Merge branch 'refs/heads/develop'

This commit is contained in:
Ruud
2012-10-26 14:36:04 +02:00
213 changed files with 23055 additions and 1166 deletions
+1
View File
@@ -0,0 +1 @@
So you feel like
+22 -16
View File
@@ -2,6 +2,7 @@ from couchpotato.core.downloaders.base import Downloader
from couchpotato.core.helpers.encoding import tryUrlencode
from couchpotato.core.helpers.variable import cleanHost, mergeDicts
from couchpotato.core.logger import CPLog
from urllib2 import URLError
import json
import traceback
@@ -36,31 +37,31 @@ class Sabnzbd(Downloader):
else:
params['name'] = data.get('url')
url = cleanHost(self.conf('host')) + "api?" + tryUrlencode(params)
url = cleanHost(self.conf('host')) + 'api?' + tryUrlencode(params)
try:
if params.get('mode') is 'addfile':
sab = self.urlopen(url, timeout = 60, params = {"nzbfile": (nzb_filename, filedata)}, multipart = True, show_error = False)
sab = self.urlopen(url, timeout = 60, params = {'nzbfile': (nzb_filename, filedata)}, multipart = True, show_error = False)
else:
sab = self.urlopen(url, timeout = 60, show_error = False)
except URLError:
log.error('Failed sending release, probably wrong HOST: %s', traceback.format_exc(0))
return False
except:
log.error('Failed sending release: %s', traceback.format_exc())
log.error('Failed sending release, use API key, NOT the NZB key: %s', traceback.format_exc(0))
return False
result = sab.strip()
if not result:
log.error("SABnzbd didn't return anything.")
log.error('SABnzbd didn\'t return anything.')
return False
log.debug("Result text from SAB: " + result[:40])
if result == "ok":
log.info("NZB sent to SAB successfully.")
log.debug('Result text from SAB: %s', result[:40])
if result[:2] == 'ok':
log.info('NZB sent to SAB successfully.')
return True
elif result == "Missing authentication":
log.error("Incorrect username/password.")
return False
else:
log.error("Unknown error: " + result[:40])
log.error(result[:40])
return False
def getAllDownloadStatus(self):
@@ -75,7 +76,7 @@ class Sabnzbd(Downloader):
'mode': 'queue',
})
except:
log.error('Failed getting queue: %s', traceback.format_exc())
log.error('Failed getting queue: %s', traceback.format_exc(0))
return False
# Go through history items
@@ -85,7 +86,7 @@ class Sabnzbd(Downloader):
'limit': 15,
})
except:
log.error('Failed getting history json: %s', traceback.format_exc())
log.error('Failed getting history json: %s', traceback.format_exc(0))
return False
statuses = []
@@ -134,21 +135,26 @@ class Sabnzbd(Downloader):
'value': item['id']
}, use_json = False)
except:
log.error('Failed deleting: %s', traceback.format_exc())
log.error('Failed deleting: %s', traceback.format_exc(0))
return False
return True
def call(self, params, use_json = True):
url = cleanHost(self.conf('host')) + "api?" + tryUrlencode(mergeDicts(params, {
url = cleanHost(self.conf('host')) + 'api?' + tryUrlencode(mergeDicts(params, {
'apikey': self.conf('api_key'),
'output': 'json'
}))
data = self.urlopen(url, timeout = 60, show_error = False)
if use_json:
return json.loads(data)[params['mode']]
d = json.loads(data)
if d.get('error'):
log.error('Error getting data from SABNZBd: %s', d.get('error'))
return {}
return d[params['mode']]
else:
return data
+1 -1
View File
@@ -19,7 +19,7 @@ def addEvent(name, handler, priority = 100):
if events.get(name):
e = events[name]
else:
e = events[name] = Event(name = name, threads = 20, exc_info = True, traceback = True, lock = threading.RLock())
e = events[name] = Event(name = name, threads = 10, exc_info = True, traceback = True, lock = threading.RLock())
def createHandle(*args, **kwargs):
+2
View File
@@ -135,3 +135,5 @@ def getTitle(library_dict):
def randomString(size = 8, chars = string.ascii_uppercase + string.digits):
return ''.join(random.choice(chars) for x in range(size))
def splitString(str, split_on = ','):
return [x.strip() for x in str.split(split_on)]
+3 -3
View File
@@ -14,7 +14,7 @@ class Notification(Plugin):
test_message = 'ZOMG Lazors Pewpewpew!'
listen_to = [
'movie.downloaded', 'movie.snatched',
'renamer.after', 'movie.snatched',
'updater.available', 'updater.updated',
]
dont_listen_to = []
@@ -30,10 +30,10 @@ class Notification(Plugin):
addEvent(listener, self.createNotifyHandler(listener))
def createNotifyHandler(self, listener):
def notify(message, data):
def notify(message = None, group = {}, data = None):
if not self.conf('on_snatch', default = True) and listener == 'movie.snatched':
return
return self.notify(message = message, data = data, listener = listener)
return self.notify(message = message, data = data if data else group, listener = listener)
return notify
+4 -4
View File
@@ -3,7 +3,7 @@ from couchpotato.api import addApiView, addNonBlockApiView
from couchpotato.core.event import addEvent
from couchpotato.core.helpers.encoding import toUnicode
from couchpotato.core.helpers.request import jsonified, getParam
from couchpotato.core.helpers.variable import tryInt
from couchpotato.core.helpers.variable import tryInt, splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.notifications.base import Notification
from couchpotato.core.settings.model import Notification as Notif
@@ -22,7 +22,7 @@ class CoreNotifier(Notification):
listeners = []
listen_to = [
'movie.downloaded', 'movie.snatched',
'renamer.after', 'movie.snatched',
'updater.available', 'updater.updated',
]
@@ -67,7 +67,7 @@ class CoreNotifier(Notification):
ids = None
if getParam('ids'):
ids = [x.strip() for x in getParam('ids').split(',')]
ids = splitString(getParam('ids'))
db = get_session()
@@ -92,7 +92,7 @@ class CoreNotifier(Notification):
q = db.query(Notif)
if limit_offset:
splt = [x.strip() for x in limit_offset.split(',')]
splt = splitString(limit_offset)
limit = splt[0]
offset = 0 if len(splt) is 1 else splt[1]
q = q.limit(limit).offset(offset)
+4 -4
View File
@@ -69,7 +69,7 @@ class NMJ(Notification):
'mount': mount,
})
def addToLibrary(self, group = {}):
def addToLibrary(self, message = None, group = {}):
if self.isDisabled(): return
host = self.conf('host')
@@ -114,8 +114,8 @@ class NMJ(Notification):
def failed(self):
return jsonified({'success': False})
def test(self):
return jsonified({'success': self.addToLibrary()})
@@ -1,3 +1,4 @@
from couchpotato.core.helpers.variable import splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.notifications.base import Notification
import pynma
@@ -11,7 +12,7 @@ class NotifyMyAndroid(Notification):
if self.isDisabled(): return
nma = pynma.PyNMA()
keys = [x.strip() for x in self.conf('api_key').split(',')]
keys = splitString(self.conf('api_key'))
nma.addkey(keys)
nma.developerkey(self.conf('dev_key'))
@@ -1,3 +1,4 @@
from couchpotato.core.helpers.variable import splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.notifications.base import Notification
from pynmwp import PyNMWP
@@ -10,7 +11,7 @@ class NotifyMyWP(Notification):
def notify(self, message = '', data = {}, listener = None):
if self.isDisabled(): return
keys = [x.strip() for x in self.conf('api_key').split(',')]
keys = splitString(self.conf('api_key'))
p = PyNMWP(keys, self.conf('dev_key'))
response = p.push(application = self.default_title, event = message, description = message, priority = self.conf('priority'), batch_mode = len(keys) > 1)
+1 -1
View File
@@ -17,7 +17,7 @@ class Plex(Notification):
super(Plex, self).__init__()
addEvent('renamer.after', self.addToLibrary)
def addToLibrary(self, group = {}):
def addToLibrary(self, message = None, group = {}):
if self.isDisabled(): return
log.info('Sending notification to Plex')
+15 -19
View File
@@ -1,39 +1,35 @@
from couchpotato.core.helpers.encoding import toUnicode, tryUrlencode
from couchpotato.core.helpers.encoding import toUnicode
from couchpotato.core.logger import CPLog
from couchpotato.core.notifications.base import Notification
from httplib import HTTPSConnection
import traceback
log = CPLog(__name__)
class Prowl(Notification):
urls = {
'api': 'https://api.prowlapp.com/publicapi/add'
}
def notify(self, message = '', data = {}, listener = None):
if self.isDisabled(): return
http_handler = HTTPSConnection('api.prowlapp.com')
data = {
'apikey': self.conf('api_key'),
'application': self.default_title,
'description': toUnicode(message),
'priority': self.conf('priority'),
}
headers = {
'Content-type': 'application/x-www-form-urlencoded'
}
http_handler.request('POST',
'/publicapi/add',
headers = {'Content-type': 'application/x-www-form-urlencoded'},
body = tryUrlencode(data)
)
response = http_handler.getresponse()
request_status = response.status
if request_status == 200:
try:
self.urlopen(self.urls['api'], headers = headers, params = data, multipart = True, show_error = False)
log.info('Prowl notifications sent.')
return True
elif request_status == 401:
log.error('Prowl auth failed: %s', response.reason)
return False
else:
log.error('Prowl notification failed.')
return False
except:
log.error('Prowl failed: %s', traceback.format_exc())
return False
@@ -16,7 +16,7 @@ class Synoindex(Notification):
super(Synoindex, self).__init__()
addEvent('renamer.after', self.addToLibrary)
def addToLibrary(self, group = {}):
def addToLibrary(self, message = None, group = {}):
if self.isDisabled(): return
command = [self.index_path, '-A', group.get('destination_dir')]
+16 -5
View File
@@ -38,22 +38,33 @@ class Twitter(Notification):
direct_message = self.conf('direct_message')
direct_message_users = self.conf('screen_name')
mention = self.conf('mention')
mention_tag = None
if mention:
if direct_message:
direct_message_users = '%s %s' % (direct_message_users, mention)
direct_message_users = direct_message_users.replace('@',' ')
direct_message_users = direct_message_users.replace(',',' ')
direct_message_users = direct_message_users.replace('@', ' ')
direct_message_users = direct_message_users.replace(',', ' ')
else:
message = '%s @%s' % (message, mention.lstrip('@'))
mention_tag = '@%s' % mention.lstrip('@')
message = '%s %s' % (message, mention_tag)
try:
if direct_message:
for user in direct_message_users.split():
api.PostDirectMessage(user, '[%s] %s' % (self.default_title, message))
else:
api.PostUpdate('[%s] %s' % (self.default_title, message))
update_message = '[%s] %s' % (self.default_title, message)
if len(update_message) > 140:
if mention_tag:
api.PostUpdate(update_message[:135 - len(mention_tag)] + ('%s 1/2 ' % mention_tag))
api.PostUpdate(update_message[135 - len(mention_tag):] + ('%s 2/2 ' % mention_tag))
else:
api.PostUpdate(update_message[:135] + ' 1/2')
api.PostUpdate(update_message[135:] + ' 2/2')
else:
api.PostUpdate(update_message)
except Exception, e:
log.error('Error sending tweet: %s', e)
return False
+37 -21
View File
@@ -1,6 +1,7 @@
from couchpotato.core.helpers.encoding import tryUrlencode
from couchpotato.core.helpers.variable import splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.notifications.base import Notification
from flask.helpers import json
import base64
log = CPLog(__name__)
@@ -8,36 +9,51 @@ log = CPLog(__name__)
class XBMC(Notification):
listen_to = ['movie.downloaded']
listen_to = ['renamer.after']
def notify(self, message = '', data = {}, listener = None):
if self.isDisabled(): return
hosts = [x.strip() for x in self.conf('host').split(",")]
hosts = splitString(self.conf('host'))
successful = 0
for host in hosts:
if self.send({'command': 'ExecBuiltIn', 'parameter': 'Notification(CouchPotato, %s)' % message}, host):
successful += 1
if self.send({'command': 'ExecBuiltIn', 'parameter': 'XBMC.updatelibrary(video)'}, host):
successful += 1
response = self.request(host, [
('GUI.ShowNotification', {"title":"CouchPotato", "message":message}),
('VideoLibrary.Scan', {}),
])
return successful == len(hosts)*2
for result in response:
if result['result'] == "OK":
successful += 1
def send(self, command, host):
return successful == len(hosts) * 2
url = 'http://%s/xbmcCmds/xbmcHttp/?%s' % (host, tryUrlencode(command))
def request(self, host, requests):
server = 'http://%s/jsonrpc' % host
data = []
for req in requests:
method, kwargs = req
data.append({
'method': method,
'params': kwargs,
'jsonrpc': '2.0',
'id': method,
})
data = json.dumps(data)
headers = {
'Content-Type': 'application/json',
}
headers = {}
if self.conf('password'):
headers = {
'Authorization': "Basic %s" % base64.encodestring('%s:%s' % (self.conf('username'), self.conf('password')))[:-1]
}
base64string = base64.encodestring('%s:%s' % (self.conf('username'), self.conf('password'))).replace('\n', '')
headers['Authorization'] = 'Basic %s' % base64string
try:
self.urlopen(url, headers = headers, show_error = False)
except:
log.error("Couldn't sent command to XBMC")
return False
log.debug('Sending request to %s: %s', (host, data))
rdata = self.urlopen(server, headers = headers, params = data, multipart = True)
response = json.loads(rdata)
log.debug('Returned from request %s: %s', (host, response))
return response
log.info('XBMC notification to %s successful.', host)
return True
+9 -1
View File
@@ -18,9 +18,17 @@ class Automation(Plugin):
def addMovies(self):
movies = fireEvent('automation.get_movies', merge = True)
movie_ids = []
for imdb_id in movies:
prop_name = 'automation.added.%s' % imdb_id
added = Env.prop(prop_name, default = False)
if not added:
fireEvent('movie.add', params = {'identifier': imdb_id}, force_readd = False)
added_movie = fireEvent('movie.add', params = {'identifier': imdb_id}, force_readd = False, search_after = False, update_library = True, single = True)
if added_movie:
movie_ids.append(added_movie['id'])
Env.prop(prop_name, True)
for movie_id in movie_ids:
movie_dict = fireEvent('movie.get', movie_id, single = True)
fireEvent('searcher.single', movie_dict)
+3 -2
View File
@@ -124,7 +124,7 @@ class Plugin(object):
try:
if multipart:
log.info('Opening multipart url: %s, params: %s', (url, [x for x in params.iterkeys()]))
log.info('Opening multipart url: %s, params: %s', (url, [x for x in params.iterkeys()] if isinstance(params, dict) else 'with data'))
request = urllib2.Request(url, params, headers)
cookies = cookielib.CookieJar()
@@ -239,7 +239,8 @@ class Plugin(object):
self.setCache(cache_key, data, timeout = cache_timeout)
return data
except:
pass
if not kwargs.get('show_error'):
raise
def setCache(self, cache_key, value, timeout = 300):
log.debug('Setting cache %s', cache_key)
+35
View File
@@ -2,9 +2,11 @@ from couchpotato import get_session
from couchpotato.api import addApiView
from couchpotato.core.event import addEvent
from couchpotato.core.helpers.encoding import toUnicode
from couchpotato.core.helpers.request import jsonified
from couchpotato.core.helpers.variable import md5, getExt
from couchpotato.core.logger import CPLog
from couchpotato.core.plugins.base import Plugin
from couchpotato.core.plugins.scanner.main import Scanner
from couchpotato.core.settings.model import FileType, File
from couchpotato.environment import Env
import os.path
@@ -29,7 +31,34 @@ class FileManager(Plugin):
'return': {'type': 'file'}
})
addApiView('file.types', self.getTypesView, docs = {
'desc': 'Return a list of all the file types and their ids.',
'return': {'type': 'object', 'example': """{
'types': [
{
"identifier": "poster_original",
"type": "image",
"id": 1,
"name": "Poster_original"
},
{
"identifier": "poster",
"type": "image",
"id": 2,
"name": "Poster"
},
etc
]
}"""}
})
addEvent('app.load', self.cleanup)
addEvent('app.load', self.init)
def init(self):
for type_tuple in Scanner.file_types.values():
self.getType(type_tuple)
def cleanup(self):
@@ -122,3 +151,9 @@ class FileManager(Plugin):
types.append(type_object.to_dict())
return types
def getTypesView(self):
return jsonified({
'types': self.getTypes()
})
+130 -30
View File
@@ -2,22 +2,32 @@ from couchpotato.api import addApiView
from couchpotato.core.event import fireEvent, addEvent, fireEventAsync
from couchpotato.core.helpers.encoding import ss
from couchpotato.core.helpers.request import jsonified, getParam
from couchpotato.core.helpers.variable import getTitle, splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.plugins.base import Plugin
from couchpotato.environment import Env
import os
import time
import traceback
log = CPLog(__name__)
class Manage(Plugin):
in_progress = False
def __init__(self):
fireEvent('scheduler.interval', identifier = 'manage.update_library', handle = self.updateLibrary, hours = 2)
addEvent('manage.update', self.updateLibrary)
# Add files after renaming
def after_rename(message = None, group = {}):
return self.scanFilesToLibrary(folder = group['destination_dir'], files = group['renamed_files'])
addEvent('renamer.after', after_rename, priority = 110)
addApiView('manage.update', self.updateLibraryView, docs = {
'desc': 'Update the library by scanning for new movies',
'params': {
@@ -25,11 +35,23 @@ class Manage(Plugin):
}
})
addApiView('manage.progress', self.getProgress, docs = {
'desc': 'Get the progress of current manage update',
'return': {'type': 'object', 'example': """{
'progress': False || object, total & to_go,
}"""},
})
if not Env.get('dev'):
def updateLibrary():
self.updateLibrary(full = False)
addEvent('app.load', updateLibrary)
def getProgress(self):
return jsonified({
'progress': self.in_progress
})
def updateLibraryView(self):
full = getParam('full', default = 1)
@@ -43,49 +65,127 @@ class Manage(Plugin):
def updateLibrary(self, full = True):
last_update = float(Env.prop('manage.last_update', default = 0))
if self.isDisabled() or (last_update > time.time() - 20):
if self.in_progress:
log.info('Already updating library: %s', self.in_progress)
return
elif self.isDisabled() or (last_update > time.time() - 20):
return
directories = self.directories()
added_identifiers = []
self.in_progress = {}
fireEvent('notify.frontend', type = 'manage.updating', data = True)
for directory in directories:
try:
if not os.path.isdir(directory):
if len(directory) > 0:
log.error('Directory doesn\'t exist: %s', directory)
continue
directories = self.directories()
added_identifiers = []
log.info('Updating manage library: %s', directory)
identifiers = fireEvent('scanner.folder', folder = directory, newer_than = last_update if not full else 0, single = True)
if identifiers:
added_identifiers.extend(identifiers)
# Add some progress
self.in_progress = {}
for directory in directories:
self.in_progress[os.path.normpath(directory)] = {
'total': None,
'to_go': None,
}
# Break if CP wants to shut down
if self.shuttingDown():
for directory in directories:
folder = os.path.normpath(directory)
if not os.path.isdir(folder):
if len(directory) > 0:
log.error('Directory doesn\'t exist: %s', folder)
continue
log.info('Updating manage library: %s', folder)
fireEvent('notify.frontend', type = 'manage.update', data = True, message = 'Scanning for movies in "%s"' % folder)
onFound = self.createAddToLibrary(folder, added_identifiers)
fireEvent('scanner.scan', folder = folder, simple = True, newer_than = last_update if not full else 0, on_found = onFound, single = True)
# Break if CP wants to shut down
if self.shuttingDown():
break
# If cleanup option is enabled, remove offline files from database
if self.conf('cleanup') and full and not self.shuttingDown():
# Get movies with done status
total_movies, done_movies = fireEvent('movie.list', status = 'done', single = True)
for done_movie in done_movies:
if done_movie['library']['identifier'] not in added_identifiers:
fireEvent('movie.delete', movie_id = done_movie['id'], delete_from = 'all')
else:
for release in done_movie.get('releases', []):
for release_file in release.get('files', []):
# Remove release not available anymore
if not os.path.isfile(ss(release_file['path'])):
fireEvent('release.clean', release['id'])
break
Env.prop('manage.last_update', time.time())
except:
log.error('Failed updating library: %s', (traceback.format_exc()))
while True and not self.shuttingDown():
delete_me = {}
for folder in self.in_progress:
if self.in_progress[folder]['to_go'] <= 0:
delete_me[folder] = True
for delete in delete_me:
del self.in_progress[delete]
if len(self.in_progress) == 0:
break
# If cleanup option is enabled, remove offline files from database
if self.conf('cleanup') and full and not self.shuttingDown():
time.sleep(1)
# Get movies with done status
total_movies, done_movies = fireEvent('movie.list', status = 'done', single = True)
fireEvent('notify.frontend', type = 'manage.updating', data = False)
self.in_progress = False
for done_movie in done_movies:
if done_movie['library']['identifier'] not in added_identifiers:
fireEvent('movie.delete', movie_id = done_movie['id'], delete_from = 'all')
else:
for release in done_movie.get('releases', []):
for release_file in release.get('files', []):
# Remove release not available anymore
if not os.path.isfile(ss(release_file['path'])):
fireEvent('release.clean', release['id'])
break
def createAddToLibrary(self, folder, added_identifiers = []):
def addToLibrary(group, total_found, to_go):
if self.in_progress[folder]['total'] is None:
self.in_progress[folder] = {
'total': total_found,
'to_go': total_found,
}
Env.prop('manage.last_update', time.time())
if group['library']:
identifier = group['library'].get('identifier')
added_identifiers.append(identifier)
# Add it to release and update the info
fireEvent('release.add', group = group)
fireEventAsync('library.update', identifier = identifier, on_complete = self.createAfterUpdate(folder, identifier))
return addToLibrary
def createAfterUpdate(self, folder, identifier):
# Notify frontend
def afterUpdate():
self.in_progress[folder]['to_go'] = self.in_progress[folder]['to_go'] - 1
total = self.in_progress[folder]['total']
movie_dict = fireEvent('movie.get', identifier, single = True)
fireEvent('notify.frontend', type = 'movie.added', data = movie_dict, message = None if total > 5 else 'Added "%s" to manage.' % getTitle(movie_dict['library']))
return afterUpdate
def directories(self):
try:
return [x.strip() for x in self.conf('library', default = '').split('::')]
return splitString(self.conf('library', default = ''), '::')
except:
return []
def scanFilesToLibrary(self, folder = None, files = None):
folder = os.path.normpath(folder)
groups = fireEvent('scanner.scan', folder = folder, files = files, single = True)
for group in groups.itervalues():
if group['library']:
fireEvent('release.add', group = group)
+14 -9
View File
@@ -3,7 +3,7 @@ from couchpotato.api import addApiView
from couchpotato.core.event import fireEvent, fireEventAsync, addEvent
from couchpotato.core.helpers.encoding import toUnicode, simplifyString
from couchpotato.core.helpers.request import getParams, jsonified, getParam
from couchpotato.core.helpers.variable import getImdb
from couchpotato.core.helpers.variable import getImdb, splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.plugins.base import Plugin
from couchpotato.core.settings.model import Library, LibraryTitle, Movie
@@ -107,13 +107,18 @@ class MoviePlugin(Plugin):
def get(self, movie_id):
db = get_session()
m = db.query(Movie).filter_by(id = movie_id).first()
imdb_id = getImdb(str(movie_id))
if(imdb_id):
m = db.query(Movie).filter(Movie.library.has(identifier = imdb_id)).first()
else:
m = db.query(Movie).filter_by(id = movie_id).first()
results = None
if m:
results = m.to_dict(self.default_dict)
#db.close()
return results
def list(self, status = ['active'], limit_offset = None, starts_with = None, search = None):
@@ -161,7 +166,7 @@ class MoviePlugin(Plugin):
.options(joinedload_all('files'))
if limit_offset:
splt = [x.strip() for x in limit_offset.split(',')]
splt = splitString(limit_offset)
limit = splt[0]
offset = 0 if len(splt) is 1 else splt[1]
q2 = q2.limit(limit).offset(offset)
@@ -239,7 +244,7 @@ class MoviePlugin(Plugin):
db = get_session()
for id in getParam('id').split(','):
for id in splitString(getParam('id')):
movie = db.query(Movie).filter_by(id = id).first()
if movie:
@@ -278,7 +283,7 @@ class MoviePlugin(Plugin):
'movies': movies,
})
def add(self, params = {}, force_readd = True, search_after = True):
def add(self, params = {}, force_readd = True, search_after = True, update_library = False):
if not params.get('identifier'):
msg = 'Can\'t add movie without imdb identifier.'
@@ -298,7 +303,7 @@ class MoviePlugin(Plugin):
pass
library = fireEvent('library.add', single = True, attrs = params, update_after = False)
library = fireEvent('library.add', single = True, attrs = params, update_after = update_library)
# Status
status_active = fireEvent('status.add', 'active', single = True)
@@ -381,7 +386,7 @@ class MoviePlugin(Plugin):
available_status = fireEvent('status.get', 'available', single = True)
ids = [x.strip() for x in params.get('id').split(',')]
ids = splitString(params.get('id'))
for movie_id in ids:
m = db.query(Movie).filter_by(id = movie_id).first()
@@ -417,7 +422,7 @@ class MoviePlugin(Plugin):
params = getParams()
ids = [x.strip() for x in params.get('id').split(',')]
ids = splitString(params.get('id'))
for movie_id in ids:
self.delete(movie_id, delete_from = params.get('delete_from', 'all'))
+15 -9
View File
@@ -33,29 +33,34 @@ var MovieList = new Class({
);
self.getMovies();
if(options.add_new)
App.addEvent('movie.added', self.movieAdded.bind(self))
App.addEvent('movie.added', self.movieAdded.bind(self))
App.addEvent('movie.deleted', self.movieDeleted.bind(self))
},
movieDeleted: function(notification){
var self = this;
if(!self.movies_added[notification.data.id])
self.movies_added[notification.data.id].destroy();
if(self.movies_added[notification.data.id]){
self.movies.each(function(movie){
if(movie.get('id') == notification.data.id){
movie.destroy();
delete self.movies_added[notification.data.id]
}
})
}
self.checkIfEmpty();
},
movieAdded: function(notification){
var self = this;
window.scroll(0,0);
if(!self.movies_added[notification.data.id])
if(self.options.add_new && !self.movies_added[notification.data.id] && notification.data.status.identifier == self.options.status){
window.scroll(0,0);
self.createMovie(notification.data, 'top');
self.checkIfEmpty();
self.checkIfEmpty();
}
},
create: function(){
@@ -100,6 +105,7 @@ var MovieList = new Class({
self.createMovie(movie);
});
self.total_movies = total;
self.setCounter(total);
},
@@ -495,7 +501,7 @@ var MovieList = new Class({
checkIfEmpty: function(){
var self = this;
var is_empty = self.movies.length == 0;
var is_empty = self.movies.length == 0 && self.total_movies == 0;
if(is_empty && self.options.on_empty_element){
self.el.grab(self.options.on_empty_element);
+73 -11
View File
@@ -24,7 +24,7 @@
.movies .movie.list_view:hover, .movies .movie.mass_edit_view:hover {
background: rgba(255,255,255,0.03);
}
.movies .movie_container {
overflow: hidden;
}
@@ -313,7 +313,7 @@
padding-bottom: 4px;
height: auto;
}
.movies .movie .trailer_container {
width: 100%;
background: #000;
@@ -324,7 +324,7 @@
.movies .movie .trailer_container.hide {
height: 0 !important;
}
.movies .movie .hide_trailer {
position: absolute;
top: 0;
@@ -340,12 +340,12 @@
.movies .movie .hide_trailer.hide {
top: -30px;
}
.movies .movie .try_container {
padding: 5px 10px;
text-align: center;
}
.movies .movie .try_container a {
margin: 0 5px;
padding: 2px 5px;
@@ -354,15 +354,15 @@
.movies .movie .releases .next_release {
border-left: 6px solid #2aa300;
}
.movies .movie .releases .next_release > :first-child {
margin-left: -6px;
}
.movies .movie .releases .last_release {
border-left: 6px solid #ffa200;
}
.movies .movie .releases .last_release > :first-child {
margin-left: -6px;
}
@@ -394,8 +394,8 @@
border-radius: 0;
}
.movies .alph_nav ul.numbers,
.movies .alph_nav .counter,
.movies .alph_nav ul.numbers,
.movies .alph_nav .counter,
.movies .alph_nav ul.actions {
list-style: none;
padding: 0 0 1px;
@@ -518,7 +518,7 @@
padding: 3px 7px;
}
.movies .alph_nav .mass_edit_form .refresh,
.movies .alph_nav .mass_edit_form .refresh,
.movies .alph_nav .mass_edit_form .delete {
float: left;
padding: 8px 0 0 8px;
@@ -536,3 +536,65 @@
.movies .alph_nav .more_menu > a {
background-position: center -158px;
}
.movies .empty_wanted {
background-image: url('../images/emptylist.png');
height: 750px;
width: 800px;
padding-top: 260px;
margin-top: -50px;
}
.movies .empty_manage {
text-align: center;
font-size: 25px;
line-height: 150%;
}
.movies .empty_manage .after_manage {
margin-top: 30px;
font-size: 16px;
}
.movies .progress {
border-radius: 2px;
padding: 10px;
margin: 5px 0;
text-align: left;
}
.movies .progress > div {
padding: 5px 10px;
font-size: 12px;
line-height: 12px;
text-align: left;
display: inline-block;
width: 49%;
background: rgba(255, 255, 255, 0.05);
margin: 2px 0.5%;
border-radius: 3px;
}
.movies .progress > div .folder {
display: inline-block;
padding: 5px 20px 5px 0;
white-space: nowrap;
text-overflow: ellipsis;
overflow: hidden;
width: 85%;
direction: rtl;
vertical-align: middle;
}
.movies .progress > div .percentage {
font-weight: bold;
display: inline-block;
text-transform: uppercase;
text-shadow: none;
font-weight: normal;
font-size: 20px;
border-left: 1px solid rgba(255, 255, 255, .2);
width: 15%;
text-align: right;
vertical-align: middle;
}
+34 -28
View File
@@ -50,7 +50,7 @@ class Renamer(Plugin):
return
if self.renaming_started is True:
log.info('Renamer is disabled to avoid infinite looping of the same error.')
log.info('Renamer is already running, if you see this often, check the logs above for errors.')
return
# Check to see if the "to" folder is inside the "from" folder.
@@ -129,6 +129,8 @@ class Renamer(Plugin):
'resolution_width': group['meta_data'].get('resolution_width'),
'resolution_height': group['meta_data'].get('resolution_height'),
'imdb_id': library['identifier'],
'cd': '',
'cd_nr': '',
}
for file_type in group['files']:
@@ -146,7 +148,7 @@ class Renamer(Plugin):
continue
# Move other files
multiple = len(group['files']['movie']) > 1 and not group['is_dvd']
multiple = len(group['files'][file_type]) > 1 and not group['is_dvd']
cd = 1 if multiple else 0
for current_file in sorted(list(group['files'][file_type])):
@@ -159,23 +161,19 @@ class Renamer(Plugin):
replacements['ext'] = getExt(current_file)
# cd #
replacements['cd'] = ' cd%d' % cd if cd else ''
replacements['cd_nr'] = cd
replacements['cd'] = ' cd%d' % cd if multiple else ''
replacements['cd_nr'] = cd if multiple else ''
# Naming
final_folder_name = self.doReplace(folder_name, replacements)
final_file_name = self.doReplace(file_name, replacements)
replacements['filename'] = final_file_name[:-(len(getExt(final_file_name)) + 1)]
# Group filename without cd extension
replacements['cd'] = ''
replacements['cd_nr'] = ''
# Meta naming
if file_type is 'trailer':
final_file_name = self.doReplace(trailer_name, replacements)
final_file_name = self.doReplace(trailer_name, replacements, remove_multiple = True)
elif file_type is 'nfo':
final_file_name = self.doReplace(nfo_name, replacements)
final_file_name = self.doReplace(nfo_name, replacements, remove_multiple = True)
# Seperator replace
if separator:
@@ -206,10 +204,16 @@ class Renamer(Plugin):
# Check for extra subtitle files
if file_type is 'subtitle':
# rename subtitles with or without language
rename_files[current_file] = os.path.join(destination, final_folder_name, final_file_name)
remove_multiple = False
if len(group['files']['movie']) == 1:
remove_multiple = True
sub_langs = group['subtitle_language'].get(current_file, [])
# rename subtitles with or without language
sub_name = self.doReplace(file_name, replacements, remove_multiple = remove_multiple)
rename_files[current_file] = os.path.join(destination, final_folder_name, sub_name)
rename_extras = self.getRenameExtras(
extra_type = 'subtitle_extra',
replacements = replacements,
@@ -217,20 +221,19 @@ class Renamer(Plugin):
file_name = file_name,
destination = destination,
group = group,
current_file = current_file
current_file = current_file,
remove_multiple = remove_multiple,
)
# Don't add language if multiple languages in 1 file
if len(sub_langs) > 1:
rename_files[current_file] = os.path.join(destination, final_folder_name, final_file_name)
elif len(sub_langs) == 1:
# Don't add language if multiple languages in 1 subtitle file
if len(sub_langs) == 1:
sub_name = final_file_name.replace(replacements['ext'], '%s.%s' % (sub_langs[0], replacements['ext']))
rename_files[current_file] = os.path.join(destination, final_folder_name, sub_name)
rename_files = mergeDicts(rename_files, rename_extras)
# Filename without cd etc
if file_type is 'movie':
elif file_type is 'movie':
rename_extras = self.getRenameExtras(
extra_type = 'movie_extra',
replacements = replacements,
@@ -242,7 +245,7 @@ class Renamer(Plugin):
)
rename_files = mergeDicts(rename_files, rename_extras)
group['filename'] = self.doReplace(file_name, replacements)[:-(len(getExt(final_file_name)) + 1)]
group['filename'] = self.doReplace(file_name, replacements, remove_multiple = True)[:-(len(getExt(final_file_name)) + 1)]
group['destination_dir'] = os.path.join(destination, final_folder_name)
if multiple:
@@ -377,12 +380,9 @@ class Renamer(Plugin):
except:
log.error('Failed removing %s: %s', (group['parentdir'], traceback.format_exc()))
# Search for trailers etc
fireEventAsync('renamer.after', group)
# Notify on download
# Notify on download, search for trailers etc
download_message = 'Downloaded %s (%s)' % (movie_title, replacements['quality'])
fireEventAsync('movie.downloaded', message = download_message, data = group)
fireEvent('renamer.after', message = download_message, group = group, in_order = True)
# Break if CP wants to shut down
if self.shuttingDown():
@@ -390,8 +390,9 @@ class Renamer(Plugin):
self.renaming_started = False
def getRenameExtras(self, extra_type = '', replacements = {}, folder_name = '', file_name = '', destination = '', group = {}, current_file = ''):
def getRenameExtras(self, extra_type = '', replacements = {}, folder_name = '', file_name = '', destination = '', group = {}, current_file = '', remove_multiple = False):
replacements = replacements.copy()
rename_files = {}
def test(s):
@@ -400,8 +401,8 @@ class Renamer(Plugin):
for extra in set(filter(test, group['files'][extra_type])):
replacements['ext'] = getExt(extra)
final_folder_name = self.doReplace(folder_name, replacements)
final_file_name = self.doReplace(file_name, replacements)
final_folder_name = self.doReplace(folder_name, replacements, remove_multiple = remove_multiple)
final_file_name = self.doReplace(file_name, replacements, remove_multiple = remove_multiple)
rename_files[extra] = os.path.join(destination, final_folder_name, final_file_name)
return rename_files
@@ -456,11 +457,16 @@ class Renamer(Plugin):
return True
def doReplace(self, string, replacements):
def doReplace(self, string, replacements, remove_multiple = False):
'''
replace confignames with the real thing
'''
replacements = replacements.copy()
if remove_multiple:
replacements['cd'] = ''
replacements['cd_nr'] = ''
replaced = toUnicode(string)
for x, r in replacements.iteritems():
if r is not None:
+27 -51
View File
@@ -34,6 +34,7 @@ class Scanner(Plugin):
'subtitle_extra': ['idx'],
'trailer': ['mov', 'mp4', 'flv']
}
file_types = {
'subtitle': ('subtitle', 'subtitle'),
'subtitle_extra': ('subtitle', 'subtitle_extra'),
@@ -42,6 +43,8 @@ class Scanner(Plugin):
'movie': ('video', 'movie'),
'movie_extra': ('movie', 'movie_extra'),
'backdrop': ('image', 'backdrop'),
'poster': ('image', 'poster'),
'thumbnail': ('image', 'thumbnail'),
'leftover': ('leftover', 'leftover'),
}
@@ -80,55 +83,10 @@ class Scanner(Plugin):
addEvent('scanner.remove_cptag', self.removeCPTag)
addEvent('scanner.scan', self.scan)
addEvent('scanner.files', self.scanFilesToLibrary)
addEvent('scanner.folder', self.scanFolderToLibrary)
addEvent('scanner.name_year', self.getReleaseNameYear)
addEvent('scanner.partnumber', self.getPartNumber)
def after_rename(group):
return self.scanFilesToLibrary(folder = group['destination_dir'], files = group['renamed_files'])
addEvent('renamer.after', after_rename)
def scanFilesToLibrary(self, folder = None, files = None):
folder = os.path.normpath(folder)
groups = self.scan(folder = folder, files = files)
for group in groups.itervalues():
if group['library']:
fireEvent('release.add', group = group)
def scanFolderToLibrary(self, folder = None, newer_than = 0, simple = True):
folder = os.path.normpath(folder)
if not os.path.isdir(folder):
return
groups = self.scan(folder = folder, simple = simple, newer_than = newer_than)
added_identifier = []
while True and not self.shuttingDown():
try:
identifier, group = groups.popitem()
except:
break
# Save to DB
if group['library']:
# Add release
fireEvent('release.add', group = group)
library_item = fireEvent('library.update', identifier = group['library'].get('identifier'), single = True)
if library_item:
added_identifier.append(library_item['identifier'])
return added_identifier
def scan(self, folder = None, files = [], simple = False, newer_than = 0):
def scan(self, folder = None, files = None, simple = False, newer_than = 0, on_found = None):
folder = ss(os.path.normpath(folder))
@@ -141,7 +99,8 @@ class Scanner(Plugin):
leftovers = []
# Scan all files of the folder if no files are set
if len(files) == 0:
if not files:
check_file_date = True
try:
files = []
for root, dirs, walk_files in os.walk(folder):
@@ -150,6 +109,7 @@ class Scanner(Plugin):
except:
log.error('Failed getting files from %s: %s', (folder, traceback.format_exc()))
else:
check_file_date = False
files = [ss(x) for x in files]
db = get_session()
@@ -279,8 +239,8 @@ class Scanner(Plugin):
del path_identifiers[identifier]
del delete_identifiers
# Determine file types
processed_movies = {}
# Make sure we remove older / still extracting files
valid_files = {}
while True and not self.shuttingDown():
try:
identifier, group = movie_files.popitem()
@@ -302,7 +262,7 @@ class Scanner(Plugin):
if file_too_new:
break
if file_too_new:
if check_file_date and file_too_new:
try:
time_string = time.ctime(file_time[0])
except:
@@ -335,6 +295,19 @@ class Scanner(Plugin):
continue
valid_files[identifier] = group
del movie_files
# Determine file types
processed_movies = {}
total_found = len(valid_files)
while True and not self.shuttingDown():
try:
identifier, group = valid_files.popitem()
except:
break
# Group extra (and easy) files first
# images = self.getImages(group['unsorted_files'])
group['files'] = {
@@ -395,9 +368,12 @@ class Scanner(Plugin):
movie = db.query(Movie).filter_by(library_id = group['library']['id']).first()
group['movie_id'] = None if not movie else movie.id
processed_movies[identifier] = group
# Notify parent & progress on something found
if on_found:
on_found(group, total_found, total_found - len(processed_movies))
if len(processed_movies) > 0:
log.info('Found %s movies in the folder %s', (len(processed_movies), folder))
else:
+43 -33
View File
@@ -180,10 +180,10 @@ class Searcher(Plugin):
status_id = available_status.get('id')
)
db.add(rls)
db.commit()
else:
[db.delete(info) for info in rls.info]
db.commit()
[db.delete(old_info) for old_info in rls.info]
db.commit()
for info in nzb:
try:
@@ -195,10 +195,11 @@ class Searcher(Plugin):
value = toUnicode(nzb[info])
)
rls.info.append(rls_info)
db.commit()
except InterfaceError:
log.debug('Couldn\'t add %s to ReleaseInfo: %s', (info, traceback.format_exc()))
db.commit()
nzb['status_id'] = rls.status_id
@@ -245,38 +246,42 @@ class Searcher(Plugin):
if successful:
# Mark release as snatched
db = get_session()
rls = db.query(Release).filter_by(identifier = md5(data['url'])).first()
rls.status_id = snatched_status.get('id')
db.commit()
try:
# Mark release as snatched
db = get_session()
rls = db.query(Release).filter_by(identifier = md5(data['url'])).first()
if rls:
rls.status_id = snatched_status.get('id')
db.commit()
log_movie = '%s (%s) in %s' % (getTitle(movie['library']), movie['library']['year'], rls.quality.label)
snatch_message = 'Snatched "%s": %s' % (data.get('name'), log_movie)
log.info(snatch_message)
fireEvent('movie.snatched', message = snatch_message, data = rls.to_dict())
log_movie = '%s (%s) in %s' % (getTitle(movie['library']), movie['library']['year'], rls.quality.label)
snatch_message = 'Snatched "%s": %s' % (data.get('name'), log_movie)
log.info(snatch_message)
fireEvent('movie.snatched', message = snatch_message, data = rls.to_dict())
# If renamer isn't used, mark movie done
if not Env.setting('enabled', 'renamer'):
active_status = fireEvent('status.get', 'active', single = True)
done_status = fireEvent('status.get', 'done', single = True)
try:
if movie['status_id'] == active_status.get('id'):
for profile_type in movie['profile']['types']:
if rls and profile_type['quality_id'] == rls.quality.id and profile_type['finish']:
log.info('Renamer disabled, marking movie as finished: %s', log_movie)
# If renamer isn't used, mark movie done
if not Env.setting('enabled', 'renamer'):
active_status = fireEvent('status.get', 'active', single = True)
done_status = fireEvent('status.get', 'done', single = True)
try:
if movie['status_id'] == active_status.get('id'):
for profile_type in movie['profile']['types']:
if profile_type['quality_id'] == rls.quality.id and profile_type['finish']:
log.info('Renamer disabled, marking movie as finished: %s', log_movie)
# Mark release done
rls.status_id = done_status.get('id')
db.commit()
# Mark release done
rls.status_id = done_status.get('id')
db.commit()
# Mark movie done
mvie = db.query(Movie).filter_by(id = movie['id']).first()
mvie.status_id = done_status.get('id')
db.commit()
except:
log.error('Failed marking movie finished, renamer disabled: %s', traceback.format_exc())
# Mark movie done
mvie = db.query(Movie).filter_by(id = movie['id']).first()
mvie.status_id = done_status.get('id')
db.commit()
except Exception, e:
log.error('Failed marking movie finished: %s %s', (e, traceback.format_exc()))
except:
log.error('Failed marking movie finished: %s', traceback.format_exc())
return True
@@ -409,12 +414,17 @@ class Searcher(Plugin):
return False
def correctYear(self, haystack, year, range):
def correctYear(self, haystack, year, year_range):
for string in haystack:
if str(year) in string or str(int(year) + range) in string or str(int(year) - range) in string: # 1 year of is fine too
year_name = fireEvent('scanner.name_year', string, single = True)
if year_name and ((year - year_range) <= year_name.get('year') <= (year + year_range)):
log.debug('Movie year matches range: %s looking for %s', (year_name.get('year'), year))
return True
log.debug('Movie year doesn\'t matche range: %s looking for %s', (year_name.get('year'), year))
return False
def correctName(self, check_name, movie_name):
+3 -2
View File
@@ -1,6 +1,7 @@
from couchpotato import get_session
from couchpotato.core.event import addEvent, fireEvent
from couchpotato.core.helpers.encoding import toUnicode
from couchpotato.core.helpers.variable import splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.plugins.base import Plugin
from couchpotato.core.settings.model import Library, FileType
@@ -13,7 +14,7 @@ log = CPLog(__name__)
class Subtitle(Plugin):
services = ['opensubtitles', 'thesubdb', 'subswiki']
services = ['opensubtitles', 'thesubdb', 'subswiki', 'podnapisi']
def __init__(self):
addEvent('renamer.before', self.searchSingle)
@@ -67,4 +68,4 @@ class Subtitle(Plugin):
return False
def getLanguages(self):
return [x.strip() for x in self.conf('languages').split(',')]
return splitString(self.conf('languages'))
+3 -1
View File
@@ -12,7 +12,7 @@ class Trailer(Plugin):
def __init__(self):
addEvent('renamer.after', self.searchSingle)
def searchSingle(self, group):
def searchSingle(self, message = None, group = {}):
if self.isDisabled() or len(group['files']['trailer']) > 0: return
@@ -28,6 +28,8 @@ class Trailer(Plugin):
else:
log.debug('Trailer already exists: %s', destination)
group['renamed_files'].append(destination)
# Download first and break
break
@@ -28,9 +28,18 @@ class Automation(Plugin):
return self.getIMDBids()
def search(self, name, year = None, imdb_only = False):
prop_name = 'automation.cached.%s.%s' % (name, year)
cached_imdb = Env.prop(prop_name, default = False)
if cached_imdb and imdb_only:
return cached_imdb
result = fireEvent('movie.search', q = '%s %s' % (name, year if year else ''), limit = 1, merge = True)
if len(result) > 0:
if imdb_only and result[0].get('imdb'):
Env.prop(prop_name, result[0].get('imdb'))
return result[0].get('imdb') if imdb_only else result[0]
else:
return None
@@ -2,7 +2,6 @@ from couchpotato.core.helpers.rss import RSS
from couchpotato.core.helpers.variable import md5, tryInt
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.automation.base import Automation
from couchpotato.environment import Env
import xml.etree.ElementTree as XMLTree
log = CPLog(__name__)
@@ -2,9 +2,6 @@ from couchpotato.core.helpers.rss import RSS
from couchpotato.core.helpers.variable import md5, getImdb
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.automation.base import Automation
from couchpotato.environment import Env
from dateutil.parser import parse
import time
import traceback
import xml.etree.ElementTree as XMLTree
@@ -34,10 +31,6 @@ class IMDB(Automation, RSS):
log.error('This isn\'t the correct url.: %s', rss_url)
continue
prop_name = 'automation.imdb.last_update.%s' % md5(rss_url)
last_update = float(Env.prop(prop_name, default = 0))
last_movie_added = 0
try:
cache_key = 'imdb.rss.%s' % md5(rss_url)
@@ -46,20 +39,10 @@ class IMDB(Automation, RSS):
rss_movies = self.getElements(data, 'channel/item')
for movie in rss_movies:
created = int(time.mktime(parse(self.getTextElement(movie, "pubDate")).timetuple()))
imdb = getImdb(self.getTextElement(movie, "link"))
if created > last_movie_added:
last_movie_added = created
if not imdb or created <= last_update:
continue
movies.append(imdb)
except:
log.error('Failed loading IMDB watchlist: %s %s', (rss_url, traceback.format_exc()))
Env.prop(prop_name, last_movie_added)
return movies
@@ -3,10 +3,7 @@ from couchpotato.core.helpers.rss import RSS
from couchpotato.core.helpers.variable import md5
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.automation.base import Automation
from couchpotato.environment import Env
from dateutil.parser import parse
from xml.etree.ElementTree import ParseError
import time
import traceback
import xml.etree.ElementTree as XMLTree
@@ -33,10 +30,6 @@ class MoviesIO(Automation, RSS):
if not enablers[index]:
continue
prop_name = 'automation.moviesio.last_update.%s' % md5(rss_url)
last_update = float(Env.prop(prop_name, default = 0))
last_movie_added = 0
try:
cache_key = 'imdb.rss.%s' % md5(rss_url)
@@ -45,12 +38,6 @@ class MoviesIO(Automation, RSS):
rss_movies = self.getElements(data, 'channel/item')
for movie in rss_movies:
created = int(time.mktime(parse(self.getTextElement(movie, "pubDate")).timetuple()))
if created > last_movie_added:
last_movie_added = created
if created <= last_update:
continue
nameyear = fireEvent('scanner.name_year', self.getTextElement(movie, "title"), single = True)
imdb = self.search(nameyear.get('name'), nameyear.get('year'), imdb_only = True)
@@ -64,6 +51,4 @@ class MoviesIO(Automation, RSS):
except:
log.error('Failed loading Movies.io watchlist: %s %s', (rss_url, traceback.format_exc()))
Env.prop(prop_name, last_movie_added)
return movies
+13 -6
View File
@@ -2,6 +2,7 @@ from couchpotato.core.event import addEvent, fireEvent
from couchpotato.core.helpers.variable import mergeDicts
from couchpotato.core.logger import CPLog
from couchpotato.core.plugins.base import Plugin
from couchpotato.environment import Env
import os
import shutil
import traceback
@@ -16,23 +17,23 @@ class MetaDataBase(Plugin):
def __init__(self):
addEvent('renamer.after', self.create)
def create(self, release):
def create(self, message = None, group = {}):
if self.isDisabled(): return
log.info('Creating %s metadata.', self.getName())
# Update library to get latest info
try:
updated_library = fireEvent('library.update', release['library']['identifier'], force = True, single = True)
release['library'] = mergeDicts(release['library'], updated_library)
updated_library = fireEvent('library.update', group['library']['identifier'], force = True, single = True)
group['library'] = mergeDicts(group['library'], updated_library)
except:
log.error('Failed to update movie, before creating metadata: %s', traceback.format_exc())
root_name = self.getRootName(release)
root_name = self.getRootName(group)
meta_name = os.path.basename(root_name)
root = os.path.dirname(root_name)
movie_info = release['library'].get('info')
movie_info = group['library'].get('info')
for file_type in ['nfo', 'thumbnail', 'fanart']:
try:
@@ -42,13 +43,19 @@ class MetaDataBase(Plugin):
if name and self.conf('meta_' + file_type):
# Get file content
content = getattr(self, 'get' + file_type.capitalize())(movie_info = movie_info, data = release)
content = getattr(self, 'get' + file_type.capitalize())(movie_info = movie_info, data = group)
if content:
log.debug('Creating %s file: %s', (file_type, name))
if os.path.isfile(content):
shutil.copy2(content, name)
else:
self.createFile(name, content)
group['renamed_files'].append(name)
try:
os.chmod(name, Env.getPermission('file'))
except:
log.debug('Failed setting permissions for %s: %s', (name, traceback.format_exc()))
except:
log.error('Unable to create %s file: %s', (file_type, traceback.format_exc()))
@@ -1,6 +1,6 @@
from couchpotato.core.event import addEvent, fireEvent
from couchpotato.core.helpers.encoding import tryUrlencode
from couchpotato.core.helpers.variable import tryInt, tryFloat
from couchpotato.core.helpers.variable import tryInt, tryFloat, splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.movie.base import MovieProvider
import json
@@ -27,8 +27,10 @@ class IMDBAPI(MovieProvider):
name_year = fireEvent('scanner.name_year', q, single = True)
if not q or not name_year or (name_year and not name_year.get('name')):
return []
if not name_year or (name_year and not name_year.get('name')):
name_year = {
'name': q
}
cache_key = 'imdbapi.cache.%s' % q
cached = self.getCache(cache_key, self.urls['search'] % tryUrlencode({'t': name_year.get('name'), 'y': name_year.get('year', '')}), timeout = 3)
@@ -97,10 +99,10 @@ class IMDBAPI(MovieProvider):
'released': movie.get('Released', ''),
'year': year if isinstance(year, (int)) else None,
'plot': movie.get('Plot', ''),
'genres': movie.get('Genre', '').split(','),
'directors': movie.get('Director', '').split(','),
'writers': movie.get('Writer', '').split(','),
'actors': movie.get('Actors', '').split(','),
'genres': splitString(movie.get('Genre', '')),
'directors': splitString(movie.get('Director', '')),
'writers': splitString(movie.get('Writer', '')),
'actors': splitString(movie.get('Actors', '')),
}
except:
log.error('Failed parsing IMDB API json: %s', traceback.format_exc())
@@ -10,7 +10,7 @@ config = [{
'tab': 'searcher',
'subtab': 'nzb_providers',
'name': 'Mysterbin',
'description': 'Free provider, less accurate. See <a href="http://www.mysterbin.com/">Mysterbin</a>',
'description': 'Free provider, less accurate. See <a href="https://www.mysterbin.com/">Mysterbin</a>',
'options': [
{
'name': 'enabled',
@@ -11,7 +11,7 @@ config = [{
'subtab': 'nzb_providers',
'name': 'newznab',
'order': 10,
'description': 'Enable multiple NewzNab providers such as <a href="http://nzb.su" target="_blank">NZB.su</a> and <a href="http://nzbs.org" target="_blank">nzbs.org</a>',
'description': 'Enable multiple NewzNab providers such as <a href="https://nzb.su" target="_blank">NZB.su</a> and <a href="https://nzbs.org" target="_blank">nzbs.org</a>',
'wizard': True,
'options': [
{
@@ -1,7 +1,7 @@
from couchpotato.core.event import fireEvent
from couchpotato.core.helpers.encoding import tryUrlencode
from couchpotato.core.helpers.rss import RSS
from couchpotato.core.helpers.variable import cleanHost
from couchpotato.core.helpers.variable import cleanHost, splitString
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.nzb.base import NZBProvider
from couchpotato.environment import Env
@@ -161,9 +161,9 @@ class Newznab(NZBProvider, RSS):
def getHosts(self):
uses = [x.strip() for x in str(self.conf('use')).split(',')]
hosts = [x.strip() for x in self.conf('host').split(',')]
api_keys = [x.strip() for x in self.conf('api_key').split(',')]
uses = splitString(str(self.conf('use')))
hosts = splitString(self.conf('host'))
api_keys = splitString(self.conf('api_key'))
list = []
for nr in range(len(hosts)):
@@ -10,7 +10,7 @@ config = [{
'tab': 'searcher',
'subtab': 'nzb_providers',
'name': 'nzbindex',
'description': 'Free provider, less accurate. See <a href="http://www.nzbindex.nl/">NZBIndex</a>',
'description': 'Free provider, less accurate. See <a href="https://www.nzbindex.com/">NZBIndex</a>',
'options': [
{
'name': 'enabled',
@@ -19,8 +19,8 @@ log = CPLog(__name__)
class NzbIndex(NZBProvider, RSS):
urls = {
'download': 'http://www.nzbindex.nl/download/',
'api': 'http://www.nzbindex.nl/rss/',
'download': 'https://www.nzbindex.com/download/',
'api': 'https://www.nzbindex.com/rss/',
}
http_time_between_calls = 1 # Seconds
@@ -1,6 +1,7 @@
from bs4 import BeautifulSoup
from couchpotato.core.event import fireEvent
from couchpotato.core.helpers.variable import tryInt
from couchpotato.core.helpers.encoding import simplifyString
from couchpotato.core.helpers.variable import tryInt, getTitle
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.torrent.base import TorrentProvider
import re
@@ -12,9 +13,9 @@ log = CPLog(__name__)
class KickAssTorrents(TorrentProvider):
urls = {
'test': 'http://kat.ph/',
'detail': 'http://kat.ph/%s',
'search': 'http://kat.ph/i%s/',
'test': 'https://kat.ph/',
'detail': 'https://kat.ph/%s',
'search': 'https://kat.ph/%s-i%s/',
}
cat_ids = [
@@ -35,8 +36,10 @@ class KickAssTorrents(TorrentProvider):
if self.isDisabled():
return results
title = simplifyString(getTitle(movie['library'])).replace(' ', '-')
cache_key = 'kickasstorrents.%s.%s' % (movie['library']['identifier'], quality.get('identifier'))
data = self.getCache(cache_key, self.urls['search'] % (movie['library']['identifier'].replace('tt', '')))
data = self.getCache(cache_key, self.urls['search'] % (title, movie['library']['identifier'].replace('tt', '')))
if data:
cat_ids = self.getCatId(quality['identifier'])
@@ -10,7 +10,7 @@ config = [{
'tab': 'searcher',
'subtab': 'torrent_providers',
'name': 'PassThePopcorn',
'description': 'See <a href="http://passthepopcorn.me">PassThePopcorn.me</a>',
'description': 'See <a href="https://passthepopcorn.me">PassThePopcorn.me</a>',
'options': [
{
'name': 'enabled',
@@ -10,7 +10,7 @@ config = [{
'tab': 'searcher',
'subtab': 'torrent_providers',
'name': 'PublicHD',
'description': 'Public Torrent site with only HD content. See <a href="http://publichd.eu/">PublicHD</a>',
'description': 'Public Torrent site with only HD content. See <a href="https://publichd.eu/">PublicHD</a>',
'options': [
{
'name': 'enabled',
@@ -14,9 +14,9 @@ log = CPLog(__name__)
class PublicHD(TorrentProvider):
urls = {
'test': 'http://publichd.eu',
'detail': 'http://publichd.eu/index.php?page=torrent-details&id=%s',
'search': 'http://publichd.eu/index.php',
'test': 'https://publichd.eu',
'detail': 'https://publichd.eu/index.php?page=torrent-details&id=%s',
'search': 'https://publichd.eu/index.php',
}
http_time_between_calls = 0
@@ -10,7 +10,7 @@ config = [{
'tab': 'searcher',
'subtab': 'torrent_providers',
'name': 'SceneHD',
'description': 'See <a href="http://scenehd.org">SceneHD</a>',
'description': 'See <a href="https://scenehd.org">SceneHD</a>',
'options': [
{
'name': 'enabled',
@@ -12,11 +12,11 @@ log = CPLog(__name__)
class SceneHD(TorrentProvider):
urls = {
'test': 'http://scenehd.org/',
'login' : 'http://scenehd.org/takelogin.php',
'detail': 'http://scenehd.org/details.php?id=%s',
'search': 'http://scenehd.org/browse.php?ajax',
'download': 'http://scenehd.org/download.php?id=%s',
'test': 'https://scenehd.org/',
'login' : 'https://scenehd.org/takelogin.php',
'detail': 'https://scenehd.org/details.php?id=%s',
'search': 'https://scenehd.org/browse.php?ajax',
'download': 'https://scenehd.org/download.php?id=%s',
}
http_time_between_calls = 1 #seconds
@@ -4,6 +4,7 @@ from couchpotato.core.helpers.variable import mergeDicts, getTitle
from couchpotato.core.logger import CPLog
from couchpotato.core.providers.trailer.base import TrailerProvider
from string import digits, ascii_letters
from urllib2 import HTTPError
import re
log = CPLog(__name__)
@@ -22,7 +23,12 @@ class HDTrailers(TrailerProvider):
movie_name = getTitle(group['library'])
url = self.urls['api'] % self.movieUrlName(movie_name)
data = self.getCache('hdtrailers.%s' % group['library']['identifier'], url)
try:
data = self.getCache('hdtrailers.%s' % group['library']['identifier'], url, show_error = False)
except HTTPError:
log.debug('No page found for: %s', movie_name)
data = None
result_data = {'480p':[], '720p':[], '1080p':[]}
if not data:
@@ -47,7 +53,14 @@ class HDTrailers(TrailerProvider):
movie_name = getTitle(group['library'])
url = "%s?%s" % (self.urls['backup'], tryUrlencode({'s':movie_name}))
data = self.getCache('hdtrailers.alt.%s' % group['library']['identifier'], url)
try:
data = self.getCache('hdtrailers.alt.%s' % group['library']['identifier'], url, show_error = False)
except HTTPError:
log.debug('No alternative page found for: %s', movie_name)
data = None
if not data:
return results
try:
tables = SoupStrainer('div')
@@ -1,5 +1,5 @@
/**
* StyleFix 1.0.3
* StyleFix 1.0.3 & PrefixFree 1.0.7
* @author Lea Verou
* MIT license
*/
@@ -122,9 +122,9 @@ var self = window.StyleFix = {
.splice(index === undefined? self.fixers.length : index, 0, fixer);
},
fix: function(css, raw) {
fix: function(css, raw, element) {
for(var i=0; i<self.fixers.length; i++) {
css = self.fixers[i](css, raw) || css;
css = self.fixers[i](css, raw, element) || css;
}
return css;
@@ -157,11 +157,9 @@ function $(expr, con) {
})();
/**
* PrefixFree 1.0.6
* @author Lea Verou
* MIT license
* PrefixFree
*/
(function(root, undefined){
(function(root){
if(!window.StyleFix || !window.getComputedStyle) {
return;
@@ -181,9 +179,17 @@ function fix(what, before, after, replacement, css) {
}
var self = window.PrefixFree = {
prefixCSS: function(css, raw) {
prefixCSS: function(css, raw, element) {
var prefix = self.prefix;
// Gradient angles hotfix
if(self.functions.indexOf('linear-gradient') > -1) {
// Gradients are supported with a prefix, convert angles to legacy
css = css.replace(/(\s|:|,)(repeating-)?linear-gradient\(\s*(-?\d*\.?\d*)deg/ig, function ($0, delim, repeating, deg) {
return delim + (repeating || '') + 'linear-gradient(' + (90-deg) + 'deg';
});
}
css = fix('functions', '(\\s|:|,)', '\\s*\\(', '$1' + prefix + '$2(', css);
css = fix('keywords', '(\\s|:)', '(\\s|;|\\}|$)', '$1' + prefix + '$2$3', css);
css = fix('properties', '(^|\\{|\\s|;)', '\\s*:', '$1' + prefix + '$2:', css);
@@ -205,6 +211,9 @@ var self = window.PrefixFree = {
// Fix double prefixing
css = css.replace(RegExp('-' + prefix, 'g'), '-');
// Prefix wildcard
css = css.replace(/-\*-(?=[a-z]+)/gi, self.prefix);
return css;
},
+76 -6
View File
@@ -29,9 +29,35 @@ Page.Manage = new Class({
'identifier': 'manage',
'status': 'done',
'actions': MovieActions,
'menu': [self.refresh_button, self.refresh_quick]
'menu': [self.refresh_button, self.refresh_quick],
'on_empty_element': new Element('div.empty_manage').adopt(
new Element('div', {
'text': 'Seems like you don\'t have anything in your library yet.'
}),
new Element('div', {
'text': 'Add your existing movie folders in '
}).adopt(
new Element('a', {
'text': 'Settings > Manage',
'href': App.createUrl('settings/manage')
})
),
new Element('div.after_manage', {
'text': 'When you\'ve done that, hit this button → '
}).adopt(
new Element('a.button.green', {
'text': 'Hit me, but not to hard',
'events':{
'click': self.refresh.bind(self, true)
}
})
)
)
});
$(self.list).inject(self.el);
// Check if search is in progress
self.startProgressInterval();
}
},
@@ -39,11 +65,55 @@ Page.Manage = new Class({
refresh: function(full){
var self = this;
Api.request('manage.update', {
'data': {
'full': +full
}
})
if(!self.update_in_progress){
Api.request('manage.update', {
'data': {
'full': +full
}
})
self.startProgressInterval();
}
},
startProgressInterval: function(){
var self = this;
self.progress_interval = setInterval(function(){
Api.request('manage.progress', {
'onComplete': function(json){
self.update_in_progress = true;
if(!json.progress){
clearInterval(self.progress_interval);
self.update_in_progress = false;
if(self.progress_container){
self.progress_container.destroy();
self.list.update();
}
}
else {
if(!self.progress_container)
self.progress_container = new Element('div.progress').inject(self.list.navigation, 'after')
self.progress_container.empty();
Object.each(json.progress, function(progress, folder){
new Element('div').adopt(
new Element('span.folder', {'text': folder}),
new Element('span.percentage', {'text': progress.total ? (((progress.total-progress.to_go)/progress.total)*100).round() + '%' : '0%'})
).inject(self.progress_container)
});
}
}
})
}, 1000);
}
+2 -11
View File
@@ -18,9 +18,6 @@ Page.Wanted = new Class({
}
});
// See if userscript can be installed
// Wanted movies
self.wanted = new MovieList({
'identifier': 'wanted',
@@ -28,13 +25,7 @@ Page.Wanted = new Class({
'actions': MovieActions,
'add_new': true,
'menu': [self.manual_search],
'on_empty_element': App.createUserscriptButtons().setStyles({
'background-image': "url('"+Api.createUrl('static/images/emptylist.png')+"')",
'height': 750,
'width': 800,
'padding-top': 260,
'margin-top': -50
})
'on_empty_element': App.createUserscriptButtons().addClass('empty_wanted')
});
$(self.wanted).inject(self.el);
@@ -145,7 +136,7 @@ window.addEvent('domready', function(){
'text': profile.label ? profile.label : profile.data.label
}).inject(self.profile_select);
if(self.movie.profile && self.movie.profile.data.id == profile_id)
if(self.movie.profile && self.movie.profile.data && self.movie.profile.data.id == profile_id)
self.profile_select.set('value', profile_id);
});
+5 -5
View File
@@ -271,7 +271,7 @@ body > .spinner, .mask{
box-shadow: inset 0 1px 0 rgba(255,255,255,.6), 0 0 3px rgba(0,0,0,.7);
background-color: #1b79b8;
text-shadow: none;
background-image: linear-gradient(0deg, rgba(255,255,255,.3) 0%, rgba(255,255,255,.1) 100%);
background-image: -*-linear-gradient(0deg, rgba(255,255,255,.3) 0%, rgba(255,255,255,.1) 100%);
}
.header .notification_menu .wrapper {
@@ -355,7 +355,7 @@ body > .spinner, .mask{
border-radius:30px;
box-shadow: 0 1px 1px rgba(0,0,0,0.35), inset 0 1px 0px rgba(255,255,255,0.20);
background: url('../images/sprite.png') no-repeat 94% -53px, linear-gradient(
background: url('../images/sprite.png') no-repeat 94% -53px, -*-linear-gradient(
270deg,
#5b9bd1 0%,
#406db8 100%
@@ -431,7 +431,7 @@ body > .spinner, .mask{
border: 1px solid #252930;
box-shadow: inset 0 1px 0px rgba(255,255,255,0.20), 0 0 3px rgba(0,0,0, 0.2);
background: rgb(55,62,74);
background-image: linear-gradient(
background-image: -*-linear-gradient(
90deg,
rgb(55,62,74) 0%,
rgb(73,83,98) 100%
@@ -520,7 +520,7 @@ body > .spinner, .mask{
text-align: center;
color: #000;
text-shadow: none;
background-image: linear-gradient(
background-image: -*-linear-gradient(
45deg,
rgb(200,200,200) 0%,
rgb(255,255,255) 100%
@@ -592,7 +592,7 @@ body > .spinner, .mask{
overflow: hidden;
transition: all .6s cubic-bezier(0.9,0,0.1,1);
box-shadow: 0 1px 1px rgba(0,0,0,0.35), inset 0 1px 0px rgba(255,255,255,0.20);
background-image: linear-gradient(
background-image: -*-linear-gradient(
270deg,
#5b9bd1 0%,
#406db8 100%
+4 -4
View File
@@ -16,7 +16,7 @@
padding: 40px 0;
margin: 0;
min-height: 470px;
background-image: linear-gradient(
background-image: -*-linear-gradient(
20deg,
rgba(0,0,0,0) 50%,
rgba(0,0,0,0.3) 100%
@@ -365,7 +365,7 @@
border-radius: 2px;
}
.page .tag_input > ul:hover > li.choice {
background: linear-gradient(
background: -*-linear-gradient(
270deg,
rgba(255,255,255,0.3) 0%,
rgba(255,255,255,0.1) 100%
@@ -373,7 +373,7 @@
}
.page .tag_input > ul > li.choice:hover,
.page .tag_input > ul > li.choice.selected {
background: linear-gradient(
background: -*-linear-gradient(
270deg,
#5b9bd1 0%,
#406db8 100%
@@ -412,7 +412,7 @@
margin: -9px 0 0 -16px;
border-radius: 30px 30px 0 0;
cursor: pointer;
background: url('../../images/icon.delete.png') no-repeat center 2px, linear-gradient(
background: url('../../images/icon.delete.png') no-repeat center 2px, -*-linear-gradient(
270deg,
#5b9bd1 0%,
#5b9bd1 100%
-1
View File
@@ -6,7 +6,6 @@
<link rel="stylesheet" href="{{ url_for('web.static', filename='style/uniform.css') }}" type="text/css">
<link rel="stylesheet" href="{{ url_for('web.static', filename='style/page/settings.css') }}" type="text/css">
<link rel="stylesheet" href="{{ url_for('web.static', filename='style/page/wanted.css') }}" type="text/css">
<script type="text/javascript" src="{{ url_for('web.static', filename='scripts/library/mootools.js') }}"></script>
<script type="text/javascript" src="{{ url_for('web.static', filename='scripts/library/mootools_more.js') }}"></script>
+66 -8
View File
@@ -18,12 +18,58 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
__version__ = '0.4.2'
__version__ = '0.5.2'
__all__ = ['Guess', 'Language',
'guess_file_info', 'guess_video_info',
'guess_movie_info', 'guess_episode_info']
# Do python3 detection before importing any other module, to be sure that
# it will then always be available
# with code from http://lucumr.pocoo.org/2011/1/22/forwards-compatible-python/
import sys
if sys.version_info[0] >= 3:
PY3 = True
unicode_text_type = str
native_text_type = str
base_text_type = str
def u(x):
return str(x)
def s(x):
return x
class UnicodeMixin(object):
__str__ = lambda x: x.__unicode__()
import binascii
def to_hex(x):
return binascii.hexlify(x).decode('utf-8')
else:
PY3 = False
__all__ = [ str(s) for s in __all__ ] # fix imports for python2
unicode_text_type = unicode
native_text_type = str
base_text_type = basestring
def u(x):
if isinstance(x, str):
return x.decode('utf-8')
return unicode(x)
def s(x):
if isinstance(x, unicode):
return x.encode('utf-8')
if isinstance(x, list):
return [ s(y) for y in x ]
if isinstance(x, tuple):
return tuple(s(y) for y in x)
if isinstance(x, dict):
return dict((s(key), s(value)) for key, value in x.items())
return x
class UnicodeMixin(object):
__str__ = lambda x: unicode(x).encode('utf-8')
def to_hex(x):
return x.encode('hex')
from guessit.guess import Guess, merge_all
from guessit.language import Language
from guessit.matcher import IterativeMatcher
@@ -32,6 +78,7 @@ import logging
log = logging.getLogger(__name__)
class NullHandler(logging.Handler):
def emit(self, record):
pass
@@ -45,7 +92,7 @@ def guess_file_info(filename, filetype, info=None):
"""info can contain the names of the various plugins, such as 'filename' to
detect filename info, or 'hash_md5' to get the md5 hash of the file.
>>> guess_file_info('test/dummy.srt', 'autodetect', info = ['hash_md5', 'hash_sha1'])
>>> guess_file_info('tests/dummy.srt', 'autodetect', info = ['hash_md5', 'hash_sha1'])
{'hash_md5': 'e781de9b94ba2753a8e2945b2c0a123d', 'hash_sha1': 'bfd18e2f4e5d59775c2bc14d80f56971891ed620'}
"""
result = []
@@ -54,7 +101,7 @@ def guess_file_info(filename, filetype, info=None):
if info is None:
info = ['filename']
if isinstance(info, basestring):
if isinstance(info, base_text_type):
info = [info]
for infotype in info:
@@ -67,7 +114,7 @@ def guess_file_info(filename, filetype, info=None):
try:
result.append(Guess({'hash_mpc': hash_file(filename)},
confidence=1.0))
except Exception, e:
except Exception as e:
log.warning('Could not compute MPC-style hash because: %s' % e)
elif infotype == 'hash_ed2k':
@@ -75,7 +122,7 @@ def guess_file_info(filename, filetype, info=None):
try:
result.append(Guess({'hash_ed2k': hash_file(filename)},
confidence=1.0))
except Exception, e:
except Exception as e:
log.warning('Could not compute ed2k hash because: %s' % e)
elif infotype.startswith('hash_'):
@@ -97,17 +144,28 @@ def guess_file_info(filename, filetype, info=None):
hasherobjs = dict(hashers).values()
with open(filename, 'rb') as f:
for chunk in iter(lambda: f.read(blocksize), ''):
chunk = f.read(blocksize)
while chunk:
for hasher in hasherobjs:
hasher.update(chunk)
chunk = f.read(blocksize)
for infotype, hasher in hashers:
result.append(Guess({infotype: hasher.hexdigest()},
confidence=1.0))
except Exception, e:
except Exception as e:
log.warning('Could not compute hash because: %s' % e)
return merge_all(result)
result = merge_all(result)
# last minute adjustments
# if country is in the guessed properties, make it part of the filename
if 'country' in result:
result['series'] += ' (%s)' % result['country'].alpha2.upper()
return result
def guess_video_info(filename, info=None):
+8 -11
View File
@@ -19,10 +19,12 @@
#
from __future__ import unicode_literals
from guessit import fileutils
from guessit.textutils import to_unicode
from guessit import UnicodeMixin, base_text_type, u
from guessit.fileutils import load_file_in_same_dir
import logging
__all__ = [ 'Country' ]
log = logging.getLogger(__name__)
@@ -32,8 +34,7 @@ log = logging.getLogger(__name__)
# "An English name, an alpha-2 code (when given),
# an alpha-3 code (when given), a numeric code, and an ISO 31666-2 code
# are all separated by pipe (|) characters."
_iso3166_contents = fileutils.load_file_in_same_dir(__file__,
'ISO-3166-1_utf8.txt').decode('utf-8')
_iso3166_contents = load_file_in_same_dir(__file__, 'ISO-3166-1_utf8.txt')
country_matrix = [ l.strip().split('|')
for l in _iso3166_contents.strip().split('\n') ]
@@ -59,7 +60,7 @@ country_alpha3_to_alpha2 = dict((c[2].lower(), c[1].lower()) for c in country_ma
class Country(object):
class Country(UnicodeMixin):
"""This class represents a country.
You can initialize it with pretty much anything, as it knows conversion
@@ -67,7 +68,7 @@ class Country(object):
"""
def __init__(self, country, strict=False):
country = to_unicode(country.strip().lower())
country = u(country.strip().lower())
self.alpha3 = country_to_alpha3.get(country)
if self.alpha3 is None and strict:
@@ -93,7 +94,7 @@ class Country(object):
if isinstance(other, Country):
return self.alpha3 == other.alpha3
if isinstance(other, basestring):
if isinstance(other, base_text_type):
try:
return self == Country(other)
except ValueError:
@@ -107,9 +108,5 @@ class Country(object):
def __unicode__(self):
return self.english_name
def __str__(self):
return unicode(self).encode('utf-8')
def __repr__(self):
return 'Country(%s)' % self.english_name
+4 -1
View File
@@ -18,9 +18,12 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
import datetime
import re
def valid_year(year):
return 1920 < year < datetime.date.today().year + 5
def search_year(string):
"""Looks for year patterns, and if found return the year and group span.
@@ -40,7 +43,7 @@ def search_year(string):
match = re.search(r'[^0-9]([0-9]{4})[^0-9]', string)
if match:
year = int(match.group(1))
if 1920 < year < datetime.date.today().year + 5:
if valid_year(year):
return (year, match.span(1))
return (None, None)
+6 -4
View File
@@ -18,6 +18,8 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import s, u
import os.path
import zipfile
@@ -31,10 +33,10 @@ def split_path(path):
- the drive letter on Windows systems (eg: r'C:\')
- the mount point '\\' on Windows systems (eg: r'\\host\share')
>>> split_path('/usr/bin/smewt')
>>> s(split_path('/usr/bin/smewt'))
['/', 'usr', 'bin', 'smewt']
>>> split_path('relative_path/to/my_folder/')
>>> s(split_path('relative_path/to/my_folder/'))
['relative_path', 'to', 'my_folder']
"""
@@ -65,7 +67,7 @@ def split_path(path):
def file_in_same_dir(ref_file, desired_file):
"""Return the path for a file in the same dir as a given reference file.
>>> file_in_same_dir('~/smewt/smewt.db', 'smewt.settings')
>>> s(file_in_same_dir('~/smewt/smewt.db', 'smewt.settings'))
'~/smewt/smewt.settings'
"""
@@ -82,4 +84,4 @@ def load_file_in_same_dir(ref_file, filename):
zfile = zipfile.ZipFile(zfilename)
return zfile.read('/'.join(path[i + 1:]))
return open(os.path.join(*path)).read()
return u(open(os.path.join(*path)).read())
+22 -20
View File
@@ -18,6 +18,10 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import UnicodeMixin, s, u, base_text_type
from guessit.language import Language
from guessit.country import Country
import json
import datetime
import logging
@@ -25,7 +29,7 @@ import logging
log = logging.getLogger(__name__)
class Guess(dict):
class Guess(UnicodeMixin, dict):
"""A Guess is a dictionary which has an associated confidence for each of
its values.
@@ -44,23 +48,21 @@ class Guess(dict):
for prop in self:
self._confidence[prop] = confidence
def to_utf8_dict(self):
from guessit.language import Language
def to_dict(self):
data = dict(self)
for prop, value in data.items():
if isinstance(value, datetime.date):
data[prop] = value.isoformat()
elif isinstance(value, Language):
data[prop] = str(value)
elif isinstance(value, unicode):
data[prop] = value.encode('utf-8')
elif isinstance(value, (Language, Country, base_text_type)):
data[prop] = u(value)
elif isinstance(value, list):
data[prop] = [str(x) for x in value]
data[prop] = [u(x) for x in value]
return data
def nice_string(self):
data = self.to_utf8_dict()
data = self.to_dict()
parts = json.dumps(data, indent=4).split('\n')
for i, p in enumerate(parts):
@@ -72,8 +74,8 @@ class Guess(dict):
return '\n'.join(parts)
def __str__(self):
return str(self.to_utf8_dict())
def __unicode__(self):
return u(self.to_dict())
def confidence(self, prop):
return self._confidence.get(prop, -1)
@@ -138,16 +140,16 @@ def choose_string(g1, g2):
differ very little, such as one string being the other one with the 'the' word
prepended to it.
>>> choose_string(('Hello', 0.75), ('World', 0.5))
>>> s(choose_string(('Hello', 0.75), ('World', 0.5)))
('Hello', 0.25)
>>> choose_string(('Hello', 0.5), ('hello', 0.5))
>>> s(choose_string(('Hello', 0.5), ('hello', 0.5)))
('Hello', 0.75)
>>> choose_string(('Hello', 0.4), ('Hello World', 0.4))
>>> s(choose_string(('Hello', 0.4), ('Hello World', 0.4)))
('Hello', 0.64)
>>> choose_string(('simpsons', 0.5), ('The Simpsons', 0.5))
>>> s(choose_string(('simpsons', 0.5), ('The Simpsons', 0.5)))
('The Simpsons', 0.75)
"""
@@ -285,12 +287,12 @@ def merge_all(guesses, append=None):
You can specify a list of properties that should be appended into a list
instead of being merged.
>>> merge_all([ Guess({ 'season': 2 }, confidence = 0.6),
... Guess({ 'episodeNumber': 13 }, confidence = 0.8) ])
>>> s(merge_all([ Guess({ 'season': 2 }, confidence = 0.6),
... Guess({ 'episodeNumber': 13 }, confidence = 0.8) ]))
{'season': 2, 'episodeNumber': 13}
>>> merge_all([ Guess({ 'episodeNumber': 27 }, confidence = 0.02),
... Guess({ 'season': 1 }, confidence = 0.2) ])
>>> s(merge_all([ Guess({ 'episodeNumber': 27 }, confidence = 0.02),
... Guess({ 'season': 1 }, confidence = 0.2) ]))
{'season': 1}
"""
@@ -320,7 +322,7 @@ def merge_all(guesses, append=None):
result.update_highest_confidence(g)
# delete very unlikely values
for p in result.keys():
for p in list(result.keys()):
if result.confidence(p) < 0.05:
del result[p]
+4 -2
View File
@@ -18,6 +18,8 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import s, to_hex
import hashlib
import os.path
@@ -25,7 +27,7 @@ import os.path
def hash_file(filename):
"""Returns the ed2k hash of a given file.
>>> hash_file('test/dummy.srt')
>>> s(hash_file('tests/dummy.srt'))
'ed2k://|file|dummy.srt|44|1CA0B9DED3473B926AA93A0A546138BB|/'
"""
return 'ed2k://|file|%s|%d|%s|/' % (os.path.basename(filename),
@@ -58,6 +60,6 @@ def hash_filehash(filename):
a = gen(f)
hashes = [md4_hash(data).digest() for data in a]
if len(hashes) == 1:
return hashes[0].encode("hex")
return to_hex(hashes[0])
else:
return md4_hash(reduce(lambda a, d: a + d, hashes, "")).hexd
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
import struct
import os
+17 -22
View File
@@ -19,9 +19,9 @@
#
from __future__ import unicode_literals
from guessit import fileutils
from guessit import UnicodeMixin, base_text_type, u, s
from guessit.fileutils import load_file_in_same_dir
from guessit.country import Country
from guessit.textutils import to_unicode
import re
import logging
@@ -39,8 +39,7 @@ log = logging.getLogger(__name__)
# "An alpha-3 (bibliographic) code, an alpha-3 (terminologic) code (when given),
# an alpha-2 code (when given), an English name, and a French name of a language
# are all separated by pipe (|) characters."
_iso639_contents = fileutils.load_file_in_same_dir(__file__,
'ISO-639-2_utf-8.txt').decode('utf-8')
_iso639_contents = load_file_in_same_dir(__file__, 'ISO-639-2_utf-8.txt')
# drop the BOM from the beginning of the file
_iso639_contents = _iso639_contents[1:]
@@ -116,7 +115,6 @@ lng_exceptions = { 'unknown': ('und', None),
'cn': ('chi', None),
'chs': ('chi', None),
'jp': ('jpn', None),
'scc': ('srp', None),
'scr': ('hrv', None)
}
@@ -137,7 +135,7 @@ def lang_set(languages, strict=False):
return set(Language(l, strict=strict) for l in languages)
class Language(object):
class Language(UnicodeMixin):
"""This class represents a human language.
You can initialize it with pretty much anything, as it knows conversion
@@ -154,30 +152,30 @@ class Language(object):
>>> Language('fr')
Language(French)
>>> Language('eng').french_name
u'anglais'
>>> s(Language('eng').french_name)
'anglais'
>>> Language('pt(br)').country.english_name
u'Brazil'
>>> s(Language('pt(br)').country.english_name)
'Brazil'
>>> Language('Español (Latinoamérica)').country.english_name
u'Latin America'
>>> s(Language('Español (Latinoamérica)').country.english_name)
'Latin America'
>>> Language('Spanish (Latin America)') == Language('Español (Latinoamérica)')
True
>>> Language('zz', strict=False).english_name
u'Undetermined'
>>> s(Language('zz', strict=False).english_name)
'Undetermined'
>>> Language('pt(br)').opensubtitles
u'pob'
>>> s(Language('pt(br)').opensubtitles)
'pob'
"""
_with_country_regexp = re.compile('(.*)\((.*)\)')
_with_country_regexp2 = re.compile('(.*)-(.*)')
def __init__(self, language, country=None, strict=False, scheme=None):
language = to_unicode(language.strip().lower())
language = u(language.strip().lower())
with_country = (Language._with_country_regexp.match(language) or
Language._with_country_regexp2.match(language))
if with_country:
@@ -249,7 +247,7 @@ class Language(object):
def opensubtitles(self):
if self.lang == 'por' and self.country and self.country.alpha2 == 'br':
return 'pob'
elif self.lang in ['gre', 'eus', 'ice', 'srp']:
elif self.lang in ['gre', 'srp']:
return self.alpha3term
return self.alpha3
@@ -266,7 +264,7 @@ class Language(object):
if isinstance(other, Language):
return self.lang == other.lang
if isinstance(other, basestring):
if isinstance(other, base_text_type):
try:
return self == Language(other)
except ValueError:
@@ -286,9 +284,6 @@ class Language(object):
else:
return self.english_name
def __str__(self):
return unicode(self).encode('utf-8')
def __repr__(self):
if self.country:
return 'Language(%s, country=%s)' % (self.english_name, self.country)
+24 -16
View File
@@ -18,8 +18,9 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import PY3, u
from guessit.matchtree import MatchTree
from guessit.textutils import to_utf8
from guessit.guess import (merge_similar_guesses, merge_all,
choose_int, choose_string)
import copy
@@ -69,12 +70,12 @@ class IterativeMatcher(object):
"""
valid_filetypes = ('autodetect', 'subtitle', 'video',
'movie', 'moviesubtitle',
'episode', 'episodesubtitle')
'movie', 'moviesubtitle',
'episode', 'episodesubtitle')
if filetype not in valid_filetypes:
raise ValueError("filetype needs to be one of %s" % valid_filetypes)
if not isinstance(filename, unicode):
log.debug('WARNING: given filename to matcher is not unicode...')
if not PY3 and not isinstance(filename, unicode):
log.warning('Given filename to matcher is not unicode...')
self.match_tree = MatchTree(filename)
mtree = self.match_tree
@@ -99,21 +100,26 @@ class IterativeMatcher(object):
apply_transfo('split_explicit_groups')
# 4- try to match information for specific patterns
# NOTE: order needs to comply to the following:
# - website before language (eg: tvu.org.ru vs russian)
# - language before episodes_rexps
# - properties before language (eg: he-aac vs hebrew)
# - release_group before properties (eg: XviD-?? vs xvid)
if mtree.guess['type'] in ('episode', 'episodesubtitle'):
strategy = ['guess_date', 'guess_video_rexps',
'guess_episodes_rexps', 'guess_website',
'guess_release_group', 'guess_properties',
'guess_weak_episodes_rexps', 'guess_language']
strategy = [ 'guess_date', 'guess_website', 'guess_release_group',
'guess_properties', 'guess_language',
'guess_video_rexps',
'guess_episodes_rexps', 'guess_weak_episodes_rexps' ]
else:
strategy = ['guess_date', 'guess_video_rexps',
'guess_website', 'guess_release_group',
'guess_properties', 'guess_language']
strategy = [ 'guess_date', 'guess_website', 'guess_release_group',
'guess_properties', 'guess_language',
'guess_video_rexps' ]
for name in strategy:
apply_transfo(name)
# more guessers for both movies and episodes
for name in ['guess_bonus_features']:
for name in ['guess_bonus_features', 'guess_year', 'guess_country']:
apply_transfo(name)
# split into '-' separated subgroups (with required separator chars
@@ -125,13 +131,12 @@ class IterativeMatcher(object):
if mtree.guess['type'] in ('episode', 'episodesubtitle'):
apply_transfo('guess_episode_info_from_position')
else:
apply_transfo('guess_year')
apply_transfo('guess_movie_title_from_position')
# 6- perform some post-processing steps
apply_transfo('post_process')
log.debug('Found match tree:\n%s' % (to_utf8(unicode(mtree))))
log.debug('Found match tree:\n%s' % u(mtree))
def matched(self):
# we need to make a copy here, as the merge functions work in place and
@@ -147,9 +152,12 @@ class IterativeMatcher(object):
for string_part in ('title', 'series', 'container', 'format',
'releaseGroup', 'website', 'audioCodec',
'videoCodec', 'screenSize', 'episodeFormat'):
'videoCodec', 'screenSize', 'episodeFormat',
'audioChannels'):
merge_similar_guesses(parts, string_part, choose_string)
# 2- merge the rest, potentially discarding information not properly
# merged before
result = merge_all(parts,
append=['language', 'subtitleLanguage', 'other'])
+6 -7
View File
@@ -18,15 +18,16 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from guessit import Guess
from guessit.textutils import clean_string, str_fill, to_utf8
from __future__ import unicode_literals
from guessit import UnicodeMixin, base_text_type, Guess
from guessit.textutils import clean_string, str_fill
from guessit.patterns import group_delimiters
import logging
log = logging.getLogger(__name__)
class BaseMatchTree(object):
class BaseMatchTree(UnicodeMixin):
"""A MatchTree represents the hierarchical split of a string into its
constituent semantic groups."""
@@ -154,6 +155,7 @@ class BaseMatchTree(object):
'extension': 'e',
'format': 'f',
'language': 'l',
'country': 'C',
'videoCodec': 'v',
'audioCodec': 'a',
'website': 'w',
@@ -198,9 +200,6 @@ class BaseMatchTree(object):
def __unicode__(self):
return self.to_string()
def __str__(self):
return to_utf8(unicode(self))
class MatchTree(BaseMatchTree):
"""The MatchTree contains a few "utility" methods which are not necessary
@@ -218,7 +217,7 @@ class MatchTree(BaseMatchTree):
return list(self._unidentified_leaves(valid))
def _leaves_containing(self, property_name):
if isinstance(property_name, basestring):
if isinstance(property_name, base_text_type):
property_name = [ property_name ]
for leaf in self._leaves():
+18 -11
View File
@@ -19,6 +19,8 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
subtitle_exts = [ 'srt', 'idx', 'sub', 'ssa', 'txt' ]
@@ -40,7 +42,10 @@ episode_rexps = [ # ... Season 2 ...
(r'saison (?P<season>[0-9]+)', 1.0, (0, 0)),
# ... s02e13 ...
(r'[Ss](?P<season>[0-9]{1,2}).{,3}(?P<episodeNumber>(?:[EeXx][0-9]{1,2})+)[^0-9]', 1.0, (0, -1)),
(r'[Ss](?P<season>[0-9]{1,2}).{,3}(?P<episodeNumber>(?:[Ee][0-9]{1,2})+)[^0-9]', 1.0, (0, -1)),
# ... s03-x02 ...
(r'[Ss](?P<season>[0-9]{1,2}).{,3}(?P<bonusNumber>(?:[Xx][0-9]{1,2})+)[^0-9]', 1.0, (0, -1)),
# ... 2x13 ...
(r'[^0-9](?P<season>[0-9]{1,2})(?P<episodeNumber>(?:[xX][0-9]{1,2})+)[^0-9]', 0.8, (1, -1)),
@@ -53,18 +58,16 @@ episode_rexps = [ # ... Season 2 ...
(r'(?P<episodeNumber>[0-9]{1,3})v[23]' + sep, 0.6, (0, 0)),
# ... ep 23 ...
('ep' + sep + r'(?P<episodeNumber>[0-9]{1,2})[^0-9]', 0.7, (0, -1))
('ep' + sep + r'(?P<episodeNumber>[0-9]{1,2})[^0-9]', 0.7, (0, -1)),
# ... e13 ... for a mini-series without a season number
(r'e(?P<episodeNumber>[0-9]{1,2})[^0-9]', 0.6, (0, -1))
]
weak_episode_rexps = [ # ... 213 or 0106 ...
(sep + r'(?P<episodeNumber>[0-9]{1,4})' + sep, (1, -1)),
# ... 2x13 ...
(sep + r'[^0-9](?P<season>[0-9]{1,2})\.(?P<episodeNumber>[0-9]{1,2})[^0-9]' + sep, (1, -1)),
# ... e13 ... for a mini-series without a season number
(r'e(?P<episodeNumber>[0-9]{1,4})[^0-9]', (0, -1)),
(sep + r'(?P<episodeNumber>[0-9]{2,4})' + sep, (1, -1))
]
non_episode_title = [ 'extras', 'rip' ]
@@ -102,7 +105,7 @@ unlikely_series = ['series']
properties = { 'format': [ 'DVDRip', 'HD-DVD', 'HDDVD', 'HDDVDRip', 'BluRay', 'Blu-ray', 'BDRip', 'BRRip',
'HDRip', 'DVD', 'DVDivX', 'HDTV', 'DVB', 'DVBRip', 'PDTV', 'WEBRip',
'DVDSCR', 'Screener', 'VHS', 'VIDEO_TS' ],
'DVDSCR', 'Screener', 'VHS', 'VIDEO_TS', 'WEB-DL', 'WEBDL' ],
'screenSize': [ '720p', '720', '1080p', '1080' ],
@@ -116,7 +119,10 @@ properties = { 'format': [ 'DVDRip', 'HD-DVD', 'HDDVD', 'HDDVDRip', 'BluRay', 'B
'CHD', 'ViTE', 'TLF', 'DEiTY', 'FLAiTE',
'MDX', 'GM4F', 'DVL', 'SVD', 'iLUMiNADOS', ' FiNaLe',
'UnSeeN', 'aXXo', 'KLAXXON', 'NoTV', 'ZeaL', 'LOL',
'HDBRiSe' ],
'SiNNERS', 'DiRTY', 'REWARD', 'ECI', 'KiNGS', 'CLUE',
'CtrlHD', 'POD', 'WiKi', 'DIMENSION', 'IMMERSE', 'FQM',
'2HD', 'REPTiLE', 'CTU', 'HALCYON', 'EbP', 'SiTV', 'SAiNTS',
'HDBRiSe', 'AlFleNi-TeaM', 'EVOLVE', '0TV' ],
'episodeFormat': [ 'Minisode', 'Minisodes' ],
@@ -149,6 +155,7 @@ def find_properties(filename):
property_synonyms = { 'DVD': [ 'DVDRip', 'VIDEO_TS' ],
'HD-DVD': [ 'HDDVD', 'HDDVDRip' ],
'BluRay': [ 'BDRip', 'BRRip', 'Blu-ray' ],
'WEB-DL': [ 'WEBDL' ],
'DVB': [ 'DVBRip', 'PDTV' ],
'Screener': [ 'DVDSCR' ],
'DivX': [ 'DVDivX' ],
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
import logging
import sys
+13 -50
View File
@@ -18,7 +18,10 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import s
from guessit.patterns import sep
import functools
import unicodedata
import copy
@@ -61,45 +64,6 @@ def str_fill(string, region, c):
return string[:start] + c * (end - start) + string[end:]
def to_utf8(o):
"""Convert all unicode strings found in the given object to utf-8
strings."""
if isinstance(o, unicode):
return o.encode('utf-8')
elif isinstance(o, list):
return [ to_utf8(i) for i in o ]
elif isinstance(o, dict):
# need to do it like that to handle Guess instances correctly
# FIXME: why is that necessary?
result = copy.deepcopy(o)
for key, value in o.items():
result[to_utf8(key)] = to_utf8(value)
return result
else:
return o
def to_unicode(o):
"""Convert all strings found in the given object to normalized
unicode strings, using the UTF-8 codec if needed."""
if isinstance(o, unicode):
return unicodedata.normalize('NFC', o)
if isinstance(o, str):
return unicodedata.normalize('NFC', o.decode('utf-8'))
elif isinstance(o, list):
return [ to_unicode(i) for i in o ]
elif isinstance(o, dict):
# need to do it like that to handle Guess instances correctly
#result = copy.deepcopy(o)
for key, value in o.items():
result[to_unicode(key)] = to_unicode(value)
return result
else:
return o
def levenshtein(a, b):
if not a:
@@ -176,21 +140,20 @@ def find_first_level_groups_span(string, enclosing):
def split_on_groups(string, groups):
"""Split the given string using the different known groups for boundaries.
>>> split_on_groups('0123456789', [ (2, 4) ])
>>> s(split_on_groups('0123456789', [ (2, 4) ]))
['01', '23', '456789']
>>> split_on_groups('0123456789', [ (2, 4), (4, 6) ])
>>> s(split_on_groups('0123456789', [ (2, 4), (4, 6) ]))
['01', '23', '45', '6789']
>>> split_on_groups('0123456789', [ (5, 7), (2, 4) ])
>>> s(split_on_groups('0123456789', [ (5, 7), (2, 4) ]))
['01', '23', '4', '56', '789']
"""
if not groups:
return [ string ]
boundaries = sorted(set(reduce(lambda l, x: l + list(x), groups, [])))
boundaries = sorted(set(functools.reduce(lambda l, x: l + list(x), groups, [])))
if boundaries[0] != 0:
boundaries.insert(0, 0)
if boundaries[-1] != len(string):
@@ -212,22 +175,22 @@ def find_first_level_groups(string, enclosing, blank_sep=None):
This does not return nested groups, ie: '(ab(c)(d))' will return a single group
containing the whole string.
>>> find_first_level_groups('', '()')
>>> s(find_first_level_groups('', '()'))
['']
>>> find_first_level_groups('abcd', '()')
>>> s(find_first_level_groups('abcd', '()'))
['abcd']
>>> find_first_level_groups('abc(de)fgh', '()')
>>> s(find_first_level_groups('abc(de)fgh', '()'))
['abc', '(de)', 'fgh']
>>> find_first_level_groups('(ab(c)(d))', '()', blank_sep = '_')
>>> s(find_first_level_groups('(ab(c)(d))', '()', blank_sep = '_'))
['_ab(c)(d)_']
>>> find_first_level_groups('ab[c]de[f]gh(i)', '[]')
>>> s(find_first_level_groups('ab[c]de[f]gh(i)', '[]'))
['ab', '[c]', 'de', '[f]', 'gh(i)']
>>> find_first_level_groups('()[]()', '()', blank_sep = '-')
>>> s(find_first_level_groups('()[]()', '()', blank_sep = '-'))
['--', '[]', '--']
"""
+4 -3
View File
@@ -18,7 +18,8 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from guessit import Guess
from __future__ import unicode_literals
from guessit import base_text_type, Guess
from guessit.patterns import canonical_form
from guessit.textutils import clean_string
import logging
@@ -41,7 +42,7 @@ def format_guess(guess):
if prop in ('season', 'episodeNumber', 'year', 'cdNumber',
'cdNumberTotal', 'bonusNumber', 'filmNumber'):
guess[prop] = int(guess[prop])
elif isinstance(value, basestring):
elif isinstance(value, base_text_type):
if prop in ('edition',):
value = clean_string(value)
guess[prop] = canonical_form(value)
@@ -63,7 +64,7 @@ def find_and_split_node(node, strategy, logger):
if isinstance(result, Guess):
if confidence is None:
confidence = result.confidence(result.keys()[0])
confidence = result.confidence(list(result.keys())[0])
else:
if confidence is None:
confidence = 1.0
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import found_property
import logging
+42
View File
@@ -0,0 +1,42 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# GuessIt - A library for guessing information from filenames
# Copyright (c) 2012 Nicolas Wack <wackou@gmail.com>
#
# GuessIt is free software; you can redistribute it and/or modify it under
# the terms of the Lesser GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# GuessIt is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# Lesser GNU General Public License for more details.
#
# You should have received a copy of the Lesser GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
#from guessit.transfo import SingleNodeGuesser
#from guessit.date import search_year
from guessit.country import Country
from guessit import Guess
import logging
log = logging.getLogger(__name__)
def process(mtree):
for node in mtree.unidentified_leaves():
# only keep explicit groups (enclosed in parentheses/brackets)
if len(node.node_idx) == 2:
try:
country = Country(node.value[1:-1], strict=True)
if node.value[0] + node.value[-1] not in ['()', '[]', '{}']:
continue
node.guess = Guess(country=country, confidence=1.0)
except ValueError:
pass
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import SingleNodeGuesser
from guessit.date import search_date
import logging
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import found_property
from guessit.patterns import non_episode_title, unlikely_series
import logging
+17 -11
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import episode_rexps
@@ -27,30 +28,35 @@ import logging
log = logging.getLogger(__name__)
def number_list(s):
return re.sub('[^0-9]+', ' ', s).split()
return list(re.sub('[^0-9]+', ' ', s).split())
def guess_episodes_rexps(string):
for rexp, confidence, span_adjust in episode_rexps:
match = re.search(rexp, string, re.IGNORECASE)
if match:
result = (Guess(match.groupdict(), confidence=confidence),
(match.start() + span_adjust[0],
match.end() + span_adjust[1]))
guess = Guess(match.groupdict(), confidence=confidence)
span = (match.start() + span_adjust[0],
match.end() + span_adjust[1])
# episodes which have a season > 25 are most likely errors
# (Simpsons is at 23!)
if int(result[0].get('season', 0)) > 25:
# (Simpsons is at 24!)
if int(guess.get('season', 0)) > 25:
continue
# decide whether we have only a single episode number or an
# episode list
if result[0].get('episodeNumber'):
eplist = number_list(result[0]['episodeNumber'])
result[0].set('episodeNumber', int(eplist[0]), confidence=confidence)
if guess.get('episodeNumber'):
eplist = number_list(guess['episodeNumber'])
guess.set('episodeNumber', int(eplist[0]), confidence=confidence)
if len(eplist) > 1:
result[0].set('episodeList', map(int, eplist), confidence=confidence)
guess.set('episodeList', list(map(int, eplist)), confidence=confidence)
return result
if guess.get('bonusNumber'):
eplist = number_list(guess['bonusNumber'])
guess.set('bonusNumber', int(eplist[0]), confidence=confidence)
return guess, span
return None, None
+83 -23
View File
@@ -18,9 +18,12 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
from guessit.patterns import (subtitle_exts, video_exts, episode_rexps,
find_properties, canonical_form)
from guessit.date import valid_year
from guessit.textutils import clean_string
import os.path
import re
import mimetypes
@@ -28,34 +31,22 @@ import logging
log = logging.getLogger(__name__)
# List of well known movies and series, hardcoded because they cannot be
# guessed appropriately otherwise
MOVIES = [ 'OSS 117' ]
SERIES = [ 'Band of Brothers' ]
def guess_filetype(filename, filetype):
other = {}
# look at the extension first
fileext = os.path.splitext(filename)[1][1:].lower()
if fileext in subtitle_exts:
if 'movie' in filetype:
filetype = 'moviesubtitle'
elif 'episode' in filetype:
filetype = 'episodesubtitle'
else:
filetype = 'subtitle'
other = { 'container': fileext }
elif fileext in video_exts:
if filetype == 'autodetect':
filetype = 'video'
other = { 'container': fileext }
else:
if filetype == 'autodetect':
filetype = 'unknown'
other = { 'extension': fileext }
MOVIES = [ m.lower() for m in MOVIES ]
SERIES = [ s.lower() for s in SERIES ]
def guess_filetype(mtree, filetype):
# put the filetype inside a dummy container to be able to have the
# following functions work correctly as closures
# this is a workaround for python 2 which doesn't have the
# 'nonlocal' keyword (python 3 does have it)
filetype_container = [filetype]
other = {}
filename = mtree.string
def upgrade_episode():
if filetype_container[0] == 'video':
@@ -69,14 +60,82 @@ def guess_filetype(filename, filetype):
elif filetype_container[0] == 'subtitle':
filetype_container[0] = 'moviesubtitle'
def upgrade_subtitle():
if 'movie' in filetype_container[0]:
filetype_container[0] = 'moviesubtitle'
elif 'episode' in filetype_container[0]:
filetype_container[0] = 'episodesubtitle'
else:
filetype_container[0] = 'subtitle'
def upgrade(type='unknown'):
if filetype_container[0] == 'autodetect':
filetype_container[0] = type
# look at the extension first
fileext = os.path.splitext(filename)[1][1:].lower()
if fileext in subtitle_exts:
upgrade_subtitle()
other = { 'container': fileext }
elif fileext in video_exts:
upgrade(type='video')
other = { 'container': fileext }
else:
upgrade(type='unknown')
other = { 'extension': fileext }
# check whether we are in a 'Movies', 'Tv Shows', ... folder
folder_rexps = [ (r'Movies?', upgrade_movie),
(r'Tv ?Shows?', upgrade_episode),
(r'Series', upgrade_episode)
]
for frexp, upgrade_func in folder_rexps:
frexp = re.compile(frexp, re.IGNORECASE)
for pathgroup in mtree.children:
if frexp.match(pathgroup.value):
upgrade_func()
# check for a few specific cases which will unintentionally make the
# following heuristics confused (eg: OSS 117 will look like an episode,
# season 1, epnum 17, when it is in fact a movie)
fname = clean_string(filename).lower()
for m in MOVIES:
if m in fname:
upgrade_movie()
for s in SERIES:
if s in fname:
upgrade_episode()
# now look whether there are some specific hints for episode vs movie
if filetype in ('video', 'subtitle'):
if filetype_container[0] in ('video', 'subtitle'):
# if we have an episode_rexp (eg: s02e13), it is an episode
for rexp, _, _ in episode_rexps:
match = re.search(rexp, filename, re.IGNORECASE)
if match:
upgrade_episode()
break
# if we have a 3-4 digit number that's not a year, maybe an episode
match = re.search(r'[^0-9]([0-9]{3,4})[^0-9]', filename)
if match:
fullnumber = int(match.group()[1:-1])
#season = fullnumber // 100
epnumber = fullnumber % 100
possible = True
# check for validity
if epnumber > 40:
possible = False
if valid_year(fullnumber):
possible = False
if possible:
upgrade_episode()
# if we have certain properties characteristic of episodes, it is an ep
for prop, value, _, _ in find_properties(filename):
log.debug('prop: %s = %s' % (prop, value))
if prop == 'episodeFormat':
@@ -87,6 +146,7 @@ def guess_filetype(filename, filetype):
upgrade_episode()
break
# origin-specific type
if 'tvu.org.ru' in filename:
upgrade_episode()
@@ -98,7 +158,7 @@ def guess_filetype(filename, filetype):
def process(mtree, filetype='autodetect'):
filetype, other = guess_filetype(mtree.string, filetype)
filetype, other = guess_filetype(mtree, filetype)
mtree.guess.set('type', filetype, confidence=1.0)
log.debug('Found with confidence %.2f: %s' % (1.0, mtree.guess))
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
from guessit.transfo import SingleNodeGuesser
from guessit.language import search_language
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
import logging
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import find_properties
import logging
+31 -2
View File
@@ -18,24 +18,53 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import properties, canonical_form
import re
import logging
log = logging.getLogger(__name__)
CODECS = properties['videoCodec']
FORMATS = properties['format']
def adjust_metadata(md):
codec = canonical_form(md['videoCodec'])
if codec in FORMATS:
md['format'] = codec
del md['videoCodec']
return md
def guess_release_group(string):
group_names = [ r'\.(Xvid)-(?P<releaseGroup>.*?)[ \.]',
r'\.(DivX)-(?P<releaseGroup>.*?)[\. ]',
r'\.(DVDivX)-(?P<releaseGroup>.*?)[\. ]',
]
# first try to see whether we have both a known codec and a known release group
group_names = [ r'\.(?P<videoCodec>' + codec + r')-(?P<releaseGroup>.*?)[ \.]'
for codec in (CODECS + FORMATS) ]
for rexp in group_names:
match = re.search(rexp, string, re.IGNORECASE)
if match:
metadata = match.groupdict()
metadata.update({ 'videoCodec': match.group(1) })
return metadata, (match.start() + 1, match.end() - 1)
if canonical_form(metadata['releaseGroup']) in properties['releaseGroup']:
return adjust_metadata(metadata), (match.start(1), match.end(2))
# pick anything as releaseGroup as long as we have a codec in front
# this doesn't include a potential dash ('-') ending the release group
# eg: [...].X264-HiS@SiLUHD-English.[...]
group_names = [ r'\.(?P<videoCodec>' + codec + r')-(?P<releaseGroup>.*?)(-(.*?))?[ \.]'
for codec in (CODECS + FORMATS) ]
for rexp in group_names:
match = re.search(rexp, string, re.IGNORECASE)
if match:
return adjust_metadata(match.groupdict()), (match.start(1), match.end(2))
return None, None
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import video_rexps, sep
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import Guess
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import weak_episode_rexps
@@ -40,8 +41,13 @@ def guess_weak_episodes_rexps(string, node):
epnum = int(metadata['episodeNumber'])
if epnum > 100:
return Guess({ 'season': epnum // 100,
'episodeNumber': epnum % 100 },
season, epnum = epnum // 100, epnum % 100
# episodes which have a season > 25 are most likely errors
# (Simpsons is at 23!)
if season > 25:
continue
return Guess({ 'season': season,
'episodeNumber': epnum },
confidence=0.6), span
else:
return Guess(metadata, confidence=0.3), span
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import SingleNodeGuesser
from guessit.patterns import websites
import logging
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.transfo import SingleNodeGuesser
from guessit.date import search_year
import logging
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.patterns import subtitle_exts
import logging
@@ -18,8 +18,10 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.textutils import find_first_level_groups
from guessit.patterns import group_delimiters
import functools
import logging
log = logging.getLogger(__name__)
@@ -33,10 +35,10 @@ def process(mtree):
groups = find_first_level_groups(c.value, group_delimiters[0])
for delimiters in group_delimiters:
flatten = lambda l, x: l + find_first_level_groups(x, delimiters)
groups = reduce(flatten, groups, [])
groups = functools.reduce(flatten, groups, [])
# do not do this at this moment, it is not strong enough and can break other
# patterns, such as dates, etc...
#groups = reduce(lambda l, x: l + x.split('-'), groups, [])
#groups = functools.reduce(lambda l, x: l + x.split('-'), groups, [])
c.split_on_components(groups)
+1
View File
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit.patterns import sep
import re
import logging
@@ -18,6 +18,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
from __future__ import unicode_literals
from guessit import fileutils
import os.path
import logging
+31 -4
View File
@@ -6,8 +6,35 @@
# /
"""
requests
~~~~~~~~
requests HTTP library
~~~~~~~~~~~~~~~~~~~~~
Requests is an HTTP library, written in Python, for human beings. Basic GET
usage:
>>> import requests
>>> r = requests.get('http://python.org')
>>> r.status_code
200
>>> 'Python is a programming language' in r.content
True
... or POST:
>>> payload = dict(key1='value1', key2='value2')
>>> r = requests.post("http://httpbin.org/post", data=payload)
>>> print r.text
{
...
"form": {
"key2": "value2",
"key1": "value1"
},
...
}
The other HTTP methods are supported - see `requests.api`. Full documentation
is at <http://python-requests.org>.
:copyright: (c) 2012 by Kenneth Reitz.
:license: ISC, see LICENSE for more details.
@@ -15,8 +42,8 @@ requests
"""
__title__ = 'requests'
__version__ = '0.13.1'
__build__ = 0x001301
__version__ = '0.14.1'
__build__ = 0x001401
__author__ = 'Kenneth Reitz'
__license__ = 'ISC'
__copyright__ = 'Copyright 2012 Kenneth Reitz'
+24
View File
@@ -0,0 +1,24 @@
# -*- coding: utf-8 -*-
"""
requests._oauth
~~~~~~~~~~~~~~~
This module contains the path hack necessary for oauthlib to be vendored into
requests while allowing upstream changes.
"""
import os
import sys
try:
from oauthlib.oauth1 import rfc5849
from oauthlib.common import extract_params
from oauthlib.oauth1.rfc5849 import (Client, SIGNATURE_HMAC, SIGNATURE_TYPE_AUTH_HEADER)
except ImportError:
directory = os.path.dirname(__file__)
path = os.path.join(directory, 'packages')
sys.path.insert(0, path)
from oauthlib.oauth1 import rfc5849
from oauthlib.common import extract_params
from oauthlib.oauth1.rfc5849 import (Client, SIGNATURE_HMAC, SIGNATURE_TYPE_AUTH_HEADER)
+13 -2
View File
@@ -14,6 +14,7 @@ This module implements the Requests API.
from . import sessions
from .safe_mode import catch_exceptions_if_in_safe_mode
@catch_exceptions_if_in_safe_mode
def request(method, url, **kwargs):
"""Constructs and sends a :class:`Request <Request>`.
@@ -38,9 +39,19 @@ def request(method, url, **kwargs):
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
"""
s = kwargs.pop('session') if 'session' in kwargs else sessions.session()
return s.request(method=method, url=url, **kwargs)
# if this session was passed in, leave it open (and retain pooled connections);
# if we're making it just for this call, then close it when we're done.
adhoc_session = False
session = kwargs.pop('session', None)
if session is None:
session = sessions.session()
adhoc_session = True
try:
return session.request(method=method, url=url, **kwargs)
finally:
if adhoc_session:
session.close()
def get(url, **kwargs):
+255 -102
View File
@@ -8,8 +8,10 @@ This module contains the authentication handlers for Requests.
"""
import os
import re
import time
import hashlib
import logging
from base64 import b64encode
@@ -17,15 +19,22 @@ from .compat import urlparse, str
from .utils import parse_dict_header
try:
from oauthlib.oauth1.rfc5849 import (Client, SIGNATURE_HMAC, SIGNATURE_TYPE_AUTH_HEADER)
from oauthlib.common import extract_params
# hush pyflakes:
SIGNATURE_HMAC; SIGNATURE_TYPE_AUTH_HEADER
from ._oauth import (Client, SIGNATURE_HMAC, SIGNATURE_TYPE_AUTH_HEADER, extract_params)
except (ImportError, SyntaxError):
SIGNATURE_HMAC = None
SIGNATURE_TYPE_AUTH_HEADER = None
try:
import kerberos as k
except ImportError as exc:
k = None
log = logging.getLogger(__name__)
CONTENT_TYPE_FORM_URLENCODED = 'application/x-www-form-urlencoded'
CONTENT_TYPE_MULTI_PART = 'multipart/form-data'
def _basic_auth_str(username, password):
"""Returns a Basic Auth string."""
@@ -66,29 +75,37 @@ class OAuth1(AuthBase):
Parameters may be included from the body if the content-type is
urlencoded, if no content type is set an educated guess is made.
"""
contenttype = r.headers.get('Content-Type', None)
# split(";") because Content-Type may be "multipart/form-data; boundary=xxxxx"
contenttype = r.headers.get('Content-Type', '').split(";")[0].lower()
# extract_params will not give params unless the body is a properly
# formatted string, a dictionary or a list of 2-tuples.
decoded_body = extract_params(r.data)
if contenttype == None and decoded_body != None:
# extract_params can only check the present r.data and does not know
# of r.files, thus an extra check is performed. We know that
# if files are present the request will not have
# Content-type: x-www-form-urlencoded. We guess it will have
# a mimetype of multipart/form-encoded and if this is not the case
# we assume the correct header will be set later.
if r.files:
# Omit body data in the signing and since it will always
# be empty (cant add paras to body if multipart) and we wish
# to preserve body.
r.headers['Content-Type'] = 'multipart/form-encoded'
r.url, r.headers, _ = self.client.sign(
unicode(r.url), unicode(r.method), None, r.headers)
else:
# Normal signing
r.headers['Content-Type'] = 'application/x-www-form-urlencoded'
r.url, r.headers, r.data = self.client.sign(
unicode(r.url), unicode(r.method), r.data, r.headers)
decoded_body = extract_params(r.data)
# extract_params can only check the present r.data and does not know
# of r.files, thus an extra check is performed. We know that
# if files are present the request will not have
# Content-type: x-www-form-urlencoded. We guess it will have
# a mimetype of multipart/form-data and if this is not the case
# we assume the correct header will be set later.
_oauth_signed = True
if r.files and contenttype == CONTENT_TYPE_MULTI_PART:
# Omit body data in the signing and since it will always
# be empty (cant add paras to body if multipart) and we wish
# to preserve body.
r.url, r.headers, _ = self.client.sign(
unicode(r.full_url), unicode(r.method), None, r.headers)
elif decoded_body != None and contenttype in (CONTENT_TYPE_FORM_URLENCODED, ''):
# Normal signing
if not contenttype:
r.headers['Content-Type'] = CONTENT_TYPE_FORM_URLENCODED
r.url, r.headers, r.data = self.client.sign(
unicode(r.full_url), unicode(r.method), r.data, r.headers)
else:
_oauth_signed = False
if _oauth_signed:
# Both flows add params to the URL by using r.full_url,
# so this prevents adding it again later
r.params = {}
# Having the authorization header, key or value, in unicode will
# result in UnicodeDecodeErrors when the request is concatenated
@@ -100,12 +117,12 @@ class OAuth1(AuthBase):
# >>> d
# { u'a' : 'foo' }
u_header = unicode('Authorization')
if u_header in r.headers:
if u_header in r.headers:
auth_header = r.headers[u_header].encode('utf-8')
del r.headers[u_header]
r.headers['Authorization'] = auth_header
return r
return r
class HTTPBasicAuth(AuthBase):
@@ -131,91 +148,101 @@ class HTTPDigestAuth(AuthBase):
def __init__(self, username, password):
self.username = username
self.password = password
self.last_nonce = ''
self.nonce_count = 0
self.chal = {}
def build_digest_header(self, method, url):
realm = self.chal['realm']
nonce = self.chal['nonce']
qop = self.chal.get('qop')
algorithm = self.chal.get('algorithm', 'MD5')
opaque = self.chal.get('opaque', None)
algorithm = algorithm.upper()
# lambdas assume digest modules are imported at the top level
if algorithm == 'MD5':
def md5_utf8(x):
if isinstance(x, str):
x = x.encode('utf-8')
return hashlib.md5(x).hexdigest()
hash_utf8 = md5_utf8
elif algorithm == 'SHA':
def sha_utf8(x):
if isinstance(x, str):
x = x.encode('utf-8')
return hashlib.sha1(x).hexdigest()
hash_utf8 = sha_utf8
# XXX MD5-sess
KD = lambda s, d: hash_utf8("%s:%s" % (s, d))
if hash_utf8 is None:
return None
# XXX not implemented yet
entdig = None
p_parsed = urlparse(url)
path = p_parsed.path
if p_parsed.query:
path += '?' + p_parsed.query
A1 = '%s:%s:%s' % (self.username, realm, self.password)
A2 = '%s:%s' % (method, path)
if qop == 'auth':
if nonce == self.last_nonce:
self.nonce_count += 1
else:
self.nonce_count = 1
ncvalue = '%08x' % self.nonce_count
s = str(self.nonce_count).encode('utf-8')
s += nonce.encode('utf-8')
s += time.ctime().encode('utf-8')
s += os.urandom(8)
cnonce = (hashlib.sha1(s).hexdigest()[:16])
noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, hash_utf8(A2))
respdig = KD(hash_utf8(A1), noncebit)
elif qop is None:
respdig = KD(hash_utf8(A1), "%s:%s" % (nonce, hash_utf8(A2)))
else:
# XXX handle auth-int.
return None
self.last_nonce = nonce
# XXX should the partial digests be encoded too?
base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
'response="%s"' % (self.username, realm, nonce, path, respdig)
if opaque:
base += ', opaque="%s"' % opaque
if entdig:
base += ', digest="%s"' % entdig
base += ', algorithm="%s"' % algorithm
if qop:
base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce)
return 'Digest %s' % (base)
def handle_401(self, r):
"""Takes the given response and tries digest-auth, if needed."""
r.request.deregister_hook('response', self.handle_401)
num_401_calls = r.request.hooks['response'].count(self.handle_401)
s_auth = r.headers.get('www-authenticate', '')
if 'digest' in s_auth.lower():
if 'digest' in s_auth.lower() and num_401_calls < 2:
last_nonce = ''
nonce_count = 0
self.chal = parse_dict_header(s_auth.replace('Digest ', ''))
chal = parse_dict_header(s_auth.replace('Digest ', ''))
# Consume content and release the original connection
# to allow our new request to reuse the same one.
r.content
r.raw.release_conn()
realm = chal['realm']
nonce = chal['nonce']
qop = chal.get('qop')
algorithm = chal.get('algorithm', 'MD5')
opaque = chal.get('opaque', None)
algorithm = algorithm.upper()
# lambdas assume digest modules are imported at the top level
if algorithm == 'MD5':
def md5_utf8(x):
if isinstance(x, str):
x = x.encode('utf-8')
return hashlib.md5(x).hexdigest()
hash_utf8 = md5_utf8
elif algorithm == 'SHA':
def sha_utf8(x):
if isinstance(x, str):
x = x.encode('utf-8')
return hashlib.sha1(x).hexdigest()
hash_utf8 = sha_utf8
# XXX MD5-sess
KD = lambda s, d: hash_utf8("%s:%s" % (s, d))
if hash_utf8 is None:
return None
# XXX not implemented yet
entdig = None
p_parsed = urlparse(r.request.url)
path = p_parsed.path
if p_parsed.query:
path += '?' + p_parsed.query
A1 = '%s:%s:%s' % (self.username, realm, self.password)
A2 = '%s:%s' % (r.request.method, path)
if qop == 'auth':
if nonce == last_nonce:
nonce_count += 1
else:
nonce_count = 1
last_nonce = nonce
ncvalue = '%08x' % nonce_count
s = str(nonce_count).encode('utf-8')
s += nonce.encode('utf-8')
s += time.ctime().encode('utf-8')
s += os.urandom(8)
cnonce = (hashlib.sha1(s).hexdigest()[:16])
noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, hash_utf8(A2))
respdig = KD(hash_utf8(A1), noncebit)
elif qop is None:
respdig = KD(hash_utf8(A1), "%s:%s" % (nonce, hash_utf8(A2)))
else:
# XXX handle auth-int.
return None
# XXX should the partial digests be encoded too?
base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
'response="%s"' % (self.username, realm, nonce, path, respdig)
if opaque:
base += ', opaque="%s"' % opaque
if entdig:
base += ', digest="%s"' % entdig
base += ', algorithm="%s"' % algorithm
if qop:
base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce)
r.request.headers['Authorization'] = 'Digest %s' % (base)
r.request.headers['Authorization'] = self.build_digest_header(r.request.method, r.request.url)
r.request.send(anyway=True)
_r = r.request.response
_r.history.append(r)
@@ -225,5 +252,131 @@ class HTTPDigestAuth(AuthBase):
return r
def __call__(self, r):
# If we have a saved nonce, skip the 401
if self.last_nonce:
r.headers['Authorization'] = self.build_digest_header(r.method, r.url)
r.register_hook('response', self.handle_401)
return r
def _negotiate_value(r):
"""Extracts the gssapi authentication token from the appropriate header"""
authreq = r.headers.get('www-authenticate', None)
if authreq:
rx = re.compile('(?:.*,)*\s*Negotiate\s*([^,]*),?', re.I)
mo = rx.search(authreq)
if mo:
return mo.group(1)
return None
class HTTPKerberosAuth(AuthBase):
"""Attaches HTTP GSSAPI/Kerberos Authentication to the given Request object."""
def __init__(self, require_mutual_auth=True):
if k is None:
raise Exception("Kerberos libraries unavailable")
self.context = None
self.require_mutual_auth = require_mutual_auth
def generate_request_header(self, r):
"""Generates the gssapi authentication token with kerberos"""
host = urlparse(r.url).netloc
tail, _, head = host.rpartition(':')
domain = tail if tail else head
result, self.context = k.authGSSClientInit("HTTP@%s" % domain)
if result < 1:
raise Exception("authGSSClientInit failed")
result = k.authGSSClientStep(self.context, _negotiate_value(r))
if result < 0:
raise Exception("authGSSClientStep failed")
response = k.authGSSClientResponse(self.context)
return "Negotiate %s" % response
def authenticate_user(self, r):
"""Handles user authentication with gssapi/kerberos"""
auth_header = self.generate_request_header(r)
log.debug("authenticate_user(): Authorization header: %s" % auth_header)
r.request.headers['Authorization'] = auth_header
r.request.send(anyway=True)
_r = r.request.response
_r.history.append(r)
log.debug("authenticate_user(): returning %s" % _r)
return _r
def handle_401(self, r):
"""Handles 401's, attempts to use gssapi/kerberos authentication"""
log.debug("handle_401(): Handling: 401")
if _negotiate_value(r) is not None:
_r = self.authenticate_user(r)
log.debug("handle_401(): returning %s" % _r)
return _r
else:
log.debug("handle_401(): Kerberos is not supported")
log.debug("handle_401(): returning %s" % r)
return r
def handle_other(self, r):
"""Handles all responses with the exception of 401s.
This is necessary so that we can authenticate responses if requested"""
log.debug("handle_other(): Handling: %d" % r.status_code)
self.deregister(r)
if self.require_mutual_auth:
if _negotiate_value(r) is not None:
log.debug("handle_other(): Authenticating the server")
_r = self.authenticate_server(r)
log.debug("handle_other(): returning %s" % _r)
return _r
else:
log.error("handle_other(): Mutual authentication failed")
raise Exception("Mutual authentication failed")
else:
log.debug("handle_other(): returning %s" % r)
return r
def authenticate_server(self, r):
"""Uses GSSAPI to authenticate the server"""
log.debug("authenticate_server(): Authenticate header: %s" % _negotiate_value(r))
result = k.authGSSClientStep(self.context, _negotiate_value(r))
if result < 1:
raise Exception("authGSSClientStep failed")
_r = r.request.response
log.debug("authenticate_server(): returning %s" % _r)
return _r
def handle_response(self, r):
"""Takes the given response and tries kerberos-auth, as needed."""
if r.status_code == 401:
_r = self.handle_401(r)
log.debug("handle_response returning %s" % _r)
return _r
else:
_r = self.handle_other(r)
log.debug("handle_response returning %s" % _r)
return _r
log.debug("handle_response returning %s" % r)
return r
def deregister(self, r):
"""Deregisters the response handler"""
r.request.deregister_hook('response', self.handle_response)
def __call__(self, r):
r.register_hook('response', self.handle_response)
return r
File diff suppressed because it is too large Load Diff
+27
View File
@@ -0,0 +1,27 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
ceritfi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem.
"""
import os
try:
import certifi
except ImportError:
certifi = None
def where():
if certifi:
return certifi.where()
else:
f = os.path.split(__file__)[0]
return os.path.join(f, 'cacert.pem')
if __name__ == '__main__':
print(where())
+15 -1
View File
@@ -72,6 +72,10 @@ is_osx = ('darwin' in str(sys.platform).lower())
is_hpux = ('hpux' in str(sys.platform).lower()) # Complete guess.
is_solaris = ('solar==' in str(sys.platform).lower()) # Complete guess.
try:
import simplejson as json
except ImportError:
import json
# ---------
# Specifics
@@ -85,10 +89,17 @@ if is_py2:
import cookielib
from Cookie import Morsel
from StringIO import StringIO
try:
import cchardet as chardet
except ImportError:
from .packages import chardet
from .packages.urllib3.packages.ordered_dict import OrderedDict
builtin_str = str
bytes = str
str = unicode
basestring = basestring
numeric_types = (int, long, float)
@@ -98,8 +109,11 @@ elif is_py3:
from http import cookiejar as cookielib
from http.cookies import Morsel
from io import StringIO
from .packages import chardet2 as chardet
from collections import OrderedDict
builtin_str = str
str = str
bytes = bytes
basestring = (str,bytes)
numeric_types = (int, float)
+25 -11
View File
@@ -14,6 +14,7 @@ try:
except ImportError:
import dummy_threading as threading
class MockRequest(object):
"""Wraps a `requests.Request` to mimic a `urllib2.Request`.
@@ -39,7 +40,7 @@ class MockRequest(object):
def get_origin_req_host(self):
if self._r.response.history:
r = self._r.response.history[0]
return urlparse(r).netloc
return urlparse(r.url).netloc
else:
return self.get_host()
@@ -66,6 +67,11 @@ class MockRequest(object):
def get_new_headers(self):
return self._new_headers
@property
def unverifiable(self):
return self.is_unverifiable()
class MockResponse(object):
"""Wraps a `httplib.HTTPMessage` to mimic a `urllib.addinfourl`.
@@ -86,6 +92,7 @@ class MockResponse(object):
def getheaders(self, name):
self._headers.getheaders(name)
def extract_cookies_to_jar(jar, request, response):
"""Extract the cookies from the response into a CookieJar.
@@ -99,12 +106,14 @@ def extract_cookies_to_jar(jar, request, response):
res = MockResponse(response._original_response.msg)
jar.extract_cookies(res, req)
def get_cookie_header(jar, request):
"""Produce an appropriate Cookie header string to be sent with `request`, or None."""
r = MockRequest(request)
jar.add_cookie_header(r)
return r.get_new_headers().get('Cookie')
def remove_cookie_by_name(cookiejar, name, domain=None, path=None):
"""Unsets a cookie by name, by default over all domains and paths.
@@ -120,10 +129,12 @@ def remove_cookie_by_name(cookiejar, name, domain=None, path=None):
for domain, path, name in clearables:
cookiejar.clear(domain, path, name)
class CookieConflictError(RuntimeError):
"""There are two cookies that meet the criteria specified in the cookie jar.
"""There are two cookies that meet the criteria specified in the cookie jar.
Use .get and .set and include domain and path args in order to be more specific."""
class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
"""Compatibility class; is a cookielib.CookieJar, but exposes a dict interface.
@@ -181,7 +192,7 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
for cookie in iter(self):
values.append(cookie.value)
return values
def items(self):
"""Dict-like items() that returns a list of name-value tuples from the jar.
See keys() and values(). Allows client-code to call "dict(RequestsCookieJar)
@@ -215,14 +226,14 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
if cookie.domain is not None and cookie.domain in domains:
return True
domains.append(cookie.domain)
return False # there is only one domain in jar
return False # there is only one domain in jar
def get_dict(self, domain=None, path=None):
"""Takes as an argument an optional domain and path and returns a plain old
Python dict of name-value pairs of cookies that meet the requirements."""
dictionary = {}
for cookie in iter(self):
if (domain == None or cookie.domain == domain) and (path == None
if (domain == None or cookie.domain == domain) and (path == None
or cookie.path == path):
dictionary[cookie.name] = cookie.value
return dictionary
@@ -244,7 +255,7 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
remove_cookie_by_name(self, name)
def _find(self, name, domain=None, path=None):
"""Requests uses this method internally to get cookie values. Takes as args name
"""Requests uses this method internally to get cookie values. Takes as args name
and optional domain and path. Returns a cookie.value. If there are conflicting cookies,
_find arbitrarily chooses one. See _find_no_duplicates if you want an exception thrown
if there are conflicting cookies."""
@@ -257,18 +268,18 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
raise KeyError('name=%r, domain=%r, path=%r' % (name, domain, path))
def _find_no_duplicates(self, name, domain=None, path=None):
"""__get_item__ and get call _find_no_duplicates -- never used in Requests internally.
Takes as args name and optional domain and path. Returns a cookie.value.
Throws KeyError if cookie is not found and CookieConflictError if there are
"""__get_item__ and get call _find_no_duplicates -- never used in Requests internally.
Takes as args name and optional domain and path. Returns a cookie.value.
Throws KeyError if cookie is not found and CookieConflictError if there are
multiple cookies that match name and optionally domain and path."""
toReturn = None
for cookie in iter(self):
if cookie.name == name:
if domain is None or cookie.domain == domain:
if path is None or cookie.path == path:
if toReturn != None: # if there are multiple cookies that meet passed in criteria
if toReturn != None: # if there are multiple cookies that meet passed in criteria
raise CookieConflictError('There are multiple cookies with name, %r' % (name))
toReturn = cookie.value # we will eventually return this as long as no cookie conflict
toReturn = cookie.value # we will eventually return this as long as no cookie conflict
if toReturn:
return toReturn
@@ -291,6 +302,7 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
"""This is not implemented. Calling this will throw an exception."""
raise NotImplementedError
def create_cookie(name, value, **kwargs):
"""Make a cookie from underspecified parameters.
@@ -326,6 +338,7 @@ def create_cookie(name, value, **kwargs):
return cookielib.Cookie(**result)
def morsel_to_cookie(morsel):
"""Convert a Morsel object into a Cookie containing the one k/v pair."""
c = create_cookie(
@@ -349,6 +362,7 @@ def morsel_to_cookie(morsel):
)
return c
def cookiejar_from_dict(cookie_dict, cookiejar=None):
"""Returns a CookieJar from a key/value dictionary.
+4 -7
View File
@@ -20,20 +20,19 @@ Configurations:
:pool_connections: The number of active HTTP connection pools to use.
:encode_uri: If true, URIs will automatically be percent-encoded.
:trust_env: If true, the surrouding environment will be trusted (environ, netrc).
:param store_cookies: If false, the received cookies as part of the HTTP response would be ignored.
:store_cookies: If false, the received cookies as part of the HTTP response would be ignored.
"""
SCHEMAS = ['http', 'https']
from . import __version__
from .utils import default_user_agent
defaults = dict()
defaults['base_headers'] = {
'User-Agent': 'python-requests/%s' % __version__,
'Accept-Encoding': ', '.join(('identity', 'deflate', 'compress', 'gzip')),
'User-Agent': default_user_agent(),
'Accept-Encoding': ', '.join(('gzip', 'deflate', 'compress')),
'Accept': '*/*'
}
@@ -49,5 +48,3 @@ defaults['keep_alive'] = True
defaults['encode_uri'] = True
defaults['trust_env'] = True
defaults['store_cookies'] = True
+10
View File
@@ -8,34 +8,44 @@ This module contains the set of Requests' exceptions.
"""
class RequestException(RuntimeError):
"""There was an ambiguous exception that occurred while handling your
request."""
class HTTPError(RequestException):
"""An HTTP error occurred."""
response = None
class ConnectionError(RequestException):
"""A Connection error occurred."""
class SSLError(ConnectionError):
"""An SSL error occurred."""
class Timeout(RequestException):
"""The request timed out."""
class URLRequired(RequestException):
"""A valid URL is required to make a request."""
class TooManyRedirects(RequestException):
"""Too many redirects."""
class MissingSchema(RequestException, ValueError):
"""The URL schema (e.g. http or https) is missing."""
class InvalidSchema(RequestException, ValueError):
"""See defaults.py for valid schemas."""
class InvalidURL(RequestException, ValueError):
""" The URL provided was somehow invalid. """
+4 -8
View File
@@ -25,11 +25,10 @@ Available hooks:
"""
import traceback
HOOKS = ('args', 'pre_request', 'pre_send', 'post_request', 'response')
def dispatch_hook(key, hooks, hook_data):
"""Dispatches a hook dictionary on a given piece of data."""
@@ -42,12 +41,9 @@ def dispatch_hook(key, hooks, hook_data):
hooks = [hooks]
for hook in hooks:
try:
_hook_data = hook(hook_data)
if _hook_data is not None:
hook_data = _hook_data
_hook_data = hook(hook_data)
if _hook_data is not None:
hook_data = _hook_data
except Exception:
traceback.print_exc()
return hook_data
+131 -76
View File
@@ -7,9 +7,10 @@ requests.models
This module contains the primary objects that power Requests.
"""
import json
import os
import socket
from datetime import datetime
from io import BytesIO
from .hooks import dispatch_hook, HOOKS
from .structures import CaseInsensitiveDict
@@ -18,6 +19,7 @@ from .status_codes import codes
from .auth import HTTPBasicAuth, HTTPProxyAuth
from .cookies import cookiejar_from_dict, extract_cookies_to_jar, get_cookie_header
from .packages.urllib3.exceptions import MaxRetryError, LocationParseError
from .packages.urllib3.exceptions import TimeoutError
from .packages.urllib3.exceptions import SSLError as _SSLError
from .packages.urllib3.exceptions import HTTPError as _HTTPError
from .packages.urllib3 import connectionpool, poolmanager
@@ -29,25 +31,18 @@ from .exceptions import (
from .utils import (
get_encoding_from_headers, stream_untransfer, guess_filename, requote_uri,
stream_decode_response_unicode, get_netrc_auth, get_environ_proxies,
DEFAULT_CA_BUNDLE_PATH)
to_key_val_list, DEFAULT_CA_BUNDLE_PATH, parse_header_links, iter_slices)
from .compat import (
cookielib, urlparse, urlunparse, urljoin, urlsplit, urlencode, str, bytes,
StringIO, is_py2)
# Import chardet if it is available.
try:
import chardet
# hush pyflakes
chardet
except ImportError:
chardet = None
StringIO, is_py2, chardet, json, builtin_str)
REDIRECT_STATI = (codes.moved, codes.found, codes.other, codes.temporary_moved)
CONTENT_CHUNK_SIZE = 10 * 1024
class Request(object):
"""The :class:`Request <Request>` object. It carries out all functionality of
Requests. Recommended interface is with the Requests functions.
"""The :class:`Request <Request>` object. It carries out all functionality
of Requests. Recommended interface is with the Requests functions.
"""
def __init__(self,
@@ -65,7 +60,7 @@ class Request(object):
proxies=None,
hooks=None,
config=None,
prefetch=False,
prefetch=True,
_poolmanager=None,
verify=None,
session=None,
@@ -79,7 +74,14 @@ class Request(object):
self.timeout = timeout
#: Request URL.
self.url = url
#: Accept objects that have string representations.
try:
self.url = unicode(url)
except NameError:
# We're on Python 3.
self.url = str(url)
except UnicodeDecodeError:
self.url = url
#: Dictionary of HTTP Headers to attach to the :class:`Request <Request>`.
self.headers = dict(headers or [])
@@ -109,6 +111,10 @@ class Request(object):
# Dictionary mapping protocol to the URL of the proxy (e.g. {'http': 'foo.bar:3128'})
self.proxies = dict(proxies or [])
for proxy_type,uri_ref in list(self.proxies.items()):
if not uri_ref:
del self.proxies[proxy_type]
# If no proxies are given, allow configuration by environment variables
# HTTP_PROXY and HTTPS_PROXY.
if not self.proxies and self.config.get('trust_env'):
@@ -191,7 +197,7 @@ class Request(object):
response.status_code = getattr(resp, 'status', None)
# Make headers case-insensitive.
response.headers = CaseInsensitiveDict(getattr(resp, 'headers', None))
response.headers = CaseInsensitiveDict(getattr(resp, 'headers', {}))
# Set encoding.
response.encoding = get_encoding_from_headers(response.headers)
@@ -299,7 +305,8 @@ class Request(object):
proxies=self.proxies,
verify=self.verify,
session=self.session,
cert=self.cert
cert=self.cert,
prefetch=self.prefetch,
)
request.send()
@@ -319,53 +326,60 @@ class Request(object):
if parameters are supplied as a dict.
"""
if isinstance(data, bytes):
return data
if isinstance(data, str):
if isinstance(data, (str, bytes)):
return data
elif hasattr(data, 'read'):
return data
elif hasattr(data, '__iter__'):
try:
dict(data)
except ValueError:
raise ValueError('Unable to encode lists with elements that are not 2-tuples.')
params = list(data.items() if isinstance(data, dict) else data)
result = []
for k, vs in params:
for k, vs in to_key_val_list(data):
for v in isinstance(vs, list) and vs or [vs]:
result.append(
(k.encode('utf-8') if isinstance(k, str) else k,
v.encode('utf-8') if isinstance(v, str) else v))
if v is not None:
result.append(
(k.encode('utf-8') if isinstance(k, str) else k,
v.encode('utf-8') if isinstance(v, str) else v))
return urlencode(result, doseq=True)
else:
return data
def _encode_files(self, files):
"""Build the body for a multipart/form-data request.
Will successfully encode files when passed as a dict or a list of
2-tuples. Order is retained if data is a list of 2-tuples but abritrary
if parameters are supplied as a dict.
"""
if (not files) or isinstance(self.data, str):
return None
try:
fields = self.data.copy()
except AttributeError:
fields = dict(self.data)
new_fields = []
fields = to_key_val_list(self.data)
files = to_key_val_list(files)
for (k, v) in list(files.items()):
for field, val in fields:
if isinstance(val, list):
for v in val:
new_fields.append((field, str(v)))
else:
new_fields.append((field, str(val)))
for (k, v) in files:
# support for explicit filename
if isinstance(v, (tuple, list)):
fn, fp = v
else:
fn = guess_filename(v) or k
fp = v
if isinstance(fp, (bytes, str)):
if isinstance(fp, str):
fp = StringIO(fp)
fields.update({k: (fn, fp.read())})
if isinstance(fp, bytes):
fp = BytesIO(fp)
new_fields.append((k, (fn, fp.read())))
(body, content_type) = encode_multipart_formdata(fields)
body, content_type = encode_multipart_formdata(new_fields)
return (body, content_type)
return body, content_type
@property
def full_url(self):
@@ -385,7 +399,10 @@ class Request(object):
if not scheme in SCHEMAS:
raise InvalidSchema("Invalid scheme %r" % scheme)
netloc = netloc.encode('idna').decode('utf-8')
try:
netloc = netloc.encode('idna').decode('utf-8')
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
if not path:
path = '/'
@@ -404,14 +421,14 @@ class Request(object):
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
url = (urlunparse([scheme, netloc, path, params, query, fragment]))
enc_params = self._encode_params(self.params)
if enc_params:
if urlparse(url).query:
url = '%s&%s' % (url, enc_params)
if query:
query = '%s&%s' % (query, enc_params)
else:
url = '%s?%s' % (url, enc_params)
query = enc_params
url = (urlunparse([scheme, netloc, path, params, query, fragment]))
if self.config.get('encode_uri', True):
url = requote_uri(url)
@@ -445,8 +462,10 @@ class Request(object):
def register_hook(self, event, hook):
"""Properly register a hook."""
self.hooks[event].append(hook)
if isinstance(hook, (list, tuple, set)):
self.hooks[event].extend(hook)
else:
self.hooks[event].append(hook)
def deregister_hook(self, event, hook):
"""Deregister a previously registered hook.
@@ -459,7 +478,7 @@ class Request(object):
except ValueError:
return False
def send(self, anyway=False, prefetch=False):
def send(self, anyway=False, prefetch=None):
"""Sends the request. Returns True if successful, False if not.
If there was an HTTPError during transmission,
self.response.status_code will contain the HTTPError code.
@@ -468,6 +487,9 @@ class Request(object):
:param anyway: If True, request will be sent, even if it has
already been sent.
:param prefetch: If not None, will override the request's own setting
for prefetch.
"""
# Build the URL
@@ -483,10 +505,6 @@ class Request(object):
datetime.now().isoformat(), self.method, url
))
# Nottin' on you.
body = None
content_type = None
# Use .netrc auth if none was provided.
if not self.auth and self.config.get('trust_env'):
self.auth = get_netrc_auth(url)
@@ -502,6 +520,10 @@ class Request(object):
# Update self to reflect the auth changes.
self.__dict__.update(r.__dict__)
# Nottin' on you.
body = None
content_type = None
# Multi-part file uploads.
if self.files:
(body, content_type) = self._encode_files(self.files)
@@ -509,7 +531,7 @@ class Request(object):
if self.data:
body = self._encode_params(self.data)
if isinstance(self.data, str) or hasattr(self.data, 'read'):
if isinstance(self.data, str) or isinstance(self.data, builtin_str) or hasattr(self.data, 'read'):
content_type = None
else:
content_type = 'application/x-www-form-urlencoded'
@@ -519,10 +541,10 @@ class Request(object):
self.headers['Content-Type'] = content_type
_p = urlparse(url)
no_proxy = filter(lambda x:x.strip(), self.proxies.get('no', '').split(','))
no_proxy = filter(lambda x: x.strip(), self.proxies.get('no', '').split(','))
proxy = self.proxies.get(_p.scheme)
if proxy and not any(map(_p.netloc.endswith, no_proxy)):
if proxy and not any(map(_p.hostname.endswith, no_proxy)):
conn = poolmanager.proxy_from_url(proxy)
_proxy = urlparse(proxy)
if '@' in _proxy.netloc:
@@ -569,7 +591,7 @@ class Request(object):
conn.cert_reqs = 'CERT_NONE'
conn.ca_certs = None
if self.cert and self.verify:
if self.cert:
if len(self.cert) == 2:
conn.cert_file = self.cert[0]
conn.key_file = self.cert[1]
@@ -605,14 +627,19 @@ class Request(object):
)
self.sent = True
except socket.error as sockerr:
raise ConnectionError(sockerr)
except MaxRetryError as e:
raise ConnectionError(e)
except (_SSLError, _HTTPError) as e:
if self.verify and isinstance(e, _SSLError):
if isinstance(e, _SSLError):
raise SSLError(e)
raise Timeout('Request timed out.')
elif isinstance(e, TimeoutError):
raise Timeout(e)
else:
raise Timeout('Request timed out.')
# build_response can throw TooManyRedirects
self._build_response(r)
@@ -625,7 +652,9 @@ class Request(object):
self.__dict__.update(r.__dict__)
# If prefetch is True, mark content as consumed.
if prefetch or self.prefetch:
if prefetch is None:
prefetch = self.prefetch
if prefetch:
# Save the response.
self.response.content
@@ -669,7 +698,7 @@ class Response(object):
#: A list of :class:`Response <Response>` objects from
#: the history of the Request. Any redirect responses will end
#: up here.
#: up here. The list is sorted from the oldest to the most recent request.
self.history = []
#: The :class:`Request <Request>` that created the Response.
@@ -707,9 +736,8 @@ class Response(object):
length of each item returned as decoding can take place.
"""
if self._content_consumed:
raise RuntimeError(
'The content for this response was already consumed'
)
# simulate reading small chunks of the content
return iter_slices(self._content, chunk_size)
def generate():
while 1:
@@ -773,6 +801,8 @@ class Response(object):
self._content = None
self._content_consumed = True
# don't need to release the connection; that's been handled by urllib3
# since we exhausted the data.
return self._content
@property
@@ -798,10 +828,12 @@ class Response(object):
# Decode unicode from given encoding.
try:
content = str(self.content, encoding, errors='replace')
except LookupError:
except (LookupError, TypeError):
# A LookupError is raised if the encoding was not found which could
# indicate a misspelling or similar mistake.
#
# A TypeError can be raised if encoding is None
#
# So we try blindly encoding.
content = str(self.content, errors='replace')
@@ -809,29 +841,52 @@ class Response(object):
@property
def json(self):
"""Returns the json-encoded content of a request, if any."""
"""Returns the json-encoded content of a response, if any."""
try:
return json.loads(self.text or self.content)
except ValueError:
return None
@property
def links(self):
"""Returns the parsed header links of the response, if any."""
header = self.headers['link']
# l = MultiDict()
l = {}
if header:
links = parse_header_links(header)
for link in links:
key = link.get('rel') or link.get('url')
l[key] = link
return l
@property
def reason(self):
"""The HTTP Reason for the response."""
return self.raw.reason
def raise_for_status(self, allow_redirects=True):
"""Raises stored :class:`HTTPError` or :class:`URLError`, if one occurred."""
if self.error:
raise self.error
if (self.status_code >= 300) and (self.status_code < 400) and not allow_redirects:
http_error = HTTPError('%s Redirection' % self.status_code)
http_error.response = self
raise http_error
http_error_msg = ''
if 300 <= self.status_code < 400 and not allow_redirects:
http_error_msg = '%s Redirection: %s' % (self.status_code, self.reason)
elif (self.status_code >= 400) and (self.status_code < 500):
http_error = HTTPError('%s Client Error' % self.status_code)
http_error.response = self
raise http_error
elif 400 <= self.status_code < 500:
http_error_msg = '%s Client Error: %s' % (self.status_code, self.reason)
elif (self.status_code >= 500) and (self.status_code < 600):
http_error = HTTPError('%s Server Error' % self.status_code)
elif 500 <= self.status_code < 600:
http_error_msg = '%s Server Error: %s' % (self.status_code, self.reason)
if http_error_msg:
http_error = HTTPError(http_error_msg)
http_error.response = self
raise http_error
+26
View File
@@ -0,0 +1,26 @@
######################## BEGIN LICENSE BLOCK ########################
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
__version__ = "1.0.1"
def detect(aBuf):
import universaldetector
u = universaldetector.UniversalDetector()
u.reset()
u.feed(aBuf)
u.close()
return u.result
+923
View File
@@ -0,0 +1,923 @@
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
# Big5 frequency table
# by Taiwan's Mandarin Promotion Council
# <http://www.edu.tw:81/mandr/>
#
# 128 --> 0.42261
# 256 --> 0.57851
# 512 --> 0.74851
# 1024 --> 0.89384
# 2048 --> 0.97583
#
# Ideal Distribution Ratio = 0.74851/(1-0.74851) =2.98
# Random Distribution Ration = 512/(5401-512)=0.105
#
# Typical Distribution Ratio about 25% of Ideal one, still much higher than RDR
BIG5_TYPICAL_DISTRIBUTION_RATIO = 0.75
#Char to FreqOrder table
BIG5_TABLE_SIZE = 5376
Big5CharToFreqOrder = ( \
1,1801,1506, 255,1431, 198, 9, 82, 6,5008, 177, 202,3681,1256,2821, 110, # 16
3814, 33,3274, 261, 76, 44,2114, 16,2946,2187,1176, 659,3971, 26,3451,2653, # 32
1198,3972,3350,4202, 410,2215, 302, 590, 361,1964, 8, 204, 58,4510,5009,1932, # 48
63,5010,5011, 317,1614, 75, 222, 159,4203,2417,1480,5012,3555,3091, 224,2822, # 64
3682, 3, 10,3973,1471, 29,2787,1135,2866,1940, 873, 130,3275,1123, 312,5013, # 80
4511,2052, 507, 252, 682,5014, 142,1915, 124, 206,2947, 34,3556,3204, 64, 604, # 96
5015,2501,1977,1978, 155,1991, 645, 641,1606,5016,3452, 337, 72, 406,5017, 80, # 112
630, 238,3205,1509, 263, 939,1092,2654, 756,1440,1094,3453, 449, 69,2987, 591, # 128
179,2096, 471, 115,2035,1844, 60, 50,2988, 134, 806,1869, 734,2036,3454, 180, # 144
995,1607, 156, 537,2907, 688,5018, 319,1305, 779,2145, 514,2379, 298,4512, 359, # 160
2502, 90,2716,1338, 663, 11, 906,1099,2553, 20,2441, 182, 532,1716,5019, 732, # 176
1376,4204,1311,1420,3206, 25,2317,1056, 113, 399, 382,1950, 242,3455,2474, 529, # 192
3276, 475,1447,3683,5020, 117, 21, 656, 810,1297,2300,2334,3557,5021, 126,4205, # 208
706, 456, 150, 613,4513, 71,1118,2037,4206, 145,3092, 85, 835, 486,2115,1246, # 224
1426, 428, 727,1285,1015, 800, 106, 623, 303,1281,5022,2128,2359, 347,3815, 221, # 240
3558,3135,5023,1956,1153,4207, 83, 296,1199,3093, 192, 624, 93,5024, 822,1898, # 256
2823,3136, 795,2065, 991,1554,1542,1592, 27, 43,2867, 859, 139,1456, 860,4514, # 272
437, 712,3974, 164,2397,3137, 695, 211,3037,2097, 195,3975,1608,3559,3560,3684, # 288
3976, 234, 811,2989,2098,3977,2233,1441,3561,1615,2380, 668,2077,1638, 305, 228, # 304
1664,4515, 467, 415,5025, 262,2099,1593, 239, 108, 300, 200,1033, 512,1247,2078, # 320
5026,5027,2176,3207,3685,2682, 593, 845,1062,3277, 88,1723,2038,3978,1951, 212, # 336
266, 152, 149, 468,1899,4208,4516, 77, 187,5028,3038, 37, 5,2990,5029,3979, # 352
5030,5031, 39,2524,4517,2908,3208,2079, 55, 148, 74,4518, 545, 483,1474,1029, # 368
1665, 217,1870,1531,3138,1104,2655,4209, 24, 172,3562, 900,3980,3563,3564,4519, # 384
32,1408,2824,1312, 329, 487,2360,2251,2717, 784,2683, 4,3039,3351,1427,1789, # 400
188, 109, 499,5032,3686,1717,1790, 888,1217,3040,4520,5033,3565,5034,3352,1520, # 416
3687,3981, 196,1034, 775,5035,5036, 929,1816, 249, 439, 38,5037,1063,5038, 794, # 432
3982,1435,2301, 46, 178,3278,2066,5039,2381,5040, 214,1709,4521, 804, 35, 707, # 448
324,3688,1601,2554, 140, 459,4210,5041,5042,1365, 839, 272, 978,2262,2580,3456, # 464
2129,1363,3689,1423, 697, 100,3094, 48, 70,1231, 495,3139,2196,5043,1294,5044, # 480
2080, 462, 586,1042,3279, 853, 256, 988, 185,2382,3457,1698, 434,1084,5045,3458, # 496
314,2625,2788,4522,2335,2336, 569,2285, 637,1817,2525, 757,1162,1879,1616,3459, # 512
287,1577,2116, 768,4523,1671,2868,3566,2526,1321,3816, 909,2418,5046,4211, 933, # 528
3817,4212,2053,2361,1222,4524, 765,2419,1322, 786,4525,5047,1920,1462,1677,2909, # 544
1699,5048,4526,1424,2442,3140,3690,2600,3353,1775,1941,3460,3983,4213, 309,1369, # 560
1130,2825, 364,2234,1653,1299,3984,3567,3985,3986,2656, 525,1085,3041, 902,2001, # 576
1475, 964,4527, 421,1845,1415,1057,2286, 940,1364,3141, 376,4528,4529,1381, 7, # 592
2527, 983,2383, 336,1710,2684,1846, 321,3461, 559,1131,3042,2752,1809,1132,1313, # 608
265,1481,1858,5049, 352,1203,2826,3280, 167,1089, 420,2827, 776, 792,1724,3568, # 624
4214,2443,3281,5050,4215,5051, 446, 229, 333,2753, 901,3818,1200,1557,4530,2657, # 640
1921, 395,2754,2685,3819,4216,1836, 125, 916,3209,2626,4531,5052,5053,3820,5054, # 656
5055,5056,4532,3142,3691,1133,2555,1757,3462,1510,2318,1409,3569,5057,2146, 438, # 672
2601,2910,2384,3354,1068, 958,3043, 461, 311,2869,2686,4217,1916,3210,4218,1979, # 688
383, 750,2755,2627,4219, 274, 539, 385,1278,1442,5058,1154,1965, 384, 561, 210, # 704
98,1295,2556,3570,5059,1711,2420,1482,3463,3987,2911,1257, 129,5060,3821, 642, # 720
523,2789,2790,2658,5061, 141,2235,1333, 68, 176, 441, 876, 907,4220, 603,2602, # 736
710, 171,3464, 404, 549, 18,3143,2398,1410,3692,1666,5062,3571,4533,2912,4534, # 752
5063,2991, 368,5064, 146, 366, 99, 871,3693,1543, 748, 807,1586,1185, 22,2263, # 768
379,3822,3211,5065,3212, 505,1942,2628,1992,1382,2319,5066, 380,2362, 218, 702, # 784
1818,1248,3465,3044,3572,3355,3282,5067,2992,3694, 930,3283,3823,5068, 59,5069, # 800
585, 601,4221, 497,3466,1112,1314,4535,1802,5070,1223,1472,2177,5071, 749,1837, # 816
690,1900,3824,1773,3988,1476, 429,1043,1791,2236,2117, 917,4222, 447,1086,1629, # 832
5072, 556,5073,5074,2021,1654, 844,1090, 105, 550, 966,1758,2828,1008,1783, 686, # 848
1095,5075,2287, 793,1602,5076,3573,2603,4536,4223,2948,2302,4537,3825, 980,2503, # 864
544, 353, 527,4538, 908,2687,2913,5077, 381,2629,1943,1348,5078,1341,1252, 560, # 880
3095,5079,3467,2870,5080,2054, 973, 886,2081, 143,4539,5081,5082, 157,3989, 496, # 896
4224, 57, 840, 540,2039,4540,4541,3468,2118,1445, 970,2264,1748,1966,2082,4225, # 912
3144,1234,1776,3284,2829,3695, 773,1206,2130,1066,2040,1326,3990,1738,1725,4226, # 928
279,3145, 51,1544,2604, 423,1578,2131,2067, 173,4542,1880,5083,5084,1583, 264, # 944
610,3696,4543,2444, 280, 154,5085,5086,5087,1739, 338,1282,3096, 693,2871,1411, # 960
1074,3826,2445,5088,4544,5089,5090,1240, 952,2399,5091,2914,1538,2688, 685,1483, # 976
4227,2475,1436, 953,4228,2055,4545, 671,2400, 79,4229,2446,3285, 608, 567,2689, # 992
3469,4230,4231,1691, 393,1261,1792,2401,5092,4546,5093,5094,5095,5096,1383,1672, # 1008
3827,3213,1464, 522,1119, 661,1150, 216, 675,4547,3991,1432,3574, 609,4548,2690, # 1024
2402,5097,5098,5099,4232,3045, 0,5100,2476, 315, 231,2447, 301,3356,4549,2385, # 1040
5101, 233,4233,3697,1819,4550,4551,5102, 96,1777,1315,2083,5103, 257,5104,1810, # 1056
3698,2718,1139,1820,4234,2022,1124,2164,2791,1778,2659,5105,3097, 363,1655,3214, # 1072
5106,2993,5107,5108,5109,3992,1567,3993, 718, 103,3215, 849,1443, 341,3357,2949, # 1088
1484,5110,1712, 127, 67, 339,4235,2403, 679,1412, 821,5111,5112, 834, 738, 351, # 1104
2994,2147, 846, 235,1497,1881, 418,1993,3828,2719, 186,1100,2148,2756,3575,1545, # 1120
1355,2950,2872,1377, 583,3994,4236,2581,2995,5113,1298,3699,1078,2557,3700,2363, # 1136
78,3829,3830, 267,1289,2100,2002,1594,4237, 348, 369,1274,2197,2178,1838,4552, # 1152
1821,2830,3701,2757,2288,2003,4553,2951,2758, 144,3358, 882,4554,3995,2759,3470, # 1168
4555,2915,5114,4238,1726, 320,5115,3996,3046, 788,2996,5116,2831,1774,1327,2873, # 1184
3997,2832,5117,1306,4556,2004,1700,3831,3576,2364,2660, 787,2023, 506, 824,3702, # 1200
534, 323,4557,1044,3359,2024,1901, 946,3471,5118,1779,1500,1678,5119,1882,4558, # 1216
165, 243,4559,3703,2528, 123, 683,4239, 764,4560, 36,3998,1793, 589,2916, 816, # 1232
626,1667,3047,2237,1639,1555,1622,3832,3999,5120,4000,2874,1370,1228,1933, 891, # 1248
2084,2917, 304,4240,5121, 292,2997,2720,3577, 691,2101,4241,1115,4561, 118, 662, # 1264
5122, 611,1156, 854,2386,1316,2875, 2, 386, 515,2918,5123,5124,3286, 868,2238, # 1280
1486, 855,2661, 785,2216,3048,5125,1040,3216,3578,5126,3146, 448,5127,1525,5128, # 1296
2165,4562,5129,3833,5130,4242,2833,3579,3147, 503, 818,4001,3148,1568, 814, 676, # 1312
1444, 306,1749,5131,3834,1416,1030, 197,1428, 805,2834,1501,4563,5132,5133,5134, # 1328
1994,5135,4564,5136,5137,2198, 13,2792,3704,2998,3149,1229,1917,5138,3835,2132, # 1344
5139,4243,4565,2404,3580,5140,2217,1511,1727,1120,5141,5142, 646,3836,2448, 307, # 1360
5143,5144,1595,3217,5145,5146,5147,3705,1113,1356,4002,1465,2529,2530,5148, 519, # 1376
5149, 128,2133, 92,2289,1980,5150,4003,1512, 342,3150,2199,5151,2793,2218,1981, # 1392
3360,4244, 290,1656,1317, 789, 827,2365,5152,3837,4566, 562, 581,4004,5153, 401, # 1408
4567,2252, 94,4568,5154,1399,2794,5155,1463,2025,4569,3218,1944,5156, 828,1105, # 1424
4245,1262,1394,5157,4246, 605,4570,5158,1784,2876,5159,2835, 819,2102, 578,2200, # 1440
2952,5160,1502, 436,3287,4247,3288,2836,4005,2919,3472,3473,5161,2721,2320,5162, # 1456
5163,2337,2068, 23,4571, 193, 826,3838,2103, 699,1630,4248,3098, 390,1794,1064, # 1472
3581,5164,1579,3099,3100,1400,5165,4249,1839,1640,2877,5166,4572,4573, 137,4250, # 1488
598,3101,1967, 780, 104, 974,2953,5167, 278, 899, 253, 402, 572, 504, 493,1339, # 1504
5168,4006,1275,4574,2582,2558,5169,3706,3049,3102,2253, 565,1334,2722, 863, 41, # 1520
5170,5171,4575,5172,1657,2338, 19, 463,2760,4251, 606,5173,2999,3289,1087,2085, # 1536
1323,2662,3000,5174,1631,1623,1750,4252,2691,5175,2878, 791,2723,2663,2339, 232, # 1552
2421,5176,3001,1498,5177,2664,2630, 755,1366,3707,3290,3151,2026,1609, 119,1918, # 1568
3474, 862,1026,4253,5178,4007,3839,4576,4008,4577,2265,1952,2477,5179,1125, 817, # 1584
4254,4255,4009,1513,1766,2041,1487,4256,3050,3291,2837,3840,3152,5180,5181,1507, # 1600
5182,2692, 733, 40,1632,1106,2879, 345,4257, 841,2531, 230,4578,3002,1847,3292, # 1616
3475,5183,1263, 986,3476,5184, 735, 879, 254,1137, 857, 622,1300,1180,1388,1562, # 1632
4010,4011,2954, 967,2761,2665,1349, 592,2134,1692,3361,3003,1995,4258,1679,4012, # 1648
1902,2188,5185, 739,3708,2724,1296,1290,5186,4259,2201,2202,1922,1563,2605,2559, # 1664
1871,2762,3004,5187, 435,5188, 343,1108, 596, 17,1751,4579,2239,3477,3709,5189, # 1680
4580, 294,3582,2955,1693, 477, 979, 281,2042,3583, 643,2043,3710,2631,2795,2266, # 1696
1031,2340,2135,2303,3584,4581, 367,1249,2560,5190,3585,5191,4582,1283,3362,2005, # 1712
240,1762,3363,4583,4584, 836,1069,3153, 474,5192,2149,2532, 268,3586,5193,3219, # 1728
1521,1284,5194,1658,1546,4260,5195,3587,3588,5196,4261,3364,2693,1685,4262, 961, # 1744
1673,2632, 190,2006,2203,3841,4585,4586,5197, 570,2504,3711,1490,5198,4587,2633, # 1760
3293,1957,4588, 584,1514, 396,1045,1945,5199,4589,1968,2449,5200,5201,4590,4013, # 1776
619,5202,3154,3294, 215,2007,2796,2561,3220,4591,3221,4592, 763,4263,3842,4593, # 1792
5203,5204,1958,1767,2956,3365,3712,1174, 452,1477,4594,3366,3155,5205,2838,1253, # 1808
2387,2189,1091,2290,4264, 492,5206, 638,1169,1825,2136,1752,4014, 648, 926,1021, # 1824
1324,4595, 520,4596, 997, 847,1007, 892,4597,3843,2267,1872,3713,2405,1785,4598, # 1840
1953,2957,3103,3222,1728,4265,2044,3714,4599,2008,1701,3156,1551, 30,2268,4266, # 1856
5207,2027,4600,3589,5208, 501,5209,4267, 594,3478,2166,1822,3590,3479,3591,3223, # 1872
829,2839,4268,5210,1680,3157,1225,4269,5211,3295,4601,4270,3158,2341,5212,4602, # 1888
4271,5213,4015,4016,5214,1848,2388,2606,3367,5215,4603, 374,4017, 652,4272,4273, # 1904
375,1140, 798,5216,5217,5218,2366,4604,2269, 546,1659, 138,3051,2450,4605,5219, # 1920
2254, 612,1849, 910, 796,3844,1740,1371, 825,3845,3846,5220,2920,2562,5221, 692, # 1936
444,3052,2634, 801,4606,4274,5222,1491, 244,1053,3053,4275,4276, 340,5223,4018, # 1952
1041,3005, 293,1168, 87,1357,5224,1539, 959,5225,2240, 721, 694,4277,3847, 219, # 1968
1478, 644,1417,3368,2666,1413,1401,1335,1389,4019,5226,5227,3006,2367,3159,1826, # 1984
730,1515, 184,2840, 66,4607,5228,1660,2958, 246,3369, 378,1457, 226,3480, 975, # 2000
4020,2959,1264,3592, 674, 696,5229, 163,5230,1141,2422,2167, 713,3593,3370,4608, # 2016
4021,5231,5232,1186, 15,5233,1079,1070,5234,1522,3224,3594, 276,1050,2725, 758, # 2032
1126, 653,2960,3296,5235,2342, 889,3595,4022,3104,3007, 903,1250,4609,4023,3481, # 2048
3596,1342,1681,1718, 766,3297, 286, 89,2961,3715,5236,1713,5237,2607,3371,3008, # 2064
5238,2962,2219,3225,2880,5239,4610,2505,2533, 181, 387,1075,4024, 731,2190,3372, # 2080
5240,3298, 310, 313,3482,2304, 770,4278, 54,3054, 189,4611,3105,3848,4025,5241, # 2096
1230,1617,1850, 355,3597,4279,4612,3373, 111,4280,3716,1350,3160,3483,3055,4281, # 2112
2150,3299,3598,5242,2797,4026,4027,3009, 722,2009,5243,1071, 247,1207,2343,2478, # 2128
1378,4613,2010, 864,1437,1214,4614, 373,3849,1142,2220, 667,4615, 442,2763,2563, # 2144
3850,4028,1969,4282,3300,1840, 837, 170,1107, 934,1336,1883,5244,5245,2119,4283, # 2160
2841, 743,1569,5246,4616,4284, 582,2389,1418,3484,5247,1803,5248, 357,1395,1729, # 2176
3717,3301,2423,1564,2241,5249,3106,3851,1633,4617,1114,2086,4285,1532,5250, 482, # 2192
2451,4618,5251,5252,1492, 833,1466,5253,2726,3599,1641,2842,5254,1526,1272,3718, # 2208
4286,1686,1795, 416,2564,1903,1954,1804,5255,3852,2798,3853,1159,2321,5256,2881, # 2224
4619,1610,1584,3056,2424,2764, 443,3302,1163,3161,5257,5258,4029,5259,4287,2506, # 2240
3057,4620,4030,3162,2104,1647,3600,2011,1873,4288,5260,4289, 431,3485,5261, 250, # 2256
97, 81,4290,5262,1648,1851,1558, 160, 848,5263, 866, 740,1694,5264,2204,2843, # 2272
3226,4291,4621,3719,1687, 950,2479, 426, 469,3227,3720,3721,4031,5265,5266,1188, # 2288
424,1996, 861,3601,4292,3854,2205,2694, 168,1235,3602,4293,5267,2087,1674,4622, # 2304
3374,3303, 220,2565,1009,5268,3855, 670,3010, 332,1208, 717,5269,5270,3603,2452, # 2320
4032,3375,5271, 513,5272,1209,2882,3376,3163,4623,1080,5273,5274,5275,5276,2534, # 2336
3722,3604, 815,1587,4033,4034,5277,3605,3486,3856,1254,4624,1328,3058,1390,4035, # 2352
1741,4036,3857,4037,5278, 236,3858,2453,3304,5279,5280,3723,3859,1273,3860,4625, # 2368
5281, 308,5282,4626, 245,4627,1852,2480,1307,2583, 430, 715,2137,2454,5283, 270, # 2384
199,2883,4038,5284,3606,2727,1753, 761,1754, 725,1661,1841,4628,3487,3724,5285, # 2400
5286, 587, 14,3305, 227,2608, 326, 480,2270, 943,2765,3607, 291, 650,1884,5287, # 2416
1702,1226, 102,1547, 62,3488, 904,4629,3489,1164,4294,5288,5289,1224,1548,2766, # 2432
391, 498,1493,5290,1386,1419,5291,2056,1177,4630, 813, 880,1081,2368, 566,1145, # 2448
4631,2291,1001,1035,2566,2609,2242, 394,1286,5292,5293,2069,5294, 86,1494,1730, # 2464
4039, 491,1588, 745, 897,2963, 843,3377,4040,2767,2884,3306,1768, 998,2221,2070, # 2480
397,1827,1195,1970,3725,3011,3378, 284,5295,3861,2507,2138,2120,1904,5296,4041, # 2496
2151,4042,4295,1036,3490,1905, 114,2567,4296, 209,1527,5297,5298,2964,2844,2635, # 2512
2390,2728,3164, 812,2568,5299,3307,5300,1559, 737,1885,3726,1210, 885, 28,2695, # 2528
3608,3862,5301,4297,1004,1780,4632,5302, 346,1982,2222,2696,4633,3863,1742, 797, # 2544
1642,4043,1934,1072,1384,2152, 896,4044,3308,3727,3228,2885,3609,5303,2569,1959, # 2560
4634,2455,1786,5304,5305,5306,4045,4298,1005,1308,3728,4299,2729,4635,4636,1528, # 2576
2610, 161,1178,4300,1983, 987,4637,1101,4301, 631,4046,1157,3229,2425,1343,1241, # 2592
1016,2243,2570, 372, 877,2344,2508,1160, 555,1935, 911,4047,5307, 466,1170, 169, # 2608
1051,2921,2697,3729,2481,3012,1182,2012,2571,1251,2636,5308, 992,2345,3491,1540, # 2624
2730,1201,2071,2406,1997,2482,5309,4638, 528,1923,2191,1503,1874,1570,2369,3379, # 2640
3309,5310, 557,1073,5311,1828,3492,2088,2271,3165,3059,3107, 767,3108,2799,4639, # 2656
1006,4302,4640,2346,1267,2179,3730,3230, 778,4048,3231,2731,1597,2667,5312,4641, # 2672
5313,3493,5314,5315,5316,3310,2698,1433,3311, 131, 95,1504,4049, 723,4303,3166, # 2688
1842,3610,2768,2192,4050,2028,2105,3731,5317,3013,4051,1218,5318,3380,3232,4052, # 2704
4304,2584, 248,1634,3864, 912,5319,2845,3732,3060,3865, 654, 53,5320,3014,5321, # 2720
1688,4642, 777,3494,1032,4053,1425,5322, 191, 820,2121,2846, 971,4643, 931,3233, # 2736
135, 664, 783,3866,1998, 772,2922,1936,4054,3867,4644,2923,3234, 282,2732, 640, # 2752
1372,3495,1127, 922, 325,3381,5323,5324, 711,2045,5325,5326,4055,2223,2800,1937, # 2768
4056,3382,2224,2255,3868,2305,5327,4645,3869,1258,3312,4057,3235,2139,2965,4058, # 2784
4059,5328,2225, 258,3236,4646, 101,1227,5329,3313,1755,5330,1391,3314,5331,2924, # 2800
2057, 893,5332,5333,5334,1402,4305,2347,5335,5336,3237,3611,5337,5338, 878,1325, # 2816
1781,2801,4647, 259,1385,2585, 744,1183,2272,4648,5339,4060,2509,5340, 684,1024, # 2832
4306,5341, 472,3612,3496,1165,3315,4061,4062, 322,2153, 881, 455,1695,1152,1340, # 2848
660, 554,2154,4649,1058,4650,4307, 830,1065,3383,4063,4651,1924,5342,1703,1919, # 2864
5343, 932,2273, 122,5344,4652, 947, 677,5345,3870,2637, 297,1906,1925,2274,4653, # 2880
2322,3316,5346,5347,4308,5348,4309, 84,4310, 112, 989,5349, 547,1059,4064, 701, # 2896
3613,1019,5350,4311,5351,3497, 942, 639, 457,2306,2456, 993,2966, 407, 851, 494, # 2912
4654,3384, 927,5352,1237,5353,2426,3385, 573,4312, 680, 921,2925,1279,1875, 285, # 2928
790,1448,1984, 719,2168,5354,5355,4655,4065,4066,1649,5356,1541, 563,5357,1077, # 2944
5358,3386,3061,3498, 511,3015,4067,4068,3733,4069,1268,2572,3387,3238,4656,4657, # 2960
5359, 535,1048,1276,1189,2926,2029,3167,1438,1373,2847,2967,1134,2013,5360,4313, # 2976
1238,2586,3109,1259,5361, 700,5362,2968,3168,3734,4314,5363,4315,1146,1876,1907, # 2992
4658,2611,4070, 781,2427, 132,1589, 203, 147, 273,2802,2407, 898,1787,2155,4071, # 3008
4072,5364,3871,2803,5365,5366,4659,4660,5367,3239,5368,1635,3872, 965,5369,1805, # 3024
2699,1516,3614,1121,1082,1329,3317,4073,1449,3873, 65,1128,2848,2927,2769,1590, # 3040
3874,5370,5371, 12,2668, 45, 976,2587,3169,4661, 517,2535,1013,1037,3240,5372, # 3056
3875,2849,5373,3876,5374,3499,5375,2612, 614,1999,2323,3877,3110,2733,2638,5376, # 3072
2588,4316, 599,1269,5377,1811,3735,5378,2700,3111, 759,1060, 489,1806,3388,3318, # 3088
1358,5379,5380,2391,1387,1215,2639,2256, 490,5381,5382,4317,1759,2392,2348,5383, # 3104
4662,3878,1908,4074,2640,1807,3241,4663,3500,3319,2770,2349, 874,5384,5385,3501, # 3120
3736,1859, 91,2928,3737,3062,3879,4664,5386,3170,4075,2669,5387,3502,1202,1403, # 3136
3880,2969,2536,1517,2510,4665,3503,2511,5388,4666,5389,2701,1886,1495,1731,4076, # 3152
2370,4667,5390,2030,5391,5392,4077,2702,1216, 237,2589,4318,2324,4078,3881,4668, # 3168
4669,2703,3615,3504, 445,4670,5393,5394,5395,5396,2771, 61,4079,3738,1823,4080, # 3184
5397, 687,2046, 935, 925, 405,2670, 703,1096,1860,2734,4671,4081,1877,1367,2704, # 3200
3389, 918,2106,1782,2483, 334,3320,1611,1093,4672, 564,3171,3505,3739,3390, 945, # 3216
2641,2058,4673,5398,1926, 872,4319,5399,3506,2705,3112, 349,4320,3740,4082,4674, # 3232
3882,4321,3741,2156,4083,4675,4676,4322,4677,2408,2047, 782,4084, 400, 251,4323, # 3248
1624,5400,5401, 277,3742, 299,1265, 476,1191,3883,2122,4324,4325,1109, 205,5402, # 3264
2590,1000,2157,3616,1861,5403,5404,5405,4678,5406,4679,2573, 107,2484,2158,4085, # 3280
3507,3172,5407,1533, 541,1301, 158, 753,4326,2886,3617,5408,1696, 370,1088,4327, # 3296
4680,3618, 579, 327, 440, 162,2244, 269,1938,1374,3508, 968,3063, 56,1396,3113, # 3312
2107,3321,3391,5409,1927,2159,4681,3016,5410,3619,5411,5412,3743,4682,2485,5413, # 3328
2804,5414,1650,4683,5415,2613,5416,5417,4086,2671,3392,1149,3393,4087,3884,4088, # 3344
5418,1076, 49,5419, 951,3242,3322,3323, 450,2850, 920,5420,1812,2805,2371,4328, # 3360
1909,1138,2372,3885,3509,5421,3243,4684,1910,1147,1518,2428,4685,3886,5422,4686, # 3376
2393,2614, 260,1796,3244,5423,5424,3887,3324, 708,5425,3620,1704,5426,3621,1351, # 3392
1618,3394,3017,1887, 944,4329,3395,4330,3064,3396,4331,5427,3744, 422, 413,1714, # 3408
3325, 500,2059,2350,4332,2486,5428,1344,1911, 954,5429,1668,5430,5431,4089,2409, # 3424
4333,3622,3888,4334,5432,2307,1318,2512,3114, 133,3115,2887,4687, 629, 31,2851, # 3440
2706,3889,4688, 850, 949,4689,4090,2970,1732,2089,4335,1496,1853,5433,4091, 620, # 3456
3245, 981,1242,3745,3397,1619,3746,1643,3326,2140,2457,1971,1719,3510,2169,5434, # 3472
3246,5435,5436,3398,1829,5437,1277,4690,1565,2048,5438,1636,3623,3116,5439, 869, # 3488
2852, 655,3890,3891,3117,4092,3018,3892,1310,3624,4691,5440,5441,5442,1733, 558, # 3504
4692,3747, 335,1549,3065,1756,4336,3748,1946,3511,1830,1291,1192, 470,2735,2108, # 3520
2806, 913,1054,4093,5443,1027,5444,3066,4094,4693, 982,2672,3399,3173,3512,3247, # 3536
3248,1947,2807,5445, 571,4694,5446,1831,5447,3625,2591,1523,2429,5448,2090, 984, # 3552
4695,3749,1960,5449,3750, 852, 923,2808,3513,3751, 969,1519, 999,2049,2325,1705, # 3568
5450,3118, 615,1662, 151, 597,4095,2410,2326,1049, 275,4696,3752,4337, 568,3753, # 3584
3626,2487,4338,3754,5451,2430,2275, 409,3249,5452,1566,2888,3514,1002, 769,2853, # 3600
194,2091,3174,3755,2226,3327,4339, 628,1505,5453,5454,1763,2180,3019,4096, 521, # 3616
1161,2592,1788,2206,2411,4697,4097,1625,4340,4341, 412, 42,3119, 464,5455,2642, # 3632
4698,3400,1760,1571,2889,3515,2537,1219,2207,3893,2643,2141,2373,4699,4700,3328, # 3648
1651,3401,3627,5456,5457,3628,2488,3516,5458,3756,5459,5460,2276,2092, 460,5461, # 3664
4701,5462,3020, 962, 588,3629, 289,3250,2644,1116, 52,5463,3067,1797,5464,5465, # 3680
5466,1467,5467,1598,1143,3757,4342,1985,1734,1067,4702,1280,3402, 465,4703,1572, # 3696
510,5468,1928,2245,1813,1644,3630,5469,4704,3758,5470,5471,2673,1573,1534,5472, # 3712
5473, 536,1808,1761,3517,3894,3175,2645,5474,5475,5476,4705,3518,2929,1912,2809, # 3728
5477,3329,1122, 377,3251,5478, 360,5479,5480,4343,1529, 551,5481,2060,3759,1769, # 3744
2431,5482,2930,4344,3330,3120,2327,2109,2031,4706,1404, 136,1468,1479, 672,1171, # 3760
3252,2308, 271,3176,5483,2772,5484,2050, 678,2736, 865,1948,4707,5485,2014,4098, # 3776
2971,5486,2737,2227,1397,3068,3760,4708,4709,1735,2931,3403,3631,5487,3895, 509, # 3792
2854,2458,2890,3896,5488,5489,3177,3178,4710,4345,2538,4711,2309,1166,1010, 552, # 3808
681,1888,5490,5491,2972,2973,4099,1287,1596,1862,3179, 358, 453, 736, 175, 478, # 3824
1117, 905,1167,1097,5492,1854,1530,5493,1706,5494,2181,3519,2292,3761,3520,3632, # 3840
4346,2093,4347,5495,3404,1193,2489,4348,1458,2193,2208,1863,1889,1421,3331,2932, # 3856
3069,2182,3521, 595,2123,5496,4100,5497,5498,4349,1707,2646, 223,3762,1359, 751, # 3872
3121, 183,3522,5499,2810,3021, 419,2374, 633, 704,3897,2394, 241,5500,5501,5502, # 3888
838,3022,3763,2277,2773,2459,3898,1939,2051,4101,1309,3122,2246,1181,5503,1136, # 3904
2209,3899,2375,1446,4350,2310,4712,5504,5505,4351,1055,2615, 484,3764,5506,4102, # 3920
625,4352,2278,3405,1499,4353,4103,5507,4104,4354,3253,2279,2280,3523,5508,5509, # 3936
2774, 808,2616,3765,3406,4105,4355,3123,2539, 526,3407,3900,4356, 955,5510,1620, # 3952
4357,2647,2432,5511,1429,3766,1669,1832, 994, 928,5512,3633,1260,5513,5514,5515, # 3968
1949,2293, 741,2933,1626,4358,2738,2460, 867,1184, 362,3408,1392,5516,5517,4106, # 3984
4359,1770,1736,3254,2934,4713,4714,1929,2707,1459,1158,5518,3070,3409,2891,1292, # 4000
1930,2513,2855,3767,1986,1187,2072,2015,2617,4360,5519,2574,2514,2170,3768,2490, # 4016
3332,5520,3769,4715,5521,5522, 666,1003,3023,1022,3634,4361,5523,4716,1814,2257, # 4032
574,3901,1603, 295,1535, 705,3902,4362, 283, 858, 417,5524,5525,3255,4717,4718, # 4048
3071,1220,1890,1046,2281,2461,4107,1393,1599, 689,2575, 388,4363,5526,2491, 802, # 4064
5527,2811,3903,2061,1405,2258,5528,4719,3904,2110,1052,1345,3256,1585,5529, 809, # 4080
5530,5531,5532, 575,2739,3524, 956,1552,1469,1144,2328,5533,2329,1560,2462,3635, # 4096
3257,4108, 616,2210,4364,3180,2183,2294,5534,1833,5535,3525,4720,5536,1319,3770, # 4112
3771,1211,3636,1023,3258,1293,2812,5537,5538,5539,3905, 607,2311,3906, 762,2892, # 4128
1439,4365,1360,4721,1485,3072,5540,4722,1038,4366,1450,2062,2648,4367,1379,4723, # 4144
2593,5541,5542,4368,1352,1414,2330,2935,1172,5543,5544,3907,3908,4724,1798,1451, # 4160
5545,5546,5547,5548,2936,4109,4110,2492,2351, 411,4111,4112,3637,3333,3124,4725, # 4176
1561,2674,1452,4113,1375,5549,5550, 47,2974, 316,5551,1406,1591,2937,3181,5552, # 4192
1025,2142,3125,3182, 354,2740, 884,2228,4369,2412, 508,3772, 726,3638, 996,2433, # 4208
3639, 729,5553, 392,2194,1453,4114,4726,3773,5554,5555,2463,3640,2618,1675,2813, # 4224
919,2352,2975,2353,1270,4727,4115, 73,5556,5557, 647,5558,3259,2856,2259,1550, # 4240
1346,3024,5559,1332, 883,3526,5560,5561,5562,5563,3334,2775,5564,1212, 831,1347, # 4256
4370,4728,2331,3909,1864,3073, 720,3910,4729,4730,3911,5565,4371,5566,5567,4731, # 4272
5568,5569,1799,4732,3774,2619,4733,3641,1645,2376,4734,5570,2938, 669,2211,2675, # 4288
2434,5571,2893,5572,5573,1028,3260,5574,4372,2413,5575,2260,1353,5576,5577,4735, # 4304
3183, 518,5578,4116,5579,4373,1961,5580,2143,4374,5581,5582,3025,2354,2355,3912, # 4320
516,1834,1454,4117,2708,4375,4736,2229,2620,1972,1129,3642,5583,2776,5584,2976, # 4336
1422, 577,1470,3026,1524,3410,5585,5586, 432,4376,3074,3527,5587,2594,1455,2515, # 4352
2230,1973,1175,5588,1020,2741,4118,3528,4737,5589,2742,5590,1743,1361,3075,3529, # 4368
2649,4119,4377,4738,2295, 895, 924,4378,2171, 331,2247,3076, 166,1627,3077,1098, # 4384
5591,1232,2894,2231,3411,4739, 657, 403,1196,2377, 542,3775,3412,1600,4379,3530, # 4400
5592,4740,2777,3261, 576, 530,1362,4741,4742,2540,2676,3776,4120,5593, 842,3913, # 4416
5594,2814,2032,1014,4121, 213,2709,3413, 665, 621,4380,5595,3777,2939,2435,5596, # 4432
2436,3335,3643,3414,4743,4381,2541,4382,4744,3644,1682,4383,3531,1380,5597, 724, # 4448
2282, 600,1670,5598,1337,1233,4745,3126,2248,5599,1621,4746,5600, 651,4384,5601, # 4464
1612,4385,2621,5602,2857,5603,2743,2312,3078,5604, 716,2464,3079, 174,1255,2710, # 4480
4122,3645, 548,1320,1398, 728,4123,1574,5605,1891,1197,3080,4124,5606,3081,3082, # 4496
3778,3646,3779, 747,5607, 635,4386,4747,5608,5609,5610,4387,5611,5612,4748,5613, # 4512
3415,4749,2437, 451,5614,3780,2542,2073,4388,2744,4389,4125,5615,1764,4750,5616, # 4528
4390, 350,4751,2283,2395,2493,5617,4391,4126,2249,1434,4127, 488,4752, 458,4392, # 4544
4128,3781, 771,1330,2396,3914,2576,3184,2160,2414,1553,2677,3185,4393,5618,2494, # 4560
2895,2622,1720,2711,4394,3416,4753,5619,2543,4395,5620,3262,4396,2778,5621,2016, # 4576
2745,5622,1155,1017,3782,3915,5623,3336,2313, 201,1865,4397,1430,5624,4129,5625, # 4592
5626,5627,5628,5629,4398,1604,5630, 414,1866, 371,2595,4754,4755,3532,2017,3127, # 4608
4756,1708, 960,4399, 887, 389,2172,1536,1663,1721,5631,2232,4130,2356,2940,1580, # 4624
5632,5633,1744,4757,2544,4758,4759,5634,4760,5635,2074,5636,4761,3647,3417,2896, # 4640
4400,5637,4401,2650,3418,2815, 673,2712,2465, 709,3533,4131,3648,4402,5638,1148, # 4656
502, 634,5639,5640,1204,4762,3649,1575,4763,2623,3783,5641,3784,3128, 948,3263, # 4672
121,1745,3916,1110,5642,4403,3083,2516,3027,4132,3785,1151,1771,3917,1488,4133, # 4688
1987,5643,2438,3534,5644,5645,2094,5646,4404,3918,1213,1407,2816, 531,2746,2545, # 4704
3264,1011,1537,4764,2779,4405,3129,1061,5647,3786,3787,1867,2897,5648,2018, 120, # 4720
4406,4407,2063,3650,3265,2314,3919,2678,3419,1955,4765,4134,5649,3535,1047,2713, # 4736
1266,5650,1368,4766,2858, 649,3420,3920,2546,2747,1102,2859,2679,5651,5652,2000, # 4752
5653,1111,3651,2977,5654,2495,3921,3652,2817,1855,3421,3788,5655,5656,3422,2415, # 4768
2898,3337,3266,3653,5657,2577,5658,3654,2818,4135,1460, 856,5659,3655,5660,2899, # 4784
2978,5661,2900,3922,5662,4408, 632,2517, 875,3923,1697,3924,2296,5663,5664,4767, # 4800
3028,1239, 580,4768,4409,5665, 914, 936,2075,1190,4136,1039,2124,5666,5667,5668, # 4816
5669,3423,1473,5670,1354,4410,3925,4769,2173,3084,4137, 915,3338,4411,4412,3339, # 4832
1605,1835,5671,2748, 398,3656,4413,3926,4138, 328,1913,2860,4139,3927,1331,4414, # 4848
3029, 937,4415,5672,3657,4140,4141,3424,2161,4770,3425, 524, 742, 538,3085,1012, # 4864
5673,5674,3928,2466,5675, 658,1103, 225,3929,5676,5677,4771,5678,4772,5679,3267, # 4880
1243,5680,4142, 963,2250,4773,5681,2714,3658,3186,5682,5683,2596,2332,5684,4774, # 4896
5685,5686,5687,3536, 957,3426,2547,2033,1931,2941,2467, 870,2019,3659,1746,2780, # 4912
2781,2439,2468,5688,3930,5689,3789,3130,3790,3537,3427,3791,5690,1179,3086,5691, # 4928
3187,2378,4416,3792,2548,3188,3131,2749,4143,5692,3428,1556,2549,2297, 977,2901, # 4944
2034,4144,1205,3429,5693,1765,3430,3189,2125,1271, 714,1689,4775,3538,5694,2333, # 4960
3931, 533,4417,3660,2184, 617,5695,2469,3340,3539,2315,5696,5697,3190,5698,5699, # 4976
3932,1988, 618, 427,2651,3540,3431,5700,5701,1244,1690,5702,2819,4418,4776,5703, # 4992
3541,4777,5704,2284,1576, 473,3661,4419,3432, 972,5705,3662,5706,3087,5707,5708, # 5008
4778,4779,5709,3793,4145,4146,5710, 153,4780, 356,5711,1892,2902,4420,2144, 408, # 5024
803,2357,5712,3933,5713,4421,1646,2578,2518,4781,4782,3934,5714,3935,4422,5715, # 5040
2416,3433, 752,5716,5717,1962,3341,2979,5718, 746,3030,2470,4783,4423,3794, 698, # 5056
4784,1893,4424,3663,2550,4785,3664,3936,5719,3191,3434,5720,1824,1302,4147,2715, # 5072
3937,1974,4425,5721,4426,3192, 823,1303,1288,1236,2861,3542,4148,3435, 774,3938, # 5088
5722,1581,4786,1304,2862,3939,4787,5723,2440,2162,1083,3268,4427,4149,4428, 344, # 5104
1173, 288,2316, 454,1683,5724,5725,1461,4788,4150,2597,5726,5727,4789, 985, 894, # 5120
5728,3436,3193,5729,1914,2942,3795,1989,5730,2111,1975,5731,4151,5732,2579,1194, # 5136
425,5733,4790,3194,1245,3796,4429,5734,5735,2863,5736, 636,4791,1856,3940, 760, # 5152
1800,5737,4430,2212,1508,4792,4152,1894,1684,2298,5738,5739,4793,4431,4432,2213, # 5168
479,5740,5741, 832,5742,4153,2496,5743,2980,2497,3797, 990,3132, 627,1815,2652, # 5184
4433,1582,4434,2126,2112,3543,4794,5744, 799,4435,3195,5745,4795,2113,1737,3031, # 5200
1018, 543, 754,4436,3342,1676,4796,4797,4154,4798,1489,5746,3544,5747,2624,2903, # 5216
4155,5748,5749,2981,5750,5751,5752,5753,3196,4799,4800,2185,1722,5754,3269,3270, # 5232
1843,3665,1715, 481, 365,1976,1857,5755,5756,1963,2498,4801,5757,2127,3666,3271, # 5248
433,1895,2064,2076,5758, 602,2750,5759,5760,5761,5762,5763,3032,1628,3437,5764, # 5264
3197,4802,4156,2904,4803,2519,5765,2551,2782,5766,5767,5768,3343,4804,2905,5769, # 5280
4805,5770,2864,4806,4807,1221,2982,4157,2520,5771,5772,5773,1868,1990,5774,5775, # 5296
5776,1896,5777,5778,4808,1897,4158, 318,5779,2095,4159,4437,5780,5781, 485,5782, # 5312
938,3941, 553,2680, 116,5783,3942,3667,5784,3545,2681,2783,3438,3344,2820,5785, # 5328
3668,2943,4160,1747,2944,2983,5786,5787, 207,5788,4809,5789,4810,2521,5790,3033, # 5344
890,3669,3943,5791,1878,3798,3439,5792,2186,2358,3440,1652,5793,5794,5795, 941, # 5360
2299, 208,3546,4161,2020, 330,4438,3944,2906,2499,3799,4439,4811,5796,5797,5798, # 5376 #last 512
#Everything below is of no interest for detection purpose
2522,1613,4812,5799,3345,3945,2523,5800,4162,5801,1637,4163,2471,4813,3946,5802, # 5392
2500,3034,3800,5803,5804,2195,4814,5805,2163,5806,5807,5808,5809,5810,5811,5812, # 5408
5813,5814,5815,5816,5817,5818,5819,5820,5821,5822,5823,5824,5825,5826,5827,5828, # 5424
5829,5830,5831,5832,5833,5834,5835,5836,5837,5838,5839,5840,5841,5842,5843,5844, # 5440
5845,5846,5847,5848,5849,5850,5851,5852,5853,5854,5855,5856,5857,5858,5859,5860, # 5456
5861,5862,5863,5864,5865,5866,5867,5868,5869,5870,5871,5872,5873,5874,5875,5876, # 5472
5877,5878,5879,5880,5881,5882,5883,5884,5885,5886,5887,5888,5889,5890,5891,5892, # 5488
5893,5894,5895,5896,5897,5898,5899,5900,5901,5902,5903,5904,5905,5906,5907,5908, # 5504
5909,5910,5911,5912,5913,5914,5915,5916,5917,5918,5919,5920,5921,5922,5923,5924, # 5520
5925,5926,5927,5928,5929,5930,5931,5932,5933,5934,5935,5936,5937,5938,5939,5940, # 5536
5941,5942,5943,5944,5945,5946,5947,5948,5949,5950,5951,5952,5953,5954,5955,5956, # 5552
5957,5958,5959,5960,5961,5962,5963,5964,5965,5966,5967,5968,5969,5970,5971,5972, # 5568
5973,5974,5975,5976,5977,5978,5979,5980,5981,5982,5983,5984,5985,5986,5987,5988, # 5584
5989,5990,5991,5992,5993,5994,5995,5996,5997,5998,5999,6000,6001,6002,6003,6004, # 5600
6005,6006,6007,6008,6009,6010,6011,6012,6013,6014,6015,6016,6017,6018,6019,6020, # 5616
6021,6022,6023,6024,6025,6026,6027,6028,6029,6030,6031,6032,6033,6034,6035,6036, # 5632
6037,6038,6039,6040,6041,6042,6043,6044,6045,6046,6047,6048,6049,6050,6051,6052, # 5648
6053,6054,6055,6056,6057,6058,6059,6060,6061,6062,6063,6064,6065,6066,6067,6068, # 5664
6069,6070,6071,6072,6073,6074,6075,6076,6077,6078,6079,6080,6081,6082,6083,6084, # 5680
6085,6086,6087,6088,6089,6090,6091,6092,6093,6094,6095,6096,6097,6098,6099,6100, # 5696
6101,6102,6103,6104,6105,6106,6107,6108,6109,6110,6111,6112,6113,6114,6115,6116, # 5712
6117,6118,6119,6120,6121,6122,6123,6124,6125,6126,6127,6128,6129,6130,6131,6132, # 5728
6133,6134,6135,6136,6137,6138,6139,6140,6141,6142,6143,6144,6145,6146,6147,6148, # 5744
6149,6150,6151,6152,6153,6154,6155,6156,6157,6158,6159,6160,6161,6162,6163,6164, # 5760
6165,6166,6167,6168,6169,6170,6171,6172,6173,6174,6175,6176,6177,6178,6179,6180, # 5776
6181,6182,6183,6184,6185,6186,6187,6188,6189,6190,6191,6192,6193,6194,6195,6196, # 5792
6197,6198,6199,6200,6201,6202,6203,6204,6205,6206,6207,6208,6209,6210,6211,6212, # 5808
6213,6214,6215,6216,6217,6218,6219,6220,6221,6222,6223,3670,6224,6225,6226,6227, # 5824
6228,6229,6230,6231,6232,6233,6234,6235,6236,6237,6238,6239,6240,6241,6242,6243, # 5840
6244,6245,6246,6247,6248,6249,6250,6251,6252,6253,6254,6255,6256,6257,6258,6259, # 5856
6260,6261,6262,6263,6264,6265,6266,6267,6268,6269,6270,6271,6272,6273,6274,6275, # 5872
6276,6277,6278,6279,6280,6281,6282,6283,6284,6285,4815,6286,6287,6288,6289,6290, # 5888
6291,6292,4816,6293,6294,6295,6296,6297,6298,6299,6300,6301,6302,6303,6304,6305, # 5904
6306,6307,6308,6309,6310,6311,4817,4818,6312,6313,6314,6315,6316,6317,6318,4819, # 5920
6319,6320,6321,6322,6323,6324,6325,6326,6327,6328,6329,6330,6331,6332,6333,6334, # 5936
6335,6336,6337,4820,6338,6339,6340,6341,6342,6343,6344,6345,6346,6347,6348,6349, # 5952
6350,6351,6352,6353,6354,6355,6356,6357,6358,6359,6360,6361,6362,6363,6364,6365, # 5968
6366,6367,6368,6369,6370,6371,6372,6373,6374,6375,6376,6377,6378,6379,6380,6381, # 5984
6382,6383,6384,6385,6386,6387,6388,6389,6390,6391,6392,6393,6394,6395,6396,6397, # 6000
6398,6399,6400,6401,6402,6403,6404,6405,6406,6407,6408,6409,6410,3441,6411,6412, # 6016
6413,6414,6415,6416,6417,6418,6419,6420,6421,6422,6423,6424,6425,4440,6426,6427, # 6032
6428,6429,6430,6431,6432,6433,6434,6435,6436,6437,6438,6439,6440,6441,6442,6443, # 6048
6444,6445,6446,6447,6448,6449,6450,6451,6452,6453,6454,4821,6455,6456,6457,6458, # 6064
6459,6460,6461,6462,6463,6464,6465,6466,6467,6468,6469,6470,6471,6472,6473,6474, # 6080
6475,6476,6477,3947,3948,6478,6479,6480,6481,3272,4441,6482,6483,6484,6485,4442, # 6096
6486,6487,6488,6489,6490,6491,6492,6493,6494,6495,6496,4822,6497,6498,6499,6500, # 6112
6501,6502,6503,6504,6505,6506,6507,6508,6509,6510,6511,6512,6513,6514,6515,6516, # 6128
6517,6518,6519,6520,6521,6522,6523,6524,6525,6526,6527,6528,6529,6530,6531,6532, # 6144
6533,6534,6535,6536,6537,6538,6539,6540,6541,6542,6543,6544,6545,6546,6547,6548, # 6160
6549,6550,6551,6552,6553,6554,6555,6556,2784,6557,4823,6558,6559,6560,6561,6562, # 6176
6563,6564,6565,6566,6567,6568,6569,3949,6570,6571,6572,4824,6573,6574,6575,6576, # 6192
6577,6578,6579,6580,6581,6582,6583,4825,6584,6585,6586,3950,2785,6587,6588,6589, # 6208
6590,6591,6592,6593,6594,6595,6596,6597,6598,6599,6600,6601,6602,6603,6604,6605, # 6224
6606,6607,6608,6609,6610,6611,6612,4826,6613,6614,6615,4827,6616,6617,6618,6619, # 6240
6620,6621,6622,6623,6624,6625,4164,6626,6627,6628,6629,6630,6631,6632,6633,6634, # 6256
3547,6635,4828,6636,6637,6638,6639,6640,6641,6642,3951,2984,6643,6644,6645,6646, # 6272
6647,6648,6649,4165,6650,4829,6651,6652,4830,6653,6654,6655,6656,6657,6658,6659, # 6288
6660,6661,6662,4831,6663,6664,6665,6666,6667,6668,6669,6670,6671,4166,6672,4832, # 6304
3952,6673,6674,6675,6676,4833,6677,6678,6679,4167,6680,6681,6682,3198,6683,6684, # 6320
6685,6686,6687,6688,6689,6690,6691,6692,6693,6694,6695,6696,6697,4834,6698,6699, # 6336
6700,6701,6702,6703,6704,6705,6706,6707,6708,6709,6710,6711,6712,6713,6714,6715, # 6352
6716,6717,6718,6719,6720,6721,6722,6723,6724,6725,6726,6727,6728,6729,6730,6731, # 6368
6732,6733,6734,4443,6735,6736,6737,6738,6739,6740,6741,6742,6743,6744,6745,4444, # 6384
6746,6747,6748,6749,6750,6751,6752,6753,6754,6755,6756,6757,6758,6759,6760,6761, # 6400
6762,6763,6764,6765,6766,6767,6768,6769,6770,6771,6772,6773,6774,6775,6776,6777, # 6416
6778,6779,6780,6781,4168,6782,6783,3442,6784,6785,6786,6787,6788,6789,6790,6791, # 6432
4169,6792,6793,6794,6795,6796,6797,6798,6799,6800,6801,6802,6803,6804,6805,6806, # 6448
6807,6808,6809,6810,6811,4835,6812,6813,6814,4445,6815,6816,4446,6817,6818,6819, # 6464
6820,6821,6822,6823,6824,6825,6826,6827,6828,6829,6830,6831,6832,6833,6834,6835, # 6480
3548,6836,6837,6838,6839,6840,6841,6842,6843,6844,6845,6846,4836,6847,6848,6849, # 6496
6850,6851,6852,6853,6854,3953,6855,6856,6857,6858,6859,6860,6861,6862,6863,6864, # 6512
6865,6866,6867,6868,6869,6870,6871,6872,6873,6874,6875,6876,6877,3199,6878,6879, # 6528
6880,6881,6882,4447,6883,6884,6885,6886,6887,6888,6889,6890,6891,6892,6893,6894, # 6544
6895,6896,6897,6898,6899,6900,6901,6902,6903,6904,4170,6905,6906,6907,6908,6909, # 6560
6910,6911,6912,6913,6914,6915,6916,6917,6918,6919,6920,6921,6922,6923,6924,6925, # 6576
6926,6927,4837,6928,6929,6930,6931,6932,6933,6934,6935,6936,3346,6937,6938,4838, # 6592
6939,6940,6941,4448,6942,6943,6944,6945,6946,4449,6947,6948,6949,6950,6951,6952, # 6608
6953,6954,6955,6956,6957,6958,6959,6960,6961,6962,6963,6964,6965,6966,6967,6968, # 6624
6969,6970,6971,6972,6973,6974,6975,6976,6977,6978,6979,6980,6981,6982,6983,6984, # 6640
6985,6986,6987,6988,6989,6990,6991,6992,6993,6994,3671,6995,6996,6997,6998,4839, # 6656
6999,7000,7001,7002,3549,7003,7004,7005,7006,7007,7008,7009,7010,7011,7012,7013, # 6672
7014,7015,7016,7017,7018,7019,7020,7021,7022,7023,7024,7025,7026,7027,7028,7029, # 6688
7030,4840,7031,7032,7033,7034,7035,7036,7037,7038,4841,7039,7040,7041,7042,7043, # 6704
7044,7045,7046,7047,7048,7049,7050,7051,7052,7053,7054,7055,7056,7057,7058,7059, # 6720
7060,7061,7062,7063,7064,7065,7066,7067,7068,7069,7070,2985,7071,7072,7073,7074, # 6736
7075,7076,7077,7078,7079,7080,4842,7081,7082,7083,7084,7085,7086,7087,7088,7089, # 6752
7090,7091,7092,7093,7094,7095,7096,7097,7098,7099,7100,7101,7102,7103,7104,7105, # 6768
7106,7107,7108,7109,7110,7111,7112,7113,7114,7115,7116,7117,7118,4450,7119,7120, # 6784
7121,7122,7123,7124,7125,7126,7127,7128,7129,7130,7131,7132,7133,7134,7135,7136, # 6800
7137,7138,7139,7140,7141,7142,7143,4843,7144,7145,7146,7147,7148,7149,7150,7151, # 6816
7152,7153,7154,7155,7156,7157,7158,7159,7160,7161,7162,7163,7164,7165,7166,7167, # 6832
7168,7169,7170,7171,7172,7173,7174,7175,7176,7177,7178,7179,7180,7181,7182,7183, # 6848
7184,7185,7186,7187,7188,4171,4172,7189,7190,7191,7192,7193,7194,7195,7196,7197, # 6864
7198,7199,7200,7201,7202,7203,7204,7205,7206,7207,7208,7209,7210,7211,7212,7213, # 6880
7214,7215,7216,7217,7218,7219,7220,7221,7222,7223,7224,7225,7226,7227,7228,7229, # 6896
7230,7231,7232,7233,7234,7235,7236,7237,7238,7239,7240,7241,7242,7243,7244,7245, # 6912
7246,7247,7248,7249,7250,7251,7252,7253,7254,7255,7256,7257,7258,7259,7260,7261, # 6928
7262,7263,7264,7265,7266,7267,7268,7269,7270,7271,7272,7273,7274,7275,7276,7277, # 6944
7278,7279,7280,7281,7282,7283,7284,7285,7286,7287,7288,7289,7290,7291,7292,7293, # 6960
7294,7295,7296,4844,7297,7298,7299,7300,7301,7302,7303,7304,7305,7306,7307,7308, # 6976
7309,7310,7311,7312,7313,7314,7315,7316,4451,7317,7318,7319,7320,7321,7322,7323, # 6992
7324,7325,7326,7327,7328,7329,7330,7331,7332,7333,7334,7335,7336,7337,7338,7339, # 7008
7340,7341,7342,7343,7344,7345,7346,7347,7348,7349,7350,7351,7352,7353,4173,7354, # 7024
7355,4845,7356,7357,7358,7359,7360,7361,7362,7363,7364,7365,7366,7367,7368,7369, # 7040
7370,7371,7372,7373,7374,7375,7376,7377,7378,7379,7380,7381,7382,7383,7384,7385, # 7056
7386,7387,7388,4846,7389,7390,7391,7392,7393,7394,7395,7396,7397,7398,7399,7400, # 7072
7401,7402,7403,7404,7405,3672,7406,7407,7408,7409,7410,7411,7412,7413,7414,7415, # 7088
7416,7417,7418,7419,7420,7421,7422,7423,7424,7425,7426,7427,7428,7429,7430,7431, # 7104
7432,7433,7434,7435,7436,7437,7438,7439,7440,7441,7442,7443,7444,7445,7446,7447, # 7120
7448,7449,7450,7451,7452,7453,4452,7454,3200,7455,7456,7457,7458,7459,7460,7461, # 7136
7462,7463,7464,7465,7466,7467,7468,7469,7470,7471,7472,7473,7474,4847,7475,7476, # 7152
7477,3133,7478,7479,7480,7481,7482,7483,7484,7485,7486,7487,7488,7489,7490,7491, # 7168
7492,7493,7494,7495,7496,7497,7498,7499,7500,7501,7502,3347,7503,7504,7505,7506, # 7184
7507,7508,7509,7510,7511,7512,7513,7514,7515,7516,7517,7518,7519,7520,7521,4848, # 7200
7522,7523,7524,7525,7526,7527,7528,7529,7530,7531,7532,7533,7534,7535,7536,7537, # 7216
7538,7539,7540,7541,7542,7543,7544,7545,7546,7547,7548,7549,3801,4849,7550,7551, # 7232
7552,7553,7554,7555,7556,7557,7558,7559,7560,7561,7562,7563,7564,7565,7566,7567, # 7248
7568,7569,3035,7570,7571,7572,7573,7574,7575,7576,7577,7578,7579,7580,7581,7582, # 7264
7583,7584,7585,7586,7587,7588,7589,7590,7591,7592,7593,7594,7595,7596,7597,7598, # 7280
7599,7600,7601,7602,7603,7604,7605,7606,7607,7608,7609,7610,7611,7612,7613,7614, # 7296
7615,7616,4850,7617,7618,3802,7619,7620,7621,7622,7623,7624,7625,7626,7627,7628, # 7312
7629,7630,7631,7632,4851,7633,7634,7635,7636,7637,7638,7639,7640,7641,7642,7643, # 7328
7644,7645,7646,7647,7648,7649,7650,7651,7652,7653,7654,7655,7656,7657,7658,7659, # 7344
7660,7661,7662,7663,7664,7665,7666,7667,7668,7669,7670,4453,7671,7672,7673,7674, # 7360
7675,7676,7677,7678,7679,7680,7681,7682,7683,7684,7685,7686,7687,7688,7689,7690, # 7376
7691,7692,7693,7694,7695,7696,7697,3443,7698,7699,7700,7701,7702,4454,7703,7704, # 7392
7705,7706,7707,7708,7709,7710,7711,7712,7713,2472,7714,7715,7716,7717,7718,7719, # 7408
7720,7721,7722,7723,7724,7725,7726,7727,7728,7729,7730,7731,3954,7732,7733,7734, # 7424
7735,7736,7737,7738,7739,7740,7741,7742,7743,7744,7745,7746,7747,7748,7749,7750, # 7440
3134,7751,7752,4852,7753,7754,7755,4853,7756,7757,7758,7759,7760,4174,7761,7762, # 7456
7763,7764,7765,7766,7767,7768,7769,7770,7771,7772,7773,7774,7775,7776,7777,7778, # 7472
7779,7780,7781,7782,7783,7784,7785,7786,7787,7788,7789,7790,7791,7792,7793,7794, # 7488
7795,7796,7797,7798,7799,7800,7801,7802,7803,7804,7805,4854,7806,7807,7808,7809, # 7504
7810,7811,7812,7813,7814,7815,7816,7817,7818,7819,7820,7821,7822,7823,7824,7825, # 7520
4855,7826,7827,7828,7829,7830,7831,7832,7833,7834,7835,7836,7837,7838,7839,7840, # 7536
7841,7842,7843,7844,7845,7846,7847,3955,7848,7849,7850,7851,7852,7853,7854,7855, # 7552
7856,7857,7858,7859,7860,3444,7861,7862,7863,7864,7865,7866,7867,7868,7869,7870, # 7568
7871,7872,7873,7874,7875,7876,7877,7878,7879,7880,7881,7882,7883,7884,7885,7886, # 7584
7887,7888,7889,7890,7891,4175,7892,7893,7894,7895,7896,4856,4857,7897,7898,7899, # 7600
7900,2598,7901,7902,7903,7904,7905,7906,7907,7908,4455,7909,7910,7911,7912,7913, # 7616
7914,3201,7915,7916,7917,7918,7919,7920,7921,4858,7922,7923,7924,7925,7926,7927, # 7632
7928,7929,7930,7931,7932,7933,7934,7935,7936,7937,7938,7939,7940,7941,7942,7943, # 7648
7944,7945,7946,7947,7948,7949,7950,7951,7952,7953,7954,7955,7956,7957,7958,7959, # 7664
7960,7961,7962,7963,7964,7965,7966,7967,7968,7969,7970,7971,7972,7973,7974,7975, # 7680
7976,7977,7978,7979,7980,7981,4859,7982,7983,7984,7985,7986,7987,7988,7989,7990, # 7696
7991,7992,7993,7994,7995,7996,4860,7997,7998,7999,8000,8001,8002,8003,8004,8005, # 7712
8006,8007,8008,8009,8010,8011,8012,8013,8014,8015,8016,4176,8017,8018,8019,8020, # 7728
8021,8022,8023,4861,8024,8025,8026,8027,8028,8029,8030,8031,8032,8033,8034,8035, # 7744
8036,4862,4456,8037,8038,8039,8040,4863,8041,8042,8043,8044,8045,8046,8047,8048, # 7760
8049,8050,8051,8052,8053,8054,8055,8056,8057,8058,8059,8060,8061,8062,8063,8064, # 7776
8065,8066,8067,8068,8069,8070,8071,8072,8073,8074,8075,8076,8077,8078,8079,8080, # 7792
8081,8082,8083,8084,8085,8086,8087,8088,8089,8090,8091,8092,8093,8094,8095,8096, # 7808
8097,8098,8099,4864,4177,8100,8101,8102,8103,8104,8105,8106,8107,8108,8109,8110, # 7824
8111,8112,8113,8114,8115,8116,8117,8118,8119,8120,4178,8121,8122,8123,8124,8125, # 7840
8126,8127,8128,8129,8130,8131,8132,8133,8134,8135,8136,8137,8138,8139,8140,8141, # 7856
8142,8143,8144,8145,4865,4866,8146,8147,8148,8149,8150,8151,8152,8153,8154,8155, # 7872
8156,8157,8158,8159,8160,8161,8162,8163,8164,8165,4179,8166,8167,8168,8169,8170, # 7888
8171,8172,8173,8174,8175,8176,8177,8178,8179,8180,8181,4457,8182,8183,8184,8185, # 7904
8186,8187,8188,8189,8190,8191,8192,8193,8194,8195,8196,8197,8198,8199,8200,8201, # 7920
8202,8203,8204,8205,8206,8207,8208,8209,8210,8211,8212,8213,8214,8215,8216,8217, # 7936
8218,8219,8220,8221,8222,8223,8224,8225,8226,8227,8228,8229,8230,8231,8232,8233, # 7952
8234,8235,8236,8237,8238,8239,8240,8241,8242,8243,8244,8245,8246,8247,8248,8249, # 7968
8250,8251,8252,8253,8254,8255,8256,3445,8257,8258,8259,8260,8261,8262,4458,8263, # 7984
8264,8265,8266,8267,8268,8269,8270,8271,8272,4459,8273,8274,8275,8276,3550,8277, # 8000
8278,8279,8280,8281,8282,8283,8284,8285,8286,8287,8288,8289,4460,8290,8291,8292, # 8016
8293,8294,8295,8296,8297,8298,8299,8300,8301,8302,8303,8304,8305,8306,8307,4867, # 8032
8308,8309,8310,8311,8312,3551,8313,8314,8315,8316,8317,8318,8319,8320,8321,8322, # 8048
8323,8324,8325,8326,4868,8327,8328,8329,8330,8331,8332,8333,8334,8335,8336,8337, # 8064
8338,8339,8340,8341,8342,8343,8344,8345,8346,8347,8348,8349,8350,8351,8352,8353, # 8080
8354,8355,8356,8357,8358,8359,8360,8361,8362,8363,4869,4461,8364,8365,8366,8367, # 8096
8368,8369,8370,4870,8371,8372,8373,8374,8375,8376,8377,8378,8379,8380,8381,8382, # 8112
8383,8384,8385,8386,8387,8388,8389,8390,8391,8392,8393,8394,8395,8396,8397,8398, # 8128
8399,8400,8401,8402,8403,8404,8405,8406,8407,8408,8409,8410,4871,8411,8412,8413, # 8144
8414,8415,8416,8417,8418,8419,8420,8421,8422,4462,8423,8424,8425,8426,8427,8428, # 8160
8429,8430,8431,8432,8433,2986,8434,8435,8436,8437,8438,8439,8440,8441,8442,8443, # 8176
8444,8445,8446,8447,8448,8449,8450,8451,8452,8453,8454,8455,8456,8457,8458,8459, # 8192
8460,8461,8462,8463,8464,8465,8466,8467,8468,8469,8470,8471,8472,8473,8474,8475, # 8208
8476,8477,8478,4180,8479,8480,8481,8482,8483,8484,8485,8486,8487,8488,8489,8490, # 8224
8491,8492,8493,8494,8495,8496,8497,8498,8499,8500,8501,8502,8503,8504,8505,8506, # 8240
8507,8508,8509,8510,8511,8512,8513,8514,8515,8516,8517,8518,8519,8520,8521,8522, # 8256
8523,8524,8525,8526,8527,8528,8529,8530,8531,8532,8533,8534,8535,8536,8537,8538, # 8272
8539,8540,8541,8542,8543,8544,8545,8546,8547,8548,8549,8550,8551,8552,8553,8554, # 8288
8555,8556,8557,8558,8559,8560,8561,8562,8563,8564,4872,8565,8566,8567,8568,8569, # 8304
8570,8571,8572,8573,4873,8574,8575,8576,8577,8578,8579,8580,8581,8582,8583,8584, # 8320
8585,8586,8587,8588,8589,8590,8591,8592,8593,8594,8595,8596,8597,8598,8599,8600, # 8336
8601,8602,8603,8604,8605,3803,8606,8607,8608,8609,8610,8611,8612,8613,4874,3804, # 8352
8614,8615,8616,8617,8618,8619,8620,8621,3956,8622,8623,8624,8625,8626,8627,8628, # 8368
8629,8630,8631,8632,8633,8634,8635,8636,8637,8638,2865,8639,8640,8641,8642,8643, # 8384
8644,8645,8646,8647,8648,8649,8650,8651,8652,8653,8654,8655,8656,4463,8657,8658, # 8400
8659,4875,4876,8660,8661,8662,8663,8664,8665,8666,8667,8668,8669,8670,8671,8672, # 8416
8673,8674,8675,8676,8677,8678,8679,8680,8681,4464,8682,8683,8684,8685,8686,8687, # 8432
8688,8689,8690,8691,8692,8693,8694,8695,8696,8697,8698,8699,8700,8701,8702,8703, # 8448
8704,8705,8706,8707,8708,8709,2261,8710,8711,8712,8713,8714,8715,8716,8717,8718, # 8464
8719,8720,8721,8722,8723,8724,8725,8726,8727,8728,8729,8730,8731,8732,8733,4181, # 8480
8734,8735,8736,8737,8738,8739,8740,8741,8742,8743,8744,8745,8746,8747,8748,8749, # 8496
8750,8751,8752,8753,8754,8755,8756,8757,8758,8759,8760,8761,8762,8763,4877,8764, # 8512
8765,8766,8767,8768,8769,8770,8771,8772,8773,8774,8775,8776,8777,8778,8779,8780, # 8528
8781,8782,8783,8784,8785,8786,8787,8788,4878,8789,4879,8790,8791,8792,4880,8793, # 8544
8794,8795,8796,8797,8798,8799,8800,8801,4881,8802,8803,8804,8805,8806,8807,8808, # 8560
8809,8810,8811,8812,8813,8814,8815,3957,8816,8817,8818,8819,8820,8821,8822,8823, # 8576
8824,8825,8826,8827,8828,8829,8830,8831,8832,8833,8834,8835,8836,8837,8838,8839, # 8592
8840,8841,8842,8843,8844,8845,8846,8847,4882,8848,8849,8850,8851,8852,8853,8854, # 8608
8855,8856,8857,8858,8859,8860,8861,8862,8863,8864,8865,8866,8867,8868,8869,8870, # 8624
8871,8872,8873,8874,8875,8876,8877,8878,8879,8880,8881,8882,8883,8884,3202,8885, # 8640
8886,8887,8888,8889,8890,8891,8892,8893,8894,8895,8896,8897,8898,8899,8900,8901, # 8656
8902,8903,8904,8905,8906,8907,8908,8909,8910,8911,8912,8913,8914,8915,8916,8917, # 8672
8918,8919,8920,8921,8922,8923,8924,4465,8925,8926,8927,8928,8929,8930,8931,8932, # 8688
4883,8933,8934,8935,8936,8937,8938,8939,8940,8941,8942,8943,2214,8944,8945,8946, # 8704
8947,8948,8949,8950,8951,8952,8953,8954,8955,8956,8957,8958,8959,8960,8961,8962, # 8720
8963,8964,8965,4884,8966,8967,8968,8969,8970,8971,8972,8973,8974,8975,8976,8977, # 8736
8978,8979,8980,8981,8982,8983,8984,8985,8986,8987,8988,8989,8990,8991,8992,4885, # 8752
8993,8994,8995,8996,8997,8998,8999,9000,9001,9002,9003,9004,9005,9006,9007,9008, # 8768
9009,9010,9011,9012,9013,9014,9015,9016,9017,9018,9019,9020,9021,4182,9022,9023, # 8784
9024,9025,9026,9027,9028,9029,9030,9031,9032,9033,9034,9035,9036,9037,9038,9039, # 8800
9040,9041,9042,9043,9044,9045,9046,9047,9048,9049,9050,9051,9052,9053,9054,9055, # 8816
9056,9057,9058,9059,9060,9061,9062,9063,4886,9064,9065,9066,9067,9068,9069,4887, # 8832
9070,9071,9072,9073,9074,9075,9076,9077,9078,9079,9080,9081,9082,9083,9084,9085, # 8848
9086,9087,9088,9089,9090,9091,9092,9093,9094,9095,9096,9097,9098,9099,9100,9101, # 8864
9102,9103,9104,9105,9106,9107,9108,9109,9110,9111,9112,9113,9114,9115,9116,9117, # 8880
9118,9119,9120,9121,9122,9123,9124,9125,9126,9127,9128,9129,9130,9131,9132,9133, # 8896
9134,9135,9136,9137,9138,9139,9140,9141,3958,9142,9143,9144,9145,9146,9147,9148, # 8912
9149,9150,9151,4888,9152,9153,9154,9155,9156,9157,9158,9159,9160,9161,9162,9163, # 8928
9164,9165,9166,9167,9168,9169,9170,9171,9172,9173,9174,9175,4889,9176,9177,9178, # 8944
9179,9180,9181,9182,9183,9184,9185,9186,9187,9188,9189,9190,9191,9192,9193,9194, # 8960
9195,9196,9197,9198,9199,9200,9201,9202,9203,4890,9204,9205,9206,9207,9208,9209, # 8976
9210,9211,9212,9213,9214,9215,9216,9217,9218,9219,9220,9221,9222,4466,9223,9224, # 8992
9225,9226,9227,9228,9229,9230,9231,9232,9233,9234,9235,9236,9237,9238,9239,9240, # 9008
9241,9242,9243,9244,9245,4891,9246,9247,9248,9249,9250,9251,9252,9253,9254,9255, # 9024
9256,9257,4892,9258,9259,9260,9261,4893,4894,9262,9263,9264,9265,9266,9267,9268, # 9040
9269,9270,9271,9272,9273,4467,9274,9275,9276,9277,9278,9279,9280,9281,9282,9283, # 9056
9284,9285,3673,9286,9287,9288,9289,9290,9291,9292,9293,9294,9295,9296,9297,9298, # 9072
9299,9300,9301,9302,9303,9304,9305,9306,9307,9308,9309,9310,9311,9312,9313,9314, # 9088
9315,9316,9317,9318,9319,9320,9321,9322,4895,9323,9324,9325,9326,9327,9328,9329, # 9104
9330,9331,9332,9333,9334,9335,9336,9337,9338,9339,9340,9341,9342,9343,9344,9345, # 9120
9346,9347,4468,9348,9349,9350,9351,9352,9353,9354,9355,9356,9357,9358,9359,9360, # 9136
9361,9362,9363,9364,9365,9366,9367,9368,9369,9370,9371,9372,9373,4896,9374,4469, # 9152
9375,9376,9377,9378,9379,4897,9380,9381,9382,9383,9384,9385,9386,9387,9388,9389, # 9168
9390,9391,9392,9393,9394,9395,9396,9397,9398,9399,9400,9401,9402,9403,9404,9405, # 9184
9406,4470,9407,2751,9408,9409,3674,3552,9410,9411,9412,9413,9414,9415,9416,9417, # 9200
9418,9419,9420,9421,4898,9422,9423,9424,9425,9426,9427,9428,9429,3959,9430,9431, # 9216
9432,9433,9434,9435,9436,4471,9437,9438,9439,9440,9441,9442,9443,9444,9445,9446, # 9232
9447,9448,9449,9450,3348,9451,9452,9453,9454,9455,9456,9457,9458,9459,9460,9461, # 9248
9462,9463,9464,9465,9466,9467,9468,9469,9470,9471,9472,4899,9473,9474,9475,9476, # 9264
9477,4900,9478,9479,9480,9481,9482,9483,9484,9485,9486,9487,9488,3349,9489,9490, # 9280
9491,9492,9493,9494,9495,9496,9497,9498,9499,9500,9501,9502,9503,9504,9505,9506, # 9296
9507,9508,9509,9510,9511,9512,9513,9514,9515,9516,9517,9518,9519,9520,4901,9521, # 9312
9522,9523,9524,9525,9526,4902,9527,9528,9529,9530,9531,9532,9533,9534,9535,9536, # 9328
9537,9538,9539,9540,9541,9542,9543,9544,9545,9546,9547,9548,9549,9550,9551,9552, # 9344
9553,9554,9555,9556,9557,9558,9559,9560,9561,9562,9563,9564,9565,9566,9567,9568, # 9360
9569,9570,9571,9572,9573,9574,9575,9576,9577,9578,9579,9580,9581,9582,9583,9584, # 9376
3805,9585,9586,9587,9588,9589,9590,9591,9592,9593,9594,9595,9596,9597,9598,9599, # 9392
9600,9601,9602,4903,9603,9604,9605,9606,9607,4904,9608,9609,9610,9611,9612,9613, # 9408
9614,4905,9615,9616,9617,9618,9619,9620,9621,9622,9623,9624,9625,9626,9627,9628, # 9424
9629,9630,9631,9632,4906,9633,9634,9635,9636,9637,9638,9639,9640,9641,9642,9643, # 9440
4907,9644,9645,9646,9647,9648,9649,9650,9651,9652,9653,9654,9655,9656,9657,9658, # 9456
9659,9660,9661,9662,9663,9664,9665,9666,9667,9668,9669,9670,9671,9672,4183,9673, # 9472
9674,9675,9676,9677,4908,9678,9679,9680,9681,4909,9682,9683,9684,9685,9686,9687, # 9488
9688,9689,9690,4910,9691,9692,9693,3675,9694,9695,9696,2945,9697,9698,9699,9700, # 9504
9701,9702,9703,9704,9705,4911,9706,9707,9708,9709,9710,9711,9712,9713,9714,9715, # 9520
9716,9717,9718,9719,9720,9721,9722,9723,9724,9725,9726,9727,9728,9729,9730,9731, # 9536
9732,9733,9734,9735,4912,9736,9737,9738,9739,9740,4913,9741,9742,9743,9744,9745, # 9552
9746,9747,9748,9749,9750,9751,9752,9753,9754,9755,9756,9757,9758,4914,9759,9760, # 9568
9761,9762,9763,9764,9765,9766,9767,9768,9769,9770,9771,9772,9773,9774,9775,9776, # 9584
9777,9778,9779,9780,9781,9782,4915,9783,9784,9785,9786,9787,9788,9789,9790,9791, # 9600
9792,9793,4916,9794,9795,9796,9797,9798,9799,9800,9801,9802,9803,9804,9805,9806, # 9616
9807,9808,9809,9810,9811,9812,9813,9814,9815,9816,9817,9818,9819,9820,9821,9822, # 9632
9823,9824,9825,9826,9827,9828,9829,9830,9831,9832,9833,9834,9835,9836,9837,9838, # 9648
9839,9840,9841,9842,9843,9844,9845,9846,9847,9848,9849,9850,9851,9852,9853,9854, # 9664
9855,9856,9857,9858,9859,9860,9861,9862,9863,9864,9865,9866,9867,9868,4917,9869, # 9680
9870,9871,9872,9873,9874,9875,9876,9877,9878,9879,9880,9881,9882,9883,9884,9885, # 9696
9886,9887,9888,9889,9890,9891,9892,4472,9893,9894,9895,9896,9897,3806,9898,9899, # 9712
9900,9901,9902,9903,9904,9905,9906,9907,9908,9909,9910,9911,9912,9913,9914,4918, # 9728
9915,9916,9917,4919,9918,9919,9920,9921,4184,9922,9923,9924,9925,9926,9927,9928, # 9744
9929,9930,9931,9932,9933,9934,9935,9936,9937,9938,9939,9940,9941,9942,9943,9944, # 9760
9945,9946,4920,9947,9948,9949,9950,9951,9952,9953,9954,9955,4185,9956,9957,9958, # 9776
9959,9960,9961,9962,9963,9964,9965,4921,9966,9967,9968,4473,9969,9970,9971,9972, # 9792
9973,9974,9975,9976,9977,4474,9978,9979,9980,9981,9982,9983,9984,9985,9986,9987, # 9808
9988,9989,9990,9991,9992,9993,9994,9995,9996,9997,9998,9999,10000,10001,10002,10003, # 9824
10004,10005,10006,10007,10008,10009,10010,10011,10012,10013,10014,10015,10016,10017,10018,10019, # 9840
10020,10021,4922,10022,4923,10023,10024,10025,10026,10027,10028,10029,10030,10031,10032,10033, # 9856
10034,10035,10036,10037,10038,10039,10040,10041,10042,10043,10044,10045,10046,10047,10048,4924, # 9872
10049,10050,10051,10052,10053,10054,10055,10056,10057,10058,10059,10060,10061,10062,10063,10064, # 9888
10065,10066,10067,10068,10069,10070,10071,10072,10073,10074,10075,10076,10077,10078,10079,10080, # 9904
10081,10082,10083,10084,10085,10086,10087,4475,10088,10089,10090,10091,10092,10093,10094,10095, # 9920
10096,10097,4476,10098,10099,10100,10101,10102,10103,10104,10105,10106,10107,10108,10109,10110, # 9936
10111,2174,10112,10113,10114,10115,10116,10117,10118,10119,10120,10121,10122,10123,10124,10125, # 9952
10126,10127,10128,10129,10130,10131,10132,10133,10134,10135,10136,10137,10138,10139,10140,3807, # 9968
4186,4925,10141,10142,10143,10144,10145,10146,10147,4477,4187,10148,10149,10150,10151,10152, # 9984
10153,4188,10154,10155,10156,10157,10158,10159,10160,10161,4926,10162,10163,10164,10165,10166, #10000
10167,10168,10169,10170,10171,10172,10173,10174,10175,10176,10177,10178,10179,10180,10181,10182, #10016
10183,10184,10185,10186,10187,10188,10189,10190,10191,10192,3203,10193,10194,10195,10196,10197, #10032
10198,10199,10200,4478,10201,10202,10203,10204,4479,10205,10206,10207,10208,10209,10210,10211, #10048
10212,10213,10214,10215,10216,10217,10218,10219,10220,10221,10222,10223,10224,10225,10226,10227, #10064
10228,10229,10230,10231,10232,10233,10234,4927,10235,10236,10237,10238,10239,10240,10241,10242, #10080
10243,10244,10245,10246,10247,10248,10249,10250,10251,10252,10253,10254,10255,10256,10257,10258, #10096
10259,10260,10261,10262,10263,10264,10265,10266,10267,10268,10269,10270,10271,10272,10273,4480, #10112
4928,4929,10274,10275,10276,10277,10278,10279,10280,10281,10282,10283,10284,10285,10286,10287, #10128
10288,10289,10290,10291,10292,10293,10294,10295,10296,10297,10298,10299,10300,10301,10302,10303, #10144
10304,10305,10306,10307,10308,10309,10310,10311,10312,10313,10314,10315,10316,10317,10318,10319, #10160
10320,10321,10322,10323,10324,10325,10326,10327,10328,10329,10330,10331,10332,10333,10334,4930, #10176
10335,10336,10337,10338,10339,10340,10341,10342,4931,10343,10344,10345,10346,10347,10348,10349, #10192
10350,10351,10352,10353,10354,10355,3088,10356,2786,10357,10358,10359,10360,4189,10361,10362, #10208
10363,10364,10365,10366,10367,10368,10369,10370,10371,10372,10373,10374,10375,4932,10376,10377, #10224
10378,10379,10380,10381,10382,10383,10384,10385,10386,10387,10388,10389,10390,10391,10392,4933, #10240
10393,10394,10395,4934,10396,10397,10398,10399,10400,10401,10402,10403,10404,10405,10406,10407, #10256
10408,10409,10410,10411,10412,3446,10413,10414,10415,10416,10417,10418,10419,10420,10421,10422, #10272
10423,4935,10424,10425,10426,10427,10428,10429,10430,4936,10431,10432,10433,10434,10435,10436, #10288
10437,10438,10439,10440,10441,10442,10443,4937,10444,10445,10446,10447,4481,10448,10449,10450, #10304
10451,10452,10453,10454,10455,10456,10457,10458,10459,10460,10461,10462,10463,10464,10465,10466, #10320
10467,10468,10469,10470,10471,10472,10473,10474,10475,10476,10477,10478,10479,10480,10481,10482, #10336
10483,10484,10485,10486,10487,10488,10489,10490,10491,10492,10493,10494,10495,10496,10497,10498, #10352
10499,10500,10501,10502,10503,10504,10505,4938,10506,10507,10508,10509,10510,2552,10511,10512, #10368
10513,10514,10515,10516,3447,10517,10518,10519,10520,10521,10522,10523,10524,10525,10526,10527, #10384
10528,10529,10530,10531,10532,10533,10534,10535,10536,10537,10538,10539,10540,10541,10542,10543, #10400
4482,10544,4939,10545,10546,10547,10548,10549,10550,10551,10552,10553,10554,10555,10556,10557, #10416
10558,10559,10560,10561,10562,10563,10564,10565,10566,10567,3676,4483,10568,10569,10570,10571, #10432
10572,3448,10573,10574,10575,10576,10577,10578,10579,10580,10581,10582,10583,10584,10585,10586, #10448
10587,10588,10589,10590,10591,10592,10593,10594,10595,10596,10597,10598,10599,10600,10601,10602, #10464
10603,10604,10605,10606,10607,10608,10609,10610,10611,10612,10613,10614,10615,10616,10617,10618, #10480
10619,10620,10621,10622,10623,10624,10625,10626,10627,4484,10628,10629,10630,10631,10632,4940, #10496
10633,10634,10635,10636,10637,10638,10639,10640,10641,10642,10643,10644,10645,10646,10647,10648, #10512
10649,10650,10651,10652,10653,10654,10655,10656,4941,10657,10658,10659,2599,10660,10661,10662, #10528
10663,10664,10665,10666,3089,10667,10668,10669,10670,10671,10672,10673,10674,10675,10676,10677, #10544
10678,10679,10680,4942,10681,10682,10683,10684,10685,10686,10687,10688,10689,10690,10691,10692, #10560
10693,10694,10695,10696,10697,4485,10698,10699,10700,10701,10702,10703,10704,4943,10705,3677, #10576
10706,10707,10708,10709,10710,10711,10712,4944,10713,10714,10715,10716,10717,10718,10719,10720, #10592
10721,10722,10723,10724,10725,10726,10727,10728,4945,10729,10730,10731,10732,10733,10734,10735, #10608
10736,10737,10738,10739,10740,10741,10742,10743,10744,10745,10746,10747,10748,10749,10750,10751, #10624
10752,10753,10754,10755,10756,10757,10758,10759,10760,10761,4946,10762,10763,10764,10765,10766, #10640
10767,4947,4948,10768,10769,10770,10771,10772,10773,10774,10775,10776,10777,10778,10779,10780, #10656
10781,10782,10783,10784,10785,10786,10787,10788,10789,10790,10791,10792,10793,10794,10795,10796, #10672
10797,10798,10799,10800,10801,10802,10803,10804,10805,10806,10807,10808,10809,10810,10811,10812, #10688
10813,10814,10815,10816,10817,10818,10819,10820,10821,10822,10823,10824,10825,10826,10827,10828, #10704
10829,10830,10831,10832,10833,10834,10835,10836,10837,10838,10839,10840,10841,10842,10843,10844, #10720
10845,10846,10847,10848,10849,10850,10851,10852,10853,10854,10855,10856,10857,10858,10859,10860, #10736
10861,10862,10863,10864,10865,10866,10867,10868,10869,10870,10871,10872,10873,10874,10875,10876, #10752
10877,10878,4486,10879,10880,10881,10882,10883,10884,10885,4949,10886,10887,10888,10889,10890, #10768
10891,10892,10893,10894,10895,10896,10897,10898,10899,10900,10901,10902,10903,10904,10905,10906, #10784
10907,10908,10909,10910,10911,10912,10913,10914,10915,10916,10917,10918,10919,4487,10920,10921, #10800
10922,10923,10924,10925,10926,10927,10928,10929,10930,10931,10932,4950,10933,10934,10935,10936, #10816
10937,10938,10939,10940,10941,10942,10943,10944,10945,10946,10947,10948,10949,4488,10950,10951, #10832
10952,10953,10954,10955,10956,10957,10958,10959,4190,10960,10961,10962,10963,10964,10965,10966, #10848
10967,10968,10969,10970,10971,10972,10973,10974,10975,10976,10977,10978,10979,10980,10981,10982, #10864
10983,10984,10985,10986,10987,10988,10989,10990,10991,10992,10993,10994,10995,10996,10997,10998, #10880
10999,11000,11001,11002,11003,11004,11005,11006,3960,11007,11008,11009,11010,11011,11012,11013, #10896
11014,11015,11016,11017,11018,11019,11020,11021,11022,11023,11024,11025,11026,11027,11028,11029, #10912
11030,11031,11032,4951,11033,11034,11035,11036,11037,11038,11039,11040,11041,11042,11043,11044, #10928
11045,11046,11047,4489,11048,11049,11050,11051,4952,11052,11053,11054,11055,11056,11057,11058, #10944
4953,11059,11060,11061,11062,11063,11064,11065,11066,11067,11068,11069,11070,11071,4954,11072, #10960
11073,11074,11075,11076,11077,11078,11079,11080,11081,11082,11083,11084,11085,11086,11087,11088, #10976
11089,11090,11091,11092,11093,11094,11095,11096,11097,11098,11099,11100,11101,11102,11103,11104, #10992
11105,11106,11107,11108,11109,11110,11111,11112,11113,11114,11115,3808,11116,11117,11118,11119, #11008
11120,11121,11122,11123,11124,11125,11126,11127,11128,11129,11130,11131,11132,11133,11134,4955, #11024
11135,11136,11137,11138,11139,11140,11141,11142,11143,11144,11145,11146,11147,11148,11149,11150, #11040
11151,11152,11153,11154,11155,11156,11157,11158,11159,11160,11161,4956,11162,11163,11164,11165, #11056
11166,11167,11168,11169,11170,11171,11172,11173,11174,11175,11176,11177,11178,11179,11180,4957, #11072
11181,11182,11183,11184,11185,11186,4958,11187,11188,11189,11190,11191,11192,11193,11194,11195, #11088
11196,11197,11198,11199,11200,3678,11201,11202,11203,11204,11205,11206,4191,11207,11208,11209, #11104
11210,11211,11212,11213,11214,11215,11216,11217,11218,11219,11220,11221,11222,11223,11224,11225, #11120
11226,11227,11228,11229,11230,11231,11232,11233,11234,11235,11236,11237,11238,11239,11240,11241, #11136
11242,11243,11244,11245,11246,11247,11248,11249,11250,11251,4959,11252,11253,11254,11255,11256, #11152
11257,11258,11259,11260,11261,11262,11263,11264,11265,11266,11267,11268,11269,11270,11271,11272, #11168
11273,11274,11275,11276,11277,11278,11279,11280,11281,11282,11283,11284,11285,11286,11287,11288, #11184
11289,11290,11291,11292,11293,11294,11295,11296,11297,11298,11299,11300,11301,11302,11303,11304, #11200
11305,11306,11307,11308,11309,11310,11311,11312,11313,11314,3679,11315,11316,11317,11318,4490, #11216
11319,11320,11321,11322,11323,11324,11325,11326,11327,11328,11329,11330,11331,11332,11333,11334, #11232
11335,11336,11337,11338,11339,11340,11341,11342,11343,11344,11345,11346,11347,4960,11348,11349, #11248
11350,11351,11352,11353,11354,11355,11356,11357,11358,11359,11360,11361,11362,11363,11364,11365, #11264
11366,11367,11368,11369,11370,11371,11372,11373,11374,11375,11376,11377,3961,4961,11378,11379, #11280
11380,11381,11382,11383,11384,11385,11386,11387,11388,11389,11390,11391,11392,11393,11394,11395, #11296
11396,11397,4192,11398,11399,11400,11401,11402,11403,11404,11405,11406,11407,11408,11409,11410, #11312
11411,4962,11412,11413,11414,11415,11416,11417,11418,11419,11420,11421,11422,11423,11424,11425, #11328
11426,11427,11428,11429,11430,11431,11432,11433,11434,11435,11436,11437,11438,11439,11440,11441, #11344
11442,11443,11444,11445,11446,11447,11448,11449,11450,11451,11452,11453,11454,11455,11456,11457, #11360
11458,11459,11460,11461,11462,11463,11464,11465,11466,11467,11468,11469,4963,11470,11471,4491, #11376
11472,11473,11474,11475,4964,11476,11477,11478,11479,11480,11481,11482,11483,11484,11485,11486, #11392
11487,11488,11489,11490,11491,11492,4965,11493,11494,11495,11496,11497,11498,11499,11500,11501, #11408
11502,11503,11504,11505,11506,11507,11508,11509,11510,11511,11512,11513,11514,11515,11516,11517, #11424
11518,11519,11520,11521,11522,11523,11524,11525,11526,11527,11528,11529,3962,11530,11531,11532, #11440
11533,11534,11535,11536,11537,11538,11539,11540,11541,11542,11543,11544,11545,11546,11547,11548, #11456
11549,11550,11551,11552,11553,11554,11555,11556,11557,11558,11559,11560,11561,11562,11563,11564, #11472
4193,4194,11565,11566,11567,11568,11569,11570,11571,11572,11573,11574,11575,11576,11577,11578, #11488
11579,11580,11581,11582,11583,11584,11585,11586,11587,11588,11589,11590,11591,4966,4195,11592, #11504
11593,11594,11595,11596,11597,11598,11599,11600,11601,11602,11603,11604,3090,11605,11606,11607, #11520
11608,11609,11610,4967,11611,11612,11613,11614,11615,11616,11617,11618,11619,11620,11621,11622, #11536
11623,11624,11625,11626,11627,11628,11629,11630,11631,11632,11633,11634,11635,11636,11637,11638, #11552
11639,11640,11641,11642,11643,11644,11645,11646,11647,11648,11649,11650,11651,11652,11653,11654, #11568
11655,11656,11657,11658,11659,11660,11661,11662,11663,11664,11665,11666,11667,11668,11669,11670, #11584
11671,11672,11673,11674,4968,11675,11676,11677,11678,11679,11680,11681,11682,11683,11684,11685, #11600
11686,11687,11688,11689,11690,11691,11692,11693,3809,11694,11695,11696,11697,11698,11699,11700, #11616
11701,11702,11703,11704,11705,11706,11707,11708,11709,11710,11711,11712,11713,11714,11715,11716, #11632
11717,11718,3553,11719,11720,11721,11722,11723,11724,11725,11726,11727,11728,11729,11730,4969, #11648
11731,11732,11733,11734,11735,11736,11737,11738,11739,11740,4492,11741,11742,11743,11744,11745, #11664
11746,11747,11748,11749,11750,11751,11752,4970,11753,11754,11755,11756,11757,11758,11759,11760, #11680
11761,11762,11763,11764,11765,11766,11767,11768,11769,11770,11771,11772,11773,11774,11775,11776, #11696
11777,11778,11779,11780,11781,11782,11783,11784,11785,11786,11787,11788,11789,11790,4971,11791, #11712
11792,11793,11794,11795,11796,11797,4972,11798,11799,11800,11801,11802,11803,11804,11805,11806, #11728
11807,11808,11809,11810,4973,11811,11812,11813,11814,11815,11816,11817,11818,11819,11820,11821, #11744
11822,11823,11824,11825,11826,11827,11828,11829,11830,11831,11832,11833,11834,3680,3810,11835, #11760
11836,4974,11837,11838,11839,11840,11841,11842,11843,11844,11845,11846,11847,11848,11849,11850, #11776
11851,11852,11853,11854,11855,11856,11857,11858,11859,11860,11861,11862,11863,11864,11865,11866, #11792
11867,11868,11869,11870,11871,11872,11873,11874,11875,11876,11877,11878,11879,11880,11881,11882, #11808
11883,11884,4493,11885,11886,11887,11888,11889,11890,11891,11892,11893,11894,11895,11896,11897, #11824
11898,11899,11900,11901,11902,11903,11904,11905,11906,11907,11908,11909,11910,11911,11912,11913, #11840
11914,11915,4975,11916,11917,11918,11919,11920,11921,11922,11923,11924,11925,11926,11927,11928, #11856
11929,11930,11931,11932,11933,11934,11935,11936,11937,11938,11939,11940,11941,11942,11943,11944, #11872
11945,11946,11947,11948,11949,4976,11950,11951,11952,11953,11954,11955,11956,11957,11958,11959, #11888
11960,11961,11962,11963,11964,11965,11966,11967,11968,11969,11970,11971,11972,11973,11974,11975, #11904
11976,11977,11978,11979,11980,11981,11982,11983,11984,11985,11986,11987,4196,11988,11989,11990, #11920
11991,11992,4977,11993,11994,11995,11996,11997,11998,11999,12000,12001,12002,12003,12004,12005, #11936
12006,12007,12008,12009,12010,12011,12012,12013,12014,12015,12016,12017,12018,12019,12020,12021, #11952
12022,12023,12024,12025,12026,12027,12028,12029,12030,12031,12032,12033,12034,12035,12036,12037, #11968
12038,12039,12040,12041,12042,12043,12044,12045,12046,12047,12048,12049,12050,12051,12052,12053, #11984
12054,12055,12056,12057,12058,12059,12060,12061,4978,12062,12063,12064,12065,12066,12067,12068, #12000
12069,12070,12071,12072,12073,12074,12075,12076,12077,12078,12079,12080,12081,12082,12083,12084, #12016
12085,12086,12087,12088,12089,12090,12091,12092,12093,12094,12095,12096,12097,12098,12099,12100, #12032
12101,12102,12103,12104,12105,12106,12107,12108,12109,12110,12111,12112,12113,12114,12115,12116, #12048
12117,12118,12119,12120,12121,12122,12123,4979,12124,12125,12126,12127,12128,4197,12129,12130, #12064
12131,12132,12133,12134,12135,12136,12137,12138,12139,12140,12141,12142,12143,12144,12145,12146, #12080
12147,12148,12149,12150,12151,12152,12153,12154,4980,12155,12156,12157,12158,12159,12160,4494, #12096
12161,12162,12163,12164,3811,12165,12166,12167,12168,12169,4495,12170,12171,4496,12172,12173, #12112
12174,12175,12176,3812,12177,12178,12179,12180,12181,12182,12183,12184,12185,12186,12187,12188, #12128
12189,12190,12191,12192,12193,12194,12195,12196,12197,12198,12199,12200,12201,12202,12203,12204, #12144
12205,12206,12207,12208,12209,12210,12211,12212,12213,12214,12215,12216,12217,12218,12219,12220, #12160
12221,4981,12222,12223,12224,12225,12226,12227,12228,12229,12230,12231,12232,12233,12234,12235, #12176
4982,12236,12237,12238,12239,12240,12241,12242,12243,12244,12245,4983,12246,12247,12248,12249, #12192
4984,12250,12251,12252,12253,12254,12255,12256,12257,12258,12259,12260,12261,12262,12263,12264, #12208
4985,12265,4497,12266,12267,12268,12269,12270,12271,12272,12273,12274,12275,12276,12277,12278, #12224
12279,12280,12281,12282,12283,12284,12285,12286,12287,4986,12288,12289,12290,12291,12292,12293, #12240
12294,12295,12296,2473,12297,12298,12299,12300,12301,12302,12303,12304,12305,12306,12307,12308, #12256
12309,12310,12311,12312,12313,12314,12315,12316,12317,12318,12319,3963,12320,12321,12322,12323, #12272
12324,12325,12326,12327,12328,12329,12330,12331,12332,4987,12333,12334,12335,12336,12337,12338, #12288
12339,12340,12341,12342,12343,12344,12345,12346,12347,12348,12349,12350,12351,12352,12353,12354, #12304
12355,12356,12357,12358,12359,3964,12360,12361,12362,12363,12364,12365,12366,12367,12368,12369, #12320
12370,3965,12371,12372,12373,12374,12375,12376,12377,12378,12379,12380,12381,12382,12383,12384, #12336
12385,12386,12387,12388,12389,12390,12391,12392,12393,12394,12395,12396,12397,12398,12399,12400, #12352
12401,12402,12403,12404,12405,12406,12407,12408,4988,12409,12410,12411,12412,12413,12414,12415, #12368
12416,12417,12418,12419,12420,12421,12422,12423,12424,12425,12426,12427,12428,12429,12430,12431, #12384
12432,12433,12434,12435,12436,12437,12438,3554,12439,12440,12441,12442,12443,12444,12445,12446, #12400
12447,12448,12449,12450,12451,12452,12453,12454,12455,12456,12457,12458,12459,12460,12461,12462, #12416
12463,12464,4989,12465,12466,12467,12468,12469,12470,12471,12472,12473,12474,12475,12476,12477, #12432
12478,12479,12480,4990,12481,12482,12483,12484,12485,12486,12487,12488,12489,4498,12490,12491, #12448
12492,12493,12494,12495,12496,12497,12498,12499,12500,12501,12502,12503,12504,12505,12506,12507, #12464
12508,12509,12510,12511,12512,12513,12514,12515,12516,12517,12518,12519,12520,12521,12522,12523, #12480
12524,12525,12526,12527,12528,12529,12530,12531,12532,12533,12534,12535,12536,12537,12538,12539, #12496
12540,12541,12542,12543,12544,12545,12546,12547,12548,12549,12550,12551,4991,12552,12553,12554, #12512
12555,12556,12557,12558,12559,12560,12561,12562,12563,12564,12565,12566,12567,12568,12569,12570, #12528
12571,12572,12573,12574,12575,12576,12577,12578,3036,12579,12580,12581,12582,12583,3966,12584, #12544
12585,12586,12587,12588,12589,12590,12591,12592,12593,12594,12595,12596,12597,12598,12599,12600, #12560
12601,12602,12603,12604,12605,12606,12607,12608,12609,12610,12611,12612,12613,12614,12615,12616, #12576
12617,12618,12619,12620,12621,12622,12623,12624,12625,12626,12627,12628,12629,12630,12631,12632, #12592
12633,12634,12635,12636,12637,12638,12639,12640,12641,12642,12643,12644,12645,12646,4499,12647, #12608
12648,12649,12650,12651,12652,12653,12654,12655,12656,12657,12658,12659,12660,12661,12662,12663, #12624
12664,12665,12666,12667,12668,12669,12670,12671,12672,12673,12674,12675,12676,12677,12678,12679, #12640
12680,12681,12682,12683,12684,12685,12686,12687,12688,12689,12690,12691,12692,12693,12694,12695, #12656
12696,12697,12698,4992,12699,12700,12701,12702,12703,12704,12705,12706,12707,12708,12709,12710, #12672
12711,12712,12713,12714,12715,12716,12717,12718,12719,12720,12721,12722,12723,12724,12725,12726, #12688
12727,12728,12729,12730,12731,12732,12733,12734,12735,12736,12737,12738,12739,12740,12741,12742, #12704
12743,12744,12745,12746,12747,12748,12749,12750,12751,12752,12753,12754,12755,12756,12757,12758, #12720
12759,12760,12761,12762,12763,12764,12765,12766,12767,12768,12769,12770,12771,12772,12773,12774, #12736
12775,12776,12777,12778,4993,2175,12779,12780,12781,12782,12783,12784,12785,12786,4500,12787, #12752
12788,12789,12790,12791,12792,12793,12794,12795,12796,12797,12798,12799,12800,12801,12802,12803, #12768
12804,12805,12806,12807,12808,12809,12810,12811,12812,12813,12814,12815,12816,12817,12818,12819, #12784
12820,12821,12822,12823,12824,12825,12826,4198,3967,12827,12828,12829,12830,12831,12832,12833, #12800
12834,12835,12836,12837,12838,12839,12840,12841,12842,12843,12844,12845,12846,12847,12848,12849, #12816
12850,12851,12852,12853,12854,12855,12856,12857,12858,12859,12860,12861,4199,12862,12863,12864, #12832
12865,12866,12867,12868,12869,12870,12871,12872,12873,12874,12875,12876,12877,12878,12879,12880, #12848
12881,12882,12883,12884,12885,12886,12887,4501,12888,12889,12890,12891,12892,12893,12894,12895, #12864
12896,12897,12898,12899,12900,12901,12902,12903,12904,12905,12906,12907,12908,12909,12910,12911, #12880
12912,4994,12913,12914,12915,12916,12917,12918,12919,12920,12921,12922,12923,12924,12925,12926, #12896
12927,12928,12929,12930,12931,12932,12933,12934,12935,12936,12937,12938,12939,12940,12941,12942, #12912
12943,12944,12945,12946,12947,12948,12949,12950,12951,12952,12953,12954,12955,12956,1772,12957, #12928
12958,12959,12960,12961,12962,12963,12964,12965,12966,12967,12968,12969,12970,12971,12972,12973, #12944
12974,12975,12976,12977,12978,12979,12980,12981,12982,12983,12984,12985,12986,12987,12988,12989, #12960
12990,12991,12992,12993,12994,12995,12996,12997,4502,12998,4503,12999,13000,13001,13002,13003, #12976
4504,13004,13005,13006,13007,13008,13009,13010,13011,13012,13013,13014,13015,13016,13017,13018, #12992
13019,13020,13021,13022,13023,13024,13025,13026,13027,13028,13029,3449,13030,13031,13032,13033, #13008
13034,13035,13036,13037,13038,13039,13040,13041,13042,13043,13044,13045,13046,13047,13048,13049, #13024
13050,13051,13052,13053,13054,13055,13056,13057,13058,13059,13060,13061,13062,13063,13064,13065, #13040
13066,13067,13068,13069,13070,13071,13072,13073,13074,13075,13076,13077,13078,13079,13080,13081, #13056
13082,13083,13084,13085,13086,13087,13088,13089,13090,13091,13092,13093,13094,13095,13096,13097, #13072
13098,13099,13100,13101,13102,13103,13104,13105,13106,13107,13108,13109,13110,13111,13112,13113, #13088
13114,13115,13116,13117,13118,3968,13119,4995,13120,13121,13122,13123,13124,13125,13126,13127, #13104
4505,13128,13129,13130,13131,13132,13133,13134,4996,4506,13135,13136,13137,13138,13139,4997, #13120
13140,13141,13142,13143,13144,13145,13146,13147,13148,13149,13150,13151,13152,13153,13154,13155, #13136
13156,13157,13158,13159,4998,13160,13161,13162,13163,13164,13165,13166,13167,13168,13169,13170, #13152
13171,13172,13173,13174,13175,13176,4999,13177,13178,13179,13180,13181,13182,13183,13184,13185, #13168
13186,13187,13188,13189,13190,13191,13192,13193,13194,13195,13196,13197,13198,13199,13200,13201, #13184
13202,13203,13204,13205,13206,5000,13207,13208,13209,13210,13211,13212,13213,13214,13215,13216, #13200
13217,13218,13219,13220,13221,13222,13223,13224,13225,13226,13227,4200,5001,13228,13229,13230, #13216
13231,13232,13233,13234,13235,13236,13237,13238,13239,13240,3969,13241,13242,13243,13244,3970, #13232
13245,13246,13247,13248,13249,13250,13251,13252,13253,13254,13255,13256,13257,13258,13259,13260, #13248
13261,13262,13263,13264,13265,13266,13267,13268,3450,13269,13270,13271,13272,13273,13274,13275, #13264
13276,5002,13277,13278,13279,13280,13281,13282,13283,13284,13285,13286,13287,13288,13289,13290, #13280
13291,13292,13293,13294,13295,13296,13297,13298,13299,13300,13301,13302,3813,13303,13304,13305, #13296
13306,13307,13308,13309,13310,13311,13312,13313,13314,13315,13316,13317,13318,13319,13320,13321, #13312
13322,13323,13324,13325,13326,13327,13328,4507,13329,13330,13331,13332,13333,13334,13335,13336, #13328
13337,13338,13339,13340,13341,5003,13342,13343,13344,13345,13346,13347,13348,13349,13350,13351, #13344
13352,13353,13354,13355,13356,13357,13358,13359,13360,13361,13362,13363,13364,13365,13366,13367, #13360
5004,13368,13369,13370,13371,13372,13373,13374,13375,13376,13377,13378,13379,13380,13381,13382, #13376
13383,13384,13385,13386,13387,13388,13389,13390,13391,13392,13393,13394,13395,13396,13397,13398, #13392
13399,13400,13401,13402,13403,13404,13405,13406,13407,13408,13409,13410,13411,13412,13413,13414, #13408
13415,13416,13417,13418,13419,13420,13421,13422,13423,13424,13425,13426,13427,13428,13429,13430, #13424
13431,13432,4508,13433,13434,13435,4201,13436,13437,13438,13439,13440,13441,13442,13443,13444, #13440
13445,13446,13447,13448,13449,13450,13451,13452,13453,13454,13455,13456,13457,5005,13458,13459, #13456
13460,13461,13462,13463,13464,13465,13466,13467,13468,13469,13470,4509,13471,13472,13473,13474, #13472
13475,13476,13477,13478,13479,13480,13481,13482,13483,13484,13485,13486,13487,13488,13489,13490, #13488
13491,13492,13493,13494,13495,13496,13497,13498,13499,13500,13501,13502,13503,13504,13505,13506, #13504
13507,13508,13509,13510,13511,13512,13513,13514,13515,13516,13517,13518,13519,13520,13521,13522, #13520
13523,13524,13525,13526,13527,13528,13529,13530,13531,13532,13533,13534,13535,13536,13537,13538, #13536
13539,13540,13541,13542,13543,13544,13545,13546,13547,13548,13549,13550,13551,13552,13553,13554, #13552
13555,13556,13557,13558,13559,13560,13561,13562,13563,13564,13565,13566,13567,13568,13569,13570, #13568
13571,13572,13573,13574,13575,13576,13577,13578,13579,13580,13581,13582,13583,13584,13585,13586, #13584
13587,13588,13589,13590,13591,13592,13593,13594,13595,13596,13597,13598,13599,13600,13601,13602, #13600
13603,13604,13605,13606,13607,13608,13609,13610,13611,13612,13613,13614,13615,13616,13617,13618, #13616
13619,13620,13621,13622,13623,13624,13625,13626,13627,13628,13629,13630,13631,13632,13633,13634, #13632
13635,13636,13637,13638,13639,13640,13641,13642,5006,13643,13644,13645,13646,13647,13648,13649, #13648
13650,13651,5007,13652,13653,13654,13655,13656,13657,13658,13659,13660,13661,13662,13663,13664, #13664
13665,13666,13667,13668,13669,13670,13671,13672,13673,13674,13675,13676,13677,13678,13679,13680, #13680
13681,13682,13683,13684,13685,13686,13687,13688,13689,13690,13691,13692,13693,13694,13695,13696, #13696
13697,13698,13699,13700,13701,13702,13703,13704,13705,13706,13707,13708,13709,13710,13711,13712, #13712
13713,13714,13715,13716,13717,13718,13719,13720,13721,13722,13723,13724,13725,13726,13727,13728, #13728
13729,13730,13731,13732,13733,13734,13735,13736,13737,13738,13739,13740,13741,13742,13743,13744, #13744
13745,13746,13747,13748,13749,13750,13751,13752,13753,13754,13755,13756,13757,13758,13759,13760, #13760
13761,13762,13763,13764,13765,13766,13767,13768,13769,13770,13771,13772,13773,13774,3273,13775, #13776
13776,13777,13778,13779,13780,13781,13782,13783,13784,13785,13786,13787,13788,13789,13790,13791, #13792
13792,13793,13794,13795,13796,13797,13798,13799,13800,13801,13802,13803,13804,13805,13806,13807, #13808
13808,13809,13810,13811,13812,13813,13814,13815,13816,13817,13818,13819,13820,13821,13822,13823, #13824
13824,13825,13826,13827,13828,13829,13830,13831,13832,13833,13834,13835,13836,13837,13838,13839, #13840
13840,13841,13842,13843,13844,13845,13846,13847,13848,13849,13850,13851,13852,13853,13854,13855, #13856
13856,13857,13858,13859,13860,13861,13862,13863,13864,13865,13866,13867,13868,13869,13870,13871, #13872
13872,13873,13874,13875,13876,13877,13878,13879,13880,13881,13882,13883,13884,13885,13886,13887, #13888
13888,13889,13890,13891,13892,13893,13894,13895,13896,13897,13898,13899,13900,13901,13902,13903, #13904
13904,13905,13906,13907,13908,13909,13910,13911,13912,13913,13914,13915,13916,13917,13918,13919, #13920
13920,13921,13922,13923,13924,13925,13926,13927,13928,13929,13930,13931,13932,13933,13934,13935, #13936
13936,13937,13938,13939,13940,13941,13942,13943,13944,13945,13946,13947,13948,13949,13950,13951, #13952
13952,13953,13954,13955,13956,13957,13958,13959,13960,13961,13962,13963,13964,13965,13966,13967, #13968
13968,13969,13970,13971,13972) #13973
+41
View File
@@ -0,0 +1,41 @@
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from mbcharsetprober import MultiByteCharSetProber
from codingstatemachine import CodingStateMachine
from chardistribution import Big5DistributionAnalysis
from mbcssm import Big5SMModel
class Big5Prober(MultiByteCharSetProber):
def __init__(self):
MultiByteCharSetProber.__init__(self)
self._mCodingSM = CodingStateMachine(Big5SMModel)
self._mDistributionAnalyzer = Big5DistributionAnalysis()
self.reset()
def get_charset_name(self):
return "Big5"
+200
View File
@@ -0,0 +1,200 @@
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
import constants
from euctwfreq import EUCTWCharToFreqOrder, EUCTW_TABLE_SIZE, EUCTW_TYPICAL_DISTRIBUTION_RATIO
from euckrfreq import EUCKRCharToFreqOrder, EUCKR_TABLE_SIZE, EUCKR_TYPICAL_DISTRIBUTION_RATIO
from gb2312freq import GB2312CharToFreqOrder, GB2312_TABLE_SIZE, GB2312_TYPICAL_DISTRIBUTION_RATIO
from big5freq import Big5CharToFreqOrder, BIG5_TABLE_SIZE, BIG5_TYPICAL_DISTRIBUTION_RATIO
from jisfreq import JISCharToFreqOrder, JIS_TABLE_SIZE, JIS_TYPICAL_DISTRIBUTION_RATIO
ENOUGH_DATA_THRESHOLD = 1024
SURE_YES = 0.99
SURE_NO = 0.01
class CharDistributionAnalysis:
def __init__(self):
self._mCharToFreqOrder = None # Mapping table to get frequency order from char order (get from GetOrder())
self._mTableSize = None # Size of above table
self._mTypicalDistributionRatio = None # This is a constant value which varies from language to language, used in calculating confidence. See http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html for further detail.
self.reset()
def reset(self):
"""reset analyser, clear any state"""
self._mDone = constants.False # If this flag is set to constants.True, detection is done and conclusion has been made
self._mTotalChars = 0 # Total characters encountered
self._mFreqChars = 0 # The number of characters whose frequency order is less than 512
def feed(self, aStr, aCharLen):
"""feed a character with known length"""
if aCharLen == 2:
# we only care about 2-bytes character in our distribution analysis
order = self.get_order(aStr)
else:
order = -1
if order >= 0:
self._mTotalChars += 1
# order is valid
if order < self._mTableSize:
if 512 > self._mCharToFreqOrder[order]:
self._mFreqChars += 1
def get_confidence(self):
"""return confidence based on existing data"""
# if we didn't receive any character in our consideration range, return negative answer
if self._mTotalChars <= 0:
return SURE_NO
if self._mTotalChars != self._mFreqChars:
r = self._mFreqChars / ((self._mTotalChars - self._mFreqChars) * self._mTypicalDistributionRatio)
if r < SURE_YES:
return r
# normalize confidence (we don't want to be 100% sure)
return SURE_YES
def got_enough_data(self):
# It is not necessary to receive all data to draw conclusion. For charset detection,
# certain amount of data is enough
return self._mTotalChars > ENOUGH_DATA_THRESHOLD
def get_order(self, aStr):
# We do not handle characters based on the original encoding string, but
# convert this encoding string to a number, here called order.
# This allows multiple encodings of a language to share one frequency table.
return -1
class EUCTWDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = EUCTWCharToFreqOrder
self._mTableSize = EUCTW_TABLE_SIZE
self._mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for euc-TW encoding, we are interested
# first byte range: 0xc4 -- 0xfe
# second byte range: 0xa1 -- 0xfe
# no validation needed here. State machine has done that
if aStr[0] >= '\xC4':
return 94 * (ord(aStr[0]) - 0xC4) + ord(aStr[1]) - 0xA1
else:
return -1
class EUCKRDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = EUCKRCharToFreqOrder
self._mTableSize = EUCKR_TABLE_SIZE
self._mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for euc-KR encoding, we are interested
# first byte range: 0xb0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
# no validation needed here. State machine has done that
if aStr[0] >= '\xB0':
return 94 * (ord(aStr[0]) - 0xB0) + ord(aStr[1]) - 0xA1
else:
return -1;
class GB2312DistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = GB2312CharToFreqOrder
self._mTableSize = GB2312_TABLE_SIZE
self._mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for GB2312 encoding, we are interested
# first byte range: 0xb0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
# no validation needed here. State machine has done that
if (aStr[0] >= '\xB0') and (aStr[1] >= '\xA1'):
return 94 * (ord(aStr[0]) - 0xB0) + ord(aStr[1]) - 0xA1
else:
return -1;
class Big5DistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = Big5CharToFreqOrder
self._mTableSize = BIG5_TABLE_SIZE
self._mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for big5 encoding, we are interested
# first byte range: 0xa4 -- 0xfe
# second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
# no validation needed here. State machine has done that
if aStr[0] >= '\xA4':
if aStr[1] >= '\xA1':
return 157 * (ord(aStr[0]) - 0xA4) + ord(aStr[1]) - 0xA1 + 63
else:
return 157 * (ord(aStr[0]) - 0xA4) + ord(aStr[1]) - 0x40
else:
return -1
class SJISDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = JISCharToFreqOrder
self._mTableSize = JIS_TABLE_SIZE
self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for sjis encoding, we are interested
# first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
# second byte range: 0x40 -- 0x7e, 0x81 -- oxfe
# no validation needed here. State machine has done that
if (aStr[0] >= '\x81') and (aStr[0] <= '\x9F'):
order = 188 * (ord(aStr[0]) - 0x81)
elif (aStr[0] >= '\xE0') and (aStr[0] <= '\xEF'):
order = 188 * (ord(aStr[0]) - 0xE0 + 31)
else:
return -1;
order = order + ord(aStr[1]) - 0x40
if aStr[1] > '\x7F':
order =- 1
return order
class EUCJPDistributionAnalysis(CharDistributionAnalysis):
def __init__(self):
CharDistributionAnalysis.__init__(self)
self._mCharToFreqOrder = JISCharToFreqOrder
self._mTableSize = JIS_TABLE_SIZE
self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
def get_order(self, aStr):
# for euc-JP encoding, we are interested
# first byte range: 0xa0 -- 0xfe
# second byte range: 0xa1 -- 0xfe
# no validation needed here. State machine has done that
if aStr[0] >= '\xA0':
return 94 * (ord(aStr[0]) - 0xA1) + ord(aStr[1]) - 0xa1
else:
return -1
+96
View File
@@ -0,0 +1,96 @@
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
import constants, sys
from charsetprober import CharSetProber
class CharSetGroupProber(CharSetProber):
def __init__(self):
CharSetProber.__init__(self)
self._mActiveNum = 0
self._mProbers = []
self._mBestGuessProber = None
def reset(self):
CharSetProber.reset(self)
self._mActiveNum = 0
for prober in self._mProbers:
if prober:
prober.reset()
prober.active = constants.True
self._mActiveNum += 1
self._mBestGuessProber = None
def get_charset_name(self):
if not self._mBestGuessProber:
self.get_confidence()
if not self._mBestGuessProber: return None
# self._mBestGuessProber = self._mProbers[0]
return self._mBestGuessProber.get_charset_name()
def feed(self, aBuf):
for prober in self._mProbers:
if not prober: continue
if not prober.active: continue
st = prober.feed(aBuf)
if not st: continue
if st == constants.eFoundIt:
self._mBestGuessProber = prober
return self.get_state()
elif st == constants.eNotMe:
prober.active = constants.False
self._mActiveNum -= 1
if self._mActiveNum <= 0:
self._mState = constants.eNotMe
return self.get_state()
return self.get_state()
def get_confidence(self):
st = self.get_state()
if st == constants.eFoundIt:
return 0.99
elif st == constants.eNotMe:
return 0.01
bestConf = 0.0
self._mBestGuessProber = None
for prober in self._mProbers:
if not prober: continue
if not prober.active:
if constants._debug:
sys.stderr.write(prober.get_charset_name() + ' not active\n')
continue
cf = prober.get_confidence()
if constants._debug:
sys.stderr.write('%s confidence = %s\n' % (prober.get_charset_name(), cf))
if bestConf < cf:
bestConf = cf
self._mBestGuessProber = prober
if not self._mBestGuessProber: return 0.0
return bestConf
# else:
# self._mBestGuessProber = self._mProbers[0]
# return self._mBestGuessProber.get_confidence()
+60
View File
@@ -0,0 +1,60 @@
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Universal charset detector code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 2001
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
# Shy Shalom - original C code
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
import constants, re
class CharSetProber:
def __init__(self):
pass
def reset(self):
self._mState = constants.eDetecting
def get_charset_name(self):
return None
def feed(self, aBuf):
pass
def get_state(self):
return self._mState
def get_confidence(self):
return 0.0
def filter_high_bit_only(self, aBuf):
aBuf = re.sub(r'([\x00-\x7F])+', ' ', aBuf)
return aBuf
def filter_without_english_letters(self, aBuf):
aBuf = re.sub(r'([A-Za-z])+', ' ', aBuf)
return aBuf
def filter_with_english_letters(self, aBuf):
# TODO
return aBuf

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