######################## 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 #########################
import constants
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
ENOUGH_DATA_THRESHOLD = 1024
SURE_YES = 0.99
SURE_NO = 0.01
class CharDistributionAnalysis:
def __init__(self):
self._mCharToFreqOrder = None # Mapping table to get frequency order from char order (get from GetOrder())
self._mTableSize = None # Size of above table
self._mTypicalDistributionRatio = None # 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.reset()
def reset(self):
"""reset analyser, clear any state"""
self._mDone = constants.False # If this flag is set to constants.True, detection is done and conclusion has been made
self._mTotalChars = 0 # Total characters encountered
self._mFreqChars = 0 # The number of characters whose frequency order is less than 512
def feed(self, aStr, 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(aStr)
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:
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, aStr):
# 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):