OLD | NEW |
(Empty) | |
| 1 ######################## BEGIN LICENSE BLOCK ######################## |
| 2 # The Original Code is Mozilla Universal charset detector code. |
| 3 # |
| 4 # The Initial Developer of the Original Code is |
| 5 # Netscape Communications Corporation. |
| 6 # Portions created by the Initial Developer are Copyright (C) 2001 |
| 7 # the Initial Developer. All Rights Reserved. |
| 8 # |
| 9 # Contributor(s): |
| 10 # Mark Pilgrim - port to Python |
| 11 # Shy Shalom - original C code |
| 12 # |
| 13 # This library is free software; you can redistribute it and/or |
| 14 # modify it under the terms of the GNU Lesser General Public |
| 15 # License as published by the Free Software Foundation; either |
| 16 # version 2.1 of the License, or (at your option) any later version. |
| 17 # |
| 18 # This library is distributed in the hope that it will be useful, |
| 19 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 21 # Lesser General Public License for more details. |
| 22 # |
| 23 # You should have received a copy of the GNU Lesser General Public |
| 24 # License along with this library; if not, write to the Free Software |
| 25 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA |
| 26 # 02110-1301 USA |
| 27 ######################### END LICENSE BLOCK ######################### |
| 28 |
| 29 from .charsetprober import CharSetProber |
| 30 from .constants import eNotMe |
| 31 from .compat import wrap_ord |
| 32 |
| 33 FREQ_CAT_NUM = 4 |
| 34 |
| 35 UDF = 0 # undefined |
| 36 OTH = 1 # other |
| 37 ASC = 2 # ascii capital letter |
| 38 ASS = 3 # ascii small letter |
| 39 ACV = 4 # accent capital vowel |
| 40 ACO = 5 # accent capital other |
| 41 ASV = 6 # accent small vowel |
| 42 ASO = 7 # accent small other |
| 43 CLASS_NUM = 8 # total classes |
| 44 |
| 45 Latin1_CharToClass = ( |
| 46 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 00 - 07 |
| 47 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 08 - 0F |
| 48 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 10 - 17 |
| 49 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 18 - 1F |
| 50 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 20 - 27 |
| 51 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 28 - 2F |
| 52 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 30 - 37 |
| 53 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 38 - 3F |
| 54 OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 40 - 47 |
| 55 ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 48 - 4F |
| 56 ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 50 - 57 |
| 57 ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH, # 58 - 5F |
| 58 OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 60 - 67 |
| 59 ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 68 - 6F |
| 60 ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 70 - 77 |
| 61 ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH, # 78 - 7F |
| 62 OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH, # 80 - 87 |
| 63 OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF, # 88 - 8F |
| 64 UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 90 - 97 |
| 65 OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO, # 98 - 9F |
| 66 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A0 - A7 |
| 67 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A8 - AF |
| 68 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B0 - B7 |
| 69 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B8 - BF |
| 70 ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO, # C0 - C7 |
| 71 ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV, # C8 - CF |
| 72 ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH, # D0 - D7 |
| 73 ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO, # D8 - DF |
| 74 ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO, # E0 - E7 |
| 75 ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV, # E8 - EF |
| 76 ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH, # F0 - F7 |
| 77 ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO, # F8 - FF |
| 78 ) |
| 79 |
| 80 # 0 : illegal |
| 81 # 1 : very unlikely |
| 82 # 2 : normal |
| 83 # 3 : very likely |
| 84 Latin1ClassModel = ( |
| 85 # UDF OTH ASC ASS ACV ACO ASV ASO |
| 86 0, 0, 0, 0, 0, 0, 0, 0, # UDF |
| 87 0, 3, 3, 3, 3, 3, 3, 3, # OTH |
| 88 0, 3, 3, 3, 3, 3, 3, 3, # ASC |
| 89 0, 3, 3, 3, 1, 1, 3, 3, # ASS |
| 90 0, 3, 3, 3, 1, 2, 1, 2, # ACV |
| 91 0, 3, 3, 3, 3, 3, 3, 3, # ACO |
| 92 0, 3, 1, 3, 1, 1, 1, 3, # ASV |
| 93 0, 3, 1, 3, 1, 1, 3, 3, # ASO |
| 94 ) |
| 95 |
| 96 |
| 97 class Latin1Prober(CharSetProber): |
| 98 def __init__(self): |
| 99 CharSetProber.__init__(self) |
| 100 self.reset() |
| 101 |
| 102 def reset(self): |
| 103 self._mLastCharClass = OTH |
| 104 self._mFreqCounter = [0] * FREQ_CAT_NUM |
| 105 CharSetProber.reset(self) |
| 106 |
| 107 def get_charset_name(self): |
| 108 return "windows-1252" |
| 109 |
| 110 def feed(self, aBuf): |
| 111 aBuf = self.filter_with_english_letters(aBuf) |
| 112 for c in aBuf: |
| 113 charClass = Latin1_CharToClass[wrap_ord(c)] |
| 114 freq = Latin1ClassModel[(self._mLastCharClass * CLASS_NUM) |
| 115 + charClass] |
| 116 if freq == 0: |
| 117 self._mState = eNotMe |
| 118 break |
| 119 self._mFreqCounter[freq] += 1 |
| 120 self._mLastCharClass = charClass |
| 121 |
| 122 return self.get_state() |
| 123 |
| 124 def get_confidence(self): |
| 125 if self.get_state() == eNotMe: |
| 126 return 0.01 |
| 127 |
| 128 total = sum(self._mFreqCounter) |
| 129 if total < 0.01: |
| 130 confidence = 0.0 |
| 131 else: |
| 132 confidence = ((self._mFreqCounter[3] / total) |
| 133 - (self._mFreqCounter[1] * 20.0 / total)) |
| 134 if confidence < 0.0: |
| 135 confidence = 0.0 |
| 136 # lower the confidence of latin1 so that other more accurate |
| 137 # detector can take priority. |
| 138 confidence = confidence * 0.5 |
| 139 return confidence |
OLD | NEW |