Gecko [ renovalkoronred.com.tr ]

Name	Size	Permission
__pycache__	[ DIR ]	drwxr-xr-x
cli	[ DIR ]	drwxr-xr-x
metadata	[ DIR ]	drwxr-xr-x
__init__.py	4.68 KB	-rw-r--r--
__main__.py	123 B	-rw-r--r--
big5freq.py	30.54 KB	-rw-r--r--
big5prober.py	1.72 KB	-rw-r--r--
chardistribution.py	9.8 KB	-rw-r--r--
charsetgroupprober.py	3.82 KB	-rw-r--r--
charsetprober.py	5.29 KB	-rw-r--r--
codingstatemachine.py	3.64 KB	-rw-r--r--
codingstatemachinedict.py	542 B	-rw-r--r--
cp949prober.py	1.82 KB	-rw-r--r--
enums.py	1.64 KB	-rw-r--r--
escprober.py	3.91 KB	-rw-r--r--
escsm.py	11.89 KB	-rw-r--r--
eucjpprober.py	3.84 KB	-rw-r--r--
euckrfreq.py	13.25 KB	-rw-r--r--
euckrprober.py	1.71 KB	-rw-r--r--
euctwfreq.py	36.05 KB	-rw-r--r--
euctwprober.py	1.71 KB	-rw-r--r--
gb2312freq.py	20.25 KB	-rw-r--r--
gb2312prober.py	1.72 KB	-rw-r--r--
hebrewprober.py	14.2 KB	-rw-r--r--
jisfreq.py	25.19 KB	-rw-r--r--
johabfreq.py	41.5 KB	-rw-r--r--
johabprober.py	1.71 KB	-rw-r--r--
jpcntx.py	26.42 KB	-rw-r--r--
langbulgarianmodel.py	102.1 KB	-rw-r--r--
langgreekmodel.py	96.16 KB	-rw-r--r--
langhebrewmodel.py	95.88 KB	-rw-r--r--
langhungarianmodel.py	98.98 KB	-rw-r--r--
langrussianmodel.py	125.02 KB	-rw-r--r--
langthaimodel.py	100.35 KB	-rw-r--r--
langturkishmodel.py	93.13 KB	-rw-r--r--
latin1prober.py	5.25 KB	-rw-r--r--
macromanprober.py	5.93 KB	-rw-r--r--
mbcharsetprober.py	3.63 KB	-rw-r--r--
mbcsgroupprober.py	2.08 KB	-rw-r--r--
mbcssm.py	29.68 KB	-rw-r--r--
py.typed	0 B	-rw-r--r--
resultdict.py	402 B	-rw-r--r--
sbcharsetprober.py	6.25 KB	-rw-r--r--
sbcsgroupprober.py	4.04 KB	-rw-r--r--
sjisprober.py	3.91 KB	-rw-r--r--
universaldetector.py	14.5 KB	-rw-r--r--
utf1632prober.py	8.31 KB	-rw-r--r--
utf8prober.py	2.75 KB	-rw-r--r--
version.py	244 B	-rw-r--r--

Code Editor : latin1prober.py

######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Universal charset detector code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 2001
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#   Shy Shalom - original C code
#
# 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 typing import List, Union

from .charsetprober import CharSetProber
from .enums import ProbingState

FREQ_CAT_NUM = 4

UDF = 0  # undefined
OTH = 1  # other
ASC = 2  # ascii capital letter
ASS = 3  # ascii small letter
ACV = 4  # accent capital vowel
ACO = 5  # accent capital other
ASV = 6  # accent small vowel
ASO = 7  # accent small other
CLASS_NUM = 8  # total classes

# fmt: off
Latin1_CharToClass = (
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 00 - 07
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 08 - 0F
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 10 - 17
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 18 - 1F
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 20 - 27
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 28 - 2F
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 30 - 37
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 38 - 3F
    OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 40 - 47
    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 48 - 4F
    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 50 - 57
    ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH,   # 58 - 5F
    OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 60 - 67
    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 68 - 6F
    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 70 - 77
    ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH,   # 78 - 7F
    OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH,   # 80 - 87
    OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF,   # 88 - 8F
    UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 90 - 97
    OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO,   # 98 - 9F
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # A0 - A7
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # A8 - AF
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # B0 - B7
    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # B8 - BF
    ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO,   # C0 - C7
    ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV,   # C8 - CF
    ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH,   # D0 - D7
    ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO,   # D8 - DF
    ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO,   # E0 - E7
    ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV,   # E8 - EF
    ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH,   # F0 - F7
    ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO,   # F8 - FF
)

# 0 : illegal
# 1 : very unlikely
# 2 : normal
# 3 : very likely
Latin1ClassModel = (
# UDF OTH ASC ASS ACV ACO ASV ASO
    0,  0,  0,  0,  0,  0,  0,  0,  # UDF
    0,  3,  3,  3,  3,  3,  3,  3,  # OTH
    0,  3,  3,  3,  3,  3,  3,  3,  # ASC
    0,  3,  3,  3,  1,  1,  3,  3,  # ASS
    0,  3,  3,  3,  1,  2,  1,  2,  # ACV
    0,  3,  3,  3,  3,  3,  3,  3,  # ACO
    0,  3,  1,  3,  1,  1,  1,  3,  # ASV
    0,  3,  1,  3,  1,  1,  3,  3,  # ASO
)
# fmt: on

class Latin1Prober(CharSetProber):
    def __init__(self) -> None:
        super().__init__()
        self._last_char_class = OTH
        self._freq_counter: List[int] = []
        self.reset()

def reset(self) -> None:
        self._last_char_class = OTH
        self._freq_counter = [0] * FREQ_CAT_NUM
        super().reset()

@property
    def charset_name(self) -> str:
        return "ISO-8859-1"

@property
    def language(self) -> str:
        return ""

def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
        byte_str = self.remove_xml_tags(byte_str)
        for c in byte_str:
            char_class = Latin1_CharToClass[c]
            freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM) + char_class]
            if freq == 0:
                self._state = ProbingState.NOT_ME
                break
            self._freq_counter[freq] += 1
            self._last_char_class = char_class

return self.state

def get_confidence(self) -> float:
        if self.state == ProbingState.NOT_ME:
            return 0.01

total = sum(self._freq_counter)
        confidence = (
            0.0
            if total < 0.01
            else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total
        )
        confidence = max(confidence, 0.0)
        # lower the confidence of latin1 so that other more accurate
        # detector can take priority.
        confidence *= 0.73
        return confidence

${this.title}

Code Editor : latin1prober.py