def handle_request(self, env, start_response):
req = swob.Request(env)
inspector = req.headers.get('inspector', '').lower().split()
if self.hmac_key:
expires = req.headers.get('inspector_expires', '')
sig = req.headers.get('inspector_sig', '')
try:
if sig == '':
raise InspectorError('Missing Header: Inspector-Sig')
if expires == '':
raise InspectorError('Missing Header: Inspector-Expires')
if int(expires) < int(time.time()):
raise InspectorError(
'Invalid Header: Inspector-Expires has expired')
valid_sig = create_sig(inspector, expires, self.hmac_key)
if sig != valid_sig:
raise InspectorError('Invalid Signature')
except InspectorError as e:
return self.handle_error(str(e), env, start_response)
except ValueError:
return self.handle_error(
'Invalid Header: Inspector-Expires must be an integer',
env, start_response)
_start_response = start_response
inspector_errors = []
def inspector_start_response(status, headers, exc_info=None):
if inspector_errors:
errors = ', '.join(inspector_errors).title()
headers.append(('Inspector-Error',
'Invalid Inspectors: {0}'.format(errors)))
return _start_response(status, headers, exc_info)
for i in inspector:
if i not in inspector_handlers['object']:
inspector_errors.append(i)
continue
_start_response = inspector_handlers['object'][i](
env, _start_response, self.app, {
'swift_dir': self.swift_dir
})
return self.app(env, inspector_start_response)
def __call__(self, env, start_response):
req = swob.Request(env)
self._calls.append((
req.method,
req.path,
# mutable dict; keep a copy so subsequent calls can't change it
swob.HeaderKeyDict(req.headers)))
if len(self.responses) > 1:
resp = self.responses.pop(0)
else:
resp = self.responses[0]
status = resp['status']
headers = resp.get('headers', [])
body_iter = resp.get('body_iter', [])
start_response(status, headers)
return body_iter
def _handle_request(self, env, start_response):
req = swob.Request(env)
# Double (or triple, etc.) slashes in the URL should be ignored;
# collapse them. fixes T34864
req.path_info = re.sub(r'/{2,}', '/', req.path_info)
# Keep a copy of the original request so we can ask the scalers for it
reqorig = swob.Request(req.environ.copy())
# Containers have 5 components: project, language, repo, zone, and shard.
# If there's no zone in the URL, the zone is assumed to be 'public' (for b/c).
# Shard is optional (and configurable), and is only used for large containers.
#
# Projects are wikipedia, wikinews, etc.
# Languages are en, de, fr, commons, etc.
# Repos are local, timeline, etc.
# Zones are public, thumb, temp, etc.
# Shard is extracted from "hash paths" in the URL and is 2 hex digits.
#
# These attributes are mapped to container names in the form of either:
# (a) proj-lang-repo-zone (if not sharded)
# (b) proj-lang-repo-zone.shard (if sharded)
# (c) global-data-repo-zone (if not sharded)
# (d) global-data-repo-zone.shard (if sharded)
#
# Rewrite wiki-global URLs of these forms:
# (a) http://upload.wikimedia.org/math/<relpath>
# => http://msfe/v1/AUTH_<hash>/global-data-math-render/<relpath>
# (b) http://upload.wikimedia.org/<proj>/<lang>/math/<relpath> (legacy)
# => http://msfe/v1/AUTH_<hash>/global-data-math-render/<relpath>
#
# Rewrite wiki-relative URLs of these forms:
# (a) http://upload.wikimedia.org/<proj>/<lang>/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-public/<relpath>
# (b) http://upload.wikimedia.org/<proj>/<lang>/archive/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-public/archive/<relpath>
# (c) http://upload.wikimedia.org/<proj>/<lang>/thumb/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-thumb/<relpath>
# (d) http://upload.wikimedia.org/<proj>/<lang>/thumb/archive/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-thumb/archive/<relpath>
# (e) http://upload.wikimedia.org/<proj>/<lang>/thumb/temp/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-thumb/temp/<relpath>
# (f) http://upload.wikimedia.org/<proj>/<lang>/transcoded/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-local-transcoded/<relpath>
# (g) http://upload.wikimedia.org/<proj>/<lang>/timeline/<relpath>
# => http://msfe/v1/AUTH_<hash>/<proj>-<lang>-timeline-render/<relpath>
# regular uploads
match = re.match(
(r'^/(?P<proj>[^/]+)/(?P<lang>[^/]+)/'
r'((?P<zone>transcoded|thumb)/)?'
r'(?P<path>((temp|archive)/)?[0-9a-f]/(?P<shard>[0-9a-f]{2})/.+)$'
), req.path)
if match:
proj = match.group('proj')
lang = match.group('lang')
repo = 'local' # the upload repo name is "local"
# Get the repo zone (if not provided that means "public")
zone = (match.group('zone') if match.group('zone') else 'public')
# Get the object path relative to the zone (and thus container)
obj = match.group('path') # e.g. "archive/a/ab/..."
shard = match.group('shard')
# timeline renderings
if match is None:
# /wikipedia/en/timeline/a876297c277d80dfd826e1f23dbfea3f.png
match = re.match(
r'^/(?P<proj>[^/]+)/(?P<lang>[^/]+)/(?P<repo>timeline)/(?P<path>.+)$',
req.path)
if match:
proj = match.group('proj') # wikipedia
lang = match.group('lang') # en
repo = match.group('repo') # timeline
zone = 'render'
obj = match.group(
'path') # a876297c277d80dfd826e1f23dbfea3f.png
shard = ''
# math renderings
if match is None:
# /math/c/9/f/c9f2055dadfb49853eff822a453d9ceb.png
# /wikipedia/en/math/c/9/f/c9f2055dadfb49853eff822a453d9ceb.png (legacy)
match = re.match(
(r'^(/(?P<proj>[^/]+)/(?P<lang>[^/]+))?/(?P<repo>math)/'
r'(?P<path>(?P<shard1>[0-9a-f])/(?P<shard2>[0-9a-f])/.+)$'),
req.path)
if match:
proj = 'global'
lang = 'data'
repo = match.group('repo') # math
zone = 'render'
obj = match.group(
'path') # c/9/f/c9f2055dadfb49853eff822a453d9ceb.png
shard = match.group('shard1') + match.group('shard2') # c9
# score renderings
if match is None:
# /score/j/q/jqn99bwy8777srpv45hxjoiu24f0636/jqn99bwy.png
# /score/override-midi/8/i/8i9pzt87wtpy45lpz1rox8wusjkt7ki.ogg
match = re.match(r'^/(?P<repo>score)/(?P<path>.+)$', req.path)
if match:
proj = 'global'
lang = 'data'
repo = match.group('repo') # score
zone = 'render'
obj = match.group(
'path') # j/q/jqn99bwy8777srpv45hxjoiu24f0636/jqn99bwy.png
shard = ''
if match is None:
match = re.match(r'^/monitoring/(?P<what>.+)$', req.path)
if match:
what = match.group('what')
if what == 'frontend':
headers = {'Content-Type': 'application/octet-stream'}
resp = swob.Response(headers=headers, body="OK\n")
elif what == 'backend':
req.host = '127.0.0.1:%s' % self.bind_port
req.path_info = "/v1/%s/monitoring/backend" % self.account
app_iter = self._app_call(env)
status = self._get_status_int()
headers = self._response_headers
resp = swob.Response(status=status,
headers=headers,
app_iter=app_iter)
else:
resp = swob.HTTPNotFound('Monitoring type not found "%s"' %
(req.path))
return resp(env, start_response)
if match is None:
match = re.match(r'^/(?P<path>[^/]+)?$', req.path)
# /index.html /favicon.ico /robots.txt etc.
# serve from a default "root" container
if match:
path = match.group('path')
if not path:
path = 'index.html'
req.host = '127.0.0.1:%s' % self.bind_port
req.path_info = "/v1/%s/root/%s" % (self.account, path)
app_iter = self._app_call(env)
status = self._get_status_int()
headers = self._response_headers
resp = swob.Response(status=status,
headers=headers,
app_iter=app_iter)
return resp(env, start_response)
# Internally rewrite the URL based on the regex it matched...
if match:
# Get the per-project "conceptual" container name, e.g. "<proj><lang><repo><zone>"
container = "%s-%s-%s-%s" % (proj, lang, repo, zone)
# Add 2-digit shard to the container if it is supposed to be sharded.
# We may thus have an "actual" container name like "<proj><lang><repo><zone>.<shard>"
if container in self.shard_container_list:
container += ".%s" % shard
# Save a url with just the account name in it.
req.path_info = "/v1/%s" % (self.account)
port = self.bind_port
req.host = '127.0.0.1:%s' % port
url = req.url[:]
# Create a path to our object's name.
req.path_info = "/v1/%s/%s/%s" % (self.account, container,
urllib2.unquote(obj))
# self.logger.warn("new path is %s" % req.path_info)
# do_start_response just remembers what it got called with,
# because our 404 handler will generate a different response.
app_iter = self._app_call(env)
status = self._get_status_int()
headers = self._response_headers
if status == 404:
# only send thumbs to the 404 handler; just return a 404 for everything else.
if repo == 'local' and zone == 'thumb':
resp = self.handle404(reqorig, url, container, obj)
return resp(env, start_response)
else:
resp = swob.HTTPNotFound('File not found: %s' % req.path)
return resp(env, start_response)
else:
if zone == 'thumb':
for key, value in headers:
if key == 'X-Delete-At' and self.thumbnail_update_expiry_headers:
# Update expiry header asynchronously
eventlet.spawn(self.update_expiry, env)
break
# Return the response verbatim
return swob.Response(status=status,
headers=headers,
app_iter=app_iter)(env, start_response)
else:
resp = swob.HTTPNotFound('Regexp failed to match URI: "%s"' %
(req.path))
return resp(env, start_response)
def __call__(self, env, start_response):
if CONF.s3_acl:
self._fake_auth_middleware(env)
req = swob.Request(env)
method = env['REQUEST_METHOD']
path = env['PATH_INFO']
_, acc, cont, obj = split_path(env['PATH_INFO'],
0,
4,
rest_with_last=True)
if env.get('QUERY_STRING'):
path += '?' + env['QUERY_STRING']
if 'swift.authorize' in env:
resp = env['swift.authorize'](req)
if resp:
return resp(env, start_response)
headers = req.headers
self._calls.append((method, path, headers))
self.swift_sources.append(env.get('swift.source'))
try:
resp_class, raw_headers, body = self._responses[(method, path)]
headers = swob.HeaderKeyDict(raw_headers)
except KeyError:
# FIXME: suppress print state error for python3 compatibility.
# pylint: disable-msg=E1601
if (env.get('QUERY_STRING')
and (method, env['PATH_INFO']) in self._responses):
resp_class, raw_headers, body = self._responses[(
method, env['PATH_INFO'])]
headers = swob.HeaderKeyDict(raw_headers)
elif method == 'HEAD' and ('GET', path) in self._responses:
resp_class, raw_headers, _ = self._responses[('GET', path)]
body = None
headers = swob.HeaderKeyDict(raw_headers)
elif method == 'GET' and obj and path in self.uploaded:
resp_class = swob.HTTPOk
headers, body = self.uploaded[path]
else:
print "Didn't find %r in allowed responses" % (
(method, path), )
raise
# simulate object PUT
if method == 'PUT' and obj:
input = env['wsgi.input'].read()
etag = md5(input).hexdigest()
headers.setdefault('Etag', etag)
headers.setdefault('Content-Length', len(input))
# keep it for subsequent GET requests later
self.uploaded[path] = (deepcopy(headers), input)
if "CONTENT_TYPE" in env:
self.uploaded[path][0]['Content-Type'] = env["CONTENT_TYPE"]
# range requests ought to work, but copies are special
support_range_and_conditional = not (method == 'PUT'
and 'X-Copy-From' in req.headers
and 'Range' in req.headers)
resp = resp_class(req=req,
headers=headers,
body=body,
conditional_response=support_range_and_conditional)
return resp(env, start_response)
def __call__(self, env, start_response):
method = env['REQUEST_METHOD']
if method not in self.ALLOWED_METHODS:
raise HTTPNotImplemented()
path = env['PATH_INFO']
_, acc, cont, obj = split_path(env['PATH_INFO'],
0,
4,
rest_with_last=True)
if env.get('QUERY_STRING'):
path += '?' + env['QUERY_STRING']
if 'swift.authorize' in env:
resp = env['swift.authorize'](swob.Request(env))
if resp:
return resp(env, start_response)
req = swob.Request(env)
self.swift_sources.append(env.get('swift.source'))
self.txn_ids.append(env.get('swift.trans_id'))
try:
resp_class, raw_headers, body = self._find_response(method, path)
headers = HeaderKeyDict(raw_headers)
except KeyError:
if (env.get('QUERY_STRING')
and (method, env['PATH_INFO']) in self._responses):
resp_class, raw_headers, body = self._find_response(
method, env['PATH_INFO'])
headers = HeaderKeyDict(raw_headers)
elif method == 'HEAD' and ('GET', path) in self._responses:
resp_class, raw_headers, body = self._find_response(
'GET', path)
body = None
headers = HeaderKeyDict(raw_headers)
elif method == 'GET' and obj and path in self.uploaded:
resp_class = swob.HTTPOk
headers, body = self.uploaded[path]
else:
raise KeyError("Didn't find %r in allowed responses" %
((method, path), ))
# simulate object PUT
if method == 'PUT' and obj:
put_body = ''.join(iter(env['wsgi.input'].read, ''))
if 'swift.callback.update_footers' in env:
footers = HeaderKeyDict()
env['swift.callback.update_footers'](footers)
req.headers.update(footers)
etag = md5(put_body).hexdigest()
headers.setdefault('Etag', etag)
headers.setdefault('Content-Length', len(put_body))
# keep it for subsequent GET requests later
self.uploaded[path] = (dict(req.headers), put_body)
if "CONTENT_TYPE" in env:
self.uploaded[path][0]['Content-Type'] = env["CONTENT_TYPE"]
# simulate object POST
elif method == 'POST' and obj:
metadata, data = self.uploaded.get(path, ({}, None))
# select items to keep from existing...
new_metadata = dict((k, v) for k, v in metadata.items()
if (not is_user_meta('object', k)
and not is_object_transient_sysmeta(k)))
# apply from new
new_metadata.update(
dict((k, v) for k, v in req.headers.items() if (
is_user_meta('object', k) or is_object_transient_sysmeta(k)
or k.lower == 'content-type')))
self.uploaded[path] = new_metadata, data
# note: tests may assume this copy of req_headers is case insensitive
# so we deliberately use a HeaderKeyDict
self._calls.append(
FakeSwiftCall(method, path, HeaderKeyDict(req.headers)))
# Apply conditional etag overrides
conditional_etag = resolve_etag_is_at_header(req, headers)
# range requests ought to work, hence conditional_response=True
if isinstance(body, list):
resp = resp_class(req=req,
headers=headers,
app_iter=body,
conditional_response=req.method
in ('GET', 'HEAD'),
conditional_etag=conditional_etag)
else:
resp = resp_class(req=req,
headers=headers,
body=body,
conditional_response=req.method
in ('GET', 'HEAD'),
conditional_etag=conditional_etag)
wsgi_iter = resp(env, start_response)
self.mark_opened(path)
return LeakTrackingIter(wsgi_iter, self.mark_closed, path)
def proxy_wrapper(env, start_response, app, config):
swift_dir = config.get('swift_dir')
request = swob.Request(env)
def _start_response(status, headers, exc_info=None):
"""start_response wrapper to add request status to env."""
try:
version, account, container, obj = request.split_path(
2, 4, rest_with_last=True)
except ValueError:
headers.append(('Inspector-Nodes', ''))
return start_response(status, headers, exc_info)
if account is not None:
account = urllib.unquote(account)
if container is not None:
container = urllib.unquote(container)
if obj is not None:
obj = urllib.unquote(obj)
storage_policy_index = None
if obj is not None:
container_info = controllers.get_container_info(
{
'PATH_INFO': '/{0}/{1}/{2}'.format(version, account,
container)
},
app,
swift_source='LE')
storage_policy_index = container_info['storage_policy']
obj_ring = storage_policy.POLICIES.get_object_ring(
storage_policy_index, swift_dir)
partition, nodes = obj_ring.get_nodes(account, container, obj)
more_nodes = obj_ring.get_more_nodes(partition)
nodes_template = ('http://{ip}:{port}/{device}/{partition}')
elif container is not None:
partition, nodes = ring.Ring(swift_dir,
ring_name='container').get_nodes(
account, container)
more_nodes = ring.Ring(
swift_dir, ring_name='container').get_more_nodes(partition)
nodes_template = ('http://{ip}:{port}/{device}/{partition}')
else:
partition, nodes = ring.Ring(
swift_dir, ring_name='account').get_nodes(account)
more_nodes = ring.Ring(
swift_dir, ring_name='account').get_more_nodes(partition)
nodes_template = ('http://{ip}:{port}/{device}/{partition}')
object_nodes = []
for node in nodes:
object_nodes.append(
nodes_template.format(ip=node['ip'],
port=node['port'],
device=node['device'],
partition=partition,
account=urllib.quote(account),
container=urllib.quote(container or ''),
obj=urllib.quote(obj or '')))
headers.append(('Inspector-Nodes', ', '.join(object_nodes)))
object_more_nodes = []
for node in more_nodes:
object_more_nodes.append(
nodes_template.format(ip=node['ip'],
port=node['port'],
device=node['device'],
partition=partition,
account=urllib.quote(account),
container=urllib.quote(container or ''),
obj=urllib.quote(obj or '')))
headers.append(('Inspector-More-Nodes', ', '.join(object_more_nodes)))
return start_response(status, headers, exc_info)
return _start_response
def __call__(self, env, start_response):
method = env['REQUEST_METHOD']
path = env['PATH_INFO']
_, acc, cont, obj = split_path(env['PATH_INFO'],
0,
4,
rest_with_last=True)
if env.get('QUERY_STRING'):
path += '?' + env['QUERY_STRING']
if 'swift.authorize' in env:
resp = env['swift.authorize']()
if resp:
return resp(env, start_response)
req_headers = swob.Request(env).headers
self.swift_sources.append(env.get('swift.source'))
try:
resp_class, raw_headers, body = self._get_response(method, path)
headers = swob.HeaderKeyDict(raw_headers)
except KeyError:
if (env.get('QUERY_STRING')
and (method, env['PATH_INFO']) in self._responses):
resp_class, raw_headers, body = self._get_response(
method, env['PATH_INFO'])
headers = swob.HeaderKeyDict(raw_headers)
elif method == 'HEAD' and ('GET', path) in self._responses:
resp_class, raw_headers, body = self._get_response('GET', path)
body = None
headers = swob.HeaderKeyDict(raw_headers)
elif method == 'GET' and obj and path in self.uploaded:
resp_class = swob.HTTPOk
headers, body = self.uploaded[path]
else:
raise KeyError("Didn't find %r in allowed responses" %
((method, path), ))
self._calls.append((method, path, req_headers))
# simulate object PUT
if method == 'PUT' and obj:
input = env['wsgi.input'].read()
etag = md5(input).hexdigest()
headers.setdefault('Etag', etag)
headers.setdefault('Content-Length', len(input))
# keep it for subsequent GET requests later
self.uploaded[path] = (deepcopy(headers), input)
if "CONTENT_TYPE" in env:
self.uploaded[path][0]['Content-Type'] = env["CONTENT_TYPE"]
# range requests ought to work, hence conditional_response=True
req = swob.Request(env)
resp = resp_class(req=req,
headers=headers,
body=body,
conditional_response=True)
wsgi_iter = resp(env, start_response)
self.mark_opened(path)
return LeakTrackingIter(wsgi_iter, self, path)
def __call__(self, env, start_response):
if time() > self._rtime:
self._reload()
req = swob.Request(env)
try:
vers, acct, cont, obj = req.split_path(2, 4, True)
except ValueError:
return self.app(env, start_response)
if req.headers.get(SHUNT_BYPASS_HEADER, ''):
self.logger.debug('Bypassing shunt (%s header) for %r',
SHUNT_BYPASS_HEADER, req.path_info)
return self.app(env, start_response)
if not constraints.valid_api_version(vers):
return self.app(env, start_response)
if not cont:
sync_profile = self.sync_profiles.get((acct, '/*'))
if req.method == 'GET' and sync_profile and\
sync_profile.get('migration'):
# TODO: make the container an optional parameter
profile, _ = maybe_munge_profile_for_all_containers(
sync_profile, '.stub-container')
return self.handle_account(req, start_response, profile, acct)
return self.app(env, start_response)
sync_profile = next(
(self.sync_profiles[(acct, c)]
for c in (cont, '/*') if (acct, c) in self.sync_profiles), None)
if sync_profile is None:
return self.app(env, start_response)
sync_profile, per_account = maybe_munge_profile_for_all_containers(
sync_profile, cont)
if req.method == 'DELETE' and sync_profile.get('migration'):
return self.handle_delete(req, start_response, sync_profile, obj,
per_account)
if not obj:
if req.method == 'GET':
return self.handle_listing(req, start_response, sync_profile,
cont, per_account)
if req.method == 'HEAD' and sync_profile.get('migration'):
return self.handle_container_head(req, start_response,
sync_profile, cont,
per_account)
if obj and req.method in ('GET', 'HEAD'):
# TODO: think about what to do for POST, COPY
return self.handle_object(req, start_response, sync_profile, obj,
per_account)
if req.method == 'POST' and sync_profile.get('migration'):
return self.handle_post(req, start_response, sync_profile, obj,
per_account)
if obj and req.method == 'PUT' and sync_profile.get('migration'):
return self.handle_object_put(req, start_response, sync_profile,
per_account)
return self.app(env, start_response)
def handle404(self, reqorig, url, container, obj):
"""
Return a swob.Response which fetches the thumbnail from the thumb
host and returns it. Note also that the thumb host might write it out
to Swift so it won't 404 next time.
"""
# go to the thumb media store for unknown files
reqorig.host = self.thumbhost
# upload doesn't like our User-agent, otherwise we could call it
# using urllib2.url()
proxy_handler = urllib2.ProxyHandler({'http': self.thumbhost})
redirect_handler = DumbRedirectHandler()
opener = urllib2.build_opener(redirect_handler, proxy_handler)
# Thumbor doesn't need (and doesn't like) the proxy
thumbor_opener = urllib2.build_opener(redirect_handler)
# Pass on certain headers from the caller squid to the scalers
opener.addheaders = []
if reqorig.headers.get('User-Agent') is not None:
opener.addheaders.append(
('User-Agent', reqorig.headers.get('User-Agent')))
else:
opener.addheaders.append(('User-Agent', self.user_agent))
for header_to_pass in [
'X-Forwarded-For', 'X-Forwarded-Proto', 'Accept',
'Accept-Encoding', 'X-Original-URI'
]:
if reqorig.headers.get(header_to_pass) is not None:
opener.addheaders.append(
(header_to_pass, reqorig.headers.get(header_to_pass)))
thumbor_opener.addheaders = opener.addheaders
# At least in theory, we shouldn't be handing out links to originals
# that we don't have (or in the case of thumbs, can't generate).
# However, someone may have a formerly valid link to a file, so we
# should do them the favor of giving them a 404.
try:
# break apach the url, url-encode it, and put it back together
urlobj = list(urlparse.urlsplit(reqorig.url))
# encode the URL but don't encode %s and /s
urlobj[2] = urllib2.quote(urlobj[2], '%/')
encodedurl = urlparse.urlunsplit(urlobj)
# Thumbor never needs URL mangling and it needs a different host
if self.thumborhost:
thumbor_reqorig = swob.Request(reqorig.environ.copy())
thumbor_reqorig.host = self.thumborhost
thumbor_urlobj = list(urlparse.urlsplit(thumbor_reqorig.url))
thumbor_urlobj[2] = urllib2.quote(thumbor_urlobj[2], '%/')
thumbor_encodedurl = urlparse.urlunsplit(thumbor_urlobj)
# if sitelang, we're supposed to mangle the URL so that
# http://upload.wm.o/wikipedia/commons/thumb/a/a2/Foo_.jpg/330px-Foo_.jpg
# changes to
# http://commons.wp.o/w/thumb_handler.php/a/a2/Foo_.jpg/330px-Foo_.jpg
if self.backend_url_format == 'sitelang':
match = re.match(
r'^http://(?P<host>[^/]+)/(?P<proj>[^-/]+)/(?P<lang>[^/]+)/thumb/(?P<path>.+)',
encodedurl)
if match:
proj = match.group('proj')
lang = match.group('lang')
# and here are all the legacy special cases, imported from thumb_handler.php
if (proj == 'wikipedia'):
if (lang in ['meta', 'commons', 'internal', 'grants']):
proj = 'wikimedia'
if (lang in ['mediawiki']):
lang = 'www'
proj = 'mediawiki'
hostname = '%s.%s.%s' % (lang, proj, self.tld)
if (proj == 'wikipedia' and lang == 'sources'):
# yay special case
hostname = 'wikisource.%s' % self.tld
# ok, replace the URL with just the part starting with thumb/
# take off the first two parts of the path
# (eg /wikipedia/commons/); make sure the string starts
# with a /
encodedurl = 'http://%s/w/thumb_handler.php/%s' % (
hostname, match.group('path'))
# add in the X-Original-URI with the swift got (minus the hostname)
opener.addheaders.append(
('X-Original-URI',
list(urlparse.urlsplit(reqorig.url))[2]))
else:
# ASSERT this code should never be hit since only thumbs
# should call the 404 handler
self.logger.warn(
"non-thumb in 404 handler! encodedurl = %s" %
encodedurl)
resp = swob.HTTPNotFound('Unexpected error')
return resp
else:
# log the result of the match here to test and make sure it's
# sane before enabling the config
match = re.match(
r'^http://(?P<host>[^/]+)/(?P<proj>[^-/]+)/(?P<lang>[^/]+)/thumb/(?P<path>.+)',
encodedurl)
if match:
proj = match.group('proj')
lang = match.group('lang')
self.logger.warn(
"sitelang match has proj %s lang %s encodedurl %s" %
(proj, lang, encodedurl))
else:
self.logger.warn("no sitelang match on encodedurl: %s" %
encodedurl)
# To turn thumbor off and have thumbnail traffic served by image scalers,
# replace the line below with this one:
# upcopy = opener.open(encodedurl)
upcopy = thumbor_opener.open(thumbor_encodedurl)
except urllib2.HTTPError as error:
# Wrap the urllib2 HTTPError into a swob HTTPException
status = error.code
if status not in swob.RESPONSE_REASONS:
# Generic status description in case of unknown status reasons.
status = "%s Error" % status
return swob.HTTPException(status=status,
body=error.msg,
headers=error.hdrs.items())
except urllib2.URLError as error:
msg = 'There was a problem while contacting the thumbnailing service: %s' % \
error.reason
return swob.HTTPServiceUnavailable(msg)
# get the Content-Type.
uinfo = upcopy.info()
c_t = uinfo.gettype()
resp = swob.Response(app_iter=upcopy, content_type=c_t)
headers_whitelist = [
'Content-Length', 'Content-Disposition', 'Last-Modified',
'Accept-Ranges', 'XKey', 'Thumbor-Engine', 'Server',
'Nginx-Request-Date', 'Nginx-Response-Date',
'Thumbor-Processing-Time', 'Thumbor-Processing-Utime',
'Thumbor-Request-Id', 'Thumbor-Request-Date'
]
# add in the headers if we've got them
for header in headers_whitelist:
if (uinfo.getheader(header) != ''):
resp.headers[header] = uinfo.getheader(header)
# also add CORS; see also our CORS middleware
resp.headers['Access-Control-Allow-Origin'] = '*'
return resp
