Gecko [ sachasauda.akalacademy.ac.in ]

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

Code Editor : 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

${this.title}

Code Editor : chardistribution.py