diffcore-rename: add computation of number of unknown renames

In directory rename detection (when a directory is removed on one side
of history and the other side adds new files to that directory), we work
to find where the greatest number of files within that directory were
renamed to so that the new files can be moved with the majority of the
files.

Naively, we can just do this by detecting renames for *all* files within
the removed/renamed directory, looking at all the destination
directories where files within that directory were moved, and if there
is more than one such directory then taking the one with the greatest
number of files as the directory where the old directory was renamed to.

However, sometimes there are enough renames from exact rename detection
or basename-guided rename detection that we have enough information to
determine the majority winner already.  The only way to know if we have
enough for a majority, though, is if we compute the number of unpaired
files for each directory.  Add a function which computes these values.
A subsequent commit will make use of these.

Note that this change means dir_rename_count might have a directory
whose only entry (for UNKNOWN_DIR) was removed by the time merge-ort
goes to check it.  To account for this, merge-ort needs to check for the
case where the max count is 0.

Signed-off-by: Elijah Newren <[email protected]>

Author: newren

diffcore-rename.c

@@ -407,6 +407,8 @@ static const char *get_highest_rename_path(struct strintmap *counts)
 	return highest_destination_dir;
 }
 
+static char *UNKNOWN_DIR = "/";  /* placeholder -- short, illegal directory */
+
 static void increment_count(struct dir_rename_info *info,
 			    char *old_dir,
 			    char *new_dir)
@@ -648,8 +650,9 @@ static void cleanup_dir_rename_info(struct dir_rename_info *info,
 		/*
 		 * 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.
+		 * return it to that caller, we first want to remove any counts
+		 * in the maps associated with UNKNOWN_DIR entries and any
+		 * data associated with directories that weren't renamed.
 		 */
 		struct string_list to_remove = STRING_LIST_INIT_NODUP;
 		int i;
@@ -663,6 +666,9 @@ static void cleanup_dir_rename_info(struct dir_rename_info *info,
 				strintmap_clear(counts);
 				continue;
 			}
+
+			if (strintmap_contains(counts, UNKNOWN_DIR))
+				strintmap_remove(counts, UNKNOWN_DIR);
 		}
 		for (i=0; i<to_remove.nr; ++i)
 			strmap_remove(info->dir_rename_count,
@@ -1034,6 +1040,49 @@ static void remove_unneeded_paths_from_src(int detecting_copies,
 	rename_src_nr = new_num_src;
 }
 
+MAYBE_UNUSED
+static void handle_early_known_dir_renames(struct dir_rename_info *info,
+					   struct strintmap *relevant_sources,
+					   struct strintmap *dirs_removed)
+{
+	int i;
+
+	if (!dirs_removed || !relevant_sources)
+		return; /* nothing to cull */
+	if (break_idx)
+		return; /* culling incompatbile with break detection */
+
+	for (i = 0; i < rename_src_nr; i++) {
+		char *old_dir;
+		struct diff_filespec *one = rename_src[i].p->one;
+
+		/*
+		 * sources that are part of a rename will have already been
+		 * removed by a prior call to remove_unneeded_paths_from_src()
+		 */
+		assert(!one->rename_used);
+
+		old_dir = get_dirname(one->path);
+		while (*old_dir != '\0' &&
+		       NOT_RELEVANT != strintmap_get(dirs_removed, old_dir)) {
+			char *freeme = old_dir;
+
+			increment_count(info, old_dir, UNKNOWN_DIR);
+			old_dir = get_dirname(old_dir);
+
+			/* Free resources we don't need anymore */
+			free(freeme);
+		}
+		/*
+		 * old_dir and new_dir free'd in increment_count, but
+		 * get_dirname() gives us a new pointer we need to free for
+		 * old_dir.  Also, if the loop runs 0 times we need old_dir
+		 * to be freed.
+		 */
+		free(old_dir);
+	}
+}
+
 void diffcore_rename_extended(struct diff_options *options,
 			      struct strintmap *relevant_sources,
 			      struct strintmap *dirs_removed,

merge-ort.c

@@ -1552,6 +1552,9 @@ static void get_provisional_directory_renames(struct merge_options *opt,
 			}
 		}
 
+		if (max == 0)
+			continue;
+
 		if (bad_max == max) {
 			path_msg(opt, source_dir, 0,
 			       _("CONFLICT (directory rename split): "