Gecko [ oric.aiou.edu.pk ]

Name	Size	Permission
cli	[ DIR ]	drwxr-xr-x
__init__.py	1.52 KB	-rw-r--r--
big5freq.py	30.52 KB	-rw-r--r--
big5prober.py	1.72 KB	-rw-r--r--
chardistribution.py	9.19 KB	-rw-r--r--
charsetgroupprober.py	3.7 KB	-rw-r--r--
charsetprober.py	4.99 KB	-rw-r--r--
codingstatemachine.py	3.51 KB	-rw-r--r--
compat.py	1.11 KB	-rw-r--r--
cp949prober.py	1.81 KB	-rw-r--r--
enums.py	1.62 KB	-rw-r--r--
escprober.py	3.86 KB	-rw-r--r--
escsm.py	10.26 KB	-rw-r--r--
eucjpprober.py	3.66 KB	-rw-r--r--
euckrfreq.py	13.23 KB	-rw-r--r--
euckrprober.py	1.71 KB	-rw-r--r--
euctwfreq.py	30.88 KB	-rw-r--r--
euctwprober.py	1.71 KB	-rw-r--r--
gb2312freq.py	20.23 KB	-rw-r--r--
gb2312prober.py	1.71 KB	-rw-r--r--
hebrewprober.py	13.51 KB	-rw-r--r--
jisfreq.py	25.17 KB	-rw-r--r--
jpcntx.py	19.18 KB	-rw-r--r--
langbulgarianmodel.py	12.54 KB	-rw-r--r--
langcyrillicmodel.py	17.53 KB	-rw-r--r--
langgreekmodel.py	12.39 KB	-rw-r--r--
langhebrewmodel.py	11.08 KB	-rw-r--r--
langhungarianmodel.py	12.3 KB	-rw-r--r--
langthaimodel.py	11.03 KB	-rw-r--r--
langturkishmodel.py	10.84 KB	-rw-r--r--
latin1prober.py	5.24 KB	-rw-r--r--
mbcharsetprober.py	3.33 KB	-rw-r--r--
mbcsgroupprober.py	1.96 KB	-rw-r--r--
mbcssm.py	24.88 KB	-rw-r--r--
sbcharsetprober.py	5.52 KB	-rw-r--r--
sbcsgroupprober.py	3.46 KB	-rw-r--r--
sjisprober.py	3.69 KB	-rw-r--r--
universaldetector.py	12.19 KB	-rw-r--r--
utf8prober.py	2.7 KB	-rw-r--r--
version.py	242 B	-rw-r--r--

Code Editor : charsetprober.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 #########################

import logging
import re

from .enums import ProbingState

class CharSetProber(object):

SHORTCUT_THRESHOLD = 0.95

def __init__(self, lang_filter=None):
        self._state = None
        self.lang_filter = lang_filter
        self.logger = logging.getLogger(__name__)

def reset(self):
        self._state = ProbingState.DETECTING

@property
    def charset_name(self):
        return None

def feed(self, buf):
        pass

@property
    def state(self):
        return self._state

def get_confidence(self):
        return 0.0

@staticmethod
    def filter_high_byte_only(buf):
        buf = re.sub(b'([\x00-\x7F])+', b' ', buf)
        return buf

@staticmethod
    def filter_international_words(buf):
        """
        We define three types of bytes:
        alphabet: english alphabets [a-zA-Z]
        international: international characters [\x80-\xFF]
        marker: everything else [^a-zA-Z\x80-\xFF]

The input buffer can be thought to contain a series of words delimited
        by markers. This function works to filter all words that contain at
        least one international character. All contiguous sequences of markers
        are replaced by a single space ascii character.

This filter applies to all scripts which do not use English characters.
        """
        filtered = bytearray()

# This regex expression filters out only words that have at-least one
        # international character. The word may include one marker character at
        # the end.
        words = re.findall(b'[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?',
                           buf)

for word in words:
            filtered.extend(word[:-1])

# If the last character in the word is a marker, replace it with a
            # space as markers shouldn't affect our analysis (they are used
            # similarly across all languages and may thus have similar
            # frequencies).
            last_char = word[-1:]
            if not last_char.isalpha() and last_char < b'\x80':
                last_char = b' '
            filtered.extend(last_char)

return filtered

@staticmethod
    def filter_with_english_letters(buf):
        """
        Returns a copy of ``buf`` that retains only the sequences of English
        alphabet and high byte characters that are not between <> characters.
        Also retains English alphabet and high byte characters immediately
        before occurrences of >.

This filter can be applied to all scripts which contain both English
        characters and extended ASCII characters, but is currently only used by
        ``Latin1Prober``.
        """
        filtered = bytearray()
        in_tag = False
        prev = 0

for curr in range(len(buf)):
            # Slice here to get bytes instead of an int with Python 3
            buf_char = buf[curr:curr + 1]
            # Check if we're coming out of or entering an HTML tag
            if buf_char == b'>':
                in_tag = False
            elif buf_char == b'<':
                in_tag = True

# If current character is not extended-ASCII and not alphabetic...
            if buf_char < b'\x80' and not buf_char.isalpha():
                # ...and we're not in a tag
                if curr > prev and not in_tag:
                    # Keep everything after last non-extended-ASCII,
                    # non-alphabetic character
                    filtered.extend(buf[prev:curr])
                    # Output a space to delimit stretch we kept
                    filtered.extend(b' ')
                prev = curr + 1

# If we're not in a tag...
        if not in_tag:
            # Keep everything after last non-extended-ASCII, non-alphabetic
            # character
            filtered.extend(buf[prev:])

return filtered

${this.title}

Code Editor : charsetprober.py