X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/93da6796796d43def17c8adde0f194489cc14b01..998a1e2aeaea0c5361e526365d1e94d7eaa9d4e8:/src/wolnelektury/utils.py

diff --git a/src/wolnelektury/utils.py b/src/wolnelektury/utils.py
index 72bc7d0c7..c65a172bd 100644
--- a/src/wolnelektury/utils.py
+++ b/src/wolnelektury/utils.py
@@ -1,22 +1,24 @@
-# -*- coding: utf-8 -*-
 # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
+import codecs
+import csv
+from functools import wraps
+from inspect import getargspec
+from io import BytesIO
 import json
 import os
-from functools import wraps
-
 import pytz
-from inspect import getargspec
+import re
 
 from django.core.mail import send_mail
 from django.http import HttpResponse
-from django.template import RequestContext
 from django.template.loader import render_to_string
 from django.utils import timezone
 from django.conf import settings
 from django.utils.translation import ugettext
 
+
 tz = pytz.timezone(settings.TIME_ZONE)
 
 
@@ -37,7 +39,7 @@ def makedirs(path):
 
 def stringify_keys(dictionary):
     return dict((keyword.encode('ascii'), value)
-                for keyword, value in dictionary.iteritems())
+                for keyword, value in dictionary.items())
 
 
 def json_encode(obj, sort_keys=True, ensure_ascii=False):
@@ -84,7 +86,7 @@ def ajax(login_required=False, method=None, template=None, permission_required=N
                 if request_params:
                     request_params = dict(
                         (key, json_decode_fallback(value))
-                        for key, value in request_params.iteritems()
+                        for key, value in request_params.items()
                         if fun_kwargs or key in fun_params)
                     kwargs.update(stringify_keys(request_params))
                 res = None
@@ -97,7 +99,7 @@ def ajax(login_required=False, method=None, template=None, permission_required=N
                 try:
                     res = fun(request, **kwargs)
                     if res and template:
-                        res = {'html': render_to_string(template, res, RequestContext(request))}
+                        res = {'html': render_to_string(template, res, request=request)}
                 except AjaxError as e:
                     res = {'result': e.args[0]}
             if 'result' not in res:
@@ -115,3 +117,50 @@ def send_noreply_mail(subject, message, recipient_list, **kwargs):
         u'[WolneLektury] ' + subject,
         message + u"\n\n-- \n" + ugettext(u'Message sent automatically. Please do not reply.'),
         'no-reply@wolnelektury.pl', recipient_list, **kwargs)
+
+
+# source: https://docs.python.org/2/library/csv.html#examples
+class UnicodeCSVWriter(object):
+    """
+    A CSV writer which will write rows to CSV file "f",
+    which is encoded in the given encoding.
+    """
+
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        # Redirect output to a queue
+        self.queue = BytesIO()
+        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
+        self.stream = f
+        self.encoder = codecs.getincrementalencoder(encoding)()
+
+    def writerow(self, row):
+        self.writer.writerow([s.encode("utf-8") for s in row])
+        # Fetch UTF-8 output from the queue ...
+        data = self.queue.getvalue()
+        data = data.decode("utf-8")
+        # ... and reencode it into the target encoding
+        data = self.encoder.encode(data)
+        # write to the target stream
+        self.stream.write(data)
+        # empty queue
+        self.queue.truncate(0)
+
+    def writerows(self, rows):
+        for row in rows:
+            self.writerow(row)
+
+
+# the original re.escape messes with unicode
+def re_escape(s):
+    return re.sub(r"[(){}\[\].*?|^$\\+-]", r"\\\g<0>", s)
+
+
+BOT_BITS = ['bot', 'slurp', 'spider', 'facebook', 'crawler', 'parser', 'http']
+
+
+def is_crawler(request):
+    user_agent = request.META.get('HTTP_USER_AGENT')
+    if not user_agent:
+        return True
+    user_agent = user_agent.lower()
+    return any(bot_bit in user_agent for bot_bit in BOT_BITS)