app/django/middleware/gzip.py
author Sverre Rabbelier <srabbelier@gmail.com>
Sat, 06 Dec 2008 14:23:53 +0000
changeset 679 77a286ff6667
parent 54 03e267d67478
permissions -rw-r--r--
Introduce dynamic scope_path regexps Instead of relying on scope_path's being "one slash deep", we should instead allow for either: 1. scope_paths that have a pre-defined depth 2. scope_paths that can be arbitrarily deep We achieve 1 by setting an entities scope_logic to another logic module. We then recursively call getScopeDepth until we get to the topmost entity (that is, an unscoped entity). A little different is the solution to 2, since some entities can have an arbitrarily deep scope (such as Documents), we need to have some way of signaling this to getScopePattern. A clean solution is to return None, rather than a number. If None is returned, the SCOPE_PATH_ARG_PATTERN is returned as regexp instead, which will match an arbitrarily deeply nested scope. The solution for 2 requires that we return None somewhere in the scope_logic chain, the most straight forward method to do so is to override getScopeDepth anywhere such a scope is needed and make it return None. A more elegant solution however, is to set the scope_logic to that module in all entities that require it. Patch by: Sverre Rabbelier

import re

from django.utils.text import compress_string
from django.utils.cache import patch_vary_headers

re_accepts_gzip = re.compile(r'\bgzip\b')

class GZipMiddleware(object):
    """
    This middleware compresses content if the browser allows gzip compression.
    It sets the Vary header accordingly, so that caches will base their storage
    on the Accept-Encoding header.
    """
    def process_response(self, request, response):
        # It's not worth compressing non-OK or really short responses.
        if response.status_code != 200 or len(response.content) < 200:
            return response

        patch_vary_headers(response, ('Accept-Encoding',))

        # Avoid gzipping if we've already got a content-encoding.
        if response.has_header('Content-Encoding'):
            return response

        # Older versions of IE have issues with gzipped pages containing either
        # Javascript and PDF.
        if "msie" in request.META.get('HTTP_USER_AGENT', '').lower():
            ctype = response.get('Content-Type', '').lower()
            if "javascript" in ctype or ctype == "application/pdf":
                return response

        ae = request.META.get('HTTP_ACCEPT_ENCODING', '')
        if not re_accepts_gzip.search(ae):
            return response

        response.content = compress_string(response.content)
        response['Content-Encoding'] = 'gzip'
        response['Content-Length'] = str(len(response.content))
        return response