git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Elijah Newren <newren@gmail.com>
To: git@vger.kernel.org
Cc: sbeller@google.com, gitster@pobox.com,
	torvalds@linux-foundation.org, Elijah Newren <newren@gmail.com>
Subject: [PATCH v10 18/36] merge-recursive: add get_directory_renames()
Date: Thu, 19 Apr 2018 10:58:05 -0700	[thread overview]
Message-ID: <20180419175823.7946-19-newren@gmail.com> (raw)
In-Reply-To: <20180419175823.7946-1-newren@gmail.com>

This populates a set of directory renames for us.  The set of directory
renames is not yet used, but will be in subsequent commits.

Note that the use of a string_list for possible_new_dirs in the new
dir_rename_entry struct implies an O(n^2) algorithm; however, in practice
I expect the number of distinct directories that files were renamed into
from a single original directory to be O(1).  My guess is that n has a
mode of 1 and a mean of less than 2, so, for now, string_list seems good
enough for possible_new_dirs.

Reviewed-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 merge-recursive.c | 224 +++++++++++++++++++++++++++++++++++++++++++++-
 merge-recursive.h |  18 ++++
 2 files changed, 239 insertions(+), 3 deletions(-)

diff --git a/merge-recursive.c b/merge-recursive.c
index 30894c1cc7..22c5e8e5c9 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -49,6 +49,44 @@ static unsigned int path_hash(const char *path)
 	return ignore_case ? strihash(path) : strhash(path);
 }
 
+static struct dir_rename_entry *dir_rename_find_entry(struct hashmap *hashmap,
+						      char *dir)
+{
+	struct dir_rename_entry key;
+
+	if (dir == NULL)
+		return NULL;
+	hashmap_entry_init(&key, strhash(dir));
+	key.dir = dir;
+	return hashmap_get(hashmap, &key, NULL);
+}
+
+static int dir_rename_cmp(const void *unused_cmp_data,
+			  const void *entry,
+			  const void *entry_or_key,
+			  const void *unused_keydata)
+{
+	const struct dir_rename_entry *e1 = entry;
+	const struct dir_rename_entry *e2 = entry_or_key;
+
+	return strcmp(e1->dir, e2->dir);
+}
+
+static void dir_rename_init(struct hashmap *map)
+{
+	hashmap_init(map, dir_rename_cmp, NULL, 0);
+}
+
+static void dir_rename_entry_init(struct dir_rename_entry *entry,
+				  char *directory)
+{
+	hashmap_entry_init(entry, strhash(directory));
+	entry->dir = directory;
+	entry->non_unique_new_dir = 0;
+	strbuf_init(&entry->new_dir, 0);
+	string_list_init(&entry->possible_new_dirs, 0);
+}
+
 static void flush_output(struct merge_options *o)
 {
 	if (o->buffer_output < 2 && o->obuf.len) {
@@ -1357,6 +1395,169 @@ static struct diff_queue_struct *get_diffpairs(struct merge_options *o,
 	return ret;
 }
 
+static void get_renamed_dir_portion(const char *old_path, const char *new_path,
+				    char **old_dir, char **new_dir)
+{
+	char *end_of_old, *end_of_new;
+	int old_len, new_len;
+
+	*old_dir = NULL;
+	*new_dir = NULL;
+
+	/*
+	 * For
+	 *    "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
+	 * the "e/foo.c" part is the same, we just want to know that
+	 *    "a/b/c/d" was renamed to "a/b/some/thing/else"
+	 * so, for this example, this function returns "a/b/c/d" in
+	 * *old_dir and "a/b/some/thing/else" in *new_dir.
+	 *
+	 * Also, if the basename of the file changed, we don't care.  We
+	 * want to know which portion of the directory, if any, changed.
+	 */
+	end_of_old = strrchr(old_path, '/');
+	end_of_new = strrchr(new_path, '/');
+
+	if (end_of_old == NULL || end_of_new == NULL)
+		return;
+	while (*--end_of_new == *--end_of_old &&
+	       end_of_old != old_path &&
+	       end_of_new != new_path)
+		; /* Do nothing; all in the while loop */
+	/*
+	 * We've found the first non-matching character in the directory
+	 * paths.  That means the current directory we were comparing
+	 * represents the rename.  Move end_of_old and end_of_new back
+	 * to the full directory name.
+	 */
+	if (*end_of_old == '/')
+		end_of_old++;
+	if (*end_of_old != '/')
+		end_of_new++;
+	end_of_old = strchr(end_of_old, '/');
+	end_of_new = strchr(end_of_new, '/');
+
+	/*
+	 * It may have been the case that old_path and new_path were the same
+	 * directory all along.  Don't claim a rename if they're the same.
+	 */
+	old_len = end_of_old - old_path;
+	new_len = end_of_new - new_path;
+
+	if (old_len != new_len || strncmp(old_path, new_path, old_len)) {
+		*old_dir = xstrndup(old_path, old_len);
+		*new_dir = xstrndup(new_path, new_len);
+	}
+}
+
+static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs,
+					     struct tree *tree)
+{
+	struct hashmap *dir_renames;
+	struct hashmap_iter iter;
+	struct dir_rename_entry *entry;
+	int i;
+
+	/*
+	 * Typically, we think of a directory rename as all files from a
+	 * certain directory being moved to a target directory.  However,
+	 * what if someone first moved two files from the original
+	 * directory in one commit, and then renamed the directory
+	 * somewhere else in a later commit?  At merge time, we just know
+	 * that files from the original directory went to two different
+	 * places, and that the bulk of them ended up in the same place.
+	 * We want each directory rename to represent where the bulk of the
+	 * files from that directory end up; this function exists to find
+	 * where the bulk of the files went.
+	 *
+	 * The first loop below simply iterates through the list of file
+	 * renames, finding out how often each directory rename pair
+	 * possibility occurs.
+	 */
+	dir_renames = xmalloc(sizeof(struct hashmap));
+	dir_rename_init(dir_renames);
+	for (i = 0; i < pairs->nr; ++i) {
+		struct string_list_item *item;
+		int *count;
+		struct diff_filepair *pair = pairs->queue[i];
+		char *old_dir, *new_dir;
+
+		/* File not part of directory rename if it wasn't renamed */
+		if (pair->status != 'R')
+			continue;
+
+		get_renamed_dir_portion(pair->one->path, pair->two->path,
+					&old_dir,        &new_dir);
+		if (!old_dir)
+			/* Directory didn't change at all; ignore this one. */
+			continue;
+
+		entry = dir_rename_find_entry(dir_renames, old_dir);
+		if (!entry) {
+			entry = xmalloc(sizeof(struct dir_rename_entry));
+			dir_rename_entry_init(entry, old_dir);
+			hashmap_put(dir_renames, entry);
+		} else {
+			free(old_dir);
+		}
+		item = string_list_lookup(&entry->possible_new_dirs, new_dir);
+		if (!item) {
+			item = string_list_insert(&entry->possible_new_dirs,
+						  new_dir);
+			item->util = xcalloc(1, sizeof(int));
+		} else {
+			free(new_dir);
+		}
+		count = item->util;
+		*count += 1;
+	}
+
+	/*
+	 * For each directory with files moved out of it, we find out which
+	 * target directory received the most files so we can declare it to
+	 * be the "winning" target location for the directory rename.  This
+	 * winner gets recorded in new_dir.  If there is no winner
+	 * (multiple target directories received the same number of files),
+	 * we set non_unique_new_dir.  Once we've determined the winner (or
+	 * that there is no winner), we no longer need possible_new_dirs.
+	 */
+	hashmap_iter_init(dir_renames, &iter);
+	while ((entry = hashmap_iter_next(&iter))) {
+		int max = 0;
+		int bad_max = 0;
+		char *best = NULL;
+
+		for (i = 0; i < entry->possible_new_dirs.nr; i++) {
+			int *count = entry->possible_new_dirs.items[i].util;
+
+			if (*count == max)
+				bad_max = max;
+			else if (*count > max) {
+				max = *count;
+				best = entry->possible_new_dirs.items[i].string;
+			}
+		}
+		if (bad_max == max)
+			entry->non_unique_new_dir = 1;
+		else {
+			assert(entry->new_dir.len == 0);
+			strbuf_addstr(&entry->new_dir, best);
+		}
+		/*
+		 * The relevant directory sub-portion of the original full
+		 * filepaths were xstrndup'ed before inserting into
+		 * possible_new_dirs, and instead of manually iterating the
+		 * list and free'ing each, just lie and tell
+		 * possible_new_dirs that it did the strdup'ing so that it
+		 * will free them for us.
+		 */
+		entry->possible_new_dirs.strdup_strings = 1;
+		string_list_clear(&entry->possible_new_dirs, 1);
+	}
+
+	return dir_renames;
+}
+
 /*
  * Get information of all renames which occurred in 'pairs', making use of
  * any implicit directory renames inferred from the other side of history.
@@ -1668,8 +1869,21 @@ struct rename_info {
 	struct string_list *merge_renames;
 };
 
-static void initial_cleanup_rename(struct diff_queue_struct *pairs)
+static void initial_cleanup_rename(struct diff_queue_struct *pairs,
+				   struct hashmap *dir_renames)
 {
+	struct hashmap_iter iter;
+	struct dir_rename_entry *e;
+
+	hashmap_iter_init(dir_renames, &iter);
+	while ((e = hashmap_iter_next(&iter))) {
+		free(e->dir);
+		strbuf_release(&e->new_dir);
+		/* possible_new_dirs already cleared in get_directory_renames */
+	}
+	hashmap_free(dir_renames, 1);
+	free(dir_renames);
+
 	free(pairs->queue);
 	free(pairs);
 }
@@ -1682,6 +1896,7 @@ static int handle_renames(struct merge_options *o,
 			  struct rename_info *ri)
 {
 	struct diff_queue_struct *head_pairs, *merge_pairs;
+	struct hashmap *dir_re_head, *dir_re_merge;
 	int clean;
 
 	ri->head_renames = NULL;
@@ -1693,6 +1908,9 @@ static int handle_renames(struct merge_options *o,
 	head_pairs = get_diffpairs(o, common, head);
 	merge_pairs = get_diffpairs(o, common, merge);
 
+	dir_re_head = get_directory_renames(head_pairs, head);
+	dir_re_merge = get_directory_renames(merge_pairs, merge);
+
 	ri->head_renames  = get_renames(o, head_pairs, head,
 					 common, head, merge, entries);
 	ri->merge_renames = get_renames(o, merge_pairs, merge,
@@ -1704,8 +1922,8 @@ static int handle_renames(struct merge_options *o,
 	 * data structures are still needed and referenced in
 	 * process_entry().  But there are a few things we can free now.
 	 */
-	initial_cleanup_rename(head_pairs);
-	initial_cleanup_rename(merge_pairs);
+	initial_cleanup_rename(head_pairs, dir_re_head);
+	initial_cleanup_rename(merge_pairs, dir_re_merge);
 
 	return clean;
 }
diff --git a/merge-recursive.h b/merge-recursive.h
index 80d69d1401..fe64c78de4 100644
--- a/merge-recursive.h
+++ b/merge-recursive.h
@@ -29,6 +29,24 @@ struct merge_options {
 	struct string_list df_conflict_file_set;
 };
 
+/*
+ * For dir_rename_entry, directory names are stored as a full path from the
+ * toplevel of the repository and do not include a trailing '/'.  Also:
+ *
+ *   dir:                original name of directory being renamed
+ *   non_unique_new_dir: if true, could not determine new_dir
+ *   new_dir:            final name of directory being renamed
+ *   possible_new_dirs:  temporary used to help determine new_dir; see comments
+ *                       in get_directory_renames() for details
+ */
+struct dir_rename_entry {
+	struct hashmap_entry ent; /* must be the first member! */
+	char *dir;
+	unsigned non_unique_new_dir:1;
+	struct strbuf new_dir;
+	struct string_list possible_new_dirs;
+};
+
 /* merge_trees() but with recursive ancestor consolidation */
 int merge_recursive(struct merge_options *o,
 		    struct commit *h1,
-- 
2.17.0.290.ge988e9ce2a


  parent reply	other threads:[~2018-04-19 18:00 UTC|newest]

Thread overview: 78+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-19 17:57 [PATCH v10 00/36] Add directory rename detection to git Elijah Newren
2018-04-19 17:57 ` [PATCH v10 01/36] directory rename detection: basic testcases Elijah Newren
2018-04-19 17:57 ` [PATCH v10 02/36] directory rename detection: directory splitting testcases Elijah Newren
2018-04-19 17:57 ` [PATCH v10 03/36] directory rename detection: testcases to avoid taking detection too far Elijah Newren
2018-04-19 17:57 ` [PATCH v10 04/36] directory rename detection: partially renamed directory testcase/discussion Elijah Newren
2018-04-19 17:57 ` [PATCH v10 05/36] directory rename detection: files/directories in the way of some renames Elijah Newren
2018-04-19 17:57 ` [PATCH v10 06/36] directory rename detection: testcases checking which side did the rename Elijah Newren
2018-04-19 17:57 ` [PATCH v10 07/36] directory rename detection: more involved edge/corner testcases Elijah Newren
2018-04-19 17:57 ` [PATCH v10 08/36] directory rename detection: testcases exploring possibly suboptimal merges Elijah Newren
2018-04-19 17:57 ` [PATCH v10 09/36] directory rename detection: miscellaneous testcases to complete coverage Elijah Newren
2018-04-19 17:57 ` [PATCH v10 10/36] directory rename detection: tests for handling overwriting untracked files Elijah Newren
2018-04-19 17:57 ` [PATCH v10 11/36] directory rename detection: tests for handling overwriting dirty files Elijah Newren
2018-04-19 17:57 ` [PATCH v10 12/36] merge-recursive: move the get_renames() function Elijah Newren
2018-04-19 17:58 ` [PATCH v10 13/36] merge-recursive: introduce new functions to handle rename logic Elijah Newren
2018-04-19 17:58 ` [PATCH v10 14/36] merge-recursive: fix leaks of allocated renames and diff_filepairs Elijah Newren
2018-04-19 17:58 ` [PATCH v10 15/36] merge-recursive: make !o->detect_rename codepath more obvious Elijah Newren
2018-04-19 17:58 ` [PATCH v10 16/36] merge-recursive: split out code for determining diff_filepairs Elijah Newren
2018-04-19 17:58 ` [PATCH v10 17/36] merge-recursive: make a helper function for cleanup for handle_renames Elijah Newren
2018-04-19 17:58 ` Elijah Newren [this message]
2018-05-06 23:41   ` [PATCH v10 18/36] merge-recursive: add get_directory_renames() SZEDER Gábor
2018-05-07 15:45     ` [PATCH] fixup! " Elijah Newren
2019-10-09 20:38   ` [PATCH v10 18/36] " Johannes Schindelin
2019-10-11 20:02     ` Elijah Newren
2019-10-12 19:23       ` Johannes Schindelin
2018-04-19 17:58 ` [PATCH v10 19/36] merge-recursive: check for directory level conflicts Elijah Newren
2018-04-19 17:58 ` [PATCH v10 20/36] merge-recursive: add computation of collisions due to dir rename & merging Elijah Newren
2018-04-19 17:58 ` [PATCH v10 21/36] merge-recursive: check for file level conflicts then get new name Elijah Newren
2018-04-19 17:58 ` [PATCH v10 22/36] merge-recursive: when comparing files, don't include trees Elijah Newren
2018-04-19 17:58 ` [PATCH v10 23/36] merge-recursive: apply necessary modifications for directory renames Elijah Newren
2018-04-19 17:58 ` [PATCH v10 24/36] merge-recursive: avoid clobbering untracked files with " Elijah Newren
2018-04-19 17:58 ` [PATCH v10 25/36] merge-recursive: fix overwriting dirty files involved in renames Elijah Newren
2018-04-19 20:48   ` Martin Ågren
2018-04-19 20:54     ` Martin Ågren
2018-04-19 21:06     ` Elijah Newren
2018-04-19 17:58 ` [PATCH v10 26/36] merge-recursive: fix remaining directory rename + dirty overwrite cases Elijah Newren
2018-04-19 17:58 ` [PATCH v10 27/36] directory rename detection: new testcases showcasing a pair of bugs Elijah Newren
2018-04-19 17:58 ` [PATCH v10 28/36] merge-recursive: avoid spurious rename/rename conflict from dir renames Elijah Newren
2018-04-19 17:58 ` [PATCH v10 29/36] merge-recursive: improve add_cacheinfo error handling Elijah Newren
2018-04-19 17:58 ` [PATCH v10 30/36] merge-recursive: move more is_dirty handling to merge_content Elijah Newren
2018-04-19 17:58 ` [PATCH v10 31/36] merge-recursive: avoid triggering add_cacheinfo error with dirty mod Elijah Newren
2018-04-19 17:58 ` [PATCH v10 32/36] t6046: testcases checking whether updates can be skipped in a merge Elijah Newren
2018-04-19 20:26   ` SZEDER Gábor
2018-04-19 20:55     ` Elijah Newren
2018-04-19 17:58 ` [PATCH v10 33/36] merge-recursive: fix was_tracked() to quit lying with some renamed paths Elijah Newren
2018-04-19 20:39   ` Martin Ågren
2018-04-19 20:54     ` Elijah Newren
2018-04-20 12:23   ` SZEDER Gábor
2018-04-20 15:23     ` Elijah Newren
2018-04-21 19:37     ` [RFC PATCH v10 32.5/36] unpack_trees: fix memory corruption with split_index when src != dst Elijah Newren
2018-04-21 20:13       ` Elijah Newren
2018-04-22 12:38       ` Duy Nguyen
2018-04-23 17:09         ` Elijah Newren
2018-04-23 17:37           ` Duy Nguyen
2018-04-23 18:05             ` Elijah Newren
2018-04-24  0:24               ` [PATCH v2] unpack_trees: fix breakage when o->src_index != o->dst_index Elijah Newren
2018-04-24  1:51                 ` Junio C Hamano
2018-04-24  3:05                 ` Junio C Hamano
2018-04-24  6:50                   ` [PATCH v3] " Elijah Newren
2018-04-29 18:05                     ` Duy Nguyen
2018-04-29 20:53                       ` Johannes Schindelin
2018-04-30 14:42                         ` Duy Nguyen
2018-04-30 14:45                           ` Duy Nguyen
2018-04-30 16:19                             ` Elijah Newren
2018-04-30 16:29                               ` Duy Nguyen
2018-04-19 17:58 ` [PATCH v10 34/36] merge-recursive: fix remainder of was_dirty() to use original index Elijah Newren
2018-04-19 17:58 ` [PATCH v10 35/36] merge-recursive: make "Auto-merging" comment show for other merges Elijah Newren
2018-04-19 17:58 ` [PATCH v10 36/36] merge-recursive: fix check for skipability of working tree updates Elijah Newren
2018-04-19 18:35 ` [PATCH v10 00/36] Add directory rename detection to git Elijah Newren
2018-04-19 18:41   ` Stefan Beller
2018-04-19 19:54     ` Derrick Stolee
2018-04-19 20:22   ` Elijah Newren
2018-04-20  3:05   ` Junio C Hamano
2018-04-23 17:50     ` Elijah Newren
2018-04-24 20:20     ` [PATCH v10 1/2] fixup! merge-recursive: fix was_tracked() to quit lying with some renamed paths Elijah Newren
2018-04-24 20:21       ` [PATCH v10 2/2] fixup! t6046: testcases checking whether updates can be skipped in a merge Elijah Newren
2018-04-23 17:28 ` [PATCH v10 00/36] Add directory rename detection to git Elijah Newren
2018-04-23 23:46   ` Junio C Hamano
2018-04-24  0:15     ` Elijah Newren

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180419175823.7946-19-newren@gmail.com \
    --to=newren@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=sbeller@google.com \
    --cc=torvalds@linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).