|
|
######################## BEGIN LICENSE BLOCK ########################
|
|
|
# The Original Code is mozilla.org code.
|
|
|
#
|
|
|
# The Initial Developer of the Original Code is
|
|
|
# Netscape Communications Corporation.
|
|
|
# Portions created by the Initial Developer are Copyright (C) 1998
|
|
|
# the Initial Developer. All Rights Reserved.
|
|
|
#
|
|
|
# Contributor(s):
|
|
|
# Mark Pilgrim - port to Python
|
|
|
#
|
|
|
# This library is free software; you can redistribute it and/or
|
|
|
# modify it under the terms of the GNU Lesser General Public
|
|
|
# License as published by the Free Software Foundation; either
|
|
|
# version 2.1 of the License, or (at your option) any later version.
|
|
|
#
|
|
|
# This library is distributed in the hope that it will be useful,
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
# Lesser General Public License for more details.
|
|
|
#
|
|
|
# You should have received a copy of the GNU Lesser General Public
|
|
|
# License along with this library; if not, write to the Free Software
|
|
|
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
|
|
# 02110-1301 USA
|
|
|
######################### END LICENSE BLOCK #########################
|
|
|
|
|
|
from .charsetprober import CharSetProber
|
|
|
from .codingstatemachine import CodingStateMachine
|
|
|
from .enums import LanguageFilter, ProbingState, MachineState
|
|
|
from .escsm import (HZ_SM_MODEL, ISO2022CN_SM_MODEL, ISO2022JP_SM_MODEL,
|
|
|
ISO2022KR_SM_MODEL)
|
|
|
|
|
|
|
|
|
class EscCharSetProber(CharSetProber):
|
|
|
"""
|
|
|
This CharSetProber uses a "code scheme" approach for detecting encodings,
|
|
|
whereby easily recognizable escape or shift sequences are relied on to
|
|
|
identify these encodings.
|
|
|
"""
|
|
|
|
|
|
def __init__(self, lang_filter=None):
|
|
|
# 初始化EscCharSetProber类
|
|
|
super(EscCharSetProber, self).__init__(lang_filter=lang_filter)
|
|
|
# 初始化编码状态机列表
|
|
|
self.coding_sm = []
|
|
|
# 如果语言过滤器包含简体中文
|
|
|
if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
|
|
|
# 添加简体中文编码状态机
|
|
|
self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
|
|
|
# 添加ISO2022CN编码状态机
|
|
|
self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL))
|
|
|
# 如果语言过滤器包含日语
|
|
|
if self.lang_filter & LanguageFilter.JAPANESE:
|
|
|
# 添加ISO2022JP编码状态机
|
|
|
self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
|
|
|
# 如果语言过滤器包含韩语
|
|
|
if self.lang_filter & LanguageFilter.KOREAN:
|
|
|
# 添加ISO2022KR编码状态机
|
|
|
self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
|
|
|
# 初始化活动状态机数量
|
|
|
self.active_sm_count = None
|
|
|
# 初始化检测到的字符集
|
|
|
self._detected_charset = None
|
|
|
# 初始化检测到的语言
|
|
|
self._detected_language = None
|
|
|
# 初始化状态
|
|
|
self._state = None
|
|
|
# 重置
|
|
|
self.reset()
|
|
|
|
|
|
def reset(self):
|
|
|
# 重置EscCharSetProber类
|
|
|
super(EscCharSetProber, self).reset()
|
|
|
# 遍历编码状态机列表
|
|
|
for coding_sm in self.coding_sm:
|
|
|
# 如果编码状态机为空，则跳过
|
|
|
if not coding_sm:
|
|
|
continue
|
|
|
# 设置编码状态机为活动状态
|
|
|
coding_sm.active = True
|
|
|
# 重置编码状态机
|
|
|
coding_sm.reset()
|
|
|
# 设置活动状态机数量为编码状态机列表的长度
|
|
|
self.active_sm_count = len(self.coding_sm)
|
|
|
# 设置检测到的字符集为空
|
|
|
self._detected_charset = None
|
|
|
# 设置检测到的语言为空
|
|
|
self._detected_language = None
|
|
|
|
|
|
@property
|
|
|
def charset_name(self):
|
|
|
# 返回检测到的字符集
|
|
|
return self._detected_charset
|
|
|
|
|
|
@property
|
|
|
def language(self):
|
|
|
# 返回检测到的语言
|
|
|
return self._detected_language
|
|
|
|
|
|
def get_confidence(self):
|
|
|
# 如果检测到了字符集，则返回0.99，否则返回0.00
|
|
|
if self._detected_charset:
|
|
|
return 0.99
|
|
|
else:
|
|
|
return 0.00
|
|
|
|
|
|
def feed(self, byte_str):
|
|
|
# 遍历字节字符串
|
|
|
for c in byte_str:
|
|
|
# 遍历编码状态机列表
|
|
|
for coding_sm in self.coding_sm:
|
|
|
# 如果编码状态机为空或非活动状态，则跳过
|
|
|
if not coding_sm or not coding_sm.active:
|
|
|
continue
|
|
|
# 获取编码状态机的下一个状态
|
|
|
coding_state = coding_sm.next_state(c)
|
|
|
# 如果状态为错误，则设置编码状态机为非活动状态，活动状态机数量减一
|
|
|
if coding_state == MachineState.ERROR:
|
|
|
coding_sm.active = False
|
|
|
self.active_sm_count -= 1
|
|
|
# 如果活动状态机数量小于等于0，则设置状态为非匹配
|
|
|
if self.active_sm_count <= 0:
|
|
|
self._state = ProbingState.NOT_ME
|
|
|
return self.state
|
|
|
# 如果状态为匹配，则设置状态为匹配，设置检测到的字符集和语言
|
|
|
elif coding_state == MachineState.ITS_ME:
|
|
|
self._state = ProbingState.FOUND_IT
|
|
|
self._detected_charset = coding_sm.get_coding_state_machine()
|
|
|
self._detected_language = coding_sm.language
|
|
|
return self.state
|
|
|
|
|
|
# 返回状态
|
|
|
return self.state
|
