python (3.12.0)
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 typing import List, Union
30
31 from .charsetprober import CharSetProber
32 from .enums import ProbingState
33
34 FREQ_CAT_NUM = 4
35
36 UDF = 0 # undefined
37 OTH = 1 # other
38 ASC = 2 # ascii capital letter
39 ASS = 3 # ascii small letter
40 ACV = 4 # accent capital vowel
41 ACO = 5 # accent capital other
42 ASV = 6 # accent small vowel
43 ASO = 7 # accent small other
44 CLASS_NUM = 8 # total classes
45
46 # fmt: off
47 Latin1_CharToClass = (
48 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 00 - 07
49 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 08 - 0F
50 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 10 - 17
51 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 18 - 1F
52 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 20 - 27
53 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 28 - 2F
54 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 30 - 37
55 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 38 - 3F
56 OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 40 - 47
57 ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 48 - 4F
58 ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, # 50 - 57
59 ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH, # 58 - 5F
60 OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 60 - 67
61 ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 68 - 6F
62 ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, # 70 - 77
63 ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH, # 78 - 7F
64 OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH, # 80 - 87
65 OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF, # 88 - 8F
66 UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # 90 - 97
67 OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO, # 98 - 9F
68 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A0 - A7
69 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # A8 - AF
70 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B0 - B7
71 OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, # B8 - BF
72 ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO, # C0 - C7
73 ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV, # C8 - CF
74 ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH, # D0 - D7
75 ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO, # D8 - DF
76 ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO, # E0 - E7
77 ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV, # E8 - EF
78 ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH, # F0 - F7
79 ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO, # F8 - FF
80 )
81
82 # 0 : illegal
83 # 1 : very unlikely
84 # 2 : normal
85 # 3 : very likely
86 Latin1ClassModel = (
87 # UDF OTH ASC ASS ACV ACO ASV ASO
88 0, 0, 0, 0, 0, 0, 0, 0, # UDF
89 0, 3, 3, 3, 3, 3, 3, 3, # OTH
90 0, 3, 3, 3, 3, 3, 3, 3, # ASC
91 0, 3, 3, 3, 1, 1, 3, 3, # ASS
92 0, 3, 3, 3, 1, 2, 1, 2, # ACV
93 0, 3, 3, 3, 3, 3, 3, 3, # ACO
94 0, 3, 1, 3, 1, 1, 1, 3, # ASV
95 0, 3, 1, 3, 1, 1, 3, 3, # ASO
96 )
97 # fmt: on
98
99
100 class ESC[4;38;5;81mLatin1Prober(ESC[4;38;5;149mCharSetProber):
101 def __init__(self) -> None:
102 super().__init__()
103 self._last_char_class = OTH
104 self._freq_counter: List[int] = []
105 self.reset()
106
107 def reset(self) -> None:
108 self._last_char_class = OTH
109 self._freq_counter = [0] * FREQ_CAT_NUM
110 super().reset()
111
112 @property
113 def charset_name(self) -> str:
114 return "ISO-8859-1"
115
116 @property
117 def language(self) -> str:
118 return ""
119
120 def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
121 byte_str = self.remove_xml_tags(byte_str)
122 for c in byte_str:
123 char_class = Latin1_CharToClass[c]
124 freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM) + char_class]
125 if freq == 0:
126 self._state = ProbingState.NOT_ME
127 break
128 self._freq_counter[freq] += 1
129 self._last_char_class = char_class
130
131 return self.state
132
133 def get_confidence(self) -> float:
134 if self.state == ProbingState.NOT_ME:
135 return 0.01
136
137 total = sum(self._freq_counter)
138 confidence = (
139 0.0
140 if total < 0.01
141 else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total
142 )
143 confidence = max(confidence, 0.0)
144 # lower the confidence of latin1 so that other more accurate
145 # detector can take priority.
146 confidence *= 0.73
147 return confidence