From a079c310b4b152dfb985d1e13d1ae016d309fed1 Mon Sep 17 00:00:00 2001
From: jonaswinkler <jonas.winkler@jpwinkler.de>
Date: Sun, 6 Dec 2020 16:13:37 +0100
Subject: [PATCH] changes to filename generation, partially addresses #90

---
 src/documents/file_handling.py            | 28 +++++++++++++++++++----
 src/documents/tests/test_consumer.py      |  2 +-
 src/documents/tests/test_file_handling.py | 22 +++++++++++++++++-
 3 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/src/documents/file_handling.py b/src/documents/file_handling.py
index 85ee37d4d..78d0d7efc 100644
--- a/src/documents/file_handling.py
+++ b/src/documents/file_handling.py
@@ -1,11 +1,14 @@
+import datetime
 import logging
 import os
 from collections import defaultdict
 
+import pathvalidate
 from django.conf import settings
 from django.template.defaultfilters import slugify
 
 
+
 def create_source_path_directory(source_path):
     os.makedirs(os.path.dirname(source_path), exist_ok=True)
 
@@ -75,14 +78,31 @@ def generate_filename(doc):
         if settings.PAPERLESS_FILENAME_FORMAT is not None:
             tags = defaultdict(lambda: slugify(None),
                                many_to_dictionary(doc.tags))
+
+            if doc.correspondent:
+                correspondent = pathvalidate.sanitize_filename(
+                    doc.correspondent.name, replacement_text="-"
+                )
+            else:
+                correspondent = "none"
+
+            if doc.document_type:
+                document_type = pathvalidate.sanitize_filename(
+                    doc.document_type.name, replacement_text="-"
+                )
+            else:
+                document_type = "none"
+
             path = settings.PAPERLESS_FILENAME_FORMAT.format(
-                correspondent=slugify(doc.correspondent),
-                title=slugify(doc.title),
-                created=slugify(doc.created),
+                title=pathvalidate.sanitize_filename(
+                    doc.title, replacement_text="-"),
+                correspondent=correspondent,
+                document_type=document_type,
+                created=datetime.date.isoformat(doc.created),
                 created_year=doc.created.year if doc.created else "none",
                 created_month=doc.created.month if doc.created else "none",
                 created_day=doc.created.day if doc.created else "none",
-                added=slugify(doc.added),
+                added=datetime.date.isoformat(doc.added),
                 added_year=doc.added.year if doc.added else "none",
                 added_month=doc.added.month if doc.added else "none",
                 added_day=doc.added.day if doc.added else "none",
diff --git a/src/documents/tests/test_consumer.py b/src/documents/tests/test_consumer.py
index 992d450db..f785bc695 100644
--- a/src/documents/tests/test_consumer.py
+++ b/src/documents/tests/test_consumer.py
@@ -598,7 +598,7 @@ class TestConsumer(DirectoriesMixin, TestCase):
 
         self.assertEqual(document.title, "new docs")
         self.assertEqual(document.correspondent.name, "Bank")
-        self.assertEqual(document.filename, "bank/new-docs-0000001.pdf")
+        self.assertEqual(document.filename, "Bank/new docs-0000001.pdf")
 
     @override_settings(PAPERLESS_FILENAME_FORMAT="{correspondent}/{title}")
     @mock.patch("documents.signals.handlers.generate_filename")
diff --git a/src/documents/tests/test_file_handling.py b/src/documents/tests/test_file_handling.py
index cc4bf8053..4ed93d1d4 100644
--- a/src/documents/tests/test_file_handling.py
+++ b/src/documents/tests/test_file_handling.py
@@ -1,5 +1,5 @@
+import datetime
 import os
-import shutil
 from pathlib import Path
 from unittest import mock
 
@@ -485,3 +485,23 @@ class TestFileHandlingWithArchive(DirectoriesMixin, TestCase):
         self.assertTrue(os.path.isfile(archive))
         self.assertTrue(os.path.isfile(doc.source_path))
         self.assertTrue(os.path.isfile(doc.archive_path))
+
+class TestFilenameGeneration(TestCase):
+
+    @override_settings(
+        PAPERLESS_FILENAME_FORMAT="{title}"
+    )
+    def test_invalid_characters(self):
+
+        doc = Document.objects.create(title="This. is the title.", mime_type="application/pdf", pk=1, checksum="1")
+        self.assertEqual(generate_filename(doc), "This. is the title-0000001.pdf")
+
+        doc = Document.objects.create(title="my\\invalid/../title:yay", mime_type="application/pdf", pk=2, checksum="2")
+        self.assertEqual(generate_filename(doc), "my-invalid-..-title-yay-0000002.pdf")
+
+    @override_settings(
+        PAPERLESS_FILENAME_FORMAT="{created}"
+    )
+    def test_date(self):
+        doc = Document.objects.create(title="does not matter", created=datetime.datetime(2020,5,21, 7,36,51, 153), mime_type="application/pdf", pk=2, checksum="2")
+        self.assertEqual(generate_filename(doc), "2020-05-21-0000002.pdf")