Empty folders in backup and restore, a full disk stops a restore, progress in the Bin

- Record folders without files in the meta record of a snapshot and restore them (#27)
- Errors writing to the restore directory stop the restore, also with --salvage
- Resume: check the folder before skipping, clean temporaries in folders that are complete
- Clean only read-ahead folders of our own; refresh the lease on skipped files
- Drop tables a failed database restore created; keep --salvage from calling a restored database fresh
- Retry a pack that fails to open on the storage (SMB)
- Without cron, running backups take turns from the open page
- Bin: read in parts with a counter and progress bar, show read errors, refresh when a run ends

lib/Job/BackupRun.php

@@ -55,9 +55,28 @@ final class BackupRun {
 			});
 			$parent = new ParentCursor($repo, $state['parent'], $state['parentPos']);
 			$lines = [];
+			$emptyDirs = [];
 			$finishedWalk = true;
 
 			foreach ($walker->walk($state['after']) as $logical => $path) {
+				if (is_dir($path)) {
+					$mtime = @filemtime($path);
+					if ($mtime === false) {
+						continue; // removed while walking
+					}
+					if (mb_check_encoding($logical, 'UTF-8')) {
+						$emptyDirs[] = json_encode([$logical, $mtime], JSON_UNESCAPED_SLASHES | JSON_THROW_ON_ERROR);
+						$stats['emptyDirs'] = ($stats['emptyDirs'] ?? 0) + 1;
+					} else {
+						self::recordUnreadable($state, $stats, $logical); // a snapshot only holds UTF-8
+					}
+					$state['after'] = $logical;
+					if (microtime(true) >= $deadline) {
+						$finishedWalk = false;
+						break;
+					}
+					continue;
+				}
 				$version = Repository::fileVersion($path);
 				if ($version === 'missing') {
 					continue; // deleted while walking
@@ -136,6 +155,11 @@ final class BackupRun {
 				$writer->write(implode("\n", $lines) . "\n");
 				$state['segments'][] = $writer->finish();
 			}
+			if ($emptyDirs !== []) {
+				$writer = $repo->blobWriter($stats);
+				$writer->write(implode("\n", $emptyDirs) . "\n");
+				$state['dirSegments'][] = $writer->finish();
+			}
 			$repo->flushPacks();
 			$state['parentPos'] = $parent->position();
 			$state['stats'] = $stats;
@@ -150,10 +174,18 @@ final class BackupRun {
 		if ($state['phase'] === 'finish') {
 			// Every segment ends with a newline, so they read as one stream: fetched together,
 			// several at a time where the location allows it.
+			// Empty folders go in the meta record, not between the files: a version that does not
+			// know them reads the snapshot as before, and only restores no empty folders.
+			$emptyDirs = [];
+			foreach (isset($state['dirSegments']) ? $repo->readLines(array_values(array_merge(...$state['dirSegments']))) : [] as $line) {
+				if ($line !== '') {
+					$emptyDirs[] = json_decode($line, true, 8, JSON_THROW_ON_ERROR);
+				}
+			}
 			$repo->putSnapshot($state['snapshot'],
 				['time' => $state['started'], 'parent' => $state['parent'], 'label' => $state['label'],
 					'roots' => array_keys($state['roots']), 'stats' => $state['stats'],
-					'warnings' => self::warnings($state)] + $state['meta'],
+					'warnings' => self::warnings($state)] + ($emptyDirs === [] ? [] : ['emptyDirs' => $emptyDirs]) + $state['meta'],
 				$repo->readLines(array_values(array_merge(...$state['segments']))));
 			$state['phase'] = 'commit';
 		}

lib/Job/TreeWalker.php

@@ -9,7 +9,9 @@ namespace OCA\NgBackup\Job;
 
 /**
  * Walks one or more source roots in a stable depth-first order (entries of a directory sorted
- * by name, children right after their directory), yielding "<root>/<relative path>" for files.
+ * by name, children right after their directory), yielding "<root>/<relative path>" for files
+ * and for directories with nothing in them to walk (the caller tells them apart with is_dir()).
+ * A root itself without a name is never yielded.
  *
  * The same order is used for comparing paths (compare()), so a walk can resume after a cursor
  * and be merge-joined with the previous snapshot without holding any list in memory.
@@ -66,6 +68,7 @@ final class TreeWalker {
 		}
 		$names = array_values(array_diff($names, ['.', '..']));
 		sort($names, SORT_STRING);
+		$empty = true; // no file or directory below it that is walked, whatever the cursor skips
 		foreach ($names as $name) {
 			$childLogical = $logical === '' ? $name : $logical . '/' . $name;
 			$childAbs = $abs . '/' . $name;
@@ -73,20 +76,26 @@ final class TreeWalker {
 				continue; // never follow symlinks out of the data directory
 			}
 			if (is_dir($childAbs)) {
+				$empty = $empty && $this->isExcluded($childLogical, true);
 				// Skip a directory entirely if everything in it sorts before the cursor.
 				if ($after !== null && self::compare($childLogical, $after) < 0 && !self::isPrefix($childLogical, $after)) {
 					continue;
 				}
 				yield from $this->walkDir($childAbs, $childLogical, $after);
 			} elseif (is_file($childAbs)) {
+				$excluded = $this->isExcluded($childLogical, false);
+				$empty = $empty && $excluded;
 				if ($after !== null && self::compare($childLogical, $after) <= 0) {
 					continue;
 				}
-				if (!$this->isExcluded($childLogical, false)) {
+				if (!$excluded) {
 					yield $childLogical => $childAbs;
 				}
 			}
 		}
+		if ($empty && $logical !== '' && ($after === null || self::compare($logical, $after) > 0)) {
+			yield $logical => $abs;
+		}
 	}
 
 	private function isExcluded(string $logical, bool $isDir): bool {