golden hour

/usr/lib/python2.7/site-packages/chardet

File/Folder	Size	Actions
__init__.py	1.26 KB
__init__.pyc	797 B
__init__.pyo	797 B
big5freq.py	80.66 KB
big5freq.pyc	111.11 KB
big5freq.pyo	111.11 KB
big5prober.py	1.64 KB
big5prober.pyc	1.07 KB
big5prober.pyo	1.07 KB
chardetect.py	1.09 KB
chardetect.pyc	1.46 KB
chardetect.pyo	1.46 KB
chardistribution.py	9.01 KB
chardistribution.pyc	7.35 KB
chardistribution.pyo	7.35 KB
charsetgroupprober.py	3.7 KB
charsetgroupprober.pyc	2.48 KB
charsetgroupprober.pyo	2.48 KB
charsetprober.py	1.86 KB
charsetprober.pyc	2.08 KB
charsetprober.pyo	2.08 KB
codingstatemachine.py	2.26 KB
codingstatemachine.pyc	1.74 KB
codingstatemachine.pyo	1.74 KB
compat.py	1.13 KB
compat.pyc	559 B
compat.pyo	559 B
constants.py	1.3 KB
constants.pyc	332 B
constants.pyo	332 B
cp949prober.py	1.74 KB
cp949prober.pyc	1.07 KB
cp949prober.pyo	1.07 KB
escprober.py	3.11 KB
escprober.pyc	2.31 KB
escprober.pyo	2.31 KB
escsm.py	7.66 KB
escsm.pyc	7.13 KB
escsm.pyo	7.13 KB
eucjpprober.py	3.59 KB
eucjpprober.pyc	2.71 KB
eucjpprober.pyo	2.71 KB
euckrfreq.py	44.9 KB
euckrfreq.pyc	86.69 KB
euckrfreq.pyo	86.69 KB
euckrprober.py	1.64 KB
euckrprober.pyc	1.08 KB
euckrprober.pyo	1.08 KB
euctwfreq.py	34.05 KB
euctwfreq.pyc	59.74 KB
euctwfreq.pyo	59.74 KB
euctwprober.py	1.64 KB
euctwprober.pyc	1.08 KB
euctwprober.pyo	1.08 KB
gb2312freq.py	35.17 KB
gb2312freq.pyc	67.17 KB
gb2312freq.pyo	67.17 KB
gb2312prober.py	1.64 KB
gb2312prober.pyc	1.08 KB
gb2312prober.pyo	1.08 KB
hebrewprober.py	13.05 KB
hebrewprober.pyc	3.32 KB
hebrewprober.pyo	3.32 KB
jisfreq.py	46.21 KB
jisfreq.pyc	82.03 KB
jisfreq.pyo	82.03 KB
jpcntx.py	18.66 KB
jpcntx.pyc	24.04 KB
jpcntx.pyo	24.04 KB
langbulgarianmodel.py	12.48 KB
langbulgarianmodel.pyc	24.3 KB
langbulgarianmodel.pyo	24.3 KB
langcyrillicmodel.py	17.31 KB
langcyrillicmodel.pyc	29.85 KB
langcyrillicmodel.pyo	29.85 KB
langgreekmodel.py	12.33 KB
langgreekmodel.pyc	24 KB
langgreekmodel.pyo	24 KB
langhebrewmodel.py	11.05 KB
langhebrewmodel.pyc	22.84 KB
langhebrewmodel.pyo	22.84 KB
langhungarianmodel.py	12.24 KB
langhungarianmodel.pyc	24.29 KB
langhungarianmodel.pyo	24.29 KB
langthaimodel.py	11.01 KB
langthaimodel.pyc	22.83 KB
langthaimodel.pyo	22.83 KB
latin1prober.py	5.12 KB
latin1prober.pyc	3.37 KB
latin1prober.pyo	3.37 KB
mbcharsetprober.py	3.19 KB
mbcharsetprober.pyc	2.36 KB
mbcharsetprober.pyo	2.36 KB
mbcsgroupprober.py	1.92 KB
mbcsgroupprober.pyc	1.22 KB
mbcsgroupprober.pyo	1.22 KB
mbcssm.py	19.15 KB
mbcssm.pyc	17.25 KB
mbcssm.pyo	17.25 KB
sbcharsetprober.py	4.68 KB
sbcharsetprober.pyc	3.22 KB
sbcharsetprober.pyo	3.22 KB
sbcsgroupprober.py	3.21 KB
sbcsgroupprober.pyc	1.89 KB
sbcsgroupprober.pyo	1.89 KB
sjisprober.py	3.65 KB
sjisprober.pyc	2.73 KB
sjisprober.pyo	2.73 KB
universaldetector.py	6.67 KB
universaldetector.pyc	4.02 KB
universaldetector.pyo	4.02 KB
utf8prober.py	2.59 KB
utf8prober.pyc	2.14 KB
utf8prober.pyo	2.14 KB

Edit: chardistribution.py

######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Communicator client 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 .euctwfreq import (EUCTWCharToFreqOrder, EUCTW_TABLE_SIZE,
                        EUCTW_TYPICAL_DISTRIBUTION_RATIO)
from .euckrfreq import (EUCKRCharToFreqOrder, EUCKR_TABLE_SIZE,
                        EUCKR_TYPICAL_DISTRIBUTION_RATIO)
from .gb2312freq import (GB2312CharToFreqOrder, GB2312_TABLE_SIZE,
                         GB2312_TYPICAL_DISTRIBUTION_RATIO)
from .big5freq import (Big5CharToFreqOrder, BIG5_TABLE_SIZE,
                       BIG5_TYPICAL_DISTRIBUTION_RATIO)
from .jisfreq import (JISCharToFreqOrder, JIS_TABLE_SIZE,
                      JIS_TYPICAL_DISTRIBUTION_RATIO)
from .compat import wrap_ord

ENOUGH_DATA_THRESHOLD = 1024
SURE_YES = 0.99
SURE_NO = 0.01
MINIMUM_DATA_THRESHOLD = 3

class CharDistributionAnalysis:
    def __init__(self):
        # Mapping table to get frequency order from char order (get from
        # GetOrder())
        self._mCharToFreqOrder = None
        self._mTableSize = None  # Size of above table
        # This is a constant value which varies from language to language,
        # used in calculating confidence.  See
        # http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html
        # for further detail.
        self._mTypicalDistributionRatio = None
        self.reset()

def reset(self):
        """reset analyser, clear any state"""
        # If this flag is set to True, detection is done and conclusion has
        # been made
        self._mDone = False
        self._mTotalChars = 0  # Total characters encountered
        # The number of characters whose frequency order is less than 512
        self._mFreqChars = 0

def feed(self, aBuf, aCharLen):
        """feed a character with known length"""
        if aCharLen == 2:
            # we only care about 2-bytes character in our distribution analysis
            order = self.get_order(aBuf)
        else:
            order = -1
        if order >= 0:
            self._mTotalChars += 1
            # order is valid
            if order < self._mTableSize:
                if 512 > self._mCharToFreqOrder[order]:
                    self._mFreqChars += 1

def get_confidence(self):
        """return confidence based on existing data"""
        # if we didn't receive any character in our consideration range,
        # return negative answer
        if self._mTotalChars <= 0 or self._mFreqChars <= MINIMUM_DATA_THRESHOLD:
            return SURE_NO

if self._mTotalChars != self._mFreqChars:
            r = (self._mFreqChars / ((self._mTotalChars - self._mFreqChars)
                 * self._mTypicalDistributionRatio))
            if r < SURE_YES:
                return r

# normalize confidence (we don't want to be 100% sure)
        return SURE_YES

def got_enough_data(self):
        # It is not necessary to receive all data to draw conclusion.
        # For charset detection, certain amount of data is enough
        return self._mTotalChars > ENOUGH_DATA_THRESHOLD

def get_order(self, aBuf):
        # We do not handle characters based on the original encoding string,
        # but convert this encoding string to a number, here called order.
        # This allows multiple encodings of a language to share one frequency
        # table.
        return -1

class EUCTWDistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = EUCTWCharToFreqOrder
        self._mTableSize = EUCTW_TABLE_SIZE
        self._mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for euc-TW encoding, we are interested
        #   first  byte range: 0xc4 -- 0xfe
        #   second byte range: 0xa1 -- 0xfe
        # no validation needed here. State machine has done that
        first_char = wrap_ord(aBuf[0])
        if first_char >= 0xC4:
            return 94 * (first_char - 0xC4) + wrap_ord(aBuf[1]) - 0xA1
        else:
            return -1

class EUCKRDistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = EUCKRCharToFreqOrder
        self._mTableSize = EUCKR_TABLE_SIZE
        self._mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for euc-KR encoding, we are interested
        #   first  byte range: 0xb0 -- 0xfe
        #   second byte range: 0xa1 -- 0xfe
        # no validation needed here. State machine has done that
        first_char = wrap_ord(aBuf[0])
        if first_char >= 0xB0:
            return 94 * (first_char - 0xB0) + wrap_ord(aBuf[1]) - 0xA1
        else:
            return -1

class GB2312DistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = GB2312CharToFreqOrder
        self._mTableSize = GB2312_TABLE_SIZE
        self._mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for GB2312 encoding, we are interested
        #  first  byte range: 0xb0 -- 0xfe
        #  second byte range: 0xa1 -- 0xfe
        # no validation needed here. State machine has done that
        first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
        if (first_char >= 0xB0) and (second_char >= 0xA1):
            return 94 * (first_char - 0xB0) + second_char - 0xA1
        else:
            return -1

class Big5DistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = Big5CharToFreqOrder
        self._mTableSize = BIG5_TABLE_SIZE
        self._mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for big5 encoding, we are interested
        #   first  byte range: 0xa4 -- 0xfe
        #   second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
        # no validation needed here. State machine has done that
        first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
        if first_char >= 0xA4:
            if second_char >= 0xA1:
                return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63
            else:
                return 157 * (first_char - 0xA4) + second_char - 0x40
        else:
            return -1

class SJISDistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = JISCharToFreqOrder
        self._mTableSize = JIS_TABLE_SIZE
        self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for sjis encoding, we are interested
        #   first  byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
        #   second byte range: 0x40 -- 0x7e,  0x81 -- oxfe
        # no validation needed here. State machine has done that
        first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
        if (first_char >= 0x81) and (first_char <= 0x9F):
            order = 188 * (first_char - 0x81)
        elif (first_char >= 0xE0) and (first_char <= 0xEF):
            order = 188 * (first_char - 0xE0 + 31)
        else:
            return -1
        order = order + second_char - 0x40
        if second_char > 0x7F:
            order = -1
        return order

class EUCJPDistributionAnalysis(CharDistributionAnalysis):
    def __init__(self):
        CharDistributionAnalysis.__init__(self)
        self._mCharToFreqOrder = JISCharToFreqOrder
        self._mTableSize = JIS_TABLE_SIZE
        self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO

def get_order(self, aBuf):
        # for euc-JP encoding, we are interested
        #   first  byte range: 0xa0 -- 0xfe
        #   second byte range: 0xa1 -- 0xfe
        # no validation needed here. State machine has done that
        char = wrap_ord(aBuf[0])
        if char >= 0xA0:
            return 94 * (char - 0xA1) + wrap_ord(aBuf[1]) - 0xa1
        else:
            return -1