How do I fix this encoding error in Google App Engine - google-app-engine

Question

I'm new to Google App Engine and Django forms. I'm getting an encoding error when I try to run the follow code:
import webapp2
from google.appengine.ext import db
from google.appengine.ext.webapp import template
from django import newforms as forms
from google.appengine.ext.db import djangoforms
import os
import re
import fix_path
import config
import static
def slugify(s):
return re.sub('[^a-zA-Z0-9-]+', '-', s).strip('-')
def format_post_path(post, num):
slug = slugify(post.title)
if num > 0:
slug += "-" + str(num)
return config.post_path_format % {
'slug': slug,
'year': post.published.year,
'month': post.published.month,
'day': post.published.day,
}
def render_template(template_name, template_vals=None, theme=None):
template_path = os.path.join("themes", theme or config.theme, template_name)
return template.render(template_path, template_vals or {})
class BlogPost(db.Model):
# The url path to the blog post. Posts have a path if they are published.
path = db.StringProperty()
title = db.StringProperty(required=True, Indexed=False)
body = db.TextProperty(required=True)
published = db.DateTimeProperty(auto_now_add=True)
updated = db.DateTimeProperty(auto_now=True)
def render(self):
template_vals = {
'config': config,
'post': self,
}
return render_template("post.html", template_vals)
def publish(self):
rendered = self.render()
if not self.path:
num = 0
content = None
while not content:
path = format_post_path(self, num)
content = static.add(path, rendered, "text/html")
num += 1
self.path = path
self.put()
else:
static.set(self.path, rendered, "text/html")
class PostForm(djangoforms.ModelForm):
class Meta:
model = BlogPost
exclude = ['path', 'published', 'update']
class PostHandler(webapp2.RequestHandler)
def render_to_response(self, template_name, template_vals=None, theme=None):
template_name = os.path.join("admin", template_name)
self.response.out.write(render_template(template_name, template_vals, theme))
def render_form(self, form):
self.render_to_response("edit.html", {'form': form})
def get(self):
self.render_form(PostForm())
def post(self)
form = PostForm(date=self.request.POST)
if form.is_valid():
post = form.save(commit=False)
post.publish()
self.render_to_response("published.html", {'post': post})
else:
self.render_form(form)
app = webapp2.WSGIApplication([('/admin/newpost', PostHandler)],
debug=True)
Here is the traceback.
ERROR 2012-05-08 10:35:03,609 cgi.py:121] Traceback (most recent call last):
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\tools\dev_appserver_import_hook.py", line 676, in Decorate
return func(self, *args, **kwargs)
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\tools\dev_appserver_import_hook.py", line 1911, in get_code
source_code.decode(encoding)
UnicodeDecodeError: 'ascii' codec can't decode byte 0xef in position 0: ordinal not in range(128)
INFO 2012-05-08 10:35:03,627 dev_appserver.py:2891] "GET /admin/newpost HTTP/1.1" 500 -
The traceback doesn't give me enough information to fix the problem. Any ideas?

Answer 1

When I had this problem with appengine I could clean all my data to unicode / utf-8 and then it worked.
Some of your data is not unicode / utf-8. I've had this problem on several occassions with GAE and it's always the data and not the source code that is not unicode in some way.
If you inspect your data and/or source formatting and set everything to utf-8 / unicode it will work. It might seem that you've already set everything to utf-8, but if you're still getting this error it means some string or the like is is some other charset than utf-8.