monkee.ch/SickGear
1
0
Fork 0
mirror of https://github.com/SickGear/SickGear.git synced 2025-01-05 17:43:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #390 from adam111316/feature/UpdateFeedparserLibs

Browse source 
Update feedparser library 5.1.3 to 5.2.0 (8c62940)
This commit is contained in:
adam111316 2015-06-06 17:46:25 +08:00
commit 1d72320757
2412 changed files with 766 additions and 33727 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
CHANGES.md
View file

@ -26,6 +26,8 @@
* Change don't create a backup from an initial zero byte main database file, PEP8 and code tidy up
* Fix show list view when no shows exist and "Group show lists shows into" is set to anything other than "One Show List"
* Add coverage testing and coveralls support
* Update feedparser library 5.1.3 to 5.2.0 (8c62940)
* Remove feedcache implementation and library
[develop changelog]
* Update Requests library 2.7.0 (ab1f493) to 2.7.0 (8b5e457)

44
lib/feedcache/__init__.py
View file

@ -1,44 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""
"""
__module_id__ = "$Id$"
#
# Import system modules
#
#
# Import local modules
#
from cache import Cache
#
# Module
#

204
lib/feedcache/cache.py
View file

@ -1,204 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""
"""
__module_id__ = "$Id$"
#
# Import system modules
#
from feedparser import feedparser
import logging
import time
#
# Import local modules
#
#
# Module
#
logger = logging.getLogger('feedcache.cache')
class Cache:
"""A class to wrap Mark Pilgrim's Universal Feed Parser module
(http://www.feedparser.org) so that parameters can be used to
cache the feed results locally instead of fetching the feed every
time it is requested. Uses both etag and modified times for
caching.
"""
def __init__(self, storage, timeToLiveSeconds=300, userAgent='feedcache'):
"""
Arguments:
storage -- Backing store for the cache. It should follow
the dictionary API, with URLs used as keys. It should
persist data.
timeToLiveSeconds=300 -- The length of time content should
live in the cache before an update is attempted.
userAgent='feedcache' -- User agent string to be used when
fetching feed contents.
"""
self.storage = storage
self.time_to_live = timeToLiveSeconds
self.user_agent = userAgent
return
def purge(self, olderThanSeconds):
"""Remove cached data from the storage if the data is older than the
date given. If olderThanSeconds is None, the entire cache is purged.
"""
if olderThanSeconds is None:
logger.debug('purging the entire cache')
for key in self.storage.keys():
del self.storage[key]
else:
now = time.time()
# Iterate over the keys and load each item one at a time
# to avoid having the entire cache loaded into memory
# at one time.
for url in self.storage.keys():
(cached_time, cached_data) = self.storage[url]
age = now - cached_time
if age >= olderThanSeconds:
logger.debug('removing %s with age %d', url, age)
del self.storage[url]
return
def fetch(self, url, force_update=False, offline=False, request_headers=None):
"""Return the feed at url.
url - The URL of the feed.
force_update=False - When True, update the cache whether the
current contents have
exceeded their time-to-live
or not.
offline=False - When True, only return data from the local
cache and never access the remote
URL.
If there is data for that feed in the cache already, check
the expiration date before accessing the server. If the
cached data has not expired, return it without accessing the
server.
In cases where the server is accessed, check for updates
before deciding what to return. If the server reports a
status of 304, the previously cached content is returned.
The cache is only updated if the server returns a status of
200, to avoid holding redirected data in the cache.
"""
logger.debug('url="%s"' % url)
# Convert the URL to a value we can use
# as a key for the storage backend.
key = url
if isinstance(key, unicode):
key = key.encode('utf-8')
modified = None
etag = None
now = time.time()
cached_time, cached_content = self.storage.get(key, (None, None))
# Offline mode support (no networked requests)
# so return whatever we found in the storage.
# If there is nothing in the storage, we'll be returning None.
if offline:
logger.debug('offline mode')
return cached_content
# Does the storage contain a version of the data
# which is older than the time-to-live?
logger.debug('cache modified time: %s' % str(cached_time))
if cached_time is not None and not force_update:
if self.time_to_live:
age = now - cached_time
if age <= self.time_to_live:
logger.debug('cache contents still valid')
return cached_content
else:
logger.debug('cache contents older than TTL')
else:
logger.debug('no TTL value')
# The cache is out of date, but we have
# something. Try to use the etag and modified_time
# values from the cached content.
etag = cached_content.get('etag')
modified = cached_content.get('modified')
logger.debug('cached etag=%s' % etag)
logger.debug('cached modified=%s' % str(modified))
else:
logger.debug('nothing in the cache, or forcing update')
# We know we need to fetch, so go ahead and do it.
logger.debug('fetching...')
parsed_result = feedparser.parse(url,
agent=self.user_agent,
modified=modified,
etag=etag,
request_headers=request_headers)
status = parsed_result.get('status', None)
logger.debug('HTTP status=%s' % status)
if status == 304:
# No new data, based on the etag or modified values.
# We need to update the modified time in the
# storage, though, so we know that what we have
# stored is up to date.
self.storage[key] = (now, cached_content)
# Return the data from the cache, since
# the parsed data will be empty.
parsed_result = cached_content
elif status == 200:
# There is new content, so store it unless there was an error.
error = parsed_result.get('bozo_exception')
if not error:
logger.debug('Updating stored data for %s' % url)
self.storage[key] = (now, parsed_result)
else:
logger.warning('Not storing data with exception: %s',
error)
else:
logger.warning('Not updating cache with HTTP status %s', status)
return parsed_result

69
lib/feedcache/cachestoragelock.py
View file

@ -1,69 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
from __future__ import with_statement
"""Lock wrapper for cache storage which do not permit multi-threaded access.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import threading
#
# Import local modules
#
#
# Module
#
class CacheStorageLock:
"""Lock wrapper for cache storage which do not permit multi-threaded access.
"""
def __init__(self, shelf):
self.lock = threading.Lock()
self.shelf = shelf
return
def __getitem__(self, key):
with self.lock:
return self.shelf[key]
def get(self, key, default=None):
with self.lock:
try:
return self.shelf[key]
except KeyError:
return default
def __setitem__(self, key, value):
with self.lock:
self.shelf[key] = value

63
lib/feedcache/example.py
View file

@ -1,63 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Example use of feedcache.Cache.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import sys
import shelve
#
# Import local modules
#
import cache
#
# Module
#
def main(urls=[]):
print 'Saving feed data to ./.feedcache'
storage = shelve.open('.feedcache')
try:
fc = cache.Cache(storage)
for url in urls:
parsed_data = fc.fetch(url)
print parsed_data.feed.title
for entry in parsed_data.entries:
print '\t', entry.title
finally:
storage.close()
return
if __name__ == '__main__':
main(sys.argv[1:])

144
lib/feedcache/example_threads.py
View file

@ -1,144 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Example use of feedcache.Cache combined with threads.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import Queue
import sys
import shove
import threading
#
# Import local modules
#
import cache
#
# Module
#
MAX_THREADS=5
OUTPUT_DIR='/tmp/feedcache_example'
def main(urls=[]):
if not urls:
print 'Specify the URLs to a few RSS or Atom feeds on the command line.'
return
# Decide how many threads to start
num_threads = min(len(urls), MAX_THREADS)
# Add the URLs to a queue
url_queue = Queue.Queue()
for url in urls:
url_queue.put(url)
# Add poison pills to the url queue to cause
# the worker threads to break out of their loops
for i in range(num_threads):
url_queue.put(None)
# Track the entries in the feeds being fetched
entry_queue = Queue.Queue()
print 'Saving feed data to', OUTPUT_DIR
storage = shove.Shove('file://' + OUTPUT_DIR)
try:
# Start a few worker threads
worker_threads = []
for i in range(num_threads):
t = threading.Thread(target=fetch_urls,
args=(storage, url_queue, entry_queue,))
worker_threads.append(t)
t.setDaemon(True)
t.start()
# Start a thread to print the results
printer_thread = threading.Thread(target=print_entries, args=(entry_queue,))
printer_thread.setDaemon(True)
printer_thread.start()
# Wait for all of the URLs to be processed
url_queue.join()
# Wait for the worker threads to finish
for t in worker_threads:
t.join()
# Poison the print thread and wait for it to exit
entry_queue.put((None,None))
entry_queue.join()
printer_thread.join()
finally:
storage.close()
return
def fetch_urls(storage, input_queue, output_queue):
"""Thread target for fetching feed data.
"""
c = cache.Cache(storage)
while True:
next_url = input_queue.get()
if next_url is None: # None causes thread to exit
input_queue.task_done()
break
feed_data = c.fetch(next_url)
for entry in feed_data.entries:
output_queue.put( (feed_data.feed, entry) )
input_queue.task_done()
return
def print_entries(input_queue):
"""Thread target for printing the contents of the feeds.
"""
while True:
feed, entry = input_queue.get()
if feed is None: # None causes thread to exist
input_queue.task_done()
break
print '%s: %s' % (feed.title, entry.title)
input_queue.task_done()
return
if __name__ == '__main__':
main(sys.argv[1:])

323
lib/feedcache/test_cache.py
View file

@ -1,323 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Unittests for feedcache.cache
"""
__module_id__ = "$Id$"
import logging
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)-8s %(name)s %(message)s',
)
logger = logging.getLogger('feedcache.test_cache')
#
# Import system modules
#
import copy
import time
import unittest
import UserDict
#
# Import local modules
#
import cache
from test_server import HTTPTestBase, TestHTTPServer
#
# Module
#
class CacheTestBase(HTTPTestBase):
CACHE_TTL = 30
def setUp(self):
HTTPTestBase.setUp(self)
self.storage = self.getStorage()
self.cache = cache.Cache(self.storage,
timeToLiveSeconds=self.CACHE_TTL,
userAgent='feedcache.test',
)
return
def getStorage(self):
"Return a cache storage for the test."
return {}
class CacheTest(CacheTestBase):
CACHE_TTL = 30
def getServer(self):
"These tests do not want to use the ETag or If-Modified-Since headers"
return TestHTTPServer(applyModifiedHeaders=False)
def testRetrieveNotInCache(self):
# Retrieve data not already in the cache.
feed_data = self.cache.fetch(self.TEST_URL)
self.failUnless(feed_data)
self.failUnlessEqual(feed_data.feed.title, 'CacheTest test data')
return
def testRetrieveIsInCache(self):
# Retrieve data which is alread in the cache,
# and verify that the second copy is identitical
# to the first.
# First fetch
feed_data = self.cache.fetch(self.TEST_URL)
# Second fetch
feed_data2 = self.cache.fetch(self.TEST_URL)
# Since it is the in-memory storage, we should have the
# exact same object.
self.failUnless(feed_data is feed_data2)
return
def testExpireDataInCache(self):
# Retrieve data which is in the cache but which
# has expired and verify that the second copy
# is different from the first.
# First fetch
feed_data = self.cache.fetch(self.TEST_URL)
# Change the timeout and sleep to move the clock
self.cache.time_to_live = 0
time.sleep(1)
# Second fetch
feed_data2 = self.cache.fetch(self.TEST_URL)
# Since we reparsed, the cache response should be different.
self.failIf(feed_data is feed_data2)
return
def testForceUpdate(self):
# Force cache to retrieve data which is alread in the cache,
# and verify that the new data is different.
# Pre-populate the storage with bad data
self.cache.storage[self.TEST_URL] = (time.time() + 100, self.id())
# Fetch the data
feed_data = self.cache.fetch(self.TEST_URL, force_update=True)
self.failIfEqual(feed_data, self.id())
return
def testOfflineMode(self):
# Retrieve data which is alread in the cache,
# whether it is expired or not.
# Pre-populate the storage with data
self.cache.storage[self.TEST_URL] = (0, self.id())
# Fetch it
feed_data = self.cache.fetch(self.TEST_URL, offline=True)
self.failUnlessEqual(feed_data, self.id())
return
def testUnicodeURL(self):
# Pass in a URL which is unicode
url = unicode(self.TEST_URL)
feed_data = self.cache.fetch(url)
storage = self.cache.storage
key = unicode(self.TEST_URL).encode('UTF-8')
# Verify that the storage has a key
self.failUnless(key in storage)
# Now pull the data from the storage directly
storage_timeout, storage_data = self.cache.storage.get(key)
self.failUnlessEqual(feed_data, storage_data)
return
class SingleWriteMemoryStorage(UserDict.UserDict):
"""Cache storage which only allows the cache value
for a URL to be updated one time.
"""
def __setitem__(self, url, data):
if url in self.keys():
modified, existing = self[url]
# Allow the modified time to change,
# but not the feed content.
if data[1] != existing:
raise AssertionError('Trying to update cache for %s to %s' \
% (url, data))
UserDict.UserDict.__setitem__(self, url, data)
return
class CacheConditionalGETTest(CacheTestBase):
CACHE_TTL = 0
def getStorage(self):
return SingleWriteMemoryStorage()
def testFetchOnceForEtag(self):
# Fetch data which has a valid ETag value, and verify
# that while we hit the server twice the response
# codes cause us to use the same data.
# First fetch populates the cache
response1 = self.cache.fetch(self.TEST_URL)
self.failUnlessEqual(response1.feed.title, 'CacheTest test data')
# Remove the modified setting from the cache so we know
# the next time we check the etag will be used
# to check for updates. Since we are using an in-memory
# cache, modifying response1 updates the cache storage
# directly.
response1['modified'] = None
# This should result in a 304 status, and no data from
# the server. That means the cache won't try to
# update the storage, so our SingleWriteMemoryStorage
# should not raise and we should have the same
# response object.
response2 = self.cache.fetch(self.TEST_URL)
self.failUnless(response1 is response2)
# Should have hit the server twice
self.failUnlessEqual(self.server.getNumRequests(), 2)
return
def testFetchOnceForModifiedTime(self):
# Fetch data which has a valid Last-Modified value, and verify
# that while we hit the server twice the response
# codes cause us to use the same data.
# First fetch populates the cache
response1 = self.cache.fetch(self.TEST_URL)
self.failUnlessEqual(response1.feed.title, 'CacheTest test data')
# Remove the etag setting from the cache so we know
# the next time we check the modified time will be used
# to check for updates. Since we are using an in-memory
# cache, modifying response1 updates the cache storage
# directly.
response1['etag'] = None
# This should result in a 304 status, and no data from
# the server. That means the cache won't try to
# update the storage, so our SingleWriteMemoryStorage
# should not raise and we should have the same
# response object.
response2 = self.cache.fetch(self.TEST_URL)
self.failUnless(response1 is response2)
# Should have hit the server twice
self.failUnlessEqual(self.server.getNumRequests(), 2)
return
class CacheRedirectHandlingTest(CacheTestBase):
def _test(self, response):
# Set up the server to redirect requests,
# then verify that the cache is not updated
# for the original or new URL and that the
# redirect status is fed back to us with
# the fetched data.
self.server.setResponse(response, '/redirected')
response1 = self.cache.fetch(self.TEST_URL)
# The response should include the status code we set
self.failUnlessEqual(response1.get('status'), response)
# The response should include the new URL, too
self.failUnlessEqual(response1.href, self.TEST_URL + 'redirected')
# The response should not have been cached under either URL
self.failIf(self.TEST_URL in self.storage)
self.failIf(self.TEST_URL + 'redirected' in self.storage)
return
def test301(self):
self._test(301)
def test302(self):
self._test(302)
def test303(self):
self._test(303)
def test307(self):
self._test(307)
class CachePurgeTest(CacheTestBase):
def testPurgeAll(self):
# Remove everything from the cache
self.cache.fetch(self.TEST_URL)
self.failUnless(self.storage.keys(),
'Have no data in the cache storage')
self.cache.purge(None)
self.failIf(self.storage.keys(),
'Still have data in the cache storage')
return
def testPurgeByAge(self):
# Remove old content from the cache
self.cache.fetch(self.TEST_URL)
self.failUnless(self.storage.keys(),
'have no data in the cache storage')
time.sleep(1)
remains = (time.time(), copy.deepcopy(self.storage[self.TEST_URL][1]))
self.storage['http://this.should.remain/'] = remains
self.cache.purge(1)
self.failUnlessEqual(self.storage.keys(),
['http://this.should.remain/'])
return
if __name__ == '__main__':
unittest.main()

90
lib/feedcache/test_cachestoragelock.py
View file

@ -1,90 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Tests for shelflock.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import os
import shelve
import tempfile
import threading
import unittest
#
# Import local modules
#
from cache import Cache
from cachestoragelock import CacheStorageLock
from test_server import HTTPTestBase
#
# Module
#
class CacheShelveTest(HTTPTestBase):
def setUp(self):
HTTPTestBase.setUp(self)
handle, self.shelve_filename = tempfile.mkstemp('.shelve')
os.close(handle) # we just want the file name, so close the open handle
os.unlink(self.shelve_filename) # remove the empty file
return
def tearDown(self):
try:
os.unlink(self.shelve_filename)
except AttributeError:
pass
HTTPTestBase.tearDown(self)
return
def test(self):
storage = shelve.open(self.shelve_filename)
locking_storage = CacheStorageLock(storage)
try:
fc = Cache(locking_storage)
# First fetch the data through the cache
parsed_data = fc.fetch(self.TEST_URL)
self.failUnlessEqual(parsed_data.feed.title, 'CacheTest test data')
# Now retrieve the same data directly from the shelf
modified, shelved_data = storage[self.TEST_URL]
# The data should be the same
self.failUnlessEqual(parsed_data, shelved_data)
finally:
storage.close()
return
if __name__ == '__main__':
unittest.main()

241
lib/feedcache/test_server.py
View file

@ -1,241 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Simple HTTP server for testing the feed cache.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import BaseHTTPServer
import logging
import md5
import threading
import time
import unittest
import urllib
#
# Import local modules
#
#
# Module
#
logger = logging.getLogger('feedcache.test_server')
def make_etag(data):
"""Given a string containing data to be returned to the client,
compute an ETag value for the data.
"""
_md5 = md5.new()
_md5.update(data)
return _md5.hexdigest()
class TestHTTPHandler(BaseHTTPServer.BaseHTTPRequestHandler):
"HTTP request handler which serves the same feed data every time."
FEED_DATA = """<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-us">
<title>CacheTest test data</title>
<link href="http://localhost/feedcache/" rel="alternate"></link>
<link href="http://localhost/feedcache/atom/" rel="self"></link>
<id>http://localhost/feedcache/</id>
<updated>2006-10-14T11:00:36Z</updated>
<entry>
<title>single test entry</title>
<link href="http://www.example.com/" rel="alternate"></link>
<updated>2006-10-14T11:00:36Z</updated>
<author>
<name>author goes here</name>
<email>authoremail@example.com</email>
</author>
<id>http://www.example.com/</id>
<summary type="html">description goes here</summary>
<link length="100" href="http://www.example.com/enclosure" type="text/html" rel="enclosure">
</link>
</entry>
</feed>"""
# The data does not change, so save the ETag and modified times
# as class attributes.
ETAG = make_etag(FEED_DATA)
# Calculated using email.utils.formatdate(usegmt=True)
MODIFIED_TIME = 'Sun, 08 Apr 2012 20:16:48 GMT'
def do_GET(self):
"Handle GET requests."
logger.debug('GET %s', self.path)
if self.path == '/shutdown':
# Shortcut to handle stopping the server
logger.debug('Stopping server')
self.server.stop()
self.send_response(200)
else:
# Record the request for tests that count them
self.server.requests.append(self.path)
# Process the request
logger.debug('pre-defined response code: %d', self.server.response)
handler_method_name = 'do_GET_%d' % self.server.response
handler_method = getattr(self, handler_method_name)
handler_method()
return
def do_GET_3xx(self):
"Handle redirects"
if self.path.endswith('/redirected'):
logger.debug('already redirected')
# We have already redirected, so return the data.
return self.do_GET_200()
new_path = self.server.new_path
logger.debug('redirecting to %s', new_path)
self.send_response(self.server.response)
self.send_header('Location', new_path)
return
do_GET_301 = do_GET_3xx
do_GET_302 = do_GET_3xx
do_GET_303 = do_GET_3xx
do_GET_307 = do_GET_3xx
def do_GET_200(self):
logger.debug('Etag: %s' % self.ETAG)
logger.debug('Last-Modified: %s' % self.MODIFIED_TIME)
incoming_etag = self.headers.get('If-None-Match', None)
logger.debug('Incoming ETag: "%s"' % incoming_etag)
incoming_modified = self.headers.get('If-Modified-Since', None)
logger.debug('Incoming If-Modified-Since: %s' % incoming_modified)
send_data = True
# Does the client have the same version of the data we have?
if self.server.apply_modified_headers:
if incoming_etag == self.ETAG:
logger.debug('Response 304, etag')
self.send_response(304)
send_data = False
elif incoming_modified == self.MODIFIED_TIME:
logger.debug('Response 304, modified time')
self.send_response(304)
send_data = False
# Now optionally send the data, if the client needs it
if send_data:
logger.debug('Response 200')
self.send_response(200)
self.send_header('Content-Type', 'application/atom+xml')
logger.debug('Outgoing Etag: %s' % self.ETAG)
self.send_header('ETag', self.ETAG)
logger.debug('Outgoing modified time: %s' % self.MODIFIED_TIME)
self.send_header('Last-Modified', self.MODIFIED_TIME)
self.end_headers()
logger.debug('Sending data')
self.wfile.write(self.FEED_DATA)
return
class TestHTTPServer(BaseHTTPServer.HTTPServer):
"""HTTP Server which counts the number of requests made
and can stop based on client instructions.
"""
def __init__(self, applyModifiedHeaders=True, handler=TestHTTPHandler):
self.apply_modified_headers = applyModifiedHeaders
self.keep_serving = True
self.requests = []
self.setResponse(200)
BaseHTTPServer.HTTPServer.__init__(self, ('', 9999), handler)
return
def setResponse(self, newResponse, newPath=None):
"""Sets the response code to use for future requests, and a new
path to be used as a redirect target, if necessary.
"""
self.response = newResponse
self.new_path = newPath
return
def getNumRequests(self):
"Return the number of requests which have been made on the server."
return len(self.requests)
def stop(self):
"Stop serving requests, after the next request."
self.keep_serving = False
return
def serve_forever(self):
"Main loop for server"
while self.keep_serving:
self.handle_request()
logger.debug('exiting')
return
class HTTPTestBase(unittest.TestCase):
"Base class for tests that use a TestHTTPServer"
TEST_URL = 'http://localhost:9999/'
CACHE_TTL = 0
def setUp(self):
self.server = self.getServer()
self.server_thread = threading.Thread(target=self.server.serve_forever)
# set daemon flag so the tests don't hang if cleanup fails
self.server_thread.setDaemon(True)
self.server_thread.start()
return
def getServer(self):
"Return a web server for the test."
s = TestHTTPServer()
s.setResponse(200)
return s
def tearDown(self):
# Stop the server thread
urllib.urlretrieve(self.TEST_URL + 'shutdown')
time.sleep(1)
self.server.server_close()
self.server_thread.join()
return

89
lib/feedcache/test_shovefilesystem.py
View file

@ -1,89 +0,0 @@
#!/usr/bin/env python
#
# Copyright 2007 Doug Hellmann.
#
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
"""Tests with shove filesystem storage.
"""
__module_id__ = "$Id$"
#
# Import system modules
#
import os
import shove
import tempfile
import threading
import unittest
#
# Import local modules
#
from cache import Cache
from test_server import HTTPTestBase
#
# Module
#
class CacheShoveTest(HTTPTestBase):
def setUp(self):
HTTPTestBase.setUp(self)
self.shove_dirname = tempfile.mkdtemp('shove')
return
def tearDown(self):
try:
os.system('rm -rf %s' % self.storage_dirname)
except AttributeError:
pass
HTTPTestBase.tearDown(self)
return
def test(self):
# First fetch the data through the cache
storage = shove.Shove('file://' + self.shove_dirname)
try:
fc = Cache(storage)
parsed_data = fc.fetch(self.TEST_URL)
self.failUnlessEqual(parsed_data.feed.title, 'CacheTest test data')
finally:
storage.close()
# Now retrieve the same data directly from the shelf
storage = shove.Shove('file://' + self.shove_dirname)
try:
modified, shelved_data = storage[self.TEST_URL]
finally:
storage.close()
# The data should be the same
self.failUnlessEqual(parsed_data, shelved_data)
return
if __name__ == '__main__':
unittest.main()

30
lib/feedparser/feedparser.egg-info/PKG-INFO
View file

@ -1,30 +0,0 @@
Metadata-Version: 1.1
Name: feedparser
Version: 5.1.3
Summary: Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds
Home-page: http://code.google.com/p/feedparser/
Author: Kurt McKee
Author-email: contactme@kurtmckee.org
License: UNKNOWN
Download-URL: http://code.google.com/p/feedparser/
Description: UNKNOWN
Keywords: atom,cdf,feed,parser,rdf,rss
Platform: POSIX
Platform: Windows
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.4
Classifier: Programming Language :: Python :: 2.5
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.0
Classifier: Programming Language :: Python :: 3.1
Classifier: Programming Language :: Python :: 3.2
Classifier: Programming Language :: Python :: 3.3
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Markup :: XML

2480
lib/feedparser/feedparser.egg-info/SOURCES.txt
View file

File diff suppressed because it is too large Load diff

1
lib/feedparser/feedparser.egg-info/dependency_links.txt
View file

@ -1 +0,0 @@

1
lib/feedparser/feedparser.egg-info/top_level.txt
View file

@ -1 +0,0 @@
feedparser

1492
lib/feedparser/feedparser.py
View file

File diff suppressed because it is too large Load diff

859
lib/feedparser/feedparsertest.py
View file

@ -1,859 +0,0 @@
#!/usr/bin/env python
__author__ = "Mark Pilgrim <http://diveintomark.org/>"
__license__ = """
Copyright (c) 2010-2012 Kurt McKee <contactme@kurtmckee.org>
Copyright (c) 2004-2008 Mark Pilgrim
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE."""
import codecs
import datetime
import glob
import operator
import os
import posixpath
import pprint
import re
import struct
import sys
import threading
import time
import unittest
import urllib
import warnings
import zlib
import BaseHTTPServer
import SimpleHTTPServer
import feedparser
if not feedparser._XML_AVAILABLE:
sys.stderr.write('No XML parsers available, unit testing can not proceed\n')
sys.exit(1)
try:
# the utf_32 codec was introduced in Python 2.6; it's necessary to
# check this as long as feedparser supports Python 2.4 and 2.5
codecs.lookup('utf_32')
except LookupError:
_UTF32_AVAILABLE = False
else:
_UTF32_AVAILABLE = True
_s2bytes = feedparser._s2bytes
_l2bytes = feedparser._l2bytes
#---------- custom HTTP server (used to serve test feeds) ----------
_PORT = 8097 # not really configurable, must match hardcoded port in tests
_HOST = '127.0.0.1' # also not really configurable
class FeedParserTestRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
headers_re = re.compile(_s2bytes(r"^Header:\s+([^:]+):(.+)$"), re.MULTILINE)
def send_head(self):
"""Send custom headers defined in test case
Example:
<!--
Header: Content-type: application/atom+xml
Header: X-Foo: bar
-->
"""
# Short-circuit the HTTP status test `test_redirect_to_304()`
if self.path == '/-/return-304.xml':
self.send_response(304)
self.send_header('Content-type', 'text/xml')
self.end_headers()
return feedparser._StringIO(u''.encode('utf-8'))
path = self.translate_path(self.path)
# the compression tests' filenames determine the header sent
if self.path.startswith('/tests/compression'):
if self.path.endswith('gz'):
headers = {'Content-Encoding': 'gzip'}
else:
headers = {'Content-Encoding': 'deflate'}
headers['Content-type'] = 'application/xml'
else:
headers = dict([(k.decode('utf-8'), v.decode('utf-8').strip()) for k, v in self.headers_re.findall(open(path, 'rb').read())])
f = open(path, 'rb')
if (self.headers.get('if-modified-since') == headers.get('Last-Modified', 'nom')) \
or (self.headers.get('if-none-match') == headers.get('ETag', 'nomatch')):
status = 304
else:
status = 200
headers.setdefault('Status', status)
self.send_response(int(headers['Status']))
headers.setdefault('Content-type', self.guess_type(path))
self.send_header("Content-type", headers['Content-type'])
self.send_header("Content-Length", str(os.stat(f.name)[6]))
for k, v in headers.items():
if k not in ('Status', 'Content-type'):
self.send_header(k, v)
self.end_headers()
return f
def log_request(self, *args):
pass
class FeedParserTestServer(threading.Thread):
"""HTTP Server that runs in a thread and handles a predetermined number of requests"""
def __init__(self, requests):
threading.Thread.__init__(self)
self.requests = requests
self.ready = threading.Event()
def run(self):
self.httpd = BaseHTTPServer.HTTPServer((_HOST, _PORT), FeedParserTestRequestHandler)
self.ready.set()
while self.requests:
self.httpd.handle_request()
self.requests -= 1
self.ready.clear()
#---------- dummy test case class (test methods are added dynamically) ----------
unicode1_re = re.compile(_s2bytes(" u'"))
unicode2_re = re.compile(_s2bytes(' u"'))
# _bytes is only used in everythingIsUnicode().
# In Python 2 it's str, and in Python 3 it's bytes.
_bytes = type(_s2bytes(''))
def everythingIsUnicode(d):
"""Takes a dictionary, recursively verifies that every value is unicode"""
for k, v in d.iteritems():
if isinstance(v, dict) and k != 'headers':
if not everythingIsUnicode(v):
return False
elif isinstance(v, list):
for i in v:
if isinstance(i, dict) and not everythingIsUnicode(i):
return False
elif isinstance(i, _bytes):
return False
elif isinstance(v, _bytes):
return False
return True
def failUnlessEval(self, xmlfile, evalString, msg=None):
"""Fail unless eval(evalString, env)"""
env = feedparser.parse(xmlfile)
try:
if not eval(evalString, globals(), env):
failure=(msg or 'not eval(%s) \nWITH env(%s)' % (evalString, pprint.pformat(env)))
raise self.failureException, failure
if not everythingIsUnicode(env):
raise self.failureException, "not everything is unicode \nWITH env(%s)" % (pprint.pformat(env), )
except SyntaxError:
# Python 3 doesn't have the `u""` syntax, so evalString needs to be modified,
# which will require the failure message to be updated
evalString = re.sub(unicode1_re, _s2bytes(" '"), evalString)
evalString = re.sub(unicode2_re, _s2bytes(' "'), evalString)
if not eval(evalString, globals(), env):
failure=(msg or 'not eval(%s) \nWITH env(%s)' % (evalString, pprint.pformat(env)))
raise self.failureException, failure
class BaseTestCase(unittest.TestCase):
failUnlessEval = failUnlessEval
class TestCase(BaseTestCase):
pass
class TestTemporaryFallbackBehavior(unittest.TestCase):
"These tests are temporarily here because of issues 310 and 328"
def test_issue_328_fallback_behavior(self):
warnings.filterwarnings('error')
d = feedparser.FeedParserDict()
d['published'] = u'pub string'
d['published_parsed'] = u'pub tuple'
d['updated'] = u'upd string'
d['updated_parsed'] = u'upd tuple'
# Ensure that `updated` doesn't map to `published` when it exists
self.assertTrue('published' in d)
self.assertTrue('published_parsed' in d)
self.assertTrue('updated' in d)
self.assertTrue('updated_parsed' in d)
self.assertEqual(d['published'], 'pub string')
self.assertEqual(d['published_parsed'], 'pub tuple')
self.assertEqual(d['updated'], 'upd string')
self.assertEqual(d['updated_parsed'], 'upd tuple')
d = feedparser.FeedParserDict()
d['published'] = u'pub string'
d['published_parsed'] = u'pub tuple'
# Ensure that `updated` doesn't actually exist
self.assertTrue('updated' not in d)
self.assertTrue('updated_parsed' not in d)
# Ensure that accessing `updated` throws a DeprecationWarning
try:
d['updated']
except DeprecationWarning:
# Expected behavior
pass
else:
# Wrong behavior
self.assertEqual(True, False)
try:
d['updated_parsed']
except DeprecationWarning:
# Expected behavior
pass
else:
# Wrong behavior
self.assertEqual(True, False)
# Ensure that `updated` maps to `published`
warnings.filterwarnings('ignore')
self.assertEqual(d['updated'], u'pub string')
self.assertEqual(d['updated_parsed'], u'pub tuple')
warnings.resetwarnings()
class TestEverythingIsUnicode(unittest.TestCase):
"Ensure that `everythingIsUnicode()` is working appropriately"
def test_everything_is_unicode(self):
self.assertTrue(everythingIsUnicode(
{'a': u'a', 'b': [u'b', {'c': u'c'}], 'd': {'e': u'e'}}
))
def test_not_everything_is_unicode(self):
self.assertFalse(everythingIsUnicode({'a': _s2bytes('a')}))
self.assertFalse(everythingIsUnicode({'a': [_s2bytes('a')]}))
self.assertFalse(everythingIsUnicode({'a': {'b': _s2bytes('b')}}))
self.assertFalse(everythingIsUnicode({'a': [{'b': _s2bytes('b')}]}))
class TestLooseParser(BaseTestCase):
"Test the sgmllib-based parser by manipulating feedparser " \
"into believing no XML parsers are installed"
def __init__(self, arg):
unittest.TestCase.__init__(self, arg)
self._xml_available = feedparser._XML_AVAILABLE
def setUp(self):
feedparser._XML_AVAILABLE = 0
def tearDown(self):
feedparser._XML_AVAILABLE = self._xml_available
class TestStrictParser(BaseTestCase):
pass
class TestMicroformats(BaseTestCase):
pass
class TestEncodings(BaseTestCase):
def test_doctype_replacement(self):
"Ensure that non-ASCII-compatible encodings don't hide " \
"disallowed ENTITY declarations"
doc = """<?xml version="1.0" encoding="utf-16be"?>
<!DOCTYPE feed [
<!ENTITY exponential1 "bogus ">
<!ENTITY exponential2 "&exponential1;&exponential1;">
<!ENTITY exponential3 "&exponential2;&exponential2;">
]>
<feed><title type="html">&exponential3;</title></feed>"""
doc = codecs.BOM_UTF16_BE + doc.encode('utf-16be')
result = feedparser.parse(doc)
self.assertEqual(result['feed']['title'], u'&amp;exponential3')
def test_gb2312_converted_to_gb18030_in_xml_encoding(self):
# \u55de was chosen because it exists in gb18030 but not gb2312
feed = u'''<?xml version="1.0" encoding="gb2312"?>
<feed><title>\u55de</title></feed>'''
result = feedparser.parse(feed.encode('gb18030'), response_headers={
'Content-Type': 'text/xml'
})
self.assertEqual(result.encoding, 'gb18030')
class TestFeedParserDict(unittest.TestCase):
"Ensure that FeedParserDict returns values as expected and won't crash"
def setUp(self):
self.d = feedparser.FeedParserDict()
def _check_key(self, k):
self.assertTrue(k in self.d)
self.assertTrue(hasattr(self.d, k))
self.assertEqual(self.d[k], 1)
self.assertEqual(getattr(self.d, k), 1)
def _check_no_key(self, k):
self.assertTrue(k not in self.d)
self.assertTrue(not hasattr(self.d, k))
def test_empty(self):
keys = (
'a','entries', 'id', 'guid', 'summary', 'subtitle', 'description',
'category', 'enclosures', 'license', 'categories',
)
for k in keys:
self._check_no_key(k)
self.assertTrue('items' not in self.d)
self.assertTrue(hasattr(self.d, 'items')) # dict.items() exists
def test_neutral(self):
self.d['a'] = 1
self._check_key('a')
def test_single_mapping_target_1(self):
self.d['id'] = 1
self._check_key('id')
self._check_key('guid')
def test_single_mapping_target_2(self):
self.d['guid'] = 1
self._check_key('id')
self._check_key('guid')
def test_multiple_mapping_target_1(self):
self.d['summary'] = 1
self._check_key('summary')
self._check_key('description')
def test_multiple_mapping_target_2(self):
self.d['subtitle'] = 1
self._check_key('subtitle')
self._check_key('description')
def test_multiple_mapping_mapped_key(self):
self.d['description'] = 1
self._check_key('summary')
self._check_key('description')
def test_license(self):
self.d['links'] = []
try:
self.d['license']
self.assertTrue(False)
except KeyError:
pass
self.d['links'].append({'rel': 'license'})
try:
self.d['license']
self.assertTrue(False)
except KeyError:
pass
self.d['links'].append({'rel': 'license', 'href': 'http://dom.test/'})
self.assertEqual(self.d['license'], 'http://dom.test/')
def test_category(self):
self.d['tags'] = []
try:
self.d['category']
self.assertTrue(False)
except KeyError:
pass
self.d['tags'] = [{}]
try:
self.d['category']
self.assertTrue(False)
except KeyError:
pass
self.d['tags'] = [{'term': 'cat'}]
self.assertEqual(self.d['category'], 'cat')
self.d['tags'].append({'term': 'dog'})
self.assertEqual(self.d['category'], 'cat')
class TestOpenResource(unittest.TestCase):
"Ensure that `_open_resource()` interprets its arguments as URIs, " \
"file-like objects, or in-memory feeds as expected"
def test_fileobj(self):
r = feedparser._open_resource(sys.stdin, '', '', '', '', [], {})
self.assertTrue(r is sys.stdin)
def test_feed(self):
f = feedparser.parse(u'feed://localhost:8097/tests/http/target.xml')
self.assertEqual(f.href, u'http://localhost:8097/tests/http/target.xml')
def test_feed_http(self):
f = feedparser.parse(u'feed:http://localhost:8097/tests/http/target.xml')
self.assertEqual(f.href, u'http://localhost:8097/tests/http/target.xml')
def test_bytes(self):
s = '<feed><item><title>text</title></item></feed>'.encode('utf-8')
r = feedparser._open_resource(s, '', '', '', '', [], {})
self.assertEqual(s, r.read())
def test_string(self):
s = '<feed><item><title>text</title></item></feed>'
r = feedparser._open_resource(s, '', '', '', '', [], {})
self.assertEqual(s.encode('utf-8'), r.read())
def test_unicode_1(self):
s = u'<feed><item><title>text</title></item></feed>'
r = feedparser._open_resource(s, '', '', '', '', [], {})
self.assertEqual(s.encode('utf-8'), r.read())
def test_unicode_2(self):
s = u'<feed><item><title>t\u00e9xt</title></item></feed>'
r = feedparser._open_resource(s, '', '', '', '', [], {})
self.assertEqual(s.encode('utf-8'), r.read())
class TestMakeSafeAbsoluteURI(unittest.TestCase):
"Exercise the URI joining and sanitization code"
base = u'http://d.test/d/f.ext'
def _mktest(rel, expect, doc):
def fn(self):
value = feedparser._makeSafeAbsoluteURI(self.base, rel)
self.assertEqual(value, expect)
fn.__doc__ = doc
return fn
# make the test cases; the call signature is:
# (relative_url, expected_return_value, test_doc_string)
test_abs = _mktest(u'https://s.test/', u'https://s.test/', 'absolute uri')
test_rel = _mktest(u'/new', u'http://d.test/new', 'relative uri')
test_bad = _mktest(u'x://bad.test/', u'', 'unacceptable uri protocol')
test_mag = _mktest(u'magnet:?xt=a', u'magnet:?xt=a', 'magnet uri')
def test_catch_ValueError(self):
'catch ValueError in Python 2.7 and up'
uri = u'http://bad]test/'
value1 = feedparser._makeSafeAbsoluteURI(uri)
value2 = feedparser._makeSafeAbsoluteURI(self.base, uri)
swap = feedparser.ACCEPTABLE_URI_SCHEMES
feedparser.ACCEPTABLE_URI_SCHEMES = ()
value3 = feedparser._makeSafeAbsoluteURI(self.base, uri)
feedparser.ACCEPTABLE_URI_SCHEMES = swap
# Only Python 2.7 and up throw a ValueError, otherwise uri is returned
self.assertTrue(value1 in (uri, u''))
self.assertTrue(value2 in (uri, u''))
self.assertTrue(value3 in (uri, u''))
class TestConvertToIdn(unittest.TestCase):
"Test IDN support (unavailable in Jython as of Jython 2.5.2)"
# this is the greek test domain
hostname = u'\u03c0\u03b1\u03c1\u03ac\u03b4\u03b5\u03b9\u03b3\u03bc\u03b1'
hostname += u'.\u03b4\u03bf\u03ba\u03b9\u03bc\u03ae'
def test_control(self):
r = feedparser._convert_to_idn(u'http://example.test/')
self.assertEqual(r, u'http://example.test/')
def test_idn(self):
r = feedparser._convert_to_idn(u'http://%s/' % (self.hostname,))
self.assertEqual(r, u'http://xn--hxajbheg2az3al.xn--jxalpdlp/')
def test_port(self):
r = feedparser._convert_to_idn(u'http://%s:8080/' % (self.hostname,))
self.assertEqual(r, u'http://xn--hxajbheg2az3al.xn--jxalpdlp:8080/')
class TestCompression(unittest.TestCase):
"Test the gzip and deflate support in the HTTP code"
def test_gzip_good(self):
f = feedparser.parse('http://localhost:8097/tests/compression/gzip.gz')
self.assertEqual(f.version, 'atom10')
def test_gzip_not_compressed(self):
f = feedparser.parse('http://localhost:8097/tests/compression/gzip-not-compressed.gz')
self.assertEqual(f.bozo, 1)
self.assertTrue(isinstance(f.bozo_exception, IOError))
self.assertEqual(f['feed']['title'], 'gzip')
def test_gzip_struct_error(self):
f = feedparser.parse('http://localhost:8097/tests/compression/gzip-struct-error.gz')
self.assertEqual(f.bozo, 1)
self.assertTrue(isinstance(f.bozo_exception, struct.error))
def test_zlib_good(self):
f = feedparser.parse('http://localhost:8097/tests/compression/deflate.z')
self.assertEqual(f.version, 'atom10')
def test_zlib_no_headers(self):
f = feedparser.parse('http://localhost:8097/tests/compression/deflate-no-headers.z')
self.assertEqual(f.version, 'atom10')
def test_zlib_not_compressed(self):
f = feedparser.parse('http://localhost:8097/tests/compression/deflate-not-compressed.z')
self.assertEqual(f.bozo, 1)
self.assertTrue(isinstance(f.bozo_exception, zlib.error))
self.assertEqual(f['feed']['title'], 'deflate')
class TestHTTPStatus(unittest.TestCase):
"Test HTTP redirection and other status codes"
def test_301(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_301.xml')
self.assertEqual(f.status, 301)
self.assertEqual(f.href, 'http://localhost:8097/tests/http/target.xml')
self.assertEqual(f.entries[0].title, 'target')
def test_302(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_302.xml')
self.assertEqual(f.status, 302)
self.assertEqual(f.href, 'http://localhost:8097/tests/http/target.xml')
self.assertEqual(f.entries[0].title, 'target')
def test_303(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_303.xml')
self.assertEqual(f.status, 303)
self.assertEqual(f.href, 'http://localhost:8097/tests/http/target.xml')
self.assertEqual(f.entries[0].title, 'target')
def test_307(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_307.xml')
self.assertEqual(f.status, 307)
self.assertEqual(f.href, 'http://localhost:8097/tests/http/target.xml')
self.assertEqual(f.entries[0].title, 'target')
def test_304(self):
# first retrieve the url
u = 'http://localhost:8097/tests/http/http_status_304.xml'
f = feedparser.parse(u)
self.assertEqual(f.status, 200)
self.assertEqual(f.entries[0].title, 'title 304')
# extract the etag and last-modified headers
e = [v for k, v in f.headers.items() if k.lower() == 'etag'][0]
mh = [v for k, v in f.headers.items() if k.lower() == 'last-modified'][0]
ms = f.updated
mt = f.updated_parsed
md = datetime.datetime(*mt[0:7])
self.assertTrue(isinstance(mh, basestring))
self.assertTrue(isinstance(ms, basestring))
self.assertTrue(isinstance(mt, time.struct_time))
self.assertTrue(isinstance(md, datetime.datetime))
# test that sending back the etag results in a 304
f = feedparser.parse(u, etag=e)
self.assertEqual(f.status, 304)
# test that sending back last-modified (string) results in a 304
f = feedparser.parse(u, modified=ms)
self.assertEqual(f.status, 304)
# test that sending back last-modified (9-tuple) results in a 304
f = feedparser.parse(u, modified=mt)
self.assertEqual(f.status, 304)
# test that sending back last-modified (datetime) results in a 304
f = feedparser.parse(u, modified=md)
self.assertEqual(f.status, 304)
def test_404(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_404.xml')
self.assertEqual(f.status, 404)
def test_9001(self):
f = feedparser.parse('http://localhost:8097/tests/http/http_status_9001.xml')
self.assertEqual(f.bozo, 1)
def test_redirect_to_304(self):
# ensure that an http redirect to an http 304 doesn't
# trigger a bozo_exception
u = 'http://localhost:8097/tests/http/http_redirect_to_304.xml'
f = feedparser.parse(u)
self.assertTrue(f.bozo == 0)
self.assertTrue(f.status == 302)
class TestDateParsers(unittest.TestCase):
"Test the various date parsers; most of the test cases are constructed " \
"dynamically based on the contents of the `date_tests` dict, below"
def test_None(self):
self.assertTrue(feedparser._parse_date(None) is None)
def _check_date(self, func, dtstring, dttuple):
try:
tup = func(dtstring)
except (OverflowError, ValueError):
tup = None
self.assertEqual(tup, dttuple)
self.assertEqual(tup, feedparser._parse_date(dtstring))
def test_year_10000_date(self):
# On some systems this date string will trigger an OverflowError.
# On Jython and x64 systems, however, it's interpreted just fine.
try:
date = feedparser._parse_date_rfc822(u'Sun, 31 Dec 9999 23:59:59 -9999')
except OverflowError:
date = None
self.assertTrue(date in (None, (10000, 1, 5, 4, 38, 59, 2, 5, 0)))
date_tests = {
feedparser._parse_date_greek: (
(u'', None), # empty string
(u'\u039a\u03c5\u03c1, 11 \u0399\u03bf\u03cd\u03bb 2004 12:00:00 EST', (2004, 7, 11, 17, 0, 0, 6, 193, 0)),
),
feedparser._parse_date_hungarian: (
(u'', None), # empty string
(u'2004-j\u00falius-13T9:15-05:00', (2004, 7, 13, 14, 15, 0, 1, 195, 0)),
),
feedparser._parse_date_iso8601: (
(u'', None), # empty string
(u'-0312', (2003, 12, 1, 0, 0, 0, 0, 335, 0)), # 2-digit year/month only variant
(u'031231', (2003, 12, 31, 0, 0, 0, 2, 365, 0)), # 2-digit year/month/day only, no hyphens
(u'03-12-31', (2003, 12, 31, 0, 0, 0, 2, 365, 0)), # 2-digit year/month/day only
(u'-03-12', (2003, 12, 1, 0, 0, 0, 0, 335, 0)), # 2-digit year/month only
(u'03335', (2003, 12, 1, 0, 0, 0, 0, 335, 0)), # 2-digit year/ordinal, no hyphens
(u'2003-12-31T10:14:55.1234Z', (2003, 12, 31, 10, 14, 55, 2, 365, 0)), # fractional seconds
# Special case for Google's extra zero in the month
(u'2003-012-31T10:14:55+00:00', (2003, 12, 31, 10, 14, 55, 2, 365, 0)),
),
feedparser._parse_date_nate: (
(u'', None), # empty string
(u'2004-05-25 \uc624\ud6c4 11:23:17', (2004, 5, 25, 14, 23, 17, 1, 146, 0)),
),
feedparser._parse_date_onblog: (
(u'', None), # empty string
(u'2004\ub144 05\uc6d4 28\uc77c 01:31:15', (2004, 5, 27, 16, 31, 15, 3, 148, 0)),
),
feedparser._parse_date_perforce: (
(u'', None), # empty string
(u'Fri, 2006/09/15 08:19:53 EDT', (2006, 9, 15, 12, 19, 53, 4, 258, 0)),
),
feedparser._parse_date_rfc822: (
(u'', None), # empty string
(u'Thu, 01 Jan 0100 00:00:01 +0100', (99, 12, 31, 23, 0, 1, 3, 365, 0)), # ancient date
(u'Thu, 01 Jan 04 19:48:21 GMT', (2004, 1, 1, 19, 48, 21, 3, 1, 0)), # 2-digit year
(u'Thu, 01 Jan 2004 19:48:21 GMT', (2004, 1, 1, 19, 48, 21, 3, 1, 0)), # 4-digit year
(u'Thu, 5 Apr 2012 10:00:00 GMT', (2012, 4, 5, 10, 0, 0, 3, 96, 0)), # 1-digit day
(u'Wed, 19 Aug 2009 18:28:00 Etc/GMT', (2009, 8, 19, 18, 28, 0, 2, 231, 0)), # etc/gmt timezone
(u'Wed, 19 Feb 2012 22:40:00 GMT-01:01', (2012, 2, 19, 23, 41, 0, 6, 50, 0)), # gmt+hh:mm timezone
(u'Mon, 13 Feb, 2012 06:28:00 UTC', (2012, 2, 13, 6, 28, 0, 0, 44, 0)), # extraneous comma
(u'Thu, 01 Jan 2004 00:00 GMT', (2004, 1, 1, 0, 0, 0, 3, 1, 0)), # no seconds
(u'Thu, 01 Jan 2004', (2004, 1, 1, 0, 0, 0, 3, 1, 0)), # no time
# Additional tests to handle Disney's long month names and invalid timezones
(u'Mon, 26 January 2004 16:31:00 AT', (2004, 1, 26, 20, 31, 0, 0, 26, 0)),
(u'Mon, 26 January 2004 16:31:00 ET', (2004, 1, 26, 21, 31, 0, 0, 26, 0)),
(u'Mon, 26 January 2004 16:31:00 CT', (2004, 1, 26, 22, 31, 0, 0, 26, 0)),
(u'Mon, 26 January 2004 16:31:00 MT', (2004, 1, 26, 23, 31, 0, 0, 26, 0)),
(u'Mon, 26 January 2004 16:31:00 PT', (2004, 1, 27, 0, 31, 0, 1, 27, 0)),
),
feedparser._parse_date_rfc822_grubby: (
(u'Thu Aug 30 2012 17:26:16 +0200', (2012, 8, 30, 15, 26, 16, 3, 243, 0)),
),
feedparser._parse_date_asctime: (
(u'Sun Jan 4 16:29:06 2004', (2004, 1, 4, 16, 29, 6, 6, 4, 0)),
),
feedparser._parse_date_w3dtf: (
(u'', None), # empty string
(u'2003-12-31T10:14:55Z', (2003, 12, 31, 10, 14, 55, 2, 365, 0)), # UTC
(u'2003-12-31T10:14:55-08:00', (2003, 12, 31, 18, 14, 55, 2, 365, 0)), # San Francisco timezone
(u'2003-12-31T18:14:55+08:00', (2003, 12, 31, 10, 14, 55, 2, 365, 0)), # Tokyo timezone
(u'2007-04-23T23:25:47.538+10:00', (2007, 4, 23, 13, 25, 47, 0, 113, 0)), # fractional seconds
(u'2003-12-31', (2003, 12, 31, 0, 0, 0, 2, 365, 0)), # year/month/day only
(u'20031231', (2003, 12, 31, 0, 0, 0, 2, 365, 0)), # year/month/day only, no hyphens
(u'2003-12', (2003, 12, 1, 0, 0, 0, 0, 335, 0)), # year/month only
(u'2003', (2003, 1, 1, 0, 0, 0, 2, 1, 0)), # year only
# MSSQL-style dates
(u'2004-07-08 23:56:58 -00:20', (2004, 7, 9, 0, 16, 58, 4, 191, 0)), # with timezone
(u'2004-07-08 23:56:58', (2004, 7, 8, 23, 56, 58, 3, 190, 0)), # without timezone
(u'2004-07-08 23:56:58.0', (2004, 7, 8, 23, 56, 58, 3, 190, 0)), # with fractional second
# Special cases for out-of-range times
(u'2003-12-31T25:14:55Z', (2004, 1, 1, 1, 14, 55, 3, 1, 0)), # invalid (25 hours)
(u'2003-12-31T10:61:55Z', (2003, 12, 31, 11, 1, 55, 2, 365, 0)), # invalid (61 minutes)
(u'2003-12-31T10:14:61Z', (2003, 12, 31, 10, 15, 1, 2, 365, 0)), # invalid (61 seconds)
# Special cases for rollovers in leap years
(u'2004-02-28T18:14:55-08:00', (2004, 2, 29, 2, 14, 55, 6, 60, 0)), # feb 28 in leap year
(u'2003-02-28T18:14:55-08:00', (2003, 3, 1, 2, 14, 55, 5, 60, 0)), # feb 28 in non-leap year
(u'2000-02-28T18:14:55-08:00', (2000, 2, 29, 2, 14, 55, 1, 60, 0)), # feb 28 in leap year on century divisible by 400
)
}
def make_date_test(f, s, t):
return lambda self: self._check_date(f, s, t)
for func, items in date_tests.iteritems():
for i, (dtstring, dttuple) in enumerate(items):
uniqfunc = make_date_test(func, dtstring, dttuple)
setattr(TestDateParsers, 'test_%s_%02i' % (func.__name__, i), uniqfunc)
class TestHTMLGuessing(unittest.TestCase):
"Exercise the HTML sniffing code"
def _mktest(text, expect, doc):
def fn(self):
value = bool(feedparser._FeedParserMixin.lookslikehtml(text))
self.assertEqual(value, expect)
fn.__doc__ = doc
return fn
test_text_1 = _mktest(u'plain text', False, u'plain text')
test_text_2 = _mktest(u'2 < 3', False, u'plain text with angle bracket')
test_html_1 = _mktest(u'<a href="">a</a>', True, u'anchor tag')
test_html_2 = _mktest(u'<i>i</i>', True, u'italics tag')
test_html_3 = _mktest(u'<b>b</b>', True, u'bold tag')
test_html_4 = _mktest(u'<code>', False, u'allowed tag, no end tag')
test_html_5 = _mktest(u'<rss> .. </rss>', False, u'disallowed tag')
test_entity_1 = _mktest(u'AT&T', False, u'corporation name')
test_entity_2 = _mktest(u'&copy;', True, u'named entity reference')
test_entity_3 = _mktest(u'&#169;', True, u'numeric entity reference')
test_entity_4 = _mktest(u'&#xA9;', True, u'hex numeric entity reference')
#---------- additional api unit tests, not backed by files
class TestBuildRequest(unittest.TestCase):
"Test that HTTP request objects are created as expected"
def test_extra_headers(self):
"""You can pass in extra headers and they go into the request object."""
request = feedparser._build_urllib2_request(
'http://example.com/feed',
'agent-name',
None, None, None, None,
{'Cache-Control': 'max-age=0'})
# nb, urllib2 folds the case of the headers
self.assertEqual(
request.get_header('Cache-control'), 'max-age=0')
class TestLxmlBug(unittest.TestCase):
def test_lxml_etree_bug(self):
try:
import lxml.etree
except ImportError:
pass
else:
doc = u"<feed>&illformed_charref</feed>".encode('utf8')
# Importing lxml.etree currently causes libxml2 to
# throw SAXException instead of SAXParseException.
feedparser.parse(feedparser._StringIO(doc))
self.assertTrue(True)
#---------- parse test files and create test methods ----------
def convert_to_utf8(data):
"Identify data's encoding using its byte order mark" \
"and convert it to its utf-8 equivalent"
if data[:4] == _l2bytes([0x4c, 0x6f, 0xa7, 0x94]):
return data.decode('cp037').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x00, 0xfe, 0xff]):
if not _UTF32_AVAILABLE:
return None
return data.decode('utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0xff, 0xfe, 0x00, 0x00]):
if not _UTF32_AVAILABLE:
return None
return data.decode('utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x00, 0x00, 0x3c]):
if not _UTF32_AVAILABLE:
return None
return data.decode('utf-32be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x00, 0x00]):
if not _UTF32_AVAILABLE:
return None
return data.decode('utf-32le').encode('utf-8')
elif data[:4] == _l2bytes([0x00, 0x3c, 0x00, 0x3f]):
return data.decode('utf-16be').encode('utf-8')
elif data[:4] == _l2bytes([0x3c, 0x00, 0x3f, 0x00]):
return data.decode('utf-16le').encode('utf-8')
elif (data[:2] == _l2bytes([0xfe, 0xff])) and (data[2:4] != _l2bytes([0x00, 0x00])):
return data[2:].decode('utf-16be').encode('utf-8')
elif (data[:2] == _l2bytes([0xff, 0xfe])) and (data[2:4] != _l2bytes([0x00, 0x00])):
return data[2:].decode('utf-16le').encode('utf-8')
elif data[:3] == _l2bytes([0xef, 0xbb, 0xbf]):
return data[3:]
# no byte order mark was found
return data
skip_re = re.compile(_s2bytes("SkipUnless:\s*(.*?)\n"))
desc_re = re.compile(_s2bytes("Description:\s*(.*?)\s*Expect:\s*(.*)\s*-->"))
def getDescription(xmlfile, data):
"""Extract test data
Each test case is an XML file which contains not only a test feed
but also the description of the test and the condition that we
would expect the parser to create when it parses the feed. Example:
<!--
Description: feed title
Expect: feed['title'] == u'Example feed'
-->
"""
skip_results = skip_re.search(data)
if skip_results:
skipUnless = skip_results.group(1).strip()
else:
skipUnless = '1'
search_results = desc_re.search(data)
if not search_results:
raise RuntimeError, "can't parse %s" % xmlfile
description, evalString = map(lambda s: s.strip(), list(search_results.groups()))
description = xmlfile + ": " + unicode(description, 'utf8')
return description, evalString, skipUnless
def buildTestCase(xmlfile, description, evalString):
func = lambda self, xmlfile=xmlfile, evalString=evalString: \
self.failUnlessEval(xmlfile, evalString)
func.__doc__ = description
return func
def runtests():
"Read the files in the tests/ directory, dynamically add tests to the " \
"TestCases above, spawn the HTTP server, and run the test suite"
if sys.argv[1:]:
allfiles = filter(lambda s: s.endswith('.xml'), reduce(operator.add, map(glob.glob, sys.argv[1:]), []))
sys.argv = [sys.argv[0]] #+ sys.argv[2:]
else:
allfiles = glob.glob(os.path.join('.', 'tests', '**', '**', '*.xml'))
wellformedfiles = glob.glob(os.path.join('.', 'tests', 'wellformed', '**', '*.xml'))
illformedfiles = glob.glob(os.path.join('.', 'tests', 'illformed', '*.xml'))
encodingfiles = glob.glob(os.path.join('.', 'tests', 'encoding', '*.xml'))
entitiesfiles = glob.glob(os.path.join('.', 'tests', 'entities', '*.xml'))
microformatfiles = glob.glob(os.path.join('.', 'tests', 'microformats', '**', '*.xml'))
httpd = None
# there are several compression test cases that must be accounted for
# as well as a number of http status tests that redirect to a target
# and a few `_open_resource`-related tests
httpcount = 6 + 17 + 2
httpcount += len([f for f in allfiles if 'http' in f])
httpcount += len([f for f in wellformedfiles if 'http' in f])
httpcount += len([f for f in illformedfiles if 'http' in f])
httpcount += len([f for f in encodingfiles if 'http' in f])
try:
for c, xmlfile in enumerate(allfiles + encodingfiles + illformedfiles + entitiesfiles):
addTo = TestCase
if xmlfile in encodingfiles:
addTo = TestEncodings
elif xmlfile in entitiesfiles:
addTo = (TestStrictParser, TestLooseParser)
elif xmlfile in microformatfiles:
addTo = TestMicroformats
elif xmlfile in wellformedfiles:
addTo = (TestStrictParser, TestLooseParser)
data = open(xmlfile, 'rb').read()
if 'encoding' in xmlfile:
data = convert_to_utf8(data)
if data is None:
# convert_to_utf8 found a byte order mark for utf_32
# but it's not supported in this installation of Python
if 'http' in xmlfile:
httpcount -= 1 + (xmlfile in wellformedfiles)
continue
description, evalString, skipUnless = getDescription(xmlfile, data)
testName = 'test_%06d' % c
ishttp = 'http' in xmlfile
try:
if not eval(skipUnless): raise NotImplementedError
except (ImportError, LookupError, NotImplementedError, AttributeError):
if ishttp:
httpcount -= 1 + (xmlfile in wellformedfiles)
continue
if ishttp:
xmlfile = 'http://%s:%s/%s' % (_HOST, _PORT, posixpath.normpath(xmlfile.replace('\\', '/')))
testFunc = buildTestCase(xmlfile, description, evalString)
if isinstance(addTo, tuple):
setattr(addTo[0], testName, testFunc)
setattr(addTo[1], testName, testFunc)
else:
setattr(addTo, testName, testFunc)
if feedparser.TIDY_MARKUP and feedparser._mxtidy:
sys.stderr.write('\nWarning: feedparser.TIDY_MARKUP invalidates tests, turning it off temporarily\n\n')
feedparser.TIDY_MARKUP = 0
if httpcount:
httpd = FeedParserTestServer(httpcount)
httpd.daemon = True
httpd.start()
httpd.ready.wait()
testsuite = unittest.TestSuite()
testloader = unittest.TestLoader()
testsuite.addTest(testloader.loadTestsFromTestCase(TestCase))
testsuite.addTest(testloader.loadTestsFromTestCase(TestStrictParser))
testsuite.addTest(testloader.loadTestsFromTestCase(TestLooseParser))
testsuite.addTest(testloader.loadTestsFromTestCase(TestEncodings))
testsuite.addTest(testloader.loadTestsFromTestCase(TestDateParsers))
testsuite.addTest(testloader.loadTestsFromTestCase(TestHTMLGuessing))
testsuite.addTest(testloader.loadTestsFromTestCase(TestHTTPStatus))
testsuite.addTest(testloader.loadTestsFromTestCase(TestCompression))
testsuite.addTest(testloader.loadTestsFromTestCase(TestConvertToIdn))
testsuite.addTest(testloader.loadTestsFromTestCase(TestMicroformats))
testsuite.addTest(testloader.loadTestsFromTestCase(TestOpenResource))
testsuite.addTest(testloader.loadTestsFromTestCase(TestFeedParserDict))
testsuite.addTest(testloader.loadTestsFromTestCase(TestMakeSafeAbsoluteURI))
testsuite.addTest(testloader.loadTestsFromTestCase(TestEverythingIsUnicode))
testsuite.addTest(testloader.loadTestsFromTestCase(TestTemporaryFallbackBehavior))
testsuite.addTest(testloader.loadTestsFromTestCase(TestLxmlBug))
testresults = unittest.TextTestRunner(verbosity=1).run(testsuite)
# Return 0 if successful, 1 if there was a failure
sys.exit(not testresults.wasSuccessful())
finally:
if httpd:
if httpd.requests:
# Should never get here unless something went horribly wrong, like the
# user hitting Ctrl-C. Tell our HTTP server that it's done, then do
# one more request to flush it. This rarely works; the combination of
# threading, self-terminating HTTP servers, and unittest is really
# quite flaky. Just what you want in a testing framework, no?
httpd.requests = 0
if httpd.ready:
urllib.urlopen('http://127.0.0.1:8097/tests/wellformed/rss/aaa_wellformed.xml').read()
httpd.join(0)
if __name__ == "__main__":
runtests()

BIN
lib/feedparser/tests/compression/deflate-no-headers.z
View file

Binary file not shown.

1
lib/feedparser/tests/compression/deflate-not-compressed.z
View file

@ -1 +0,0 @@
<feed><title>deflate</title></feed>

BIN
lib/feedparser/tests/compression/deflate.z
View file

Binary file not shown.

1
lib/feedparser/tests/compression/gzip-not-compressed.gz
View file

@ -1 +0,0 @@
<feed><title>gzip</title></feed>

BIN
lib/feedparser/tests/compression/gzip-struct-error.gz
View file

Binary file not shown.

BIN
lib/feedparser/tests/compression/gzip.gz
View file

Binary file not shown.

1
lib/feedparser/tests/compression/sample.xml
View file

@ -1 +0,0 @@
<feed xmlns="http://www.w3.org/2005/Atom"></feed>

8
lib/feedparser/tests/encoding/big5.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="big5"?>
<!--
SkipUnless: __import__('codecs').lookup('big5')
Description: big5
Expect: not bozo and encoding == 'big5'
-->
<rss>
</rss>

7
lib/feedparser/tests/encoding/bozo_bogus_encoding.xml
View file

@ -1,7 +0,0 @@
<?xml version="1.0" encoding="bogus"?>
<!--
Description: bogus encoding
Expect: bozo
-->
<rss>
</rss>

13
lib/feedparser/tests/encoding/bozo_double-encoded-html.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0"?>
<!--
Description: utf-8 interpreted as iso-8859-1 and re-encoded as utf-8
Expect: bozo and ord(entries[0]['description']) == 8230
-->
<rss version="2.0">
<channel>
<item>
<description>&acirc;&#128;&brvbar;</description>
</item>
</channel>
</rss>

10
lib/feedparser/tests/encoding/bozo_encoding_mismatch_crash.xml
View file

@ -1,10 +0,0 @@
<!--
SkipUnless: __import__('sys').version.split()[0] >= '2.2.0'
Description: crashes
Expect: 1
-->
<rss>
<item>
<description><![CDATA[<a href="http://www.example.com/">¤</a><a href="&#38;"></a>]]></description>
</item>
</rss>

11
lib/feedparser/tests/encoding/bozo_http_i18n.xml
View file

@ -1,11 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!--
Note: text/xml defaults to us-ascii, in conflict with the XML declaration of utf-8
Header: Content-type: text/xml
Description: Content-type with no charset (text/xml defaults to us-ascii)
Expect: bozo and isinstance(bozo_exception, feedparser.CharacterEncodingOverride)
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
<title>Iñtërnâtiônàlizætiøn</title>
</feed>

8
lib/feedparser/tests/encoding/bozo_http_text_plain.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/plain
Description: text/plain + no encoding
Expect: bozo
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/bozo_http_text_plain_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/plain; charset=utf-8
Description: text/plain + charset
Expect: bozo and encoding == 'utf-8'
-->
<rss version="2.0">
</rss>

10
lib/feedparser/tests/encoding/bozo_invalid-bytes-with-bom.xml
View file

@ -1,10 +0,0 @@
<!--
Description: Ensure when there are invalid bytes in encoding specified by BOM, feedparser doesn't crash
Expect: bozo
-->
<rss version="2.0">
<channel>
<title>Valid UTF8: ѨInvalid UTF8: España</title>
<description><pre class="screen"></pre></description>
</channel>
</rss

13
lib/feedparser/tests/encoding/bozo_linenoise.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!--
Description: unguessable characters
Expect: bozo and entries[0].summary == u'\xe2\u20ac\u2122\xe2\u20ac\x9d\u0160'
-->
<rss version="2.0">
<channel>
<item>
<description><![CDATA[ ’<>â€<C3A2>© ]]></description>
</item>
</channel>
</rss>

BIN
lib/feedparser/tests/encoding/csucs4.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/csunicode.xml
View file

Binary file not shown.

13
lib/feedparser/tests/encoding/demoronize-1.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0"?>
<!--
Description: using win-1252 character points instead of unicode
Expect: not bozo and entries[0]['description'] == u'don\u2019t'
-->
<rss version="2.0">
<channel>
<item>
<description>don’t</description>
</item>
</channel>
</rss>

13
lib/feedparser/tests/encoding/demoronize-2.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0"?>
<!--
Description: using win-1252 character points instead of unicode
Expect: not bozo and entries[0]['description'] == u'don\u2019t'
-->
<rss version="2.0">
<channel>
<item>
<description>don&#146;t</description>
</item>
</channel>
</rss>

13
lib/feedparser/tests/encoding/demoronize-3.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0"?>
<!--
Description: using win-1252 character points instead of unicode
Expect: not bozo and entries[0]['description'] == u'don&#x2019;t'
-->
<rss version="2.0">
<channel>
<item>
<description>don&amp;#146;t</description>
</item>
</channel>
</rss>

13
lib/feedparser/tests/encoding/double-encoded-html.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0"?>
<!--
Description: utf-8 interpreted as iso-8859-1 and re-encoded as utf-8
Expect: not bozo and ord(entries[0]['description']) == 8230
-->
<rss version="2.0">
<channel>
<item>
<description>&#226;&#128;&#166;</description>
</item>
</channel>
</rss>

9
lib/feedparser/tests/encoding/encoding_attribute_crash.xml
View file

@ -1,9 +0,0 @@
<!--
Description: crashes
Expect: 1
-->
<rss>
<item>
<description><![CDATA[<img alt="&#169;" />]]></description>
</item>
</rss>

9
lib/feedparser/tests/encoding/encoding_attribute_crash_2.xml
View file

@ -1,9 +0,0 @@
<!--
Description: crashes
Expect: 1
-->
<rss>
<item>
<description>&lt;a href=&quot;http://example.com&quot;&gt;&lt;img src=&quot;http://example.com/logo.gif&quot; alt=&quot;The image &amp;acirc;&amp;#128;&amp;#156;http://example.com/logo.gif&amp;acirc;&amp;#128;&amp;#65533; cannot be displayed, because it contains errors.&quot;&gt;&lt;/a&gt;&lt;br&gt;</description>
</item>
</rss>

14
lib/feedparser/tests/encoding/euc-kr-attribute.xml
View file

@ -1,14 +0,0 @@
<?xml version="1.0" encoding="euc-kr"?>
<!--
SkipUnless: __import__('codecs').lookup('euc-kr')
Description: euc-kr character in attribute of embedded HTML
Expect: not bozo and entries[0]['description'] == u'<img alt="\ub144" />'
-->
<rss version="2.0">
<channel>
<item>
<description>&lt;img alt="³â" /></description>
</item>
</channel>
</rss>

14
lib/feedparser/tests/encoding/euc-kr-item.xml
View file

@ -1,14 +0,0 @@
<?xml version="1.0" encoding="euc-kr"?>
<!--
SkipUnless: __import__('codecs').lookup('euc-kr')
Description: euc-kr encoding in item description
Expect: not bozo and entries[0]['description'] == u'\ub144'
-->
<rss version="2.0">
<channel>
<item>
<description>³â</description>
</item>
</channel>
</rss>

12
lib/feedparser/tests/encoding/euc-kr.xml
View file

@ -1,12 +0,0 @@
<?xml version="1.0" encoding="euc-kr"?>
<!--
SkipUnless: __import__('codecs').lookup('euc-kr')
Description: euc-kr encoding
Expect: not bozo and feed['title'] == u'\ub144'
-->
<rss version="2.0">
<channel>
<title>³â</title>
</channel>
</rss>

8
lib/feedparser/tests/encoding/http_application_atom_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/atom+xml;charset='us-ascii'
Description: application/atom+xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_atom_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/atom+xml; charset='us-ascii'
Description: application/atom+xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_atom_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/atom+xml
Description: application/atom+xml + no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_atom_xml_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/atom+xml
Description: application/atom+xml + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

9
lib/feedparser/tests/encoding/http_application_atom_xml_gb2312_charset.xml
View file

@ -1,9 +0,0 @@
<?xml version="1.0"?>
<!--
SkipUnless: __import__('codecs').lookup('gb2312')
Header: Content-type: application/atom+xml;charset='gb2312'
Description: application/atom+xml + explicit charset
Expect: not bozo and encoding == 'gb18030'
-->
<feed xmlns="http://www.w3.org/2005/Atom">
</feed>

9
lib/feedparser/tests/encoding/http_application_atom_xml_gb2312_charset_overrides_encoding.xml
View file

@ -1,9 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!--
SkipUnless: __import__('codecs').lookup('gb2312')
Header: Content-type: application/atom+xml; charset='gb2312'
Description: application/atom+xml + charset overrides encoding
Expect: not bozo and encoding == 'gb18030'
-->
<feed xmlns="http://www.w3.org/2005/Atom">
</feed>

9
lib/feedparser/tests/encoding/http_application_atom_xml_gb2312_encoding.xml
View file

@ -1,9 +0,0 @@
<?xml version="1.0" encoding="gb2312"?>
<!--
SkipUnless: __import__('codecs').lookup('gb2312')
Header: Content-type: application/atom+xml
Description: application/atom+xml + explicit encoding
Expect: not bozo and encoding == 'gb18030'
-->
<feed xmlns="http://www.w3.org/2005/Atom">
</feed>

8
lib/feedparser/tests/encoding/http_application_rss_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/rss+xml;charset= 'us-ascii'
Description: application/rss+xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_rss_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/rss+xml;charset= "us-ascii"
Description: application/rss+xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_rss_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/rss+xml
Description: application/rss+xml + no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_rss_xml_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/rss+xml
Description: application/rss+xml + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml;charset= "us-ascii"
Description: application/xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml;charset = us-ascii
Description: application/xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml
Description: application/xml + no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_xml_dtd_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml-dtd; charset="us-ascii"
Description: application/xml-dtd + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_dtd_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml-dtd; charset="us-ascii"
Description: application/xml-dtd + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_dtd_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml-dtd
Description: application/xml-dtd + no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_dtd_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml-dtd
Description: application/xml-dtd + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml
Description: application/xml + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_application_xml_epe_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml-external-parsed-entity; charset="us-ascii"
Description: application/xml-external-parsed-entity + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_epe_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml-external-parsed-entity;charset=us-ascii
Description: application/xml-external-parsed-entity + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_epe_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: application/xml-external-parsed-entity
Description: application/xml-external-parsed-entity + no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_application_xml_epe_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: application/xml-external-parsed-entity
Description: application/xml-parsed-entity + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

13
lib/feedparser/tests/encoding/http_encoding_attribute_crash.xml
View file

@ -1,13 +0,0 @@
<?xml version='1.0' encoding='UTF-8'?>
<!--
Header: Content-type: application/atom+xml
Description: crashes while resolving relative URIs when content contains attributes which contain (valid) non-ASCII characters
Expect: not bozo
-->
<feed xmlns='http://www.w3.org/2005/Atom'>
<entry>
<content type='xhtml'><div xmlns='http://www.w3.org/1999/xhtml'>
<img alt="Browser market shares at ‘ongoing’" />
</div></content>
</entry>
</feed>

13
lib/feedparser/tests/encoding/http_i18n.xml
View file

@ -1,13 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<!--
Header: Content-type: application/xml
Description: application/xml with no charset (control for tests/illformed/encoding/http_i18n.xml)
Expect: not bozo
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
<title>Iñtërnâtiônàlizætiøn</title>
<link rel='alternate' type='text/html' href='http://example.com/'/>
<modified>2004-06-02T19:07:55-04:00</modified>
<tagline>If your parser thinks this is well-formed, it's right.</tagline>
</feed>

8
lib/feedparser/tests/encoding/http_text_atom_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/atom+xml;charset='us-ascii'
Description: text/atom+xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_atom_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/atom+xml; charset='us-ascii'
Description: text/atom+xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_atom_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/atom+xml
Description: text/atom+xml + no encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_atom_xml_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/atom+xml
Description: text/atom+xml + explicit encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_rss_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/rss+xml;charset= 'us-ascii'
Description: text/rss+xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_rss_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/rss+xml;charset= "us-ascii"
Description: text/rss+xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_rss_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/rss+xml
Description: text/rss+xml + no encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_rss_xml_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/rss+xml
Description: text/rss+xml + explicit encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_bogus_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml;
Description: text/xml + bogus charset
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_bogus_param.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml; charset:iso-8859-1
Description: text/xml + bogus parameter
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml;charset= "us-ascii"
Description: text/xml + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

16
lib/feedparser/tests/encoding/http_text_xml_charset_2.xml
View file

@ -1,16 +0,0 @@
<!--
SkipUnless: __import__('codecs').lookup('windows-1252')
Header: Content-type: text/xml; charset=windows-1252
Description: text/xml + explicit charset (this one is harder than the others)
Expect: not bozo and entries[0]['description'] == u'This is a \xa3\u201ctest.\u201d'
-->
<rss version="2.0">
<channel>
<item>
<title>Foo</title>
<link>http://purl.org/rss/2.0/?item</link>
<description>This is a £“test.”</description>
</item>
</channel>
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/xml;charset = us-ascii
Description: text/xml + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

17
lib/feedparser/tests/encoding/http_text_xml_charset_overrides_encoding_2.xml
View file

@ -1,17 +0,0 @@
<?xml version='1.0' encoding='iso-8859-1'?>
<!--
SkipUnless: __import__('codecs').lookup('windows-1252')
Header: Content-type: text/xml; charset=windows-1252
Description: text/xml + charset overrides encoding (this one is harder than the others)
Expect: not bozo and entries[0]['description'] == u'This is a \xa3\u201ctest.\u201d'
-->
<rss version="2.0">
<channel>
<item>
<title>Foo</title>
<link>http://purl.org/rss/2.0/?item</link>
<description>This is a £“test.”</description>
</item>
</channel>
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml
Description: text/xml + no encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<rss version="2.0">
</rss>

8
lib/feedparser/tests/encoding/http_text_xml_epe_charset.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml-external-parsed-entity; charset="us-ascii"
Description: text/xml-external-parsed-entity + explicit charset
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_xml_epe_charset_overrides_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/xml-external-parsed-entity;charset=us-ascii
Description: text/xml-external-parsed-entity + charset overrides encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_xml_epe_default.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml-external-parsed-entity
Description: text/xml-external-parsed-entity + no encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_xml_epe_encoding.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Header: Content-type: text/xml-external-parsed-entity
Description: text/xml-parsed-entity + explicit encoding
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

8
lib/feedparser/tests/encoding/http_text_xml_qs.xml
View file

@ -1,8 +0,0 @@
<?xml version="1.0"?>
<!--
Header: Content-type: text/xml; qs=0.9
Description: text/xml + qs value
Expect: not bozo and encoding == 'us-ascii'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

BIN
lib/feedparser/tests/encoding/iso-10646-ucs-2.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/iso-10646-ucs-4.xml
View file

Binary file not shown.

7
lib/feedparser/tests/encoding/no_content_type_default.xml
View file

@ -1,7 +0,0 @@
<?xml version="1.0"?>
<!--
Description: no content-type and no encoding
Expect: not bozo and encoding == 'utf-8'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

7
lib/feedparser/tests/encoding/no_content_type_encoding.xml
View file

@ -1,7 +0,0 @@
<?xml version="1.0" encoding="iso-8859-1"?>
<!--
Description: no content-type + explicit encoding
Expect: not bozo and encoding == 'iso-8859-1'
-->
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
</feed>

BIN
lib/feedparser/tests/encoding/u16.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/ucs-2.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/ucs-4.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/utf-16be-autodetect.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/utf-16be-bom.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/utf-16be.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/utf-16le-autodetect.xml
View file

Binary file not shown.

BIN
lib/feedparser/tests/encoding/utf-16le-bom.xml
View file

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show more