webull-openapi-python-sdk 1.0.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- samples/__init__.py +1 -0
- samples/data/__init__.py +1 -0
- samples/data/data_client.py +57 -0
- samples/data/data_streaming_client.py +86 -0
- samples/data/data_streaming_client_async.py +101 -0
- samples/trade/__init__.py +0 -0
- samples/trade/trade_client.py +163 -0
- samples/trade/trade_client_v2.py +181 -0
- samples/trade/trade_event_client.py +47 -0
- webull/__init__.py +1 -0
- webull/core/__init__.py +12 -0
- webull/core/auth/__init__.py +0 -0
- webull/core/auth/algorithm/__init__.py +0 -0
- webull/core/auth/algorithm/sha_hmac1.py +65 -0
- webull/core/auth/algorithm/sha_hmac256.py +75 -0
- webull/core/auth/composer/__init__.py +0 -0
- webull/core/auth/composer/default_signature_composer.py +125 -0
- webull/core/auth/credentials.py +46 -0
- webull/core/auth/signers/__init__.py +0 -0
- webull/core/auth/signers/app_key_signer.py +72 -0
- webull/core/auth/signers/signer.py +48 -0
- webull/core/auth/signers/signer_factory.py +58 -0
- webull/core/cache/__init__.py +225 -0
- webull/core/client.py +410 -0
- webull/core/common/__init__.py +0 -0
- webull/core/common/api_type.py +19 -0
- webull/core/common/easy_enum.py +35 -0
- webull/core/common/region.py +7 -0
- webull/core/compat.py +85 -0
- webull/core/context/__init__.py +0 -0
- webull/core/context/request_context_holder.py +33 -0
- webull/core/data/endpoints.json +22 -0
- webull/core/data/retry_config.json +15 -0
- webull/core/endpoint/__init__.py +8 -0
- webull/core/endpoint/chained_endpoint_resolver.py +57 -0
- webull/core/endpoint/default_endpoint_resolver.py +60 -0
- webull/core/endpoint/local_config_regional_endpoint_resolver.py +77 -0
- webull/core/endpoint/resolver_endpoint_request.py +46 -0
- webull/core/endpoint/user_customized_endpoint_resolver.py +55 -0
- webull/core/exception/__init__.py +0 -0
- webull/core/exception/error_code.py +23 -0
- webull/core/exception/error_msg.py +21 -0
- webull/core/exception/exceptions.py +53 -0
- webull/core/headers.py +57 -0
- webull/core/http/__init__.py +0 -0
- webull/core/http/initializer/__init__.py +0 -0
- webull/core/http/initializer/client_initializer.py +79 -0
- webull/core/http/initializer/token/__init__.py +0 -0
- webull/core/http/initializer/token/bean/__init__.py +0 -0
- webull/core/http/initializer/token/bean/access_token.py +40 -0
- webull/core/http/initializer/token/bean/check_token_request.py +44 -0
- webull/core/http/initializer/token/bean/create_token_request.py +45 -0
- webull/core/http/initializer/token/bean/refresh_token_request.py +44 -0
- webull/core/http/initializer/token/token_manager.py +208 -0
- webull/core/http/initializer/token/token_operation.py +72 -0
- webull/core/http/method_type.py +43 -0
- webull/core/http/protocol_type.py +43 -0
- webull/core/http/request.py +121 -0
- webull/core/http/response.py +166 -0
- webull/core/request.py +278 -0
- webull/core/retry/__init__.py +0 -0
- webull/core/retry/backoff_strategy.py +102 -0
- webull/core/retry/retry_condition.py +214 -0
- webull/core/retry/retry_policy.py +63 -0
- webull/core/retry/retry_policy_context.py +51 -0
- webull/core/utils/__init__.py +0 -0
- webull/core/utils/common.py +62 -0
- webull/core/utils/data.py +25 -0
- webull/core/utils/desensitize.py +33 -0
- webull/core/utils/validation.py +49 -0
- webull/core/vendored/__init__.py +0 -0
- webull/core/vendored/requests/__init__.py +94 -0
- webull/core/vendored/requests/__version__.py +28 -0
- webull/core/vendored/requests/_internal_utils.py +56 -0
- webull/core/vendored/requests/adapters.py +539 -0
- webull/core/vendored/requests/api.py +166 -0
- webull/core/vendored/requests/auth.py +307 -0
- webull/core/vendored/requests/certs.py +34 -0
- webull/core/vendored/requests/compat.py +85 -0
- webull/core/vendored/requests/cookies.py +555 -0
- webull/core/vendored/requests/exceptions.py +136 -0
- webull/core/vendored/requests/help.py +134 -0
- webull/core/vendored/requests/hooks.py +48 -0
- webull/core/vendored/requests/models.py +960 -0
- webull/core/vendored/requests/packages/__init__.py +17 -0
- webull/core/vendored/requests/packages/certifi/__init__.py +17 -0
- webull/core/vendored/requests/packages/certifi/__main__.py +16 -0
- webull/core/vendored/requests/packages/certifi/cacert.pem +4433 -0
- webull/core/vendored/requests/packages/certifi/core.py +51 -0
- webull/core/vendored/requests/packages/chardet/__init__.py +53 -0
- webull/core/vendored/requests/packages/chardet/big5freq.py +400 -0
- webull/core/vendored/requests/packages/chardet/big5prober.py +61 -0
- webull/core/vendored/requests/packages/chardet/chardistribution.py +247 -0
- webull/core/vendored/requests/packages/chardet/charsetgroupprober.py +120 -0
- webull/core/vendored/requests/packages/chardet/charsetprober.py +159 -0
- webull/core/vendored/requests/packages/chardet/cli/__init__.py +1 -0
- webull/core/vendored/requests/packages/chardet/cli/chardetect.py +99 -0
- webull/core/vendored/requests/packages/chardet/codingstatemachine.py +102 -0
- webull/core/vendored/requests/packages/chardet/compat.py +48 -0
- webull/core/vendored/requests/packages/chardet/cp949prober.py +63 -0
- webull/core/vendored/requests/packages/chardet/enums.py +90 -0
- webull/core/vendored/requests/packages/chardet/escprober.py +115 -0
- webull/core/vendored/requests/packages/chardet/escsm.py +260 -0
- webull/core/vendored/requests/packages/chardet/eucjpprober.py +106 -0
- webull/core/vendored/requests/packages/chardet/euckrfreq.py +209 -0
- webull/core/vendored/requests/packages/chardet/euckrprober.py +61 -0
- webull/core/vendored/requests/packages/chardet/euctwfreq.py +401 -0
- webull/core/vendored/requests/packages/chardet/euctwprober.py +60 -0
- webull/core/vendored/requests/packages/chardet/gb2312freq.py +297 -0
- webull/core/vendored/requests/packages/chardet/gb2312prober.py +60 -0
- webull/core/vendored/requests/packages/chardet/hebrewprober.py +306 -0
- webull/core/vendored/requests/packages/chardet/jisfreq.py +339 -0
- webull/core/vendored/requests/packages/chardet/jpcntx.py +247 -0
- webull/core/vendored/requests/packages/chardet/langbulgarianmodel.py +242 -0
- webull/core/vendored/requests/packages/chardet/langcyrillicmodel.py +347 -0
- webull/core/vendored/requests/packages/chardet/langgreekmodel.py +239 -0
- webull/core/vendored/requests/packages/chardet/langhebrewmodel.py +214 -0
- webull/core/vendored/requests/packages/chardet/langhungarianmodel.py +239 -0
- webull/core/vendored/requests/packages/chardet/langthaimodel.py +213 -0
- webull/core/vendored/requests/packages/chardet/langturkishmodel.py +207 -0
- webull/core/vendored/requests/packages/chardet/latin1prober.py +159 -0
- webull/core/vendored/requests/packages/chardet/mbcharsetprober.py +105 -0
- webull/core/vendored/requests/packages/chardet/mbcsgroupprober.py +68 -0
- webull/core/vendored/requests/packages/chardet/mbcssm.py +586 -0
- webull/core/vendored/requests/packages/chardet/sbcharsetprober.py +146 -0
- webull/core/vendored/requests/packages/chardet/sbcsgroupprober.py +87 -0
- webull/core/vendored/requests/packages/chardet/sjisprober.py +106 -0
- webull/core/vendored/requests/packages/chardet/universaldetector.py +300 -0
- webull/core/vendored/requests/packages/chardet/utf8prober.py +96 -0
- webull/core/vendored/requests/packages/chardet/version.py +23 -0
- webull/core/vendored/requests/packages/urllib3/__init__.py +114 -0
- webull/core/vendored/requests/packages/urllib3/_collections.py +346 -0
- webull/core/vendored/requests/packages/urllib3/connection.py +405 -0
- webull/core/vendored/requests/packages/urllib3/connectionpool.py +910 -0
- webull/core/vendored/requests/packages/urllib3/contrib/__init__.py +0 -0
- webull/core/vendored/requests/packages/urllib3/contrib/_appengine_environ.py +44 -0
- webull/core/vendored/requests/packages/urllib3/contrib/_securetransport/__init__.py +0 -0
- webull/core/vendored/requests/packages/urllib3/contrib/_securetransport/bindings.py +607 -0
- webull/core/vendored/requests/packages/urllib3/contrib/_securetransport/low_level.py +360 -0
- webull/core/vendored/requests/packages/urllib3/contrib/appengine.py +303 -0
- webull/core/vendored/requests/packages/urllib3/contrib/ntlmpool.py +125 -0
- webull/core/vendored/requests/packages/urllib3/contrib/pyopenssl.py +484 -0
- webull/core/vendored/requests/packages/urllib3/contrib/securetransport.py +818 -0
- webull/core/vendored/requests/packages/urllib3/contrib/socks.py +206 -0
- webull/core/vendored/requests/packages/urllib3/exceptions.py +260 -0
- webull/core/vendored/requests/packages/urllib3/fields.py +192 -0
- webull/core/vendored/requests/packages/urllib3/filepost.py +112 -0
- webull/core/vendored/requests/packages/urllib3/packages/__init__.py +19 -0
- webull/core/vendored/requests/packages/urllib3/packages/backports/__init__.py +0 -0
- webull/core/vendored/requests/packages/urllib3/packages/backports/makefile.py +67 -0
- webull/core/vendored/requests/packages/urllib3/packages/ordered_dict.py +273 -0
- webull/core/vendored/requests/packages/urllib3/packages/six.py +882 -0
- webull/core/vendored/requests/packages/urllib3/packages/socks.py +887 -0
- webull/core/vendored/requests/packages/urllib3/packages/ssl_match_hostname/__init__.py +19 -0
- webull/core/vendored/requests/packages/urllib3/packages/ssl_match_hostname/_implementation.py +170 -0
- webull/core/vendored/requests/packages/urllib3/poolmanager.py +467 -0
- webull/core/vendored/requests/packages/urllib3/request.py +164 -0
- webull/core/vendored/requests/packages/urllib3/response.py +721 -0
- webull/core/vendored/requests/packages/urllib3/util/__init__.py +68 -0
- webull/core/vendored/requests/packages/urllib3/util/connection.py +148 -0
- webull/core/vendored/requests/packages/urllib3/util/queue.py +35 -0
- webull/core/vendored/requests/packages/urllib3/util/request.py +132 -0
- webull/core/vendored/requests/packages/urllib3/util/response.py +101 -0
- webull/core/vendored/requests/packages/urllib3/util/retry.py +426 -0
- webull/core/vendored/requests/packages/urllib3/util/selectors.py +601 -0
- webull/core/vendored/requests/packages/urllib3/util/ssl_.py +396 -0
- webull/core/vendored/requests/packages/urllib3/util/timeout.py +256 -0
- webull/core/vendored/requests/packages/urllib3/util/url.py +252 -0
- webull/core/vendored/requests/packages/urllib3/util/wait.py +164 -0
- webull/core/vendored/requests/packages.py +28 -0
- webull/core/vendored/requests/sessions.py +750 -0
- webull/core/vendored/requests/status_codes.py +105 -0
- webull/core/vendored/requests/structures.py +119 -0
- webull/core/vendored/requests/utils.py +916 -0
- webull/core/vendored/six.py +905 -0
- webull/data/__init__.py +3 -0
- webull/data/common/__init__.py +0 -0
- webull/data/common/category.py +26 -0
- webull/data/common/connect_ack.py +29 -0
- webull/data/common/direction.py +25 -0
- webull/data/common/exchange_code.py +33 -0
- webull/data/common/exercise_style.py +22 -0
- webull/data/common/expiration_cycle.py +26 -0
- webull/data/common/instrument_status.py +23 -0
- webull/data/common/option_type.py +20 -0
- webull/data/common/subscribe_type.py +22 -0
- webull/data/common/timespan.py +29 -0
- webull/data/data_client.py +35 -0
- webull/data/data_streaming_client.py +89 -0
- webull/data/internal/__init__.py +0 -0
- webull/data/internal/default_retry_policy.py +84 -0
- webull/data/internal/exceptions.py +60 -0
- webull/data/internal/quotes_client.py +314 -0
- webull/data/internal/quotes_decoder.py +40 -0
- webull/data/internal/quotes_payload_decoder.py +35 -0
- webull/data/internal/quotes_topic.py +36 -0
- webull/data/quotes/__init__.py +0 -0
- webull/data/quotes/instrument.py +33 -0
- webull/data/quotes/market_data.py +187 -0
- webull/data/quotes/market_streaming_data.py +66 -0
- webull/data/quotes/subscribe/__init__.py +0 -0
- webull/data/quotes/subscribe/ask_bid_result.py +49 -0
- webull/data/quotes/subscribe/basic_result.py +45 -0
- webull/data/quotes/subscribe/broker_result.py +33 -0
- webull/data/quotes/subscribe/message_pb2.py +37 -0
- webull/data/quotes/subscribe/order_result.py +30 -0
- webull/data/quotes/subscribe/payload_type.py +19 -0
- webull/data/quotes/subscribe/quote_decoder.py +28 -0
- webull/data/quotes/subscribe/quote_result.py +47 -0
- webull/data/quotes/subscribe/snapshot_decoder.py +30 -0
- webull/data/quotes/subscribe/snapshot_result.py +69 -0
- webull/data/quotes/subscribe/tick_decoder.py +29 -0
- webull/data/quotes/subscribe/tick_result.py +47 -0
- webull/data/request/__init__.py +0 -0
- webull/data/request/get_batch_historical_bars_request.py +43 -0
- webull/data/request/get_corp_action_request.py +47 -0
- webull/data/request/get_eod_bars_request.py +32 -0
- webull/data/request/get_historical_bars_request.py +43 -0
- webull/data/request/get_instruments_request.py +30 -0
- webull/data/request/get_quotes_request.py +35 -0
- webull/data/request/get_snapshot_request.py +38 -0
- webull/data/request/get_tick_request.py +37 -0
- webull/data/request/subscribe_request.py +43 -0
- webull/data/request/unsubscribe_request.py +42 -0
- webull/trade/__init__.py +2 -0
- webull/trade/common/__init__.py +0 -0
- webull/trade/common/account_type.py +22 -0
- webull/trade/common/category.py +29 -0
- webull/trade/common/combo_ticker_type.py +23 -0
- webull/trade/common/combo_type.py +31 -0
- webull/trade/common/currency.py +24 -0
- webull/trade/common/forbid_reason.py +27 -0
- webull/trade/common/instrument_type.py +27 -0
- webull/trade/common/markets.py +27 -0
- webull/trade/common/order_entrust_type.py +21 -0
- webull/trade/common/order_side.py +23 -0
- webull/trade/common/order_status.py +25 -0
- webull/trade/common/order_tif.py +24 -0
- webull/trade/common/order_type.py +30 -0
- webull/trade/common/trade_policy.py +22 -0
- webull/trade/common/trading_date_type.py +24 -0
- webull/trade/common/trailing_type.py +23 -0
- webull/trade/events/__init__.py +0 -0
- webull/trade/events/default_retry_policy.py +64 -0
- webull/trade/events/events_pb2.py +43 -0
- webull/trade/events/events_pb2_grpc.py +66 -0
- webull/trade/events/signature_composer.py +61 -0
- webull/trade/events/types.py +21 -0
- webull/trade/request/__init__.py +0 -0
- webull/trade/request/cancel_order_request.py +28 -0
- webull/trade/request/get_account_balance_request.py +28 -0
- webull/trade/request/get_account_positions_request.py +30 -0
- webull/trade/request/get_account_profile_request.py +26 -0
- webull/trade/request/get_app_subscriptions.py +28 -0
- webull/trade/request/get_open_orders_request.py +30 -0
- webull/trade/request/get_order_detail_request.py +27 -0
- webull/trade/request/get_today_orders_request.py +31 -0
- webull/trade/request/get_trade_calendar_request.py +30 -0
- webull/trade/request/get_trade_instrument_detail_request.py +24 -0
- webull/trade/request/get_trade_security_detail_request.py +42 -0
- webull/trade/request/get_tradeable_instruments_request.py +27 -0
- webull/trade/request/palce_order_request.py +91 -0
- webull/trade/request/place_order_request_v2.py +58 -0
- webull/trade/request/replace_order_request.py +73 -0
- webull/trade/request/replace_order_request_v2.py +38 -0
- webull/trade/request/v2/__init__.py +0 -0
- webull/trade/request/v2/cancel_option_request.py +28 -0
- webull/trade/request/v2/cancel_order_request.py +28 -0
- webull/trade/request/v2/get_account_balance_request.py +28 -0
- webull/trade/request/v2/get_account_list.py +23 -0
- webull/trade/request/v2/get_account_positions_request.py +24 -0
- webull/trade/request/v2/get_order_detail_request.py +26 -0
- webull/trade/request/v2/get_order_history_request.py +35 -0
- webull/trade/request/v2/palce_order_request.py +87 -0
- webull/trade/request/v2/place_option_request.py +64 -0
- webull/trade/request/v2/preview_option_request.py +28 -0
- webull/trade/request/v2/preview_order_request.py +59 -0
- webull/trade/request/v2/replace_option_request.py +28 -0
- webull/trade/request/v2/replace_order_request.py +57 -0
- webull/trade/trade/__init__.py +0 -0
- webull/trade/trade/account_info.py +83 -0
- webull/trade/trade/order_operation.py +246 -0
- webull/trade/trade/trade_calendar.py +37 -0
- webull/trade/trade/trade_instrument.py +72 -0
- webull/trade/trade/v2/__init__.py +0 -0
- webull/trade/trade/v2/account_info_v2.py +55 -0
- webull/trade/trade/v2/order_operation_v2.py +206 -0
- webull/trade/trade_client.py +43 -0
- webull/trade/trade_events_client.py +233 -0
- webull_openapi_python_sdk-1.0.0.dist-info/METADATA +28 -0
- webull_openapi_python_sdk-1.0.0.dist-info/RECORD +295 -0
- webull_openapi_python_sdk-1.0.0.dist-info/WHEEL +5 -0
- webull_openapi_python_sdk-1.0.0.dist-info/licenses/LICENSE +202 -0
- webull_openapi_python_sdk-1.0.0.dist-info/licenses/NOTICE +56 -0
- webull_openapi_python_sdk-1.0.0.dist-info/top_level.txt +2 -0
|
@@ -0,0 +1,106 @@
|
|
|
1
|
+
# Copyright 2022 Webull
|
|
2
|
+
#
|
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
4
|
+
# you may not use this file except in compliance with the License.
|
|
5
|
+
# You may obtain a copy of the License at
|
|
6
|
+
#
|
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
8
|
+
#
|
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
12
|
+
# See the License for the specific language governing permissions and
|
|
13
|
+
# limitations under the License.
|
|
14
|
+
|
|
15
|
+
######################## BEGIN LICENSE BLOCK ########################
|
|
16
|
+
# The Original Code is mozilla.org code.
|
|
17
|
+
#
|
|
18
|
+
# The Initial Developer of the Original Code is
|
|
19
|
+
# Netscape Communications Corporation.
|
|
20
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
|
21
|
+
# the Initial Developer. All Rights Reserved.
|
|
22
|
+
#
|
|
23
|
+
# Contributor(s):
|
|
24
|
+
# Mark Pilgrim - port to Python
|
|
25
|
+
#
|
|
26
|
+
# This library is free software; you can redistribute it and/or
|
|
27
|
+
# modify it under the terms of the GNU Lesser General Public
|
|
28
|
+
# License as published by the Free Software Foundation; either
|
|
29
|
+
# version 2.1 of the License, or (at your option) any later version.
|
|
30
|
+
#
|
|
31
|
+
# This library is distributed in the hope that it will be useful,
|
|
32
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
33
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
34
|
+
# Lesser General Public License for more details.
|
|
35
|
+
#
|
|
36
|
+
# You should have received a copy of the GNU Lesser General Public
|
|
37
|
+
# License along with this library; if not, write to the Free Software
|
|
38
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
|
39
|
+
# 02110-1301 USA
|
|
40
|
+
######################### END LICENSE BLOCK #########################
|
|
41
|
+
|
|
42
|
+
from .enums import ProbingState, MachineState
|
|
43
|
+
from .mbcharsetprober import MultiByteCharSetProber
|
|
44
|
+
from .codingstatemachine import CodingStateMachine
|
|
45
|
+
from .chardistribution import EUCJPDistributionAnalysis
|
|
46
|
+
from .jpcntx import EUCJPContextAnalysis
|
|
47
|
+
from .mbcssm import EUCJP_SM_MODEL
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
class EUCJPProber(MultiByteCharSetProber):
|
|
51
|
+
def __init__(self):
|
|
52
|
+
super(EUCJPProber, self).__init__()
|
|
53
|
+
self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
|
|
54
|
+
self.distribution_analyzer = EUCJPDistributionAnalysis()
|
|
55
|
+
self.context_analyzer = EUCJPContextAnalysis()
|
|
56
|
+
self.reset()
|
|
57
|
+
|
|
58
|
+
def reset(self):
|
|
59
|
+
super(EUCJPProber, self).reset()
|
|
60
|
+
self.context_analyzer.reset()
|
|
61
|
+
|
|
62
|
+
@property
|
|
63
|
+
def charset_name(self):
|
|
64
|
+
return "EUC-JP"
|
|
65
|
+
|
|
66
|
+
@property
|
|
67
|
+
def language(self):
|
|
68
|
+
return "Japanese"
|
|
69
|
+
|
|
70
|
+
def feed(self, byte_str):
|
|
71
|
+
for i in range(len(byte_str)):
|
|
72
|
+
# PY3K: byte_str is a byte array, so byte_str[i] is an int, not a byte
|
|
73
|
+
coding_state = self.coding_sm.next_state(byte_str[i])
|
|
74
|
+
if coding_state == MachineState.ERROR:
|
|
75
|
+
self.logger.debug('%s %s prober hit error at byte %s',
|
|
76
|
+
self.charset_name, self.language, i)
|
|
77
|
+
self._state = ProbingState.NOT_ME
|
|
78
|
+
break
|
|
79
|
+
elif coding_state == MachineState.ITS_ME:
|
|
80
|
+
self._state = ProbingState.FOUND_IT
|
|
81
|
+
break
|
|
82
|
+
elif coding_state == MachineState.START:
|
|
83
|
+
char_len = self.coding_sm.get_current_charlen()
|
|
84
|
+
if i == 0:
|
|
85
|
+
self._last_char[1] = byte_str[0]
|
|
86
|
+
self.context_analyzer.feed(self._last_char, char_len)
|
|
87
|
+
self.distribution_analyzer.feed(self._last_char, char_len)
|
|
88
|
+
else:
|
|
89
|
+
self.context_analyzer.feed(byte_str[i - 1:i + 1],
|
|
90
|
+
char_len)
|
|
91
|
+
self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
|
|
92
|
+
char_len)
|
|
93
|
+
|
|
94
|
+
self._last_char[0] = byte_str[-1]
|
|
95
|
+
|
|
96
|
+
if self.state == ProbingState.DETECTING:
|
|
97
|
+
if (self.context_analyzer.got_enough_data() and
|
|
98
|
+
(self.get_confidence() > self.SHORTCUT_THRESHOLD)):
|
|
99
|
+
self._state = ProbingState.FOUND_IT
|
|
100
|
+
|
|
101
|
+
return self.state
|
|
102
|
+
|
|
103
|
+
def get_confidence(self):
|
|
104
|
+
context_conf = self.context_analyzer.get_confidence()
|
|
105
|
+
distrib_conf = self.distribution_analyzer.get_confidence()
|
|
106
|
+
return max(context_conf, distrib_conf)
|
|
@@ -0,0 +1,209 @@
|
|
|
1
|
+
# Copyright 2022 Webull
|
|
2
|
+
#
|
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
4
|
+
# you may not use this file except in compliance with the License.
|
|
5
|
+
# You may obtain a copy of the License at
|
|
6
|
+
#
|
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
8
|
+
#
|
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
12
|
+
# See the License for the specific language governing permissions and
|
|
13
|
+
# limitations under the License.
|
|
14
|
+
|
|
15
|
+
######################## BEGIN LICENSE BLOCK ########################
|
|
16
|
+
# The Original Code is Mozilla Communicator client code.
|
|
17
|
+
#
|
|
18
|
+
# The Initial Developer of the Original Code is
|
|
19
|
+
# Netscape Communications Corporation.
|
|
20
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
|
21
|
+
# the Initial Developer. All Rights Reserved.
|
|
22
|
+
#
|
|
23
|
+
# Contributor(s):
|
|
24
|
+
# Mark Pilgrim - port to Python
|
|
25
|
+
#
|
|
26
|
+
# This library is free software; you can redistribute it and/or
|
|
27
|
+
# modify it under the terms of the GNU Lesser General Public
|
|
28
|
+
# License as published by the Free Software Foundation; either
|
|
29
|
+
# version 2.1 of the License, or (at your option) any later version.
|
|
30
|
+
#
|
|
31
|
+
# This library is distributed in the hope that it will be useful,
|
|
32
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
33
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
34
|
+
# Lesser General Public License for more details.
|
|
35
|
+
#
|
|
36
|
+
# You should have received a copy of the GNU Lesser General Public
|
|
37
|
+
# License along with this library; if not, write to the Free Software
|
|
38
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
|
39
|
+
# 02110-1301 USA
|
|
40
|
+
######################### END LICENSE BLOCK #########################
|
|
41
|
+
|
|
42
|
+
# Sampling from about 20M text materials include literature and computer technology
|
|
43
|
+
|
|
44
|
+
# 128 --> 0.79
|
|
45
|
+
# 256 --> 0.92
|
|
46
|
+
# 512 --> 0.986
|
|
47
|
+
# 1024 --> 0.99944
|
|
48
|
+
# 2048 --> 0.99999
|
|
49
|
+
#
|
|
50
|
+
# Idea Distribution Ratio = 0.98653 / (1-0.98653) = 73.24
|
|
51
|
+
# Random Distribution Ration = 512 / (2350-512) = 0.279.
|
|
52
|
+
#
|
|
53
|
+
# Typical Distribution Ratio
|
|
54
|
+
|
|
55
|
+
EUCKR_TYPICAL_DISTRIBUTION_RATIO = 6.0
|
|
56
|
+
|
|
57
|
+
EUCKR_TABLE_SIZE = 2352
|
|
58
|
+
|
|
59
|
+
# Char to FreqOrder table ,
|
|
60
|
+
EUCKR_CHAR_TO_FREQ_ORDER = (
|
|
61
|
+
13, 130, 120,1396, 481,1719,1720, 328, 609, 212,1721, 707, 400, 299,1722, 87,
|
|
62
|
+
1397,1723, 104, 536,1117,1203,1724,1267, 685,1268, 508,1725,1726,1727,1728,1398,
|
|
63
|
+
1399,1729,1730,1731, 141, 621, 326,1057, 368,1732, 267, 488, 20,1733,1269,1734,
|
|
64
|
+
945,1400,1735, 47, 904,1270,1736,1737, 773, 248,1738, 409, 313, 786, 429,1739,
|
|
65
|
+
116, 987, 813,1401, 683, 75,1204, 145,1740,1741,1742,1743, 16, 847, 667, 622,
|
|
66
|
+
708,1744,1745,1746, 966, 787, 304, 129,1747, 60, 820, 123, 676,1748,1749,1750,
|
|
67
|
+
1751, 617,1752, 626,1753,1754,1755,1756, 653,1757,1758,1759,1760,1761,1762, 856,
|
|
68
|
+
344,1763,1764,1765,1766, 89, 401, 418, 806, 905, 848,1767,1768,1769, 946,1205,
|
|
69
|
+
709,1770,1118,1771, 241,1772,1773,1774,1271,1775, 569,1776, 999,1777,1778,1779,
|
|
70
|
+
1780, 337, 751,1058, 28, 628, 254,1781, 177, 906, 270, 349, 891,1079,1782, 19,
|
|
71
|
+
1783, 379,1784, 315,1785, 629, 754,1402, 559,1786, 636, 203,1206,1787, 710, 567,
|
|
72
|
+
1788, 935, 814,1789,1790,1207, 766, 528,1791,1792,1208,1793,1794,1795,1796,1797,
|
|
73
|
+
1403,1798,1799, 533,1059,1404,1405,1156,1406, 936, 884,1080,1800, 351,1801,1802,
|
|
74
|
+
1803,1804,1805, 801,1806,1807,1808,1119,1809,1157, 714, 474,1407,1810, 298, 899,
|
|
75
|
+
885,1811,1120, 802,1158,1812, 892,1813,1814,1408, 659,1815,1816,1121,1817,1818,
|
|
76
|
+
1819,1820,1821,1822, 319,1823, 594, 545,1824, 815, 937,1209,1825,1826, 573,1409,
|
|
77
|
+
1022,1827,1210,1828,1829,1830,1831,1832,1833, 556, 722, 807,1122,1060,1834, 697,
|
|
78
|
+
1835, 900, 557, 715,1836,1410, 540,1411, 752,1159, 294, 597,1211, 976, 803, 770,
|
|
79
|
+
1412,1837,1838, 39, 794,1413, 358,1839, 371, 925,1840, 453, 661, 788, 531, 723,
|
|
80
|
+
544,1023,1081, 869, 91,1841, 392, 430, 790, 602,1414, 677,1082, 457,1415,1416,
|
|
81
|
+
1842,1843, 475, 327,1024,1417, 795, 121,1844, 733, 403,1418,1845,1846,1847, 300,
|
|
82
|
+
119, 711,1212, 627,1848,1272, 207,1849,1850, 796,1213, 382,1851, 519,1852,1083,
|
|
83
|
+
893,1853,1854,1855, 367, 809, 487, 671,1856, 663,1857,1858, 956, 471, 306, 857,
|
|
84
|
+
1859,1860,1160,1084,1861,1862,1863,1864,1865,1061,1866,1867,1868,1869,1870,1871,
|
|
85
|
+
282, 96, 574,1872, 502,1085,1873,1214,1874, 907,1875,1876, 827, 977,1419,1420,
|
|
86
|
+
1421, 268,1877,1422,1878,1879,1880, 308,1881, 2, 537,1882,1883,1215,1884,1885,
|
|
87
|
+
127, 791,1886,1273,1423,1887, 34, 336, 404, 643,1888, 571, 654, 894, 840,1889,
|
|
88
|
+
0, 886,1274, 122, 575, 260, 908, 938,1890,1275, 410, 316,1891,1892, 100,1893,
|
|
89
|
+
1894,1123, 48,1161,1124,1025,1895, 633, 901,1276,1896,1897, 115, 816,1898, 317,
|
|
90
|
+
1899, 694,1900, 909, 734,1424, 572, 866,1425, 691, 85, 524,1010, 543, 394, 841,
|
|
91
|
+
1901,1902,1903,1026,1904,1905,1906,1907,1908,1909, 30, 451, 651, 988, 310,1910,
|
|
92
|
+
1911,1426, 810,1216, 93,1912,1913,1277,1217,1914, 858, 759, 45, 58, 181, 610,
|
|
93
|
+
269,1915,1916, 131,1062, 551, 443,1000, 821,1427, 957, 895,1086,1917,1918, 375,
|
|
94
|
+
1919, 359,1920, 687,1921, 822,1922, 293,1923,1924, 40, 662, 118, 692, 29, 939,
|
|
95
|
+
887, 640, 482, 174,1925, 69,1162, 728,1428, 910,1926,1278,1218,1279, 386, 870,
|
|
96
|
+
217, 854,1163, 823,1927,1928,1929,1930, 834,1931, 78,1932, 859,1933,1063,1934,
|
|
97
|
+
1935,1936,1937, 438,1164, 208, 595,1938,1939,1940,1941,1219,1125,1942, 280, 888,
|
|
98
|
+
1429,1430,1220,1431,1943,1944,1945,1946,1947,1280, 150, 510,1432,1948,1949,1950,
|
|
99
|
+
1951,1952,1953,1954,1011,1087,1955,1433,1043,1956, 881,1957, 614, 958,1064,1065,
|
|
100
|
+
1221,1958, 638,1001, 860, 967, 896,1434, 989, 492, 553,1281,1165,1959,1282,1002,
|
|
101
|
+
1283,1222,1960,1961,1962,1963, 36, 383, 228, 753, 247, 454,1964, 876, 678,1965,
|
|
102
|
+
1966,1284, 126, 464, 490, 835, 136, 672, 529, 940,1088,1435, 473,1967,1968, 467,
|
|
103
|
+
50, 390, 227, 587, 279, 378, 598, 792, 968, 240, 151, 160, 849, 882,1126,1285,
|
|
104
|
+
639,1044, 133, 140, 288, 360, 811, 563,1027, 561, 142, 523,1969,1970,1971, 7,
|
|
105
|
+
103, 296, 439, 407, 506, 634, 990,1972,1973,1974,1975, 645,1976,1977,1978,1979,
|
|
106
|
+
1980,1981, 236,1982,1436,1983,1984,1089, 192, 828, 618, 518,1166, 333,1127,1985,
|
|
107
|
+
818,1223,1986,1987,1988,1989,1990,1991,1992,1993, 342,1128,1286, 746, 842,1994,
|
|
108
|
+
1995, 560, 223,1287, 98, 8, 189, 650, 978,1288,1996,1437,1997, 17, 345, 250,
|
|
109
|
+
423, 277, 234, 512, 226, 97, 289, 42, 167,1998, 201,1999,2000, 843, 836, 824,
|
|
110
|
+
532, 338, 783,1090, 182, 576, 436,1438,1439, 527, 500,2001, 947, 889,2002,2003,
|
|
111
|
+
2004,2005, 262, 600, 314, 447,2006, 547,2007, 693, 738,1129,2008, 71,1440, 745,
|
|
112
|
+
619, 688,2009, 829,2010,2011, 147,2012, 33, 948,2013,2014, 74, 224,2015, 61,
|
|
113
|
+
191, 918, 399, 637,2016,1028,1130, 257, 902,2017,2018,2019,2020,2021,2022,2023,
|
|
114
|
+
2024,2025,2026, 837,2027,2028,2029,2030, 179, 874, 591, 52, 724, 246,2031,2032,
|
|
115
|
+
2033,2034,1167, 969,2035,1289, 630, 605, 911,1091,1168,2036,2037,2038,1441, 912,
|
|
116
|
+
2039, 623,2040,2041, 253,1169,1290,2042,1442, 146, 620, 611, 577, 433,2043,1224,
|
|
117
|
+
719,1170, 959, 440, 437, 534, 84, 388, 480,1131, 159, 220, 198, 679,2044,1012,
|
|
118
|
+
819,1066,1443, 113,1225, 194, 318,1003,1029,2045,2046,2047,2048,1067,2049,2050,
|
|
119
|
+
2051,2052,2053, 59, 913, 112,2054, 632,2055, 455, 144, 739,1291,2056, 273, 681,
|
|
120
|
+
499,2057, 448,2058,2059, 760,2060,2061, 970, 384, 169, 245,1132,2062,2063, 414,
|
|
121
|
+
1444,2064,2065, 41, 235,2066, 157, 252, 877, 568, 919, 789, 580,2067, 725,2068,
|
|
122
|
+
2069,1292,2070,2071,1445,2072,1446,2073,2074, 55, 588, 66,1447, 271,1092,2075,
|
|
123
|
+
1226,2076, 960,1013, 372,2077,2078,2079,2080,2081,1293,2082,2083,2084,2085, 850,
|
|
124
|
+
2086,2087,2088,2089,2090, 186,2091,1068, 180,2092,2093,2094, 109,1227, 522, 606,
|
|
125
|
+
2095, 867,1448,1093, 991,1171, 926, 353,1133,2096, 581,2097,2098,2099,1294,1449,
|
|
126
|
+
1450,2100, 596,1172,1014,1228,2101,1451,1295,1173,1229,2102,2103,1296,1134,1452,
|
|
127
|
+
949,1135,2104,2105,1094,1453,1454,1455,2106,1095,2107,2108,2109,2110,2111,2112,
|
|
128
|
+
2113,2114,2115,2116,2117, 804,2118,2119,1230,1231, 805,1456, 405,1136,2120,2121,
|
|
129
|
+
2122,2123,2124, 720, 701,1297, 992,1457, 927,1004,2125,2126,2127,2128,2129,2130,
|
|
130
|
+
22, 417,2131, 303,2132, 385,2133, 971, 520, 513,2134,1174, 73,1096, 231, 274,
|
|
131
|
+
962,1458, 673,2135,1459,2136, 152,1137,2137,2138,2139,2140,1005,1138,1460,1139,
|
|
132
|
+
2141,2142,2143,2144, 11, 374, 844,2145, 154,1232, 46,1461,2146, 838, 830, 721,
|
|
133
|
+
1233, 106,2147, 90, 428, 462, 578, 566,1175, 352,2148,2149, 538,1234, 124,1298,
|
|
134
|
+
2150,1462, 761, 565,2151, 686,2152, 649,2153, 72, 173,2154, 460, 415,2155,1463,
|
|
135
|
+
2156,1235, 305,2157,2158,2159,2160,2161,2162, 579,2163,2164,2165,2166,2167, 747,
|
|
136
|
+
2168,2169,2170,2171,1464, 669,2172,2173,2174,2175,2176,1465,2177, 23, 530, 285,
|
|
137
|
+
2178, 335, 729,2179, 397,2180,2181,2182,1030,2183,2184, 698,2185,2186, 325,2187,
|
|
138
|
+
2188, 369,2189, 799,1097,1015, 348,2190,1069, 680,2191, 851,1466,2192,2193, 10,
|
|
139
|
+
2194, 613, 424,2195, 979, 108, 449, 589, 27, 172, 81,1031, 80, 774, 281, 350,
|
|
140
|
+
1032, 525, 301, 582,1176,2196, 674,1045,2197,2198,1467, 730, 762,2199,2200,2201,
|
|
141
|
+
2202,1468,2203, 993,2204,2205, 266,1070, 963,1140,2206,2207,2208, 664,1098, 972,
|
|
142
|
+
2209,2210,2211,1177,1469,1470, 871,2212,2213,2214,2215,2216,1471,2217,2218,2219,
|
|
143
|
+
2220,2221,2222,2223,2224,2225,2226,2227,1472,1236,2228,2229,2230,2231,2232,2233,
|
|
144
|
+
2234,2235,1299,2236,2237, 200,2238, 477, 373,2239,2240, 731, 825, 777,2241,2242,
|
|
145
|
+
2243, 521, 486, 548,2244,2245,2246,1473,1300, 53, 549, 137, 875, 76, 158,2247,
|
|
146
|
+
1301,1474, 469, 396,1016, 278, 712,2248, 321, 442, 503, 767, 744, 941,1237,1178,
|
|
147
|
+
1475,2249, 82, 178,1141,1179, 973,2250,1302,2251, 297,2252,2253, 570,2254,2255,
|
|
148
|
+
2256, 18, 450, 206,2257, 290, 292,1142,2258, 511, 162, 99, 346, 164, 735,2259,
|
|
149
|
+
1476,1477, 4, 554, 343, 798,1099,2260,1100,2261, 43, 171,1303, 139, 215,2262,
|
|
150
|
+
2263, 717, 775,2264,1033, 322, 216,2265, 831,2266, 149,2267,1304,2268,2269, 702,
|
|
151
|
+
1238, 135, 845, 347, 309,2270, 484,2271, 878, 655, 238,1006,1478,2272, 67,2273,
|
|
152
|
+
295,2274,2275, 461,2276, 478, 942, 412,2277,1034,2278,2279,2280, 265,2281, 541,
|
|
153
|
+
2282,2283,2284,2285,2286, 70, 852,1071,2287,2288,2289,2290, 21, 56, 509, 117,
|
|
154
|
+
432,2291,2292, 331, 980, 552,1101, 148, 284, 105, 393,1180,1239, 755,2293, 187,
|
|
155
|
+
2294,1046,1479,2295, 340,2296, 63,1047, 230,2297,2298,1305, 763,1306, 101, 800,
|
|
156
|
+
808, 494,2299,2300,2301, 903,2302, 37,1072, 14, 5,2303, 79, 675,2304, 312,
|
|
157
|
+
2305,2306,2307,2308,2309,1480, 6,1307,2310,2311,2312, 1, 470, 35, 24, 229,
|
|
158
|
+
2313, 695, 210, 86, 778, 15, 784, 592, 779, 32, 77, 855, 964,2314, 259,2315,
|
|
159
|
+
501, 380,2316,2317, 83, 981, 153, 689,1308,1481,1482,1483,2318,2319, 716,1484,
|
|
160
|
+
2320,2321,2322,2323,2324,2325,1485,2326,2327, 128, 57, 68, 261,1048, 211, 170,
|
|
161
|
+
1240, 31,2328, 51, 435, 742,2329,2330,2331, 635,2332, 264, 456,2333,2334,2335,
|
|
162
|
+
425,2336,1486, 143, 507, 263, 943,2337, 363, 920,1487, 256,1488,1102, 243, 601,
|
|
163
|
+
1489,2338,2339,2340,2341,2342,2343,2344, 861,2345,2346,2347,2348,2349,2350, 395,
|
|
164
|
+
2351,1490,1491, 62, 535, 166, 225,2352,2353, 668, 419,1241, 138, 604, 928,2354,
|
|
165
|
+
1181,2355,1492,1493,2356,2357,2358,1143,2359, 696,2360, 387, 307,1309, 682, 476,
|
|
166
|
+
2361,2362, 332, 12, 222, 156,2363, 232,2364, 641, 276, 656, 517,1494,1495,1035,
|
|
167
|
+
416, 736,1496,2365,1017, 586,2366,2367,2368,1497,2369, 242,2370,2371,2372,1498,
|
|
168
|
+
2373, 965, 713,2374,2375,2376,2377, 740, 982,1499, 944,1500,1007,2378,2379,1310,
|
|
169
|
+
1501,2380,2381,2382, 785, 329,2383,2384,1502,2385,2386,2387, 932,2388,1503,2389,
|
|
170
|
+
2390,2391,2392,1242,2393,2394,2395,2396,2397, 994, 950,2398,2399,2400,2401,1504,
|
|
171
|
+
1311,2402,2403,2404,2405,1049, 749,2406,2407, 853, 718,1144,1312,2408,1182,1505,
|
|
172
|
+
2409,2410, 255, 516, 479, 564, 550, 214,1506,1507,1313, 413, 239, 444, 339,1145,
|
|
173
|
+
1036,1508,1509,1314,1037,1510,1315,2411,1511,2412,2413,2414, 176, 703, 497, 624,
|
|
174
|
+
593, 921, 302,2415, 341, 165,1103,1512,2416,1513,2417,2418,2419, 376,2420, 700,
|
|
175
|
+
2421,2422,2423, 258, 768,1316,2424,1183,2425, 995, 608,2426,2427,2428,2429, 221,
|
|
176
|
+
2430,2431,2432,2433,2434,2435,2436,2437, 195, 323, 726, 188, 897, 983,1317, 377,
|
|
177
|
+
644,1050, 879,2438, 452,2439,2440,2441,2442,2443,2444, 914,2445,2446,2447,2448,
|
|
178
|
+
915, 489,2449,1514,1184,2450,2451, 515, 64, 427, 495,2452, 583,2453, 483, 485,
|
|
179
|
+
1038, 562, 213,1515, 748, 666,2454,2455,2456,2457, 334,2458, 780, 996,1008, 705,
|
|
180
|
+
1243,2459,2460,2461,2462,2463, 114,2464, 493,1146, 366, 163,1516, 961,1104,2465,
|
|
181
|
+
291,2466,1318,1105,2467,1517, 365,2468, 355, 951,1244,2469,1319,2470, 631,2471,
|
|
182
|
+
2472, 218,1320, 364, 320, 756,1518,1519,1321,1520,1322,2473,2474,2475,2476, 997,
|
|
183
|
+
2477,2478,2479,2480, 665,1185,2481, 916,1521,2482,2483,2484, 584, 684,2485,2486,
|
|
184
|
+
797,2487,1051,1186,2488,2489,2490,1522,2491,2492, 370,2493,1039,1187, 65,2494,
|
|
185
|
+
434, 205, 463,1188,2495, 125, 812, 391, 402, 826, 699, 286, 398, 155, 781, 771,
|
|
186
|
+
585,2496, 590, 505,1073,2497, 599, 244, 219, 917,1018, 952, 646,1523,2498,1323,
|
|
187
|
+
2499,2500, 49, 984, 354, 741,2501, 625,2502,1324,2503,1019, 190, 357, 757, 491,
|
|
188
|
+
95, 782, 868,2504,2505,2506,2507,2508,2509, 134,1524,1074, 422,1525, 898,2510,
|
|
189
|
+
161,2511,2512,2513,2514, 769,2515,1526,2516,2517, 411,1325,2518, 472,1527,2519,
|
|
190
|
+
2520,2521,2522,2523,2524, 985,2525,2526,2527,2528,2529,2530, 764,2531,1245,2532,
|
|
191
|
+
2533, 25, 204, 311,2534, 496,2535,1052,2536,2537,2538,2539,2540,2541,2542, 199,
|
|
192
|
+
704, 504, 468, 758, 657,1528, 196, 44, 839,1246, 272, 750,2543, 765, 862,2544,
|
|
193
|
+
2545,1326,2546, 132, 615, 933,2547, 732,2548,2549,2550,1189,1529,2551, 283,1247,
|
|
194
|
+
1053, 607, 929,2552,2553,2554, 930, 183, 872, 616,1040,1147,2555,1148,1020, 441,
|
|
195
|
+
249,1075,2556,2557,2558, 466, 743,2559,2560,2561, 92, 514, 426, 420, 526,2562,
|
|
196
|
+
2563,2564,2565,2566,2567,2568, 185,2569,2570,2571,2572, 776,1530, 658,2573, 362,
|
|
197
|
+
2574, 361, 922,1076, 793,2575,2576,2577,2578,2579,2580,1531, 251,2581,2582,2583,
|
|
198
|
+
2584,1532, 54, 612, 237,1327,2585,2586, 275, 408, 647, 111,2587,1533,1106, 465,
|
|
199
|
+
3, 458, 9, 38,2588, 107, 110, 890, 209, 26, 737, 498,2589,1534,2590, 431,
|
|
200
|
+
202, 88,1535, 356, 287,1107, 660,1149,2591, 381,1536, 986,1150, 445,1248,1151,
|
|
201
|
+
974,2592,2593, 846,2594, 446, 953, 184,1249,1250, 727,2595, 923, 193, 883,2596,
|
|
202
|
+
2597,2598, 102, 324, 539, 817,2599, 421,1041,2600, 832,2601, 94, 175, 197, 406,
|
|
203
|
+
2602, 459,2603,2604,2605,2606,2607, 330, 555,2608,2609,2610, 706,1108, 389,2611,
|
|
204
|
+
2612,2613,2614, 233,2615, 833, 558, 931, 954,1251,2616,2617,1537, 546,2618,2619,
|
|
205
|
+
1009,2620,2621,2622,1538, 690,1328,2623, 955,2624,1539,2625,2626, 772,2627,2628,
|
|
206
|
+
2629,2630,2631, 924, 648, 863, 603,2632,2633, 934,1540, 864, 865,2634, 642,1042,
|
|
207
|
+
670,1190,2635,2636,2637,2638, 168,2639, 652, 873, 542,1054,1541,2640,2641,2642, # 512, 256
|
|
208
|
+
)
|
|
209
|
+
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
# Copyright 2022 Webull
|
|
2
|
+
#
|
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
4
|
+
# you may not use this file except in compliance with the License.
|
|
5
|
+
# You may obtain a copy of the License at
|
|
6
|
+
#
|
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
8
|
+
#
|
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
12
|
+
# See the License for the specific language governing permissions and
|
|
13
|
+
# limitations under the License.
|
|
14
|
+
|
|
15
|
+
######################## BEGIN LICENSE BLOCK ########################
|
|
16
|
+
# The Original Code is mozilla.org code.
|
|
17
|
+
#
|
|
18
|
+
# The Initial Developer of the Original Code is
|
|
19
|
+
# Netscape Communications Corporation.
|
|
20
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
|
21
|
+
# the Initial Developer. All Rights Reserved.
|
|
22
|
+
#
|
|
23
|
+
# Contributor(s):
|
|
24
|
+
# Mark Pilgrim - port to Python
|
|
25
|
+
#
|
|
26
|
+
# This library is free software; you can redistribute it and/or
|
|
27
|
+
# modify it under the terms of the GNU Lesser General Public
|
|
28
|
+
# License as published by the Free Software Foundation; either
|
|
29
|
+
# version 2.1 of the License, or (at your option) any later version.
|
|
30
|
+
#
|
|
31
|
+
# This library is distributed in the hope that it will be useful,
|
|
32
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
33
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
34
|
+
# Lesser General Public License for more details.
|
|
35
|
+
#
|
|
36
|
+
# You should have received a copy of the GNU Lesser General Public
|
|
37
|
+
# License along with this library; if not, write to the Free Software
|
|
38
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
|
39
|
+
# 02110-1301 USA
|
|
40
|
+
######################### END LICENSE BLOCK #########################
|
|
41
|
+
|
|
42
|
+
from .mbcharsetprober import MultiByteCharSetProber
|
|
43
|
+
from .codingstatemachine import CodingStateMachine
|
|
44
|
+
from .chardistribution import EUCKRDistributionAnalysis
|
|
45
|
+
from .mbcssm import EUCKR_SM_MODEL
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
class EUCKRProber(MultiByteCharSetProber):
|
|
49
|
+
def __init__(self):
|
|
50
|
+
super(EUCKRProber, self).__init__()
|
|
51
|
+
self.coding_sm = CodingStateMachine(EUCKR_SM_MODEL)
|
|
52
|
+
self.distribution_analyzer = EUCKRDistributionAnalysis()
|
|
53
|
+
self.reset()
|
|
54
|
+
|
|
55
|
+
@property
|
|
56
|
+
def charset_name(self):
|
|
57
|
+
return "EUC-KR"
|
|
58
|
+
|
|
59
|
+
@property
|
|
60
|
+
def language(self):
|
|
61
|
+
return "Korean"
|