Compare commits

..
Author SHA1 Message Date
panni fc2208f9e5 bump version 2017-05-05 19:32:12 +02:00
panni 1a4eb366bb add helping indicator to FPS mod; add 30fps 2017-05-05 19:31:43 +02:00
panni b89c64a2c2 add modification management menu 2017-05-05 19:19:34 +02:00
panni 68e8f6e753 don't remove HI by default 2017-05-05 19:11:43 +02:00
panni f15cc4cb3c add offset shifter submod 2017-05-05 19:10:32 +02:00
panni 903273e3ef add advanced submods; add global (non-line) submods; test implementation of ChangeFPS mod 2017-05-05 15:39:18 +02:00
panni 1c9b744d31 move subtitle modification menu to separate file 2017-05-05 14:58:19 +02:00
panni 7c0fb29886 fix init_cache whoopsie 2017-05-05 14:58:06 +02:00
panni 2505a7510c enzyme: incorporate 0.4.2 fixes 2017-05-05 14:44:59 +02:00
panni 0a66db40a2 fix findbetter 2017-05-05 14:30:49 +02:00
panni 6c68893979 add mod.long_description; add remove_last action to subtitle modification menu 2017-05-04 20:10:35 +02:00
panni c512eab0b6 testcommit 2017-05-04 20:00:12 +02:00
panni 3cedd4bd0f try getting plex token from environment by default 2017-05-04 19:33:05 +02:00
panni 0759c5e4c6 add environment debug 2017-05-04 19:31:07 +02:00
panni ad6cf4be79 move config debug to better position; verify readability of log files 2017-05-04 19:15:38 +02:00
panni 23c3899fb2 add fixme 2017-05-04 14:30:25 +02:00
panni 1a6515a660 add platform and os to config debug 2017-05-04 14:20:29 +02:00
panni 58815a7650 use external ip fallback when logs were requested from plex.tv 2017-05-04 14:16:10 +02:00
panni c15ec9fefc disable get_logs when universal plex token is None 2017-05-04 13:49:02 +02:00
panni 0e18d59680 2.0.0.12 2017-05-03 23:12:42 +02:00
panni 2d88efa5b4 add doc 2017-05-03 23:12:26 +02:00
panni b3da7572f3 add PartialWordsAlways to OCR_fixes 2017-05-03 23:11:02 +02:00
panni 099ec4e85d remove debug print; add doc 2017-05-03 23:04:25 +02:00
panni ff88a15c61 reset initialized mods after load 2017-05-03 22:59:47 +02:00
panni 839791b0fa add OCR fixes as default; fix little whoopsie in SubtitleModifications.modify 2017-05-03 22:52:33 +02:00
panni 159a533731 add precompiled patterns to data dict; add more parsed data; add OCR fixes finally 2017-05-03 22:44:54 +02:00
panni fb5835baa4 separate ocr fix data further into line, word, partial 2017-05-03 15:19:52 +02:00
panni a3f05cd597 separat partial and full replace data 2017-05-03 15:16:22 +02:00
28 changed files with 810 additions and 148 deletions

No files matched your search

-1
View File
@@ -24,7 +24,6 @@ import support
import interface
sys.modules["interface"] = interface
from subliminal.cli import MutexLock
from subzero.constants import OS_PLEX_USERAGENT, PERSONAL_MEDIA_IDENTIFIER
from interface.menu import *
from support.plex_media import media_to_videos, get_media_item_ids, scan_videos
+3
View File
@@ -18,3 +18,6 @@ sys.modules["interface.refresh_item"] = refresh_item
import item_details
sys.modules["interface.item_details"] = item_details
import sub_mod
sys.modules["interface.modification"] = sub_mod
+12 -2
View File
@@ -148,24 +148,34 @@ def TriggerStorageMaintenance(randomize=None):
@route(PREFIX + '/get_logs_link')
def GetLogsLink():
if not config.plex_token:
oc = ObjectContainer(title2="Download Logs", no_cache=True, no_history=True,
header="Sorry, feature unavailable",
message="Universal Plex token not available")
return oc
# try getting the link base via the request in context, first, otherwise use the public ip
req_headers = Core.sandbox.context.request.headers
get_external_ip = True
link_base = ""
if "Origin" in req_headers:
link_base = req_headers["Origin"]
Log.Debug("Using origin-based link_base")
get_external_ip = False
elif "Referer" in req_headers:
parsed = urlparse.urlparse(req_headers["Referer"])
link_base = "%s://%s:%s" % (parsed.scheme, parsed.hostname, parsed.port)
Log.Debug("Using referer-based link_base")
get_external_ip = False
else:
if get_external_ip or "plex.tv" in link_base:
ip = Core.networking.http_request("http://www.plexapp.com/ip.php", cacheTime=7200).content.strip()
link_base = "https://%s:32400" % ip
Log.Debug("Using ip-based fallback link_base")
logs_link = "%s%s?X-Plex-Token=%s" % (link_base, PREFIX + '/logs', config.universal_plex_token)
logs_link = "%s%s?X-Plex-Token=%s" % (link_base, PREFIX + '/logs', config.plex_token)
oc = ObjectContainer(title2="Download Logs", no_cache=True, no_history=True,
header="Copy this link and open this in your browser, please",
message=logs_link)
+3 -68
View File
@@ -1,13 +1,11 @@
# coding=utf-8
import os
import traceback
from babelfish import Language
from sub_mod import SubtitleModificationsMenu
from menu_helpers import debounce, SubFolderObjectContainer, default_thumb, add_ignore_options, get_item_task_data, \
set_refresh_menu_state
from subzero.modification import registry as mod_registry
from refresh_item import RefreshItem
from subliminal_patch import PatchedSubtitle as Subtitle
from subzero.constants import PREFIX
from support.config import config
from support.helpers import timestamp, cast_bool, df, get_language
@@ -15,7 +13,7 @@ from support.items import get_item_kind_from_rating_key, get_item, get_current_s
from support.lib import Plex
from support.plex_media import get_plex_metadata, scan_videos
from support.scheduler import scheduler
from support.storage import get_subtitle_storage, save_subtitles
from support.storage import get_subtitle_storage
@route(PREFIX + '/item/{rating_key}/actions')
@@ -139,69 +137,6 @@ def SubtitleOptionsMenu(**kwargs):
return oc
@route(PREFIX + '/item/sub_mods/{rating_key}/{part_id}', force=bool)
@debounce
def SubtitleModificationsMenu(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
language = kwargs["language"]
current_sub, stored_subs, storage = get_current_sub(rating_key, part_id, language)
kwargs.pop("randomize")
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
for identifier, mod in mod_registry.mods.iteritems():
oc.add(DirectoryObject(
key=Callback(SubtitleApplyMod, mod_identifier=identifier, randomize=timestamp(), **kwargs),
title=mod.description
))
oc.add(DirectoryObject(
key=Callback(SubtitleApplyMod, mod_identifier=None, randomize=timestamp(), **kwargs),
title="Restore original version",
summary=u"Currently applied mods: %s" % (", ".join(current_sub.mods) if current_sub.mods else "none")
))
return oc
@route(PREFIX + '/item/sub_add_mod/{rating_key}/{part_id}/{mod_identifier}', force=bool)
@debounce
def SubtitleApplyMod(mod_identifier=None, **kwargs):
if mod_identifier is not None and mod_identifier not in mod_registry.mods:
raise NotImplementedError
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
lang_a2 = kwargs["language"]
item_type = kwargs["item_type"]
language = Language.fromietf(lang_a2)
current_sub, stored_subs, storage = get_current_sub(rating_key, part_id, language)
current_sub.add_mod(mod_identifier)
storage.save(stored_subs)
metadata = get_plex_metadata(rating_key, part_id, item_type)
scanned_parts = scan_videos([metadata], kind="series" if item_type == "episode" else "movie", ignore_all=True)
video, plex_part = scanned_parts.items()[0]
subtitle = Subtitle(language, mods=current_sub.mods)
subtitle.content = current_sub.content
subtitle.plex_media_fps = plex_part.fps
subtitle.page_link = "modify subtitles with: %s" % (", ".join(current_sub.mods) if current_sub.mods else "none")
subtitle.language = language
try:
save_subtitles(scanned_parts, {video: [subtitle]}, mode="m", bare_save=True)
Log.Debug("Modified %s subtitle for: %s:%s with: %s", language.name, rating_key, part_id,
", ".join(current_sub.mods) if current_sub.mods else "none")
except:
Log.Error("Something went wrong when modifying subtitle: %s", traceback.format_exc())
kwargs.pop("randomize")
return SubtitleModificationsMenu(randomize=timestamp(), **kwargs)
@route(PREFIX + '/item/search/{rating_key}/{part_id}', force=bool)
@debounce
def ListAvailableSubsForItemMenu(rating_key=None, part_id=None, title=None, item_title=None, filename=None,
+38 -10
View File
@@ -1,5 +1,7 @@
# coding=utf-8
import logging
import os
import logger
from item_details import ItemDetailsMenu
@@ -147,16 +149,6 @@ def RefreshMissing(randomize=None):
@route(PREFIX + '/ValidatePrefs', enforce_route=True)
def ValidatePrefs():
Core.log.setLevel(logging.DEBUG)
Log.Debug("Validate Prefs called.")
# SZ config debug
Log.Debug("--- SZ Config-Debug ---")
for attr in [
"app_support_path", "data_path", "data_items_path", "plugin_log_path", "server_log_path", "enable_agent",
"enable_channel", "permissions_ok", "missing_permissions", "fs_encoding"]:
Log.Debug("config.%s: %s", attr, getattr(config, attr))
Log.Debug("-----------------------")
# cache the channel state
update_dict = False
@@ -191,6 +183,42 @@ def ValidatePrefs():
Core.log.removeHandler(logger.console_handler)
Log.Debug("Stop logging to console")
Log.Debug("Validate Prefs called.")
# SZ config debug
Log.Debug("--- SZ Config-Debug ---")
for attr in [
"app_support_path", "data_path", "data_items_path", "enable_agent",
"enable_channel", "permissions_ok", "missing_permissions", "fs_encoding"]:
Log.Debug("config.%s: %s", attr, getattr(config, attr))
for attr in ["plugin_log_path", "server_log_path"]:
value = getattr(config, attr)
access = os.access(value, os.R_OK)
if Core.runtime.os == "Windows":
try:
f = open(value, "r")
f.read(1)
f.close()
except:
access = False
Log.Debug("config.%s: %s (accessible: %s)", attr, value, access)
# fixme: check existance of and os access of logs
Log.Debug("Platform: %s", Core.runtime.platform)
Log.Debug("OS: %s", Core.runtime.os)
Log.Debug("----- Environment -----")
for key, value in os.environ.iteritems():
if key.startswith("PLEX"):
if "TOKEN" in key:
outval = "xxxxxxxxxxxxxxxxxxx"
else:
outval = value
Log.Debug("%s: %s", key, outval)
Log.Debug("-----------------------")
Log.Debug("Setting log-level to %s", Prefs["log_level"])
logger.register_logging_handler(DEPENDENCY_MODULE_NAMES, level=Prefs["log_level"])
Core.log.setLevel(logging.getLevelName(Prefs["log_level"]))
+231
View File
@@ -0,0 +1,231 @@
# coding=utf-8
import traceback
import types
from babelfish import Language
from menu_helpers import debounce, SubFolderObjectContainer
from subliminal_patch import PatchedSubtitle as Subtitle
from subzero.modification import registry as mod_registry, SubtitleModifications
from subzero.constants import PREFIX
from support.plex_media import get_plex_metadata, scan_videos
from support.storage import save_subtitles
from support.helpers import timestamp, pad_title
from support.items import get_current_sub
@route(PREFIX + '/item/sub_mods/{rating_key}/{part_id}', force=bool)
@debounce
def SubtitleModificationsMenu(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
language = kwargs["language"]
current_sub, stored_subs, storage = get_current_sub(rating_key, part_id, language)
kwargs.pop("randomize")
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
for identifier, mod in mod_registry.mods.iteritems():
if mod.advanced:
continue
if mod.exclusive and identifier in current_sub.mods:
continue
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=identifier, mode="add", randomize=timestamp(), **kwargs),
title=pad_title(mod.description), summary=mod.long_description or ""
))
fps_mod = SubtitleModifications.get_mod_class("change_FPS")
oc.add(DirectoryObject(
key=Callback(SubtitleFPSModMenu, randomize=timestamp(), **kwargs),
title=pad_title(fps_mod.description), summary=fps_mod.long_description or ""
))
shift_mod = SubtitleModifications.get_mod_class("shift_offset")
oc.add(DirectoryObject(
key=Callback(SubtitleShiftModUnitMenu, randomize=timestamp(), **kwargs),
title=pad_title(shift_mod.description), summary=shift_mod.long_description or ""
))
if current_sub.mods:
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=None, mode="remove_last", randomize=timestamp(), **kwargs),
title=pad_title("Remove last applied mod (%s)" % current_sub.mods[-1]),
summary=u"Currently applied mods: %s" % (", ".join(current_sub.mods) if current_sub.mods else "none")
))
oc.add(DirectoryObject(
key=Callback(SubtitleListMods, randomize=timestamp(), **kwargs),
title=pad_title("Manage applied mods"),
summary=u"Currently applied mods: %s" % (", ".join(current_sub.mods))
))
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=None, mode="clear", randomize=timestamp(), **kwargs),
title=pad_title("Restore original version"),
summary=u"Currently applied mods: %s" % (", ".join(current_sub.mods) if current_sub.mods else "none")
))
return oc
@route(PREFIX + '/item/sub_mod_fps/{rating_key}/{part_id}', force=bool)
@debounce
def SubtitleFPSModMenu(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
item_type = kwargs["item_type"]
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
metadata = get_plex_metadata(rating_key, part_id, item_type)
scanned_parts = scan_videos([metadata], kind="series" if item_type == "episode" else "movie", ignore_all=True)
video, plex_part = scanned_parts.items()[0]
target_fps = plex_part.fps
kwargs.pop("randomize")
for fps in ["23.976", "24.000", "25.000", "29.970", "30.000", "50.000", "59.940", "60.000"]:
if float(fps) == float(target_fps):
continue
if float(fps) > float(target_fps):
indicator = "subs constantly getting faster"
else:
indicator = "subs constantly getting slower"
mod_ident = SubtitleModifications.get_mod_signature("change_FPS", **{"from": fps, "to": target_fps})
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=mod_ident, mode="add", randomize=timestamp(), **kwargs),
title="%s fps -> %s fps (%s)" % (fps, target_fps, indicator)
))
return oc
POSSIBLE_UNITS = (("ms", "milliseconds"), ("s", "seconds"), ("m", "minutes"), ("h", "hours"))
POSSIBLE_UNITS_D = dict(POSSIBLE_UNITS)
@route(PREFIX + '/item/sub_mod_shift_unit/{rating_key}/{part_id}', force=bool)
@debounce
def SubtitleShiftModUnitMenu(**kwargs):
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
kwargs.pop("randomize")
for unit, title in POSSIBLE_UNITS:
oc.add(DirectoryObject(
key=Callback(SubtitleShiftModMenu, unit=unit, randomize=timestamp(), **kwargs),
title="Adjust by %s" % title
))
return oc
@route(PREFIX + '/item/sub_mod_shift/{rating_key}/{part_id}/{unit}', force=bool)
@debounce
def SubtitleShiftModMenu(unit=None, **kwargs):
if unit not in POSSIBLE_UNITS_D:
raise NotImplementedError
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
kwargs.pop("randomize")
rng = []
if unit == "h":
rng = range(-10, 11)
elif unit in ("m", "s"):
rng = range(-59, 60)
elif unit == "ms":
rng = range(-900, 1000, 100)
for i in rng:
if i == 0:
continue
mod_ident = SubtitleModifications.get_mod_signature("shift_offset", **{unit: i})
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=mod_ident, mode="add", randomize=timestamp(), **kwargs),
title="%s %s" % (("%s" if i < 0 else "+%s") % i, unit)
))
return oc
@route(PREFIX + '/item/sub_set_mods/{rating_key}/{part_id}/{mods}/{mode}', force=bool)
@debounce
def SubtitleSetMods(mods=None, mode=None, **kwargs):
if not isinstance(mods, types.ListType) and mods:
mods = [mods]
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
lang_a2 = kwargs["language"]
item_type = kwargs["item_type"]
language = Language.fromietf(lang_a2)
current_sub, stored_subs, storage = get_current_sub(rating_key, part_id, language)
if mode == "add":
for mod in mods:
identifier, args = SubtitleModifications.parse_identifier(mod)
if identifier not in mod_registry.mods_available:
raise NotImplementedError("Mod unknown or not registered")
current_sub.add_mod(mod)
elif mode == "clear":
current_sub.add_mod(None)
elif mode == "remove":
for mod in mods:
current_sub.mods.remove(mod)
elif mode == "remove_last":
if current_sub.mods:
current_sub.mods.pop()
else:
raise NotImplementedError("Wrong mode given")
storage.save(stored_subs)
metadata = get_plex_metadata(rating_key, part_id, item_type)
scanned_parts = scan_videos([metadata], kind="series" if item_type == "episode" else "movie", ignore_all=True)
video, plex_part = scanned_parts.items()[0]
subtitle = Subtitle(language, mods=current_sub.mods)
subtitle.content = current_sub.content
subtitle.plex_media_fps = plex_part.fps
subtitle.page_link = "modify subtitles with: %s" % (", ".join(current_sub.mods) if current_sub.mods else "none")
subtitle.language = language
try:
save_subtitles(scanned_parts, {video: [subtitle]}, mode="m", bare_save=True)
Log.Debug("Modified %s subtitle for: %s:%s with: %s", language.name, rating_key, part_id,
", ".join(current_sub.mods) if current_sub.mods else "none")
except:
Log.Error("Something went wrong when modifying subtitle: %s", traceback.format_exc())
kwargs.pop("randomize")
return SubtitleModificationsMenu(randomize=timestamp(), **kwargs)
@route(PREFIX + '/item/sub_list_mods/{rating_key}/{part_id}', force=bool)
@debounce
def SubtitleListMods(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs["part_id"]
language = kwargs["language"]
current_sub, stored_subs, storage = get_current_sub(rating_key, part_id, language)
kwargs.pop("randomize")
oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
for identifier in current_sub.mods:
oc.add(DirectoryObject(
key=Callback(SubtitleSetMods, mods=identifier, mode="remove", randomize=timestamp(), **kwargs),
title="Remove: %s" % identifier
))
return oc
+2 -2
View File
@@ -11,9 +11,9 @@ class PlexActivityManager(object):
def start(self):
activity_sources_enabled = None
if config.universal_plex_token:
if config.plex_token:
from plex import Plex
Plex.configuration.defaults.authentication(config.universal_plex_token)
Plex.configuration.defaults.authentication(config.plex_token)
activity_sources_enabled = ["websocket"]
Activity.on('websocket.playing', self.on_playing)
+9
View File
@@ -9,6 +9,7 @@ import datetime
import subliminal
import subliminal_patch
from babelfish import Language
from subliminal.cli import MutexLock
from subzero.lib.io import FileIO, get_viable_encoding
from subzero.constants import PLUGIN_NAME, PLUGIN_IDENTIFIER, MOVIE, SHOW
from lib import Plex
@@ -45,6 +46,7 @@ class Config(object):
data_path = None
data_items_path = None
universal_plex_token = None
plex_token = None
is_development = False
enable_channel = True
@@ -68,6 +70,7 @@ class Config(object):
sections = None
enabled_sections = None
remove_hi = False
fix_ocr = False
enforce_encoding = False
chmod = None
forced_only = False
@@ -91,6 +94,7 @@ class Config(object):
self.data_path = getattr(Data, "_core").storage.data_path
self.data_items_path = os.path.join(self.data_path, "DataItems")
self.universal_plex_token = self.get_universal_plex_token()
self.plex_token = os.environ.get("PLEXTOKEN", self.universal_plex_token)
self.set_plugin_mode()
self.set_plugin_lock()
@@ -109,6 +113,7 @@ class Config(object):
self.permissions_ok = self.check_permissions()
self.notify_executable = self.check_notify_executable()
self.remove_hi = cast_bool(Prefs['subtitles.remove_hi'])
self.fix_ocr = cast_bool(Prefs['subtitles.fix_ocr'])
self.enforce_encoding = cast_bool(Prefs['subtitles.enforce_encoding'])
self.chmod = self.check_chmod()
self.forced_only = cast_bool(Prefs["subtitles.only_foreign"])
@@ -159,6 +164,8 @@ class Config(object):
else:
Log("Did NOT find Preferences file - please check logfile and hierarchy. Aborting!")
# fixme: windows
def set_plugin_mode(self):
if Prefs["plugin_mode"] == "only agent":
self.enable_channel = False
@@ -427,6 +434,8 @@ class Config(object):
mods = []
if self.remove_hi:
mods.append("remove_HI")
if self.fix_ocr:
mods.append("OCR_fixes")
return mods
+2 -2
View File
@@ -110,9 +110,9 @@ def str_pad(s, length, align='left', pad_char=' ', trim=False):
raise ValueError("Unknown align type, expected either 'left' or 'right'")
def pad_title(value):
def pad_title(value, width=49):
"""Pad a title to 30 characters to force the 'details' view."""
return str_pad(value, 49, pad_char=' ')
return str_pad(value, width, pad_char=' ')
def get_plex_item_display_title(item, kind, parent=None, parent_title=None, section_title=None,
+1
View File
@@ -374,6 +374,7 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
video_id = stored_subs.video_id
if stored_subs.item_type == "episode":
cutoff = self.series_cutoff
min_score = min_score_series
else:
cutoff = self.movies_cutoff
+6
View File
@@ -399,6 +399,12 @@
"id": "subtitles.remove_hi",
"label": "Remove Hearing Impaired tags from downloaded subtitles",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.fix_ocr",
"label": "Fix common OCR errors in downloaded subtitles",
"type": "bool",
"default": "true"
},
{
+2 -2
View File
@@ -13,7 +13,7 @@
<key>CFBundleSignature</key>
<string>????</string>
<key>CFBundleVersion</key>
<string>2.0.0.11</string>
<string>2.0.0.13</string>
<key>PlexFrameworkVersion</key>
<string>2</string>
<key>PlexPluginClass</key>
@@ -32,7 +32,7 @@
&lt;h1&gt;Sub-Zero for Plex&lt;/h1&gt;&lt;i&gt;Subtitles done right&lt;/i&gt;
Version 2.0.0.11 DEV
Version 2.0.0.13 DEV
Originally based on @bramwalet's awesome &lt;a href=&quot;https://github.com/bramwalet/Subliminal.bundle&quot;&gt;Subliminal.bundle&lt;/a&gt;
+2 -1
View File
@@ -369,7 +369,8 @@ class Chapter(object):
if chapterdisplays:
string = chapterdisplays[0].get('ChapString')
language = chapterdisplays[0].get('ChapLanguage')
return cls(start, hidden, enabled, end, string, language)
return cls(start, hidden, enabled, end, string, language)
return cls(start, hidden, enabled, end)
def __repr__(self):
return '<%s [%s, enabled=%s]>' % (self.__class__.__name__, self.start, self.enabled)
@@ -138,8 +138,6 @@ class PatchedSubtitle(Subtitle):
def get_modified_content(self):
"""
:param language:
:param fps:
:return: string
"""
if not self.mods:
@@ -148,14 +146,12 @@ class PatchedSubtitle(Subtitle):
encoding = self.guess_encoding()
submods = SubtitleModifications()
submods.load(content=self.text, fps=self.plex_media_fps)
submods.load(content=self.text, language=self.language)
submods.modify(*self.mods)
return submods.to_string("srt", encoding=encoding).encode(encoding=encoding)
def get_modified_text(self):
"""
:param language:
:param fps:
:return: unicode
"""
content = self.get_modified_content()
+6 -2
View File
@@ -3,6 +3,8 @@
import logging
import sys
from babelfish import Language
logger = logging.getLogger(__name__)
from subzero.modification import SubMod
@@ -14,7 +16,9 @@ if debug:
logging.basicConfig(level=logging.DEBUG)
submod = SubMod(debug=debug)
submod.load(fn)
submod.modify("remove_HI")
submod.load(fn, language=Language.fromietf("eng"))
#submod.modify("remove_HI", "OCR_fixes")
#submod.modify("OCR_fixes")
submod.modify("change_FPS(from=24,to=25)")
#print submod.f.to_string("srt")
@@ -1,5 +1,5 @@
# coding=utf-8
from registry import registry
from mods import hearing_impaired
from mods import hearing_impaired, ocr_fixes, fps, offset
from main import SubtitleModifications, SubMod
@@ -1,15 +1,174 @@
import re
from collections import OrderedDict
data = {'dan': OrderedDict([(u'Haner', u'Han er'), (u'JaveL', u'Javel'), (u'Pa//e', u'Palle'), (u'bffte', u'bitte'), (u'Utro//gt', u'Utroligt'), (u'Kommerdu', u'Kommer du'), (u'smi/er', u'smiler'), (u'/eg', u'leg'), (u'harvinger', u'har vinger'), (u'/et', u'let'), (u'erjeres', u'er jeres'), (u'hardet', u'har det'), (u't\xe6nktjer', u't\xe6nkt jer'), (u'erjo', u'er jo'), (u'sti/', u'stil'), (u'Iappe', u'lappe'), (u'Beklagel\xe7', u'Beklager,'), (u'vardet', u'var det'), (u'afden', u'af den'), (u'snupperjeg', u'snupper jeg'), (u'ikkejeg', u'ikke jeg'), (u'bliverjeg', u'bliver jeg'), (u'hartravit', u'har travlt'), (u'pandekagef/ag', u'pandekageflag'), (u'Stormvarsell', u'Stormvarsel!'), (u'stormvejn', u'stormvejr.'), (u'morgenkomp/et', u'morgenkomplet'), (u'/yv', u'lyv'), (u'varjo', u'var jo'), (u'/eger', u'leger'), (u'harjeg', u'har jeg'), (u'havdejeg', u'havde jeg'), (u'hvorjeg', u'hvor jeg'), (u'n\xe5rjeg', u'n\xe5r jeg'), (u'g\xe5rvi', u'g\xe5r vi'), (u'atjeg', u'at jeg'), (u'isine', u'i sine'), (u'f\xe5rjeg', u'f\xe5r jeg'), (u'k\xe6rtighed', u'k\xe6rlighed'), (u'skullejeg', u'skulle jeg'), (u'laest', u'l\xe6st'), (u'laese', u'l\xe6se'), (u'g\xf8rjeg', u'g\xf8r jeg'), (u'g\xf8rvi', u'g\xf8r vi'), (u'angrerjo', u'angrer jo'), (u'Hvergang', u'Hver gang'), (u'erder', u'er der'), (u'villetilgive', u'ville tilgive'), (u'\ufb01eme', u'fjeme'), (u'genopst\xe5ri', u'genopst\xe5r i'), (u'svigtejer', u'svigte jer'), (u'kommernu', u'kommer nu'), (u'n\xe5rman', u'n\xe5r man'), (u'erfire', u'er fire'), (u'Hvorfor\ufb01nderdu', u'Hvorfor \ufb01nder du'), (u'undertigt', u'underligt'), (u'itroen', u'i troen'), (u'erl\xf8gnt', u'er l\xf8gn!'), (u'g\xf8rden', u'g\xf8r den'), (u'forhelvede', u'for helvede'), (u'hjpe', u'hj\xe6lpe'), (u'togeti', u'toget i'), (u'M\xe5jeg', u'M\xe5 jeg'), (u'savnerjer', u'savner jer'), (u'erjeg', u'er jeg'), (u'vaere', u'v\xe6re'), (u'geme', u'gerne'), (u'trorp\xe5', u'tror p\xe5'), (u'forham', u'for ham'), (u'afham', u'af ham'), (u'harjo', u'har jo'), (u'ovema\ufb01et', u'overnattet'), (u'begae\ufb01ighed', u'beg\xe6rlighed'), (u'sy\u2019g', u'syg'), (u'Imensjeg', u'Imens jeg'), (u'bliverdu', u'bliver du'), (u'\ufb01ser', u'fiser'), (u'manipuierer', u'manipulerer'), (u'forjeg', u'for jeg'), (u'iivgivendefor', u'livgivende for'), (u'formig', u'for mig'), (u'Hardu', u'Har du'), (u'fornold', u'forhold'), (u'defrelste', u'de frelste'), (u'S\xe5jeg', u'S\xe5 jeg'), (u'varjeg', u'var jeg'), (u'g\xf8rved', u'g\xf8r ved'), (u'kalderjeg', u'kalder jeg'), (u'\ufb02ytte', u'flytte'), (u'handlerdet', u'handler det'), (u'trorjeg', u'tror jeg'), (u'\ufb02ytter', u'flytter'), (u'soverjeg', u'sover jeg'), (u'\ufb01nderud', u'\ufb01nder ud'), (u'naboerp\xe5', u'naboer p\xe5'), (u'ervildt', u'er vildt'), (u'v\xe6reher', u'v\xe6re her'), (u'hyggerjer', u'hygger jer'), (u'borjo', u'bor jo'), (u'kommerikke', u'kommer ikke'), (u'folkynde', u'forkynde'), (u'farglad', u'far glad'), (u'misterjeg', u'mister jeg'), (u'\ufb01nt', u'fint'), (u'Harl', u'Har I'), (u'bedejer', u'bede jer'), (u'synesjeg', u'synes jeg'), (u'vartil', u'var til'), (u'eren', u'er en'), (u'\\Al', u'Vil'), (u'\\A', u'Vi'), (u'fjeme', u'fjerne'), (u'Iigefyldt', u'lige fyldt'), (u'ertil', u'er til'), (u'fa\ufb01igt', u'farligt'), (u'\ufb01nder', u'finder'), (u'\ufb01ndes', u'findes'), (u'irettesae\ufb01else', u'irettes\xe6ttelse'), (u'ermed', u'er med'), (u'\xe8n', u'\xe9n'), (u'gikjoi', u'gik jo i'), (u'Hvisjeg', u'Hvis jeg'), (u'ovema\ufb01er', u'overnatter'), (u'hoident', u'holdent'), (u'\\Adne', u'Vidne'), (u'fori', u'for i'), (u'vei', u'vel'), (u'savnerjerjo', u'savner jer jo'), (u'elskerjer', u'elsker jer'), (u'harl\xf8jet', u'har l\xf8jet'), (u'eri', u'er i'), (u'\ufb01ende', u'fjende'), (u'derjo', u'der jo'), (u'sigerjo', u'siger jo'), (u'menerjeg', u'mener jeg'), (u'Harjeg', u'Har jeg'), (u'sigerjeg', u'siger jeg'), (u'splitterjeg', u'splitter jeg'), (u'erjournalist', u'er journalist'), (u'erjoumalist', u'er journalist'), (u'Forjeg', u'For jeg'), (u'g\xe2rjeg', u'g\xe5r jeg'), (u'N\xe2rjeg', u'N\xe5r jeg'), (u'a\ufb02lom', u'afkom'), (u'farerjo', u'farer jo'), (u'tagerjeg', u'tager jeg'), (u'Virkerjeg', u'Virker jeg'), (u'morerjer', u'morer jer'), (u'kommerjo', u'kommer jo'), (u'istand', u'i stand'), (u'b\xf8m', u'b\xf8rn'), (u'frygterjeg', u'frygter jeg'), (u'kommerjeg', u'kommer jeg'), (u'eriournalistelev', u'er journalistelev'), (u'harfat', u'har fat'), (u'f\xe5r\ufb01ngre', u'f\xe5r \ufb01ngre'), (u'sl\xe2rjeg', u'sl\xe5r jeg'), (u'bam', u'barn'), (u'erjournalistelev', u'er journalistelev'), (u'politietjo', u'politiet jo'), (u'elskerjo', u'elsker jo'), (u'vari', u'var i'), (u'fornemmerjeres', u'fornemmer jeres'), (u'udkl\xe6kketl', u'udkl\xe6kket!'), (u'\xed', u'i'), (u'nyi', u'ny i'), (u'Iumijelse', u'forn\xf8jelse'), (u'vures', u'vores'), (u'I/Vash\xedngtan', u'Washington'), (u'opleverjeg', u'oplever jeg'), (u'PANTEL\xc3NER', u'PANTEL\xc5NER'), (u'Gudmurgen', u'Godmorgen'), (u'SKYDEV\xc3BEN', u'SKYDEV\xc5BEN'), (u'P\xc3LIDELIG', u'P\xLine truncated
'deu': OrderedDict([(u'/a', u'Ja'), (u'/ch', u'Ich'), (u'/d/of', u'Idiot'), (u'/ebte', u'lebte'), (u'/eid', u'leid'), (u'/hn', u'ihn'), (u'/hnen', u'Ihnen'), (u'/hr', u'Ihr'), (u'/hre', u'Ihre'), (u'/hren', u'Ihren'), (u'/m', u'im'), (u'/mmer', u'immer'), (u'/n', u'In'), (u'/ndividuen', u'Individuen'), (u'/nn', u'Inn'), (u'/oe', u'Joe'), (u'/sf', u'ist'), (u'/sf/0/1n', u'Ist John'), (u'/ungs', u'Jungs'), (u'/Vfinuten', u'Minuten'), (u'/\xe9nger', u'l\xe4nger'), (u'/\xe9uft', u'l\xe4uft'), (u'0/1', u'Oh'), (u'0/me', u'ohne'), (u'0/vne', u'ohne'), (u'00om', u'000 m'), (u'100m', u'100 m'), (u'120m', u'120 m'), (u'13Oj\xa7hrie', u'130-j\xe4hrige'), (u'145m', u'145 m'), (u'150m', u'150 m'), (u'160m', u'160 m'), (u'165m', u'165 m'), (u'19m', u'19 m'), (u'20m', u'20 m'), (u'27m', u'27 m'), (u'30m', u'30 m'), (u'37m', u'37 m'), (u'38m', u'38 m'), (u'3km', u'3 km'), (u'5/ch', u'sich'), (u'5/cher', u'sicher'), (u'5/cherer', u'sicherer'), (u'5/e', u'Sie'), (u'5/nd', u'Sind'), (u'500m', u'500 m'), (u'5ulSere', u'\xe4u\xdfere'), (u'60m', u'60 m'), (u'6de', u'\xf6de'), (u'6dere', u'\xf6dere'), (u'6ffne', u'\xf6ffne'), (u'6ffnen', u'\xf6ffnen'), (u'6ffnet', u'\xd6ffnet'), (u'6fter', u'\xf6fter'), (u'750m', u'750 m'), (u'85m', u'85 m'), (u'90m', u'90 m'), (u'a//em', u'allem'), (u'A//es', u'Alles'), (u'abbeif$en', u'abbei\xdfen'), (u'abdrficken', u'abdr\xfccken'), (u'aBen', u'a\xdfen'), (u'abergl\xe9iubischen', u'abergl\xe4ubischen'), (u'aberja', u'aber ja'), (u'aberjemand', u'aber jemand'), (u'Aberjetzt', u'Aber jetzt'), (u'abf\xe9hrt', u'abf\xe4hrt'), (u'abf\xe9illt', u'abf\xe4llt'), (u'abgef\xe9rbt', u'abgef\xe4rbt'), (u'abgeh\xe9ngt', u'abgeh\xe4ngt'), (u'abgeh\xe9rt', u'abgeh\xf6rt'), (u'abgelost', u'abgel\xf6st'), (u'abgesprengli', u'abgesprengt!'), (u'abgestfirztl', u'abgest\xfcrzt'), (u'abgestilrzt', u'abgest\xfcrzt'), (u'abgestofien', u'abgesto\xdfen'), (u'abgew\xe9hlt', u'abgew\xe4hlt'), (u'abgew\xe9hnen', u'abgew\xf6hnen'), (u'abgew\xe9hnt', u'abgew\xf6hnt'), (u'abge\xe9nderten', u'abge\xe4nderten'), (u'abh\xe9ingt', u'abh\xe4ngt'), (u'abh\xe9ngen', u'abh\xe4ngen'), (u'abh\xe9ngig', u'abh\xe4ngig'), (u'abh\xe9ngiges', u'abh\xe4ngiges'), (u'Abh\xe9rstationen', u'Abh\xf6rstationen'), (u'Abjetzt', u'Ab jetzt'), (u'abkfihlen', u'abk\xfchlen'), (u'Abkfirzung', u'Abk\xfcrzung'), (u'abkommlich', u'abk\xf6mmlich'), (u'Ablegenl', u'Ablegen!'), (u'ablfisen', u'abl\xf6sen'), (u'ablosen', u'abl\xf6sen'), (u'Ablosung', u'Abl\xf6sung'), (u'abreif$en', u'abrei\xdfen'), (u'Abrijcken', u'Abr\xfccken'), (u'abr\xe9umen', u'abr\xe4umen'), (u'Absch/ed', u'Abschied'), (u'abschiefien', u'abschie\xdfen'), (u'abschlief$en', u'abschlie\xdfen'), (u'abschliefien', u'abschlie\xdfen'), (u'abschwiiren', u'abschw\xf6ren'), (u'abstoflsend', u'absto\xdfend'), (u'Abtrijnnige', u'Abtr\xfcnnige'), (u'abwiirgt', u'abw\xfcrgt'), (u'abw\xe9gen', u'abw\xe4gen'), (u'abzuh\xe9ren', u'abzuh\xf6ren'), (u'abzuschwiiren', u'abzuschw\xf6ren'), (u'abzusfofien', u'abzusto\xdfen'), (u'ACh', u'Ach'), (u'Achtungl', u'Achtung!'), (u'Achzen', u'\xc4chzen'), (u'ACHZT', u'\xc4CHZT'), (u'Acic', u'Acid'), (u'ADDRESSDATEI', u'ADRESSDATEI'), (u'Adi\xf6s', u'Adi\xf3s'), (u'Admiralitat', u'Admiralit\xe4t'), (u'Admiralit\xe9it', u'Admiralit\xe4t'), (u'Admiralit\xe9t', u'Admiralit\xe4t'), (u'Aff\xe9re', u'Aff\xe4re'), (u'Aff\xe9ren', u'Aff\xe4ren'), (u'AFl', u'AFI'), (u'aggresivem', u'aggressivem'), (u'Agypten', u'\xc4gypten'), (u'aher', u'aber'), (u'AI/en/vichtigste', u'Allerwichtigste'), (u'Ain/vays', u'Airways'), (u'AIs', u'Als'), (u'Aktivit\xe9iten', u'Aktivit\xe4ten'), (u'Aktivit\xe9ten', u'Aktivit\xe4ten'), (u'AKTMERT', u'AKTIVIERT'), (u'Alarmsfufe', u'Alarmstufe'), (u'albem', u'albern'), (u'Albtriiume', u'Albtr\xe4ume'), (u'ale', u'als'), (u'alleinl', u'allein!'), (u'allejubeln', u'alle jubeln'), (u'allern\xe9chsten', u'allern\xe4chsten'), (u'Allmiichtigerl', u'Allm\xe4chtiger!'), (u'Allm\xe9chtige', u'Allm\xe4chtige'), (u'Allm\xe9chtiger', u'Allm\xe4chtiger'), (u'allm\xe9hlich', u'allm\xe4hlich'), (u'Allm\xe9ichtiger', u'Allm\xe4chtiger'), (u'Allsparkl', u'Allspark!'), (u'allt\xe9iglichen', u'allt\xe4glichen'), (u'ALTESTE', u'\xc4LTESTE'), (u'Altester', u'\xc4ltester'), (u'Alzte', u'\xc4rzte'), (u"Amerx'kaner", u'Amerikaner'), (u'amfisierst', u'am\xfcsierst'), (u'Amiilsierst', u'Am\xfcsierst'), (u'amiisieren', u'am\xfcsieren'), (u'amiisierenl', u'am\xfcsieren!'), (u'amiisierte', u'am\xfcsierte'), (u'Amijsant', u'Am\xfcsant'), (u'amlllsant', u'am\xfcsant'), (u'amlllsiert', u'am\xfcsiert'), (u'amtlsant', u'am\xfcsant'), (u'Amusanf', u'Am\xfcsant'), (u'amusant', u'am\xfcsant'), (u'Amusiert', u'Am\xfcsiert'), (u'Anderst', u'\xc4nderst'), (u'Anderung', u'\xc4nderung'), (u'Anderungen', u'\xc4nderungen'), (u"anfa'ngt", u'anf\xe4ngt'), (u'Anffihrer', u'Anf\xfchrer'), (u'Anffingerl', u'Anf\xe4nger!'), (u'Anfiihrer', u'Anf\xfchrer'), (u'anfijhlt', u'anf\xfchlt'), (u'Anfingerl', u'Anf\xe4nger!'), (u'Anfuhrer', u'Anf\xfchrer'), (u'Anfuhrern', u'Anf\xfchrern'), (u'Anf\xe9inger', Line truncated
'eng': OrderedDict([(u'H ey.', u'Hey.'), (u'He)\u2019-', u'Hey.'), (u'N0.', u'No.'), (u'-N0.', u'-No.'), (u'Noll', u'No!!'), (u'(G ROANS)', u'(GROANS)'), (u'[G ROANS]', u'[GROANS]'), (u'(M EOWS)', u'(MEOWS)'), (u'[M EOWS]', u'[MEOWS]'), (u'Uaughs]', u'[laughs]'), (u'[chitte rs]', u'[chitters]'), (u'Hil\u2018 it!', u'Hit it!'), (u'<i>Hil\u2018 it!</i>', u'<i>Hit it!</i>'), (u'ISIGHS]', u'[SIGHS]'), (u'$COff$', u'scoffs'), (u'$ergei', u'Sergei'), (u"$'llOp", u'Stop'), (u"/'//", u"I'll"), (u"/'/I", u"I'll"), (u'/ennifer', u'Jennifer'), (u'/got', u'I got'), (u'/have', u'I have'), (u'/hope', u'I hope'), (u'/just', u'I just'), (u'/love', u'I love'), (u"/'m", u"I'm"), (u'/mmerse', u'immerse'), (u'/nsu/ts', u'Insults'), (u'/ong', u'long'), (u'/ook', u'look'), (u"/t's", u"It's"), (u"/'ve", u"I've"), (u"\\/\\/e'd", u"We'd"), (u"\\/\\/e're", u"We're"), (u"\\/\\/e've", u"We've"), (u'\\/\\/hat', u'What'), (u"\\/\\/here'd", u"Where'd"), (u'\\/\\/hoo', u'Whoo'), (u'\\/\\/hy', u'Why'), (u"\\/\\/hy'd", u"Why'd"), (u"\\/\\le're", u"We're"), (u'\\/Ve', u'We'), (u"\\Ne're", u"We're"), (u"\\Nhat's", u"What's"), (u"\\Nhere's", u"Where's"), (u"|'mjust", u"I'm just"), (u'\xa4ff', u'off'), (u'\xa4Id', u'old'), (u'\xa4Ids', u'olds'), (u'\xa4n', u'on'), (u'\xa4ne', u'one'), (u'\xa4nly', u'only'), (u'\xa4pen', u'open'), (u'\xa4r', u'or'), (u'\xa4rder', u'order'), (u'\xa4ther', u'other'), (u'\xa4ur', u'our'), (u'\xa4ut', u'out'), (u'\xa4ver', u'over'), (u'\xa4wn', u'own'), (u"\u20acV\u20acI'y", u'every'), (u"0'clock", u"o'clock"), (u'0f', u'of'), (u'0fEngland', u'of England'), (u'0fft0', u'off to'), (u'0l/er', u'over'), (u'0n', u'on'), (u'0ne', u'one'), (u"0ne's", u"one's"), (u'0r', u'or'), (u'0rders', u'orders'), (u"0thers'", u"others'"), (u'0ut', u'out'), (u"0utlaw's", u"outlaw's"), (u"0utlaws'", u"outlaws'"), (u'0ver', u'over'), (u'13oos', u'1300s'), (u'18oos', u'1800s'), (u'195os', u'1950s'), (u"1et's", u"let's"), (u'1o', u'10'), (u'1oo', u'100'), (u'1ooth', u'100th'), (u'1oth', u'10th'), (u'2E_', u'2E.'), (u"2'IST", u'21ST'), (u"2'Ist_", u"2'1st."), (u'2o', u'20'), (u'2oth', u'20th'), (u'3o', u'30'), (u'3oth', u'30th'), (u'4o', u'40'), (u'4os', u'40s'), (u'4oth', u'40th'), (u'50rry', u'sorry'), (u'5o', u'50'), (u'5oth', u'50th'), (u'6o', u'60'), (u'6os', u'60s'), (u"'6os", u"'60s"), (u'6oth', u'60th'), (u'7o', u'70'), (u"'7os", u"'70s"), (u'7oth', u'70th'), (u'8o', u'80'), (u"'8os", u"'80s"), (u'8oth', u'80th'), (u'9/aim', u'alarm'), (u'9o', u'90'), (u'9oth', u'90th'), (u'9UnShQt', u'gunshot'), (u'a//', u'all'), (u'a/bum', u'album'), (u'a/so', u'also'), (u'A/ways', u'Always'), (u'abcut', u'about'), (u'aboutjoining', u'about joining'), (u'aboutposh', u'about posh'), (u'aboutus', u'about us'), (u'aboutyou', u'about you'), (u'accldent', u'accident'), (u'Acool', u'A cool'), (u'afier', u'after'), (u'affraid', u'afraid'), (u'Afriend', u'A friend'), (u'afterall', u'after all'), (u'afterthe', u'after the'), (u'afulcrum', u'a fulcrum'), (u'Afunny', u'A funny'), (u'aga/nst', u'against'), (u'ahsolutes', u'absolutes'), (u'AI_I_', u'ALL'), (u'AIien', u'Alien'), (u'AIex', u'Alex'), (u'AII', u'All'), (u'AIIan', u'Allan'), (u'AIIow', u'Allow'), (u'AIive', u'Alive'), (u"ain'tgotno", u"ain't got no"), (u"Ain'tgotno", u"Ain't got no"), (u'airstrike', u'air strike'), (u'AIVIBULANCE', u'AMBULANCE'), (u'ajob', u'a job'), (u'ajockey_', u'a jockey.'), (u'ajoke', u'a joke'), (u'Ajoke', u'A joke'), (u'ajoking', u'a joking'), (u'al/', u'all'), (u'al/en', u'alien'), (u'alittle', u'a little'), (u'allgasp', u'all gasp'), (u'alljustforshow', u'all just for show'), (u"aln't", u"ain't"), (u'alot', u'a lot'), (u'Alot', u'A lot'), (u'An5wer', u'Answer'), (u'Andit', u'And it'), (u"Andit's", u"And it's"), (u'andl', u'and I'), (u'andlaughs', u'and laughs'), (u'andleave', u'and leave'), (u'andthe', u'and the'), (u'andyou', u'and you'), (u'Andyou', u'And you'), (u'ANNOUNC/NG', u'ANNOUNCING'), (u'anotherstep', u'another step'), (u'ANSWER/NG', u'ANSWERING'), (u'answerwhat', u'answer what'), (u'antiquejoke', u'antique joke'), (u"anyhcdy's", u"anybody's"), (u'Anyidea', u'Any idea'), (u"anyone's_", u"anyone's."), (u'apejust', u'ape just'), (u'ARABlc', u'ARABIC'), (u"aren't_", u"aren't."), (u"arerl't", u"aren't"), (u"Arnsteln's", u"Arnstein's"), (u'atleast', u'at least'), (u'Atough', u'A tough'), (u'Awhole', u'A whole'), (u'awoman', u'a woman'), (u'Awoman', u'A woman'), (u'barelytalked', u'barely talked'), (u'bcat', u'boat'), (u'Bcllvla', u'Bolivia'), (u'bcmb', u'bomb'), (u'bcmbs', u'bombs'), (u'be//y', u'belly'), (u'becuase', u'because'), (u"Beep/'ng", u'Beeping'), (u'bejumpy', u'be jumpy'), (u'besldes', u'besides'), (u'bestfriend', u'best friend'), (u'bestguy', u'best guy'), (u'bestjob', u'best job'), (u'BIack', u'Black'), (u'BIess', u'Bless'), (u'bigos___', u'bigos...'), (u'BIame', u'Blame'), (u'BIind', u'Blind'), (u'BIood', u'Blood'), (u'BIue', u'Blue'), (u'BLOVVS', u'BLOWS'), (u'blowholel', u'blowhole!'), (u'blt', u'bit'), (u'Bo99', u'Bogg'), (u'bodiedyoung', u'bodied Line truncated
'fin': OrderedDict([(u'Katsokaa pa.', u'Katsokaapa.'), (u'Mik!\r\n""e\u201c9ir\xe4\u0131', u'Mik!\r\n-Hengit\xe4!'), (u'Tu lta!', u'Tulta!'), (u'...0I1...', u'...on...'), (u'Ken g\xe4n nauh oja?', u'Keng\xe4nnauhoja?'), (u'k\xe3mmott\xe3V\xe3ll\xe3 mUiStoll\xe3.', u'kammottavana muistona.'), (u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen ksen asun to o ns\xe4.', u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen asuntoonsa.'), (u'Min\xe4 etsin k\xe4siini miehen, joka\r\non aurtanutiestradea ja minua:', u'Min\xe4 etsin k\xe4siini miehen, joka\r\non auttanut Lestradea ja minua:'), (u'Huomaa erityisesti\r\npunaisella merkitty "kitoris.', u'Huomaa erityisesti\r\npunaisella merkitty "klitoris".'), (u'Tulkaa, meill\xe4 on\r\nHa va\u0131ji-bileet suihkussa', u'Tulkaa, meill\xe4 on\r\nHavaiji-bileet suihkussa'), (u'Ta rkoitatko ett\xe4\r\nh\xe4net myrkytettiin?', u'Tarkoitatko ett\xe4\r\nh\xe4net myrkytettiin?'), (u'Odotta kaa soittoani\r\nIev\xe4hdyspaikalla.', u'Odottakaa soittoani\r\nlev\xe4hdyspaikalla.'), (u'Nyt kuuntelet, perska rva.', u'Nyt kuuntelet, perskarva.'), (u'Ta patko h\xe4net sitten?', u'Tapatko h\xe4net sitten?'), (u'Seuraa vissa va/oissa.', u'Seuraavissa valoissa.'), (u'A\u0131o\u0131t rapattaa minut.\r\n- En.', u'Aioit tapattaa minut.\r\n- En.'), (u'Todella vaku uttavaa.', u'Todella vakuuttavaa.'), (u'I-le ovat tuolla alhaalla', u'He ovat tuolla alhaalla'), (u'Nainen kuuluu minulle.\r\n- I-I\xe0ivy siit\xe4, ylikasvuinen hyttynen!', u'Nainen kuuluu minulle.\r\n- H\xe4ivy siit\xe4, ylikasvuinen hyttynen!'), (u'I-Ialuatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.', u'Haluatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.'), (u'Mit\xe4f?', u'Mit\xe4.. ?'), (u'Kuuluuko Hiru ko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.', u'Kuuluuko Hiruko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.'), (u'Anteeks\u0131} painoin kai... -', u'Anteeksi, painoin kai... -'), (u'ja Rea! Ho usew\xedves.', u'ja Real Housewives.'), (u'Et halu n n ut Julkkistansseihinkaan.', u'Et halunnut Julkkistansseihinkaan.'), (u'Laard i k\xe4si?', u'Laardik\xe4si?'), (u'Varo kaa!', u'Varokaa!'), (u'N\xe4ytt\xe4v\xe4t k\xf6 tyt\xf6t v\xe4h \xe4n\r\nh uorahtavi m m i lta?', u'N\xe4ytt\xe4v\xe4tk\xf6 tyt\xf6t v\xe4h\xe4n\r\nhuorahtavimmilta?'), (u'Stif... Ier.', u'Stif... ler.'), (u'J u mantsu kka! M it\xe4?', u'Jumantsukka! Mit\xe4?'), (u'Varasin Ch u m bawam ban,', u'Varasin Chumbawamban,'), (u'J u malavita!', u'Jumalavita!'), (u'S', u'Isi...'), (u'Haluan kertoa jotai n', u'Haluan kertoa jotain'), (u'I-Ialuatte', u'Haluatte'), (u'kellojo', u'kello jo'), (u'onjo', u'on jo'), (u'senj\xe4lkeen', u'sen j\xe4lkeen'), (u'Ts\xe4u', u'Tsau'), (u'hydraulinenjousitus', u'hydraulinen jousitus'), (u'Kevyetja', u'Kevyet ja'), (u'Oleijo', u'Olet jo'), (u'viimeinenjuna', u'viimeinen juna'), (u'n\xe4ytt\xe4\xe4jotenkin', u'n\xe4ytt\xe4\xe4 jotenkin'), (u'onjoku', u'on joku'), (u'Iapsuuteen', u'Lapsuuteen'), (u'Ieikitjunill\xe4', u'leikit junilla'), (u'Sfiy', u'Stig'), (u'Iukulasejani', u'Lukulasejani'), (u'Ieikkiminen', u'Leikkiminen'), (u'K\xe4\xe4lik\xe4\xe4rylepizz\xe4', u'Kaalik\xe4\xe4rylepizza'), (u'sukl\xe4\xe4k\xe4stikkeen', u'suklaakastikkeen'), (u'p\xe4istetun', u'paistetun'), (u'b\xe4n\xe4\xe4nin', u'banaanin'), (u'pifi', u'piti'), (u'a\u0131keasfaan', u'oikeastaan'), (u'Stg', u'Stig'), (u'sikain\ufb02uenssatja', u'sikainfluenssat ja'), (u'Hienojuna', u'Hieno juna'), (u'kiinnostuajunista', u'kiinnostua junista'), (u'h\xe4y\u0131yvetu\u0131\xedn', u'h\xf6yryveturin'), (u'pienaismalli', u'pienoismalli'), (u'ena', u'eno'), (u'racfios\xe3hk\xe4ff\xe1j\xe3n\xe3', u'radios\xe4hk\xf6tt\xe4j\xe4n\xe4'), (u'Amenkan', u'Amerikan'), (u'laiva/la', u'laivalla'), (u'0/in', u'Olin'), (u'Junaha\u0131rasfus', u'Junaharrastus'), (u'enasfa', u'enosta'), (u'/V\u0131\xedn', u'Niin'), (u'Oliivarmasii', u'Olit varmasti'), (u'Internetist\xe4juuri', u'Internetist\xe4 juuri'), (u'hu\u0131janj\xe3nniff\xe5v\xe3\xe0l', u'hurjan j\xe4nnitt\xe4v\xe4\xe4.'), (u'Vaikkajunat', u'Vaikka junat'), (u'k\xe4\xe4ntyija', u'k\xe4\xe4ntyi ja'), (u'osaajotain', u'osaa jotain'), (u'Ieikill\xe4mme', u'leikill\xe4mme'), (u'Bellinjuna', u'Beltin juna'), (u't\xe4st\xe4johtolangasta', u't\xe4st\xe4 johtolangasta'), (u'tuntisijonkun', u'tuntisi jonkun'), (u'Olgajotain', u'Olga jotain'), (u'tulokseivuodesia', u'tulokset vuodesta'), (u'tuloksetvuodesta', u'tulokset vuodesta'), (u'Vainjalkapallo', u'Vain jalkapallo'), (u'lloveyou', u'I love you'), (u'po\ufb02\u2039aisi', u'potkaisi'), (u'minufulos', u'minut ulos'), (u'Ieiv\xe4npaahdinl', u'leiv\xe4npaahdin!'), (u'Ieiv\xe4npaahdinta', u'leiv\xe4npaahdinta'), (u'asuajossain', u'asua jossain'), (u'Koiratjuoksentelivat', u'Koirat juoksentelivat'), (u'tiet\xe4\xe4jotain', u'tiet\xe4\xe4 jotain'), (u'osaatjuna', u'osaat juna'), (u'va/as', u'valas'), (u'va/asperhe', u'valasperhe'), (u'koskeejotain', u'koskee jotain'), (u'I\xe4\xe4kkeeLine truncated
'fra': OrderedDict([(u'"D\'ac:c:ord."', u'"D\'accord."'), (u'\u201ci QU\xce gagne, qui perd,', u'ni qui gagne, qui perd,'), (u"L'ac:c:ent est mis \r\n \r\n sur son trajet jusqu'en Suisse.", u"L'accent est mis \r\n \r\n sur son trajet jusqu'en Suisse."), (u"C'est la plus gentille chose \r\n \r\n qu'Hitchc:oc:k m'ait jamais dite.", u"C'est la plus gentille chose \r\n \r\n qu'Hitchcock m'ait jamais dite."), (u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventu re structur\xe9e,", u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventure structur\xe9e,"), (u'et le film Shadow of a man \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.', u'et le film <i>Shadow of a man</i> \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.'), (u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec One night with you.', u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec <i>One night with you</i>.'), (u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 C)c:ala, en Floride.', u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 Ocala, en Floride.'), (u'Tokyo Pop et A Taxing Woman? Return.', u"Tokyo Pop et A Taxing Woman's Return."), (u'Peter H u nt.', u'Peter Hunt.'), (u'"C\'est bien mieux dans Peau. \r\n \r\n On peut s\ufb02\xe9clabousser, faire du bruit."', u'"C\'est bien mieux dans l\'eau. \r\n \r\n On peut s\'\xe9clabousser, faire du bruit."'), (u'@immatriculation', u"d'immatriculation"), (u'acquer', u'acqu\xe9r'), (u'acteurjoue', u'acteur joue'), (u'aerien', u'a\xe9rien'), (u'agreable', u'agr\xe9able'), (u'aientjamais', u'aient jamais'), (u'AII', u'All'), (u'aitjamais', u'ait jamais'), (u'aitjus', u'ait jus'), (u'alle', u'all\xe9'), (u'alles', u'all\xe9s'), (u'appele', u'appel\xe9'), (u'apres', u'apr\xe8s'), (u'aujourdhui', u"aujourd'hui"), (u'aupres', u'aupr\xe8s'), (u'beaute', u'beaut\xe9'), (u'cabossee', u'caboss\xe9e'), (u"carj'", u"car j'"), (u"Carj'", u"Car j'"), (u'carla', u'car la'), (u'CEdipe', u'\u0152dipe'), (u'Cest', u"C'est"), (u"c'etaient", u"c'\xe9taient"), (u'C\xe9taient', u"C'\xe9taient"), (u"c'etait", u"c'\xe9tait"), (u"C'etait", u"C'\xe9tait"), (u'C\xe9tait', u"C'\xe9tait"), (u'choregraphiee', u'chor\xe9graphi\xe9e'), (u'cinema', u'cin\xe9ma'), (u"cl'AIcatraz", u"d'Alcatraz"), (u'cles', u'cl\xe9s'), (u'c\u0153urjoie', u'c\u0153ur-joie'), (u'completer', u'compl\xe9ter'), (u'costumiere', u'costumi\xe8re'), (u'cree', u'cr\xe9\xe9'), (u'daccord', u"d'accord"), (u"d'AIbert", u"d'Albert"), (u"d'AIdous", u"d'Aldous"), (u"d'AIec", u"d'Alec"), (u'danniversaire', u"d'anniversaire"), (u"d'Arra'bida", u"d'Arrabida"), (u"d'autod\xe9rision", u"d'auto-d\xe9rision"), (u'dautres', u"d'autres"), (u'debattait', u'd\xe9battait'), (u'decor', u'd\xe9cor'), (u'decorateurs', u'd\xe9corateurs'), (u'decors', u'd\xe9cors'), (u'defi', u'd\xe9fi'), (u'dej\xe0', u'd\xe9j\xe0'), (u'd\xe9j\xe0m', u'd\xe9j\xe0...'), (u'dejeunait', u'd\xe9jeunait'), (u'dengager', u"d'engager"), (u'd\xe9quipement', u"d'\xe9quipement"), (u'd\xe9rni\xe8r\xe9', u'derni\xe8re'), (u'Desole', u'D\xe9sol\xe9'), (u'dessayage', u"d'essayage"), (u'dessence', u"d'essence"), (u'd\xe9taient', u"c'\xe9taient"), (u'detail', u'd\xe9tail'), (u'dexcellents', u"d'excellents"), (u'dexp\xe9rience', u"d'exp\xe9rience"), (u'dexp\xe9riences', u"d'exp\xe9riences"), (u"d'h\xe9ro'l'ne", u"d'h\xe9ro\xefne"), (u"d'idees", u"d'id\xe9es"), (u"d'intensite", u"d'intensit\xe9"), (u'dontj', u'dont j'), (u'doublaitAlfo', u'doublait Alfo'), (u'DrNo', u'Dr No'), (u"e'", u'\xe9'), (u'ecrit', u'\xe9crit'), (u'elegant', u'\xe9l\xe9gant'), (u'Ell\xe9', u'Elle'), (u'\xe9n', u'en'), (u'equipe', u'\xe9quipe'), (u'erjus', u'er jus'), (u'estjamais', u'est jamais'), (u'\xe9t', u'et'), (u'etaient', u'\xe9taient'), (u'etait', u'\xe9tait'), (u'ete', u'\xe9t\xe9'), (u'etiez', u'\xe9tiez'), (u"etj'", u"et j'"), (u"Etj'", u"Et j'"), (u'etje', u'et je'), (u'Etje', u'Et je'), (u'EtsouvenL', u'Et souvent'), (u'eviter', u'\xe9viter'), (u'Fabsence', u"l'absence"), (u'fadapter', u"t'adapter"), (u'fadore', u"j'adore"), (u'F\xe2ge', u"l'\xe2ge"), (u'Fagent', u"l'agent"), (u'faiessay\xe9', u"j'ai essay\xe9"), (u'Failure', u"l'alllure"), (u'Fambiance', u"l'ambiance"), (u'Famener', u"l'amener"), (u'Fanniversaire', u"l'anniversaire"), (u'Fapparence', u"l'apparence"), (u'Fapres', u"l'apres"), (u'Fapr\xe8s', u"l'apr\xe8s"), (u'Farm\xe9e', u"l'arm\xe9e"), (u'Farri\xe8re', u"l'arri\xe8re"), (u'Farriv\xe9e', u"l'arriv\xe9e"), (u'Fascenseur', u"l'ascenseur"), (u'Fascension', u"l'ascension"), (u'Fassaut', u"l'assaut"), (u'Fassomme', u"l'assomme"), (u'Fatmosph\xe8re', u"l'atmosph\xe8re"), (u'Fattention', u"l'attention"), (u'Favalanche', u"l'avalanche"), (u'F\xe9clairage', u"l'\xe9clairage"), (u'F\xe9cran', u"l'\xe9cran"), (u'F\xe9motion', u"l'\xe9motion"), (u'Femplacement', u"l'emplacement"), (u'Fendroit', u"l'endroit"), (u'Fenseigne', u"l'enseigne"), (u'Fensemble', u"l'ensemble"), (u'Fentouraient', u"l'entouraient"), (u'Fentr\xe9e', u"l'entr\xe9e"), (u'F\xe9paisseur', uLine truncated
'hrv': OrderedDict([(u'advokati', u'odvjetnici'), (u'Advokati', u'Odvjetnici'), (u'advokatima', u'odvjetnicima'), (u'Advokatima', u'Odvjetnicima'), (u'amin', u'amen'), (u'Amin', u'Amen'), (u'ba\u0161ta', u'vrt'), (u'Ba\u0161ta', u'Vrt'), (u'ba\u0161te', u'vrtovi'), (u'Ba\u0161te', u'Vrtovi'), (u'ba\u0161ti', u'vrtu'), (u'ba\u0161tu', u'vrt'), (u'Ba\u0161tu', u'Vrt'), (u'ba\u0161tom', u'vrtom'), (u'bedan', u'bijedan'), (u'bede', u'bijede'), (u'bedi', u'bijedi'), (u'bejah', u'bijah'), (u'bele\u0161ci', u'bilje\u0161ci'), (u'bimso', u'bismo'), (u'bioskop', u'kino'), (u'bioskopi', u'kina'), (u'bitci', u'bitki'), (u'blije\u0111i', u'blje\u0111i'), (u'beg', u'bijeg'), (u'begu', u'bijegu'), (u'beja\u0161e', u'bija\u0161e'), (u'bekstvo', u'bijeg'), (u'bekstvu', u'bijegu'), (u'begstvu', u'bijegu'), (u'bes', u'bijes'), (u'besa', u'bijesa'), (u'besan', u'bijesan'), (u'besom', u'bijesom'), (u'besu', u'bijesu'), (u'be\u0161e', u'bje\u0161e'), (u'bioje', u'bio je'), (u'bi smo', u'bismo'), (u'bi ste', u'biste'), (u'bled', u'blijed'), (u'blede', u'blijede'), (u'boksuje\u0161', u'boksa\u0161'), (u'bolesan', u'bolestan'), (u'braon', u'sme\u0111a'), (u'bregu', u'brijegu'), (u'bti', u'biti'), (u'ceo', u'cijeli'), (u'Ceo', u'Cijeli'), (u'cepa', u'cijepa'), (u'cev', u'cijev'), (u'cevi', u'cijevi'), (u'cev\u010dica', u'cjev\u010dica'), (u'cev\u010dicu', u'cjev\u010dicu'), (u'cvetu', u'cvijetu'), (u'cvjetu', u'cvijetu'), (u'cvjetom', u'cvijetom'), (u'\u010dar\u0161av', u'plahta'), (u'\u010dar\u0161ave', u'plahte'), (u'\u010dar\u0161avima', u'plahtama'), (u'\u010das', u'sat'), (u'\u010detvoro', u'\u010detvero'), (u'\u010cita\u0107u', u'\u010citat \u0107u'), (u'\u010derku', u'k\u0107er'), (u'\u010cerku', u'K\u0107er'), (u'\u0107erku', u'k\u0107er'), (u'\u0106erku', u'K\u0107er'), (u'\u0107erkama', u'k\u0107erima'), (u'\u010derkama', u'k\u0107erima'), (u'\u0107erkom', u'k\u0107eri'), (u'\u010derkom', u'k\u0107eri'), (u'k\u0107erkom', u'k\u0107eri'), (u'k\u010derkom', u'k\u0107eri'), (u'\u0107ebe', u'deku'), (u'\u0107ebetu', u'deki'), (u'\u010dk', u'\u010dak'), (u'\u0107\u0161', u'\u0107e\u0161'), (u'\u0107ale', u'tata'), (u'\u0107aletom', u'ocem'), (u'\u0107aleta', u'oca'), (u'\u0107aletu', u'ocu'), (u'\u0107orsokak', u'slijepa ulica'), (u'\u0107orsokaku', u'slijepoj ulici'), (u'\u0107o\u0161ak', u'ugao'), (u'\u0107o\u0161ku', u'uglu'), (u'\u0107erka', u'k\u0107i'), (u'\u0106erka', u'K\u0107i'), (u'\u0107mo', u'\u0107emo'), (u'\u0107te', u'\u0107ete'), (u'\u010du\u0107e', u'\u010dut \u0107e'), (u'\u010du\u0107emo', u'\u010dut \u0107emo'), (u'\u010cu\u0107ete', u'\u010cut \u0107ete'), (u'\u010cu\u0107e', u'\u010cut \u0107e'), (u'\u0107utao', u'\u0161utio'), (u'\u0106utao', u'\u0160utio'), (u'daga', u'da ga'), (u'damas', u'danas'), (u'deda', u'djed'), (u'Deda', u'Djed'), (u'dede', u'djeda'), (u'dedi', u'djedu'), (u'dedom', u'djedom'), (u'defini\u0161e', u'definira'), (u'dele\u0107i', u'dijele\u0107i'), (u'deo', u'dio'), (u'Deo', u'Dio'), (u'de\u0161ava', u'doga\u0111a'), (u'dete', u'dijete'), (u'djete', u'dijete'), (u'Dete', u'Dijete'), (u'Djete', u'Dijete'), (u'detektuje', u'detektira'), (u'dodju', u'do\u0111u'), (u'dole', u'dolje'), (u'Dole', u'Dolje'), (u'Donije\u0107u', u'Donijet \u0107u'), (u'do ovde', u'dovde'), (u'dospeo', u'dospio'), (u'dospeju', u'dospiju'), (u'do\u0111avola', u'dovraga'), (u'Do\u0111avola', u'Dovraga'), (u'drug', u'prijatelj'), (u'drugde', u'drugdje'), (u'duuga', u'd\xfaga'), (u'dve', u'dvije'), (u'Dve', u'Dvije'), (u'\u0111avo', u'vrag'), (u'\u0111avola', u'vraga'), (u'\u0111emper', u'd\u017eemper'), (u'd\u017eanki', u'ovisnik'), (u'\u0111ubre', u'sme\u0107e'), (u'eksperti', u'stru\u010dnjaci'), (u'Eksperti', u'Stru\u010dnjaci'), (u'ekspertima', u'stru\u010dnjacima'), (u'en', u'ne'), (u'emitovao', u'emitirao'), (u'emituje', u'emitira'), (u'emitujem', u'emitiram'), (u'emituju', u'emitiraju'), (u'familijama', u'obiteljima'), (u'familiji', u'obitelji'), (u'flertuje', u'o\u010dijuka'), (u'foka', u'tuljan'), (u'foku', u'tuljana'), (u'foke', u'tuljani'), (u'fokama', u'tuljanima'), (u'gde', u'gdje'), (u'Gde', u'Gdje'), (u'Gre\u010den', u'Gretchen'), (u'gre\u0161e', u'grije\u0161e'), (u'gre\u0161ki', u'gre\u0161ci'), (u'Historija', u'Povijest'), (u'Historiju', u'Povijest'), (u'Historije', u'Povijesti'), (u'Historiji', u'Povijesti'), (u'Istorija', u'Povijest'), (u'Istoriju', u'Povijest'), (u'Istorije', u'Povijesti'), (u'Istoriji', u'Povijesti'), (u'historije', u'povijesti'), (u'historiji', u'povijesti'), (u'istorije', u'povijesti'), (u'istoriji', u'povijesti'), (u'ho\u010du', u'ho\u0107u'), (u'Ho\u010du', u'Ho\u0107u'), (u'hte\u0107e', u'htjet \u0107e'), (u'htedoh', u'htjedoh'), (u'i\u010di', u'i\u0107i'), (u'I\u010di', u'I\u0107i'), (u'iko', u'itko'), (u'ignori\u0161i', u'ignoriraj'), (u'Ignori\u0161i', u'Ignoriraj'), (u'ignori\u0161ite', u'ignorirajte'), (u'Ignori\u0161ite', u'Ignorirajte'), (u'ignori\u0161u', u'ignoriraju'), (u'Interesuje', u'Zanima'), (u'Interesuju', u'Zanimaju'), (u'interesuju', u'zanimaju'), Line truncated
'hun': OrderedDict(),
'nld': OrderedDict([(u'ls', u'Is'), (u'ln', u'In'), (u'lk', u'Ik'), (u'ledereen', u'Iedereen'), (u'ledere', u'Iedere'), (u'lemand', u'Iemand')]),
'nor': OrderedDict(),
'por': OrderedDict([(u'abitual', u'habitual'), (u'\xe0cerca', u'acerca'), (u'acessor', u'assessor'), (u'ac\xf3lico', u'ac\xf3lito'), (u'a\xe7oreano', u'a\xe7oriano'), (u'actuacao', u'actua\xe7\xe3o'), (u'acucar', u'a\xe7\xfacar'), (u'a\xe7ucar', u'a\xe7\xfacar'), (u'advinhar', u'adivinhar'), (u'africa', u'\xc1frica'), (u'ajuisar', u'ajuizar'), (u'album', u'\xe1lbum'), (u'alcool\xe9mia', u'alcoolemia'), (u'aldi\xe3o', u'alde\xe3o'), (u'algerino', u'argelino'), (u'ameixeal', u'ameixial'), (u'amia\xe7a', u'amea\xe7a'), (u'analizar', u'analisar'), (u'and\xe1ste', u'andaste'), (u'anemona', u'an\xe9mona'), (u'antartico', u'ant\xe1rctico'), (u'ant\xe1rtico', u'ant\xe1rctico'), (u'antep\xf4r', u'antepor'), (u'ap\xe1rte', u'aparte'), (u'apiadeiro', u'apeadeiro'), (u'apiar', u'apear'), (u'apreciacao', u'aprecia\xe7\xe3o'), (u'arctico', u'\xe1rctico'), (u'arrazar', u'arrasar'), (u'\xe1rtico', u'\xe1rctico'), (u'artifice', u'art\xedfice'), (u'artif\xedcial', u'artificial'), (u'ascen\xe7\xe3o', u'ascens\xe3o'), (u'ass\xfacar', u'a\xe7\xfacar'), (u'aste', u'haste'), (u'aster\xedstico', u'asterisco'), (u'aver\xe7\xe3o', u'avers\xe3o'), (u'avizar', u'avisar'), (u'avulsso', u'avulso'), (u'ba\xednha', u'bainha'), (u'banca-rota', u'bancarrota'), (u'bandeija', u'bandeja'), (u'b\xe9b\xe9', u'beb\xe9'), (u'beige', u'bege'), (u'ben\xe7\xe3o', u'b\xean\xe7\xe3o'), (u'benefici\xeancia', u'benefic\xeancia'), (u'beneficiente', u'beneficente'), (u'benvinda', u'bem-vinda'), (u'benvindo', u'bem-vindo'), (u'boasvindas', u'boas-vindas'), (u'borborinho', u'burburinho'), (u'Brazil', u'Brasil'), (u'bussula', u'b\xfassola'), (u'cabo-verdeano', u'cabo-verdiano'), (u'caimbras', u'c\xe3ibras'), (u'calc\xe1reo', u'calc\xe1rio'), (u'calsado', u'cal\xe7ado'), (u'calv\xedce', u'calv\xedcie'), (u'camoneano', u'camoniano'), (u'campi\xe3o', u'campe\xe3o'), (u'can\xe7acos', u'cansa\xe7os'), (u'caracter', u'car\xe1cter'), (u'caract\xe9res', u'caracteres'), (u'catequeze', u'catequese'), (u'catequisador', u'catequizador'), (u'catequisar', u'catequizar'), (u'ch\xedcara', u'x\xedcara'), (u'ciclano', u'sicrano'), (u'cicrano', u'sicrano'), (u'cidad\xe3es', u'cidad\xe3os'), (u'cidad\xf5es', u'cidad\xe3os'), (u'cincoenta', u'cinquenta'), (u'cinseiro', u'cinzeiro'), (u'cinsero', u'sincero'), (u'citacoes', u'cita\xe7\xf5es'), (u'coaliz\xe3o', u'colis\xe3o'), (u'c\xf4dia', u'c\xf4dea'), (u'comb\xf3io', u'comboio'), (u'comp\xf4r', u'compor'), (u'concerteza', u'com certeza'), (u'constituia', u'constitu\xeda'), (u'constitu\xedu', u'constituiu'), (u'contato', u'contacto'), (u'contens\xe3o', u'conten\xe7\xe3o'), (u'contribuicoes', u'contribui\xe7\xf5es'), (u'c\xf4r', u'cor'), (u'corass\xe3o', u'cora\xe7\xe3o'), (u'cor\xe7ario', u'cors\xe1rio'), (u'cor\xe7\xe1rio', u'cors\xe1rio'), (u'cornprimidosinbo', u'comprimidozinho'), (u'cr\xe2neo', u'cr\xe2nio'), (u'dE', u'de'), (u'defeni\xe7\xe3o', u'defini\xe7\xe3o'), (u'defenido', u'definido'), (u'defenir', u'definir'), (u'deficite', u'd\xe9fice'), (u'degladiar', u'digladiar'), (u'deiche', u'deixe'), (u'desinteria', u'disenteria'), (u'despendio', u'disp\xeandio'), (u'desp\xeandio', u'disp\xeandio'), (u'desplic\xeancia', u'displic\xeancia'), (u'dificulidade', u'dificuldade'), (u'dispender', u'despender'), (u'dispendio', u'disp\xeandio'), (u'distribuido', u'distribu\xeddo'), (u'dru\xedda', u'druida'), (u'\xe9cr\xe3', u'ecr\xe3'), (u'ecran', u'ecr\xe3'), (u'\xe9cran', u'ecr\xe3'), (u'\xeale', u'ele'), (u'elice', u'h\xe9lice'), (u'\xe9lice', u'h\xe9lice'), (u'emiratos', u'emirados'), (u'engolis-te', u'engoliste'), (u'engulir', u'engolir'), (u'enguliste', u'engoliste'), (u'entertido', u'entretido'), (u'entitular', u'intitular'), (u'entreterimento', u'entretenimento'), (u'entreti-me', u'entretive-me'), (u'env\xf3lucro', u'inv\xf3lucro'), (u'er\xf3i', u'her\xf3i'), (u'escluir', u'excluir'), (u'esclus\xe3o', u'exclus\xe3o'), (u'escriv\xf5es', u'escriv\xe3es'), (u'esqueiro', u'isqueiro'), (u'esquesito', u'esquisito'), (u'estacoes', u'esta\xe7\xf5es'), (u'esteje', u'esteja'), (u'excava\xe7\xe3o', u'escava\xe7\xe3o'), (u'excavar', u'escavar'), (u'exdr\xfaxula', u'esdr\xfaxula'), (u'exdr\xfaxulas', u'esdr\xfaxulas'), (u'exitar', u'hesitar'), (u'explicacoes', u'explica\xe7\xf5es'), (u'exquisito', u'esquisito'), (u'extende', u'estende'), (u'extender', u'estender'), (u'f\xe0cilmenfe', u'facilmente'), (u'f\xe0cilmente', u'facilmente'), (u'fariam-lhe', u'far-lhe-iam'), (u'FARM\xc1ClAS', u'FARM\xc1CIAS'), (u'farmec\xeautico', u'farmac\xeautico'), (u'fassa', u'fa\xe7a'), (u'f\xe9bre', u'febre'), (u'fecula', u'f\xe9cula'), (u'f\xe9mea', u'f\xeamea'), (u'femenino', u'feminino'), (u'femininismo', u'feminismo'), (u'f\xedsiologista', u'fisiologista'), (u'fiz\xe9mos', u'fizemos'), (u'fizes-te', u'fizeste'), (u'fl\xf4r', u'flor'), (u'for\xe3o', u'foram'), (u'formalisar', u'formalizar'), (u'f\xf4ro', u'foro'), (u'fos-te', u'foste'), (u'frag\xe2ncia', u'fragr\xe2ncia'), (u'fran\xe7\xeas', u'franc\xeas'), (u'frasqutnho', u'frasquinho'), (u'frustado', u'fLine truncated
'rus': OrderedDict([(u'\u041d\u0404\u0419', u'\u041d\u0415\u0419'), (u'\u041e\u0420\u0413\u0417\u041d\u0418\u0417\u041c\u041e\u0411', u'\u041e\u0420\u0413\u0410\u041d\u0418\u0417\u041c\u0410'), (u'\u0427\u04570', u'\u0427\u0422\u041e'), (u'\u041d\u042d', u'\u041d\u0410'), (u'\u0421\u041e\u0421\u0404\u0414\u041d\u042e\u042e', u'\u0421\u041e\u0421\u0415\u0414\u041d\u042e\u042e'), (u'\u041f\u041b\u0417\u041d\u0404\u0422\u0423', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0423'), (u'\u0417\u0417\u0413\u042d\u0414\u041e\u041a', u'\u0417\u0410\u0413\u0410\u0414\u041e\u041a'), (u'\u0421\u041e\u0422\u0412\u041e\u0420\u0404\u041d\u0418\u042f', u'\u0421\u041e\u0422\u0412\u041e\u0420\u0415\u041d\u0418\u042f'), (u'\u041c\u0418\u0420\u042d', u'\u041c\u0418\u0420\u0410'), (u'\u041f\u041e\u042f\u0411\u041b\u0404\u041d\u0418\u042f', u'\u041f\u041e\u042f\u0412\u041b\u0415\u041d\u0418\u042f'), (u'\u0417\u0404\u041c\u041b\u0404', u'\u0417\u0415\u041c\u041b\u0415'), (u'\u0404\u0429\u0404', u'\u0415\u0429\u0401'), (u'\u0422\u0404\u041c\u041d\u042c\u0406\u0425', u'\u0422\u0415\u041c\u041d\u042b\u0425'), (u'\u0421\u0404\u0420\u042c\u0404\u0417\u041d\u042c\u0406\u041c', u'\u0421\u0415\u0420\u042c\u0415\u0417\u041d\u042b\u041c'), (u'\u041f\u041e\u0428\u0406\u04060', u'\u041f\u041e\u0428\u041b\u041e'), (u'\u041f\u04400\u0418\u04170\u0428\u0404\u041b', u'\u041f\u0420\u041e\u0418\u0417\u041e\u0428\u0415\u041b'), (u'\u0421\u0404\u041a\u0420\u0404\u0422\u042d\u041c\u0418', u'\u0421\u0415\u041a\u0420\u0415\u0422\u0410\u041c\u0418'), (u'\u041c\u042d\u0422\u0404\u0420\u0418\u0417\u041b\u042c\u0406', u'\u041c\u0410\u0422\u0415\u0420\u0418\u0410\u041b\u042b'), (u'\u041f\u042f\u0422\u0404\u041d', u'\u041f\u042f\u0422\u0415\u041d'), (u'\u041f\u041b\u0430\u041d\u0404\u0457\u0404', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0415'), (u'\u041a\u0417\u0422\u042d\u041a\u041b\u0418\u0417\u041c', u'\u041a\u0410\u0422\u0410\u041a\u041b\u0418\u0417\u041c'), (u'\u041e\u041a\u0417\u0417\u0417\u041b\u0421\u042f', u'\u041e\u041a\u0410\u0417\u0410\u041b\u0421\u042f'), (u'\u0414\u042d\u041b\u042c\u0428\u0415', u'\u0414\u0410\u041b\u042c\u0428\u0415'), (u'\u0422\u0412\u041a', u'\u0422\u0410\u041a'), (u'\u041f\u041b\u0417\u041d\u0404\u0422\u0417', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0410'), (u'\u0427\u0404\u0413\u041e', u'\u0427\u0415\u0413\u041e'), (u'\u0423\u0417\u041d\u042d\u0422\u042c', u'\u0423\u0417\u041d\u0410\u0422\u042c'), (u'\u041f\u041b\u042d\u041d\u0404\u0422\u0404', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0415'), (u'\u041d\u0404\u041c', u'\u041d\u0415\u041c'), (u'\u0411\u041e\u0417\u041c\u041e\u0416\u041d\u0417', u'\u0412\u041e\u0417\u041c\u041e\u0416\u041d\u0410'), (u'\u0421\u041e\u0411\u0404\u0420\u0428\u0404\u041d\u041d\u041e', u'\u0421\u041e\u0412\u0415\u0420\u0428\u0415\u041d\u041d\u041e'), (u'\u0418\u041d\u042d\u0427\u0404', u'\u0418\u041d\u0410\u0427\u0415'), (u'\u0411\u0421\u0404', u'\u0412\u0421\u0415'), (u'\u041d\u0415\u0414\u041e\u0421\u0422\u0417\u0422\u041a\u0418', u'\u041d\u0415\u0414\u041e\u0421\u0422\u0410\u0422\u041a\u0418'), (u'\u041d\u041e\u0412\u042c\u0406\u0404', u'\u041d\u041e\u0412\u042b\u0415'), (u'\u0412\u0404\u041b\u0418\u041a\u041e\u041b\u0404\u041f\u041d\u042d\u042f', u'\u0412\u0415\u041b\u0418\u041a\u041e\u041b\u0415\u041f\u041d\u0410\u042f'), (u'\u041e\u0421\u0422\u042d\u0406\u0406\u041e\u0421\u042c', u'\u041e\u0421\u0422\u0410\u041b\u041e\u0421\u042c'), (u'\u041d\u0417\u041b\u0418\u0427\u0418\u0404', u'\u041d\u0410\u041b\u0418\u0427\u0418\u0415'), (u'\u0431\u042b', u'\u0431\u044b'), (u'\u041f\u0420\u041e\u0426\u0412\u0415\u0422\u0412\u0422\u042c', u'\u041f\u0420\u041e\u0426\u0412\u0415\u0422\u0410\u0422\u042c'), (u'\u041a\u0417\u041a', u'\u041a\u0410\u041a'), (u'\u0412\u041e\u0414\u0417', u'\u0412\u041e\u0414\u0410'), (u'\u041d\u0417\u0428\u0415\u041b', u'\u041d\u0410\u0428\u0415\u041b'), (u'\u041d\u0404', u'\u041d\u0415'), (u'\u0422\u041e\u0416\u0404', u'\u0422\u041e\u0416\u0415'), (u'\u0412\u0423\u041b\u041a\u042d\u041d\u0418\u0427\u0404\u0421\u041a\u041e\u0419', u'\u0412\u0423\u041b\u041a\u0410\u041d\u0418\u0427\u0415\u0421\u041a\u041e\u0419'), (u'\u042d\u041a\u0422\u0418\u0411\u041d\u041e\u0421\u0422\u0418', u'\u0410\u041a\u0422\u0418\u0412\u041d\u041e\u0421\u0422\u0418'), (u'\u041f\u041e\u042f\u0412\u0418\u041b\u0417\u0421\u042c', u'\u041f\u041e\u042f\u0412\u0418\u041b\u0410\u0421\u042c'), (u'\u041d\u041e\u0412\u0417\u042f', u'\u041d\u041e\u0412\u0410\u042f'), (u'\u0421\u0422\u0420\u042d\u0422\u0404\u0413\u0418\u042f', u'\u0421\u0422\u0420\u0410\u0422\u0415\u0413\u0418\u042f'), (u'\u0423\u0421\u041f\u0404\u0428\u041d0', u'\u0423\u0421\u041f\u0415\u0428\u041d\u041e'), (u'\u041f\u041e\u0421\u0417\u0414\u041a\u0423', u'\u041f\u041e\u0421\u0410\u0414\u041a\u0423'), (u'\u0413\u041e\u0422\u041e\u0411\u042b', u'\u0413\u041e\u0422\u041e\u0412\u042b'), (u'\u041d\u0417\u0427\u0417\u0422\u042c', u'\u041d\u0410\u0427\u0410\u0422\u042c'), (u'\u041e\u0425\u041e\u0422\u042d', u'\u041e\u0425\u041e\u0422\u0410'), (u'\u041f\u0420\uLine truncated
'spa': OrderedDict([(u'No', u'No.'), (u'KBs', u'kB'), (u'Vd', u'Ud'), (u'N\xb0', u'N.\xb0'), (u'n\xb0', u'n.\xb0'), (u'nro.', u'n.\xb0'), (u'Nro.', u'N.\xb0'), (u'aca', u'ac\xe1'), (u'actuas', u'act\xfaas'), (u'actues', u'act\xfaes'), (u'adios', u'adi\xf3s'), (u'agarrenla', u'ag\xe1rrenla'), (u'agarrenlo', u'ag\xe1rrenlo'), (u'agarrandose', u'agarr\xe1ndose'), (u'algun', u'alg\xfan'), (u'alli', u'all\xed'), (u'alla', u'all\xe1'), (u'alejate', u'al\xe9jate'), (u'ahi', u'ah\xed'), (u'angel', u'\xe1ngel'), (u'angeles', u'\xe1ngeles'), (u'apagala', u'ap\xe1gala'), (u'aqui', u'aqu\xed'), (u'asi', u'as\xed'), (u'bahia', u'bah\xeda'), (u'busqueda', u'b\xfasqueda'), (u'busquedas', u'b\xfasquedas'), (u'callate', u'c\xe1llate'), (u'carcel', u'c\xe1rcel'), (u'camara', u'c\xe1mara'), (u'caido', u'ca\xeddo'), (u'cabron', u'cabr\xf3n'), (u'camion', u'cami\xf3n'), (u'codigo', u'c\xf3digo'), (u'codigos', u'c\xf3digos'), (u'comence', u'comenc\xe9'), (u'comprate', u'c\xf3mprate'), (u'consegui', u'consegu\xed'), (u'confias', u'conf\xedas'), (u'convertira', u'convertir\xe1'), (u'corazon', u'coraz\xf3n'), (u'crei', u'cre\xed'), (u'creia', u'cre\xeda'), (u'creido', u'cre\xeddo'), (u'creiste', u'cre\xedste'), (u'cubrenos', u'c\xfabrenos'), (u'comio', u'comi\xf3'), (u'dara', u'dar\xe1'), (u'dia', u'd\xeda'), (u'dias', u'd\xedas'), (u'debio', u'debi\xf3'), (u'demelo', u'd\xe9melo'), (u'dimelo', u'd\xedmelo'), (u'denoslo', u'd\xe9noslo'), (u'deselo', u'd\xe9selo'), (u'decia', u'dec\xeda'), (u'decian', u'dec\xedan'), (u'detras', u'detr\xe1s'), (u'deberia', u'deber\xeda'), (u'deberas', u'deber\xe1s'), (u'deberias', u'deber\xedas'), (u'deberian', u'deber\xedan'), (u'deberiamos', u'deber\xedamos'), (u'dejame', u'd\xe9jame'), (u'dejate', u'd\xe9jate'), (u'dejalo', u'd\xe9jalo'), (u'dejarian', u'dejar\xedan'), (u'damela', u'd\xe1mela'), (u'despues', u'despu\xe9s'), (u'diciendome', u'dici\xe9ndome'), (u'dificil', u'dif\xedcil'), (u'dificiles', u'dif\xedciles'), (u'disculpate', u'disc\xfalpate'), (u'dolares', u'd\xf3lares'), (u'hechar', u'echar'), (u'examenes', u'ex\xe1menes'), (u'empezo', u'empez\xf3'), (u'empujon', u'empuj\xf3n'), (u'empujalo', u'emp\xfajalo'), (u'escondanme', u'esc\xf3ndanme'), (u'esperame', u'esp\xe9rame'), (u'estara', u'estar\xe1'), (u'estare', u'estar\xe9'), (u'estaria', u'estar\xeda'), (u'estan', u'est\xe1n'), (u'estaran', u'estar\xe1n'), (u'estabamos', u'est\xe1bamos'), (u'estuvieramos', u'estuvi\xe9ramos'), (u'exito', u'\xe9xito'), (u'facil', u'f\xe1cil'), (u'fiscalia', u'fiscal\xeda'), (u'fragil', u'fr\xe1gil'), (u'fragiles', u'fr\xe1giles'), (u'frances', u'franc\xe9s'), (u'gustaria', u'gustar\xeda'), (u'habia', u'hab\xeda'), (u'habias', u'hab\xedas'), (u'habian', u'hab\xedan'), (u'habrian', u'habr\xedan'), (u'habrias', u'habr\xedas'), (u'hagalo', u'h\xe1galo'), (u'haria', u'har\xeda'), (u'increible', u'incre\xedble'), (u'incredulo', u'incr\xe9dulo'), (u'intentalo', u'int\xe9ntalo'), (u'ire', u'ir\xe9'), (u'jovenes', u'j\xf3venes'), (u'ladron', u'ladr\xf3n'), (u'linea', u'l\xednea'), (u'llamame', u'll\xe1mame'), (u'llevalo', u'll\xe9valo'), (u'mama', u'mam\xe1'), (u'maricon', u'maric\xf3n'), (u'mayoria', u'mayor\xeda'), (u'metodo', u'm\xe9todo'), (u'metodos', u'm\xe9todos'), (u'mio', u'm\xedo'), (u'mostro', u'mostr\xf3'), (u'morira', u'morir\xe1'), (u'muevete', u'mu\xe9vete'), (u'murio', u'muri\xf3'), (u'numero', u'n\xfamero'), (u'numeros', u'n\xfameros'), (u'ningun', u'ning\xfan'), (u'oido', u'o\xeddo'), (u'oidos', u'o\xeddos'), (u'oimos', u'o\xedmos'), (u'oiste', u'o\xedste'), (u'pasale', u'p\xe1sale'), (u'pasame', u'p\xe1same'), (u'paraiso', u'para\xedso'), (u'parate', u'p\xe1rate'), (u'pense', u'pens\xe9'), (u'peluqueria', u'peluquer\xeda'), (u'platano', u'pl\xe1tano'), (u'plastico', u'pl\xe1stico'), (u'plasticos', u'pl\xe1sticos'), (u'policia', u'polic\xeda'), (u'policias', u'polic\xedas'), (u'poster', u'p\xf3ster'), (u'podia', u'pod\xeda'), (u'podias', u'pod\xedas'), (u'podria', u'podr\xeda'), (u'podrian', u'podr\xedan'), (u'podrias', u'podr\xedas'), (u'podriamos', u'podr\xedamos'), (u'prometio', u'prometi\xf3'), (u'proposito', u'prop\xf3sito'), (u'pideselo', u'p\xeddeselo'), (u'ponganse', u'p\xf3nganse'), (u'prometeme', u'prom\xe9teme'), (u'publico', u'p\xfablico'), (u'publicos', u'p\xfablicos'), (u'publicamente', u'p\xfablicamente'), (u'quedate', u'qu\xe9date'), (u'queria', u'quer\xeda'), (u'querrias', u'querr\xedas'), (u'querian', u'quer\xedan'), (u'rapido', u'r\xe1pido'), (u'rapidamente', u'r\xe1pidamente'), (u'razon', u'raz\xf3n'), (u'rehusen', u'reh\xfasen'), (u'rie', u'r\xede'), (u'rias', u'r\xedas'), (u'rindete', u'r\xedndete'), (u'sacame', u's\xe1came'), (u'sentian', u'sent\xedan'), (u'sientate', u'si\xe9ntate'), (u'sera', u'ser\xe1'), (u'soplon', u'sopl\xf3n'), (u'sueltalo', u'su\xe9ltalo'), (u'tambien', u'tambi\xe9n'), (u'teoria', u'teor\xeda'), (u'tendra', u'tendr\xe1'), (u'telefono', u'tel\xe9fono'), (u'tipica', u't\xedpica'), (u'todavia', u'todav\xeda'), (u'tomalo', u't\xf3malo'), (u'tonteriaLine truncated
'srp': OrderedDict([(u'\u010du', u'\u0107u'), (u'\u010de\u0161', u'\u0107e\u0161'), (u'\u010de', u'\u0107e'), (u'\u0107\u0161', u'\u0107e\u0161'), (u'\u0107mo', u'\u0107emo'), (u'\u0107te', u'\u0107ete'), (u'\u010demo', u'\u0107emo'), (u'\u010dete', u'\u010dete'), (u'djete', u'dijete'), (u'Hey', u'Hej'), (u'hey', u'hej'), (u'htjeo', u'htio'), (u'Ho\u010de\u0161', u'Ho\u0107e\u0161'), (u'ho\u010de\u0161', u'ho\u0107e\u0161'), (u'i\u010di', u'i\u0107i'), (u'jel', u"je l'"), (u'Jel', u"Je l'"), (u'nedaj', u'ne daj'), (u'Rje\u0161it', u'Rije\u0161it'), (u'smjeo', u'smio'), (u'uop\u010de', u'uop\u0107e'), (u'valda', u'valjda'), (u'\u017eelila', u'\u017eeljela')]),
'swe': OrderedDict([(u'l\xe2rt', u'l\xe4rt'), (u'hederv\xe5rda', u'hederv\xe4rda'), (u'storm\xe2stare', u'storm\xe4stare'), (u'Avf\xe2rd', u'Avf\xe4rd'), (u't\xe2lten', u't\xe4lten'), (u'\xe2rjag', u'\xe4r jag'), (u'\xe4rjag', u'\xe4r jag'), (u'j\xe2mlikar', u'j\xe4mlikar'), (u'Riskako\ufb02', u'Riskakor'), (u'Karamellen/', u'Karamellen'), (u'Lngen\xfcng', u'Ingenting'), (u'\xe4rju', u'\xe4r ju'), (u'S\xe1', u'S\xe5'), (u'n\xe4rjag', u'n\xe4r jag'), (u'alltjag', u'allt jag'), (u'g\xf6rjag', u'g\xf6r jag'), (u'trorjag', u'tror jag'), (u'varju', u'var ju'), (u'g\xf6rju', u'g\xf6r ju'), (u'kanju', u'kan ju'), (u'blirjag', u'blir jag'), (u's\xe4gerjag', u's\xe4ger jag'), (u'beh\xe5llerjag', u'beh\xe5ller jag'), (u'pr\xf8blem', u'problem'), (u'r\xe4ddadeju', u'r\xe4ddade ju'), (u'hon\xf8m', u'honom'), (u'Ln', u'In'), (u'sv\xe5r\ufb02\xf6rtad', u'sv\xe5rfl\xf6rtad'), (u'\xf8ch', u'och'), (u'\ufb02\xf6rtar', u'fl\xf6rtar'), (u'k\xe4nnerjag', u'k\xe4nner jag'), (u'\ufb02ickan', u'flickan'), (u'sn\xf8', u'sn\xf6'), (u'gerju', u'ger ju'), (u'k\xf8ntakter', u'kontakter'), (u'\xf8lycka', u'olycka'), (u'n\xf8lla', u'nolla'), (u'sinnenajublar', u'sinnena jublar'), (u'ijobbet', u'i jobbet'), (u'F\xe5rjag', u'F\xe5r jag'), (u'Ar', u'\xc4r'), (u'liggerju', u'ligger ju'), (u'um', u'om'), (u'lbland', u'Ibland'), (u'skjuterjag', u'skjuter jag'), (u'Vadd\xe5', u'Vad d\xe5'), (u'pratarj\xe4mt', u'pratar j\xe4mt'), (u'harju', u'har ju'), (u'sitterjag', u'sitter jag'), (u'h\xe4\ufb02a', u'h\xe4rja'), (u's\ufb01\xe4l', u'stj\xe4l'), (u'F\xd6U', u'F\xf6lj'), (u'varf\xf6rjag', u'varf\xf6r jag'), (u's\ufb01\xe4rna', u'stj\xe4rna'), (u'b\xf6\ufb02ar', u'b\xf6rjar'), (u'b\xf6\ufb02an', u'b\xf6rjan'), (u'st\xe4ri', u'st\xe5r'), (u'p\xe4', u'p\xe5'), (u'harjag', u'har jag'), (u'attjag', u'att jag'), (u'Verkarjag', u'Verkar jag'), (u'K\xe4nnerjag', u'K\xe4nner jag'), (u'd\xe4rjag', u'd\xe4r jag'), (u'tu\ufb01', u'tuff'), (u'lurarjag', u'lurar jag'), (u'varj\xe4ttebra', u'var j\xe4ttebra'), (u'allvan', u'allvar'), (u'deth\xe4r', u'det h\xe4r'), (u'va\ufb02e', u'varje'), (u'F\xf6Uer', u'F\xf6ljer'), (u'personalm\xf6tetl', u'personalm\xf6tet!'), (u'harjust', u'har just'), (u'\xe4rj\xe4tteduktig', u'\xe4r j\xe4tteduktig'), (u'd\xe4rja', u'd\xe4r ja'), (u'lngen\xfcng', u'lngenting'), (u'iluften', u'i luften'), (u'\xf6sen', u'\xf6ser'), (u'tv\xe2', u'tv\xe5'), (u'Uejerna', u'Tjejerna'), (u'h\xe5n*', u'h\xe5rt'), (u'\xc4rjag', u'\xc4r jag'), (u'keL', u'Okej'), (u'F\xf6rjag', u'F\xf6r jag'), (u'varj\xe4ttekul', u'var j\xe4ttekul'), (u'k\xe4mpan', u'k\xe4mpar'), (u'mycketjobb', u'mycket jobb'), (u'Uus', u'ljus'), (u'serjag', u'ser jag'), (u'vetjag', u'vet jag'), (u'f\xe5rjag', u'f\xe5r jag'), (u'hurjag', u'hur jag'), (u'f\xf6rs\xf6kerjag', u'f\xf6rs\xf6ker jag'), (u't\xe1nagel', u't\xe5nagel'), (u'va\xfce', u'varje'), (u'Uudet', u'ljudet'), (u'amhopa', u'allihopa'), (u'V\xe4\xfc', u'V\xe4lj'), (u'g\xe4ri', u'g\xe5r'), (u'r\xf6d\xfcus', u'r\xf6dljus'), (u'Uuset', u'ljuset'), (u'Rid\xe0n', u'Rid\xe5n'), (u'vi\xfca', u'vilja'), (u'g\xe5ri', u'g\xe5r i'), (u'Hurd\xe5', u'Hur d\xe5'), (u'inter\\/juar', u'intervjuar'), (u'menarjag', u'menar jag'), (u'spyrjag', u'spyr jag'), (u'bri\xfcera', u'briljera'), (u'N\xe4rjag', u'N\xe4r jag'), (u'ner\\/\xf6s', u'nerv\xf6s'), (u'ilivets', u'i livets'), (u'n\xe4got', u'n\xe5got'), (u'p\xe0', u'p\xe5'), (u'Lnnan', u'Innan'), (u'Uf', u'Ut'), (u'lnnan', u'Innan'), (u'D\xe0ren', u'D\xe5ren'), (u'F\xe0rjag', u'F\xe5r jag'), (u'Vad\xe4rdetd\xe4L', u'Vad \xe4r det d\xe4r'), (u'sm\xe0tjuv', u'sm\xe5tjuv'), (u't\xe0gr\xe5nare', u't\xe5gr\xe5nare'), (u'dit\xe0t', u'dit\xe5t'), (u's\xe4', u's\xe5'), (u'v\xe0rdsl\xf6sa', u'v\xe5rdsl\xf6sa'), (u'n\xe0n', u'n\xe5n'), (u'kommerjag', u'kommer jag'), (u'\xe4rj\xe4ttebra', u'\xe4r j\xe4ttebra'), (u'\xe4rj\xe4vligt', u'\xe4r j\xe4vligt'), (u'\xe0kerjag', u'\xe5ker jag'), (u'ellerjapaner', u'eller japaner'), (u'attjaga', u'att jaga'), (u'eften', u'efter'), (u'h\xe4stan', u'h\xe4star'), (u'Lntensivare', u'Intensivare'), (u'fr\xe0garjag', u'fr\xe5gar jag'), (u'pen/ers', u'pervers'), (u'r\xe0barkade', u'r\xe5barkade'), (u'styrkon', u'styrkor'), (u'Dif\xe5f', u'Dit\xe5t'), (u'h\xe4nden', u'h\xe4nder'), (u'f\xf6\ufb01a', u'f\xf6lja'), (u'Idioten/', u'Idioter!'), (u'Varf\xf6rjagade', u'Varf\xf6r jagade'), (u'd\xe4rf\xf6rjag', u'd\xe4rf\xf6r jag'), (u'forjag', u'for jag'), (u'Iivsgladje', u'livsgl\xe4dje'), (u'narjag', u'n\xe4r jag'), (u'sajag', u'sa jag'), (u'genastja', u'genast ja'), (u'rockument\xe0ren', u'rockument\xe4ren'), (u'turne', u'turn\xe9'), (u'fickjag', u'fick jag'), (u'sager', u's\xe4ger'), (u'Ijush\xe5rig', u'ljush\xe5rig'), (u'tradg\xe5rdsolycka', u'tr\xe4dg\xe5rdsolycka'), (u'kvavdes', u'kv\xe4vdes'), (u'd\xe0rja', u'd\xe4r ja'), (u'hedersgaster', u'hedersg\xe4ster'), (u'Nar', u'N\xe4r'), (u'smaki\xf6sa', u'smakl\xf6sa'), (u'lan', u'Ian'), (u'Lan', u'Ian'), (u'eri', u'er i'), (u'universitetsamne', u'universitets\xe4mne'), (u'garna', u'g\xe4rna'), (u'ar', u'\xe4r'), (u'baltdLine truncated
data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'IVI', u'M'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'Haner', u'Han er'), (u'JaveL', u'Javel'), (u'Pa//e', u'Palle'), (u'bffte', u'bitte'), (u'Utro//gt', u'Utroligt'), (u'Kommerdu', u'Kommer du'), (u'smi/er', u'smiler'), (u'/eg', u'leg'), (u'harvinger', u'har vinger'), (u'/et', u'let'), (u'erjeres', u'er jeres'), (u'hardet', u'har det'), (u't\xe6nktjer', u't\xe6nkt jer'), (u'erjo', u'er jo'), (u'sti/', u'stil'), (u'Iappe', u'lappe'), (u'Beklagel\xe7', u'Beklager,'), (u'vardet', u'var det'), (u'afden', u'af den'), (u'snupperjeg', u'snupper jeg'), (u'ikkejeg', u'ikke jeg'), (u'bliverjeg', u'bliver jeg'), (u'hartravit', u'har travlt'), (u'pandekagef/ag', u'pandekageflag'), (u'Stormvarsell', u'Stormvarsel!'), (u'stormvejn', u'stormvejr.'), (u'morgenkomp/et', u'morgenkomplet'), (u'/yv', u'lyv'), (u'varjo', u'var jo'), (u'/eger', u'leger'), (u'harjeg', u'har jeg'), (u'havdejeg', u'havde jeg'), (u'hvorjeg', u'hvor jeg'), (u'n\xe5rjeg', u'n\xe5r jeg'), (u'g\xe5rvi', u'g\xe5r vi'), (u'atjeg', u'at jeg'), (u'isine', u'i sine'), (u'f\xe5rjeg', u'f\xe5r jeg'), (u'k\xe6rtighed', u'k\xe6rlighed'), (u'skullejeg', u'skulle jeg'), (u'laest', u'l\xe6st'), (u'laese', u'l\xe6se'), (u'g\xf8rjeg', u'g\xf8r jeg'), (u'g\xf8rvi', u'g\xf8r vi'), (u'angrerjo', u'angrer jo'), (u'Hvergang', u'Hver gang'), (u'erder', u'er der'), (u'villetilgive', u'ville tilgive'), (u'\ufb01eme', u'fjeme'), (u'genopst\xe5ri', u'genopst\xe5r i'), (u'svigtejer', u'svigte jer'), (u'kommernu', u'kommer nu'), (u'n\xe5rman', u'n\xe5r man'), (u'erfire', u'er fire'), (u'Hvorfor\ufb01nderdu', u'Hvorfor \ufb01nder du'), (u'undertigt', u'underligt'), (u'itroen', u'i troen'), (u'erl\xf8gnt', u'er l\xf8gn!'), (u'g\xf8rden', u'g\xf8r den'), (u'forhelvede', u'for helvede'), (u'hjpe', u'hj\xe6lpe'), (u'togeti', u'toget i'), (u'M\xe5jeg', u'M\xe5 jeg'), (u'savnerjer', u'savner jer'), (u'erjeg', u'er jeg'), (u'vaere', u'v\xe6re'), (u'geme', u'gerne'), (u'trorp\xe5', u'tror p\xe5'), (u'forham', u'for ham'), (u'afham', u'af ham'), (u'harjo', u'har jo'), (u'ovema\ufb01et', u'overnattet'), (u'begae\ufb01ighed', u'beg\xe6rlighed'), (u'sy\u2019g', u'syg'), (u'Imensjeg', u'Imens jeg'), (u'bliverdu', u'bliver du'), (u'\ufb01ser', u'fiser'), (u'manipuierer', u'manipulerer'), (u'forjeg', u'for jeg'), (u'iivgivendefor', u'livgivende for'), (u'formig', u'for mig'), (u'Hardu', u'Har du'), (u'fornold', u'forhold'), (u'defrelste', u'de frelste'), (u'S\xe5jeg', u'S\xe5 jeg'), (u'varjeg', u'var jeg'), (u'g\xf8rved', u'g\xf8r ved'), (u'kalderjeg', u'kalder jeg'), (u'\ufb02ytte', u'flytte'), (u'handlerdet', u'handler det'), (u'trorjeg', u'tror jeg'), (u'\ufb02ytter', u'flytter'), (u'soverjeg', u'sover jeg'), (u'\ufb01nderud', u'\ufb01nder ud'), (u'naboerp\xe5', u'naboer p\xe5'), (u'ervildt', u'er vildt'), (u'v\xe6reher', u'v\xe6re her'), (u'hyggerjer', u'hygger jer'), (u'borjo', u'bor jo'), (u'kommerikke', u'kommer ikke'), (u'folkynde', u'forkynde'), (u'farglad', u'far glad'), (u'misterjeg', u'mister jeg'), (u'\ufb01nt', u'fint'), (u'Harl', u'Har I'), (u'bedejer', u'bede jer'), (u'synesjeg', u'synes jeg'), (u'vartil', u'var til'), (u'eren', u'er en'), (u'\\Al', u'Vil'), (u'\\A', u'Vi'), (u'fjeme', u'fjerne'), (u'Iigefyldt', u'lige fyldt'), (u'ertil', u'er til'), (u'fa\ufb01igt', u'farligt'), (u'\ufb01nder', u'finder'), (u'\ufb01ndes', u'findes'), (u'irettesae\ufb01else', u'irettes\xe6ttelse'), (u'ermed', u'er med'), (u'\xe8n', u'\xe9n'), (u'gikjoi', u'gik jo i'), (u'Hvisjeg', u'Hvis jeg'), (u'ovema\ufb01er', u'overnatter'), (u'hoident', u'holdent'), (u'\\Adne', u'Vidne'), (u'fori', u'for i'), (u'vei', u'vel'), (u'savnerjerjo', u'savner jer jo'), (u'elskerjer', u'elsker jer'), (u'harl\xf8jet', u'har l\xf8jet'), (u'eri', u'er i'), (u'\ufb01ende', u'fjende'), (u'derjo', u'der jo'), (u'sigerjo', u'siger jo'), (u'menerjeg', u'mener jeg'), (u'Harjeg', u'Har jeg'), (u'sigerjeg', u'siger jeg'), (u'splitterjeg', u'splitter jeg'), (u'erjournalist', u'er journalist'), (u'erjoumalist', u'er journalist'), (u'Forjeg', u'For jeg'), (u'g\xe2rjeg', u'g\xe5r jeg'), (u'N\xe2rjeg', u'N\xe5r jeg'), (u'a\ufb02lom', u'afkom'), (u'farerjo', u'farer jo'), (u'tagerjeg', u'tager jeg'), (u'Virkerjeg', u'Virker jeg'), (u'morerjer', u'morer jer'), (u'kommerjo', u'kommer jo'), (u'istand', u'i stand'), (u'b\xf8m', u'b\xf8rn'), (u'frygterjeg', u'frygter jeg'), (u'kommerjeg', u'kommer jeg'), (u'eriournalistelev', u'er journalistelev'), (u'harfat', u'har fat'), (u'f\xe5r\ufb01ngre', u'f\xe5r \ufb01ngre'), (u'sl\xe2rjeg', u'sl\xe5r jeg'), (u'bam', u'barn'), (u'erjournalistelev', u'er journalistelev'), (u'politietjo', u'politiet jo'), (u'elskerjo', u'elsker jo'), (u'vari', u'var i'), (u'fornemmerjeres', u'fornemmer jeres'), (u'udkl\xe6kketl', u'udkl\xe6kket!'), (u'\xed', u'i'), (u'nyi', u'ny i'), (u'Iumijelse', u'forn\xf8jelse'), (u'vures', u'vores'), (u'I/Vash\xedngtan', u'Washington'), (u'opleverjeg', u'oplever jeg'), (u'PANTEL\xc3NER', u'PANTEL\xc5NER'), (u'Gudmurgen', u'Godmorgen'), (u'SKYDEV\xc3BEN', u'SKYDEV\xc5BEN'), (u'P\xLine truncated
'pattern': u"(um)\\bHaner\\b|\\bJaveL\\b|\\bPa\\/\\/e\\b|\\bbffte\\b|\\bUtro\\/\\/gt\\b|\\bKommerdu\\b|\\bsmi\\/er\\b|\\b\\/eg\\b|\\bharvinger\\b|\\b\\/et\\b|\\berjeres\\b|\\bhardet\\b|\\bt\\\xe6nktjer\\b|\\berjo\\b|\\bsti\\/\\b|\\bIappe\\b|\\bBeklagel\\\xe7\\b|\\bvardet\\b|\\bafden\\b|\\bsnupperjeg\\b|\\bikkejeg\\b|\\bbliverjeg\\b|\\bhartravit\\b|\\bpandekagef\\/ag\\b|\\bStormvarsell\\b|\\bstormvejn\\b|\\bmorgenkomp\\/et\\b|\\b\\/yv\\b|\\bvarjo\\b|\\b\\/eger\\b|\\bharjeg\\b|\\bhavdejeg\\b|\\bhvorjeg\\b|\\bn\\\xe5rjeg\\b|\\bg\\\xe5rvi\\b|\\batjeg\\b|\\bisine\\b|\\bf\\\xe5rjeg\\b|\\bk\\\xe6rtighed\\b|\\bskullejeg\\b|\\blaest\\b|\\blaese\\b|\\bg\\\xf8rjeg\\b|\\bg\\\xf8rvi\\b|\\bangrerjo\\b|\\bHvergang\\b|\\berder\\b|\\bvilletilgive\\b|\\b\\\ufb01eme\\b|\\bgenopst\\\xe5ri\\b|\\bsvigtejer\\b|\\bkommernu\\b|\\bn\\\xe5rman\\b|\\berfire\\b|\\bHvorfor\\\ufb01nderdu\\b|\\bundertigt\\b|\\bitroen\\b|\\berl\\\xf8gnt\\b|\\bg\\\xf8rden\\b|\\bforhelvede\\b|\\bhjpe\\b|\\btogeti\\b|\\bM\\\xe5jeg\\b|\\bsavnerjer\\b|\\berjeg\\b|\\bvaere\\b|\\bgeme\\b|\\btrorp\\\xe5\\b|\\bforham\\b|\\bafham\\b|\\bharjo\\b|\\bovema\\\ufb01et\\b|\\bbegae\\\ufb01ighed\\b|\\bsy\\\u2019g\\b|\\bImensjeg\\b|\\bbliverdu\\b|\\b\\\ufb01ser\\b|\\bmanipuierer\\b|\\bforjeg\\b|\\biivgivendefor\\b|\\bformig\\b|\\bHardu\\b|\\bfornold\\b|\\bdefrelste\\b|\\bS\\\xe5jeg\\b|\\bvarjeg\\b|\\bg\\\xf8rved\\b|\\bkalderjeg\\b|\\b\\\ufb02ytte\\b|\\bhandlerdet\\b|\\btrorjeg\\b|\\b\\\ufb02ytter\\b|\\bsoverjeg\\b|\\b\\\ufb01nderud\\b|\\bnaboerp\\\xe5\\b|\\bervildt\\b|\\bv\\\xe6reher\\b|\\bhyggerjer\\b|\\bborjo\\b|\\bkommerikke\\b|\\bfolkynde\\b|\\bfarglad\\b|\\bmisterjeg\\b|\\b\\\ufb01nt\\b|\\bHarl\\b|\\bbedejer\\b|\\bsynesjeg\\b|\\bvartil\\b|\\beren\\b|\\b\\\\Al\\b|\\b\\\\A\\b|\\bfjeme\\b|\\bIigefyldt\\b|\\bertil\\b|\\bfa\\\ufb01igt\\b|\\b\\\ufb01nder\\b|\\b\\\ufb01ndes\\b|\\birettesae\\\ufb01else\\b|\\bermed\\b|\\b\\\xe8n\\b|\\bgikjoi\\b|\\bHvisjeg\\b|\\bovema\\\ufb01er\\b|\\bhoident\\b|\\b\\\\Adne\\b|\\bfori\\b|\\bvei\\b|\\bsavnerjerjo\\b|\\belskerjer\\b|\\bharl\\\xf8jet\\b|\\beri\\b|\\b\\\ufb01ende\\b|\\bderjo\\b|\\bsigerjo\\b|\\bmenerjeg\\b|\\bHarjeg\\b|\\bsigerjeg\\b|\\bsplitterjeg\\b|\\berjournalist\\b|\\berjoumalist\\b|\\bForjeg\\b|\\bg\\\xe2rjeg\\b|\\bN\\\xe2rjeg\\b|\\ba\\\ufb02lom\\b|\\bfarerjo\\b|\\btagerjeg\\b|\\bVirkerjeg\\b|\\bmorerjer\\b|\\bkommerjo\\b|\\bistand\\b|\\bb\\\xf8m\\b|\\bfrygterjeg\\b|\\bkommerjeg\\b|\\beriournalistelev\\b|\\bharfat\\b|\\bf\\\xe5r\\\ufb01ngre\\b|\\bsl\\\xe2rjeg\\b|\\bbam\\b|\\berjournalistelev\\b|\\bpolitietjo\\b|\\belskerjo\\b|\\bvari\\b|\\bfornemmerjeres\\b|\\budkl\\\xe6kketl\\b|\\b\\\xed\\b|\\bnyi\\b|\\bIumijelse\\b|\\bvures\\b|\\bI\\/Vash\\\xedngtan\\b|\\bopleverjeg\\b|\\bPANTEL\\\xc3NER\\b|\\bGudmurgen\\b|\\bSKYDEV\\\xc3BEN\\b|\\bP\\\xc3LIDELIG\\b|\\bavertalte\\b|\\bOms\\\xedder\\b|\\blurteb\\\xe5d\\b|\\bTelrslning\\b|\\bmiU\\\xf8\\b|\\bg\\\xe5ri\\b|\\bFan\\/el\\b|\\babe\\\ufb01\\\xe6s\\b|\\bhartalt\\b|\\b\\\\\\\xc5rkelig\\b|\\bbeklagerjeg\\b|\\bN\\\xe5rjeg\\b|\\brnaend\\b|\\bvaskebjorn\\b|\\bIvil\\b|\\bbesog\\b|\\bVaer\\b|\\bUndersogte\\b|\\bmodte\\b|\\btoj\\b|\\bfodt\\b|\\bgore\\b|\\bprovede\\b|\\bforste\\b|\\bigang\\b|\\bligenu\\b|\\bclet\\b|\\bStrombell\\b|\\btmvlt\\b|\\bstudererjournalistik\\b|\\binforrnererjeg\\b|\\bomk\\\ufb01ng\\b|\\btilAsg\\\xe5rd\\b|\\bKederjeg\\b|\\bjaettetamp\\b|\\berjer\\b|\\batjulehygge\\b|\\bUeneste\\b|\\bfoltsaetter\\b|\\bA\\/ice\\b|\\btvivlerjeg\\b|\\bhenterjer\\b|\\bforst\\\xe5rjeg\\b|\\bhvisjeg\\b|\\b\\/\\\xe6rt\\b|\\bvfgtrgt\\b|\\bhurtigtjeg\\b|\\bkenderjo\\b|\\bseiv\\b|\\b\\/\\\xe6gehuset\\b|\\bherjo\\b|\\bstolerjeg\\b|\\bdigi\\b|\\btaberi\\b|\\bsl\\\xe5rjeres\\b|\\blaere\\b|\\btr\\\xe6nerwushu\\b|\\befterjeg\\b|\\be\\\ufb01er\\b|\\bdui\\b|\\ba\\\ufb01en\\b|\\bbliveri\\b|\\bacceptererjer\\b|\\bdrikkerjo\\b|\\b\\\ufb01anjin\\b|\\berl\\\xe6nge\\b|\\berikke\\b|\\bmedjer\\b|\\bTmykke\\b|\\b\\'\\\ufb01anjins\\b|\\bMesteri\\b|\\bsagdetil\\b|\\bindei\\b|\\bo\\\ufb01e\\b|\\b\\'\\\ufb01lgiv\\b|\\bLf\\\xe5r\\b|\\bviserjer\\b|\\bRejsjerblot\\b|\\b\\'\\\ufb01llad\\b|\\biiiie\\\ufb01nger\\b|\\bVILOMFATTE\\b|\\bmo\\\ufb01o\\b|\\bg\\\xf8rjer\\b|\\bgifi\\b|\\bhardu\\b|\\bgi\\\ufb01\\b|\\bIaeggerjeg\\b|\\biet\\b|\\bsv\\/yte\\b|\\bti\\/\\b|\\bWdal\\b|\\b\\\ufb01\\\xe5et\\b|\\bHvo\\/for\\b|\\bhellerikke\\b|\\bWlle\\b|\\bdr\\/ver\\b|\\bV\\\\\\\ufb02lliam\\b|\\bV\\\\\\\ufb02lliams\\b|\\bVk\\\ufb01lliam\\b|\\bv\\\xe5dejakke\\b|\\bk\\\xe6\\\ufb02l\\b|\\bsagdejeg\\b|\\boven\\/ejet\\b|\\bkarameisauce\\b|\\bLf\\\xf8lgej\\\xf8disk\\b|\\bblevjo\\b|\\basiateri\\b|\\berV\\\\\\\ufb02lliam\\b|\\blidt\\\ufb02ov\\b|\\bsagdejo\\b|\\berlige\\b|\\bVt\\\ufb01lliam\\b|\\bW\\\ufb01II\\b|\\ba\\\ufb02darede\\b|\\bhj\\\xe6iperjeg\\b|\\bladerjeg\\b|\\bH\\\xe2ndledsbeskyttere\\b|\\bLsabels\\b|\\bG\\\xf8rjeg\\b|\\bm\\\xe2jeg\\b|\\bogjeg\\b|\\bgjordejeg\\b|\\bvillejeg\\b|\\bVl\\\ufb02lliams\\b|\\bDajeg\\b|\\biorden\\b|\\bfandtjeg\\b|\\bTilykke\\b|\\bk\\\xf8rerjer\\b|\\bg\\\xf8fjeg\\b|\\bSelvflgelig\\b|\\bfdderLine truncated
'deu': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'IVI', u'M'), (u'IVl', u'M'), (u'I\\/I', u'M'), (u'I\\/l', u'M'), (u'lVI', u'M'), (u'lVl', u'M'), (u'l\\/I', u'M'), (u'l\\/l', u'M'), (u'\xa4', u'o')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'/a', u'Ja'), (u'/ch', u'Ich'), (u'/d/of', u'Idiot'), (u'/ebte', u'lebte'), (u'/eid', u'leid'), (u'/hn', u'ihn'), (u'/hnen', u'Ihnen'), (u'/hr', u'Ihr'), (u'/hre', u'Ihre'), (u'/hren', u'Ihren'), (u'/m', u'im'), (u'/mmer', u'immer'), (u'/n', u'In'), (u'/ndividuen', u'Individuen'), (u'/nn', u'Inn'), (u'/oe', u'Joe'), (u'/sf', u'ist'), (u'/sf/0/1n', u'Ist John'), (u'/ungs', u'Jungs'), (u'/Vfinuten', u'Minuten'), (u'/\xe9nger', u'l\xe4nger'), (u'/\xe9uft', u'l\xe4uft'), (u'0/1', u'Oh'), (u'0/me', u'ohne'), (u'0/vne', u'ohne'), (u'00om', u'000 m'), (u'100m', u'100 m'), (u'120m', u'120 m'), (u'13Oj\xa7hrie', u'130-j\xe4hrige'), (u'145m', u'145 m'), (u'150m', u'150 m'), (u'160m', u'160 m'), (u'165m', u'165 m'), (u'19m', u'19 m'), (u'20m', u'20 m'), (u'27m', u'27 m'), (u'30m', u'30 m'), (u'37m', u'37 m'), (u'38m', u'38 m'), (u'3km', u'3 km'), (u'5/ch', u'sich'), (u'5/cher', u'sicher'), (u'5/cherer', u'sicherer'), (u'5/e', u'Sie'), (u'5/nd', u'Sind'), (u'500m', u'500 m'), (u'5ulSere', u'\xe4u\xdfere'), (u'60m', u'60 m'), (u'6de', u'\xf6de'), (u'6dere', u'\xf6dere'), (u'6ffne', u'\xf6ffne'), (u'6ffnen', u'\xf6ffnen'), (u'6ffnet', u'\xd6ffnet'), (u'6fter', u'\xf6fter'), (u'750m', u'750 m'), (u'85m', u'85 m'), (u'90m', u'90 m'), (u'a//em', u'allem'), (u'A//es', u'Alles'), (u'abbeif$en', u'abbei\xdfen'), (u'abdrficken', u'abdr\xfccken'), (u'aBen', u'a\xdfen'), (u'abergl\xe9iubischen', u'abergl\xe4ubischen'), (u'aberja', u'aber ja'), (u'aberjemand', u'aber jemand'), (u'Aberjetzt', u'Aber jetzt'), (u'abf\xe9hrt', u'abf\xe4hrt'), (u'abf\xe9illt', u'abf\xe4llt'), (u'abgef\xe9rbt', u'abgef\xe4rbt'), (u'abgeh\xe9ngt', u'abgeh\xe4ngt'), (u'abgeh\xe9rt', u'abgeh\xf6rt'), (u'abgelost', u'abgel\xf6st'), (u'abgesprengli', u'abgesprengt!'), (u'abgestfirztl', u'abgest\xfcrzt'), (u'abgestilrzt', u'abgest\xfcrzt'), (u'abgestofien', u'abgesto\xdfen'), (u'abgew\xe9hlt', u'abgew\xe4hlt'), (u'abgew\xe9hnen', u'abgew\xf6hnen'), (u'abgew\xe9hnt', u'abgew\xf6hnt'), (u'abge\xe9nderten', u'abge\xe4nderten'), (u'abh\xe9ingt', u'abh\xe4ngt'), (u'abh\xe9ngen', u'abh\xe4ngen'), (u'abh\xe9ngig', u'abh\xe4ngig'), (u'abh\xe9ngiges', u'abh\xe4ngiges'), (u'Abh\xe9rstationen', u'Abh\xf6rstationen'), (u'Abjetzt', u'Ab jetzt'), (u'abkfihlen', u'abk\xfchlen'), (u'Abkfirzung', u'Abk\xfcrzung'), (u'abkommlich', u'abk\xf6mmlich'), (u'Ablegenl', u'Ablegen!'), (u'ablfisen', u'abl\xf6sen'), (u'ablosen', u'abl\xf6sen'), (u'Ablosung', u'Abl\xf6sung'), (u'abreif$en', u'abrei\xdfen'), (u'Abrijcken', u'Abr\xfccken'), (u'abr\xe9umen', u'abr\xe4umen'), (u'Absch/ed', u'Abschied'), (u'abschiefien', u'abschie\xdfen'), (u'abschlief$en', u'abschlie\xdfen'), (u'abschliefien', u'abschlie\xdfen'), (u'abschwiiren', u'abschw\xf6ren'), (u'abstoflsend', u'absto\xdfend'), (u'Abtrijnnige', u'Abtr\xfcnnige'), (u'abwiirgt', u'abw\xfcrgt'), (u'abw\xe9gen', u'abw\xe4gen'), (u'abzuh\xe9ren', u'abzuh\xf6ren'), (u'abzuschwiiren', u'abzuschw\xf6ren'), (u'abzusfofien', u'abzusto\xdfen'), (u'ACh', u'Ach'), (u'Achtungl', u'Achtung!'), (u'Achzen', u'\xc4chzen'), (u'ACHZT', u'\xc4CHZT'), (u'Acic', u'Acid'), (u'ADDRESSDATEI', u'ADRESSDATEI'), (u'Adi\xf6s', u'Adi\xf3s'), (u'Admiralitat', u'Admiralit\xe4t'), (u'Admiralit\xe9it', u'Admiralit\xe4t'), (u'Admiralit\xe9t', u'Admiralit\xe4t'), (u'Aff\xe9re', u'Aff\xe4re'), (u'Aff\xe9ren', u'Aff\xe4ren'), (u'AFl', u'AFI'), (u'aggresivem', u'aggressivem'), (u'Agypten', u'\xc4gypten'), (u'aher', u'aber'), (u'AI/en/vichtigste', u'Allerwichtigste'), (u'Ain/vays', u'Airways'), (u'AIs', u'Als'), (u'Aktivit\xe9iten', u'Aktivit\xe4ten'), (u'Aktivit\xe9ten', u'Aktivit\xe4ten'), (u'AKTMERT', u'AKTIVIERT'), (u'Alarmsfufe', u'Alarmstufe'), (u'albem', u'albern'), (u'Albtriiume', u'Albtr\xe4ume'), (u'ale', u'als'), (u'alleinl', u'allein!'), (u'allejubeln', u'alle jubeln'), (u'allern\xe9chsten', u'allern\xe4chsten'), (u'Allmiichtigerl', u'Allm\xe4chtiger!'), (u'Allm\xe9chtige', u'Allm\xe4chtige'), (u'Allm\xe9chtiger', u'Allm\xe4chtiger'), (u'allm\xe9hlich', u'allm\xe4hlich'), (u'Allm\xe9ichtiger', u'Allm\xe4chtiger'), (u'Allsparkl', u'Allspark!'), (u'allt\xe9iglichen', u'allt\xe4glichen'), (u'ALTESTE', u'\xc4LTESTE'), (u'Altester', u'\xc4ltester'), (u'Alzte', u'\xc4rzte'), (u"Amerx'kaner", u'Amerikaner'), (u'amfisierst', u'am\xfcsierst'), (u'Amiilsierst', u'Am\xfcsierst'), (u'amiisieren', u'am\xfcsieren'), (u'amiisierenl', u'am\xfcsieren!'), (u'amiisierte', u'am\xfcsierte'), (u'Amijsant', u'Am\xfcsant'), (u'amlllsant', u'am\xfcsant'), (u'amlllsiert', u'am\xfcsiert'), (u'amtlsant', u'am\xfcsant'), (u'Amusanf', u'Am\xfcsant'), (u'amusant', u'am\xfcsant'), (u'Amusiert', u'Am\xfcsiert'), (u'Anderst', u'\xc4nderst'), (u'Anderung', u'\xc4nderung'), (u'Anderungen', u'\xc4nderungen'), (u"anfa'ngt", u'anf\xe4ngt'), (u'Anffihrer', u'Anf\xfchrer'), (u'Anffingerl', u'Anf\xe4nger!'), (u'Anfiihrer', u'Anf\xfchrer'), (u'anfijhlt', u'anf\xfchlt'), (u'Anfingerl', u'Anf\xe4nger!'), (u'Anfuhrer', u'Anf\xfchrer'), (u'Anfuhrern', u'Anf\xfchreLine truncated
'pattern': u"(um)\\b\\/a\\b|\\b\\/ch\\b|\\b\\/d\\/of\\b|\\b\\/ebte\\b|\\b\\/eid\\b|\\b\\/hn\\b|\\b\\/hnen\\b|\\b\\/hr\\b|\\b\\/hre\\b|\\b\\/hren\\b|\\b\\/m\\b|\\b\\/mmer\\b|\\b\\/n\\b|\\b\\/ndividuen\\b|\\b\\/nn\\b|\\b\\/oe\\b|\\b\\/sf\\b|\\b\\/sf\\/0\\/1n\\b|\\b\\/ungs\\b|\\b\\/Vfinuten\\b|\\b\\/\\\xe9nger\\b|\\b\\/\\\xe9uft\\b|\\b0\\/1\\b|\\b0\\/me\\b|\\b0\\/vne\\b|\\b00om\\b|\\b100m\\b|\\b120m\\b|\\b13Oj\\\xa7hrie\\b|\\b145m\\b|\\b150m\\b|\\b160m\\b|\\b165m\\b|\\b19m\\b|\\b20m\\b|\\b27m\\b|\\b30m\\b|\\b37m\\b|\\b38m\\b|\\b3km\\b|\\b5\\/ch\\b|\\b5\\/cher\\b|\\b5\\/cherer\\b|\\b5\\/e\\b|\\b5\\/nd\\b|\\b500m\\b|\\b5ulSere\\b|\\b60m\\b|\\b6de\\b|\\b6dere\\b|\\b6ffne\\b|\\b6ffnen\\b|\\b6ffnet\\b|\\b6fter\\b|\\b750m\\b|\\b85m\\b|\\b90m\\b|\\ba\\/\\/em\\b|\\bA\\/\\/es\\b|\\babbeif\\$en\\b|\\babdrficken\\b|\\baBen\\b|\\babergl\\\xe9iubischen\\b|\\baberja\\b|\\baberjemand\\b|\\bAberjetzt\\b|\\babf\\\xe9hrt\\b|\\babf\\\xe9illt\\b|\\babgef\\\xe9rbt\\b|\\babgeh\\\xe9ngt\\b|\\babgeh\\\xe9rt\\b|\\babgelost\\b|\\babgesprengli\\b|\\babgestfirztl\\b|\\babgestilrzt\\b|\\babgestofien\\b|\\babgew\\\xe9hlt\\b|\\babgew\\\xe9hnen\\b|\\babgew\\\xe9hnt\\b|\\babge\\\xe9nderten\\b|\\babh\\\xe9ingt\\b|\\babh\\\xe9ngen\\b|\\babh\\\xe9ngig\\b|\\babh\\\xe9ngiges\\b|\\bAbh\\\xe9rstationen\\b|\\bAbjetzt\\b|\\babkfihlen\\b|\\bAbkfirzung\\b|\\babkommlich\\b|\\bAblegenl\\b|\\bablfisen\\b|\\bablosen\\b|\\bAblosung\\b|\\babreif\\$en\\b|\\bAbrijcken\\b|\\babr\\\xe9umen\\b|\\bAbsch\\/ed\\b|\\babschiefien\\b|\\babschlief\\$en\\b|\\babschliefien\\b|\\babschwiiren\\b|\\babstoflsend\\b|\\bAbtrijnnige\\b|\\babwiirgt\\b|\\babw\\\xe9gen\\b|\\babzuh\\\xe9ren\\b|\\babzuschwiiren\\b|\\babzusfofien\\b|\\bACh\\b|\\bAchtungl\\b|\\bAchzen\\b|\\bACHZT\\b|\\bAcic\\b|\\bADDRESSDATEI\\b|\\bAdi\\\xf6s\\b|\\bAdmiralitat\\b|\\bAdmiralit\\\xe9it\\b|\\bAdmiralit\\\xe9t\\b|\\bAff\\\xe9re\\b|\\bAff\\\xe9ren\\b|\\bAFl\\b|\\baggresivem\\b|\\bAgypten\\b|\\baher\\b|\\bAI\\/en\\/vichtigste\\b|\\bAin\\/vays\\b|\\bAIs\\b|\\bAktivit\\\xe9iten\\b|\\bAktivit\\\xe9ten\\b|\\bAKTMERT\\b|\\bAlarmsfufe\\b|\\balbem\\b|\\bAlbtriiume\\b|\\bale\\b|\\balleinl\\b|\\ballejubeln\\b|\\ballern\\\xe9chsten\\b|\\bAllmiichtigerl\\b|\\bAllm\\\xe9chtige\\b|\\bAllm\\\xe9chtiger\\b|\\ballm\\\xe9hlich\\b|\\bAllm\\\xe9ichtiger\\b|\\bAllsparkl\\b|\\ballt\\\xe9iglichen\\b|\\bALTESTE\\b|\\bAltester\\b|\\bAlzte\\b|\\bAmerx\\'kaner\\b|\\bamfisierst\\b|\\bAmiilsierst\\b|\\bamiisieren\\b|\\bamiisierenl\\b|\\bamiisierte\\b|\\bAmijsant\\b|\\bamlllsant\\b|\\bamlllsiert\\b|\\bamtlsant\\b|\\bAmusanf\\b|\\bamusant\\b|\\bAmusiert\\b|\\bAnderst\\b|\\bAnderung\\b|\\bAnderungen\\b|\\banfa\\'ngt\\b|\\bAnffihrer\\b|\\bAnffingerl\\b|\\bAnfiihrer\\b|\\banfijhlt\\b|\\bAnfingerl\\b|\\bAnfuhrer\\b|\\bAnfuhrern\\b|\\bAnf\\\xe9inger\\b|\\bAnf\\\xe9ingergliick\\b|\\bAnf\\\xe9nge\\b|\\banf\\\xe9ngst\\b|\\banf\\\xe9ngt\\b|\\bangebrfillt\\b|\\bangebrullt\\b|\\bangefiihrt\\b|\\bANGEHCHDRIGE\\b|\\bangehfirt\\b|\\bAngehtirigen\\b|\\bangeh\\\xe9ren\\b|\\bangeh\\\xe9rt\\b|\\bangel\\\xe9chelt\\b|\\bangerilhrt\\b|\\banger\\\ufb02hrt\\b|\\bangeschweifit\\b|\\bangespruht\\b|\\bangetiltert\\b|\\bAngriffspl\\\xe9nen\\b|\\bAngstschweili\\b|\\banhiiren\\b|\\bAnh\\\xe9inger\\b|\\banh\\\xe9lt\\b|\\banh\\\xe9ngen\\b|\\banh\\\xe9ren\\b|\\bankijndigen\\b|\\banliigen\\b|\\banlugen\\b|\\banmal3ende\\b|\\bann\\\xe9hern\\b|\\banriihrst\\b|\\banrijuhren\\b|\\banst\\\xe9indig\\b|\\banst\\\xe9indiger\\b|\\banst\\\xe9indiges\\b|\\banst\\\xe9ndig\\b|\\banst\\\xe9ndige\\b|\\banst\\\xe9ndigen\\b|\\bAnst\\\xe9ndiges\\b|\\bAntik\\\xe9rper\\b|\\bAntiquit\\\xe9t\\b|\\bAntistrahlenger\\\xe9t\\b|\\bantwortenl\\b|\\bAnwe\\/sung\\b|\\bAnwe\\/sungen\\b|\\bAnw\\\xe9iltin\\b|\\bAnw\\\xe9lte\\b|\\bAnw\\\xe9ltin\\b|\\bAnzilge\\b|\\bAnztinden\\b|\\bAnzuge\\b|\\bAnzugen\\b|\\banzuhiiren\\b|\\banzuhoren\\b|\\banzundenl\\b|\\banzupiibeln\\b|\\bAn\\\xe9sthesie\\b|\\bAn\\\xe9sthesieprofessor\\b|\\bAn\\\xe9sthesieteam\\b|\\bAn\\\xe9sthesist\\b|\\bAn\\\xe9sthesisten\\b|\\bAn\\\xe9sthetikum\\b|\\bARBEITERI\\b|\\bArbeitsfl\\\ufb02gel\\b|\\bArmeefunkger\\\xe9t\\b|\\bArmel\\b|\\bArschkichern\\b|\\bArschliicher\\b|\\bArschliichern\\b|\\bArschl\\\xe9cher\\b|\\bArschl\\\xe9chern\\b|\\bArzte\\b|\\bArzten\\b|\\bArztin\\b|\\bAtemger\\\xe9usche\\b|\\bAtlantikkiiste\\b|\\bAtlantikkuste\\b|\\bATMOSPHARE\\b|\\bAtmosph\\\xe9re\\b|\\bAtmosph\\\xe9renbereich\\b|\\bAtmosph\\\xe9reneinflugsequenz\\b|\\bAtmosph\\\xe9reneintritt\\b|\\bAttenfaiter\\b|\\bAttent\\\xe9iter\\b|\\bAttent\\\xe9ter\\b|\\bAttent\\\xe9ters\\b|\\bAttraktivit\\\xe9t\\b|\\bauBen\\b|\\bAubenblick\\b|\\bAuBenbord\\b|\\bAuBenwelt\\b|\\bauBer\\b|\\bAuBerdem\\b|\\bauBerhalb\\b|\\bauc\\/1\\b|\\bauchl\\b|\\bAuf\\$erdem\\b|\\bauf3er\\b|\\baufAugenh6he\\b|\\baufblilhende\\b|\\bauff\\'a\\'ngt\\b|\\bAuff\\\xe9lliges\\b|\\baufgebltiht\\b|\\baufgeftlhrt\\b|\\baufgeh\\\xe9ingt\\b|\\baufgeh\\\xe9rt\\b|\\baufgekl\\\xe9rt\\b|\\baufger\\\xe9umt\\b|\\baufgespiefit\\b|\\baufgewiihlter\\b|\\baufgez\\\xe9hlt\\b|\\bAufh6ren\\b|Line truncated
'eng': {'BeginLines': {'data': OrderedDict([(u'Don,t ', u"Don't "), (u'Can,t ', u"Can't "), (u'Let,s ', u"Let's "), (u'He,s ', u"He's "), (u'I,m ', u"I'm "), (u'I,ve ', u"I've "), (u'I,ll ', u"I'll "), (u'You,ll ', u"You'll "), (u'T hey ', u'They '), (u'T here ', u'There '), (u'W here ', u'Where '), (u'M aybe ', u'Maybe '), (u'S hould ', u'Should '), (u'|was', u'I was'), (u'|am ', u'I am'), (u'No w, ', u'Now, '), (u'l... I ', u'I... I '), (u'L... I ', u'I... I '), (u'lrn gonna', u"I'm gonna"), (u"-l don't", u"-I don't"), (u"l don't", u"I don't"), (u'L ', u'I '), (u'-L ', u'-I '), (u'- L ', u'- I '), (u'-l ', u'-I '), (u'- l ', u'- I '), (u'G0', u'Go'), (u'GO get', u'Go get'), (u'GO to', u'Go to'), (u'GO for', u'Go for'), (u'Ifl', u'If I'), (u"lt'll", u"It'll"), (u"Lt'll", u"It'll"), (u'IVIa', u'Ma'), (u'IVIu', u'Mu'), (u'0ne', u'One'), (u'0nly', u'Only'), (u'0n ', u'On '), (u'lt ', u'It '), (u'Lt ', u'It '), (u"lt's ", u"It's "), (u"Lt's ", u"It's "), (u'ln ', u'In '), (u'Ln ', u'In '), (u'l-in ', u'I-in '), (u'l-impossible', u'I-impossible'), (u'l- impossible', u'I-impossible'), (u'L- impossible', u'I-impossible'), (u"l-isn't ", u"I-isn't "), (u"L-isn't ", u"I-isn't "), (u"l- isn't ", u"I-isn't "), (u"L- isn't ", u"I-isn't "), (u'l- l ', u'I-I '), (u'L- l ', u'I-I '), (u'l- it ', u'I-it '), (u'L- it ', u'I-it '), (u'Ls it ', u'Is it '), (u'Ls there ', u'Is there '), (u'Ls he ', u'Is he '), (u'Ls she ', u'Is she '), (u'L can', u'I can'), (u'l can', u'I can'), (u"L'm ", u"I'm "), (u"L' m ", u"I'm "), (u"Lt' s ", u"It's "), (u"I']I ", u"I'll "), (u'...ls ', u'...Is '), (u'- ls ', u'- Is '), (u'...l ', u'...I '), (u'Ill ', u"I'll "), (u'L hope ', u'I hope '), (u"|\u2019E'$ ", u"It's "), (u"The y're ", u"They're "), (u'<i>/ ', u'<i>I '), (u'/ ', u'I '), (u'<i>/n ', u'<i>In '), (u'/n ', u'In '), (u'<i>Ana\u2019 ', u'<i>And '), (u"<i>Ana' ", u'<i>And '), (u'~ ', u'- '), (u"<i>A'|'|'EN BOROUGH:", u'<i>ATTENBOROUGH:'), (u"A'|'|'EN BOROUGH:", u'ATTENBOROUGH:'), (u"DAVID A'|'|'EN BOROUGH:", u'DAVID ATTENBOROUGH:'), (u"AT|'EN BOROUGH:", u'ATTENBOROUGH:'), (u"DAVID AT|'EN BOROUGH:", u'DAVID ATTENBOROUGH:'), (u"<i>AT|'EN BOROUGH:", u'<i>ATTENBOROUGH:'), (u'TH REE ', u'THREE '), (u'NARRA TOR', u'NARRATOR'), (u'<i>NARRA TOR', u'<i>NARRATOR'), (u"lt'syour", u"It's your"), (u"It'syour", u"It's your"), (u'Ls ', u'Is ')]),
'pattern': u"(um)^\\bDon\\,t\\ \\b|\\bCan\\,t\\ \\b|\\bLet\\,s\\ \\b|\\bHe\\,s\\ \\b|\\bI\\,m\\ \\b|\\bI\\,ve\\ \\b|\\bI\\,ll\\ \\b|\\bYou\\,ll\\ \\b|\\bT\\ hey\\ \\b|\\bT\\ here\\ \\b|\\bW\\ here\\ \\b|\\bM\\ aybe\\ \\b|\\bS\\ hould\\ \\b|\\b\\|was\\b|\\b\\|am\\ \\b|\\bNo\\ w\\,\\ \\b|\\bl\\.\\.\\.\\ I\\ \\b|\\bL\\.\\.\\.\\ I\\ \\b|\\blrn\\ gonna\\b|\\b\\-l\\ don\\'t\\b|\\bl\\ don\\'t\\b|\\bL\\ \\b|\\b\\-L\\ \\b|\\b\\-\\ L\\ \\b|\\b\\-l\\ \\b|\\b\\-\\ l\\ \\b|\\bG0\\b|\\bGO\\ get\\b|\\bGO\\ to\\b|\\bGO\\ for\\b|\\bIfl\\b|\\blt\\'ll\\b|\\bLt\\'ll\\b|\\bIVIa\\b|\\bIVIu\\b|\\b0ne\\b|\\b0nly\\b|\\b0n\\ \\b|\\blt\\ \\b|\\bLt\\ \\b|\\blt\\'s\\ \\b|\\bLt\\'s\\ \\b|\\bln\\ \\b|\\bLn\\ \\b|\\bl\\-in\\ \\b|\\bl\\-impossible\\b|\\bl\\-\\ impossible\\b|\\bL\\-\\ impossible\\b|\\bl\\-isn\\'t\\ \\b|\\bL\\-isn\\'t\\ \\b|\\bl\\-\\ isn\\'t\\ \\b|\\bL\\-\\ isn\\'t\\ \\b|\\bl\\-\\ l\\ \\b|\\bL\\-\\ l\\ \\b|\\bl\\-\\ it\\ \\b|\\bL\\-\\ it\\ \\b|\\bLs\\ it\\ \\b|\\bLs\\ there\\ \\b|\\bLs\\ he\\ \\b|\\bLs\\ she\\ \\b|\\bL\\ can\\b|\\bl\\ can\\b|\\bL\\'m\\ \\b|\\bL\\'\\ m\\ \\b|\\bLt\\'\\ s\\ \\b|\\bI\\'\\]I\\ \\b|\\b\\.\\.\\.ls\\ \\b|\\b\\-\\ ls\\ \\b|\\b\\.\\.\\.l\\ \\b|\\bIll\\ \\b|\\bL\\ hope\\ \\b|\\b\\|\\\u2019E\\'\\$\\ \\b|\\bThe\\ y\\'re\\ \\b|\\b\\<i\\>\\/\\ \\b|\\b\\/\\ \\b|\\b\\<i\\>\\/n\\ \\b|\\b\\/n\\ \\b|\\b\\<i\\>Ana\\\u2019\\ \\b|\\b\\<i\\>Ana\\'\\ \\b|\\b\\~\\ \\b|\\b\\<i\\>A\\'\\|\\'\\|\\'EN\\ BOROUGH\\:\\b|\\bA\\'\\|\\'\\|\\'EN\\ BOROUGH\\:\\b|\\bDAVID\\ A\\'\\|\\'\\|\\'EN\\ BOROUGH\\:\\b|\\bAT\\|\\'EN\\ BOROUGH\\:\\b|\\bDAVID\\ AT\\|\\'EN\\ BOROUGH\\:\\b|\\b\\<i\\>AT\\|\\'EN\\ BOROUGH\\:\\b|\\bTH\\ REE\\ \\b|\\bNARRA\\ TOR\\b|\\b\\<i\\>NARRA\\ TOR\\b|\\blt\\'syour\\b|\\bIt\\'syour\\b|\\bLs\\ \\b"},
'EndLines': {'data': OrderedDict([(u', sin', u', sir.'), (u' mothen', u' mother.'), (u" can't_", u" can't."), (u' openiL', u' open it.'), (u' of\ufb02', u' off!'), (u'pshycol', u'psycho!')]),
'pattern': u"(um)\\b\\,\\ sin\\b|\\b\\ mothen\\b|\\b\\ can\\'t\\_\\b|\\b\\ openiL\\b|\\b\\ of\\\ufb02\\b|\\bpshycol\\b$"},
'PartialLines': {'data': OrderedDict([(u' /be ', u' I be '), (u" aren '1'", u" aren't"), (u" aren'tyou", u" aren't you"), (u" doesn '1'", u" doesn't"), (u" fr/eno'", u' friend'), (u" fr/eno'.", u' friend.'), (u" haven 'z' ", u" haven't "), (u" haven 'z'.", u" haven't."), (u' I ha ve ', u' I have '), (u" I']I ", u" I'll "), (u' L am', u' I am'), (u' L can', u' I can'), (u" L don't ", u" I don't "), (u' L hate ', u' I hate '), (u' L have ', u' I have '), (u' L like ', u' I like '), (u' L will', u' I will'), (u' L would', u' I would'), (u" L'll ", u" I'll "), (u" L've ", u" I've "), (u' m y family', u' my family'), (u" 's ", u"'s "), (u" shou/dn '1 ", u" shouldn't "), (u" won 'z' ", u" won't "), (u" won 'z'.", u" won't."), (u" wou/c/n 'z' ", u" wouldn't "), (u" wou/c/n 'z'.", u" wouldn't."), (u" wou/dn 'z' ", u" wouldn't "), (u" wou/dn 'z'.", u" wouldn't."), (u'/ did', u'I did'), (u'/ have ', u'I have '), (u'/ just ', u'I just '), (u'/ loved ', u'I loved '), (u'/ need', u'I need'), (u'|was11', u'I was 11'), (u'at Hrst', u'at first'), (u"B ullshiz'", u'Bullshit'), (u'big lunk', u'love you'), (u"can 't", u"can't"), (u"can' t ", u"can't "), (u"can 't ", u"can't "), (u'CHA TTERING', u'CHATTERING'), (u'come 0n', u'come on'), (u'Come 0n', u'Come on'), (u"couldn 't", u"couldn't"), (u"couldn' t ", u"couldn't "), (u"couldn 't ", u"couldn't "), (u"Destin y's", u"Destiny's"), (u"didn 't", u"didn't"), (u"didn' t ", u"didn't "), (u"didn 't ", u"didn't "), (u"Doesn '1'", u"Doesn't"), (u"doesn '1' ", u"doesn't "), (u"doesn '1\u2018 ", u"doesn't "), (u"doesn 't", u"doesn't"), (u"doesn'1' ", u"doesn't "), (u"doesn'1\u2018 ", u"doesn't "), (u"don '1' ", u"don't "), (u"don '1\u2018 ", u"don't "), (u"don '2' ", u"don't "), (u" aren '2'", u" aren't"), (u"aren '2' ", u"aren't "), (u"don '2\u2018 ", u"don't "), (u"don 't", u"don't"), (u"Don' t ", u"Don't "), (u"Don 't ", u"Don't "), (u"don'1' ", u"don't "), (u"don'1\u2018 ", u"don't "), (u"there '5 ", u"there's "), (u'E very', u'Every'), (u'get 0n', u'get on'), (u'go 0n', u'go on'), (u'Go 0n', u'Go on'), (u"H3993' birthday", u'Happy birthday'), (u"hadn 't", u"hadn't"), (u"he 's", u"he's"), (u"He 's", u"He's"), (u'He y', u'Hey'), (u'he)/', u'hey'), (u'He)/', u'Hey'), (u'HEA VY', u'HEAVY'), (u'Hold 0n', u'Hold on'), (u'I am. ls', u'I am. Is'), (u'I d0', u'I do'), (u"I 'm", u"I'm"), (u"I 'rn ", u"I'm "), (u"I 've", u"I've"), (u'I0 ve her', u'love her'), (u'I0 ve you', u'love you'), (u"I02'", u'lot'), (u"I'm sony", u"I'm sorry"), (u"isn' t ", u"isn't "), (u"isn 't ", u"isn't "), (u'K)/le', u'Kyle'), (u'L ook', u'Look'), (u'let me 90', u'let me go'), (u'Let me 90', u'Let me go'), (u"let's 90", u"let's go"), (u"Let's 90", u"Let's go"), (u'lfl had', u'If I had'), (u'lova you', u'love you'), (u'Lova you', u'love you'), (u'lovo you', u'love you'), (u'Lovo you', u'love you'), (u'ls anyone', u'Is anyone'), (u'ls he', u'Is he'), (u'-ls he', u'- Is he'), (u'ls it', u'Is it'), (u'-ls it', u'- Is it'), (u'ls she', u'Is she'), (u'-ls she', u'- Is she'), (u'ls that', u'Is that'), (u'-ls that', u'- Is that'), (u'ls this', u'Is this'), (u'-ls this', u'- Is this'), (u'Maze] tov', u'Mazel tov'), (u"N02' ", u'Not '), (u' of 0ur ', u' of our '), (u' ot mine ', u' of mine '), (u'PLA YING', u'PLAYING'), (u'REPEA TING ', u'REPEATING '), (u'Sa y', u'Say'), (u"she 's", u"she's"), (u"She 's", u"She's"), (u"shouldn 't", u"shouldn't"), (u'sta y', u'stay'), (u'Sta y', u'Stay'), (u'SWO rd', u'Sword'), (u'taka care', u'take care'), (u'Taka care', u'Take care'), (u'the Hrst', u'the first'), (u'toc late', u'too late'), (u'uf me', u'of me'), (u'uf our', u'of our'), (u'wa y', u'way'), (u'Wal-I\\/Iart', u'Wal-Mart'), (u"wasn '1' ", u"wasn't "), (u"Wasn '1' ", u"Wasn't "), (u"wasn '1\u2018 ", u"wasn't "), (u"Wasn '1\u2018 ", u"Wasn't "), (u"wasn 't", u"wasn't"), (u"Wasn 't", u"Wasn't"), (u"we 've", u"we've"), (u"We 've", u"We've"), (u"wem' off", u'went off'), (u"weren 't", u"weren't"), (u"who 's", u"who's"), (u"won 't", u"won't"), (u'would ha ve', u'would have '), (u"wouldn 't", u"wouldn't"), (u"Wouldn 't", u"Wouldn't"), (u'y()u', u'you'), (u'you QUYS', u'you guys'), (u"you' re ", u"you're "), (u"you 're ", u"you're "), (u"you 've", u"you've"), (u"You 've", u"You've"), (u"you' ve ", u"you've "), (u"you 've ", u"you've "), (u'aftera while', u'after a while'), (u'Aftera while', u'After a while'), (u'THUN DERCLAPS', u'THUNDERCLAPS'), (u'(BUZZI N G)', u'(BUZZING)'), (u'[BUZZI N G]', u'[BUZZING]'), (u'(G RU NTING', u'(GRUNTING'), (u'[G RU NTING', u'[GRUNTING'), (u'(G ROWLING', u'(GROWLING'), (u'[G ROWLING', u'[GROWLING'), (u' WAI LS)', u'WAILS)'), (u' WAI LS]', u'WAILS]'), (u'(scu RRYING)', u'(SCURRYING)'), (u'[scu RRYING]', u'[SCURRYING]'), (u'(GRUNT5)', u'(GRUNTS)'), (u'[GRUNT5]', u'[GRUNTS]'), (u'NARRA TOR:', u'NARRATOR:'), (u'(GROAN ING', u'(GROANING'), (u'[GROAN ING', u'[GROANING'), (u'GROAN ING)', u'GROANING)'), (u'GROAN ING]', u'GROANING]'), (u'(LAUGH ING', u'(LAUGHING'), (u'[LAUGH ING', u'[LAUGHING'), (u'LAUGLine truncated
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M'), (u'I\\/I', u'M'), (u'l\\/I', u'M'), (u'I\\/l', u'M'), (u'l\\/l', u'M'), (u'IVIa', u'Ma'), (u'IVIe', u'Me'), (u'IVIi', u'Mi'), (u'IVIo', u'Mo'), (u'IVIu', u'Mu'), (u'IVIy', u'My')]),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'H ey.', u'Hey.'), (u'He)\u2019-', u'Hey.'), (u'N0.', u'No.'), (u'-N0.', u'-No.'), (u'Noll', u'No!!'), (u'(G ROANS)', u'(GROANS)'), (u'[G ROANS]', u'[GROANS]'), (u'(M EOWS)', u'(MEOWS)'), (u'[M EOWS]', u'[MEOWS]'), (u'Uaughs]', u'[laughs]'), (u'[chitte rs]', u'[chitters]'), (u'Hil\u2018 it!', u'Hit it!'), (u'<i>Hil\u2018 it!</i>', u'<i>Hit it!</i>'), (u'ISIGHS]', u'[SIGHS]')]),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'$COff$', u'scoffs'), (u'$ergei', u'Sergei'), (u"$'llOp", u'Stop'), (u"/'//", u"I'll"), (u"/'/I", u"I'll"), (u'/ennifer', u'Jennifer'), (u'/got', u'I got'), (u'/have', u'I have'), (u'/hope', u'I hope'), (u'/just', u'I just'), (u'/love', u'I love'), (u"/'m", u"I'm"), (u'/mmerse', u'immerse'), (u'/nsu/ts', u'Insults'), (u'/ong', u'long'), (u'/ook', u'look'), (u"/t's", u"It's"), (u"/'ve", u"I've"), (u"\\/\\/e'd", u"We'd"), (u"\\/\\/e're", u"We're"), (u"\\/\\/e've", u"We've"), (u'\\/\\/hat', u'What'), (u"\\/\\/here'd", u"Where'd"), (u'\\/\\/hoo', u'Whoo'), (u'\\/\\/hy', u'Why'), (u"\\/\\/hy'd", u"Why'd"), (u"\\/\\le're", u"We're"), (u'\\/Ve', u'We'), (u"\\Ne're", u"We're"), (u"\\Nhat's", u"What's"), (u"\\Nhere's", u"Where's"), (u"|'mjust", u"I'm just"), (u'\xa4ff', u'off'), (u'\xa4Id', u'old'), (u'\xa4Ids', u'olds'), (u'\xa4n', u'on'), (u'\xa4ne', u'one'), (u'\xa4nly', u'only'), (u'\xa4pen', u'open'), (u'\xa4r', u'or'), (u'\xa4rder', u'order'), (u'\xa4ther', u'other'), (u'\xa4ur', u'our'), (u'\xa4ut', u'out'), (u'\xa4ver', u'over'), (u'\xa4wn', u'own'), (u"\u20acV\u20acI'y", u'every'), (u"0'clock", u"o'clock"), (u'0f', u'of'), (u'0fEngland', u'of England'), (u'0fft0', u'off to'), (u'0l/er', u'over'), (u'0n', u'on'), (u'0ne', u'one'), (u"0ne's", u"one's"), (u'0r', u'or'), (u'0rders', u'orders'), (u"0thers'", u"others'"), (u'0ut', u'out'), (u"0utlaw's", u"outlaw's"), (u"0utlaws'", u"outlaws'"), (u'0ver', u'over'), (u'13oos', u'1300s'), (u'18oos', u'1800s'), (u'195os', u'1950s'), (u"1et's", u"let's"), (u'1o', u'10'), (u'1oo', u'100'), (u'1ooth', u'100th'), (u'1oth', u'10th'), (u'2E_', u'2E.'), (u"2'IST", u'21ST'), (u"2'Ist_", u"2'1st."), (u'2o', u'20'), (u'2oth', u'20th'), (u'3o', u'30'), (u'3oth', u'30th'), (u'4o', u'40'), (u'4os', u'40s'), (u'4oth', u'40th'), (u'50rry', u'sorry'), (u'5o', u'50'), (u'5oth', u'50th'), (u'6o', u'60'), (u'6os', u'60s'), (u"'6os", u"'60s"), (u'6oth', u'60th'), (u'7o', u'70'), (u"'7os", u"'70s"), (u'7oth', u'70th'), (u'8o', u'80'), (u"'8os", u"'80s"), (u'8oth', u'80th'), (u'9/aim', u'alarm'), (u'9o', u'90'), (u'9oth', u'90th'), (u'9UnShQt', u'gunshot'), (u'a//', u'all'), (u'a/bum', u'album'), (u'a/so', u'also'), (u'A/ways', u'Always'), (u'abcut', u'about'), (u'aboutjoining', u'about joining'), (u'aboutposh', u'about posh'), (u'aboutus', u'about us'), (u'aboutyou', u'about you'), (u'accldent', u'accident'), (u'Acool', u'A cool'), (u'afier', u'after'), (u'affraid', u'afraid'), (u'Afriend', u'A friend'), (u'afterall', u'after all'), (u'afterthe', u'after the'), (u'afulcrum', u'a fulcrum'), (u'Afunny', u'A funny'), (u'aga/nst', u'against'), (u'ahsolutes', u'absolutes'), (u'AI_I_', u'ALL'), (u'AIien', u'Alien'), (u'AIex', u'Alex'), (u'AII', u'All'), (u'AIIan', u'Allan'), (u'AIIow', u'Allow'), (u'AIive', u'Alive'), (u"ain'tgotno", u"ain't got no"), (u"Ain'tgotno", u"Ain't got no"), (u'airstrike', u'air strike'), (u'AIVIBULANCE', u'AMBULANCE'), (u'ajob', u'a job'), (u'ajockey_', u'a jockey.'), (u'ajoke', u'a joke'), (u'Ajoke', u'A joke'), (u'ajoking', u'a joking'), (u'al/', u'all'), (u'al/en', u'alien'), (u'alittle', u'a little'), (u'allgasp', u'all gasp'), (u'alljustforshow', u'all just for show'), (u"aln't", u"ain't"), (u'alot', u'a lot'), (u'Alot', u'A lot'), (u'An5wer', u'Answer'), (u'Andit', u'And it'), (u"Andit's", u"And it's"), (u'andl', u'and I'), (u'andlaughs', u'and laughs'), (u'andleave', u'and leave'), (u'andthe', u'and the'), (u'andyou', u'and you'), (u'Andyou', u'And you'), (u'ANNOUNC/NG', u'ANNOUNCING'), (u'anotherstep', u'another step'), (u'ANSWER/NG', u'ANSWERING'), (u'answerwhat', u'answer what'), (u'antiquejoke', u'antique joke'), (u"anyhcdy's", u"anybody's"), (u'Anyidea', u'Any idea'), (u"anyone's_", u"anyone's."), (u'apejust', u'ape just'), (u'ARABlc', u'ARABIC'), (u"aren't_", u"aren't."), (u"arerl't", u"aren't"), (u"Arnsteln's", u"Arnstein's"), (u'atleast', u'at least'), (u'Atough', u'A tough'), (u'Awhole', u'A whole'), (u'awoman', u'a woman'), (u'Awoman', u'A woman'), (u'barelytalked', u'barely talked'), (u'bcat', u'boat'), (u'Bcllvla', u'Bolivia'), (u'bcmb', u'bomb'), (u'bcmbs', u'bombs'), (u'be//y', u'belly'), (u'becuase', u'because'), (u"Beep/'ng", u'Beeping'), (u'bejumpy', u'be jumpy'), (u'besldes', u'besides'), (u'bestfriend', u'best friend'), (u'bestguy', u'best guy'), (u'bestjob', u'best job'), (u'BIack', u'Black'), (u'BIess', u'Bless'), (u'bigos___', u'bigos...'), (u'BIame', u'Blame'), (u'BIind', u'Blind'), (u'BIood', u'Blood'), (u'BIue', u'Blue'), (u'BLOVVS', u'BLOWS'), (u'blowholel', u'blowhole!'), (u'blt', u'bit'), (u'Bo99', u'Bogg'), (u'bodiedyoung', u'bodied young'), (u'breakf\xe9wtl', u'breakfast!'), (u'bulldozlng', u'bulldozing'), (u'butjust', u'but just'), (u'butl', u'but I'), (u'Butl', u'But I'), (u'butljust', u'but I just'), (u"Butljustcan'tgetenough", u"But I just can't get enough"), (u"Butyou're", u"But you're"), (u'buythem', u'buy them'), (u'buyyou', u'buy you'), (u'byjust', u'by just'), (u'bythe', u'Line truncated
'pattern': u"(um)\\b\\$COff\\$\\b|\\b\\$ergei\\b|\\b\\$\\'llOp\\b|\\b\\/\\'\\/\\/\\b|\\b\\/\\'\\/I\\b|\\b\\/ennifer\\b|\\b\\/got\\b|\\b\\/have\\b|\\b\\/hope\\b|\\b\\/just\\b|\\b\\/love\\b|\\b\\/\\'m\\b|\\b\\/mmerse\\b|\\b\\/nsu\\/ts\\b|\\b\\/ong\\b|\\b\\/ook\\b|\\b\\/t\\'s\\b|\\b\\/\\'ve\\b|\\b\\\\\\/\\\\\\/e\\'d\\b|\\b\\\\\\/\\\\\\/e\\'re\\b|\\b\\\\\\/\\\\\\/e\\'ve\\b|\\b\\\\\\/\\\\\\/hat\\b|\\b\\\\\\/\\\\\\/here\\'d\\b|\\b\\\\\\/\\\\\\/hoo\\b|\\b\\\\\\/\\\\\\/hy\\b|\\b\\\\\\/\\\\\\/hy\\'d\\b|\\b\\\\\\/\\\\le\\'re\\b|\\b\\\\\\/Ve\\b|\\b\\\\Ne\\'re\\b|\\b\\\\Nhat\\'s\\b|\\b\\\\Nhere\\'s\\b|\\b\\|\\'mjust\\b|\\b\\\xa4ff\\b|\\b\\\xa4Id\\b|\\b\\\xa4Ids\\b|\\b\\\xa4n\\b|\\b\\\xa4ne\\b|\\b\\\xa4nly\\b|\\b\\\xa4pen\\b|\\b\\\xa4r\\b|\\b\\\xa4rder\\b|\\b\\\xa4ther\\b|\\b\\\xa4ur\\b|\\b\\\xa4ut\\b|\\b\\\xa4ver\\b|\\b\\\xa4wn\\b|\\b\\\u20acV\\\u20acI\\'y\\b|\\b0\\'clock\\b|\\b0f\\b|\\b0fEngland\\b|\\b0fft0\\b|\\b0l\\/er\\b|\\b0n\\b|\\b0ne\\b|\\b0ne\\'s\\b|\\b0r\\b|\\b0rders\\b|\\b0thers\\'\\b|\\b0ut\\b|\\b0utlaw\\'s\\b|\\b0utlaws\\'\\b|\\b0ver\\b|\\b13oos\\b|\\b18oos\\b|\\b195os\\b|\\b1et\\'s\\b|\\b1o\\b|\\b1oo\\b|\\b1ooth\\b|\\b1oth\\b|\\b2E\\_\\b|\\b2\\'IST\\b|\\b2\\'Ist\\_\\b|\\b2o\\b|\\b2oth\\b|\\b3o\\b|\\b3oth\\b|\\b4o\\b|\\b4os\\b|\\b4oth\\b|\\b50rry\\b|\\b5o\\b|\\b5oth\\b|\\b6o\\b|\\b6os\\b|\\b\\'6os\\b|\\b6oth\\b|\\b7o\\b|\\b\\'7os\\b|\\b7oth\\b|\\b8o\\b|\\b\\'8os\\b|\\b8oth\\b|\\b9\\/aim\\b|\\b9o\\b|\\b9oth\\b|\\b9UnShQt\\b|\\ba\\/\\/\\b|\\ba\\/bum\\b|\\ba\\/so\\b|\\bA\\/ways\\b|\\babcut\\b|\\baboutjoining\\b|\\baboutposh\\b|\\baboutus\\b|\\baboutyou\\b|\\baccldent\\b|\\bAcool\\b|\\bafier\\b|\\baffraid\\b|\\bAfriend\\b|\\bafterall\\b|\\bafterthe\\b|\\bafulcrum\\b|\\bAfunny\\b|\\baga\\/nst\\b|\\bahsolutes\\b|\\bAI\\_I\\_\\b|\\bAIien\\b|\\bAIex\\b|\\bAII\\b|\\bAIIan\\b|\\bAIIow\\b|\\bAIive\\b|\\bain\\'tgotno\\b|\\bAin\\'tgotno\\b|\\bairstrike\\b|\\bAIVIBULANCE\\b|\\bajob\\b|\\bajockey\\_\\b|\\bajoke\\b|\\bAjoke\\b|\\bajoking\\b|\\bal\\/\\b|\\bal\\/en\\b|\\balittle\\b|\\ballgasp\\b|\\balljustforshow\\b|\\baln\\'t\\b|\\balot\\b|\\bAlot\\b|\\bAn5wer\\b|\\bAndit\\b|\\bAndit\\'s\\b|\\bandl\\b|\\bandlaughs\\b|\\bandleave\\b|\\bandthe\\b|\\bandyou\\b|\\bAndyou\\b|\\bANNOUNC\\/NG\\b|\\banotherstep\\b|\\bANSWER\\/NG\\b|\\banswerwhat\\b|\\bantiquejoke\\b|\\banyhcdy\\'s\\b|\\bAnyidea\\b|\\banyone\\'s\\_\\b|\\bapejust\\b|\\bARABlc\\b|\\baren\\'t\\_\\b|\\barerl\\'t\\b|\\bArnsteln\\'s\\b|\\batleast\\b|\\bAtough\\b|\\bAwhole\\b|\\bawoman\\b|\\bAwoman\\b|\\bbarelytalked\\b|\\bbcat\\b|\\bBcllvla\\b|\\bbcmb\\b|\\bbcmbs\\b|\\bbe\\/\\/y\\b|\\bbecuase\\b|\\bBeep\\/\\'ng\\b|\\bbejumpy\\b|\\bbesldes\\b|\\bbestfriend\\b|\\bbestguy\\b|\\bbestjob\\b|\\bBIack\\b|\\bBIess\\b|\\bbigos\\_\\_\\_\\b|\\bBIame\\b|\\bBIind\\b|\\bBIood\\b|\\bBIue\\b|\\bBLOVVS\\b|\\bblowholel\\b|\\bblt\\b|\\bBo99\\b|\\bbodiedyoung\\b|\\bbreakf\\\xe9wtl\\b|\\bbulldozlng\\b|\\bbutjust\\b|\\bbutl\\b|\\bButl\\b|\\bbutljust\\b|\\bButljustcan\\'tgetenough\\b|\\bButyou\\'re\\b|\\bbuythem\\b|\\bbuyyou\\b|\\bbyjust\\b|\\bbythe\\b|\\bC\\/latter\\/\\'\\/7g\\b|\\bca\\/\\/\\/ng\\b|\\bca\\/I\\b|\\bcall\\/ng\\b|\\bcallyou\\b|\\bcan\\*t\\b|\\bcan\\'i\\b|\\bcan\\'I\\b|\\bcanlgetyou\\b|\\bcannotchange\\b|\\bcannut\\b|\\bcan\\'T\\b|\\bcan\\'t\\_\\b|\\bcan\\'tjust\\b|\\bcan\\'tletgo\\b|\\bCar0l\\b|\\bCarhorn\\b|\\bcarrled\\b|\\bCcug\\b|\\bCcugs\\b|\\bCcver\\b|\\bcellularchange\\b|\\bcff\\b|\\bcfycu\\b|\\bcfycur\\b|\\bCh\\/rping\\b|\\bchaletgirl\\b|\\bchangejobs\\b|\\bCharliejust\\b|\\bChatter\\/\\'rtg\\b|\\bCHATTERWG\\b|\\bChequeredlove\\b|\\bcHIRPINcs\\b|\\bchjldishness\\b|\\bchlldrcn\\b|\\bchlldren\\b|\\bchocolatte\\b|\\bCho\\/r\\b|\\bcHucKl\\_Es\\b|\\bCIark\\b|\\bCIear\\b|\\bcircumcised\\_\\b|\\bckay\\b|\\bcl\\_osEs\\b|\\bCLATTERWG\\b|\\bcn\\b|\\bcne\\b|\\bcnes\\b|\\bCoincidenta\\/\\/y\\b|\\bCOm\\\u20ac\\b|\\bcomp\\/etey\\b|\\bcomplainingabout\\b|\\bcoms\\b|\\bcond\\/lion\\b|\\bconfdence\\b|\\bconhrmed\\b|\\bconnrm\\b|\\bConsecutivelyl\\b|\\bCOUGH5\\b|\\bCouGHING\\b|\\bcouIdn\\'t\\b|\\bcouldjust\\b|\\bcouldn\\'T\\b|\\bcouldn\\'tjust\\b|\\bCouldyou\\b|\\bcrappyjob\\b|\\bCRAsHING\\b|\\bcrder\\b|\\bCrowdcheers\\b|\\bCruoially\\b|\\bcther\\b|\\bcuuld\\b|\\bcver\\b|\\bd\\/\\'dn\\'t\\b|\\bd\\/squietude\\b|\\bD\\\xa4esn\\'t\\b|\\bd\\\xa4n\\'i\\b|\\bd\\\xa4n\\'t\\b|\\bd\\\xb09\\b|\\bd0\\b|\\bD0\\b|\\bD0asn\\'t\\b|\\bDad\\'\\/\\/\\b|\\bdairyjust\\b|\\bDar\\/\\/ng\\b|\\bdc\\b|\\bDcbby\\b|\\bdccsn\\'t\\b|\\bdcctcr\\b|\\bDces\\b|\\bdcgs\\b|\\bdcing\\b|\\bdcn\\'I\\b|\\bdcn\\'t\\b|\\bDcn\\'t\\b|\\bdcughnut\\b|\\bdeclslons\\b|\\bdeedhas\\b|\\bDehnitely\\b|\\bdesewes\\b|\\bdesperate\\/\\\xbby\\b|\\bD\\\ufb02nk\\b|\\bDIAl\\_lNcs\\b|\\bdidn\\'\\!\\b|\\bdidnt\\b|\\bdidn\\'T\\b|\\bdIdn\\'t\\b|\\bdidn\\'t\\_\\b|\\bdidrft\\b|\\bdidrl\\'t\\b|\\bdidyou\\b|\\bdivorcing\\_\\b|\\bdld\\b|\\bdldn\\'t\\b|\\bdlfflcull\\b|\\bdlg\\b|\\bdlsobeyed\\b|\\bdoasn\\'t\\b|\\bDoasn\\'t\\b|\\bdoctoh\\b|\\bDoctor\\_\\_\\_tell\\b|\\bdoesnt\\b|\\bdoesn\\'T\\b|\\bdoesri\\'t\\b|\\bdoesrt\\b|\\bDoesrt\\Line truncated
'fin': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'Katsokaa pa.', u'Katsokaapa.'), (u'Mik!\r\n""e\u201c9ir\xe4\u0131', u'Mik!\r\n-Hengit\xe4!'), (u'Tu lta!', u'Tulta!'), (u'...0I1...', u'...on...'), (u'Ken g\xe4n nauh oja?', u'Keng\xe4nnauhoja?'), (u'k\xe3mmott\xe3V\xe3ll\xe3 mUiStoll\xe3.', u'kammottavana muistona.'), (u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen ksen asun to o ns\xe4.', u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen asuntoonsa.'), (u'Min\xe4 etsin k\xe4siini miehen, joka\r\non aurtanutiestradea ja minua:', u'Min\xe4 etsin k\xe4siini miehen, joka\r\non auttanut Lestradea ja minua:'), (u'Huomaa erityisesti\r\npunaisella merkitty "kitoris.', u'Huomaa erityisesti\r\npunaisella merkitty "klitoris".'), (u'Tulkaa, meill\xe4 on\r\nHa va\u0131ji-bileet suihkussa', u'Tulkaa, meill\xe4 on\r\nHavaiji-bileet suihkussa'), (u'Ta rkoitatko ett\xe4\r\nh\xe4net myrkytettiin?', u'Tarkoitatko ett\xe4\r\nh\xe4net myrkytettiin?'), (u'Odotta kaa soittoani\r\nIev\xe4hdyspaikalla.', u'Odottakaa soittoani\r\nlev\xe4hdyspaikalla.'), (u'Nyt kuuntelet, perska rva.', u'Nyt kuuntelet, perskarva.'), (u'Ta patko h\xe4net sitten?', u'Tapatko h\xe4net sitten?'), (u'Seuraa vissa va/oissa.', u'Seuraavissa valoissa.'), (u'A\u0131o\u0131t rapattaa minut.\r\n- En.', u'Aioit tapattaa minut.\r\n- En.'), (u'Todella vaku uttavaa.', u'Todella vakuuttavaa.'), (u'I-le ovat tuolla alhaalla', u'He ovat tuolla alhaalla'), (u'Nainen kuuluu minulle.\r\n- I-I\xe0ivy siit\xe4, ylikasvuinen hyttynen!', u'Nainen kuuluu minulle.\r\n- H\xe4ivy siit\xe4, ylikasvuinen hyttynen!'), (u'I-Ialuatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.', u'Haluatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.'), (u'Mit\xe4f?', u'Mit\xe4.. ?'), (u'Kuuluuko Hiru ko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.', u'Kuuluuko Hiruko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.'), (u'Anteeks\u0131} painoin kai... -', u'Anteeksi, painoin kai... -'), (u'ja Rea! Ho usew\xedves.', u'ja Real Housewives.'), (u'Et halu n n ut Julkkistansseihinkaan.', u'Et halunnut Julkkistansseihinkaan.'), (u'Laard i k\xe4si?', u'Laardik\xe4si?'), (u'Varo kaa!', u'Varokaa!'), (u'N\xe4ytt\xe4v\xe4t k\xf6 tyt\xf6t v\xe4h \xe4n\r\nh uorahtavi m m i lta?', u'N\xe4ytt\xe4v\xe4tk\xf6 tyt\xf6t v\xe4h\xe4n\r\nhuorahtavimmilta?'), (u'Stif... Ier.', u'Stif... ler.'), (u'J u mantsu kka! M it\xe4?', u'Jumantsukka! Mit\xe4?'), (u'Varasin Ch u m bawam ban,', u'Varasin Chumbawamban,'), (u'J u malavita!', u'Jumalavita!'), (u'S', u'Isi...'), (u'Haluan kertoa jotai n', u'Haluan kertoa jotain'), (u'I-Ialuatte', u'Haluatte')]),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'kellojo', u'kello jo'), (u'onjo', u'on jo'), (u'senj\xe4lkeen', u'sen j\xe4lkeen'), (u'Ts\xe4u', u'Tsau'), (u'hydraulinenjousitus', u'hydraulinen jousitus'), (u'Kevyetja', u'Kevyet ja'), (u'Oleijo', u'Olet jo'), (u'viimeinenjuna', u'viimeinen juna'), (u'n\xe4ytt\xe4\xe4jotenkin', u'n\xe4ytt\xe4\xe4 jotenkin'), (u'onjoku', u'on joku'), (u'Iapsuuteen', u'Lapsuuteen'), (u'Ieikitjunill\xe4', u'leikit junilla'), (u'Sfiy', u'Stig'), (u'Iukulasejani', u'Lukulasejani'), (u'Ieikkiminen', u'Leikkiminen'), (u'K\xe4\xe4lik\xe4\xe4rylepizz\xe4', u'Kaalik\xe4\xe4rylepizza'), (u'sukl\xe4\xe4k\xe4stikkeen', u'suklaakastikkeen'), (u'p\xe4istetun', u'paistetun'), (u'b\xe4n\xe4\xe4nin', u'banaanin'), (u'pifi', u'piti'), (u'a\u0131keasfaan', u'oikeastaan'), (u'Stg', u'Stig'), (u'sikain\ufb02uenssatja', u'sikainfluenssat ja'), (u'Hienojuna', u'Hieno juna'), (u'kiinnostuajunista', u'kiinnostua junista'), (u'h\xe4y\u0131yvetu\u0131\xedn', u'h\xf6yryveturin'), (u'pienaismalli', u'pienoismalli'), (u'ena', u'eno'), (u'racfios\xe3hk\xe4ff\xe1j\xe3n\xe3', u'radios\xe4hk\xf6tt\xe4j\xe4n\xe4'), (u'Amenkan', u'Amerikan'), (u'laiva/la', u'laivalla'), (u'0/in', u'Olin'), (u'Junaha\u0131rasfus', u'Junaharrastus'), (u'enasfa', u'enosta'), (u'/V\u0131\xedn', u'Niin'), (u'Oliivarmasii', u'Olit varmasti'), (u'Internetist\xe4juuri', u'Internetist\xe4 juuri'), (u'hu\u0131janj\xe3nniff\xe5v\xe3\xe0l', u'hurjan j\xe4nnitt\xe4v\xe4\xe4.'), (u'Vaikkajunat', u'Vaikka junat'), (u'k\xe4\xe4ntyija', u'k\xe4\xe4ntyi ja'), (u'osaajotain', u'osaa jotain'), (u'Ieikill\xe4mme', u'leikill\xe4mme'), (u'Bellinjuna', u'Beltin juna'), (u't\xe4st\xe4johtolangasta', u't\xe4st\xe4 johtolangasta'), (u'tuntisijonkun', u'tuntisi jonkun'), (u'Olgajotain', u'Olga jotain'), (u'tulokseivuodesia', u'tulokset vuodesta'), (u'tuloksetvuodesta', u'tulokset vuodesta'), (u'Vainjalkapallo', u'Vain jalkapallo'), (u'lloveyou', u'I love you'), (u'po\ufb02\u2039aisi', u'potkaisi'), (u'minufulos', u'minut ulos'), (u'Ieiv\xe4npaahdinl', u'leiv\xe4npaahdin!'), (u'Ieiv\xe4npaahdinta', u'leiv\xe4npaahdinta'), (u'asuajossain', u'asua jossain'), (u'Koiratjuoksentelivat', u'Koirat juoksentelivat'), (u'tiet\xe4\xe4jotain', u'tiet\xe4\xe4 jotain'), (u'osaatjuna', u'osaat juna'), (u'va/as', u'valas'), (u'va/asperhe', u'valasperhe'), (u'koskeejotain', u'koskee jotain'), (u'I\xe4\xe4kkeens\xe4', u'l\xe4\xe4kkeens\xe4'), (u'Iaulavan', u'laulavan'), (u'Kuulitj\xe4\xe4n', u'Kuulit j\xe4\xe4n'), (u'Ievolle', u'levolle'), (u'Va/aa//e', u'Valaalle'), (u'va/aa//a', u'valaalla'), (u'I\xe4hdenkin', u'l\xe4hdenkin'), (u'Iakkiin', u'lakkiin'), (u'Iohik\xe4\xe4rmeell\xe4', u'lohik\xe4\xe4rmeell\xe4'), (u'Mik\u0131', u'Mik!'), (u'Iukossa', u'lukossa'), (u'Va/aan', u'Valaan'), (u's\xe4ve/m\xe4', u's\xe4velm\xe4'), (u'j\xe4//een', u'j\xe4lleen'), (u'P\xf6\xf6\u0131', u'P\xf6\xf6!'), (u'Hnjaa', u'Hiljaa'), (u'Iiftasin', u'liftasin'), (u'Jute//aan', u'Jutellaan'), (u'Iohduttamaan', u'lohduttamaan'), (u"L'lYP\xe4f\xe4\xe4n", u'Hyp\xe4t\xe4\xe4n'), (u'\xc4\u0131r\u0131\u0131', u'\xc4iti!'), (u'F\u0131\u0131\u0131p\u0131', u'Filip!'), (u'Yr\u203ar\u203a\xe4\xe4\u0131', u'Hypp\xe4\xe4!'), (u'Miki', u'Mik!'), (u'Heng\u0131r\xe4\u0131', u'Hengit\xe4!'), (u'Va/as', u'Valas'), (u'Ko///is', u'Koillis'), (u'Audieja', u'Audie ja'), (u'I/man', u'Ilman'), (u'/entotukia/ukse/ta', u'lentotukialukselta'), (u'/aivastosta', u'laivastosta'), (u'/entotukikohtaan', u'lentotukikohtaan'), (u'tu/ee', u'tulee'), (u'akse/iva//at', u'akselivallat'), (u'a\u0131\u0131ek\u0131rjo\u0131rerr\u0131\u0131n', u'allekirjoitettiin'), (u'Iitkua', u'litkua'), (u'0li', u'Oli'), (u'Iaskuvarjojoukkoihin', u'laskuvarjojoukkoihin'), (u'Iaskuvarjojoukoissa', u'laskuvarjojoukoissa'), (u'Tarvitsetjotain', u'Tarvitset jotain'), (u'Ieukaremmi', u'leukaremmi'), (u'Iainaatko', u'lainaatko'), (u'p\xe4\xe4llik\xf6lleja', u'p\xe4\xe4llik\xf6lle ja'), (u'I\xe4hell\xe4ni', u'l\xe4hell\xe4ni'), (u'Soti/aan', u'Sotilaan'), (u'va//attava', u'vallattava'), (u'viho//ise/ta', u'viholliselta'), (u'/iittoutuneet', u'liittoutuneet'), (u'voitjohtaa', u'voit johtaa'), (u'pohditkojotain', u'pohditko jotain'), (u'viho//ista', u'vihollista'), (u'sej\xe4isi', u'se j\xe4isi'), (u'Ient\xe4jill\xe4', u'lent\xe4jill\xe4'), (u'Soltutl', u'Soltut!'), (u'Iaulustamme', u'laulustamme'), (u'Iakkiani', u'lakkiani'), (u'Iiemeen', u'liemeen'), (u'kanadala\u0131\u0161ia', u'kanadalaisia'), (u'si//anp\xe4\xe4asema', u'sillanp\xe4\xe4asema'), (u'vahv\u0131\u0161tettiin', u'vahv\u0131stettiin'), (u'tu/ituki', u'tulituki'), (u'eliitt\u0131joukkoa', u'eliittijoukkoa'), (u'pa\u0131ka\u0131\u0131as\u0131\u0131', u'paikallasi!'), (u'Ieikkinyt', u'leikkinyt'), (u'Iujitettu', u'lujitettu'), (u'Ete/\xe4', u'Etel\xe4'), (u'viho//isranna//e', u'vihollisrannalle'), (u'sivusta/ta', u'sivustalta'), (u'/oppuisi', u'loppuisi'), (u'Iaskuvarjojoukkojen', u'laskuvarjojoukkojen'), (u'p\xe4\xe4tt\xe4nytj\xe4\xe4d\xe4', u'p\xe4\xe4tt\xe4nyt j\xe4\xe4d\xe4'), (u'IuutnanteillLine truncated
'pattern': u"(um)\\bkellojo\\b|\\bonjo\\b|\\bsenj\\\xe4lkeen\\b|\\bTs\\\xe4u\\b|\\bhydraulinenjousitus\\b|\\bKevyetja\\b|\\bOleijo\\b|\\bviimeinenjuna\\b|\\bn\\\xe4ytt\\\xe4\\\xe4jotenkin\\b|\\bonjoku\\b|\\bIapsuuteen\\b|\\bIeikitjunill\\\xe4\\b|\\bSfiy\\b|\\bIukulasejani\\b|\\bIeikkiminen\\b|\\bK\\\xe4\\\xe4lik\\\xe4\\\xe4rylepizz\\\xe4\\b|\\bsukl\\\xe4\\\xe4k\\\xe4stikkeen\\b|\\bp\\\xe4istetun\\b|\\bb\\\xe4n\\\xe4\\\xe4nin\\b|\\bpifi\\b|\\ba\\\u0131keasfaan\\b|\\bStg\\b|\\bsikain\\\ufb02uenssatja\\b|\\bHienojuna\\b|\\bkiinnostuajunista\\b|\\bh\\\xe4y\\\u0131yvetu\\\u0131\\\xedn\\b|\\bpienaismalli\\b|\\bena\\b|\\bracfios\\\xe3hk\\\xe4ff\\\xe1j\\\xe3n\\\xe3\\b|\\bAmenkan\\b|\\blaiva\\/la\\b|\\b0\\/in\\b|\\bJunaha\\\u0131rasfus\\b|\\benasfa\\b|\\b\\/V\\\u0131\\\xedn\\b|\\bOliivarmasii\\b|\\bInternetist\\\xe4juuri\\b|\\bhu\\\u0131janj\\\xe3nniff\\\xe5v\\\xe3\\\xe0l\\b|\\bVaikkajunat\\b|\\bk\\\xe4\\\xe4ntyija\\b|\\bosaajotain\\b|\\bIeikill\\\xe4mme\\b|\\bBellinjuna\\b|\\bt\\\xe4st\\\xe4johtolangasta\\b|\\btuntisijonkun\\b|\\bOlgajotain\\b|\\btulokseivuodesia\\b|\\btuloksetvuodesta\\b|\\bVainjalkapallo\\b|\\blloveyou\\b|\\bpo\\\ufb02\\\u2039aisi\\b|\\bminufulos\\b|\\bIeiv\\\xe4npaahdinl\\b|\\bIeiv\\\xe4npaahdinta\\b|\\basuajossain\\b|\\bKoiratjuoksentelivat\\b|\\btiet\\\xe4\\\xe4jotain\\b|\\bosaatjuna\\b|\\bva\\/as\\b|\\bva\\/asperhe\\b|\\bkoskeejotain\\b|\\bI\\\xe4\\\xe4kkeens\\\xe4\\b|\\bIaulavan\\b|\\bKuulitj\\\xe4\\\xe4n\\b|\\bIevolle\\b|\\bVa\\/aa\\/\\/e\\b|\\bva\\/aa\\/\\/a\\b|\\bI\\\xe4hdenkin\\b|\\bIakkiin\\b|\\bIohik\\\xe4\\\xe4rmeell\\\xe4\\b|\\bMik\\\u0131\\b|\\bIukossa\\b|\\bVa\\/aan\\b|\\bs\\\xe4ve\\/m\\\xe4\\b|\\bj\\\xe4\\/\\/een\\b|\\bP\\\xf6\\\xf6\\\u0131\\b|\\bHnjaa\\b|\\bIiftasin\\b|\\bJute\\/\\/aan\\b|\\bIohduttamaan\\b|\\bL\\'lYP\\\xe4f\\\xe4\\\xe4n\\b|\\b\\\xc4\\\u0131r\\\u0131\\\u0131\\b|\\bF\\\u0131\\\u0131\\\u0131p\\\u0131\\b|\\bYr\\\u203ar\\\u203a\\\xe4\\\xe4\\\u0131\\b|\\bMiki\\b|\\bHeng\\\u0131r\\\xe4\\\u0131\\b|\\bVa\\/as\\b|\\bKo\\/\\/\\/is\\b|\\bAudieja\\b|\\bI\\/man\\b|\\b\\/entotukia\\/ukse\\/ta\\b|\\b\\/aivastosta\\b|\\b\\/entotukikohtaan\\b|\\btu\\/ee\\b|\\bakse\\/iva\\/\\/at\\b|\\ba\\\u0131\\\u0131ek\\\u0131rjo\\\u0131rerr\\\u0131\\\u0131n\\b|\\bIitkua\\b|\\b0li\\b|\\bIaskuvarjojoukkoihin\\b|\\bIaskuvarjojoukoissa\\b|\\bTarvitsetjotain\\b|\\bIeukaremmi\\b|\\bIainaatko\\b|\\bp\\\xe4\\\xe4llik\\\xf6lleja\\b|\\bI\\\xe4hell\\\xe4ni\\b|\\bSoti\\/aan\\b|\\bva\\/\\/attava\\b|\\bviho\\/\\/ise\\/ta\\b|\\b\\/iittoutuneet\\b|\\bvoitjohtaa\\b|\\bpohditkojotain\\b|\\bviho\\/\\/ista\\b|\\bsej\\\xe4isi\\b|\\bIent\\\xe4jill\\\xe4\\b|\\bSoltutl\\b|\\bIaulustamme\\b|\\bIakkiani\\b|\\bIiemeen\\b|\\bkanadala\\\u0131\\\u0161ia\\b|\\bsi\\/\\/anp\\\xe4\\\xe4asema\\b|\\bvahv\\\u0131\\\u0161tettiin\\b|\\btu\\/ituki\\b|\\beliitt\\\u0131joukkoa\\b|\\bpa\\\u0131ka\\\u0131\\\u0131as\\\u0131\\\u0131\\b|\\bIeikkinyt\\b|\\bIujitettu\\b|\\bEte\\/\\\xe4\\b|\\bviho\\/\\/isranna\\/\\/e\\b|\\bsivusta\\/ta\\b|\\b\\/oppuisi\\b|\\bIaskuvarjojoukkojen\\b|\\bp\\\xe4\\\xe4tt\\\xe4nytj\\\xe4\\\xe4d\\\xe4\\b|\\bIuutnanteille\\b|\\bI\\\xe4ht\\\xf6valmiiksi\\b|\\bIokoisat\\b|\\bKorjaus\\/ukemat\\b|\\btanke\\/\\/\\/e\\b|\\bky\\\u0131\\\u0131\\\xe4\\\u0131\\b|\\bIisti\\\xe4\\b|\\bKunniamita\\/in\\b|\\bVemon\\b|\\bfied\\\xe3n\\b|\\bEi\\\u0131is\\b|\\bInlem\\\xe4tion\\\xe4\\b|\\bholelfss\\\xe4\\b|\\bHan\\\u0131ey\\b|\\bpeikk\\\xe4\\b|\\bEhisl\\\xe3\\b|\\bY\\\ufb02\\\xe3ll\\\xe3v\\\xe3\\b|\\bmahdolisuus\\b|\\bloisteiaan\\b|\\baku\\b|\\bGaronilie\\b|\\bIikainen\\b|\\bvaiehtelijoita\\b|\\bpuutari\\\u0131aasi\\b|\\bGarunin\\b|\\boravaietti\\\xe4\\b|\\bpaijon\\b|\\bsutja\\b|\\bgospeikvartetissa\\b|\\bIauiajaksi\\b|\\bviihdylt\\\xe4j\\\xe4\\b|\\bhannaala\\b|\\bIaulajalta\\b|\\bsaatjotain\\b|\\bL\\\xf6yd\\\xe4njonkun\\b|\\bpy\\\xfcr\\\xedyi\\b|\\bCn\\\u0131dupia\\b|\\bIiikaa\\b|\\bke\\\u0131taa\\b|\\bThafs\\b|\\bKappaietta\\b|\\bsoijoka\\b|\\bLevytl\\\xe4\\b|\\bpaiaamista\\b|\\bkuonnunn\\b|\\bTytt\\\xfcyst\\\xe4v\\\xe4t\\b|\\bk\\\xe3p\\\xe3l\\\xf6ifiin\\b|\\bOiko\\b|\\btuipalo\\b|\\bhebofiavaa\\b|\\bongeina\\b|\\bongeimia\\b|\\bAjateikaa\\b|\\bku\\\u0131ki\\b|\\blhailen\\b|\\bL\\\xe4ht\\\xfcsi\\b|\\byhti\\\xf6ile\\b|\\beitoimi\\b|\\bvoij\\\xe4\\\xe4d\\\xe4\\b|\\bPomkat\\b|\\bkon\\\u0131ata\\b|\\bkonsentien\\b|\\bSep\\\xe3\\b|\\bhebolus\\b|\\bk\\\xfcyryss\\\xe4\\b|\\brepiat\\b|\\bkuikee\\b|\\bpon\\\u0131koita\\b|\\bnaisetja\\b|\\bten\\\u0131etuileeksi\\b|\\byl\\\xe4puolelia\\b|\\bkuullut180\\b|\\bIapsellista\\b|\\besiinnytja\\b|\\bIaulat\\b|\\bHenanjestas\\b|\\bteilie\\b|\\bIIe\\b|\\bt\\\xe4ilaisia\\b|\\bVaru\\b|\\bnimeli\\\xe4\\\xe4n\\b|\\banneijaan\\b|\\bpen\\\u0131staa\\b|\\bminkkitu\\\u0131kkia\\b|\\bminkkituiiiilla\\b|\\bTen\\\u0131etuioa\\b|\\bkuitalevy\\\xe4\\b|\\bei\\\xe4m\\\xe4ss\\\xe4\\b|\\bjutkaisua\\b|\\bFo\\\u0131t\\b|\\boien\\b|\\basioilie\\b|\\bEitarvitsekaan\\b|\\bp\\\xf6kenyin\\b|\\byll\\\xe4iiyy\\b|\\bkomeaita\\b|\\bChadie\\b|\\blaulaisilteko\\b|\\bIaittaa\\b|\\biytt\\\xe4renne\\b|\\bpikkutytLine truncated
'fra': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u" I'", u" l'"), (u" |'", u" l'")]),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'"D\'ac:c:ord."', u'"D\'accord."'), (u'\u201ci QU\xce gagne, qui perd,', u'ni qui gagne, qui perd,'), (u"L'ac:c:ent est mis \r\n \r\n sur son trajet jusqu'en Suisse.", u"L'accent est mis \r\n \r\n sur son trajet jusqu'en Suisse."), (u"C'est la plus gentille chose \r\n \r\n qu'Hitchc:oc:k m'ait jamais dite.", u"C'est la plus gentille chose \r\n \r\n qu'Hitchcock m'ait jamais dite."), (u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventu re structur\xe9e,", u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventure structur\xe9e,"), (u'et le film Shadow of a man \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.', u'et le film <i>Shadow of a man</i> \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.'), (u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec One night with you.', u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec <i>One night with you</i>.'), (u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 C)c:ala, en Floride.', u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 Ocala, en Floride.'), (u'Tokyo Pop et A Taxing Woman? Return.', u"Tokyo Pop et A Taxing Woman's Return."), (u'Peter H u nt.', u'Peter Hunt.'), (u'"C\'est bien mieux dans Peau. \r\n \r\n On peut s\ufb02\xe9clabousser, faire du bruit."', u'"C\'est bien mieux dans l\'eau. \r\n \r\n On peut s\'\xe9clabousser, faire du bruit."')]),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'@immatriculation', u"d'immatriculation"), (u'acquer', u'acqu\xe9r'), (u'acteurjoue', u'acteur joue'), (u'aerien', u'a\xe9rien'), (u'agreable', u'agr\xe9able'), (u'aientjamais', u'aient jamais'), (u'AII', u'All'), (u'aitjamais', u'ait jamais'), (u'aitjus', u'ait jus'), (u'alle', u'all\xe9'), (u'alles', u'all\xe9s'), (u'appele', u'appel\xe9'), (u'apres', u'apr\xe8s'), (u'aujourdhui', u"aujourd'hui"), (u'aupres', u'aupr\xe8s'), (u'beaute', u'beaut\xe9'), (u'cabossee', u'caboss\xe9e'), (u"carj'", u"car j'"), (u"Carj'", u"Car j'"), (u'carla', u'car la'), (u'CEdipe', u'\u0152dipe'), (u'Cest', u"C'est"), (u"c'etaient", u"c'\xe9taient"), (u'C\xe9taient', u"C'\xe9taient"), (u"c'etait", u"c'\xe9tait"), (u"C'etait", u"C'\xe9tait"), (u'C\xe9tait', u"C'\xe9tait"), (u'choregraphiee', u'chor\xe9graphi\xe9e'), (u'cinema', u'cin\xe9ma'), (u"cl'AIcatraz", u"d'Alcatraz"), (u'cles', u'cl\xe9s'), (u'c\u0153urjoie', u'c\u0153ur-joie'), (u'completer', u'compl\xe9ter'), (u'costumiere', u'costumi\xe8re'), (u'cree', u'cr\xe9\xe9'), (u'daccord', u"d'accord"), (u"d'AIbert", u"d'Albert"), (u"d'AIdous", u"d'Aldous"), (u"d'AIec", u"d'Alec"), (u'danniversaire', u"d'anniversaire"), (u"d'Arra'bida", u"d'Arrabida"), (u"d'autod\xe9rision", u"d'auto-d\xe9rision"), (u'dautres', u"d'autres"), (u'debattait', u'd\xe9battait'), (u'decor', u'd\xe9cor'), (u'decorateurs', u'd\xe9corateurs'), (u'decors', u'd\xe9cors'), (u'defi', u'd\xe9fi'), (u'dej\xe0', u'd\xe9j\xe0'), (u'd\xe9j\xe0m', u'd\xe9j\xe0...'), (u'dejeunait', u'd\xe9jeunait'), (u'dengager', u"d'engager"), (u'd\xe9quipement', u"d'\xe9quipement"), (u'd\xe9rni\xe8r\xe9', u'derni\xe8re'), (u'Desole', u'D\xe9sol\xe9'), (u'dessayage', u"d'essayage"), (u'dessence', u"d'essence"), (u'd\xe9taient', u"c'\xe9taient"), (u'detail', u'd\xe9tail'), (u'dexcellents', u"d'excellents"), (u'dexp\xe9rience', u"d'exp\xe9rience"), (u'dexp\xe9riences', u"d'exp\xe9riences"), (u"d'h\xe9ro'l'ne", u"d'h\xe9ro\xefne"), (u"d'idees", u"d'id\xe9es"), (u"d'intensite", u"d'intensit\xe9"), (u'dontj', u'dont j'), (u'doublaitAlfo', u'doublait Alfo'), (u'DrNo', u'Dr No'), (u"e'", u'\xe9'), (u'ecrit', u'\xe9crit'), (u'elegant', u'\xe9l\xe9gant'), (u'Ell\xe9', u'Elle'), (u'\xe9n', u'en'), (u'equipe', u'\xe9quipe'), (u'erjus', u'er jus'), (u'estjamais', u'est jamais'), (u'\xe9t', u'et'), (u'etaient', u'\xe9taient'), (u'etait', u'\xe9tait'), (u'ete', u'\xe9t\xe9'), (u'etiez', u'\xe9tiez'), (u"etj'", u"et j'"), (u"Etj'", u"Et j'"), (u'etje', u'et je'), (u'Etje', u'Et je'), (u'EtsouvenL', u'Et souvent'), (u'eviter', u'\xe9viter'), (u'Fabsence', u"l'absence"), (u'fadapter', u"t'adapter"), (u'fadore', u"j'adore"), (u'F\xe2ge', u"l'\xe2ge"), (u'Fagent', u"l'agent"), (u'faiessay\xe9', u"j'ai essay\xe9"), (u'Failure', u"l'alllure"), (u'Fambiance', u"l'ambiance"), (u'Famener', u"l'amener"), (u'Fanniversaire', u"l'anniversaire"), (u'Fapparence', u"l'apparence"), (u'Fapres', u"l'apres"), (u'Fapr\xe8s', u"l'apr\xe8s"), (u'Farm\xe9e', u"l'arm\xe9e"), (u'Farri\xe8re', u"l'arri\xe8re"), (u'Farriv\xe9e', u"l'arriv\xe9e"), (u'Fascenseur', u"l'ascenseur"), (u'Fascension', u"l'ascension"), (u'Fassaut', u"l'assaut"), (u'Fassomme', u"l'assomme"), (u'Fatmosph\xe8re', u"l'atmosph\xe8re"), (u'Fattention', u"l'attention"), (u'Favalanche', u"l'avalanche"), (u'F\xe9clairage', u"l'\xe9clairage"), (u'F\xe9cran', u"l'\xe9cran"), (u'F\xe9motion', u"l'\xe9motion"), (u'Femplacement', u"l'emplacement"), (u'Fendroit', u"l'endroit"), (u'Fenseigne', u"l'enseigne"), (u'Fensemble', u"l'ensemble"), (u'Fentouraient', u"l'entouraient"), (u'Fentr\xe9e', u"l'entr\xe9e"), (u'F\xe9paisseur', u"l'\xe9paisseur"), (u'F\xe9poque', u"l'\xe9poque"), (u'F\xe9quipe', u'\xc9quipe'), (u'Fespace', u"l'espace"), (u'fesp\xe9rais', u"j'esp\xe9rais"), (u'Fesp\xe8re', u"l'esp\xe8re"), (u'Festh\xe9tique', u"l'esth\xe9tique"), (u'Fetranger', u"l'etranger"), (u'F\xe9vasion', u"l'\xe9vasion"), (u'F\xe9voque', u"l'\xe9voque"), (u'Fexp\xe9rience', u"l'exp\xe9rience"), (u'Fexplique', u"l'explique"), (u'Fexplosion', u"l'explosion"), (u'Fext\xe9rieur', u"l'ext\xe9rieur"), (u'Fhabituelle', u"l'habituelle"), (u'Fh\xe9licopt\xe8re', u"l'h\xe9licopt\xe8re"), (u'Fh\xe9liport', u"l'h\xe9liport"), (u'Fh\xe9listation', u"l'h\xe9listation"), (u'Fhonneur', u"l'honneur"), (u'Fhorloge', u"l'horloge"), (u'Fid\xe9e', u"l'id\xe9e"), (u'Fimage', u"l'image"), (u'Fimportance', u"l'importance"), (u'Fimpression', u"l'impression"), (u'Finfluence', u"l'influence"), (u'Finscription', u"l'inscription"), (u'Fint\xe9rieur', u"l'int\xe9rieur"), (u'Fintrigue', u"l'intrigue"), (u'Fobjectif', u"l'objectif"), (u'Foccasion', u"l'occasion"), (u'Fordre', u"l'ordre"), (u'Forigine', u"l'origine"), (u'fr\xeare', u'fr\xe8re'), (u'gaylns', u'gaijins'), (u'general', u'g\xe9n\xe9ral'), (u'hawa\xefennel', u'hawa\xefenne'), (u"hawa'l'en", u'hawa\xefen'), (u'Ia', u'la'), (u'I\xe0', u'l\xe0'), (u'Iaryngotomie', u'laryngotomie'), (u'idee', u'id\xe9e'), (u'idees', u'id\xe9es'), (u'Ie', u'le'), (u'IeLine truncated
'pattern': u"(um)\\b\\@immatriculation\\b|\\bacquer\\b|\\bacteurjoue\\b|\\baerien\\b|\\bagreable\\b|\\baientjamais\\b|\\bAII\\b|\\baitjamais\\b|\\baitjus\\b|\\balle\\b|\\balles\\b|\\bappele\\b|\\bapres\\b|\\baujourdhui\\b|\\baupres\\b|\\bbeaute\\b|\\bcabossee\\b|\\bcarj\\'\\b|\\bCarj\\'\\b|\\bcarla\\b|\\bCEdipe\\b|\\bCest\\b|\\bc\\'etaient\\b|\\bC\\\xe9taient\\b|\\bc\\'etait\\b|\\bC\\'etait\\b|\\bC\\\xe9tait\\b|\\bchoregraphiee\\b|\\bcinema\\b|\\bcl\\'AIcatraz\\b|\\bcles\\b|\\bc\\\u0153urjoie\\b|\\bcompleter\\b|\\bcostumiere\\b|\\bcree\\b|\\bdaccord\\b|\\bd\\'AIbert\\b|\\bd\\'AIdous\\b|\\bd\\'AIec\\b|\\bdanniversaire\\b|\\bd\\'Arra\\'bida\\b|\\bd\\'autod\\\xe9rision\\b|\\bdautres\\b|\\bdebattait\\b|\\bdecor\\b|\\bdecorateurs\\b|\\bdecors\\b|\\bdefi\\b|\\bdej\\\xe0\\b|\\bd\\\xe9j\\\xe0m\\b|\\bdejeunait\\b|\\bdengager\\b|\\bd\\\xe9quipement\\b|\\bd\\\xe9rni\\\xe8r\\\xe9\\b|\\bDesole\\b|\\bdessayage\\b|\\bdessence\\b|\\bd\\\xe9taient\\b|\\bdetail\\b|\\bdexcellents\\b|\\bdexp\\\xe9rience\\b|\\bdexp\\\xe9riences\\b|\\bd\\'h\\\xe9ro\\'l\\'ne\\b|\\bd\\'idees\\b|\\bd\\'intensite\\b|\\bdontj\\b|\\bdoublaitAlfo\\b|\\bDrNo\\b|\\be\\'\\b|\\becrit\\b|\\belegant\\b|\\bEll\\\xe9\\b|\\b\\\xe9n\\b|\\bequipe\\b|\\berjus\\b|\\bestjamais\\b|\\b\\\xe9t\\b|\\betaient\\b|\\betait\\b|\\bete\\b|\\betiez\\b|\\betj\\'\\b|\\bEtj\\'\\b|\\betje\\b|\\bEtje\\b|\\bEtsouvenL\\b|\\beviter\\b|\\bFabsence\\b|\\bfadapter\\b|\\bfadore\\b|\\bF\\\xe2ge\\b|\\bFagent\\b|\\bfaiessay\\\xe9\\b|\\bFailure\\b|\\bFambiance\\b|\\bFamener\\b|\\bFanniversaire\\b|\\bFapparence\\b|\\bFapres\\b|\\bFapr\\\xe8s\\b|\\bFarm\\\xe9e\\b|\\bFarri\\\xe8re\\b|\\bFarriv\\\xe9e\\b|\\bFascenseur\\b|\\bFascension\\b|\\bFassaut\\b|\\bFassomme\\b|\\bFatmosph\\\xe8re\\b|\\bFattention\\b|\\bFavalanche\\b|\\bF\\\xe9clairage\\b|\\bF\\\xe9cran\\b|\\bF\\\xe9motion\\b|\\bFemplacement\\b|\\bFendroit\\b|\\bFenseigne\\b|\\bFensemble\\b|\\bFentouraient\\b|\\bFentr\\\xe9e\\b|\\bF\\\xe9paisseur\\b|\\bF\\\xe9poque\\b|\\bF\\\xe9quipe\\b|\\bFespace\\b|\\bfesp\\\xe9rais\\b|\\bFesp\\\xe8re\\b|\\bFesth\\\xe9tique\\b|\\bFetranger\\b|\\bF\\\xe9vasion\\b|\\bF\\\xe9voque\\b|\\bFexp\\\xe9rience\\b|\\bFexplique\\b|\\bFexplosion\\b|\\bFext\\\xe9rieur\\b|\\bFhabituelle\\b|\\bFh\\\xe9licopt\\\xe8re\\b|\\bFh\\\xe9liport\\b|\\bFh\\\xe9listation\\b|\\bFhonneur\\b|\\bFhorloge\\b|\\bFid\\\xe9e\\b|\\bFimage\\b|\\bFimportance\\b|\\bFimpression\\b|\\bFinfluence\\b|\\bFinscription\\b|\\bFint\\\xe9rieur\\b|\\bFintrigue\\b|\\bFobjectif\\b|\\bFoccasion\\b|\\bFordre\\b|\\bForigine\\b|\\bfr\\\xeare\\b|\\bgaylns\\b|\\bgeneral\\b|\\bhawa\\\xefennel\\b|\\bhawa\\'l\\'en\\b|\\bIa\\b|\\bI\\\xe0\\b|\\bIaryngotomie\\b|\\bidee\\b|\\bidees\\b|\\bIe\\b|\\bIes\\b|\\bIester\\b|\\bII\\b|\\bIimit\\b|\\bIIs\\b|\\bimmediatement\\b|\\binsufflee\\b|\\bintegrer\\b|\\binteressante\\b|\\bIogions\\b|\\bIorsqu\\b|\\bisee\\b|\\bIumiere\\b|\\bIynchage\\b|\\bJ\\'espere\\b|\\bJessaie\\b|\\bj\\'etais\\b|\\bJ\\'etais\\b|\\blat\\\xe9ral\\\xe9m\\\xe9nt\\b|\\blci\\b|\\bLci\\b|\\bl\\\xe9\\-\\b|\\blepidopteres\\b|\\blitteraire\\b|\\bll\\b|\\bLl\\b|\\blls\\b|\\bLls\\b|\\bmaintenanu\\b|\\bmaniere\\b|\\bmariee\\b|\\bMayer\\/ing\\b|\\bmeilleurjour\\b|\\bmelange\\b|\\bn\\'avai\\\xe9nt\\b|\\bn\\'etait\\b|\\boitjamais\\b|\\boitjus\\b|\\bontete\\b|\\boperateur\\b|\\bouv\\\xe9rt\\\xe9\\b|\\bP\\\xe9preuve\\b|\\bpere\\b|\\bplateforme\\b|\\bpourjouer\\b|\\bprecipice\\b|\\bpreferes\\b|\\bpremierjour\\b|\\bpresenter\\b|\\bprevu\\b|\\bprevue\\b|\\bpropriete\\b|\\bprot\\\xe8geraient\\b|\\bqu\\\xe9\\b|\\bqwangoiss\\\xe9\\b|\\brealisateur\\b|\\breception\\b|\\bre\\\xe9valu\\b|\\brepute\\b|\\breussi\\b|\\bs\\'arr\\\xe9tait\\b|\\bs\\'ave\\'rer\\b|\\bscenario\\b|\\bscene\\b|\\bscenes\\b|\\bseances\\b|\\bsequence\\b|\\bs\\\ufb02\\\xe9crasa\\b|\\bspeciale\\b|\\bSupen\\b|\\btorturee\\b|\\bUadmirable\\b|\\bUensemblier\\b|\\bUexplosion\\b|\\bUouvre\\b|\\bVaise\\b|\\bvecu\\b|\\bvehicules\\b|\\b\\\u0178appr\\\xe9ciais\\b|\\b\\\u0178esp\\\xe8re\\b|\\b\\\xff\\\xe9trangle\\b"}},
'hrv': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'Ako ej', u'Ako je'), (u'ako ej', u'ako je'), (u'bez svesti', u'bez svijesti'), (u'Bi\u0107u uz', u'Bit \u0107u uz'), (u'bi ja', u'bih ja'), (u'bi la', u'bila'), (u'biti uredu', u'biti u redu'), (u'bi da bude', u'bi biti'), (u'Bi ste', u'Biste'), (u'bilo ko', u'bilo tko'), (u'\u0107e da do\u0111e', u'\u0107e do\u0107i'), (u'da li \u0107u', u'ho\u0107u li'), (u'dali \u0107u', u'ho\u0107u li'), (u'Da li je', u'Je li'), (u'da li je', u'je li'), (u'Da li ste', u'Jeste li'), (u'Da li si', u'Jesi li'), (u'dali si', u'jesi li'), (u'da li \u0107e', u'ho\u0107e li'), (u'dali \u0107e', u'ho\u0107e li'), (u'do srede', u'do srijede'), (u'Dobro ve\u010de', u'Dobra ve\u010der'), (u'Dobro ve\u010der', u'Dobra ve\u010der'), (u'Dobar ve\u010der', u'Dobra ve\u010der'), (u'gdje ide\u0161', u'kamo ide\u0161'), (u'Gdje ide\u0161', u'Kamo ide\u0161'), (u'Gdje sada', u'Kamo sada'), (u'gle ko', u'gle tko'), (u'ho\u0107u da budem', u'\u017eelim biti'), (u'Ho\u0107u da budem', u'\u017delim biti'), (u'ho\u0107u da ka\u017eem', u'\u017eelim re\u0107i'), (u'ho\u0107e\u0161 da ka\u017ee\u0161', u'\u017eeli\u0161 re\u0107i'), (u'ho\u0107e da ka\u017ee', u'\u017eeli re\u0107i'), (u'Izvinite me', u'Ispri\u010dajte me'), (u'Izvinite nas', u'Ispri\u010dajte nas'), (u'izvinite nas', u'ispri\u010dajte nas'), (u'ja bi', u'ja bih'), (u'Ja bi', u'Ja bih'), (u'Jel sam ti', u'Jesam li ti'), (u'Jeli se', u'Je li se'), (u'Jeli sve', u'Je li sve'), (u'Jeli ti', u'Je li ti'), (u'ko zna', u'tko zna'), (u'moglo da bude', u'moglo biti'), (u'moje sau\u010de\u0161\u0107e', u'moja su\u0107ut'), (u'mora da bude', u'mora biti'), (u'Moram da idem', u'Moram i\u0107i'), (u'Moramo da idemo', u'Moramo i\u0107i'), (u'mora\u0161 da ide\u0161', u'mora\u0161 i\u0107i'), (u'na ve\u010der', u'nave\u010der'), (u'Na ve\u010der', u'Nave\u010der'), (u'neko ko', u'netko tko'), (u'nedjelju dana', u'tjedan dana'), (u'Ne mogu da verujem', u'Ne mogu vjerovati'), (u'od kako', u'otkako'), (u'pravo u o\u010di', u'ravno u o\u010di'), (u'Si dobro', u'Jesi li dobro'), (u'Svako ko', u'Svatko tko'), (u'Svo vreme', u'Sve vrijeme'), (u'Svo vrijeme', u'Sve vrijeme'), (u'smeo da', u'smio'), (u'smeli da', u'smjeli'), (u'\u0160to ej', u'\u0160to je'), (u'\u0161to ej', u'\u0161to je'), (u'to ej', u'to je'), (u'To ej', u'To je'), (u'tamo natrag', u'tamo iza'), (u'tamo je natrag', u'tamo je iza'), (u'Tamo je natrag', u'Tamo je iza'), (u'zato sto', u'zato \u0161to'), (u'znati ko', u'znati tko'), (u'\u017eelim da budem', u'\u017eelim biti'), (u'\u017delim da budem', u'\u017delim biti'), (u'\u017eeli\u0161 da bude\u0161', u'\u017eeli\u0161 biti'), (u'\u017eelim da odem', u'\u017eelim oti\u0107i'), (u'\u017eeli\u0161 da ode\u0161', u'\u017eeli\u0161 oti\u0107i'), (u'\u017eelim da znam', u'\u017eelim znati'), (u'\u017eeli\u0161 da zna\u0161', u'\u017eeli\u0161 znati')]),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'advokati', u'odvjetnici'), (u'Advokati', u'Odvjetnici'), (u'advokatima', u'odvjetnicima'), (u'Advokatima', u'Odvjetnicima'), (u'amin', u'amen'), (u'Amin', u'Amen'), (u'ba\u0161ta', u'vrt'), (u'Ba\u0161ta', u'Vrt'), (u'ba\u0161te', u'vrtovi'), (u'Ba\u0161te', u'Vrtovi'), (u'ba\u0161ti', u'vrtu'), (u'ba\u0161tu', u'vrt'), (u'Ba\u0161tu', u'Vrt'), (u'ba\u0161tom', u'vrtom'), (u'bedan', u'bijedan'), (u'bede', u'bijede'), (u'bedi', u'bijedi'), (u'bejah', u'bijah'), (u'bele\u0161ci', u'bilje\u0161ci'), (u'bimso', u'bismo'), (u'bioskop', u'kino'), (u'bioskopi', u'kina'), (u'bitci', u'bitki'), (u'blije\u0111i', u'blje\u0111i'), (u'beg', u'bijeg'), (u'begu', u'bijegu'), (u'beja\u0161e', u'bija\u0161e'), (u'bekstvo', u'bijeg'), (u'bekstvu', u'bijegu'), (u'begstvu', u'bijegu'), (u'bes', u'bijes'), (u'besa', u'bijesa'), (u'besan', u'bijesan'), (u'besom', u'bijesom'), (u'besu', u'bijesu'), (u'be\u0161e', u'bje\u0161e'), (u'bioje', u'bio je'), (u'bi smo', u'bismo'), (u'bi ste', u'biste'), (u'bled', u'blijed'), (u'blede', u'blijede'), (u'boksuje\u0161', u'boksa\u0161'), (u'bolesan', u'bolestan'), (u'braon', u'sme\u0111a'), (u'bregu', u'brijegu'), (u'bti', u'biti'), (u'ceo', u'cijeli'), (u'Ceo', u'Cijeli'), (u'cepa', u'cijepa'), (u'cev', u'cijev'), (u'cevi', u'cijevi'), (u'cev\u010dica', u'cjev\u010dica'), (u'cev\u010dicu', u'cjev\u010dicu'), (u'cvetu', u'cvijetu'), (u'cvjetu', u'cvijetu'), (u'cvjetom', u'cvijetom'), (u'\u010dar\u0161av', u'plahta'), (u'\u010dar\u0161ave', u'plahte'), (u'\u010dar\u0161avima', u'plahtama'), (u'\u010das', u'sat'), (u'\u010detvoro', u'\u010detvero'), (u'\u010cita\u0107u', u'\u010citat \u0107u'), (u'\u010derku', u'k\u0107er'), (u'\u010cerku', u'K\u0107er'), (u'\u0107erku', u'k\u0107er'), (u'\u0106erku', u'K\u0107er'), (u'\u0107erkama', u'k\u0107erima'), (u'\u010derkama', u'k\u0107erima'), (u'\u0107erkom', u'k\u0107eri'), (u'\u010derkom', u'k\u0107eri'), (u'k\u0107erkom', u'k\u0107eri'), (u'k\u010derkom', u'k\u0107eri'), (u'\u0107ebe', u'deku'), (u'\u0107ebetu', u'deki'), (u'\u010dk', u'\u010dak'), (u'\u0107\u0161', u'\u0107e\u0161'), (u'\u0107ale', u'tata'), (u'\u0107aletom', u'ocem'), (u'\u0107aleta', u'oca'), (u'\u0107aletu', u'ocu'), (u'\u0107orsokak', u'slijepa ulica'), (u'\u0107orsokaku', u'slijepoj ulici'), (u'\u0107o\u0161ak', u'ugao'), (u'\u0107o\u0161ku', u'uglu'), (u'\u0107erka', u'k\u0107i'), (u'\u0106erka', u'K\u0107i'), (u'\u0107mo', u'\u0107emo'), (u'\u0107te', u'\u0107ete'), (u'\u010du\u0107e', u'\u010dut \u0107e'), (u'\u010du\u0107emo', u'\u010dut \u0107emo'), (u'\u010cu\u0107ete', u'\u010cut \u0107ete'), (u'\u010cu\u0107e', u'\u010cut \u0107e'), (u'\u0107utao', u'\u0161utio'), (u'\u0106utao', u'\u0160utio'), (u'daga', u'da ga'), (u'damas', u'danas'), (u'deda', u'djed'), (u'Deda', u'Djed'), (u'dede', u'djeda'), (u'dedi', u'djedu'), (u'dedom', u'djedom'), (u'defini\u0161e', u'definira'), (u'dele\u0107i', u'dijele\u0107i'), (u'deo', u'dio'), (u'Deo', u'Dio'), (u'de\u0161ava', u'doga\u0111a'), (u'dete', u'dijete'), (u'djete', u'dijete'), (u'Dete', u'Dijete'), (u'Djete', u'Dijete'), (u'detektuje', u'detektira'), (u'dodju', u'do\u0111u'), (u'dole', u'dolje'), (u'Dole', u'Dolje'), (u'Donije\u0107u', u'Donijet \u0107u'), (u'do ovde', u'dovde'), (u'dospeo', u'dospio'), (u'dospeju', u'dospiju'), (u'do\u0111avola', u'dovraga'), (u'Do\u0111avola', u'Dovraga'), (u'drug', u'prijatelj'), (u'drugde', u'drugdje'), (u'duuga', u'd\xfaga'), (u'dve', u'dvije'), (u'Dve', u'Dvije'), (u'\u0111avo', u'vrag'), (u'\u0111avola', u'vraga'), (u'\u0111emper', u'd\u017eemper'), (u'd\u017eanki', u'ovisnik'), (u'\u0111ubre', u'sme\u0107e'), (u'eksperti', u'stru\u010dnjaci'), (u'Eksperti', u'Stru\u010dnjaci'), (u'ekspertima', u'stru\u010dnjacima'), (u'en', u'ne'), (u'emitovao', u'emitirao'), (u'emituje', u'emitira'), (u'emitujem', u'emitiram'), (u'emituju', u'emitiraju'), (u'familijama', u'obiteljima'), (u'familiji', u'obitelji'), (u'flertuje', u'o\u010dijuka'), (u'foka', u'tuljan'), (u'foku', u'tuljana'), (u'foke', u'tuljani'), (u'fokama', u'tuljanima'), (u'gde', u'gdje'), (u'Gde', u'Gdje'), (u'Gre\u010den', u'Gretchen'), (u'gre\u0161e', u'grije\u0161e'), (u'gre\u0161ki', u'gre\u0161ci'), (u'Historija', u'Povijest'), (u'Historiju', u'Povijest'), (u'Historije', u'Povijesti'), (u'Historiji', u'Povijesti'), (u'Istorija', u'Povijest'), (u'Istoriju', u'Povijest'), (u'Istorije', u'Povijesti'), (u'Istoriji', u'Povijesti'), (u'historije', u'povijesti'), (u'historiji', u'povijesti'), (u'istorije', u'povijesti'), (u'istoriji', u'povijesti'), (u'ho\u010du', u'ho\u0107u'), (u'Ho\u010du', u'Ho\u0107u'), (u'hte\u0107e', u'htjet \u0107e'), (u'htedoh', u'htjedoh'), (u'i\u010di', u'i\u0107i'), (u'I\u010di', u'I\u0107i'), (u'iko', u'itko'), (u'ignori\u0161i', u'ignoriraj'), (u'Ignori\u0161i', u'Ignoriraj'), (u'ignori\u0161ite', u'ignorirajte'), (u'Ignori\u0161ite', u'Ignorirajte'), (u'ignori\u0161u', u'ignoriraju'), (u'Interesuje', u'Zanima'), (u'Interesuju', u'Zanimaju'), (u'intLine truncated
'pattern': u'(um)\\badvokati\\b|\\bAdvokati\\b|\\badvokatima\\b|\\bAdvokatima\\b|\\bamin\\b|\\bAmin\\b|\\bba\\\u0161ta\\b|\\bBa\\\u0161ta\\b|\\bba\\\u0161te\\b|\\bBa\\\u0161te\\b|\\bba\\\u0161ti\\b|\\bba\\\u0161tu\\b|\\bBa\\\u0161tu\\b|\\bba\\\u0161tom\\b|\\bbedan\\b|\\bbede\\b|\\bbedi\\b|\\bbejah\\b|\\bbele\\\u0161ci\\b|\\bbimso\\b|\\bbioskop\\b|\\bbioskopi\\b|\\bbitci\\b|\\bblije\\\u0111i\\b|\\bbeg\\b|\\bbegu\\b|\\bbeja\\\u0161e\\b|\\bbekstvo\\b|\\bbekstvu\\b|\\bbegstvu\\b|\\bbes\\b|\\bbesa\\b|\\bbesan\\b|\\bbesom\\b|\\bbesu\\b|\\bbe\\\u0161e\\b|\\bbioje\\b|\\bbi\\ smo\\b|\\bbi\\ ste\\b|\\bbled\\b|\\bblede\\b|\\bboksuje\\\u0161\\b|\\bbolesan\\b|\\bbraon\\b|\\bbregu\\b|\\bbti\\b|\\bceo\\b|\\bCeo\\b|\\bcepa\\b|\\bcev\\b|\\bcevi\\b|\\bcev\\\u010dica\\b|\\bcev\\\u010dicu\\b|\\bcvetu\\b|\\bcvjetu\\b|\\bcvjetom\\b|\\b\\\u010dar\\\u0161av\\b|\\b\\\u010dar\\\u0161ave\\b|\\b\\\u010dar\\\u0161avima\\b|\\b\\\u010das\\b|\\b\\\u010detvoro\\b|\\b\\\u010cita\\\u0107u\\b|\\b\\\u010derku\\b|\\b\\\u010cerku\\b|\\b\\\u0107erku\\b|\\b\\\u0106erku\\b|\\b\\\u0107erkama\\b|\\b\\\u010derkama\\b|\\b\\\u0107erkom\\b|\\b\\\u010derkom\\b|\\bk\\\u0107erkom\\b|\\bk\\\u010derkom\\b|\\b\\\u0107ebe\\b|\\b\\\u0107ebetu\\b|\\b\\\u010dk\\b|\\b\\\u0107\\\u0161\\b|\\b\\\u0107ale\\b|\\b\\\u0107aletom\\b|\\b\\\u0107aleta\\b|\\b\\\u0107aletu\\b|\\b\\\u0107orsokak\\b|\\b\\\u0107orsokaku\\b|\\b\\\u0107o\\\u0161ak\\b|\\b\\\u0107o\\\u0161ku\\b|\\b\\\u0107erka\\b|\\b\\\u0106erka\\b|\\b\\\u0107mo\\b|\\b\\\u0107te\\b|\\b\\\u010du\\\u0107e\\b|\\b\\\u010du\\\u0107emo\\b|\\b\\\u010cu\\\u0107ete\\b|\\b\\\u010cu\\\u0107e\\b|\\b\\\u0107utao\\b|\\b\\\u0106utao\\b|\\bdaga\\b|\\bdamas\\b|\\bdeda\\b|\\bDeda\\b|\\bdede\\b|\\bdedi\\b|\\bdedom\\b|\\bdefini\\\u0161e\\b|\\bdele\\\u0107i\\b|\\bdeo\\b|\\bDeo\\b|\\bde\\\u0161ava\\b|\\bdete\\b|\\bdjete\\b|\\bDete\\b|\\bDjete\\b|\\bdetektuje\\b|\\bdodju\\b|\\bdole\\b|\\bDole\\b|\\bDonije\\\u0107u\\b|\\bdo\\ ovde\\b|\\bdospeo\\b|\\bdospeju\\b|\\bdo\\\u0111avola\\b|\\bDo\\\u0111avola\\b|\\bdrug\\b|\\bdrugde\\b|\\bduuga\\b|\\bdve\\b|\\bDve\\b|\\b\\\u0111avo\\b|\\b\\\u0111avola\\b|\\b\\\u0111emper\\b|\\bd\\\u017eanki\\b|\\b\\\u0111ubre\\b|\\beksperti\\b|\\bEksperti\\b|\\bekspertima\\b|\\ben\\b|\\bemitovao\\b|\\bemituje\\b|\\bemitujem\\b|\\bemituju\\b|\\bfamilijama\\b|\\bfamiliji\\b|\\bflertuje\\b|\\bfoka\\b|\\bfoku\\b|\\bfoke\\b|\\bfokama\\b|\\bgde\\b|\\bGde\\b|\\bGre\\\u010den\\b|\\bgre\\\u0161e\\b|\\bgre\\\u0161ki\\b|\\bHistorija\\b|\\bHistoriju\\b|\\bHistorije\\b|\\bHistoriji\\b|\\bIstorija\\b|\\bIstoriju\\b|\\bIstorije\\b|\\bIstoriji\\b|\\bhistorije\\b|\\bhistoriji\\b|\\bistorije\\b|\\bistoriji\\b|\\bho\\\u010du\\b|\\bHo\\\u010du\\b|\\bhte\\\u0107e\\b|\\bhtedoh\\b|\\bi\\\u010di\\b|\\bI\\\u010di\\b|\\biko\\b|\\bignori\\\u0161i\\b|\\bIgnori\\\u0161i\\b|\\bignori\\\u0161ite\\b|\\bIgnori\\\u0161ite\\b|\\bignori\\\u0161u\\b|\\bInteresuje\\b|\\bInteresuju\\b|\\binteresuju\\b|\\bisekao\\b|\\bisterao\\b|\\bistera\\\u0161\\b|\\bIstera\\\u0161\\b|\\bisuvi\\\u0161e\\b|\\bivica\\b|\\bivice\\b|\\bivici\\b|\\bivicu\\b|\\bIzolujete\\b|\\bIzolujte\\b|\\bizgladneo\\b|\\bizmeriti\\b|\\bizmerio\\b|\\bizneti\\b|\\bizvinim\\b|\\bizvini\\\u0161\\b|\\bizviniti\\b|\\bjedamput\\b|\\bjelda\\b|\\bju\\\u010de\\b|\\bJu\\\u010de\\b|\\bkakava\\b|\\bkampuje\\b|\\bkampujemo\\b|\\bkampuju\\b|\\bkancelariji\\b|\\bkancelarijom\\b|\\bkancera\\b|\\bkarmin\\b|\\bkarminom\\b|\\bk\\\u0107erci\\b|\\bk\\\u0107erka\\b|\\bk\\\u010derka\\b|\\bK\\\u0107erka\\b|\\bK\\\u010derka\\b|\\bk\\\u0107erkama\\b|\\bker\\b|\\bKer\\b|\\bkerova\\b|\\bkidnapovan\\b|\\bKidnapovan\\b|\\bkiji\\b|\\bkijim\\b|\\bklasifikuju\\b|\\bKo\\b|\\bkoa\\b|\\bkoaj\\b|\\bkola\\b|\\bkolima\\b|\\bkomandni\\b|\\bkombinuju\\b|\\bkompanija\\b|\\bkom\\\u0161ija\\b|\\bkom\\\u0161iji\\b|\\bkom\\\u0161iluk\\b|\\bkom\\\u0161iluku\\b|\\bkom\\\u0161ije\\b|\\bkom\\\u0161ijama\\b|\\bkontroli\\\u0161u\\b|\\bKontroli\\\u0161u\\b|\\bKontroli\\\u0161i\\b|\\bkontroli\\\u0161i\\b|\\bKontroli\\\u0161ite\\b|\\bkontroli\\\u0161ite\\b|\\bkorpu\\b|\\bkritikuju\\b|\\bkrsta\\b|\\bkrstu\\b|\\bkrsti\\\u0107a\\b|\\bkrsti\\\u0107u\\b|\\bKrsta\\b|\\bKrstu\\b|\\bKrsti\\\u0107a\\b|\\bKrsti\\\u0107u\\b|\\bkrstom\\b|\\bkrstove\\b|\\bKrstove\\b|\\bkrstovima\\b|\\bKrstovima\\b|\\bkri\\\u017eom\\b|\\bkupatilo\\b|\\bkupatilu\\b|\\bkvalifikuju\\b|\\bla\\\u017eeju\\b|\\bla\\\u017eov\\b|\\bla\\\u017eovi\\b|\\bla\\\u017eovu\\b|\\bla\\\u017eovima\\b|\\blebdeo\\b|\\ble\\\u010di\\b|\\blje\\\u010di\\b|\\bLe\\\u010di\\b|\\bLje\\\u010di\\b|\\bLejn\\b|\\bLenja\\b|\\blenji\\b|\\blenja\\b|\\ble\\\u0161nik\\b|\\bleto\\b|\\bletiti\\b|\\bleve\\b|\\blo\\\u017ei\\b|\\bmajca\\b|\\bmajcu\\b|\\bmajcom\\b|\\bMalopre\\b|\\bmalopre\\b|\\bmaloprije\\b|\\bmanifestuje\\b|\\bmehur\\b|\\bmenom\\b|\\bmera\\\u010d\\b|\\bmeri\\b|\\bmere\\b|\\bmerdevine\\b|\\bmerdevinama\\b|\\bme\\\u0161ane\\b|\\bme\\\u0161avina\\b|\\bme\\\u0161avine\\b|\\bme\\\u0161avinu\\b|\\bminut\\b|\\bmo\\\u010d\\b|\\bmuzejem\\b|\\bmuzici\\b|\\bna\\\u010di\\b|\\bnaduvan\\b|\Line truncated
'hun': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict(),
'pattern': None}},
'nld': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'ls', u'Is'), (u'ln', u'In'), (u'lk', u'Ik'), (u'ledereen', u'Iedereen'), (u'ledere', u'Iedere'), (u'lemand', u'Iemand')]),
'pattern': u'(um)\\bls\\b|\\bln\\b|\\blk\\b|\\bledereen\\b|\\bledere\\b|\\blemand\\b'}},
'nor': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict(),
'pattern': None}},
'por': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'IN 6-E', u'N 6 E'), (u'in tegrar-se', u'integrar-se'), (u'in teresse', u'interesse'), (u'in testinos', u'intestinos'), (u'indica \xe7\xe3o', u'indica\xe7\xe3o'), (u'inte tino', u'intestino'), (u'intes tinos', u'intestinos'), (u'L da', u'Lda'), (u'mal estar', u'mal-estar'), (u'mastiga \xe7\xe1o', u'mastiga\xe7\xe3o'), (u'm\xe9di cas', u'm\xe9dicas'), (u'mineo rais', u'minerais'), (u'mola res', u'molares'), (u'movi mentos', u'movimentos'), (u'movimen to', u'movimento'), (u'N 5-Estendido', u'N\xba 5 Estendido'), (u'oxig\xe9 nio', u'oxig\xe9nio'), (u'pod mos', u'podemos'), (u'poder-se ia', u'poder-se-ia'), (u'pos sibilidade', u'possibilidade'), (u'possibi lidades', u'possibilidades'), (u'pro duto', u'produto'), (u'procu rar', u'procurar'), (u'Q u e', u'Que'), (u'qualifi cam', u'qualificam'), (u'R egi\xe3o', u'Regi\xe3o'), (u'unsuficien temente', u'insuficientemente')]),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'abitual', u'habitual'), (u'\xe0cerca', u'acerca'), (u'acessor', u'assessor'), (u'ac\xf3lico', u'ac\xf3lito'), (u'a\xe7oreano', u'a\xe7oriano'), (u'actuacao', u'actua\xe7\xe3o'), (u'acucar', u'a\xe7\xfacar'), (u'a\xe7ucar', u'a\xe7\xfacar'), (u'advinhar', u'adivinhar'), (u'africa', u'\xc1frica'), (u'ajuisar', u'ajuizar'), (u'album', u'\xe1lbum'), (u'alcool\xe9mia', u'alcoolemia'), (u'aldi\xe3o', u'alde\xe3o'), (u'algerino', u'argelino'), (u'ameixeal', u'ameixial'), (u'amia\xe7a', u'amea\xe7a'), (u'analizar', u'analisar'), (u'and\xe1ste', u'andaste'), (u'anemona', u'an\xe9mona'), (u'antartico', u'ant\xe1rctico'), (u'ant\xe1rtico', u'ant\xe1rctico'), (u'antep\xf4r', u'antepor'), (u'ap\xe1rte', u'aparte'), (u'apiadeiro', u'apeadeiro'), (u'apiar', u'apear'), (u'apreciacao', u'aprecia\xe7\xe3o'), (u'arctico', u'\xe1rctico'), (u'arrazar', u'arrasar'), (u'\xe1rtico', u'\xe1rctico'), (u'artifice', u'art\xedfice'), (u'artif\xedcial', u'artificial'), (u'ascen\xe7\xe3o', u'ascens\xe3o'), (u'ass\xfacar', u'a\xe7\xfacar'), (u'aste', u'haste'), (u'aster\xedstico', u'asterisco'), (u'aver\xe7\xe3o', u'avers\xe3o'), (u'avizar', u'avisar'), (u'avulsso', u'avulso'), (u'ba\xednha', u'bainha'), (u'banca-rota', u'bancarrota'), (u'bandeija', u'bandeja'), (u'b\xe9b\xe9', u'beb\xe9'), (u'beige', u'bege'), (u'ben\xe7\xe3o', u'b\xean\xe7\xe3o'), (u'benefici\xeancia', u'benefic\xeancia'), (u'beneficiente', u'beneficente'), (u'benvinda', u'bem-vinda'), (u'benvindo', u'bem-vindo'), (u'boasvindas', u'boas-vindas'), (u'borborinho', u'burburinho'), (u'Brazil', u'Brasil'), (u'bussula', u'b\xfassola'), (u'cabo-verdeano', u'cabo-verdiano'), (u'caimbras', u'c\xe3ibras'), (u'calc\xe1reo', u'calc\xe1rio'), (u'calsado', u'cal\xe7ado'), (u'calv\xedce', u'calv\xedcie'), (u'camoneano', u'camoniano'), (u'campi\xe3o', u'campe\xe3o'), (u'can\xe7acos', u'cansa\xe7os'), (u'caracter', u'car\xe1cter'), (u'caract\xe9res', u'caracteres'), (u'catequeze', u'catequese'), (u'catequisador', u'catequizador'), (u'catequisar', u'catequizar'), (u'ch\xedcara', u'x\xedcara'), (u'ciclano', u'sicrano'), (u'cicrano', u'sicrano'), (u'cidad\xe3es', u'cidad\xe3os'), (u'cidad\xf5es', u'cidad\xe3os'), (u'cincoenta', u'cinquenta'), (u'cinseiro', u'cinzeiro'), (u'cinsero', u'sincero'), (u'citacoes', u'cita\xe7\xf5es'), (u'coaliz\xe3o', u'colis\xe3o'), (u'c\xf4dia', u'c\xf4dea'), (u'comb\xf3io', u'comboio'), (u'comp\xf4r', u'compor'), (u'concerteza', u'com certeza'), (u'constituia', u'constitu\xeda'), (u'constitu\xedu', u'constituiu'), (u'contato', u'contacto'), (u'contens\xe3o', u'conten\xe7\xe3o'), (u'contribuicoes', u'contribui\xe7\xf5es'), (u'c\xf4r', u'cor'), (u'corass\xe3o', u'cora\xe7\xe3o'), (u'cor\xe7ario', u'cors\xe1rio'), (u'cor\xe7\xe1rio', u'cors\xe1rio'), (u'cornprimidosinbo', u'comprimidozinho'), (u'cr\xe2neo', u'cr\xe2nio'), (u'dE', u'de'), (u'defeni\xe7\xe3o', u'defini\xe7\xe3o'), (u'defenido', u'definido'), (u'defenir', u'definir'), (u'deficite', u'd\xe9fice'), (u'degladiar', u'digladiar'), (u'deiche', u'deixe'), (u'desinteria', u'disenteria'), (u'despendio', u'disp\xeandio'), (u'desp\xeandio', u'disp\xeandio'), (u'desplic\xeancia', u'displic\xeancia'), (u'dificulidade', u'dificuldade'), (u'dispender', u'despender'), (u'dispendio', u'disp\xeandio'), (u'distribuido', u'distribu\xeddo'), (u'dru\xedda', u'druida'), (u'\xe9cr\xe3', u'ecr\xe3'), (u'ecran', u'ecr\xe3'), (u'\xe9cran', u'ecr\xe3'), (u'\xeale', u'ele'), (u'elice', u'h\xe9lice'), (u'\xe9lice', u'h\xe9lice'), (u'emiratos', u'emirados'), (u'engolis-te', u'engoliste'), (u'engulir', u'engolir'), (u'enguliste', u'engoliste'), (u'entertido', u'entretido'), (u'entitular', u'intitular'), (u'entreterimento', u'entretenimento'), (u'entreti-me', u'entretive-me'), (u'env\xf3lucro', u'inv\xf3lucro'), (u'er\xf3i', u'her\xf3i'), (u'escluir', u'excluir'), (u'esclus\xe3o', u'exclus\xe3o'), (u'escriv\xf5es', u'escriv\xe3es'), (u'esqueiro', u'isqueiro'), (u'esquesito', u'esquisito'), (u'estacoes', u'esta\xe7\xf5es'), (u'esteje', u'esteja'), (u'excava\xe7\xe3o', u'escava\xe7\xe3o'), (u'excavar', u'escavar'), (u'exdr\xfaxula', u'esdr\xfaxula'), (u'exdr\xfaxulas', u'esdr\xfaxulas'), (u'exitar', u'hesitar'), (u'explicacoes', u'explica\xe7\xf5es'), (u'exquisito', u'esquisito'), (u'extende', u'estende'), (u'extender', u'estender'), (u'f\xe0cilmenfe', u'facilmente'), (u'f\xe0cilmente', u'facilmente'), (u'fariam-lhe', u'far-lhe-iam'), (u'FARM\xc1ClAS', u'FARM\xc1CIAS'), (u'farmec\xeautico', u'farmac\xeautico'), (u'fassa', u'fa\xe7a'), (u'f\xe9bre', u'febre'), (u'fecula', u'f\xe9cula'), (u'f\xe9mea', u'f\xeamea'), (u'femenino', u'feminino'), (u'femininismo', u'feminismo'), (u'f\xedsiologista', u'fisiologista'), (u'fiz\xe9mos', u'fizemos'), (u'fizes-te', u'fizeste'), (u'fl\xf4r', u'flor'), (u'for\xe3o', u'foram'), (u'formalisar', u'formalizar'), (u'f\xf4ro', u'foro'), (u'fos-te', u'foste'), (u'frag\xe2ncia', u'fragr\xe2ncia'), (u'fran\xe7\xeas', u'franc\xeas'), (u'frasqutnho', u'frasquiLine truncated
'pattern': u'(um)\\babitual\\b|\\b\\\xe0cerca\\b|\\bacessor\\b|\\bac\\\xf3lico\\b|\\ba\\\xe7oreano\\b|\\bactuacao\\b|\\bacucar\\b|\\ba\\\xe7ucar\\b|\\badvinhar\\b|\\bafrica\\b|\\bajuisar\\b|\\balbum\\b|\\balcool\\\xe9mia\\b|\\baldi\\\xe3o\\b|\\balgerino\\b|\\bameixeal\\b|\\bamia\\\xe7a\\b|\\banalizar\\b|\\band\\\xe1ste\\b|\\banemona\\b|\\bantartico\\b|\\bant\\\xe1rtico\\b|\\bantep\\\xf4r\\b|\\bap\\\xe1rte\\b|\\bapiadeiro\\b|\\bapiar\\b|\\bapreciacao\\b|\\barctico\\b|\\barrazar\\b|\\b\\\xe1rtico\\b|\\bartifice\\b|\\bartif\\\xedcial\\b|\\bascen\\\xe7\\\xe3o\\b|\\bass\\\xfacar\\b|\\baste\\b|\\baster\\\xedstico\\b|\\baver\\\xe7\\\xe3o\\b|\\bavizar\\b|\\bavulsso\\b|\\bba\\\xednha\\b|\\bbanca\\-rota\\b|\\bbandeija\\b|\\bb\\\xe9b\\\xe9\\b|\\bbeige\\b|\\bben\\\xe7\\\xe3o\\b|\\bbenefici\\\xeancia\\b|\\bbeneficiente\\b|\\bbenvinda\\b|\\bbenvindo\\b|\\bboasvindas\\b|\\bborborinho\\b|\\bBrazil\\b|\\bbussula\\b|\\bcabo\\-verdeano\\b|\\bcaimbras\\b|\\bcalc\\\xe1reo\\b|\\bcalsado\\b|\\bcalv\\\xedce\\b|\\bcamoneano\\b|\\bcampi\\\xe3o\\b|\\bcan\\\xe7acos\\b|\\bcaracter\\b|\\bcaract\\\xe9res\\b|\\bcatequeze\\b|\\bcatequisador\\b|\\bcatequisar\\b|\\bch\\\xedcara\\b|\\bciclano\\b|\\bcicrano\\b|\\bcidad\\\xe3es\\b|\\bcidad\\\xf5es\\b|\\bcincoenta\\b|\\bcinseiro\\b|\\bcinsero\\b|\\bcitacoes\\b|\\bcoaliz\\\xe3o\\b|\\bc\\\xf4dia\\b|\\bcomb\\\xf3io\\b|\\bcomp\\\xf4r\\b|\\bconcerteza\\b|\\bconstituia\\b|\\bconstitu\\\xedu\\b|\\bcontato\\b|\\bcontens\\\xe3o\\b|\\bcontribuicoes\\b|\\bc\\\xf4r\\b|\\bcorass\\\xe3o\\b|\\bcor\\\xe7ario\\b|\\bcor\\\xe7\\\xe1rio\\b|\\bcornprimidosinbo\\b|\\bcr\\\xe2neo\\b|\\bdE\\b|\\bdefeni\\\xe7\\\xe3o\\b|\\bdefenido\\b|\\bdefenir\\b|\\bdeficite\\b|\\bdegladiar\\b|\\bdeiche\\b|\\bdesinteria\\b|\\bdespendio\\b|\\bdesp\\\xeandio\\b|\\bdesplic\\\xeancia\\b|\\bdificulidade\\b|\\bdispender\\b|\\bdispendio\\b|\\bdistribuido\\b|\\bdru\\\xedda\\b|\\b\\\xe9cr\\\xe3\\b|\\becran\\b|\\b\\\xe9cran\\b|\\b\\\xeale\\b|\\belice\\b|\\b\\\xe9lice\\b|\\bemiratos\\b|\\bengolis\\-te\\b|\\bengulir\\b|\\benguliste\\b|\\bentertido\\b|\\bentitular\\b|\\bentreterimento\\b|\\bentreti\\-me\\b|\\benv\\\xf3lucro\\b|\\ber\\\xf3i\\b|\\bescluir\\b|\\besclus\\\xe3o\\b|\\bescriv\\\xf5es\\b|\\besqueiro\\b|\\besquesito\\b|\\bestacoes\\b|\\besteje\\b|\\bexcava\\\xe7\\\xe3o\\b|\\bexcavar\\b|\\bexdr\\\xfaxula\\b|\\bexdr\\\xfaxulas\\b|\\bexitar\\b|\\bexplicacoes\\b|\\bexquisito\\b|\\bextende\\b|\\bextender\\b|\\bf\\\xe0cilmenfe\\b|\\bf\\\xe0cilmente\\b|\\bfariam\\-lhe\\b|\\bFARM\\\xc1ClAS\\b|\\bfarmec\\\xeautico\\b|\\bfassa\\b|\\bf\\\xe9bre\\b|\\bfecula\\b|\\bf\\\xe9mea\\b|\\bfemenino\\b|\\bfemininismo\\b|\\bf\\\xedsiologista\\b|\\bfiz\\\xe9mos\\b|\\bfizes\\-te\\b|\\bfl\\\xf4r\\b|\\bfor\\\xe3o\\b|\\bformalisar\\b|\\bf\\\xf4ro\\b|\\bfos\\-te\\b|\\bfrag\\\xe2ncia\\b|\\bfran\\\xe7\\\xeas\\b|\\bfrasqutnho\\b|\\bfrustado\\b|\\bfur\\\xe1\\b|\\bgaz\\b|\\bg\\\xe1z\\b|\\bgeito\\b|\\bgeneceu\\b|\\bgeropiga\\b|\\bglic\\\xe9mia\\b|\\bgorgeta\\b|\\bgrangear\\b|\\bguizar\\b|\\bhectar\\b|\\bherm\\\xe9ticamente\\b|\\bhernia\\b|\\bhigi\\\xe9ne\\b|\\bhilariedade\\b|\\bhiperac\\\xeddez\\b|\\bhontem\\b|\\bigiene\\b|\\bigienico\\b|\\bigi\\\xe9nico\\b|\\bigreija\\b|\\biguasu\\b|\\bilac\\\xe7\\\xe3o\\b|\\bimbigo\\b|\\bimpecilho\\b|\\b\\\xedncas\\b|\\binc\\\xeasto\\b|\\binclusiv\\\xe9\\b|\\binc\\\xf4modos\\b|\\bincontest\\\xe1velmente\\b|\\bincontest\\\xe0velmente\\b|\\bindespens\\\xe1veis\\b|\\bindespens\\\xe1vel\\b|\\bIndia\\b|\\bindiguina\\\xe7\\\xe3o\\b|\\bindiguinado\\b|\\bindiguinar\\b|\\binflac\\\xe7\\\xe3o\\b|\\bingreja\\b|\\bINSCRICOES\\b|\\bintens\\\xe3o\\b|\\bintertido\\b|\\bintoxica\\b|\\bintrega\\b|\\binveros\\\xedmel\\b|\\biorgute\\b|\\bipop\\\xf3tamo\\b|\\bipsilon\\b|\\bipslon\\b|\\bisquesito\\b|\\bju\\\xedz\\b|\\bjuiza\\b|\\bj\\\xfaniores\\b|\\bjustanzente\\b|\\bjuz\\b|\\bkilo\\b|\\blaborat\\\xf3rio\\-porque\\b|\\bladravaz\\b|\\blament\\\xe0velmente\\b|\\blampe\\\xe3o\\b|\\blargartixa\\b|\\blargarto\\b|\\bl\\\xeam\\b|\\bleuc\\\xe9mia\\b|\\blicensa\\b|\\blingu\\\xedsta\\b|\\blisongear\\b|\\blogista\\b|\\bma\\\xe7ajar\\b|\\bMacfadden\\-o\\b|\\bmae\\b|\\bmagestade\\b|\\bm\\\xe3gua\\b|\\bmangerico\\b|\\bmangerona\\b|\\bmanteem\\-se\\b|\\bmantega\\b|\\bmantem\\-se\\b|\\bmassi\\\xe7o\\b|\\bmassisso\\b|\\bm\\\xe9dica\\-Rio\\b|\\bmenistro\\b|\\bmerciaria\\b|\\bmetrelhadora\\b|\\bmiscegena\\\xe7\\\xe3o\\b|\\bmisogenia\\b|\\bmisogeno\\b|\\bmis\\\xf3geno\\b|\\bm\\\xba\\b|\\bm\\\xf4lho\\b|\\bmonument\\\xe2nea\\b|\\bmortandela\\b|\\bmorteIa\\b|\\bmuinto\\b|\\bnasaias\\b|\\bn\\\xeale\\b|\\bnest\\b|\\bNivea\\b|\\bnonagessimo\\b|\\bnonag\\\xe9ssimo\\b|\\bnornal\\b|\\bnot\\\xe0velmente\\b|\\bobcess\\\xe3o\\b|\\bobesidae\\b|\\b\\\xf3bviamente\\b|\\b\\\xf2bviamente\\b|\\bofecina\\b|\\boje\\b|\\bomem\\b|\\bopcoes\\b|\\bop\\\xf3brio\\b|\\bopr\\\xf3bio\\b|\\borf\\\xe3o\\b|\\borganigrama\\b|\\borganisar\\b|\\borg\\\xe3o\\b|\\borta\\b|\\b\\\xf3tima\\b|\\b\\\xf3timos\\b|\\bparaliza\\\xe7\\\xe3o\\b|\\bparalizado\\b|\\bparalizar\\b|\\bpar\\\xe1ste\\b|\\bP\\Line truncated
'rus': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'\u041d\u0404\u0419', u'\u041d\u0415\u0419'), (u'\u041e\u0420\u0413\u0417\u041d\u0418\u0417\u041c\u041e\u0411', u'\u041e\u0420\u0413\u0410\u041d\u0418\u0417\u041c\u0410'), (u'\u0427\u04570', u'\u0427\u0422\u041e'), (u'\u041d\u042d', u'\u041d\u0410'), (u'\u0421\u041e\u0421\u0404\u0414\u041d\u042e\u042e', u'\u0421\u041e\u0421\u0415\u0414\u041d\u042e\u042e'), (u'\u041f\u041b\u0417\u041d\u0404\u0422\u0423', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0423'), (u'\u0417\u0417\u0413\u042d\u0414\u041e\u041a', u'\u0417\u0410\u0413\u0410\u0414\u041e\u041a'), (u'\u0421\u041e\u0422\u0412\u041e\u0420\u0404\u041d\u0418\u042f', u'\u0421\u041e\u0422\u0412\u041e\u0420\u0415\u041d\u0418\u042f'), (u'\u041c\u0418\u0420\u042d', u'\u041c\u0418\u0420\u0410'), (u'\u041f\u041e\u042f\u0411\u041b\u0404\u041d\u0418\u042f', u'\u041f\u041e\u042f\u0412\u041b\u0415\u041d\u0418\u042f'), (u'\u0417\u0404\u041c\u041b\u0404', u'\u0417\u0415\u041c\u041b\u0415'), (u'\u0404\u0429\u0404', u'\u0415\u0429\u0401'), (u'\u0422\u0404\u041c\u041d\u042c\u0406\u0425', u'\u0422\u0415\u041c\u041d\u042b\u0425'), (u'\u0421\u0404\u0420\u042c\u0404\u0417\u041d\u042c\u0406\u041c', u'\u0421\u0415\u0420\u042c\u0415\u0417\u041d\u042b\u041c'), (u'\u041f\u041e\u0428\u0406\u04060', u'\u041f\u041e\u0428\u041b\u041e'), (u'\u041f\u04400\u0418\u04170\u0428\u0404\u041b', u'\u041f\u0420\u041e\u0418\u0417\u041e\u0428\u0415\u041b'), (u'\u0421\u0404\u041a\u0420\u0404\u0422\u042d\u041c\u0418', u'\u0421\u0415\u041a\u0420\u0415\u0422\u0410\u041c\u0418'), (u'\u041c\u042d\u0422\u0404\u0420\u0418\u0417\u041b\u042c\u0406', u'\u041c\u0410\u0422\u0415\u0420\u0418\u0410\u041b\u042b'), (u'\u041f\u042f\u0422\u0404\u041d', u'\u041f\u042f\u0422\u0415\u041d'), (u'\u041f\u041b\u0430\u041d\u0404\u0457\u0404', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0415'), (u'\u041a\u0417\u0422\u042d\u041a\u041b\u0418\u0417\u041c', u'\u041a\u0410\u0422\u0410\u041a\u041b\u0418\u0417\u041c'), (u'\u041e\u041a\u0417\u0417\u0417\u041b\u0421\u042f', u'\u041e\u041a\u0410\u0417\u0410\u041b\u0421\u042f'), (u'\u0414\u042d\u041b\u042c\u0428\u0415', u'\u0414\u0410\u041b\u042c\u0428\u0415'), (u'\u0422\u0412\u041a', u'\u0422\u0410\u041a'), (u'\u041f\u041b\u0417\u041d\u0404\u0422\u0417', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0410'), (u'\u0427\u0404\u0413\u041e', u'\u0427\u0415\u0413\u041e'), (u'\u0423\u0417\u041d\u042d\u0422\u042c', u'\u0423\u0417\u041d\u0410\u0422\u042c'), (u'\u041f\u041b\u042d\u041d\u0404\u0422\u0404', u'\u041f\u041b\u0410\u041d\u0415\u0422\u0415'), (u'\u041d\u0404\u041c', u'\u041d\u0415\u041c'), (u'\u0411\u041e\u0417\u041c\u041e\u0416\u041d\u0417', u'\u0412\u041e\u0417\u041c\u041e\u0416\u041d\u0410'), (u'\u0421\u041e\u0411\u0404\u0420\u0428\u0404\u041d\u041d\u041e', u'\u0421\u041e\u0412\u0415\u0420\u0428\u0415\u041d\u041d\u041e'), (u'\u0418\u041d\u042d\u0427\u0404', u'\u0418\u041d\u0410\u0427\u0415'), (u'\u0411\u0421\u0404', u'\u0412\u0421\u0415'), (u'\u041d\u0415\u0414\u041e\u0421\u0422\u0417\u0422\u041a\u0418', u'\u041d\u0415\u0414\u041e\u0421\u0422\u0410\u0422\u041a\u0418'), (u'\u041d\u041e\u0412\u042c\u0406\u0404', u'\u041d\u041e\u0412\u042b\u0415'), (u'\u0412\u0404\u041b\u0418\u041a\u041e\u041b\u0404\u041f\u041d\u042d\u042f', u'\u0412\u0415\u041b\u0418\u041a\u041e\u041b\u0415\u041f\u041d\u0410\u042f'), (u'\u041e\u0421\u0422\u042d\u0406\u0406\u041e\u0421\u042c', u'\u041e\u0421\u0422\u0410\u041b\u041e\u0421\u042c'), (u'\u041d\u0417\u041b\u0418\u0427\u0418\u0404', u'\u041d\u0410\u041b\u0418\u0427\u0418\u0415'), (u'\u0431\u042b', u'\u0431\u044b'), (u'\u041f\u0420\u041e\u0426\u0412\u0415\u0422\u0412\u0422\u042c', u'\u041f\u0420\u041e\u0426\u0412\u0415\u0422\u0410\u0422\u042c'), (u'\u041a\u0417\u041a', u'\u041a\u0410\u041a'), (u'\u0412\u041e\u0414\u0417', u'\u0412\u041e\u0414\u0410'), (u'\u041d\u0417\u0428\u0415\u041b', u'\u041d\u0410\u0428\u0415\u041b'), (u'\u041d\u0404', u'\u041d\u0415'), (u'\u0422\u041e\u0416\u0404', u'\u0422\u041e\u0416\u0415'), (u'\u0412\u0423\u041b\u041a\u042d\u041d\u0418\u0427\u0404\u0421\u041a\u041e\u0419', u'\u0412\u0423\u041b\u041a\u0410\u041d\u0418\u0427\u0415\u0421\u041a\u041e\u0419'), (u'\u042d\u041a\u0422\u0418\u0411\u041d\u041e\u0421\u0422\u0418', u'\u0410\u041a\u0422\u0418\u0412\u041d\u041e\u0421\u0422\u0418'), (u'\u041f\u041e\u042f\u0412\u0418\u041b\u0417\u0421\u042c', u'\u041f\u041e\u042f\u0412\u0418\u041b\u0410\u0421\u042c'), (u'\u041d\u041e\u0412\u0417\u042f', u'\u041d\u041e\u0412\u0410\u042f'), (u'\u0421\u0422\u0420\u042d\u0422\u0404\u0413\u0418\u042f', u'\u0421\u0422\u0420\u0410\u0422\u0415\u0413\u0418\u042f'), (u'\u0423\u0421\u041f\u0404\u0428\u041d0', u'\u0423\u0421\u041f\u0415\u0428\u041d\u041e'), (u'\u041f\u041e\u0421\u0417\u0414\u041a\u0423', u'\u041f\u041e\u0421\u0410\u0414\u041a\u0423'), (u'\u0413\u041e\u0422\u041e\u0411\u042b', u'\u0413\u041e\u0422\u041e\u0412\u042b'), (u'\u041d\u0417\u0427\u0417\u0422\u042c', u'\u041d\u0410\u0427\u0410\u0422\u042c'), (u'\u041e\u0425\u041e\u0422\u042d', u'\u041e\u0425\u041e\u0422\u0Line truncated
'pattern': u'(um)\\b\\\u041d\\\u0404\\\u0419\\b|\\b\\\u041e\\\u0420\\\u0413\\\u0417\\\u041d\\\u0418\\\u0417\\\u041c\\\u041e\\\u0411\\b|\\b\\\u0427\\\u04570\\b|\\b\\\u041d\\\u042d\\b|\\b\\\u0421\\\u041e\\\u0421\\\u0404\\\u0414\\\u041d\\\u042e\\\u042e\\b|\\b\\\u041f\\\u041b\\\u0417\\\u041d\\\u0404\\\u0422\\\u0423\\b|\\b\\\u0417\\\u0417\\\u0413\\\u042d\\\u0414\\\u041e\\\u041a\\b|\\b\\\u0421\\\u041e\\\u0422\\\u0412\\\u041e\\\u0420\\\u0404\\\u041d\\\u0418\\\u042f\\b|\\b\\\u041c\\\u0418\\\u0420\\\u042d\\b|\\b\\\u041f\\\u041e\\\u042f\\\u0411\\\u041b\\\u0404\\\u041d\\\u0418\\\u042f\\b|\\b\\\u0417\\\u0404\\\u041c\\\u041b\\\u0404\\b|\\b\\\u0404\\\u0429\\\u0404\\b|\\b\\\u0422\\\u0404\\\u041c\\\u041d\\\u042c\\\u0406\\\u0425\\b|\\b\\\u0421\\\u0404\\\u0420\\\u042c\\\u0404\\\u0417\\\u041d\\\u042c\\\u0406\\\u041c\\b|\\b\\\u041f\\\u041e\\\u0428\\\u0406\\\u04060\\b|\\b\\\u041f\\\u04400\\\u0418\\\u04170\\\u0428\\\u0404\\\u041b\\b|\\b\\\u0421\\\u0404\\\u041a\\\u0420\\\u0404\\\u0422\\\u042d\\\u041c\\\u0418\\b|\\b\\\u041c\\\u042d\\\u0422\\\u0404\\\u0420\\\u0418\\\u0417\\\u041b\\\u042c\\\u0406\\b|\\b\\\u041f\\\u042f\\\u0422\\\u0404\\\u041d\\b|\\b\\\u041f\\\u041b\\\u0430\\\u041d\\\u0404\\\u0457\\\u0404\\b|\\b\\\u041a\\\u0417\\\u0422\\\u042d\\\u041a\\\u041b\\\u0418\\\u0417\\\u041c\\b|\\b\\\u041e\\\u041a\\\u0417\\\u0417\\\u0417\\\u041b\\\u0421\\\u042f\\b|\\b\\\u0414\\\u042d\\\u041b\\\u042c\\\u0428\\\u0415\\b|\\b\\\u0422\\\u0412\\\u041a\\b|\\b\\\u041f\\\u041b\\\u0417\\\u041d\\\u0404\\\u0422\\\u0417\\b|\\b\\\u0427\\\u0404\\\u0413\\\u041e\\b|\\b\\\u0423\\\u0417\\\u041d\\\u042d\\\u0422\\\u042c\\b|\\b\\\u041f\\\u041b\\\u042d\\\u041d\\\u0404\\\u0422\\\u0404\\b|\\b\\\u041d\\\u0404\\\u041c\\b|\\b\\\u0411\\\u041e\\\u0417\\\u041c\\\u041e\\\u0416\\\u041d\\\u0417\\b|\\b\\\u0421\\\u041e\\\u0411\\\u0404\\\u0420\\\u0428\\\u0404\\\u041d\\\u041d\\\u041e\\b|\\b\\\u0418\\\u041d\\\u042d\\\u0427\\\u0404\\b|\\b\\\u0411\\\u0421\\\u0404\\b|\\b\\\u041d\\\u0415\\\u0414\\\u041e\\\u0421\\\u0422\\\u0417\\\u0422\\\u041a\\\u0418\\b|\\b\\\u041d\\\u041e\\\u0412\\\u042c\\\u0406\\\u0404\\b|\\b\\\u0412\\\u0404\\\u041b\\\u0418\\\u041a\\\u041e\\\u041b\\\u0404\\\u041f\\\u041d\\\u042d\\\u042f\\b|\\b\\\u041e\\\u0421\\\u0422\\\u042d\\\u0406\\\u0406\\\u041e\\\u0421\\\u042c\\b|\\b\\\u041d\\\u0417\\\u041b\\\u0418\\\u0427\\\u0418\\\u0404\\b|\\b\\\u0431\\\u042b\\b|\\b\\\u041f\\\u0420\\\u041e\\\u0426\\\u0412\\\u0415\\\u0422\\\u0412\\\u0422\\\u042c\\b|\\b\\\u041a\\\u0417\\\u041a\\b|\\b\\\u0412\\\u041e\\\u0414\\\u0417\\b|\\b\\\u041d\\\u0417\\\u0428\\\u0415\\\u041b\\b|\\b\\\u041d\\\u0404\\b|\\b\\\u0422\\\u041e\\\u0416\\\u0404\\b|\\b\\\u0412\\\u0423\\\u041b\\\u041a\\\u042d\\\u041d\\\u0418\\\u0427\\\u0404\\\u0421\\\u041a\\\u041e\\\u0419\\b|\\b\\\u042d\\\u041a\\\u0422\\\u0418\\\u0411\\\u041d\\\u041e\\\u0421\\\u0422\\\u0418\\b|\\b\\\u041f\\\u041e\\\u042f\\\u0412\\\u0418\\\u041b\\\u0417\\\u0421\\\u042c\\b|\\b\\\u041d\\\u041e\\\u0412\\\u0417\\\u042f\\b|\\b\\\u0421\\\u0422\\\u0420\\\u042d\\\u0422\\\u0404\\\u0413\\\u0418\\\u042f\\b|\\b\\\u0423\\\u0421\\\u041f\\\u0404\\\u0428\\\u041d0\\b|\\b\\\u041f\\\u041e\\\u0421\\\u0417\\\u0414\\\u041a\\\u0423\\b|\\b\\\u0413\\\u041e\\\u0422\\\u041e\\\u0411\\\u042b\\b|\\b\\\u041d\\\u0417\\\u0427\\\u0417\\\u0422\\\u042c\\b|\\b\\\u041e\\\u0425\\\u041e\\\u0422\\\u042d\\b|\\b\\\u041f\\\u0420\\\u0418\\\u0417\\\u041d\\\u0417\\\u041a\\\u0417\\\u041c\\\u0418\\b|\\b\\\u041f\\\u04400\\\u0428\\\u041b\\\u041e\\\u041c\\b|\\b\\\u041d\\\u042d\\\u0421\\\u0422\\\u041e\\\u042f\\\u0429\\\u0404\\\u041c\\b|\\b\\\u041f\\\u0423\\\u0421\\\u0422\\\u041e\\\u0422\\\u0417\\\u0425\\b|\\b\\\u0411\\\u041b\\\u0417\\\u0416\\\u041d\\\u041e\\\u0419\\b|\\b\\\u041f\\\u041e\\\u0427\\\u0411\\\u0404\\b|\\b\\\u041c\\\u042c\\\u0406\\b|\\b\\\u0421\\\u0404\\\u0419\\\u0427\\\u0417\\\u0421\\b|\\b\\\u0404\\\u0421\\\u041b\\\u0418\\b|\\b\\\u0417\\\u0417\\\u0422\\\u0420\\\u041e\\\u041d\\\u0415\\\u041c\\b|\\b\\\u041e\\\u041f\\\u0417\\\u0421\\\u0417\\\u0404\\\u041c\\\u0421\\\u042f\\b|\\b\\\u0421\\\u0418\\\u041b\\\u042c\\\u041d0\\b|\\b\\\u041e\\\u0422\\\u041b\\\u0418\\\u0427\\\u0417\\\u0404\\\u0422\\\u0421\\\u042f\\b|\\b\\\u0420\\\u042d\\\u041d\\\u042c\\\u0428\\\u0404\\b|\\b\\\u041d\\\u0417\\\u0417\\\u042c\\\u0406\\\u0412\\\u0417\\\u042e\\\u0422\\b|\\b\\\u0422\\\u0404\\\u041a\\\u041b3\\b|\\b\\\u041e\\\u0421\\\u0417\\\u0414\\\u041e\\\u0427\\\u041d\\\u042b\\\u041c\\\u0418\\b|\\b\\\u041f\\\u041e\\\u0421\\\u0422\\\u0404\\\u041f\\\u0404\\\u041d\\\u041d0\\b|\\b\\\u0418\\\u0421\\\u041f\\\u042d\\\u0420\\\u042f\\\u041b\\\u0417\\\u0421\\\u042c\\b|\\b\\\u0404\\\u041e\\\u041b\\\u042c\\\u0428\\\u041e\\\u0404\\b|\\b\\\u041a\\\u041e\\\u041b\\\u0418\\\u0427\\\u0404\\\u0421\\\u0422\\\u0411\\\u041e\\b|\\b\\\u0413\\\u0404\\\u041c\\\u0417\\\u0422\\\u0418\\\u0422\\\u0415\\b|\\b\\\u041f\\\u041e\\\u041b\\\u0423\\\u0427\\\u042d\\\u0404\\\u0422\\b|\\b\\\u041d\\\u0404\\\u0414\\\u041e\\\u0421\\\u0422\\\u0417\\\u0427\\\u041d0\\b|\\b\\\u041f\\\u0418\\\u0422\\\u042d\\\u041d\\\u0418\\\u042f\\b|\\b\\\u041f\\\u041e\Line truncated
'spa': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict([(u'.\xbb.', u'\xbb.')]),
'pattern': u'(um)\\b\\.\\\xbb\\.\\b$'},
'PartialLines': {'data': OrderedDict([(u'de gratis', u'gratis'), (u'si quiera', u'siquiera'), (u'Cada una de los', u'Cada uno de los'), (u'Cada uno de las', u'Cada una de las'), (u'haber que', u'a ver qu\xe9'), (u'haber qu\xe9', u'a ver qu\xe9'), (u'Haber si', u'A ver si'), (u' que hora', u' qu\xe9 hora'), (u'yo que se', u'yo qu\xe9 s\xe9'), (u'Yo que se', u'Yo qu\xe9 s\xe9'), (u' tu!', u' t\xfa!'), (u' si!', u' s\xed!'), (u' mi!', u' m\xed!'), (u' el!', u' \xe9l!'), (u' tu?', u' t\xfa?'), (u' si?', u' s\xed?'), (u' mi?', u' m\xed?'), (u' el?', u' \xe9l?'), (u' aun?', u' a\xfan?'), (u' mas?', u' m\xe1s?'), (u' que?', u' qu\xe9?'), (u' paso?', u' pas\xf3?'), (u' cuando?', u' cu\xe1ndo?'), (u' cuanto?', u' cu\xe1nto?'), (u' cuanta?', u' cu\xe1nta?'), (u' cuantas?', u' cu\xe1ntas?'), (u' cuantos?', u' cu\xe1ntos?'), (u' donde?', u' d\xf3nde?'), (u' quien?', u' qui\xe9n?'), (u' como?', u' c\xf3mo?'), (u' adonde?', u' ad\xf3nde?'), (u' cual?', u' cu\xe1l?'), (u'\xbfSi?', u'\xbfS\xed?'), (u'\xbfesta bien?', u'\xbfest\xe1 bien?'), (u'\xbfPero qu\xe9 haces?', u'\xa1\xbfPero qu\xe9 haces?!'), (u'\xbfpero qu\xe9 haces?', u'\xa1\xbfpero qu\xe9 haces?!'), (u'\xbfEs que no me has escuchado?', u'\xa1\xbfEs que no me has escuchado?!'), (u'\xa1\xbfes que no me has escuchado?!', u'\xa1\xbfes que no me has escuchado?!'), (u'\xbfaun', u'\xbfa\xfan'), (u'\xbftu ', u'\xbft\xfa '), (u'\xbfque ', u'\xbfqu\xe9 '), (u'\xbfsabes que', u'\xbfsabes qu\xe9'), (u'\xbfsabes adonde', u'\xbfsabes ad\xf3nde'), (u'\xbfsabes cual', u'\xbfsabes cu\xe1l'), (u'\xbfsabes quien', u'\xbfsabes qui\xe9n'), (u'\xbfsabes como', u'\xbfsabes c\xf3mo'), (u'\xbfsabes cuan', u'\xbfsabes cu\xe1n'), (u'\xbfsabes cuanto', u'\xbfsabes cu\xe1nto'), (u'\xbfsabes cuanta', u'\xbfsabes cu\xe1nta'), (u'\xbfsabes cuantos', u'\xbfsabes cu\xe1ntos'), (u'\xbfsabes cuantas', u'\xbfsabes cu\xe1ntas'), (u'\xbfsabes cuando', u'\xbfsabes cu\xe1ndo'), (u'\xbfsabes donde', u'\xbfsabes d\xf3nde'), (u'\xbfsabe que', u'\xbfsabe qu\xe9'), (u'\xbfsabe adonde', u'\xbfsabe ad\xf3nde'), (u'\xbfsabe cual', u'\xbfsabe cu\xe1l'), (u'\xbfsabe quien', u'\xbfsabe qui\xe9n'), (u'\xbfsabe como', u'\xbfsabe c\xf3mo'), (u'\xbfsabe cuan', u'\xbfsabe cu\xe1n'), (u'\xbfsabe cuanto', u'\xbfsabe cu\xe1nto'), (u'\xbfsabe cuanta', u'\xbfsabe cu\xe1nta'), (u'\xbfsabe cuantos', u'\xbfsabe cu\xe1ntos'), (u'\xbfsabe cuantas', u'\xbfsabe cu\xe1ntas'), (u'\xbfsabe cuando', u'\xbfsabe cu\xe1ndo'), (u'\xbfsabe donde', u'\xbfsabe d\xf3nde'), (u'\xbfsaben que', u'\xbfsaben qu\xe9'), (u'\xbfsaben adonde', u'\xbfsaben ad\xf3nde'), (u'\xbfsaben cual', u'\xbfsaben cu\xe1l'), (u'\xbfsaben quien', u'\xbfsaben qui\xe9n'), (u'\xbfsaben como', u'\xbfsaben c\xf3mo'), (u'\xbfsaben cuan', u'\xbfsaben cu\xe1n'), (u'\xbfsaben cuanto', u'\xbfsaben cu\xe1nto'), (u'\xbfsaben cuanta', u'\xbfsaben cu\xe1nta'), (u'\xbfsaben cuantos', u'\xbfsaben cu\xe1ntos'), (u'\xbfsaben cuantas', u'\xbfsaben cu\xe1ntas'), (u'\xbfsaben cuando', u'\xbfsaben cu\xe1ndo'), (u'\xbfsaben donde', u'\xbfsaben d\xf3nde'), (u'\xbfde que', u'\xbfde qu\xe9'), (u'\xbfde donde', u'\xbfde d\xf3nde'), (u'\xbfde cual', u'\xbfde cu\xe1l'), (u'\xbfde quien', u'\xbfde qui\xe9n'), (u'\xbfde cuanto', u'\xbfde cu\xe1nto'), (u'\xbfde cuanta', u'\xbfde cu\xe1nta'), (u'\xbfde cuantos', u'\xbfde cu\xe1ntos'), (u'\xbfde cuantas', u'\xbfde cu\xe1ntas'), (u'\xbfde cuando', u'\xbfde cu\xe1ndo'), (u'\xbfsobre que', u'\xbfsobre qu\xe9'), (u'\xbfcomo ', u'\xbfc\xf3mo '), (u'\xbfcual ', u'\xbfcu\xe1l '), (u'\xbfen cual', u'\xbfen cu\xe1l'), (u'\xbfcuando', u'\xbfcu\xe1ndo'), (u'\xbfhasta cual', u'\xbfhasta cu\xe1l'), (u'\xbfhasta quien', u'\xbfhasta qui\xe9n'), (u'\xbfhasta cuanto', u'\xbfhasta cu\xe1nto'), (u'\xbfhasta cuantas', u'\xbfhasta cu\xe1ntas'), (u'\xbfhasta cuantos', u'\xbfhasta cu\xe1ntos'), (u'\xbfhasta cuando', u'\xbfhasta cu\xe1ndo'), (u'\xbfhasta donde', u'\xbfhasta d\xf3nde'), (u'\xbfhasta que', u'\xbfhasta qu\xe9'), (u'\xbfhasta adonde', u'\xbfhasta ad\xf3nde'), (u'\xbfdesde que', u'\xbfdesde qu\xe9'), (u'\xbfdesde cuando', u'\xbfdesde cu\xe1ndo'), (u'\xbfdesde quien', u'\xbfdesde qui\xe9n'), (u'\xbfdesde donde', u'\xbfdesde d\xf3nde'), (u'\xbfcuanto', u'\xbfcu\xe1nto'), (u'\xbfcuantos', u'\xbfcu\xe1ntos'), (u'\xbfdonde', u'\xbfd\xf3nde'), (u'\xbfadonde', u'\xbfad\xf3nde'), (u'\xbfcon que', u'\xbfcon qu\xe9'), (u'\xbfcon cual', u'\xbfcon cu\xe1l'), (u'\xbfcon quien', u'\xbfcon qui\xe9n'), (u'\xbfcon cuantos', u'\xbfcon cu\xe1ntos'), (u'\xbfcon cuantas', u'\xbfcon cu\xe1ntas'), (u'\xbfcon cuanta', u'\xbfcon cu\xe1nta'), (u'\xbfcon cuanto', u'\xbfcon cu\xe1nto'), (u'\xbfpara donde', u'\xbfpara d\xf3nde'), (u'\xbfpara adonde', u'\xbfpara ad\xf3nde'), (u'\xbfpara cuando', u'\xbfpara cu\xe1ndo'), (u'\xbfpara que', u'\xbfpara qu\xe9'), (u'\xbfpara quien', u'\xbfpara qui\xe9n'), (u'\xbfpara cuanto', u'\xbfpara cu\xe1nto'), (u'\xbfpara cuanta', u'\xbfpara cu\xe1nta'), (u'\xbfpara cuantos', u'\xbfpara cu\xe1ntos'), (u'\xbfpara cuantas', u'\xbfpara cu\xe1ntas'), (Line truncated
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'No', u'No.')]),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'KBs', u'kB'), (u'Vd', u'Ud'), (u'N\xb0', u'N.\xb0'), (u'n\xb0', u'n.\xb0'), (u'nro.', u'n.\xb0'), (u'Nro.', u'N.\xb0'), (u'aca', u'ac\xe1'), (u'actuas', u'act\xfaas'), (u'actues', u'act\xfaes'), (u'adios', u'adi\xf3s'), (u'agarrenla', u'ag\xe1rrenla'), (u'agarrenlo', u'ag\xe1rrenlo'), (u'agarrandose', u'agarr\xe1ndose'), (u'algun', u'alg\xfan'), (u'alli', u'all\xed'), (u'alla', u'all\xe1'), (u'alejate', u'al\xe9jate'), (u'ahi', u'ah\xed'), (u'angel', u'\xe1ngel'), (u'angeles', u'\xe1ngeles'), (u'apagala', u'ap\xe1gala'), (u'aqui', u'aqu\xed'), (u'asi', u'as\xed'), (u'bahia', u'bah\xeda'), (u'busqueda', u'b\xfasqueda'), (u'busquedas', u'b\xfasquedas'), (u'callate', u'c\xe1llate'), (u'carcel', u'c\xe1rcel'), (u'camara', u'c\xe1mara'), (u'caido', u'ca\xeddo'), (u'cabron', u'cabr\xf3n'), (u'camion', u'cami\xf3n'), (u'codigo', u'c\xf3digo'), (u'codigos', u'c\xf3digos'), (u'comence', u'comenc\xe9'), (u'comprate', u'c\xf3mprate'), (u'consegui', u'consegu\xed'), (u'confias', u'conf\xedas'), (u'convertira', u'convertir\xe1'), (u'corazon', u'coraz\xf3n'), (u'crei', u'cre\xed'), (u'creia', u'cre\xeda'), (u'creido', u'cre\xeddo'), (u'creiste', u'cre\xedste'), (u'cubrenos', u'c\xfabrenos'), (u'comio', u'comi\xf3'), (u'dara', u'dar\xe1'), (u'dia', u'd\xeda'), (u'dias', u'd\xedas'), (u'debio', u'debi\xf3'), (u'demelo', u'd\xe9melo'), (u'dimelo', u'd\xedmelo'), (u'denoslo', u'd\xe9noslo'), (u'deselo', u'd\xe9selo'), (u'decia', u'dec\xeda'), (u'decian', u'dec\xedan'), (u'detras', u'detr\xe1s'), (u'deberia', u'deber\xeda'), (u'deberas', u'deber\xe1s'), (u'deberias', u'deber\xedas'), (u'deberian', u'deber\xedan'), (u'deberiamos', u'deber\xedamos'), (u'dejame', u'd\xe9jame'), (u'dejate', u'd\xe9jate'), (u'dejalo', u'd\xe9jalo'), (u'dejarian', u'dejar\xedan'), (u'damela', u'd\xe1mela'), (u'despues', u'despu\xe9s'), (u'diciendome', u'dici\xe9ndome'), (u'dificil', u'dif\xedcil'), (u'dificiles', u'dif\xedciles'), (u'disculpate', u'disc\xfalpate'), (u'dolares', u'd\xf3lares'), (u'hechar', u'echar'), (u'examenes', u'ex\xe1menes'), (u'empezo', u'empez\xf3'), (u'empujon', u'empuj\xf3n'), (u'empujalo', u'emp\xfajalo'), (u'escondanme', u'esc\xf3ndanme'), (u'esperame', u'esp\xe9rame'), (u'estara', u'estar\xe1'), (u'estare', u'estar\xe9'), (u'estaria', u'estar\xeda'), (u'estan', u'est\xe1n'), (u'estaran', u'estar\xe1n'), (u'estabamos', u'est\xe1bamos'), (u'estuvieramos', u'estuvi\xe9ramos'), (u'exito', u'\xe9xito'), (u'facil', u'f\xe1cil'), (u'fiscalia', u'fiscal\xeda'), (u'fragil', u'fr\xe1gil'), (u'fragiles', u'fr\xe1giles'), (u'frances', u'franc\xe9s'), (u'gustaria', u'gustar\xeda'), (u'habia', u'hab\xeda'), (u'habias', u'hab\xedas'), (u'habian', u'hab\xedan'), (u'habrian', u'habr\xedan'), (u'habrias', u'habr\xedas'), (u'hagalo', u'h\xe1galo'), (u'haria', u'har\xeda'), (u'increible', u'incre\xedble'), (u'incredulo', u'incr\xe9dulo'), (u'intentalo', u'int\xe9ntalo'), (u'ire', u'ir\xe9'), (u'jovenes', u'j\xf3venes'), (u'ladron', u'ladr\xf3n'), (u'linea', u'l\xednea'), (u'llamame', u'll\xe1mame'), (u'llevalo', u'll\xe9valo'), (u'mama', u'mam\xe1'), (u'maricon', u'maric\xf3n'), (u'mayoria', u'mayor\xeda'), (u'metodo', u'm\xe9todo'), (u'metodos', u'm\xe9todos'), (u'mio', u'm\xedo'), (u'mostro', u'mostr\xf3'), (u'morira', u'morir\xe1'), (u'muevete', u'mu\xe9vete'), (u'murio', u'muri\xf3'), (u'numero', u'n\xfamero'), (u'numeros', u'n\xfameros'), (u'ningun', u'ning\xfan'), (u'oido', u'o\xeddo'), (u'oidos', u'o\xeddos'), (u'oimos', u'o\xedmos'), (u'oiste', u'o\xedste'), (u'pasale', u'p\xe1sale'), (u'pasame', u'p\xe1same'), (u'paraiso', u'para\xedso'), (u'parate', u'p\xe1rate'), (u'pense', u'pens\xe9'), (u'peluqueria', u'peluquer\xeda'), (u'platano', u'pl\xe1tano'), (u'plastico', u'pl\xe1stico'), (u'plasticos', u'pl\xe1sticos'), (u'policia', u'polic\xeda'), (u'policias', u'polic\xedas'), (u'poster', u'p\xf3ster'), (u'podia', u'pod\xeda'), (u'podias', u'pod\xedas'), (u'podria', u'podr\xeda'), (u'podrian', u'podr\xedan'), (u'podrias', u'podr\xedas'), (u'podriamos', u'podr\xedamos'), (u'prometio', u'prometi\xf3'), (u'proposito', u'prop\xf3sito'), (u'pideselo', u'p\xeddeselo'), (u'ponganse', u'p\xf3nganse'), (u'prometeme', u'prom\xe9teme'), (u'publico', u'p\xfablico'), (u'publicos', u'p\xfablicos'), (u'publicamente', u'p\xfablicamente'), (u'quedate', u'qu\xe9date'), (u'queria', u'quer\xeda'), (u'querrias', u'querr\xedas'), (u'querian', u'quer\xedan'), (u'rapido', u'r\xe1pido'), (u'rapidamente', u'r\xe1pidamente'), (u'razon', u'raz\xf3n'), (u'rehusen', u'reh\xfasen'), (u'rie', u'r\xede'), (u'rias', u'r\xedas'), (u'rindete', u'r\xedndete'), (u'sacame', u's\xe1came'), (u'sentian', u'sent\xedan'), (u'sientate', u'si\xe9ntate'), (u'sera', u'ser\xe1'), (u'soplon', u'sopl\xf3n'), (u'sueltalo', u'su\xe9ltalo'), (u'tambien', u'tambi\xe9n'), (u'teoria', u'teor\xeda'), (u'tendra', u'tendr\xe1'), (u'telefono', u'tel\xe9fono'), (u'tipica', u't\xedpica'), (u'todavia', u'todav\xeda'), (u'tomalo', u't\xf3malo'), (u'tLine truncated
'pattern': u'(um)\\bKBs\\b|\\bVd\\b|\\bN\\\xb0\\b|\\bn\\\xb0\\b|\\bnro\\.\\b|\\bNro\\.\\b|\\baca\\b|\\bactuas\\b|\\bactues\\b|\\badios\\b|\\bagarrenla\\b|\\bagarrenlo\\b|\\bagarrandose\\b|\\balgun\\b|\\balli\\b|\\balla\\b|\\balejate\\b|\\bahi\\b|\\bangel\\b|\\bangeles\\b|\\bapagala\\b|\\baqui\\b|\\basi\\b|\\bbahia\\b|\\bbusqueda\\b|\\bbusquedas\\b|\\bcallate\\b|\\bcarcel\\b|\\bcamara\\b|\\bcaido\\b|\\bcabron\\b|\\bcamion\\b|\\bcodigo\\b|\\bcodigos\\b|\\bcomence\\b|\\bcomprate\\b|\\bconsegui\\b|\\bconfias\\b|\\bconvertira\\b|\\bcorazon\\b|\\bcrei\\b|\\bcreia\\b|\\bcreido\\b|\\bcreiste\\b|\\bcubrenos\\b|\\bcomio\\b|\\bdara\\b|\\bdia\\b|\\bdias\\b|\\bdebio\\b|\\bdemelo\\b|\\bdimelo\\b|\\bdenoslo\\b|\\bdeselo\\b|\\bdecia\\b|\\bdecian\\b|\\bdetras\\b|\\bdeberia\\b|\\bdeberas\\b|\\bdeberias\\b|\\bdeberian\\b|\\bdeberiamos\\b|\\bdejame\\b|\\bdejate\\b|\\bdejalo\\b|\\bdejarian\\b|\\bdamela\\b|\\bdespues\\b|\\bdiciendome\\b|\\bdificil\\b|\\bdificiles\\b|\\bdisculpate\\b|\\bdolares\\b|\\bhechar\\b|\\bexamenes\\b|\\bempezo\\b|\\bempujon\\b|\\bempujalo\\b|\\bescondanme\\b|\\besperame\\b|\\bestara\\b|\\bestare\\b|\\bestaria\\b|\\bestan\\b|\\bestaran\\b|\\bestabamos\\b|\\bestuvieramos\\b|\\bexito\\b|\\bfacil\\b|\\bfiscalia\\b|\\bfragil\\b|\\bfragiles\\b|\\bfrances\\b|\\bgustaria\\b|\\bhabia\\b|\\bhabias\\b|\\bhabian\\b|\\bhabrian\\b|\\bhabrias\\b|\\bhagalo\\b|\\bharia\\b|\\bincreible\\b|\\bincredulo\\b|\\bintentalo\\b|\\bire\\b|\\bjovenes\\b|\\bladron\\b|\\blinea\\b|\\bllamame\\b|\\bllevalo\\b|\\bmama\\b|\\bmaricon\\b|\\bmayoria\\b|\\bmetodo\\b|\\bmetodos\\b|\\bmio\\b|\\bmostro\\b|\\bmorira\\b|\\bmuevete\\b|\\bmurio\\b|\\bnumero\\b|\\bnumeros\\b|\\bningun\\b|\\boido\\b|\\boidos\\b|\\boimos\\b|\\boiste\\b|\\bpasale\\b|\\bpasame\\b|\\bparaiso\\b|\\bparate\\b|\\bpense\\b|\\bpeluqueria\\b|\\bplatano\\b|\\bplastico\\b|\\bplasticos\\b|\\bpolicia\\b|\\bpolicias\\b|\\bposter\\b|\\bpodia\\b|\\bpodias\\b|\\bpodria\\b|\\bpodrian\\b|\\bpodrias\\b|\\bpodriamos\\b|\\bprometio\\b|\\bproposito\\b|\\bpideselo\\b|\\bponganse\\b|\\bprometeme\\b|\\bpublico\\b|\\bpublicos\\b|\\bpublicamente\\b|\\bquedate\\b|\\bqueria\\b|\\bquerrias\\b|\\bquerian\\b|\\brapido\\b|\\brapidamente\\b|\\brazon\\b|\\brehusen\\b|\\brie\\b|\\brias\\b|\\brindete\\b|\\bsacame\\b|\\bsentian\\b|\\bsientate\\b|\\bsera\\b|\\bsoplon\\b|\\bsueltalo\\b|\\btambien\\b|\\bteoria\\b|\\btendra\\b|\\btelefono\\b|\\btipica\\b|\\btodavia\\b|\\btomalo\\b|\\btonterias\\b|\\btorci\\b|\\btraelos\\b|\\btraiganlo\\b|\\btraiganlos\\b|\\btrio\\b|\\btuvieramos\\b|\\bunion\\b|\\bultimo\\b|\\bultima\\b|\\bultimos\\b|\\bultimas\\b|\\bunica\\b|\\bunico\\b|\\bvamonos\\b|\\bvayanse\\b|\\bvictima\\b|\\bvivira\\b|\\bvolvio\\b|\\bvolvia\\b|\\bvolvian\\b|\\breir\\b|\\bfreir\\b|\\bsonreir\\b|\\bhazmerreir\\b|\\boir\\b|\\boirlo\\b|\\boirte\\b|\\boirse\\b|\\boirme\\b|\\boirle\\b|\\boirla\\b|\\boirles\\b|\\boirnos\\b|\\boirlas\\b|\\bbi\\\xe9n\\b|\\bcr\\\xedmen\\b|\\bfu\\\xe9\\b|\\bfu\\\xed\\b|\\bqui\\\xe9res\\b|\\bt\\\xed\\b|\\bd\\\xed\\b|\\bv\\\xe1\\b|\\bv\\\xe9\\b|\\bv\\\xed\\b|\\bvi\\\xf3\\b|\\b\\\xf3\\b|\\bcl\\\xf3n\\b|\\bdi\\\xf3\\b|\\bgui\\\xf3n\\b|\\bd\\\xf3n\\b|\\bf\\\xe9\\b|\\b\\\xe1quel\\b|\\b\\\xe9ste\\b|\\b\\\xe9sta\\b|\\b\\\xe9stos\\b|\\b\\\xe9stas\\b|\\b\\\xe9se\\b|\\b\\\xe9sa\\b|\\b\\\xe9sos\\b|\\b\\\xe9sas\\b|\\bs\\\xf3lo\\b|\\bcoktel\\b|\\bcocktel\\b|\\bconciente\\b|\\bcomenz\\\xe9\\b|\\bdesilucionarte\\b|\\bdijieron\\b|\\bempez\\\xe9\\b|\\bhize\\b|\\bilucionarte\\b|\\binconciente\\b|\\bquize\\b|\\bquizo\\b|\\bverguenza\\b|\\bNu\\\xf1ez\\b|\\bIvan\\b|\\bJapon\\b|\\bMonica\\b|\\bMaria\\b|\\bJose\\b|\\bRamon\\b|\\bGarcia\\b|\\bGonzalez\\b|\\bJesus\\b|\\bAlvarez\\b|\\bDamian\\b|\\bRene\\b|\\bNicolas\\b|\\bJonas\\b|\\bLopez\\b|\\bHernandez\\b|\\bBermudez\\b|\\bFernandez\\b|\\bSuarez\\b|\\bSofia\\b|\\bSeneca\\b|\\bTokyo\\b|\\bCanada\\b|\\bParis\\b|\\bTurquia\\b|\\bMexico\\b|\\bMejico\\b|\\bMatias\\b|\\bValentin\\b|\\bmejicano\\b|\\bmejicanos\\b|\\bmejicana\\b|\\bmejicanas\\b|\\bio\\b|\\bia\\b|\\bie\\b|\\bIo\\b|\\bIa\\b|\\bAI\\b|\\bIe\\b|\\bEI\\b|\\bsuba\\\ufb02uente\\b|\\ba\\\ufb02\\\xf3jalo\\b|\\bA\\\ufb02\\\xf3jalo\\b|\\bperdi\\b|\\bPodria\\b|\\bconfia\\b|\\bpasaria\\b|\\bPodias\\b|\\bresponsabke\\b|\\bTodavia\\b|\\benvien\\b|\\bQueria\\b|\\btio\\b|\\btraido\\b|\\bAsi\\b|\\belegi\\b|\\bhabria\\b|\\bencantaria\\b|\\bleido\\b|\\bconocias\\b|\\bharias\\b|\\bAqui\\b|\\bdecidi\\b|\\bmia\\b|\\bCrei\\b|\\bpodiamos\\b|\\bavisame\\b|\\bdebia\\b|\\bpensarias\\b|\\breuniamos\\b|\\bPO\\\xcf\\b|\\bvendria\\b|\\bcaida\\b|\\bvenian\\b|\\bcompa\\\xf1ias\\b|\\bleiste\\b|\\bLeiste\\b|\\bfiaria\\b|\\bHungria\\b|\\bfotografia\\b|\\bcafeteria\\b|\\bDigame\\b|\\bdebias\\b|\\btendria\\b|\\bC\\\xcfGO\\b|\\banteg\\b|\\bS\\\xf3Io\\b|\\bIlam\\\xe1ndola\\b|\\bC\\\xe1\\\ufb02at\\\xe9\\b|\\bIlamaste\\b|\\bdaria\\b|\\bIargaba\\b|\\bYati\\b|\\bquerias\\b|\\bIimpiarlo\\b|\\bIargado\\b|\\bgaleria\\b|\\bBartomeu\\b|\\bIocalizarlo\\b|\\bIl\\\xe1mame\\b'}},
'srp': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'bi smo', u'bismo'), (u'dali je', u'da li je'), (u'dali si', u'da li si'), (u'Dali si', u'Da li si'), (u'Jel sam ti', u'Jesam li ti'), (u'Jel si', u'Jesi li'), (u"Jel' si", u'Jesi li'), (u"Je I'", u'Jesi li'), (u'Jel si to', u'Jesi li to'), (u"Jel' si to", u'Da li si to'), (u'jel si to', u'da li si to'), (u"jel' si to", u'jesi li to'), (u'Jel si ti', u'Da li si ti'), (u"Jel' si ti", u'Da li si ti'), (u'jel si ti', u'da li si ti'), (u"jel' si ti", u'da li si ti'), (u'jel ste ', u'jeste li '), (u'Jel ste', u'Jeste li'), (u"jel' ste ", u'jeste li '), (u"Jel' ste ", u'Jeste li '), (u'Jel su ', u'Jesu li '), (u'Jel da ', u'Zar ne'), (u'jel da ', u'zar ne'), (u"jel'da ", u'zar ne'), (u'Jeli sve ', u'Je li sve'), (u'Jeli on ', u'Je li on'), (u'Jeli ti ', u'Je li ti'), (u'jeli ti ', u'je li ti'), (u'Jeli to ', u'Je li to'), (u'Nebrini', u'Ne brini'), (u'nedaj', u'ne daj'), (u'ne \u0107u', u'ne\u0107u'), (u'Nemogu', u'Ne mogu'), (u'ne mogu', u'ne mogu'), (u'Nemora\u0161', u'Ne mora\u0161'), (u'od kako', u'otkako'), (u'Si dobro', u'Jesi li dobro'), (u'Svo vreme', u'Sve vrijeme'), (u'Svo vrijeme', u'Sve vrijeme'), (u'Cijelo vrijeme', u'Sve vrijeme')]),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'\u010du', u'\u0107u'), (u'\u010de\u0161', u'\u0107e\u0161'), (u'\u010de', u'\u0107e'), (u'\u0107\u0161', u'\u0107e\u0161'), (u'\u0107mo', u'\u0107emo'), (u'\u0107te', u'\u0107ete'), (u'\u010demo', u'\u0107emo'), (u'\u010dete', u'\u010dete'), (u'djete', u'dijete'), (u'Hey', u'Hej'), (u'hey', u'hej'), (u'htjeo', u'htio'), (u'Ho\u010de\u0161', u'Ho\u0107e\u0161'), (u'ho\u010de\u0161', u'ho\u0107e\u0161'), (u'i\u010di', u'i\u0107i'), (u'jel', u"je l'"), (u'Jel', u"Je l'"), (u'nedaj', u'ne daj'), (u'Rje\u0161it', u'Rije\u0161it'), (u'smjeo', u'smio'), (u'uop\u010de', u'uop\u0107e'), (u'valda', u'valjda'), (u'\u017eelila', u'\u017eeljela')]),
'pattern': u'(um)\\b\\\u010du\\b|\\b\\\u010de\\\u0161\\b|\\b\\\u010de\\b|\\b\\\u0107\\\u0161\\b|\\b\\\u0107mo\\b|\\b\\\u0107te\\b|\\b\\\u010demo\\b|\\b\\\u010dete\\b|\\bdjete\\b|\\bHey\\b|\\bhey\\b|\\bhtjeo\\b|\\bHo\\\u010de\\\u0161\\b|\\bho\\\u010de\\\u0161\\b|\\bi\\\u010di\\b|\\bjel\\b|\\bJel\\b|\\bnedaj\\b|\\bRje\\\u0161it\\b|\\bsmjeo\\b|\\buop\\\u010de\\b|\\bvalda\\b|\\b\\\u017eelila\\b'}},
'swe': {'BeginLines': {'data': OrderedDict([(u'Ln ', u'In '), (u'U ppfattat', u'Uppfattat')]),
'pattern': u'(um)^\\bLn\\ \\b|\\bU\\ ppfattat\\b'},
'EndLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
'WholeWords': {'data': OrderedDict([(u'l\xe2rt', u'l\xe4rt'), (u'hederv\xe5rda', u'hederv\xe4rda'), (u'storm\xe2stare', u'storm\xe4stare'), (u'Avf\xe2rd', u'Avf\xe4rd'), (u't\xe2lten', u't\xe4lten'), (u'\xe2rjag', u'\xe4r jag'), (u'\xe4rjag', u'\xe4r jag'), (u'j\xe2mlikar', u'j\xe4mlikar'), (u'Riskako\ufb02', u'Riskakor'), (u'Karamellen/', u'Karamellen'), (u'Lngen\xfcng', u'Ingenting'), (u'\xe4rju', u'\xe4r ju'), (u'S\xe1', u'S\xe5'), (u'n\xe4rjag', u'n\xe4r jag'), (u'alltjag', u'allt jag'), (u'g\xf6rjag', u'g\xf6r jag'), (u'trorjag', u'tror jag'), (u'varju', u'var ju'), (u'g\xf6rju', u'g\xf6r ju'), (u'kanju', u'kan ju'), (u'blirjag', u'blir jag'), (u's\xe4gerjag', u's\xe4ger jag'), (u'beh\xe5llerjag', u'beh\xe5ller jag'), (u'pr\xf8blem', u'problem'), (u'r\xe4ddadeju', u'r\xe4ddade ju'), (u'hon\xf8m', u'honom'), (u'Ln', u'In'), (u'sv\xe5r\ufb02\xf6rtad', u'sv\xe5rfl\xf6rtad'), (u'\xf8ch', u'och'), (u'\ufb02\xf6rtar', u'fl\xf6rtar'), (u'k\xe4nnerjag', u'k\xe4nner jag'), (u'\ufb02ickan', u'flickan'), (u'sn\xf8', u'sn\xf6'), (u'gerju', u'ger ju'), (u'k\xf8ntakter', u'kontakter'), (u'\xf8lycka', u'olycka'), (u'n\xf8lla', u'nolla'), (u'sinnenajublar', u'sinnena jublar'), (u'ijobbet', u'i jobbet'), (u'F\xe5rjag', u'F\xe5r jag'), (u'Ar', u'\xc4r'), (u'liggerju', u'ligger ju'), (u'um', u'om'), (u'lbland', u'Ibland'), (u'skjuterjag', u'skjuter jag'), (u'Vadd\xe5', u'Vad d\xe5'), (u'pratarj\xe4mt', u'pratar j\xe4mt'), (u'harju', u'har ju'), (u'sitterjag', u'sitter jag'), (u'h\xe4\ufb02a', u'h\xe4rja'), (u's\ufb01\xe4l', u'stj\xe4l'), (u'F\xd6U', u'F\xf6lj'), (u'varf\xf6rjag', u'varf\xf6r jag'), (u's\ufb01\xe4rna', u'stj\xe4rna'), (u'b\xf6\ufb02ar', u'b\xf6rjar'), (u'b\xf6\ufb02an', u'b\xf6rjan'), (u'st\xe4ri', u'st\xe5r'), (u'p\xe4', u'p\xe5'), (u'harjag', u'har jag'), (u'attjag', u'att jag'), (u'Verkarjag', u'Verkar jag'), (u'K\xe4nnerjag', u'K\xe4nner jag'), (u'd\xe4rjag', u'd\xe4r jag'), (u'tu\ufb01', u'tuff'), (u'lurarjag', u'lurar jag'), (u'varj\xe4ttebra', u'var j\xe4ttebra'), (u'allvan', u'allvar'), (u'deth\xe4r', u'det h\xe4r'), (u'va\ufb02e', u'varje'), (u'F\xf6Uer', u'F\xf6ljer'), (u'personalm\xf6tetl', u'personalm\xf6tet!'), (u'harjust', u'har just'), (u'\xe4rj\xe4tteduktig', u'\xe4r j\xe4tteduktig'), (u'd\xe4rja', u'd\xe4r ja'), (u'lngen\xfcng', u'lngenting'), (u'iluften', u'i luften'), (u'\xf6sen', u'\xf6ser'), (u'tv\xe2', u'tv\xe5'), (u'Uejerna', u'Tjejerna'), (u'h\xe5n*', u'h\xe5rt'), (u'\xc4rjag', u'\xc4r jag'), (u'keL', u'Okej'), (u'F\xf6rjag', u'F\xf6r jag'), (u'varj\xe4ttekul', u'var j\xe4ttekul'), (u'k\xe4mpan', u'k\xe4mpar'), (u'mycketjobb', u'mycket jobb'), (u'Uus', u'ljus'), (u'serjag', u'ser jag'), (u'vetjag', u'vet jag'), (u'f\xe5rjag', u'f\xe5r jag'), (u'hurjag', u'hur jag'), (u'f\xf6rs\xf6kerjag', u'f\xf6rs\xf6ker jag'), (u't\xe1nagel', u't\xe5nagel'), (u'va\xfce', u'varje'), (u'Uudet', u'ljudet'), (u'amhopa', u'allihopa'), (u'V\xe4\xfc', u'V\xe4lj'), (u'g\xe4ri', u'g\xe5r'), (u'r\xf6d\xfcus', u'r\xf6dljus'), (u'Uuset', u'ljuset'), (u'Rid\xe0n', u'Rid\xe5n'), (u'vi\xfca', u'vilja'), (u'g\xe5ri', u'g\xe5r i'), (u'Hurd\xe5', u'Hur d\xe5'), (u'inter\\/juar', u'intervjuar'), (u'menarjag', u'menar jag'), (u'spyrjag', u'spyr jag'), (u'bri\xfcera', u'briljera'), (u'N\xe4rjag', u'N\xe4r jag'), (u'ner\\/\xf6s', u'nerv\xf6s'), (u'ilivets', u'i livets'), (u'n\xe4got', u'n\xe5got'), (u'p\xe0', u'p\xe5'), (u'Lnnan', u'Innan'), (u'Uf', u'Ut'), (u'lnnan', u'Innan'), (u'D\xe0ren', u'D\xe5ren'), (u'F\xe0rjag', u'F\xe5r jag'), (u'Vad\xe4rdetd\xe4L', u'Vad \xe4r det d\xe4r'), (u'sm\xe0tjuv', u'sm\xe5tjuv'), (u't\xe0gr\xe5nare', u't\xe5gr\xe5nare'), (u'dit\xe0t', u'dit\xe5t'), (u's\xe4', u's\xe5'), (u'v\xe0rdsl\xf6sa', u'v\xe5rdsl\xf6sa'), (u'n\xe0n', u'n\xe5n'), (u'kommerjag', u'kommer jag'), (u'\xe4rj\xe4ttebra', u'\xe4r j\xe4ttebra'), (u'\xe4rj\xe4vligt', u'\xe4r j\xe4vligt'), (u'\xe0kerjag', u'\xe5ker jag'), (u'ellerjapaner', u'eller japaner'), (u'attjaga', u'att jaga'), (u'eften', u'efter'), (u'h\xe4stan', u'h\xe4star'), (u'Lntensivare', u'Intensivare'), (u'fr\xe0garjag', u'fr\xe5gar jag'), (u'pen/ers', u'pervers'), (u'r\xe0barkade', u'r\xe5barkade'), (u'styrkon', u'styrkor'), (u'Dif\xe5f', u'Dit\xe5t'), (u'h\xe4nden', u'h\xe4nder'), (u'f\xf6\ufb01a', u'f\xf6lja'), (u'Idioten/', u'Idioter!'), (u'Varf\xf6rjagade', u'Varf\xf6r jagade'), (u'd\xe4rf\xf6rjag', u'd\xe4rf\xf6r jag'), (u'forjag', u'for jag'), (u'Iivsgladje', u'livsgl\xe4dje'), (u'narjag', u'n\xe4r jag'), (u'sajag', u'sa jag'), (u'genastja', u'genast ja'), (u'rockument\xe0ren', u'rockument\xe4ren'), (u'turne', u'turn\xe9'), (u'fickjag', u'fick jag'), (u'sager', u's\xe4ger'), (u'Ijush\xe5rig', u'ljush\xe5rig'), (u'tradg\xe5rdsolycka', u'tr\xe4dg\xe5rdsolycka'), (u'kvavdes', u'kv\xe4vdes'), (u'd\xe0rja', u'd\xe4r ja'), (u'hedersgaster', u'hedersg\xe4ster'), (u'Nar', u'N\xe4r'), (u'smaki\xf6sa', u'smakl\xf6sa'), (u'lan', u'Ian'), (u'Lan', u'Ian'), (u'eri', u'er i'), (u'universitetsamne', u'universitets\xe4mne'), (u'garna', u'g\xe4rna'), (u'Line truncated
'pattern': u"(um)\\bl\\\xe2rt\\b|\\bhederv\\\xe5rda\\b|\\bstorm\\\xe2stare\\b|\\bAvf\\\xe2rd\\b|\\bt\\\xe2lten\\b|\\b\\\xe2rjag\\b|\\b\\\xe4rjag\\b|\\bj\\\xe2mlikar\\b|\\bRiskako\\\ufb02\\b|\\bKaramellen\\/\\b|\\bLngen\\\xfcng\\b|\\b\\\xe4rju\\b|\\bS\\\xe1\\b|\\bn\\\xe4rjag\\b|\\balltjag\\b|\\bg\\\xf6rjag\\b|\\btrorjag\\b|\\bvarju\\b|\\bg\\\xf6rju\\b|\\bkanju\\b|\\bblirjag\\b|\\bs\\\xe4gerjag\\b|\\bbeh\\\xe5llerjag\\b|\\bpr\\\xf8blem\\b|\\br\\\xe4ddadeju\\b|\\bhon\\\xf8m\\b|\\bLn\\b|\\bsv\\\xe5r\\\ufb02\\\xf6rtad\\b|\\b\\\xf8ch\\b|\\b\\\ufb02\\\xf6rtar\\b|\\bk\\\xe4nnerjag\\b|\\b\\\ufb02ickan\\b|\\bsn\\\xf8\\b|\\bgerju\\b|\\bk\\\xf8ntakter\\b|\\b\\\xf8lycka\\b|\\bn\\\xf8lla\\b|\\bsinnenajublar\\b|\\bijobbet\\b|\\bF\\\xe5rjag\\b|\\bAr\\b|\\bliggerju\\b|\\bum\\b|\\blbland\\b|\\bskjuterjag\\b|\\bVadd\\\xe5\\b|\\bpratarj\\\xe4mt\\b|\\bharju\\b|\\bsitterjag\\b|\\bh\\\xe4\\\ufb02a\\b|\\bs\\\ufb01\\\xe4l\\b|\\bF\\\xd6U\\b|\\bvarf\\\xf6rjag\\b|\\bs\\\ufb01\\\xe4rna\\b|\\bb\\\xf6\\\ufb02ar\\b|\\bb\\\xf6\\\ufb02an\\b|\\bst\\\xe4ri\\b|\\bp\\\xe4\\b|\\bharjag\\b|\\battjag\\b|\\bVerkarjag\\b|\\bK\\\xe4nnerjag\\b|\\bd\\\xe4rjag\\b|\\btu\\\ufb01\\b|\\blurarjag\\b|\\bvarj\\\xe4ttebra\\b|\\ballvan\\b|\\bdeth\\\xe4r\\b|\\bva\\\ufb02e\\b|\\bF\\\xf6Uer\\b|\\bpersonalm\\\xf6tetl\\b|\\bharjust\\b|\\b\\\xe4rj\\\xe4tteduktig\\b|\\bd\\\xe4rja\\b|\\blngen\\\xfcng\\b|\\biluften\\b|\\b\\\xf6sen\\b|\\btv\\\xe2\\b|\\bUejerna\\b|\\bh\\\xe5n\\*\\b|\\b\\\xc4rjag\\b|\\bkeL\\b|\\bF\\\xf6rjag\\b|\\bvarj\\\xe4ttekul\\b|\\bk\\\xe4mpan\\b|\\bmycketjobb\\b|\\bUus\\b|\\bserjag\\b|\\bvetjag\\b|\\bf\\\xe5rjag\\b|\\bhurjag\\b|\\bf\\\xf6rs\\\xf6kerjag\\b|\\bt\\\xe1nagel\\b|\\bva\\\xfce\\b|\\bUudet\\b|\\bamhopa\\b|\\bV\\\xe4\\\xfc\\b|\\bg\\\xe4ri\\b|\\br\\\xf6d\\\xfcus\\b|\\bUuset\\b|\\bRid\\\xe0n\\b|\\bvi\\\xfca\\b|\\bg\\\xe5ri\\b|\\bHurd\\\xe5\\b|\\binter\\\\\\/juar\\b|\\bmenarjag\\b|\\bspyrjag\\b|\\bbri\\\xfcera\\b|\\bN\\\xe4rjag\\b|\\bner\\\\\\/\\\xf6s\\b|\\bilivets\\b|\\bn\\\xe4got\\b|\\bp\\\xe0\\b|\\bLnnan\\b|\\bUf\\b|\\blnnan\\b|\\bD\\\xe0ren\\b|\\bF\\\xe0rjag\\b|\\bVad\\\xe4rdetd\\\xe4L\\b|\\bsm\\\xe0tjuv\\b|\\bt\\\xe0gr\\\xe5nare\\b|\\bdit\\\xe0t\\b|\\bs\\\xe4\\b|\\bv\\\xe0rdsl\\\xf6sa\\b|\\bn\\\xe0n\\b|\\bkommerjag\\b|\\b\\\xe4rj\\\xe4ttebra\\b|\\b\\\xe4rj\\\xe4vligt\\b|\\b\\\xe0kerjag\\b|\\bellerjapaner\\b|\\battjaga\\b|\\beften\\b|\\bh\\\xe4stan\\b|\\bLntensivare\\b|\\bfr\\\xe0garjag\\b|\\bpen\\/ers\\b|\\br\\\xe0barkade\\b|\\bstyrkon\\b|\\bDif\\\xe5f\\b|\\bh\\\xe4nden\\b|\\bf\\\xf6\\\ufb01a\\b|\\bIdioten\\/\\b|\\bVarf\\\xf6rjagade\\b|\\bd\\\xe4rf\\\xf6rjag\\b|\\bforjag\\b|\\bIivsgladje\\b|\\bnarjag\\b|\\bsajag\\b|\\bgenastja\\b|\\brockument\\\xe0ren\\b|\\bturne\\b|\\bfickjag\\b|\\bsager\\b|\\bIjush\\\xe5rig\\b|\\btradg\\\xe5rdsolycka\\b|\\bkvavdes\\b|\\bd\\\xe0rja\\b|\\bhedersgaster\\b|\\bNar\\b|\\bsmaki\\\xf6sa\\b|\\blan\\b|\\bLan\\b|\\beri\\b|\\buniversitetsamne\\b|\\bgarna\\b|\\bar\\b|\\bbaltdjur\\b|\\bvarjag\\b|\\b\\\xe0r\\b|\\bf\\\xf6rf\\\xf6rst\\\xe0rkare\\b|\\barjattespeciell\\b|\\bh\\\xe0rg\\\xe5r\\b|\\bIa\\b|\\bIimousinen\\b|\\bkrickettra\\b|\\bh\\\xe5rdrockv\\\xe0rlden\\b|\\btr\\\xe0bit\\b|\\bMellanvastern\\b|\\barju\\b|\\bturnen\\b|\\bkanns\\b|\\bbattre\\b|\\bv\\\xe0rldsturne\\b|\\bdar\\b|\\bsj\\\xe0lvant\\\xe0nder\\b|\\bjattelange\\b|\\bberattade\\b|\\bS\\\xe4\\b|\\bvandpunkten\\b|\\bN\\\xe0rjag\\b|\\blasa\\b|\\bskitl\\\xe0skigt\\b|\\bsambandsv\\\xe0g\\b|\\bvaldigt\\b|\\bStamga\\\ufb01el\\b|\\b\\\xe0rjag\\b|\\btajming\\b|\\butg\\\xe4ng\\b|\\bH\\\xe0r\\\xe5t\\b|\\bh\\\xe0r\\\xe5t\\b|\\banvander\\b|\\bharjobbat\\b|\\bimageide\\b|\\bkla\\\ufb01en\\b|\\bsjalv\\b|\\bdvarg\\b|\\bdetjag\\b|\\bdvargarna\\b|\\bfantasiv\\\xe0rld\\b|\\b\\\ufb01olliga\\b|\\bmandoiinstr\\\xe0ngar\\b|\\bmittjobb\\b|\\bSkajag\\b|\\blandari\\b|\\bgang\\b|\\bDetjag\\b|\\bNarmre\\b|\\bI\\\xe5tjavelni\\b|\\bH\\\xe5llerjag\\b|\\bvisionarer\\b|\\bT\\\xfclvad\\b|\\bmilit\\\xe0rbas\\b|\\bjattegiada\\b|\\bFastjag\\b|\\bs\\\xe5jag\\b|\\brockvarlden\\b|\\bsaknarjag\\b|\\ballafall\\b|\\b\\\ufb01anta\\b|\\bKr\\\xe0ma\\b|\\bstammer\\b|\\bbudb\\\xe0rare\\b|\\bIivsfiiosofi\\b|\\bf\\\xf6rj\\\xe4mnan\\b|\\bgillarjag\\b|\\bIarvat\\b|\\bklararjag\\b|\\bhatta\\\ufb01\\'\\\xe0r\\b|\\bD\\\xe0\\b|\\bupp\\\ufb01nna\\b|\\bR\\\xe0ttf\\\xe5glar\\b|\\bSv\\\xe4\\\xfcboda\\b|\\bP\\\xe5b\\\xf6\\\ufb02ar\\b|\\bslutarju\\b|\\bni\\\ufb01skebu\\\xfcken\\b|\\bh\\\xe4rj\\\xe4keln\\b|\\bH\\\xdfppa\\b|\\bf\\\xf6rst\\\xf6rds\\b|\\bvarj\\\xe4ttegoda\\b|\\bKor\\\\\\/\\b|\\bbr\\\xfcl\\\xe9el\\b|\\bHei\\b|\\b\\\xe4lskarjordgubbsglass\\b|\\bSn\\\xf6bom\\b|\\bSn\\\xf6boH\\b|\\bSn\\\xf6bol\\b|\\bsn\\\xf6boH\\b|\\bL\\\xe4ggerp\\\xe5\\b|\\blnge\\\ufb02\\b|\\bS\\\xe4gerj\\\xe4ttesmarta\\b|\\bdopplen\\/\\\xe4derradar\\b|\\bs\\\xe4kertj\\\xe4ttefin\\b|\\b\\\xe4rj\\\xe4ttefin\\b|\\bverkarju\\b|\\bblirju\\b|\\bkor\\\\\\/\\b|\\bnaturkatastro\\\ufb01\\b|\\bstickerjag\\b|\\bj\\\xe4ttebu\\\ufb01\\\xe9\\b|\\bbe\\\ufb01nner\\b|\\bSp\\\ufb02ng\\b|\\btrec\\\ufb01e\\b|\\bryckerjag\\b|\\bskullejag\\Line truncated
for lang, grps in data.iteritems():
for grp in grps.iterkeys():
if data[lang][grp]["pattern"]:
data[lang][grp]["pattern"] = re.compile(data[lang][grp]["pattern"])
@@ -1,5 +1,6 @@
# coding=utf-8
import re
import os
import pprint
from collections import OrderedDict
@@ -7,9 +8,17 @@ from collections import OrderedDict
from bs4 import BeautifulSoup
TEMPLATE = """\
import re
from collections import OrderedDict
data = """
TEMPLATE_END = """\
for lang, grps in data.iteritems():
for grp in grps.iterkeys():
if data[lang][grp]["pattern"]:
data[lang][grp]["pattern"] = re.compile(data[lang][grp]["pattern"])
"""
if __name__ == "__main__":
cur_dir = os.path.dirname(os.path.realpath(__file__))
@@ -23,14 +32,28 @@ if __name__ == "__main__":
lang = fn.split("_")[0]
soup = BeautifulSoup(open(os.path.join(xml_dir, fn)), "xml")
data[lang] = OrderedDict()
fetch_data = (
# group, item_name, pattern
("WholeLines", "Line", None),
("WholeWords", "Word", lambda d: (ur"(um)" + u"|".join([ur'\b' + re.escape(k) + ur'\b' for k in d.keys()])) if d else None),
("PartialWordsAlways", "WordPart", None),
("PartialLines", "LinePart", None),
("BeginLines", "Beginning", lambda d: (ur"(um)^"+u"|".join([ur'\b' + re.escape(k) + ur'\b' for k in d.keys()])) if d else None),
("EndLines", "Ending", lambda d: (ur"(um)" + u"|".join([ur'\b' + re.escape(k) + ur'\b' for k in d.keys()]) + ur"$") if d else None,),
)
for wanted in ("WholeLines", "WholeWords", "PartialWordsAlways"):
for grp in soup.find_all(wanted):
for line in grp.find_all(["Line", "Word", "WordPart"]):
data[lang][line["from"]] = line["to"]
data[lang] = dict((grp, {"data": OrderedDict(), "pattern": None}) for grp, item_name, pattern in fetch_data)
for grp, item_name, pattern in fetch_data:
for grp_data in soup.find_all(grp):
for line in grp_data.find_all(item_name):
data[lang][grp]["data"][line["from"]] = line["to"]
if pattern:
data[lang][grp]["pattern"] = pattern(data[lang][grp]["data"])
f = open(os.path.join(cur_dir, "data.py"), "w+")
f.write(TEMPLATE)
f.write(pprint.pformat(data, width=1))
f.write(TEMPLATE_END)
f.close()
@@ -11,23 +11,28 @@ logger = logging.getLogger(__name__)
class SubtitleModifications(object):
debug = False
language = None
initialized_mods = {}
def __init__(self, debug=False):
self.debug = debug
self.initialized_mods = {}
def load(self, fn=None, content=None, fps=None):
def load(self, fn=None, content=None, language=None):
"""
:param language: babelfish.Language language of the subtitle
:param fn: filename
:param content: unicode
:param fps:
:return:
"""
self.language = language
self.initialized_mods = {}
try:
if fn:
self.f = pysubs2.load(fn, fps=fps)
self.f = pysubs2.load(fn)
elif content:
self.f = pysubs2.SSAFile.from_string(content, fps=fps)
self.f = pysubs2.SSAFile.from_string(content)
except (IOError,
UnicodeDecodeError,
pysubs2.exceptions.UnknownFPSError,
@@ -38,32 +43,76 @@ class SubtitleModifications(object):
elif content:
logger.exception("Couldn't load subtitle: %s", traceback.format_exc())
@classmethod
def parse_identifier(cls, identifier):
# simple identifier
if identifier in registry.mods:
return identifier, {}
# identifier with params; identifier(param=value)
split_args = identifier[identifier.find("(")+1:-1].split(",")
args = dict((key, value) for key, value in [sub.split("=") for sub in split_args])
return identifier[:identifier.find("(")], args
@classmethod
def get_mod_class(cls, identifier):
identifier, args = cls.parse_identifier(identifier)
return registry.mods[identifier]
@classmethod
def get_mod_signature(cls, identifier, **kwargs):
return cls.get_mod_class(identifier).get_signature(**kwargs)
def modify(self, *mods):
new_f = []
for identifier in mods:
parsed_mods = [SubtitleModifications.parse_identifier(mod) for mod in mods]
line_mods = []
non_line_mods = []
print parsed_mods
for identifier, args in parsed_mods:
if identifier not in registry.mods:
raise NotImplementedError("Mod %s not loaded" % identifier)
for line in self.f:
applied_mods = []
for identifier in mods:
if identifier in registry.mods:
mod = registry.mods[identifier]
mod_cls = registry.mods[identifier]
if mod_cls.modifies_whole_file:
non_line_mods.append((identifier, args))
else:
line_mods.append((identifier, args))
if identifier not in self.initialized_mods:
self.initialized_mods[identifier] = mod_cls(self)
# apply file mods
if non_line_mods:
for identifier, args in non_line_mods:
mod = self.initialized_mods[identifier]
mod.modify(None, debug=self.debug, parent=self, **args)
# apply line mods
if line_mods:
for line in self.f:
applied_mods = []
for identifier, args in line_mods:
mod = self.initialized_mods[identifier]
# don't bother reapplying exclusive mods multiple times
if mod.exclusive and identifier in applied_mods:
continue
new_content = mod.modify(line.text, debug=self.debug)
if not mod.processors:
continue
new_content = mod.modify(line.text, debug=self.debug, parent=self, **args)
if not new_content:
if self.debug:
logger.debug("%s: deleting %s", identifier, line)
continue
line.text = new_content
new_f.append(line)
applied_mods.append(identifier)
new_f.append(line)
self.f.events = new_f
@@ -10,18 +10,30 @@ logger = logging.getLogger(__name__)
class SubtitleModification(object):
identifier = None
description = None
long_description = None
exclusive = False
advanced = False # has parameters
modifies_whole_file = False # operates on the whole file, not individual entries
pre_processors = []
processors = []
post_processors = []
@classmethod
def _process(cls, content, processors, debug=False):
def __init__(self, parent):
return
def _process(self, content, processors, debug=False, parent=None, **kwargs):
if not content:
return
# processors may be a list or a callable
#if callable(processors):
# _processors = processors()
#else:
# _processors = processors
_processors = processors
new_content = content
for processor in processors:
for processor in _processors:
old_content = new_content
new_content = processor.process(new_content, debug=debug)
if not new_content:
@@ -34,26 +46,27 @@ class SubtitleModification(object):
logger.debug("%s: %s -> %s", processor, old_content, new_content)
return new_content
@classmethod
def pre_process(cls, content, debug=False):
return cls._process(content, cls.pre_processors, debug=debug)
def pre_process(self, content, debug=False, parent=None, **kwargs):
return self._process(content, self.pre_processors, debug=debug, parent=parent, **kwargs)
@classmethod
def process(cls, content, debug=False):
return cls._process(content, cls.processors, debug=debug)
def process(self, content, debug=False, parent=None, **kwargs):
return self._process(content, self.processors, debug=debug, parent=parent, **kwargs)
@classmethod
def post_process(cls, content, debug=False):
return cls._process(content, cls.post_processors, debug=debug)
def post_process(self, content, debug=False, parent=None, **kwargs):
return self._process(content, self.post_processors, debug=debug, parent=parent, **kwargs)
@classmethod
def modify(cls, content, debug=False):
def modify(self, content, debug=False, parent=None, **kwargs):
new_content = content
for method in ("pre_process", "process", "post_process"):
new_content = getattr(cls, method)(new_content, debug=debug)
new_content = getattr(self, method)(new_content, debug=debug, parent=parent, **kwargs)
return new_content
@classmethod
def get_signature(cls, **kwargs):
string_args = ",".join(["%s=%s" % (key, value) for key, value in kwargs.iteritems()])
return "%s(%s)" % (cls.identifier, string_args)
class SubtitleTextModification(SubtitleModification):
post_processors = [
@@ -0,0 +1,27 @@
# coding=utf-8
import logging
from subzero.modification.mods import SubtitleModification
from subzero.modification import registry
logger = logging.getLogger(__name__)
class ChangeFPS(SubtitleModification):
identifier = "change_FPS"
description = "Change the FPS of the subtitle"
exclusive = True
advanced = True
modifies_whole_file = True
long_description = """\
Re-syncs the subtitle to the framerate of the current media file.
"""
def modify(self, content, debug=False, parent=None, **kwargs):
fps_from = kwargs.get("from")
fps_to = kwargs.get("to")
parent.f.transform_framerate(float(fps_from), float(fps_to))
registry.register(ChangeFPS)
@@ -11,6 +11,10 @@ class HearingImpaired(SubtitleTextModification):
description = "Remove Hearing Impaired tags"
exclusive = True
long_description = """\
Removes tags, text and characters from subtitles that are meant for hearing impaired people
"""
processors = [
# brackets
NReProcessor(re.compile(r'(?sux)[([].+[)\]]'), "", name="HI_brackets"),
@@ -0,0 +1,47 @@
# coding=utf-8
import logging
from subzero.modification.mods import SubtitleTextModification
from subzero.modification.processors.string_processor import MultipleLineProcessor
from subzero.modification.processors.re_processor import MultipleWordReProcessor
from subzero.modification import registry
from subzero.modification.dictionaries.data import data as OCR_fix_data
logger = logging.getLogger(__name__)
class FixOCR(SubtitleTextModification):
identifier = "OCR_fixes"
description = "Fix common OCR issues"
exclusive = True
data_dict = None
long_description = """\
Fix issues that happen when a subtitle gets converted from bitmap to text through OCR
"""
def __init__(self, parent):
super(FixOCR, self).__init__(parent)
data_dict = OCR_fix_data.get(parent.language.alpha3t)
if not data_dict:
logger.debug("No SnR-data available for language %s", parent.language)
return
self.data_dict = data_dict
self.processors = self.get_processors()
def get_processors(self):
if not self.data_dict:
return []
return [
MultipleLineProcessor(self.data_dict["WholeLines"], name="SE_replace_line"),
MultipleWordReProcessor(self.data_dict["WholeWords"], name="SE_replace_word"),
MultipleWordReProcessor(self.data_dict["BeginLines"], name="SE_replace_beginline"),
MultipleWordReProcessor(self.data_dict["EndLines"], name="SE_replace_endline"),
MultipleLineProcessor(self.data_dict["PartialLines"], name="SE_replace_partialline"),
MultipleLineProcessor(self.data_dict["PartialWordsAlways"], name="SE_replace_partialwordsalways")
]
registry.register(FixOCR)
@@ -0,0 +1,27 @@
# coding=utf-8
import logging
from subzero.modification.mods import SubtitleModification
from subzero.modification import registry
logger = logging.getLogger(__name__)
class ShiftOffset(SubtitleModification):
identifier = "shift_offset"
description = "Change the timing of the subtitle"
exclusive = True
advanced = True
modifies_whole_file = True
long_description = """\
Adds or substracts a certain amount of time from the whole subtitle to match your media
"""
def modify(self, content, debug=False, parent=None, **kwargs):
parent.f.shift(h=int(kwargs.get("h", 0)), m=int(kwargs.get("m", 0)), s=int(kwargs.get("s", 0)),
ms=int(kwargs.get("ms", 0)))
registry.register(ShiftOffset)
@@ -6,15 +6,17 @@ class Processor(object):
Processor base class
"""
name = None
parent = None
def __init__(self, name=None):
def __init__(self, name=None, parent=None):
self.name = name
self.parent = parent
@property
def info(self):
return self.name
def process(self, content):
def process(self, content, debug=False):
return content
def __repr__(self):
@@ -1,6 +1,11 @@
# coding=utf-8
import re
import logging
from subzero.modification.processors import Processor
logger = logging.getLogger(__name__)
class ReProcessor(Processor):
"""
@@ -31,3 +36,27 @@ class NReProcessor(ReProcessor):
continue
lines.append(a)
return r"\N".join(lines)
class MultipleWordReProcessor(ReProcessor):
"""
Expects a dictionary in the form of:
dict = {
"data": {"old_value": "new_value"},
"pattern": compiled re object that matches data.keys()
}
replaces found key in pattern with the corresponding value in data
"""
def __init__(self, snr_dict, name=None, parent=None):
super(ReProcessor, self).__init__(name=name)
self.snr_dict = snr_dict
def process(self, content, debug=False):
if not self.snr_dict["data"]:
return content
out = []
for a in content.split(ur"\N"):
out.append(self.snr_dict["pattern"].sub(lambda x: self.snr_dict["data"][x.group(0)], a))
return ur"\N".join(out)
@@ -1,16 +1,75 @@
# coding=utf-8
import logging
from subzero.modification.processors import Processor
logger = logging.getLogger(__name__)
class StringProcessor(Processor):
"""
String replacement processor base
"""
def __init__(self, search, replace, name=None):
def __init__(self, search, replace, name=None, parent=None):
super(StringProcessor, self).__init__(name=name)
self.search = search
self.replace = replace
def process(self, content):
def process(self, content, debug=False):
return content.replace(self.search, self.replace)
class MultipleLineProcessor(Processor):
"""
replaces stuff in whole lines
takes a search/replace dict as first argument
Expects a dictionary in the form of:
dict = {
"data": {"old_value": "new_value"}
}
"""
def __init__(self, snr_dict, name=None, parent=None):
super(MultipleLineProcessor, self).__init__(name=name)
self.snr_dict = snr_dict
def process(self, content, debug=False):
if not self.snr_dict["data"]:
return content
out = []
for cnt in content.split(ur"\N"):
cnt_ = cnt
for key, value in self.snr_dict["data"].iteritems():
if debug and key in cnt_:
logger.debug(u"Replacing '%s' with '%s' in '%s'", key, value, cnt_)
cnt_ = cnt_.replace(key, value)
out.append(cnt_)
return ur"\N".join(out)
class MultipleWordProcessor(MultipleLineProcessor):
"""
replaces words
takes a search/replace dict as first argument
Expects a dictionary in the form of:
dict = {
"data": {"old_value": "new_value"}
}
"""
def process(self, content, debug=False):
new_lines = []
for line in content.split(u"\\N"):
words = line.split(u" ")
new_words = []
for word in words:
new_words.append(self.snr_dict.get(word, word))
new_lines.append(u" ".join(new_words))
return u"\\N".join(new_lines)
+2 -2
View File
@@ -22,11 +22,11 @@ less text before colons: Earth. Utah, North America.
6
00:00:19,686 --> 00:00:21,103
About half a mile underground.
Ithinkyou're About half a mile underground.
7
00:00:21,103 --> 00:00:23,603
And when are we?
lrn gonna And when are we?
8
00:00:24,274 --> 00:00:26,649