From a305350f5f400492de175b359a982799eaa22b4b Mon Sep 17 00:00:00 2001
From: Ethan Dalool <git@voussoir.net>
Date: Sat, 24 Dec 2016 18:34:34 -0800
Subject: [PATCH] Fix handling of unicode filename downloads

Add photo attribute dot_extension

Fix bug using unnormalized offset in calculations
---
 etiquette.py         | 15 +++++++--------
 helpers.py           |  3 ---
 objects.py           |  5 +++++
 phototagger.py       | 10 +++++++++-
 templates/photo.html |  7 +++----
 5 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/etiquette.py b/etiquette.py
index c7cce00..f49e88b 100644
--- a/etiquette.py
+++ b/etiquette.py
@@ -4,6 +4,7 @@ import json
 import mimetypes
 import os
 import random
+import urllib.parse
 import warnings
 import zipstream
 
@@ -303,10 +304,10 @@ def get_album_zip(albumid):
         download_as = '%s - %s.zip' % (album.id, album.title)
     else:
         download_as = '%s.zip' % album.id
-    download_as = download_as.replace('"', '\\"')
+    download_as = urllib.parse.quote(download_as)
     outgoing_headers = {
         'Content-Type': 'application/octet-stream',
-        'Content-Disposition': 'attachment; filename=%s' % download_as,
+        'Content-Disposition': 'attachment; filename*=UTF-8\'\'%s' % download_as,
 
     }
     return flask.Response(streamed_zip, headers=outgoing_headers)
@@ -354,13 +355,11 @@ def get_file(photoid):
         if use_original_filename:
             download_as = photo.basename
         else:
-            download_as = photo.id
-            if photo.extension:
-                download_as += photo.extension
+            download_as = photo.id + photo.dot_extension
 
-        download_as = download_as.replace('"', '\\"')
+        download_as =  urllib.parse.quote(download_as)
         response = flask.make_response(send_file(photo.real_filepath))
-        response.headers['Content-Disposition'] = 'attachment; filename="%s"' % download_as
+        response.headers['Content-Disposition'] = 'attachment; filename*=UTF-8\'\'%s' % download_as
         return response
     else:
         return send_file(photo.real_filepath)
@@ -485,7 +484,7 @@ def get_search_core():
     total_tags = sorted(total_tags)
 
     # PREV-NEXT PAGE URLS
-    offset = offset or 0
+    offset = search_kwargs['offset'] or 0
     original_params = request.args.to_dict()
     if len(photos) == limit:
         next_params = helpers.edit_params(original_params, {'offset': offset + limit})
diff --git a/helpers.py b/helpers.py
index 9c1da2a..313034a 100644
--- a/helpers.py
+++ b/helpers.py
@@ -191,9 +191,6 @@ def is_xor(*args):
     '''
     return [bool(a) for a in args].count(True) == 1
 
-def normalize_extension(extension):
-    pass
-
 def normalize_filepath(filepath, allowed=''):
     '''
     Remove some bad characters.
diff --git a/objects.py b/objects.py
index 818bc80..a0f3e03 100644
--- a/objects.py
+++ b/objects.py
@@ -292,6 +292,11 @@ class Photo(ObjectBase):
         self.extension = row_tuple['extension']
         self.tagged_at = row_tuple['tagged_at']
 
+        if self.extension == '':
+            self.dot_extension = ''
+        else:
+            self.dot_extension = '.' + self.extension
+
         self.area = row_tuple['area']
         self.bytes = row_tuple['bytes']
         self.duration = row_tuple['duration']
diff --git a/phototagger.py b/phototagger.py
index bf98ee6..204ecc5 100644
--- a/phototagger.py
+++ b/phototagger.py
@@ -567,6 +567,7 @@ class PDBPhotoMixin:
 
         extension_not:
             A string or list of strings of unacceptable file extensions.
+            Including '*' will forbid all extensions
 
         filename:
             A string or list of strings which will be split into words. The file's basename
@@ -722,7 +723,14 @@ class PDBPhotoMixin:
                 #print('Failed extension')
                 continue
 
-            if extension_not and photo.extension in extension_not:
+            ext_fail = (
+                extension_not and
+                (
+                    ('*' in extension_not and photo.extension) or
+                    (photo.extension in extension_not)
+                )
+            )
+            if (ext_fail):
                 #print('Failed extension_not')
                 continue
 
diff --git a/templates/photo.html b/templates/photo.html
index 5222937..148e84b 100644
--- a/templates/photo.html
+++ b/templates/photo.html
@@ -6,7 +6,7 @@
     <meta charset="UTF-8">
     <link rel="stylesheet" href="/static/common.css">
     <script src="/static/common.js"></script>
-    {% set filename = photo.id + "." + photo.extension %}
+    {% set filename = photo.id + photo.dot_extension %}
     {% set link = "/file/" + filename %}
 
 <style>
@@ -122,9 +122,8 @@
         {% if photo.duration %}
             <li>Duration: {{photo.duration_string()}}</li>
         {% endif %}
-        {% set extension= "." + photo.extension if photo.extension != "" else "" %}
-            <li><a href="/file/{{photo.id}}{{extension}}?download=1">Download as {{photo.id}}.{{photo.extension}}</a></li>
-            <li><a href="/file/{{photo.id}}{{extension}}?download=1&original_filename=1">Download as "{{photo.basename}}"</a></li>
+            <li><a href="/file/{{photo.id}}{{photo.dot_extension}}?download=1">Download as {{photo.id}}.{{photo.extension}}</a></li>
+            <li><a href="/file/{{photo.id}}{{photo.dot_extension}}?download=1&original_filename=1">Download as "{{photo.basename}}"</a></li>
         </ul>
 
         <!-- CONTAINING ALBUMS -->