From 2ab99c9a4b61764667b16b1d2b5f33091da0117c Mon Sep 17 00:00:00 2001
From: xenofem <xenofem@xeno.science>
Date: Mon, 22 Jan 2024 07:56:45 -0500
Subject: [PATCH] don't get tripped up as much by random extra files during
 collation

---
 dlibrary.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/dlibrary.py b/dlibrary.py
index cccf5e1..2e5019c 100755
--- a/dlibrary.py
+++ b/dlibrary.py
@@ -19,6 +19,9 @@ NUMBER_REGEX = re.compile('[0-9]+')
 
 IMAGE_FILE_EXTENSIONS = ['.png', '.jpg', '.jpeg', '.gif', '.tiff']
 
+IGNOREABLE_FILES = ['Thumbs.db', '__MACOSX', '.DS_Store']
+IGNOREABLE_EXTENSIONS = ['.txt', '.html', '.htm']
+
 def open_zipfile_with_encoding(path):
     try:
         return zipfile.ZipFile(path, metadata_encoding="utf-8")
@@ -151,6 +154,12 @@ def link_ordered_files(ordering, dest, start_index=0):
         link_path = dest / f'{idx:04d}{ext}'
         link_path.symlink_to(relpath(src_path, dest))
 
+def ls_ignore(directory):
+    return [
+        path for path in directory.iterdir()
+        if path.name not in IGNOREABLE_FILES and path.suffix.lower() not in IGNOREABLE_EXTENSIONS
+    ]
+
 def collate(args):
     con = sqlite3.connect(args.destdir / 'meta.db')
     cur = con.cursor()
@@ -171,11 +180,11 @@ def collate(args):
 
         if work_id in hint_map:
             hint = hint_map[work_id]
-            entries = list(hint.iterdir()) if hint.is_dir() else [hint]
+            entries = ls_ignore(hint) if hint.is_dir() else [hint]
         else:
             search_dir = work_path
             while True:
-                entries = list(search_dir.iterdir())
+                entries = ls_ignore(search_dir)
                 if len(entries) == 1 and entries[0].is_dir():
                     search_dir = entries[0]
                 else: