[PATCH v2 05/17] merge-ort: add outline of get_provisional_directory_renames()

From: "Elijah Newren via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: Junio C Hamano <gitster@pobox.com>,
	Elijah Newren <newren@gmail.com>,
	Elijah Newren <newren@gmail.com>
Subject: [PATCH v2 05/17] merge-ort: add outline of get_provisional_directory_renames()
Date: Thu, 07 Jan 2021 21:35:53 +0000	[thread overview]
Message-ID: <bb4285250cdef2fcd16a22f8540968c871302c9f.1610055365.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.835.v2.git.1610055365.gitgitgadget@gmail.com>

From: Elijah Newren <newren@gmail.com>

This function is based on merge-recursive.c's get_directory_renames(),
except that the first half has been split out into a not-yet-implemented
compute_rename_counts().  The primary difference here is our lack of the
non_unique_new_dir boolean in our strmap.  The lack of that field will
at first cause us to fail testcase 2b of t6423; however, future
optimizations will obviate the need for that ugly field so we have just
left it out.

Signed-off-by: Elijah Newren <newren@gmail.com>
---
 merge-ort.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/merge-ort.c b/merge-ort.c
index 378ac495d09..73d3ff97f52 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -721,11 +721,69 @@ static int handle_content_merge(struct merge_options *opt,
 
 /*** Function Grouping: functions related to directory rename detection ***/
 
+static void compute_rename_counts(struct diff_queue_struct *pairs,
+				  struct strmap *dir_rename_count,
+				  struct strset *dirs_removed)
+{
+	die("Not yet implemented!");
+}
+
 static void get_provisional_directory_renames(struct merge_options *opt,
 					      unsigned side,
 					      int *clean)
 {
-	die("Not yet implemented!");
+	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 (max == 0)
+			continue;
+
+		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)
-- 
gitgitgadget

