2.0.15.1216 RC3

Contents/Code/__init__.py

@@ -24,12 +24,11 @@ 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
 from support.subtitlehelpers import get_subtitles_from_metadata
-from support.storage import whack_missing_parts, save_subtitles, get_subtitle_storage
+from support.storage import whack_missing_parts, save_subtitles
 from support.items import is_ignored
 from support.config import config
 from support.lib import get_intent
@@ -43,13 +42,7 @@ def Start():
     HTTP.CacheTime = 0
     HTTP.Headers['User-agent'] = OS_PLEX_USERAGENT
 
-    try:
-        subliminal.region.configure('dogpile.cache.dbm', expiration_time=datetime.timedelta(days=30),
-                                    arguments={'filename': os.path.join(config.data_items_path, 'subzero.dbm'),
-                                               'lock_factory': MutexLock})
-    except:
-        Log.Warn("Not using file based cache!")
-        subliminal.region.configure('dogpile.cache.memory')
+    config.init_cache()
 
     # clear expired intents
     intent = get_intent()
@@ -191,6 +184,9 @@ class SubZeroAgent(object):
             config.init_subliminal_patches()
             videos = media_to_videos(media, kind=self.agent_type)
 
+            # find local media
+            update_local_media(metadata, media, media_type=self.agent_type)
+
             # media ignored?
             use_any_parts = False
             for video in videos:
@@ -211,9 +207,6 @@ class SubZeroAgent(object):
 
             set_refresh_menu_state(media, media_type=self.agent_type)
 
-            # find local media
-            update_local_media(metadata, media, media_type=self.agent_type)
-
             # scanned_video_part_map = {subliminal.Video: plex_part, ...}
             scanned_video_part_map = scan_videos(videos, kind=self.agent_type)
 

Contents/Code/interface/__init__.py

@@ -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

Contents/Code/interface/advanced.py

@@ -7,15 +7,18 @@ import urlparse
 
 from zipfile import ZipFile, ZIP_DEFLATED
 
+from babelfish import Language
+
 from subzero.lib.io import FileIO
 from subzero.constants import PREFIX, PLUGIN_IDENTIFIER
-from menu_helpers import SubFolderObjectContainer, debounce, set_refresh_menu_state, ZipObject
+from menu_helpers import SubFolderObjectContainer, debounce, set_refresh_menu_state, ZipObject, ObjectContainer
 from main import fatality
 from support.helpers import timestamp, pad_title
 from support.config import config
 from support.lib import Plex
-from support.storage import reset_storage, log_storage
+from support.storage import reset_storage, log_storage, get_subtitle_storage
 from support.scheduler import scheduler
+from support.items import set_mods_for_part, get_item_kind_from_rating_key
 
 
 @route(PREFIX + '/advanced')
@@ -49,6 +52,14 @@ def AdvancedMenu(randomize=None, header=None, message=None):
         key=Callback(TriggerStorageMaintenance, randomize=timestamp()),
         title=pad_title("Trigger subtitle storage maintenance"),
     ))
+    oc.add(DirectoryObject(
+        key=Callback(ApplyDefaultMods, randomize=timestamp()),
+        title=pad_title("Apply configured default subtitle mods to all (active) stored subtitles"),
+    ))
+    oc.add(DirectoryObject(
+        key=Callback(ReApplyMods, randomize=timestamp()),
+        title=pad_title("Re-Apply mods of all stored subtitles"),
+    ))
     oc.add(DirectoryObject(
         key=Callback(LogStorage, key="tasks", randomize=timestamp()),
         title=pad_title("Log the plugin's scheduled tasks state storage"),
@@ -92,6 +103,7 @@ def Restart():
 
 
 @route(PREFIX + '/storage/reset', sure=bool)
+@debounce
 def ResetStorage(key, randomize=None, sure=False):
     if not sure:
         oc = SubFolderObjectContainer(no_history=True, title1="Reset subtitle storage", title2="Are you sure?")
@@ -127,6 +139,7 @@ def LogStorage(key, randomize=None):
 
 
 @route(PREFIX + '/triggerbetter')
+@debounce
 def TriggerBetterSubtitles(randomize=None):
     scheduler.dispatch_task("FindBetterSubtitles")
     return AdvancedMenu(
@@ -137,6 +150,7 @@ def TriggerBetterSubtitles(randomize=None):
 
 
 @route(PREFIX + '/triggermaintenance')
+@debounce
 def TriggerStorageMaintenance(randomize=None):
     scheduler.dispatch_task("SubtitleStorageMaintenance")
     return AdvancedMenu(
@@ -146,26 +160,94 @@ def TriggerStorageMaintenance(randomize=None):
     )
 
 
+def apply_default_mods(reapply_current=False):
+    storage = get_subtitle_storage()
+    subs_applied = 0
+    for fn in storage.get_all_files():
+        data = storage.load(None, filename=fn)
+        if data:
+            video_id = data.video_id
+            item_type = get_item_kind_from_rating_key(video_id)
+            if not item_type:
+                continue
+
+            for part_id, part in data.parts.iteritems():
+                for lang, subs in part.iteritems():
+                    current_sub = subs.get("current")
+                    if not current_sub:
+                        continue
+                    sub = subs[current_sub]
+
+                    if not sub.content:
+                        continue
+
+                    current_mods = sub.mods or []
+                    if not reapply_current:
+                        add_mods = list(set(config.default_mods).difference(set(current_mods)))
+                        if not add_mods:
+                            continue
+                    else:
+                        if not current_mods:
+                            continue
+                        add_mods = []
+
+                    set_mods_for_part(video_id, part_id, Language.fromietf(lang), item_type, add_mods, mode="add")
+                    subs_applied += 1
+    Log.Debug("Applied mods to %i items" % subs_applied)
+
+
+@route(PREFIX + '/applydefaultmods')
+@debounce
+def ApplyDefaultMods(randomize=None):
+    Thread.CreateTimer(1.0, apply_default_mods)
+    return AdvancedMenu(
+        randomize=timestamp(),
+        header='Success',
+        message='This may take some time ...'
+    )
+
+
+@route(PREFIX + '/reapplyallmods')
+@debounce
+def ReApplyMods(randomize=None):
+    Thread.CreateTimer(1.0, apply_default_mods, reapply_current=True)
+    return AdvancedMenu(
+        randomize=timestamp(),
+        header='Success',
+        message='This may take some time ...'
+    )
+
+
 @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)
@@ -189,6 +271,7 @@ def DownloadLogs():
 
 
 @route(PREFIX + '/invalidatecache')
+@debounce
 def InvalidateCache(randomize=None):
     from subliminal.cache import region
     region.invalidate()

Contents/Code/interface/item_details.py

@@ -1,23 +1,19 @@
 # coding=utf-8
 import os
-import traceback
 
-from babelfish import Language
-
-from subzero.constants import PREFIX
+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 refresh_item import RefreshItem
+from subzero.constants import PREFIX
+from support.config import config
 from support.helpers import timestamp, cast_bool, df, get_language
 from support.items import get_item_kind_from_rating_key, get_item, get_current_sub
-from support.plex_media import get_plex_metadata, scan_videos
 from support.lib import Plex
-from support.storage import get_subtitle_storage, save_subtitles
-from support.config import config
+from support.plex_media import get_plex_metadata, scan_videos, PMSMediaProxy
 from support.scheduler import scheduler
-
-from subliminal_patch import PatchedSubtitle as Subtitle
-from subzero.modification import registry as mod_registry
+from support.storage import get_subtitle_storage
 
 
 @route(PREFIX + '/item/{rating_key}/actions')
@@ -41,6 +37,29 @@ def ItemDetailsMenu(rating_key, title=None, base_title=None, item_title=None, ra
     timeout = 30
 
     oc = SubFolderObjectContainer(title2=title, replace_parent=True)
+
+    # add back to season for episode
+    if current_kind == "episode":
+        from interface.menu import MetadataMenu
+        show = get_item(item.show.rating_key)
+        season = get_item(item.season.rating_key)
+
+        oc.add(DirectoryObject(
+            key=Callback(MetadataMenu, rating_key=season.rating_key, title=season.title, base_title=show.title,
+                         previous_item_type="show", previous_rating_key=show.rating_key,
+                         display_items=True, randomize=timestamp()),
+            title=u"< Back to %s" % season.title,
+            summary="Back to %s > %s" % (show.title, season.title),
+            thumb=season.thumb or default_thumb
+        ))
+
+    oc.add(DirectoryObject(
+        key=Callback(UpdateLocalMedia, rating_key=rating_key, title=title, item_title=item_title, base_title=base_title,
+                     randomize=timestamp()),
+        title=u"Find local subtitles (doesn't refresh metadata)",
+        summary="Searches for locally available subtitles",
+        thumb=item.thumb or default_thumb
+    ))
     oc.add(DirectoryObject(
         key=Callback(RefreshItem, rating_key=rating_key, item_title=item_title, randomize=timestamp(),
                      timeout=timeout * 1000),
@@ -109,6 +128,20 @@ def ItemDetailsMenu(rating_key, title=None, base_title=None, item_title=None, ra
     return oc
 
 
+@route(PREFIX + '/item/update_local_media/{rating_key}', force=bool)
+@debounce
+def UpdateLocalMedia(**kwargs):
+    from support.localmedia import find_subtitles
+    rating_key = kwargs["rating_key"]
+    parts = PMSMediaProxy(rating_key).get_all_parts()
+    for part in parts:
+        find_subtitles(part)
+
+    kwargs.pop("randomize")
+
+    return ItemDetailsMenu(**kwargs)
+
+
 @route(PREFIX + '/item/current_sub/{rating_key}/{part_id}', force=bool)
 @debounce
 def SubtitleOptionsMenu(**kwargs):
@@ -123,7 +156,7 @@ def SubtitleOptionsMenu(**kwargs):
     oc.add(DirectoryObject(
         key=Callback(ItemDetailsMenu, rating_key=kwargs["rating_key"], item_title=kwargs["item_title"],
                      title=kwargs["title"], randomize=timestamp()),
-        title=u"Back to: %s" % kwargs["title"],
+        title=u"< Back to %s" % kwargs["title"],
         summary=kwargs["current_data"],
         thumb=default_thumb
     ))
@@ -141,69 +174,6 @@ 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,
@@ -223,7 +193,7 @@ def ListAvailableSubsForItemMenu(rating_key=None, part_id=None, title=None, item
     oc = SubFolderObjectContainer(title2=unicode(title), replace_parent=True)
     oc.add(DirectoryObject(
         key=Callback(ItemDetailsMenu, rating_key=rating_key, item_title=item_title, title=title, randomize=timestamp()),
-        title=u"Back to: %s" % title,
+        title=u"< Back to %s" % title,
         summary=current_data,
         thumb=default_thumb
     ))
@@ -269,11 +239,15 @@ def ListAvailableSubsForItemMenu(rating_key=None, part_id=None, title=None, item
         return oc
 
     for subtitle in search_results:
+        wrong_fps_addon = ""
+        if subtitle.wrong_fps:
+            wrong_fps_addon = " (wrong FPS, sub: %s, media: %s)" % (subtitle.fps, plex_part.fps)
+
         oc.add(DirectoryObject(
             key=Callback(TriggerDownloadSubtitle, rating_key=rating_key, randomize=timestamp(), item_title=item_title,
                          subtitle_id=str(subtitle.id), language=language),
-            title=u"%s: %s, score: %s" % ("Available" if current_id != subtitle.id else "Current",
-                                          subtitle.provider_name, subtitle.score),
+            title=u"%s: %s, score: %s%s" % ("Available" if current_id != subtitle.id else "Current",
+                                            subtitle.provider_name, subtitle.score, wrong_fps_addon),
             summary=u"Release: %s, Matches: %s" % (subtitle.release_info, ", ".join(subtitle.matches)),
             thumb=default_thumb
         ))

Contents/Code/interface/main.py

@@ -2,11 +2,13 @@
 
 from subzero.constants import PREFIX, TITLE, ART
 from support.config import config
-from support.helpers import pad_title, timestamp, df
+from support.helpers import pad_title, timestamp, df, get_plex_item_display_title
 from support.scheduler import scheduler
 from support.ignore import ignore_list
-from support.items import get_item_thumb, get_on_deck_items, get_all_items, get_items_info
-from menu_helpers import main_icon, debounce, SubFolderObjectContainer, default_thumb, dig_tree, add_ignore_options
+from support.items import get_item_thumb, get_on_deck_items, get_all_items, get_items_info, get_item, \
+    get_item_kind_from_item
+from menu_helpers import main_icon, debounce, SubFolderObjectContainer, default_thumb, dig_tree, add_ignore_options,\
+    ObjectContainer
 from item_details import ItemDetailsMenu
 
 
@@ -69,16 +71,24 @@ def fatality(randomize=None, force_title=None, header=None, message=None, only_r
 
         oc.add(DirectoryObject(
             key=Callback(OnDeckMenu),
-            title="On Deck items",
+            title="On-deck items",
             summary="Shows the current on deck items and allows you to individually (force-) refresh their metadata/"
                     "subtitles.",
             thumb=R("icon-ondeck.jpg")
         ))
+        if "last_played_items" in Dict and Dict["last_played_items"]:
+            oc.add(DirectoryObject(
+                key=Callback(RecentlyPlayedMenu),
+                title=pad_title("Recently played items"),
+                summary="Shows the %i recently played items and allows you to individually (force-) refresh their "
+                        "metadata/subtitles." % config.store_recently_played_amount,
+                thumb=R("icon-played.jpg")
+            ))
         oc.add(DirectoryObject(
             key=Callback(RecentlyAddedMenu),
-            title="Recently Added items",
+            title="Recently-added items",
             summary="Shows the recently added items per section.",
-            thumb=R("icon-recent.jpg")
+            thumb=R("icon-added.jpg")
         ))
         oc.add(DirectoryObject(
             key=Callback(RecentMissingSubtitlesMenu, randomize=timestamp()),
@@ -168,6 +178,31 @@ def OnDeckMenu(message=None):
     return mergedItemsMenu(title="Items On Deck", base_title="Items On Deck", itemGetter=get_on_deck_items)
 
 
+@route(PREFIX + '/recently_played')
+def RecentlyPlayedMenu():
+    base_title = "Recently Played"
+    oc = SubFolderObjectContainer(title2=base_title, replace_parent=True)
+
+    for item in [get_item(rating_key) for rating_key in Dict["last_played_items"]]:
+        kind = get_item_kind_from_item(item)
+        if kind not in ("episode", "movie"):
+            continue
+
+        if kind == "episode":
+            item_title = get_plex_item_display_title(item, "show", parent=item.season, section_title=None,
+                                                     parent_title=item.show.title)
+        else:
+            item_title = get_plex_item_display_title(item, kind, section_title=None)
+
+        oc.add(DirectoryObject(
+            title=item_title,
+            key=Callback(ItemDetailsMenu, title=base_title + " > " + item.title, item_title=item.title,
+                         rating_key=item.rating_key)
+        ))
+
+    return oc
+
+
 @route(PREFIX + '/recently_added')
 def RecentlyAddedMenu(message=None):
     """

Contents/Code/interface/menu.py

@@ -1,5 +1,7 @@
 # coding=utf-8
 import logging
+import os
+
 import logger
 
 from item_details import ItemDetailsMenu
@@ -11,10 +13,10 @@ from advanced import DispatchRestart
 from subzero.constants import ART, PREFIX, DEPENDENCY_MODULE_NAMES
 from support.scheduler import scheduler
 from support.config import config
-from support.helpers import timestamp,  df
+from support.helpers import timestamp, df
 from support.ignore import ignore_list
 from support.items import get_all_items, get_items_info, \
-    get_item_kind_from_rating_key
+    get_item_kind_from_rating_key, get_item
 
 # init GUI
 ObjectContainer.art = R(ART)
@@ -53,7 +55,7 @@ def FirstLetterMetadataMenu(rating_key, key, title=None, base_title=None, displa
 
 @route(PREFIX + '/section/contents', display_items=bool)
 def MetadataMenu(rating_key, title=None, base_title=None, display_items=False, previous_item_type=None,
-                 previous_rating_key=None):
+                 previous_rating_key=None, randomize=None):
     """
     displays the contents of a section based on whether it has a deeper tree or not (movies->movie (item) list; series->series list)
     :param rating_key:
@@ -72,6 +74,22 @@ def MetadataMenu(rating_key, title=None, base_title=None, display_items=False, p
     current_kind = get_item_kind_from_rating_key(rating_key)
 
     if display_items:
+        timeout = 30
+
+        # add back to series for season
+        if current_kind == "season":
+            timeout = 360
+
+            show = get_item(previous_rating_key)
+            oc.add(DirectoryObject(
+                key=Callback(MetadataMenu, rating_key=show.rating_key, title=show.title, base_title=show.section.title,
+                             previous_item_type="section", display_items=True, randomize=timestamp()),
+                title=u"< Back to %s" % show.title,
+                thumb=show.thumb or default_thumb
+            ))
+        elif current_kind == "series":
+            timeout = 1800
+
         items = get_all_items(key="children", value=rating_key, base="library/metadata")
         kind, deeper = get_items_info(items)
         dig_tree(oc, items, MetadataMenu,
@@ -81,12 +99,6 @@ def MetadataMenu(rating_key, title=None, base_title=None, display_items=False, p
         if should_display_ignore(items, previous=previous_item_type):
             add_ignore_options(oc, "series", title=item_title, rating_key=rating_key, callback_menu=IgnoreMenu)
 
-        timeout = 30
-        if current_kind == "season":
-            timeout = 360
-        elif current_kind == "series":
-            timeout = 1800
-
         # add refresh
         oc.add(DirectoryObject(
             key=Callback(RefreshItem, rating_key=rating_key, item_title=title, refresh_kind=current_kind,
@@ -147,7 +159,6 @@ def RefreshMissing(randomize=None):
 @route(PREFIX + '/ValidatePrefs', enforce_route=True)
 def ValidatePrefs():
     Core.log.setLevel(logging.DEBUG)
-    Log.Debug("Validate Prefs called.")
 
     # cache the channel state
     update_dict = False
@@ -182,9 +193,44 @@ 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"]))
 
     return
-

Contents/Code/interface/sub_mod.py

@@ -0,0 +1,222 @@
+# coding=utf-8
+
+import traceback
+import types
+
+from babelfish import Language
+
+from menu_helpers import debounce, SubFolderObjectContainer, default_thumb
+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.helpers import timestamp, pad_title
+from support.items import get_current_sub, set_mods_for_part
+
+
+@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")
+
+    current_mods = current_sub.mods or []
+
+    oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
+
+    from interface.item_details import SubtitleOptionsMenu
+    oc.add(DirectoryObject(
+        key=Callback(SubtitleOptionsMenu, randomize=timestamp(), **kwargs),
+        title=u"< Back to subtitle options for: %s" % kwargs["title"],
+        summary=kwargs["current_data"],
+        thumb=default_thumb
+    ))
+
+    for identifier, mod in mod_registry.mods.iteritems():
+        if mod.advanced:
+            continue
+
+        if mod.exclusive and identifier in current_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_mods:
+        oc.add(DirectoryObject(
+            key=Callback(SubtitleSetMods, mods=None, mode="remove_last", randomize=timestamp(), **kwargs),
+            title=pad_title("Remove last applied mod (%s)" % current_mods[-1]),
+            summary=u"Currently applied mods: %s" % (", ".join(current_mods) if current_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_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_mods) if current_mods else "none")
+    ))
+
+    return oc
+
+
+@route(PREFIX + '/item/sub_mod_fps/{rating_key}/{part_id}', force=bool)
+def SubtitleFPSModMenu(**kwargs):
+    rating_key = kwargs["rating_key"]
+    part_id = kwargs["part_id"]
+    item_type = kwargs["item_type"]
+
+    kwargs.pop("randomize")
+
+    oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
+
+    oc.add(DirectoryObject(
+        key=Callback(SubtitleModificationsMenu, randomize=timestamp(), **kwargs),
+        title="< Back to subtitle modification menu"
+    ))
+
+    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
+
+    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)
+def SubtitleShiftModUnitMenu(**kwargs):
+    oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
+
+    kwargs.pop("randomize")
+
+    oc.add(DirectoryObject(
+        key=Callback(SubtitleModificationsMenu, randomize=timestamp(), **kwargs),
+        title="< Back to subtitle modifications"
+    ))
+
+    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)
+def SubtitleShiftModMenu(unit=None, **kwargs):
+    if unit not in POSSIBLE_UNITS_D:
+        raise NotImplementedError
+
+    kwargs.pop("randomize")
+
+    oc = SubFolderObjectContainer(title2=kwargs["title"], replace_parent=True)
+
+    oc.add(DirectoryObject(
+        key=Callback(SubtitleShiftModUnitMenu, randomize=timestamp(), **kwargs),
+        title="< Back to unit selection"
+    ))
+
+    rng = []
+    if unit == "h":
+        rng = range(-10, 11)
+    elif unit in ("m", "s"):
+        rng = range(-15, 15)
+    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)
+
+    set_mods_for_part(rating_key, part_id, language, item_type, mods, mode=mode)
+
+    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)
+
+    oc.add(DirectoryObject(
+        key=Callback(SubtitleModificationsMenu, randomize=timestamp(), **kwargs),
+        title="< Back to subtitle modifications"
+    ))
+
+    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

Contents/Code/support/__init__.py

@@ -18,7 +18,7 @@ sys.modules["support.plex_media"] = plex_media
 
 import localmedia
 
-sys.modules["subzero.localmedia"] = localmedia
+sys.modules["support.localmedia"] = localmedia
 
 import subtitlehelpers
 

Contents/Code/support/activities.py

@@ -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)
 
@@ -27,9 +27,6 @@ class PlexActivityManager(object):
 
     @throttle(5, instance_method=True)
     def on_playing(self, info):
-        if not config.use_activities:
-            return
-
         # ignore non-playing states and anything too far in
         if info["state"] != "playing" or info["viewOffset"] > 60000:
             return
@@ -41,13 +38,22 @@ class PlexActivityManager(object):
             return
 
         rating_key = info["ratingKey"]
-        if rating_key not in Dict["last_played_items"]:
-            # new playing; store last 10 recently played items
+        if rating_key in Dict["last_played_items"] and rating_key != Dict["last_played_items"][0]:
+            # shift last played
+            Dict["last_played_items"].insert(0,
+                                             Dict["last_played_items"].pop(Dict["last_played_items"].index(rating_key)))
+            Dict.Save()
+
+        elif rating_key not in Dict["last_played_items"]:
+            # new playing; store last X recently played items
             Dict["last_played_items"].insert(0, rating_key)
-            Dict["last_played_items"] = Dict["last_played_items"][:10]
+            Dict["last_played_items"] = Dict["last_played_items"][:config.store_recently_played_amount]
 
             Dict.Save()
 
+            if not config.react_to_activities:
+                return
+
             debug_msg = "Started playing %s. Refreshing it." % rating_key
 
             key_to_refresh = None
@@ -108,4 +114,5 @@ class PlexActivityManager(object):
                                 if ep.index == 1:
                                     return ep
 
+
 activity = PlexActivityManager()

Contents/Code/support/config.py

@@ -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 +70,8 @@ class Config(object):
     sections = None
     enabled_sections = None
     remove_hi = False
+    fix_ocr = False
+    fix_common = False
     enforce_encoding = False
     chmod = None
     forced_only = False
@@ -75,9 +79,12 @@ class Config(object):
     treat_und_as_first = False
     ext_match_strictness = False
     default_mods = None
-    use_activities = False
+    debug_mods = False
+    react_to_activities = False
     activity_mode = None
 
+    store_recently_played_amount = 20
+
     initialized = False
 
     def initialize(self):
@@ -91,6 +98,7 @@ 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()
@@ -98,6 +106,7 @@ class Config(object):
 
         self.lang_list = self.get_lang_list()
         self.subtitle_destination_folder = self.get_subtitle_destination_folder()
+        self.forced_only = cast_bool(Prefs["subtitles.only_foreign"])
         self.providers = self.get_providers()
         self.provider_settings = self.get_provider_settings()
         self.max_recent_items_per_library = int_or_default(Prefs["scheduler.max_recent_items_per_library"], 2000)
@@ -109,15 +118,32 @@ 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.fix_common = cast_bool(Prefs['subtitles.fix_common'])
         self.enforce_encoding = cast_bool(Prefs['subtitles.enforce_encoding'])
         self.chmod = self.check_chmod()
-        self.forced_only = cast_bool(Prefs["subtitles.only_foreign"])
         self.exotic_ext = cast_bool(Prefs["subtitles.scan.exotic_ext"])
         self.treat_und_as_first = cast_bool(Prefs["subtitles.language.treat_und_as_first"])
         self.ext_match_strictness = self.determine_ext_sub_strictness()
         self.default_mods = self.get_default_mods()
+        self.debug_mods = cast_bool(Prefs['log_debug_mods'])
         self.initialized = True
 
+    def init_cache(self):
+        use_fallback_cache = True
+        if Core.runtime.os != "Windows":
+            try:
+                subliminal.region.configure('dogpile.cache.dbm', expiration_time=datetime.timedelta(days=30),
+                                            arguments={'filename': os.path.join(config.data_items_path, 'subzero.dbm'),
+                                                       'lock_factory': MutexLock})
+                use_fallback_cache = False
+            except:
+                pass
+
+        if use_fallback_cache:
+            Log.Warn("Not using file based cache!")
+            subliminal.region.configure('dogpile.cache.memory')
+
     def set_log_paths(self):
         # find log handler
         for handler in Core.log.handlers:
@@ -144,6 +170,8 @@ 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
@@ -347,10 +375,13 @@ class Config(object):
                      }
 
         # ditch non-forced-subtitles-reporting providers
-        if cast_bool(Prefs['subtitles.only_foreign']):
+        if self.forced_only:
             providers["addic7ed"] = False
             providers["tvsubtitles"] = False
             providers["legendastv"] = False
+            providers["napiprojekt"] = False
+            providers["shooter"] = False
+            providers["subscenter"] = False
 
         return filter(lambda prov: providers[prov], providers)
 
@@ -412,16 +443,20 @@ class Config(object):
         mods = []
         if self.remove_hi:
             mods.append("remove_HI")
+        if self.fix_ocr:
+            mods.append("OCR_fixes")
+        if self.fix_common:
+            mods.append("common")
 
         return mods
 
     def set_activity_modes(self):
         val = Prefs["activity.on_playback"]
         if val == "never":
-            self.use_activities = False
+            self.react_to_activities = False
             return
 
-        self.use_activities = True
+        self.react_to_activities = True
         if val == "current media item":
             self.activity_mode = "refresh"
         elif val == "hybrid: current item or next episode":

Contents/Code/support/helpers.py

@@ -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,
@@ -303,3 +303,7 @@ def dispatch_track_usage(*args, **kwargs):
 
 def get_language(lang_short):
     return Language.fromietf(lang_short)
+
+
+class PartUnknownException(Exception):
+    pass

Contents/Code/support/items.py

@@ -2,12 +2,15 @@
 
 import logging
 import re
+import traceback
 import types
 import os
 from ignore import ignore_list
-from helpers import is_recent, get_plex_item_display_title, query_plex
+from helpers import is_recent, get_plex_item_display_title, query_plex, PartUnknownException
 from lib import Plex, get_intent
 from config import config, IGNORE_FN
+from subliminal_patch.subtitle import ModifiedSubtitle
+from subzero.modification import registry as mod_registry, SubtitleModifications
 
 logger = logging.getLogger(__name__)
 
@@ -40,11 +43,11 @@ PLEX_API_TYPE_MAP = {
 
 def get_item_kind_from_rating_key(key):
     item = get_item(key)
-    return PLEX_API_TYPE_MAP[get_item_kind(item)]
+    return PLEX_API_TYPE_MAP.get(get_item_kind(item))
 
 
 def get_item_kind_from_item(item):
-    return PLEX_API_TYPE_MAP[get_item_kind(item)]
+    return PLEX_API_TYPE_MAP.get(get_item_kind(item))
 
 
 def get_item_thumb(item):
@@ -292,4 +295,52 @@ def get_current_sub(rating_key, part_id, language):
     subtitle_storage = get_subtitle_storage()
     stored_subs = subtitle_storage.load_or_new(item)
     current_sub = stored_subs.get_any(part_id, language)
-    return current_sub, stored_subs, subtitle_storage
+    return current_sub, stored_subs, subtitle_storage
+
+
+def set_mods_for_part(rating_key, part_id, language, item_type, mods, mode="add"):
+    from support.plex_media import get_plex_metadata, scan_videos
+    from support.storage import save_subtitles
+
+    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)
+
+    try:
+        metadata = get_plex_metadata(rating_key, part_id, item_type)
+    except PartUnknownException:
+        return
+
+    scanned_parts = scan_videos([metadata], kind="series" if item_type == "episode" else "movie", ignore_all=True)
+    video, plex_part = scanned_parts.items()[0]
+
+    subtitle = ModifiedSubtitle(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
+    subtitle.id = current_sub.id
+
+    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())

Contents/Code/support/localmedia.py

@@ -108,7 +108,8 @@ def find_subtitles(part):
                     if ext.lower()[1:] in config.SUBTITLE_EXTS:
                         # get fn without forced/default/normal tag
                         split_tag = root.rsplit(".", 1)
-                        if len(split_tag) > 1 and split_tag[1].lower() in ['forced', 'normal', 'default']:
+                        if len(split_tag) > 1 and split_tag[1].lower() in ['forced', 'normal', 'default', 'embedded',
+                                                                           'custom']:
                             root = split_tag[0]
 
                         # get associated media file name without language
@@ -160,9 +161,8 @@ def find_subtitles(part):
         # determine whether to pick up the subtitle based on our match strictness
         elif not filename_matches_part:
             if sz_config.ext_match_strictness == "strict" or (
-                    sz_config.ext_match_strictness == "loose" and not filename_contains_part):
-
-                #Log.Debug("%s doesn't match %s, skipping" % (helpers.unicodize(local_filename),
+                            sz_config.ext_match_strictness == "loose" and not filename_contains_part):
+                # Log.Debug("%s doesn't match %s, skipping" % (helpers.unicodize(local_filename),
                 #                                             helpers.unicodize(part_basename)))
                 continue
 

Contents/Code/support/missing_subtitles.py

@@ -1,5 +1,6 @@
 # coding=utf-8
 import traceback
+import time
 
 from support.config import config
 from support.helpers import get_plex_item_display_title, cast_bool
@@ -47,7 +48,7 @@ def item_discover_missing_subs(rating_key, kind="show", added_at=None, section_t
         return added_at, item_id, item_title, item, missing
 
 
-def items_get_all_missing_subs(items):
+def items_get_all_missing_subs(items, sleep_after_request=False):
     missing = []
     for added_at, kind, section_title, key in items:
         try:
@@ -65,6 +66,8 @@ def items_get_all_missing_subs(items):
                 missing.append(state)
         except:
             Log.Error("Something went wrong when getting the state of item %s: %s", key, traceback.format_exc())
+        if sleep_after_request:
+            time.sleep(sleep_after_request)
     return missing
 
 

Contents/Code/support/plex_media.py

@@ -3,13 +3,11 @@
 import os
 
 import helpers
-
+from config import config
 from items import get_item
 from lib import get_intent, Plex
-from config import config
 from subzero.video import parse_video
 
-
 def get_metadata_dict(item, part, add):
     data = {
         "item": item,
@@ -179,10 +177,6 @@ def scan_videos(videos, kind="series", ignore_all=False):
     return ret
 
 
-class PartUnknownException(Exception):
-    pass
-
-
 def get_plex_metadata(rating_key, part_id, item_type):
     """
     uses the Plex 3rd party API accessor to get metadata information
@@ -202,7 +196,7 @@ def get_plex_metadata(rating_key, part_id, item_type):
             current_part = part
 
     if not current_part:
-        raise PartUnknownException("Part unknown")
+        raise helpers.PartUnknownException("Part unknown")
 
     # get normalized metadata
     if item_type == "episode":
@@ -257,3 +251,24 @@ class PMSMediaProxy(object):
                 break
 
             m = m.children[0]
+
+    def get_all_parts(self):
+        """
+        walk the mediatree until the given part was found; if no part was given, return the first one
+        :param part_id:
+        :return:
+        """
+        m = self.mediatree
+        parts = []
+        while 1:
+            if m.items:
+                media_item = m.items[0]
+                for part in media_item.parts:
+                    parts.append(part)
+                break
+
+            if not m.children:
+                break
+
+            m = m.children[0]
+        return parts

Contents/Code/support/scheduler.py

@@ -168,6 +168,7 @@ class DefaultScheduler(object):
                 for args, kwargs in queue:
                     Log.Debug("Dispatching single task: %s, %s", args, kwargs)
                     Thread.Create(self.run_task, True, *args, **kwargs)
+                    Thread.Sleep(5.0)
 
             # scheduled tasks
             for name, info in self.tasks.iteritems():
@@ -185,9 +186,13 @@ class DefaultScheduler(object):
                     continue
 
                 if not task.last_run or (task.last_run + datetime.timedelta(**{frequency_key: frequency_num}) <= now):
+                    # fixme: scheduled tasks run synchronously. is this the best idea?
+                    #Thread.Create(self.run_task, True, name)
+                    #Thread.Sleep(5.0)
                     self.run_task(name)
+                    Thread.Sleep(5.0)
 
-            Thread.Sleep(5.0)
+            Thread.Sleep(1)
 
 
 scheduler = DefaultScheduler()

Contents/Code/support/storage.py

@@ -137,7 +137,8 @@ def save_subtitles_to_file(subtitles):
                 os.makedirs(fld)
         subliminal.save_subtitles(video, video_subtitles, directory=fld, single=cast_bool(Prefs['subtitles.only_one']),
                                       encode_with=force_utf8 if config.enforce_encoding else None,
-                                      chmod=config.chmod, forced_tag=config.forced_only, path_decoder=force_unicode)
+                                      chmod=config.chmod, forced_tag=config.forced_only, path_decoder=force_unicode,
+                                      debug_mods=config.debug_mods)
     return True
 
 
@@ -145,7 +146,8 @@ def save_subtitles_to_metadata(videos, subtitles):
     for video, video_subtitles in subtitles.items():
         mediaPart = videos[video]
         for subtitle in video_subtitles:
-            content = force_utf8(subtitle.text) if config.enforce_encoding else subtitle.content
+            content = force_utf8(subtitle.get_modified_text(debug=config.debug_mods)) if config.enforce_encoding else \
+                subtitle.get_modified_content(debug=config.debug_mods)
 
             if not isinstance(mediaPart, Framework.api.agentkit.MediaPart):
                 # we're being handed a Plex.py model instance here, not an internal PMS MediaPart object.
@@ -207,3 +209,5 @@ def save_subtitles(scanned_video_part_map, downloaded_subtitles, mode="a", bare_
     if not bare_save:
         store_subtitle_info(scanned_video_part_map, downloaded_subtitles, storage, mode=mode)
 
+    return save_successful
+

Contents/Code/support/tasks.py

@@ -16,8 +16,8 @@ from storage import save_subtitles, whack_missing_parts, get_subtitle_storage
 from support.config import config
 from support.items import get_recent_items, is_ignored, get_item
 from support.lib import Plex
-from support.helpers import track_usage, get_title_for_video_metadata, cast_bool
-from support.plex_media import scan_videos, get_plex_metadata, PartUnknownException
+from support.helpers import track_usage, get_title_for_video_metadata, cast_bool, PartUnknownException
+from support.plex_media import scan_videos, get_plex_metadata
 
 
 class Task(object):
@@ -80,14 +80,16 @@ class Task(object):
         return
 
     def run(self):
+        Log.Info(u"Task: running: %s", self.name)
         self.time_start = datetime.datetime.now()
 
     def post_run(self, data_holder):
         self.running = False
         self.last_run = datetime.datetime.now()
-        if self.time_start:
+        if self.time_start and self.last_run:
             self.last_run_time = self.last_run - self.time_start
         self.time_start = None
+        Log.Info(u"Task: ran: %s", self.name)
 
 
 class SearchAllRecentlyAddedMissing(Task):
@@ -122,7 +124,7 @@ class SearchAllRecentlyAddedMissing(Task):
     def prepare(self, *args, **kwargs):
         self.items_done = []
         recent_items = get_recent_items()
-        missing = items_get_all_missing_subs(recent_items)
+        missing = items_get_all_missing_subs(recent_items, sleep_after_request=0.2)
         ids = set([id for added_at, id, title, item, missing_languages in missing if not is_ignored(id, item=item)])
         self.items_searching = missing
         self.items_searching_ids = ids
@@ -179,7 +181,7 @@ class SearchAllRecentlyAddedMissing(Task):
 
 
 class SubtitleListingMixin(object):
-    def list_subtitles(self, rating_key, item_type, part_id, language):
+    def list_subtitles(self, rating_key, item_type, part_id, language, skip_wrong_fps=True):
         metadata = get_plex_metadata(rating_key, part_id, item_type)
 
         if item_type == "episode":
@@ -195,9 +197,14 @@ class SubtitleListingMixin(object):
         video, plex_part = scanned_parts.items()[0]
         config.init_subliminal_patches()
 
+        provider_settings = config.provider_settings.copy()
+        if not skip_wrong_fps:
+            provider_settings = config.provider_settings.copy()
+            provider_settings["opensubtitles"]["skip_wrong_fps"] = False
+
         available_subs = list_all_subtitles(scanned_parts, {Language.fromietf(language)},
                                             providers=config.providers,
-                                            provider_configs=config.provider_settings,
+                                            provider_configs=provider_settings,
                                             pool_class=config.provider_pool)
 
         use_hearing_impaired = Prefs['subtitles.search.hearingImpaired'] in ("prefer", "force HI")
@@ -248,7 +255,7 @@ class DownloadSubtitleMixin(object):
         if subtitle.content:
             try:
                 whack_missing_parts(scanned_parts)
-                save_subtitles(scanned_parts, {video: [subtitle]}, mode=mode)
+                save_subtitles(scanned_parts, {video: [subtitle]}, mode=mode, mods=config.default_mods)
                 Log.Debug("Manually downloaded subtitle for: %s", rating_key)
                 download_successful = True
                 refresh_item(rating_key)
@@ -291,7 +298,8 @@ class AvailableSubsForItem(SubtitleListingMixin, Task):
         super(AvailableSubsForItem, self).run()
         self.running = True
         track_usage("Subtitle", "manual", "list", 1)
-        self.data = self.list_subtitles(self.rating_key, self.item_type, self.part_id, self.language)
+        self.data = self.list_subtitles(self.rating_key, self.item_type, self.part_id, self.language,
+                                        skip_wrong_fps=False)
 
     def post_run(self, task_data):
         super(AvailableSubsForItem, self).post_run(task_data)
@@ -362,13 +370,25 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
                 return
 
         now = datetime.datetime.now()
+        min_score_series = int(Prefs["subtitles.search.minimumTVScore2"].strip())
+        min_score_movies = int(Prefs["subtitles.search.minimumMovieScore2"].strip())
+        overwrite_manually_modified = cast_bool(
+            Prefs["scheduler.tasks.FindBetterSubtitles.overwrite_manually_modified"])
+        overwrite_manually_selected = cast_bool(
+            Prefs["scheduler.tasks.FindBetterSubtitles.overwrite_manually_selected"])
 
         subtitle_storage = get_subtitle_storage()
         recent_subs = subtitle_storage.load_recent_files(age_days=max_search_days)
 
         for fn, stored_subs in recent_subs.iteritems():
             video_id = stored_subs.video_id
-            cutoff = self.series_cutoff if stored_subs.item_type == "episode" else self.movies_cutoff
+
+            if stored_subs.item_type == "episode":
+                cutoff = self.series_cutoff
+                min_score = min_score_series
+            else:
+                cutoff = self.movies_cutoff
+                min_score = min_score_movies
 
             # don't search for better subtitles until at least 30 minutes have passed
             if stored_subs.added_at + datetime.timedelta(minutes=30) > now:
@@ -403,11 +423,15 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
                         continue
 
                     # got manual subtitle but don't want to touch those?
-                    if current_mode == "m" and \
-                            not cast_bool(Prefs["scheduler.tasks.FindBetterSubtitles.overwrite_manually_selected"]):
+                    if current_mode == "m" and not overwrite_manually_selected:
                         Log.Debug(u"Skipping finding better subs, had manual: %s", stored_subs.title)
                         continue
 
+                    # subtitle modifications different from default
+                    if not overwrite_manually_modified and set(current.mods).difference(set(config.default_mods)):
+                        Log.Debug(u"Skipping finding better subs, it has manual modifications: %s", stored_subs.title)
+                        continue
+
                     try:
                         subs = self.list_subtitles(video_id, stored_subs.item_type, part_id, language)
                     except PartUnknownException:
@@ -420,7 +444,7 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
                         better_downloaded = False
                         better_tried_download = 0
                         for sub in subs:
-                            if sub.score > current_score:
+                            if sub.score > current_score and sub.score > min_score:
                                 Log.Debug("Better subtitle found for %s, downloading", video_id)
                                 better_tried_download += 1
                                 ret = self.download_subtitle(sub, video_id, mode="b")
@@ -444,8 +468,12 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
                         pass
                 subtitle_storage.save(stored_subs)
 
+            time.sleep(1)
+
         if better_found:
             Log.Debug("Task: %s, done. Better subtitles found for %s items", self.name, better_found)
+        else:
+            Log.Debug("Task: %s, done. No better subtitles found for %s items", self.name, len(recent_subs))
 
 
 class SubtitleStorageMaintenance(Task):

Contents/DefaultPrefs.json

@@ -258,13 +258,14 @@
       "35",
       "30",
       "25",
+      "21",
       "20",
       "15",
       "10",
       "5",
       "0"
     ],
-    "default": "25"
+    "default": "21"
   },
   {
     "id": "provider.addic7ed.use_random_agents",
@@ -332,7 +333,7 @@
   },
   {
     "id": "providers.multithreading",
-    "label": "Search enabled providers simuntaneously (multithreading)",
+    "label": "Search enabled providers simultaneously (multithreading)",
     "type": "bool",
     "default": "true"
   },
@@ -381,7 +382,7 @@
     "id": "subtitles.search.minimumMovieScore2",
     "label": "Minimum score for movies (min: 60, def/sane: 69, min-ideal: 82; see http://v.ht/szscores)",
     "type": "text",
-    "default": "69"
+    "default": "60"
   },
   {
     "id": "subtitles.search.hearingImpaired",
@@ -399,6 +400,18 @@
     "id": "subtitles.remove_hi",
     "label": "Remove Hearing Impaired tags from downloaded subtitles",
     "type": "bool",
+    "default": "false"
+  },
+  {
+    "id": "subtitles.fix_common",
+    "label": "Fix common whitespace/punctuation issues in subtitles",
+    "type": "bool",
+    "default": "true"
+  },
+  {
+    "id": "subtitles.fix_ocr",
+    "label": "Fix common OCR errors in downloaded subtitles",
+    "type": "bool",
     "default": "true"
   },
   {
@@ -524,6 +537,12 @@
     "type": "bool",
     "default": "true"
   },
+  {
+    "id": "scheduler.tasks.FindBetterSubtitles.overwrite_manually_modified",
+    "label": "Scheduler: Overwrite subtitles with non-default subtitle modifications when better found",
+    "type": "bool",
+    "default": "false"
+  },
   {
     "id": "history_size",
     "label": "History: amount of items to store historical data for",
@@ -622,6 +641,12 @@
     ],
     "default": "WARNING"
   },
+  {
+    "id": "log_debug_mods",
+    "label": "Log subtitle modification (debug)",
+    "type": "bool",
+    "default": "false"
+  },
   {
     "id": "log_console",
     "label": "Log to console (for development/debugging)",

Contents/Info.plist

@@ -9,11 +9,11 @@
         <key>CFBundleInfoDictionaryVersion</key>
         <string>6.0</string>
         <key>CFBundleShortVersionString</key>
-        <string>2.0.0</string>
+        <string>2.0.15</string>
         <key>CFBundleSignature</key>
         <string>????</string>
         <key>CFBundleVersion</key>
-        <string>2.0.0.10</string>
+        <string>2.0.15.1216</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 2.0.0.10 DEV
+Version 2.0.15.1216 RC3
 
 Originally based on @bramwalet's awesome &lt;a href=&quot;https://github.com/bramwalet/Subliminal.bundle&quot;&gt;Subliminal.bundle&lt;/a&gt;
 

Contents/Libraries/Shared/enzyme/mkv.py

@@ -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)

Contents/Libraries/Shared/subliminal_patch/core.py

@@ -460,7 +460,7 @@ def get_subtitle_path(video_path, language=None, extension='.srt', forced_tag=Fa
 
 
 def save_subtitles(video, subtitles, single=False, directory=None, encoding=None, encode_with=None, chmod=None,
-                   forced_tag=False, path_decoder=None):
+                   forced_tag=False, path_decoder=None, debug_mods=False):
     """Save subtitles on filesystem.
 
     Subtitles are saved in the order of the list. If a subtitle with a language has already been saved, other subtitles
@@ -515,7 +515,8 @@ def save_subtitles(video, subtitles, single=False, directory=None, encoding=None
 
         # save normalized subtitle if encoder or no encoding is given
         if has_encoder or encoding is None:
-            content = encode_with(subtitle.get_modified_text()) if has_encoder else subtitle.get_modified_content()
+            content = encode_with(subtitle.get_modified_text(debug=debug_mods)) if has_encoder else \
+                subtitle.get_modified_content(debug=debug_mods)
             with io.open(subtitle_path, 'wb') as f:
                 f.write(content)
 

Contents/Libraries/Shared/subliminal_patch/http.py

@@ -4,7 +4,8 @@ from xmlrpclib import SafeTransport
 import certifi
 import ssl
 import os
-from requests import Session
+import socket
+from requests import Session, exceptions
 from retry.api import retry_call
 
 pem_file = os.path.normpath(os.path.join(os.path.dirname(os.path.realpath(__file__)), "..", certifi.where()))
@@ -23,7 +24,14 @@ class RetryingSession(Session):
         self.verify = pem_file
 
     def retry_method(self, method, *args, **kwargs):
-        return retry_call(getattr(super(RetryingSession, self), method), fargs=args, fkwargs=kwargs, tries=3, delay=1)
+        return retry_call(getattr(super(RetryingSession, self), method), fargs=args, fkwargs=kwargs, tries=3, delay=5,
+                          exceptions=(exceptions.ConnectionError,
+                                      exceptions.ProxyError,
+                                      exceptions.SSLError,
+                                      exceptions.Timeout,
+                                      exceptions.ConnectTimeout,
+                                      exceptions.ReadTimeout,
+                                      socket.timeout))
 
     def get(self, *args, **kwargs):
         return self.retry_method("get", *args, **kwargs)

Contents/Libraries/Shared/subliminal_patch/providers/__init__.py

@@ -5,3 +5,5 @@ from subliminal.providers import Provider as _Provider
 
 class Provider(_Provider):
     hash_verifiable = False
+    skip_wrong_fps = True
+

Contents/Libraries/Shared/subliminal_patch/providers/opensubtitles.py

@@ -19,7 +19,7 @@ class OpenSubtitlesSubtitle(_OpenSubtitlesSubtitle):
 
     def __init__(self, language, hearing_impaired, page_link, subtitle_id, matched_by, movie_kind, hash, movie_name,
                  movie_release_name, movie_year, movie_imdb_id, series_season, series_episode, query_parameters,
-                 filename, encoding, fps):
+                 filename, encoding, fps, skip_wrong_fps=True):
         super(OpenSubtitlesSubtitle, self).__init__(language, hearing_impaired, page_link, subtitle_id,
                                                     matched_by, movie_kind, hash,
                                                     movie_name, movie_release_name, movie_year, movie_imdb_id,
@@ -27,6 +27,8 @@ class OpenSubtitlesSubtitle(_OpenSubtitlesSubtitle):
         self.query_parameters = query_parameters or {}
         self.fps = fps
         self.release_info = movie_release_name
+        self.wrong_fps = False
+        self.skip_wrong_fps = skip_wrong_fps
 
     def get_matches(self, video, hearing_impaired=False):
         matches = super(OpenSubtitlesSubtitle, self).get_matches(video)
@@ -39,9 +41,14 @@ class OpenSubtitlesSubtitle(_OpenSubtitlesSubtitle):
 
         # video has fps info, sub also, and sub's fps is greater than 0
         if video.fps and sub_fps and (video.fps != self.fps):
-            logger.debug("Wrong FPS (expected: %s, got: %s, lowering score massively)", video.fps, self.fps)
-            # fixme: may be too harsh
-            return set()
+            self.wrong_fps = True
+
+            if self.skip_wrong_fps:
+                logger.debug("Wrong FPS (expected: %s, got: %s, lowering score massively)", video.fps, self.fps)
+                # fixme: may be too harsh
+                return set()
+            else:
+                logger.debug("Wrong FPS (expected: %s, got: %s, continuing)", video.fps, self.fps)
 
         # matched by tag?
         if self.matched_by == "tag":
@@ -57,8 +64,9 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
     only_foreign = True
     subtitle_class = OpenSubtitlesSubtitle
     hash_verifiable = True
+    skip_wrong_fps = True
 
-    def __init__(self, username=None, password=None, use_tag_search=False, only_foreign=False):
+    def __init__(self, username=None, password=None, use_tag_search=False, only_foreign=False, skip_wrong_fps=True):
         if username is not None and password is None or username is None and password is not None:
             raise ConfigurationError('Username and password must be specified')
 
@@ -66,6 +74,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
         self.password = password or ''
         self.use_tag_search = use_tag_search
         self.only_foreign = only_foreign
+        self.skip_wrong_fps = skip_wrong_fps
 
         if use_tag_search:
             logger.info("Using tag/exact filename search")
@@ -176,7 +185,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
                                            movie_kind,
                                            hash, movie_name, movie_release_name, movie_year, movie_imdb_id,
                                            series_season, series_episode, query_parameters, filename, encoding,
-                                           movie_fps)
+                                           movie_fps, skip_wrong_fps=self.skip_wrong_fps)
             logger.debug('Found subtitle %r by %s', subtitle, matched_by)
             subtitles.append(subtitle)
 

Contents/Libraries/Shared/subliminal_patch/subtitle.py

@@ -7,8 +7,8 @@ import chardet
 import pysrt
 import pysubs2
 from bs4 import UnicodeDammit
-from subliminal import Subtitle
 from subzero.modification import SubtitleModifications
+from subliminal import Subtitle
 
 logger = logging.getLogger(__name__)
 
@@ -20,6 +20,8 @@ class PatchedSubtitle(Subtitle):
     hash_verifiable = False
     mods = None
     plex_media_fps = None
+    skip_wrong_fps = False
+    wrong_fps = False
 
     def __init__(self, language, hearing_impaired=False, page_link=None, encoding=None, mods=None):
         super(PatchedSubtitle, self).__init__(language, hearing_impaired=hearing_impaired, page_link=page_link,
@@ -136,28 +138,28 @@ class PatchedSubtitle(Subtitle):
 
         return True
 
-    def get_modified_content(self):
+    def get_modified_content(self, debug=False):
         """
-        :param language: 
-        :param fps: 
         :return: string 
         """
         if not self.mods:
             return self.content
 
         encoding = self.guess_encoding()
-
-        submods = SubtitleModifications()
-        submods.load(content=self.text, fps=self.plex_media_fps)
+        submods = SubtitleModifications(debug=debug)
+        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):
+    def get_modified_text(self, debug=False):
         """
-        :param language: 
-        :param fps: 
         :return: unicode 
         """
-        content = self.get_modified_content()
+        content = self.get_modified_content(debug=debug)
         encoding = self.guess_encoding()
         return content.decode(encoding=encoding)
+
+
+class ModifiedSubtitle(PatchedSubtitle):
+    id = None

Contents/Libraries/Shared/submod_test.py

@@ -1,7 +1,10 @@
 # coding=utf-8
 
-import sys
 import logging
+import sys
+import codecs
+
+from babelfish import Language
 
 logger = logging.getLogger(__name__)
 
@@ -14,7 +17,15 @@ if debug:
     logging.basicConfig(level=logging.DEBUG)
 
 submod = SubMod(debug=debug)
-submod.load(fn)
-submod.modify("remove_HI")
+submod.load(fn, language=Language.fromietf("spa"), encoding="latin-1")
+submod.modify("remove_HI", "OCR_fixes", "common", "shift_offset(s=20)")
+#srt = submod.to_string("srt", "utf-8")
+#f = codecs.open("testout.srt", "w+", encoding="utf-8")
+#f.write(srt)
+#f.close()
+#print submod.f.to_string("srt")
+#submod.modify("OCR_fixes")
+#submod.modify("change_FPS(from=24,to=25)")
+#submod.modify("common")
 
 #print submod.f.to_string("srt")

Contents/Libraries/Shared/subzero/modification.py

@@ -1,246 +0,0 @@
-# coding=utf-8
-
-import re
-import traceback
-from collections import OrderedDict
-
-import pysubs2
-import logging
-
-logger = logging.getLogger(__name__)
-
-
-class SubtitleModifications(object):
-    debug = False
-
-    def __init__(self, debug=False):
-        self.debug = debug
-
-    def load(self, fn=None, content=None, fps=None):
-        """
-        
-        :param fn:  filename
-        :param content: unicode 
-        :param fps: 
-        :return: 
-        """
-        try:
-            if fn:
-                self.f = pysubs2.load(fn, fps=fps)
-            elif content:
-                self.f = pysubs2.SSAFile.from_string(content, fps=fps)
-        except (IOError,
-                UnicodeDecodeError,
-                pysubs2.exceptions.UnknownFPSError,
-                pysubs2.exceptions.UnknownFormatIdentifierError,
-                pysubs2.exceptions.FormatAutodetectionError):
-            if fn:
-                logger.exception("Couldn't load subtitle: %s: %s", fn, traceback.format_exc())
-            elif content:
-                logger.exception("Couldn't load subtitle: %s", traceback.format_exc())
-
-    def modify(self, *mods):
-        new_f = []
-        for line in self.f:
-            applied_mods = []
-            for identifier in mods:
-                if identifier in registry.mods:
-                    mod = registry.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 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)
-
-        self.f.events = new_f
-
-    def to_string(self, format="srt", encoding="utf-8"):
-        return self.f.to_string(format, encoding=encoding)
-
-    def save(self, fn):
-        self.f.save(fn)
-
-
-SubMod = SubtitleModifications
-
-
-class SubtitleModRegistry(object):
-    mods = None
-    mods_available = None
-
-    def __init__(self):
-        self.mods = OrderedDict()
-        self.mods_available = []
-
-    def register(self, mod):
-        self.mods[mod.identifier] = mod
-        self.mods_available.append(mod.identifier)
-
-registry = SubtitleModRegistry()
-
-
-class Processor(object):
-    """
-    Processor base class
-    """
-    name = None
-
-    def __init__(self, name=None):
-        self.name = name
-
-    @property
-    def info(self):
-        return self.name
-
-    def process(self, content):
-        return content
-
-    def __repr__(self):
-        return "Processor <%s %s>" % (self.__class__.__name__, self.info)
-
-    def __str__(self):
-        return repr(self)
-
-    def __unicode__(self):
-        return unicode(repr(self))
-
-
-class StringProcessor(Processor):
-    """
-    String replacement processor base
-    """
-
-    def __init__(self, search, replace, name=None):
-        super(StringProcessor, self).__init__(name=name)
-        self.search = search
-        self.replace = replace
-
-    def process(self, content):
-        return content.replace(self.search, self.replace)
-
-
-class ReProcessor(Processor):
-    """
-    Regex processor
-    """
-    pattern = None
-    replace_with = None
-
-    def __init__(self, pattern, replace_with, name=None):
-        super(ReProcessor, self).__init__(name=name)
-        self.pattern = pattern
-        self.replace_with = replace_with
-
-    def process(self, content, debug=False):
-        return self.pattern.sub(self.replace_with, content)
-
-
-class NReProcessor(ReProcessor):
-    """
-    Single line regex processor
-    """
-
-    def process(self, content, debug=False):
-        lines = []
-        for line in content.split(r"\N"):
-            a = super(NReProcessor, self).process(line, debug=debug)
-            if not a:
-                continue
-            lines.append(a)
-        return r"\N".join(lines)
-
-
-class SubtitleModification(object):
-    identifier = None
-    description = None
-    exclusive = False
-    pre_processors = []
-    processors = []
-    post_processors = []
-
-    @classmethod
-    def _process(cls, content, processors, debug=False):
-        if not content:
-            return
-
-        new_content = content
-        for processor in processors:
-            old_content = new_content
-            new_content = processor.process(new_content, debug=debug)
-            if not new_content:
-                if debug:
-                    logger.debug("Processor returned empty line: %s", processor)
-                break
-            if debug:
-                if old_content == new_content:
-                    continue
-                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)
-
-    @classmethod
-    def process(cls, content, debug=False):
-        return cls._process(content, cls.processors, debug=debug)
-
-    @classmethod
-    def post_process(cls, content, debug=False):
-        return cls._process(content, cls.post_processors, debug=debug)
-
-    @classmethod
-    def modify(cls, content, debug=False):
-        new_content = content
-        for method in ("pre_process", "process", "post_process"):
-            new_content = getattr(cls, method)(new_content, debug=debug)
-
-        return new_content
-
-
-class SubtitleTextModification(SubtitleModification):
-    post_processors = [
-        # empty tag
-        ReProcessor(re.compile(r'({\\\w+1})[\s.,-_!?]+({\\\w+0})'), "", name="empty_tag"),
-
-        # empty line (needed?)
-        NReProcessor(re.compile(r'^\s+$'), "", name="empty_line"),
-
-        # empty dash line (needed?)
-        NReProcessor(re.compile(r'(^[\s]*[\-]+[\s]*)$'), "", name="empty_dash_line"),
-
-        # clean whitespace at start and end
-        ReProcessor(re.compile(r'^\s*([^\s]+)\s*$'), r"\1", name="surrounding_whitespace"),
-    ]
-
-
-class HearingImpaired(SubtitleTextModification):
-    identifier = "remove_HI"
-    description = "Remove Hearing Impaired tags"
-    exclusive = True
-
-    processors = [
-        # brackets
-        NReProcessor(re.compile(r'(?sux)[([].+[)\]]'), "", name="HI_brackets"),
-
-        # text before colon (and possible dash in front)
-        NReProcessor(re.compile(r'(?u)(^[A-z\-]+[\w\s]*:[^0-9{2}][\s]*)'), "", name="HI_before_colon"),
-
-        # all caps line (at least 3 chars)
-        NReProcessor(re.compile(r'(?u)(^[A-Z]{3,}$)'), "", name="HI_all_caps"),
-
-        # dash in front
-        NReProcessor(re.compile(r'(?u)^\s*-\s*'), "", name="HI_starting_dash"),
-    ]
-
-
-registry.register(HearingImpaired)

Contents/Libraries/Shared/subzero/modification/__init__.py

@@ -0,0 +1,5 @@
+# coding=utf-8
+
+from registry import registry
+from mods import hearing_impaired, ocr_fixes, fps, offset, common
+from main import SubtitleModifications, SubMod

Contents/Libraries/Shared/subzero/modification/dictionaries/__init__.py

@@ -0,0 +1,3 @@
+# coding=utf-8
+
+from data import data

Contents/Libraries/Shared/subzero/modification/dictionaries/make_data.py

@@ -0,0 +1,59 @@
+# coding=utf-8
+
+import re
+import os
+import pprint
+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__))
+    xml_dir = os.path.join(cur_dir, "xml")
+    file_list = os.listdir(xml_dir)
+
+    data = {}
+
+    for fn in file_list:
+        if fn.endswith("_OCRFixReplaceList.xml"):
+            lang = fn.split("_")[0]
+            soup = BeautifulSoup(open(os.path.join(xml_dir, fn)), "xml")
+
+            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,),
+            )
+
+            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()

Contents/Libraries/Shared/subzero/modification/dictionaries/test_data.py

@@ -0,0 +1,10 @@
+# coding=utf-8
+
+from babelfish import Language
+from data import data
+
+#for lang, data in data.iteritems():
+#    print Language.fromietf(lang).alpha2
+
+for find, rep in data["dan"].iteritems():
+    print find, rep

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/dan_OCRFixReplaceList.xml

@@ -0,0 +1,638 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="Haner" to="Han er" />
+    <Word from="JaveL" to="Javel" />
+    <Word from="Pa//e" to="Palle" />
+    <Word from="bffte" to="bitte" />
+    <Word from="Utro//gt" to="Utroligt" />
+    <Word from="Kommerdu" to="Kommer du" />
+    <Word from="smi/er" to="smiler" />
+    <Word from="/eg" to="leg" />
+    <Word from="harvinger" to="har vinger" />
+    <Word from="/et" to="let" />
+    <Word from="erjeres" to="er jeres" />
+    <Word from="hardet" to="har det" />
+    <Word from="tænktjer" to="tænkt jer" />
+    <Word from="erjo" to="er jo" />
+    <Word from="sti/" to="stil" />
+    <Word from="Iappe" to="lappe" />
+    <Word from="Beklagelç" to="Beklager," />
+    <Word from="vardet" to="var det" />
+    <Word from="afden" to="af den" />
+    <Word from="snupperjeg" to="snupper jeg" />
+    <Word from="ikkejeg" to="ikke jeg" />
+    <Word from="bliverjeg" to="bliver jeg" />
+    <Word from="hartravit" to="har travlt" />
+    <Word from="pandekagef/ag" to="pandekageflag" />
+    <Word from="Stormvarsell" to="Stormvarsel!" />
+    <Word from="stormvejn" to="stormvejr." />
+    <Word from="morgenkomp/et" to="morgenkomplet" />
+    <Word from="/yv" to="lyv" />
+    <Word from="varjo" to="var jo" />
+    <Word from="/eger" to="leger" />
+    <Word from="harjeg" to="har jeg" />
+    <Word from="havdejeg" to="havde jeg" />
+    <Word from="hvorjeg" to="hvor jeg" />
+    <Word from="nårjeg" to="når jeg" />
+    <Word from="gårvi" to="går vi" />
+    <Word from="atjeg" to="at jeg" />
+    <Word from="isine" to="i sine" />
+    <Word from="fårjeg" to="får jeg" />
+    <Word from="kærtighed" to="kærlighed" />
+    <Word from="skullejeg" to="skulle jeg" />
+    <Word from="laest" to="læst" />
+    <Word from="laese" to="læse" />
+    <Word from="gørjeg" to="gør jeg" />
+    <Word from="gørvi" to="gør vi" />
+    <Word from="angrerjo" to="angrer jo" />
+    <Word from="Hvergang" to="Hver gang" />
+    <Word from="erder" to="er der" />
+    <Word from="villetilgive" to="ville tilgive" />
+    <Word from="fieme" to="fjeme" />
+    <Word from="genopståri" to="genopstår i" />
+    <Word from="svigtejer" to="svigte jer" />
+    <Word from="kommernu" to="kommer nu" />
+    <Word from="nårman" to="når man" />
+    <Word from="erfire" to="er fire" />
+    <Word from="Hvorforfinderdu" to="Hvorfor finder du" />
+    <Word from="undertigt" to="underligt" />
+    <Word from="itroen" to="i troen" />
+    <Word from="erløgnt" to="er løgn!" />
+    <Word from="gørden" to="gør den" />
+    <Word from="forhelvede" to="for helvede" />
+    <Word from="hjpe" to="hjælpe" />
+    <Word from="togeti" to="toget i" />
+    <Word from="Måjeg" to="Må jeg" />
+    <Word from="savnerjer" to="savner jer" />
+    <Word from="erjeg" to="er jeg" />
+    <Word from="vaere" to="være" />
+    <Word from="geme" to="gerne" />
+    <Word from="trorpå" to="tror på" />
+    <Word from="forham" to="for ham" />
+    <Word from="afham" to="af ham" />
+    <Word from="harjo" to="har jo" />
+    <Word from="ovemafiet" to="overnattet" />
+    <Word from="begaefiighed" to="begærlighed" />
+    <Word from="sy’g" to="syg" />
+    <Word from="Imensjeg" to="Imens jeg" />
+    <Word from="bliverdu" to="bliver du" />
+    <Word from="fiser" to="fiser" />
+    <Word from="manipuierer" to="manipulerer" />
+    <Word from="forjeg" to="for jeg" />
+    <Word from="iivgivendefor" to="livgivende for" />
+    <Word from="formig" to="for mig" />
+    <Word from="Hardu" to="Har du" />
+    <Word from="fornold" to="forhold" />
+    <Word from="defrelste" to="de frelste" />
+    <Word from="Såjeg" to="Så jeg" />
+    <Word from="varjeg" to="var jeg" />
+    <Word from="gørved" to="gør ved" />
+    <Word from="kalderjeg" to="kalder jeg" />
+    <Word from="flytte" to="flytte" />
+    <Word from="handlerdet" to="handler det" />
+    <Word from="trorjeg" to="tror jeg" />
+    <Word from="flytter" to="flytter" />
+    <Word from="soverjeg" to="sover jeg" />
+    <Word from="finderud" to="finder ud" />
+    <Word from="naboerpå" to="naboer på" />
+    <Word from="ervildt" to="er vildt" />
+    <Word from="væreher" to="være her" />
+    <Word from="hyggerjer" to="hygger jer" />
+    <Word from="borjo" to="bor jo" />
+    <Word from="kommerikke" to="kommer ikke" />
+    <Word from="folkynde" to="forkynde" />
+    <Word from="farglad" to="far glad" />
+    <Word from="misterjeg" to="mister jeg" />
+    <Word from="fint" to="fint" />
+    <Word from="Harl" to="Har I" />
+    <Word from="bedejer" to="bede jer" />
+    <Word from="synesjeg" to="synes jeg" />
+    <Word from="vartil" to="var til" />
+    <Word from="eren" to="er en" />
+    <Word from="\Al" to="Vil" />
+    <Word from="\A" to="Vi" />
+    <Word from="fjeme" to="fjerne" />
+    <Word from="Iigefyldt" to="lige fyldt" />
+    <Word from="ertil" to="er til" />
+    <Word from="fafiigt" to="farligt" />
+    <Word from="finder" to="finder" />
+    <Word from="findes" to="findes" />
+    <Word from="irettesaefielse" to="irettesættelse" />
+    <Word from="ermed" to="er med" />
+    <Word from="èn" to="én" />
+    <Word from="gikjoi" to="gik jo i" />
+    <Word from="Hvisjeg" to="Hvis jeg" />
+    <Word from="ovemafier" to="overnatter" />
+    <Word from="hoident" to="holdent" />
+    <Word from="\Adne" to="Vidne" />
+    <Word from="fori" to="for i" />
+    <Word from="vei" to="vel" />
+    <Word from="savnerjerjo" to="savner jer jo" />
+    <Word from="elskerjer" to="elsker jer" />
+    <Word from="harløjet" to="har løjet" />
+    <Word from="eri" to="er i" />
+    <Word from="fiende" to="fjende" />
+    <Word from="derjo" to="der jo" />
+    <Word from="sigerjo" to="siger jo" />
+    <Word from="menerjeg" to="mener jeg" />
+    <Word from="Harjeg" to="Har jeg" />
+    <Word from="sigerjeg" to="siger jeg" />
+    <Word from="splitterjeg" to="splitter jeg" />
+    <Word from="erjournalist" to="er journalist" />
+    <Word from="erjoumalist" to="er journalist" />
+    <Word from="Forjeg" to="For jeg" />
+    <Word from="gârjeg" to="går jeg" />
+    <Word from="Nârjeg" to="Når jeg" />
+    <Word from="afllom" to="afkom" />
+    <Word from="farerjo" to="farer jo" />
+    <Word from="tagerjeg" to="tager jeg" />
+    <Word from="Virkerjeg" to="Virker jeg" />
+    <Word from="morerjer" to="morer jer" />
+    <Word from="kommerjo" to="kommer jo" />
+    <Word from="istand" to="i stand" />
+    <Word from="bøm" to="børn" />
+    <Word from="frygterjeg" to="frygter jeg" />
+    <Word from="kommerjeg" to="kommer jeg" />
+    <Word from="eriournalistelev" to="er journalistelev" />
+    <Word from="harfat" to="har fat" />
+    <Word from="fårfingre" to="får fingre" />
+    <Word from="slârjeg" to="slår jeg" />
+    <Word from="bam" to="barn" />
+    <Word from="erjournalistelev" to="er journalistelev" />
+    <Word from="politietjo" to="politiet jo" />
+    <Word from="elskerjo" to="elsker jo" />
+    <Word from="vari" to="var i" />
+    <Word from="fornemmerjeres" to="fornemmer jeres" />
+    <Word from="udklækketl" to="udklækket!" />
+    <Word from="í" to="i" />
+    <Word from="nyi" to="ny i" />
+    <Word from="Iumijelse" to="fornøjelse" />
+    <Word from="vures" to="vores" />
+    <Word from="I/Vashíngtan" to="Washington" />
+    <Word from="opleverjeg" to="oplever jeg" />
+    <Word from="PANTELÃNER" to="PANTELÅNER" />
+    <Word from="Gudmurgen" to="Godmorgen" />
+    <Word from="SKYDEVÃBEN" to="SKYDEVÅBEN" />
+    <Word from="PÃLIDELIG" to="PÅLIDELIG" />
+    <Word from="avertalte" to="overtalte" />
+    <Word from="Omsíder" to="Omsider" />
+    <Word from="lurtebåd" to="lortebåd" />
+    <Word from="Telrslning" to="Tekstning" />
+    <Word from="miUø" to="miljø" />
+    <Word from="gåri" to="går i" />
+    <Word from="Fan/el" to="Farvel" />
+    <Word from="abefiæs" to="abefjæs" />
+    <Word from="hartalt" to="har talt" />
+    <Word from="\Årkelig" to="Virkelig" />
+    <Word from="beklagerjeg" to="beklager jeg" />
+    <Word from="Nårjeg" to="Når jeg" />
+    <Word from="rnaend" to="mænd" />
+    <Word from="vaskebjorn" to="vaskebjørn" />
+    <Word from="Ivil" to="I vil" />
+    <Word from="besog" to="besøg" />
+    <Word from="Vaer" to="Vær" />
+    <Word from="Undersogte" to="Undersøgte" />
+    <Word from="modte" to="mødte" />
+    <Word from="toj" to="tøj" />
+    <Word from="fodt" to="født" />
+    <Word from="gore" to="gøre" />
+    <Word from="provede" to="prøvede" />
+    <Word from="forste" to="første" />
+    <Word from="igang" to="i gang" />
+    <Word from="ligenu" to="lige nu" />
+    <Word from="clet" to="det" />
+    <Word from="Strombell" to="Strombel!" />
+    <Word from="tmvlt" to="travlt" />
+    <Word from="studererjournalistik" to="studerer journalistik" />
+    <Word from="inforrnererjeg" to="informerer jeg" />
+    <Word from="omkfing" to="omkring" />
+    <Word from="tilAsgård" to="til Asgård" />
+    <Word from="Kederjeg" to="Keder jeg" />
+    <Word from="jaettetamp" to="jættetamp" />
+    <Word from="erjer" to="er jer" />
+    <Word from="atjulehygge" to="at julehygge" />
+    <Word from="Ueneste" to="tjeneste" />
+    <Word from="foltsaetter" to="fortsætter" />
+    <Word from="A/ice" to="Alice" />
+    <Word from="tvivlerjeg" to="tvivler jeg" />
+    <Word from="henterjer" to="henter jer" />
+    <Word from="forstårjeg" to="forstår jeg" />
+    <Word from="hvisjeg" to="hvis jeg" />
+    <Word from="/ært" to="lært" />
+    <Word from="vfgtrgt" to="vigtigt" />
+    <Word from="hurtigtjeg" to="hurtigt jeg" />
+    <Word from="kenderjo" to="kender jo" />
+    <Word from="seiv" to="selv" />
+    <Word from="/ægehuset" to="lægehuset" />
+    <Word from="herjo" to="her jo" />
+    <Word from="stolerjeg" to="stoler jeg" />
+    <Word from="digi" to="dig i" />
+    <Word from="taberi" to="taber i" />
+    <Word from="slårjeres" to="slår jeres" />
+    <Word from="laere" to="lære" />
+    <Word from="trænerwushu" to="træner wushu" />
+    <Word from="efterjeg" to="efter jeg" />
+    <Word from="efier" to="efter" />
+    <Word from="dui" to="du i" />
+    <Word from="afien" to="aften" />
+    <Word from="bliveri" to="bliver i" />
+    <Word from="acceptererjer" to="accepterer jer" />
+    <Word from="drikkerjo" to="drikker jo" />
+    <Word from="fianjin" to="Tianjin" />
+    <Word from="erlænge" to="er længe" />
+    <Word from="erikke" to="er ikke" />
+    <Word from="medjer" to="med jer" />
+    <Word from="Tmykke" to="Tillykke" />
+    <Word from="'fianjins" to="Tianjins" />
+    <Word from="Mesteri" to="Mester i" />
+    <Word from="sagdetil" to="sagde til" />
+    <Word from="indei" to="inde i" />
+    <Word from="ofie" to="ofte" />
+    <Word from="'filgiv" to="Tilgiv" />
+    <Word from="Lfår" to="I får" />
+    <Word from="viserjer" to="viser jer" />
+    <Word from="Rejsjerblot" to="Rejs jer blot" />
+    <Word from="'fillad" to="Tillad" />
+    <Word from="iiiiefinger" to="lillefinger" />
+    <Word from="VILOMFATTE" to="VIL OMFATTE" />
+    <Word from="mofio" to="motto" />
+    <Word from="gørjer" to="gør jer" />
+    <Word from="gifi" to="gift" />
+    <Word from="hardu" to="har du" />
+    <Word from="gifi" to="gift" />
+    <Word from="Iaeggerjeg" to="lægger jeg" />
+    <Word from="iet" to="i et" />
+    <Word from="sv/yte" to="svigte" />
+    <Word from="ti/" to="til" />
+    <Word from="Wdal" to="Vidal" />
+    <Word from="fiået" to="fået" />
+    <Word from="Hvo/for" to="Hvorfor" />
+    <Word from="hellerikke" to="heller ikke" />
+    <Word from="Wlle" to="Ville" />
+    <Word from="dr/ver" to="driver" />
+    <Word from="V\fllliam" to="William" />
+    <Word from="V\fllliams" to="Williams" />
+    <Word from="Vkfilliam" to="William" />
+    <Word from="vådejakke" to="våde jakke" />
+    <Word from="kæfll" to="kæft!" />
+    <Word from="sagdejeg" to="sagde jeg" />
+    <Word from="oven/ejet" to="overvejet" />
+    <Word from="karameisauce" to="karamelsauce" />
+    <Word from="Lfølgejødisk" to="Ifølge jødisk" />
+    <Word from="blevjo" to="blev jo" />
+    <Word from="asiateri" to="asiater i" />
+    <Word from="erV\fllliam" to="er William" />
+    <Word from="lidtflov" to="lidt flov" />
+    <Word from="sagdejo" to="sagde jo" />
+    <Word from="erlige" to="er lige" />
+    <Word from="Vtfilliam" to="William" />
+    <Word from="WfiII" to="Will" />
+    <Word from="afldarede" to="afklarede" />
+    <Word from="hjæiperjeg" to="hjælper jeg" />
+    <Word from="laderjeg" to="lader jeg" />
+    <Word from="Hândledsbeskyttere" to="Håndledsbeskyttere" />
+    <Word from="Lsabels" to="Isabels" />
+    <Word from="Gørjeg" to="Gør jeg" />
+    <Word from="mâjeg" to="må jeg" />
+    <Word from="ogjeg" to="og jeg" />
+    <Word from="gjordejeg" to="gjorde jeg" />
+    <Word from="villejeg" to="ville jeg" />
+    <Word from="Vlfllliams" to="Williams" />
+    <Word from="Dajeg" to="Da jeg" />
+    <Word from="iorden" to="i orden" />
+    <Word from="fandtjeg" to="fandt jeg" />
+    <Word from="Tilykke" to="Tillykke" />
+    <Word from="kørerjer" to="kører jer" />
+    <Word from="gøfjeg" to="gør jeg" />
+    <Word from="Selvflgelig" to="Selvfølgelig" />
+    <Word from="fdder" to="fadder" />
+    <Word from="bnfaldt" to="bønfaldt" />
+    <Word from="t\/ehovedede" to="tvehovedede" />
+    <Word from="EIler" to="Eller" />
+    <Word from="ringerjeg" to="ringer jeg" />
+    <Word from="blevvæk" to="blev væk" />
+    <Word from="stárjeg" to="står jeg" />
+    <Word from="varforbi" to="var forbi" />
+    <Word from="harfortalt" to="har fortalt" />
+    <Word from="iflere" to="i flere" />
+    <Word from="tørjeg" to="tør jeg" />
+    <Word from="kunnejeg" to="kunne jeg" />
+    <Word from="má" to="må" />
+    <Word from="hartænkt" to="har tænkt" />
+    <Word from="Fárjeg" to="Får jeg" />
+    <Word from="afdelingervar" to="afdelinger var" />
+    <Word from="0rd" to="ord" />
+    <Word from="pástá" to="påstå" />
+    <Word from="gráharet" to="gråharet" />
+    <Word from="varforbløffende" to="var forbløffende" />
+    <Word from="holdtjeg" to="holdt jeg" />
+    <Word from="hængerjo" to="hænger jo" />
+    <Word from="fikjeg" to="fik jeg" />
+    <Word from="fár" to="får" />
+    <Word from="Hvorforfølerjeg" to="Hvorfor føler jeg" />
+    <Word from="harfeber" to="har feber" />
+    <Word from="ándssvagt" to="åndssvagt" />
+    <Word from="0g" to="Og" />
+    <Word from="vartre" to="var tre" />
+    <Word from="abner" to="åbner" />
+    <Word from="garjeg" to="går jeg" />
+    <Word from="sertil" to="ser til" />
+    <Word from="hvorfin" to="hvor fin" />
+    <Word from="harfri" to="har fri" />
+    <Word from="forstarjeg" to="forstår jeg" />
+    <Word from="Sä" to="Så" />
+    <Word from="hvorfint" to="hvor fint" />
+    <Word from="mærkerjeg" to="mærker jeg" />
+    <Word from="ogsa" to="også" />
+    <Word from="nárjeg" to="når jeg" />
+    <Word from="Jasá" to="Jaså" />
+    <Word from="bándoptager" to="båndoptager" />
+    <Word from="bedárende" to="bedårende" />
+    <Word from="sá" to="så" />
+    <Word from="nár" to="når" />
+    <Word from="kunnejo" to="kunne jo" />
+    <Word from="Brammertil" to="Brammer til" />
+    <Word from="serjeg" to="ser jeg" />
+    <Word from="gikjeg" to="gik jeg" />
+    <Word from="udholderjeg" to="udholder jeg" />
+    <Word from="máneder" to="måneder" />
+    <Word from="vartræt" to="var træt" />
+    <Word from="dárligt" to="dårligt" />
+    <Word from="klaretjer" to="klaret jer" />
+    <Word from="pavirkelig" to="påvirkelig" />
+    <Word from="spekulererjeg" to="spekulerer jeg" />
+    <Word from="forsøgerjeg" to="forsøger jeg" />
+    <Word from="huskerjeg" to="husker jeg" />
+    <Word from="ifavnen" to="i favnen" />
+    <Word from="skullejo" to="skulle jo" />
+    <Word from="vartung" to="var tung" />
+    <Word from="varfuldstændig" to="var fuldstændig" />
+    <Word from="Paskedag" to="Påskedag" />
+    <Word from="turi" to="tur i" />
+    <Word from="spillerschumanns" to="spiller Schumanns" />
+    <Word from="forstárjeg" to="forstår jeg" />
+    <Word from="istedet" to="i stedet" />
+    <Word from="nárfrem" to="når frem" />
+    <Word from="habertrods" to="håber trods" />
+    <Word from="forførste" to="for første" />
+    <Word from="varto" to="var to" />
+    <Word from="overtil" to="over til" />
+    <Word from="forfem" to="for fem" />
+    <Word from="holdtjo" to="holdt jo" />
+    <Word from="passerjo" to="passer jo" />
+    <Word from="ellerto" to="eller to" />
+    <Word from="hartrods" to="har trods" />
+    <Word from="harfuldstændig" to="har fuldstændig" />
+    <Word from="gårjeg" to="går jeg" />
+    <Word from="giderjeg" to="gider jeg" />
+    <Word from="forjer" to="for jer" />
+    <Word from="erindrerjeg" to="erindrer jeg" />
+    <Word from="tænkerjeg" to="tænker jeg" />
+    <Word from="GAEt" to="GÅET" />
+    <Word from="hørerjo" to="hører jo" />
+    <Word from="forladerjeg" to="forlader jeg" />
+    <Word from="kosterjo" to="koster jo" />
+    <Word from="fortællerjeg" to="fortæller jeg" />
+    <Word from="Forstyrrerjeg" to="Forstyrrer jeg" />
+    <Word from="tjekkerjeg" to="tjekker jeg" />
+    <Word from="erjurist" to="er jurist" />
+    <Word from="tlLBUD" to="TILBUD" />
+    <Word from="serjo" to="se rjo" />
+    <Word from="bederjeg" to="beder jeg" />
+    <Word from="bilderjeg" to="bilder jeg" />
+    <Word from="ULVEtlME" to="ULVETlME" />
+    <Word from="skærerjo" to="skærer jo" />
+    <Word from="afjer" to="af jer" />
+    <Word from="ordnerjeg" to="ordner jeg" />
+    <Word from="giverjeg" to="giver jeg" />
+    <Word from="rejservi" to="rejser vi" />
+    <Word from="fangerjeg" to="fanger jeg" />
+    <Word from="erjaloux" to="er jaloux" />
+    <Word from="glemmerjeg" to="glemmer jeg" />
+    <Word from="Behøverjeg" to="Behøver jeg" />
+    <Word from="harvi" to="har vi" />
+    <Word from="ertyndere" to="er tyndere" />
+    <Word from="fårtordenvejr" to="får tordenvejr" />
+    <Word from="varfærdig" to="var færdig" />
+    <Word from="hørerfor" to="hører for" />
+    <Word from="varvel" to="var vel" />
+    <Word from="erforbi" to="er forbi" />
+    <Word from="AIle" to="Alle" />
+    <Word from="læserjo" to="læser jo" />
+    <Word from="Edgarer" to="Edgar er" />
+    <Word from="hartaget" to="har taget" />
+    <Word from="derer" to="der er" />
+    <Word from="stikkerfrem" to="stikker frem" />
+    <Word from="haraldrig" to="har aldrig" />
+    <Word from="ellerfar" to="eller far" />
+    <Word from="erat" to="er at" />
+    <Word from="turtil" to="tur til" />
+    <Word from="erfærdig" to="er færdig" />
+    <Word from="følerjeg" to="føler jeg" />
+    <Word from="jerfra" to="jer fra" />
+    <Word from="eralt" to="er alt" />
+    <Word from="harfaktisk" to="har faktisk" />
+    <Word from="harfundet" to="har fundet" />
+    <Word from="harvendt" to="har vendt" />
+    <Word from="Kunstneraf" to="Kunstner af" />
+    <Word from="ervel" to="er vel" />
+    <Word from="ståransigt" to="står ansigt" />
+    <Word from="Erjeg" to="Er jeg" />
+    <Word from="venterjeg" to="venter jeg" />
+    <Word from="Hvorvar" to="Hvor var" />
+    <Word from="varfint" to="var fint" />
+    <Word from="ervarmt" to="er varmt" />
+    <Word from="gårfint" to="går fint" />
+    <Word from="flyverforbi" to="flyver forbi" />
+    <Word from="Dervar" to="Der var" />
+    <Word from="dervar" to="der var" />
+    <Word from="meneråndeligt" to="mener åndeligt" />
+    <Word from="forat" to="for at" />
+    <Word from="herovertil" to="herover til" />
+    <Word from="soverfor" to="sover for" />
+    <Word from="begyndtejeg" to="begyndte jeg" />
+    <Word from="vendertilbage" to="vender tilbage" />
+    <Word from="erforfærdelig" to="er forfærdelig" />
+    <Word from="gøraltid" to="gør altid" />
+    <Word from="ertilbage" to="er tilbage" />
+    <Word from="harværet" to="har været" />
+    <Word from="bagoverellertil" to="bagover eller til" />
+    <Word from="hertaler" to="her taler" />
+    <Word from="vågnerjeg" to="vågner jeg" />
+    <Word from="vartomt" to="var tomt" />
+    <Word from="gårfrem" to="går frem" />
+    <Word from="talertil" to="taler til" />
+    <Word from="ertryg" to="er tryg" />
+    <Word from="ansigtervendes" to="ansigter vendes" />
+    <Word from="hervirkeligt" to="her virkeligt" />
+    <Word from="herer" to="her er" />
+    <Word from="drømmerjo" to="drømmer jo" />
+    <Word from="erfuldkommen" to="er fuldkommen" />
+    <Word from="hveren" to="hver en" />
+    <Word from="erfej" to="er fej" />
+    <Word from="datterforgæves" to="datter forgæves" />
+    <Word from="forsøgerjo" to="forsøger jo" />
+    <Word from="ertom" to="er tom" />
+    <Word from="vareftermiddag" to="var eftermiddag" />
+    <Word from="vartom" to="var tom" />
+    <Word from="angerellerforventninger" to="anger eller forventninger" />
+    <Word from="kørtejeg" to="kørte jeg" />
+    <Word from="Hvorforfortæller" to="Hvorfor fortæller" />
+    <Word from="gårtil" to="går til" />
+    <Word from="ringerefter" to="ringer efter" />
+    <Word from="søgertilflugt" to="søger tilflugt" />
+    <Word from="ertvunget" to="er tvunget" />
+    <Word from="megetjeg" to="meget jeg" />
+    <Word from="varikke" to="var ikke" />
+    <Word from="Derermange" to="Der e rmange" />
+    <Word from="dervilhindre" to="der vil hindre" />
+    <Word from="erså" to="er så" />
+    <Word from="DetforstårLeggodt" to="Det forstår jeg godt" />
+    <Word from="ergodt" to="er godt" />
+    <Word from="vorventen" to="vor venten" />
+    <Word from="tagerfejl" to="tager fejl" />
+    <Word from="ellerer" to="eller er" />
+    <Word from="laverjeg" to="laver jeg" />
+    <Word from="0mgang" to="omgang" />
+    <Word from="afstár" to="afstår" />
+    <Word from="pá" to="på" />
+    <Word from="rejserjeg" to="rejser jeg" />
+    <Word from="ellertage" to="eller tage" />
+    <Word from="takkerjeg" to="takker jeg" />
+    <Word from="ertilfældigvis" to="er tilfældigvis" />
+    <Word from="fremstar" to="fremstår" />
+    <Word from="ertæt" to="er tæt" />
+    <Word from="ijeres" to="i jeres" />
+    <Word from="Sagdejeg" to="Sagde jeg" />
+    <Word from="overi" to="over i" />
+    <Word from="plukkerjordbær" to="plukker jordbær" />
+    <Word from="klarerjeg" to="klarer jeg" />
+    <Word from="jerfire" to="jer fire" />
+    <Word from="tábeligste" to="tåbeligste" />
+    <Word from="sigertvillingerne" to="siger tvillingerne" />
+    <Word from="erfaktisk" to="er faktisk" />
+    <Word from="gár" to="går" />
+    <Word from="harvasket" to="har vasket" />
+    <Word from="harplukketjordbærtil" to="har plukket jordbær til" />
+    <Word from="plukketjordbær" to="plukket jordbær" />
+    <Word from="klaverfirehændigt" to="klaver firehændigt" />
+    <Word from="erjævnaldrende" to="er jævnaldrende" />
+    <Word from="tierjeg" to="tier jeg" />
+    <Word from="Hvorerden" to="Hvor er den" />
+    <Word from="0veraltjeg" to="overalt jeg" />
+    <Word from="gårpå" to="går på" />
+    <Word from="finderjeg" to="finder jeg" />
+    <Word from="serhans" to="ser hans" />
+    <Word from="tiderbliver" to="tider bliver" />
+    <Word from="ellertrist" to="eller trist" />
+    <Word from="forstårjeres" to="forstår jeres" />
+    <Word from="Hvorsjælen" to="Hvor sjælen" />
+    <Word from="finderro" to="finder ro" />
+    <Word from="sidderjeg" to="sidder jeg" />
+    <Word from="tagerjo" to="tager jo" />
+    <Word from="efterjeres" to="efter jeres" />
+    <Word from="10O" to="100" />
+    <Word from="besluttedejeg" to="besluttede jeg" />
+    <Word from="varsket" to="var sket" />
+    <Word from="uadskillige" to="uadskillelige" />
+    <Word from="harjetlag" to="har jetlag" />
+    <Word from="lkke" to="Ikke" />
+    <Word from="lntet" to="Intet" />
+    <Word from="afslørerjeg" to="afslører jeg" />
+    <Word from="måjeg" to="må jeg" />
+    <Word from="Vl" to="VI" />
+    <Word from="atbygge" to="at bygge" />
+    <Word from="detmakabre" to="det makabre" />
+    <Word from="vilikke" to="vil ikke" />
+    <Word from="talsmandbekræfter" to="talsmand bekræfter" />
+    <Word from="vedatrenovere" to="ved at renovere" />
+    <Word from="forsøgeratforstå" to="forsøger at forstå" />
+    <Word from="ersket" to="er sket" />
+    <Word from="morderpå" to="morder på" />
+    <Word from="frifodiRosewood" to="fri fod i Rosewood" />
+    <Word from="holdtpressemøde" to="holdt pressemøde" />
+    <Word from="lngen" to="Ingen" />
+    <Word from="lND" to="IND" />
+    <Word from="henterjeg" to="henter jeg" />
+    <Word from="lsabel" to="Isabel" />
+    <Word from="lsabels" to="Isabels" />
+    <Word from="vinderjo" to="vinder jo" />
+    <Word from="rødmerjo" to="rødmer jo" />
+    <Word from="etjakkesæt" to="et jakkesæt" />
+    <Word from="glæderjeg" to="glæder jeg" />
+    <Word from="lgen" to="Igen" />
+    <Word from="lsær" to="Især" />
+    <Word from="iparken" to="i parken" />
+    <Word from="nårl" to="når I" />
+    <Word from="tilA1" to="til A1" />
+    <Word from="FBl" to="FBI" />
+    <Word from="viljo" to="vil jo" />
+    <Word from="detpå" to="det på" />
+    <Word from="KIar" to="Klar" />
+    <Word from="PIan" to="Plan" />
+    <Word from="EIIer" to="Eller" />
+    <Word from="FIot" to="Flot" />
+    <Word from="AIIe" to="Alle" />
+    <Word from="AIt" to="Alt" />
+    <Word from="KIap" to="Klap" />
+    <Word from="PIaza" to="Plaza" />
+    <Word from="SIap" to="Slap" />
+    <Word from="Iå" to="lå" />
+    <Word from="BIing" to="Bling" />
+    <Word from="GIade" to="Glade" />
+    <Word from="Iejrbålssange" to="lejrbålssange" />
+    <Word from="bedtjer" to="bedt jer" />
+    <Word from="hørerjeg" to="hører jeg" />
+    <Word from="Fårjeg" to="Får jeg" />
+    <Word from="fikJames" to="fik James" />
+    <Word from="atsnakke" to="at snakke" />
+    <Word from="varkun" to="var kun" />
+    <Word from="retterjeg" to="retter jeg" />
+    <Word from="ernormale" to="er normale" />
+    <Word from="viljeg" to="vil jeg" />
+    <Word from="Sætjer" to="Sæt jer" />
+    <Word from="udsatham" to="udsat ham" />
+  </WholeWords>
+  <PartialWordsAlways>
+    <WordPart from="¤" to="o" />
+    <WordPart from="IVI" to="M" />
+    <WordPart from="lVI" to="M" />
+    <WordPart from="IVl" to="M" />
+    <WordPart from="lVl" to="M" />
+  </PartialWordsAlways>
+  <PartialWords>
+    <!-- Will be used to check words not in dictionary -->
+    <!-- If new word(s) exists in spelling dictionary, it(they) is accepted -->
+    <WordPart from="fi" to="fi" />
+    <WordPart from="fl" to="fl" />
+    <WordPart from="/" to="l" />
+    <WordPart from="vv" to="w" />
+    <WordPart from="m" to="rn" />
+    <WordPart from="l" to="i" />
+    <WordPart from="€" to="e" />
+    <WordPart from="I" to="l" />
+    <WordPart from="c" to="o" />
+    <WordPart from="i" to="t" />
+    <WordPart from="cc" to="oo" />
+    <WordPart from="ii" to="tt" />
+    <WordPart from="n/" to="ry" />
+    <WordPart from="ae" to="æ" />
+    <!-- "f " will be two words -->
+    <WordPart from="f" to="f " />
+    <WordPart from="c" to="e" />
+    <WordPart from="o" to="e" />
+    <WordPart from="I" to="t" />
+    <WordPart from="n" to="o" />
+    <WordPart from="s" to="e" />
+    <WordPart from="\A" to="Vi" />
+    <WordPart from="n/" to="rv" />
+    <WordPart from="Ã" to="Å" />
+    <WordPart from="í" to="i" />
+  </PartialWords>
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions />
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/fra_OCRFixReplaceList.xml

@@ -0,0 +1,270 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="@immatriculation" to="d'immatriculation" />
+    <Word from="acquer" to="acquér" />
+    <Word from="acteurjoue" to="acteur joue" />
+    <Word from="aerien" to="aérien" />
+    <Word from="agreable" to="agréable" />
+    <Word from="aientjamais" to="aient jamais" />
+    <Word from="AII" to="All" />
+    <Word from="aitjamais" to="ait jamais" />
+    <Word from="aitjus" to="ait jus" />
+    <Word from="alle" to="allé" />
+    <Word from="alles" to="allés" />
+    <Word from="appele" to="appelé" />
+    <Word from="apres" to="après" />
+    <Word from="aujourdhui" to="aujourd'hui" />
+    <Word from="aupres" to="auprès" />
+    <Word from="beaute" to="beauté" />
+    <Word from="cabossee" to="cabossée" />
+    <Word from="carj'" to="car j'" />
+    <Word from="Carj'" to="Car j'" />
+    <Word from="carla" to="car la" />
+    <Word from="CEdipe" to="Œdipe" />
+    <Word from="Cest" to="C'est" />
+    <Word from="c'etaient" to="c'étaient" />
+    <Word from="Cétaient" to="C'étaient" />
+    <Word from="c'etait" to="c'était" />
+    <Word from="C'etait" to="C'était" />
+    <Word from="Cétait" to="C'était" />
+    <Word from="choregraphiee" to="chorégraphiée" />
+    <Word from="cinema" to="cinéma" />
+    <Word from="cl'AIcatraz" to="d'Alcatraz" />
+    <Word from="cles" to="clés" />
+    <Word from="cœurjoie" to="cœur-joie" />
+    <Word from="completer" to="compléter" />
+    <Word from="costumiere" to="costumière" />
+    <Word from="cree" to="créé" />
+    <Word from="daccord" to="d'accord" />
+    <Word from="d'AIbert" to="d'Albert" />
+    <Word from="d'AIdous" to="d'Aldous" />
+    <Word from="d'AIec" to="d'Alec" />
+    <Word from="danniversaire" to="d'anniversaire" />
+    <Word from="d'Arra'bida" to="d'Arrabida" />
+    <Word from="d'autodérision" to="d'auto-dérision" />
+    <Word from="dautres" to="d'autres" />
+    <Word from="debattait" to="débattait" />
+    <Word from="decor" to="décor" />
+    <Word from="decorateurs" to="décorateurs" />
+    <Word from="decors" to="décors" />
+    <Word from="defi" to="défi" />
+    <Word from="dejà" to="déjà" />
+    <Word from="déjàm" to="déjà..." />
+    <Word from="dejeunait" to="déjeunait" />
+    <Word from="dengager" to="d'engager" />
+    <Word from="déquipement" to="d'équipement" />
+    <Word from="dérnièré" to="dernière" />
+    <Word from="Desole" to="Désolé" />
+    <Word from="dessayage" to="d'essayage" />
+    <Word from="dessence" to="d'essence" />
+    <Word from="détaient" to="c'étaient" />
+    <Word from="detail" to="détail" />
+    <Word from="dexcellents" to="d'excellents" />
+    <Word from="dexpérience" to="d'expérience" />
+    <Word from="dexpériences" to="d'expériences" />
+    <Word from="d'héro'l'ne" to="d'héroïne" />
+    <Word from="d'idees" to="d'idées" />
+    <Word from="d'intensite" to="d'intensité" />
+    <Word from="dontj" to="dont j" />
+    <Word from="doublaitAlfo" to="doublait Alfo" />
+    <Word from="DrNo" to="Dr No" />
+    <Word from="e'" to="é" />
+    <Word from="ecrit" to="écrit" />
+    <Word from="elegant" to="élégant" />
+    <Word from="Ellé" to="Elle" />
+    <Word from="én" to="en" />
+    <Word from="equipe" to="équipe" />
+    <Word from="erjus" to="er jus" />
+    <Word from="estjamais" to="est jamais" />
+    <Word from="ét" to="et" />
+    <Word from="etaient" to="étaient" />
+    <Word from="etait" to="était" />
+    <Word from="ete" to="été" />
+    <Word from="etiez" to="étiez" />
+    <Word from="etj'" to="et j'" />
+    <Word from="Etj'" to="Et j'" />
+    <Word from="etje" to="et je" />
+    <Word from="Etje" to="Et je" />
+    <Word from="EtsouvenL" to="Et souvent" />
+    <Word from="eviter" to="éviter" />
+    <Word from="Fabsence" to="l'absence" />
+    <Word from="fadapter" to="t'adapter" />
+    <Word from="fadore" to="j'adore" />
+    <Word from="Fâge" to="l'âge" />
+    <Word from="Fagent" to="l'agent" />
+    <Word from="faiessayé" to="j'ai essayé" />
+    <Word from="Failure" to="l'alllure" />
+    <Word from="Fambiance" to="l'ambiance" />
+    <Word from="Famener" to="l'amener" />
+    <Word from="Fanniversaire" to="l'anniversaire" />
+    <Word from="Fapparence" to="l'apparence" />
+    <Word from="Fapres" to="l'apres" />
+    <Word from="Faprès" to="l'après" />
+    <Word from="Farmée" to="l'armée" />
+    <Word from="Farrière" to="l'arrière" />
+    <Word from="Farrivée" to="l'arrivée" />
+    <Word from="Fascenseur" to="l'ascenseur" />
+    <Word from="Fascension" to="l'ascension" />
+    <Word from="Fassaut" to="l'assaut" />
+    <Word from="Fassomme" to="l'assomme" />
+    <Word from="Fatmosphère" to="l'atmosphère" />
+    <Word from="Fattention" to="l'attention" />
+    <Word from="Favalanche" to="l'avalanche" />
+    <Word from="Féclairage" to="l'éclairage" />
+    <Word from="Fécran" to="l'écran" />
+    <Word from="Fémotion" to="l'émotion" />
+    <Word from="Femplacement" to="l'emplacement" />
+    <Word from="Fendroit" to="l'endroit" />
+    <Word from="Fenseigne" to="l'enseigne" />
+    <Word from="Fensemble" to="l'ensemble" />
+    <Word from="Fentouraient" to="l'entouraient" />
+    <Word from="Fentrée" to="l'entrée" />
+    <Word from="Fépaisseur" to="l'épaisseur" />
+    <Word from="Fépoque" to="l'époque" />
+    <Word from="Féquipe" to="Équipe" />
+    <Word from="Fespace" to="l'espace" />
+    <Word from="fespérais" to="j'espérais" />
+    <Word from="Fespère" to="l'espère" />
+    <Word from="Festhétique" to="l'esthétique" />
+    <Word from="Fetranger" to="l'etranger" />
+    <Word from="Févasion" to="l'évasion" />
+    <Word from="Févoque" to="l'évoque" />
+    <Word from="Fexpérience" to="l'expérience" />
+    <Word from="Fexplique" to="l'explique" />
+    <Word from="Fexplosion" to="l'explosion" />
+    <Word from="Fextérieur" to="l'extérieur" />
+    <Word from="Fhabituelle" to="l'habituelle" />
+    <Word from="Fhélicoptère" to="l'hélicoptère" />
+    <Word from="Fhéliport" to="l'héliport" />
+    <Word from="Fhélistation" to="l'hélistation" />
+    <Word from="Fhonneur" to="l'honneur" />
+    <Word from="Fhorloge" to="l'horloge" />
+    <Word from="Fidée" to="l'idée" />
+    <Word from="Fimage" to="l'image" />
+    <Word from="Fimportance" to="l'importance" />
+    <Word from="Fimpression" to="l'impression" />
+    <Word from="Finfluence" to="l'influence" />
+    <Word from="Finscription" to="l'inscription" />
+    <Word from="Fintérieur" to="l'intérieur" />
+    <Word from="Fintrigue" to="l'intrigue" />
+    <Word from="Fobjectif" to="l'objectif" />
+    <Word from="Foccasion" to="l'occasion" />
+    <Word from="Fordre" to="l'ordre" />
+    <Word from="Forigine" to="l'origine" />
+    <Word from="frêre" to="frère" />
+    <Word from="gaylns" to="gaijins" />
+    <Word from="general" to="général" />
+    <Word from="hawaïennel" to="hawaïenne" />
+    <Word from="hawa'l'en" to="hawaïen" />
+    <Word from="Ia" to="la" />
+    <Word from="Ià" to="là" />
+    <Word from="Iaryngotomie" to="laryngotomie" />
+    <Word from="idee" to="idée" />
+    <Word from="idees" to="idées" />
+    <Word from="Ie" to="le" />
+    <Word from="Ies" to="les" />
+    <Word from="Iester" to="Lester" />
+    <Word from="II" to="Il" />
+    <Word from="Iimit" to="limit" />
+    <Word from="IIs" to="Ils" />
+    <Word from="immediatement" to="immédiatement" />
+    <Word from="insufflee" to="insufflée" />
+    <Word from="integrer" to="intégrer" />
+    <Word from="interessante" to="intéressante" />
+    <Word from="Iogions" to="logions" />
+    <Word from="Iorsqu" to="lorsqu" />
+    <Word from="isee" to="isée" />
+    <Word from="Iumiere" to="lumiere" />
+    <Word from="Iynchage" to="lynchage" />
+    <Word from="J'espere" to="J'espère" />
+    <Word from="Jessaie" to="J'essaie" />
+    <Word from="j'etais" to="j'étais" />
+    <Word from="J'etais" to="J'étais" />
+    <Word from="latéralémént" to="latéralement" />
+    <Word from="lci" to="Ici" />
+    <Word from="Lci" to="Ici" />
+    <Word from="lé-" to="là-" />
+    <Word from="lepidopteres" to="lépidoptères" />
+    <Word from="litteraire" to="littéraire" />
+    <Word from="ll" to="il" />
+    <Word from="Ll" to="Il" />
+    <Word from="lls" to="ils" />
+    <Word from="Lls" to="Ils" />
+    <Word from="maintenanu" to="maintenant" />
+    <Word from="maniere" to="manière" />
+    <Word from="mariee" to="mariée" />
+    <Word from="Mayer/ing" to="Mayerling" />
+    <Word from="meilleurjour" to="meilleur jour" />
+    <Word from="melange" to="mélange" />
+    <Word from="n'avaiént" to="n'avaient" />
+    <Word from="n'etait" to="n'était" />
+    <Word from="oitjamais" to="oit jamais" />
+    <Word from="oitjus" to="oit jus" />
+    <Word from="ontete" to="ont été" />
+    <Word from="operateur" to="opérateur" />
+    <Word from="ouvérté" to="ouverte" />
+    <Word from="Pépreuve" to="l'épreuve" />
+    <Word from="pere" to="père" />
+    <Word from="plateforme" to="plate-forme" />
+    <Word from="pourjouer" to="pour jouer" />
+    <Word from="precipice" to="précipice" />
+    <Word from="preferes" to="préférés" />
+    <Word from="premierjour" to="premier jour" />
+    <Word from="presenter" to="présenter" />
+    <Word from="prevu" to="prévu" />
+    <Word from="prevue" to="prévue" />
+    <Word from="propriete" to="propriété" />
+    <Word from="protègeraient" to="protégeraient" />
+    <Word from="qué" to="que" />
+    <Word from="qwangoissé" to="qu'angoissé" />
+    <Word from="realisateur" to="réalisateur" />
+    <Word from="reception" to="réception" />
+    <Word from="reévalu" to="réévalu" />
+    <Word from="repute" to="réputé" />
+    <Word from="reussi" to="réussi" />
+    <Word from="s'arrétait" to="s'arrêtait" />
+    <Word from="s'ave'rer" to="s'avérer" />
+    <Word from="scenario" to="scénario" />
+    <Word from="scene" to="scène" />
+    <Word from="scenes" to="scènes" />
+    <Word from="seances" to="séances" />
+    <Word from="sequence" to="séquence" />
+    <Word from="sflécrasa" to="s'écrasa" />
+    <Word from="speciale" to="spéciale" />
+    <Word from="Supen" to="Super" />
+    <Word from="torturee" to="torturée" />
+    <Word from="Uadmirable" to="L'admirable" />
+    <Word from="Uensemblier" to="L'ensemblier" />
+    <Word from="Uexplosion" to="L'explosion" />
+    <Word from="Uouvre" to="L'ouvre" />
+    <Word from="Vaise" to="l'aise" />
+    <Word from="vecu" to="vécu" />
+    <Word from="vehicules" to="véhicules" />
+    <Word from="Ÿappréciais" to="J'appréciais" />
+    <Word from="Ÿespère" to="J'espère" />
+    <Word from="ÿétrangle" to="s'étrangle" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords />
+  <PartialLines>
+    <LinePart from=" I'" to=" l'" />
+    <LinePart from=" |'" to=" l'" />
+  </PartialLines>
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines>
+    <Line from="&quot;D'ac:c:ord.&quot;" to="&quot;D'accord.&quot;" />
+    <Line from="“i QUÎ gagne, qui perd," to="ni qui gagne, qui perd," />
+    <Line from="L'ac:c:ent est mis &#xD;&#xA; &#xD;&#xA; sur son trajet jusqu'en Suisse." to="L'accent est mis &#xD;&#xA; &#xD;&#xA; sur son trajet jusqu'en Suisse." />
+    <Line from="C'est la plus gentille chose &#xD;&#xA; &#xD;&#xA; qu'Hitchc:oc:k m'ait jamais dite." to="C'est la plus gentille chose &#xD;&#xA; &#xD;&#xA; qu'Hitchcock m'ait jamais dite." />
+    <Line from="Tout le monde, en revanche, qualifie &#xD;&#xA; &#xD;&#xA; Goldfinger d'aventu re structurée," to="Tout le monde, en revanche, qualifie &#xD;&#xA; &#xD;&#xA; Goldfinger d'aventure structurée," />
+    <Line from="et le film Shadow of a man &#xD;&#xA; &#xD;&#xA; a lancé sa carrière au cinéma." to="et le film &lt;i&gt;Shadow of a man&lt;/i&gt; &#xD;&#xA; &#xD;&#xA; a lancé sa carrière au cinéma." />
+    <Line from="En 1948, Young est passé à la réalisation &#xD;&#xA; &#xD;&#xA; avec One night with you." to="En 1948, Young est passé à la réalisation &#xD;&#xA; &#xD;&#xA; avec &lt;i&gt;One night with you&lt;/i&gt;." />
+    <Line from="Il a construit tous ces véhicules &#xD;&#xA; &#xD;&#xA; à C)c:ala, en Floride." to="Il a construit tous ces véhicules &#xD;&#xA; &#xD;&#xA; à Ocala, en Floride." />
+    <Line from="Tokyo Pop et A Taxing Woman? Return." to="Tokyo Pop et A Taxing Woman's Return." />
+    <Line from="Peter H u nt." to="Peter Hunt." />
+    <Line from="&quot;C'est bien mieux dans Peau. &#xD;&#xA; &#xD;&#xA; On peut sfléclabousser, faire du bruit.&quot;" to="&quot;C'est bien mieux dans l'eau. &#xD;&#xA; &#xD;&#xA; On peut s'éclabousser, faire du bruit.&quot;" />
+  </WholeLines>
+  <RegularExpressions />
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/hun_OCRFixReplaceList.xml

@@ -0,0 +1,25 @@
+<OCRFixReplaceList>
+  <WholeWords />
+  <PartialWordsAlways />
+  <PartialWords />
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions>
+    <!-- nagy I-l javítások -->
+    <RegEx find="([\x41-\x5a\x61-\x7a\xc1-\xfc])II" replaceWith="$1ll" />
+    <RegEx find="II([\x61-\x7a\xe1-\xfc])" replaceWith="ll$1" />
+    <RegEx find="([\x61-\x7a\xe1-\xfc])I" replaceWith="$1l" />
+    <RegEx find="([\x20])I([^aeou\x41-\x5a\xc1-\xdc])" replaceWith="$1l$2" />
+    <RegEx find="\bl([bcdfghjklmnpqrstvwxz])" replaceWith="I$1" />
+    <RegEx find="([\x41-\x5a\xc1-\xdc])I([\x61-\x7a\xe1-\xfc])" replaceWith="$1l$2" />
+    <RegEx find="([\x61-\x7a\xe1-\xfc][\-])I([\x61-\x7a\xe1-\xfc])" replaceWith="$1l$2" />
+    <RegEx find="([\x41-\x5a\xc1-\xdc])I([\-][\x41-\x5a\xc1-\xdc][\x61-\x7a\xe1-\xfc])" replaceWith="$1l$2" />
+    <RegEx find="\b([AEÜÓ])I([^\x41-\x5a\xc1-\xdc])" replaceWith="$1l$2" />
+    <RegEx find="\bI([aáeéiíoóöuúüy\xf5\xfb])" replaceWith="l$1" />
+    <RegEx find="\b(?:II|ll)" replaceWith="Il" />
+    <RegEx find="([\xf5\xfb])I" replaceWith="$1l" />
+  </RegularExpressions>
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/nld_OCRFixReplaceList.xml

@@ -0,0 +1,24 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="ls" to="Is" />
+    <Word from="ln" to="In" />
+    <Word from="lk" to="Ik" />
+    <Word from="ledereen" to="Iedereen" />
+    <Word from="ledere" to="Iedere" />
+    <Word from="lemand" to="Iemand" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords />
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions>
+    <RegEx find="\blk(?=\p{Ll}{2})" replaceWith="Ik" />
+    <RegEx find="\bln(?=\p{Ll}{2})" replaceWith="In" />
+    <RegEx find="\bls(?=\p{Ll}{2})" replaceWith="Is" />
+    <RegEx find="\beIk" replaceWith="elk" />
+    <RegEx find="\bler(land|se|s|)\b" replaceWith="Ier$1" />
+  </RegularExpressions>
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/nor_OCRFixReplaceList.xml

@@ -0,0 +1,43 @@
+<OCRFixReplaceList>
+  <WholeWords />
+  <PartialWordsAlways />
+  <PartialWords>
+    <!-- Will be used to check words not in dictionary -->
+    <!-- If new word(s) exists in spelling dictionary, it(they) is accepted -->
+    <WordPart from="¤" to="o" />
+    <WordPart from="fi" to="fi" />
+    <WordPart from="fl" to="fl" />
+    <WordPart from="/" to="l" />
+    <WordPart from="vv" to="w" />
+    <WordPart from="IVI" to="M" />
+    <WordPart from="lVI" to="M" />
+    <WordPart from="IVl" to="M" />
+    <WordPart from="lVl" to="M" />
+    <WordPart from="m" to="rn" />
+    <WordPart from="l" to="i" />
+    <WordPart from="€" to="e" />
+    <WordPart from="I" to="l" />
+    <WordPart from="c" to="o" />
+    <WordPart from="i" to="t" />
+    <WordPart from="cc" to="oo" />
+    <WordPart from="ii" to="tt" />
+    <WordPart from="n/" to="ry" />
+    <WordPart from="ae" to="æ" />
+    <!-- "f " will be two words -->
+    <WordPart from="f" to="f " />
+    <WordPart from="c" to="e" />
+    <WordPart from="I" to="t" />
+    <WordPart from="n" to="o" />
+    <WordPart from="s" to="e" />
+    <WordPart from="\A" to="Vi" />
+    <WordPart from="n/" to="rv" />
+    <WordPart from="Ã" to="Å" />
+    <WordPart from="í" to="i" />
+  </PartialWords>
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions />
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/por_OCRFixReplaceList.xml

@@ -0,0 +1,508 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="abitual" to="habitual" />
+    <Word from="àcerca" to="acerca" />
+    <Word from="acessor" to="assessor" />
+    <Word from="acólico" to="acólito" />
+    <Word from="açoreano" to="açoriano" />
+    <Word from="actuacao" to="actuação" />
+    <Word from="acucar" to="açúcar" />
+    <Word from="açucar" to="açúcar" />
+    <Word from="advinhar" to="adivinhar" />
+    <Word from="africa" to="África" />
+    <Word from="ajuisar" to="ajuizar" />
+    <Word from="album" to="álbum" />
+    <Word from="alcoolémia" to="alcoolemia" />
+    <Word from="aldião" to="aldeão" />
+    <Word from="algerino" to="argelino" />
+    <Word from="ameixeal" to="ameixial" />
+    <Word from="amiaça" to="ameaça" />
+    <Word from="analizar" to="analisar" />
+    <Word from="andáste" to="andaste" />
+    <Word from="anemona" to="anémona" />
+    <Word from="antartico" to="antárctico" />
+    <Word from="antártico" to="antárctico" />
+    <Word from="antepôr" to="antepor" />
+    <Word from="apárte" to="aparte" />
+    <Word from="apiadeiro" to="apeadeiro" />
+    <Word from="apiar" to="apear" />
+    <Word from="apreciacao" to="apreciação" />
+    <Word from="arctico" to="árctico" />
+    <Word from="arrazar" to="arrasar" />
+    <Word from="ártico" to="árctico" />
+    <Word from="artifice" to="artífice" />
+    <Word from="artifícial" to="artificial" />
+    <Word from="ascenção" to="ascensão" />
+    <!-- <Word from="assucar" to="açúcar" /> assucar é uma palavra existente no dicionário -->
+    <Word from="assúcar" to="açúcar" />
+    <Word from="aste" to="haste" />
+    <Word from="asterístico" to="asterisco" />
+    <Word from="averção" to="aversão" />
+    <Word from="avizar" to="avisar" />
+    <Word from="avulsso" to="avulso" />
+    <Word from="baínha" to="bainha" />
+    <Word from="banca-rota" to="bancarrota" />
+    <Word from="bandeija" to="bandeja" />
+    <Word from="bébé" to="bebé" />
+    <Word from="beige" to="bege" />
+    <Word from="benção" to="bênção" />
+    <Word from="beneficiência" to="beneficência" />
+    <Word from="beneficiente" to="beneficente" />
+    <Word from="benvinda" to="bem-vinda" />
+    <Word from="benvindo" to="bem-vindo" />
+    <Word from="boasvindas" to="boas-vindas" />
+    <Word from="borborinho" to="burburinho" />
+    <Word from="Brazil" to="Brasil" />
+    <Word from="bussula" to="bússola" />
+    <Word from="cabo-verdeano" to="cabo-verdiano" />
+    <Word from="caimbras" to="cãibras" />
+    <Word from="calcáreo" to="calcário" />
+    <Word from="calsado" to="calçado" />
+    <Word from="calvíce" to="calvície" />
+    <Word from="camoneano" to="camoniano" />
+    <Word from="campião" to="campeão" />
+    <Word from="cançacos" to="cansaços" />
+    <Word from="caracter" to="carácter" />
+    <Word from="caractéres" to="caracteres" />
+    <Word from="catequeze" to="catequese" />
+    <Word from="catequisador" to="catequizador" />
+    <Word from="catequisar" to="catequizar" />
+    <Word from="chícara" to="xícara" />
+    <Word from="ciclano" to="sicrano" />
+    <Word from="cicrano" to="sicrano" />
+    <Word from="cidadães" to="cidadãos" />
+    <Word from="cidadões" to="cidadãos" />
+    <Word from="cincoenta" to="cinquenta" />
+    <Word from="cinseiro" to="cinzeiro" />
+    <Word from="cinsero" to="sincero" />
+    <Word from="citacoes" to="citações" />
+    <Word from="coalizão" to="colisão" />
+    <Word from="côdia" to="côdea" />
+    <Word from="combóio" to="comboio" />
+    <Word from="compôr" to="compor" />
+    <Word from="concerteza" to="com certeza" />
+    <Word from="constituia" to="constituía" />
+    <Word from="constituíu" to="constituiu" />
+    <Word from="contato" to="contacto" />
+    <Word from="contensão" to="contenção" />
+    <Word from="contribuicoes" to="contribuições" />
+    <Word from="côr" to="cor" />
+    <Word from="corassão" to="coração" />
+    <Word from="corçario" to="corsário" />
+    <Word from="corçário" to="corsário" />
+    <Word from="cornprimidosinbo" to="comprimidozinho" />
+    <!-- <Word from="cota-parte" to="quota-parte" /> é uma palavra existente no dicionário -->
+    <Word from="crâneo" to="crânio" />
+    <Word from="dE" to="de" />
+    <Word from="defenição" to="definição" />
+    <Word from="defenido" to="definido" />
+    <Word from="defenir" to="definir" />
+    <Word from="deficite" to="défice" />
+    <Word from="degladiar" to="digladiar" />
+    <Word from="deiche" to="deixe" />
+    <Word from="desinteria" to="disenteria" />
+    <Word from="despendio" to="dispêndio" />
+    <Word from="despêndio" to="dispêndio" />
+    <Word from="desplicência" to="displicência" />
+    <Word from="dificulidade" to="dificuldade" />
+    <Word from="dispender" to="despender" />
+    <Word from="dispendio" to="dispêndio" />
+    <Word from="distribuido" to="distribuído" />
+    <Word from="druída" to="druida" />
+    <Word from="écrã" to="ecrã" />
+    <Word from="ecran" to="ecrã" />
+    <Word from="écran" to="ecrã" />
+    <Word from="êle" to="ele" />
+    <Word from="elice" to="hélice" />
+    <Word from="élice" to="hélice" />
+    <Word from="emiratos" to="emirados" />
+    <Word from="engolis-te" to="engoliste" />
+    <Word from="engulir" to="engolir" />
+    <Word from="enguliste" to="engoliste" />
+    <Word from="entertido" to="entretido" />
+    <Word from="entitular" to="intitular" />
+    <Word from="entreterimento" to="entretenimento" />
+    <Word from="entreti-me" to="entretive-me" />
+    <Word from="envólucro" to="invólucro" />
+    <Word from="erói" to="herói" />
+    <Word from="escluir" to="excluir" />
+    <Word from="esclusão" to="exclusão" />
+    <Word from="escrivões" to="escrivães" />
+    <Word from="esqueiro" to="isqueiro" />
+    <Word from="esquesito" to="esquisito" />
+    <Word from="estacoes" to="estações" />
+    <Word from="esteje" to="esteja" />
+    <Word from="excavação" to="escavação" />
+    <Word from="excavar" to="escavar" />
+    <Word from="exdrúxula" to="esdrúxula" />
+    <Word from="exdrúxulas" to="esdrúxulas" />
+    <Word from="exitar" to="hesitar" />
+    <Word from="explicacoes" to="explicações" />
+    <Word from="exquisito" to="esquisito" />
+    <Word from="extende" to="estende" />
+    <Word from="extender" to="estender" />
+    <Word from="fàcilmenfe" to="facilmente" />
+    <Word from="fàcilmente" to="facilmente" />
+    <Word from="fariam-lhe" to="far-lhe-iam" />
+    <Word from="FARMÁClAS" to="FARMÁCIAS" />
+    <Word from="farmecêutico" to="farmacêutico" />
+    <Word from="fassa" to="faça" />
+    <Word from="fébre" to="febre" />
+    <Word from="fecula" to="fécula" />
+    <Word from="fémea" to="fêmea" />
+    <Word from="femenino" to="feminino" />
+    <Word from="femininismo" to="feminismo" />
+    <Word from="físiologista" to="fisiologista" />
+    <Word from="fizémos" to="fizemos" />
+    <Word from="fizes-te" to="fizeste" />
+    <Word from="flôr" to="flor" />
+    <Word from="forão" to="foram" />
+    <Word from="formalisar" to="formalizar" />
+    <Word from="fôro" to="foro" />
+    <Word from="fos-te" to="foste" />
+    <Word from="fragância" to="fragrância" />
+    <Word from="françês" to="francês" />
+    <Word from="frasqutnho" to="frasquinho" />
+    <Word from="frustado" to="frustrado" />
+    <Word from="furá" to="furar" />
+    <Word from="gaz" to="gás" />
+    <Word from="gáz" to="gás" />
+    <Word from="geito" to="jeito" />
+    <Word from="geneceu" to="gineceu" />
+    <Word from="geropiga" to="jeropiga" />
+    <Word from="glicémia" to="glicemia" />
+    <Word from="gorgeta" to="gorjeta" />
+    <Word from="grangear" to="granjear" />
+    <Word from="guizar" to="guisar" />
+    <Word from="hectar" to="hectare" />
+    <Word from="herméticamente" to="hermeticamente" />
+    <Word from="hernia" to="hérnia" />
+    <Word from="higiéne" to="higiene" />
+    <Word from="hilariedade" to="hilaridade" />
+    <Word from="hiperacídez" to="hiperacidez" />
+    <Word from="hontem" to="ontem" />
+    <Word from="igiene" to="higiene" />
+    <Word from="igienico" to="higiénico" />
+    <Word from="igiénico" to="higiénico" />
+    <Word from="igreija" to="igreja" />
+    <Word from="iguasu" to="iguaçu" />
+    <Word from="ilacção" to="ilação" />
+    <Word from="imbigo" to="umbigo" />
+    <Word from="impecilho" to="empecilho" />
+    <Word from="íncas" to="incas" />
+    <Word from="incêsto" to="incesto" />
+    <Word from="inclusivé" to="inclusive" />
+    <Word from="incômodos" to="incómodos" />
+    <Word from="incontestávelmente" to="incontestavelmente" />
+    <Word from="incontestàvelmente" to="incontestavelmente" />
+    <Word from="indespensáveis" to="indispensáveis" />
+    <Word from="indespensável" to="indispensável" />
+    <Word from="India" to="Índia" />
+    <Word from="indiguinação" to="indignação" />
+    <Word from="indiguinado" to="indignado" />
+    <Word from="indiguinar" to="indignar" />
+    <Word from="inflacção" to="inflação" />
+    <Word from="ingreja" to="igreja" />
+    <Word from="INSCRICOES" to="INSCRIÇÕES" />
+    <Word from="intensão" to="intenção" />
+    <Word from="intertido" to="entretido" />
+    <Word from="intoxica" to="Intoxica" />
+    <Word from="intrega" to="entrega" />
+    <Word from="inverosímel" to="inverosímil" />
+    <Word from="iorgute" to="iogurte" />
+    <Word from="ipopótamo" to="hipopótamo" />
+    <Word from="ipsilon" to="ípsilon" />
+    <Word from="ipslon" to="ípsilon" />
+    <Word from="isquesito" to="esquisito" />
+    <Word from="juíz" to="juiz" />
+    <Word from="juiza" to="juíza" />
+    <Word from="júniores" to="juniores" />
+    <Word from="justanzente" to="justamente" />
+    <Word from="juz" to="jus" />
+    <Word from="kilo" to="quilo" />
+    <Word from="laboratório-porque" to="laboratório porque" />
+    <Word from="ladravaz" to="ladrava" />
+    <Word from="lamentàvelmente" to="lamentavelmente" />
+    <Word from="lampeão" to="lampião" />
+    <Word from="largartixa" to="lagartixa" />
+    <Word from="largarto" to="lagarto" />
+    <Word from="lêm" to="lêem" />
+    <Word from="leucémia" to="leucemia" />
+    <Word from="licensa" to="licença" />
+    <Word from="linguísta" to="linguista" />
+    <Word from="lisongear" to="lisonjear" />
+    <Word from="logista" to="lojista" />
+    <Word from="maçajar" to="massajar" />
+    <Word from="Macfadden-o" to="Macfadden o" />
+    <Word from="mae" to="mãe" />
+    <Word from="magestade" to="majestade" />
+    <Word from="mãgua" to="mágoa" />
+    <Word from="mangerico" to="manjerico" />
+    <Word from="mangerona" to="manjerona" />
+    <Word from="manteem-se" to="mantêm-se" />
+    <Word from="mantega" to="manteiga" />
+    <Word from="mantem-se" to="mantém-se" />
+    <Word from="massiço" to="maciço" />
+    <Word from="massisso" to="maciço" />
+    <Word from="médica-Rio" to="médica Rio" />
+    <Word from="menistro" to="ministro" />
+    <Word from="merciaria" to="mercearia" />
+    <Word from="metrelhadora" to="metralhadora" />
+    <Word from="miscegenação" to="miscigenação" />
+    <Word from="misogenia" to="misoginia" />
+    <Word from="misogeno" to="misógino" />
+    <Word from="misógeno" to="misógino" />
+    <Word from="mº" to="º" />
+    <Word from="môlho" to="molho" />
+    <Word from="monumentânea" to="momentânea" />
+    <Word from="mortandela" to="mortadela" />
+    <Word from="morteIa" to="mortela" />
+    <Word from="muinto" to="muito" />
+    <Word from="nasaias" to="nasais" />
+    <Word from="nêle" to="nele" />
+    <Word from="nest" to="neste" />
+    <Word from="Nivea" to="Nívea" />
+    <Word from="nonagessimo" to="nonagésimo" />
+    <Word from="nonagéssimo" to="nonagésimo" />
+    <Word from="nornal" to="normal" />
+    <Word from="notàvelmente" to="notavelmente" />
+    <Word from="obcessão" to="obsessão" />
+    <Word from="obesidae" to="obesidade" />
+    <Word from="óbviamente" to="obviamente" />
+    <Word from="òbviamente" to="obviamente" />
+    <Word from="ofecina" to="oficina" />
+    <Word from="oje" to="hoje" />
+    <Word from="omem" to="homem" />
+    <Word from="opcoes" to="opções" />
+    <Word from="opóbrio" to="opróbrio" />
+    <Word from="opróbio" to="opróbrio" />
+    <Word from="orfão" to="órfão" />
+    <Word from="organigrama" to="organograma" />
+    <Word from="organisar" to="organizar" />
+    <Word from="orgão" to="órgão" />
+    <Word from="orta" to="horta" />
+    <Word from="ótima" to="óptima" />
+    <Word from="ótimos" to="óptimos" />
+    <Word from="paralização" to="paralisação" />
+    <Word from="paralizado" to="paralisado" />
+    <Word from="paralizar" to="paralisar" />
+    <Word from="paráste" to="paraste" />
+    <Word from="Pátria" to="pátria" />
+    <Word from="paúl" to="Paul" />
+    <Word from="pecalço" to="percalço" />
+    <Word from="pêga" to="pega" />
+    <Word from="periodo" to="período" />
+    <Word from="pertubar" to="perturbar" />
+    <Word from="perú" to="peru" />
+    <Word from="piqueno" to="pequeno" />
+    <Word from="pirinéus" to="Pirenéus" />
+    <Word from="poblema" to="problema" />
+    <Word from="pobrema" to="problema" />
+    <Word from="poden" to="podem" />
+    <Word from="poder-mos" to="pudermos" />
+    <Word from="ponteagudo" to="pontiagudo" />
+    <Word from="pontuacoes" to="pontuações" />
+    <Word from="prazeiroso" to="prazeroso" />
+    <Word from="precaridade" to="precariedade" />
+    <Word from="precizar" to="precisar" />
+    <Word from="preserverança" to="perseverança" />
+    <Word from="previlégio" to="privilégio" />
+    <Word from="primária-que" to="primária que" />
+    <Word from="priúdo" to="período" />
+    <Word from="probalidade" to="probabilidade" />
+    <Word from="progreso" to="progresso" />
+    <Word from="proibído" to="proibido" />
+    <Word from="proíbido" to="proibido" />
+    <Word from="própia" to="própria" />
+    <Word from="propiedade" to="propriedade" />
+    <Word from="propio" to="próprio" />
+    <Word from="própio" to="próprio" />
+    <Word from="provocacoes" to="provocações" />
+    <Word from="prsença" to="presença" />
+    <Word from="prustituta" to="prostituta" />
+    <Word from="pudérmos" to="pudermos" />
+    <Word from="púlico" to="público" />
+    <Word from="pús" to="pus" />
+    <Word from="pusémos" to="pusemos" />
+    <Word from="quadricomia" to="quadricromia" />
+    <Word from="quadriplicado" to="quadruplicado" />
+    <Word from="quaisqueres" to="quaisquer" />
+    <Word from="quer-a" to="quere-a" />
+    <Word from="quere-se" to="quer-se" />
+    <Word from="quer-o" to="quere-o" />
+    <Word from="químco" to="químico" />
+    <Word from="quises-te" to="quiseste" />
+    <Word from="quizer" to="quiser" />
+    <Word from="quizeram" to="quiseram" />
+    <Word from="quizesse" to="quisesse" />
+    <Word from="quizessem" to="quisessem" />
+    <Word from="raínha" to="rainha" />
+    <Word from="raíz" to="raiz" />
+    <Word from="raizes" to="raízes" />
+    <Word from="ratato" to="retrato" />
+    <Word from="raúl" to="raul" />
+    <Word from="razar" to="rasar" />
+    <Word from="rectaguarda" to="retaguarda" />
+    <Word from="rédia" to="rédea" />
+    <Word from="reestabelecer" to="restabelecer" />
+    <Word from="refeicoes" to="refeições" />
+    <Word from="refêrencia" to="referência" />
+    <Word from="regeitar" to="rejeitar" />
+    <Word from="regurjitar" to="regurgitar" />
+    <Word from="reinvidicação" to="reivindicação" />
+    <Word from="reinvidicar" to="reivindicar" />
+    <Word from="requer-a" to="requere-a" />
+    <Word from="requere-se" to="requer-se" />
+    <Word from="requer-o" to="requere-o" />
+    <Word from="requesito" to="requisito" />
+    <Word from="requisicoes" to="requisições" />
+    <Word from="RESIDENCIA" to="RESIDÊNCIA" />
+    <Word from="respiraçáo" to="respiração" />
+    <Word from="restablecer" to="restabelecer" />
+    <Word from="réstea" to="réstia" />
+    <Word from="ruborisar" to="ruborizar" />
+    <Word from="rúbrica" to="rubrica" />
+    <Word from="sàdia" to="sadia" />
+    <Word from="saiem" to="saem" />
+    <Word from="salchicha" to="salsicha" />
+    <Word from="salchichas" to="salsichas" />
+    <Word from="saloice" to="saloiice" />
+    <Word from="salvé" to="salve" />
+    <Word from="salve-raínha" to="salve-rainha" />
+    <Word from="salvé-rainha" to="salve-rainha" />
+    <Word from="salvé-raínha" to="salve-rainha" />
+    <Word from="sao" to="são" />
+    <Word from="sargeta" to="sarjeta" />
+    <Word from="seções" to="secções" />
+    <Word from="seija" to="seja" />
+    <Word from="seissentos" to="seiscentos" />
+    <Word from="seje" to="seja" />
+    <Word from="semiar" to="semear" />
+    <Word from="séniores" to="seniores" />
+    <Word from="sensibilidadc" to="sensibilidade" />
+    <Word from="sensívelmente" to="sensivelmente" />
+    <Word from="setessentos" to="setecentos" />
+    <Word from="siclano" to="sicrano" />
+    <Word from="Sifilis" to="Sífilis" />
+    <Word from="sifílis" to="sífilis" />
+    <Word from="sinão" to="senão" />
+    <Word from="sinmtoma" to="sintoma" />
+    <Word from="sintéticamente" to="sinteticamente" />
+    <Word from="sintetisa" to="sintetiza" />
+    <Word from="SÓ" to="só" />
+    <Word from="sôfra" to="sofra" />
+    <Word from="sôfregamente" to="sofregamente" />
+    <Word from="somáste" to="somaste" />
+    <Word from="sombracelha" to="sobrancelha" />
+    <Word from="sombrancelha" to="sobrancelha" />
+    <Word from="sombrancelhas" to="sobrancelhas" />
+    <Word from="suavisar" to="suavizar" />
+    <Word from="substituido" to="substituído" />
+    <Word from="suburbio" to="subúrbio" />
+    <!-- <Word from="sues" to="seus" /> sues existe "Cuidado, não sues muito." -->
+    <Word from="suI" to="sul" />
+    <Word from="Suiça" to="Suíça" />
+    <Word from="suiças" to="suíças" />
+    <Word from="suiço" to="suíço" />
+    <Word from="suiços" to="suíços" />
+    <Word from="supôr" to="supor" />
+    <Word from="tabeliões" to="tabeliães" />
+    <Word from="taínha" to="tainha" />
+    <Word from="tava" to="estava" />
+    <Word from="têem" to="têm" />
+    <Word from="telemovel" to="telemóvel" />
+    <Word from="telémovel" to="telemóvel" />
+    <Word from="terminacoes" to="terminações" />
+    <Word from="toráxico" to="torácico" />
+    <Word from="tou" to="estou" />
+    <Word from="transpôr" to="transpor" />
+    <Word from="trasnporte" to="transporte" />
+    <Word from="tumors" to="tumores" />
+    <Word from="úmida" to="húmida" />
+    <Word from="umidade" to="unidade" />
+    <Word from="vai-vem" to="vaivém" />
+    <Word from="vegilância" to="vigilância" />
+    <Word from="vegilante" to="vigilante" />
+    <Word from="ventoínha" to="ventoinha" />
+    <Word from="verosímel" to="verosímil" />
+    <Word from="video" to="vídeo" />
+    <Word from="virus" to="vírus" />
+    <Word from="visiense" to="viseense" />
+    <Word from="voçe" to="você" />
+    <Word from="voçê" to="você" />
+    <Word from="vôo" to="voo" />
+    <Word from="xadrês" to="xadrez" />
+    <Word from="xafariz" to="chafariz" />
+    <Word from="xéxé" to="xexé" />
+    <Word from="xilindró" to="chilindró" />
+    <Word from="zaíre" to="Zaire" />
+    <Word from="zepelin" to="zepelim" />
+    <Word from="zig-zag" to="ziguezague" />
+    <Word from="zoô" to="zoo" />
+    <Word from="zôo" to="zoo" />
+    <Word from="zuar" to="zoar" />
+    <Word from="zum-zum" to="zunzum" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords />
+  <PartialLines>
+    <LinePart from="IN 6-E" to="N 6 E" />
+    <LinePart from="in tegrar-se" to="integrar-se" />
+    <LinePart from="in teresse" to="interesse" />
+    <LinePart from="in testinos" to="intestinos" />
+    <LinePart from="indica ção" to="indicação" />
+    <LinePart from="inte tino" to="intestino" />
+    <LinePart from="intes tinos" to="intestinos" />
+    <LinePart from="L da" to="Lda" />
+    <LinePart from="mal estar" to="mal-estar" />
+    <LinePart from="mastiga çáo" to="mastigação" />
+    <LinePart from="médi cas" to="médicas" />
+    <LinePart from="mineo rais" to="minerais" />
+    <LinePart from="mola res" to="molares" />
+    <LinePart from="movi mentos" to="movimentos" />
+    <LinePart from="movimen to" to="movimento" />
+    <LinePart from="N 5-Estendido" to="Nº 5 Estendido" />
+    <LinePart from="oxigé nio" to="oxigénio" />
+    <LinePart from="pod mos" to="podemos" />
+    <LinePart from="poder-se ia" to="poder-se-ia" />
+    <LinePart from="pos sibilidade" to="possibilidade" />
+    <LinePart from="possibi lidades" to="possibilidades" />
+    <LinePart from="pro duto" to="produto" />
+    <LinePart from="procu rar" to="procurar" />
+    <LinePart from="Q u e" to="Que" />
+    <LinePart from="qualifi cam" to="qualificam" />
+    <LinePart from="R egião" to="Região" />
+    <LinePart from="unsuficien temente" to="insuficientemente" />
+  </PartialLines>
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions>
+    <!-- <RegEx find="\bi\b" replaceWith="I" /> just an example - do not use this regex -->
+    <RegEx find="([0-9]) +º" replaceWith="$1º" />
+    <RegEx find="\Bcao\b" replaceWith="ção" />
+    <RegEx find="\Bcoes\b" replaceWith="ções" />
+    <!-- <RegEx find="\Bccao\b" replaceWith="cção" /> não faz sentido ter este e ter a linha de cima -->
+    <!-- <RegEx find="\Bccoes\b" replaceWith="cções" /> não faz sentido ter este e ter a linha de cima -->
+    <RegEx find="\b(m|M)ae\b" replaceWith="$1ãe" />
+    <RegEx find="\Bdmnis\B" replaceWith="dminis" />
+    <RegEx find="\Blcól\B" replaceWith="lcoól" />
+    <RegEx find="\b(t|T)a[nm]b[eé]m\b" replaceWith="$1ambém" />
+    <RegEx find="\bzeppeli[mn]\b" replaceWith="zepelim" />
+    <RegEx find="\b(s|S)ufe?ciente\b" replaceWith="$1uficiente" />
+    <RegEx find="\b(n|N)ao\b" replaceWith="$1ão" />
+    <RegEx find="\b(B|b)elem\b" replaceWith="$1elém" />
+    <RegEx find="\b(s|S)u[íi]sso(s)?\b" replaceWith="$1uíço$2" />
+    <RegEx find="\b(s|S)u[íi]ssa(s)?\b" replaceWith="$1uíça$2" />
+    <RegEx find="\b(p|P)rivelig[ie]\p{Ll}d" replaceWith="$1rivelegiad" />
+    <RegEx find="\bpud(?:és|e-)se\b" replaceWith="pudesse" />
+    <RegEx find="\biquilíbr(?:e|i)o\b" replaceWith="equilíbrio" />
+    <RegEx find="\b(c|C)orregi\B" replaceWith="$1orrigid" />
+    <RegEx find="(?&lt;=A|a)ssociacao" replaceWith="ssociação" />
+    <RegEx find="(?&lt;=N|n)inguem" replaceWith="inguém" />
+    <RegEx find="(?&lt;=g|G)rat(?:uí|úi)to" replaceWith="ratuito" />
+    <RegEx find="(?&lt;=d|D)esiquilíbr[ei]o" replaceWith="esequilíbrio" />
+    <RegEx find="\b[k|K]il(ogramas?|ómetros?)" replaceWith="qui$1" />
+  </RegularExpressions>
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/rus_OCRFixReplaceList.xml

@@ -0,0 +1,257 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="НЄЙ" to="НЕЙ" />
+    <Word from="ОРГЗНИЗМОБ" to="ОРГАНИЗМА" />
+    <Word from="Чї0" to="ЧТО" />
+    <Word from="НЭ" to="НА" />
+    <Word from="СОСЄДНЮЮ" to="СОСЕДНЮЮ" />
+    <Word from="ПЛЗНЄТУ" to="ПЛАНЕТУ" />
+    <Word from="ЗЗГЭДОК" to="ЗАГАДОК" />
+    <Word from="СОТВОРЄНИЯ" to="СОТВОРЕНИЯ" />
+    <Word from="МИРЭ" to="МИРА" />
+    <Word from="ПОЯБЛЄНИЯ" to="ПОЯВЛЕНИЯ" />
+    <Word from="ЗЄМЛЄ" to="ЗЕМЛЕ" />
+    <Word from="ЄЩЄ" to="ЕЩЁ" />
+    <Word from="ТЄМНЬІХ" to="ТЕМНЫХ" />
+    <Word from="СЄРЬЄЗНЬІМ" to="СЕРЬЕЗНЫМ" />
+    <Word from="ПОШІІ0" to="ПОШЛО" />
+    <Word from="Пр0ИЗ0ШЄЛ" to="ПРОИЗОШЕЛ" />
+    <Word from="СЄКРЄТЭМИ" to="СЕКРЕТАМИ" />
+    <Word from="МЭТЄРИЗЛЬІ" to="МАТЕРИАЛЫ" />
+    <Word from="ПЯТЄН" to="ПЯТЕН" />
+    <Word from="ПЛаНЄїЄ" to="ПЛАНЕТЕ" />
+    <Word from="КЗТЭКЛИЗМ" to="КАТАКЛИЗМ" />
+    <Word from="ОКЗЗЗЛСЯ" to="ОКАЗАЛСЯ" />
+    <Word from="ДЭЛЬШЕ" to="ДАЛЬШЕ" />
+    <Word from="ТВК" to="ТАК" />
+    <Word from="ПЛЗНЄТЗ" to="ПЛАНЕТА" />
+    <Word from="ЧЄГО" to="ЧЕГО" />
+    <Word from="УЗНЭТЬ" to="УЗНАТЬ" />
+    <Word from="ПЛЭНЄТЄ" to="ПЛАНЕТЕ" />
+    <Word from="НЄМ" to="НЕМ" />
+    <Word from="БОЗМОЖНЗ" to="ВОЗМОЖНА" />
+    <Word from="СОБЄРШЄННО" to="СОВЕРШЕННО" />
+    <Word from="ИНЭЧЄ" to="ИНАЧЕ" />
+    <Word from="БСЄ" to="ВСЕ" />
+    <Word from="НЕДОСТЗТКИ" to="НЕДОСТАТКИ" />
+    <Word from="НОВЬІЄ" to="НОВЫЕ" />
+    <Word from="ВЄЛИКОЛЄПНЭЯ" to="ВЕЛИКОЛЕПНАЯ" />
+    <Word from="ОСТЭІІОСЬ" to="ОСТАЛОСЬ" />
+    <Word from="НЗЛИЧИЄ" to="НАЛИЧИЕ" />
+    <Word from="бЫ" to="бы" />
+    <Word from="ПРОЦВЕТВТЬ" to="ПРОЦВЕТАТЬ" />
+    <Word from="КЗК" to="КАК" />
+    <Word from="ВОДЗ" to="ВОДА" />
+    <Word from="НЗШЕЛ" to="НАШЕЛ" />
+    <Word from="НЄ" to="НЕ" />
+    <Word from="ТОЖЄ" to="ТОЖЕ" />
+    <Word from="ВУЛКЭНИЧЄСКОЙ" to="ВУЛКАНИЧЕСКОЙ" />
+    <Word from="ЭКТИБНОСТИ" to="АКТИВНОСТИ" />
+    <Word from="ПОЯВИЛЗСЬ" to="ПОЯВИЛАСЬ" />
+    <Word from="НОВЗЯ" to="НОВАЯ" />
+    <Word from="СТРЭТЄГИЯ" to="СТРАТЕГИЯ" />
+    <Word from="УСПЄШН0" to="УСПЕШНО" />
+    <Word from="ПОСЗДКУ" to="ПОСАДКУ" />
+    <Word from="ГОТОБЫ" to="ГОТОВЫ" />
+    <Word from="НЗЧЗТЬ" to="НАЧАТЬ" />
+    <Word from="ОХОТЭ" to="ОХОТА" />
+    <Word from="ПРИЗНЗКЗМИ" to="ПРИЗНАКАМИ" />
+    <Word from="Пр0ШЛОМ" to="ПРОШЛОМ" />
+    <Word from="НЭСТОЯЩЄМ" to="НАСТОЯЩЕМ" />
+    <Word from="ПУСТОТЗХ" to="ПУСТОТАХ" />
+    <Word from="БЛЗЖНОЙ" to="ВЛАЖНОЙ" />
+    <Word from="ПОЧБЄ" to="ПОЧВЕ" />
+    <Word from="МЬІ" to="МЫ" />
+    <Word from="СЄЙЧЗС" to="СЕЙЧАС" />
+    <Word from="ЄСЛИ" to="ЕСЛИ" />
+    <Word from="ЗЗТРОНЕМ" to="ЗАТРОНЕМ" />
+    <Word from="ОПЗСЗЄМСЯ" to="ОПАСАЕМСЯ" />
+    <Word from="СИЛЬН0" to="СИЛЬНО" />
+    <Word from="ОТЛИЧЗЄТСЯ" to="ОТЛИЧАЕТСЯ" />
+    <Word from="РЭНЬШЄ" to="РАНЬШЕ" />
+    <Word from="НЗЗЬІВЗЮТ" to="НАЗЫВАЮТ" />
+    <Word from="ТЄКЛ3" to="ТЕКЛА" />
+    <Word from="ОСЗДОЧНЫМИ" to="ОСАДОЧНЫМИ" />
+    <Word from="ПОСТЄПЄНН0" to="ПОСТЕПЕННО" />
+    <Word from="ИСПЭРЯЛЗСЬ" to="ИСПАРЯЛАСЬ" />
+    <Word from="ЄОЛЬШОЄ" to="БОЛЬШОЕ" />
+    <Word from="КОЛИЧЄСТБО" to="КОЛИЧЕСТВО" />
+    <Word from="ГЄМЗТИТЕ" to="ГЕМАТИТА" />
+    <Word from="ПОЛУЧЭЄТ" to="ПОЛУЧАЕТ" />
+    <Word from="НЄДОСТЗЧН0" to="НЕДОСТАТОЧНО" />
+    <Word from="ПИТЭНИЯ" to="ПИТАНИЯ" />
+    <Word from="ПОКЗ" to="ПОКА" />
+    <Word from="БЬІХОДИЛИ" to="ВЫХОДИЛИ" />
+    <Word from="ЗЄМІІЄ" to="ЗЕМЛЕ" />
+    <Word from="ВЄСЬІИЗ" to="ВЕСЬМА" />
+    <Word from="ЗЄМЛИ" to="ЗЕМЛИ" />
+    <Word from="бЬІЛО" to="БЫЛО" />
+    <Word from="КИЗНИ" to="ЖИЗНИ" />
+    <Word from="СТЗНОВИЛЗСЬ" to="СТАНОВИЛАСЬ" />
+    <Word from="СОЛЄНЄЄ" to="СОЛЁНЕЕ" />
+    <Word from="МЭГНИТНЫМ" to="МАГНИТНЫМ" />
+    <Word from="ЧТОбЬІ" to="ЧТОБЫ" />
+    <Word from="СОЗДЕТЬ" to="СОЗДАТЬ" />
+    <Word from="МЗГНИТНОЄ" to="МАГНИТНОЕ" />
+    <Word from="КЭЖУТСЯ" to="КАЖУТСЯ" />
+    <Word from="ОЗНЗЧЗЄТ" to="ОЗНАЧАЕТ" />
+    <Word from="МОГЛЗ" to="МОГЛА" />
+    <Word from="ИМЄТЬ" to="ИМЕТЬ" />
+    <Word from="КОСМОСЭ" to="КОСМОСА" />
+    <Word from="СОЛНЄЧНЗЯ" to="СОЛНЕЧНАЯ" />
+    <Word from="СИСТЄМЗ" to="СИСТЕМА" />
+    <Word from="ПОСІІУЖИЛО" to="ПОСЛУЖИЛО" />
+    <Word from="МЗГНИТНОГО" to="МАГНИТНОГО" />
+    <Word from="ПЛВНЄТЫ" to="ПЛАНЕТЫ" />
+    <Word from="ЛОКЗЛЬНЬІХ" to="ЛОКАЛЬНЫХ" />
+    <Word from="ПОЛЄЙ" to="ПОЛЕЙ" />
+    <Word from="КЗЖУТСЯ" to="КАЖУТСЯ" />
+    <Word from="КЗКОГО" to="КАКОГО" />
+    <Word from="СТРЗШНОГО" to="СТРАШНОГО" />
+    <Word from="СТОЛКНОЕЄНИЯ" to="СТОЛКНОВЕНИЯ" />
+    <Word from="МЕСТЗМИ" to="МЕСТАМИ" />
+    <Word from="СДЄЛЗТЬ" to="СДЕЛАТЬ" />
+    <Word from="СТЗЛО" to="СТАЛО" />
+    <Word from="МЭГНИТНОГО" to="МАГНИТНОГО" />
+    <Word from="ЗЗКЛЮЧЗВШЄЙСЯ" to="ЗАКЛЮЧАВШЕЙСЯ" />
+    <Word from="ЄГО" to="ЕГО" />
+    <Word from="ЯДРЄ" to="ЯДРЕ" />
+    <Word from="НЗ" to="НА" />
+    <Word from="ИСЧЄЗЛ3" to="ИСЧЕЗЛА" />
+    <Word from="СЧИТЗЮ" to="СЧИТАЮ" />
+    <Word from="ШЭНСЫ" to="ШАНСЫ" />
+    <Word from="ИНЗЧЄ" to="ИНАЧЕ" />
+    <Word from="СТЗЛ" to="СТАЛ" />
+    <Word from="ТРЗТИТЬ" to="ТРАТИТЬ" />
+    <Word from="НЗПРЗВЛЯЄТСЯ" to="НАПРАВЛЯЕТСЯ" />
+    <Word from="ОБЛЭСТИ" to="ОБЛАСТИ" />
+    <Word from="ЯВЛЯІОТСЯ" to="ЯВЛЯЮТСЯ" />
+    <Word from="ГЛЭВНОЙ" to="ГЛАВНОЙ" />
+    <Word from="ДОКЗЗЗТЄЛЬСТВ" to="ДОКАЗАТЕЛЬСТВ" />
+    <Word from="КИСЛОТЭМИ" to="КИСЛОТАМИ" />
+    <Word from="ОНЭ" to="ОНА" />
+    <Word from="ПРЗКТИЧЄСКИ" to="ПРАКТИЧЕСКИ" />
+    <Word from="ЛЄСУ" to="ЛЕСУ" />
+    <Word from="УСЛОБИЯМ" to="УСЛОВИЯМ" />
+    <Word from="СПЗСТИСЬ" to="СПАСТИСЬ" />
+    <Word from="РЗЗВИВЗЮЩИЄСЯ" to="РАЗВИВАЮЩИЕСЯ" />
+    <Word from="ШЭПКИ" to="ШАПКИ" />
+    <Word from="ЗНЗЄМ" to="ЗНАЕМ" />
+    <Word from="СООИРЭЄМСЯ" to="СОБИРАЕМСЯ" />
+    <Word from="БЫЯСНИТЬ" to="ВЫЯСНИТЬ" />
+    <Word from="СЗМ" to="САМ" />
+    <Word from="РЗСПОЗНЗТЬ" to="РАСПОЗНАТЬ" />
+    <Word from="УЗНЗТЬ" to="УЗНАТЬ" />
+    <Word from="КЭЖЄТСЯ" to="КАЖЕТСЯ" />
+    <Word from="ОРЄИТЗЛЬНЬІЄ" to="ОРБИТАЛЬНЫЕ" />
+    <Word from="ЛЄТЭТЄЛЬНЬІЄ" to="ЛЕТАТЕЛЬНЫЕ" />
+    <Word from="ЗППЗРЕТЬІ" to="АППАРАТЫ" />
+    <Word from="ЖЄ" to="ЖЕ" />
+    <Word from="ТЗКЗЯ" to="ТАКАЯ" />
+    <Word from="МЗЛЄНЬКЗЯ" to="МАЛЕНЬКАЯ" />
+    <Word from="ПЛЭНЄТЗ" to="ПЛАНЕТА" />
+    <Word from="СПЗІІЬКО" to="СТОЛЬКО" />
+    <Word from="бЬІЛ3" to="БЫЛА" />
+    <Word from="ЁЕСЧИСЛЄННОЄ" to="БЕСЧИСЛЕННОЕ" />
+    <Word from="МЗГНИїНЬІХ" to="МАГНИТНЫХ" />
+    <Word from="ПОСТраД3Л" to="ПОСТРАДАЛ" />
+    <Word from="ДЗЖЄ" to="ДАЖЕ" />
+    <Word from="РЗЗНЬІМИ" to="РАЗНЫМИ" />
+    <Word from="СУЩЄСТБОВЭНИЄ" to="СУЩЕСТВОВАНИЕ" />
+    <Word from="ПЛаНЄїЬІ" to="ПЛАНЕТЫ" />
+    <Word from="ПОДВЄРГЛЗСЬ" to="ПОДВЕРГЛАСЬ" />
+    <Word from="ОПЗСІ-ІОСТИ" to="ОПАСНОСТИ" />
+    <Word from="ПЛЗНЄТЄ" to="ПЛАНЕТЕ" />
+    <Word from="Н0" to="НО" />
+    <Word from="бЬІ" to="БЫ" />
+    <Word from="ОТДЗЛЄННЫЄ" to="ОТДАЛЁННЫЕ" />
+    <Word from="ПОЛЯРНЬІЄ" to="ПОЛЯРНЫЕ" />
+    <Word from="ЦЄЛЬІ-О" to="ЦЕЛЬЮ" />
+    <Word from="ПЄЩЄРЗХ" to="ПЕЩЕРАХ" />
+    <Word from="НЗПОЛНЄННЬІХ" to="НАПОЛНЕННЫХ" />
+    <Word from="ИСПЗРЄНИЯМИ" to="ИСПАРЕНИЯМИ" />
+    <Word from="МИНИЗТЮРНЬІЄ" to="МИНИАТЮРНЫЕ" />
+    <Word from="ТЭКЗЯ" to="ТАКАЯ" />
+    <Word from="ПрИСП0СОбИТЬСЯ" to="ПРИСПОСОБИТЬСЯ" />
+    <Word from="НЄОЄХОДИМЬІЄ" to="НЕОБХОДИМЫЕ" />
+    <Word from="ОРГВНИЧЄСКИЄ" to="ОРГАНИЧЕСКИЕ" />
+    <Word from="МЗРСИЗНСКИЄ" to="МАРСИАНСКИЕ" />
+    <Word from="МЄСТЄ" to="МЕСТЕ" />
+    <Word from="І\/ІАККЕЙШ" to="МАККЕЙН" />
+    <Word from="НЗХОДЯЩИЄСЯ" to="НАХОДЯЩИЕСЯ" />
+    <Word from="НЄЗКТИВНОМ" to="НЕАКТИВНОМ" />
+    <Word from="ЗЭСНЯТЬ" to="ЗАСНЯТЬ" />
+    <Word from="ОРГЗНИЗМЬІ" to="ОРГАНИЗМЫ" />
+    <Word from="ВЗЕИМОДЄЙСТВОВЕТЬ" to="ВЗАИМОДЕЙСТВОВАТЬ" />
+    <Word from="ПУТЄШЄСТБИЄ" to="ПУТЕШЕСТВИЕ" />
+    <Word from="ПуСїЬІННЫХ" to="ПУСТЫННЫХ" />
+    <Word from="ТЗКИХ" to="ТАКИХ" />
+    <Word from="ПЄРЄТЗСКИВЗЄМ" to="ПЕРЕТАСКИВАЕМ" />
+    <Word from="ЧТ0" to="ЧТО" />
+    <Word from="ВЄСЬМЗ" to="ВЕСЬМА" />
+    <Word from="ПОЛОСЗМИ" to="ПОЛОСАМИ" />
+    <Word from="ОрїЭНИЗМЬІ" to="ОРГАНИЗМЫ" />
+    <Word from="ОЁЛЗСТИ" to="ОБЛАСТИ" />
+    <Word from="ЯБЛЯЮТСЯ" to="ЯВЛЯЮТСЯ" />
+    <Word from="ЦЄЛЬЮ" to="ЦЕЛЬЮ" />
+    <Word from="ПОИСКОБ" to="ПОИСКОВ" />
+    <Word from="ДОКЗЗЗТЄІІЬСТВ" to="ДОКАЗАТЕЛЬСТВ" />
+    <Word from="МОЖЄТ" to="МОЖЕТ" />
+    <Word from="НЭХОДИТЬСЯ" to="НАХОДИТЬСЯ" />
+    <Word from="ОЧЄНЬ" to="ОЧЕНЬ" />
+    <Word from="СРЗВНИТЬ" to="СРАВНИТЬ" />
+    <Word from="ОЄНЗРУЖИЛ" to="ОБНАРУЖИЛ" />
+    <Word from="ЛЬДЗ" to="ЛЬДА" />
+    <Word from="ПОТЄПЛЄНИЄІИ" to="ПОТЕПЛЕНИЕМ" />
+    <Word from="ПОХОЛОДЗНИЄБД" to="ПОХОЛОДАНИЕМ" />
+    <Word from="КЭК" to="КАК" />
+    <Word from="ТЄЛО" to="ТЕЛО" />
+    <Word from="бОЛЬШЄ" to="БОЛЬШЕ" />
+    <Word from="НЭКЛОНЯЄТСЯ" to="НАКЛОНЯЕТСЯ" />
+    <Word from="СОІІНЦУ" to="СОЛНЦУ" />
+    <Word from="СТ3бИЛИЗИрОБЗТЬ" to="СТАБИЛИЗИРОВАТЬ" />
+    <Word from="СТЭБИЛЬНЭ" to="СТАБИЛЬНА" />
+    <Word from="МИЛІІИОНОВ" to="МИЛЛИОНОВ" />
+    <Word from="НЗЗЭД" to="НАЗАД" />
+    <Word from="ТЄПЛ0" to="ТЕПЛО" />
+    <Word from="ПОІІЯРНЫХ" to="ПОЛЯРНЫХ" />
+    <Word from="СОІІЕНЫМИ" to="СОЛЕНЫМИ" />
+    <Word from="КЕКИМИ" to="КАКИМИ" />
+    <Word from="кислютнюсггь" to="кислотность" />
+    <Word from="ТЗМ" to="ТАМ" />
+    <Word from="ОРГЗНИЗМЫ" to="ОРГАНИЗМЫ" />
+    <Word from="СУЩЄСТВОВЄТЬ" to="СУЩЕСТВОВАТЬ" />
+    <Word from="ВНИМЗНИЄ" to="ВНИМАНИЕ" />
+    <Word from="СДЄЛЗЄТ" to="СДЕЛАЕТ" />
+    <Word from="ПОЗНЭКОМИТЬСЯ" to="ПОЗНАКОМИТЬСЯ" />
+    <Word from="НЭШИМ" to="НАШИМ" />
+    <Word from="ДОКЗЗЭТЄЛЬСТБО" to="ДОКАЗАТЕЛЬСТВО" />
+    <Word from="ЩЗЗЩЄНИЯ" to="ВРАЩЕНИЯ" />
+    <Word from="бЬІЛ0" to="БЫЛО" />
+    <Word from="ОЄЛЕСТЯХ" to="ОБЛАСТЯХ" />
+    <Word from="бЬІЛИ" to="БЫЛИ" />
+    <Word from="РЭЗМЬІШЛЯІІИ" to="РАЗМЫШЛЯЛИ" />
+    <Word from="КОЛИЧЄСТБЄ" to="КОЛИЧЕСТВЕ" />
+    <Word from="ЩЄІІОЧНЫЄ" to="ЩЕЛОЧНЫЕ" />
+    <Word from="НЄКОТЩЗЬІЄ" to="НЕКОТОРЫЕ" />
+    <Word from="ПрИБІ1ЕКуї" to="ПРИВЛЕКУТ" />
+    <Word from="НЗЗЬІВЭЄМЫЄ" to="НАЗЫВАЕМЫЕ" />
+    <Word from="Чї06Ы" to="ЧТОБЫ" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords>
+    <WordPart from="Є" to="Е" />
+    <WordPart from="ЬІ" to="Ы" />
+    <WordPart from="КЗ" to="КА" />
+    <WordPart from="ЛЗ" to="ЛА" />
+    <WordPart from="НЗ" to="НА" />
+    <WordPart from="ШЗ" to="ША" />
+    <WordPart from="І\/І" to="М" />
+  </PartialWords>
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions />
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/spa_OCRFixReplaceList.xml

@@ -0,0 +1,946 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <!-- Abreviaturas simples -->
+    <Word from="KBs" to="kB" />
+    <Word from="Vd" to="Ud" />
+    <Word from="N°" to="N.°" />
+    <Word from="n°" to="n.°" />
+    <Word from="nro." to="n.°" />
+    <Word from="Nro." to="N.°" />
+    <!-- Ortografía básica -->
+    <Word from="aca" to="acá" />
+    <Word from="actuas" to="actúas" />
+    <Word from="actues" to="actúes" />
+    <Word from="adios" to="adiós" />
+    <Word from="agarrenla" to="agárrenla" />
+    <Word from="agarrenlo" to="agárrenlo" />
+    <Word from="agarrandose" to="agarrándose" />
+    <Word from="algun" to="algún" />
+    <Word from="alli" to="allí" />
+    <Word from="alla" to="allá" />
+    <Word from="alejate" to="aléjate" />
+    <Word from="ahi" to="ahí" />
+    <Word from="angel" to="ángel" />
+    <Word from="angeles" to="ángeles" />
+    <Word from="apagala" to="apágala" />
+    <Word from="aqui" to="aquí" />
+    <Word from="asi" to="así" />
+    <Word from="bahia" to="bahía" />
+    <Word from="busqueda" to="búsqueda" />
+    <Word from="busquedas" to="búsquedas" />
+    <Word from="callate" to="cállate" />
+    <Word from="carcel" to="cárcel" />
+    <Word from="camara" to="cámara" />
+    <Word from="caido" to="caído" />
+    <Word from="cabron" to="cabrón" />
+    <Word from="camion" to="camión" />
+    <Word from="codigo" to="código" />
+    <Word from="codigos" to="códigos" />
+    <Word from="comence" to="comencé" />
+    <Word from="comprate" to="cómprate" />
+    <Word from="consegui" to="conseguí" />
+    <Word from="confias" to="confías" />
+    <Word from="convertira" to="convertirá" />
+    <Word from="corazon" to="corazón" />
+    <Word from="crei" to="creí" />
+    <Word from="creia" to="creía" />
+    <Word from="creido" to="creído" />
+    <Word from="creiste" to="creíste" />
+    <Word from="cubrenos" to="cúbrenos" />
+    <Word from="comio" to="comió" />
+    <Word from="dara" to="dará" />
+    <Word from="dia" to="día" />
+    <Word from="dias" to="días" />
+    <Word from="debio" to="debió" />
+    <Word from="demelo" to="démelo" />
+    <Word from="dimelo" to="dímelo" />
+    <Word from="denoslo" to="dénoslo" />
+    <Word from="deselo" to="déselo" />
+    <Word from="decia" to="decía" />
+    <Word from="decian" to="decían" />
+    <Word from="detras" to="detrás" />
+    <Word from="deberia" to="debería" />
+    <Word from="deberas" to="deberás" />
+    <Word from="deberias" to="deberías" />
+    <Word from="deberian" to="deberían" />
+    <Word from="deberiamos" to="deberíamos" />
+    <Word from="dejame" to="déjame" />
+    <Word from="dejate" to="déjate" />
+    <Word from="dejalo" to="déjalo" />
+    <Word from="dejarian" to="dejarían" />
+    <Word from="damela" to="dámela" />
+    <Word from="despues" to="después" />
+    <Word from="diciendome" to="diciéndome" />
+    <Word from="dificil" to="difícil" />
+    <Word from="dificiles" to="difíciles" />
+    <Word from="disculpate" to="discúlpate" />
+    <Word from="dolares" to="dólares" />
+    <Word from="hechar" to="echar" />
+    <Word from="examenes" to="exámenes" />
+    <Word from="empezo" to="empezó" />
+    <Word from="empujon" to="empujón" />
+    <Word from="empujalo" to="empújalo" />
+    <Word from="escondanme" to="escóndanme" />
+    <Word from="esperame" to="espérame" />
+    <Word from="estara" to="estará" />
+    <Word from="estare" to="estaré" />
+    <Word from="estaria" to="estaría" />
+    <Word from="estan" to="están" />
+    <Word from="estaran" to="estarán" />
+    <Word from="estabamos" to="estábamos" />
+    <Word from="estuvieramos" to="estuviéramos" />
+    <Word from="exito" to="éxito" />
+    <Word from="facil" to="fácil" />
+    <Word from="fiscalia" to="fiscalía" />
+    <Word from="fragil" to="frágil" />
+    <Word from="fragiles" to="frágiles" />
+    <Word from="frances" to="francés" />
+    <Word from="gustaria" to="gustaría" />
+    <Word from="habia" to="había" />
+    <Word from="habias" to="habías" />
+    <Word from="habian" to="habían" />
+    <Word from="habrian" to="habrían" />
+    <Word from="habrias" to="habrías" />
+    <Word from="hagalo" to="hágalo" />
+    <Word from="haria" to="haría" />
+    <Word from="increible" to="increíble" />
+    <Word from="incredulo" to="incrédulo" />
+    <Word from="intentalo" to="inténtalo" />
+    <Word from="ire" to="iré" />
+    <Word from="jovenes" to="jóvenes" />
+    <Word from="ladron" to="ladrón" />
+    <Word from="linea" to="línea" />
+    <Word from="llamame" to="llámame" />
+    <Word from="llevalo" to="llévalo" />
+    <Word from="mama" to="mamá" />
+    <Word from="maricon" to="maricón" />
+    <Word from="mayoria" to="mayoría" />
+    <Word from="metodo" to="método" />
+    <Word from="metodos" to="métodos" />
+    <Word from="mio" to="mío" />
+    <Word from="mostro" to="mostró" />
+    <Word from="morira" to="morirá" />
+    <Word from="muevete" to="muévete" />
+    <Word from="murio" to="murió" />
+    <Word from="numero" to="número" />
+    <Word from="numeros" to="números" />
+    <Word from="ningun" to="ningún" />
+    <Word from="oido" to="oído" />
+    <Word from="oidos" to="oídos" />
+    <Word from="oimos" to="oímos" />
+    <Word from="oiste" to="oíste" />
+    <Word from="pasale" to="pásale" />
+    <Word from="pasame" to="pásame" />
+    <Word from="paraiso" to="paraíso" />
+    <Word from="parate" to="párate" />
+    <Word from="pense" to="pensé" />
+    <Word from="peluqueria" to="peluquería" />
+    <Word from="platano" to="plátano" />
+    <Word from="plastico" to="plástico" />
+    <Word from="plasticos" to="plásticos" />
+    <Word from="policia" to="policía" />
+    <Word from="policias" to="policías" />
+    <Word from="poster" to="póster" />
+    <Word from="podia" to="podía" />
+    <Word from="podias" to="podías" />
+    <Word from="podria" to="podría" />
+    <Word from="podrian" to="podrían" />
+    <Word from="podrias" to="podrías" />
+    <Word from="podriamos" to="podríamos" />
+    <Word from="prometio" to="prometió" />
+    <Word from="proposito" to="propósito" />
+    <Word from="pideselo" to="pídeselo" />
+    <Word from="ponganse" to="pónganse" />
+    <Word from="prometeme" to="prométeme" />
+    <Word from="publico" to="público" />
+    <Word from="publicos" to="públicos" />
+    <Word from="publicamente" to="públicamente" />
+    <Word from="quedate" to="quédate" />
+    <Word from="queria" to="quería" />
+    <Word from="querrias" to="querrías" />
+    <Word from="querian" to="querían" />
+    <Word from="rapido" to="rápido" />
+    <Word from="rapidamente" to="rápidamente" />
+    <Word from="razon" to="razón" />
+    <Word from="rehusen" to="rehúsen" />
+    <Word from="rie" to="ríe" />
+    <Word from="rias" to="rías" />
+    <Word from="rindete" to="ríndete" />
+    <Word from="sacame" to="sácame" />
+    <Word from="sentian" to="sentían" />
+    <Word from="sientate" to="siéntate" />
+    <Word from="sera" to="será" />
+    <Word from="soplon" to="soplón" />
+    <Word from="sueltalo" to="suéltalo" />
+    <Word from="tambien" to="también" />
+    <Word from="teoria" to="teoría" />
+    <Word from="tendra" to="tendrá" />
+    <Word from="telefono" to="teléfono" />
+    <Word from="tipica" to="típica" />
+    <Word from="todavia" to="todavía" />
+    <Word from="tomalo" to="tómalo" />
+    <Word from="tonterias" to="tonterías" />
+    <Word from="torci" to="torcí" />
+    <Word from="traelos" to="tráelos" />
+    <Word from="traiganlo" to="tráiganlo" />
+    <Word from="traiganlos" to="tráiganlos" />
+    <Word from="trio" to="trío" />
+    <Word from="tuvieramos" to="tuviéramos" />
+    <Word from="union" to="unión" />
+    <Word from="ultimo" to="último" />
+    <Word from="ultima" to="última" />
+    <Word from="ultimos" to="últimos" />
+    <Word from="ultimas" to="últimas" />
+    <Word from="unica" to="única" />
+    <Word from="unico" to="único" />
+    <Word from="vamonos" to="vámonos" />
+    <Word from="vayanse" to="váyanse" />
+    <Word from="victima" to="víctima" />
+    <Word from="vivira" to="vivirá" />
+    <Word from="volvio" to="volvió" />
+    <Word from="volvia" to="volvía" />
+    <Word from="volvian" to="volvían" />
+    <!-- Palabras con eír/oír más usadas -->
+    <Word from="reir" to="reír" />
+    <Word from="freir" to="freír" />
+    <Word from="sonreir" to="sonreír" />
+    <Word from="hazmerreir" to="hazmerreír" />
+    <Word from="oir" to="oír" />
+    <Word from="oirlo" to="oírlo" />
+    <Word from="oirte" to="oírte" />
+    <Word from="oirse" to="oírse" />
+    <Word from="oirme" to="oírme" />
+    <Word from="oirle" to="oírle" />
+    <Word from="oirla" to="oírla" />
+    <Word from="oirles" to="oírles" />
+    <Word from="oirnos" to="oírnos" />
+    <Word from="oirlas" to="oírlas" />
+    <!-- Palabras que no llevan acento -->
+    <Word from="bién" to="bien" />
+    <Word from="crímen" to="crimen" />
+    <Word from="fué" to="fue" />
+    <Word from="fuí" to="fui" />
+    <Word from="quiéres" to="quieres" />
+    <Word from="tí" to="ti" />
+    <Word from="dí" to="di" />
+    <Word from="vá" to="va" />
+    <Word from="vé" to="ve" />
+    <Word from="ví" to="vi" />
+    <Word from="vió" to="vio" />
+    <Word from="ó" to="o" />
+    <Word from="clón" to="clon" />
+    <Word from="dió" to="dio" />
+    <Word from="guión" to="guion" />
+    <Word from="dón" to="don" />
+    <Word from="fé" to="fe" />
+    <Word from="áquel" to="aquel" />
+    <!-- Palabras donde se puede prescindir de la tilde diacrítica -->
+    <Word from="éste" to="este" />
+    <Word from="ésta" to="esta" />
+    <Word from="éstos" to="estos" />
+    <Word from="éstas" to="estas" />
+    <Word from="ése" to="ese" />
+    <Word from="ésa" to="esa" />
+    <Word from="ésos" to="esos" />
+    <Word from="ésas" to="esas" />
+    <Word from="sólo" to="solo" />
+    <!-- Errores no relacionados con los tildes -->
+    <Word from="coktel" to="cóctel" />
+    <Word from="cocktel" to="cóctel" />
+    <Word from="conciente" to="consciente" />
+    <Word from="comenzé" to="comencé" />
+    <Word from="desilucionarte" to="desilusionarte" />
+    <Word from="dijieron" to="dijeron" />
+    <Word from="empezé" to="empecé" />
+    <Word from="hize" to="hice" />
+    <Word from="ilucionarte" to="ilusionarte" />
+    <Word from="inconciente" to="inconsciente" />
+    <Word from="quize" to="quise" />
+    <Word from="quizo" to="quiso" />
+    <Word from="verguenza" to="vergüenza" />
+    <!-- Errores en nombres propios o de países -->
+    <Word from="Nuñez" to="Núñez" />
+    <Word from="Ivan" to="Iván" />
+    <Word from="Japon" to="Japón" />
+    <Word from="Monica" to="Mónica" />
+    <Word from="Maria" to="María" />
+    <Word from="Jose" to="José" />
+    <Word from="Ramon" to="Ramón" />
+    <Word from="Garcia" to="García" />
+    <Word from="Gonzalez" to="González" />
+    <Word from="Jesus" to="Jesús" />
+    <Word from="Alvarez" to="Álvarez" />
+    <Word from="Damian" to="Damián" />
+    <Word from="Rene" to="René" />
+    <Word from="Nicolas" to="Nicolás" />
+    <Word from="Jonas" to="Jonás" />
+    <Word from="Lopez" to="López" />
+    <Word from="Hernandez" to="Hernández" />
+    <Word from="Bermudez" to="Bermúdez" />
+    <Word from="Fernandez" to="Fernández" />
+    <Word from="Suarez" to="Suárez" />
+    <Word from="Sofia" to="Sofía" />
+    <Word from="Seneca" to="Séneca" />
+    <Word from="Tokyo" to="Tokio" />
+    <Word from="Canada" to="Canadá" />
+    <Word from="Paris" to="París" />
+    <Word from="Turquia" to="Turquía" />
+    <Word from="Mexico" to="México" />
+    <Word from="Mejico" to="México" />
+    <Word from="Matias" to="Matías" />
+    <Word from="Valentin" to="Valentín" />
+    <Word from="mejicano" to="mexicano" />
+    <Word from="mejicanos" to="mexicanos" />
+    <Word from="mejicana" to="mexicana" />
+    <Word from="mejicanas" to="mexicanas" />
+    <!-- Creados por SE -->
+    <Word from="io" to="lo" />
+    <Word from="ia" to="la" />
+    <Word from="ie" to="le" />
+    <Word from="Io" to="lo" />
+    <Word from="Ia" to="la" />
+    <Word from="AI" to="Al" />
+    <Word from="Ie" to="le" />
+    <Word from="EI" to="El" />
+    <Word from="subafluente" to="subafluente" />
+    <Word from="aflójalo" to="aflójalo" />
+    <Word from="Aflójalo" to="Aflójalo" />
+    <Word from="perdi" to="perdí" />
+    <Word from="Podria" to="Podría" />
+    <Word from="confia" to="confía" />
+    <Word from="pasaria" to="pasaría" />
+    <Word from="Podias" to="Podías" />
+    <Word from="responsabke" to="responsable" />
+    <Word from="Todavia" to="Todavía" />
+    <Word from="envien" to="envíen" />
+    <Word from="Queria" to="Quería" />
+    <Word from="tio" to="tío" />
+    <Word from="traido" to="traído" />
+    <Word from="Asi" to="Así" />
+    <Word from="elegi" to="elegí" />
+    <Word from="habria" to="habría" />
+    <Word from="encantaria" to="encantaría" />
+    <Word from="leido" to="leído" />
+    <Word from="conocias" to="conocías" />
+    <Word from="harias" to="harías" />
+    <Word from="Aqui" to="Aquí" />
+    <Word from="decidi" to="decidí" />
+    <Word from="mia" to="mía" />
+    <Word from="Crei" to="Creí" />
+    <Word from="podiamos" to="podíamos" />
+    <Word from="avisame" to="avísame" />
+    <Word from="debia" to="debía" />
+    <Word from="pensarias" to="pensarías" />
+    <Word from="reuniamos" to="reuníamos" />
+    <Word from="POÏ" to="por" />
+    <Word from="vendria" to="vendría" />
+    <Word from="caida" to="caída" />
+    <Word from="venian" to="venían" />
+    <Word from="compañias" to="compañías" />
+    <Word from="leiste" to="leíste" />
+    <Word from="Leiste" to="Leíste" />
+    <Word from="fiaria" to="fiaría" />
+    <Word from="Hungria" to="Hungría" />
+    <Word from="fotografia" to="fotografía" />
+    <Word from="cafeteria" to="cafetería" />
+    <Word from="Digame" to="Dígame" />
+    <Word from="debias" to="debías" />
+    <Word from="tendria" to="tendría" />
+    <Word from="CÏGO" to="creo" />
+    <Word from="anteg" to="antes" />
+    <Word from="SóIo" to="Solo" />
+    <Word from="Ilamándola" to="llamándola" />
+    <Word from="Cáflaté" to="Cállate" />
+    <Word from="Ilamaste" to="llamaste" />
+    <Word from="daria" to="daría" />
+    <Word from="Iargaba" to="largaba" />
+    <Word from="Yati" to="Y a ti" />
+    <Word from="querias" to="querías" />
+    <Word from="Iimpiarlo" to="limpiarlo" />
+    <Word from="Iargado" to="largado" />
+    <Word from="galeria" to="galería" />
+    <Word from="Bartomeu" to="Bertomeu" />
+    <Word from="Iocalizarlo" to="localizarlo" />
+    <Word from="Ilámame" to="llámame" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords />
+  <PartialLines>
+    <!-- Varios -->
+    <LinePart from="de gratis" to="gratis" />
+    <LinePart from="si quiera" to="siquiera" />
+    <LinePart from="Cada una de los" to="Cada uno de los" />
+    <LinePart from="Cada uno de las" to="Cada una de las" />
+    <!-- Uso incorrecto de haber / a ver -->
+    <LinePart from="haber que" to="a ver qué" />
+    <LinePart from="haber qué" to="a ver qué" />
+    <LinePart from="Haber si" to="A ver si" />
+    <!-- Ponombres exclamativos o interrogativos Parte 1 -->
+    <LinePart from=" que hora" to=" qué hora" />
+    <LinePart from="yo que se" to="yo qué sé" />
+    <LinePart from="Yo que se" to="Yo qué sé" />
+    <!-- Acentos al final de los signos de exclamación -->
+    <LinePart from=" tu!" to=" tú!" />
+    <LinePart from=" si!" to=" sí!" />
+    <LinePart from=" mi!" to=" mí!" />
+    <LinePart from=" el!" to=" él!" />
+    <!-- Acentos al final de los signos de interrogación -->
+    <LinePart from=" tu?" to=" tú?" />
+    <LinePart from=" si?" to=" sí?" />
+    <LinePart from=" mi?" to=" mí?" />
+    <LinePart from=" el?" to=" él?" />
+    <LinePart from=" aun?" to=" aún?" />
+    <LinePart from=" mas?" to=" más?" />
+    <LinePart from=" que?" to=" qué?" />
+    <LinePart from=" paso?" to=" pasó?" />
+    <LinePart from=" cuando?" to=" cuándo?" />
+    <LinePart from=" cuanto?" to=" cuánto?" />
+    <LinePart from=" cuanta?" to=" cuánta?" />
+    <LinePart from=" cuantas?" to=" cuántas?" />
+    <LinePart from=" cuantos?" to=" cuántos?" />
+    <LinePart from=" donde?" to=" dónde?" />
+    <LinePart from=" quien?" to=" quién?" />
+    <LinePart from=" como?" to=" cómo?" />
+    <LinePart from=" adonde?" to=" adónde?" />
+    <LinePart from=" cual?" to=" cuál?" />
+    <!-- Acentos en los signos de interrogación completos -->
+    <LinePart from="¿Si?" to="¿Sí?" />
+    <LinePart from="¿esta bien?" to="¿está bien?" />
+    <!-- Enunciados que son a la vez interrogativos y exclamativos -->
+    <LinePart from="¿Pero qué haces?" to="¡¿Pero qué haces?!" />
+    <LinePart from="¿pero qué haces?" to="¡¿pero qué haces?!" />
+    <LinePart from="¿Es que no me has escuchado?" to="¡¿Es que no me has escuchado?!" />
+    <LinePart from="¡¿es que no me has escuchado?!" to="¡¿es que no me has escuchado?!" />
+    <!-- Acentos al principio de los signos de interrogación con minúsculas -->
+    <LinePart from="¿aun" to="¿aún" />
+    <LinePart from="¿tu " to="¿tú " />
+    <LinePart from="¿que " to="¿qué " />
+    <LinePart from="¿sabes que" to="¿sabes qué" />
+    <LinePart from="¿sabes adonde" to="¿sabes adónde" />
+    <LinePart from="¿sabes cual" to="¿sabes cuál" />
+    <LinePart from="¿sabes quien" to="¿sabes quién" />
+    <LinePart from="¿sabes como" to="¿sabes cómo" />
+    <LinePart from="¿sabes cuan" to="¿sabes cuán" />
+    <LinePart from="¿sabes cuanto" to="¿sabes cuánto" />
+    <LinePart from="¿sabes cuanta" to="¿sabes cuánta" />
+    <LinePart from="¿sabes cuantos" to="¿sabes cuántos" />
+    <LinePart from="¿sabes cuantas" to="¿sabes cuántas" />
+    <LinePart from="¿sabes cuando" to="¿sabes cuándo" />
+    <LinePart from="¿sabes donde" to="¿sabes dónde" />
+    <LinePart from="¿sabe que" to="¿sabe qué" />
+    <LinePart from="¿sabe adonde" to="¿sabe adónde" />
+    <LinePart from="¿sabe cual" to="¿sabe cuál" />
+    <LinePart from="¿sabe quien" to="¿sabe quién" />
+    <LinePart from="¿sabe como" to="¿sabe cómo" />
+    <LinePart from="¿sabe cuan" to="¿sabe cuán" />
+    <LinePart from="¿sabe cuanto" to="¿sabe cuánto" />
+    <LinePart from="¿sabe cuanta" to="¿sabe cuánta" />
+    <LinePart from="¿sabe cuantos" to="¿sabe cuántos" />
+    <LinePart from="¿sabe cuantas" to="¿sabe cuántas" />
+    <LinePart from="¿sabe cuando" to="¿sabe cuándo" />
+    <LinePart from="¿sabe donde" to="¿sabe dónde" />
+    <LinePart from="¿saben que" to="¿saben qué" />
+    <LinePart from="¿saben adonde" to="¿saben adónde" />
+    <LinePart from="¿saben cual" to="¿saben cuál" />
+    <LinePart from="¿saben quien" to="¿saben quién" />
+    <LinePart from="¿saben como" to="¿saben cómo" />
+    <LinePart from="¿saben cuan" to="¿saben cuán" />
+    <LinePart from="¿saben cuanto" to="¿saben cuánto" />
+    <LinePart from="¿saben cuanta" to="¿saben cuánta" />
+    <LinePart from="¿saben cuantos" to="¿saben cuántos" />
+    <LinePart from="¿saben cuantas" to="¿saben cuántas" />
+    <LinePart from="¿saben cuando" to="¿saben cuándo" />
+    <LinePart from="¿saben donde" to="¿saben dónde" />
+    <LinePart from="¿de que" to="¿de qué" />
+    <LinePart from="¿de donde" to="¿de dónde" />
+    <LinePart from="¿de cual" to="¿de cuál" />
+    <LinePart from="¿de quien" to="¿de quién" />
+    <LinePart from="¿de cuanto" to="¿de cuánto" />
+    <LinePart from="¿de cuanta" to="¿de cuánta" />
+    <LinePart from="¿de cuantos" to="¿de cuántos" />
+    <LinePart from="¿de cuantas" to="¿de cuántas" />
+    <LinePart from="¿de cuando" to="¿de cuándo" />
+    <LinePart from="¿sobre que" to="¿sobre qué" />
+    <LinePart from="¿como " to="¿cómo " />
+    <LinePart from="¿cual " to="¿cuál " />
+    <LinePart from="¿en cual" to="¿en cuál" />
+    <LinePart from="¿cuando" to="¿cuándo" />
+    <LinePart from="¿hasta cual" to="¿hasta cuál" />
+    <LinePart from="¿hasta quien" to="¿hasta quién" />
+    <LinePart from="¿hasta cuanto" to="¿hasta cuánto" />
+    <LinePart from="¿hasta cuantas" to="¿hasta cuántas" />
+    <LinePart from="¿hasta cuantos" to="¿hasta cuántos" />
+    <LinePart from="¿hasta cuando" to="¿hasta cuándo" />
+    <LinePart from="¿hasta donde" to="¿hasta dónde" />
+    <LinePart from="¿hasta que" to="¿hasta qué" />
+    <LinePart from="¿hasta adonde" to="¿hasta adónde" />
+    <LinePart from="¿desde que" to="¿desde qué" />
+    <LinePart from="¿desde cuando" to="¿desde cuándo" />
+    <LinePart from="¿desde quien" to="¿desde quién" />
+    <LinePart from="¿desde donde" to="¿desde dónde" />
+    <LinePart from="¿cuanto" to="¿cuánto" />
+    <LinePart from="¿cuantos" to="¿cuántos" />
+    <LinePart from="¿donde" to="¿dónde" />
+    <LinePart from="¿adonde" to="¿adónde" />
+    <LinePart from="¿con que" to="¿con qué" />
+    <LinePart from="¿con cual" to="¿con cuál" />
+    <LinePart from="¿con quien" to="¿con quién" />
+    <LinePart from="¿con cuantos" to="¿con cuántos" />
+    <LinePart from="¿con cuantas" to="¿con cuántas" />
+    <LinePart from="¿con cuanta" to="¿con cuánta" />
+    <LinePart from="¿con cuanto" to="¿con cuánto" />
+    <LinePart from="¿para donde" to="¿para dónde" />
+    <LinePart from="¿para adonde" to="¿para adónde" />
+    <LinePart from="¿para cuando" to="¿para cuándo" />
+    <LinePart from="¿para que" to="¿para qué" />
+    <LinePart from="¿para quien" to="¿para quién" />
+    <LinePart from="¿para cuanto" to="¿para cuánto" />
+    <LinePart from="¿para cuanta" to="¿para cuánta" />
+    <LinePart from="¿para cuantos" to="¿para cuántos" />
+    <LinePart from="¿para cuantas" to="¿para cuántas" />
+    <LinePart from="¿a donde" to="¿a dónde" />
+    <LinePart from="¿a que" to="¿a qué" />
+    <LinePart from="¿a cual" to="¿a cuál" />
+    <LinePart from="¿a quien" to="¿a quien" />
+    <LinePart from="¿a como" to="¿a cómo" />
+    <LinePart from="¿a cuanto" to="¿a cuánto" />
+    <LinePart from="¿a cuanta" to="¿a cuánta" />
+    <LinePart from="¿a cuantos" to="¿a cuántos" />
+    <LinePart from="¿a cuantas" to="¿a cuántas" />
+    <LinePart from="¿por que" to="¿por qué" />
+    <LinePart from="¿por cual" to="¿por cuál" />
+    <LinePart from="¿por quien" to="¿por quién" />
+    <LinePart from="¿por cuanto" to="¿por cuánto" />
+    <LinePart from="¿por cuanta" to="¿por cuánta" />
+    <LinePart from="¿por cuantos" to="¿por cuántos" />
+    <LinePart from="¿por cuantas" to="¿por cuántas" />
+    <LinePart from="¿por donde" to="¿por dónde" />
+    <LinePart from="¿porque" to="¿por qué" />
+    <LinePart from="¿porqué" to="¿por qué" />
+    <LinePart from="¿y que" to="¿y qué" />
+    <LinePart from="¿y como" to="¿y cómo" />
+    <LinePart from="¿y cuando" to="¿y cuándo" />
+    <LinePart from="¿y cual" to="¿y cuál" />
+    <LinePart from="¿y quien" to="¿y quién" />
+    <LinePart from="¿y cuanto" to="¿y cuánto" />
+    <LinePart from="¿y cuanta" to="¿y cuánta" />
+    <LinePart from="¿y cuantos" to="¿y cuántos" />
+    <LinePart from="¿y cuantas" to="¿y cuántas" />
+    <LinePart from="¿y donde" to="¿y dónde" />
+    <LinePart from="¿y adonde" to="¿y adónde" />
+    <LinePart from="¿quien " to="¿quién " />
+    <LinePart from="¿esta " to="¿está " />
+    <LinePart from="¿estas " to="¿estás " />
+    <!-- Acentos al principio de los signos de interrogación con mayúsculas -->
+    <LinePart from="¿Aun" to="¿Aún" />
+    <LinePart from="¿Que " to="¿Qué " />
+    <LinePart from="¿Sabes que" to="¿Sabes qué" />
+    <LinePart from="¿Sabes adonde" to="¿Sabes adónde" />
+    <LinePart from="¿Sabes cual" to="¿Sabes cuál" />
+    <LinePart from="¿Sabes quien" to="¿Sabes quién" />
+    <LinePart from="¿Sabes como" to="¿Sabes cómo" />
+    <LinePart from="¿Sabes cuan" to="¿Sabes cuán" />
+    <LinePart from="¿Sabes cuanto" to="¿Sabes cuánto" />
+    <LinePart from="¿Sabes cuanta" to="¿Sabes cuánta" />
+    <LinePart from="¿Sabes cuantos" to="¿Sabes cuántos" />
+    <LinePart from="¿Sabes cuantas" to="¿Sabes cuántas" />
+    <LinePart from="¿Sabes cuando" to="¿Sabes cuándo" />
+    <LinePart from="¿Sabes donde" to="¿Sabes dónde" />
+    <LinePart from="¿Sabe que" to="¿Sabe qué" />
+    <LinePart from="¿Sabe adonde" to="¿Sabe adónde" />
+    <LinePart from="¿Sabe cual" to="¿Sabe cuál" />
+    <LinePart from="¿Sabe quien" to="¿Sabe quién" />
+    <LinePart from="¿Sabe como" to="¿Sabe cómo" />
+    <LinePart from="¿Sabe cuan" to="¿Sabe cuán" />
+    <LinePart from="¿Sabe cuanto" to="¿Sabe cuánto" />
+    <LinePart from="¿Sabe cuanta" to="¿Sabe cuánta" />
+    <LinePart from="¿Sabe cuantos" to="¿Sabe cuántos" />
+    <LinePart from="¿Sabe cuantas" to="¿Sabe cuántas" />
+    <LinePart from="¿Sabe cuando" to="¿Sabe cuándo" />
+    <LinePart from="¿Sabe donde" to="¿Sabe dónde" />
+    <LinePart from="¿Saben que" to="¿Saben qué" />
+    <LinePart from="¿Saben adonde" to="¿Saben adónde" />
+    <LinePart from="¿Saben cual" to="¿Saben cuál" />
+    <LinePart from="¿Saben quien" to="¿Saben quién" />
+    <LinePart from="¿Saben como" to="¿Saben cómo" />
+    <LinePart from="¿Saben cuan" to="¿Saben cuán" />
+    <LinePart from="¿Saben cuanto" to="¿Saben cuánto" />
+    <LinePart from="¿Saben cuanta" to="¿Saben cuánta" />
+    <LinePart from="¿Saben cuantos" to="¿Saben cuántos" />
+    <LinePart from="¿Saben cuantas" to="¿Saben cuántas" />
+    <LinePart from="¿Saben cuando" to="¿Saben cuándo" />
+    <LinePart from="¿Saben donde" to="¿Saben dónde" />
+    <LinePart from="¿De que" to="¿De qué" />
+    <LinePart from="¿De donde" to="¿De dónde" />
+    <LinePart from="¿De cual" to="¿De cuál" />
+    <LinePart from="¿De quien" to="¿De quién" />
+    <LinePart from="¿De cuanto" to="¿De cuánto" />
+    <LinePart from="¿De cuanta" to="¿De cuánta" />
+    <LinePart from="¿De cuantos" to="¿De cuántos" />
+    <LinePart from="¿De cuantas" to="¿De cuántas" />
+    <LinePart from="¿De cuando" to="¿De cuándo" />
+    <LinePart from="¿Desde que" to="¿Desde qué" />
+    <LinePart from="¿Desde cuando" to="¿Desde cuándo" />
+    <LinePart from="¿Desde quien" to="¿Desde quién" />
+    <LinePart from="¿Desde donde" to="¿Desde dónde" />
+    <LinePart from="¿Sobre que" to="¿Sobre qué" />
+    <LinePart from="¿Como " to="¿Cómo " />
+    <LinePart from="¿Cual " to="¿Cuál " />
+    <LinePart from="¿En cual" to="¿En cuál" />
+    <LinePart from="¿Cuando" to="¿Cuándo" />
+    <LinePart from="¿Hasta cual" to="¿Hasta cuál" />
+    <LinePart from="¿Hasta quien" to="¿Hasta quién" />
+    <LinePart from="¿Hasta cuanto" to="¿Hasta cuánto" />
+    <LinePart from="¿Hasta cuantas" to="¿Hasta cuántas" />
+    <LinePart from="¿Hasta cuantos" to="¿Hasta cuántos" />
+    <LinePart from="¿Hasta cuando" to="¿Hasta cuándo" />
+    <LinePart from="¿Hasta donde" to="¿Hasta dónde" />
+    <LinePart from="¿Hasta que" to="¿Hasta qué" />
+    <LinePart from="¿Hasta adonde" to="¿Hasta adónde" />
+    <LinePart from="¿Cuanto" to="¿Cuánto" />
+    <LinePart from="¿Cuantos" to="¿Cuántos" />
+    <LinePart from="¿Donde" to="¿Dónde" />
+    <LinePart from="¿Adonde" to="¿Adónde" />
+    <LinePart from="¿Con que" to="¿Con qué" />
+    <LinePart from="¿Con cual" to="¿Con cuál" />
+    <LinePart from="¿Con quien" to="¿Con quién" />
+    <LinePart from="¿Con cuantos" to="¿Con cuántos" />
+    <LinePart from="¿Con cuanta" to="¿Con cuántas" />
+    <LinePart from="¿Con cuanta" to="¿Con cuánta" />
+    <LinePart from="¿Con cuanto" to="¿Con cuánto" />
+    <LinePart from="¿Para donde" to="¿Para dónde" />
+    <LinePart from="¿Para adonde" to="¿Para adónde" />
+    <LinePart from="¿Para cuando" to="¿Para cuándo" />
+    <LinePart from="¿Para que" to="¿Para qué" />
+    <LinePart from="¿Para quien" to="¿Para quién" />
+    <LinePart from="¿Para cuanto" to="¿Para cuánto" />
+    <LinePart from="¿Para cuanta" to="¿Para cuánta" />
+    <LinePart from="¿Para cuantos" to="¿Para cuántos" />
+    <LinePart from="¿Para cuantas" to="¿Para cuántas" />
+    <LinePart from="¿A donde" to="¿A dónde" />
+    <LinePart from="¿A que" to="¿A qué" />
+    <LinePart from="¿A cual" to="¿A cuál" />
+    <LinePart from="¿A quien" to="¿A quien" />
+    <LinePart from="¿A como" to="¿A cómo" />
+    <LinePart from="¿A cuanto" to="¿A cuánto" />
+    <LinePart from="¿A cuanta" to="¿A cuánta" />
+    <LinePart from="¿A cuantos" to="¿A cuántos" />
+    <LinePart from="¿A cuantas" to="¿A cuántas" />
+    <LinePart from="¿Por que" to="¿Por qué" />
+    <LinePart from="¿Por cual" to="¿Por cuál" />
+    <LinePart from="¿Por quien" to="¿Por quién" />
+    <LinePart from="¿Por cuanto" to="¿Por cuánto" />
+    <LinePart from="¿Por cuanta" to="¿Por cuánta" />
+    <LinePart from="¿Por cuantos" to="¿Por cuántos" />
+    <LinePart from="¿Por cuantas" to="¿Por cuántas" />
+    <LinePart from="¿Por donde" to="¿Por dónde" />
+    <LinePart from="¿Porque" to="¿Por qué" />
+    <LinePart from="¿Porqué" to="¿Por qué" />
+    <LinePart from="¿Y que" to="¿Y qué" />
+    <LinePart from="¿Y como" to="¿Y cómo" />
+    <LinePart from="¿Y cuando" to="¿Y cuándo" />
+    <LinePart from="¿Y cual" to="¿Y cuál" />
+    <LinePart from="¿Y quien" to="¿Y quién" />
+    <LinePart from="¿Y cuanto" to="¿Y cuánto" />
+    <LinePart from="¿Y cuanta" to="¿Y cuánta" />
+    <LinePart from="¿Y cuantos" to="¿Y cuántos" />
+    <LinePart from="¿Y cuantas" to="¿Y cuántas" />
+    <LinePart from="¿Y donde" to="¿Y dónde" />
+    <LinePart from="¿Y adonde" to="¿Y adónde" />
+    <LinePart from="¿Quien " to="¿Quién " />
+    <LinePart from="¿Esta " to="¿Está " />
+    <!-- Tilde diacrítica en oraciones interrogativas o exclamativas indirectas -->
+    <LinePart from="el porque" to="el porqué" />
+    <LinePart from="su porque" to="su porqué" />
+    <LinePart from="los porqués" to="los porqués" />
+    <!-- aún -->
+    <LinePart from="aun," to="aún," />
+    <LinePart from="aun no" to="aún no" />
+    <!-- dé -->
+    <LinePart from=" de y " to=" dé y " />
+    <LinePart from=" nos de " to=" nos dé " />
+    <!-- tú -->
+    <LinePart from=" tu ya " to=" tú ya " />
+    <LinePart from="Tu ya " to="Tú ya " />
+    <!-- casos específicos antes de la coma -->
+    <LinePart from=" de, " to=" dé," />
+    <LinePart from=" mi, " to=" mí," />
+    <LinePart from=" tu, " to=" tú," />
+    <LinePart from=" el, " to=" él," />
+    <LinePart from=" te, " to=" té," />
+    <LinePart from=" mas, " to=" más," />
+    <LinePart from=" quien, " to=" quién," />
+    <LinePart from=" cual," to=" cuál," />
+    <LinePart from="porque, " to="porqué," />
+    <LinePart from="cuanto, " to="cuánto," />
+    <LinePart from="cuando, " to="cuándo," />
+    <!-- sé -->
+    <LinePart from=" se," to=" sé," />
+    <LinePart from="se donde" to="sé dónde" />
+    <LinePart from="se cuando" to="sé cuándo" />
+    <LinePart from="se adonde" to="sé adónde" />
+    <LinePart from="se como" to="sé cómo" />
+    <LinePart from="se cual" to="sé cuál" />
+    <LinePart from="se quien" to="sé quién" />
+    <LinePart from="se cuanto" to="sé cuánto" />
+    <LinePart from="se cuanta" to="sé cuánta" />
+    <LinePart from="se cuantos" to="sé cuántos" />
+    <LinePart from="se cuantas" to="sé cuántas" />
+    <LinePart from="se cuan" to="sé cuán" />
+    <!-- si/sí -->
+    <LinePart from=" el si " to=" el sí " />
+    <LinePart from="si mismo" to="sí mismo" />
+    <LinePart from="si misma" to="sí misma" />
+    <!-- Errores de "l" en vez de "i" en casos específicos -->
+    <LinePart from=" llegal" to=" ilegal" />
+    <LinePart from=" lluminar" to=" iluminar" />
+    <LinePart from="sllbato" to="silbato" />
+    <LinePart from="sllenclo" to="silencio" />
+    <LinePart from="clemencla" to="clemencia" />
+    <LinePart from="socledad" to="sociedad" />
+    <LinePart from="tlene" to="tiene" />
+    <LinePart from="tlempo" to="tiempo" />
+    <LinePart from="equlvocaba" to="equivocaba" />
+    <LinePart from="qulnce" to="quince" />
+    <LinePart from="comlen" to="comien" />
+    <LinePart from="historl" to="histori" />
+    <LinePart from="misterl" to="misteri" />
+    <LinePart from="vivencl" to="vivenci" />
+  </PartialLines>
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines>
+    <Ending from=".»." to="»." />
+  </EndLines>
+  <WholeLines>
+    <!-- Todas las líneas -->
+    <Line from="No" to="No." />
+  </WholeLines>
+  <RegularExpressions>
+    <!-- Abreviaturas compuestas -->
+    <RegEx find="\b[Ss](r|ra|rta)\b\.?" replaceWith="S$1." />
+    <RegEx find="\b[Dd](r|ra)\b\.?" replaceWith="D$1." />
+    <RegEx find="\b[Uu](d|ds)\b\.?" replaceWith="U$1." />
+    <RegEx find="(\d)(\s){0,1}([Aa])(\.){0,1}([Mm])(\.){0,1}(\W){0,1}" replaceWith="$1 a. m.$7" />
+    <RegEx find="(\d)(\s){0,1}([Pp])(\.){0,1}([Mm])(\.){0,1}(\W){0,1}" replaceWith="$1 p. m.$7" />
+    <RegEx find="(\d)(\s){0,1}(h)(s\b|r\b|rs\b){0,1}(\.){0,1}(\W){0,1}" replaceWith="$1 $3$6" />
+    <RegEx find="(\d)(\s){0,1}([Kk])(m\b|ms\b)(\.){0,1}(\W){0,1}" replaceWith="$1 km$6" />
+    <RegEx find="(\d)(\s){0,1}(s)(g\b|eg\b){0,1}(\.){0,1}(\W){0,1}" replaceWith="$1 s$6" />
+    <RegEx find="(\d)(\s){0,1}([Kk])(g\b|gs\b)(\.){0,1}(\W){0,1}" replaceWith="$1 kg$6" />
+    <RegEx find="(\d)(\s){0,1}(m)(t\b|ts\b){0,1}(\.){0,1}(\W){0,1}" replaceWith="$1 m$6" />
+    <RegEx find="(\d)KBs(\W){0,1}" replaceWith="$1 kB$2" />
+    <RegEx find="([Nn])°(\s){0,1}(\d)" replaceWith="$1.° $3" />
+    <RegEx find="([Nn])ro(\.){0,1}(\s){0,1}(\d)" replaceWith="$1.° $4" />
+    <!-- Signos invertidos -->
+    <RegEx find="\?¿(\W|\w)" replaceWith="? ¿$1" />
+    <RegEx find="\!¡(\W|\w)" replaceWith="! ¡$1" />
+    <RegEx find="\?¿¿(\W|\w)" replaceWith="? ¿$1" />
+    <RegEx find="\!¡¡(\W|\w)" replaceWith="! ¡$1" />
+    <!-- Inicio de línea -->
+    <RegEx find="^_(\s)" replaceWith="-$1" />
+    <RegEx find="^_(\w)" replaceWith="- $1" />
+    <!-- Uso de comillas según la recomendación de la RAE y la Wikipedia -->
+    <RegEx find="(«[^“«»]+)«" replaceWith="$1“" />
+    <RegEx find="(“[^«»”]+)»" replaceWith="$1”" />
+    <RegEx find="`" replaceWith="‘" />
+    <RegEx find="´" replaceWith="’" />
+    <RegEx find="([\wá-ú])(\.)(«|»)" replaceWith="$1»." />
+    <RegEx find="«(\?)" replaceWith="»?" />
+    <RegEx find="«(\!)" replaceWith="»!" />
+    <RegEx find="«\s" replaceWith="» " />
+    <RegEx find="«(\))" replaceWith="»)" />
+    <RegEx find="(\?)«" replaceWith="?»" />
+    <RegEx find="(\!)«" replaceWith="!»" />
+    <RegEx find="«(,)" replaceWith="»," />
+    <RegEx find="«(;)" replaceWith="»;" />
+    <RegEx find="«(:)" replaceWith="»:" />
+    <RegEx find="(¿)»" replaceWith="¿«" />
+    <RegEx find="(¡)»" replaceWith="¡«" />
+    <!-- Uso de comillas (ANSI) según la recomendación de la RAE («\x22» es el carácter «"») -->
+    <RegEx find="([\wá-ú])([\.,]) ?[\x22»]" replaceWith="$1»$2" />
+    <RegEx find="([\wá-ú])\?[\x22»](\s|$)" replaceWith="$1?».$2" />
+    <RegEx find="^(\.\.\.)(\s){0,1}\x22" replaceWith="$1«" />
+    <RegEx find="«\x22" replaceWith="«" />
+    <RegEx find="\x22»" replaceWith="»" />
+    <RegEx find="^\x22{2,}" replaceWith="«" />
+    <RegEx find="\x22{2,}$" replaceWith="»" />
+    <RegEx find="\x22\r" replaceWith="»" />
+    <RegEx find="^\x22" replaceWith="«" />
+    <RegEx find="\x22$" replaceWith="»." />
+    <RegEx find="([\wá-ú])\.[\x22»]" replaceWith="$1»." />
+    <RegEx find="\s\x22" replaceWith=" «" />
+    <RegEx find="\x22\s" replaceWith="» " />
+    <RegEx find="\x22(,)" replaceWith="»," />
+    <RegEx find="\x22(\.)" replaceWith="»." />
+    <RegEx find="\x22(;)" replaceWith="»;" />
+    <RegEx find="\x22(:)" replaceWith="»:" />
+    <RegEx find="(\!)\x22" replaceWith="!»" />
+    <RegEx find="\x22(\!)" replaceWith="»!" />
+    <RegEx find="(\?)\x22" replaceWith="?»" />
+    <RegEx find="\x22(\?)" replaceWith="»?" />
+    <RegEx find="\x22(¿)" replaceWith="«¿" />
+    <RegEx find="(¿)\x22" replaceWith="¿«" />
+    <RegEx find="\x22(¡)" replaceWith="«¡" />
+    <RegEx find="(¡)\x22" replaceWith="¡«" />
+    <RegEx find="\x22(\))" replaceWith="»)" />
+    <RegEx find="(\))\x22" replaceWith=")»" />
+    <RegEx find="(\()\x22" replaceWith="(«" />
+    <!-- Uso de comillas (Unicode) según la recomendación de la RAE («\u0022» es el carácter «"») -->
+    <RegEx find="^(\.\.\.)(\s){0,1}\u0022" replaceWith="$1«" />
+    <RegEx find="^\u0022{2,}" replaceWith="«" />
+    <RegEx find="\u0022{2,}$" replaceWith="»" />
+    <RegEx find="\u0022\r" replaceWith="»" />
+    <RegEx find="^\u0022" replaceWith="«" />
+    <RegEx find="\u0022$" replaceWith="»" />
+    <RegEx find="(\w)(\.)\u0022" replaceWith="$1»." />
+    <RegEx find="\s\u0022" replaceWith=" «" />
+    <RegEx find="\u0022\s" replaceWith="» " />
+    <RegEx find="\u0022(,)" replaceWith="»," />
+    <RegEx find="\u0022(\.)" replaceWith="»." />
+    <RegEx find="\u0022(;)" replaceWith="»;" />
+    <RegEx find="\u0022(:)" replaceWith="»:" />
+    <RegEx find="(\!)\u0022" replaceWith="!»" />
+    <RegEx find="\u0022(\!)" replaceWith="»!" />
+    <RegEx find="(\?)\u0022" replaceWith="?»" />
+    <RegEx find="\u0022(\?)" replaceWith="»?" />
+    <RegEx find="\u0022(¿)" replaceWith="«¿" />
+    <RegEx find="(¿)\u0022" replaceWith="¿«" />
+    <RegEx find="\u0022(¡)" replaceWith="«¡" />
+    <RegEx find="(¡)\u0022" replaceWith="¡«" />
+    <RegEx find="\u0022(\))" replaceWith="»)" />
+    <RegEx find="(\))\u0022" replaceWith=")»" />
+    <RegEx find="(\()\u0022" replaceWith="(«" />
+    <!-- Numeración -->
+    <RegEx find="([0-9])\.([0-9])\b" replaceWith="$1,$2" />
+    <RegEx find="(^|\s|[¡¿«])([0-9])(,|\.)?([0-9]{3})\b" replaceWith="$1$2$4" />
+    <RegEx find="(\d)\s(?=\d{2}\b)" replaceWith="$1-" />
+    <!-- "1 :", "2 :"... "n :" a "n:" -->
+    <RegEx find="(\d) ([:;])" replaceWith="$1$2" />
+    <!-- Corregir las comas y puntos por ej. «, ,» por «,» & «,,,» o similar por «...» -->
+    <RegEx find="(\.\.\.+)$" replaceWith="..." />
+    <RegEx find="(, ,+)$" replaceWith="," />
+    <RegEx find="(,\s),+\s" replaceWith="$1" />
+    <RegEx find="(\.\.\.),$" replaceWith="$1" />
+    <RegEx find="([\wá-ú])(\.\.)$" replaceWith="$1." />
+    <!-- Puntos innecesarios (complemento) -->
+    <RegEx find="([\w\W]\.{3})([¡¿])" replaceWith="$1 $2" />
+    <RegEx find="(\w)\.\.(\s)" replaceWith="$1.$2" />
+    <RegEx find="([\wá-ú\x22»])\.([\?\!])" replaceWith="$1$2" />
+    <RegEx find="([\:\;])\." replaceWith="$1" />
+    <RegEx find="\.([\:\;])" replaceWith="$1" />
+    <RegEx find="\:+" replaceWith=":" />
+    <!-- Terminaciones ción/sión -->
+    <RegEx find="([sc]i)o(n)\b" replaceWith="$1ó$2" />
+    <RegEx find="([SC]I)O(N)\b" replaceWith="$1Ó$2" />
+    <!-- "i" en vez de "l" en terminaciones «clón» -->
+    <RegEx find="clón\b" replaceWith="ción" />
+    <!-- "si" en vez de "sl" -->
+    <RegEx find="\b([Ss])(l)\b" replaceWith="$1i" />
+    <!-- Para corregir por ej. raclones, perforaclones, opclones, etc -->
+    <RegEx find="([Rr]ac)l(o)" replaceWith="$1i$2" />
+    <RegEx find="([Oo]pc)l(o)" replaceWith="$1i$2" />
+    <!-- Para corregir por ej. tenldo, víctlmas, olvldarlo, legítlmo, etc -->
+    <RegEx find="([BbCcDdFfHhMmNnRrSsTtVv])l([bcdhmnrstv])" replaceWith="$1i$2" />
+    <!-- Corrige los errores en el ripeo de la «o» mayúscula por el cero «0» y viceversa -->
+    <RegEx find="(\d)O" replaceWith="$1 0" />
+    <RegEx find="(\d)[,\.]O" replaceWith="$1.0" />
+    <RegEx find="([A-Z])0" replaceWith="$1O" />
+    <RegEx find="\b0([A-Za-z])" replaceWith="O$1" />
+    <!-- Signos musicales -->
+    <RegEx find="[♪♫☺☹♥©☮☯Σ∞≡⇒π#](\r\n)[♪♫☺☹♥©☮☯Σ∞≡⇒π#]" replaceWith="$1" />
+    <!-- Tilde diacrítica antes del punto -->
+    <RegEx find="(\s)([dst])e\.(\s|\$)" replaceWith="$1$2é.$3" />
+    <RegEx find="(\s)mi\.(\s|\$)" replaceWith="$1mí.$2" />
+    <RegEx find="(\s)el\.(\s|\$)" replaceWith="$1él.$2" />
+    <RegEx find="(\s)tu\.(\s|\$)" replaceWith="$1tú.$2" />
+    <RegEx find="(\s)si\.(\s|\$)" replaceWith="$1sí.$2" />
+    <RegEx find="(\s)aun\.(\s|\$)" replaceWith="$1aún.$2" />
+    <RegEx find="(\s)mas\.(\s|\$)" replaceWith="$1más.$2" />
+    <RegEx find="(\s)quien\.(\s|\$)" replaceWith="$1quién.$2" />
+    <RegEx find="(\s)cual\.(\s|\$)" replaceWith="$1cuál.$2" />
+    <RegEx find="(\s)que\.(\s|\$)" replaceWith="$1qué.$2" />
+    <RegEx find="(\s)porque\.(\s|\$)" replaceWith="$1porqué.$2" />
+    <RegEx find="(\s)cuanto\.(\s|\$)" replaceWith="$1cuánto.$2" />
+    <RegEx find="(\s)cuando\.(\s|\$)" replaceWith="$1cuándo.$2" />
+    <!-- Prefijos; palabras compuestas (simple) -->
+    <RegEx find="(\b[Ee]x|\b[Ss]uper|\b[Aa]nti|\b[Pp]os|\b[Pp]re|\b[Pp]ro|\b[Vv]ice)[\s\x2D]([a-zá-ú]{3,20})(\b)" replaceWith="$1$2" />
+    <!-- Prefijos; palabras compuestas (números) -->
+    <RegEx find="(\b[Ss]ub|\b[Ss]uper)[\s\x2D](\d{2})(\b)" replaceWith="$1-$2$3" />
+    <!-- Prefijos; palabras compuestas (mayúsculas) -->
+    <RegEx find="(\b[Aa]nti|\b[Mm]ini|\b[Pp]os|\b[Pp]ro)\s([A-Z]{1,10})([A-Z][a-zá-ú]){0,10}(\b)" replaceWith="$1-$2$3" />
+    <!-- Casos de mayúsculas con dos puntos -->
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(a)" replaceWith="$1A" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(b)" replaceWith="$1B" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(c)" replaceWith="$1C" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(d)" replaceWith="$1D" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(e)" replaceWith="$1E" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(f)" replaceWith="$1F" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(g)" replaceWith="$1G" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(h)" replaceWith="$1H" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(i)" replaceWith="$1I" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(j)" replaceWith="$1J" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(k)" replaceWith="$1K" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(l)" replaceWith="$1L" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(m)" replaceWith="$1M" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(n)" replaceWith="$1N" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(ñ)" replaceWith="$1Ñ" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(o)" replaceWith="$1O" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(p)" replaceWith="$1P" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(q)" replaceWith="$1Q" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(r)" replaceWith="$1R" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(s)" replaceWith="$1S" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(t)" replaceWith="$1T" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(u)" replaceWith="$1U" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(v)" replaceWith="$1V" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(w)" replaceWith="$1W" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(x)" replaceWith="$1X" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(y)" replaceWith="$1Y" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(z)" replaceWith="$1Z" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(á)" replaceWith="$1Á" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(é)" replaceWith="$1É" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(í)" replaceWith="$1Í" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(ó)" replaceWith="$1Ó" />
+    <RegEx find="([\wá-ú]:\s[«\x22]?)(ú)" replaceWith="$1Ú" />
+    <!-- Usos correctos de la coma -->
+    <RegEx find="(\b[Pp]ero),(\s)([¡¿])" replaceWith="$1$2$3" />
+    <RegEx find="(\b[Aa]unque),(\s|$)" replaceWith="$1$2" />
+    <!-- Vocativos -->
+    <RegEx find="(\bHola|\bBueno|\bBien|\bVen|\bVen acá|\besto|\bBuenos días|\bFeliz cumpleaños|\bsiento)\s([A-Z][a-zá-ú]{3,12}\b|seño(r|ra|rita)\b|hij(o|a) mío\b|amig(o|a)\b)" replaceWith="$1, $2" />
+    <!-- «aún» cuando son sinónimos de «incluso» o «hasta» -->
+    <RegEx find="(\W|^)(\b[Aa])ú(n)(\s)(así\b|cuando\b|los\b|las\b|negar(te|se)\b)" replaceWith="$1$2u$3$4$5" />
+    <RegEx find="(\b[Nn]i)(\s)(a)ú(n)(\W|$)" replaceWith="$1$2$3u$4$5" />
+    <!-- «sí» -->
+    <RegEx find="\b([Ss])i(:|;|\.)" replaceWith="$1í$2" />
+    <!-- «sé» -->
+    <RegEx find="(\b[Ll]o|\b[Ll]a|\b[Ll]e)(\s)se(\W|$)" replaceWith="$1$2sé$3" />
+    <RegEx find="[Ss]e\s(dónde\b|cuándo\b|adónde\b|cómo\b|cuál\b|quién\b|cuánto\b|cuánta\b|cuántos\b|cuántas\b|cuán\b)" replaceWith="sé $1" />
+    <!-- «té» -->
+    <RegEx find="\b([Tt])e\s(verde\b|negro\b|perla\b|de manzanilla\b|de lim[óo]n\b|de jazm[íi]n\b)" replaceWith="$1é $2" />
+    <!-- Apóstrofo -->
+    <RegEx find="(\b[A-Z][a-zá-ú]{3,12})\s(’|')(\d\d(\s|$))" replaceWith="$1 $3" />
+    <RegEx find="(\b[A-Z]{2,5})(’|')(s)" replaceWith="(Ej. Devedés)$1$3" />
+    <RegEx find="(\b\d{1,2})(’|')(\d{2})\s(s|m)(\W|$)" replaceWith="$1,$3 $4$5" />
+    <RegEx find="(\b\d{1,2})(’|')(\d{2})\s(h)(\W|$)" replaceWith="$1:$3 $4$5" />
+    <!-- Porcentaje (debe llevar espacio) -->
+    <RegEx find="(\b\d{1,3})%(\W)" replaceWith="$1 %$2" />
+    <!-- Haz/has -->
+    <RegEx find="(\b)([Hh])as\s(la\b|lo\b|clic\b)(\W)" replaceWith="$1$2az $3$4" />
+    <RegEx find="(\b)([Hh])az\s(de\b)(\W)" replaceWith="$1$2as $3$4" />
+    <RegEx find="(\b)([Hh])as(le\b|nos\b|me\b)(\W)" replaceWith="$1$2az$3$4" />
+    <!-- Quitar itálicas en 3 o menos letras -->
+    <RegEx find="\x3ci\x3e(.{1,3})\x3c\/i\x3e" replaceWith="$1" />
+    <!-- Miscelánea -->
+    <RegEx find="(\b[Cc]erca|\b[Ee]ncima|\b[Dd]ebajo|\b[Dd]etrás|\b[Dd]elante)(\s)mío" replaceWith="$1 de mí" />
+    <RegEx find="(\b[Cc]erca|\b[Ee]ncima|\b[Dd]ebajo|\b[Dd]etrás|\b[Dd]elante)(\s)tuyo" replaceWith="$1 de ti" />
+    <!-- Punto antes de «¿» y «¡» -->
+    <RegEx find="([\wá-ú»])\s(?=(¿|¡)[A-ZÁ-Ú])" replaceWith="$1. " />
+    <!-- Espacios después del guión -->
+    <RegEx find="(^|\n)(-)([^\s])" replaceWith="$1$2 $3" />
+    <!-- Punto antes del guión -->
+    <RegEx find="([^\.\?\!]) - " replaceWith="$1. - " />
+    <!-- Terminaciones en «ólogo», «ílogo» y «álogo» -->
+    <RegEx find="\Bo(log[ao]s?\b)" replaceWith="ó$1" />
+    <RegEx find="\Ba(log[ao]s?\b)" replaceWith="á$1" />
+    <RegEx find="\Bi(log[ao]s?\b)" replaceWith="í$1" />
+  </RegularExpressions>
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/srp_OCRFixReplaceList.xml

@@ -0,0 +1,234 @@
+<!-- Credit goes to: MilanRS [http://www.prijevodi-online.org] -->
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="ču" to="ću" />
+    <Word from="češ" to="ćeš" />
+    <Word from="če" to="će" />
+    <Word from="ćš" to="ćeš" />
+    <Word from="ćmo" to="ćemo" />
+    <Word from="ćte" to="ćete" />
+    <Word from="čemo" to="ćemo" />
+    <Word from="čete" to="čete" />
+    <Word from="djete" to="dijete" />
+    <Word from="Hey" to="Hej" />
+    <Word from="hey" to="hej" />
+    <Word from="htjeo" to="htio" />
+    <Word from="Hočeš" to="Hoćeš" />
+    <Word from="hočeš" to="hoćeš" />
+    <Word from="iči" to="ići" />
+    <Word from="jel" to="je l'" />
+    <Word from="Jel" to="Je l'" />
+    <Word from="nedaj" to="ne daj" />
+    <Word from="Rješit" to="Riješit" />
+    <Word from="smjeo" to="smio" />
+    <Word from="uopče" to="uopće" />
+    <Word from="valda" to="valjda" />
+    <Word from="želila" to="željela" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords>
+    <WordPart from="¤" to="o" />
+    <WordPart from="vv" to="w" />
+    <WordPart from="IVI" to="M" />
+    <WordPart from="lVI" to="M" />
+    <WordPart from="IVl" to="M" />
+    <WordPart from="lVl" to="M" />
+  </PartialWords>
+  <PartialLines>
+    <LinePart from="bi smo" to="bismo" />
+    <LinePart from="dali je" to="da li je" />
+    <LinePart from="dali si" to="da li si" />
+    <LinePart from="Dali si" to="Da li si" />
+    <LinePart from="Jel sam ti" to="Jesam li ti" />
+    <LinePart from="Jel si" to="Jesi li" />
+    <LinePart from="Jel' si" to="Jesi li" />
+    <LinePart from="Je I'" to="Jesi li" />
+    <LinePart from="Jel si to" to="Jesi li to" />
+    <LinePart from="Jel' si to" to="Da li si to" />
+    <LinePart from="jel si to" to="da li si to" />
+    <LinePart from="jel' si to" to="jesi li to" />
+    <LinePart from="Jel si ti" to="Da li si ti" />
+    <LinePart from="Jel' si ti" to="Da li si ti" />
+    <LinePart from="jel si ti" to="da li si ti" />
+    <LinePart from="jel' si ti" to="da li si ti" />
+    <LinePart from="jel ste " to="jeste li " />
+    <LinePart from="Jel ste" to="Jeste li" />
+    <LinePart from="jel' ste " to="jeste li " />
+    <LinePart from="Jel' ste " to="Jeste li " />
+    <LinePart from="Jel su " to="Jesu li " />
+    <LinePart from="Jel da " to="Zar ne" />
+    <LinePart from="jel da " to="zar ne" />
+    <LinePart from="jel'da " to="zar ne" />
+    <LinePart from="Jeli sve " to="Je li sve" />
+    <LinePart from="Jeli on " to="Je li on" />
+    <LinePart from="Jeli ti " to="Je li ti" />
+    <LinePart from="jeli ti " to="je li ti" />
+    <LinePart from="Jeli to " to="Je li to" />
+    <LinePart from="Nebrini" to="Ne brini" />
+    <LinePart from="nedaj" to="ne daj" />
+    <LinePart from="ne ću" to="neću" />
+    <LinePart from="Nemogu" to="Ne mogu" />
+    <LinePart from="ne mogu" to="ne mogu" />
+    <LinePart from="Nemoraš" to="Ne moraš" />
+    <LinePart from="od kako" to="otkako" />
+    <LinePart from="Si dobro" to="Jesi li dobro" />
+    <LinePart from="Svo vreme" to="Sve vrijeme" />
+    <LinePart from="Svo vrijeme" to="Sve vrijeme" />
+    <LinePart from="Cijelo vrijeme" to="Sve vrijeme" />
+  </PartialLines>
+  <PartialLinesAlways />
+  <BeginLines />
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions>
+    <RegEx find="đž" replaceWith="dž" />
+    <RegEx find="ajsmiješnij" replaceWith="ajsmješnij" />
+    <RegEx find="boži[čć]([aeiu]|em|ima)?\b" replaceWith="Božić$1" />
+    <RegEx find=" g-dine\.$" replaceWith=" gospodine." />
+    <RegEx find=" g-dine +(?=[A-ZČĐŠŽ])" replaceWith=" g. " />
+    <RegEx find="([gG])dine? +(?=[A-ZČĐŠŽ])" replaceWith="$1. " />
+    <RegEx find="([gG])-đo +(?=[A-ZČĐŠŽ])" replaceWith="$1gđo " />
+    <RegEx find="gdina +(?=[A-ZČĐŠŽ])" replaceWith="g. " />
+    <RegEx find=" gosp +" replaceWith=" g. " />
+    <RegEx find="Jel si sigur" replaceWith="Jesi li sigur" />
+    <RegEx find="Jel' si sigur" replaceWith="Jesi li sigur" />
+    <RegEx find="\b([jJ])el\?" replaceWith="$1e l'?" />
+    <RegEx find="\bJel'" replaceWith="Je l'" />
+    <RegEx find="([kK]alib(?:ar|r[aeui]))\. *([0-9])" replaceWith="$1 .$2" />
+    <RegEx find="([mM])jenjati" replaceWith="$1ijenjati" />
+    <RegEx find="([mM])oguč" replaceWith="$1oguć" />
+    <RegEx find="\b([nN])ebih?" replaceWith="$1e bi" />
+    <RegEx find="\b([nN])eč([ue]š?|emo|ete)\b" replaceWith="$1eć$2" />
+    <RegEx find="\b([nN])emože(mo|š|te)?\b" replaceWith="$1e može$2" />
+    <RegEx find="\b([nN])ezna([šm]o?|t[ei]|ju|jući|vši)?\b" replaceWith="$1e zna$2" />
+    <RegEx find="najcijenjen" replaceWith="najcjenjen" />
+    <RegEx find="N[jJ]u Jork" replaceWith="Njujork" />
+    <RegEx find="([oO])d([kp])" replaceWith="$1t$2" />
+    <RegEx find="([oO])ružij([aeu])" replaceWith="$1ružj$2" />
+    <RegEx find="([oO])sječa" replaceWith="$1sjeća" />
+    <RegEx find="([pPdD])onje([lt])" replaceWith="$1onije$2" />
+    <RegEx find="([pP])objedi([mšto])" replaceWith="$1obijedi$2" />
+    <RegEx find="redamnom" replaceWith="reda mnom" />
+    <RegEx find="redpostav" replaceWith="retpostav" />
+    <RegEx find="([pP])rimjeti" replaceWith="$1rimijeti" />
+    <RegEx find="([pP])romjeni([mštol])" replaceWith="$1romijeni$2" />
+    <RegEx find="([rR])azumijeć" replaceWith="$1azumjeć" />
+    <RegEx find="rascjepljen" replaceWith="rascijepljen" />
+    <RegEx find="redhodn" replaceWith="rethodn" />
+    <RegEx find="rimjenjen" replaceWith="rimijenjen" />
+    <RegEx find="([^d])rješit" replaceWith="$1riješit" />
+    <RegEx find="([sSzZ])amnom" replaceWith="$1a mnom" />
+    <RegEx find="([sS])lijede[čć]([aeiu]|e[mg])" replaceWith="$1ljedeć$2" />
+    <RegEx find="([sS])mješno" replaceWith="$1miješno" />
+    <RegEx find="([uU])mijesto" replaceWith="$1mjesto" />
+    <RegEx find="([uU])spijeh" replaceWith="$1spjeh" />
+    <RegEx find="([uU])spiješ(an|n[aeiou]|no[mgj])" replaceWith="$1spješ$2" />
+    <RegEx find="([uU])vjek" replaceWith="$1vijek" />
+    <RegEx find="\b([vV])eč([aeiou])" replaceWith="$1eć$2" />
+    <RegEx find="([zZ])ahtijeva" replaceWith="$1ahtjeva" />
+    <RegEx find="([zZ])ahtjeva([ojlmšt])" replaceWith="$1ahtijeva$2" />
+    <RegEx find="([ks]ao)\.:" replaceWith="$1:" />
+    <RegEx find="(?&lt;=[a-zčđšž])Ij(?=[a-zčđšž])" replaceWith="lj" />
+    <RegEx find="(?&lt;=[^A-ZČĐŠŽa-zčđšž])Iju(?=bav|d|t)" replaceWith="lju" />
+    <!-- kad ima razmak između tagova </i> <i> -->
+    <!-- <RegEx find="(&gt;) +(&lt;)" replaceWith="$1$2" /> -->
+    <!-- ',"' to '",' -->
+    <RegEx find="(?&lt;=\w),&quot;(?=\s|$)" replaceWith="&quot;," />
+    <RegEx find=",\.{3}|\.{3},|\.{2} \." replaceWith="..." />
+    <!-- "1 :", "2 :"... "n :" to "n:" -->
+    <RegEx find="([0-9]) +: +(\D)" replaceWith="$1: $2" />
+    <!-- Two or more consecutive "," to "..." -->
+    <RegEx find=",{2,}" replaceWith="..." />
+    <!-- Two or more consecutive "-" to "..." -->
+    <RegEx find="-{2,}" replaceWith="..." />
+    <RegEx find="([^().])\.{2}([^().:])" replaceWith="$1...$2" />
+    <!-- separator stotica i decimalnog ostatka 1,499,000.00 -> 1.499.000,00 -->
+    <RegEx find="([0-9]{3})\.([0-9]{2}[^0-9])" replaceWith="$1,$2" />
+    <RegEx find="([0-9]),([0-9]{3}\D)" replaceWith="$1.$2" />
+    <!-- Apostrophes -->
+    <RegEx find="´´" replaceWith="&quot;" />
+    <!-- <RegEx find="[´`]" replaceWith="'" /> -->
+    <!-- <RegEx find="[“”]" replaceWith="&quot;" /> -->
+    <RegEx find="''" replaceWith="&quot;" />
+    <!-- Two or more consecutive '"' to one '"' -->
+    <RegEx find="&quot;{2,}" replaceWith="&quot;" />
+    <!-- Fix zero and capital 'o' ripping mistakes -->
+    <RegEx find="(?&lt;=[0-9]\.?)O" replaceWith="0" />
+    <RegEx find="\b0(?=[A-ZČĐŠŽa-zčđšž])" replaceWith="O" />
+    <!-- Brisanje crte - na početku 1. reda (i kada ima dva reda) -->
+    <RegEx find="\A- ?([A-ZČĐŠŽa-zčđšž0-9„'&quot;]|\.{3})" replaceWith="$1" />
+    <RegEx find="\A(&lt;[ibu]&gt;)- ?" replaceWith="$1" />
+    <RegEx find="  - " replaceWith=" -" />
+    <!-- Brisanje razmaka iza crte - na početku 2. reda -->
+    <RegEx find="(?&lt;=\n(&lt;[ibu]&gt;)?)- (?=[A-ZČĐŠŽčš0-9„'&quot;&lt;])" replaceWith="-" />
+    <!-- Korigovanje crte - kad je u sredini prvog reda -->
+    <RegEx find="([.!?&quot;&gt;]) - ([A-ZČĐŠŽčš'&quot;&lt;])" replaceWith="$1 -$2" />
+    <!-- Zatvoren tag pa razmak poslije crtice -->
+    <RegEx find="(&gt;) - ([A-ZČĐŠŽčš„'&quot;])" replaceWith="$1 -$2" />
+    <!-- Zatvoren tag pa crtica razmak -->
+    <RegEx find="(&gt;)- ([A-ZČĐŠŽčš„'&quot;])" replaceWith="$1-$2" />
+    <!-- Zagrada pa crtica razmak -->
+    <RegEx find="\(- ([A-ZČĐŠŽčš„'&quot;])" replaceWith="(-$1" />
+    <!-- Smart space after dot -->
+    <!-- osim kad je zadnje t (riječ kolt) -->
+    <RegEx find="(?&lt;=[a-su-zá-úñä-ü])\.(?=[^\s\n().:?!*^“”'&quot;&lt;])" replaceWith=". " />
+    <!-- Oznaka za kalibar. Npr. "Colt .45" -->
+    <!-- Da bi radilo, da bi ovaj razmak bio dozvoljen, odčekirajte "Razmaci ispred tačke" -->
+    <RegEx find="t\.(?=[0-9]{2})" replaceWith="t ." />
+    <!-- Joey(j)a -->
+    <RegEx find="(?&lt;=\b[A-Z][a-z])eyj(?=[a-z])" replaceWith="ey" />
+    <!-- Sređuje zarez sa razmakom -->
+    <RegEx find="(?&lt;=[A-ZČĐŠŽa-zčđšžá-úñä-ü&quot;]),(?=[^\s(),?!“&lt;])" replaceWith=", " />
+    <RegEx find=" +,(?=[A-ZČĐŠŽa-zčđšž])" replaceWith=", " />
+    <RegEx find=" +, +" replaceWith=", " />
+    <RegEx find=" +,$" replaceWith="," />
+    <RegEx find="([?!])-" replaceWith="$1 -" />
+    <!-- Space after last of some consecutive dots (eg. "...") -->
+    <RegEx find="(?&lt;=[a-zčđšž])(\.{3}|!)(?=[a-zčđšž])" replaceWith="$1 " />
+    <!-- Delete space after "..." that is at the beginning of the line. You may delete this line if you don't like it -->
+    <!-- <RegEx find="^\.{3} +" replaceWith="..." /> -->
+    <!-- "tekst ... tekst" mijenja u "tekst... tekst" -->
+    <RegEx find="(?&lt;=[A-ZČĐŠŽa-zčđšž]) +\.{3} +" replaceWith="... " />
+    <RegEx find="(?&lt;=\S)\. +&quot;" replaceWith=".&quot;" />
+    <RegEx find="&quot; +\." replaceWith="&quot;." />
+    <RegEx find="(?&lt;=\S\.{3}) +&quot;(?=\s|$)" replaceWith="&quot;" />
+    <RegEx find=" +\.{3}$" replaceWith="..." />
+    <RegEx find="(?&lt;=[a-zčđšž])(?: +\.{3}|\.{2}$)" replaceWith="..." />
+    <!-- Razmak ispred zagrade -->
+    <RegEx find="(?&lt;=[A-ZČĐŠŽa-zčđšž])\(" replaceWith=" (" />
+    <!-- Razmak iza upitnika -->
+    <RegEx find="\?(?=[A-ZČĐŠŽčš])" replaceWith="? " />
+    <RegEx find="(?&lt;=^|&gt;)\.{3} +(?=[A-ZČĐŠŽčš])" replaceWith="..." />
+    <!-- Brise ... kad je na poč. reda "... -->
+    <RegEx find="^&quot;\.{3} +" replaceWith="&quot;" />
+    <RegEx find="(?&lt;=[0-9])\$" replaceWith=" $$" />
+    <!-- ti š -> t š by Strider -->
+    <!-- Zamijeni sva "**ti šu*" s "**t šu*" i "**ti še*" s "**t še*" -->
+    <!-- <RegEx find="([a-z])ti (š+[eu])" replaceWith="$1t $2" /> -->
+    <!-- <RegEx find="([A-Za-z])ti( |\r?\n)(š[eu])" replaceWith="$1t$2$3" /> -->
+    <!-- <RegEx find="(?i)\b(ni)t (š[eu])" replaceWith="$1ti $2" /> -->
+    <!-- <RegEx find="\. +Mr. " replaceWith=". G. " /> -->
+    <!-- <RegEx find="\. +Mrs. " replaceWith=". Gđa " /> -->
+    <!-- <RegEx find="\. +Miss " replaceWith=". Gđica " /> -->
+    <!-- <RegEx find=", +Mrs. " replaceWith=", gđo " /> -->
+    <!-- <RegEx find=", +Miss " replaceWith=", gđice " /> -->
+    <!-- Razmak poslije <i> i poslije .. -->
+    <RegEx find="^(&lt;[ibu]&gt;) +" replaceWith="$1" />
+    <RegEx find="^\.{2} +" replaceWith="..." />
+    <!-- Razmak ? "</i> -->
+    <RegEx find="([.?!]) +(&quot;&lt;)" replaceWith="$1$2" />
+    <!-- Bez razmaka kod Npr.: -->
+    <RegEx find="(?&lt;=[Nn]pr\.) *: *" replaceWith=": " />
+    <RegEx find="\. ," replaceWith=".," />
+    <RegEx find="([?!])\." replaceWith="$1" />
+    <!-- Da ne kvari potpise sa ..:: -->
+    <RegEx find="\.{3}::" replaceWith="..::" />
+    <RegEx find="::\.{3}" replaceWith="::.." />
+    <RegEx find="\.{2} +::" replaceWith="..::" />
+    <!-- Skracenice bez razmaka -->
+    <RegEx find="d\. o\.o\." replaceWith="d.o.o." />
+    <!-- Kad red počinje sa ...pa malo slovo -->
+    <!-- <RegEx find="^\.{3}([a-zčđšž&quot;&lt;])" replaceWith="$1" /> -->
+    <!-- <RegEx find=" +([.?!])" replaceWith="$1" /> -->
+  </RegularExpressions>
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/dictionaries/xml/swe_OCRFixReplaceList.xml

@@ -0,0 +1,405 @@
+<OCRFixReplaceList>
+  <WholeWords>
+    <Word from="lârt" to="lärt" />
+    <Word from="hedervårda" to="hedervärda" />
+    <Word from="stormâstare" to="stormästare" />
+    <Word from="Avfârd" to="Avfärd" />
+    <Word from="tâlten" to="tälten" />
+    <Word from="ârjag" to="är jag" />
+    <Word from="ärjag" to="är jag" />
+    <Word from="jâmlikar" to="jämlikar" />
+    <Word from="Riskakofl" to="Riskakor" />
+    <Word from="Karamellen/" to="Karamellen" />
+    <Word from="Lngenüng" to="Ingenting" />
+    <Word from="ärju" to="är ju" />
+    <Word from="Sá" to="Så" />
+    <Word from="närjag" to="när jag" />
+    <Word from="alltjag" to="allt jag" />
+    <Word from="görjag" to="gör jag" />
+    <Word from="trorjag" to="tror jag" />
+    <Word from="varju" to="var ju" />
+    <Word from="görju" to="gör ju" />
+    <Word from="kanju" to="kan ju" />
+    <Word from="blirjag" to="blir jag" />
+    <Word from="sägerjag" to="säger jag" />
+    <Word from="behållerjag" to="behåller jag" />
+    <Word from="prøblem" to="problem" />
+    <Word from="räddadeju" to="räddade ju" />
+    <Word from="honøm" to="honom" />
+    <Word from="Ln" to="In" />
+    <Word from="svårflörtad" to="svårflörtad" />
+    <Word from="øch" to="och" />
+    <Word from="flörtar" to="flörtar" />
+    <Word from="kännerjag" to="känner jag" />
+    <Word from="flickan" to="flickan" />
+    <Word from="snø" to="snö" />
+    <Word from="gerju" to="ger ju" />
+    <Word from="køntakter" to="kontakter" />
+    <Word from="ølycka" to="olycka" />
+    <Word from="nølla" to="nolla" />
+    <Word from="sinnenajublar" to="sinnena jublar" />
+    <Word from="ijobbet" to="i jobbet" />
+    <Word from="Fårjag" to="Får jag" />
+    <Word from="Ar" to="Är" />
+    <Word from="liggerju" to="ligger ju" />
+    <Word from="um" to="om" />
+    <Word from="lbland" to="Ibland" />
+    <Word from="skjuterjag" to="skjuter jag" />
+    <Word from="Vaddå" to="Vad då" />
+    <Word from="pratarjämt" to="pratar jämt" />
+    <Word from="harju" to="har ju" />
+    <Word from="sitterjag" to="sitter jag" />
+    <Word from="häfla" to="härja" />
+    <Word from="sfiäl" to="stjäl" />
+    <Word from="FÖU" to="Följ" />
+    <Word from="varförjag" to="varför jag" />
+    <Word from="sfiärna" to="stjärna" />
+    <Word from="böflar" to="börjar" />
+    <Word from="böflan" to="början" />
+    <Word from="stäri" to="står" />
+    <Word from="pä" to="på" />
+    <Word from="harjag" to="har jag" />
+    <Word from="attjag" to="att jag" />
+    <Word from="Verkarjag" to="Verkar jag" />
+    <Word from="Kännerjag" to="Känner jag" />
+    <Word from="därjag" to="där jag" />
+    <Word from="tufi" to="tuff" />
+    <Word from="lurarjag" to="lurar jag" />
+    <Word from="varjättebra" to="var jättebra" />
+    <Word from="allvan" to="allvar" />
+    <Word from="dethär" to="det här" />
+    <Word from="vafle" to="varje" />
+    <Word from="FöUer" to="Följer" />
+    <Word from="personalmötetl" to="personalmötet!" />
+    <Word from="harjust" to="har just" />
+    <Word from="ärjätteduktig" to="är jätteduktig" />
+    <Word from="därja" to="där ja" />
+    <Word from="lngenüng" to="lngenting" />
+    <Word from="iluften" to="i luften" />
+    <Word from="ösen" to="öser" />
+    <Word from="tvâ" to="två" />
+    <Word from="Uejerna" to="Tjejerna" />
+    <Word from="hån*" to="hårt" />
+    <Word from="Ärjag" to="Är jag" />
+    <Word from="keL" to="Okej" />
+    <Word from="Förjag" to="För jag" />
+    <Word from="varjättekul" to="var jättekul" />
+    <Word from="kämpan" to="kämpar" />
+    <Word from="mycketjobb" to="mycket jobb" />
+    <Word from="Uus" to="ljus" />
+    <Word from="serjag" to="ser jag" />
+    <Word from="vetjag" to="vet jag" />
+    <Word from="fårjag" to="får jag" />
+    <Word from="hurjag" to="hur jag" />
+    <Word from="försökerjag" to="försöker jag" />
+    <Word from="tánagel" to="tånagel" />
+    <Word from="vaüe" to="varje" />
+    <Word from="Uudet" to="ljudet" />
+    <Word from="amhopa" to="allihopa" />
+    <Word from="Väü" to="Välj" />
+    <Word from="gäri" to="går" />
+    <Word from="rödüus" to="rödljus" />
+    <Word from="Uuset" to="ljuset" />
+    <Word from="Ridàn" to="Ridån" />
+    <Word from="viüa" to="vilja" />
+    <Word from="gåri" to="går i" />
+    <Word from="Hurdå" to="Hur då" />
+    <Word from="inter\/juar" to="intervjuar" />
+    <Word from="menarjag" to="menar jag" />
+    <Word from="spyrjag" to="spyr jag" />
+    <Word from="briüera" to="briljera" />
+    <Word from="Närjag" to="När jag" />
+    <Word from="ner\/ös" to="nervös" />
+    <Word from="ilivets" to="i livets" />
+    <Word from="nägot" to="något" />
+    <Word from="pà" to="på" />
+    <Word from="Lnnan" to="Innan" />
+    <Word from="Uf" to="Ut" />
+    <Word from="lnnan" to="Innan" />
+    <Word from="Dàren" to="Dåren" />
+    <Word from="Fàrjag" to="Får jag" />
+    <Word from="VadärdetdäL" to="Vad är det där" />
+    <Word from="smàtjuv" to="småtjuv" />
+    <Word from="tàgrånare" to="tågrånare" />
+    <Word from="ditàt" to="ditåt" />
+    <Word from="sä" to="så" />
+    <Word from="vàrdslösa" to="vårdslösa" />
+    <Word from="nàn" to="nån" />
+    <Word from="kommerjag" to="kommer jag" />
+    <Word from="ärjättebra" to="är jättebra" />
+    <Word from="ärjävligt" to="är jävligt" />
+    <Word from="àkerjag" to="åker jag" />
+    <Word from="ellerjapaner" to="eller japaner" />
+    <Word from="attjaga" to="att jaga" />
+    <Word from="eften" to="efter" />
+    <Word from="hästan" to="hästar" />
+    <Word from="Lntensivare" to="Intensivare" />
+    <Word from="fràgarjag" to="frågar jag" />
+    <Word from="pen/ers" to="pervers" />
+    <Word from="ràbarkade" to="råbarkade" />
+    <Word from="styrkon" to="styrkor" />
+    <Word from="Difåf" to="Ditåt" />
+    <Word from="händen" to="händer" />
+    <Word from="föfia" to="följa" />
+    <Word from="Idioten/" to="Idioter!" />
+    <Word from="Varförjagade" to="Varför jagade" />
+    <Word from="därförjag" to="därför jag" />
+    <Word from="forjag" to="for jag" />
+    <Word from="Iivsgladje" to="livsglädje" />
+    <Word from="narjag" to="när jag" />
+    <Word from="sajag" to="sa jag" />
+    <Word from="genastja" to="genast ja" />
+    <Word from="rockumentàren" to="rockumentären" />
+    <Word from="turne" to="turné" />
+    <Word from="fickjag" to="fick jag" />
+    <Word from="sager" to="säger" />
+    <Word from="Ijushårig" to="ljushårig" />
+    <Word from="tradgårdsolycka" to="trädgårdsolycka" />
+    <Word from="kvavdes" to="kvävdes" />
+    <Word from="dàrja" to="där ja" />
+    <Word from="hedersgaster" to="hedersgäster" />
+    <Word from="Nar" to="När" />
+    <Word from="smakiösa" to="smaklösa" />
+    <Word from="lan" to="Ian" />
+    <Word from="Lan" to="Ian" />
+    <Word from="eri" to="er i" />
+    <Word from="universitetsamne" to="universitetsämne" />
+    <Word from="garna" to="gärna" />
+    <Word from="ar" to="är" />
+    <Word from="baltdjur" to="bältdjur" />
+    <Word from="varjag" to="var jag" />
+    <Word from="àr" to="är" />
+    <Word from="förförstàrkare" to="förförstärkare" />
+    <Word from="arjattespeciell" to="är jättespeciell" />
+    <Word from="hàrgår" to="här går" />
+    <Word from="Ia" to="la" />
+    <Word from="Iimousinen" to="limousinen" />
+    <Word from="krickettra" to="kricketträ" />
+    <Word from="hårdrockvàrlden" to="hårdrockvärlden" />
+    <Word from="tràbit" to="träbit" />
+    <Word from="Mellanvastern" to="Mellanvästern" />
+    <Word from="arju" to="är ju" />
+    <Word from="turnen" to="turnén" />
+    <Word from="kanns" to="känns" />
+    <Word from="battre" to="bättre" />
+    <Word from="vàrldsturne" to="världsturne" />
+    <Word from="dar" to="där" />
+    <Word from="sjàlvantànder" to="självantänder" />
+    <Word from="jattelange" to="jättelänge" />
+    <Word from="berattade" to="berättade" />
+    <Word from="Sä" to="Så" />
+    <Word from="vandpunkten" to="vändpunkten" />
+    <Word from="Nàrjag" to="När jag" />
+    <Word from="lasa" to="läsa" />
+    <Word from="skitlàskigt" to="skitläskigt" />
+    <Word from="sambandsvàg" to="sambandsväg" />
+    <Word from="valdigt" to="väldigt" />
+    <Word from="Stamgafiel" to="Stämgaffel" />
+    <Word from="àrjag" to="är jag" />
+    <Word from="tajming" to="tajmning" />
+    <Word from="utgäng" to="utgång" />
+    <Word from="Hàråt" to="Häråt" />
+    <Word from="hàråt" to="häråt" />
+    <Word from="anvander" to="använder" />
+    <Word from="harjobbat" to="har jobbat" />
+    <Word from="imageide" to="imageidé" />
+    <Word from="klafien" to="klaffen" />
+    <Word from="sjalv" to="själv" />
+    <Word from="dvarg" to="dvärg" />
+    <Word from="detjag" to="det jag" />
+    <Word from="dvargarna" to="dvärgarna" />
+    <Word from="fantasivàrld" to="fantasivärld" />
+    <Word from="fiolliga" to="Fjolliga" />
+    <Word from="mandoiinstràngar" to="mandollnsträngar" />
+    <Word from="mittjobb" to="mitt jobb" />
+    <Word from="Skajag" to="Ska jag" />
+    <Word from="landari" to="landar i" />
+    <Word from="gang" to="gäng" />
+    <Word from="Detjag" to="Det jag" />
+    <Word from="Narmre" to="Närmre" />
+    <Word from="Iåtjavelni" to="låtjäveln" />
+    <Word from="Hållerjag" to="Håller jag" />
+    <Word from="visionarer" to="visionärer" />
+    <Word from="Tülvad" to="Till vad" />
+    <Word from="militàrbas" to="militärbas" />
+    <Word from="jattegiada" to="jätteglada" />
+    <Word from="Fastjag" to="Fast jag" />
+    <Word from="såjag" to="så jag" />
+    <Word from="rockvarlden" to="rockvärlden" />
+    <Word from="saknarjag" to="saknar jag" />
+    <Word from="allafall" to="alla fall" />
+    <Word from="fianta" to="fjanta" />
+    <Word from="Kràma" to="Kräma" />
+    <Word from="stammer" to="stämmer" />
+    <Word from="budbàrare" to="budbärare" />
+    <Word from="Iivsfiiosofi" to="livsfiiosofi" />
+    <Word from="förjämnan" to="för jämnan" />
+    <Word from="gillarjag" to="gillar jag" />
+    <Word from="Iarvat" to="larvat" />
+    <Word from="klararjag" to="klarar jag" />
+    <Word from="hattafi'àr" to="hattaffär" />
+    <Word from="Dà" to="Då" />
+    <Word from="uppfinna" to="uppfinna" />
+    <Word from="Ràttfåglar" to="Råttfåglar" />
+    <Word from="Sväüboda" to="Sväljboda" />
+    <Word from="Påböflar" to="Påbörjar" />
+    <Word from="slutarju" to="slutar ju" />
+    <Word from="nifiskebuüken" to="i fiskebutiken" />
+    <Word from="härjäkeln" to="här jäkeln" />
+    <Word from="Hßppa" to="Hoppa" />
+    <Word from="förstörds" to="förstördes" />
+    <Word from="varjättegoda" to="var jättegoda" />
+    <Word from="Kor\/" to="Korv" />
+    <Word from="brüléel" to="brülée!" />
+    <Word from="Hei" to="Hej" />
+    <Word from="älskarjordgubbsglass" to="älskar jordgubbsglass" />
+    <Word from="Snöbom" to="Snöboll" />
+    <Word from="SnöboH" to="Snöboll" />
+    <Word from="Snöbol" to="Snöboll" />
+    <Word from="snöboH" to="snöboll" />
+    <Word from="Läggerpå" to="Lägger på" />
+    <Word from="lngefl" to="lnget!" />
+    <Word from="Sägerjättesmarta" to="Säger jättesmarta" />
+    <Word from="dopplen/äderradar" to="dopplerväderradar" />
+    <Word from="säkertjättefin" to="säkert jättefin" />
+    <Word from="ärjättefin" to="är jättefin" />
+    <Word from="verkarju" to="verkar ju" />
+    <Word from="blirju" to="blir ju" />
+    <Word from="kor\/" to="korv" />
+    <Word from="naturkatastrofi" to="naturkatastrof!" />
+    <Word from="stickerjag" to="stickerj ag" />
+    <Word from="jättebufié" to="jättebuffé" />
+    <Word from="befinner" to="befinner" />
+    <Word from="Spflng" to="Spring" />
+    <Word from="trecfie" to="tredje" />
+    <Word from="ryckerjag" to="rycker jag" />
+    <Word from="skullejag" to="skulle jag" />
+    <Word from="vetju" to="vet ju" />
+    <Word from="afljag" to="att jag" />
+    <Word from="flnns" to="finns" />
+    <Word from="ärlång" to="är lång" />
+    <Word from="kåra" to="kära" />
+    <Word from="ärfina" to="är fina" />
+    <Word from="äri" to="är i" />
+    <Word from="hörden" to="hör den" />
+    <Word from="ättjäg" to="att jäg" />
+    <Word from="gär" to="går" />
+    <Word from="föri" to="för i" />
+    <Word from="Hurvisste" to="Hur visste" />
+    <Word from="fick" to="fick" />
+    <Word from="finns" to="finns" />
+    <Word from="fin" to="fin" />
+    <Word from="Fa" to="Bra." />
+    <Word from="bori" to="bor i" />
+    <Word from="fiendeplanl" to="fiendeplan!" />
+    <Word from="iförnamn" to="i förnamn" />
+    <Word from="detju" to="det ju" />
+    <Word from="Nüd" to="Niki" />
+    <Word from="hatarjag" to="hatar jag" />
+    <Word from="Klararjag" to="Klarar jag" />
+    <Word from="detafier" to="detaljer" />
+    <Word from="vä/" to="väl" />
+    <Word from="smakarju" to="smakar ju" />
+    <Word from="Teachefl" to="Teacher!" />
+    <Word from="imorse" to="i morse" />
+    <Word from="drickerjag" to="dricker jag" />
+    <Word from="ståri" to="står i" />
+    <Word from="Harjag" to="Har jag" />
+    <Word from="Talarjag" to="Talar jag" />
+    <Word from="undrarjag" to="undrar jag" />
+    <Word from="ålderjag" to="ålder jag" />
+    <Word from="vafie" to="varje" />
+    <Word from="förfalskningl" to="förfalskning!" />
+    <Word from="Vifiiiiam" to="William" />
+    <Word from="V\filliams" to="Williams" />
+    <Word from="attjobba" to="att jobba" />
+    <Word from="intei" to="inte i" />
+    <Word from="närV\filliam" to="när William" />
+    <Word from="V\filliam" to="William" />
+    <Word from="Efiersom" to="Eftersom" />
+    <Word from="Vlfilliam" to="William" />
+    <Word from="Iängejag" to="länge jag" />
+    <Word from="'fidigare" to="Tidigare" />
+    <Word from="börjadei" to="började i" />
+    <Word from="merjust" to="mer just" />
+    <Word from="efieråt" to="efteråt" />
+    <Word from="gjordejag" to="gjorde jag" />
+    <Word from="hadeju" to="hade ju" />
+    <Word from="gårvi" to="går vi" />
+    <Word from="köperjag" to="köper jag" />
+    <Word from="Måstejag" to="Måste jag" />
+    <Word from="kännerju" to="känner ju" />
+    <Word from="fln" to="fin" />
+    <Word from="treviig" to="trevlig" />
+    <Word from="Grattisl" to="Grattis!" />
+    <Word from="kande" to="kände" />
+    <Word from="'llden" to="Tiden" />
+    <Word from="sakjag" to="sak jag" />
+    <Word from="klartjag" to="klart jag" />
+    <Word from="häfiigt" to="häftigt" />
+    <Word from="Iämnarjag" to="lämnar jag" />
+    <Word from="gickju" to="gick ju" />
+    <Word from="skajag" to="ska jag" />
+    <Word from="Görjag" to="Gör jag" />
+    <Word from="måstejag" to="måste jag" />
+    <Word from="gra\/iditet" to="graviditet" />
+    <Word from="hittadqdin" to="hittade din" />
+    <Word from="ärjobbigt" to="är jobbigt" />
+    <Word from="Overdrivet" to="Överdrivet" />
+    <Word from="hOgtidlig" to="högtidlig" />
+    <Word from="Overtyga" to="Övertyga" />
+    <Word from="SKILSMASSA" to="SKILSMÄSSA" />
+    <Word from="brukarju" to="brukar ju" />
+    <Word from="lsabel" to="Isabel" />
+    <Word from="kundejag" to="kunde jag" />
+    <Word from="ärläget" to="är läget" />
+    <Word from="blirinte" to="blir inte" />
+    <Word from="l'm" to="I'm" />
+    <Word from="lt's" to="It's" />
+    <Word from="ijakt" to="i jakt" />
+    <Word from="avjordens" to="av jordens" />
+  </WholeWords>
+  <PartialWordsAlways />
+  <PartialWords>
+    <!-- Will be used to check words not in dictionary -->
+    <!-- If new word(s) exists in spelling dictionary, it(they) is accepted -->
+    <WordPart from="¤" to="o" />
+    <WordPart from="fi" to="fi" />
+    <WordPart from="â" to="ä" />
+    <WordPart from="/" to="l" />
+    <WordPart from="vv" to="w" />
+    <WordPart from="IVI" to="M" />
+    <WordPart from="lVI" to="M" />
+    <WordPart from="IVl" to="M" />
+    <WordPart from="lVl" to="M" />
+    <WordPart from="m" to="rn" />
+    <WordPart from="l" to="i" />
+    <WordPart from="€" to="e" />
+    <WordPart from="I" to="l" />
+    <WordPart from="c" to="o" />
+    <WordPart from="i" to="t" />
+    <WordPart from="cc" to="oo" />
+    <WordPart from="ii" to="tt" />
+    <WordPart from="n/" to="ry" />
+    <WordPart from="ae" to="æ" />
+    <!-- "f " will be two words -->
+    <WordPart from="f" to="f " />
+    <WordPart from="c" to="e" />
+    <WordPart from="o" to="e" />
+    <WordPart from="I" to="t" />
+    <WordPart from="n" to="o" />
+    <WordPart from="s" to="e" />
+    <WordPart from="å" to="ä" />
+    <WordPart from="à" to="å" />
+    <WordPart from="n/" to="rv" />
+  </PartialWords>
+  <PartialLines />
+  <PartialLinesAlways />
+  <BeginLines>
+    <Beginning from="Ln " to="In " />
+    <Beginning from="U ppfattat" to="Uppfattat" />
+  </BeginLines>
+  <EndLines />
+  <WholeLines />
+  <RegularExpressions />
+</OCRFixReplaceList>

Contents/Libraries/Shared/subzero/modification/main.py

@@ -0,0 +1,133 @@
+# coding=utf-8
+
+import traceback
+import pysubs2
+import logging
+
+from registry import registry
+
+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, language=None, encoding="utf-8"):
+        """
+        
+        :param encoding: used for decoding the content when fn is given, not used in case content is given
+        :param language: babelfish.Language language of the subtitle
+        :param fn:  filename
+        :param content: unicode 
+        :return: 
+        """
+        self.language = language
+        self.initialized_mods = {}
+        try:
+            if fn:
+                self.f = pysubs2.load(fn, encoding=encoding)
+            elif content:
+                self.f = pysubs2.SSAFile.from_string(content)
+        except (IOError,
+                UnicodeDecodeError,
+                pysubs2.exceptions.UnknownFPSError,
+                pysubs2.exceptions.UnknownFormatIdentifierError,
+                pysubs2.exceptions.FormatAutodetectionError):
+            if fn:
+                logger.exception("Couldn't load subtitle: %s: %s", fn, traceback.format_exc())
+            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 = []
+
+        parsed_mods = [SubtitleModifications.parse_identifier(mod) for mod in mods]
+        line_mods = []
+        non_line_mods = []
+
+        for identifier, args in parsed_mods:
+            if identifier not in registry.mods:
+                raise NotImplementedError("Mod %s not loaded" % 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 = []
+                skip_line = False
+                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
+
+                    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)
+                        skip_line = True
+                        break
+
+                    line.text = new_content
+                    applied_mods.append(identifier)
+                if not skip_line:
+                    new_f.append(line)
+
+        self.f.events = new_f
+
+    def to_string(self, format="srt", encoding="utf-8"):
+        return self.f.to_string(format, encoding=encoding)
+
+    def save(self, fn):
+        self.f.save(fn)
+
+
+SubMod = SubtitleModifications
+
+
+
+

Contents/Libraries/Shared/subzero/modification/mods/__init__.py

@@ -0,0 +1,84 @@
+# coding=utf-8
+import re
+import logging
+
+from subzero.modification.processors.re_processor import ReProcessor, NReProcessor
+
+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 = []
+
+    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:
+            old_content = new_content
+            new_content = processor.process(new_content, debug=debug)
+            if not new_content:
+                if debug:
+                    logger.debug("Processor returned empty line: %s", processor)
+                break
+            if debug:
+                if old_content == new_content:
+                    continue
+                logger.debug("%s: %s -> %s", processor, old_content, new_content)
+        return new_content
+
+    def pre_process(self, content, debug=False, parent=None, **kwargs):
+        return self._process(content, self.pre_processors, debug=debug, parent=parent, **kwargs)
+
+    def process(self, content, debug=False, parent=None, **kwargs):
+        return self._process(content, self.processors, debug=debug, parent=parent, **kwargs)
+
+    def post_process(self, content, debug=False, parent=None, **kwargs):
+        return self._process(content, self.post_processors, debug=debug, parent=parent, **kwargs)
+
+    def modify(self, content, debug=False, parent=None, **kwargs):
+        new_content = content
+        for method in ("pre_process", "process", "post_process"):
+            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 = [
+        # empty tag
+        ReProcessor(re.compile(r'({\\\w+1})[\s.,-_!?]+({\\\w+0})'), "", name="empty_tag"),
+
+        # empty line (needed?)
+        NReProcessor(re.compile(r'^\s+$'), "", name="empty_line"),
+
+        # empty dash line (needed?)
+        NReProcessor(re.compile(r'(^[\s]*[\-]+[\s]*)$'), "", name="empty_dash_line"),
+
+        # clean whitespace at start and end
+        ReProcessor(re.compile(r'^\s*([^\s]+)\s*$'), r"\1", name="surrounding_whitespace"),
+    ]

Contents/Libraries/Shared/subzero/modification/mods/common.py

@@ -0,0 +1,61 @@
+# coding=utf-8
+
+import re
+
+from subzero.modification.mods import SubtitleTextModification
+from subzero.modification.processors.string_processor import StringProcessor
+from subzero.modification.processors.re_processor import NReProcessor
+from subzero.modification import registry
+
+
+class CommonFixes(SubtitleTextModification):
+    identifier = "common"
+    description = "Basic common fixes"
+    exclusive = True
+
+    long_description = """\
+    Fix common whitespace/punctuation issues in subtitles
+    """
+
+    processors = [
+        # no space after ellipsis
+        NReProcessor(re.compile(r'(?u)\.\.\.(?![\s.,!?\'"])(?!$)'), "... ", name="CM_ellipsis_no_space"),
+
+        # multiple spaces
+        NReProcessor(re.compile(r'(?u)[\s]{2,}'), " ", name="CM_multiple_spaces"),
+
+        # no space after starting dash
+        NReProcessor(re.compile(r'(?u)^-(?![\s-])'), "- ", name="CM_dash_space"),
+
+        # '' = "
+        StringProcessor("''", '"', name="CM_double_apostrophe"),
+
+        # remove starting spaced dots (not matching ellipses
+        NReProcessor(re.compile(r'(?u)^(?!\s?(\.\s\.\s\.)|(\s?\.{3}))[\s.]*'), "", name="CM_starting_spacedots"),
+
+        # space missing before doublequote
+        #ReProcessor(re.compile(r'(?u)(?<!^)(?<![\s(\["])("[^"]+")'), r' \1', name="CM_space_before_dblquote"),
+
+        # space missing after doublequote
+        #ReProcessor(re.compile(r'(?u)("[^"\s][^"]+")([^\s.,!?)\]]+)'), r"\1 \2", name="CM_space_after_dblquote"),
+
+        # space before ending doublequote?
+
+        # -- = ...
+        StringProcessor("-- ", '... ', name="CM_doubledash"),
+
+        # remove >>
+        NReProcessor(re.compile(r'(?u)^>>[\s]*'), "", name="CM_leading_crocodiles"),
+
+        # remove leading ...
+        NReProcessor(re.compile(r'(?u)^\.\.\.[\s]*'), "", name="CM_leading_ellipsis"),
+
+        # replace uppercase I with lowercase L in words
+        NReProcessor(re.compile(r'(?u)([A-z]+)I([a-z]+)'), r"\1l\2", name="CM_uppercase_i_in_word"),
+
+        # fix spaces in numbers
+        NReProcessor(re.compile(r'(?u)([0-9]+)[\s]+([0-9:.]*[0-9]+)'), r"\1\2", name="CM_spaces_in_numbers"),
+    ]
+
+
+registry.register(CommonFixes)

Contents/Libraries/Shared/subzero/modification/mods/fps.py

@@ -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)

Contents/Libraries/Shared/subzero/modification/mods/hearing_impaired.py

@@ -0,0 +1,33 @@
+# coding=utf-8
+import re
+
+from subzero.modification.mods import SubtitleTextModification
+from subzero.modification.processors.re_processor import NReProcessor
+from subzero.modification import registry
+
+
+class HearingImpaired(SubtitleTextModification):
+    identifier = "remove_HI"
+    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 (only remove if at least 3 consecutive uppercase chars in brackets
+        NReProcessor(re.compile(r'(?sux)[([].+(?=[A-Z]{3,}).+[)\]]'), "", name="HI_brackets"),
+
+        # text before colon (and possible dash in front), max 11 chars after the first whitespace (if any)
+        NReProcessor(re.compile(r'(?u)(^[A-z\-\'"_]+[\w\s]{0,11}:[^0-9{2}][\s]*)'), "", name="HI_before_colon"),
+
+        # all caps line (at least 4 chars)
+        NReProcessor(re.compile(r'(?u)(^(?=.*[A-Z]{4,})[A-Z\s]+$)'), "", name="HI_all_caps"),
+
+        # dash in front
+        # NReProcessor(re.compile(r'(?u)^\s*-\s*'), "", name="HI_starting_dash"),
+    ]
+
+
+registry.register(HearingImpaired)

Contents/Libraries/Shared/subzero/modification/mods/ocr_fixes.py

@@ -0,0 +1,47 @@
+# coding=utf-8
+import logging
+
+from subzero.modification.mods import SubtitleTextModification
+from subzero.modification.processors.string_processor import MultipleLineProcessor, WholeLineProcessor
+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 [
+            WholeLineProcessor(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)

Contents/Libraries/Shared/subzero/modification/mods/offset.py

@@ -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)

Contents/Libraries/Shared/subzero/modification/processors/__init__.py

@@ -0,0 +1,29 @@
+# coding=utf-8
+
+
+class Processor(object):
+    """
+    Processor base class
+    """
+    name = None
+    parent = 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, debug=False):
+        return content
+
+    def __repr__(self):
+        return "Processor <%s %s>" % (self.__class__.__name__, self.info)
+
+    def __str__(self):
+        return repr(self)
+
+    def __unicode__(self):
+        return unicode(repr(self))

Contents/Libraries/Shared/subzero/modification/processors/re_processor.py

@@ -0,0 +1,63 @@
+# coding=utf-8
+import re
+import logging
+
+from subzero.modification.processors import Processor
+
+logger = logging.getLogger(__name__)
+
+
+class ReProcessor(Processor):
+    """
+    Regex processor
+    """
+    pattern = None
+    replace_with = None
+
+    def __init__(self, pattern, replace_with, name=None):
+        super(ReProcessor, self).__init__(name=name)
+        self.pattern = pattern
+        self.replace_with = replace_with
+
+    def process(self, content, debug=False):
+        return self.pattern.sub(self.replace_with, content)
+
+
+class NReProcessor(ReProcessor):
+    """
+    Single line regex processor
+    """
+
+    def process(self, content, debug=False):
+        lines = []
+        for line in content.split(r"\N"):
+            a = line.strip()
+            a = super(NReProcessor, self).process(a, debug=debug)
+            if not a:
+                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)
+

Contents/Libraries/Shared/subzero/modification/processors/string_processor.py

@@ -0,0 +1,92 @@
+# 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, parent=None):
+        super(StringProcessor, self).__init__(name=name)
+        self.search = search
+        self.replace = replace
+
+    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 WholeLineProcessor(MultipleLineProcessor):
+    def process(self, content, debug=False):
+        if not self.snr_dict["data"]:
+            return content
+        content = content.strip()
+
+        for key, value in self.snr_dict["data"].iteritems():
+            if content == key:
+                if debug:
+                    logger.debug(u"Replacing '%s' with '%s'", key, value)
+
+                content = value
+                break
+
+        return content
+
+
+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)

Contents/Libraries/Shared/subzero/modification/registry.py

@@ -0,0 +1,17 @@
+# coding=utf-8
+from collections import OrderedDict
+
+
+class SubtitleModRegistry(object):
+    mods = None
+    mods_available = None
+
+    def __init__(self):
+        self.mods = OrderedDict()
+        self.mods_available = []
+
+    def register(self, mod):
+        self.mods[mod.identifier] = mod
+        self.mods_available.append(mod.identifier)
+
+registry = SubtitleModRegistry()

Contents/Libraries/Shared/subzero/subtitle_storage.py

@@ -178,9 +178,11 @@ class StoredSubtitlesManager(object):
         try:
             subs_for_video = self.storage.LoadObject(fn)
         except:
-            logger.error("Failed to load item %s: %s" % (fn, traceback.format_exc()))
+            logger.error("Failed to load item \"%s\": %s" % (fn, traceback.format_exc()))
 
-        if not subs_for_video:
+        if not subs_for_video or not hasattr(subs_for_video, "version"):
+            logger.error("Invalid subtitle storage for \"%s\", removing" % fn)
+            self.delete(fn)
             return
 
         # apply possible migrations

Contents/Libraries/Shared/test.srt

@@ -4,37 +4,37 @@
 
 2
 00:00:10,759 --> 00:00:12,678
-ROSE: So what is it?
-What's wrong?
+ROSE: (Help us. Please. . .help us.)
+What's "wrong"?
 
 3
 00:00:12,679 --> 00:00:16,097
-I don't know. Some kind
+I don't know. Some kind of wrong "1 00" number
 of signal, drawing the Tardis off course.
 
 4
 00:00:16,099 --> 00:00:17,224
-Where are we?
+this is a"subtitle" test "with a"text before colons and "peter"following: Where are we?."
 
 5
 00:00:17,225 --> 00:00:19,684
-Earth. Utah, North America.
+"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 miIe 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
-2012.
+...2012.  it's 1 2:00 o'clock
 
 9
 00:00:26,650 --> 00:00:29,370
-God, that's so close. I should be 26!
+(BIG BROTHER THEME MUSIC)
 
 10
 00:00:30,612 --> 00:00:33,112
@@ -43,27 +43,28 @@ God, that's so close. I should be 26!
 11
 00:00:33,658 --> 00:00:34,783
 (WHOO
-SHING) geil
+SHING) >>geil
 
 12
 00:00:34,783 --> 00:00:36,826
-Blimey.
+-- Blimey.
 
 13
 00:00:36,828 --> 00:00:39,328
-ROSE: Like a great big museum.
+ROSE: Like a "great...big museum".
 
 14
 00:00:40,414 --> 00:00:42,914
-DOCTOR: An alien museum.
+DOCTOR's MOM: ''An alien museum".
 
 15
 00:00:43,542 --> 00:00:46,042
-Someone's got a hobby.
+Someone's got a   hobby.
 
 16
 00:00:46,378 --> 00:00:49,048
-They must've spent a fortune on this.
+FULL UPPERCASE LINE HERE
+and some text
 
 17
 00:00:49,631 --> 00:00:51,924

README.md

@@ -10,6 +10,40 @@ Checkout **[the Sub-Zero Wiki](https://github.com/pannal/Sub-Zero.bundle/wiki)**
 
 ## Changelog
 
+2.0.15.1216 RC3
+- core: fixes
+- scheduler: revert some of the aggressive changes in RC2
+- submod: be smarter about WholeLine matches
+
+
+2.0.15.1209 RC2
+- core: fixes
+- core: submod-common: fix multiple dots at start of line
+- core/menu: add subtitle modification debug setting
+- core/menu: when manually listing available subtitles in menu, display those with wrong FPS also (opensubtitles), because you can fix them later
+- core/menu: advanced-menu: add apply-all-default-mods menu item; add re-apply all mods menu item
+- core: always look for currently (not-) existing subtitles when called; hopefully fixes #276
+- scheduler/menu: be faster; also launch scheduled tasks in threads, not just manually launched ones
+- core: don't delete subtitles with .custom or .embedded in their filenames when running auto cleanup, if the correct media file exists
+- menu: add back-to-previous menu items
+
+
+2.0.12.1180 RC1
+- core: update subliminal to version 2
+- core: update all dependencies
+- core: add new providers: legendastv (pt-BR), napiprojekt (pl), shooter (cn), subscenter (heb)
+- core: rewritten all subliminal patches for version 2
+- menu: add icons for menu items; update main channel icon
+- core: use SSL again for opensubtitles
+- core: improved matching due to subliminal 2 (and SZ custom) tvdb/omdb refiners
+- menu: add "Get my logs" function to the advanced menu, which zips up all necessary logs suitable for posting in the forums
+- core: on non-windows systems, utilize a file-based cache database for provider media lists and subliminal refiner results
+- core: add manual and automatic subtitle modification framework (fix common OCR issues, remove hearing impaired etc.)
+- menu: add subtitle modifications (subtitle content fixes, offset-based shifting, framerate conversion)
+- menu: add recently played menu
+- improve almost everything Sub-Zero did in 1.4 :)
+
+
 1.4.27.973
 - core: ignore "obfuscated" and "scrambled" tags in filenames when searching for subtitles
 - core: exotic embedded subtitles are now also considered when searching (and when the option is enabled); fixes #264