Added code to strip accents from show names and add as a possible show match

changelog.md

 # Changelog
 
-- * 4be64d5 - 2018-10-21: Release v9.3.98 
+- * c4e7cda - 2018-10-21: Added code to strip accents from show names and add as a possible show match 
+- * e3b3be9 - 2018-10-21: Release v9.3.98 
 - * d5ec001 - 2018-10-21: Fixed issues with matching shows with parsed results when containing accents 
 - * 84de9fe - 2018-10-21: Release v9.3.97 
 - * a5f7b6a - 2018-10-21: Fixed issues with network timezones 

sickrage/core/__init__.py

@@ -343,9 +343,10 @@ class Core(object):
  IntervalTrigger(
  hours=self.config.version_updater_freq
  ),
+ next_run_time=datetime.datetime.now(),
  name=self.version_updater.name,
  id=self.version_updater.name
- ).func()
+ )
 
  # add network timezones updater job
  self.scheduler.add_job(
@@ -353,9 +354,10 @@ class Core(object):
  IntervalTrigger(
  days=1
  ),
+ next_run_time=datetime.datetime.now(),
  name="TZUPDATER",
  id="TZUPDATER"
- ).func()
+ )
 
  # add show updater job
  self.scheduler.add_job(

sickrage/core/caches/name_cache.py

@@ -20,6 +20,7 @@
 from __future__ import unicode_literals
 
 import time
+import unicodedata
 from datetime import datetime, timedelta
 
 from CodernityDB.database import RecordNotFound
@@ -125,6 +126,27 @@ class NameCache(object):
  self.last_update[show.name] = datetime.fromtimestamp(int(time.mktime(datetime.today().timetuple())))
 
  self.clear(show.indexerid)
+
+ show_names = []
  for curSeason in [-1] + get_scene_seasons(show.indexerid):
  for name in list(set(get_scene_exceptions(show.indexerid, season=curSeason) + [show.name])):
- self.put(name, show.indexerid)
+ show_names.append(name)
+
+ # strip accents
+ try:
+ try:
+ name.decode('ascii')
+ except UnicodeEncodeError:
+ pass
+
+ show_names.append(
+ unicodedata.normalize('NFKD', name).encode('ASCII', 'ignore')
+ )
+ show_names.append(
+ unicodedata.normalize('NFKD', name).encode('ASCII', 'ignore').replace("'", " ")
+ )
+ except UnicodeDecodeError:
+ pass
+
+ for show_name in set(show_names):
+ self.put(show_name, show.indexerid)
\ No newline at end of file

sickrage/core/helpers/show_names.py

@@ -21,6 +21,7 @@ from __future__ import unicode_literals
 import fnmatch
 import os
 import re
+import unicodedata
 from datetime import date
 from functools import partial
 
@@ -309,19 +310,30 @@ def allPossibleShowNames(show, season=-1):
  :rtype: list[unicode]
  """
 
- showNames = get_scene_exceptions(show.indexerid, season=season)[:]
- if not showNames: # if we dont have any season specific exceptions fallback to generic exceptions
+ show_names = get_scene_exceptions(show.indexerid, season=season)[:]
+ if not show_names: # if we dont have any season specific exceptions fallback to generic exceptions
  season = -1
- showNames = get_scene_exceptions(show.indexerid, season=season)[:]
+ show_names = get_scene_exceptions(show.indexerid, season=season)[:]
 
  if season in [-1, 1]:
- showNames.append(show.name)
+ show_names.append(show.name)
+
+ try:
+ # strip accents
+ try:
+ show.name.decode('ascii')
+ except UnicodeEncodeError:
+ pass
+ show_names.append(unicodedata.normalize('NFKD', show.name).encode('ASCII', 'ignore'))
+ show_names.append(unicodedata.normalize('NFKD', show.name).encode('ASCII', 'ignore').replace("'", " "))
+ except UnicodeDecodeError:
+ pass
 
  if not show.is_anime:
- newShowNames = []
+ new_show_names = []
  country_list = countryList
  country_list.update(dict(zip(countryList.values(), countryList.keys())))
- for curName in set(showNames):
+ for curName in set(show_names):
  if not curName:
  continue
 
@@ -330,16 +342,16 @@ def allPossibleShowNames(show, season=-1):
  # (and vice versa)
  for curCountry in country_list:
  if curName.endswith(' ' + curCountry):
- newShowNames.append(curName.replace(' ' + curCountry, ' (' + country_list[curCountry] + ')'))
+ new_show_names.append(curName.replace(' ' + curCountry, ' (' + country_list[curCountry] + ')'))
  elif curName.endswith(' (' + curCountry + ')'):
- newShowNames.append(curName.replace(' (' + curCountry + ')', ' (' + country_list[curCountry] + ')'))
+ new_show_names.append(curName.replace(' (' + curCountry + ')', ' (' + country_list[curCountry] + ')'))
 
  # # if we have "Show Name (2013)" this will strip the (2013) show year from the show name
- # newShowNames.append(re.sub('\(\d{4}\)', '', curName))
+ # new_show_names.append(re.sub('\(\d{4}\)', '', curName))
 
- showNames += newShowNames
+ show_names += new_show_names
 
- return showNames
+ return list(set(show_names))
 
 
 def determineReleaseName(dir_name=None, nzb_name=None):

sickrage/core/nameparser/__init__.py

@@ -60,26 +60,38 @@ class NameParser(object):
  def get_show(self, name):
  show = None
  show_id = None
+ show_names = [name]
 
  if not all([name, sickrage.app.showlist]):
  return show, show_id
 
- def cache_lookup(show_name):
- return sickrage.app.name_cache.get(show_name)
+ def cache_lookup(term):
+ return sickrage.app.name_cache.get(term)
 
- def scene_exception_lookup(show_name):
- return get_scene_exception_by_name(show_name)[0]
+ def scene_exception_lookup(term):
+ return get_scene_exception_by_name(term)[0]
 
- def indexer_lookup(show_name):
- show_id1 = int(IndexerApi().searchForShowID(full_sanitizeSceneName(show_name))[2])
- show_id2 = int(srTraktAPI()['search'].query(full_sanitizeSceneName(show_name), 'show')[0].ids['tvdb'])
+ def indexer_lookup(term):
+ show_id1 = int(IndexerApi().searchForShowID(full_sanitizeSceneName(term))[2])
+ show_id2 = int(srTraktAPI()['search'].query(full_sanitizeSceneName(term), 'show')[0].ids['tvdb'])
  return (None, show_id1)[show_id1 == show_id2]
 
- for x in [unicodedata.normalize('NFKD', name).encode('ASCII', 'ignore'), name]:
+ try:
+ # strip accents
+ try:
+ name.decode('ascii')
+ except UnicodeEncodeError:
+ pass
+ show_names.append(unicodedata.normalize('NFKD', name).encode('ASCII', 'ignore'))
+ show_names.append(unicodedata.normalize('NFKD', name).encode('ASCII', 'ignore').replace("'", " "))
+ except UnicodeDecodeError:
+ pass
+
+ for show_name in set(show_names):
  lookup_list = [
- lambda: cache_lookup(x),
- lambda: scene_exception_lookup(x),
- lambda: indexer_lookup(x),
+ lambda: cache_lookup(show_name),
+ lambda: scene_exception_lookup(show_name),
+ lambda: indexer_lookup(show_name),
  ]
 
  # lookup show id
@@ -92,7 +104,7 @@ class NameParser(object):
  if show_id == 0:
  continue
 
- sickrage.app.name_cache.put(x, show_id)
+ sickrage.app.name_cache.put(show_name, show_id)
  if self.validate_show:
  show = findCertainShow(show_id)
  else:
@@ -103,7 +115,7 @@ class NameParser(object):
 
  if show_id is None:
  # ignore show name by caching it with a indexerid of 0
- sickrage.app.name_cache.put(x, 0)
+ sickrage.app.name_cache.put(show_name, 0)
 
  return show, show_id or 0