;
     ++	for (i = 0; i < repo->index->cache_nr; i++) {
     ++		const struct cache_entry *ce = repo->index->cache[i];
     ++		struct stat st;
     ++		int stat_err;
     + 
      -			construct_fullname(&fullname, repo, ce);
     --
     ++		construct_fullname(&fullname, repo, ce);
     + 
      -			if ((dir->flags & DIR_SHOW_IGNORED) &&
      -			    !ce_excluded(dir, repo->index, fullname.buf, ce))
      -				continue;
     @@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_s
      -				continue;
      -			if (ce_skip_worktree(ce))
      -				continue;
     --			err = lstat(fullname.buf, &st);
     --			if (err) {
     --				if (errno != ENOENT && errno != ENOTDIR)
     --				    error_errno("cannot lstat '%s'", fullname.buf);
     --				if (show_deleted)
     --					show_ce(repo, dir, ce, fullname.buf, tag_removed);
     --				if (show_modified)
     +-			stat_err = lstat(fullname.buf, &st);
     +-			if (stat_err && (errno != ENOENT && errno != ENOTDIR))
     +-				error_errno("cannot lstat '%s'", fullname.buf);
     +-			if (stat_err && show_deleted)
     +-				show_ce(repo, dir, ce, fullname.buf, tag_removed);
     +-			if (show_modified &&
     +-				(stat_err || ie_modified(repo->index, ce, &st, 0)))
      -					show_ce(repo, dir, ce, fullname.buf, tag_modified);
     --			} else if (show_modified && ie_modified(repo->index, ce, &st, 0))
     ++		if ((dir->flags & DIR_SHOW_IGNORED) &&
     ++			!ce_excluded(dir, repo->index, fullname.buf, ce))
     ++			continue;
     ++		if (ce->ce_flags & CE_UPDATE)
     ++			continue;
     ++		if (show_cached || show_stage) {
     ++			if (!show_unmerged || ce_stage(ce))
     ++				show_ce(repo, dir, ce, fullname.buf,
     ++					ce_stage(ce) ? tag_unmerged :
     ++					(ce_skip_worktree(ce) ? tag_skip_worktree :
     ++						tag_cached));
     + 		}
     ++		if (!show_deleted && !show_modified)
     ++			continue;
      +		if (ce_skip_worktree(ce))
      +			continue;
     -+		err = lstat(fullname.buf, &st);
     -+		if (err) {
     -+			if (errno != ENOENT && errno != ENOTDIR)
     -+				error_errno("cannot lstat '%s'", fullname.buf);
     -+			if (show_deleted)
     -+				show_ce(repo, dir, ce, fullname.buf, tag_removed);
     -+			if (show_modified)
     - 				show_ce(repo, dir, ce, fullname.buf, tag_modified);
     --		}
     -+		} else if (show_modified && ie_modified(repo->index, ce, &st, 0))
     -+			show_ce(repo, dir, ce, fullname.buf, tag_modified);
     ++		stat_err = lstat(fullname.buf, &st);
     ++		if (stat_err && (errno != ENOENT && errno != ENOTDIR))
     ++			error_errno("cannot lstat '%s'", fullname.buf);
     ++		if (stat_err && show_deleted)
     ++			show_ce(repo, dir, ce, fullname.buf, tag_removed);
     ++		if (show_modified &&
     ++			(stat_err || ie_modified(repo->index, ce, &st, 0)))
     ++				show_ce(repo, dir, ce, fullname.buf, tag_modified);
       	}
       
       	strbuf_release(&fullname);
 3:  e9c53186706 ! 3:  07b603fd97c ls-files.c: add --deduplicate option
     @@ builtin/ls-files.c: static int line_terminator = '\n';
       static const char *prefix;
       static int max_prefix_len;
      @@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     - {
     - 	int i;
     - 	struct strbuf fullname = STRBUF_INIT;
     -+	const struct cache_entry *last_shown_ce;
     - 
     - 	/* For cached/deleted files we don't need to even do the readdir */
     - 	if (show_others || show_killed) {
     -@@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     - 	}
     - 	if (! (show_cached || show_stage || show_deleted || show_modified))
     - 		return;
     -+	last_shown_ce = NULL;
     - 	for (i = 0; i < repo->index->cache_nr; i++) {
     - 		const struct cache_entry *ce = repo->index->cache[i];
     - 		struct stat st;
     -@@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     - 
     - 		construct_fullname(&fullname, repo, ce);
     - 
     -+		if (skipping_duplicates && last_shown_ce &&
     -+			!strcmp(last_shown_ce->name,ce->name))
     -+				continue;
     - 		if ((dir->flags & DIR_SHOW_IGNORED) &&
     - 			!ce_excluded(dir, repo->index, fullname.buf, ce))
       			continue;
       		if (ce->ce_flags & CE_UPDATE)
       			continue;
     - 		if (show_cached || show_stage) {
     -+			if (skipping_duplicates && last_shown_ce &&
     -+				!strcmp(last_shown_ce->name,ce->name))
     -+					continue;
     - 			if (!show_unmerged || ce_stage(ce))
     +-		if (show_cached || show_stage) {
     +-			if (!show_unmerged || ce_stage(ce))
     ++		if ((show_cached || show_stage) &&
     ++			(!show_unmerged || ce_stage(ce))) {
       				show_ce(repo, dir, ce, fullname.buf,
       					ce_stage(ce) ? tag_unmerged :
       					(ce_skip_worktree(ce) ? tag_skip_worktree :
       						tag_cached));
     -+			if (show_cached && skipping_duplicates)
     -+				last_shown_ce = ce;
     ++			if (skipping_duplicates)
     ++				goto skip_to_next_name;
       		}
     - 		if (ce_skip_worktree(ce))
     + 		if (!show_deleted && !show_modified)
       			continue;
     -+		if (skipping_duplicates && last_shown_ce &&
     -+			!strcmp(last_shown_ce->name,ce->name))
     -+				continue;
     - 		err = lstat(fullname.buf, &st);
     - 		if (err) {
     --			if (errno != ENOENT && errno != ENOTDIR)
     --				error_errno("cannot lstat '%s'", fullname.buf);
     --			if (show_deleted)
     -+			if (skipping_duplicates && show_deleted && show_modified)
     - 				show_ce(repo, dir, ce, fullname.buf, tag_removed);
     --			if (show_modified)
     --				show_ce(repo, dir, ce, fullname.buf, tag_modified);
     -+			else {
     -+				if (errno != ENOENT && errno != ENOTDIR)
     -+					error_errno("cannot lstat '%s'", fullname.buf);
     -+				if (show_deleted)
     -+					show_ce(repo, dir, ce, fullname.buf, tag_removed);
     -+				if (show_modified)
     -+					show_ce(repo, dir, ce, fullname.buf, tag_modified);
     -+			}
     - 		} else if (show_modified && ie_modified(repo->index, ce, &st, 0))
     - 			show_ce(repo, dir, ce, fullname.buf, tag_modified);
     -+		last_shown_ce = ce;
     +@@ builtin/ls-files.c: static void show_files(struct repository *repo, struct dir_struct *dir)
     + 		stat_err = lstat(fullname.buf, &st);
     + 		if (stat_err && (errno != ENOENT && errno != ENOTDIR))
     + 			error_errno("cannot lstat '%s'", fullname.buf);
     +-		if (stat_err && show_deleted)
     ++		if (stat_err && show_deleted) {
     + 			show_ce(repo, dir, ce, fullname.buf, tag_removed);
     ++			if (skipping_duplicates)
     ++				goto skip_to_next_name;
     ++		}
     + 		if (show_modified &&
     +-			(stat_err || ie_modified(repo->index, ce, &st, 0)))
     ++			(stat_err || ie_modified(repo->index, ce, &st, 0))) {
     + 				show_ce(repo, dir, ce, fullname.buf, tag_modified);
     ++			if (skipping_duplicates)
     ++				goto skip_to_next_name;
     ++		}
     ++		continue;
     ++skip_to_next_name:
     ++		{
     ++			int j;
     ++			struct cache_entry **cache = repo->index->cache;
     ++			for (j = i + 1; j < repo->index->cache_nr; j++)
     ++				if (strcmp(ce->name, cache[j]->name))
     ++					break;
     ++			i = j - 1; /* compensate for outer for loop */
     ++		}
       	}
       
       	strbuf_release(&fullname);