From 5173ca0454556cd75c9ccc26a37c6be9d7949999 Mon Sep 17 00:00:00 2001
From: Nick Craig-Wood <nick@craig-wood.com>
Date: Tue, 3 Jun 2025 09:47:03 +0100
Subject: [PATCH] march: fix syncing with a duplicate file and directory

As part of the out of memory syncing code, in this commit

0148bd46688c1d1a march: Implement callback based syncing

we changed the syncing method to use a sorted stream of directory
entries.

Unfortunately as part of this change the sort order of files and
directories became undefined.

This meant that if there existed both a file `foo` and a directory
`foo` in the same directory (as is common on object storage systems)
then these could be matched up incorrectly.

They could be matched up correctly like this

- `foo` (directory) - `foo` (directory)
- `foo` (file)      - `foo` (file)

Or incorrectly like this (one of many possibilities)

- no match          - `foo` (file)
- `foo` (directory) - `foo` (directory)
- `foo` (file)      - no match

Just depending on how the input listings were ordered.

This in turn made container based syncing with a duplicated file and
directory name erratic, deleting files when it shouldn't.

This patch ensures that directories always sync before files by adding
a suffix to the sort key depending on whether the entry was a file or
directory.
---
 fs/march/march.go      |  7 +++++++
 fs/march/march_test.go | 11 +++++++++++
 2 files changed, 18 insertions(+)

diff --git a/fs/march/march.go b/fs/march/march.go
index a879871af..578aea512 100644
--- a/fs/march/march.go
+++ b/fs/march/march.go
@@ -89,6 +89,13 @@ func (m *March) key(entry fs.DirEntry) string {
 	for _, transform := range m.transforms {
 		name = transform(name)
 	}
+	// Suffix entries to make identically named files and
+	// directories sort consistently with directories first.
+	if _, isDirectory := entry.(fs.Directory); isDirectory {
+		name += "D"
+	} else {
+		name += "F"
+	}
 	return name
 }
 
diff --git a/fs/march/march_test.go b/fs/march/march_test.go
index 2d1d03e74..ad71e6dd3 100644
--- a/fs/march/march_test.go
+++ b/fs/march/march_test.go
@@ -477,6 +477,17 @@ func TestMatchListings(t *testing.T) {
 				{dirA, dirA},
 			},
 		},
+		{
+			what: "Sync with duplicate files and dirs",
+			input: fs.DirEntries{
+				dirA, A,
+				A, dirA,
+			},
+			matches: []matchPair{
+				{dirA, dirA},
+				{A, A},
+			},
+		},
 	} {
 		t.Run(fmt.Sprintf("TestMatchListings-%s", test.what), func(t *testing.T) {
 			ctx := context.Background()