Compare commits

..

8 Commits

Author SHA1 Message Date
Antoine Bertin 04fdd0bf4e Release v0.2 2011-07-11 20:42:16 +02:00
Antoine Bertin dff90cb90e Fix an encoding issue when passing unicode entries 2011-07-08 08:16:53 +02:00
Antoine Bertin a56f6db0ca Update Copyright notice 2011-07-07 22:57:34 +02:00
Antoine Bertin 95cae1213c Remove some extra logging 2011-07-07 22:57:09 +02:00
Antoine Bertin f4fb9dd9d6 Fix a bug where plugins didn't save to config file 2011-07-07 22:56:52 +02:00
Antoine Bertin 67a6647aa8 Switch version to master 2011-07-07 22:26:42 +02:00
Antoine Bertin bb355c214d License update 2011-07-07 08:51:48 +02:00
Antoine Bertin 9f298366a9 Initial commit 2011-07-05 02:27:11 +02:00
1697 changed files with 2454 additions and 350429 deletions
+4 -58
View File
@@ -1,58 +1,4 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
# C extensions
*.so
# Distribution / packaging
.Python
env/
bin/
build/
develop-eggs/
dist/
eggs/
lib64/
parts/
sdist/
var/
*.egg-info/
.installed.cfg
*.egg
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.cache
nosetests.xml
coverage.xml
# Translations
*.mo
# Mr Developer
.mr.developer.cfg
.project
.pydevproject
.settings
# Rope
.ropeproject
# Django stuff:
*.log
*.pot
# Sphinx documentation
docs/_build/
# pycharm
.idea
icon.psd
build
dist
subliminal.egg-info
*.pyc
-411
View File
@@ -1,411 +0,0 @@
1.4.27.957
- core: correctly fall back to the next best subtitle if the current one couldn't be downloaded; hopefully fixes #231
- core: add "Scan: which external subtitles should be picked up?"-setting
- core: add optional on_playing activities. refresh currently playing movie, refresh next episode in season, both or none; fixes #259 #33
- core: skip to next best subtitle if findbettersubtitles failed
- core: add setting to treat undefined-language embedded subtitle as configured language1 #239
- core: fix handling of inexistant addic7ed show id
- core: fix regression issue breaking relative custom subtitle folder handling
- core: fix loading of stored subtitle info data of now-non-existant items
- core: re-add separate global subtitle folder handling
- menu: remove obsolete actions from the advanced menu
1.4.23.920
- core: handle undecodable paths better #255
- core: don't fail on unrecoverable data #257
- core: increase default scores from 110 (series) and 23 (movies) to 116 and 33
- core: fix global subtitle folder handling #234
- core: better invoking of configured executable after subtitle addition #247
1.4.22.908
- core: hotfix for more robust migrations
1.4.22.898
- core: migrate history and subtitle storage to a better implementation, making it far more stable. subtitle storage now also stores the downloaded subtitle data for future usage, so it will be possible to switch between them
- core/menu: manual subtitle download and the FindBetterSubtitles-task now also work with metadata storage (hi @ shield users)
- core: optimize FindBetterSubtitles-task
1.4.19.882
- core: fix tasks for new users
- core: double check pin correctness/existance when pin is enabled
1.4.19.878
- core/menu: fix a task's last runtime display
- core: task optimizations
- core: fix leftover subtitles cleanup handling in case of a custom subtitle folder #234
- core: run the scheduler even if permissions for libraries are wrong ("fixes" #236)
- core: store subtitle history data in a different data format; reduce used storage size drastically (#233)
1.4.19.866
- core: fix wrong usage of LogKit
1.4.19.857
- core: add option to enable/disable channel and/or agent modes (fixes #220)
- core: skip inexistent internal streams when scanning for internal subtitles (fixes #222)
- core: fix filename encoding (fixes #223)
- core: storage optimizations
- menu: add pin-based channel menu locking (the whole channel or only the advanced menu)
1.4.17.836
- core: support for any media file that PMS supports (internal subtitles on mp4 for example)
- core: fix broken ignore folders containing "subzero.ignore/.subzero.ignore/.nosz"
- core: fix duplicate subtitles (lowercase/default case)
- core: fix broken tasks queue due to oversight
1.4.16.822
- menu: add per-section recently added menu
- menu: fix accidentally double-triggering a just triggered force-refresh
- core: reorder settings in a more logical, grouped way
- core: add simple automatic filesystem/external leftover subtitle cleaning (#133, #152)
- core: fix force-refresh for big seasons/series
- core: add setting to look for forced/foreign-only subtitles only (only works for opensubtitles and podnapisi)
- core: fix custom subtitle folder was being ignored (#211)
- core: only trust PMS for its movie name, not the series title (fixes #210)
- core: full support (in filesystem/external mode) for forced/default/normal subtitle tags
- core: ignore "non-standard" external subtitle files when scanning by default (everything but .srt, .ass, .ssa, fixes #192)
- core: lower default max_recent_items_per_library to 500
- core: skip forced/foreign-only subtitles if not specifically wanted
- core: modify the task queue, hopefully helping #206
- core: update anonymous usage collection
1.4.11.781
- core: cleanup, logging
- core/menu: fix addic7ed display in manual subtitle list
- core: use HTTP for OpenSubtitles instead of HTTPS because of current certificate errors
- core: find better subtitles should now run smoothly even with replaced files (newer parts)
1.4.10.769
- core: hotfix for legacy intent storage regression
1.4.10.768
- core: automatically find better subtitles (configurable)
- menu: display how the subtitle was downloaded (auto, manual, auto-better), in history menu
- menu/core: correctly handle subtitle list for multiple languages
- core: lower minimum series score to list subtitles for to 66
- core: better matching of garbage filenames; we trust Plex now for the series name/movie title fully
- core: add setting to specifically set the file permissions (chmod)
1.4.5.742
- core: fix force-refresh in certain situations
- menu: add history
- menu: add manual subtitle selection
- menu: run Items with missing subtitles in separate thread for big libraries
- settings: add history list size option (default: 100)
- settings: add new default scores (TV: 110); use input instead of dropdown
- settings: increase default missing subtitles amount per library to 2000
- core: generic rewrites and optimizations
- core: better hash verification
- core: add anonymous usage data (opt-out in settings)
- core: fix pt-BR display (IETF) again
- wiki: update (thanks @dane22!) - quick URL: http://v.ht/szwiki
- wiki: add score explanation - quick URL: http://v.ht/szscores
- core: add persian/farsi encoding support
1.3.49.636
- core/menu: fix force refreshing (again)
- core/menu: fix redundant route calls
1.3.49.630 (backported some changes of the develop-1.4 branch to 1.3)
- core/menu: make addic7ed boost configurable; lower the default boost value massively (to 10)
- core: fix force refreshing (hopefully)
- core: add (thai) tis-620 subtitle encoding support
- menu: lower letter based menu browsing from 200 to 80 items
- core: support greek encodings (windows-1253, cp1253, cp737, iso8859_7, cp875, cp869, iso2022_jp_2, mac_greek); hopefully fixes badly saved greek subs
- menu: add generic back-to-home button to the top of every container view
- menu: warn the user when SZ isn't enabled for any sections/libraries
- menu: always re-check permissions status and enabled sections when opening the main menu; no server restart necessary anymore
1.3.46.606
- core: hotfix for new users (who've never downloaded a subtitle with SZ before); fixes #169
1.3.46.605
- add wiki (thanks @ukdtom / @dane22)
- core: remove necessity of Plex credentials; fixes #148
- core: fix non-SRT subtitle support; fixes #138
- core: generic source overhaul in preparation for release 1.4
- core: better filesystem encoding detection; may fix #159
- core: add encoding handling for windows-1250 and windows-1251 encoding (eastern europe); fixes #162
- core: overhaul ignore handling; fixes #164
- core: implement ignore by path setting; fixes #134
- core: add setting for optional fallback to metadata storage, if filesystem storage failed; fixes #100
- core: add setting for notifying an executable after a subtitle has been downloaded (see Wiki); fixes #65
- core: only handle sections for which Sub-Zero is enabled (in PMS agent settings); fixes #167
- menu: add series/season force-refresh
- menu: show item thumbnail/art where applicable
- menu: mitigate PlexWeb behaviour of calling our handlers twice; fixes #168
1.3.33.522
- core: fix library permission detection on windows; fixes #151
- core: "Restrict to one language" now behaves like it should (one found subtitle of any language is treated as sufficient); fixes #149
- core: add support for other subtitle formats such as ssa/ass/microdvd, convert to srt; fixes #138
- core: hopefully more consistent force-refresh handling (intent); fixes #118
1.3.31.513
- core: add option to only download one language again (and skip the addition of .lang to the subtitle filename) (default: off); fixes #126
- core: add option to always encode saved subtitles to UTF-8 (default: on); fixes #128
- core: add fallback encoding detection using bs4.UnicodeDammit; hopefully fixes #101
- core: update libraries: chardet, beautifulsoup, six
- menu/core: check Plex libraries for permission problems on plugin start and report them in the channel menu (option, default: on); fixes #143
- menu: while a manual refresh takes place, add a refresh button to the top of the SZ menu for convenience
- menu: move the "add/remove X to ignore list" menu item to the bottom of the list on item detail
1.3.27.491
- menu/core: make Sub-Zero channel menu optional (setting: "Enable Sub-Zero channel (disabling doesn't affect the subtitle features)?")
- OpenSubtitles: detect and match video/subtitle FPS (framerate) to reduce out of sync subtitle matches
- core: internal fixes; add _markerlib library (rare)
- core: don't score tvshow episode title matches, should improve episode subtitle matches quite a bit (and reduce out of sync subtitles)
- OpenSubtitles: make tag/exact filename matches optional (setting: "I keep the exact (release-) filename of my media files")
- menu: unicode video title errors fixed
- TVSubtitles: correctly match certain show IDs (such as "Series Name (US)")
- core: don't break subtitle evaluation on crashed guessing
1.3.23.459
- core: slight code cleanup and fixes
- core: add physical (filesystem) ignore mode (create files named `subzero.ignore`, `.subzero.ignore`, `.nosz` to ignore specific files/seasons/series/libraries)
- core: fix guessit hinting of tv series with rare folder layout (e.g. series_name/a/S01E01.mkv)
- core: remove "format" necessity from (opensubtitles) hash-validation
- OpenSubtitles: dramatically improve matching: add tag (exact filename) matching and treat it just like hash matches
- core: ignore embedded forced subtitles (fixes #106)
- docs: update
- settings: clarify
1.3.20.422
- tvsubtitles: show matching was partially broken
- addic7ed: better show matching
- core: correctly skip subtitles stored in filesystem if metadata storage was selected (Local Media Assets agent may still pick them up)
- core: fix local API access (switch from HTTPS to HTTP)
- core: fix handling of library names and media paths with non-ascii chars in it
- core: fix bundle version to correctly display current bundle version
- core: skip downloading multi-CD subtitle
- settings: clarify
1.3.20.403
- core: handle & and - ("and" and dash) in names
- core: fixed handling of internal metadata subtitles
- re-upped the minimum tv score to 85 (may be even higher in the future)
- opensubtitles: possibly significantly better movie matching (now also query for movie title, instead of only querying for video hash)
1.3.20.396
- core: fix logging handlers (when saving log_level settings loggers got duplicated)
- core: better movie matching by only hinting the filename and the last subdirectory to guessit (instead of the full path)
- core: don't fail on wrong detection/scanning of media file
- lower minimum tv series score from 85 to 67 (removed title; composed of: series=44 + season=11 + episode=11 + hearing_impaired=1)
1.3.19.379
- core: new recent items implementation (used in "Items with missing subtitles"), now really picking up everything instead of using Plex's recently_added API endpoint
- core: be more strict about title matching - a matched title doesn't automatically mean season and episode are correct, too
- core: rewrote the hash matching algorithm to not blindly trust hash matches anymore, but instead episodes have to match the series name, season number, episode number and format (BluRay, HDTV...); movie have to at least match the title, format and codec for the hash to be considered
- core: remove TheSubDB support for now, as it only supports hash-based matching
- scheduler: more robust item-fail-handling (fixes #81)
- config: "Scan: include embedded subtitles" now by default is off, as embedded subs have proven to be pretty unreliable
- config: add configuration option for how many items per library are to be considered recent (default: 200)
- config: make logging verbosity configurable, default: WARNING - log files should be considerably smaller now
- config: make console logging optional, default: off - good for development/debugging
- config: removed the ignore lists
- menu: added "Browse all items", where you can browse all your libraries and manage your ignore list (add/remove sections/series/items)
- menu: added "Display ignore list", where you can manage your ignored sections, series and items
- menu: the submenu titles are now dynamically composed of a breadcrumb-style tree so you see where you are
- menu: show the current and past state of the important menu actions such as (force)-refresh an item or refreshing the menu, on the Refresh-button's description
- plugin now isn't in the dev mode by default and has logging to the console off (in certain configurations this resulted in huge syslogs)
1.3.6.316
- scheduler: missing subtitles task now able to handle huge libraries (thanks @chopeta, @comrade)
- scheduler: detect item-stalling, add wait and retry logic to make missing subtitles task more robust
- scheduler: report failed items to logs after task run completion
- hint series name and episode title, or movie title to guessit to make detection way better (e.g. for Mr. Robot)
1.3.6.304
- scheduler: correct the recent-determination of the search for missing subtitles in recently_added task
- scheduler: rewrote search for missing subtitles task; it now requests refreshes one by one and not in bulk anymore (hopefully fixes stalling)
- handle rare cases of weird file system encodings (ANSI_X3.4-1968 for example)
- fix simplejson warning on startup
1.3.6.297
- rename Sub-Zero to Sub-Zero.bundle (requirement for adding Sub-Zero to the Plex channel directory)
- channel: add logging actions for the internal storage to the advanced menu
- channel: handle item titles with foreign characters in them correctly
- (hopefully) fix handling file names with foreign characters in them when scanning for local media
- reformat the whole project, mostly honoring pep8
- scheduler: fixed some serious bugs; broken tasks (stalled) and some errors many of you have seen should be gone now
- scheduler: partly rewritten to be more robust, again
- settings: move Plex.tv credentials to the top
1.3.5.281
- fix tasks broken for 1.2 -> 1.3.5 upgraders
1.3.5.273 (same build as Beta Release 1.3.0.273) - changes from previous stable 1.2.11.180
- add a channel menu, making this plugin a hybrid (Agent+Channel)
- add a generic background task scheduler
- add a task to search for subtitles for items with missing subtitles (manually triggered and automatic)
- add artwork
- add Plex.tv credentials/token-generation support (needed for Plex Home users for the API to work)
- addic7ed: improve show name matching again
- channel: able to browse current on-deck and recently-added items, and refresh or force-refresh (search for new subtitles) single items
- add library/series/video blacklist for items which should be skipped in "Search for missing subtitles"-task
- add donation links
- change the license to The Unlicense (while keeping the original MIT license from subliminal.bundle intact)
- store subtitle information in internal plugin storage (for later usage)
- many internal code improvements
- update documentation
1.3.0.273
- more robust update functionality
- menu: add refresh button to menu (to see the task state updating)
- scheduler: actually skip a task if it's already running
- scheduler: better behaviour when a task is running and a single item is refreshed at the same time
- menu: enforce ascii on item titles
1.3.0.261
- removed localization again
1.3.0.259
- forgot locale-data
1.3.0.256
- fix force-refresh single items to actually force-refresh
- re-add babel library
1.3.0.253
- rewrote background tasks subsystem
- keep track of the status of a task and its runtime
- add task state in channel menu to "Search for missing subtitles"
- add date/time localization to channel menu
- hide plex token from logs, when requesting
- fix addic7ed show id parsing for shows with year set
- test PMS API connectivity and fail miserably if needed (channel disabled, scheduler disabled)
- feature-freeze for 1.3.0 final
1.3.0.245
- add the option to buy me a beer
- clarify menu items
- more robust scheduler handling (should fix the issues of scheduler runs in the past)
- internal cleanups
- add date_added to stored subtitle info (all of the 1.3.0 testers: please delete your internal subtitle storage using the channel->advanced menu)
1.3.0.232
- integrate plex.tv authentication for plex home users (test phase)
- menu cleanup
- more info in the menu (scheduler last and next run for example)
- hopefully fixed intent handling (should throw less errors now)
- fix version display in agent names
1.3.0.222
- bugfix for search missing subtitles
- schedduler: honor "never"
1.3.0.216
- add channel menu
- add generic task scheduler
- add functionality to search for missing subtitles (via recently added items)
- add artwork
- change license to The Unlicense
- ...
1.2.11.180
- fix #49 (metadata storage didn't work)
- add better detection for existing subtitles stored in metadata
1.2.11.177
- updated naming scheme to reflect rewrite.major.minor.build (this release is the same as 1.1.0.5)
1.1.0.5
- addic7ed: fixed error in show id search
- addic7ed: even better show matching
- adjusted default scores: TV: 85, movies: 23
- add support for com.plexapp.agents.xbmcnfo/xbmcnfotv (proposed to the author [here](https://github.com/gboudreau/XBMCnfoMoviesImporter.bundle/pull/63) and [here](https://github.com/gboudreau/XBMCnfoTVImporter.bundle/pull/70))
1.1.0.3
- addic7ed/tvsubtitles: be way smarter about punctuation in series names (*A.G.E.N.T.S. ...*)
- ditch LocalMediaExtended and incorporate the functionality in Sub-Zero (**RC-users: delete LocalMediaExtended.bundle and re-enable LocalMedia!**)
- remove (unused) setting "Restrict to one language"
- add "Treat IETF language tags as ISO 639-1 (e.g. pt-BR = pt)" setting (default: true)
- change default external storage to "current folder" instead of "/subs"
- adjust default scores
RC-5.2
- revert back to /plexinc-agents/LocalMedia.bundle/tree/dist instead of /plexinc-agents/LocalMedia.bundle/tree/master, as the current public PMS version is too old for that
RC-5.1
- make hearing_impaired option more configurable and clear (see #configuration-)
RC-5
- fix wrong video type matching by hinting video type to guessit
- update to newest LocalMediaExtended.bundle (incorporated plex-inc's changes)
- show page links for subtitles in log file instead of subtitle ID
- add custom language setting in addition to the three hardcoded ones
- if a subtitle doesn't match our hearing_impaired setting, ignore it
- add an optional boost for addic7ed subtitles, if their series, season, episode, year, and format (e.g. WEB-DL) matches
RC-4
- rename project to Sub-Zero
- incorporate LocalMediaExtended.bundle
- making this a multi-bundle plugin
- update default scores
- add icon
RC-3
- addic7ed/tvsubtitles: punctuation fixes (correctly get show ids for series like "Mr. Poopster" now)
- podnapisi: fix logging
- opensubtitles: add login credentials (for VIPs)
- add retry functionality to retry failed subtitle downloads, including configurable amount of retries until discarding of provider
- move possibly not needed setting "Restrict to one language" to the bottom
- more detailed logging
- some cleanup
RC-2
- fix empty custom subtitle folder creation
- fix detection of existing embedded subtitles (switch to https://github.com/tonswieb/enzyme)
- better logging
- set default TV score to 15; movie score to 30
RC-1
- fix subliminal's logging error on min_score not met (fixes #15)
- separated tv and movies subtitle scores settings (fixes #16)
- add option to save only one subtitle per video (skipping the ".lang." naming scheme plex supports) (fixes #3)
beta5
- fix storing subtitles besides the actual video file, not subfolder (fixes #14)
- "custom folder" setting now always used if given (properly overrides "subtitle folder" setting)
- also scan (custom) given subtitle folders for existing subtitles instead of redownloading them on every refresh (fixes #9, #2)
beta4
- ~~increased score of addic7ed subtitles a bit~~ (not existing currently)
- **support for newest Subliminal ([1.0.1](27a6e51cd36ffb2910cd9a7add6d797a2c6469b7)) and guessit ([0.11.0](2814f57e8999dcc31575619f076c0c1a63ce78f2))**
- **plugin now also [works with com.plexapp.agents.thetvdbdvdorder](924470d2c0db3a71529278bce4b7247eaf2f85b8)**
- providers fixed for subliminal 1.0.1 ([at least addic7ed](131504e7eed8b3400c457fbe49beea3b115bc916))
- providers [don't simply fail and get excluded on non-detected language](1a779020792e0201ad689eefbf5a126155e89c97)
- support for addic7ed languages: [French (Canadian)](b11a051c233fd72033f0c3b5a8c1965260e7e19f)
- support for additional languages: [pt-br (Portuguese (Brasil)), fa (Persian (Farsi))](131504e7eed8b3400c457fbe49beea3b115bc916)
- support for [three (two optional) subtitle languages](e543c927cf49c264eaece36640c99d67a99c7da2)
- optionally use [random user agent for addic7ed provider](83ace14faf75fbd75313f0ceda9b78161895fbcf) (should not be needed)
-258
View File
@@ -1,258 +0,0 @@
# coding=utf-8
import sys
from subliminal_patch import compute_score
from subzero.sandbox import restore_builtins
module = sys.modules['__main__']
restore_builtins(module, {})
globals = getattr(module, "__builtins__")["globals"]
for key, value in getattr(module, "__builtins__").iteritems():
if key != "globals":
globals()[key] = value
import logger
sys.modules["logger"] = logger
import subliminal
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
from support.items import is_ignored
from support.config import config
from support.lib import get_intent
from support.helpers import track_usage, get_title_for_video_metadata, get_identifier, cast_bool
from support.history import get_history
from support.data import dispatch_migrate
from support.activities import activity
def Start():
HTTP.CacheTime = 0
HTTP.Headers['User-agent'] = OS_PLEX_USERAGENT
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})
# clear expired intents
intent = get_intent()
intent.cleanup()
# clear expired menu history items
now = datetime.datetime.now()
if "menu_history" in Dict:
for key, timeout in Dict["menu_history"].items():
if now > timeout:
del Dict["menu_history"][key]
# run migrations
if "subs" in Dict or "history" in Dict:
Thread.Create(dispatch_migrate)
# clear old task data
scheduler.clear_task_data()
# init defaults; perhaps not the best idea to use ValidatePrefs here, but we'll see
ValidatePrefs()
Log.Debug(config.full_version)
if not config.permissions_ok:
Log.Error("Insufficient permissions on library folders:")
for title, path in config.missing_permissions:
Log.Error("Insufficient permissions on library %s, folder: %s" % (title, path))
# run task scheduler
scheduler.run()
# bind activities
Thread.Create(activity.start)
if "anon_id" not in Dict:
Dict["anon_id"] = get_identifier()
# track usage
if cast_bool(Prefs["track_usage"]):
if "first_use" not in Dict:
Dict["first_use"] = datetime.datetime.utcnow()
Dict.Save()
track_usage("General", "plugin", "first_start", config.version)
track_usage("General", "plugin", "start", config.version)
def download_best_subtitles(video_part_map, min_score=0):
hearing_impaired = Prefs['subtitles.search.hearingImpaired']
languages = config.lang_list
if not languages:
return
missing_languages = False
for video, part in video_part_map.iteritems():
if not Prefs['subtitles.save.filesystem']:
# scan for existing metadata subtitles
meta_subs = get_subtitles_from_metadata(part)
for language, subList in meta_subs.iteritems():
if subList:
video.subtitle_languages.add(language)
Log.Debug("Found metadata subtitle %s for %s", language, video)
missing_subs = (languages - video.subtitle_languages)
# all languages are found if we either really have subs for all languages or we only want to have exactly one language
# and we've only found one (the case for a selected language, Prefs['subtitles.only_one'] (one found sub matches any language))
found_one_which_is_enough = len(video.subtitle_languages) >= 1 and Prefs['subtitles.only_one']
if not missing_subs or found_one_which_is_enough:
if found_one_which_is_enough:
Log.Debug('Only one language was requested, and we\'ve got a subtitle for %s', video)
else:
Log.Debug('All languages %r exist for %s', languages, video)
continue
missing_languages = True
break
if missing_languages:
Log.Debug("Download best subtitles using settings: min_score: %s, hearing_impaired: %s" % (min_score, hearing_impaired))
return subliminal.download_best_subtitles(video_part_map.keys(), languages, min_score, hearing_impaired, providers=config.providers,
provider_configs=config.provider_settings, pool_class=config.provider_pool,
compute_score=compute_score)
Log.Debug("All languages for all requested videos exist. Doing nothing.")
def update_local_media(metadata, media, media_type="movies"):
# Look for subtitles
if media_type == "movies":
for item in media.items:
for part in item.parts:
support.localmedia.find_subtitles(part)
return
# Look for subtitles for each episode.
for s in media.seasons:
# If we've got a date based season, ignore it for now, otherwise it'll collide with S/E folders/XML and PMS
# prefers date-based (why?)
if int(s) < 1900 or metadata.guid.startswith(PERSONAL_MEDIA_IDENTIFIER):
for e in media.seasons[s].episodes:
for i in media.seasons[s].episodes[e].items:
# Look for subtitles.
for part in i.parts:
support.localmedia.find_subtitles(part)
else:
pass
class SubZeroAgent(object):
agent_type = None
agent_type_verbose = None
languages = [Locale.Language.English]
primary_provider = False
score_prefs_key = None
def __init__(self, *args, **kwargs):
super(SubZeroAgent, self).__init__(*args, **kwargs)
self.agent_type = "movies" if isinstance(self, Agent.Movies) else "series"
self.name = "Sub-Zero Subtitles (%s, %s)" % (self.agent_type_verbose, config.get_version())
def search(self, results, media, lang):
Log.Debug("Sub-Zero %s, %s search" % (config.version, self.agent_type))
results.Append(MetadataSearchResult(id='null', score=100))
def update(self, metadata, media, lang):
if not config.enable_agent:
Log.Debug("Skipping Sub-Zero agent(s)")
return
Log.Debug("Sub-Zero %s, %s update called" % (config.version, self.agent_type))
intent = get_intent()
if not media:
Log.Error("Called with empty media, something is really wrong with your setup!")
return
item_ids = []
try:
config.init_subliminal_patches()
videos = media_to_videos(media, kind=self.agent_type)
# media ignored?
use_any_parts = False
for video in videos:
if is_ignored(video["id"]):
Log.Debug(u"Ignoring %s" % video)
continue
use_any_parts = True
if not use_any_parts:
Log.Debug(u"Nothing to do.")
return
try:
use_score = int(Prefs[self.score_prefs_key].strip())
except ValueError:
Log.Error("Please only put numbers into the scores setting. Exiting")
return
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)
# downloaded_subtitles = {subliminal.Video: [subtitle, subtitle, ...]}
downloaded_subtitles = download_best_subtitles(scanned_video_part_map, min_score=use_score)
item_ids = get_media_item_ids(media, kind=self.agent_type)
whack_missing_parts(scanned_video_part_map)
if downloaded_subtitles:
save_subtitles(scanned_video_part_map, downloaded_subtitles)
track_usage("Subtitle", "refreshed", "download", 1)
for video, video_subtitles in downloaded_subtitles.items():
# store item(s) in history
for subtitle in video_subtitles:
item_title = get_title_for_video_metadata(video.plexapi_metadata, add_section_title=False)
history = get_history()
history.add(item_title, video.id, section_title=video.plexapi_metadata["section"],
subtitle=subtitle)
update_local_media(metadata, media, media_type=self.agent_type)
finally:
# update the menu state
set_refresh_menu_state(None)
# notify any running tasks about our finished update
for item_id in item_ids:
scheduler.signal("updated_metadata", item_id)
# resolve existing intent for that id
intent.resolve("force", item_id)
Dict.Save()
class SubZeroSubtitlesAgentMovies(SubZeroAgent, Agent.Movies):
contributes_to = ['com.plexapp.agents.imdb', 'com.plexapp.agents.xbmcnfo', 'com.plexapp.agents.themoviedb', 'com.plexapp.agents.hama']
score_prefs_key = "subtitles.search.minimumMovieScore2"
agent_type_verbose = "Movies"
class SubZeroSubtitlesAgentTvShows(SubZeroAgent, Agent.TV_Shows):
contributes_to = ['com.plexapp.agents.thetvdb', 'com.plexapp.agents.themoviedb',
'com.plexapp.agents.thetvdbdvdorder', 'com.plexapp.agents.xbmcnfotv', 'com.plexapp.agents.hama']
score_prefs_key = "subtitles.search.minimumTVScore2"
agent_type_verbose = "TV"
-7
View File
@@ -1,7 +0,0 @@
import sys
import menu
sys.modules["interface.menu"] = menu
import menu_helpers
sys.modules["interface.menu_helpers"] = menu_helpers
-957
View File
@@ -1,957 +0,0 @@
# coding=utf-8
import logging
import datetime
import logger
import os
import StringIO
import glob
from zipfile import ZipFile, ZIP_DEFLATED
from menu_helpers import add_ignore_options, dig_tree, set_refresh_menu_state, \
should_display_ignore, enable_channel_wrapper, default_thumb, debounce, ObjectContainer, SubFolderObjectContainer, \
ZipObject
from subzero.constants import TITLE, ART, ICON, PREFIX, PLUGIN_IDENTIFIER, DEPENDENCY_MODULE_NAMES
from support.background import scheduler
from support.config import config
from support.helpers import pad_title, timestamp, get_language, df, cast_bool
from support.ignore import ignore_list
from support.items import get_item, get_on_deck_items, refresh_item, get_all_items, get_items_info, \
get_item_thumb, get_item_kind_from_rating_key
from support.lib import Plex
from subzero.lib.io import FileIO
from support.plex_media import get_plex_metadata, scan_videos
from support.storage import reset_storage, log_storage, get_subtitle_storage
# init GUI
ObjectContainer.art = R(ART)
ObjectContainer.no_cache = True
# default thumb for DirectoryObjects
DirectoryObject.thumb = default_thumb
# noinspection PyUnboundLocalVariable
route = enable_channel_wrapper(route)
# noinspection PyUnboundLocalVariable
handler = enable_channel_wrapper(handler)
main_icon = ICON if not config.is_development else "icon-dev.jpg"
@handler(PREFIX, TITLE if not config.is_development else TITLE + " DEV", art=ART, thumb=main_icon)
@route(PREFIX)
def fatality(randomize=None, force_title=None, header=None, message=None, only_refresh=False, no_history=False,
replace_parent=False):
"""
subzero main menu
"""
title = config.full_version # force_title if force_title is not None else config.full_version
oc = ObjectContainer(title1=title, title2=title, header=unicode(header) if header else title, message=message,
no_history=no_history,
replace_parent=replace_parent, no_cache=True)
# always re-check permissions
config.refresh_permissions_status()
# always re-check enabled sections
config.refresh_enabled_sections()
if config.lock_menu and not config.pin_correct:
oc.add(DirectoryObject(
key=Callback(PinMenu, randomize=timestamp()),
title=pad_title("Enter PIN"),
summary="The owner has restricted the access to this menu. Please enter the correct pin",
))
return oc
if not config.permissions_ok and config.missing_permissions:
for title, path in config.missing_permissions:
oc.add(DirectoryObject(
key=Callback(fatality, randomize=timestamp()),
title=pad_title("Insufficient permissions"),
summary="Insufficient permissions on library %s, folder: %s" % (title, path),
))
return oc
if not config.enabled_sections:
oc.add(DirectoryObject(
key=Callback(fatality, randomize=timestamp()),
title=pad_title("I'm not enabled!"),
summary="Please enable me for some of your libraries in your server settings; currently I do nothing",
))
return oc
if not only_refresh:
if Dict["current_refresh_state"]:
oc.add(DirectoryObject(
key=Callback(fatality, force_title=" ", randomize=timestamp()),
title=pad_title("Working ... refresh here"),
summary="Current state: %s; Last state: %s" % (
(Dict["current_refresh_state"] or "Idle") if "current_refresh_state" in Dict else "Idle",
(Dict["last_refresh_state"] or "None") if "last_refresh_state" in Dict else "None"
)
))
oc.add(DirectoryObject(
key=Callback(OnDeckMenu),
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")
))
oc.add(DirectoryObject(
key=Callback(RecentlyAddedMenu),
title="Recently Added items",
summary="Shows the recently added items per section.",
thumb=R("icon-recent.jpg")
))
oc.add(DirectoryObject(
key=Callback(RecentMissingSubtitlesMenu, randomize=timestamp()),
title="Items with missing subtitles",
summary="Shows the items honoring the configured 'Item age to be considered recent'-setting (%s)"
" and allowing you to individually (force-) refresh their metadata/subtitles. " %
Prefs["scheduler.item_is_recent_age"],
thumb=R("icon-missing.jpg")
))
oc.add(DirectoryObject(
key=Callback(SectionsMenu),
title="Browse all items",
summary="Go through your whole library and manage your ignore list. You can also "
"(force-) refresh the metadata/subtitles of individual items.",
thumb=R("icon-browse.jpg")
))
task_name = "SearchAllRecentlyAddedMissing"
task = scheduler.task(task_name)
if task.ready_for_display:
task_state = "Running: %s/%s (%s%%)" % (len(task.items_done), len(task.items_searching), task.percentage)
else:
task_state = "Last scheduler run: %s; Next scheduled run: %s; Last runtime: %s" % (
df(scheduler.last_run(task_name)) or "never",
df(scheduler.next_run(task_name)) or "never",
str(task.last_run_time).split(".")[0])
oc.add(DirectoryObject(
key=Callback(RefreshMissing, randomize=timestamp()),
title="Search for missing subtitles (in recently-added items, max-age: %s)" % Prefs[
"scheduler.item_is_recent_age"],
summary="Automatically run periodically by the scheduler, if configured. %s" % task_state,
thumb=R("icon-search.jpg")
))
oc.add(DirectoryObject(
key=Callback(IgnoreListMenu),
title="Display ignore list (%d)" % len(ignore_list),
summary="Show the current ignore list (mainly used for the automatic tasks)",
thumb=R("icon-ignore.jpg")
))
oc.add(DirectoryObject(
key=Callback(HistoryMenu),
title="History",
summary="Show the last %i downloaded subtitles" % int(Prefs["history_size"]),
thumb=R("icon-history.jpg")
))
oc.add(DirectoryObject(
key=Callback(fatality, force_title=" ", randomize=timestamp()),
title=pad_title("Refresh"),
summary="Current state: %s; Last state: %s" % (
(Dict["current_refresh_state"] or "Idle") if "current_refresh_state" in Dict else "Idle",
(Dict["last_refresh_state"] or "None") if "last_refresh_state" in Dict else "None"
),
thumb=R("icon-refresh.jpg")
))
# add re-lock after pin unlock
if config.pin:
oc.add(DirectoryObject(
key=Callback(ClearPin, randomize=timestamp()),
title=pad_title("Re-lock menu(s)"),
summary="Enabled the PIN again for menu(s)"
))
if not only_refresh:
oc.add(DirectoryObject(
key=Callback(AdvancedMenu),
title=pad_title("Advanced functions"),
summary="Use at your own risk",
thumb=R("icon-advanced.jpg")
))
return oc
@route(PREFIX + '/pin')
def PinMenu(pin="", randomize=None, success_go_to="channel"):
oc = ObjectContainer(title2="Enter PIN number %s" % (len(pin) + 1), no_cache=True, no_history=True,
skip_pin_lock=True)
if pin == config.pin:
Dict["pin_correct_time"] = datetime.datetime.now()
config.locked = False
if success_go_to == "channel":
return fatality(force_title="PIN correct", header="PIN correct", no_history=True)
elif success_go_to == "advanced":
return AdvancedMenu(randomize=timestamp())
for i in range(10):
oc.add(DirectoryObject(
key=Callback(PinMenu, randomize=timestamp(), pin=pin + str(i), success_go_to=success_go_to),
title=pad_title(str(i)),
))
oc.add(DirectoryObject(
key=Callback(PinMenu, randomize=timestamp(), success_go_to=success_go_to),
title=pad_title("Reset"),
))
return oc
@route(PREFIX + '/pin_lock')
def ClearPin(randomize=None):
Dict["pin_correct_time"] = None
config.locked = True
return fatality(force_title="Menu locked", header=" ", no_history=True)
@route(PREFIX + '/on_deck')
def OnDeckMenu(message=None):
"""
displays the items on deck
:param message:
:return:
"""
return mergedItemsMenu(title="Items On Deck", base_title="Items On Deck", itemGetter=get_on_deck_items)
@route(PREFIX + '/recently_added')
def RecentlyAddedMenu(message=None):
"""
displays the items recently added per section
:param message:
:return:
"""
return SectionsMenu(base_title="Recently added", section_items_key="recently_added", ignore_options=False)
@route(PREFIX + '/recent', force=bool)
@debounce
def RecentMissingSubtitlesMenu(force=False, randomize=None):
title = "Items with missing subtitles"
oc = SubFolderObjectContainer(title2=title, no_cache=True, no_history=True)
running = scheduler.is_task_running("MissingSubtitles")
task_data = scheduler.get_task_data("MissingSubtitles")
missing_items = task_data["missing_subtitles"] if task_data else None
if ((missing_items is None) or force) and not running:
scheduler.dispatch_task("MissingSubtitles")
running = True
if not running:
oc.add(DirectoryObject(
key=Callback(RecentMissingSubtitlesMenu, force=True, randomize=timestamp()),
title=u"Get items with missing subtitles",
thumb=default_thumb
))
else:
oc.add(DirectoryObject(
key=Callback(RecentMissingSubtitlesMenu, force=False, randomize=timestamp()),
title=u"Updating, refresh here ...",
thumb=default_thumb
))
if missing_items is not None:
for added_at, item_id, item_title, item, missing_languages in missing_items:
oc.add(DirectoryObject(
key=Callback(ItemDetailsMenu, title=title + " > " + item_title, item_title=item_title,
rating_key=item_id),
title=item_title,
summary="Missing: %s" % ", ".join(l.name for l in missing_languages),
thumb=get_item_thumb(item) or default_thumb
))
scheduler.clear_task_data("MissingSubtitles")
return oc
def mergedItemsMenu(title, itemGetter, itemGetterKwArgs=None, base_title=None, *args, **kwargs):
"""
displays an item list of dynamic kinds of items
:param title:
:param itemGetter:
:param itemGetterKwArgs:
:param base_title:
:param args:
:param kwargs:
:return:
"""
oc = SubFolderObjectContainer(title2=title, no_cache=True, no_history=True)
items = itemGetter(*args, **kwargs)
for kind, title, item_id, deeper, item in items:
oc.add(DirectoryObject(
title=title,
key=Callback(ItemDetailsMenu, title=base_title + " > " + title, item_title=title, rating_key=item_id),
thumb=get_item_thumb(item) or default_thumb
))
return oc
def determine_section_display(kind, item, pass_kwargs=None):
"""
returns the menu function for a section based on the size of it (amount of items)
:param kind:
:param item:
:return:
"""
if pass_kwargs and pass_kwargs.get("section_items_key", "all") != "all":
return SectionMenu
if item.size > 80:
return SectionFirstLetterMenu
return SectionMenu
@route(PREFIX + '/ignore/set/{kind}/{rating_key}/{todo}/sure={sure}', kind=str, rating_key=str, todo=str, sure=bool)
def IgnoreMenu(kind, rating_key, title=None, sure=False, todo="not_set"):
"""
displays the ignore options for a menu
:param kind:
:param rating_key:
:param title:
:param sure:
:param todo:
:return:
"""
is_ignored = rating_key in ignore_list[kind]
if not sure:
oc = SubFolderObjectContainer(no_history=True, replace_parent=True, title1="%s %s %s %s the ignore list" % (
"Add" if not is_ignored else "Remove", ignore_list.verbose(kind), title,
"to" if not is_ignored else "from"), title2="Are you sure?")
oc.add(DirectoryObject(
key=Callback(IgnoreMenu, kind=kind, rating_key=rating_key, title=title, sure=True,
todo="add" if not is_ignored else "remove"),
title=pad_title("Are you sure?"),
))
return oc
rel = ignore_list[kind]
dont_change = False
if todo == "remove":
if not is_ignored:
dont_change = True
else:
rel.remove(rating_key)
Log.Info("Removed %s (%s) from the ignore list", title, rating_key)
ignore_list.remove_title(kind, rating_key)
ignore_list.save()
state = "removed from"
elif todo == "add":
if is_ignored:
dont_change = True
else:
rel.append(rating_key)
Log.Info("Added %s (%s) to the ignore list", title, rating_key)
ignore_list.add_title(kind, rating_key, title)
ignore_list.save()
state = "added to"
else:
dont_change = True
if dont_change:
return fatality(force_title=" ", header="Didn't change the ignore list", no_history=True)
return fatality(force_title=" ", header="%s %s the ignore list" % (title, state), no_history=True)
@route(PREFIX + '/sections')
def SectionsMenu(base_title="Sections", section_items_key="all", ignore_options=True):
"""
displays the menu for all sections
:return:
"""
items = get_all_items("sections")
return dig_tree(SubFolderObjectContainer(title2="Sections", no_cache=True, no_history=True), items, None,
menu_determination_callback=determine_section_display, pass_kwargs={"base_title": base_title,
"section_items_key": section_items_key,
"ignore_options": ignore_options},
fill_args={"title": "section_title"})
@route(PREFIX + '/section', ignore_options=bool)
def SectionMenu(rating_key, title=None, base_title=None, section_title=None, ignore_options=True,
section_items_key="all"):
"""
displays the contents of a section
:param section_items_key:
:param rating_key:
:param title:
:param base_title:
:param section_title:
:param ignore_options:
:return:
"""
items = get_all_items(key=section_items_key, value=rating_key, base="library/sections")
kind, deeper = get_items_info(items)
title = unicode(title)
section_title = title
title = base_title + " > " + title
oc = SubFolderObjectContainer(title2=title, no_cache=True, no_history=True)
if ignore_options:
add_ignore_options(oc, "sections", title=section_title, rating_key=rating_key, callback_menu=IgnoreMenu)
return dig_tree(oc, items, MetadataMenu,
pass_kwargs={"base_title": title, "display_items": deeper, "previous_item_type": "section",
"previous_rating_key": rating_key})
@route(PREFIX + '/section/firstLetter', deeper=bool)
def SectionFirstLetterMenu(rating_key, title=None, base_title=None, section_title=None, ignore_options=True,
section_items_key="all"):
"""
displays the contents of a section indexed by its first char (A-Z, 0-9...)
:param ignore_options: ignored
:param section_items_key: ignored
:param rating_key:
:param title:
:param base_title:
:param section_title:
:return:
"""
items = get_all_items(key="first_character", value=rating_key, base="library/sections")
kind, deeper = get_items_info(items)
title = unicode(title)
oc = SubFolderObjectContainer(title2=section_title, no_cache=True, no_history=True)
title = base_title + " > " + title
add_ignore_options(oc, "sections", title=section_title, rating_key=rating_key, callback_menu=IgnoreMenu)
oc.add(DirectoryObject(
key=Callback(SectionMenu, title="All", base_title=title, rating_key=rating_key, ignore_options=False),
title="All"
)
)
return dig_tree(oc, items, FirstLetterMetadataMenu, force_rating_key=rating_key, fill_args={"key": "key"},
pass_kwargs={"base_title": title, "display_items": deeper, "previous_rating_key": rating_key})
@route(PREFIX + '/section/firstLetter/key', deeper=bool)
def FirstLetterMetadataMenu(rating_key, key, title=None, base_title=None, display_items=False, previous_item_type=None,
previous_rating_key=None):
"""
displays the contents of a section filtered by the first letter
:param rating_key: actually is the section's key
:param key: the firstLetter wanted
:param title: the first letter, or #
:param deeper:
:return:
"""
title = base_title + " > " + unicode(title)
oc = SubFolderObjectContainer(title2=title, no_cache=True, no_history=True)
items = get_all_items(key="first_character", value=[rating_key, key], base="library/sections", flat=False)
kind, deeper = get_items_info(items)
dig_tree(oc, items, MetadataMenu,
pass_kwargs={"base_title": title, "display_items": deeper, "previous_item_type": kind,
"previous_rating_key": rating_key})
return oc
@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):
"""
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:
:param title:
:param base_title:
:param display_items:
:param previous_item_type:
:param previous_rating_key:
:return:
"""
title = unicode(title)
item_title = title
title = base_title + " > " + title
oc = SubFolderObjectContainer(title2=title, no_cache=True, no_history=True)
current_kind = get_item_kind_from_rating_key(rating_key)
if display_items:
items = get_all_items(key="children", value=rating_key, base="library/metadata")
kind, deeper = get_items_info(items)
dig_tree(oc, items, MetadataMenu,
pass_kwargs={"base_title": title, "display_items": deeper, "previous_item_type": kind,
"previous_rating_key": rating_key})
# we don't know exactly where we are here, only add ignore option to series
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,
previous_rating_key=previous_rating_key, timeout=timeout * 1000, randomize=timestamp()),
title=u"Refresh: %s" % item_title,
summary="Refreshes the %s, possibly searching for missing and picking up new subtitles on disk" % current_kind
))
oc.add(DirectoryObject(
key=Callback(RefreshItem, rating_key=rating_key, item_title=title, force=True,
refresh_kind=current_kind, previous_rating_key=previous_rating_key, timeout=timeout * 1000,
randomize=timestamp()),
title=u"Auto-Find subtitles: %s" % item_title,
summary="Issues a forced refresh, ignoring known subtitles and searching for new ones"
))
else:
return ItemDetailsMenu(rating_key=rating_key, title=title, item_title=item_title)
return oc
@route(PREFIX + '/ignore_list')
def IgnoreListMenu():
oc = SubFolderObjectContainer(title2="Ignore list", replace_parent=True)
for key in ignore_list.key_order:
values = ignore_list[key]
for value in values:
add_ignore_options(oc, key, title=ignore_list.get_title(key, value), rating_key=value,
callback_menu=IgnoreMenu)
return oc
@route(PREFIX + '/history')
def HistoryMenu():
from support.history import get_history
history = get_history()
oc = SubFolderObjectContainer(title2="History", replace_parent=True)
for item in history.history_items:
oc.add(DirectoryObject(
key=Callback(ItemDetailsMenu, title=item.title, item_title=item.item_title,
rating_key=item.rating_key),
title=u"%s (%s)" % (item.item_title, item.mode_verbose),
summary=u"%s in %s (%s, score: %s), %s" % (item.lang_name, item.section_title,
item.provider_name, item.score, df(item.time))
))
return oc
@route(PREFIX + '/item/{rating_key}/actions')
@debounce
def ItemDetailsMenu(rating_key, title=None, base_title=None, item_title=None, randomize=None):
"""
displays the item details menu of an item that doesn't contain any deeper tree, such as a movie or an episode
:param rating_key:
:param title:
:param base_title:
:param item_title:
:param randomize:
:return:
"""
title = unicode(base_title) + " > " + unicode(title) if base_title else unicode(title)
item = get_item(rating_key)
current_kind = get_item_kind_from_rating_key(rating_key)
timeout = 30
oc = SubFolderObjectContainer(title2=title, replace_parent=True)
oc.add(DirectoryObject(
key=Callback(RefreshItem, rating_key=rating_key, item_title=item_title, randomize=timestamp(),
timeout=timeout * 1000),
title=u"Refresh: %s" % item_title,
summary="Refreshes the %s, possibly searching for missing and picking up new subtitles on disk" % current_kind,
thumb=item.thumb or default_thumb
))
oc.add(DirectoryObject(
key=Callback(RefreshItem, rating_key=rating_key, item_title=item_title, force=True, randomize=timestamp(),
timeout=timeout * 1000),
title=u"Auto-search: %s" % item_title,
summary="Issues a forced refresh, ignoring known subtitles and searching for new ones",
thumb=item.thumb or default_thumb
))
# get stored subtitle info for item id
subtitle_storage = get_subtitle_storage()
stored_subs = subtitle_storage.load_or_new(item)
# get the plex item
plex_item = list(Plex["library"].metadata(rating_key))[0]
# get current media info for that item
media = plex_item.media
# look for subtitles for all available media parts and all of their languages
for part in media.parts:
filename = os.path.basename(part.file)
part_id = str(part.id)
# iterate through all configured languages
for lang in config.lang_list:
lang_a2 = lang.alpha2
# ietf lang?
if cast_bool(Prefs["subtitles.language.ietf"]) and "-" in lang_a2:
lang_a2 = lang_a2.split("-")[0]
# get corresponding stored subtitle data for that media part (physical media item), for language
current_sub = stored_subs.get_any(part_id, lang_a2)
current_sub_id = None
current_sub_provider_name = None
summary = u"No current subtitle in storage"
current_score = None
if current_sub:
current_sub_id = current_sub.id
current_sub_provider_name = current_sub.provider_name
current_score = current_sub.score
summary = u"Current subtitle: %s (added: %s, %s), Language: %s, Score: %i, Storage: %s" % \
(current_sub.provider_name, df(current_sub.date_added), current_sub.mode_verbose, lang,
current_sub.score, current_sub.storage_type)
oc.add(DirectoryObject(
key=Callback(ListAvailableSubsForItemMenu, rating_key=rating_key, part_id=part_id, title=title,
item_title=item_title, language=lang, current_id=current_sub_id,
item_type=plex_item.type, filename=filename, current_data=summary,
randomize=timestamp(), current_provider=current_sub_provider_name,
current_score=current_score),
title=u"List %s subtitles" % lang.name,
summary=summary
))
add_ignore_options(oc, "videos", title=item_title, rating_key=rating_key, callback_menu=IgnoreMenu)
return oc
def get_item_task_data(task_name, rating_key, language):
task_data = scheduler.get_task_data(task_name)
search_results = task_data.get(rating_key, {}) if task_data else {}
return search_results.get(language)
@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,
item_type="episode", language=None, force=False, current_id=None, current_data=None,
current_provider=None, current_score=None, randomize=None):
assert rating_key, part_id
running = scheduler.is_task_running("AvailableSubsForItem")
search_results = get_item_task_data("AvailableSubsForItem", rating_key, language)
if (search_results is None or force) and not running:
scheduler.dispatch_task("AvailableSubsForItem", rating_key=rating_key, item_type=item_type, part_id=part_id,
language=language)
running = True
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,
summary=current_data,
thumb=default_thumb
))
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)
if not scanned_parts:
Log.Error("Couldn't list available subtitles for %s", rating_key)
return oc
video, plex_part = scanned_parts.items()[0]
video_display_data = [video.format] if video.format else []
if video.release_group:
video_display_data.append(u"by %s" % video.release_group)
video_display_data = " ".join(video_display_data)
current_display = (u"Current: %s (%s) " % (current_provider, current_score) if current_provider else "")
if not running:
oc.add(DirectoryObject(
key=Callback(ListAvailableSubsForItemMenu, rating_key=rating_key, item_title=item_title, language=language,
filename=filename, part_id=part_id, title=title, current_id=current_id, force=True,
current_provider=current_provider, current_score=current_score,
current_data=current_data, item_type=item_type, randomize=timestamp()),
title=u"Search for %s subs (%s)" % (get_language(language).name, video_display_data),
summary=u"%sFilename: %s" % (current_display, filename),
thumb=default_thumb
))
else:
oc.add(DirectoryObject(
key=Callback(ListAvailableSubsForItemMenu, rating_key=rating_key, item_title=item_title,
language=language, filename=filename, current_data=current_data,
part_id=part_id, title=title, current_id=current_id, item_type=item_type,
current_provider=current_provider, current_score=current_score,
randomize=timestamp()),
title=u"Searching for %s subs (%s), refresh here ..." % (get_language(language).name, video_display_data),
summary=u"%sFilename: %s" % (current_display, filename),
thumb=default_thumb
))
if not search_results:
return oc
for subtitle in search_results:
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),
summary=u"Release: %s, Matches: %s" % (subtitle.release_info, ", ".join(subtitle.matches)),
thumb=default_thumb
))
return oc
@route(PREFIX + '/download_subtitle/{rating_key}')
@debounce
def TriggerDownloadSubtitle(rating_key=None, subtitle_id=None, item_title=None, language=None, randomize=None):
set_refresh_menu_state("Downloading subtitle for %s" % item_title or rating_key)
search_results = get_item_task_data("AvailableSubsForItem", rating_key, language)
download_subtitle = None
for subtitle in search_results:
if str(subtitle.id) == subtitle_id:
download_subtitle = subtitle
break
if not download_subtitle:
Log.Error(u"Something went horribly wrong")
else:
scheduler.dispatch_task("DownloadSubtitleForItem", rating_key=rating_key, subtitle=download_subtitle)
return fatality(randomize=timestamp(), header=" ", replace_parent=True)
@route(PREFIX + '/item/{rating_key}')
@debounce
def RefreshItem(rating_key=None, came_from="/recent", item_title=None, force=False, refresh_kind=None,
previous_rating_key=None, timeout=8000, randomize=None, trigger=True):
assert rating_key
header = " "
if trigger:
set_refresh_menu_state(u"Triggering %sRefresh for %s" % ("Force-" if force else "", item_title))
Thread.Create(refresh_item, rating_key=rating_key, force=force, refresh_kind=refresh_kind,
parent_rating_key=previous_rating_key, timeout=int(timeout))
header = u"%s of item %s triggered" % ("Refresh" if not force else "Forced-refresh", rating_key)
return fatality(randomize=timestamp(), header=header, replace_parent=True)
@route(PREFIX + '/missing/refresh')
@debounce
def RefreshMissing(randomize=None):
scheduler.dispatch_task("SearchAllRecentlyAddedMissing")
header = "Refresh of recently added items with missing subtitles triggered"
return fatality(header=header, replace_parent=True)
@route(PREFIX + '/advanced')
def AdvancedMenu(randomize=None, header=None, message=None):
oc = SubFolderObjectContainer(header=header or "Internal stuff, pay attention!", message=message, no_cache=True,
no_history=True,
replace_parent=False, title2="Advanced")
if config.lock_advanced_menu and not config.pin_correct:
oc.add(DirectoryObject(
key=Callback(PinMenu, randomize=timestamp(), success_go_to="advanced"),
title=pad_title("Enter PIN"),
summary="The owner has restricted the access to this menu. Please enter the correct pin",
))
return oc
oc.add(DirectoryObject(
key=Callback(TriggerRestart, randomize=timestamp()),
title=pad_title("Restart the plugin"),
))
oc.add(DirectoryObject(
key=Callback(GetLogsLink),
title="Get my logs (copy the appearing link and open it in your browser, please)",
summary="Copy the appearing link and open it in your browser, please",
))
oc.add(DirectoryObject(
key=Callback(TriggerBetterSubtitles, randomize=timestamp()),
title=pad_title("Trigger find better subtitles"),
))
oc.add(DirectoryObject(
key=Callback(LogStorage, key="tasks", randomize=timestamp()),
title=pad_title("Log the plugin's scheduled tasks state storage"),
))
oc.add(DirectoryObject(
key=Callback(LogStorage, key="ignore", randomize=timestamp()),
title=pad_title("Log the plugin's internal ignorelist storage"),
))
oc.add(DirectoryObject(
key=Callback(ResetStorage, key="tasks", randomize=timestamp()),
title=pad_title("Reset the plugin's scheduled tasks state storage"),
))
oc.add(DirectoryObject(
key=Callback(ResetStorage, key="ignore", randomize=timestamp()),
title=pad_title("Reset the plugin's internal ignorelist storage"),
))
oc.add(DirectoryObject(
key=Callback(InvalidateCache, randomize=timestamp()),
title=pad_title("Invalidate Sub-Zero metadata caches (subliminal)"),
))
return oc
@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
restart = False
# reset pin
Dict["pin_correct_time"] = None
config.initialize()
if "channel_enabled" not in Dict:
update_dict = True
elif Dict["channel_enabled"] != config.enable_channel:
Log.Debug("Channel features %s, restarting plugin", "enabled" if config.enable_channel else "disabled")
update_dict = True
restart = True
if update_dict:
Dict["channel_enabled"] = config.enable_channel
Dict.Save()
if restart:
DispatchRestart()
scheduler.setup_tasks()
set_refresh_menu_state(None)
if Prefs["log_console"]:
Core.log.addHandler(logger.console_handler)
Log.Debug("Logging to console from now on")
else:
Core.log.removeHandler(logger.console_handler)
Log.Debug("Stop logging to console")
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
def DispatchRestart():
Thread.CreateTimer(1.0, Restart)
@route(PREFIX + '/advanced/restart/trigger')
@debounce
def TriggerRestart(randomize=None):
set_refresh_menu_state("Restarting the plugin")
DispatchRestart()
return fatality(header="Restart triggered, please wait about 5 seconds", force_title=" ", only_refresh=True,
replace_parent=True,
no_history=True, randomize=timestamp())
@route(PREFIX + '/advanced/restart/execute')
def Restart():
Plex[":/plugins"].restart(PLUGIN_IDENTIFIER)
@route(PREFIX + '/storage/reset', sure=bool)
def ResetStorage(key, randomize=None, sure=False):
if not sure:
oc = SubFolderObjectContainer(no_history=True, title1="Reset subtitle storage", title2="Are you sure?")
oc.add(DirectoryObject(
key=Callback(ResetStorage, key=key, sure=True, randomize=timestamp()),
title=pad_title("Are you really sure?"),
))
return oc
reset_storage(key)
if key == "tasks":
# reinitialize the scheduler
scheduler.init_storage()
scheduler.setup_tasks()
return AdvancedMenu(
randomize=timestamp(),
header='Success',
message='Information Storage (%s) reset' % key
)
@route(PREFIX + '/storage/log')
def LogStorage(key, randomize=None):
log_storage(key)
return AdvancedMenu(
randomize=timestamp(),
header='Success',
message='Information Storage (%s) logged' % key
)
@route(PREFIX + '/triggerbetter')
def TriggerBetterSubtitles(randomize=None):
scheduler.dispatch_task("FindBetterSubtitles")
return AdvancedMenu(
randomize=timestamp(),
header='Success',
message='FindBetterSubtitles triggered'
)
@route(PREFIX + '/get_logs_link')
def GetLogsLink():
ip = Core.networking.http_request("http://www.plexapp.com/ip.php", cacheTime=7200).content.strip()
logs_link = "http://%s:32400%s?X-Plex-Token=%s" % (ip, PREFIX + '/logs', config.universal_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)
return oc
@route(PREFIX + '/logs')
def DownloadLogs():
buff = StringIO.StringIO()
zip_archive = ZipFile(buff, mode='w', compression=ZIP_DEFLATED)
logs = sorted(glob.glob(config.plugin_log_path + '*')) + [config.server_log_path]
for path in logs:
data = StringIO.StringIO()
data.write(FileIO.read(path))
zip_archive.writestr(os.path.basename(path), data.getvalue())
zip_archive.close()
return ZipObject(buff.getvalue())
@route(PREFIX + '/invalidatecache')
def InvalidateCache(randomize=None):
from subliminal.cache import region
region.invalidate()
return AdvancedMenu(
randomize=timestamp(),
header='Success',
message='Cache invalidated'
)
-210
View File
@@ -1,210 +0,0 @@
# coding=utf-8
import types
import datetime
from support.items import get_kind, get_item_thumb
from support.helpers import get_video_display_title
from support.ignore import ignore_list
from support.lib import get_intent
from support.config import config
from subzero.constants import ICON_SUB
default_thumb = R(ICON_SUB)
def should_display_ignore(items, previous=None):
kind = get_kind(items)
return items and (
(kind in ("show", "season")) or
(kind == "episode" and previous != "season")
)
def add_ignore_options(oc, kind, callback_menu=None, title=None, rating_key=None, add_kind=True):
"""
:param oc: oc to add our options to
:param kind: movie, show, episode ... - gets translated to the ignore key (sections, series, items)
:param callback_menu: menu to inject
:param title:
:param rating_key:
:return:
"""
# try to translate kind to the ignore key
use_kind = kind
if kind not in ignore_list:
use_kind = ignore_list.translate_key(kind)
if not use_kind or use_kind not in ignore_list:
return
in_list = rating_key in ignore_list[use_kind]
oc.add(DirectoryObject(
key=Callback(callback_menu, kind=use_kind, rating_key=rating_key, title=title),
title=u"%s %s \"%s\" %s the ignore list" % (
"Remove" if in_list else "Add", ignore_list.verbose(kind) if add_kind else "", unicode(title), "from" if in_list else "to")
)
)
def dig_tree(oc, items, menu_callback, menu_determination_callback=None, force_rating_key=None, fill_args=None,
pass_kwargs=None, thumb=default_thumb):
for kind, title, key, dig_deeper, item in items:
thumb = get_item_thumb(item) or thumb
add_kwargs = {}
if fill_args:
add_kwargs = dict((name, getattr(item, k)) for k, name in fill_args.iteritems() if item and hasattr(item, k))
if pass_kwargs:
add_kwargs.update(pass_kwargs)
# force details view for show/season
summary = " " if kind in ("show", "season") else None
oc.add(DirectoryObject(
key=Callback(menu_callback or menu_determination_callback(kind, item, pass_kwargs=pass_kwargs), title=title,
rating_key=force_rating_key or key, **add_kwargs),
title=title, thumb=thumb, summary=summary
))
return oc
def set_refresh_menu_state(state_or_media, media_type="movies"):
"""
:param state_or_media: string, None, or Media argument from Agent.update()
:param media_type: movies or series
:return:
"""
if not state_or_media:
# store it in last state and remove the current
Dict["last_refresh_state"] = Dict["current_refresh_state"]
Dict["current_refresh_state"] = None
return
if isinstance(state_or_media, types.StringTypes):
Dict["current_refresh_state"] = state_or_media
return
media = state_or_media
media_id = media.id
title = None
if media_type == "series":
for season in media.seasons:
for episode in media.seasons[season].episodes:
ep = media.seasons[season].episodes[episode]
media_id = ep.id
title = get_video_display_title("show", ep.title, parent_title=media.title, season=int(season), episode=int(episode))
else:
title = get_video_display_title("movie", media.title)
intent = get_intent()
force_refresh = intent.get("force", media_id)
Dict["current_refresh_state"] = u"%sRefreshing %s" % ("Force-" if force_refresh else "", unicode(title))
def enable_channel_wrapper(func):
"""
returns the original wrapper :func: (route or handler) if applicable, else the plain to-be-wrapped function
:param func: original wrapper
:return: original wrapper or wrapped function
"""
def noop(*args, **kwargs):
def inner(*a, **k):
"""
:param a: args
:param k: kwargs
:return: originally to-be-wrapped function
"""
return a[0]
return inner
def wrap(*args, **kwargs):
enforce_route = kwargs.pop("enforce_route", None)
return (func if config.enable_channel or enforce_route else noop)(*args, **kwargs)
return wrap
def debounce(func):
"""
prevent func from being called twice with the same arguments
:param func:
:return:
"""
def get_lookup_key(args, kwargs):
func_name = list(args).pop(0).__name__
return tuple([func_name] + [(key, value) for key, value in kwargs.iteritems()])
def wrap(*args, **kwargs):
if "randomize" in kwargs:
if not "menu_history" in Dict:
Dict["menu_history"] = {}
key = get_lookup_key([func] + list(args), kwargs)
if key in Dict["menu_history"]:
Log.Debug("not triggering %s twice with %s, %s" % (func, args, kwargs))
return ObjectContainer()
else:
Dict["menu_history"][key] = datetime.datetime.now() + datetime.timedelta(days=1)
Dict.Save()
return func(*args, **kwargs)
return wrap
class SZObjectContainer(ObjectContainer):
def __init__(self, *args, **kwargs):
skip_pin_lock = kwargs.pop("skip_pin_lock", False)
super(SZObjectContainer, self).__init__(*args, **kwargs)
if (config.lock_menu or config.lock_advanced_menu) and not config.pin_correct and not skip_pin_lock:
config.locked = True
def add(self, *args, **kwargs):
# disable self.add if we're in lockdown
container = args[0]
current_menu_target = container.key.split("?")[0]
is_pin_menu = current_menu_target.endswith("/pin")
if config.locked and config.lock_menu and not is_pin_menu:
return
return super(SZObjectContainer, self).add(*args, **kwargs)
OriginalObjectContainer = ObjectContainer
ObjectContainer = SZObjectContainer
class SubFolderObjectContainer(ObjectContainer):
def __init__(self, *args, **kwargs):
super(SubFolderObjectContainer, self).__init__(*args, **kwargs)
from interface.menu import fatality
from support.helpers import pad_title, timestamp
self.add(DirectoryObject(
key=Callback(fatality, force_title=" ", randomize=timestamp()),
title=pad_title("<< Back to home"),
summary="Current state: %s; Last state: %s" % (
(Dict["current_refresh_state"] or "Idle") if "current_refresh_state" in Dict else "Idle",
(Dict["last_refresh_state"] or "None") if "last_refresh_state" in Dict else "None"
)
))
ObjectClass = getattr(getattr(Redirect, "_object_class"), "__bases__")[0]
class ZipObject(ObjectClass):
def __init__(self, data):
ObjectClass.__init__(self, "")
self.zipdata = data
self.SetHeader("Content-Type", "application/zip")
def Content(self):
self.SetHeader("Content-Disposition",
'attachment; filename="' + datetime.datetime.now().strftime("Logs_%y%m%d_%H-%M-%S.zip")
+ '"')
return self.zipdata
-45
View File
@@ -1,45 +0,0 @@
import logging
def register_logging_handler(dependencies, level="ERROR"):
plex_handler = PlexLoggerHandler()
for dependency in dependencies:
Log.Debug("Registering LoggerHandler for dependency: %s" % dependency)
log = logging.getLogger(dependency)
# remove previous plex logging handlers
# fixme: this is not the most elegant solution...
for handler in log.handlers:
if isinstance(handler, PlexLoggerHandler):
log.removeHandler(handler)
log.setLevel(level)
log.addHandler(plex_handler)
class PlexLoggerHandler(logging.StreamHandler):
def __init__(self, level=0):
super(PlexLoggerHandler, self).__init__(level)
def getFormattedString(self, record):
return record.name + ": " + record.getMessage()
def emit(self, record):
if record.levelno == logging.DEBUG:
Log.Debug(self.getFormattedString(record))
elif record.levelno == logging.INFO:
Log.Info(self.getFormattedString(record))
elif record.levelno == logging.WARNING:
Log.Warn(self.getFormattedString(record))
elif record.levelno == logging.ERROR:
Log.Error(self.getFormattedString(record))
elif record.levelno == logging.CRITICAL:
Log.Critical(self.getFormattedString(record))
elif record.levelno == logging.FATAL:
Log.Exception(self.getFormattedString(record))
else:
Log.Error("UNKNOWN LEVEL: %s", record.getMessage())
console_handler = logging.StreamHandler()
console_formatter = Framework.core.LogFormatter('%(asctime)-15s - %(name)-32s (%(thread)x) : %(levelname)s (%(module)s:%(lineno)d) - %(message)s')
console_handler.setFormatter(console_formatter)
-6
View File
@@ -1,6 +0,0 @@
License for parts taken out of plexinc-agents/LocalMedia.bundle
License
-------
If the software submitted to this repository accesses or calls any software provided by Plex (“Interfacing Software”), then as a condition for receiving services from Plex in response to such accesses or calls, you agree to grant and do hereby grant to Plex and its affiliates worldwide a worldwide, nonexclusive, and royalty-free right and license to use (including testing, hosting and linking to), copy, publicly perform, publicly display, reproduce in copies for distribution, and distribute the copies of any Interfacing Software made by you or with your assistance; provided, however, that you may notify Plex at legal@plex.tv if you do not wish for Plex to use, distribute, copy, publicly perform, publicly display, reproduce in copies for distribution, or distribute copies of an Interfacing Software that was created by you, and Plex will reasonable efforts to comply with such a request within a reasonable time.
-60
View File
@@ -1,60 +0,0 @@
import sys
# thanks, https://github.com/trakt/Plex-Trakt-Scrobbler/blob/master/Trakttv.bundle/Contents/Code/core/__init__.py
import config
sys.modules["support.config"] = config
import helpers
sys.modules["support.helpers"] = helpers
import lib
sys.modules["support.lib"] = lib
import plex_media
sys.modules["support.plex_media"] = plex_media
import localmedia
sys.modules["subzero.localmedia"] = localmedia
import subtitlehelpers
sys.modules["support.subtitlehelpers"] = subtitlehelpers
import items
sys.modules["support.items"] = items
import missing_subtitles
sys.modules["support.missing_subtitles"] = missing_subtitles
import background
sys.modules["support.background"] = background
import tasks
sys.modules["support.tasks"] = tasks
import storage
sys.modules["support.storage"] = storage
import ignore
sys.modules["support.ignore"] = ignore
import history
sys.modules["support.history"] = history
import data
sys.modules["support.data"] = data
import activities
sys.modules["support.activities"] = activities
-111
View File
@@ -1,111 +0,0 @@
# coding=utf-8
from wraptor.decorators import throttle
from config import config
from items import get_item, get_item_kind_from_item, refresh_item
from plex_activity import Activity
from plex_activity.sources.s_logging.main import Logging as Activity_Logging
class PlexActivityManager(object):
def start(self):
activity_sources_enabled = None
if config.universal_plex_token:
from plex import Plex
Plex.configuration.defaults.authentication(config.universal_plex_token)
activity_sources_enabled = ["websocket"]
Activity.on('websocket.playing', self.on_playing)
elif config.server_log_path:
Activity_Logging.add_hint(config.server_log_path, None)
activity_sources_enabled = ["logging"]
Activity.on('logging.playing', self.on_playing)
if activity_sources_enabled:
Activity.start(activity_sources_enabled)
@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
# don't trigger on the first hit ever
if "last_played_items" not in Dict:
Dict["last_played_items"] = []
Dict.Save()
return
rating_key = info["ratingKey"]
if rating_key not in Dict["last_played_items"]:
# new playing; store last 10 recently played items
Dict["last_played_items"].insert(0, rating_key)
Dict["last_played_items"] = Dict["last_played_items"][:10]
Dict.Save()
debug_msg = "Started playing %s. Refreshing it." % rating_key
key_to_refresh = None
if config.activity_mode in ["refresh", "next_episode", "hybrid"]:
# next episode or next episode and current movie
if config.activity_mode in ["next_episode", "hybrid"]:
plex_item = get_item(rating_key)
if not plex_item:
Log.Warn("Can't determine media type of %s, skipping" % rating_key)
return
if get_item_kind_from_item(plex_item) == "episode":
next_ep = self.get_next_episode(rating_key)
if next_ep:
key_to_refresh = next_ep.rating_key
debug_msg = "Started playing %s. Refreshing next episode (%s, S%02iE%02i)." % \
(rating_key, next_ep.rating_key, int(next_ep.season.index), int(next_ep.index))
else:
if config.activity_mode == "hybrid":
key_to_refresh = rating_key
elif config.activity_mode == "refresh":
key_to_refresh = rating_key
if key_to_refresh:
Log.Debug(debug_msg)
refresh_item(key_to_refresh)
def get_next_episode(self, rating_key):
plex_item = get_item(rating_key)
if not plex_item:
return
if get_item_kind_from_item(plex_item) == "episode":
# get season
season = get_item(plex_item.season.rating_key)
if not season:
return
# determine next episode
# next episode is in the same season
if plex_item.index < season.episode_count:
# get next ep
for ep in season.children():
if ep.index == plex_item.index + 1:
return ep
# it's not, try getting the first episode of the next season
else:
# get show
show = get_item(plex_item.show.rating_key)
# is there a next season?
if season.index < show.season_count:
for other_season in show.children():
if other_season.index == season.index + 1:
next_season = other_season
for ep in next_season.children():
if ep.index == 1:
return ep
activity = PlexActivityManager()
-42
View File
@@ -1,42 +0,0 @@
# coding=utf-8
def refresh_plex_token():
username = Prefs["plex_username"]
password = Prefs["plex_password"]
if not username or not password:
if "token" in Dict:
del Dict["token"]
Dict.Save()
return
if "uuid" not in Dict:
Dict["uuid"] = String.UUID()
Dict.Save()
current_uuid = Dict["uuid"]
headers = {
'X-Plex-Device-Name': 'Sub-Zero',
'X-Plex-Product': 'Sub-Zero',
'X-Plex-Version': '1.3.0',
'X-Plex-Client-Identifier': "%s" % current_uuid,
}
request = HTTP.Request("https://plex.tv/users/sign_in.json", headers=headers,
values={'user[login]': Prefs["plex_username"], 'user[password]': Prefs["plex_password"]}, immediate=True)
token = None
if request:
try:
data = JSON.ObjectFromString(request.content)
token = data["user"]["authentication_token"]
log_data = data.copy()
log_data["user"]["authentication_token"] = "xxxxxxxxxxxxxxxxxx"
Log.Debug("Data returned from plex.tv: %s", log_data)
except:
pass
if token:
Dict["token"] = token
Dict.Save()
return True
-193
View File
@@ -1,193 +0,0 @@
# coding=utf-8
import datetime
import logging
import traceback
def parse_frequency(s):
if s == "never" or s == None:
return None, None
kind, num, unit = s.split()
return int(num), unit
class DefaultScheduler(object):
thread = None
running = False
registry = None
def __init__(self):
self.thread = None
self.running = False
self.registry = []
self.tasks = {}
self.init_storage()
def init_storage(self):
if "tasks" not in Dict:
Dict["tasks"] = {"queue": []}
Dict.Save()
if "queue" not in Dict["tasks"]:
Dict["tasks"]["queue"] = []
def get_task_data(self, name):
if name not in Dict["tasks"]:
raise NotImplementedError("Task missing! %s" % name)
if "data" in Dict["tasks"][name]:
return Dict["tasks"][name]["data"]
def clear_task_data(self, name=None):
if name is None:
# full clean
Log.Debug("Clearing previous task data")
if Dict["tasks"]:
for task_name in Dict["tasks"].keys():
if task_name == "queue":
continue
Dict["tasks"][task_name]["data"] = {}
Dict["tasks"][task_name]["running"] = False
Dict.Save()
return
if name not in Dict["tasks"]:
raise NotImplementedError("Task missing! %s" % name)
Dict["tasks"][name]["data"] = {}
Dict.Save()
Log.Debug("Task data cleared: %s", name)
def register(self, task):
self.registry.append(task)
def setup_tasks(self):
# discover tasks;
self.tasks = {}
for cls in self.registry:
task = cls(self)
try:
task_frequency = Prefs["scheduler.tasks.%s.frequency" % task.name]
except KeyError:
task_frequency = None
self.tasks[task.name] = {"task": task, "frequency": parse_frequency(task_frequency)}
def run(self):
self.running = True
self.thread = Thread.Create(self.worker)
def stop(self):
self.running = False
def task(self, name):
if name not in self.tasks:
return None
return self.tasks[name]["task"]
def is_task_running(self, name):
task = self.task(name)
if task:
return task.running
def last_run(self, task):
if task not in self.tasks:
return None
return self.tasks[task]["task"].last_run
def next_run(self, task):
if task not in self.tasks or not self.tasks[task]["task"].periodic:
return None
frequency_num, frequency_key = self.tasks[task]["frequency"]
if not frequency_num:
return None
last = self.tasks[task]["task"].last_run
use_date = last
now = datetime.datetime.now()
if not use_date:
use_date = now
return max(use_date + datetime.timedelta(**{frequency_key: frequency_num}), now)
def run_task(self, name, *args, **kwargs):
task = self.tasks[name]["task"]
if task.running:
Log.Debug("Scheduler: Not running %s, as it's currently running.", name)
return False
Log.Debug("Scheduler: Running task %s", name)
try:
task.prepare(*args, **kwargs)
task.run()
except Exception, e:
Log.Error("Scheduler: Something went wrong when running %s: %s", name, traceback.format_exc())
finally:
task.post_run(Dict["tasks"][name]["data"])
Dict.Save()
def dispatch_task(self, *args, **kwargs):
if "queue" not in Dict["tasks"]:
Dict["tasks"]["queue"] = []
Dict["tasks"]["queue"].append((args, kwargs))
def signal(self, name, *args, **kwargs):
for task_name, info in self.tasks.iteritems():
task = info["task"]
if not task.periodic:
continue
if task.running:
Log.Debug("Scheduler: Sending signal %s to task %s (%s, %s)", name, task_name, args, kwargs)
try:
status = task.signal(name, *args, **kwargs)
except NotImplementedError:
Log.Debug("Scheduler: Signal ignored by %s", task_name)
continue
if status:
Log.Debug("Scheduler: Signal accepted by %s", task_name)
else:
Log.Debug("Scheduler: Signal not accepted by %s", task_name)
continue
Log.Debug("Scheduler: Not sending signal %s to task %s, because: not running", name, task_name)
def worker(self):
Thread.Sleep(10.0)
while 1:
if not self.running:
break
# single dispatch requested?
if Dict["tasks"]["queue"]:
# work queue off
queue = Dict["tasks"]["queue"][:]
Dict["tasks"]["queue"] = []
Dict.Save()
for args, kwargs in queue:
Log.Debug("Dispatching single task: %s, %s", args, kwargs)
Thread.Create(self.run_task, True, *args, **kwargs)
# scheduled tasks
for name, info in self.tasks.iteritems():
now = datetime.datetime.now()
task = info["task"]
if name not in Dict["tasks"] or not task.periodic:
continue
if task.running:
continue
frequency_num, frequency_key = info["frequency"]
if not frequency_num:
continue
if not task.last_run or (task.last_run + datetime.timedelta(**{frequency_key: frequency_num}) <= now):
self.run_task(name)
Thread.Sleep(5.0)
scheduler = DefaultScheduler()
-433
View File
@@ -1,433 +0,0 @@
# coding=utf-8
import os
import re
import inspect
import datetime
import subliminal
import subliminal_patch
from babelfish import Language
from subzero.lib.io import FileIO, get_viable_encoding
from subzero.constants import PLUGIN_NAME, PLUGIN_IDENTIFIER, MOVIE, SHOW
from lib import Plex
from helpers import check_write_permissions, cast_bool
SUBTITLE_EXTS = ['utf', 'utf8', 'utf-8', 'srt', 'smi', 'rt', 'ssa', 'aqt', 'jss', 'ass', 'idx', 'sub', 'txt', 'psb']
VIDEO_EXTS = ['3g2', '3gp', 'asf', 'asx', 'avc', 'avi', 'avs', 'bivx', 'bup', 'divx', 'dv', 'dvr-ms', 'evo', 'fli',
'flv',
'm2t', 'm2ts', 'm2v', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'mts', 'nsv', 'nuv', 'ogm', 'ogv', 'tp',
'pva', 'qt', 'rm', 'rmvb', 'sdp', 'svq3', 'strm', 'ts', 'ty', 'vdr', 'viv', 'vob', 'vp3', 'wmv', 'wpl',
'wtv', 'xsp', 'xvid',
'webm']
IGNORE_FN = ("subzero.ignore", ".subzero.ignore", ".nosz")
VERSION_RE = re.compile(ur'CFBundleVersion.+?<string>([0-9\.]+)</string>', re.DOTALL)
DEV_RE = re.compile(ur'PlexPluginDevMode.+?<string>([01]+)</string>', re.DOTALL)
def int_or_default(s, default):
try:
return int(s)
except ValueError:
return default
class Config(object):
plugin_info = ""
version = None
full_version = None
plugin_log_path = None
server_log_path = None
app_support_path = None
data_path = None
data_items_path = None
universal_plex_token = None
is_development = False
enable_channel = True
enable_agent = True
pin = None
lock_menu = False
lock_advanced_menu = False
locked = False
pin_valid_minutes = 10
lang_list = None
subtitle_destination_folder = None
providers = None
provider_settings = None
max_recent_items_per_library = 200
permissions_ok = False
missing_permissions = None
ignore_sz_files = False
ignore_paths = None
fs_encoding = None
notify_executable = None
sections = None
enabled_sections = None
enforce_encoding = False
chmod = None
forced_only = False
exotic_ext = False
treat_und_as_first = False
ext_match_strictness = False
use_activities = False
activity_mode = None
initialized = False
def initialize(self):
self.fs_encoding = get_viable_encoding()
self.plugin_info = self.get_plugin_info()
self.is_development = self.get_dev_mode()
self.version = self.get_version()
self.full_version = u"%s %s" % (PLUGIN_NAME, self.version)
self.set_log_paths()
self.app_support_path = Core.app_support_path
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.set_plugin_mode()
self.set_plugin_lock()
self.set_activity_modes()
self.lang_list = self.get_lang_list()
self.subtitle_destination_folder = self.get_subtitle_destination_folder()
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)
self.sections = list(Plex["library"].sections())
self.missing_permissions = []
self.ignore_sz_files = cast_bool(Prefs["subtitles.ignore_fs"])
self.ignore_paths = self.parse_ignore_paths()
self.enabled_sections = self.check_enabled_sections()
self.permissions_ok = self.check_permissions()
self.notify_executable = self.check_notify_executable()
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.initialized = True
def set_log_paths(self):
# find log handler
for handler in Core.log.handlers:
if getattr(getattr(handler, "__class__"), "__name__") in (
'FileHandler', 'RotatingFileHandler', 'TimedRotatingFileHandler'):
plugin_log_file = handler.baseFilename
if os.path.isfile(os.path.realpath(plugin_log_file)):
self.plugin_log_path = plugin_log_file
if plugin_log_file:
server_log_file = os.path.realpath(os.path.join(plugin_log_file, "../../Plex Media Server.log"))
if os.path.isfile(server_log_file):
self.server_log_path = server_log_file
def get_universal_plex_token(self):
# thanks to: https://forums.plex.tv/discussion/247136/read-current-x-plex-token-in-an-agent-ensure-that-a-http-request-gets-executed-exactly-once#latest
pref_path = os.path.join(self.app_support_path, "Preferences.xml")
if os.path.exists(pref_path):
try:
global_prefs = Core.storage.load(pref_path)
return XML.ElementFromString(global_prefs).xpath('//Preferences/@PlexOnlineToken')[0]
except:
Log.Warn("Couldn't determine Plex Token")
else:
Log("Did NOT find Preferences file - please check logfile and hierarchy. Aborting!")
def set_plugin_mode(self):
if Prefs["plugin_mode"] == "only agent":
self.enable_channel = False
elif Prefs["plugin_mode"] == "only channel":
self.enable_agent = False
def set_plugin_lock(self):
if Prefs["plugin_pin_mode"] in ("channel menu", "advanced menu"):
# check pin
pin = Prefs["plugin_pin"]
if not pin or not len(pin):
Log.Warn("PIN enabled but not set, disabling PIN!")
return
pin = pin.strip()
try:
int(pin)
except ValueError:
Log.Warn("PIN has to be an integer (0-9)")
self.pin = pin
self.lock_advanced_menu = Prefs["plugin_pin_mode"] == "advanced menu"
self.lock_menu = Prefs["plugin_pin_mode"] == "channel menu"
try:
self.pin_valid_minutes = int(Prefs["plugin_pin_valid_for"].strip())
except ValueError:
pass
@property
def pin_correct(self):
if isinstance(Dict["pin_correct_time"], datetime.datetime) \
and Dict["pin_correct_time"] + datetime.timedelta(
minutes=self.pin_valid_minutes) > datetime.datetime.now():
return True
def refresh_permissions_status(self):
self.permissions_ok = self.check_permissions()
def check_permissions(self):
if not Prefs["subtitles.save.filesystem"] or not Prefs["check_permissions"]:
return True
self.missing_permissions = []
use_ignore_fs = Prefs["subtitles.ignore_fs"]
all_permissions_ok = True
for section in self.sections:
if section.key not in self.enabled_sections:
continue
title = section.title
for location in section:
path_str = location.path
if isinstance(path_str, unicode):
path_str = path_str.encode(self.fs_encoding)
if use_ignore_fs:
# check whether we've got an ignore file inside the section path
if self.is_physically_ignored(path_str):
continue
if self.is_path_ignored(path_str):
# is the path in our ignored paths setting?
continue
# section not ignored, check for write permissions
if not check_write_permissions(path_str):
# not enough permissions
self.missing_permissions.append((title, location.path))
all_permissions_ok = False
return all_permissions_ok
def get_version(self):
result = VERSION_RE.search(self.plugin_info)
add = "" if not self.is_development else " DEV"
if result:
return result.group(1) + add
def get_dev_mode(self):
dev = DEV_RE.search(self.plugin_info)
if dev and dev.group(1) == "1":
return True
def get_plugin_info(self):
curDir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
info_file_path = os.path.abspath(os.path.join(curDir, "..", "..", "Info.plist"))
return FileIO.read(info_file_path)
def parse_ignore_paths(self):
paths = Prefs["subtitles.ignore_paths"]
if paths:
try:
return [path.strip() for path in paths.split(",")]
except:
Log.Error("Couldn't parse your ignore paths settings: %s" % paths)
return []
def is_physically_ignored(self, folder):
# check whether we've got an ignore file inside the path
for ifn in IGNORE_FN:
if os.path.isfile(os.path.join(folder, ifn)):
Log.Info(u'Ignoring "%s" because "%s" exists', folder, ifn)
return True
return False
def is_path_ignored(self, fn):
for path in self.ignore_paths:
if fn.startswith(path):
return True
return False
def check_notify_executable(self):
fn = Prefs["notify_executable"]
if not fn:
return
splitted_fn = fn.split()
exe_fn = splitted_fn[0]
arguments = [arg.strip() for arg in splitted_fn[1:]]
if os.path.isfile(exe_fn) and os.access(exe_fn, os.X_OK):
return exe_fn, arguments
Log.Error("Notify executable not existing or not executable: %s" % exe_fn)
def refresh_enabled_sections(self):
self.enabled_sections = self.check_enabled_sections()
def check_enabled_sections(self):
enabled_for_primary_agents = []
enabled_sections = {}
# find which agents we're enabled for
for agent in Plex.agents():
if not agent.primary:
continue
for t in list(agent.media_types):
if t.media_type in (MOVIE, SHOW):
related_agents = Plex.primary_agent(agent.identifier, t.media_type)
for a in related_agents:
if a.identifier == PLUGIN_IDENTIFIER and a.enabled:
enabled_for_primary_agents.append(agent.identifier)
# find the libraries that use them
for library in self.sections:
if library.agent in enabled_for_primary_agents:
enabled_sections[library.key] = library
Log.Debug(u"I'm enabled for: %s" % [lib.title for key, lib in enabled_sections.iteritems()])
return enabled_sections
# Prepare a list of languages we want subs for
def get_lang_list(self):
l = {Language.fromietf(Prefs["langPref1"])}
lang_custom = Prefs["langPrefCustom"].strip()
if Prefs['subtitles.only_one']:
return l
if Prefs["langPref2"] != "None":
l.update({Language.fromietf(Prefs["langPref2"])})
if Prefs["langPref3"] != "None":
l.update({Language.fromietf(Prefs["langPref3"])})
if len(lang_custom) and lang_custom != "None":
for lang in lang_custom.split(u","):
lang = lang.strip()
try:
real_lang = Language.fromietf(lang)
except:
try:
real_lang = Language.fromname(lang)
except:
continue
l.update({real_lang})
return l
def get_subtitle_destination_folder(self):
if not Prefs["subtitles.save.filesystem"]:
return
fld_custom = Prefs["subtitles.save.subFolder.Custom"].strip() if cast_bool(
Prefs["subtitles.save.subFolder.Custom"]) else None
return fld_custom or (
Prefs["subtitles.save.subFolder"] if Prefs["subtitles.save.subFolder"] != "current folder" else None)
def get_providers(self):
providers = {'opensubtitles': cast_bool(Prefs['provider.opensubtitles.enabled']),
# 'thesubdb': Prefs['provider.thesubdb.enabled'],
'podnapisi': cast_bool(Prefs['provider.podnapisi.enabled']),
'addic7ed': cast_bool(Prefs['provider.addic7ed.enabled']),
'tvsubtitles': cast_bool(Prefs['provider.tvsubtitles.enabled']),
'legendastv': cast_bool(Prefs['provider.legendastv.enabled']),
'napiprojekt': cast_bool(Prefs['provider.napiprojekt.enabled']),
'shooter': cast_bool(Prefs['provider.shooter.enabled']),
'subscenter': cast_bool(Prefs['provider.subscenter.enabled']),
}
# ditch non-forced-subtitles-reporting providers
if cast_bool(Prefs['subtitles.only_foreign']):
providers["addic7ed"] = False
providers["tvsubtitles"] = False
providers["legendastv"] = False
return filter(lambda prov: providers[prov], providers)
def get_provider_settings(self):
provider_settings = {'addic7ed': {'username': Prefs['provider.addic7ed.username'],
'password': Prefs['provider.addic7ed.password'],
'use_random_agents': cast_bool(Prefs['provider.addic7ed.use_random_agents']),
},
'opensubtitles': {'username': Prefs['provider.opensubtitles.username'],
'password': Prefs['provider.opensubtitles.password'],
'use_tag_search': cast_bool(Prefs['provider.opensubtitles.use_tags']),
'only_foreign': cast_bool(Prefs['subtitles.only_foreign'])
},
'podnapisi': {
'only_foreign': cast_bool(Prefs['subtitles.only_foreign'])
},
'legendastv': {'username': Prefs['provider.legendastv.username'],
'password': Prefs['provider.legendastv.password'],
},
'subscenter': {'username': Prefs['provider.subscenter.username'],
'password': Prefs['provider.subscenter.password'],
},
}
return provider_settings
@property
def provider_pool(self):
if cast_bool(Prefs['providers.multithreading']):
return subliminal_patch.core.SZAsyncProviderPool
return subliminal_patch.core.SZProviderPool
def check_chmod(self):
val = Prefs["subtitles.save.chmod"]
if not val or not len(val):
return
wrong_chmod = False
if len(val) != 4:
wrong_chmod = True
try:
return int(val, 8)
except ValueError:
wrong_chmod = True
if wrong_chmod:
Log.Warn("Chmod setting ignored, please use only 4-digit integers with leading 0 (e.g.: 775)")
def determine_ext_sub_strictness(self):
val = Prefs["subtitles.scan.filename_strictness"]
if val == "any":
return "any"
elif val.startswith("loose"):
return "loose"
return "strict"
def set_activity_modes(self):
val = Prefs["activity.on_playback"]
if val == "never":
self.use_activities = False
return
self.use_activities = True
if val == "current media item":
self.activity_mode = "refresh"
elif val == "hybrid: current item or next episode":
self.activity_mode = "hybrid"
else:
self.activity_mode = "next_episode"
def init_subliminal_patches(self):
# configure custom subtitle destination folders for scanning pre-existing subs
Log.Debug("Patching subliminal ...")
dest_folder = self.subtitle_destination_folder
subliminal_patch.core.CUSTOM_PATHS = [dest_folder] if dest_folder else []
subliminal_patch.core.INCLUDE_EXOTIC_SUBS = self.exotic_ext
subliminal_patch.core.DOWNLOAD_TRIES = int(Prefs['subtitles.try_downloads'])
subliminal.score.episode_scores["addic7ed_boost"] = int(Prefs['provider.addic7ed.boost_by1'])
config = Config()
config.initialize()
-84
View File
@@ -1,84 +0,0 @@
# coding=utf-8
def dispatch_migrate():
try:
migrate()
except:
Log.Error("Migration failed: %s" % traceback.format_exc())
def migrate():
"""
some Dict/Data migrations here, no need for a more in-depth migration path for now
:return:
"""
# migrate subtitle history from Dict to Data
if "history" in Dict and Dict["history"].get("history_items"):
Log.Debug("Running migration for history data")
from support.history import get_history
history = get_history()
for item in reversed(Dict["history"]["history_items"]):
history.add(item.item_title, item.rating_key, item.section_title, subtitle=item.subtitle, mode=item.mode,
time=item.time)
del Dict["history"]
Dict.Save()
# migrate subtitle storage from Dict to Data
if "subs" in Dict:
from support.storage import get_subtitle_storage
from subzero.subtitle_storage import StoredSubtitle
from support.plex_media import get_item
subtitle_storage = get_subtitle_storage()
for video_id, parts in Dict["subs"].iteritems():
try:
item = get_item(video_id)
except:
continue
if not item:
continue
stored_subs = subtitle_storage.load_or_new(item)
stored_subs.version = 1
Log.Debug(u"Migrating %s" % video_id)
stored_any = False
for part_id, lang_dict in parts.iteritems():
part_id = str(part_id)
Log.Debug(u"Migrating %s, %s" % (video_id, part_id))
for lang, subs in lang_dict.iteritems():
lang = str(lang)
if "current" in subs:
current_key = subs["current"]
provider_name, subtitle_id = current_key
sub = subs.get(current_key)
if sub and sub.get("title") and sub.get("mode"): # ditch legacy data without sufficient info
stored_subs.title = sub["title"]
new_sub = StoredSubtitle(sub["score"], sub["storage"], sub["hash"], provider_name,
subtitle_id, date_added=sub["date_added"], mode=sub["mode"])
if part_id not in stored_subs.parts:
stored_subs.parts[part_id] = {}
if lang not in stored_subs.parts[part_id]:
stored_subs.parts[part_id][lang] = {}
Log.Debug(u"Migrating %s, %s, %s" % (video_id, part_id, current_key))
stored_subs.parts[part_id][lang][current_key] = new_sub
stored_subs.parts[part_id][lang]["current"] = current_key
stored_any = True
if stored_any:
subtitle_storage.save(stored_subs)
del Dict["subs"]
Dict.Save()
-305
View File
@@ -1,305 +0,0 @@
# coding=utf-8
import os
import traceback
import types
import unicodedata
import datetime
import urllib
import time
import re
import platform
import subprocess
from bs4 import UnicodeDammit
import chardet
from babelfish import Language
from subzero.analytics import track_event
# Unicode control characters can appear in ID3v2 tags but are not legal in XML.
RE_UNICODE_CONTROL = u'([\u0000-\u0008\u000b-\u000c\u000e-\u001f\ufffe-\uffff])' + \
u'|' + \
u'([%s-%s][^%s-%s])|([^%s-%s][%s-%s])|([%s-%s]$)|(^[%s-%s])' % \
(
unichr(0xd800), unichr(0xdbff), unichr(0xdc00), unichr(0xdfff),
unichr(0xd800), unichr(0xdbff), unichr(0xdc00), unichr(0xdfff),
unichr(0xd800), unichr(0xdbff), unichr(0xdc00), unichr(0xdfff)
)
def cast_bool(value):
return str(value) in ("true", "True")
# A platform independent way to split paths which might come in with different separators.
def split_path(str):
if str.find('\\') != -1:
return str.split('\\')
else:
return str.split('/')
def unicodize(s):
filename = s
try:
filename = unicodedata.normalize('NFC', unicode(s.decode('utf-8')))
except:
Log('Failed to unicodize: ' + repr(filename))
try:
filename = re.sub(RE_UNICODE_CONTROL, '', filename)
except:
Log('Couldn\'t strip control characters: ' + repr(filename))
return filename
def force_unicode(s):
if not isinstance(s, types.UnicodeType):
try:
s = s.decode("utf-8")
except UnicodeDecodeError:
t = chardet.detect(s)
try:
s = s.decode(t["encoding"])
except UnicodeDecodeError:
s = UnicodeDammit(s).unicode_markup
return s
def clean_filename(filename):
# this will remove any whitespace and punctuation chars and replace them with spaces, strip and return as lowercase
return string.translate(filename.encode('utf-8'), string.maketrans(string.punctuation + string.whitespace,
' ' * len(
string.punctuation + string.whitespace))).strip().lower()
def is_recent(t):
now = datetime.datetime.now()
when = datetime.datetime.fromtimestamp(t)
value, key = Prefs["scheduler.item_is_recent_age"].split()
if now - datetime.timedelta(**{key: int(value)}) < when:
return True
return False
# thanks, Plex-Trakt-Scrobbler
def str_pad(s, length, align='left', pad_char=' ', trim=False):
if not s:
return s
if not isinstance(s, (str, unicode)):
s = str(s)
if len(s) == length:
return s
elif len(s) > length and not trim:
return s
if align == 'left':
if len(s) > length:
return s[:length]
else:
return s + (pad_char * (length - len(s)))
elif align == 'right':
if len(s) > length:
return s[len(s) - length:]
else:
return (pad_char * (length - len(s))) + s
else:
raise ValueError("Unknown align type, expected either 'left' or 'right'")
def pad_title(value):
"""Pad a title to 30 characters to force the 'details' view."""
return str_pad(value, 49, pad_char=' ')
def get_plex_item_display_title(item, kind, parent=None, parent_title=None, section_title=None,
add_section_title=False):
"""
:param item: plex item
:param kind: show or movie
:param parent: season or None
:param parent_title: parentTitle or None
:return:
"""
return get_video_display_title(kind, item.title,
section_title=(
section_title or (parent.section.title if parent and getattr(parent, "section")
else None)),
parent_title=(parent_title or (parent.show.title if parent else None)),
season=parent.index if parent else None,
episode=item.index if kind == "show" else None,
add_section_title=add_section_title)
def get_video_display_title(kind, title, section_title=None, parent_title=None, season=None, episode=None,
add_section_title=False):
section_add = ""
if add_section_title:
section_add = ("%s: " % section_title) if section_title else ""
if kind == "show" and parent_title:
if season and episode:
return '%s%s S%02dE%02d%s' % (section_add, parent_title, season or 0, episode or 0,
(", %s" % title if title else ""))
return '%s%s%s' % (section_add, parent_title, (", %s" % title if title else ""))
return "%s%s" % (section_add, title)
def get_title_for_video_metadata(metadata, add_section_title=True, add_episode_title=False):
"""
:param metadata:
:param add_section_title:
:param add_episode_title: add the episode's title if its an episode else always add title
:return:
"""
# compute item title
add_title = (add_episode_title and metadata["series_id"]) or not metadata["series_id"]
return get_video_display_title(
"show" if metadata["series_id"] else "movie",
metadata["title"] if add_title else "",
parent_title=metadata.get("series", None),
season=metadata.get("season", None),
episode=metadata.get("episode", None),
section_title=metadata.get("section", None),
add_section_title=add_section_title
)
def get_identifier():
identifier = None
try:
identifier = Platform.MachineIdentifier
except:
pass
if not identifier:
identifier = String.UUID()
return Hash.SHA1(identifier + "SUBZEROOOOOOOOOO")
def encode_message(base, s):
return "%s?message=%s" % (base, urllib.quote_plus(s))
def decode_message(s):
return urllib.unquote_plus(s)
def timestamp():
return int(time.time())
def df(d):
return d.strftime("%Y-%m-%d %H:%M:%S") if d else "legacy data"
def query_plex(url, args):
"""
simple http query to the plex API without parsing anything too complicated
:param url:
:param args:
:return:
"""
use_args = args.copy()
computed_args = "&".join(["%s=%s" % (key, String.Quote(value)) for key, value in use_args.iteritems()])
return HTTP.Request(url + ("?%s" % computed_args) if computed_args else "", immediate=True)
def check_write_permissions(path):
if platform.system() == "Windows":
# physical access check
check_path = os.path.join(os.path.realpath(path), ".sz_perm_chk")
try:
if os.path.exists(check_path):
os.rmdir(check_path)
os.mkdir(check_path)
os.rmdir(check_path)
return True
except OSError:
pass
else:
# os.access check
return os.access(path, os.W_OK | os.X_OK)
return False
def get_item_hints(data):
"""
:param data: video item dict of media_to_videos
:return:
"""
hints = {"title": data["title"], "type": "movie"}
if data["type"] == "episode":
hints.update(
{
"type": "episode",
"episode_title": data["title"],
"title": data["series"],
}
)
return hints
def notify_executable(exe_info, videos, subtitles, storage):
variables = (
"subtitle_language", "subtitle_path", "subtitle_filename", "provider", "score", "storage", "series_id",
"series", "title", "section", "filename", "path", "folder", "season_id", "type", "id", "season"
)
exe, arguments = exe_info
for video, video_subtitles in subtitles.items():
for subtitle in video_subtitles:
lang = Locale.Language.Match(subtitle.language.alpha2)
data = video.plexapi_metadata.copy()
data.update({
"subtitle_language": lang,
"provider": subtitle.provider_name,
"score": subtitle.score,
"storage": storage,
"subtitle_path": subtitle.storage_path,
"subtitle_filename": os.path.basename(subtitle.storage_path)
})
# fill missing data with None
prepared_data = dict((v, data.get(v)) for v in variables)
prepared_arguments = [arg % prepared_data for arg in arguments]
Log.Debug(u"Calling %s with arguments: %s" % (exe, prepared_arguments))
try:
output = subprocess.check_output(subprocess.list2cmdline([exe] + prepared_arguments),
stderr=subprocess.STDOUT, shell=True)
except subprocess.CalledProcessError:
Log.Error(u"Calling %s failed: %s" % (exe, traceback.format_exc()))
else:
Log.Debug(u"Process output: %s" % output)
def track_usage(category=None, action=None, label=None, value=None):
if not cast_bool(Prefs["track_usage"]):
return
Thread.Create(dispatch_track_usage, category, action, label, value,
identifier=Dict["anon_id"], first_use=Dict["first_use"],
add=Network.PublicAddress)
def dispatch_track_usage(*args, **kwargs):
identifier = kwargs.pop("identifier")
first_use = kwargs.pop("first_use")
add = kwargs.pop("add")
try:
track_event(identifier=identifier, first_use=first_use, add=add, *[str(a) for a in args])
except:
Log.Debug("Something went wrong when reporting anonymous user statistics: %s", traceback.format_exc())
def get_language(lang_short):
return Language.fromietf(lang_short)
-4
View File
@@ -1,4 +0,0 @@
# coding=utf-8
from subzero.history_storage import SubtitleHistory
get_history = lambda: SubtitleHistory(Data, int(Prefs["history_size"]))
-62
View File
@@ -1,62 +0,0 @@
# coding=utf-8
from subzero.lib.dict import DictProxy
class IgnoreDict(DictProxy):
store = "ignore"
# single item keys returned by helpers.items.getItems mapped to their parents
translate_keys = {
"section": "sections",
"show": "series",
"movie": "videos",
"episode": "videos"
}
# getItems types mapped to their verbose names
keys_verbose = {
"sections": "Section",
"series": "Series",
"videos": "Item",
}
key_order = ("sections", "series", "videos")
def __len__(self):
try:
return sum(len(self.Dict[self.store][key]) for key in self.key_order)
except KeyError:
# old version
self.Dict[self.store] = self.setup_defaults()
return 0
def translate_key(self, name):
return self.translate_keys.get(name)
def verbose(self, name):
return self.keys_verbose.get(name)
def get_title_key(self, kind, key):
return "%s_%s" % (kind, key)
def add_title(self, kind, key, title):
self["titles"][self.get_title_key(kind, key)] = title
def remove_title(self, kind, key):
title_key = self.get_title_key(kind, key)
if title_key in self.titles:
del self.titles[title_key]
def get_title(self, kind, key):
title_key = self.get_title_key(kind, key)
if title_key in self.titles:
return self.titles[title_key]
def save(self):
Dict.Save()
def setup_defaults(self):
return {"sections": [], "series": [], "videos": [], "titles": {}}
ignore_list = IgnoreDict(Dict)
-285
View File
@@ -1,285 +0,0 @@
# coding=utf-8
import logging
import re
import types
import os
from ignore import ignore_list
from helpers import is_recent, get_plex_item_display_title, query_plex
from lib import Plex, get_intent
from config import config, IGNORE_FN
logger = logging.getLogger(__name__)
MI_KIND, MI_TITLE, MI_KEY, MI_DEEPER, MI_ITEM = 0, 1, 2, 3, 4
container_size_re = re.compile(ur'totalSize="(\d+)"')
def get_item(key):
item_id = int(key)
item_container = Plex["library"].metadata(item_id)
try:
return list(item_container)[0]
except IndexError:
pass
def get_item_kind(item):
return type(item).__name__
PLEX_API_TYPE_MAP = {
"Show": "series",
"Season": "season",
"Episode": "episode",
"Movie": "movie",
}
def get_item_kind_from_rating_key(key):
item = get_item(key)
return PLEX_API_TYPE_MAP[get_item_kind(item)]
def get_item_kind_from_item(item):
return PLEX_API_TYPE_MAP[get_item_kind(item)]
def get_item_thumb(item):
kind = get_item_kind(item)
if kind == "Episode":
return item.show.thumb
elif kind == "Section":
return item.art
return item.thumb
def get_items_info(items):
return items[0][MI_KIND], items[0][MI_DEEPER]
def get_kind(items):
return items[0][MI_KIND]
def get_section_size(key):
"""
quick query to determine the section size
:param key:
:return:
"""
size = None
url = "http://127.0.0.1:32400/library/sections/%s/all" % int(key)
use_args = {
"X-Plex-Container-Size": "0",
"X-Plex-Container-Start": "0"
}
response = query_plex(url, use_args)
matches = container_size_re.findall(response.content)
if matches:
size = int(matches[0])
return size
def get_items(key="recently_added", base="library", value=None, flat=False, add_section_title=False):
"""
try to handle all return types plex throws at us and return a generalized item tuple
"""
items = []
apply_value = None
if value:
if isinstance(value, types.ListType):
apply_value = value
else:
apply_value = [value]
result = getattr(Plex[base], key)(*(apply_value or []))
for item in result:
cls = getattr(getattr(item, "__class__"), "__name__")
if hasattr(item, "scanner"):
kind = "section"
elif cls == "Directory":
kind = "directory"
else:
kind = item.type
# only return items for our enabled sections
section_key = None
if kind == "section":
section_key = item.key
else:
if hasattr(item, "section_key"):
section_key = getattr(item, "section_key")
if section_key and section_key not in config.enabled_sections:
continue
if kind == "season":
# fixme: i think this case is unused now
if flat:
# return episodes
for child in item.children():
items.append(("episode", get_plex_item_display_title(child, "show", parent=item, add_section_title=add_section_title), int(item.rating_key),
False, child))
else:
# return seasons
items.append(("season", item.title, int(item.rating_key), True, item))
elif kind == "directory":
items.append(("directory", item.title, item.key, True, item))
elif kind == "section":
if item.type in ['movie', 'show']:
item.size = get_section_size(item.key)
items.append(("section", item.title, int(item.key), True, item))
elif kind == "episode":
items.append(
(kind, get_plex_item_display_title(item, "show", parent=item.season, parent_title=item.show.title, section_title=item.section.title,
add_section_title=add_section_title), int(item.rating_key), False, item))
elif kind in ("movie", "artist", "photo"):
items.append((kind, get_plex_item_display_title(item, kind, section_title=item.section.title, add_section_title=add_section_title),
int(item.rating_key), False, item))
elif kind == "show":
items.append((
kind, get_plex_item_display_title(item, kind, section_title=item.section.title, add_section_title=add_section_title), int(item.rating_key), True,
item))
return items
def get_recent_items():
"""
actually get the recent items, not limited like /library/recentlyAdded
:return:
"""
args = {
"sort": "addedAt:desc",
"X-Plex-Container-Start": "0",
"X-Plex-Container-Size": "%s" % config.max_recent_items_per_library
}
episode_re = re.compile(ur'ratingKey="(?P<key>\d+)"'
ur'.+?grandparentRatingKey="(?P<parent_key>\d+)"'
ur'.+?title="(?P<title>.*?)"'
ur'.+?grandparentTitle="(?P<parent_title>.*?)"'
ur'.+?index="(?P<episode>\d+?)"'
ur'.+?parentIndex="(?P<season>\d+?)".+?addedAt="(?P<added>\d+)"')
movie_re = re.compile(ur'ratingKey="(?P<key>\d+)".+?title="(?P<title>.*?)".+?addedAt="(?P<added>\d+)"')
available_keys = ("key", "title", "parent_key", "parent_title", "season", "episode", "added")
recent = []
for section in Plex["library"].sections():
if section.type not in ("movie", "show") \
or section.key not in config.enabled_sections \
or section.key in ignore_list.sections:
Log.Debug(u"Skipping section: %s" % section.title)
continue
use_args = args.copy()
if section.type == "show":
use_args["type"] = "4"
url = "http://127.0.0.1:32400/library/sections/%s/all" % int(section.key)
response = query_plex(url, use_args)
matcher = episode_re if section.type == "show" else movie_re
matches = [m.groupdict() for m in matcher.finditer(response.content)]
for match in matches:
data = dict((key, match[key] if key in match else None) for key in available_keys)
if section.type == "show" and data["parent_key"] in ignore_list.series:
Log.Debug(u"Skipping series: %s" % data["parent_title"])
continue
if data["key"] in ignore_list.videos:
Log.Debug(u"Skipping item: %s" % data["title"])
continue
if is_recent(int(data["added"])):
recent.append((int(data["added"]), section.type, section.title, data["key"]))
return recent
def get_on_deck_items():
return get_items(key="on_deck", add_section_title=True)
def get_recently_added_items():
return get_items(key="recently_added", add_section_title=True, flat=False)
def get_all_items(key, base="library", value=None, flat=False):
return get_items(key, base=base, value=value, flat=flat)
def is_ignored(rating_key, item=None):
"""
check whether an item, its show/season/section is in the soft or the hard ignore list
:param rating_key:
:param item:
:return:
"""
# item in soft ignore list
if rating_key in ignore_list["videos"]:
Log.Debug("Item %s is in the soft ignore list" % rating_key)
return True
item = item or get_item(rating_key)
kind = get_item_kind(item)
# show in soft ignore list
if kind == "Episode" and item.show.rating_key in ignore_list["series"]:
Log.Debug("Item %s's show is in the soft ignore list" % rating_key)
return True
# section in soft ignore list
if item.section.key in ignore_list["sections"]:
Log.Debug("Item %s's section is in the soft ignore list" % rating_key)
return True
# physical/path ignore
if config.ignore_sz_files or config.ignore_paths:
# normally check current item folder and the library
check_ignore_paths = [".", "../"]
if kind == "Episode":
# series/episode, we've got a season folder here, also
check_ignore_paths.append("../../")
for part in item.media.parts:
if config.ignore_paths and config.is_path_ignored(part.file):
Log.Debug("Item %s's path is manually ignored" % rating_key)
return True
if config.ignore_sz_files:
for sub_path in check_ignore_paths:
if config.is_physically_ignored(os.path.abspath(os.path.join(os.path.dirname(part.file), sub_path))):
Log.Debug("An ignore file exists in either the items or its parent folders")
return True
return False
def refresh_item(rating_key, force=False, timeout=8000, refresh_kind=None, parent_rating_key=None):
intent = get_intent()
# timeout actually is the time for which the intent will be valid
if force:
Log.Debug("Setting intent for force-refresh of %s to timeout: %s", rating_key, timeout)
intent.set("force", rating_key, timeout=timeout)
# force Dict.Save()
intent.store.save()
refresh = [rating_key]
if refresh_kind == "season":
# season refresh, needs explicit per-episode refresh
refresh = [item.rating_key for item in list(Plex["library/metadata"].children(int(rating_key)))]
for key in refresh:
Log.Info("%s item %s", "Refreshing" if not force else "Forced-refreshing", key)
Plex["library/metadata"].refresh(key)
-56
View File
@@ -1,56 +0,0 @@
# coding=utf-8
import plex
from subzero.intent import TempIntent
from subzero.lib.dict import DictProxy
from subzero.lib.httpfake import PlexPyNativeResponseProxy
from subzero.constants import DEFAULT_TIMEOUT
class PlexPyNativeRequestProxy(object):
"""
A really dumb object that tries to mimic requests.Request in an incomplete way, so that plex.Plex
uses native plex HTTPRequests instead of the better requests.Request class.
This allows us to operate freely on 127.0.0.1's PMS.
To be used in conjunction with subzero.lib.httpfake.PlexPyNativeResponseProxy
"""
url = None
data = None
headers = None
method = None
def prepare(self):
return self
def send(self):
# fixme: add self.data to HTTP.Request
data = None
status_code = 200
try:
data = HTTP.Request(self.url, headers=self.headers, immediate=True, method=self.method,
timeout=DEFAULT_TIMEOUT)
except Ex.HTTPError as e:
status_code = e.code
return PlexPyNativeResponseProxy(data, status_code, self)
plex.request.Request = PlexPyNativeRequestProxy
Plex = plex.Plex
class IntentDictStorage(DictProxy):
store = "intent"
def setup_defaults(self):
return {"force": {}}
def get_intent():
"""
use this to get an intent from inside a separate thread
:return:
"""
return TempIntent(store=IntentDictStorage(Dict))
-195
View File
@@ -1,195 +0,0 @@
# coding=utf-8
import os
import config
import helpers
import subtitlehelpers
from config import config as sz_config
def find_subtitles(part):
lang_sub_map = {}
part_filename = helpers.unicodize(part.file)
part_basename = os.path.splitext(os.path.basename(part_filename))[0]
use_filesystem = helpers.cast_bool(Prefs["subtitles.save.filesystem"])
paths = [os.path.dirname(part_filename)] if use_filesystem else []
global_subtitle_folder = None
global_folders = []
if use_filesystem:
# Check for local subtitles subdirectory
sub_dir_base = paths[0]
sub_dir_list = []
if Prefs["subtitles.save.subFolder"] != "current folder":
# got selected subfolder
sub_dir_list.append(os.path.join(sub_dir_base, Prefs["subtitles.save.subFolder"]))
sub_dir_custom = Prefs["subtitles.save.subFolder.Custom"].strip() \
if Prefs["subtitles.save.subFolder.Custom"] else None
if sub_dir_custom:
# got custom subfolder
sub_dir_custom = os.path.normpath(sub_dir_custom)
if os.path.isdir(sub_dir_custom) and os.path.isabs(sub_dir_custom):
# absolute folder
sub_dir_list.append(sub_dir_custom)
global_folders.append(sub_dir_custom)
else:
# relative folder
fld = os.path.join(sub_dir_base, sub_dir_custom)
sub_dir_list.append(fld)
for sub_dir in sub_dir_list:
if os.path.isdir(sub_dir):
paths.append(sub_dir)
# Check for a global subtitle location
global_subtitle_folder = os.path.join(Core.app_support_path, 'Subtitles')
if os.path.exists(global_subtitle_folder):
paths.append(global_subtitle_folder)
global_folders.append(global_subtitle_folder)
# normalize all paths
paths = [os.path.normpath(helpers.unicodize(path)) for path in paths]
# We start by building a dictionary of files to their absolute paths. We also need to know
# the number of media files that are actually present, in case the found local media asset
# is limited to a single instance per media file.
#
file_paths = {}
total_media_files = 0
media_files = []
for path in paths:
for file_path_listing in os.listdir(path.encode(sz_config.fs_encoding)):
# When using os.listdir with a unicode path, it will always return a string using the
# NFD form. However, we internally are using the form NFC and therefore need to convert
# it to allow correct regex / comparisons to be performed.
#
file_path_listing = helpers.unicodize(file_path_listing)
if os.path.isfile(os.path.join(path, file_path_listing).encode(sz_config.fs_encoding)):
file_paths[file_path_listing.lower()] = os.path.join(path, file_path_listing)
# If we've found an actual media file, we should record it.
(root, ext) = os.path.splitext(file_path_listing)
if ext.lower()[1:] in config.VIDEO_EXTS:
total_media_files += 1
# collect found media files
media_files.append(root)
# cleanup any leftover subtitle if no associated media file was found
if helpers.cast_bool(Prefs["subtitles.autoclean"]):
for path in paths:
# we can't housekeep the global subtitle folders as we don't know about *all* media files
# in a library; skip them
skip_path = False
for fld in global_folders:
if path.startswith(fld):
Log.Info("Skipping housekeeping of folder: %s", path)
skip_path = True
break
if skip_path:
continue
for file_path_listing in os.listdir(path.encode(sz_config.fs_encoding)):
file_path_listing = helpers.unicodize(file_path_listing)
enc_fn = os.path.join(path, file_path_listing).encode(sz_config.fs_encoding)
if os.path.isfile(enc_fn):
(root, ext) = os.path.splitext(file_path_listing)
# it's a subtitle file
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']:
root = split_tag[0]
# get associated media file name without language
sub_fn = subtitlehelpers.ENDSWITH_LANGUAGECODE_RE.sub("", root)
# subtitle basename and basename without possible language tag not found in collected
# media files? kill.
if root not in media_files and sub_fn not in media_files:
Log.Info("Removing leftover subtitle: %s", os.path.join(path, file_path_listing))
try:
os.remove(enc_fn)
except (OSError, IOError):
Log.Error("Removing failed")
Log('Looking for subtitle media in %d paths with %d media files.', len(paths), total_media_files)
Log('Paths: %s', ", ".join([helpers.unicodize(p) for p in paths]))
for file_path in file_paths.values():
local_filename = os.path.basename(file_path)
bn, ext = os.path.splitext(local_filename)
local_basename = helpers.unicodize(bn)
# get fn without forced/default/normal tag
split_tag = local_basename.rsplit(".", 1)
has_additional_tag = False
if len(split_tag) > 1 and split_tag[1].lower() in ['forced', 'normal', 'default', 'embedded', 'custom']:
local_basename = split_tag[0]
has_additional_tag = True
# split off possible language tag
local_basename2 = local_basename.rsplit('.', 1)[0]
filename_matches_part = local_basename == part_basename or local_basename2 == part_basename
filename_contains_part = part_basename in local_basename
if not ext.lower()[1:] in config.SUBTITLE_EXTS:
continue
# if the file is located within the global subtitle folders and its name doesn't match exactly, ignore it
if global_folders and not filename_matches_part:
skip_path = False
for fld in global_folders:
if file_path.startswith(fld):
skip_path = True
break
if skip_path:
continue
# 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),
# helpers.unicodize(part_basename)))
continue
subtitle_helper = subtitlehelpers.subtitle_helpers(file_path)
if subtitle_helper is not None:
local_lang_map = subtitle_helper.process_subtitles(part)
for new_language, subtitles in local_lang_map.items():
# Add the possible new language along with the located subtitles so that we can validate them
# at the end...
#
if not lang_sub_map.has_key(new_language):
lang_sub_map[new_language] = []
lang_sub_map[new_language] = lang_sub_map[new_language] + subtitles
# add known metadata subs to our sub list
if not use_filesystem:
for language, sub_list in subtitlehelpers.get_subtitles_from_metadata(part).iteritems():
if sub_list:
if language not in lang_sub_map:
lang_sub_map[language] = []
lang_sub_map[language] = lang_sub_map[language] + sub_list
# Now whack subtitles that don't exist anymore.
for language in lang_sub_map.keys():
part.subtitles[language].validate_keys(lang_sub_map[language])
# Now whack the languages that don't exist anymore.
for language in list(set(part.subtitles.keys()) - set(lang_sub_map.keys())):
part.subtitles[language].validate_keys({})
@@ -1,77 +0,0 @@
# coding=utf-8
import traceback
from support.config import config
from support.helpers import get_plex_item_display_title, cast_bool
from support.items import get_item
from support.lib import Plex
def item_discover_missing_subs(rating_key, kind="show", added_at=None, section_title=None, internal=False, external=True, languages=()):
existing_subs = {"internal": [], "external": [], "count": 0}
item_id = int(rating_key)
item = get_item(rating_key)
if kind == "show":
item_title = get_plex_item_display_title(item, kind, parent=item.season, section_title=section_title, parent_title=item.show.title)
else:
item_title = get_plex_item_display_title(item, kind, section_title=section_title)
video = item.media
for part in video.parts:
for stream in part.streams:
if stream.stream_type == 3:
if stream.index:
key = "internal"
else:
key = "external"
existing_subs[key].append(Locale.Language.Match(stream.language_code or ""))
existing_subs["count"] = existing_subs["count"] + 1
missing = languages
if existing_subs["count"]:
existing_flat = (existing_subs["internal"] if internal else []) + (existing_subs["external"] if external else [])
languages_set = set(languages)
if languages_set.issubset(existing_flat) or (len(existing_flat) >= 1 and Prefs['subtitles.only_one']):
# all subs found
Log.Info(u"All subtitles exist for '%s'", item_title)
return
missing = languages_set - set(existing_flat)
Log.Info(u"Subs still missing for '%s': %s", item_title, missing)
if missing:
return added_at, item_id, item_title, item, missing
def items_get_all_missing_subs(items):
missing = []
for added_at, kind, section_title, key in items:
try:
state = item_discover_missing_subs(
key,
kind=kind,
added_at=added_at,
section_title=section_title,
languages=config.lang_list,
internal=cast_bool(Prefs["subtitles.scan.embedded"]),
external=cast_bool(Prefs["subtitles.scan.external"])
)
if state:
# (added_at, item_id, title, item, missing_languages)
missing.append(state)
except:
Log.Error("Something went wrong when getting the state of item %s: %s", key, traceback.format_exc())
return missing
def refresh_item(item):
Plex["library/metadata"].refresh(item)
def refresh_items(items):
for item, title in items:
refresh_item(item)
-259
View File
@@ -1,259 +0,0 @@
# coding=utf-8
import os
import helpers
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,
"section": item.section.title,
"path": part.file,
"folder": os.path.dirname(part.file),
"filename": os.path.basename(part.file)
}
data.update(add)
return data
def media_to_videos(media, kind="series"):
"""
iterates through media and returns the associated parts (videos)
:param media:
:param kind:
:return:
"""
videos = []
if kind == "series":
for season in media.seasons:
season_object = media.seasons[season]
for episode in media.seasons[season].episodes:
ep = media.seasons[season].episodes[episode]
# get plex item via API for additional metadata
plex_episode = get_item(ep.id)
for item in media.seasons[season].episodes[episode].items:
for part in item.parts:
videos.append(
get_metadata_dict(plex_episode, part,
{"plex_part": part, "type": "episode", "title": ep.title,
"series": media.title, "id": ep.id,
"series_id": media.id, "season_id": season_object.id,
"episode": plex_episode.index, "season": plex_episode.season.index,
"section": plex_episode.section.title
})
)
else:
plex_item = get_item(media.id)
for item in media.items:
for part in item.parts:
videos.append(
get_metadata_dict(plex_item, part, {"plex_part": part, "type": "movie",
"title": media.title, "id": media.id,
"series_id": None,
"season_id": None,
"section": plex_item.section.title})
)
return videos
IGNORE_FN = ("subzero.ignore", ".subzero.ignore", ".nosz")
def get_stream_fps(streams):
"""
accepts a list of plex streams or a list of the plex api streams
"""
for stream in streams:
# video
stream_type = getattr(stream, "type", getattr(stream, "stream_type", None))
if stream_type == 1:
return getattr(stream, "frameRate", getattr(stream, "frame_rate", "25.000"))
return "25.000"
def get_media_item_ids(media, kind="series"):
ids = []
if kind == "movies":
ids.append(media.id)
else:
for season in media.seasons:
for episode in media.seasons[season].episodes:
ids.append(media.seasons[season].episodes[episode].id)
return ids
def scan_video(plex_part, ignore_all=False, hints=None, rating_key=None):
"""
returnes a subliminal/guessit-refined parsed video
:param plex_part:
:param ignore_all:
:param hints:
:param rating_key:
:return:
"""
embedded_subtitles = not ignore_all and Prefs['subtitles.scan.embedded']
external_subtitles = not ignore_all and Prefs['subtitles.scan.external']
if ignore_all:
Log.Debug("Force refresh intended.")
Log.Debug("Scanning video: %s, subtitles=%s, embedded_subtitles=%s" % (
plex_part.file, external_subtitles, embedded_subtitles))
known_embedded = []
parts = list(Plex["library"].metadata(rating_key))[0].media.parts
plexpy_part = None
for part in parts:
if int(part.id) == int(plex_part.id):
plexpy_part = part
# embedded subtitles
if plexpy_part:
for stream in plexpy_part.streams:
# subtitle stream
if stream.stream_type == 3:
if (config.forced_only and getattr(stream, "forced")) or \
(not config.forced_only and not getattr(stream, "forced")):
# embedded subtitle
if not stream.stream_key:
if config.exotic_ext or stream.codec in ("srt", "ass", "ssa"):
lang_code = stream.language_code
# treat unknown language as lang1?
if not lang_code and config.treat_und_as_first:
lang_code = list(config.lang_list)[0].alpha3
known_embedded.append(lang_code)
else:
Log.Warn("Part %s missing of %s, not able to scan internal streams", plex_part.id, rating_key)
try:
# get basic video info scan (filename)
video = parse_video(plex_part.file, hints, external_subtitles=external_subtitles,
embedded_subtitles=embedded_subtitles, known_embedded=known_embedded,
forced_only=config.forced_only, video_fps=plex_part.fps)
return video
except ValueError:
Log.Warn("File could not be guessed by subliminal: %s" % plex_part.file)
def scan_videos(videos, kind="series", ignore_all=False):
"""
receives a list of videos containing dictionaries returned by media_to_videos
:param videos:
:param kind: series or movies
:return: dictionary of subliminal.video.scan_video, key=subliminal scanned video, value=plex file part
"""
ret = {}
for video in videos:
intent = get_intent()
force_refresh = intent.get("force", video["id"], video["series_id"], video["season_id"])
Log.Debug("Determining force-refresh (video: %s, series: %s, season: %s), result: %s"
% (video["id"], video["series_id"], video["season_id"], force_refresh))
hints = helpers.get_item_hints(video)
video["plex_part"].fps = get_stream_fps(video["plex_part"].streams)
scanned_video = scan_video(video["plex_part"], ignore_all=force_refresh or ignore_all, hints=hints,
rating_key=video["id"])
if not scanned_video:
continue
scanned_video.id = video["id"]
part_metadata = video.copy()
del part_metadata["plex_part"]
scanned_video.plexapi_metadata = part_metadata
ret[scanned_video] = video["plex_part"]
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
:param rating_key:
:param part_id:
:param item_type:
:return:
"""
plex_item = list(Plex["library"].metadata(rating_key))[0]
# find current part
current_part = None
for part in plex_item.media.parts:
if str(part.id) == part_id:
current_part = part
if not current_part:
raise PartUnknownException("Part unknown")
# get normalized metadata
if item_type == "episode":
metadata = get_metadata_dict(plex_item, current_part,
{"plex_part": current_part, "type": "episode", "title": plex_item.title,
"series": plex_item.show.title, "id": plex_item.rating_key,
"series_id": plex_item.show.rating_key,
"season_id": plex_item.season.rating_key,
"season": plex_item.season.index,
"episode": plex_item.index
})
else:
metadata = get_metadata_dict(plex_item, current_part, {"plex_part": current_part, "type": "movie",
"title": plex_item.title, "id": plex_item.rating_key,
"series_id": None,
"season_id": None,
"season": None,
"episode": None,
"section": plex_item.section.title})
return metadata
class PMSMediaProxy(object):
"""
Proxy object for getting data from a mediatree items "internally" via the PMS
note: this could be useful later on: Media.TV_Show(getattr(Metadata, "_access_point"), id=XXXXXX)
"""
def __init__(self, media_id):
self.mediatree = Media.TreeForDatabaseID(media_id)
def get_part(self, part_id=None):
"""
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
while 1:
if m.items:
media_item = m.items[0]
if not part_id:
return media_item.parts[0] if media_item.parts else None
for part in media_item.parts:
if str(part.id) == str(part_id):
return part
break
if not m.children:
break
m = m.children[0]
-186
View File
@@ -1,186 +0,0 @@
# coding=utf-8
import datetime
import os
import pprint
import copy
import subliminal
from items import get_item
from subzero.subtitle_storage import StoredSubtitlesManager
from subtitlehelpers import force_utf8
from config import config
from helpers import notify_executable, get_title_for_video_metadata, cast_bool, force_unicode
from plex_media import PMSMediaProxy
get_subtitle_storage = lambda: StoredSubtitlesManager(Data, get_item)
def whack_missing_parts(scanned_video_part_map, existing_parts=None):
"""
cleans out our internal storage's video parts (parts may get updated/deleted/whatever)
:param existing_parts: optional list of part ids known
:param scanned_video_part_map: videos to check for
:return:
"""
# shortcut
if "subs" not in Dict:
return
if not existing_parts:
existing_parts = []
for part in scanned_video_part_map.viewvalues():
existing_parts.append(str(part.id))
whacked_parts = False
for video in scanned_video_part_map.keys():
video_id = str(video.id)
if video_id not in Dict["subs"]:
continue
parts = Dict["subs"][video_id].keys()
for part_id in parts:
part_id = str(part_id)
if part_id not in existing_parts:
Log.Info("Whacking part %s in internal storage of video %s (%s, %s)", part_id, video_id,
repr(existing_parts), repr(parts))
del Dict["subs"][video_id][part_id]
whacked_parts = True
if whacked_parts:
Dict.Save()
def store_subtitle_info(scanned_video_part_map, downloaded_subtitles, storage_type, mode="a"):
"""
stores information about downloaded subtitles in plex's Dict()
"""
existing_parts = []
for video, video_subtitles in downloaded_subtitles.items():
part = scanned_video_part_map[video]
part_id = str(part.id)
video_id = str(video.id)
plex_item = get_item(video_id)
metadata = video.plexapi_metadata
title = get_title_for_video_metadata(metadata)
subtitle_storage = get_subtitle_storage()
stored_subs = subtitle_storage.load_or_new(plex_item)
existing_parts.append(part_id)
stored_any = False
for subtitle in video_subtitles:
lang = Locale.Language.Match(subtitle.language.alpha2)
Log.Debug(u"Adding subtitle to storage: %s, %s, %s" % (video_id, part_id, title))
ret_val = stored_subs.add(part_id, lang, subtitle, storage_type, mode=mode)
if ret_val:
Log.Debug("Subtitle stored")
stored_any = True
else:
Log.Debug("Subtitle already existing in storage")
if stored_any:
Log.Debug("Saving subtitle storage for %s" % video_id)
subtitle_storage.save(stored_subs)
#if existing_parts:
# whack_missing_parts(scanned_video_part_map, existing_parts=existing_parts)
def reset_storage(key):
"""
resets the Dict[key] storage, thanks to https://docs.google.com/document/d/1hhLjV1pI-TA5y91TiJq64BdgKwdLnFt4hWgeOqpz1NA/edit#
We can't use the nice Plex interface for this, as it calls get multiple times before set
#Plex[":/plugins/*/prefs"].set("com.plexapp.agents.subzero", "reset_storage", False)
"""
Log.Debug("resetting storage")
Dict[key] = {}
Dict.Save()
def log_storage(key):
if key in Dict:
Log.Debug(pprint.pformat(Dict[key]))
def save_subtitles_to_file(subtitles):
fld_custom = Prefs["subtitles.save.subFolder.Custom"].strip() \
if Prefs["subtitles.save.subFolder.Custom"] else None
for video, video_subtitles in subtitles.items():
if not video_subtitles:
continue
fld = None
if fld_custom or Prefs["subtitles.save.subFolder"] != "current folder":
# specific subFolder requested, create it if it doesn't exist
fld_base = os.path.split(video.name)[0]
if fld_custom:
if fld_custom.startswith("/"):
# absolute folder
fld = fld_custom
else:
fld = os.path.join(fld_base, fld_custom)
else:
fld = os.path.join(fld_base, Prefs["subtitles.save.subFolder"])
fld = force_unicode(fld)
if not os.path.exists(fld):
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)
return True
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
if not isinstance(mediaPart, Framework.api.agentkit.MediaPart):
# we're being handed a Plex.py model instance here, not an internal PMS MediaPart object.
# get the correct one
mp = PMSMediaProxy(video.id).get_part(mediaPart.id)
else:
mp = mediaPart
mp.subtitles[Locale.Language.Match(subtitle.language.alpha2)][subtitle.id] = Proxy.Media(content, ext="srt")
return True
def save_subtitles(scanned_video_part_map, downloaded_subtitles, mode="a"):
meta_fallback = False
save_successful = False
storage = "metadata"
if Prefs['subtitles.save.filesystem']:
storage = "filesystem"
try:
Log.Debug("Using filesystem as subtitle storage")
save_subtitles_to_file(downloaded_subtitles)
except OSError:
if Prefs["subtitles.save.metadata_fallback"]:
meta_fallback = True
else:
raise
else:
save_successful = True
if not Prefs['subtitles.save.filesystem'] or meta_fallback:
if meta_fallback:
Log.Debug("Using metadata as subtitle storage, because filesystem storage failed")
else:
Log.Debug("Using metadata as subtitle storage")
save_successful = save_subtitles_to_metadata(scanned_video_part_map, downloaded_subtitles)
if save_successful and config.notify_executable:
notify_executable(config.notify_executable, scanned_video_part_map, downloaded_subtitles, storage)
store_subtitle_info(scanned_video_part_map, downloaded_subtitles, storage, mode=mode)
-203
View File
@@ -1,203 +0,0 @@
# coding=utf-8
import re, os
import config
import helpers
from bs4 import UnicodeDammit
class SubtitleHelper(object):
def __init__(self, filename):
self.filename = filename
def subtitle_helpers(filename):
filename = helpers.unicodize(filename)
helper_classes = [DefaultSubtitleHelper]
if helpers.cast_bool(Prefs["subtitles.scan.exotic_ext"]):
helper_classes.insert(0, VobSubSubtitleHelper)
for cls in helper_classes:
if cls.is_helper_for(filename):
return cls(filename)
return None
#####################################################################################################################
class VobSubSubtitleHelper(SubtitleHelper):
@classmethod
def is_helper_for(cls, filename):
(file, file_extension) = os.path.splitext(filename)
# We only support idx (and maybe sub)
if not file_extension.lower() in ['.idx', '.sub']:
return False
# If we've been given a sub, we only support it if there exists a matching idx file
return os.path.exists(file + '.idx')
def process_subtitles(self, part):
lang_sub_map = {}
# We don't directly process the sub file, only the idx. Therefore if we are passed on of these files, we simply
# ignore it.
(file, ext) = os.path.splitext(self.filename)
if ext == '.sub':
return lang_sub_map
# If we have an idx file, we need to confirm there is an identically names sub file before we can proceed.
sub_filename = file + ".sub"
if not os.path.exists(sub_filename):
return lang_sub_map
Log('Attempting to parse VobSub file: ' + self.filename)
idx = Core.storage.load(os.path.join(self.filename))
if idx.count('VobSub index file') == 0:
Log('The idx file does not appear to be a VobSub, skipping...')
return lang_sub_map
languages = {}
language_index = 0
basename = os.path.basename(self.filename)
for language in re.findall('\nid: ([A-Za-z]{2})', idx):
if not languages.has_key(language):
languages[language] = []
Log('Found .idx subtitle file: ' + self.filename + ' language: ' + language + ' stream index: ' + str(language_index))
languages[language].append(Proxy.LocalFile(self.filename, index=str(language_index), format="vobsub"))
language_index += 1
if not lang_sub_map.has_key(language):
lang_sub_map[language] = []
lang_sub_map[language].append(basename)
for language, subs in languages.items():
part.subtitles[language][basename] = subs
return lang_sub_map
#####################################################################################################################
IETF_MATCH = ".+\.([^-.]+)(?:-[A-Za-z]+)?$"
ENDSWITH_LANGUAGECODE_RE = re.compile("\.([^-.]{2,3})(?:-[A-Za-z]{2})?$")
def match_ietf_language(s):
language_match = re.match(".+\.([^\.]+)$" if not helpers.cast_bool(Prefs["subtitles.language.ietf"])
else IETF_MATCH, s)
if language_match and len(language_match.groups()) == 1:
language = language_match.groups()[0]
return language
return s
class DefaultSubtitleHelper(SubtitleHelper):
@classmethod
def is_helper_for(cls, filename):
(file, file_extension) = os.path.splitext(filename)
return file_extension.lower()[1:] in config.SUBTITLE_EXTS
def process_subtitles(self, part):
lang_sub_map = {}
if not os.path.exists(self.filename):
return lang_sub_map
basename = os.path.basename(self.filename)
(file, ext) = os.path.splitext(self.filename)
# Remove the initial '.' from the extension
ext = ext[1:]
forced = ''
default = ''
split_tag = file.rsplit('.', 1)
if len(split_tag) > 1 and split_tag[1].lower() in ['forced', 'normal', 'default', 'embedded', 'custom']:
file = split_tag[0]
# don't do anything with 'normal', we don't need it
if 'forced' == split_tag[1].lower():
forced = '1'
if 'default' == split_tag[1].lower():
default = '1'
# Attempt to extract the language from the filename (e.g. Avatar (2009).eng)
language = ""
# IETF support thanks to https://github.com/hpsbranco/LocalMedia.bundle/commit/4fad9aefedece78a1fa96401304351347f644369
language = Locale.Language.Match(match_ietf_language(file))
# skip non-SRT if wanted
if not helpers.cast_bool(Prefs["subtitles.scan.exotic_ext"]) and ext not in ["srt", "ass", "ssa"]:
return lang_sub_map
codec = None
format = None
if ext in ['txt', 'sub']:
try:
file_contents = Core.storage.load(self.filename)
lines = [line.strip() for line in file_contents.splitlines(True)]
if re.match('^\{[0-9]+\}\{[0-9]*\}', lines[1]):
format = 'microdvd'
elif re.match('^[0-9]{1,2}:[0-9]{2}:[0-9]{2}[:=,]', lines[1]):
format = 'txt'
elif '[SUBTITLE]' in lines[1]:
format = 'subviewer'
else:
Log("The subtitle file does not have a known format, skipping... : " + self.filename)
return lang_sub_map
except:
Log("An error occurred while attempting to parse the subtitle file, skipping... : " + self.filename)
return lang_sub_map
if codec is None and ext in ['ass', 'ssa', 'smi', 'srt', 'psb']:
codec = ext.replace('ass', 'ssa')
if format is None:
format = codec
Log('Found subtitle file: ' + self.filename + ' language: ' + language + ' codec: ' + str(
codec) + ' format: ' + str(format) + ' default: ' + default + ' forced: ' + forced)
part.subtitles[language][basename] = Proxy.LocalFile(self.filename, codec=codec, format=format, default=default,
forced=forced)
lang_sub_map[language] = [basename]
return lang_sub_map
def get_subtitles_from_metadata(part):
subs = {}
for language in part.subtitles:
subs[language] = []
for key, proxy in getattr(part.subtitles[language], "_proxies").iteritems():
if not proxy or not len(proxy) >= 5:
Log.Debug("Can't parse metadata: %s" % repr(proxy))
continue
p_type = proxy[0]
if p_type == "Media":
# metadata subtitle
Log.Debug(u"Found metadata subtitle: %s, %s" % (language, repr(proxy)))
subs[language].append(key)
return subs
def force_utf8(content):
a = UnicodeDammit(content)
Log.Debug("detected encoding: %s (None: most likely already successfully decoded)" % a.original_encoding)
# easy way out - already utf-8
if a.original_encoding and a.original_encoding == "utf-8":
return content
return (a.unicode_markup if a.unicode_markup else content.decode('ascii', 'replace')).encode("utf-8")
-456
View File
@@ -1,456 +0,0 @@
# coding=utf-8
import datetime
import time
import operator
import traceback
from subliminal_patch.score import compute_score
from subliminal_patch.core import download_subtitles
from subliminal import list_subtitles as list_all_subtitles
from babelfish import Language
from missing_subtitles import items_get_all_missing_subs, refresh_item
from background import scheduler
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
class Task(object):
name = None
scheduler = None
periodic = False
running = False
time_start = None
data = None
stored_attributes = ("last_run", "last_run_time", "running")
default_data = {"last_run": None, "last_run_time": None, "running": False, "data": {}}
# task ready for being status-displayed?
ready_for_display = False
def __init__(self, scheduler):
self.name = self.get_class_name()
self.ready_for_display = False
self.time_start = None
self.scheduler = scheduler
self.setup_defaults()
self.running = False
def get_class_name(self):
return getattr(getattr(self, "__class__"), "__name__")
def __getattribute__(self, name):
if name in object.__getattribute__(self, "stored_attributes"):
return Dict["tasks"].get(self.name, {}).get(name, None)
return object.__getattribute__(self, name)
def __setattr__(self, name, value):
if name in object.__getattribute__(self, "stored_attributes"):
Dict["tasks"][self.name][name] = value
Dict.Save()
return
object.__setattr__(self, name, value)
def setup_defaults(self):
if self.name not in Dict["tasks"]:
Dict["tasks"][self.name] = self.default_data.copy()
return
sd = Dict["tasks"][self.name]
# forward-migration
for key, def_value in self.default_data.iteritems():
hasval = key in sd
if not hasval:
sd[key] = def_value
def signal(self, *args, **kwargs):
raise NotImplementedError
def prepare(self, *args, **kwargs):
return
def run(self):
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:
self.last_run_time = self.last_run - self.time_start
self.time_start = None
class SearchAllRecentlyAddedMissing(Task):
periodic = True
items_done = None
items_searching = None
items_searching_ids = None
items_failed = None
percentage = 0
stall_time = 30
def __init__(self, scheduler):
super(SearchAllRecentlyAddedMissing, self).__init__(scheduler)
self.items_done = None
self.items_searching = None
self.items_searching_ids = None
self.items_failed = None
self.percentage = 0
def signal(self, signal_name, *args, **kwargs):
handler = getattr(self, "signal_%s" % signal_name)
return handler(*args, **kwargs) if handler else None
def signal_updated_metadata(self, *args, **kwargs):
item_id = int(args[0])
if self.items_searching_ids is not None and item_id in self.items_searching_ids:
self.items_done.append(item_id)
return True
def prepare(self, *args, **kwargs):
self.items_done = []
recent_items = get_recent_items()
missing = items_get_all_missing_subs(recent_items)
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
self.items_failed = []
self.percentage = 0
self.ready_for_display = True
def run(self):
super(SearchAllRecentlyAddedMissing, self).run()
self.running = True
missing_count = len(self.items_searching)
items_done_count = 0
for added_at, item_id, title, item, missing_languages in self.items_searching:
Log.Debug(u"Task: %s, triggering refresh for %s (%s)", self.name, title, item_id)
refresh_item(item_id)
search_started = datetime.datetime.now()
tries = 1
while 1:
if item_id in self.items_done:
items_done_count += 1
Log.Debug(u"Task: %s, item %s done", self.name, item_id)
self.percentage = int(items_done_count * 100 / missing_count)
break
# item considered stalled after self.stall_time seconds passed after last refresh
if (datetime.datetime.now() - search_started).total_seconds() > self.stall_time:
if tries > 3:
self.items_failed.append(item_id)
Log.Debug(u"Task: %s, item stalled for %s times: %s, skipping", self.name, tries, item_id)
break
Log.Debug(u"Task: %s, item stalled for %s seconds: %s, retrying", self.name, self.stall_time,
item_id)
tries += 1
refresh_item(item_id)
search_started = datetime.datetime.now()
time.sleep(1)
time.sleep(0.1)
# we can't hammer the PMS, otherwise requests will be stalled
time.sleep(1)
Log.Debug("Task: %s, done. Failed items: %s", self.name, self.items_failed)
self.running = False
def post_run(self, task_data):
super(SearchAllRecentlyAddedMissing, self).post_run(task_data)
self.ready_for_display = False
self.percentage = 0
self.items_done = None
self.items_failed = None
self.items_searching = None
self.items_searching_ids = None
class SubtitleListingMixin(object):
def list_subtitles(self, rating_key, item_type, part_id, language):
metadata = get_plex_metadata(rating_key, part_id, item_type)
if item_type == "episode":
min_score = 240
else:
min_score = 60
scanned_parts = scan_videos([metadata], kind="series" if item_type == "episode" else "movie", ignore_all=True)
if not scanned_parts:
Log.Error("Couldn't list available subtitles for %s", rating_key)
return
video, plex_part = scanned_parts.items()[0]
config.init_subliminal_patches()
available_subs = list_all_subtitles(scanned_parts, {Language.fromietf(language)},
providers=config.providers,
provider_configs=config.provider_settings,
pool_class=config.provider_pool)
use_hearing_impaired = Prefs['subtitles.search.hearingImpaired'] in ("prefer", "force HI")
# sort subtitles by score
unsorted_subtitles = []
for s in available_subs[video]:
Log.Debug("Starting score computation for %s", s)
try:
matches = s.get_matches(video)
except AttributeError:
Log.Error("Match computation failed for %s: %s", s, traceback.format_exc())
continue
unsorted_subtitles.append(
(s, compute_score(matches, s, video, hearing_impaired=use_hearing_impaired), matches))
scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1), reverse=True)
subtitles = []
for subtitle, score, matches in scored_subtitles:
# check score
if score < min_score:
Log.Info('Score %d is below min_score (%d)', score, min_score)
continue
subtitle.score = score
subtitle.matches = matches
subtitle.part_id = part_id
subtitle.item_type = item_type
subtitles.append(subtitle)
return subtitles
class DownloadSubtitleMixin(object):
def download_subtitle(self, subtitle, rating_key, mode="m"):
from interface.menu_helpers import set_refresh_menu_state
item_type = subtitle.item_type
part_id = subtitle.part_id
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]
# downloaded_subtitles = {subliminal.Video: [subtitle, subtitle, ...]}
download_subtitles([subtitle], providers=config.providers, provider_configs=config.provider_settings,
pool_class=config.provider_pool)
download_successful = False
if subtitle.content:
try:
whack_missing_parts(scanned_parts)
save_subtitles(scanned_parts, {video: [subtitle]}, mode=mode)
Log.Debug("Manually downloaded subtitle for: %s", rating_key)
download_successful = True
refresh_item(rating_key)
track_usage("Subtitle", "manual", "download", 1)
except:
Log.Error("Something went wrong when downloading specific subtitle: %s", traceback.format_exc())
finally:
set_refresh_menu_state(None)
if download_successful:
# store item in history
from support.history import get_history
item_title = get_title_for_video_metadata(metadata, add_section_title=False)
history = get_history()
history.add(item_title, video.id, section_title=video.plexapi_metadata["section"],
subtitle=subtitle,
mode=mode)
return download_successful
class AvailableSubsForItem(SubtitleListingMixin, Task):
item_type = None
part_id = None
language = None
rating_key = None
def prepare(self, *args, **kwargs):
self.item_type = kwargs.get("item_type")
self.part_id = kwargs.get("part_id")
self.language = kwargs.get("language")
self.rating_key = kwargs.get("rating_key")
def setup_defaults(self):
super(AvailableSubsForItem, self).setup_defaults()
# reset any previous data
Dict["tasks"][self.name]["data"] = {}
def run(self):
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)
def post_run(self, task_data):
super(AvailableSubsForItem, self).post_run(task_data)
if self.rating_key not in task_data:
task_data[self.rating_key] = {}
task_data[self.rating_key][self.language] = self.data
class DownloadSubtitleForItem(DownloadSubtitleMixin, Task):
subtitle = None
rating_key = None
def prepare(self, *args, **kwargs):
self.subtitle = kwargs["subtitle"]
self.rating_key = kwargs["rating_key"]
def run(self):
super(DownloadSubtitleForItem, self).run()
self.running = True
self.download_subtitle(self.subtitle, self.rating_key)
self.running = False
class MissingSubtitles(Task):
rating_key = None
item_type = None
part_id = None
language = None
def run(self):
super(MissingSubtitles, self).run()
self.running = True
self.data = []
recent_items = get_recent_items()
if recent_items:
self.data = items_get_all_missing_subs(recent_items)
def post_run(self, task_data):
super(MissingSubtitles, self).post_run(task_data)
task_data["missing_subtitles"] = self.data
class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
periodic = True
# TV: episode, format, series, year, season, video_codec, release_group, hearing_impaired
series_cutoff = 355
# movies: format, title, release_group, year, video_codec, resolution, hearing_impaired
movies_cutoff = 117
def signal_updated_metadata(self, *args, **kwargs):
return True
def run(self):
super(FindBetterSubtitles, self).run()
self.running = True
better_found = 0
try:
max_search_days = int(Prefs["scheduler.tasks.FindBetterSubtitles.max_days_after_added"].strip())
except ValueError:
Log.Error("Please only put numbers into the FindBetterSubtitles.max_days_after_added setting. Exiting")
return
else:
if max_search_days > 30:
Log.Error("FindBetterSubtitles.max_days_after_added is too big. Max is 30 days.")
return
now = datetime.datetime.now()
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
# don't search for better subtitles until at least 30 minutes have passed
if stored_subs.added_at + datetime.timedelta(minutes=30) > now:
Log.Debug("Item %s too new, skipping", video_id)
continue
# added_date <= max_search_days?
if stored_subs.added_at + datetime.timedelta(days=max_search_days) <= now:
continue
ditch_parts = []
# look through all stored subtitle data
for part_id, languages in stored_subs.parts.iteritems():
part_id = str(part_id)
# all languages
for language, current_subs in languages.iteritems():
current_key = current_subs.get("current")
current = current_subs.get(current_key)
# currently got subtitle?
if not current:
continue
current_score = current.score
current_mode = current.mode
# late cutoff met? skip
if current_score >= cutoff:
Log.Debug(u"Skipping finding better subs, cutoff met (current: %s, cutoff: %s): %s",
current_score, cutoff, stored_subs.title)
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"]):
Log.Debug(u"Skipping finding better subs, had manual: %s", stored_subs.title)
continue
try:
subs = self.list_subtitles(video_id, stored_subs.item_type, part_id, language)
except PartUnknownException:
Log.Info("Part %s unknown/gone; ditching subtitle info", part_id)
ditch_parts.append(part_id)
continue
if subs:
# subs are already sorted by score
better_downloaded = False
better_tried_download = 0
for sub in subs:
if sub.score > current_score:
Log.Debug("Better subtitle found for %s, downloading", video_id)
better_tried_download += 1
ret = self.download_subtitle(sub, video_id, mode="b")
if ret:
better_found += 1
better_downloaded = True
break
else:
Log.Debug("Couldn't download/save subtitle. Continuing to the next one")
if better_tried_download and not better_downloaded:
Log.Debug("Tried downloading better subtitle for %s, but every try failed.", video_id)
elif better_downloaded:
Log.Debug("Better subtitle downloaded for %s", video_id)
if ditch_parts:
for part_id in ditch_parts:
try:
del stored_subs.parts[part_id]
except KeyError:
pass
subtitle_storage.save(stored_subs)
if better_found:
Log.Debug("Task: %s, done. Better subtitles found for %s items", self.name, better_found)
self.running = False
scheduler.register(SearchAllRecentlyAddedMissing)
scheduler.register(AvailableSubsForItem)
scheduler.register(DownloadSubtitleForItem)
scheduler.register(MissingSubtitles)
scheduler.register(FindBetterSubtitles)
-631
View File
@@ -1,631 +0,0 @@
[
{
"id": "langPref1",
"label": "Subtitle Language (1)",
"type": "enum",
"values": [
"sq",
"ar",
"be",
"bs",
"bg",
"ca",
"zh",
"cs",
"da",
"nl",
"en",
"et",
"fi",
"fr",
"de",
"el",
"he",
"hi",
"hu",
"is",
"id",
"it",
"ja",
"ko",
"lv",
"lt",
"mk",
"ms",
"no",
"fa",
"pl",
"pt",
"pt-br",
"ro",
"ru",
"sr",
"sk",
"sl",
"es",
"sv",
"th",
"tr",
"uk",
"vi",
"hr"
],
"default": "en"
},
{
"id": "langPref2",
"label": "Subtitle Language (2)",
"type": "enum",
"values": [
"None",
"sq",
"ar",
"be",
"bs",
"bg",
"ca",
"zh",
"cs",
"da",
"nl",
"en",
"et",
"fi",
"fr",
"de",
"el",
"he",
"hi",
"hu",
"is",
"id",
"it",
"ja",
"ko",
"lv",
"lt",
"mk",
"ms",
"no",
"fa",
"pl",
"pt",
"pt-br",
"ro",
"ru",
"sr",
"sk",
"sl",
"es",
"sv",
"th",
"tr",
"uk",
"vi",
"hr"
],
"default": "None"
},
{
"id": "langPref3",
"label": "Subtitle Language (3)",
"type": "enum",
"values": [
"None",
"sq",
"ar",
"be",
"bs",
"bg",
"ca",
"zh",
"cs",
"da",
"nl",
"en",
"et",
"fi",
"fr",
"de",
"el",
"he",
"hi",
"hu",
"is",
"id",
"it",
"ja",
"ko",
"lv",
"lt",
"mk",
"ms",
"no",
"fa",
"pl",
"pt",
"pt-br",
"ro",
"ru",
"sr",
"sk",
"sl",
"es",
"sv",
"th",
"tr",
"uk",
"vi",
"hr"
],
"default": "None"
},
{
"id": "langPrefCustom",
"label": "Additional Subtitle Languages (use ISO-639-1 codes; comma-separated)",
"type": "text",
"default": "None"
},
{
"id": "subtitles.only_foreign",
"label": "Only download foreign/forced subtitles",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.language.ietf",
"label": "Treat IETF language tags as ISO 639-1 (e.g. pt-BR = pt)",
"type": "bool",
"default": "true"
},
{
"id": "subtitles.only_one",
"label": "Restrict to one language (skips adding \".lang.\" to the subtitle filename; only uses \"Subtitle Language (1)\")",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.language.treat_und_as_first",
"label": "Embedded subtitles: Treat \"Undefined\" (und) as language 1",
"type": "bool",
"default": "true"
},
{
"id": "provider.opensubtitles.enabled",
"label": "Provider: Enable OpenSubtitles",
"type": "bool",
"default": "true"
},
{
"id": "provider.opensubtitles.username",
"label": "Opensubtitles Username (VIP)",
"type": "text",
"default": ""
},
{
"id": "provider.opensubtitles.password",
"label": "Opensubtitles Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.podnapisi.enabled",
"label": "Provider: Enable Podnapisi.NET",
"type": "bool",
"default": "true"
},
{
"id": "provider.addic7ed.enabled",
"label": "Provider: Enable Addic7ed",
"type": "bool",
"default": "true"
},
{
"id": "provider.addic7ed.username",
"label": "Addic7ed Username",
"type": "text",
"default": ""
},
{
"id": "provider.addic7ed.password",
"label": "Addic7ed Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.addic7ed.boost_by1",
"label": "Addic7ed: boost score (if requirements met)",
"type": "enum",
"values": [
"100",
"95",
"90",
"85",
"80",
"75",
"70",
"67",
"65",
"60",
"55",
"50",
"45",
"40",
"35",
"30",
"25",
"20",
"15",
"10",
"5",
"0"
],
"default": "25"
},
{
"id": "provider.addic7ed.use_random_agents",
"label": "Addic7ed: Use random user agents",
"type": "bool",
"default": "false"
},
{
"id": "provider.legendastv.enabled",
"label": "Provider: Enable Legendas TV (mostly pt-BR)",
"type": "bool",
"default": "false"
},
{
"id": "provider.legendastv.username",
"label": "Legendas TV Username",
"type": "text",
"default": ""
},
{
"id": "provider.legendastv.password",
"label": "Legendas TV Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.tvsubtitles.enabled",
"label": "Provider: Enable TVsubtitles.net",
"type": "bool",
"default": "true"
},
{
"id": "provider.napiprojekt.enabled",
"label": "Provider: Enable NapiProjekt.pl (Polish)",
"type": "bool",
"default": "false"
},
{
"id": "provider.shooter.enabled",
"label": "Provider: Enable Shooter.cn (Chinese)",
"type": "bool",
"default": "false"
},
{
"id": "provider.subscenter.enabled",
"label": "Provider: Enable SubsCenter (Hebrew)",
"type": "bool",
"default": "false"
},
{
"id": "provider.subscenter.username",
"label": "SubsCenter Username",
"type": "text",
"default": ""
},
{
"id": "provider.subscenter.password",
"label": "SubsCenter Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "providers.multithreading",
"label": "Search enabled providers simuntaneously (multithreading)",
"type": "bool",
"default": "true"
},
{
"id": "provider.opensubtitles.use_tags",
"label": "I keep the exact (release-) filename of my media files",
"type": "bool",
"default": "true"
},
{
"id": "subtitles.scan.embedded",
"label": "Scan: include embedded subtitles (in the media file (MKV/MP4), don't download if existing)",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.scan.external",
"label": "Scan: include external subtitles (metadata/filesystem, don't download if existing)",
"type": "bool",
"default": "true"
},
{
"id": "subtitles.scan.exotic_ext",
"label": "Scan: include \"exotic\" external subtitle formats (anything else than .srt/.ssa/.ass)",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.scan.filename_strictness",
"label": "Scan: which external subtitles should be picked up?",
"type": "enum",
"values": [
"exact: media filename match",
"loose: filename contains media filename",
"any"
],
"default": "loose: filename contains media filename"
},
{
"id": "subtitles.search.minimumTVScore2",
"label": "Minimum score for TV (min: 240, def/sane: 337, min-ideal: 352; see http://v.ht/szscores)",
"type": "text",
"default": "337"
},
{
"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"
},
{
"id": "subtitles.search.hearingImpaired",
"label": "Download hearing impaired subtitles.",
"type": "enum",
"values": [
"prefer",
"don't prefer",
"force HI",
"force non-HI"
],
"default": "don't prefer"
},
{
"id": "subtitles.enforce_encoding",
"label": "Normalize subtitle encoding to UTF-8",
"type": "bool",
"default": "true"
},
{
"id": "subtitles.save.filesystem",
"label": "Store subtitles next to media files (instead of metadata)",
"type": "bool",
"default": "true"
},
{
"id": "subtitles.save.subFolder",
"label": "Subtitle Folder (\"current folder\" is the folder the current media file lives in)",
"type": "enum",
"values": [
"current folder",
"sub",
"subs",
"subtitle",
"subtitles"
],
"default": "current folder"
},
{
"id": "subtitles.save.subFolder.Custom",
"label": "Custom Subtitle folder (overrides \"Subtitle Folder\"; computes to real paths)",
"type": "text",
"default": ""
},
{
"id": "subtitles.save.metadata_fallback",
"label": "Fall back to metadata storage if filesystem storage failed",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.save.chmod",
"label": "Set subtitle file permissions to (integer, e.g.: 0775)",
"type": "text",
"default": ""
},
{
"id": "subtitles.autoclean",
"label": "Automatically delete leftover/unused (externally saved) subtitles",
"type": "bool",
"default": "true"
},
{
"id": "activity.on_playback",
"label": "On media playback: search for missing subtitles (refresh item)",
"type": "enum",
"values": [
"never",
"current media item",
"next episode (series)",
"hybrid: current item or next episode"
],
"default": "never"
},
{
"id": "scheduler.tasks.SearchAllRecentlyAddedMissing.frequency",
"label": "Scheduler: Periodically search for recent items with missing subtitles",
"type": "enum",
"values": [
"never",
"every 1 hours",
"every 3 hours",
"every 6 hours",
"every 12 hours",
"every 24 hours"
],
"default": "every 6 hours"
},
{
"id": "scheduler.item_is_recent_age",
"label": "Scheduler: Item age to be considered recent",
"type": "enum",
"values": [
"1 days",
"2 days",
"3 days",
"4 days",
"1 weeks",
"2 weeks",
"3 weeks",
"4 weeks",
"5 weeks",
"6 weeks"
],
"default": "2 weeks"
},
{
"id": "scheduler.max_recent_items_per_library",
"label": "Scheduler: Recent items to consider per library",
"type": "text",
"default": "500"
},
{
"id": "scheduler.tasks.FindBetterSubtitles.frequency",
"label": "Scheduler: Periodically search for better subtitles",
"type": "enum",
"values": [
"never",
"every 6 hours",
"every 12 hours",
"every 24 hours"
],
"default": "every 12 hours"
},
{
"id": "scheduler.tasks.FindBetterSubtitles.max_days_after_added",
"label": "Scheduler: Days to search for better subtitles (max: 30 days)",
"type": "text",
"default": "7"
},
{
"id": "scheduler.tasks.FindBetterSubtitles.overwrite_manually_selected",
"label": "Scheduler: Overwrite manually selected subtitles when better found",
"type": "bool",
"default": "true"
},
{
"id": "history_size",
"label": "History: amount of items to store historical data for",
"type": "enum",
"values": [
"50",
"100",
"150",
"250",
"500"
],
"default": "100"
},
{
"id": "subtitles.try_downloads",
"label": "How many download tries per subtitle (on timeout or error)",
"type": "enum",
"values": [
"1",
"2",
"3",
"4"
],
"default": "2"
},
{
"id": "subtitles.ignore_fs",
"label": "Ignore folders (with \"subzero.ignore/.subzero.ignore/.nosz\" files in them)",
"type": "bool",
"default": "false"
},
{
"id": "subtitles.ignore_paths",
"label": "Ignore anything in the following paths (comma-separated)",
"type": "text",
"default": ""
},
{
"id": "plugin_mode",
"label": "Sub-Zero mode",
"type": "enum",
"values": [
"agent + channel",
"only agent",
"only channel"
],
"default": "agent + channel"
},
{
"id": "plugin_pin",
"label": "Access PIN (any amount of numbers, 0-9)",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "plugin_pin_valid_for",
"label": "Access PIN valid for minutes",
"type": "text",
"default": "10"
},
{
"id": "plugin_pin_mode",
"label": "Use PIN to restrict access to (needs plugin or PMS restart)",
"type": "enum",
"values": [
"disabled",
"channel menu",
"advanced menu"
],
"default": "disabled"
},
{
"id": "notify_executable",
"label": "Call this executable upon successful subtitle download",
"type": "text",
"default": ""
},
{
"id": "check_permissions",
"label": "Check for correct folder permissions of every library on plugin start",
"type": "bool",
"default": "true"
},
{
"id": "log_level",
"label": "How verbose should the logging be?",
"type": "enum",
"values": [
"CRITICAL",
"ERROR",
"WARNING",
"INFO",
"DEBUG"
],
"default": "WARNING"
},
{
"id": "log_console",
"label": "Log to console (for development/debugging)",
"type": "bool",
"default": "false"
},
{
"id": "track_usage",
"label": "Collect anonymous usage statistics",
"type": "bool",
"default": "true"
}
]
-51
View File
@@ -1,51 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>English</string>
<key>CFBundleIdentifier</key>
<string>com.plexapp.agents.subzero</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleShortVersionString</key>
<string>2.0.0</string>
<key>CFBundleSignature</key>
<string>????</string>
<key>CFBundleVersion</key>
<string>2.0.0.0</string>
<key>PlexFrameworkVersion</key>
<string>2</string>
<key>PlexPluginClass</key>
<string>Agent</string>
<key>PlexPluginMode</key>
<string>Daemon</string>
<key>PlexPluginConsoleLogging</key>
<string>0</string>
<key>PlexPluginDevMode</key>
<string>1</string>
<key>PlexPluginCodePolicy</key>
<!-- this allows channels to access some python methods which are otherwise blocked, as well as import external code libraries, and interact with the PMS HTTP API -->
<string>Elevated</string>
<key>PlexAgentAttributionText</key>
<string>&lt;div style=&quot;white-space: pre;&quot;&gt;&lt;img src=&quot;https://raw.githubusercontent.com/pannal/Sub-Zero.bundle/master/Contents/Resources/subzero.gif&quot; /&gt;
&lt;h1&gt;Sub-Zero for Plex&lt;/h1&gt;&lt;i&gt;Subtitles done right&lt;/i&gt;
Version 2.0.0.0 DEV #7
Originally based on @bramwalet's awesome &lt;a href=&quot;https://github.com/bramwalet/Subliminal.bundle&quot;&gt;Subliminal.bundle&lt;/a&gt;
If you like this, buy me a beer: &lt;a href=&quot;https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&amp;hosted_button_id=G9VKR2B8PMNKG&quot; target=&quot;_blank&quot; title=&quot;donate&quot;&gt;&lt;img src=&quot;https://www.paypalobjects.com/en_US/i/btn/btn_donate_LG.gif&quot; alt=&quot;donate&quot; title=&quot;donate&quot; /&gt;&lt;/a&gt;
&lt;strong&gt;Need help?&lt;/strong&gt;
Wiki: &lt;a href=&quot;http://v.ht/szwiki&quot;&gt;http://v.ht/szwiki&lt;/a&gt;
Score info: &lt;a href=&quot;http://v.ht/szscores&quot;&gt;http://v.ht/szscores&lt;/a&gt;
Plex thread: &lt;a href=&quot;https://forums.plex.tv/discussion/186575&quot;>https://forums.plex.tv/discussion/186575&lt;/a&gt;
Github: &lt;a href=&quot;https://github.com/pannal/Sub-Zero.bundle&quot;&gt;https://github.com/pannal/Sub-Zero&lt;/a&gt;
panni, 2017
&lt;/div&gt;
</string>
</dict>
</plist>
@@ -1,16 +0,0 @@
try:
import ast
from _markerlib.markers import default_environment, compile, interpret
except ImportError:
if 'ast' in globals():
raise
def default_environment():
return {}
def compile(marker):
def marker_fn(environment=None, override=None):
# 'empty markers are True' heuristic won't install extra deps.
return not marker.strip()
marker_fn.__doc__ = marker
return marker_fn
def interpret(marker, environment=None, override=None):
return compile(marker)()
@@ -1,119 +0,0 @@
# -*- coding: utf-8 -*-
"""Interpret PEP 345 environment markers.
EXPR [in|==|!=|not in] EXPR [or|and] ...
where EXPR belongs to any of those:
python_version = '%s.%s' % (sys.version_info[0], sys.version_info[1])
python_full_version = sys.version.split()[0]
os.name = os.name
sys.platform = sys.platform
platform.version = platform.version()
platform.machine = platform.machine()
platform.python_implementation = platform.python_implementation()
a free string, like '2.6', or 'win32'
"""
__all__ = ['default_environment', 'compile', 'interpret']
import ast
import os
import platform
import sys
import weakref
_builtin_compile = compile
try:
from platform import python_implementation
except ImportError:
if os.name == "java":
# Jython 2.5 has ast module, but not platform.python_implementation() function.
def python_implementation():
return "Jython"
else:
raise
# restricted set of variables
_VARS = {'sys.platform': sys.platform,
'python_version': '%s.%s' % sys.version_info[:2],
# FIXME parsing sys.platform is not reliable, but there is no other
# way to get e.g. 2.7.2+, and the PEP is defined with sys.version
'python_full_version': sys.version.split(' ', 1)[0],
'os.name': os.name,
'platform.version': platform.version(),
'platform.machine': platform.machine(),
'platform.python_implementation': python_implementation(),
'extra': None # wheel extension
}
for var in list(_VARS.keys()):
if '.' in var:
_VARS[var.replace('.', '_')] = _VARS[var]
def default_environment():
"""Return copy of default PEP 385 globals dictionary."""
return dict(_VARS)
class ASTWhitelist(ast.NodeTransformer):
def __init__(self, statement):
self.statement = statement # for error messages
ALLOWED = (ast.Compare, ast.BoolOp, ast.Attribute, ast.Name, ast.Load, ast.Str)
# Bool operations
ALLOWED += (ast.And, ast.Or)
# Comparison operations
ALLOWED += (ast.Eq, ast.Gt, ast.GtE, ast.In, ast.Is, ast.IsNot, ast.Lt, ast.LtE, ast.NotEq, ast.NotIn)
def visit(self, node):
"""Ensure statement only contains allowed nodes."""
if not isinstance(node, self.ALLOWED):
raise SyntaxError('Not allowed in environment markers.\n%s\n%s' %
(self.statement,
(' ' * node.col_offset) + '^'))
return ast.NodeTransformer.visit(self, node)
def visit_Attribute(self, node):
"""Flatten one level of attribute access."""
new_node = ast.Name("%s.%s" % (node.value.id, node.attr), node.ctx)
return ast.copy_location(new_node, node)
def parse_marker(marker):
tree = ast.parse(marker, mode='eval')
new_tree = ASTWhitelist(marker).generic_visit(tree)
return new_tree
def compile_marker(parsed_marker):
return _builtin_compile(parsed_marker, '<environment marker>', 'eval',
dont_inherit=True)
_cache = weakref.WeakValueDictionary()
def compile(marker):
"""Return compiled marker as a function accepting an environment dict."""
try:
return _cache[marker]
except KeyError:
pass
if not marker.strip():
def marker_fn(environment=None, override=None):
""""""
return True
else:
compiled_marker = compile_marker(parse_marker(marker))
def marker_fn(environment=None, override=None):
"""override updates environment"""
if override is None:
override = {}
if environment is None:
environment = default_environment()
environment.update(override)
return eval(compiled_marker, environment)
marker_fn.__doc__ = marker
_cache[marker] = marker_fn
return _cache[marker]
def interpret(marker, environment=None):
return compile(marker)(environment)
-552
View File
@@ -1,552 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright (c) 2005-2010 ActiveState Software Inc.
# Copyright (c) 2013 Eddy Petrișor
"""Utilities for determining application-specific dirs.
See <http://github.com/ActiveState/appdirs> for details and usage.
"""
# Dev Notes:
# - MSDN on where to store app data files:
# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120
# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html
# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html
__version_info__ = (1, 4, 0)
__version__ = '.'.join(map(str, __version_info__))
import sys
import os
PY3 = sys.version_info[0] == 3
if PY3:
unicode = str
if sys.platform.startswith('java'):
import platform
os_name = platform.java_ver()[3][0]
if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc.
system = 'win32'
elif os_name.startswith('Mac'): # "Mac OS X", etc.
system = 'darwin'
else: # "Linux", "SunOS", "FreeBSD", etc.
# Setting this to "linux2" is not ideal, but only Windows or Mac
# are actually checked for and the rest of the module expects
# *sys.platform* style strings.
system = 'linux2'
else:
system = sys.platform
def user_data_dir(appname=None, appauthor=None, version=None, roaming=False):
r"""Return full path to the user-specific data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"roaming" (boolean, default False) can be set True to use the Windows
roaming appdata directory. That means that for users on a Windows
network setup for roaming profiles, this user data will be
sync'd on login. See
<http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
for a discussion of issues.
Typical user data directories are:
Mac OS X: ~/Library/Application Support/<AppName>
Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined
Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName>
Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>
Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>
Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName>
For Unix, we follow the XDG spec and support $XDG_DATA_HOME.
That means, by default "~/.local/share/<AppName>".
"""
if system == "win32":
if appauthor is None:
appauthor = appname
const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA"
path = os.path.normpath(_get_win_folder(const))
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
elif system == 'darwin':
path = os.path.expanduser('~/Library/Application Support/')
if appname:
path = os.path.join(path, appname)
else:
path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share"))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def site_data_dir(appname=None, appauthor=None, version=None, multipath=False):
"""Return full path to the user-shared data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"multipath" is an optional parameter only applicable to *nix
which indicates that the entire list of data dirs should be
returned. By default, the first item from XDG_DATA_DIRS is
returned, or '/usr/local/share/<AppName>',
if XDG_DATA_DIRS is not set
Typical user data directories are:
Mac OS X: /Library/Application Support/<AppName>
Unix: /usr/local/share/<AppName> or /usr/share/<AppName>
Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName>
Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7.
For Unix, this is using the $XDG_DATA_DIRS[0] default.
WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
"""
if system == "win32":
if appauthor is None:
appauthor = appname
path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA"))
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
elif system == 'darwin':
path = os.path.expanduser('/Library/Application Support')
if appname:
path = os.path.join(path, appname)
else:
# XDG default for $XDG_DATA_DIRS
# only first, if multipath is False
path = os.getenv('XDG_DATA_DIRS',
os.pathsep.join(['/usr/local/share', '/usr/share']))
pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)]
if appname:
if version:
appname = os.path.join(appname, version)
pathlist = [os.sep.join([x, appname]) for x in pathlist]
if multipath:
path = os.pathsep.join(pathlist)
else:
path = pathlist[0]
return path
if appname and version:
path = os.path.join(path, version)
return path
def user_config_dir(appname=None, appauthor=None, version=None, roaming=False):
r"""Return full path to the user-specific config dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"roaming" (boolean, default False) can be set True to use the Windows
roaming appdata directory. That means that for users on a Windows
network setup for roaming profiles, this user data will be
sync'd on login. See
<http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
for a discussion of issues.
Typical user data directories are:
Mac OS X: same as user_data_dir
Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined
Win *: same as user_data_dir
For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME.
That means, by deafult "~/.config/<AppName>".
"""
if system in ["win32", "darwin"]:
path = user_data_dir(appname, appauthor, None, roaming)
else:
path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config"))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def site_config_dir(appname=None, appauthor=None, version=None, multipath=False):
"""Return full path to the user-shared data dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"multipath" is an optional parameter only applicable to *nix
which indicates that the entire list of config dirs should be
returned. By default, the first item from XDG_CONFIG_DIRS is
returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set
Typical user data directories are:
Mac OS X: same as site_data_dir
Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in
$XDG_CONFIG_DIRS
Win *: same as site_data_dir
Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False
WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
"""
if system in ["win32", "darwin"]:
path = site_data_dir(appname, appauthor)
if appname and version:
path = os.path.join(path, version)
else:
# XDG default for $XDG_CONFIG_DIRS
# only first, if multipath is False
path = os.getenv('XDG_CONFIG_DIRS', '/etc/xdg')
pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)]
if appname:
if version:
appname = os.path.join(appname, version)
pathlist = [os.sep.join([x, appname]) for x in pathlist]
if multipath:
path = os.pathsep.join(pathlist)
else:
path = pathlist[0]
return path
def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True):
r"""Return full path to the user-specific cache dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"opinion" (boolean) can be False to disable the appending of
"Cache" to the base app data dir for Windows. See
discussion below.
Typical user cache directories are:
Mac OS X: ~/Library/Caches/<AppName>
Unix: ~/.cache/<AppName> (XDG default)
Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache
Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache
On Windows the only suggestion in the MSDN docs is that local settings go in
the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming
app data dir (the default returned by `user_data_dir` above). Apps typically
put cache data somewhere *under* the given dir here. Some examples:
...\Mozilla\Firefox\Profiles\<ProfileName>\Cache
...\Acme\SuperApp\Cache\1.0
OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value.
This can be disabled with the `opinion=False` option.
"""
if system == "win32":
if appauthor is None:
appauthor = appname
path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA"))
if appname:
if appauthor is not False:
path = os.path.join(path, appauthor, appname)
else:
path = os.path.join(path, appname)
if opinion:
path = os.path.join(path, "Cache")
elif system == 'darwin':
path = os.path.expanduser('~/Library/Caches')
if appname:
path = os.path.join(path, appname)
else:
path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache'))
if appname:
path = os.path.join(path, appname)
if appname and version:
path = os.path.join(path, version)
return path
def user_log_dir(appname=None, appauthor=None, version=None, opinion=True):
r"""Return full path to the user-specific log dir for this application.
"appname" is the name of application.
If None, just the system directory is returned.
"appauthor" (only used on Windows) is the name of the
appauthor or distributing body for this application. Typically
it is the owning company name. This falls back to appname. You may
pass False to disable it.
"version" is an optional version path element to append to the
path. You might want to use this if you want multiple versions
of your app to be able to run independently. If used, this
would typically be "<major>.<minor>".
Only applied when appname is present.
"opinion" (boolean) can be False to disable the appending of
"Logs" to the base app data dir for Windows, and "log" to the
base cache dir for Unix. See discussion below.
Typical user cache directories are:
Mac OS X: ~/Library/Logs/<AppName>
Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined
Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs
Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs
On Windows the only suggestion in the MSDN docs is that local settings
go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in
examples of what some windows apps use for a logs dir.)
OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA`
value for Windows and appends "log" to the user cache dir for Unix.
This can be disabled with the `opinion=False` option.
"""
if system == "darwin":
path = os.path.join(
os.path.expanduser('~/Library/Logs'),
appname)
elif system == "win32":
path = user_data_dir(appname, appauthor, version)
version = False
if opinion:
path = os.path.join(path, "Logs")
else:
path = user_cache_dir(appname, appauthor, version)
version = False
if opinion:
path = os.path.join(path, "log")
if appname and version:
path = os.path.join(path, version)
return path
class AppDirs(object):
"""Convenience wrapper for getting application dirs."""
def __init__(self, appname, appauthor=None, version=None, roaming=False,
multipath=False):
self.appname = appname
self.appauthor = appauthor
self.version = version
self.roaming = roaming
self.multipath = multipath
@property
def user_data_dir(self):
return user_data_dir(self.appname, self.appauthor,
version=self.version, roaming=self.roaming)
@property
def site_data_dir(self):
return site_data_dir(self.appname, self.appauthor,
version=self.version, multipath=self.multipath)
@property
def user_config_dir(self):
return user_config_dir(self.appname, self.appauthor,
version=self.version, roaming=self.roaming)
@property
def site_config_dir(self):
return site_config_dir(self.appname, self.appauthor,
version=self.version, multipath=self.multipath)
@property
def user_cache_dir(self):
return user_cache_dir(self.appname, self.appauthor,
version=self.version)
@property
def user_log_dir(self):
return user_log_dir(self.appname, self.appauthor,
version=self.version)
#---- internal support stuff
def _get_win_folder_from_registry(csidl_name):
"""This is a fallback technique at best. I'm not sure if using the
registry for this guarantees us the correct answer for all CSIDL_*
names.
"""
import _winreg
shell_folder_name = {
"CSIDL_APPDATA": "AppData",
"CSIDL_COMMON_APPDATA": "Common AppData",
"CSIDL_LOCAL_APPDATA": "Local AppData",
}[csidl_name]
key = _winreg.OpenKey(
_winreg.HKEY_CURRENT_USER,
r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders"
)
dir, type = _winreg.QueryValueEx(key, shell_folder_name)
return dir
def _get_win_folder_with_pywin32(csidl_name):
from win32com.shell import shellcon, shell
dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0)
# Try to make this a unicode path because SHGetFolderPath does
# not return unicode strings when there is unicode data in the
# path.
try:
dir = unicode(dir)
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in dir:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
try:
import win32api
dir = win32api.GetShortPathName(dir)
except ImportError:
pass
except UnicodeError:
pass
return dir
def _get_win_folder_with_ctypes(csidl_name):
import ctypes
csidl_const = {
"CSIDL_APPDATA": 26,
"CSIDL_COMMON_APPDATA": 35,
"CSIDL_LOCAL_APPDATA": 28,
}[csidl_name]
buf = ctypes.create_unicode_buffer(1024)
ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf)
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in buf:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
buf2 = ctypes.create_unicode_buffer(1024)
if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024):
buf = buf2
return buf.value
def _get_win_folder_with_jna(csidl_name):
import array
from com.sun import jna
from com.sun.jna.platform import win32
buf_size = win32.WinDef.MAX_PATH * 2
buf = array.zeros('c', buf_size)
shell = win32.Shell32.INSTANCE
shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf)
dir = jna.Native.toString(buf.tostring()).rstrip("\0")
# Downgrade to short path name if have highbit chars. See
# <http://bugs.activestate.com/show_bug.cgi?id=85099>.
has_high_char = False
for c in dir:
if ord(c) > 255:
has_high_char = True
break
if has_high_char:
buf = array.zeros('c', buf_size)
kernel = win32.Kernel32.INSTANCE
if kernal.GetShortPathName(dir, buf, buf_size):
dir = jna.Native.toString(buf.tostring()).rstrip("\0")
return dir
if system == "win32":
try:
import win32com.shell
_get_win_folder = _get_win_folder_with_pywin32
except ImportError:
try:
from ctypes import windll
_get_win_folder = _get_win_folder_with_ctypes
except ImportError:
try:
import com.sun.jna
_get_win_folder = _get_win_folder_with_jna
except ImportError:
_get_win_folder = _get_win_folder_from_registry
#---- self test code
if __name__ == "__main__":
appname = "MyApp"
appauthor = "MyCompany"
props = ("user_data_dir", "site_data_dir",
"user_config_dir", "site_config_dir",
"user_cache_dir", "user_log_dir")
print("-- app dirs (with optional 'version')")
dirs = AppDirs(appname, appauthor, version="1.0")
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (without optional 'version')")
dirs = AppDirs(appname, appauthor)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (without optional 'appauthor')")
dirs = AppDirs(appname)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
print("\n-- app dirs (with disabled 'appauthor')")
dirs = AppDirs(appname, appauthor=False)
for prop in props:
print("%s: %s" % (prop, getattr(dirs, prop)))
File diff suppressed because it is too large Load Diff
@@ -1,61 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from asio.file import SEEK_ORIGIN_CURRENT
from asio.file_opener import FileOpener
from asio.open_parameters import OpenParameters
from asio.interfaces.posix import PosixInterface
from asio.interfaces.windows import WindowsInterface
import os
class ASIO(object):
platform_handler = None
@classmethod
def get_handler(cls):
if cls.platform_handler:
return cls.platform_handler
if os.name == 'nt':
cls.platform_handler = WindowsInterface
elif os.name == 'posix':
cls.platform_handler = PosixInterface
else:
raise NotImplementedError()
return cls.platform_handler
@classmethod
def open(cls, file_path, opener=True, parameters=None):
"""Open file
:type file_path: str
:param opener: Use FileOpener, for use with the 'with' statement
:type opener: bool
:rtype: asio.file.File
"""
if not parameters:
parameters = OpenParameters()
if opener:
return FileOpener(file_path, parameters)
return ASIO.get_handler().open(
file_path,
parameters=parameters.handlers.get(ASIO.get_handler())
)
-92
View File
@@ -1,92 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from io import RawIOBase
import time
DEFAULT_BUFFER_SIZE = 4096
SEEK_ORIGIN_BEGIN = 0
SEEK_ORIGIN_CURRENT = 1
SEEK_ORIGIN_END = 2
class ReadTimeoutError(Exception):
pass
class File(RawIOBase):
platform_handler = None
def __init__(self, *args, **kwargs):
super(File, self).__init__(*args, **kwargs)
def get_handler(self):
"""
:rtype: asio.interfaces.base.Interface
"""
if not self.platform_handler:
raise ValueError()
return self.platform_handler
def get_size(self):
"""Get the current file size
:rtype: int
"""
return self.get_handler().get_size(self)
def get_path(self):
"""Get the path of this file
:rtype: str
"""
return self.get_handler().get_path(self)
def seek(self, offset, origin):
"""Sets a reference point of a file to the given value.
:param offset: The point relative to origin to move
:type offset: int
:param origin: Reference point to seek (SEEK_ORIGIN_BEGIN, SEEK_ORIGIN_CURRENT, SEEK_ORIGIN_END)
:type origin: int
"""
return self.get_handler().seek(self, offset, origin)
def read(self, n=-1):
"""Read up to n bytes from the object and return them.
:type n: int
:rtype: str
"""
return self.get_handler().read(self, n)
def readinto(self, b):
"""Read up to len(b) bytes into bytearray b and return the number of bytes read."""
data = self.read(len(b))
if data is None:
return None
b[:len(data)] = data
return len(data)
def close(self):
"""Close the file handle"""
return self.get_handler().close(self)
def readable(self, *args, **kwargs):
return True
@@ -1,21 +0,0 @@
class FileOpener(object):
def __init__(self, file_path, parameters=None):
self.file_path = file_path
self.parameters = parameters
self.file = None
def __enter__(self):
self.file = ASIO.get_handler().open(
self.file_path,
self.parameters.handlers.get(ASIO.get_handler())
)
return self.file
def __exit__(self, exc_type, exc_val, exc_tb):
if not self.file:
return
self.file.close()
self.file = None
@@ -1,41 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from asio.file import DEFAULT_BUFFER_SIZE
class Interface(object):
@classmethod
def open(cls, file_path, parameters=None):
raise NotImplementedError()
@classmethod
def get_size(cls, fp):
raise NotImplementedError()
@classmethod
def get_path(cls, fp):
raise NotImplementedError()
@classmethod
def seek(cls, fp, pointer, distance):
raise NotImplementedError()
@classmethod
def read(cls, fp, n=DEFAULT_BUFFER_SIZE):
raise NotImplementedError()
@classmethod
def close(cls, fp):
raise NotImplementedError()
@@ -1,123 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from asio.file import File, DEFAULT_BUFFER_SIZE
from asio.interfaces.base import Interface
import sys
import os
if os.name == 'posix':
import select
# fcntl is only required on darwin
if sys.platform == 'darwin':
import fcntl
F_GETPATH = 50
class PosixInterface(Interface):
@classmethod
def open(cls, file_path, parameters=None):
"""
:type file_path: str
:rtype: asio.interfaces.posix.PosixFile
"""
if not parameters:
parameters = {}
if not parameters.get('mode'):
parameters.pop('mode')
if not parameters.get('buffering'):
parameters.pop('buffering')
fd = os.open(file_path, os.O_RDONLY | os.O_NONBLOCK)
return PosixFile(fd)
@classmethod
def get_size(cls, fp):
"""
:type fp: asio.interfaces.posix.PosixFile
:rtype: int
"""
return os.fstat(fp.fd).st_size
@classmethod
def get_path(cls, fp):
"""
:type fp: asio.interfaces.posix.PosixFile
:rtype: int
"""
# readlink /dev/fd fails on darwin, so instead use fcntl F_GETPATH
if sys.platform == 'darwin':
return fcntl.fcntl(fp.fd, F_GETPATH, '\0' * 1024).rstrip('\0')
# Use /proc/self/fd if available
if os.path.lexists("/proc/self/fd/"):
return os.readlink("/proc/self/fd/%s" % fp.fd)
# Fallback to /dev/fd
if os.path.lexists("/dev/fd/"):
return os.readlink("/dev/fd/%s" % fp.fd)
raise NotImplementedError('Environment not supported (fdescfs not mounted?)')
@classmethod
def seek(cls, fp, offset, origin):
"""
:type fp: asio.interfaces.posix.PosixFile
:type offset: int
:type origin: int
"""
os.lseek(fp.fd, offset, origin)
@classmethod
def read(cls, fp, n=DEFAULT_BUFFER_SIZE):
"""
:type fp: asio.interfaces.posix.PosixFile
:type n: int
:rtype: str
"""
r, w, x = select.select([fp.fd], [], [], 5)
if r:
return os.read(fp.fd, n)
return None
@classmethod
def close(cls, fp):
"""
:type fp: asio.interfaces.posix.PosixFile
"""
os.close(fp.fd)
class PosixFile(File):
platform_handler = PosixInterface
def __init__(self, fd, *args, **kwargs):
"""
:type fd: asio.file.File
"""
super(PosixFile, self).__init__(*args, **kwargs)
self.fd = fd
def __str__(self):
return "<asio_posix.PosixFile file: %s>" % self.fd
@@ -1,201 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from asio.file import File, DEFAULT_BUFFER_SIZE
from asio.interfaces.base import Interface
import os
NULL = 0
if os.name == 'nt':
from asio.interfaces.windows.interop import WindowsInterop
class WindowsInterface(Interface):
@classmethod
def open(cls, file_path, parameters=None):
"""
:type file_path: str
:rtype: asio.interfaces.windows.WindowsFile
"""
if not parameters:
parameters = {}
return WindowsFile(WindowsInterop.create_file(
file_path,
parameters.get('desired_access', WindowsInterface.GenericAccess.READ),
parameters.get('share_mode', WindowsInterface.ShareMode.ALL),
parameters.get('creation_disposition', WindowsInterface.CreationDisposition.OPEN_EXISTING),
parameters.get('flags_and_attributes', NULL)
))
@classmethod
def get_size(cls, fp):
"""
:type fp: asio.interfaces.windows.WindowsFile
:rtype: int
"""
return WindowsInterop.get_file_size(fp.handle)
@classmethod
def get_path(cls, fp):
"""
:type fp: asio.interfaces.windows.WindowsFile
:rtype: str
"""
if not fp.file_map:
fp.file_map = WindowsInterop.create_file_mapping(fp.handle, WindowsInterface.Protection.READONLY)
if not fp.map_view:
fp.map_view = WindowsInterop.map_view_of_file(fp.file_map, WindowsInterface.FileMapAccess.READ, 1)
file_name = WindowsInterop.get_mapped_file_name(fp.map_view)
return file_name
@classmethod
def seek(cls, fp, offset, origin):
"""
:type fp: asio.interfaces.windows.WindowsFile
:type offset: int
:type origin: int
:rtype: int
"""
return WindowsInterop.set_file_pointer(
fp.handle,
offset,
origin
)
@classmethod
def read(cls, fp, n=DEFAULT_BUFFER_SIZE):
"""
:type fp: asio.interfaces.windows.WindowsFile
:type n: int
:rtype: str
"""
return WindowsInterop.read(fp.handle, n)
@classmethod
def read_into(cls, fp, b):
"""
:type fp: asio.interfaces.windows.WindowsFile
:type b: str
:rtype: int
"""
return WindowsInterop.read_into(fp.handle, b)
@classmethod
def close(cls, fp):
"""
:type fp: asio.interfaces.windows.WindowsFile
:rtype: bool
"""
if fp.map_view:
WindowsInterop.unmap_view_of_file(fp.map_view)
if fp.file_map:
WindowsInterop.close_handle(fp.file_map)
return bool(WindowsInterop.close_handle(fp.handle))
class GenericAccess(object):
READ = 0x80000000
WRITE = 0x40000000
EXECUTE = 0x20000000
ALL = 0x10000000
class ShareMode(object):
READ = 0x00000001
WRITE = 0x00000002
DELETE = 0x00000004
ALL = READ | WRITE | DELETE
class CreationDisposition(object):
CREATE_NEW = 1
CREATE_ALWAYS = 2
OPEN_EXISTING = 3
OPEN_ALWAYS = 4
TRUNCATE_EXISTING = 5
class Attribute(object):
READONLY = 0x00000001
HIDDEN = 0x00000002
SYSTEM = 0x00000004
DIRECTORY = 0x00000010
ARCHIVE = 0x00000020
DEVICE = 0x00000040
NORMAL = 0x00000080
TEMPORARY = 0x00000100
SPARSE_FILE = 0x00000200
REPARSE_POINT = 0x00000400
COMPRESSED = 0x00000800
OFFLINE = 0x00001000
NOT_CONTENT_INDEXED = 0x00002000
ENCRYPTED = 0x00004000
class Flag(object):
WRITE_THROUGH = 0x80000000
OVERLAPPED = 0x40000000
NO_BUFFERING = 0x20000000
RANDOM_ACCESS = 0x10000000
SEQUENTIAL_SCAN = 0x08000000
DELETE_ON_CLOSE = 0x04000000
BACKUP_SEMANTICS = 0x02000000
POSIX_SEMANTICS = 0x01000000
OPEN_REPARSE_POINT = 0x00200000
OPEN_NO_RECALL = 0x00100000
FIRST_PIPE_INSTANCE = 0x00080000
class Protection(object):
NOACCESS = 0x01
READONLY = 0x02
READWRITE = 0x04
WRITECOPY = 0x08
EXECUTE = 0x10
EXECUTE_READ = 0x20,
EXECUTE_READWRITE = 0x40
EXECUTE_WRITECOPY = 0x80
GUARD = 0x100
NOCACHE = 0x200
WRITECOMBINE = 0x400
class FileMapAccess(object):
COPY = 0x0001
WRITE = 0x0002
READ = 0x0004
ALL_ACCESS = 0x001f
EXECUTE = 0x0020
class WindowsFile(File):
platform_handler = WindowsInterface
def __init__(self, handle, *args, **kwargs):
super(WindowsFile, self).__init__(*args, **kwargs)
self.handle = handle
self.file_map = None
self.map_view = None
def readinto(self, b):
return self.get_handler().read_into(self, b)
def __str__(self):
return "<asio_windows.WindowsFile file: %s>" % self.handle
@@ -1,230 +0,0 @@
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from ctypes.wintypes import *
from ctypes import *
import logging
log = logging.getLogger(__name__)
CreateFileW = windll.kernel32.CreateFileW
CreateFileW.argtypes = (LPCWSTR, DWORD, DWORD, c_void_p, DWORD, DWORD, HANDLE)
CreateFileW.restype = HANDLE
ReadFile = windll.kernel32.ReadFile
ReadFile.argtypes = (HANDLE, c_void_p, DWORD, POINTER(DWORD), HANDLE)
ReadFile.restype = BOOL
NULL = 0
MAX_PATH = 260
DEFAULT_BUFFER_SIZE = 4096
LPSECURITY_ATTRIBUTES = c_void_p
class WindowsInterop(object):
ri_buffer = None
@classmethod
def create_file(cls, path, desired_access, share_mode, creation_disposition, flags_and_attributes):
h = CreateFileW(
path,
desired_access,
share_mode,
NULL,
creation_disposition,
flags_and_attributes,
NULL
)
error = GetLastError()
if error != 0:
raise Exception('[WindowsASIO.open] "%s"' % FormatError(error))
return h
@classmethod
def read(cls, handle, buf_size=DEFAULT_BUFFER_SIZE):
buf = create_string_buffer(buf_size)
bytes_read = c_ulong(0)
success = ReadFile(handle, buf, buf_size, byref(bytes_read), NULL)
error = GetLastError()
if error:
log.debug('read_file - error: (%s) "%s"', error, FormatError(error))
if not success and error:
raise Exception('[WindowsInterop.read_file] (%s) "%s"' % (error, FormatError(error)))
# Return if we have a valid buffer
if success and bytes_read.value:
return buf.value
return None
@classmethod
def read_into(cls, handle, b):
if cls.ri_buffer is None or len(cls.ri_buffer) < len(b):
cls.ri_buffer = create_string_buffer(len(b))
bytes_read = c_ulong(0)
success = ReadFile(handle, cls.ri_buffer, len(b), byref(bytes_read), NULL)
bytes_read = int(bytes_read.value)
b[:bytes_read] = cls.ri_buffer[:bytes_read]
error = GetLastError()
if not success and error:
raise Exception('[WindowsInterop.read_file] (%s) "%s"' % (error, FormatError(error)))
# Return if we have a valid buffer
if success and bytes_read:
return bytes_read
return None
@classmethod
def set_file_pointer(cls, handle, distance, method):
pos_high = DWORD(NULL)
result = windll.kernel32.SetFilePointer(
handle,
c_ulong(distance),
byref(pos_high),
DWORD(method)
)
if result == -1:
raise Exception('[WindowsASIO.seek] INVALID_SET_FILE_POINTER: "%s"' % FormatError(GetLastError()))
return result
@classmethod
def get_file_size(cls, handle):
return windll.kernel32.GetFileSize(
handle,
DWORD(NULL)
)
@classmethod
def close_handle(cls, handle):
return windll.kernel32.CloseHandle(handle)
@classmethod
def create_file_mapping(cls, handle, protect, maximum_size_high=0, maximum_size_low=1):
return HANDLE(windll.kernel32.CreateFileMappingW(
handle,
LPSECURITY_ATTRIBUTES(NULL),
DWORD(protect),
DWORD(maximum_size_high),
DWORD(maximum_size_low),
LPCSTR(NULL)
))
@classmethod
def map_view_of_file(cls, map_handle, desired_access, num_bytes, file_offset_high=0, file_offset_low=0):
return HANDLE(windll.kernel32.MapViewOfFile(
map_handle,
DWORD(desired_access),
DWORD(file_offset_high),
DWORD(file_offset_low),
num_bytes
))
@classmethod
def unmap_view_of_file(cls, view_handle):
return windll.kernel32.UnmapViewOfFile(view_handle)
@classmethod
def get_mapped_file_name(cls, view_handle, translate_device_name=True):
buf = create_string_buffer(MAX_PATH + 1)
result = windll.psapi.GetMappedFileNameW(
cls.get_current_process(),
view_handle,
buf,
MAX_PATH
)
# Raise exception on error
error = GetLastError()
if result == 0:
raise Exception(FormatError(error))
# Retrieve a clean file name (skipping over NUL bytes)
file_name = cls.clean_buffer_value(buf)
# If we are not translating the device name return here
if not translate_device_name:
return file_name
drives = cls.get_logical_drive_strings()
# Find the drive matching the file_name device name
translated = False
for drive in drives:
device_name = cls.query_dos_device(drive)
if file_name.startswith(device_name):
file_name = drive + file_name[len(device_name):]
translated = True
break
if not translated:
raise Exception('Unable to translate device name')
return file_name
@classmethod
def get_logical_drive_strings(cls, buf_size=512):
buf = create_string_buffer(buf_size)
result = windll.kernel32.GetLogicalDriveStringsW(buf_size, buf)
error = GetLastError()
if result == 0:
raise Exception(FormatError(error))
drive_strings = cls.clean_buffer_value(buf)
return [dr for dr in drive_strings.split('\\') if dr != '']
@classmethod
def query_dos_device(cls, drive, buf_size=MAX_PATH):
buf = create_string_buffer(buf_size)
result = windll.kernel32.QueryDosDeviceA(
drive,
buf,
buf_size
)
return cls.clean_buffer_value(buf)
@classmethod
def get_current_process(cls):
return HANDLE(windll.kernel32.GetCurrentProcess())
@classmethod
def clean_buffer_value(cls, buf):
value = ""
for ch in buf.raw:
if ord(ch) != 0:
value += ch
return value
@@ -1,47 +0,0 @@
from asio.interfaces.posix import PosixInterface
from asio.interfaces.windows import WindowsInterface
class OpenParameters(object):
def __init__(self):
self.handlers = {}
# Update handler_parameters with defaults
self.posix()
self.windows()
def posix(self, mode=None, buffering=None):
"""
:type mode: str
:type buffering: int
"""
self.handlers.update({PosixInterface: {
'mode': mode,
'buffering': buffering
}})
def windows(self, desired_access=WindowsInterface.GenericAccess.READ,
share_mode=WindowsInterface.ShareMode.ALL,
creation_disposition=WindowsInterface.CreationDisposition.OPEN_EXISTING,
flags_and_attributes=0):
"""
:param desired_access: WindowsInterface.DesiredAccess
:type desired_access: int
:param share_mode: WindowsInterface.ShareMode
:type share_mode: int
:param creation_disposition: WindowsInterface.CreationDisposition
:type creation_disposition: int
:param flags_and_attributes: WindowsInterface.Attribute, WindowsInterface.Flag
:type flags_and_attributes: int
"""
self.handlers.update({WindowsInterface: {
'desired_access': desired_access,
'share_mode': share_mode,
'creation_disposition': creation_disposition,
'flags_and_attributes': flags_and_attributes
}})
@@ -1,25 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
__title__ = 'babelfish'
__version__ = '0.5.5-dev'
__author__ = 'Antoine Bertin'
__license__ = 'BSD'
__copyright__ = 'Copyright 2015 the BabelFish authors'
import sys
if sys.version_info[0] >= 3:
basestr = str
else:
basestr = basestring
from .converters import (LanguageConverter, LanguageReverseConverter, LanguageEquivalenceConverter, CountryConverter,
CountryReverseConverter)
from .country import country_converters, COUNTRIES, COUNTRY_MATRIX, Country
from .exceptions import Error, LanguageConvertError, LanguageReverseError, CountryConvertError, CountryReverseError
from .language import language_converters, LANGUAGES, LANGUAGE_MATRIX, Language
from .script import SCRIPTS, SCRIPT_MATRIX, Script
@@ -1,287 +0,0 @@
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
import collections
from pkg_resources import iter_entry_points, EntryPoint
from ..exceptions import LanguageConvertError, LanguageReverseError
# from https://github.com/kennethreitz/requests/blob/master/requests/structures.py
class CaseInsensitiveDict(collections.MutableMapping):
"""A case-insensitive ``dict``-like object.
Implements all methods and operations of
``collections.MutableMapping`` as well as dict's ``copy``. Also
provides ``lower_items``.
All keys are expected to be strings. The structure remembers the
case of the last key to be set, and ``iter(instance)``,
``keys()``, ``items()``, ``iterkeys()``, and ``iteritems()``
will contain case-sensitive keys. However, querying and contains
testing is case insensitive:
cid = CaseInsensitiveDict()
cid['English'] = 'eng'
cid['ENGLISH'] == 'eng' # True
list(cid) == ['English'] # True
If the constructor, ``.update``, or equality comparison
operations are given keys that have equal ``.lower()``s, the
behavior is undefined.
"""
def __init__(self, data=None, **kwargs):
self._store = dict()
if data is None:
data = {}
self.update(data, **kwargs)
def __setitem__(self, key, value):
# Use the lowercased key for lookups, but store the actual
# key alongside the value.
self._store[key.lower()] = (key, value)
def __getitem__(self, key):
return self._store[key.lower()][1]
def __delitem__(self, key):
del self._store[key.lower()]
def __iter__(self):
return (casedkey for casedkey, mappedvalue in self._store.values())
def __len__(self):
return len(self._store)
def lower_items(self):
"""Like iteritems(), but with all lowercase keys."""
return (
(lowerkey, keyval[1])
for (lowerkey, keyval)
in self._store.items()
)
def __eq__(self, other):
if isinstance(other, collections.Mapping):
other = CaseInsensitiveDict(other)
else:
return NotImplemented
# Compare insensitively
return dict(self.lower_items()) == dict(other.lower_items())
# Copy is required
def copy(self):
return CaseInsensitiveDict(self._store.values())
def __repr__(self):
return '%s(%r)' % (self.__class__.__name__, dict(self.items()))
class LanguageConverter(object):
"""A :class:`LanguageConverter` supports converting an alpha3 language code with an
alpha2 country code and a script code into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha3, country=None, script=None):
"""Convert an alpha3 language code with an alpha2 country code and a script code
into a custom code
:param string alpha3: ISO-639-3 language code
:param country: ISO-3166 country code, if any
:type country: string or None
:param script: ISO-15924 script code, if any
:type script: string or None
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.LanguageConvertError`
"""
raise NotImplementedError
class LanguageReverseConverter(LanguageConverter):
"""A :class:`LanguageConverter` able to reverse a custom code into a alpha3
ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
"""
def reverse(self, code):
"""Reverse a custom code into alpha3, country and script code
:param string code: custom code to reverse
:return: the corresponding alpha3 ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
:rtype: tuple
:raise: :class:`~babelfish.exceptions.LanguageReverseError`
"""
raise NotImplementedError
class LanguageEquivalenceConverter(LanguageReverseConverter):
"""A :class:`LanguageEquivalenceConverter` is a utility class that allows you to easily define a
:class:`LanguageReverseConverter` by only specifying the dict from alpha3 to their corresponding symbols.
You must specify the dict of equivalence as a class variable named SYMBOLS.
If you also set the class variable CASE_SENSITIVE to ``True`` then the reverse conversion function will be
case-sensitive (it is case-insensitive by default).
Example::
class MyCodeConverter(babelfish.LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {'fra': 'mycode1', 'eng': 'mycode2'}
"""
CASE_SENSITIVE = False
def __init__(self):
self.codes = set()
self.to_symbol = {}
if self.CASE_SENSITIVE:
self.from_symbol = {}
else:
self.from_symbol = CaseInsensitiveDict()
for alpha3, symbol in self.SYMBOLS.items():
self.to_symbol[alpha3] = symbol
self.from_symbol[symbol] = (alpha3, None, None)
self.codes.add(symbol)
def convert(self, alpha3, country=None, script=None):
try:
return self.to_symbol[alpha3]
except KeyError:
raise LanguageConvertError(alpha3, country, script)
def reverse(self, code):
try:
return self.from_symbol[code]
except KeyError:
raise LanguageReverseError(code)
class CountryConverter(object):
"""A :class:`CountryConverter` supports converting an alpha2 country code
into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha2):
"""Convert an alpha2 country code into a custom code
:param string alpha2: ISO-3166-1 language code
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryConvertError`
"""
raise NotImplementedError
class CountryReverseConverter(CountryConverter):
"""A :class:`CountryConverter` able to reverse a custom code into a alpha2
ISO-3166-1 country code
"""
def reverse(self, code):
"""Reverse a custom code into alpha2 code
:param string code: custom code to reverse
:return: the corresponding alpha2 ISO-3166-1 country code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryReverseError`
"""
raise NotImplementedError
class ConverterManager(object):
"""Manager for babelfish converters behaving like a dict with lazy loading
Loading is done in this order:
* Entry point converters
* Registered converters
* Internal converters
.. attribute:: entry_point
The entry point where to look for converters
.. attribute:: internal_converters
Internal converters with entry point syntax
"""
entry_point = ''
internal_converters = []
def __init__(self):
#: Registered converters with entry point syntax
self.registered_converters = []
#: Loaded converters
self.converters = {}
def __getitem__(self, name):
"""Get a converter, lazy loading it if necessary"""
if name in self.converters:
return self.converters[name]
for ep in iter_entry_points(self.entry_point):
if ep.name == name:
self.converters[ep.name] = ep.load()()
return self.converters[ep.name]
for ep in (EntryPoint.parse(c) for c in self.registered_converters + self.internal_converters):
if ep.name == name:
# `require` argument of ep.load() is deprecated in newer versions of setuptools
if hasattr(ep, 'resolve'):
plugin = ep.resolve()
elif hasattr(ep, '_load'):
plugin = ep._load()
else:
plugin = ep.load(require=False)
self.converters[ep.name] = plugin()
return self.converters[ep.name]
raise KeyError(name)
def __setitem__(self, name, converter):
"""Load a converter"""
self.converters[name] = converter
def __delitem__(self, name):
"""Unload a converter"""
del self.converters[name]
def __iter__(self):
"""Iterator over loaded converters"""
return iter(self.converters)
def register(self, entry_point):
"""Register a converter
:param string entry_point: converter to register (entry point syntax)
:raise: ValueError if already registered
"""
if entry_point in self.registered_converters:
raise ValueError('Already registered')
self.registered_converters.insert(0, entry_point)
def unregister(self, entry_point):
"""Unregister a converter
:param string entry_point: converter to unregister (entry point syntax)
"""
self.registered_converters.remove(entry_point)
def __contains__(self, name):
return name in self.converters
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha2Converter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha2:
SYMBOLS[iso_language.alpha3] = iso_language.alpha2
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3BConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3b:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3b
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3TConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3t:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3t
@@ -1,31 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import CountryReverseConverter, CaseInsensitiveDict
from ..country import COUNTRY_MATRIX
from ..exceptions import CountryConvertError, CountryReverseError
class CountryNameConverter(CountryReverseConverter):
def __init__(self):
self.codes = set()
self.to_name = {}
self.from_name = CaseInsensitiveDict()
for country in COUNTRY_MATRIX:
self.codes.add(country.name)
self.to_name[country.alpha2] = country.name
self.from_name[country.name] = country.alpha2
def convert(self, alpha2):
if alpha2 not in self.to_name:
raise CountryConvertError(alpha2)
return self.to_name[alpha2]
def reverse(self, name):
if name not in self.from_name:
raise CountryReverseError(name)
return self.from_name[name]
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class NameConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = False
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.name:
SYMBOLS[iso_language.alpha3] = iso_language.name
@@ -1,36 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageReverseConverter, CaseInsensitiveDict
from ..exceptions import LanguageReverseError
from ..language import language_converters
class OpenSubtitlesConverter(LanguageReverseConverter):
def __init__(self):
self.alpha3b_converter = language_converters['alpha3b']
self.alpha2_converter = language_converters['alpha2']
self.to_opensubtitles = {('por', 'BR'): 'pob', ('gre', None): 'ell', ('srp', None): 'scc', ('srp', 'ME'): 'mne'}
self.from_opensubtitles = CaseInsensitiveDict({'pob': ('por', 'BR'), 'pb': ('por', 'BR'), 'ell': ('ell', None),
'scc': ('srp', None), 'mne': ('srp', 'ME')})
self.codes = (self.alpha2_converter.codes | self.alpha3b_converter.codes | set(['pob', 'pb', 'scc', 'mne']))
def convert(self, alpha3, country=None, script=None):
alpha3b = self.alpha3b_converter.convert(alpha3, country, script)
if (alpha3b, country) in self.to_opensubtitles:
return self.to_opensubtitles[(alpha3b, country)]
return alpha3b
def reverse(self, opensubtitles):
if opensubtitles in self.from_opensubtitles:
return self.from_opensubtitles[opensubtitles]
for conv in [self.alpha3b_converter, self.alpha2_converter]:
try:
return conv.reverse(opensubtitles)
except LanguageReverseError:
pass
raise LanguageReverseError(opensubtitles)
@@ -1,23 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class ScopeConverter(LanguageConverter):
FULLNAME = {'I': 'individual', 'M': 'macrolanguage', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.scope
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)
@@ -1,23 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class LanguageTypeConverter(LanguageConverter):
FULLNAME = {'A': 'ancient', 'C': 'constructed', 'E': 'extinct', 'H': 'historical', 'L': 'living', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.type
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)
@@ -1,104 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
from pkg_resources import resource_stream # @UnresolvedImport
from .converters import ConverterManager
from . import basestr
COUNTRIES = {}
COUNTRY_MATRIX = []
#: The namedtuple used in the :data:`COUNTRY_MATRIX`
IsoCountry = namedtuple('IsoCountry', ['name', 'alpha2'])
f = resource_stream('babelfish', 'data/iso-3166-1.txt')
f.readline()
for l in f:
iso_country = IsoCountry(*l.decode('utf-8').strip().split(';'))
COUNTRIES[iso_country.alpha2] = iso_country.name
COUNTRY_MATRIX.append(iso_country)
f.close()
class CountryConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for country converters"""
entry_point = 'babelfish.country_converters'
internal_converters = ['name = babelfish.converters.countryname:CountryNameConverter']
country_converters = CountryConverterManager()
class CountryMeta(type):
"""The :class:`Country` metaclass
Dynamically redirect :meth:`Country.frommycode` to :meth:`Country.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Country(CountryMeta(str('CountryBase'), (object,), {})):
"""A country on Earth
A country is represented by a 2-letter code from the ISO-3166 standard
:param string country: 2-letter ISO-3166 country code
"""
def __init__(self, country):
if country not in COUNTRIES:
raise ValueError('%r is not a valid country' % country)
#: ISO-3166 2-letter country code
self.alpha2 = country
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Country` by its `code` using `converter` to
:meth:`~babelfish.converters.CountryReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.CountryReverseConverter` to use
:return: the corresponding :class:`Country` instance
:rtype: :class:`Country`
"""
return cls(country_converters[converter].reverse(code))
def __getstate__(self):
return self.alpha2
def __setstate__(self, state):
self.alpha2 = state
def __getattr__(self, name):
return country_converters[name].convert(self.alpha2)
def __hash__(self):
return hash(self.alpha2)
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Country):
return False
return self.alpha2 == other.alpha2
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Country [%s]>' % self
def __str__(self):
return self.alpha2
@@ -1,45 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
import os.path
import tempfile
import zipfile
import requests
DATA_DIR = os.path.dirname(__file__)
# iso-3166-1.txt
print('Downloading ISO-3166-1 standard (ISO country codes)...')
with open(os.path.join(DATA_DIR, 'iso-3166-1.txt'), 'w') as f:
r = requests.get('http://www.iso.org/iso/home/standards/country_codes/country_names_and_code_elements_txt.htm')
f.write(r.content.strip())
# iso-639-3.tab
print('Downloading ISO-639-3 standard (ISO language codes)...')
with tempfile.TemporaryFile() as f:
r = requests.get('http://www-01.sil.org/iso639-3/iso-639-3_Code_Tables_20130531.zip')
f.write(r.content)
with zipfile.ZipFile(f) as z:
z.extract('iso-639-3.tab', DATA_DIR)
# iso-15924
print('Downloading ISO-15924 standard (ISO script codes)...')
with tempfile.TemporaryFile() as f:
r = requests.get('http://www.unicode.org/iso15924/iso15924.txt.zip')
f.write(r.content)
with zipfile.ZipFile(f) as z:
z.extract('iso15924-utf8-20131012.txt', DATA_DIR)
# opensubtitles supported languages
print('Downloading OpenSubtitles supported languages...')
with open(os.path.join(DATA_DIR, 'opensubtitles_languages.txt'), 'w') as f:
r = requests.get('http://www.opensubtitles.org/addons/export_languages.php')
f.write(r.content)
print('Done!')
@@ -1,250 +0,0 @@
Country Name;ISO 3166-1-alpha-2 code
AFGHANISTAN;AF
ÅLAND ISLANDS;AX
ALBANIA;AL
ALGERIA;DZ
AMERICAN SAMOA;AS
ANDORRA;AD
ANGOLA;AO
ANGUILLA;AI
ANTARCTICA;AQ
ANTIGUA AND BARBUDA;AG
ARGENTINA;AR
ARMENIA;AM
ARUBA;AW
AUSTRALIA;AU
AUSTRIA;AT
AZERBAIJAN;AZ
BAHAMAS;BS
BAHRAIN;BH
BANGLADESH;BD
BARBADOS;BB
BELARUS;BY
BELGIUM;BE
BELIZE;BZ
BENIN;BJ
BERMUDA;BM
BHUTAN;BT
BOLIVIA, PLURINATIONAL STATE OF;BO
BONAIRE, SINT EUSTATIUS AND SABA;BQ
BOSNIA AND HERZEGOVINA;BA
BOTSWANA;BW
BOUVET ISLAND;BV
BRAZIL;BR
BRITISH INDIAN OCEAN TERRITORY;IO
BRUNEI DARUSSALAM;BN
BULGARIA;BG
BURKINA FASO;BF
BURUNDI;BI
CAMBODIA;KH
CAMEROON;CM
CANADA;CA
CAPE VERDE;CV
CAYMAN ISLANDS;KY
CENTRAL AFRICAN REPUBLIC;CF
CHAD;TD
CHILE;CL
CHINA;CN
CHRISTMAS ISLAND;CX
COCOS (KEELING) ISLANDS;CC
COLOMBIA;CO
COMOROS;KM
CONGO;CG
CONGO, THE DEMOCRATIC REPUBLIC OF THE;CD
COOK ISLANDS;CK
COSTA RICA;CR
CÔTE D'IVOIRE;CI
CROATIA;HR
CUBA;CU
CURAÇAO;CW
CYPRUS;CY
CZECH REPUBLIC;CZ
DENMARK;DK
DJIBOUTI;DJ
DOMINICA;DM
DOMINICAN REPUBLIC;DO
ECUADOR;EC
EGYPT;EG
EL SALVADOR;SV
EQUATORIAL GUINEA;GQ
ERITREA;ER
ESTONIA;EE
ETHIOPIA;ET
FALKLAND ISLANDS (MALVINAS);FK
FAROE ISLANDS;FO
FIJI;FJ
FINLAND;FI
FRANCE;FR
FRENCH GUIANA;GF
FRENCH POLYNESIA;PF
FRENCH SOUTHERN TERRITORIES;TF
GABON;GA
GAMBIA;GM
GEORGIA;GE
GERMANY;DE
GHANA;GH
GIBRALTAR;GI
GREECE;GR
GREENLAND;GL
GRENADA;GD
GUADELOUPE;GP
GUAM;GU
GUATEMALA;GT
GUERNSEY;GG
GUINEA;GN
GUINEA-BISSAU;GW
GUYANA;GY
HAITI;HT
HEARD ISLAND AND MCDONALD ISLANDS;HM
HOLY SEE (VATICAN CITY STATE);VA
HONDURAS;HN
HONG KONG;HK
HUNGARY;HU
ICELAND;IS
INDIA;IN
INDONESIA;ID
IRAN, ISLAMIC REPUBLIC OF;IR
IRAQ;IQ
IRELAND;IE
ISLE OF MAN;IM
ISRAEL;IL
ITALY;IT
JAMAICA;JM
JAPAN;JP
JERSEY;JE
JORDAN;JO
KAZAKHSTAN;KZ
KENYA;KE
KIRIBATI;KI
KOREA, DEMOCRATIC PEOPLE'S REPUBLIC OF;KP
KOREA, REPUBLIC OF;KR
KUWAIT;KW
KYRGYZSTAN;KG
LAO PEOPLE'S DEMOCRATIC REPUBLIC;LA
LATVIA;LV
LEBANON;LB
LESOTHO;LS
LIBERIA;LR
LIBYA;LY
LIECHTENSTEIN;LI
LITHUANIA;LT
LUXEMBOURG;LU
MACAO;MO
MACEDONIA, THE FORMER YUGOSLAV REPUBLIC OF;MK
MADAGASCAR;MG
MALAWI;MW
MALAYSIA;MY
MALDIVES;MV
MALI;ML
MALTA;MT
MARSHALL ISLANDS;MH
MARTINIQUE;MQ
MAURITANIA;MR
MAURITIUS;MU
MAYOTTE;YT
MEXICO;MX
MICRONESIA, FEDERATED STATES OF;FM
MOLDOVA, REPUBLIC OF;MD
MONACO;MC
MONGOLIA;MN
MONTENEGRO;ME
MONTSERRAT;MS
MOROCCO;MA
MOZAMBIQUE;MZ
MYANMAR;MM
NAMIBIA;NA
NAURU;NR
NEPAL;NP
NETHERLANDS;NL
NEW CALEDONIA;NC
NEW ZEALAND;NZ
NICARAGUA;NI
NIGER;NE
NIGERIA;NG
NIUE;NU
NORFOLK ISLAND;NF
NORTHERN MARIANA ISLANDS;MP
NORWAY;NO
OMAN;OM
PAKISTAN;PK
PALAU;PW
PALESTINE, STATE OF;PS
PANAMA;PA
PAPUA NEW GUINEA;PG
PARAGUAY;PY
PERU;PE
PHILIPPINES;PH
PITCAIRN;PN
POLAND;PL
PORTUGAL;PT
PUERTO RICO;PR
QATAR;QA
RÉUNION;RE
ROMANIA;RO
RUSSIAN FEDERATION;RU
RWANDA;RW
SAINT BARTHÉLEMY;BL
SAINT HELENA, ASCENSION AND TRISTAN DA CUNHA;SH
SAINT KITTS AND NEVIS;KN
SAINT LUCIA;LC
SAINT MARTIN (FRENCH PART);MF
SAINT PIERRE AND MIQUELON;PM
SAINT VINCENT AND THE GRENADINES;VC
SAMOA;WS
SAN MARINO;SM
SAO TOME AND PRINCIPE;ST
SAUDI ARABIA;SA
SENEGAL;SN
SERBIA;RS
SEYCHELLES;SC
SIERRA LEONE;SL
SINGAPORE;SG
SINT MAARTEN (DUTCH PART);SX
SLOVAKIA;SK
SLOVENIA;SI
SOLOMON ISLANDS;SB
SOMALIA;SO
SOUTH AFRICA;ZA
SOUTH GEORGIA AND THE SOUTH SANDWICH ISLANDS;GS
SOUTH SUDAN;SS
SPAIN;ES
SRI LANKA;LK
SUDAN;SD
SURINAME;SR
SVALBARD AND JAN MAYEN;SJ
SWAZILAND;SZ
SWEDEN;SE
SWITZERLAND;CH
SYRIAN ARAB REPUBLIC;SY
TAIWAN, PROVINCE OF CHINA;TW
TAJIKISTAN;TJ
TANZANIA, UNITED REPUBLIC OF;TZ
THAILAND;TH
TIMOR-LESTE;TL
TOGO;TG
TOKELAU;TK
TONGA;TO
TRINIDAD AND TOBAGO;TT
TUNISIA;TN
TURKEY;TR
TURKMENISTAN;TM
TURKS AND CAICOS ISLANDS;TC
TUVALU;TV
UGANDA;UG
UKRAINE;UA
UNITED ARAB EMIRATES;AE
UNITED KINGDOM;GB
UNITED STATES;US
UNITED STATES MINOR OUTLYING ISLANDS;UM
URUGUAY;UY
UZBEKISTAN;UZ
VANUATU;VU
VENEZUELA, BOLIVARIAN REPUBLIC OF;VE
VIET NAM;VN
VIRGIN ISLANDS, BRITISH;VG
VIRGIN ISLANDS, U.S.;VI
WALLIS AND FUTUNA;WF
WESTERN SAHARA;EH
YEMEN;YE
ZAMBIA;ZM
ZIMBABWE;ZW
File diff suppressed because it is too large Load Diff
@@ -1,176 +0,0 @@
#
# ISO 15924 - Codes for the representation of names of scripts
# Codes pour la représentation des noms d’écritures
# Format:
# Code;N°;English Name;Nom français;PVA;Date
#
Afak;439;Afaka;afaka;;2010-12-21
Aghb;239;Caucasian Albanian;aghbanien;;2012-10-16
Ahom;338;Ahom, Tai Ahom;âhom;;2012-11-01
Arab;160;Arabic;arabe;Arabic;2004-05-01
Armi;124;Imperial Aramaic;araméen impérial;Imperial_Aramaic;2009-06-01
Armn;230;Armenian;arménien;Armenian;2004-05-01
Avst;134;Avestan;avestique;Avestan;2009-06-01
Bali;360;Balinese;balinais;Balinese;2006-10-10
Bamu;435;Bamum;bamoum;Bamum;2009-06-01
Bass;259;Bassa Vah;bassa;;2010-03-26
Batk;365;Batak;batik;Batak;2010-07-23
Beng;325;Bengali;bengalî;Bengali;2004-05-01
Blis;550;Blissymbols;symboles Bliss;;2004-05-01
Bopo;285;Bopomofo;bopomofo;Bopomofo;2004-05-01
Brah;300;Brahmi;brahma;Brahmi;2010-07-23
Brai;570;Braille;braille;Braille;2004-05-01
Bugi;367;Buginese;bouguis;Buginese;2006-06-21
Buhd;372;Buhid;bouhide;Buhid;2004-05-01
Cakm;349;Chakma;chakma;Chakma;2012-02-06
Cans;440;Unified Canadian Aboriginal Syllabics;syllabaire autochtone canadien unifié;Canadian_Aboriginal;2004-05-29
Cari;201;Carian;carien;Carian;2007-07-02
Cham;358;Cham;cham (čam, tcham);Cham;2009-11-11
Cher;445;Cherokee;tchérokî;Cherokee;2004-05-01
Cirt;291;Cirth;cirth;;2004-05-01
Copt;204;Coptic;copte;Coptic;2006-06-21
Cprt;403;Cypriot;syllabaire chypriote;Cypriot;2004-05-01
Cyrl;220;Cyrillic;cyrillique;Cyrillic;2004-05-01
Cyrs;221;Cyrillic (Old Church Slavonic variant);cyrillique (variante slavonne);;2004-05-01
Deva;315;Devanagari (Nagari);dévanâgarî;Devanagari;2004-05-01
Dsrt;250;Deseret (Mormon);déseret (mormon);Deseret;2004-05-01
Dupl;755;Duployan shorthand, Duployan stenography;sténographie Duployé;;2010-07-18
Egyd;070;Egyptian demotic;démotique égyptien;;2004-05-01
Egyh;060;Egyptian hieratic;hiératique égyptien;;2004-05-01
Egyp;050;Egyptian hieroglyphs;hiéroglyphes égyptiens;Egyptian_Hieroglyphs;2009-06-01
Elba;226;Elbasan;elbasan;;2010-07-18
Ethi;430;Ethiopic (Geʻez);éthiopien (geʻez, guèze);Ethiopic;2004-10-25
Geor;240;Georgian (Mkhedruli);géorgien (mkhédrouli);Georgian;2004-05-29
Geok;241;Khutsuri (Asomtavruli and Nuskhuri);khoutsouri (assomtavrouli et nouskhouri);Georgian;2012-10-16
Glag;225;Glagolitic;glagolitique;Glagolitic;2006-06-21
Goth;206;Gothic;gotique;Gothic;2004-05-01
Gran;343;Grantha;grantha;;2009-11-11
Grek;200;Greek;grec;Greek;2004-05-01
Gujr;320;Gujarati;goudjarâtî (gujrâtî);Gujarati;2004-05-01
Guru;310;Gurmukhi;gourmoukhî;Gurmukhi;2004-05-01
Hang;286;Hangul (Hangŭl, Hangeul);hangûl (hangŭl, hangeul);Hangul;2004-05-29
Hani;500;Han (Hanzi, Kanji, Hanja);idéogrammes han (sinogrammes);Han;2009-02-23
Hano;371;Hanunoo (Hanunóo);hanounóo;Hanunoo;2004-05-29
Hans;501;Han (Simplified variant);idéogrammes han (variante simplifiée);;2004-05-29
Hant;502;Han (Traditional variant);idéogrammes han (variante traditionnelle);;2004-05-29
Hatr;127;Hatran;hatrénien;;2012-11-01
Hebr;125;Hebrew;hébreu;Hebrew;2004-05-01
Hira;410;Hiragana;hiragana;Hiragana;2004-05-01
Hluw;080;Anatolian Hieroglyphs (Luwian Hieroglyphs, Hittite Hieroglyphs);hiéroglyphes anatoliens (hiéroglyphes louvites, hiéroglyphes hittites);;2011-12-09
Hmng;450;Pahawh Hmong;pahawh hmong;;2004-05-01
Hrkt;412;Japanese syllabaries (alias for Hiragana + Katakana);syllabaires japonais (alias pour hiragana + katakana);Katakana_Or_Hiragana;2011-06-21
Hung;176;Old Hungarian (Hungarian Runic);runes hongroises (ancien hongrois);;2012-10-16
Inds;610;Indus (Harappan);indus;;2004-05-01
Ital;210;Old Italic (Etruscan, Oscan, etc.);ancien italique (étrusque, osque, etc.);Old_Italic;2004-05-29
Java;361;Javanese;javanais;Javanese;2009-06-01
Jpan;413;Japanese (alias for Han + Hiragana + Katakana);japonais (alias pour han + hiragana + katakana);;2006-06-21
Jurc;510;Jurchen;jurchen;;2010-12-21
Kali;357;Kayah Li;kayah li;Kayah_Li;2007-07-02
Kana;411;Katakana;katakana;Katakana;2004-05-01
Khar;305;Kharoshthi;kharochthî;Kharoshthi;2006-06-21
Khmr;355;Khmer;khmer;Khmer;2004-05-29
Khoj;322;Khojki;khojkî;;2011-06-21
Knda;345;Kannada;kannara (canara);Kannada;2004-05-29
Kore;287;Korean (alias for Hangul + Han);coréen (alias pour hangûl + han);;2007-06-13
Kpel;436;Kpelle;kpèllé;;2010-03-26
Kthi;317;Kaithi;kaithî;Kaithi;2009-06-01
Lana;351;Tai Tham (Lanna);taï tham (lanna);Tai_Tham;2009-06-01
Laoo;356;Lao;laotien;Lao;2004-05-01
Latf;217;Latin (Fraktur variant);latin (variante brisée);;2004-05-01
Latg;216;Latin (Gaelic variant);latin (variante gaélique);;2004-05-01
Latn;215;Latin;latin;Latin;2004-05-01
Lepc;335;Lepcha (Róng);lepcha (róng);Lepcha;2007-07-02
Limb;336;Limbu;limbou;Limbu;2004-05-29
Lina;400;Linear A;linéaire A;;2004-05-01
Linb;401;Linear B;linéaire B;Linear_B;2004-05-29
Lisu;399;Lisu (Fraser);lisu (Fraser);Lisu;2009-06-01
Loma;437;Loma;loma;;2010-03-26
Lyci;202;Lycian;lycien;Lycian;2007-07-02
Lydi;116;Lydian;lydien;Lydian;2007-07-02
Mahj;314;Mahajani;mahâjanî;;2012-10-16
Mand;140;Mandaic, Mandaean;mandéen;Mandaic;2010-07-23
Mani;139;Manichaean;manichéen;;2007-07-15
Maya;090;Mayan hieroglyphs;hiéroglyphes mayas;;2004-05-01
Mend;438;Mende Kikakui;mendé kikakui;;2013-10-12
Merc;101;Meroitic Cursive;cursif méroïtique;Meroitic_Cursive;2012-02-06
Mero;100;Meroitic Hieroglyphs;hiéroglyphes méroïtiques;Meroitic_Hieroglyphs;2012-02-06
Mlym;347;Malayalam;malayâlam;Malayalam;2004-05-01
Modi;323;Modi, Moḍī;modî;;2013-10-12
Moon;218;Moon (Moon code, Moon script, Moon type);écriture Moon;;2006-12-11
Mong;145;Mongolian;mongol;Mongolian;2004-05-01
Mroo;199;Mro, Mru;mro;;2010-12-21
Mtei;337;Meitei Mayek (Meithei, Meetei);meitei mayek;Meetei_Mayek;2009-06-01
Mult;323; Multani;multanî;;2012-11-01
Mymr;350;Myanmar (Burmese);birman;Myanmar;2004-05-01
Narb;106;Old North Arabian (Ancient North Arabian);nord-arabique;;2010-03-26
Nbat;159;Nabataean;nabatéen;;2010-03-26
Nkgb;420;Nakhi Geba ('Na-'Khi ²Ggŏ-¹baw, Naxi Geba);nakhi géba;;2009-02-23
Nkoo;165;NKo;nko;Nko;2006-10-10
Nshu;499;Nüshu;nüshu;;2010-12-21
Ogam;212;Ogham;ogam;Ogham;2004-05-01
Olck;261;Ol Chiki (Ol Cemet, Ol, Santali);ol tchiki;Ol_Chiki;2007-07-02
Orkh;175;Old Turkic, Orkhon Runic;orkhon;Old_Turkic;2009-06-01
Orya;327;Oriya;oriyâ;Oriya;2004-05-01
Osma;260;Osmanya;osmanais;Osmanya;2004-05-01
Palm;126;Palmyrene;palmyrénien;;2010-03-26
Pauc;263;Pau Cin Hau;paou chin haou;;2013-10-12
Perm;227;Old Permic;ancien permien;;2004-05-01
Phag;331;Phags-pa;phags pa;Phags_Pa;2006-10-10
Phli;131;Inscriptional Pahlavi;pehlevi des inscriptions;Inscriptional_Pahlavi;2009-06-01
Phlp;132;Psalter Pahlavi;pehlevi des psautiers;;2007-11-26
Phlv;133;Book Pahlavi;pehlevi des livres;;2007-07-15
Phnx;115;Phoenician;phénicien;Phoenician;2006-10-10
Plrd;282;Miao (Pollard);miao (Pollard);Miao;2012-02-06
Prti;130;Inscriptional Parthian;parthe des inscriptions;Inscriptional_Parthian;2009-06-01
Qaaa;900;Reserved for private use (start);réservé à lusage privé (début);;2004-05-29
Qabx;949;Reserved for private use (end);réservé à lusage privé (fin);;2004-05-29
Rjng;363;Rejang (Redjang, Kaganga);redjang (kaganga);Rejang;2009-02-23
Roro;620;Rongorongo;rongorongo;;2004-05-01
Runr;211;Runic;runique;Runic;2004-05-01
Samr;123;Samaritan;samaritain;Samaritan;2009-06-01
Sara;292;Sarati;sarati;;2004-05-29
Sarb;105;Old South Arabian;sud-arabique, himyarite;Old_South_Arabian;2009-06-01
Saur;344;Saurashtra;saurachtra;Saurashtra;2007-07-02
Sgnw;095;SignWriting;SignÉcriture, SignWriting;;2006-10-10
Shaw;281;Shavian (Shaw);shavien (Shaw);Shavian;2004-05-01
Shrd;319;Sharada, Śāradā;charada, shard;Sharada;2012-02-06
Sidd;302;Siddham, Siddhaṃ, Siddhamātṛkā;siddham;;2013-10-12
Sind;318;Khudawadi, Sindhi;khoudawadî, sindhî;;2010-12-21
Sinh;348;Sinhala;singhalais;Sinhala;2004-05-01
Sora;398;Sora Sompeng;sora sompeng;Sora_Sompeng;2012-02-06
Sund;362;Sundanese;sundanais;Sundanese;2007-07-02
Sylo;316;Syloti Nagri;sylotî nâgrî;Syloti_Nagri;2006-06-21
Syrc;135;Syriac;syriaque;Syriac;2004-05-01
Syre;138;Syriac (Estrangelo variant);syriaque (variante estranghélo);;2004-05-01
Syrj;137;Syriac (Western variant);syriaque (variante occidentale);;2004-05-01
Syrn;136;Syriac (Eastern variant);syriaque (variante orientale);;2004-05-01
Tagb;373;Tagbanwa;tagbanoua;Tagbanwa;2004-05-01
Takr;321;Takri, Ṭākrī, Ṭāṅkrī;tâkrî;Takri;2012-02-06
Tale;353;Tai Le;taï-le;Tai_Le;2004-10-25
Talu;354;New Tai Lue;nouveau taï-lue;New_Tai_Lue;2006-06-21
Taml;346;Tamil;tamoul;Tamil;2004-05-01
Tang;520;Tangut;tangoute;;2010-12-21
Tavt;359;Tai Viet;taï viêt;Tai_Viet;2009-06-01
Telu;340;Telugu;télougou;Telugu;2004-05-01
Teng;290;Tengwar;tengwar;;2004-05-01
Tfng;120;Tifinagh (Berber);tifinagh (berbère);Tifinagh;2006-06-21
Tglg;370;Tagalog (Baybayin, Alibata);tagal (baybayin, alibata);Tagalog;2009-02-23
Thaa;170;Thaana;thâna;Thaana;2004-05-01
Thai;352;Thai;thaï;Thai;2004-05-01
Tibt;330;Tibetan;tibétain;Tibetan;2004-05-01
Tirh;326;Tirhuta;tirhouta;;2011-12-09
Ugar;040;Ugaritic;ougaritique;Ugaritic;2004-05-01
Vaii;470;Vai;vaï;Vai;2007-07-02
Visp;280;Visible Speech;parole visible;;2004-05-01
Wara;262;Warang Citi (Varang Kshiti);warang citi;;2009-11-11
Wole;480;Woleai;woléaï;;2010-12-21
Xpeo;030;Old Persian;cunéiforme persépolitain;Old_Persian;2006-06-21
Xsux;020;Cuneiform, Sumero-Akkadian;cunéiforme suméro-akkadien;Cuneiform;2006-10-10
Yiii;460;Yi;yi;Yi;2004-05-01
Zinh;994;Code for inherited script;codet pour écriture héritée;Inherited;2009-02-23
Zmth;995;Mathematical notation;notation mathématique;;2007-11-26
Zsym;996;Symbols;symboles;;2007-11-26
Zxxx;997;Code for unwritten documents;codet pour les documents non écrits;;2011-06-21
Zyyy;998;Code for undetermined script;codet pour écriture indéterminée;Common;2004-05-29
Zzzz;999;Code for uncoded script;codet pour écriture non codée;Unknown;2006-10-10
@@ -1,474 +0,0 @@
IdSubLanguage ISO639 LanguageName UploadEnabled WebEnabled
aar aa Afar, afar 0 0
abk ab Abkhazian 0 0
ace Achinese 0 0
ach Acoli 0 0
ada Adangme 0 0
ady adyghé 0 0
afa Afro-Asiatic (Other) 0 0
afh Afrihili 0 0
afr af Afrikaans 1 0
ain Ainu 0 0
aka ak Akan 0 0
akk Akkadian 0 0
alb sq Albanian 1 1
ale Aleut 0 0
alg Algonquian languages 0 0
alt Southern Altai 0 0
amh am Amharic 0 0
ang English, Old (ca.450-1100) 0 0
apa Apache languages 0 0
ara ar Arabic 1 1
arc Aramaic 0 0
arg an Aragonese 0 0
arm hy Armenian 1 0
arn Araucanian 0 0
arp Arapaho 0 0
art Artificial (Other) 0 0
arw Arawak 0 0
asm as Assamese 0 0
ast Asturian, Bable 0 0
ath Athapascan languages 0 0
aus Australian languages 0 0
ava av Avaric 0 0
ave ae Avestan 0 0
awa Awadhi 0 0
aym ay Aymara 0 0
aze az Azerbaijani 0 0
bad Banda 0 0
bai Bamileke languages 0 0
bak ba Bashkir 0 0
bal Baluchi 0 0
bam bm Bambara 0 0
ban Balinese 0 0
baq eu Basque 1 1
bas Basa 0 0
bat Baltic (Other) 0 0
bej Beja 0 0
bel be Belarusian 0 0
bem Bemba 0 0
ben bn Bengali 1 0
ber Berber (Other) 0 0
bho Bhojpuri 0 0
bih bh Bihari 0 0
bik Bikol 0 0
bin Bini 0 0
bis bi Bislama 0 0
bla Siksika 0 0
bnt Bantu (Other) 0 0
bos bs Bosnian 1 0
bra Braj 0 0
bre br Breton 1 0
btk Batak (Indonesia) 0 0
bua Buriat 0 0
bug Buginese 0 0
bul bg Bulgarian 1 1
bur my Burmese 1 0
byn Blin 0 0
cad Caddo 0 0
cai Central American Indian (Other) 0 0
car Carib 0 0
cat ca Catalan 1 1
cau Caucasian (Other) 0 0
ceb Cebuano 0 0
cel Celtic (Other) 0 0
cha ch Chamorro 0 0
chb Chibcha 0 0
che ce Chechen 0 0
chg Chagatai 0 0
chi zh Chinese 1 1
chk Chuukese 0 0
chm Mari 0 0
chn Chinook jargon 0 0
cho Choctaw 0 0
chp Chipewyan 0 0
chr Cherokee 0 0
chu cu Church Slavic 0 0
chv cv Chuvash 0 0
chy Cheyenne 0 0
cmc Chamic languages 0 0
cop Coptic 0 0
cor kw Cornish 0 0
cos co Corsican 0 0
cpe Creoles and pidgins, English based (Other) 0 0
cpf Creoles and pidgins, French-based (Other) 0 0
cpp Creoles and pidgins, Portuguese-based (Other) 0 0
cre cr Cree 0 0
crh Crimean Tatar 0 0
crp Creoles and pidgins (Other) 0 0
csb Kashubian 0 0
cus Cushitic (Other)' couchitiques, autres langues 0 0
cze cs Czech 1 1
dak Dakota 0 0
dan da Danish 1 1
dar Dargwa 0 0
day Dayak 0 0
del Delaware 0 0
den Slave (Athapascan) 0 0
dgr Dogrib 0 0
din Dinka 0 0
div dv Divehi 0 0
doi Dogri 0 0
dra Dravidian (Other) 0 0
dua Duala 0 0
dum Dutch, Middle (ca.1050-1350) 0 0
dut nl Dutch 1 1
dyu Dyula 0 0
dzo dz Dzongkha 0 0
efi Efik 0 0
egy Egyptian (Ancient) 0 0
eka Ekajuk 0 0
elx Elamite 0 0
eng en English 1 1
enm English, Middle (1100-1500) 0 0
epo eo Esperanto 1 0
est et Estonian 1 1
ewe ee Ewe 0 0
ewo Ewondo 0 0
fan Fang 0 0
fao fo Faroese 0 0
fat Fanti 0 0
fij fj Fijian 0 0
fil Filipino 0 0
fin fi Finnish 1 1
fiu Finno-Ugrian (Other) 0 0
fon Fon 0 0
fre fr French 1 1
frm French, Middle (ca.1400-1600) 0 0
fro French, Old (842-ca.1400) 0 0
fry fy Frisian 0 0
ful ff Fulah 0 0
fur Friulian 0 0
gaa Ga 0 0
gay Gayo 0 0
gba Gbaya 0 0
gem Germanic (Other) 0 0
geo ka Georgian 1 1
ger de German 1 1
gez Geez 0 0
gil Gilbertese 0 0
gla gd Gaelic 0 0
gle ga Irish 0 0
glg gl Galician 1 1
glv gv Manx 0 0
gmh German, Middle High (ca.1050-1500) 0 0
goh German, Old High (ca.750-1050) 0 0
gon Gondi 0 0
gor Gorontalo 0 0
got Gothic 0 0
grb Grebo 0 0
grc Greek, Ancient (to 1453) 0 0
ell el Greek 1 1
grn gn Guarani 0 0
guj gu Gujarati 0 0
gwi Gwich´in 0 0
hai Haida 0 0
hat ht Haitian 0 0
hau ha Hausa 0 0
haw Hawaiian 0 0
heb he Hebrew 1 1
her hz Herero 0 0
hil Hiligaynon 0 0
him Himachali 0 0
hin hi Hindi 1 1
hit Hittite 0 0
hmn Hmong 0 0
hmo ho Hiri Motu 0 0
hrv hr Croatian 1 1
hun hu Hungarian 1 1
hup Hupa 0 0
iba Iban 0 0
ibo ig Igbo 0 0
ice is Icelandic 1 1
ido io Ido 0 0
iii ii Sichuan Yi 0 0
ijo Ijo 0 0
iku iu Inuktitut 0 0
ile ie Interlingue 0 0
ilo Iloko 0 0
ina ia Interlingua (International Auxiliary Language Asso 0 0
inc Indic (Other) 0 0
ind id Indonesian 1 1
ine Indo-European (Other) 0 0
inh Ingush 0 0
ipk ik Inupiaq 0 0
ira Iranian (Other) 0 0
iro Iroquoian languages 0 0
ita it Italian 1 1
jav jv Javanese 0 0
jpn ja Japanese 1 1
jpr Judeo-Persian 0 0
jrb Judeo-Arabic 0 0
kaa Kara-Kalpak 0 0
kab Kabyle 0 0
kac Kachin 0 0
kal kl Kalaallisut 0 0
kam Kamba 0 0
kan kn Kannada 0 0
kar Karen 0 0
kas ks Kashmiri 0 0
kau kr Kanuri 0 0
kaw Kawi 0 0
kaz kk Kazakh 1 0
kbd Kabardian 0 0
kha Khasi 0 0
khi Khoisan (Other) 0 0
khm km Khmer 1 1
kho Khotanese 0 0
kik ki Kikuyu 0 0
kin rw Kinyarwanda 0 0
kir ky Kirghiz 0 0
kmb Kimbundu 0 0
kok Konkani 0 0
kom kv Komi 0 0
kon kg Kongo 0 0
kor ko Korean 1 1
kos Kosraean 0 0
kpe Kpelle 0 0
krc Karachay-Balkar 0 0
kro Kru 0 0
kru Kurukh 0 0
kua kj Kuanyama 0 0
kum Kumyk 0 0
kur ku Kurdish 0 0
kut Kutenai 0 0
lad Ladino 0 0
lah Lahnda 0 0
lam Lamba 0 0
lao lo Lao 0 0
lat la Latin 0 0
lav lv Latvian 1 0
lez Lezghian 0 0
lim li Limburgan 0 0
lin ln Lingala 0 0
lit lt Lithuanian 1 0
lol Mongo 0 0
loz Lozi 0 0
ltz lb Luxembourgish 1 0
lua Luba-Lulua 0 0
lub lu Luba-Katanga 0 0
lug lg Ganda 0 0
lui Luiseno 0 0
lun Lunda 0 0
luo Luo (Kenya and Tanzania) 0 0
lus lushai 0 0
mac mk Macedonian 1 1
mad Madurese 0 0
mag Magahi 0 0
mah mh Marshallese 0 0
mai Maithili 0 0
mak Makasar 0 0
mal ml Malayalam 1 0
man Mandingo 0 0
mao mi Maori 0 0
map Austronesian (Other) 0 0
mar mr Marathi 0 0
mas Masai 0 0
may ms Malay 1 1
mdf Moksha 0 0
mdr Mandar 0 0
men Mende 0 0
mga Irish, Middle (900-1200) 0 0
mic Mi'kmaq 0 0
min Minangkabau 0 0
mis Miscellaneous languages 0 0
mkh Mon-Khmer (Other) 0 0
mlg mg Malagasy 0 0
mlt mt Maltese 0 0
mnc Manchu 0 0
mni Manipuri 0 0
mno Manobo languages 0 0
moh Mohawk 0 0
mol mo Moldavian 0 0
mon mn Mongolian 1 0
mos Mossi 0 0
mwl Mirandese 0 0
mul Multiple languages 0 0
mun Munda languages 0 0
mus Creek 0 0
mwr Marwari 0 0
myn Mayan languages 0 0
myv Erzya 0 0
nah Nahuatl 0 0
nai North American Indian 0 0
nap Neapolitan 0 0
nau na Nauru 0 0
nav nv Navajo 0 0
nbl nr Ndebele, South 0 0
nde nd Ndebele, North 0 0
ndo ng Ndonga 0 0
nds Low German 0 0
nep ne Nepali 0 0
new Nepal Bhasa 0 0
nia Nias 0 0
nic Niger-Kordofanian (Other) 0 0
niu Niuean 0 0
nno nn Norwegian Nynorsk 0 0
nob nb Norwegian Bokmal 0 0
nog Nogai 0 0
non Norse, Old 0 0
nor no Norwegian 1 1
nso Northern Sotho 0 0
nub Nubian languages 0 0
nwc Classical Newari 0 0
nya ny Chichewa 0 0
nym Nyamwezi 0 0
nyn Nyankole 0 0
nyo Nyoro 0 0
nzi Nzima 0 0
oci oc Occitan 1 1
oji oj Ojibwa 0 0
ori or Oriya 0 0
orm om Oromo 0 0
osa Osage 0 0
oss os Ossetian 0 0
ota Turkish, Ottoman (1500-1928) 0 0
oto Otomian languages 0 0
paa Papuan (Other) 0 0
pag Pangasinan 0 0
pal Pahlavi 0 0
pam Pampanga 0 0
pan pa Panjabi 0 0
pap Papiamento 0 0
pau Palauan 0 0
peo Persian, Old (ca.600-400 B.C.) 0 0
per fa Persian 1 1
phi Philippine (Other) 0 0
phn Phoenician 0 0
pli pi Pali 0 0
pol pl Polish 1 1
pon Pohnpeian 0 0
por pt Portuguese 1 1
pra Prakrit languages 0 0
pro Provençal, Old (to 1500) 0 0
pus ps Pushto 0 0
que qu Quechua 0 0
raj Rajasthani 0 0
rap Rapanui 0 0
rar Rarotongan 0 0
roa Romance (Other) 0 0
roh rm Raeto-Romance 0 0
rom Romany 0 0
run rn Rundi 0 0
rup Aromanian 0 0
rus ru Russian 1 1
sad Sandawe 0 0
sag sg Sango 0 0
sah Yakut 0 0
sai South American Indian (Other) 0 0
sal Salishan languages 0 0
sam Samaritan Aramaic 0 0
san sa Sanskrit 0 0
sas Sasak 0 0
sat Santali 0 0
scc sr Serbian 1 1
scn Sicilian 0 0
sco Scots 0 0
sel Selkup 0 0
sem Semitic (Other) 0 0
sga Irish, Old (to 900) 0 0
sgn Sign Languages 0 0
shn Shan 0 0
sid Sidamo 0 0
sin si Sinhalese 1 1
sio Siouan languages 0 0
sit Sino-Tibetan (Other) 0 0
sla Slavic (Other) 0 0
slo sk Slovak 1 1
slv sl Slovenian 1 1
sma Southern Sami 0 0
sme se Northern Sami 0 0
smi Sami languages (Other) 0 0
smj Lule Sami 0 0
smn Inari Sami 0 0
smo sm Samoan 0 0
sms Skolt Sami 0 0
sna sn Shona 0 0
snd sd Sindhi 0 0
snk Soninke 0 0
sog Sogdian 0 0
som so Somali 0 0
son Songhai 0 0
sot st Sotho, Southern 0 0
spa es Spanish 1 1
srd sc Sardinian 0 0
srr Serer 0 0
ssa Nilo-Saharan (Other) 0 0
ssw ss Swati 0 0
suk Sukuma 0 0
sun su Sundanese 0 0
sus Susu 0 0
sux Sumerian 0 0
swa sw Swahili 1 0
swe sv Swedish 1 1
syr Syriac 1 0
tah ty Tahitian 0 0
tai Tai (Other) 0 0
tam ta Tamil 1 0
tat tt Tatar 0 0
tel te Telugu 1 0
tem Timne 0 0
ter Tereno 0 0
tet Tetum 0 0
tgk tg Tajik 0 0
tgl tl Tagalog 1 1
tha th Thai 1 1
tib bo Tibetan 0 0
tig Tigre 0 0
tir ti Tigrinya 0 0
tiv Tiv 0 0
tkl Tokelau 0 0
tlh Klingon 0 0
tli Tlingit 0 0
tmh Tamashek 0 0
tog Tonga (Nyasa) 0 0
ton to Tonga (Tonga Islands) 0 0
tpi Tok Pisin 0 0
tsi Tsimshian 0 0
tsn tn Tswana 0 0
tso ts Tsonga 0 0
tuk tk Turkmen 0 0
tum Tumbuka 0 0
tup Tupi languages 0 0
tur tr Turkish 1 1
tut Altaic (Other) 0 0
tvl Tuvalu 0 0
twi tw Twi 0 0
tyv Tuvinian 0 0
udm Udmurt 0 0
uga Ugaritic 0 0
uig ug Uighur 0 0
ukr uk Ukrainian 1 1
umb Umbundu 0 0
und Undetermined 0 0
urd ur Urdu 1 0
uzb uz Uzbek 0 0
vai Vai 0 0
ven ve Venda 0 0
vie vi Vietnamese 1 1
vol vo Volapük 0 0
vot Votic 0 0
wak Wakashan languages 0 0
wal Walamo 0 0
war Waray 0 0
was Washo 0 0
wel cy Welsh 0 0
wen Sorbian languages 0 0
wln wa Walloon 0 0
wol wo Wolof 0 0
xal Kalmyk 0 0
xho xh Xhosa 0 0
yao Yao 0 0
yap Yapese 0 0
yid yi Yiddish 0 0
yor yo Yoruba 0 0
ypk Yupik languages 0 0
zap Zapotec 0 0
zen Zenaga 0 0
zha za Zhuang 0 0
znd Zande 0 0
zul zu Zulu 0 0
zun Zuni 0 0
rum ro Romanian 1 1
pob pb Brazilian 1 1
mne Montenegrin 1 0
@@ -1,85 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
class Error(Exception):
"""Base class for all exceptions in babelfish"""
pass
class LanguageError(Error, AttributeError):
"""Base class for all language exceptions in babelfish"""
pass
class LanguageConvertError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageConverter.convert` fails
:param string alpha3: alpha3 code that failed conversion
:param country: country code that failed conversion, if any
:type country: string or None
:param script: script code that failed conversion, if any
:type script: string or None
"""
def __init__(self, alpha3, country=None, script=None):
self.alpha3 = alpha3
self.country = country
self.script = script
def __str__(self):
s = self.alpha3
if self.country is not None:
s += '-' + self.country
if self.script is not None:
s += '-' + self.script
return s
class LanguageReverseError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
class CountryError(Error, AttributeError):
"""Base class for all country exceptions in babelfish"""
pass
class CountryConvertError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryConverter.convert` fails
:param string alpha2: alpha2 code that failed conversion
"""
def __init__(self, alpha2):
self.alpha2 = alpha2
def __str__(self):
return self.alpha2
class CountryReverseError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
@@ -1,185 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
from pkg_resources import resource_stream # @UnresolvedImport
from .converters import ConverterManager
from .country import Country
from .exceptions import LanguageConvertError
from .script import Script
from . import basestr
LANGUAGES = set()
LANGUAGE_MATRIX = []
#: The namedtuple used in the :data:`LANGUAGE_MATRIX`
IsoLanguage = namedtuple('IsoLanguage', ['alpha3', 'alpha3b', 'alpha3t', 'alpha2', 'scope', 'type', 'name', 'comment'])
f = resource_stream('babelfish', 'data/iso-639-3.tab')
f.readline()
for l in f:
iso_language = IsoLanguage(*l.decode('utf-8').split('\t'))
LANGUAGES.add(iso_language.alpha3)
LANGUAGE_MATRIX.append(iso_language)
f.close()
class LanguageConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for language converters"""
entry_point = 'babelfish.language_converters'
internal_converters = ['alpha2 = babelfish.converters.alpha2:Alpha2Converter',
'alpha3b = babelfish.converters.alpha3b:Alpha3BConverter',
'alpha3t = babelfish.converters.alpha3t:Alpha3TConverter',
'name = babelfish.converters.name:NameConverter',
'scope = babelfish.converters.scope:ScopeConverter',
'type = babelfish.converters.type:LanguageTypeConverter',
'opensubtitles = babelfish.converters.opensubtitles:OpenSubtitlesConverter']
language_converters = LanguageConverterManager()
class LanguageMeta(type):
"""The :class:`Language` metaclass
Dynamically redirect :meth:`Language.frommycode` to :meth:`Language.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Language(LanguageMeta(str('LanguageBase'), (object,), {})):
"""A human language
A human language is composed of a language part following the ISO-639
standard and can be country-specific when a :class:`~babelfish.country.Country`
is specified.
The :class:`Language` is extensible with custom converters (see :ref:`custom_converters`)
:param string language: the language as a 3-letter ISO-639-3 code
:param country: the country (if any) as a 2-letter ISO-3166 code or :class:`~babelfish.country.Country` instance
:type country: string or :class:`~babelfish.country.Country` or None
:param script: the script (if any) as a 4-letter ISO-15924 code or :class:`~babelfish.script.Script` instance
:type script: string or :class:`~babelfish.script.Script` or None
:param unknown: the unknown language as a three-letters ISO-639-3 code to use as fallback
:type unknown: string or None
:raise: ValueError if the language could not be recognized and `unknown` is ``None``
"""
def __init__(self, language, country=None, script=None, unknown=None):
if unknown is not None and language not in LANGUAGES:
language = unknown
if language not in LANGUAGES:
raise ValueError('%r is not a valid language' % language)
self.alpha3 = language
self.country = None
if isinstance(country, Country):
self.country = country
elif country is None:
self.country = None
else:
self.country = Country(country)
self.script = None
if isinstance(script, Script):
self.script = script
elif script is None:
self.script = None
else:
self.script = Script(script)
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Language` by its `code` using `converter` to
:meth:`~babelfish.converters.LanguageReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.LanguageReverseConverter` to use
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
return cls(*language_converters[converter].reverse(code))
@classmethod
def fromietf(cls, ietf):
"""Create a :class:`Language` by from an IETF language code
:param string ietf: the ietf code
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
subtags = ietf.split('-')
language_subtag = subtags.pop(0).lower()
if len(language_subtag) == 2:
language = cls.fromalpha2(language_subtag)
else:
language = cls(language_subtag)
while subtags:
subtag = subtags.pop(0)
if len(subtag) == 2:
language.country = Country(subtag.upper())
else:
language.script = Script(subtag.capitalize())
if language.script is not None:
if subtags:
raise ValueError('Wrong IETF format. Unmatched subtags: %r' % subtags)
break
return language
def __getstate__(self):
return self.alpha3, self.country, self.script
def __setstate__(self, state):
self.alpha3, self.country, self.script = state
def __getattr__(self, name):
alpha3 = self.alpha3
country = self.country.alpha2 if self.country is not None else None
script = self.script.code if self.script is not None else None
try:
return language_converters[name].convert(alpha3, country, script)
except KeyError:
raise AttributeError(name)
def __hash__(self):
return hash(str(self))
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Language):
return False
return (self.alpha3 == other.alpha3 and
self.country == other.country and
self.script == other.script)
def __ne__(self, other):
return not self == other
def __bool__(self):
return self.alpha3 != 'und'
__nonzero__ = __bool__
def __repr__(self):
return '<Language [%s]>' % self
def __str__(self):
try:
s = self.alpha2
except LanguageConvertError:
s = self.alpha3
if self.country is not None:
s += '-' + str(self.country)
if self.script is not None:
s += '-' + str(self.script)
return s
@@ -1,76 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from pkg_resources import resource_stream # @UnresolvedImport
from . import basestr
#: Script code to script name mapping
SCRIPTS = {}
#: List of countries in the ISO-15924 as namedtuple of code, number, name, french_name, pva and date
SCRIPT_MATRIX = []
#: The namedtuple used in the :data:`SCRIPT_MATRIX`
IsoScript = namedtuple('IsoScript', ['code', 'number', 'name', 'french_name', 'pva', 'date'])
f = resource_stream('babelfish', 'data/iso15924-utf8-20131012.txt')
f.readline()
for l in f:
l = l.decode('utf-8').strip()
if not l or l.startswith('#'):
continue
script = IsoScript._make(l.split(';'))
SCRIPT_MATRIX.append(script)
SCRIPTS[script.code] = script.name
f.close()
class Script(object):
"""A human writing system
A script is represented by a 4-letter code from the ISO-15924 standard
:param string script: 4-letter ISO-15924 script code
"""
def __init__(self, script):
if script not in SCRIPTS:
raise ValueError('%r is not a valid script' % script)
#: ISO-15924 4-letter script code
self.code = script
@property
def name(self):
"""English name of the script"""
return SCRIPTS[self.code]
def __getstate__(self):
return self.code
def __setstate__(self, state):
self.code = state
def __hash__(self):
return hash(self.code)
def __eq__(self, other):
if isinstance(other, basestr):
return self.code == other
if not isinstance(other, Script):
return False
return self.code == other.code
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Script [%s]>' % self
def __str__(self):
return self.code
@@ -1,368 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
import re
import sys
import pickle
from unittest import TestCase, TestSuite, TestLoader, TextTestRunner
from pkg_resources import resource_stream # @UnresolvedImport
from babelfish import (LANGUAGES, Language, Country, Script, language_converters, country_converters,
LanguageReverseConverter, LanguageConvertError, LanguageReverseError, CountryReverseError)
if sys.version_info[:2] <= (2, 6):
_MAX_LENGTH = 80
def safe_repr(obj, short=False):
try:
result = repr(obj)
except Exception:
result = object.__repr__(obj)
if not short or len(result) < _MAX_LENGTH:
return result
return result[:_MAX_LENGTH] + ' [truncated]...'
class _AssertRaisesContext(object):
"""A context manager used to implement TestCase.assertRaises* methods."""
def __init__(self, expected, test_case, expected_regexp=None):
self.expected = expected
self.failureException = test_case.failureException
self.expected_regexp = expected_regexp
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, tb):
if exc_type is None:
try:
exc_name = self.expected.__name__
except AttributeError:
exc_name = str(self.expected)
raise self.failureException(
"{0} not raised".format(exc_name))
if not issubclass(exc_type, self.expected):
# let unexpected exceptions pass through
return False
self.exception = exc_value # store for later retrieval
if self.expected_regexp is None:
return True
expected_regexp = self.expected_regexp
if isinstance(expected_regexp, basestring):
expected_regexp = re.compile(expected_regexp)
if not expected_regexp.search(str(exc_value)):
raise self.failureException('"%s" does not match "%s"' %
(expected_regexp.pattern, str(exc_value)))
return True
class _Py26FixTestCase(object):
def assertIsNone(self, obj, msg=None):
"""Same as self.assertTrue(obj is None), with a nicer default message."""
if obj is not None:
standardMsg = '%s is not None' % (safe_repr(obj),)
self.fail(self._formatMessage(msg, standardMsg))
def assertIsNotNone(self, obj, msg=None):
"""Included for symmetry with assertIsNone."""
if obj is None:
standardMsg = 'unexpectedly None'
self.fail(self._formatMessage(msg, standardMsg))
def assertIn(self, member, container, msg=None):
"""Just like self.assertTrue(a in b), but with a nicer default message."""
if member not in container:
standardMsg = '%s not found in %s' % (safe_repr(member),
safe_repr(container))
self.fail(self._formatMessage(msg, standardMsg))
def assertNotIn(self, member, container, msg=None):
"""Just like self.assertTrue(a not in b), but with a nicer default message."""
if member in container:
standardMsg = '%s unexpectedly found in %s' % (safe_repr(member),
safe_repr(container))
self.fail(self._formatMessage(msg, standardMsg))
def assertIs(self, expr1, expr2, msg=None):
"""Just like self.assertTrue(a is b), but with a nicer default message."""
if expr1 is not expr2:
standardMsg = '%s is not %s' % (safe_repr(expr1),
safe_repr(expr2))
self.fail(self._formatMessage(msg, standardMsg))
def assertIsNot(self, expr1, expr2, msg=None):
"""Just like self.assertTrue(a is not b), but with a nicer default message."""
if expr1 is expr2:
standardMsg = 'unexpectedly identical: %s' % (safe_repr(expr1),)
self.fail(self._formatMessage(msg, standardMsg))
else:
class _Py26FixTestCase(object):
pass
class TestScript(TestCase, _Py26FixTestCase):
def test_wrong_script(self):
self.assertRaises(ValueError, lambda: Script('Azer'))
def test_eq(self):
self.assertEqual(Script('Latn'), Script('Latn'))
def test_ne(self):
self.assertNotEqual(Script('Cyrl'), Script('Latn'))
def test_hash(self):
self.assertEqual(hash(Script('Hira')), hash('Hira'))
def test_pickle(self):
self.assertEqual(pickle.loads(pickle.dumps(Script('Latn'))), Script('Latn'))
class TestCountry(TestCase, _Py26FixTestCase):
def test_wrong_country(self):
self.assertRaises(ValueError, lambda: Country('ZZ'))
def test_eq(self):
self.assertEqual(Country('US'), Country('US'))
def test_ne(self):
self.assertNotEqual(Country('GB'), Country('US'))
self.assertIsNotNone(Country('US'))
def test_hash(self):
self.assertEqual(hash(Country('US')), hash('US'))
def test_pickle(self):
for country in [Country('GB'), Country('US')]:
self.assertEqual(pickle.loads(pickle.dumps(country)), country)
def test_converter_name(self):
self.assertEqual(Country('US').name, 'UNITED STATES')
self.assertEqual(Country.fromname('UNITED STATES'), Country('US'))
self.assertEqual(Country.fromcode('UNITED STATES', 'name'), Country('US'))
self.assertRaises(CountryReverseError, lambda: Country.fromname('ZZZZZ'))
self.assertEqual(len(country_converters['name'].codes), 249)
class TestLanguage(TestCase, _Py26FixTestCase):
def test_languages(self):
self.assertEqual(len(LANGUAGES), 7874)
def test_wrong_language(self):
self.assertRaises(ValueError, lambda: Language('zzz'))
def test_unknown_language(self):
self.assertEqual(Language('zzzz', unknown='und'), Language('und'))
def test_converter_alpha2(self):
self.assertEqual(Language('eng').alpha2, 'en')
self.assertEqual(Language.fromalpha2('en'), Language('eng'))
self.assertEqual(Language.fromcode('en', 'alpha2'), Language('eng'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha2('zz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha2)
self.assertEqual(len(language_converters['alpha2'].codes), 184)
def test_converter_alpha3b(self):
self.assertEqual(Language('fra').alpha3b, 'fre')
self.assertEqual(Language.fromalpha3b('fre'), Language('fra'))
self.assertEqual(Language.fromcode('fre', 'alpha3b'), Language('fra'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha3b('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha3b)
self.assertEqual(len(language_converters['alpha3b'].codes), 418)
def test_converter_alpha3t(self):
self.assertEqual(Language('fra').alpha3t, 'fra')
self.assertEqual(Language.fromalpha3t('fra'), Language('fra'))
self.assertEqual(Language.fromcode('fra', 'alpha3t'), Language('fra'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha3t('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha3t)
self.assertEqual(len(language_converters['alpha3t'].codes), 418)
def test_converter_name(self):
self.assertEqual(Language('eng').name, 'English')
self.assertEqual(Language.fromname('English'), Language('eng'))
self.assertEqual(Language.fromcode('English', 'name'), Language('eng'))
self.assertRaises(LanguageReverseError, lambda: Language.fromname('Zzzzzzzzz'))
self.assertEqual(len(language_converters['name'].codes), 7874)
def test_converter_scope(self):
self.assertEqual(language_converters['scope'].codes, set(['I', 'S', 'M']))
self.assertEqual(Language('eng').scope, 'individual')
self.assertEqual(Language('und').scope, 'special')
def test_converter_type(self):
self.assertEqual(language_converters['type'].codes, set(['A', 'C', 'E', 'H', 'L', 'S']))
self.assertEqual(Language('eng').type, 'living')
self.assertEqual(Language('und').type, 'special')
def test_converter_opensubtitles(self):
self.assertEqual(Language('fra').opensubtitles, Language('fra').alpha3b)
self.assertEqual(Language('por', 'BR').opensubtitles, 'pob')
self.assertEqual(Language.fromopensubtitles('fre'), Language('fra'))
self.assertEqual(Language.fromopensubtitles('pob'), Language('por', 'BR'))
self.assertEqual(Language.fromopensubtitles('pb'), Language('por', 'BR'))
# Montenegrin is not recognized as an ISO language (yet?) but for now it is
# unofficially accepted as Serbian from Montenegro
self.assertEqual(Language.fromopensubtitles('mne'), Language('srp', 'ME'))
self.assertEqual(Language.fromcode('pob', 'opensubtitles'), Language('por', 'BR'))
self.assertRaises(LanguageReverseError, lambda: Language.fromopensubtitles('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').opensubtitles)
self.assertEqual(len(language_converters['opensubtitles'].codes), 606)
# test with all the LANGUAGES from the opensubtitles api
# downloaded from: http://www.opensubtitles.org/addons/export_languages.php
f = resource_stream('babelfish', 'data/opensubtitles_languages.txt')
f.readline()
for l in f:
idlang, alpha2, _, upload_enabled, web_enabled = l.decode('utf-8').strip().split('\t')
if not int(upload_enabled) and not int(web_enabled):
# do not test LANGUAGES that are too esoteric / not widely available
continue
self.assertEqual(Language.fromopensubtitles(idlang).opensubtitles, idlang)
if alpha2:
self.assertEqual(Language.fromopensubtitles(idlang), Language.fromopensubtitles(alpha2))
f.close()
def test_fromietf_country_script(self):
language = Language.fromietf('fra-FR-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_country_no_script(self):
language = Language.fromietf('fra-FR')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertIsNone(language.script)
def test_fromietf_no_country_no_script(self):
language = Language.fromietf('fra-FR')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertIsNone(language.script)
def test_fromietf_no_country_script(self):
language = Language.fromietf('fra-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertIsNone(language.country)
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_alpha2_language(self):
language = Language.fromietf('fr-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertIsNone(language.country)
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_wrong_language(self):
self.assertRaises(ValueError, lambda: Language.fromietf('xyz-FR'))
def test_fromietf_wrong_country(self):
self.assertRaises(ValueError, lambda: Language.fromietf('fra-YZ'))
def test_fromietf_wrong_script(self):
self.assertRaises(ValueError, lambda: Language.fromietf('fra-FR-Wxyz'))
def test_eq(self):
self.assertEqual(Language('eng'), Language('eng'))
def test_ne(self):
self.assertNotEqual(Language('fra'), Language('eng'))
self.assertIsNotNone(Language('fra'))
def test_nonzero(self):
self.assertFalse(bool(Language('und')))
self.assertTrue(bool(Language('eng')))
def test_language_hasattr(self):
self.assertTrue(hasattr(Language('fra'), 'alpha3'))
self.assertTrue(hasattr(Language('fra'), 'alpha2'))
self.assertFalse(hasattr(Language('bej'), 'alpha2'))
def test_country(self):
self.assertEqual(Language('por', 'BR').country, Country('BR'))
self.assertEqual(Language('eng', Country('US')).country, Country('US'))
def test_eq_with_country(self):
self.assertEqual(Language('eng', 'US'), Language('eng', Country('US')))
def test_ne_with_country(self):
self.assertNotEqual(Language('eng', 'US'), Language('eng', Country('GB')))
def test_script(self):
self.assertEqual(Language('srp', script='Latn').script, Script('Latn'))
self.assertEqual(Language('srp', script=Script('Cyrl')).script, Script('Cyrl'))
def test_eq_with_script(self):
self.assertEqual(Language('srp', script='Latn'), Language('srp', script=Script('Latn')))
def test_ne_with_script(self):
self.assertNotEqual(Language('srp', script='Latn'), Language('srp', script=Script('Cyrl')))
def test_eq_with_country_and_script(self):
self.assertEqual(Language('srp', 'SR', 'Latn'), Language('srp', Country('SR'), Script('Latn')))
def test_ne_with_country_and_script(self):
self.assertNotEqual(Language('srp', 'SR', 'Latn'), Language('srp', Country('SR'), Script('Cyrl')))
def test_hash(self):
self.assertEqual(hash(Language('fra')), hash('fr'))
self.assertEqual(hash(Language('ace')), hash('ace'))
self.assertEqual(hash(Language('por', 'BR')), hash('pt-BR'))
self.assertEqual(hash(Language('srp', script='Cyrl')), hash('sr-Cyrl'))
self.assertEqual(hash(Language('eng', 'US', 'Latn')), hash('en-US-Latn'))
def test_pickle(self):
for lang in [Language('fra'),
Language('eng', 'US'),
Language('srp', script='Latn'),
Language('eng', 'US', 'Latn')]:
self.assertEqual(pickle.loads(pickle.dumps(lang)), lang)
def test_str(self):
self.assertEqual(Language.fromietf(str(Language('eng', 'US', 'Latn'))), Language('eng', 'US', 'Latn'))
self.assertEqual(Language.fromietf(str(Language('fra', 'FR'))), Language('fra', 'FR'))
self.assertEqual(Language.fromietf(str(Language('bel'))), Language('bel'))
def test_register_converter(self):
class TestConverter(LanguageReverseConverter):
def __init__(self):
self.to_test = {'fra': 'test1', 'eng': 'test2'}
self.from_test = {'test1': 'fra', 'test2': 'eng'}
def convert(self, alpha3, country=None, script=None):
if alpha3 not in self.to_test:
raise LanguageConvertError(alpha3, country, script)
return self.to_test[alpha3]
def reverse(self, test):
if test not in self.from_test:
raise LanguageReverseError(test)
return (self.from_test[test], None)
language = Language('fra')
self.assertFalse(hasattr(language, 'test'))
language_converters['test'] = TestConverter()
self.assertTrue(hasattr(language, 'test'))
self.assertIn('test', language_converters)
self.assertEqual(Language('fra').test, 'test1')
self.assertEqual(Language.fromtest('test2').alpha3, 'eng')
del language_converters['test']
self.assertNotIn('test', language_converters)
self.assertRaises(KeyError, lambda: Language.fromtest('test1'))
self.assertRaises(AttributeError, lambda: Language('fra').test)
def suite():
suite = TestSuite()
suite.addTest(TestLoader().loadTestsFromTestCase(TestScript))
suite.addTest(TestLoader().loadTestsFromTestCase(TestCountry))
suite.addTest(TestLoader().loadTestsFromTestCase(TestLanguage))
return suite
if __name__ == '__main__':
TextTestRunner().run(suite())
@@ -1,25 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
__title__ = 'babelfish'
__version__ = '0.5.5-dev'
__author__ = 'Antoine Bertin'
__license__ = 'BSD'
__copyright__ = 'Copyright 2015 the BabelFish authors'
import sys
if sys.version_info[0] >= 3:
basestr = str
else:
basestr = basestring
from .converters import (LanguageConverter, LanguageReverseConverter, LanguageEquivalenceConverter, CountryConverter,
CountryReverseConverter)
from .country import country_converters, COUNTRIES, COUNTRY_MATRIX, Country
from .exceptions import Error, LanguageConvertError, LanguageReverseError, CountryConvertError, CountryReverseError
from .language import language_converters, LANGUAGES, LANGUAGE_MATRIX, Language
from .script import SCRIPTS, SCRIPT_MATRIX, Script
@@ -1,287 +0,0 @@
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
import collections
from pkg_resources import iter_entry_points, EntryPoint
from ..exceptions import LanguageConvertError, LanguageReverseError
# from https://github.com/kennethreitz/requests/blob/master/requests/structures.py
class CaseInsensitiveDict(collections.MutableMapping):
"""A case-insensitive ``dict``-like object.
Implements all methods and operations of
``collections.MutableMapping`` as well as dict's ``copy``. Also
provides ``lower_items``.
All keys are expected to be strings. The structure remembers the
case of the last key to be set, and ``iter(instance)``,
``keys()``, ``items()``, ``iterkeys()``, and ``iteritems()``
will contain case-sensitive keys. However, querying and contains
testing is case insensitive:
cid = CaseInsensitiveDict()
cid['English'] = 'eng'
cid['ENGLISH'] == 'eng' # True
list(cid) == ['English'] # True
If the constructor, ``.update``, or equality comparison
operations are given keys that have equal ``.lower()``s, the
behavior is undefined.
"""
def __init__(self, data=None, **kwargs):
self._store = dict()
if data is None:
data = {}
self.update(data, **kwargs)
def __setitem__(self, key, value):
# Use the lowercased key for lookups, but store the actual
# key alongside the value.
self._store[key.lower()] = (key, value)
def __getitem__(self, key):
return self._store[key.lower()][1]
def __delitem__(self, key):
del self._store[key.lower()]
def __iter__(self):
return (casedkey for casedkey, mappedvalue in self._store.values())
def __len__(self):
return len(self._store)
def lower_items(self):
"""Like iteritems(), but with all lowercase keys."""
return (
(lowerkey, keyval[1])
for (lowerkey, keyval)
in self._store.items()
)
def __eq__(self, other):
if isinstance(other, collections.Mapping):
other = CaseInsensitiveDict(other)
else:
return NotImplemented
# Compare insensitively
return dict(self.lower_items()) == dict(other.lower_items())
# Copy is required
def copy(self):
return CaseInsensitiveDict(self._store.values())
def __repr__(self):
return '%s(%r)' % (self.__class__.__name__, dict(self.items()))
class LanguageConverter(object):
"""A :class:`LanguageConverter` supports converting an alpha3 language code with an
alpha2 country code and a script code into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha3, country=None, script=None):
"""Convert an alpha3 language code with an alpha2 country code and a script code
into a custom code
:param string alpha3: ISO-639-3 language code
:param country: ISO-3166 country code, if any
:type country: string or None
:param script: ISO-15924 script code, if any
:type script: string or None
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.LanguageConvertError`
"""
raise NotImplementedError
class LanguageReverseConverter(LanguageConverter):
"""A :class:`LanguageConverter` able to reverse a custom code into a alpha3
ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
"""
def reverse(self, code):
"""Reverse a custom code into alpha3, country and script code
:param string code: custom code to reverse
:return: the corresponding alpha3 ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
:rtype: tuple
:raise: :class:`~babelfish.exceptions.LanguageReverseError`
"""
raise NotImplementedError
class LanguageEquivalenceConverter(LanguageReverseConverter):
"""A :class:`LanguageEquivalenceConverter` is a utility class that allows you to easily define a
:class:`LanguageReverseConverter` by only specifying the dict from alpha3 to their corresponding symbols.
You must specify the dict of equivalence as a class variable named SYMBOLS.
If you also set the class variable CASE_SENSITIVE to ``True`` then the reverse conversion function will be
case-sensitive (it is case-insensitive by default).
Example::
class MyCodeConverter(babelfish.LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {'fra': 'mycode1', 'eng': 'mycode2'}
"""
CASE_SENSITIVE = False
def __init__(self):
self.codes = set()
self.to_symbol = {}
if self.CASE_SENSITIVE:
self.from_symbol = {}
else:
self.from_symbol = CaseInsensitiveDict()
for alpha3, symbol in self.SYMBOLS.items():
self.to_symbol[alpha3] = symbol
self.from_symbol[symbol] = (alpha3, None, None)
self.codes.add(symbol)
def convert(self, alpha3, country=None, script=None):
try:
return self.to_symbol[alpha3]
except KeyError:
raise LanguageConvertError(alpha3, country, script)
def reverse(self, code):
try:
return self.from_symbol[code]
except KeyError:
raise LanguageReverseError(code)
class CountryConverter(object):
"""A :class:`CountryConverter` supports converting an alpha2 country code
into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha2):
"""Convert an alpha2 country code into a custom code
:param string alpha2: ISO-3166-1 language code
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryConvertError`
"""
raise NotImplementedError
class CountryReverseConverter(CountryConverter):
"""A :class:`CountryConverter` able to reverse a custom code into a alpha2
ISO-3166-1 country code
"""
def reverse(self, code):
"""Reverse a custom code into alpha2 code
:param string code: custom code to reverse
:return: the corresponding alpha2 ISO-3166-1 country code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryReverseError`
"""
raise NotImplementedError
class ConverterManager(object):
"""Manager for babelfish converters behaving like a dict with lazy loading
Loading is done in this order:
* Entry point converters
* Registered converters
* Internal converters
.. attribute:: entry_point
The entry point where to look for converters
.. attribute:: internal_converters
Internal converters with entry point syntax
"""
entry_point = ''
internal_converters = []
def __init__(self):
#: Registered converters with entry point syntax
self.registered_converters = []
#: Loaded converters
self.converters = {}
def __getitem__(self, name):
"""Get a converter, lazy loading it if necessary"""
if name in self.converters:
return self.converters[name]
for ep in iter_entry_points(self.entry_point):
if ep.name == name:
self.converters[ep.name] = ep.load()()
return self.converters[ep.name]
for ep in (EntryPoint.parse(c) for c in self.registered_converters + self.internal_converters):
if ep.name == name:
# `require` argument of ep.load() is deprecated in newer versions of setuptools
if hasattr(ep, 'resolve'):
plugin = ep.resolve()
elif hasattr(ep, '_load'):
plugin = ep._load()
else:
plugin = ep.load(require=False)
self.converters[ep.name] = plugin()
return self.converters[ep.name]
raise KeyError(name)
def __setitem__(self, name, converter):
"""Load a converter"""
self.converters[name] = converter
def __delitem__(self, name):
"""Unload a converter"""
del self.converters[name]
def __iter__(self):
"""Iterator over loaded converters"""
return iter(self.converters)
def register(self, entry_point):
"""Register a converter
:param string entry_point: converter to register (entry point syntax)
:raise: ValueError if already registered
"""
if entry_point in self.registered_converters:
raise ValueError('Already registered')
self.registered_converters.insert(0, entry_point)
def unregister(self, entry_point):
"""Unregister a converter
:param string entry_point: converter to unregister (entry point syntax)
"""
self.registered_converters.remove(entry_point)
def __contains__(self, name):
return name in self.converters
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha2Converter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha2:
SYMBOLS[iso_language.alpha3] = iso_language.alpha2
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3BConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3b:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3b
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3TConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3t:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3t
@@ -1,31 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import CountryReverseConverter, CaseInsensitiveDict
from ..country import COUNTRY_MATRIX
from ..exceptions import CountryConvertError, CountryReverseError
class CountryNameConverter(CountryReverseConverter):
def __init__(self):
self.codes = set()
self.to_name = {}
self.from_name = CaseInsensitiveDict()
for country in COUNTRY_MATRIX:
self.codes.add(country.name)
self.to_name[country.alpha2] = country.name
self.from_name[country.name] = country.alpha2
def convert(self, alpha2):
if alpha2 not in self.to_name:
raise CountryConvertError(alpha2)
return self.to_name[alpha2]
def reverse(self, name):
if name not in self.from_name:
raise CountryReverseError(name)
return self.from_name[name]
@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class NameConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = False
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.name:
SYMBOLS[iso_language.alpha3] = iso_language.name
@@ -1,36 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageReverseConverter, CaseInsensitiveDict
from ..exceptions import LanguageReverseError
from ..language import language_converters
class OpenSubtitlesConverter(LanguageReverseConverter):
def __init__(self):
self.alpha3b_converter = language_converters['alpha3b']
self.alpha2_converter = language_converters['alpha2']
self.to_opensubtitles = {('por', 'BR'): 'pob', ('gre', None): 'ell', ('srp', None): 'scc', ('srp', 'ME'): 'mne'}
self.from_opensubtitles = CaseInsensitiveDict({'pob': ('por', 'BR'), 'pb': ('por', 'BR'), 'ell': ('ell', None),
'scc': ('srp', None), 'mne': ('srp', 'ME')})
self.codes = (self.alpha2_converter.codes | self.alpha3b_converter.codes | set(self.from_opensubtitles.keys()))
def convert(self, alpha3, country=None, script=None):
alpha3b = self.alpha3b_converter.convert(alpha3, country, script)
if (alpha3b, country) in self.to_opensubtitles:
return self.to_opensubtitles[(alpha3b, country)]
return alpha3b
def reverse(self, opensubtitles):
if opensubtitles in self.from_opensubtitles:
return self.from_opensubtitles[opensubtitles]
for conv in [self.alpha3b_converter, self.alpha2_converter]:
try:
return conv.reverse(opensubtitles)
except LanguageReverseError:
pass
raise LanguageReverseError(opensubtitles)
@@ -1,23 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class ScopeConverter(LanguageConverter):
FULLNAME = {'I': 'individual', 'M': 'macrolanguage', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.scope
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)
@@ -1,23 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class LanguageTypeConverter(LanguageConverter):
FULLNAME = {'A': 'ancient', 'C': 'constructed', 'E': 'extinct', 'H': 'historical', 'L': 'living', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.type
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)
@@ -1,107 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
from pkg_resources import resource_stream # @UnresolvedImport
from .converters import ConverterManager
from . import basestr
COUNTRIES = {}
COUNTRY_MATRIX = []
#: The namedtuple used in the :data:`COUNTRY_MATRIX`
IsoCountry = namedtuple('IsoCountry', ['name', 'alpha2'])
f = resource_stream('babelfish', 'data/iso-3166-1.txt')
f.readline()
for l in f:
iso_country = IsoCountry(*l.decode('utf-8').strip().split(';'))
COUNTRIES[iso_country.alpha2] = iso_country.name
COUNTRY_MATRIX.append(iso_country)
f.close()
class CountryConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for country converters"""
entry_point = 'babelfish.country_converters'
internal_converters = ['name = babelfish.converters.countryname:CountryNameConverter']
country_converters = CountryConverterManager()
class CountryMeta(type):
"""The :class:`Country` metaclass
Dynamically redirect :meth:`Country.frommycode` to :meth:`Country.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Country(CountryMeta(str('CountryBase'), (object,), {})):
"""A country on Earth
A country is represented by a 2-letter code from the ISO-3166 standard
:param string country: 2-letter ISO-3166 country code
"""
def __init__(self, country):
if country not in COUNTRIES:
raise ValueError('%r is not a valid country' % country)
#: ISO-3166 2-letter country code
self.alpha2 = country
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Country` by its `code` using `converter` to
:meth:`~babelfish.converters.CountryReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.CountryReverseConverter` to use
:return: the corresponding :class:`Country` instance
:rtype: :class:`Country`
"""
return cls(country_converters[converter].reverse(code))
def __getstate__(self):
return self.alpha2
def __setstate__(self, state):
self.alpha2 = state
def __getattr__(self, name):
try:
return country_converters[name].convert(self.alpha2)
except KeyError:
raise AttributeError(name)
def __hash__(self):
return hash(self.alpha2)
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Country):
return False
return self.alpha2 == other.alpha2
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Country [%s]>' % self
def __str__(self):
return self.alpha2
@@ -1,45 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
import os.path
import tempfile
import zipfile
import requests
DATA_DIR = os.path.dirname(__file__)
# iso-3166-1.txt
print('Downloading ISO-3166-1 standard (ISO country codes)...')
with open(os.path.join(DATA_DIR, 'iso-3166-1.txt'), 'w') as f:
r = requests.get('http://www.iso.org/iso/home/standards/country_codes/country_names_and_code_elements_txt.htm')
f.write(r.content.strip())
# iso-639-3.tab
print('Downloading ISO-639-3 standard (ISO language codes)...')
with tempfile.TemporaryFile() as f:
r = requests.get('http://www-01.sil.org/iso639-3/iso-639-3_Code_Tables_20130531.zip')
f.write(r.content)
with zipfile.ZipFile(f) as z:
z.extract('iso-639-3.tab', DATA_DIR)
# iso-15924
print('Downloading ISO-15924 standard (ISO script codes)...')
with tempfile.TemporaryFile() as f:
r = requests.get('http://www.unicode.org/iso15924/iso15924.txt.zip')
f.write(r.content)
with zipfile.ZipFile(f) as z:
z.extract('iso15924-utf8-20131012.txt', DATA_DIR)
# opensubtitles supported languages
print('Downloading OpenSubtitles supported languages...')
with open(os.path.join(DATA_DIR, 'opensubtitles_languages.txt'), 'w') as f:
r = requests.get('http://www.opensubtitles.org/addons/export_languages.php')
f.write(r.content)
print('Done!')
@@ -1,250 +0,0 @@
Country Name;ISO 3166-1-alpha-2 code
AFGHANISTAN;AF
ÅLAND ISLANDS;AX
ALBANIA;AL
ALGERIA;DZ
AMERICAN SAMOA;AS
ANDORRA;AD
ANGOLA;AO
ANGUILLA;AI
ANTARCTICA;AQ
ANTIGUA AND BARBUDA;AG
ARGENTINA;AR
ARMENIA;AM
ARUBA;AW
AUSTRALIA;AU
AUSTRIA;AT
AZERBAIJAN;AZ
BAHAMAS;BS
BAHRAIN;BH
BANGLADESH;BD
BARBADOS;BB
BELARUS;BY
BELGIUM;BE
BELIZE;BZ
BENIN;BJ
BERMUDA;BM
BHUTAN;BT
BOLIVIA, PLURINATIONAL STATE OF;BO
BONAIRE, SINT EUSTATIUS AND SABA;BQ
BOSNIA AND HERZEGOVINA;BA
BOTSWANA;BW
BOUVET ISLAND;BV
BRAZIL;BR
BRITISH INDIAN OCEAN TERRITORY;IO
BRUNEI DARUSSALAM;BN
BULGARIA;BG
BURKINA FASO;BF
BURUNDI;BI
CAMBODIA;KH
CAMEROON;CM
CANADA;CA
CAPE VERDE;CV
CAYMAN ISLANDS;KY
CENTRAL AFRICAN REPUBLIC;CF
CHAD;TD
CHILE;CL
CHINA;CN
CHRISTMAS ISLAND;CX
COCOS (KEELING) ISLANDS;CC
COLOMBIA;CO
COMOROS;KM
CONGO;CG
CONGO, THE DEMOCRATIC REPUBLIC OF THE;CD
COOK ISLANDS;CK
COSTA RICA;CR
CÔTE D'IVOIRE;CI
CROATIA;HR
CUBA;CU
CURAÇAO;CW
CYPRUS;CY
CZECH REPUBLIC;CZ
DENMARK;DK
DJIBOUTI;DJ
DOMINICA;DM
DOMINICAN REPUBLIC;DO
ECUADOR;EC
EGYPT;EG
EL SALVADOR;SV
EQUATORIAL GUINEA;GQ
ERITREA;ER
ESTONIA;EE
ETHIOPIA;ET
FALKLAND ISLANDS (MALVINAS);FK
FAROE ISLANDS;FO
FIJI;FJ
FINLAND;FI
FRANCE;FR
FRENCH GUIANA;GF
FRENCH POLYNESIA;PF
FRENCH SOUTHERN TERRITORIES;TF
GABON;GA
GAMBIA;GM
GEORGIA;GE
GERMANY;DE
GHANA;GH
GIBRALTAR;GI
GREECE;GR
GREENLAND;GL
GRENADA;GD
GUADELOUPE;GP
GUAM;GU
GUATEMALA;GT
GUERNSEY;GG
GUINEA;GN
GUINEA-BISSAU;GW
GUYANA;GY
HAITI;HT
HEARD ISLAND AND MCDONALD ISLANDS;HM
HOLY SEE (VATICAN CITY STATE);VA
HONDURAS;HN
HONG KONG;HK
HUNGARY;HU
ICELAND;IS
INDIA;IN
INDONESIA;ID
IRAN, ISLAMIC REPUBLIC OF;IR
IRAQ;IQ
IRELAND;IE
ISLE OF MAN;IM
ISRAEL;IL
ITALY;IT
JAMAICA;JM
JAPAN;JP
JERSEY;JE
JORDAN;JO
KAZAKHSTAN;KZ
KENYA;KE
KIRIBATI;KI
KOREA, DEMOCRATIC PEOPLE'S REPUBLIC OF;KP
KOREA, REPUBLIC OF;KR
KUWAIT;KW
KYRGYZSTAN;KG
LAO PEOPLE'S DEMOCRATIC REPUBLIC;LA
LATVIA;LV
LEBANON;LB
LESOTHO;LS
LIBERIA;LR
LIBYA;LY
LIECHTENSTEIN;LI
LITHUANIA;LT
LUXEMBOURG;LU
MACAO;MO
MACEDONIA, THE FORMER YUGOSLAV REPUBLIC OF;MK
MADAGASCAR;MG
MALAWI;MW
MALAYSIA;MY
MALDIVES;MV
MALI;ML
MALTA;MT
MARSHALL ISLANDS;MH
MARTINIQUE;MQ
MAURITANIA;MR
MAURITIUS;MU
MAYOTTE;YT
MEXICO;MX
MICRONESIA, FEDERATED STATES OF;FM
MOLDOVA, REPUBLIC OF;MD
MONACO;MC
MONGOLIA;MN
MONTENEGRO;ME
MONTSERRAT;MS
MOROCCO;MA
MOZAMBIQUE;MZ
MYANMAR;MM
NAMIBIA;NA
NAURU;NR
NEPAL;NP
NETHERLANDS;NL
NEW CALEDONIA;NC
NEW ZEALAND;NZ
NICARAGUA;NI
NIGER;NE
NIGERIA;NG
NIUE;NU
NORFOLK ISLAND;NF
NORTHERN MARIANA ISLANDS;MP
NORWAY;NO
OMAN;OM
PAKISTAN;PK
PALAU;PW
PALESTINE, STATE OF;PS
PANAMA;PA
PAPUA NEW GUINEA;PG
PARAGUAY;PY
PERU;PE
PHILIPPINES;PH
PITCAIRN;PN
POLAND;PL
PORTUGAL;PT
PUERTO RICO;PR
QATAR;QA
RÉUNION;RE
ROMANIA;RO
RUSSIAN FEDERATION;RU
RWANDA;RW
SAINT BARTHÉLEMY;BL
SAINT HELENA, ASCENSION AND TRISTAN DA CUNHA;SH
SAINT KITTS AND NEVIS;KN
SAINT LUCIA;LC
SAINT MARTIN (FRENCH PART);MF
SAINT PIERRE AND MIQUELON;PM
SAINT VINCENT AND THE GRENADINES;VC
SAMOA;WS
SAN MARINO;SM
SAO TOME AND PRINCIPE;ST
SAUDI ARABIA;SA
SENEGAL;SN
SERBIA;RS
SEYCHELLES;SC
SIERRA LEONE;SL
SINGAPORE;SG
SINT MAARTEN (DUTCH PART);SX
SLOVAKIA;SK
SLOVENIA;SI
SOLOMON ISLANDS;SB
SOMALIA;SO
SOUTH AFRICA;ZA
SOUTH GEORGIA AND THE SOUTH SANDWICH ISLANDS;GS
SOUTH SUDAN;SS
SPAIN;ES
SRI LANKA;LK
SUDAN;SD
SURINAME;SR
SVALBARD AND JAN MAYEN;SJ
SWAZILAND;SZ
SWEDEN;SE
SWITZERLAND;CH
SYRIAN ARAB REPUBLIC;SY
TAIWAN, PROVINCE OF CHINA;TW
TAJIKISTAN;TJ
TANZANIA, UNITED REPUBLIC OF;TZ
THAILAND;TH
TIMOR-LESTE;TL
TOGO;TG
TOKELAU;TK
TONGA;TO
TRINIDAD AND TOBAGO;TT
TUNISIA;TN
TURKEY;TR
TURKMENISTAN;TM
TURKS AND CAICOS ISLANDS;TC
TUVALU;TV
UGANDA;UG
UKRAINE;UA
UNITED ARAB EMIRATES;AE
UNITED KINGDOM;GB
UNITED STATES;US
UNITED STATES MINOR OUTLYING ISLANDS;UM
URUGUAY;UY
UZBEKISTAN;UZ
VANUATU;VU
VENEZUELA, BOLIVARIAN REPUBLIC OF;VE
VIET NAM;VN
VIRGIN ISLANDS, BRITISH;VG
VIRGIN ISLANDS, U.S.;VI
WALLIS AND FUTUNA;WF
WESTERN SAHARA;EH
YEMEN;YE
ZAMBIA;ZM
ZIMBABWE;ZW
File diff suppressed because it is too large Load Diff
@@ -1,176 +0,0 @@
#
# ISO 15924 - Codes for the representation of names of scripts
# Codes pour la représentation des noms d’écritures
# Format:
# Code;N°;English Name;Nom français;PVA;Date
#
Afak;439;Afaka;afaka;;2010-12-21
Aghb;239;Caucasian Albanian;aghbanien;;2012-10-16
Ahom;338;Ahom, Tai Ahom;âhom;;2012-11-01
Arab;160;Arabic;arabe;Arabic;2004-05-01
Armi;124;Imperial Aramaic;araméen impérial;Imperial_Aramaic;2009-06-01
Armn;230;Armenian;arménien;Armenian;2004-05-01
Avst;134;Avestan;avestique;Avestan;2009-06-01
Bali;360;Balinese;balinais;Balinese;2006-10-10
Bamu;435;Bamum;bamoum;Bamum;2009-06-01
Bass;259;Bassa Vah;bassa;;2010-03-26
Batk;365;Batak;batik;Batak;2010-07-23
Beng;325;Bengali;bengalî;Bengali;2004-05-01
Blis;550;Blissymbols;symboles Bliss;;2004-05-01
Bopo;285;Bopomofo;bopomofo;Bopomofo;2004-05-01
Brah;300;Brahmi;brahma;Brahmi;2010-07-23
Brai;570;Braille;braille;Braille;2004-05-01
Bugi;367;Buginese;bouguis;Buginese;2006-06-21
Buhd;372;Buhid;bouhide;Buhid;2004-05-01
Cakm;349;Chakma;chakma;Chakma;2012-02-06
Cans;440;Unified Canadian Aboriginal Syllabics;syllabaire autochtone canadien unifié;Canadian_Aboriginal;2004-05-29
Cari;201;Carian;carien;Carian;2007-07-02
Cham;358;Cham;cham (čam, tcham);Cham;2009-11-11
Cher;445;Cherokee;tchérokî;Cherokee;2004-05-01
Cirt;291;Cirth;cirth;;2004-05-01
Copt;204;Coptic;copte;Coptic;2006-06-21
Cprt;403;Cypriot;syllabaire chypriote;Cypriot;2004-05-01
Cyrl;220;Cyrillic;cyrillique;Cyrillic;2004-05-01
Cyrs;221;Cyrillic (Old Church Slavonic variant);cyrillique (variante slavonne);;2004-05-01
Deva;315;Devanagari (Nagari);dévanâgarî;Devanagari;2004-05-01
Dsrt;250;Deseret (Mormon);déseret (mormon);Deseret;2004-05-01
Dupl;755;Duployan shorthand, Duployan stenography;sténographie Duployé;;2010-07-18
Egyd;070;Egyptian demotic;démotique égyptien;;2004-05-01
Egyh;060;Egyptian hieratic;hiératique égyptien;;2004-05-01
Egyp;050;Egyptian hieroglyphs;hiéroglyphes égyptiens;Egyptian_Hieroglyphs;2009-06-01
Elba;226;Elbasan;elbasan;;2010-07-18
Ethi;430;Ethiopic (Geʻez);éthiopien (geʻez, guèze);Ethiopic;2004-10-25
Geor;240;Georgian (Mkhedruli);géorgien (mkhédrouli);Georgian;2004-05-29
Geok;241;Khutsuri (Asomtavruli and Nuskhuri);khoutsouri (assomtavrouli et nouskhouri);Georgian;2012-10-16
Glag;225;Glagolitic;glagolitique;Glagolitic;2006-06-21
Goth;206;Gothic;gotique;Gothic;2004-05-01
Gran;343;Grantha;grantha;;2009-11-11
Grek;200;Greek;grec;Greek;2004-05-01
Gujr;320;Gujarati;goudjarâtî (gujrâtî);Gujarati;2004-05-01
Guru;310;Gurmukhi;gourmoukhî;Gurmukhi;2004-05-01
Hang;286;Hangul (Hangŭl, Hangeul);hangûl (hangŭl, hangeul);Hangul;2004-05-29
Hani;500;Han (Hanzi, Kanji, Hanja);idéogrammes han (sinogrammes);Han;2009-02-23
Hano;371;Hanunoo (Hanunóo);hanounóo;Hanunoo;2004-05-29
Hans;501;Han (Simplified variant);idéogrammes han (variante simplifiée);;2004-05-29
Hant;502;Han (Traditional variant);idéogrammes han (variante traditionnelle);;2004-05-29
Hatr;127;Hatran;hatrénien;;2012-11-01
Hebr;125;Hebrew;hébreu;Hebrew;2004-05-01
Hira;410;Hiragana;hiragana;Hiragana;2004-05-01
Hluw;080;Anatolian Hieroglyphs (Luwian Hieroglyphs, Hittite Hieroglyphs);hiéroglyphes anatoliens (hiéroglyphes louvites, hiéroglyphes hittites);;2011-12-09
Hmng;450;Pahawh Hmong;pahawh hmong;;2004-05-01
Hrkt;412;Japanese syllabaries (alias for Hiragana + Katakana);syllabaires japonais (alias pour hiragana + katakana);Katakana_Or_Hiragana;2011-06-21
Hung;176;Old Hungarian (Hungarian Runic);runes hongroises (ancien hongrois);;2012-10-16
Inds;610;Indus (Harappan);indus;;2004-05-01
Ital;210;Old Italic (Etruscan, Oscan, etc.);ancien italique (étrusque, osque, etc.);Old_Italic;2004-05-29
Java;361;Javanese;javanais;Javanese;2009-06-01
Jpan;413;Japanese (alias for Han + Hiragana + Katakana);japonais (alias pour han + hiragana + katakana);;2006-06-21
Jurc;510;Jurchen;jurchen;;2010-12-21
Kali;357;Kayah Li;kayah li;Kayah_Li;2007-07-02
Kana;411;Katakana;katakana;Katakana;2004-05-01
Khar;305;Kharoshthi;kharochthî;Kharoshthi;2006-06-21
Khmr;355;Khmer;khmer;Khmer;2004-05-29
Khoj;322;Khojki;khojkî;;2011-06-21
Knda;345;Kannada;kannara (canara);Kannada;2004-05-29
Kore;287;Korean (alias for Hangul + Han);coréen (alias pour hangûl + han);;2007-06-13
Kpel;436;Kpelle;kpèllé;;2010-03-26
Kthi;317;Kaithi;kaithî;Kaithi;2009-06-01
Lana;351;Tai Tham (Lanna);taï tham (lanna);Tai_Tham;2009-06-01
Laoo;356;Lao;laotien;Lao;2004-05-01
Latf;217;Latin (Fraktur variant);latin (variante brisée);;2004-05-01
Latg;216;Latin (Gaelic variant);latin (variante gaélique);;2004-05-01
Latn;215;Latin;latin;Latin;2004-05-01
Lepc;335;Lepcha (Róng);lepcha (róng);Lepcha;2007-07-02
Limb;336;Limbu;limbou;Limbu;2004-05-29
Lina;400;Linear A;linéaire A;;2004-05-01
Linb;401;Linear B;linéaire B;Linear_B;2004-05-29
Lisu;399;Lisu (Fraser);lisu (Fraser);Lisu;2009-06-01
Loma;437;Loma;loma;;2010-03-26
Lyci;202;Lycian;lycien;Lycian;2007-07-02
Lydi;116;Lydian;lydien;Lydian;2007-07-02
Mahj;314;Mahajani;mahâjanî;;2012-10-16
Mand;140;Mandaic, Mandaean;mandéen;Mandaic;2010-07-23
Mani;139;Manichaean;manichéen;;2007-07-15
Maya;090;Mayan hieroglyphs;hiéroglyphes mayas;;2004-05-01
Mend;438;Mende Kikakui;mendé kikakui;;2013-10-12
Merc;101;Meroitic Cursive;cursif méroïtique;Meroitic_Cursive;2012-02-06
Mero;100;Meroitic Hieroglyphs;hiéroglyphes méroïtiques;Meroitic_Hieroglyphs;2012-02-06
Mlym;347;Malayalam;malayâlam;Malayalam;2004-05-01
Modi;323;Modi, Moḍī;modî;;2013-10-12
Moon;218;Moon (Moon code, Moon script, Moon type);écriture Moon;;2006-12-11
Mong;145;Mongolian;mongol;Mongolian;2004-05-01
Mroo;199;Mro, Mru;mro;;2010-12-21
Mtei;337;Meitei Mayek (Meithei, Meetei);meitei mayek;Meetei_Mayek;2009-06-01
Mult;323; Multani;multanî;;2012-11-01
Mymr;350;Myanmar (Burmese);birman;Myanmar;2004-05-01
Narb;106;Old North Arabian (Ancient North Arabian);nord-arabique;;2010-03-26
Nbat;159;Nabataean;nabatéen;;2010-03-26
Nkgb;420;Nakhi Geba ('Na-'Khi ²Ggŏ-¹baw, Naxi Geba);nakhi géba;;2009-02-23
Nkoo;165;NKo;nko;Nko;2006-10-10
Nshu;499;Nüshu;nüshu;;2010-12-21
Ogam;212;Ogham;ogam;Ogham;2004-05-01
Olck;261;Ol Chiki (Ol Cemet, Ol, Santali);ol tchiki;Ol_Chiki;2007-07-02
Orkh;175;Old Turkic, Orkhon Runic;orkhon;Old_Turkic;2009-06-01
Orya;327;Oriya;oriyâ;Oriya;2004-05-01
Osma;260;Osmanya;osmanais;Osmanya;2004-05-01
Palm;126;Palmyrene;palmyrénien;;2010-03-26
Pauc;263;Pau Cin Hau;paou chin haou;;2013-10-12
Perm;227;Old Permic;ancien permien;;2004-05-01
Phag;331;Phags-pa;phags pa;Phags_Pa;2006-10-10
Phli;131;Inscriptional Pahlavi;pehlevi des inscriptions;Inscriptional_Pahlavi;2009-06-01
Phlp;132;Psalter Pahlavi;pehlevi des psautiers;;2007-11-26
Phlv;133;Book Pahlavi;pehlevi des livres;;2007-07-15
Phnx;115;Phoenician;phénicien;Phoenician;2006-10-10
Plrd;282;Miao (Pollard);miao (Pollard);Miao;2012-02-06
Prti;130;Inscriptional Parthian;parthe des inscriptions;Inscriptional_Parthian;2009-06-01
Qaaa;900;Reserved for private use (start);réservé à lusage privé (début);;2004-05-29
Qabx;949;Reserved for private use (end);réservé à lusage privé (fin);;2004-05-29
Rjng;363;Rejang (Redjang, Kaganga);redjang (kaganga);Rejang;2009-02-23
Roro;620;Rongorongo;rongorongo;;2004-05-01
Runr;211;Runic;runique;Runic;2004-05-01
Samr;123;Samaritan;samaritain;Samaritan;2009-06-01
Sara;292;Sarati;sarati;;2004-05-29
Sarb;105;Old South Arabian;sud-arabique, himyarite;Old_South_Arabian;2009-06-01
Saur;344;Saurashtra;saurachtra;Saurashtra;2007-07-02
Sgnw;095;SignWriting;SignÉcriture, SignWriting;;2006-10-10
Shaw;281;Shavian (Shaw);shavien (Shaw);Shavian;2004-05-01
Shrd;319;Sharada, Śāradā;charada, shard;Sharada;2012-02-06
Sidd;302;Siddham, Siddhaṃ, Siddhamātṛkā;siddham;;2013-10-12
Sind;318;Khudawadi, Sindhi;khoudawadî, sindhî;;2010-12-21
Sinh;348;Sinhala;singhalais;Sinhala;2004-05-01
Sora;398;Sora Sompeng;sora sompeng;Sora_Sompeng;2012-02-06
Sund;362;Sundanese;sundanais;Sundanese;2007-07-02
Sylo;316;Syloti Nagri;sylotî nâgrî;Syloti_Nagri;2006-06-21
Syrc;135;Syriac;syriaque;Syriac;2004-05-01
Syre;138;Syriac (Estrangelo variant);syriaque (variante estranghélo);;2004-05-01
Syrj;137;Syriac (Western variant);syriaque (variante occidentale);;2004-05-01
Syrn;136;Syriac (Eastern variant);syriaque (variante orientale);;2004-05-01
Tagb;373;Tagbanwa;tagbanoua;Tagbanwa;2004-05-01
Takr;321;Takri, Ṭākrī, Ṭāṅkrī;tâkrî;Takri;2012-02-06
Tale;353;Tai Le;taï-le;Tai_Le;2004-10-25
Talu;354;New Tai Lue;nouveau taï-lue;New_Tai_Lue;2006-06-21
Taml;346;Tamil;tamoul;Tamil;2004-05-01
Tang;520;Tangut;tangoute;;2010-12-21
Tavt;359;Tai Viet;taï viêt;Tai_Viet;2009-06-01
Telu;340;Telugu;télougou;Telugu;2004-05-01
Teng;290;Tengwar;tengwar;;2004-05-01
Tfng;120;Tifinagh (Berber);tifinagh (berbère);Tifinagh;2006-06-21
Tglg;370;Tagalog (Baybayin, Alibata);tagal (baybayin, alibata);Tagalog;2009-02-23
Thaa;170;Thaana;thâna;Thaana;2004-05-01
Thai;352;Thai;thaï;Thai;2004-05-01
Tibt;330;Tibetan;tibétain;Tibetan;2004-05-01
Tirh;326;Tirhuta;tirhouta;;2011-12-09
Ugar;040;Ugaritic;ougaritique;Ugaritic;2004-05-01
Vaii;470;Vai;vaï;Vai;2007-07-02
Visp;280;Visible Speech;parole visible;;2004-05-01
Wara;262;Warang Citi (Varang Kshiti);warang citi;;2009-11-11
Wole;480;Woleai;woléaï;;2010-12-21
Xpeo;030;Old Persian;cunéiforme persépolitain;Old_Persian;2006-06-21
Xsux;020;Cuneiform, Sumero-Akkadian;cunéiforme suméro-akkadien;Cuneiform;2006-10-10
Yiii;460;Yi;yi;Yi;2004-05-01
Zinh;994;Code for inherited script;codet pour écriture héritée;Inherited;2009-02-23
Zmth;995;Mathematical notation;notation mathématique;;2007-11-26
Zsym;996;Symbols;symboles;;2007-11-26
Zxxx;997;Code for unwritten documents;codet pour les documents non écrits;;2011-06-21
Zyyy;998;Code for undetermined script;codet pour écriture indéterminée;Common;2004-05-29
Zzzz;999;Code for uncoded script;codet pour écriture non codée;Unknown;2006-10-10
@@ -1,474 +0,0 @@
IdSubLanguage ISO639 LanguageName UploadEnabled WebEnabled
aar aa Afar, afar 0 0
abk ab Abkhazian 0 0
ace Achinese 0 0
ach Acoli 0 0
ada Adangme 0 0
ady adyghé 0 0
afa Afro-Asiatic (Other) 0 0
afh Afrihili 0 0
afr af Afrikaans 1 0
ain Ainu 0 0
aka ak Akan 0 0
akk Akkadian 0 0
alb sq Albanian 1 1
ale Aleut 0 0
alg Algonquian languages 0 0
alt Southern Altai 0 0
amh am Amharic 0 0
ang English, Old (ca.450-1100) 0 0
apa Apache languages 0 0
ara ar Arabic 1 1
arc Aramaic 0 0
arg an Aragonese 0 0
arm hy Armenian 1 0
arn Araucanian 0 0
arp Arapaho 0 0
art Artificial (Other) 0 0
arw Arawak 0 0
asm as Assamese 0 0
ast Asturian, Bable 0 0
ath Athapascan languages 0 0
aus Australian languages 0 0
ava av Avaric 0 0
ave ae Avestan 0 0
awa Awadhi 0 0
aym ay Aymara 0 0
aze az Azerbaijani 0 0
bad Banda 0 0
bai Bamileke languages 0 0
bak ba Bashkir 0 0
bal Baluchi 0 0
bam bm Bambara 0 0
ban Balinese 0 0
baq eu Basque 1 1
bas Basa 0 0
bat Baltic (Other) 0 0
bej Beja 0 0
bel be Belarusian 0 0
bem Bemba 0 0
ben bn Bengali 1 0
ber Berber (Other) 0 0
bho Bhojpuri 0 0
bih bh Bihari 0 0
bik Bikol 0 0
bin Bini 0 0
bis bi Bislama 0 0
bla Siksika 0 0
bnt Bantu (Other) 0 0
bos bs Bosnian 1 0
bra Braj 0 0
bre br Breton 1 0
btk Batak (Indonesia) 0 0
bua Buriat 0 0
bug Buginese 0 0
bul bg Bulgarian 1 1
bur my Burmese 1 0
byn Blin 0 0
cad Caddo 0 0
cai Central American Indian (Other) 0 0
car Carib 0 0
cat ca Catalan 1 1
cau Caucasian (Other) 0 0
ceb Cebuano 0 0
cel Celtic (Other) 0 0
cha ch Chamorro 0 0
chb Chibcha 0 0
che ce Chechen 0 0
chg Chagatai 0 0
chi zh Chinese 1 1
chk Chuukese 0 0
chm Mari 0 0
chn Chinook jargon 0 0
cho Choctaw 0 0
chp Chipewyan 0 0
chr Cherokee 0 0
chu cu Church Slavic 0 0
chv cv Chuvash 0 0
chy Cheyenne 0 0
cmc Chamic languages 0 0
cop Coptic 0 0
cor kw Cornish 0 0
cos co Corsican 0 0
cpe Creoles and pidgins, English based (Other) 0 0
cpf Creoles and pidgins, French-based (Other) 0 0
cpp Creoles and pidgins, Portuguese-based (Other) 0 0
cre cr Cree 0 0
crh Crimean Tatar 0 0
crp Creoles and pidgins (Other) 0 0
csb Kashubian 0 0
cus Cushitic (Other)' couchitiques, autres langues 0 0
cze cs Czech 1 1
dak Dakota 0 0
dan da Danish 1 1
dar Dargwa 0 0
day Dayak 0 0
del Delaware 0 0
den Slave (Athapascan) 0 0
dgr Dogrib 0 0
din Dinka 0 0
div dv Divehi 0 0
doi Dogri 0 0
dra Dravidian (Other) 0 0
dua Duala 0 0
dum Dutch, Middle (ca.1050-1350) 0 0
dut nl Dutch 1 1
dyu Dyula 0 0
dzo dz Dzongkha 0 0
efi Efik 0 0
egy Egyptian (Ancient) 0 0
eka Ekajuk 0 0
elx Elamite 0 0
eng en English 1 1
enm English, Middle (1100-1500) 0 0
epo eo Esperanto 1 0
est et Estonian 1 1
ewe ee Ewe 0 0
ewo Ewondo 0 0
fan Fang 0 0
fao fo Faroese 0 0
fat Fanti 0 0
fij fj Fijian 0 0
fil Filipino 0 0
fin fi Finnish 1 1
fiu Finno-Ugrian (Other) 0 0
fon Fon 0 0
fre fr French 1 1
frm French, Middle (ca.1400-1600) 0 0
fro French, Old (842-ca.1400) 0 0
fry fy Frisian 0 0
ful ff Fulah 0 0
fur Friulian 0 0
gaa Ga 0 0
gay Gayo 0 0
gba Gbaya 0 0
gem Germanic (Other) 0 0
geo ka Georgian 1 1
ger de German 1 1
gez Geez 0 0
gil Gilbertese 0 0
gla gd Gaelic 0 0
gle ga Irish 0 0
glg gl Galician 1 1
glv gv Manx 0 0
gmh German, Middle High (ca.1050-1500) 0 0
goh German, Old High (ca.750-1050) 0 0
gon Gondi 0 0
gor Gorontalo 0 0
got Gothic 0 0
grb Grebo 0 0
grc Greek, Ancient (to 1453) 0 0
ell el Greek 1 1
grn gn Guarani 0 0
guj gu Gujarati 0 0
gwi Gwich´in 0 0
hai Haida 0 0
hat ht Haitian 0 0
hau ha Hausa 0 0
haw Hawaiian 0 0
heb he Hebrew 1 1
her hz Herero 0 0
hil Hiligaynon 0 0
him Himachali 0 0
hin hi Hindi 1 1
hit Hittite 0 0
hmn Hmong 0 0
hmo ho Hiri Motu 0 0
hrv hr Croatian 1 1
hun hu Hungarian 1 1
hup Hupa 0 0
iba Iban 0 0
ibo ig Igbo 0 0
ice is Icelandic 1 1
ido io Ido 0 0
iii ii Sichuan Yi 0 0
ijo Ijo 0 0
iku iu Inuktitut 0 0
ile ie Interlingue 0 0
ilo Iloko 0 0
ina ia Interlingua (International Auxiliary Language Asso 0 0
inc Indic (Other) 0 0
ind id Indonesian 1 1
ine Indo-European (Other) 0 0
inh Ingush 0 0
ipk ik Inupiaq 0 0
ira Iranian (Other) 0 0
iro Iroquoian languages 0 0
ita it Italian 1 1
jav jv Javanese 0 0
jpn ja Japanese 1 1
jpr Judeo-Persian 0 0
jrb Judeo-Arabic 0 0
kaa Kara-Kalpak 0 0
kab Kabyle 0 0
kac Kachin 0 0
kal kl Kalaallisut 0 0
kam Kamba 0 0
kan kn Kannada 0 0
kar Karen 0 0
kas ks Kashmiri 0 0
kau kr Kanuri 0 0
kaw Kawi 0 0
kaz kk Kazakh 1 0
kbd Kabardian 0 0
kha Khasi 0 0
khi Khoisan (Other) 0 0
khm km Khmer 1 1
kho Khotanese 0 0
kik ki Kikuyu 0 0
kin rw Kinyarwanda 0 0
kir ky Kirghiz 0 0
kmb Kimbundu 0 0
kok Konkani 0 0
kom kv Komi 0 0
kon kg Kongo 0 0
kor ko Korean 1 1
kos Kosraean 0 0
kpe Kpelle 0 0
krc Karachay-Balkar 0 0
kro Kru 0 0
kru Kurukh 0 0
kua kj Kuanyama 0 0
kum Kumyk 0 0
kur ku Kurdish 0 0
kut Kutenai 0 0
lad Ladino 0 0
lah Lahnda 0 0
lam Lamba 0 0
lao lo Lao 0 0
lat la Latin 0 0
lav lv Latvian 1 0
lez Lezghian 0 0
lim li Limburgan 0 0
lin ln Lingala 0 0
lit lt Lithuanian 1 0
lol Mongo 0 0
loz Lozi 0 0
ltz lb Luxembourgish 1 0
lua Luba-Lulua 0 0
lub lu Luba-Katanga 0 0
lug lg Ganda 0 0
lui Luiseno 0 0
lun Lunda 0 0
luo Luo (Kenya and Tanzania) 0 0
lus lushai 0 0
mac mk Macedonian 1 1
mad Madurese 0 0
mag Magahi 0 0
mah mh Marshallese 0 0
mai Maithili 0 0
mak Makasar 0 0
mal ml Malayalam 1 0
man Mandingo 0 0
mao mi Maori 0 0
map Austronesian (Other) 0 0
mar mr Marathi 0 0
mas Masai 0 0
may ms Malay 1 1
mdf Moksha 0 0
mdr Mandar 0 0
men Mende 0 0
mga Irish, Middle (900-1200) 0 0
mic Mi'kmaq 0 0
min Minangkabau 0 0
mis Miscellaneous languages 0 0
mkh Mon-Khmer (Other) 0 0
mlg mg Malagasy 0 0
mlt mt Maltese 0 0
mnc Manchu 0 0
mni Manipuri 0 0
mno Manobo languages 0 0
moh Mohawk 0 0
mol mo Moldavian 0 0
mon mn Mongolian 1 0
mos Mossi 0 0
mwl Mirandese 0 0
mul Multiple languages 0 0
mun Munda languages 0 0
mus Creek 0 0
mwr Marwari 0 0
myn Mayan languages 0 0
myv Erzya 0 0
nah Nahuatl 0 0
nai North American Indian 0 0
nap Neapolitan 0 0
nau na Nauru 0 0
nav nv Navajo 0 0
nbl nr Ndebele, South 0 0
nde nd Ndebele, North 0 0
ndo ng Ndonga 0 0
nds Low German 0 0
nep ne Nepali 0 0
new Nepal Bhasa 0 0
nia Nias 0 0
nic Niger-Kordofanian (Other) 0 0
niu Niuean 0 0
nno nn Norwegian Nynorsk 0 0
nob nb Norwegian Bokmal 0 0
nog Nogai 0 0
non Norse, Old 0 0
nor no Norwegian 1 1
nso Northern Sotho 0 0
nub Nubian languages 0 0
nwc Classical Newari 0 0
nya ny Chichewa 0 0
nym Nyamwezi 0 0
nyn Nyankole 0 0
nyo Nyoro 0 0
nzi Nzima 0 0
oci oc Occitan 1 1
oji oj Ojibwa 0 0
ori or Oriya 0 0
orm om Oromo 0 0
osa Osage 0 0
oss os Ossetian 0 0
ota Turkish, Ottoman (1500-1928) 0 0
oto Otomian languages 0 0
paa Papuan (Other) 0 0
pag Pangasinan 0 0
pal Pahlavi 0 0
pam Pampanga 0 0
pan pa Panjabi 0 0
pap Papiamento 0 0
pau Palauan 0 0
peo Persian, Old (ca.600-400 B.C.) 0 0
per fa Persian 1 1
phi Philippine (Other) 0 0
phn Phoenician 0 0
pli pi Pali 0 0
pol pl Polish 1 1
pon Pohnpeian 0 0
por pt Portuguese 1 1
pra Prakrit languages 0 0
pro Provençal, Old (to 1500) 0 0
pus ps Pushto 0 0
que qu Quechua 0 0
raj Rajasthani 0 0
rap Rapanui 0 0
rar Rarotongan 0 0
roa Romance (Other) 0 0
roh rm Raeto-Romance 0 0
rom Romany 0 0
run rn Rundi 0 0
rup Aromanian 0 0
rus ru Russian 1 1
sad Sandawe 0 0
sag sg Sango 0 0
sah Yakut 0 0
sai South American Indian (Other) 0 0
sal Salishan languages 0 0
sam Samaritan Aramaic 0 0
san sa Sanskrit 0 0
sas Sasak 0 0
sat Santali 0 0
scc sr Serbian 1 1
scn Sicilian 0 0
sco Scots 0 0
sel Selkup 0 0
sem Semitic (Other) 0 0
sga Irish, Old (to 900) 0 0
sgn Sign Languages 0 0
shn Shan 0 0
sid Sidamo 0 0
sin si Sinhalese 1 1
sio Siouan languages 0 0
sit Sino-Tibetan (Other) 0 0
sla Slavic (Other) 0 0
slo sk Slovak 1 1
slv sl Slovenian 1 1
sma Southern Sami 0 0
sme se Northern Sami 0 0
smi Sami languages (Other) 0 0
smj Lule Sami 0 0
smn Inari Sami 0 0
smo sm Samoan 0 0
sms Skolt Sami 0 0
sna sn Shona 0 0
snd sd Sindhi 0 0
snk Soninke 0 0
sog Sogdian 0 0
som so Somali 0 0
son Songhai 0 0
sot st Sotho, Southern 0 0
spa es Spanish 1 1
srd sc Sardinian 0 0
srr Serer 0 0
ssa Nilo-Saharan (Other) 0 0
ssw ss Swati 0 0
suk Sukuma 0 0
sun su Sundanese 0 0
sus Susu 0 0
sux Sumerian 0 0
swa sw Swahili 1 0
swe sv Swedish 1 1
syr Syriac 1 0
tah ty Tahitian 0 0
tai Tai (Other) 0 0
tam ta Tamil 1 0
tat tt Tatar 0 0
tel te Telugu 1 0
tem Timne 0 0
ter Tereno 0 0
tet Tetum 0 0
tgk tg Tajik 0 0
tgl tl Tagalog 1 1
tha th Thai 1 1
tib bo Tibetan 0 0
tig Tigre 0 0
tir ti Tigrinya 0 0
tiv Tiv 0 0
tkl Tokelau 0 0
tlh Klingon 0 0
tli Tlingit 0 0
tmh Tamashek 0 0
tog Tonga (Nyasa) 0 0
ton to Tonga (Tonga Islands) 0 0
tpi Tok Pisin 0 0
tsi Tsimshian 0 0
tsn tn Tswana 0 0
tso ts Tsonga 0 0
tuk tk Turkmen 0 0
tum Tumbuka 0 0
tup Tupi languages 0 0
tur tr Turkish 1 1
tut Altaic (Other) 0 0
tvl Tuvalu 0 0
twi tw Twi 0 0
tyv Tuvinian 0 0
udm Udmurt 0 0
uga Ugaritic 0 0
uig ug Uighur 0 0
ukr uk Ukrainian 1 1
umb Umbundu 0 0
und Undetermined 0 0
urd ur Urdu 1 0
uzb uz Uzbek 0 0
vai Vai 0 0
ven ve Venda 0 0
vie vi Vietnamese 1 1
vol vo Volapük 0 0
vot Votic 0 0
wak Wakashan languages 0 0
wal Walamo 0 0
war Waray 0 0
was Washo 0 0
wel cy Welsh 0 0
wen Sorbian languages 0 0
wln wa Walloon 0 0
wol wo Wolof 0 0
xal Kalmyk 0 0
xho xh Xhosa 0 0
yao Yao 0 0
yap Yapese 0 0
yid yi Yiddish 0 0
yor yo Yoruba 0 0
ypk Yupik languages 0 0
zap Zapotec 0 0
zen Zenaga 0 0
zha za Zhuang 0 0
znd Zande 0 0
zul zu Zulu 0 0
zun Zuni 0 0
rum ro Romanian 1 1
pob pb Brazilian 1 1
mne Montenegrin 1 0
@@ -1,85 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
class Error(Exception):
"""Base class for all exceptions in babelfish"""
pass
class LanguageError(Error, AttributeError):
"""Base class for all language exceptions in babelfish"""
pass
class LanguageConvertError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageConverter.convert` fails
:param string alpha3: alpha3 code that failed conversion
:param country: country code that failed conversion, if any
:type country: string or None
:param script: script code that failed conversion, if any
:type script: string or None
"""
def __init__(self, alpha3, country=None, script=None):
self.alpha3 = alpha3
self.country = country
self.script = script
def __str__(self):
s = self.alpha3
if self.country is not None:
s += '-' + self.country
if self.script is not None:
s += '-' + self.script
return s
class LanguageReverseError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
class CountryError(Error, AttributeError):
"""Base class for all country exceptions in babelfish"""
pass
class CountryConvertError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryConverter.convert` fails
:param string alpha2: alpha2 code that failed conversion
"""
def __init__(self, alpha2):
self.alpha2 = alpha2
def __str__(self):
return self.alpha2
class CountryReverseError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
@@ -1,185 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
from pkg_resources import resource_stream # @UnresolvedImport
from .converters import ConverterManager
from .country import Country
from .exceptions import LanguageConvertError
from .script import Script
from . import basestr
LANGUAGES = set()
LANGUAGE_MATRIX = []
#: The namedtuple used in the :data:`LANGUAGE_MATRIX`
IsoLanguage = namedtuple('IsoLanguage', ['alpha3', 'alpha3b', 'alpha3t', 'alpha2', 'scope', 'type', 'name', 'comment'])
f = resource_stream('babelfish', 'data/iso-639-3.tab')
f.readline()
for l in f:
iso_language = IsoLanguage(*l.decode('utf-8').split('\t'))
LANGUAGES.add(iso_language.alpha3)
LANGUAGE_MATRIX.append(iso_language)
f.close()
class LanguageConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for language converters"""
entry_point = 'babelfish.language_converters'
internal_converters = ['alpha2 = babelfish.converters.alpha2:Alpha2Converter',
'alpha3b = babelfish.converters.alpha3b:Alpha3BConverter',
'alpha3t = babelfish.converters.alpha3t:Alpha3TConverter',
'name = babelfish.converters.name:NameConverter',
'scope = babelfish.converters.scope:ScopeConverter',
'type = babelfish.converters.type:LanguageTypeConverter',
'opensubtitles = babelfish.converters.opensubtitles:OpenSubtitlesConverter']
language_converters = LanguageConverterManager()
class LanguageMeta(type):
"""The :class:`Language` metaclass
Dynamically redirect :meth:`Language.frommycode` to :meth:`Language.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Language(LanguageMeta(str('LanguageBase'), (object,), {})):
"""A human language
A human language is composed of a language part following the ISO-639
standard and can be country-specific when a :class:`~babelfish.country.Country`
is specified.
The :class:`Language` is extensible with custom converters (see :ref:`custom_converters`)
:param string language: the language as a 3-letter ISO-639-3 code
:param country: the country (if any) as a 2-letter ISO-3166 code or :class:`~babelfish.country.Country` instance
:type country: string or :class:`~babelfish.country.Country` or None
:param script: the script (if any) as a 4-letter ISO-15924 code or :class:`~babelfish.script.Script` instance
:type script: string or :class:`~babelfish.script.Script` or None
:param unknown: the unknown language as a three-letters ISO-639-3 code to use as fallback
:type unknown: string or None
:raise: ValueError if the language could not be recognized and `unknown` is ``None``
"""
def __init__(self, language, country=None, script=None, unknown=None):
if unknown is not None and language not in LANGUAGES:
language = unknown
if language not in LANGUAGES:
raise ValueError('%r is not a valid language' % language)
self.alpha3 = language
self.country = None
if isinstance(country, Country):
self.country = country
elif country is None:
self.country = None
else:
self.country = Country(country)
self.script = None
if isinstance(script, Script):
self.script = script
elif script is None:
self.script = None
else:
self.script = Script(script)
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Language` by its `code` using `converter` to
:meth:`~babelfish.converters.LanguageReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.LanguageReverseConverter` to use
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
return cls(*language_converters[converter].reverse(code))
@classmethod
def fromietf(cls, ietf):
"""Create a :class:`Language` by from an IETF language code
:param string ietf: the ietf code
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
subtags = ietf.split('-')
language_subtag = subtags.pop(0).lower()
if len(language_subtag) == 2:
language = cls.fromalpha2(language_subtag)
else:
language = cls(language_subtag)
while subtags:
subtag = subtags.pop(0)
if len(subtag) == 2:
language.country = Country(subtag.upper())
else:
language.script = Script(subtag.capitalize())
if language.script is not None:
if subtags:
raise ValueError('Wrong IETF format. Unmatched subtags: %r' % subtags)
break
return language
def __getstate__(self):
return self.alpha3, self.country, self.script
def __setstate__(self, state):
self.alpha3, self.country, self.script = state
def __getattr__(self, name):
alpha3 = self.alpha3
country = self.country.alpha2 if self.country is not None else None
script = self.script.code if self.script is not None else None
try:
return language_converters[name].convert(alpha3, country, script)
except KeyError:
raise AttributeError(name)
def __hash__(self):
return hash(str(self))
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Language):
return False
return (self.alpha3 == other.alpha3 and
self.country == other.country and
self.script == other.script)
def __ne__(self, other):
return not self == other
def __bool__(self):
return self.alpha3 != 'und'
__nonzero__ = __bool__
def __repr__(self):
return '<Language [%s]>' % self
def __str__(self):
try:
s = self.alpha2
except LanguageConvertError:
s = self.alpha3
if self.country is not None:
s += '-' + str(self.country)
if self.script is not None:
s += '-' + str(self.script)
return s
@@ -1,76 +0,0 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from pkg_resources import resource_stream # @UnresolvedImport
from . import basestr
#: Script code to script name mapping
SCRIPTS = {}
#: List of countries in the ISO-15924 as namedtuple of code, number, name, french_name, pva and date
SCRIPT_MATRIX = []
#: The namedtuple used in the :data:`SCRIPT_MATRIX`
IsoScript = namedtuple('IsoScript', ['code', 'number', 'name', 'french_name', 'pva', 'date'])
f = resource_stream('babelfish', 'data/iso15924-utf8-20131012.txt')
f.readline()
for l in f:
l = l.decode('utf-8').strip()
if not l or l.startswith('#'):
continue
script = IsoScript._make(l.split(';'))
SCRIPT_MATRIX.append(script)
SCRIPTS[script.code] = script.name
f.close()
class Script(object):
"""A human writing system
A script is represented by a 4-letter code from the ISO-15924 standard
:param string script: 4-letter ISO-15924 script code
"""
def __init__(self, script):
if script not in SCRIPTS:
raise ValueError('%r is not a valid script' % script)
#: ISO-15924 4-letter script code
self.code = script
@property
def name(self):
"""English name of the script"""
return SCRIPTS[self.code]
def __getstate__(self):
return self.code
def __setstate__(self, state):
self.code = state
def __hash__(self):
return hash(self.code)
def __eq__(self, other):
if isinstance(other, basestr):
return self.code == other
if not isinstance(other, Script):
return False
return self.code == other.code
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Script [%s]>' % self
def __str__(self):
return self.code
@@ -1,377 +0,0 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
import re
import sys
import pickle
from unittest import TestCase, TestSuite, TestLoader, TextTestRunner
from pkg_resources import resource_stream # @UnresolvedImport
from babelfish import (LANGUAGES, Language, Country, Script, language_converters, country_converters,
LanguageReverseConverter, LanguageConvertError, LanguageReverseError, CountryReverseError)
if sys.version_info[:2] <= (2, 6):
_MAX_LENGTH = 80
def safe_repr(obj, short=False):
try:
result = repr(obj)
except Exception:
result = object.__repr__(obj)
if not short or len(result) < _MAX_LENGTH:
return result
return result[:_MAX_LENGTH] + ' [truncated]...'
class _AssertRaisesContext(object):
"""A context manager used to implement TestCase.assertRaises* methods."""
def __init__(self, expected, test_case, expected_regexp=None):
self.expected = expected
self.failureException = test_case.failureException
self.expected_regexp = expected_regexp
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, tb):
if exc_type is None:
try:
exc_name = self.expected.__name__
except AttributeError:
exc_name = str(self.expected)
raise self.failureException(
"{0} not raised".format(exc_name))
if not issubclass(exc_type, self.expected):
# let unexpected exceptions pass through
return False
self.exception = exc_value # store for later retrieval
if self.expected_regexp is None:
return True
expected_regexp = self.expected_regexp
if isinstance(expected_regexp, basestring):
expected_regexp = re.compile(expected_regexp)
if not expected_regexp.search(str(exc_value)):
raise self.failureException('"%s" does not match "%s"' %
(expected_regexp.pattern, str(exc_value)))
return True
class _Py26FixTestCase(object):
def assertIsNone(self, obj, msg=None):
"""Same as self.assertTrue(obj is None), with a nicer default message."""
if obj is not None:
standardMsg = '%s is not None' % (safe_repr(obj),)
self.fail(self._formatMessage(msg, standardMsg))
def assertIsNotNone(self, obj, msg=None):
"""Included for symmetry with assertIsNone."""
if obj is None:
standardMsg = 'unexpectedly None'
self.fail(self._formatMessage(msg, standardMsg))
def assertIn(self, member, container, msg=None):
"""Just like self.assertTrue(a in b), but with a nicer default message."""
if member not in container:
standardMsg = '%s not found in %s' % (safe_repr(member),
safe_repr(container))
self.fail(self._formatMessage(msg, standardMsg))
def assertNotIn(self, member, container, msg=None):
"""Just like self.assertTrue(a not in b), but with a nicer default message."""
if member in container:
standardMsg = '%s unexpectedly found in %s' % (safe_repr(member),
safe_repr(container))
self.fail(self._formatMessage(msg, standardMsg))
def assertIs(self, expr1, expr2, msg=None):
"""Just like self.assertTrue(a is b), but with a nicer default message."""
if expr1 is not expr2:
standardMsg = '%s is not %s' % (safe_repr(expr1),
safe_repr(expr2))
self.fail(self._formatMessage(msg, standardMsg))
def assertIsNot(self, expr1, expr2, msg=None):
"""Just like self.assertTrue(a is not b), but with a nicer default message."""
if expr1 is expr2:
standardMsg = 'unexpectedly identical: %s' % (safe_repr(expr1),)
self.fail(self._formatMessage(msg, standardMsg))
else:
class _Py26FixTestCase(object):
pass
class TestScript(TestCase, _Py26FixTestCase):
def test_wrong_script(self):
self.assertRaises(ValueError, lambda: Script('Azer'))
def test_eq(self):
self.assertEqual(Script('Latn'), Script('Latn'))
def test_ne(self):
self.assertNotEqual(Script('Cyrl'), Script('Latn'))
def test_hash(self):
self.assertEqual(hash(Script('Hira')), hash('Hira'))
def test_pickle(self):
self.assertEqual(pickle.loads(pickle.dumps(Script('Latn'))), Script('Latn'))
class TestCountry(TestCase, _Py26FixTestCase):
def test_wrong_country(self):
self.assertRaises(ValueError, lambda: Country('ZZ'))
def test_eq(self):
self.assertEqual(Country('US'), Country('US'))
def test_ne(self):
self.assertNotEqual(Country('GB'), Country('US'))
self.assertIsNotNone(Country('US'))
def test_hash(self):
self.assertEqual(hash(Country('US')), hash('US'))
def test_pickle(self):
for country in [Country('GB'), Country('US')]:
self.assertEqual(pickle.loads(pickle.dumps(country)), country)
def test_converter_name(self):
self.assertEqual(Country('US').name, 'UNITED STATES')
self.assertEqual(Country.fromname('UNITED STATES'), Country('US'))
self.assertEqual(Country.fromcode('UNITED STATES', 'name'), Country('US'))
self.assertRaises(CountryReverseError, lambda: Country.fromname('ZZZZZ'))
self.assertEqual(len(country_converters['name'].codes), 249)
class TestLanguage(TestCase, _Py26FixTestCase):
def test_languages(self):
self.assertEqual(len(LANGUAGES), 7874)
def test_wrong_language(self):
self.assertRaises(ValueError, lambda: Language('zzz'))
def test_unknown_language(self):
self.assertEqual(Language('zzzz', unknown='und'), Language('und'))
def test_converter_alpha2(self):
self.assertEqual(Language('eng').alpha2, 'en')
self.assertEqual(Language.fromalpha2('en'), Language('eng'))
self.assertEqual(Language.fromcode('en', 'alpha2'), Language('eng'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha2('zz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha2)
self.assertEqual(len(language_converters['alpha2'].codes), 184)
def test_converter_alpha3b(self):
self.assertEqual(Language('fra').alpha3b, 'fre')
self.assertEqual(Language.fromalpha3b('fre'), Language('fra'))
self.assertEqual(Language.fromcode('fre', 'alpha3b'), Language('fra'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha3b('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha3b)
self.assertEqual(len(language_converters['alpha3b'].codes), 418)
def test_converter_alpha3t(self):
self.assertEqual(Language('fra').alpha3t, 'fra')
self.assertEqual(Language.fromalpha3t('fra'), Language('fra'))
self.assertEqual(Language.fromcode('fra', 'alpha3t'), Language('fra'))
self.assertRaises(LanguageReverseError, lambda: Language.fromalpha3t('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').alpha3t)
self.assertEqual(len(language_converters['alpha3t'].codes), 418)
def test_converter_name(self):
self.assertEqual(Language('eng').name, 'English')
self.assertEqual(Language.fromname('English'), Language('eng'))
self.assertEqual(Language.fromcode('English', 'name'), Language('eng'))
self.assertRaises(LanguageReverseError, lambda: Language.fromname('Zzzzzzzzz'))
self.assertEqual(len(language_converters['name'].codes), 7874)
def test_converter_scope(self):
self.assertEqual(language_converters['scope'].codes, set(['I', 'S', 'M']))
self.assertEqual(Language('eng').scope, 'individual')
self.assertEqual(Language('und').scope, 'special')
def test_converter_type(self):
self.assertEqual(language_converters['type'].codes, set(['A', 'C', 'E', 'H', 'L', 'S']))
self.assertEqual(Language('eng').type, 'living')
self.assertEqual(Language('und').type, 'special')
def test_converter_opensubtitles(self):
self.assertEqual(Language('fra').opensubtitles, Language('fra').alpha3b)
self.assertEqual(Language('por', 'BR').opensubtitles, 'pob')
self.assertEqual(Language.fromopensubtitles('fre'), Language('fra'))
self.assertEqual(Language.fromopensubtitles('pob'), Language('por', 'BR'))
self.assertEqual(Language.fromopensubtitles('pb'), Language('por', 'BR'))
# Montenegrin is not recognized as an ISO language (yet?) but for now it is
# unofficially accepted as Serbian from Montenegro
self.assertEqual(Language.fromopensubtitles('mne'), Language('srp', 'ME'))
self.assertEqual(Language.fromcode('pob', 'opensubtitles'), Language('por', 'BR'))
self.assertRaises(LanguageReverseError, lambda: Language.fromopensubtitles('zzz'))
self.assertRaises(LanguageConvertError, lambda: Language('aaa').opensubtitles)
self.assertEqual(len(language_converters['opensubtitles'].codes), 607)
# test with all the LANGUAGES from the opensubtitles api
# downloaded from: http://www.opensubtitles.org/addons/export_languages.php
f = resource_stream('babelfish', 'data/opensubtitles_languages.txt')
f.readline()
for l in f:
idlang, alpha2, _, upload_enabled, web_enabled = l.decode('utf-8').strip().split('\t')
if not int(upload_enabled) and not int(web_enabled):
# do not test LANGUAGES that are too esoteric / not widely available
continue
self.assertEqual(Language.fromopensubtitles(idlang).opensubtitles, idlang)
if alpha2:
self.assertEqual(Language.fromopensubtitles(idlang), Language.fromopensubtitles(alpha2))
f.close()
def test_converter_opensubtitles_codes(self):
for code in language_converters['opensubtitles'].from_opensubtitles.keys():
self.assertIn(code, language_converters['opensubtitles'].codes)
def test_fromietf_country_script(self):
language = Language.fromietf('fra-FR-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_country_no_script(self):
language = Language.fromietf('fra-FR')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertIsNone(language.script)
def test_fromietf_no_country_no_script(self):
language = Language.fromietf('fra-FR')
self.assertEqual(language.alpha3, 'fra')
self.assertEqual(language.country, Country('FR'))
self.assertIsNone(language.script)
def test_fromietf_no_country_script(self):
language = Language.fromietf('fra-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertIsNone(language.country)
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_alpha2_language(self):
language = Language.fromietf('fr-Latn')
self.assertEqual(language.alpha3, 'fra')
self.assertIsNone(language.country)
self.assertEqual(language.script, Script('Latn'))
def test_fromietf_wrong_language(self):
self.assertRaises(ValueError, lambda: Language.fromietf('xyz-FR'))
def test_fromietf_wrong_country(self):
self.assertRaises(ValueError, lambda: Language.fromietf('fra-YZ'))
def test_fromietf_wrong_script(self):
self.assertRaises(ValueError, lambda: Language.fromietf('fra-FR-Wxyz'))
def test_eq(self):
self.assertEqual(Language('eng'), Language('eng'))
def test_ne(self):
self.assertNotEqual(Language('fra'), Language('eng'))
self.assertIsNotNone(Language('fra'))
def test_nonzero(self):
self.assertFalse(bool(Language('und')))
self.assertTrue(bool(Language('eng')))
def test_language_hasattr(self):
self.assertTrue(hasattr(Language('fra'), 'alpha3'))
self.assertTrue(hasattr(Language('fra'), 'alpha2'))
self.assertFalse(hasattr(Language('bej'), 'alpha2'))
def test_country_hasattr(self):
self.assertTrue(hasattr(Country('US'), 'name'))
self.assertTrue(hasattr(Country('FR'), 'alpha2'))
self.assertFalse(hasattr(Country('BE'), 'none'))
def test_country(self):
self.assertEqual(Language('por', 'BR').country, Country('BR'))
self.assertEqual(Language('eng', Country('US')).country, Country('US'))
def test_eq_with_country(self):
self.assertEqual(Language('eng', 'US'), Language('eng', Country('US')))
def test_ne_with_country(self):
self.assertNotEqual(Language('eng', 'US'), Language('eng', Country('GB')))
def test_script(self):
self.assertEqual(Language('srp', script='Latn').script, Script('Latn'))
self.assertEqual(Language('srp', script=Script('Cyrl')).script, Script('Cyrl'))
def test_eq_with_script(self):
self.assertEqual(Language('srp', script='Latn'), Language('srp', script=Script('Latn')))
def test_ne_with_script(self):
self.assertNotEqual(Language('srp', script='Latn'), Language('srp', script=Script('Cyrl')))
def test_eq_with_country_and_script(self):
self.assertEqual(Language('srp', 'SR', 'Latn'), Language('srp', Country('SR'), Script('Latn')))
def test_ne_with_country_and_script(self):
self.assertNotEqual(Language('srp', 'SR', 'Latn'), Language('srp', Country('SR'), Script('Cyrl')))
def test_hash(self):
self.assertEqual(hash(Language('fra')), hash('fr'))
self.assertEqual(hash(Language('ace')), hash('ace'))
self.assertEqual(hash(Language('por', 'BR')), hash('pt-BR'))
self.assertEqual(hash(Language('srp', script='Cyrl')), hash('sr-Cyrl'))
self.assertEqual(hash(Language('eng', 'US', 'Latn')), hash('en-US-Latn'))
def test_pickle(self):
for lang in [Language('fra'),
Language('eng', 'US'),
Language('srp', script='Latn'),
Language('eng', 'US', 'Latn')]:
self.assertEqual(pickle.loads(pickle.dumps(lang)), lang)
def test_str(self):
self.assertEqual(Language.fromietf(str(Language('eng', 'US', 'Latn'))), Language('eng', 'US', 'Latn'))
self.assertEqual(Language.fromietf(str(Language('fra', 'FR'))), Language('fra', 'FR'))
self.assertEqual(Language.fromietf(str(Language('bel'))), Language('bel'))
def test_register_converter(self):
class TestConverter(LanguageReverseConverter):
def __init__(self):
self.to_test = {'fra': 'test1', 'eng': 'test2'}
self.from_test = {'test1': 'fra', 'test2': 'eng'}
def convert(self, alpha3, country=None, script=None):
if alpha3 not in self.to_test:
raise LanguageConvertError(alpha3, country, script)
return self.to_test[alpha3]
def reverse(self, test):
if test not in self.from_test:
raise LanguageReverseError(test)
return (self.from_test[test], None)
language = Language('fra')
self.assertFalse(hasattr(language, 'test'))
language_converters['test'] = TestConverter()
self.assertTrue(hasattr(language, 'test'))
self.assertIn('test', language_converters)
self.assertEqual(Language('fra').test, 'test1')
self.assertEqual(Language.fromtest('test2').alpha3, 'eng')
del language_converters['test']
self.assertNotIn('test', language_converters)
self.assertRaises(KeyError, lambda: Language.fromtest('test1'))
self.assertRaises(AttributeError, lambda: Language('fra').test)
def suite():
suite = TestSuite()
suite.addTest(TestLoader().loadTestsFromTestCase(TestScript))
suite.addTest(TestLoader().loadTestsFromTestCase(TestCountry))
suite.addTest(TestLoader().loadTestsFromTestCase(TestLanguage))
return suite
if __name__ == '__main__':
TextTestRunner().run(suite())
-43
View File
@@ -1,43 +0,0 @@
Behold, mortal, the origins of Beautiful Soup...
================================================
Leonard Richardson is the primary programmer.
Aaron DeVore is awesome.
Mark Pilgrim provided the encoding detection code that forms the base
of UnicodeDammit.
Thomas Kluyver and Ezio Melotti finished the work of getting Beautiful
Soup 4 working under Python 3.
Simon Willison wrote soupselect, which was used to make Beautiful Soup
support CSS selectors.
Sam Ruby helped with a lot of edge cases.
Jonathan Ellis was awarded the prestigous Beau Potage D'Or for his
work in solving the nestable tags conundrum.
An incomplete list of people have contributed patches to Beautiful
Soup:
Istvan Albert, Andrew Lin, Anthony Baxter, Andrew Boyko, Tony Chang,
Zephyr Fang, Fuzzy, Roman Gaufman, Yoni Gilad, Richie Hindle, Peteris
Krumins, Kent Johnson, Ben Last, Robert Leftwich, Staffan Malmgren,
Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon", Ed
Oskiewicz, Greg Phillips, Giles Radford, Arthur Rudolph, Marko
Samastur, Jouni Seppänen, Alexander Schmolck, Andy Theyers, Glyn
Webster, Paul Wright, Danny Yoo
An incomplete list of people who made suggestions or found bugs or
found ways to break Beautiful Soup:
Hanno Böck, Matteo Bertini, Chris Curvey, Simon Cusack, Bruce Eckel,
Matt Ernst, Michael Foord, Tom Harris, Bill de hOra, Donald Howes,
Matt Patterson, Scott Roberts, Steve Strassmann, Mike Williams,
warchild at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison,
Joren Mc, Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed
Summers, Dennis Sutch, Chris Smith, Aaron Sweep^W Swartz, Stuart
Turner, Greg Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de
Sousa Rocha, Yichun Wei, Per Vognsen
-27
View File
@@ -1,27 +0,0 @@
Beautiful Soup is made available under the MIT license:
Copyright (c) 2004-2015 Leonard Richardson
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
Beautiful Soup incorporates code from the html5lib library, which is
also made available under the MIT license. Copyright (c) 2006-2013
James Graham and other contributors
File diff suppressed because it is too large Load Diff
-63
View File
@@ -1,63 +0,0 @@
= Introduction =
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>
= Full documentation =
The bs4/doc/ directory contains full documentation in Sphinx
format. Run "make html" in that directory to create HTML
documentation.
= Running the unit tests =
Beautiful Soup supports unit test discovery from the project root directory:
$ nosetests
$ python -m unittest discover -s bs4 # Python 2.7 and up
If you checked out the source tree, you should see a script in the
home directory called test-all-versions. This script will run the unit
tests under Python 2.7, then create a temporary Python 3 conversion of
the source and run the unit tests again under Python 3.
= Links =
Homepage: http://www.crummy.com/software/BeautifulSoup/bs4/
Documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
http://readthedocs.org/docs/beautiful-soup-4/
Discussion group: http://groups.google.com/group/beautifulsoup/
Development: https://code.launchpad.net/beautifulsoup/
Bug tracker: https://bugs.launchpad.net/beautifulsoup/
-31
View File
@@ -1,31 +0,0 @@
Additions
---------
More of the jQuery API: nextUntil?
Optimizations
-------------
The html5lib tree builder doesn't use the standard tree-building API,
which worries me and has resulted in a number of bugs.
markup_attr_map can be optimized since it's always a map now.
Upon encountering UTF-16LE data or some other uncommon serialization
of Unicode, UnicodeDammit will convert the data to Unicode, then
encode it at UTF-8. This is wasteful because it will just get decoded
back to Unicode.
CDATA
-----
The elementtree XMLParser has a strip_cdata argument that, when set to
False, should allow Beautiful Soup to preserve CDATA sections instead
of treating them as text. Except it doesn't. (This argument is also
present for HTMLParser, and also does nothing there.)
Currently, htm5lib converts CDATA sections into comments. An
as-yet-unreleased version of html5lib changes the parser's handling of
CDATA sections to allow CDATA sections in tags like <svg> and
<math>. The HTML5TreeBuilder will need to be updated to create CData
objects instead of Comment objects in this situation.
-468
View File
@@ -1,468 +0,0 @@
"""Beautiful Soup
Elixir and Tonic
"The Screen-Scraper's Friend"
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup uses a pluggable XML or HTML parser to parse a
(possibly invalid) document into a tree representation. Beautiful Soup
provides provides methods and Pythonic idioms that make it easy to
navigate, search, and modify the parse tree.
Beautiful Soup works with Python 2.6 and up. It works better if lxml
and/or html5lib is installed.
For more than you ever wanted to know about Beautiful Soup, see the
documentation:
http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.4.1"
__copyright__ = "Copyright (c) 2004-2015 Leonard Richardson"
__license__ = "MIT"
__all__ = ['BeautifulSoup']
import os
import re
import warnings
from .builder import builder_registry, ParserRejectedMarkup
from .dammit import UnicodeDammit
from .element import (
CData,
Comment,
DEFAULT_OUTPUT_ENCODING,
Declaration,
Doctype,
NavigableString,
PageElement,
ProcessingInstruction,
ResultSet,
SoupStrainer,
Tag,
)
# The very first thing we do is give a useful error if someone is
# running this code under Python 3 without converting it.
'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
class BeautifulSoup(Tag):
"""
This class defines the basic interface called by the tree builders.
These methods will be called by the parser:
reset()
feed(markup)
The tree builder may call these methods from its feed() implementation:
handle_starttag(name, attrs) # See note about return value
handle_endtag(name)
handle_data(data) # Appends to the current data node
endData(containerClass=NavigableString) # Ends the current data node
No matter how complicated the underlying parser is, you should be
able to build a tree using 'start tag' events, 'end tag' events,
'data' events, and "done with data" events.
If you encounter an empty-element tag (aka a self-closing tag,
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
ROOT_TAG_NAME = u'[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"%(parser)s\")\n"
def __init__(self, markup="", features=None, builder=None,
parse_only=None, from_encoding=None, exclude_encodings=None,
**kwargs):
"""The Soup object is initialized as the 'root tag', and the
provided markup (which can be a string or a file-like object)
is fed into the underlying parser."""
if 'convertEntities' in kwargs:
warnings.warn(
"BS4 does not respect the convertEntities argument to the "
"BeautifulSoup constructor. Entities are always converted "
"to Unicode characters.")
if 'markupMassage' in kwargs:
del kwargs['markupMassage']
warnings.warn(
"BS4 does not respect the markupMassage argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for any necessary markup massage.")
if 'smartQuotesTo' in kwargs:
del kwargs['smartQuotesTo']
warnings.warn(
"BS4 does not respect the smartQuotesTo argument to the "
"BeautifulSoup constructor. Smart quotes are always converted "
"to Unicode characters.")
if 'selfClosingTags' in kwargs:
del kwargs['selfClosingTags']
warnings.warn(
"BS4 does not respect the selfClosingTags argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for understanding self-closing tags.")
if 'isHTML' in kwargs:
del kwargs['isHTML']
warnings.warn(
"BS4 does not respect the isHTML argument to the "
"BeautifulSoup constructor. Suggest you use "
"features='lxml' for HTML and features='lxml-xml' for "
"XML.")
def deprecated_argument(old_name, new_name):
if old_name in kwargs:
warnings.warn(
'The "%s" argument to the BeautifulSoup constructor '
'has been renamed to "%s."' % (old_name, new_name))
value = kwargs[old_name]
del kwargs[old_name]
return value
return None
parse_only = parse_only or deprecated_argument(
"parseOnlyThese", "parse_only")
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if len(kwargs) > 0:
arg = kwargs.keys().pop()
raise TypeError(
"__init__() got an unexpected keyword argument '%s'" % arg)
if builder is None:
original_features = features
if isinstance(features, basestring):
features = [features]
if features is None or len(features) == 0:
features = self.DEFAULT_BUILDER_FEATURES
builder_class = builder_registry.lookup(*features)
if builder_class is None:
raise FeatureNotFound(
"Couldn't find a tree builder with the features you "
"requested: %s. Do you need to install a parser library?"
% ",".join(features))
builder = builder_class()
if not (original_features == builder.NAME or
original_features in builder.ALTERNATE_NAMES):
if builder.is_xml:
markup_type = "XML"
else:
markup_type = "HTML"
warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % dict(
parser=builder.NAME,
markup_type=markup_type))
self.builder = builder
self.is_xml = builder.is_xml
self.builder.soup = self
self.parse_only = parse_only
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
elif len(markup) <= 256:
# Print out warnings for a couple beginner problems
# involving passing non-markup to Beautiful Soup.
# Beautiful Soup will still parse the input as markup,
# just in case that's what the user really wants.
if (isinstance(markup, unicode)
and not os.path.supports_unicode_filenames):
possible_filename = markup.encode("utf8")
else:
possible_filename = markup
is_file = False
try:
is_file = os.path.exists(possible_filename)
except Exception, e:
# This is almost certainly a problem involving
# characters not valid in filenames on this
# system. Just let it go.
pass
if is_file:
if isinstance(markup, unicode):
markup = markup.encode("utf8")
warnings.warn(
'"%s" looks like a filename, not markup. You should probably open this file and pass the filehandle into Beautiful Soup.' % markup)
if markup[:5] == "http:" or markup[:6] == "https:":
# TODO: This is ugly but I couldn't get it to work in
# Python 3 otherwise.
if ((isinstance(markup, bytes) and not b' ' in markup)
or (isinstance(markup, unicode) and not u' ' in markup)):
if isinstance(markup, unicode):
markup = markup.encode("utf8")
warnings.warn(
'"%s" looks like a URL. Beautiful Soup is not an HTTP client. You should probably use an HTTP client to get the document behind the URL, and feed that document to Beautiful Soup.' % markup)
for (self.markup, self.original_encoding, self.declared_html_encoding,
self.contains_replacement_characters) in (
self.builder.prepare_markup(
markup, from_encoding, exclude_encodings=exclude_encodings)):
self.reset()
try:
self._feed()
break
except ParserRejectedMarkup:
pass
# Clear out the markup and remove the builder's circular
# reference to this object.
self.markup = None
self.builder.soup = None
def __copy__(self):
return type(self)(self.encode(), builder=self.builder)
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and not self.builder.picklable:
del d['builder']
return d
def _feed(self):
# Convert the document to Unicode.
self.builder.reset()
self.builder.feed(self.markup)
# Close out any unfinished strings and close all the open tags.
self.endData()
while self.currentTag.name != self.ROOT_TAG_NAME:
self.popTag()
def reset(self):
Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
self.hidden = 1
self.builder.reset()
self.current_data = []
self.currentTag = None
self.tagStack = []
self.preserve_whitespace_tag_stack = []
self.pushTag(self)
def new_tag(self, name, namespace=None, nsprefix=None, **attrs):
"""Create a new tag associated with this soup."""
return Tag(None, self.builder, name, namespace, nsprefix, attrs)
def new_string(self, s, subclass=NavigableString):
"""Create a new NavigableString associated with this soup."""
return subclass(s)
def insert_before(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
tag = self.tagStack.pop()
if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
self.preserve_whitespace_tag_stack.pop()
#print "Pop", tag.name
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
#print "Push", tag.name
if self.currentTag:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
def endData(self, containerClass=NavigableString):
if self.current_data:
current_data = u''.join(self.current_data)
# If whitespace is not preserved, and this string contains
# nothing but ASCII spaces, replace it with a single space
# or newline.
if not self.preserve_whitespace_tag_stack:
strippable = True
for i in current_data:
if i not in self.ASCII_SPACES:
strippable = False
break
if strippable:
if '\n' in current_data:
current_data = '\n'
else:
current_data = ' '
# Reset the data collector.
self.current_data = []
# Should we add this string to the tree at all?
if self.parse_only and len(self.tagStack) <= 1 and \
(not self.parse_only.text or \
not self.parse_only.search(current_data)):
return
o = containerClass(current_data)
self.object_was_parsed(o)
def object_was_parsed(self, o, parent=None, most_recent_element=None):
"""Add an object to the parse tree."""
parent = parent or self.currentTag
previous_element = most_recent_element or self._most_recent_element
next_element = previous_sibling = next_sibling = None
if isinstance(o, Tag):
next_element = o.next_element
next_sibling = o.next_sibling
previous_sibling = o.previous_sibling
if not previous_element:
previous_element = o.previous_element
o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
self._most_recent_element = o
parent.contents.append(o)
if parent.next_sibling:
# This node is being inserted into an element that has
# already been parsed. Deal with any dangling references.
index = parent.contents.index(o)
if index == 0:
previous_element = parent
previous_sibling = None
else:
previous_element = previous_sibling = parent.contents[index-1]
if index == len(parent.contents)-1:
next_element = parent.next_sibling
next_sibling = None
else:
next_element = next_sibling = parent.contents[index+1]
o.previous_element = previous_element
if previous_element:
previous_element.next_element = o
o.next_element = next_element
if next_element:
next_element.previous_element = o
o.next_sibling = next_sibling
if next_sibling:
next_sibling.previous_sibling = o
o.previous_sibling = previous_sibling
if previous_sibling:
previous_sibling.next_sibling = o
def _popToTag(self, name, nsprefix=None, inclusivePop=True):
"""Pops the tag stack up to and including the most recent
instance of the given tag. If inclusivePop is false, pops the tag
stack up to but *not* including the most recent instqance of
the given tag."""
#print "Popping to %s" % name
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
most_recently_popped = None
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
most_recently_popped = self.popTag()
break
most_recently_popped = self.popTag()
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs):
"""Push a start tag on to the stack.
If this method returns None, the tag was rejected by the
SoupStrainer. You should proceed as if the tag had not occured
in the document. For instance, if this was a self-closing tag,
don't call handle_endtag.
"""
# print "Start tag %s: %s" % (name, attrs)
self.endData()
if (self.parse_only and len(self.tagStack) <= 1
and (self.parse_only.text
or not self.parse_only.search_tag(name, attrs))):
return None
tag = Tag(self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element)
if tag is None:
return tag
if self._most_recent_element:
self._most_recent_element.next_element = tag
self._most_recent_element = tag
self.pushTag(tag)
return tag
def handle_endtag(self, name, nsprefix=None):
#print "End tag: " + name
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
self.current_data.append(data)
def decode(self, pretty_print=False,
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
formatter="minimal"):
"""Returns a string or Unicode representation of this document.
To get Unicode, pass None for encoding."""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = u'<?xml version="1.0"%s?>\n' % encoding_part
else:
prefix = u''
if not pretty_print:
indent_level = None
else:
indent_level = 0
return prefix + super(BeautifulSoup, self).decode(
indent_level, eventual_encoding, formatter)
# Alias to make it easier to type import: 'from bs4 import _soup'
_s = BeautifulSoup
_soup = BeautifulSoup
class BeautifulStoneSoup(BeautifulSoup):
"""Deprecated interface to an XML parser."""
def __init__(self, *args, **kwargs):
kwargs['features'] = 'xml'
warnings.warn(
'The BeautifulStoneSoup class is deprecated. Instead of using '
'it, pass features="xml" into the BeautifulSoup constructor.')
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
class StopParsing(Exception):
pass
class FeatureNotFound(ValueError):
pass
#By default, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print soup.prettify()
@@ -1,324 +0,0 @@
from collections import defaultdict
import itertools
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
whitespace_re
)
__all__ = [
'HTMLTreeBuilder',
'SAXTreeBuilder',
'TreeBuilder',
'TreeBuilderRegistry',
]
# Some useful features for a TreeBuilder to have.
FAST = 'fast'
PERMISSIVE = 'permissive'
STRICT = 'strict'
XML = 'xml'
HTML = 'html'
HTML_5 = 'html5'
class TreeBuilderRegistry(object):
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features."""
for feature in treebuilder_class.features:
self.builders_for_feature[feature].insert(0, treebuilder_class)
self.builders.insert(0, treebuilder_class)
def lookup(self, *features):
if len(self.builders) == 0:
# There are no builders at all.
return None
if len(features) == 0:
# They didn't ask for any features. Give them the most
# recently registered builder.
return self.builders[0]
# Go down the list of features in order, and eliminate any builders
# that don't match every feature.
features = list(features)
features.reverse()
candidates = None
candidate_set = None
while len(features) > 0:
feature = features.pop()
we_have_the_feature = self.builders_for_feature.get(feature, [])
if len(we_have_the_feature) > 0:
if candidates is None:
candidates = we_have_the_feature
candidate_set = set(candidates)
else:
# Eliminate any candidates that don't have this feature.
candidate_set = candidate_set.intersection(
set(we_have_the_feature))
# The only valid candidates are the ones in candidate_set.
# Go through the original list of candidates and pick the first one
# that's in candidate_set.
if candidate_set is None:
return None
for candidate in candidates:
if candidate in candidate_set:
return candidate
return None
# The BeautifulSoup class will take feature lists from developers and use them
# to look up builders in this registry.
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
is_xml = False
picklable = False
preserve_whitespace_tags = set()
empty_element_tags = None # A tag will be considered an empty-element
# tag when and only when it has no contents.
# A value for these tag/attribute combinations is a space- or
# comma-separated list of CDATA, rather than a single CDATA.
cdata_list_attributes = {}
def __init__(self):
self.soup = None
def reset(self):
pass
def can_be_empty_element(self, tag_name):
"""Might a tag with this name be an empty-element tag?
The final markup may or may not actually present this tag as
self-closing.
For instance: an HTMLBuilder does not consider a <p> tag to be
an empty-element tag (it's not in
HTMLBuilder.empty_element_tags). This means an empty <p> tag
will be presented as "<p></p>", not "<p />".
The default implementation has no opinion about which tags are
empty-element tags, so a tag will be presented as an
empty-element tag if and only if it has no contents.
"<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
be left alone.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None):
return markup, None, None, False
def test_fragment_to_document(self, fragment):
"""Wrap an HTML fragment to make it look like a document.
Different parsers do this differently. For instance, lxml
introduces an empty <head> tag, and html5lib
doesn't. Abstracting this away lets us write simple tests
which run HTML fragments through the parser and compare the
results against other HTML fragments.
This method should not be used outside of tests.
"""
return fragment
def set_up_substitutions(self, tag):
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""Replaces class="foo bar" with class=["foo", "bar"]
Modifies its input in place.
"""
if not attrs:
return attrs
if self.cdata_list_attributes:
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in attrs.keys():
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, basestring):
values = whitespace_re.split(value)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
# tree. On the second call the attribute value
# here is already a list. If this happens,
# leave the value alone rather than trying to
# split it again.
values = value
attrs[attr] = values
return attrs
class SAXTreeBuilder(TreeBuilder):
"""A Beautiful Soup treebuilder that listens for SAX events."""
def feed(self, markup):
raise NotImplementedError()
def close(self):
pass
def startElement(self, name, attrs):
attrs = dict((key[1], value) for key, value in list(attrs.items()))
#print "Start %s, %r" % (name, attrs)
self.soup.handle_starttag(name, attrs)
def endElement(self, name):
#print "End %s" % name
self.soup.handle_endtag(name)
def startElementNS(self, nsTuple, nodeName, attrs):
# Throw away (ns, nodeName) for now.
self.startElement(nodeName, attrs)
def endElementNS(self, nsTuple, nodeName):
# Throw away (ns, nodeName) for now.
self.endElement(nodeName)
#handler.endElementNS((ns, node.nodeName), node.nodeName)
def startPrefixMapping(self, prefix, nodeValue):
# Ignore the prefix for now.
pass
def endPrefixMapping(self, prefix):
# Ignore the prefix for now.
# handler.endPrefixMapping(prefix)
pass
def characters(self, content):
self.soup.handle_data(content)
def startDocument(self):
pass
def endDocument(self):
pass
class HTMLTreeBuilder(TreeBuilder):
"""This TreeBuilder knows facts about HTML.
Such as which tags are empty-element tags.
"""
preserve_whitespace_tags = set(['pre', 'textarea'])
empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
'spacer', 'link', 'frame', 'base'])
# The HTML standard defines these attributes as containing a
# space-separated list of values, not a single value. That is,
# class="foo bar" means that the 'class' attribute has two values,
# 'foo' and 'bar', not the single value 'foo bar'. When we
# encounter one of these attributes, we will parse its value into
# a list of values if possible. Upon output, the list will be
# converted back into a string.
cdata_list_attributes = {
"*" : ['class', 'accesskey', 'dropzone'],
"a" : ['rel', 'rev'],
"link" : ['rel', 'rev'],
"td" : ["headers"],
"th" : ["headers"],
"td" : ["headers"],
"form" : ["accept-charset"],
"object" : ["archive"],
# These are HTML5 specific, as are *.accesskey and *.dropzone above.
"area" : ["rel"],
"icon" : ["sizes"],
"iframe" : ["sandbox"],
"output" : ["for"],
}
def set_up_substitutions(self, tag):
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
# I'm fairly sure this is not the best way to do this.
this_module = sys.modules['bs4.builder']
for name in module.__all__:
obj = getattr(module, name)
if issubclass(obj, TreeBuilder):
setattr(this_module, name, obj)
this_module.__all__.append(name)
# Register the builder while we're at it.
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
pass
# Builders are registered in reverse order of priority, so that custom
# builder registrations will take precedence. In general, we want lxml
# to take precedence over html5lib, because it's faster. And we only
# want to use HTMLParser as a last result.
from . import _htmlparser
register_treebuilders_from(_htmlparser)
try:
from . import _html5lib
register_treebuilders_from(_html5lib)
except ImportError:
# They don't have html5lib installed.
pass
try:
from . import _lxml
register_treebuilders_from(_lxml)
except ImportError:
# They don't have lxml installed.
pass
@@ -1,332 +0,0 @@
__all__ = [
'HTML5TreeBuilder',
]
from pdb import set_trace
import warnings
from bs4.builder import (
PERMISSIVE,
HTML,
HTML_5,
HTMLTreeBuilder,
)
from bs4.element import (
NamespacedAttribute,
whitespace_re,
)
import html5lib
from html5lib.constants import namespaces
from bs4.element import (
Comment,
Doctype,
NavigableString,
Tag,
)
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree."""
NAME = "html5lib"
features = [NAME, PERMISSIVE, HTML_5, HTML]
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
# document_declared_encoding and exclude_encodings aren't used
# ATM because the html5lib TreeBuilder doesn't use
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
yield (markup, None, None, False)
# These methods are defined by Beautiful Soup.
def feed(self, markup):
if self.soup.parse_only is not None:
warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
doc = parser.parse(markup, encoding=self.user_specified_encoding)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, unicode):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
self.soup, namespaceHTMLElements)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
def __init__(self, soup, namespaceHTMLElements):
self.soup = soup
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
def documentClass(self):
self.soup.reset()
return Element(self.soup, self.soup, None)
def insertDoctype(self, token):
name = token["name"]
publicId = token["publicId"]
systemId = token["systemId"]
doctype = Doctype.for_name_and_ids(name, publicId, systemId)
self.soup.object_was_parsed(doctype)
def elementClass(self, name, namespace):
tag = self.soup.new_tag(name, namespace)
return Element(tag, self.soup, namespace)
def commentClass(self, data):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
self.soup = BeautifulSoup("")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
def appendChild(self, node):
# XXX This code is not covered by the BS4 tests.
self.soup.append(node.element)
def getDocument(self):
return self.soup
def getFragment(self):
return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element
class AttrList(object):
def __init__(self, element):
self.element = element
self.attrs = dict(self.element.attrs)
def __iter__(self):
return list(self.attrs.items()).__iter__()
def __setitem__(self, name, value):
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = HTML5TreeBuilder.cdata_list_attributes
if (name in list_attr['*']
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = whitespace_re.split(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
def keys(self):
return list(self.attrs.keys())
def __len__(self):
return len(self.attrs)
def __getitem__(self, name):
return self.attrs[name]
def __contains__(self, name):
return name in list(self.attrs.keys())
class Element(html5lib.treebuilders._base.Node):
def __init__(self, element, soup, namespace):
html5lib.treebuilders._base.Node.__init__(self, element.name)
self.element = element
self.soup = soup
self.namespace = namespace
def appendChild(self, node):
string_child = child = None
if isinstance(node, basestring):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
string_child = child = node
elif isinstance(node, Tag):
# Some other piece of code decided to pass in a Tag
# instead of creating an Element object to contain the
# Tag.
child = node
elif node.element.__class__ == NavigableString:
string_child = child = node.element
else:
child = node.element
if not isinstance(child, basestring) and child.parent is not None:
node.element.extract()
if (string_child and self.element.contents
and self.element.contents[-1].__class__ == NavigableString):
# We are appending a string onto another string.
# TODO This has O(n^2) performance, for input like
# "a</a>a</a>a</a>..."
old_element = self.element.contents[-1]
new_element = self.soup.new_string(old_element + string_child)
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
if isinstance(node, basestring):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
# Tell Beautiful Soup to act as if it parsed this element
# immediately after the parent's last descendant. (Or
# immediately after the parent, if it has no children.)
if self.element.contents:
most_recent_element = self.element._last_descendant(False)
elif self.element.next_element is not None:
# Something from further ahead in the parse tree is
# being inserted into this earlier element. This is
# very annoying because it means an expensive search
# for the last element in the tree.
most_recent_element = self.soup._last_descendant()
else:
most_recent_element = self.element
self.soup.object_was_parsed(
child, parent=self.element,
most_recent_element=most_recent_element)
def getAttributes(self):
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
for name, value in list(attributes.items()):
if isinstance(name, tuple):
new_name = NamespacedAttribute(*name)
del attributes[name]
attributes[new_name] = value
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in attributes.items():
self.element[name] = value
# The attributes may contain variables that need substitution.
# Call set_up_substitutions manually.
#
# The Tag constructor called this method when the Tag was created,
# but we just set/changed the attributes, so call it again.
self.soup.builder.set_up_substitutions(self.element)
attributes = property(getAttributes, setAttributes)
def insertText(self, data, insertBefore=None):
if insertBefore:
text = TextNode(self.soup.new_string(data), self.soup)
self.insertBefore(data, insertBefore)
else:
self.appendChild(data)
def insertBefore(self, node, refNode):
index = self.element.index(refNode.element)
if (node.element.__class__ == NavigableString and self.element.contents
and self.element.contents[index-1].__class__ == NavigableString):
# (See comments in appendChild)
old_node = self.element.contents[index-1]
new_str = self.soup.new_string(old_node + node.element)
old_node.replace_with(new_str)
else:
self.element.insert(index, node.element)
node.parent = self
def removeChild(self, node):
node.element.extract()
def reparentChildren(self, new_parent):
"""Move all of this tag's children into another tag."""
# print "MOVE", self.element.contents
# print "FROM", self.element
# print "TO", new_parent.element
element = self.element
new_parent_element = new_parent.element
# Determine what this tag's next_element will be once all the children
# are removed.
final_next_element = element.next_sibling
new_parents_last_descendant = new_parent_element._last_descendant(False, False)
if len(new_parent_element.contents) > 0:
# The new parent already contains children. We will be
# appending this tag's children to the end.
new_parents_last_child = new_parent_element.contents[-1]
new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
else:
# The new parent contains no children.
new_parents_last_child = None
new_parents_last_descendant_next_element = new_parent_element.next_element
to_append = element.contents
append_after = new_parent_element.contents
if len(to_append) > 0:
# Set the first child's previous_element and previous_sibling
# to elements within the new parent
first_child = to_append[0]
if new_parents_last_descendant:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child:
new_parents_last_child.next_sibling = first_child
# Fix the last child's next_element and next_sibling
last_child = to_append[-1]
last_child.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element:
new_parents_last_descendant_next_element.previous_element = last_child
last_child.next_sibling = None
for child in to_append:
child.parent = new_parent_element
new_parent_element.contents.append(child)
# Now that this element has no children, change its .next_element.
element.contents = []
element.next_element = final_next_element
# print "DONE WITH MOVE"
# print "FROM", self.element
# print "TO", new_parent_element
def cloneNode(self):
tag = self.soup.new_tag(self.element.name, self.namespace)
node = Element(tag, self.soup, self.namespace)
for key,value in self.attributes:
node.attributes[key] = value
return node
def hasContent(self):
return self.element.contents
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
nameTuple = property(getNameTuple)
class TextNode(Element):
def __init__(self, element, soup):
html5lib.treebuilders._base.Node.__init__(self, None)
self.element = element
self.soup = soup
def cloneNode(self):
raise NotImplementedError
@@ -1,262 +0,0 @@
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
__all__ = [
'HTMLParserTreeBuilder',
]
from HTMLParser import HTMLParser
try:
from HTMLParser import HTMLParseError
except ImportError, e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
pass
import sys
import warnings
# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
# argument, which we'd like to set to False. Unfortunately,
# http://bugs.python.org/issue13273 makes strict=True a better bet
# before Python 3.2.3.
#
# At the end of this file, we monkeypatch HTMLParser so that
# strict=True works well on Python 3.2.2.
major, minor, release = sys.version_info[:3]
CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
from bs4.element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
def handle_starttag(self, name, attrs):
# XXX namespace
attr_dict = {}
for key, value in attrs:
# Change None attribute values to the empty string
# for consistency with the other tree builders.
if value is None:
value = ''
attr_dict[key] = value
attrvalue = '""'
self.soup.handle_starttag(name, None, None, attr_dict)
def handle_endtag(self, name):
self.soup.handle_endtag(name)
def handle_data(self, data):
self.soup.handle_data(data)
def handle_charref(self, name):
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
real_name = int(name.lstrip('X'), 16)
else:
real_name = int(name)
try:
data = unichr(real_name)
except (ValueError, OverflowError), e:
data = u"\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
else:
data = "&%s;" % name
self.handle_data(data)
def handle_comment(self, data):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
self.soup.endData()
if data.startswith("DOCTYPE "):
data = data[len("DOCTYPE "):]
elif data == 'DOCTYPE':
# i.e. "<!DOCTYPE>"
data = ''
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
else:
cls = Declaration
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(cls)
def handle_pi(self, data):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
def __init__(self, *args, **kwargs):
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
kwargs['convert_charrefs'] = False
self.parser_args = (args, kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""
if isinstance(markup, unicode):
yield (markup, None, None, False)
return
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(markup, try_encodings, is_html=True,
exclude_encodings=exclude_encodings)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
except HTMLParseError, e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
# string.
#
# XXX This code can be removed once most Python 3 users are on 3.2.3.
if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
import re
attrfind_tolerant = re.compile(
r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
""", re.VERBOSE)
BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
from html.parser import tagfind, attrfind
def parse_starttag(self, i):
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
return endpos
rawdata = self.rawdata
self.__starttag_text = rawdata[i:endpos]
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)
else:
m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
if not rest:
attrvalue = None
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
if self.strict:
self.error("junk characters in start tag: %r"
% (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs)
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
return endpos
def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
BeautifulSoupHTMLParser.parse_starttag = parse_starttag
BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
CONSTRUCTOR_TAKES_STRICT = True
@@ -1,248 +0,0 @@
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
from io import BytesIO
from StringIO import StringIO
import collections
from lxml import etree
from bs4.element import (
Comment,
Doctype,
NamespacedAttribute,
ProcessingInstruction,
)
from bs4.builder import (
FAST,
HTML,
HTMLTreeBuilder,
PERMISSIVE,
ParserRejectedMarkup,
TreeBuilder,
XML)
from bs4.dammit import EncodingDetector
LXML = 'lxml'
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
is_xml = True
NAME = "lxml-xml"
ALTERNATE_NAMES = ["xml"]
# Well, it's permissive by XML parser standards.
features = [NAME, LXML, XML, FAST, PERMISSIVE]
CHUNK_SIZE = 512
# This namespace mapping is specified in the XML Namespace
# standard.
DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
def default_parser(self, encoding):
# This can either return a parser object or a class, which
# will be instantiated with default arguments.
if self._default_parser is not None:
return self._default_parser
return etree.XMLParser(
target=self, strip_cdata=False, recover=True, encoding=encoding)
def parser_for(self, encoding):
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, collections.Callable):
# Instantiate the parser with default arguments
parser = parser(target=self, strip_cdata=False, encoding=encoding)
return parser
def __init__(self, parser=None, empty_element_tags=None):
# TODO: Issue a warning if parser is present but not a
# callable, since that means there's no way to create new
# parsers for different encodings.
self._default_parser = parser
if empty_element_tags is not None:
self.empty_element_tags = set(empty_element_tags)
self.soup = None
self.nsmaps = [self.DEFAULT_NSMAPS]
def _getNsTag(self, tag):
# Split the namespace URL out of a fully-qualified lxml tag
# name. Copied from lxml's src/lxml/sax.py.
if tag[0] == '{':
return tuple(tag[1:].split('}', 1))
else:
return (None, tag)
def prepare_markup(self, markup, user_specified_encoding=None,
exclude_encodings=None,
document_declared_encoding=None):
"""
:yield: A series of 4-tuples.
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for parsing the document.
"""
if isinstance(markup, unicode):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
yield markup, None, document_declared_encoding, False
if isinstance(markup, unicode):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
# Instead of using UnicodeDammit to convert the bytestring to
# Unicode using different encodings, use EncodingDetector to
# iterate over the encodings, and tell lxml to try to parse
# the document as each one in turn.
is_html = not self.is_xml
try_encodings = [user_specified_encoding, document_declared_encoding]
detector = EncodingDetector(
markup, try_encodings, is_html, exclude_encodings)
for encoding in detector.encodings:
yield (detector.markup, encoding, document_declared_encoding, False)
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
elif isinstance(markup, unicode):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
# or the parser won't be initialized.
data = markup.read(self.CHUNK_SIZE)
try:
self.parser = self.parser_for(self.soup.original_encoding)
self.parser.feed(data)
while len(data) != 0:
# Now call feed() on the rest of the data, chunk by chunk.
data = markup.read(self.CHUNK_SIZE)
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
raise ParserRejectedMarkup(str(e))
def close(self):
self.nsmaps = [self.DEFAULT_NSMAPS]
def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
attrs = dict(attrs)
nsprefix = None
# Invert each namespace map as it comes in.
if len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
inverted_nsmap = dict((value, key) for key, value in nsmap.items())
self.nsmaps.append(inverted_nsmap)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in nsmap.items():
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
# Namespaces are in play. Find any attributes that came in
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in attrs.items():
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
else:
nsprefix = self._prefix_for_namespace(namespace)
attr = NamespacedAttribute(nsprefix, attr, namespace)
new_attrs[attr] = value
attrs = new_attrs
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
return None
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
return inverted_nsmap[namespace]
return None
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
namespace, name = self._getNsTag(name)
nsprefix = None
if namespace is not None:
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
nsprefix = inverted_nsmap[namespace]
break
self.soup.handle_endtag(name, nsprefix)
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
self.nsmaps.pop()
def pi(self, target, data):
self.soup.endData()
self.soup.handle_data(target + ' ' + data)
self.soup.endData(ProcessingInstruction)
def data(self, content):
self.soup.handle_data(content)
def doctype(self, name, pubid, system):
self.soup.endData()
doctype = Doctype.for_name_and_ids(name, pubid, system)
self.soup.object_was_parsed(doctype)
def comment(self, content):
"Handle comments as Comment objects."
self.soup.endData()
self.soup.handle_data(content)
self.soup.endData(Comment)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
NAME = LXML
ALTERNATE_NAMES = ["lxml-html"]
features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
is_xml = False
def default_parser(self, encoding):
return etree.HTMLParser
def feed(self, markup):
encoding = self.soup.original_encoding
try:
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
raise ParserRejectedMarkup(str(e))
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><body>%s</body></html>' % fragment
-840
View File
@@ -1,840 +0,0 @@
# -*- coding: utf-8 -*-
"""Beautiful Soup bonus library: Unicode, Dammit
This library converts a bytestream to Unicode through any means
necessary. It is heavily based on code from Mark Pilgrim's Universal
Feed Parser. It works best on XML and HTML, but it does not rewrite the
XML or HTML to reflect a new encoding; that's the tree builder's job.
"""
__license__ = "MIT"
from pdb import set_trace
import codecs
from htmlentitydefs import codepoint2name
import re
import logging
import string
# Import a library to autodetect character encodings.
chardet_type = None
try:
# First try the fast C implementation.
# PyPI package: cchardet
import cchardet
def chardet_dammit(s):
return cchardet.detect(s)['encoding']
except ImportError:
try:
# Fall back to the pure Python implementation
# Debian package: python-chardet
# PyPI package: chardet
import chardet
def chardet_dammit(s):
return chardet.detect(s)['encoding']
#import chardet.constants
#chardet.constants._debug = 1
except ImportError:
# No chardet available.
def chardet_dammit(s):
return None
# Available from http://cjkpython.i18n.org/.
try:
import iconv_codec
except ImportError:
pass
xml_encoding_re = re.compile(
'^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I)
html_meta_re = re.compile(
'<\s*meta[^>]+charset\s*=\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I)
class EntitySubstitution(object):
"""Substitute XML or HTML entities for the corresponding characters."""
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
for codepoint, name in list(codepoint2name.items()):
character = unichr(codepoint)
if codepoint != 34:
# There's no point in turning the quotation mark into
# &quot;, unless it happens within an attribute value, which
# is handled elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to turn &quot; into the quotation mark.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
(CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
CHARACTER_TO_XML_ENTITY = {
"'": "apos",
'"': "quot",
"&": "amp",
"<": "lt",
">": "gt",
}
BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
"&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)"
")")
AMPERSAND_OR_BRACKET = re.compile("([<>&])")
@classmethod
def _substitute_html_entity(cls, matchobj):
entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
return "&%s;" % entity
@classmethod
def _substitute_xml_entity(cls, matchobj):
"""Used with a regular expression to substitute the
appropriate XML entity for an XML special character."""
entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
return "&%s;" % entity
@classmethod
def quoted_attribute_value(self, value):
"""Make a value into a quoted XML attribute, possibly escaping it.
Most strings will be quoted using double quotes.
Bob's Bar -> "Bob's Bar"
If a string contains double quotes, it will be quoted using
single quotes.
Welcome to "my bar" -> 'Welcome to "my bar"'
If a string contains both single and double quotes, the
double quotes will be escaped, and the string will be quoted
using double quotes.
Welcome to "Bob's Bar" -> "Welcome to &quot;Bob's bar&quot;
"""
quote_with = '"'
if '"' in value:
if "'" in value:
# The string contains both single and double
# quotes. Turn the double quotes into
# entities. We quote the double quotes rather than
# the single quotes because the entity name is
# "&quot;" whether this is HTML or XML. If we
# quoted the single quotes, we'd have to decide
# between &apos; and &squot;.
replace_with = "&quot;"
value = value.replace('"', replace_with)
else:
# There are double quotes but no single quotes.
# We can use single quotes to quote the attribute.
quote_with = "'"
return quote_with + value + quote_with
@classmethod
def substitute_xml(cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign
will become &lt;, the greater-than sign will become &gt;,
and any ampersands will become &amp;. If you want ampersands
that appear to be part of an entity definition to be left
alone, use substitute_xml_containing_entities() instead.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets and ampersands.
value = cls.AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_xml_containing_entities(
cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign will
become &lt;, the greater-than sign will become &gt;, and any
ampersands that are not part of an entity defition will
become &amp;.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets, and ampersands that aren't part of
# entities.
value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_html(cls, s):
"""Replace certain Unicode characters with named HTML entities.
This differs from data.encode(encoding, 'xmlcharrefreplace')
in that the goal is to make the result more readable (to those
with ASCII displays) rather than to recover from
errors. There's absolutely nothing wrong with a UTF-8 string
containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
character with "&eacute;" will make it more readable to some
people.
"""
return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
cls._substitute_html_entity, s)
class EncodingDetector:
"""Suggests a number of possible encodings for a bytestring.
Order of precedence:
1. Encodings you specifically tell EncodingDetector to try first
(the override_encodings argument to the constructor).
2. An encoding declared within the bytestring itself, either in an
XML declaration (if the bytestring is to be interpreted as an XML
document), or in a <meta> tag (if the bytestring is to be
interpreted as an HTML document.)
3. An encoding detected through textual analysis by chardet,
cchardet, or a similar external library.
4. UTF-8.
5. Windows-1252.
"""
def __init__(self, markup, override_encodings=None, is_html=False,
exclude_encodings=None):
self.override_encodings = override_encodings or []
exclude_encodings = exclude_encodings or []
self.exclude_encodings = set([x.lower() for x in exclude_encodings])
self.chardet_encoding = None
self.is_html = is_html
self.declared_encoding = None
# First order of business: strip a byte-order mark.
self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
def _usable(self, encoding, tried):
if encoding is not None:
encoding = encoding.lower()
if encoding in self.exclude_encodings:
return False
if encoding not in tried:
tried.add(encoding)
return True
return False
@property
def encodings(self):
"""Yield a number of encodings that might work for this markup."""
tried = set()
for e in self.override_encodings:
if self._usable(e, tried):
yield e
# Did the document originally start with a byte-order mark
# that indicated its encoding?
if self._usable(self.sniffed_encoding, tried):
yield self.sniffed_encoding
# Look within the document for an XML or HTML encoding
# declaration.
if self.declared_encoding is None:
self.declared_encoding = self.find_declared_encoding(
self.markup, self.is_html)
if self._usable(self.declared_encoding, tried):
yield self.declared_encoding
# Use third-party character set detection to guess at the
# encoding.
if self.chardet_encoding is None:
self.chardet_encoding = chardet_dammit(self.markup)
if self._usable(self.chardet_encoding, tried):
yield self.chardet_encoding
# As a last-ditch effort, try utf-8 and windows-1252.
for e in ('utf-8', 'windows-1252'):
if self._usable(e, tried):
yield e
@classmethod
def strip_byte_order_mark(cls, data):
"""If a byte-order mark is present, strip it and return the encoding it implies."""
encoding = None
if isinstance(data, unicode):
# Unicode data cannot have a byte-order mark.
return data, encoding
if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16be'
data = data[2:]
elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16le'
data = data[2:]
elif data[:3] == b'\xef\xbb\xbf':
encoding = 'utf-8'
data = data[3:]
elif data[:4] == b'\x00\x00\xfe\xff':
encoding = 'utf-32be'
data = data[4:]
elif data[:4] == b'\xff\xfe\x00\x00':
encoding = 'utf-32le'
data = data[4:]
return data, encoding
@classmethod
def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
"""Given a document, tries to find its declared encoding.
An XML encoding is declared at the beginning of the document.
An HTML encoding is declared in a <meta> tag, hopefully near the
beginning of the document.
"""
if search_entire_document:
xml_endpos = html_endpos = len(markup)
else:
xml_endpos = 1024
html_endpos = max(2048, int(len(markup) * 0.05))
declared_encoding = None
declared_encoding_match = xml_encoding_re.search(markup, endpos=xml_endpos)
if not declared_encoding_match and is_html:
declared_encoding_match = html_meta_re.search(markup, endpos=html_endpos)
if declared_encoding_match is not None:
declared_encoding = declared_encoding_match.groups()[0].decode(
'ascii', 'replace')
if declared_encoding:
return declared_encoding.lower()
return None
class UnicodeDammit:
"""A class for detecting the encoding of a *ML document and
converting it to a Unicode string. If the source encoding is
windows-1252, can replace MS smart quotes with their HTML or XML
equivalents."""
# This dictionary maps commonly seen values for "charset" in HTML
# meta tags to the corresponding Python codec names. It only covers
# values that aren't in Python's aliases and can't be determined
# by the heuristics in find_codec.
CHARSET_ALIASES = {"macintosh": "mac-roman",
"x-sjis": "shift-jis"}
ENCODINGS_WITH_SMART_QUOTES = [
"windows-1252",
"iso-8859-1",
"iso-8859-2",
]
def __init__(self, markup, override_encodings=[],
smart_quotes_to=None, is_html=False, exclude_encodings=[]):
self.smart_quotes_to = smart_quotes_to
self.tried_encodings = []
self.contains_replacement_characters = False
self.is_html = is_html
self.detector = EncodingDetector(
markup, override_encodings, is_html, exclude_encodings)
# Short-circuit if the data is in Unicode to begin with.
if isinstance(markup, unicode) or markup == '':
self.markup = markup
self.unicode_markup = unicode(markup)
self.original_encoding = None
return
# The encoding detector may have stripped a byte-order mark.
# Use the stripped markup from this point on.
self.markup = self.detector.markup
u = None
for encoding in self.detector.encodings:
markup = self.detector.markup
u = self._convert_from(encoding)
if u is not None:
break
if not u:
# None of the encodings worked. As an absolute last resort,
# try them again with character replacement.
for encoding in self.detector.encodings:
if encoding != "ascii":
u = self._convert_from(encoding, "replace")
if u is not None:
logging.warning(
"Some characters could not be decoded, and were "
"replaced with REPLACEMENT CHARACTER.")
self.contains_replacement_characters = True
break
# If none of that worked, we could at this point force it to
# ASCII, but that would destroy so much data that I think
# giving up is better.
self.unicode_markup = u
if not u:
self.original_encoding = None
def _sub_ms_char(self, match):
"""Changes a MS smart quote character to an XML or HTML
entity, or an ASCII character."""
orig = match.group(1)
if self.smart_quotes_to == 'ascii':
sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
else:
sub = self.MS_CHARS.get(orig)
if type(sub) == tuple:
if self.smart_quotes_to == 'xml':
sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
else:
sub = '&'.encode() + sub[0].encode() + ';'.encode()
else:
sub = sub.encode()
return sub
def _convert_from(self, proposed, errors="strict"):
proposed = self.find_codec(proposed)
if not proposed or (proposed, errors) in self.tried_encodings:
return None
self.tried_encodings.append((proposed, errors))
markup = self.markup
# Convert smart quotes to HTML if coming from an encoding
# that might have them.
if (self.smart_quotes_to is not None
and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
smart_quotes_re = b"([\x80-\x9f])"
smart_quotes_compiled = re.compile(smart_quotes_re)
markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
try:
#print "Trying to convert document to %s (errors=%s)" % (
# proposed, errors)
u = self._to_unicode(markup, proposed, errors)
self.markup = u
self.original_encoding = proposed
except Exception as e:
#print "That didn't work!"
#print e
return None
#print "Correct encoding: %s" % proposed
return self.markup
def _to_unicode(self, data, encoding, errors="strict"):
'''Given a string and its encoding, decodes the string into Unicode.
%encoding is a string recognized by encodings.aliases'''
return unicode(data, encoding, errors)
@property
def declared_html_encoding(self):
if not self.is_html:
return None
return self.detector.declared_encoding
def find_codec(self, charset):
value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
or (charset and self._codec(charset.replace("-", "")))
or (charset and self._codec(charset.replace("-", "_")))
or (charset and charset.lower())
or charset
)
if value:
return value.lower()
return None
def _codec(self, charset):
if not charset:
return charset
codec = None
try:
codecs.lookup(charset)
codec = charset
except (LookupError, ValueError):
pass
return codec
# A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
MS_CHARS = {b'\x80': ('euro', '20AC'),
b'\x81': ' ',
b'\x82': ('sbquo', '201A'),
b'\x83': ('fnof', '192'),
b'\x84': ('bdquo', '201E'),
b'\x85': ('hellip', '2026'),
b'\x86': ('dagger', '2020'),
b'\x87': ('Dagger', '2021'),
b'\x88': ('circ', '2C6'),
b'\x89': ('permil', '2030'),
b'\x8A': ('Scaron', '160'),
b'\x8B': ('lsaquo', '2039'),
b'\x8C': ('OElig', '152'),
b'\x8D': '?',
b'\x8E': ('#x17D', '17D'),
b'\x8F': '?',
b'\x90': '?',
b'\x91': ('lsquo', '2018'),
b'\x92': ('rsquo', '2019'),
b'\x93': ('ldquo', '201C'),
b'\x94': ('rdquo', '201D'),
b'\x95': ('bull', '2022'),
b'\x96': ('ndash', '2013'),
b'\x97': ('mdash', '2014'),
b'\x98': ('tilde', '2DC'),
b'\x99': ('trade', '2122'),
b'\x9a': ('scaron', '161'),
b'\x9b': ('rsaquo', '203A'),
b'\x9c': ('oelig', '153'),
b'\x9d': '?',
b'\x9e': ('#x17E', '17E'),
b'\x9f': ('Yuml', ''),}
# A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
# horrors like stripping diacritical marks to turn á into a, but also
# contains non-horrors like turning “ into ".
MS_CHARS_TO_ASCII = {
b'\x80' : 'EUR',
b'\x81' : ' ',
b'\x82' : ',',
b'\x83' : 'f',
b'\x84' : ',,',
b'\x85' : '...',
b'\x86' : '+',
b'\x87' : '++',
b'\x88' : '^',
b'\x89' : '%',
b'\x8a' : 'S',
b'\x8b' : '<',
b'\x8c' : 'OE',
b'\x8d' : '?',
b'\x8e' : 'Z',
b'\x8f' : '?',
b'\x90' : '?',
b'\x91' : "'",
b'\x92' : "'",
b'\x93' : '"',
b'\x94' : '"',
b'\x95' : '*',
b'\x96' : '-',
b'\x97' : '--',
b'\x98' : '~',
b'\x99' : '(TM)',
b'\x9a' : 's',
b'\x9b' : '>',
b'\x9c' : 'oe',
b'\x9d' : '?',
b'\x9e' : 'z',
b'\x9f' : 'Y',
b'\xa0' : ' ',
b'\xa1' : '!',
b'\xa2' : 'c',
b'\xa3' : 'GBP',
b'\xa4' : '$', #This approximation is especially parochial--this is the
#generic currency symbol.
b'\xa5' : 'YEN',
b'\xa6' : '|',
b'\xa7' : 'S',
b'\xa8' : '..',
b'\xa9' : '',
b'\xaa' : '(th)',
b'\xab' : '<<',
b'\xac' : '!',
b'\xad' : ' ',
b'\xae' : '(R)',
b'\xaf' : '-',
b'\xb0' : 'o',
b'\xb1' : '+-',
b'\xb2' : '2',
b'\xb3' : '3',
b'\xb4' : ("'", 'acute'),
b'\xb5' : 'u',
b'\xb6' : 'P',
b'\xb7' : '*',
b'\xb8' : ',',
b'\xb9' : '1',
b'\xba' : '(th)',
b'\xbb' : '>>',
b'\xbc' : '1/4',
b'\xbd' : '1/2',
b'\xbe' : '3/4',
b'\xbf' : '?',
b'\xc0' : 'A',
b'\xc1' : 'A',
b'\xc2' : 'A',
b'\xc3' : 'A',
b'\xc4' : 'A',
b'\xc5' : 'A',
b'\xc6' : 'AE',
b'\xc7' : 'C',
b'\xc8' : 'E',
b'\xc9' : 'E',
b'\xca' : 'E',
b'\xcb' : 'E',
b'\xcc' : 'I',
b'\xcd' : 'I',
b'\xce' : 'I',
b'\xcf' : 'I',
b'\xd0' : 'D',
b'\xd1' : 'N',
b'\xd2' : 'O',
b'\xd3' : 'O',
b'\xd4' : 'O',
b'\xd5' : 'O',
b'\xd6' : 'O',
b'\xd7' : '*',
b'\xd8' : 'O',
b'\xd9' : 'U',
b'\xda' : 'U',
b'\xdb' : 'U',
b'\xdc' : 'U',
b'\xdd' : 'Y',
b'\xde' : 'b',
b'\xdf' : 'B',
b'\xe0' : 'a',
b'\xe1' : 'a',
b'\xe2' : 'a',
b'\xe3' : 'a',
b'\xe4' : 'a',
b'\xe5' : 'a',
b'\xe6' : 'ae',
b'\xe7' : 'c',
b'\xe8' : 'e',
b'\xe9' : 'e',
b'\xea' : 'e',
b'\xeb' : 'e',
b'\xec' : 'i',
b'\xed' : 'i',
b'\xee' : 'i',
b'\xef' : 'i',
b'\xf0' : 'o',
b'\xf1' : 'n',
b'\xf2' : 'o',
b'\xf3' : 'o',
b'\xf4' : 'o',
b'\xf5' : 'o',
b'\xf6' : 'o',
b'\xf7' : '/',
b'\xf8' : 'o',
b'\xf9' : 'u',
b'\xfa' : 'u',
b'\xfb' : 'u',
b'\xfc' : 'u',
b'\xfd' : 'y',
b'\xfe' : 'b',
b'\xff' : 'y',
}
# A map used when removing rogue Windows-1252/ISO-8859-1
# characters in otherwise UTF-8 documents.
#
# Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
# Windows-1252.
WINDOWS_1252_TO_UTF8 = {
0x80 : b'\xe2\x82\xac', # €
0x82 : b'\xe2\x80\x9a', #
0x83 : b'\xc6\x92', # ƒ
0x84 : b'\xe2\x80\x9e', # „
0x85 : b'\xe2\x80\xa6', # …
0x86 : b'\xe2\x80\xa0', # †
0x87 : b'\xe2\x80\xa1', # ‡
0x88 : b'\xcb\x86', # ˆ
0x89 : b'\xe2\x80\xb0', # ‰
0x8a : b'\xc5\xa0', # Š
0x8b : b'\xe2\x80\xb9', #
0x8c : b'\xc5\x92', # Œ
0x8e : b'\xc5\xbd', # Ž
0x91 : b'\xe2\x80\x98', #
0x92 : b'\xe2\x80\x99', #
0x93 : b'\xe2\x80\x9c', # “
0x94 : b'\xe2\x80\x9d', # ”
0x95 : b'\xe2\x80\xa2', # •
0x96 : b'\xe2\x80\x93', #
0x97 : b'\xe2\x80\x94', # —
0x98 : b'\xcb\x9c', # ˜
0x99 : b'\xe2\x84\xa2', # ™
0x9a : b'\xc5\xa1', # š
0x9b : b'\xe2\x80\xba', #
0x9c : b'\xc5\x93', # œ
0x9e : b'\xc5\xbe', # ž
0x9f : b'\xc5\xb8', # Ÿ
0xa0 : b'\xc2\xa0', #  
0xa1 : b'\xc2\xa1', # ¡
0xa2 : b'\xc2\xa2', # ¢
0xa3 : b'\xc2\xa3', # £
0xa4 : b'\xc2\xa4', # ¤
0xa5 : b'\xc2\xa5', # ¥
0xa6 : b'\xc2\xa6', # ¦
0xa7 : b'\xc2\xa7', # §
0xa8 : b'\xc2\xa8', # ¨
0xa9 : b'\xc2\xa9', # ©
0xaa : b'\xc2\xaa', # ª
0xab : b'\xc2\xab', # «
0xac : b'\xc2\xac', # ¬
0xad : b'\xc2\xad', # ­
0xae : b'\xc2\xae', # ®
0xaf : b'\xc2\xaf', # ¯
0xb0 : b'\xc2\xb0', # °
0xb1 : b'\xc2\xb1', # ±
0xb2 : b'\xc2\xb2', # ²
0xb3 : b'\xc2\xb3', # ³
0xb4 : b'\xc2\xb4', # ´
0xb5 : b'\xc2\xb5', # µ
0xb6 : b'\xc2\xb6', # ¶
0xb7 : b'\xc2\xb7', # ·
0xb8 : b'\xc2\xb8', # ¸
0xb9 : b'\xc2\xb9', # ¹
0xba : b'\xc2\xba', # º
0xbb : b'\xc2\xbb', # »
0xbc : b'\xc2\xbc', # ¼
0xbd : b'\xc2\xbd', # ½
0xbe : b'\xc2\xbe', # ¾
0xbf : b'\xc2\xbf', # ¿
0xc0 : b'\xc3\x80', # À
0xc1 : b'\xc3\x81', # Á
0xc2 : b'\xc3\x82', # Â
0xc3 : b'\xc3\x83', # Ã
0xc4 : b'\xc3\x84', # Ä
0xc5 : b'\xc3\x85', # Å
0xc6 : b'\xc3\x86', # Æ
0xc7 : b'\xc3\x87', # Ç
0xc8 : b'\xc3\x88', # È
0xc9 : b'\xc3\x89', # É
0xca : b'\xc3\x8a', # Ê
0xcb : b'\xc3\x8b', # Ë
0xcc : b'\xc3\x8c', # Ì
0xcd : b'\xc3\x8d', # Í
0xce : b'\xc3\x8e', # Î
0xcf : b'\xc3\x8f', # Ï
0xd0 : b'\xc3\x90', # Ð
0xd1 : b'\xc3\x91', # Ñ
0xd2 : b'\xc3\x92', # Ò
0xd3 : b'\xc3\x93', # Ó
0xd4 : b'\xc3\x94', # Ô
0xd5 : b'\xc3\x95', # Õ
0xd6 : b'\xc3\x96', # Ö
0xd7 : b'\xc3\x97', # ×
0xd8 : b'\xc3\x98', # Ø
0xd9 : b'\xc3\x99', # Ù
0xda : b'\xc3\x9a', # Ú
0xdb : b'\xc3\x9b', # Û
0xdc : b'\xc3\x9c', # Ü
0xdd : b'\xc3\x9d', # Ý
0xde : b'\xc3\x9e', # Þ
0xdf : b'\xc3\x9f', # ß
0xe0 : b'\xc3\xa0', # à
0xe1 : b'\xa1', # á
0xe2 : b'\xc3\xa2', # â
0xe3 : b'\xc3\xa3', # ã
0xe4 : b'\xc3\xa4', # ä
0xe5 : b'\xc3\xa5', # å
0xe6 : b'\xc3\xa6', # æ
0xe7 : b'\xc3\xa7', # ç
0xe8 : b'\xc3\xa8', # è
0xe9 : b'\xc3\xa9', # é
0xea : b'\xc3\xaa', # ê
0xeb : b'\xc3\xab', # ë
0xec : b'\xc3\xac', # ì
0xed : b'\xc3\xad', # í
0xee : b'\xc3\xae', # î
0xef : b'\xc3\xaf', # ï
0xf0 : b'\xc3\xb0', # ð
0xf1 : b'\xc3\xb1', # ñ
0xf2 : b'\xc3\xb2', # ò
0xf3 : b'\xc3\xb3', # ó
0xf4 : b'\xc3\xb4', # ô
0xf5 : b'\xc3\xb5', # õ
0xf6 : b'\xc3\xb6', # ö
0xf7 : b'\xc3\xb7', # ÷
0xf8 : b'\xc3\xb8', # ø
0xf9 : b'\xc3\xb9', # ù
0xfa : b'\xc3\xba', # ú
0xfb : b'\xc3\xbb', # û
0xfc : b'\xc3\xbc', # ü
0xfd : b'\xc3\xbd', # ý
0xfe : b'\xc3\xbe', # þ
}
MULTIBYTE_MARKERS_AND_SIZES = [
(0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
(0xe0, 0xef, 3), # 3-byte characters start with E0-EF
(0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
]
FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
@classmethod
def detwingle(cls, in_bytes, main_encoding="utf8",
embedded_encoding="windows-1252"):
"""Fix characters from one encoding embedded in some other encoding.
Currently the only situation supported is Windows-1252 (or its
subset ISO-8859-1), embedded in UTF-8.
The input must be a bytestring. If you've already converted
the document to Unicode, you're too late.
The output is a bytestring in which `embedded_encoding`
characters have been converted to their `main_encoding`
equivalents.
"""
if embedded_encoding.replace('_', '-').lower() not in (
'windows-1252', 'windows_1252'):
raise NotImplementedError(
"Windows-1252 and ISO-8859-1 are the only currently supported "
"embedded encodings.")
if main_encoding.lower() not in ('utf8', 'utf-8'):
raise NotImplementedError(
"UTF-8 is the only currently supported main encoding.")
byte_chunks = []
chunk_start = 0
pos = 0
while pos < len(in_bytes):
byte = in_bytes[pos]
if not isinstance(byte, int):
# Python 2.x
byte = ord(byte)
if (byte >= cls.FIRST_MULTIBYTE_MARKER
and byte <= cls.LAST_MULTIBYTE_MARKER):
# This is the start of a UTF-8 multibyte character. Skip
# to the end.
for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
if byte >= start and byte <= end:
pos += size
break
elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
# We found a Windows-1252 character!
# Save the string up to this point as a chunk.
byte_chunks.append(in_bytes[chunk_start:pos])
# Now translate the Windows-1252 character into UTF-8
# and add it as another, one-byte chunk.
byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
pos += 1
chunk_start = pos
else:
# Go on to the next character.
pos += 1
if chunk_start == 0:
# The string is unchanged.
return in_bytes
else:
# Store the final chunk.
byte_chunks.append(in_bytes[chunk_start:])
return b''.join(byte_chunks)
-216
View File
@@ -1,216 +0,0 @@
"""Diagnostic functions, mainly for use when doing tech support."""
__license__ = "MIT"
import cProfile
from StringIO import StringIO
from HTMLParser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
import os
import pstats
import random
import tempfile
import time
import traceback
import sys
import cProfile
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print "Diagnostic running on Beautiful Soup %s" % __version__
print "Python version %s" % sys.version
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print (
"I noticed that %s is not installed. Installing it may help." %
name)
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
try:
from lxml import etree
print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
except ImportError, e:
print (
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print "Found html5lib version %s" % html5lib.__version__
except ImportError, e:
print (
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print '"%s" looks like a filename. Reading data from the file.' % data
data = open(data).read()
elif data.startswith("http:") or data.startswith("https:"):
print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
return
print
for parser in basic_parsers:
print "Trying to parse your markup with %s" % parser
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception, e:
print "%s could not parse the markup." % parser
traceback.print_exc()
if success:
print "Here's what %s did with the markup:" % parser
print soup.prettify()
print "-" * 80
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
This lets you see how lxml parses a document when no Beautiful
Soup code is running.
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
print("%s, %4s, %s" % (event, element.tag, element.text))
class AnnouncingParser(HTMLParser):
"""Announces HTMLParser parse events, without doing anything else."""
def _p(self, s):
print(s)
def handle_starttag(self, name, attrs):
self._p("%s START" % name)
def handle_endtag(self, name):
self._p("%s END" % name)
def handle_data(self, data):
self._p("%s DATA" % data)
def handle_charref(self, name):
self._p("%s CHARREF" % name)
def handle_entityref(self, name):
self._p("%s ENTITYREF" % name)
def handle_comment(self, data):
self._p("%s COMMENT" % data)
def handle_decl(self, data):
self._p("%s DECL" % data)
def unknown_decl(self, data):
self._p("%s UNKNOWN-DECL" % data)
def handle_pi(self, data):
self._p("%s PI" % data)
def htmlparser_trace(data):
"""Print out the HTMLParser events that occur during parsing.
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
"""
parser = AnnouncingParser()
parser.feed(data)
_vowels = "aeiou"
_consonants = "bcdfghjklmnpqrstvwxyz"
def rword(length=5):
"Generate a random word-like string."
s = ''
for i in range(length):
if i % 2 == 0:
t = _consonants
else:
t = _vowels
s += random.choice(t)
return s
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
elements = []
for i in range(num_elements):
choice = random.randint(0,3)
if choice == 0:
# New tag.
tag_name = random.choice(tag_names)
elements.append("<%s>" % tag_name)
elif choice == 1:
elements.append(rsentence(random.randint(1,4)))
elif choice == 2:
# Close a tag.
tag_name = random.choice(tag_names)
elements.append("</%s>" % tag_name)
return "<html>" + "\n".join(elements) + "</html>"
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print "Comparative parser benchmark on Beautiful Soup %s" % __version__
data = rdoc(num_elements)
print "Generated a large invalid HTML document (%d bytes)." % len(data)
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception, e:
print "%s could not parse the markup." % parser
traceback.print_exc()
if success:
print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print "Raw lxml parsed the markup in %.2fs." % (b-a)
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print "Raw html5lib parsed the markup in %.2fs." % (b-a)
def profile(num_elements=100000, parser="lxml"):
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
data = rdoc(num_elements)
vars = dict(bs4=bs4, data=data, parser=parser)
cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
stats = pstats.Stats(filename)
# stats.strip_dirs()
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
if __name__ == '__main__':
diagnose(sys.stdin.read())
File diff suppressed because it is too large Load Diff
-687
View File
@@ -1,687 +0,0 @@
"""Helper classes for tests."""
__license__ = "MIT"
import pickle
import copy
import functools
import unittest
from unittest import TestCase
from bs4 import BeautifulSoup
from bs4.element import (
CharsetMetaAttributeValue,
Comment,
ContentMetaAttributeValue,
Doctype,
SoupStrainer,
)
from bs4.builder import HTMLParserTreeBuilder
default_builder = HTMLParserTreeBuilder
class SoupTest(unittest.TestCase):
@property
def default_builder(self):
return default_builder()
def soup(self, markup, **kwargs):
"""Build a Beautiful Soup object from markup."""
builder = kwargs.pop('builder', self.default_builder)
return BeautifulSoup(markup, builder=builder, **kwargs)
def document_for(self, markup):
"""Turn an HTML fragment into a document.
The details depend on the builder.
"""
return self.default_builder.test_fragment_to_document(markup)
def assertSoupEquals(self, to_parse, compare_parsed_to=None):
builder = self.default_builder
obj = BeautifulSoup(to_parse, builder=builder)
if compare_parsed_to is None:
compare_parsed_to = to_parse
self.assertEqual(obj.decode(), self.document_for(compare_parsed_to))
def assertConnectedness(self, element):
"""Ensure that next_element and previous_element are properly
set for all descendants of the given element.
"""
earlier = None
for e in element.descendants:
if earlier:
self.assertEqual(e, earlier.next_element)
self.assertEqual(earlier, e.previous_element)
earlier = e
class HTMLTreeBuilderSmokeTest(object):
"""A basic test of a treebuilder's competence.
Any HTML treebuilder, present or future, should be able to pass
these tests. With invalid markup, there's room for interpretation,
and different parsers can handle it differently. But with the
markup in these tests, there's not much room for interpretation.
"""
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertEqual(loaded.__class__, BeautifulSoup)
self.assertEqual(loaded.decode(), tree.decode())
def assertDoctypeHandled(self, doctype_fragment):
"""Assert that a given doctype string is handled correctly."""
doctype_str, soup = self._document_with_doctype(doctype_fragment)
# Make sure a Doctype object was created.
doctype = soup.contents[0]
self.assertEqual(doctype.__class__, Doctype)
self.assertEqual(doctype, doctype_fragment)
self.assertEqual(str(soup)[:len(doctype_str)], doctype_str)
# Make sure that the doctype was correctly associated with the
# parse tree and that the rest of the document parsed.
self.assertEqual(soup.p.contents[0], 'foo')
def _document_with_doctype(self, doctype_fragment):
"""Generate and parse a document with the given doctype."""
doctype = '<!DOCTYPE %s>' % doctype_fragment
markup = doctype + '\n<p>foo</p>'
soup = self.soup(markup)
return doctype, soup
def test_normal_doctypes(self):
"""Make sure normal, everyday HTML doctypes are handled correctly."""
self.assertDoctypeHandled("html")
self.assertDoctypeHandled(
'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
def test_empty_doctype(self):
soup = self.soup("<!DOCTYPE>")
doctype = soup.contents[0]
self.assertEqual("", doctype.strip())
def test_public_doctype_with_url(self):
doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
self.assertDoctypeHandled(doctype)
def test_system_doctype(self):
self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
def test_namespaced_system_doctype(self):
# We can handle a namespaced doctype with a system ID.
self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
def test_namespaced_public_doctype(self):
# Test a namespaced doctype with a public id.
self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
def test_real_xhtml_document(self):
"""A real XHTML document should come out more or less the same as it went in."""
markup = b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><title>Hello.</title></head>
<body>Goodbye.</body>
</html>"""
soup = self.soup(markup)
self.assertEqual(
soup.encode("utf-8").replace(b"\n", b""),
markup.replace(b"\n", b""))
def test_processing_instruction(self):
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.encode("utf8"))
def test_deepcopy(self):
"""Make sure you can copy the tree builder.
This is important because the builder is part of a
BeautifulSoup object, and we want to be able to copy that.
"""
copy.deepcopy(self.default_builder)
def test_p_tag_is_never_empty_element(self):
"""A <p> tag is never designated as an empty-element tag.
Even if the markup shows it as an empty-element tag, it
shouldn't be presented that way.
"""
soup = self.soup("<p/>")
self.assertFalse(soup.p.is_empty_element)
self.assertEqual(str(soup.p), "<p></p>")
def test_unclosed_tags_get_closed(self):
"""A tag that's not closed by the end of the document should be closed.
This applies to all tags except empty-element tags.
"""
self.assertSoupEquals("<p>", "<p></p>")
self.assertSoupEquals("<b>", "<b></b>")
self.assertSoupEquals("<br>", "<br/>")
def test_br_is_always_empty_element_tag(self):
"""A <br> tag is designated as an empty-element tag.
Some parsers treat <br></br> as one <br/> tag, some parsers as
two tags, but it should always be an empty-element tag.
"""
soup = self.soup("<br></br>")
self.assertTrue(soup.br.is_empty_element)
self.assertEqual(str(soup.br), "<br/>")
def test_nested_formatting_elements(self):
self.assertSoupEquals("<em><em></em></em>")
def test_double_head(self):
html = '''<!DOCTYPE html>
<html>
<head>
<title>Ordinary HEAD element test</title>
</head>
<script type="text/javascript">
alert("Help!");
</script>
<body>
Hello, world!
</body>
</html>
'''
soup = self.soup(html)
self.assertEqual("text/javascript", soup.find('script')['type'])
def test_comment(self):
# Comments are represented as Comment objects.
markup = "<p>foo<!--foobar-->baz</p>"
self.assertSoupEquals(markup)
soup = self.soup(markup)
comment = soup.find(text="foobar")
self.assertEqual(comment.__class__, Comment)
# The comment is properly integrated into the tree.
foo = soup.find(text="foo")
self.assertEqual(comment, foo.next_element)
baz = soup.find(text="baz")
self.assertEqual(comment, baz.previous_element)
def test_preserved_whitespace_in_pre_and_textarea(self):
"""Whitespace must be preserved in <pre> and <textarea> tags."""
self.assertSoupEquals("<pre> </pre>")
self.assertSoupEquals("<textarea> woo </textarea>")
def test_nested_inline_elements(self):
"""Inline elements can be nested indefinitely."""
b_tag = "<b>Inside a B tag</b>"
self.assertSoupEquals(b_tag)
nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
self.assertSoupEquals(nested_b_tag)
double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
self.assertSoupEquals(nested_b_tag)
def test_nested_block_level_elements(self):
"""Block elements can be nested."""
soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
blockquote = soup.blockquote
self.assertEqual(blockquote.p.b.string, 'Foo')
self.assertEqual(blockquote.b.string, 'Foo')
def test_correctly_nested_tables(self):
"""One table can go inside another one."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assertSoupEquals(
markup,
'<table id="1"><tr><td>Here\'s another table:'
'<table id="2"><tr><td>foo</td></tr></table>'
'</td></tr></table>')
self.assertSoupEquals(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_deeply_nested_multivalued_attribute(self):
# html5lib can set the attributes of the same tag many times
# as it rearranges the tree. This has caused problems with
# multivalued attributes.
markup = '<table><div><div class="css"></div></div></table>'
soup = self.soup(markup)
self.assertEqual(["css"], soup.div.div['class'])
def test_multivalued_attribute_on_html(self):
# html5lib uses a different API to set the attributes ot the
# <html> tag. This has caused problems with multivalued
# attributes.
markup = '<html class="a b"></html>'
soup = self.soup(markup)
self.assertEqual(["a", "b"], soup.html['class'])
def test_angle_brackets_in_attribute_values_are_escaped(self):
self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
def test_entities_in_attributes_converted_to_unicode(self):
expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
def test_entities_in_text_converted_to_unicode(self):
expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&ntilde;ata</p>", expect)
def test_quot_entity_converted_to_quotation_mark(self):
self.assertSoupEquals("<p>I said &quot;good day!&quot;</p>",
'<p>I said "good day!"</p>')
def test_out_of_range_entity(self):
expect = u"\N{REPLACEMENT CHARACTER}"
self.assertSoupEquals("&#10000000000000;", expect)
self.assertSoupEquals("&#x10000000000000;", expect)
self.assertSoupEquals("&#1000000000;", expect)
def test_multipart_strings(self):
"Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
soup = self.soup("<html><h2>\nfoo</h2><p></p></html>")
self.assertEqual("p", soup.h2.string.next_element.name)
self.assertEqual("p", soup.p.name)
self.assertConnectedness(soup)
def test_head_tag_between_head_and_body(self):
"Prevent recurrence of a bug in the html5lib treebuilder."
content = """<html><head></head>
<link></link>
<body>foo</body>
</html>
"""
soup = self.soup(content)
self.assertNotEqual(None, soup.html.body)
self.assertConnectedness(soup)
def test_multiple_copies_of_a_tag(self):
"Prevent recurrence of a bug in the html5lib treebuilder."
content = """<!DOCTYPE html>
<html>
<body>
<article id="a" >
<div><a href="1"></div>
<footer>
<a href="2"></a>
</footer>
</article>
</body>
</html>
"""
soup = self.soup(content)
self.assertConnectedness(soup.article)
def test_basic_namespaces(self):
"""Parsers don't need to *understand* namespaces, but at the
very least they should not choke on namespaces or lose
data."""
markup = b'<html xmlns="http://www.w3.org/1999/xhtml" xmlns:mathml="http://www.w3.org/1998/Math/MathML" xmlns:svg="http://www.w3.org/2000/svg"><head></head><body><mathml:msqrt>4</mathml:msqrt><b svg:fill="red"></b></body></html>'
soup = self.soup(markup)
self.assertEqual(markup, soup.encode())
html = soup.html
self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
self.assertEqual(
'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
self.assertEqual(
'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
def test_multivalued_attribute_value_becomes_list(self):
markup = b'<a class="foo bar">'
soup = self.soup(markup)
self.assertEqual(['foo', 'bar'], soup.a['class'])
#
# Generally speaking, tests below this point are more tests of
# Beautiful Soup than tests of the tree builders. But parsers are
# weird, so we run these tests separately for every tree builder
# to detect any differences between them.
#
def test_can_parse_unicode_document(self):
# A seemingly innocuous document... but it's in Unicode! And
# it contains characters that can't be represented in the
# encoding found in the declaration! The horror!
markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
def test_soupstrainer(self):
"""Parsers should be able to work with SoupStrainers."""
strainer = SoupStrainer("b")
soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
parse_only=strainer)
self.assertEqual(soup.decode(), "<b>bold</b>")
def test_single_quote_attribute_values_become_double_quotes(self):
self.assertSoupEquals("<foo attr='bar'></foo>",
'<foo attr="bar"></foo>')
def test_attribute_values_with_nested_quotes_are_left_alone(self):
text = """<foo attr='bar "brawls" happen'>a</foo>"""
self.assertSoupEquals(text)
def test_attribute_values_with_double_nested_quotes_get_quoted(self):
text = """<foo attr='bar "brawls" happen'>a</foo>"""
soup = self.soup(text)
soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
self.assertSoupEquals(
soup.foo.decode(),
"""<foo attr="Brawls happen at &quot;Bob\'s Bar&quot;">a</foo>""")
def test_ampersand_in_attribute_value_gets_escaped(self):
self.assertSoupEquals('<this is="really messed up & stuff"></this>',
'<this is="really messed up &amp; stuff"></this>')
self.assertSoupEquals(
'<a href="http://example.org?a=1&b=2;3">foo</a>',
'<a href="http://example.org?a=1&amp;b=2;3">foo</a>')
def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
self.assertSoupEquals('<a href="http://example.org?a=1&amp;b=2;3"></a>')
def test_entities_in_strings_converted_during_parsing(self):
# Both XML and HTML entities are converted to Unicode characters
# during parsing.
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
self.assertSoupEquals(text, expected)
def test_smart_quotes_converted_on_the_way_in(self):
# Microsoft smart quotes are converted to Unicode characters during
# parsing.
quote = b"<p>\x91Foo\x92</p>"
soup = self.soup(quote)
self.assertEqual(
soup.p.string,
u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
def test_non_breaking_spaces_converted_on_the_way_in(self):
soup = self.soup("<a>&nbsp;&nbsp;</a>")
self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
def test_entities_converted_on_the_way_out(self):
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
soup = self.soup(text)
self.assertEqual(soup.p.encode("utf-8"), expected)
def test_real_iso_latin_document(self):
# Smoke test of interrelated functionality, using an
# easy-to-understand document.
# Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
# That's because we're going to encode it into ISO-Latin-1, and use
# that to test.
iso_latin_html = unicode_html.encode("iso-8859-1")
# Parse the ISO-Latin-1 HTML.
soup = self.soup(iso_latin_html)
# Encode it to UTF-8.
result = soup.encode("utf-8")
# What do we expect the result to look like? Well, it would
# look like unicode_html, except that the META tag would say
# UTF-8 instead of ISO-Latin-1.
expected = unicode_html.replace("ISO-Latin-1", "utf-8")
# And, of course, it would be in UTF-8, not Unicode.
expected = expected.encode("utf-8")
# Ta-da!
self.assertEqual(result, expected)
def test_real_shift_jis_document(self):
# Smoke test to make sure the parser can handle a document in
# Shift-JIS encoding, without choking.
shift_jis_html = (
b'<html><head></head><body><pre>'
b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
b'</pre></body></html>')
unicode_html = shift_jis_html.decode("shift-jis")
soup = self.soup(unicode_html)
# Make sure the parse tree is correctly encoded to various
# encodings.
self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
def test_real_hebrew_document(self):
# A real-world test to make sure we can convert ISO-8859-9 (a
# Hebrew encoding) to UTF-8.
hebrew_document = b'<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xed\xe5\xec\xf9</body></html>'
soup = self.soup(
hebrew_document, from_encoding="iso8859-8")
self.assertEqual(soup.original_encoding, 'iso8859-8')
self.assertEqual(
soup.encode('utf-8'),
hebrew_document.decode("iso8859-8").encode("utf-8"))
def test_meta_tag_reflects_current_encoding(self):
# Here's the <meta> tag saying that a document is
# encoded in Shift-JIS.
meta_tag = ('<meta content="text/html; charset=x-sjis" '
'http-equiv="Content-type"/>')
# Here's a document incorporating that meta tag.
shift_jis_html = (
'<html><head>\n%s\n'
'<meta http-equiv="Content-language" content="ja"/>'
'</head><body>Shift-JIS markup goes here.') % meta_tag
soup = self.soup(shift_jis_html)
# Parse the document, and the charset is seemingly unaffected.
parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
content = parsed_meta['content']
self.assertEqual('text/html; charset=x-sjis', content)
# But that value is actually a ContentMetaAttributeValue object.
self.assertTrue(isinstance(content, ContentMetaAttributeValue))
# And it will take on a value that reflects its current
# encoding.
self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
# For the rest of the story, see TestSubstitutions in
# test_tree.py.
def test_html5_style_meta_tag_reflects_current_encoding(self):
# Here's the <meta> tag saying that a document is
# encoded in Shift-JIS.
meta_tag = ('<meta id="encoding" charset="x-sjis" />')
# Here's a document incorporating that meta tag.
shift_jis_html = (
'<html><head>\n%s\n'
'<meta http-equiv="Content-language" content="ja"/>'
'</head><body>Shift-JIS markup goes here.') % meta_tag
soup = self.soup(shift_jis_html)
# Parse the document, and the charset is seemingly unaffected.
parsed_meta = soup.find('meta', id="encoding")
charset = parsed_meta['charset']
self.assertEqual('x-sjis', charset)
# But that value is actually a CharsetMetaAttributeValue object.
self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
# And it will take on a value that reflects its current
# encoding.
self.assertEqual('utf8', charset.encode("utf8"))
def test_tag_with_no_attributes_can_have_attributes_added(self):
data = self.soup("<a>text</a>")
data.a['foo'] = 'bar'
self.assertEqual('<a foo="bar">text</a>', data.a.decode())
class XMLTreeBuilderSmokeTest(object):
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertEqual(loaded.__class__, BeautifulSoup)
self.assertEqual(loaded.decode(), tree.decode())
def test_docstring_generated(self):
soup = self.soup("<root/>")
self.assertEqual(
soup.encode(), b'<?xml version="1.0" encoding="utf-8"?>\n<root/>')
def test_xml_declaration(self):
markup = b"""<?xml version="1.0" encoding="utf8"?>\n<foo/>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.encode("utf8"))
def test_real_xhtml_document(self):
"""A real XHTML document should come out *exactly* the same as it went in."""
markup = b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><title>Hello.</title></head>
<body>Goodbye.</body>
</html>"""
soup = self.soup(markup)
self.assertEqual(
soup.encode("utf-8"), markup)
def test_formatter_processes_script_tag_for_xml_documents(self):
doc = """
<script type="text/javascript">
</script>
"""
soup = BeautifulSoup(doc, "lxml-xml")
# lxml would have stripped this while parsing, but we can add
# it later.
soup.script.string = 'console.log("< < hey > > ");'
encoded = soup.encode()
self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
def test_can_parse_unicode_document(self):
markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
def test_popping_namespaced_tag(self):
markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
soup = self.soup(markup)
self.assertEqual(
unicode(soup.rss), markup)
def test_docstring_includes_correct_encoding(self):
soup = self.soup("<root/>")
self.assertEqual(
soup.encode("latin1"),
b'<?xml version="1.0" encoding="latin1"?>\n<root/>')
def test_large_xml_document(self):
"""A large XML document should come out the same as it went in."""
markup = (b'<?xml version="1.0" encoding="utf-8"?>\n<root>'
+ b'0' * (2**12)
+ b'</root>')
soup = self.soup(markup)
self.assertEqual(soup.encode("utf-8"), markup)
def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
self.assertSoupEquals("<p>", "<p/>")
self.assertSoupEquals("<p>foo</p>")
def test_namespaces_are_preserved(self):
markup = '<root xmlns:a="http://example.com/" xmlns:b="http://example.net/"><a:foo>This tag is in the a namespace</a:foo><b:foo>This tag is in the b namespace</b:foo></root>'
soup = self.soup(markup)
root = soup.root
self.assertEqual("http://example.com/", root['xmlns:a'])
self.assertEqual("http://example.net/", root['xmlns:b'])
def test_closing_namespaced_tag(self):
markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.p), markup)
def test_namespaced_attributes(self):
markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
def test_namespaced_attributes_xml_namespace(self):
markup = '<foo xml:lang="fr">bar</foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
"""Smoke test for a tree builder that supports HTML5."""
def test_real_xhtml_document(self):
# Since XHTML is not HTML5, HTML5 parsers are not tested to handle
# XHTML documents in any particular way.
pass
def test_html_tags_have_namespace(self):
markup = "<a>"
soup = self.soup(markup)
self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
def test_svg_tags_have_namespace(self):
markup = '<svg><circle/></svg>'
soup = self.soup(markup)
namespace = "http://www.w3.org/2000/svg"
self.assertEqual(namespace, soup.svg.namespace)
self.assertEqual(namespace, soup.circle.namespace)
def test_mathml_tags_have_namespace(self):
markup = '<math><msqrt>5</msqrt></math>'
soup = self.soup(markup)
namespace = 'http://www.w3.org/1998/Math/MathML'
self.assertEqual(namespace, soup.math.namespace)
self.assertEqual(namespace, soup.msqrt.namespace)
def test_xml_declaration_becomes_comment(self):
markup = '<?xml version="1.0" encoding="utf-8"?><html></html>'
soup = self.soup(markup)
self.assertTrue(isinstance(soup.contents[0], Comment))
self.assertEqual(soup.contents[0], '?xml version="1.0" encoding="utf-8"?')
self.assertEqual("html", soup.contents[0].next_element.name)
def skipIf(condition, reason):
def nothing(test, *args, **kwargs):
return None
def decorator(test_item):
if condition:
return nothing
else:
return test_item
return decorator
@@ -1 +0,0 @@
"The beautifulsoup tests."
@@ -1,147 +0,0 @@
"""Tests of the builder registry."""
import unittest
import warnings
from bs4 import BeautifulSoup
from bs4.builder import (
builder_registry as registry,
HTMLParserTreeBuilder,
TreeBuilderRegistry,
)
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError:
HTML5LIB_PRESENT = False
try:
from bs4.builder import (
LXMLTreeBuilderForXML,
LXMLTreeBuilder,
)
LXML_PRESENT = True
except ImportError:
LXML_PRESENT = False
class BuiltInRegistryTest(unittest.TestCase):
"""Test the built-in registry with the default builders registered."""
def test_combination(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('fast', 'html'),
LXMLTreeBuilder)
if LXML_PRESENT:
self.assertEqual(registry.lookup('permissive', 'xml'),
LXMLTreeBuilderForXML)
self.assertEqual(registry.lookup('strict', 'html'),
HTMLParserTreeBuilder)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html5lib', 'html'),
HTML5TreeBuilder)
def test_lookup_by_markup_type(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('html'), LXMLTreeBuilder)
self.assertEqual(registry.lookup('xml'), LXMLTreeBuilderForXML)
else:
self.assertEqual(registry.lookup('xml'), None)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html'), HTML5TreeBuilder)
else:
self.assertEqual(registry.lookup('html'), HTMLParserTreeBuilder)
def test_named_library(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('lxml', 'xml'),
LXMLTreeBuilderForXML)
self.assertEqual(registry.lookup('lxml', 'html'),
LXMLTreeBuilder)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html5lib'),
HTML5TreeBuilder)
self.assertEqual(registry.lookup('html.parser'),
HTMLParserTreeBuilder)
def test_beautifulsoup_constructor_does_lookup(self):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
# You can pass in a string.
BeautifulSoup("", features="html")
# Or a list of strings.
BeautifulSoup("", features=["html", "fast"])
# You'll get an exception if BS can't find an appropriate
# builder.
self.assertRaises(ValueError, BeautifulSoup,
"", features="no-such-feature")
class RegistryTest(unittest.TestCase):
"""Test the TreeBuilderRegistry class in general."""
def setUp(self):
self.registry = TreeBuilderRegistry()
def builder_for_features(self, *feature_list):
cls = type('Builder_' + '_'.join(feature_list),
(object,), {'features' : feature_list})
self.registry.register(cls)
return cls
def test_register_with_no_features(self):
builder = self.builder_for_features()
# Since the builder advertises no features, you can't find it
# by looking up features.
self.assertEqual(self.registry.lookup('foo'), None)
# But you can find it by doing a lookup with no features, if
# this happens to be the only registered builder.
self.assertEqual(self.registry.lookup(), builder)
def test_register_with_features_makes_lookup_succeed(self):
builder = self.builder_for_features('foo', 'bar')
self.assertEqual(self.registry.lookup('foo'), builder)
self.assertEqual(self.registry.lookup('bar'), builder)
def test_lookup_fails_when_no_builder_implements_feature(self):
builder = self.builder_for_features('foo', 'bar')
self.assertEqual(self.registry.lookup('baz'), None)
def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
builder1 = self.builder_for_features('foo')
builder2 = self.builder_for_features('bar')
self.assertEqual(self.registry.lookup(), builder2)
def test_lookup_fails_when_no_tree_builders_registered(self):
self.assertEqual(self.registry.lookup(), None)
def test_lookup_gets_most_recent_builder_supporting_all_features(self):
has_one = self.builder_for_features('foo')
has_the_other = self.builder_for_features('bar')
has_both_early = self.builder_for_features('foo', 'bar', 'baz')
has_both_late = self.builder_for_features('foo', 'bar', 'quux')
lacks_one = self.builder_for_features('bar')
has_the_other = self.builder_for_features('foo')
# There are two builders featuring 'foo' and 'bar', but
# the one that also features 'quux' was registered later.
self.assertEqual(self.registry.lookup('foo', 'bar'),
has_both_late)
# There is only one builder featuring 'foo', 'bar', and 'baz'.
self.assertEqual(self.registry.lookup('foo', 'bar', 'baz'),
has_both_early)
def test_lookup_fails_when_cannot_reconcile_requested_features(self):
builder1 = self.builder_for_features('foo', 'bar')
builder2 = self.builder_for_features('foo', 'baz')
self.assertEqual(self.registry.lookup('bar', 'baz'), None)
@@ -1,36 +0,0 @@
"Test harness for doctests."
# pylint: disable-msg=E0611,W0142
__metaclass__ = type
__all__ = [
'additional_tests',
]
import atexit
import doctest
import os
#from pkg_resources import (
# resource_filename, resource_exists, resource_listdir, cleanup_resources)
import unittest
DOCTEST_FLAGS = (
doctest.ELLIPSIS |
doctest.NORMALIZE_WHITESPACE |
doctest.REPORT_NDIFF)
# def additional_tests():
# "Run the doc tests (README.txt and docs/*, if any exist)"
# doctest_files = [
# os.path.abspath(resource_filename('bs4', 'README.txt'))]
# if resource_exists('bs4', 'docs'):
# for name in resource_listdir('bs4', 'docs'):
# if name.endswith('.txt'):
# doctest_files.append(
# os.path.abspath(
# resource_filename('bs4', 'docs/%s' % name)))
# kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
# atexit.register(cleanup_resources)
# return unittest.TestSuite((
# doctest.DocFileSuite(*doctest_files, **kwargs)))
@@ -1,98 +0,0 @@
"""Tests to ensure that the html5lib tree builder generates good trees."""
import warnings
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError, e:
HTML5LIB_PRESENT = False
from bs4.element import SoupStrainer
from bs4.testing import (
HTML5TreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not HTML5LIB_PRESENT,
"html5lib seems not to be present, not testing its tree builder.")
class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
"""See ``HTML5TreeBuilderSmokeTest``."""
@property
def default_builder(self):
return HTML5TreeBuilder()
def test_soupstrainer(self):
# The html5lib tree builder does not support SoupStrainers.
strainer = SoupStrainer("b")
markup = "<p>A <b>bold</b> statement.</p>"
with warnings.catch_warnings(record=True) as w:
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(
soup.decode(), self.document_for(markup))
self.assertTrue(
"the html5lib tree builder doesn't support parse_only" in
str(w[0].message))
def test_correctly_nested_tables(self):
"""html5lib inserts <tbody> tags where other parsers don't."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assertSoupEquals(
markup,
'<table id="1"><tbody><tr><td>Here\'s another table:'
'<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
'</td></tr></tbody></table>')
self.assertSoupEquals(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_xml_declaration_followed_by_doctype(self):
markup = '''<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html>
<html>
<head>
</head>
<body>
<p>foo</p>
</body>
</html>'''
soup = self.soup(markup)
# Verify that we can reach the <p> tag; this means the tree is connected.
self.assertEqual(b"<p>foo</p>", soup.p.encode())
def test_reparented_markup(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
soup = self.soup(markup)
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
def test_reparented_markup_ends_with_whitespace(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
soup = self.soup(markup)
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
def test_processing_instruction(self):
"""Processing instructions become comments."""
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
assert str(soup).startswith("<!--?PITarget PIContent?-->")
def test_cloned_multivalue_node(self):
markup = b"""<a class="my_class"><p></a>"""
soup = self.soup(markup)
a1, a2 = soup.find_all('a')
self.assertEqual(a1, a2)
assert a1 is not a2
@@ -1,32 +0,0 @@
"""Tests to ensure that the html.parser tree builder generates good
trees."""
from pdb import set_trace
import pickle
from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
from bs4.builder import HTMLParserTreeBuilder
class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
@property
def default_builder(self):
return HTMLParserTreeBuilder()
def test_namespaced_system_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_namespaced_public_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_builder_is_pickled(self):
"""Unlike most tree builders, HTMLParserTreeBuilder and will
be restored after pickling.
"""
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertTrue(isinstance(loaded.builder, type(tree.builder)))
@@ -1,76 +0,0 @@
"""Tests to ensure that the lxml tree builder generates good trees."""
import re
import warnings
try:
import lxml.etree
LXML_PRESENT = True
LXML_VERSION = lxml.etree.LXML_VERSION
except ImportError, e:
LXML_PRESENT = False
LXML_VERSION = (0,)
if LXML_PRESENT:
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
)
from bs4.element import Comment, Doctype, SoupStrainer
from bs4.testing import skipIf
from bs4.tests import test_htmlparser
from bs4.testing import (
HTMLTreeBuilderSmokeTest,
XMLTreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its tree builder.")
class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilder()
def test_out_of_range_entity(self):
self.assertSoupEquals(
"<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
self.assertSoupEquals(
"<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
self.assertSoupEquals(
"<p>foo&#1000000000;bar</p>", "<p>foobar</p>")
# In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
# test if an old version of lxml is installed.
@skipIf(
not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
"Skipping doctype test for old version of lxml to avoid segfault.")
def test_empty_doctype(self):
soup = self.soup("<!DOCTYPE>")
doctype = soup.contents[0]
self.assertEqual("", doctype.strip())
def test_beautifulstonesoup_is_xml_parser(self):
# Make sure that the deprecated BSS class uses an xml builder
# if one is installed.
with warnings.catch_warnings(record=True) as w:
soup = BeautifulStoneSoup("<b />")
self.assertEqual(u"<b/>", unicode(soup.b))
self.assertTrue("BeautifulStoneSoup class is deprecated" in str(w[0].message))
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its XML tree builder.")
class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilderForXML()

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