summaryrefslogtreecommitdiff
path: root/src/pip/_vendor/chardet/langhungarianmodel.py
diff options
context:
space:
mode:
Diffstat (limited to 'src/pip/_vendor/chardet/langhungarianmodel.py')
-rw-r--r--src/pip/_vendor/chardet/langhungarianmodel.py1061
1 files changed, 530 insertions, 531 deletions
diff --git a/src/pip/_vendor/chardet/langhungarianmodel.py b/src/pip/_vendor/chardet/langhungarianmodel.py
index bbc5cda64..09a0d326b 100644
--- a/src/pip/_vendor/chardet/langhungarianmodel.py
+++ b/src/pip/_vendor/chardet/langhungarianmodel.py
@@ -1,9 +1,5 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
from pip._vendor.chardet.sbcharsetprober import SingleByteCharSetModel
-
# 3: Positive
# 2: Likely
# 1: Unlikely
@@ -4115,536 +4111,539 @@ HUNGARIAN_LANG_MODEL = {
# Character Mapping Table(s):
WINDOWS_1250_HUNGARIAN_CHAR_TO_ORDER = {
- 0: 255, # '\x00'
- 1: 255, # '\x01'
- 2: 255, # '\x02'
- 3: 255, # '\x03'
- 4: 255, # '\x04'
- 5: 255, # '\x05'
- 6: 255, # '\x06'
- 7: 255, # '\x07'
- 8: 255, # '\x08'
- 9: 255, # '\t'
- 10: 254, # '\n'
- 11: 255, # '\x0b'
- 12: 255, # '\x0c'
- 13: 254, # '\r'
- 14: 255, # '\x0e'
- 15: 255, # '\x0f'
- 16: 255, # '\x10'
- 17: 255, # '\x11'
- 18: 255, # '\x12'
- 19: 255, # '\x13'
- 20: 255, # '\x14'
- 21: 255, # '\x15'
- 22: 255, # '\x16'
- 23: 255, # '\x17'
- 24: 255, # '\x18'
- 25: 255, # '\x19'
- 26: 255, # '\x1a'
- 27: 255, # '\x1b'
- 28: 255, # '\x1c'
- 29: 255, # '\x1d'
- 30: 255, # '\x1e'
- 31: 255, # '\x1f'
- 32: 253, # ' '
- 33: 253, # '!'
- 34: 253, # '"'
- 35: 253, # '#'
- 36: 253, # '$'
- 37: 253, # '%'
- 38: 253, # '&'
- 39: 253, # "'"
- 40: 253, # '('
- 41: 253, # ')'
- 42: 253, # '*'
- 43: 253, # '+'
- 44: 253, # ','
- 45: 253, # '-'
- 46: 253, # '.'
- 47: 253, # '/'
- 48: 252, # '0'
- 49: 252, # '1'
- 50: 252, # '2'
- 51: 252, # '3'
- 52: 252, # '4'
- 53: 252, # '5'
- 54: 252, # '6'
- 55: 252, # '7'
- 56: 252, # '8'
- 57: 252, # '9'
- 58: 253, # ':'
- 59: 253, # ';'
- 60: 253, # '<'
- 61: 253, # '='
- 62: 253, # '>'
- 63: 253, # '?'
- 64: 253, # '@'
- 65: 28, # 'A'
- 66: 40, # 'B'
- 67: 54, # 'C'
- 68: 45, # 'D'
- 69: 32, # 'E'
- 70: 50, # 'F'
- 71: 49, # 'G'
- 72: 38, # 'H'
- 73: 39, # 'I'
- 74: 53, # 'J'
- 75: 36, # 'K'
- 76: 41, # 'L'
- 77: 34, # 'M'
- 78: 35, # 'N'
- 79: 47, # 'O'
- 80: 46, # 'P'
- 81: 72, # 'Q'
- 82: 43, # 'R'
- 83: 33, # 'S'
- 84: 37, # 'T'
- 85: 57, # 'U'
- 86: 48, # 'V'
- 87: 64, # 'W'
- 88: 68, # 'X'
- 89: 55, # 'Y'
- 90: 52, # 'Z'
- 91: 253, # '['
- 92: 253, # '\\'
- 93: 253, # ']'
- 94: 253, # '^'
- 95: 253, # '_'
- 96: 253, # '`'
- 97: 2, # 'a'
- 98: 18, # 'b'
- 99: 26, # 'c'
- 100: 17, # 'd'
- 101: 1, # 'e'
- 102: 27, # 'f'
- 103: 12, # 'g'
- 104: 20, # 'h'
- 105: 9, # 'i'
- 106: 22, # 'j'
- 107: 7, # 'k'
- 108: 6, # 'l'
- 109: 13, # 'm'
- 110: 4, # 'n'
- 111: 8, # 'o'
- 112: 23, # 'p'
- 113: 67, # 'q'
- 114: 10, # 'r'
- 115: 5, # 's'
- 116: 3, # 't'
- 117: 21, # 'u'
- 118: 19, # 'v'
- 119: 65, # 'w'
- 120: 62, # 'x'
- 121: 16, # 'y'
- 122: 11, # 'z'
- 123: 253, # '{'
- 124: 253, # '|'
- 125: 253, # '}'
- 126: 253, # '~'
- 127: 253, # '\x7f'
- 128: 161, # '€'
- 129: 162, # None
- 130: 163, # '‚'
- 131: 164, # None
- 132: 165, # '„'
- 133: 166, # '…'
- 134: 167, # '†'
- 135: 168, # '‡'
- 136: 169, # None
- 137: 170, # '‰'
- 138: 171, # 'Š'
- 139: 172, # '‹'
- 140: 173, # 'Ś'
- 141: 174, # 'Ť'
- 142: 175, # 'Ž'
- 143: 176, # 'Ź'
- 144: 177, # None
- 145: 178, # '‘'
- 146: 179, # '’'
- 147: 180, # '“'
- 148: 78, # '”'
- 149: 181, # '•'
- 150: 69, # '–'
- 151: 182, # '—'
- 152: 183, # None
- 153: 184, # '™'
- 154: 185, # 'š'
- 155: 186, # '›'
- 156: 187, # 'ś'
- 157: 188, # 'ť'
- 158: 189, # 'ž'
- 159: 190, # 'ź'
- 160: 191, # '\xa0'
- 161: 192, # 'ˇ'
- 162: 193, # '˘'
- 163: 194, # 'Ł'
- 164: 195, # '¤'
- 165: 196, # 'Ą'
- 166: 197, # '¦'
- 167: 76, # '§'
- 168: 198, # '¨'
- 169: 199, # '©'
- 170: 200, # 'Ş'
- 171: 201, # '«'
- 172: 202, # '¬'
- 173: 203, # '\xad'
- 174: 204, # '®'
- 175: 205, # 'Ż'
- 176: 81, # '°'
- 177: 206, # '±'
- 178: 207, # '˛'
- 179: 208, # 'ł'
- 180: 209, # '´'
- 181: 210, # 'µ'
- 182: 211, # '¶'
- 183: 212, # '·'
- 184: 213, # '¸'
- 185: 214, # 'ą'
- 186: 215, # 'ş'
- 187: 216, # '»'
- 188: 217, # 'Ľ'
- 189: 218, # '˝'
- 190: 219, # 'ľ'
- 191: 220, # 'ż'
- 192: 221, # 'Ŕ'
- 193: 51, # 'Á'
- 194: 83, # 'Â'
- 195: 222, # 'Ă'
- 196: 80, # 'Ä'
- 197: 223, # 'Ĺ'
- 198: 224, # 'Ć'
- 199: 225, # 'Ç'
- 200: 226, # 'Č'
- 201: 44, # 'É'
- 202: 227, # 'Ę'
- 203: 228, # 'Ë'
- 204: 229, # 'Ě'
- 205: 61, # 'Í'
- 206: 230, # 'Î'
- 207: 231, # 'Ď'
- 208: 232, # 'Đ'
- 209: 233, # 'Ń'
- 210: 234, # 'Ň'
- 211: 58, # 'Ó'
- 212: 235, # 'Ô'
- 213: 66, # 'Ő'
- 214: 59, # 'Ö'
- 215: 236, # '×'
- 216: 237, # 'Ř'
- 217: 238, # 'Ů'
- 218: 60, # 'Ú'
- 219: 70, # 'Ű'
- 220: 63, # 'Ü'
- 221: 239, # 'Ý'
- 222: 240, # 'Ţ'
- 223: 241, # 'ß'
- 224: 84, # 'ŕ'
- 225: 14, # 'á'
- 226: 75, # 'â'
- 227: 242, # 'ă'
- 228: 71, # 'ä'
- 229: 82, # 'ĺ'
- 230: 243, # 'ć'
- 231: 73, # 'ç'
- 232: 244, # 'č'
- 233: 15, # 'é'
- 234: 85, # 'ę'
- 235: 79, # 'ë'
- 236: 86, # 'ě'
- 237: 30, # 'í'
- 238: 77, # 'î'
- 239: 87, # 'ď'
- 240: 245, # 'đ'
- 241: 246, # 'ń'
- 242: 247, # 'ň'
- 243: 25, # 'ó'
- 244: 74, # 'ô'
- 245: 42, # 'ő'
- 246: 24, # 'ö'
- 247: 248, # '÷'
- 248: 249, # 'ř'
- 249: 250, # 'ů'
- 250: 31, # 'ú'
- 251: 56, # 'ű'
- 252: 29, # 'ü'
- 253: 251, # 'ý'
- 254: 252, # 'ţ'
- 255: 253, # '˙'
+ 0: 255, # '\x00'
+ 1: 255, # '\x01'
+ 2: 255, # '\x02'
+ 3: 255, # '\x03'
+ 4: 255, # '\x04'
+ 5: 255, # '\x05'
+ 6: 255, # '\x06'
+ 7: 255, # '\x07'
+ 8: 255, # '\x08'
+ 9: 255, # '\t'
+ 10: 254, # '\n'
+ 11: 255, # '\x0b'
+ 12: 255, # '\x0c'
+ 13: 254, # '\r'
+ 14: 255, # '\x0e'
+ 15: 255, # '\x0f'
+ 16: 255, # '\x10'
+ 17: 255, # '\x11'
+ 18: 255, # '\x12'
+ 19: 255, # '\x13'
+ 20: 255, # '\x14'
+ 21: 255, # '\x15'
+ 22: 255, # '\x16'
+ 23: 255, # '\x17'
+ 24: 255, # '\x18'
+ 25: 255, # '\x19'
+ 26: 255, # '\x1a'
+ 27: 255, # '\x1b'
+ 28: 255, # '\x1c'
+ 29: 255, # '\x1d'
+ 30: 255, # '\x1e'
+ 31: 255, # '\x1f'
+ 32: 253, # ' '
+ 33: 253, # '!'
+ 34: 253, # '"'
+ 35: 253, # '#'
+ 36: 253, # '$'
+ 37: 253, # '%'
+ 38: 253, # '&'
+ 39: 253, # "'"
+ 40: 253, # '('
+ 41: 253, # ')'
+ 42: 253, # '*'
+ 43: 253, # '+'
+ 44: 253, # ','
+ 45: 253, # '-'
+ 46: 253, # '.'
+ 47: 253, # '/'
+ 48: 252, # '0'
+ 49: 252, # '1'
+ 50: 252, # '2'
+ 51: 252, # '3'
+ 52: 252, # '4'
+ 53: 252, # '5'
+ 54: 252, # '6'
+ 55: 252, # '7'
+ 56: 252, # '8'
+ 57: 252, # '9'
+ 58: 253, # ':'
+ 59: 253, # ';'
+ 60: 253, # '<'
+ 61: 253, # '='
+ 62: 253, # '>'
+ 63: 253, # '?'
+ 64: 253, # '@'
+ 65: 28, # 'A'
+ 66: 40, # 'B'
+ 67: 54, # 'C'
+ 68: 45, # 'D'
+ 69: 32, # 'E'
+ 70: 50, # 'F'
+ 71: 49, # 'G'
+ 72: 38, # 'H'
+ 73: 39, # 'I'
+ 74: 53, # 'J'
+ 75: 36, # 'K'
+ 76: 41, # 'L'
+ 77: 34, # 'M'
+ 78: 35, # 'N'
+ 79: 47, # 'O'
+ 80: 46, # 'P'
+ 81: 72, # 'Q'
+ 82: 43, # 'R'
+ 83: 33, # 'S'
+ 84: 37, # 'T'
+ 85: 57, # 'U'
+ 86: 48, # 'V'
+ 87: 64, # 'W'
+ 88: 68, # 'X'
+ 89: 55, # 'Y'
+ 90: 52, # 'Z'
+ 91: 253, # '['
+ 92: 253, # '\\'
+ 93: 253, # ']'
+ 94: 253, # '^'
+ 95: 253, # '_'
+ 96: 253, # '`'
+ 97: 2, # 'a'
+ 98: 18, # 'b'
+ 99: 26, # 'c'
+ 100: 17, # 'd'
+ 101: 1, # 'e'
+ 102: 27, # 'f'
+ 103: 12, # 'g'
+ 104: 20, # 'h'
+ 105: 9, # 'i'
+ 106: 22, # 'j'
+ 107: 7, # 'k'
+ 108: 6, # 'l'
+ 109: 13, # 'm'
+ 110: 4, # 'n'
+ 111: 8, # 'o'
+ 112: 23, # 'p'
+ 113: 67, # 'q'
+ 114: 10, # 'r'
+ 115: 5, # 's'
+ 116: 3, # 't'
+ 117: 21, # 'u'
+ 118: 19, # 'v'
+ 119: 65, # 'w'
+ 120: 62, # 'x'
+ 121: 16, # 'y'
+ 122: 11, # 'z'
+ 123: 253, # '{'
+ 124: 253, # '|'
+ 125: 253, # '}'
+ 126: 253, # '~'
+ 127: 253, # '\x7f'
+ 128: 161, # '€'
+ 129: 162, # None
+ 130: 163, # '‚'
+ 131: 164, # None
+ 132: 165, # '„'
+ 133: 166, # '…'
+ 134: 167, # '†'
+ 135: 168, # '‡'
+ 136: 169, # None
+ 137: 170, # '‰'
+ 138: 171, # 'Š'
+ 139: 172, # '‹'
+ 140: 173, # 'Ś'
+ 141: 174, # 'Ť'
+ 142: 175, # 'Ž'
+ 143: 176, # 'Ź'
+ 144: 177, # None
+ 145: 178, # '‘'
+ 146: 179, # '’'
+ 147: 180, # '“'
+ 148: 78, # '”'
+ 149: 181, # '•'
+ 150: 69, # '–'
+ 151: 182, # '—'
+ 152: 183, # None
+ 153: 184, # '™'
+ 154: 185, # 'š'
+ 155: 186, # '›'
+ 156: 187, # 'ś'
+ 157: 188, # 'ť'
+ 158: 189, # 'ž'
+ 159: 190, # 'ź'
+ 160: 191, # '\xa0'
+ 161: 192, # 'ˇ'
+ 162: 193, # '˘'
+ 163: 194, # 'Ł'
+ 164: 195, # '¤'
+ 165: 196, # 'Ą'
+ 166: 197, # '¦'
+ 167: 76, # '§'
+ 168: 198, # '¨'
+ 169: 199, # '©'
+ 170: 200, # 'Ş'
+ 171: 201, # '«'
+ 172: 202, # '¬'
+ 173: 203, # '\xad'
+ 174: 204, # '®'
+ 175: 205, # 'Ż'
+ 176: 81, # '°'
+ 177: 206, # '±'
+ 178: 207, # '˛'
+ 179: 208, # 'ł'
+ 180: 209, # '´'
+ 181: 210, # 'µ'
+ 182: 211, # '¶'
+ 183: 212, # '·'
+ 184: 213, # '¸'
+ 185: 214, # 'ą'
+ 186: 215, # 'ş'
+ 187: 216, # '»'
+ 188: 217, # 'Ľ'
+ 189: 218, # '˝'
+ 190: 219, # 'ľ'
+ 191: 220, # 'ż'
+ 192: 221, # 'Ŕ'
+ 193: 51, # 'Á'
+ 194: 83, # 'Â'
+ 195: 222, # 'Ă'
+ 196: 80, # 'Ä'
+ 197: 223, # 'Ĺ'
+ 198: 224, # 'Ć'
+ 199: 225, # 'Ç'
+ 200: 226, # 'Č'
+ 201: 44, # 'É'
+ 202: 227, # 'Ę'
+ 203: 228, # 'Ë'
+ 204: 229, # 'Ě'
+ 205: 61, # 'Í'
+ 206: 230, # 'Î'
+ 207: 231, # 'Ď'
+ 208: 232, # 'Đ'
+ 209: 233, # 'Ń'
+ 210: 234, # 'Ň'
+ 211: 58, # 'Ó'
+ 212: 235, # 'Ô'
+ 213: 66, # 'Ő'
+ 214: 59, # 'Ö'
+ 215: 236, # '×'
+ 216: 237, # 'Ř'
+ 217: 238, # 'Ů'
+ 218: 60, # 'Ú'
+ 219: 70, # 'Ű'
+ 220: 63, # 'Ü'
+ 221: 239, # 'Ý'
+ 222: 240, # 'Ţ'
+ 223: 241, # 'ß'
+ 224: 84, # 'ŕ'
+ 225: 14, # 'á'
+ 226: 75, # 'â'
+ 227: 242, # 'ă'
+ 228: 71, # 'ä'
+ 229: 82, # 'ĺ'
+ 230: 243, # 'ć'
+ 231: 73, # 'ç'
+ 232: 244, # 'č'
+ 233: 15, # 'é'
+ 234: 85, # 'ę'
+ 235: 79, # 'ë'
+ 236: 86, # 'ě'
+ 237: 30, # 'í'
+ 238: 77, # 'î'
+ 239: 87, # 'ď'
+ 240: 245, # 'đ'
+ 241: 246, # 'ń'
+ 242: 247, # 'ň'
+ 243: 25, # 'ó'
+ 244: 74, # 'ô'
+ 245: 42, # 'ő'
+ 246: 24, # 'ö'
+ 247: 248, # '÷'
+ 248: 249, # 'ř'
+ 249: 250, # 'ů'
+ 250: 31, # 'ú'
+ 251: 56, # 'ű'
+ 252: 29, # 'ü'
+ 253: 251, # 'ý'
+ 254: 252, # 'ţ'
+ 255: 253, # '˙'
}
-WINDOWS_1250_HUNGARIAN_MODEL = SingleByteCharSetModel(charset_name='windows-1250',
- language='Hungarian',
- char_to_order_map=WINDOWS_1250_HUNGARIAN_CHAR_TO_ORDER,
- language_model=HUNGARIAN_LANG_MODEL,
- typical_positive_ratio=0.947368,
- keep_ascii_letters=True,
- alphabet='ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű')
+WINDOWS_1250_HUNGARIAN_MODEL = SingleByteCharSetModel(
+ charset_name="windows-1250",
+ language="Hungarian",
+ char_to_order_map=WINDOWS_1250_HUNGARIAN_CHAR_TO_ORDER,
+ language_model=HUNGARIAN_LANG_MODEL,
+ typical_positive_ratio=0.947368,
+ keep_ascii_letters=True,
+ alphabet="ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű",
+)
ISO_8859_2_HUNGARIAN_CHAR_TO_ORDER = {
- 0: 255, # '\x00'
- 1: 255, # '\x01'
- 2: 255, # '\x02'
- 3: 255, # '\x03'
- 4: 255, # '\x04'
- 5: 255, # '\x05'
- 6: 255, # '\x06'
- 7: 255, # '\x07'
- 8: 255, # '\x08'
- 9: 255, # '\t'
- 10: 254, # '\n'
- 11: 255, # '\x0b'
- 12: 255, # '\x0c'
- 13: 254, # '\r'
- 14: 255, # '\x0e'
- 15: 255, # '\x0f'
- 16: 255, # '\x10'
- 17: 255, # '\x11'
- 18: 255, # '\x12'
- 19: 255, # '\x13'
- 20: 255, # '\x14'
- 21: 255, # '\x15'
- 22: 255, # '\x16'
- 23: 255, # '\x17'
- 24: 255, # '\x18'
- 25: 255, # '\x19'
- 26: 255, # '\x1a'
- 27: 255, # '\x1b'
- 28: 255, # '\x1c'
- 29: 255, # '\x1d'
- 30: 255, # '\x1e'
- 31: 255, # '\x1f'
- 32: 253, # ' '
- 33: 253, # '!'
- 34: 253, # '"'
- 35: 253, # '#'
- 36: 253, # '$'
- 37: 253, # '%'
- 38: 253, # '&'
- 39: 253, # "'"
- 40: 253, # '('
- 41: 253, # ')'
- 42: 253, # '*'
- 43: 253, # '+'
- 44: 253, # ','
- 45: 253, # '-'
- 46: 253, # '.'
- 47: 253, # '/'
- 48: 252, # '0'
- 49: 252, # '1'
- 50: 252, # '2'
- 51: 252, # '3'
- 52: 252, # '4'
- 53: 252, # '5'
- 54: 252, # '6'
- 55: 252, # '7'
- 56: 252, # '8'
- 57: 252, # '9'
- 58: 253, # ':'
- 59: 253, # ';'
- 60: 253, # '<'
- 61: 253, # '='
- 62: 253, # '>'
- 63: 253, # '?'
- 64: 253, # '@'
- 65: 28, # 'A'
- 66: 40, # 'B'
- 67: 54, # 'C'
- 68: 45, # 'D'
- 69: 32, # 'E'
- 70: 50, # 'F'
- 71: 49, # 'G'
- 72: 38, # 'H'
- 73: 39, # 'I'
- 74: 53, # 'J'
- 75: 36, # 'K'
- 76: 41, # 'L'
- 77: 34, # 'M'
- 78: 35, # 'N'
- 79: 47, # 'O'
- 80: 46, # 'P'
- 81: 71, # 'Q'
- 82: 43, # 'R'
- 83: 33, # 'S'
- 84: 37, # 'T'
- 85: 57, # 'U'
- 86: 48, # 'V'
- 87: 64, # 'W'
- 88: 68, # 'X'
- 89: 55, # 'Y'
- 90: 52, # 'Z'
- 91: 253, # '['
- 92: 253, # '\\'
- 93: 253, # ']'
- 94: 253, # '^'
- 95: 253, # '_'
- 96: 253, # '`'
- 97: 2, # 'a'
- 98: 18, # 'b'
- 99: 26, # 'c'
- 100: 17, # 'd'
- 101: 1, # 'e'
- 102: 27, # 'f'
- 103: 12, # 'g'
- 104: 20, # 'h'
- 105: 9, # 'i'
- 106: 22, # 'j'
- 107: 7, # 'k'
- 108: 6, # 'l'
- 109: 13, # 'm'
- 110: 4, # 'n'
- 111: 8, # 'o'
- 112: 23, # 'p'
- 113: 67, # 'q'
- 114: 10, # 'r'
- 115: 5, # 's'
- 116: 3, # 't'
- 117: 21, # 'u'
- 118: 19, # 'v'
- 119: 65, # 'w'
- 120: 62, # 'x'
- 121: 16, # 'y'
- 122: 11, # 'z'
- 123: 253, # '{'
- 124: 253, # '|'
- 125: 253, # '}'
- 126: 253, # '~'
- 127: 253, # '\x7f'
- 128: 159, # '\x80'
- 129: 160, # '\x81'
- 130: 161, # '\x82'
- 131: 162, # '\x83'
- 132: 163, # '\x84'
- 133: 164, # '\x85'
- 134: 165, # '\x86'
- 135: 166, # '\x87'
- 136: 167, # '\x88'
- 137: 168, # '\x89'
- 138: 169, # '\x8a'
- 139: 170, # '\x8b'
- 140: 171, # '\x8c'
- 141: 172, # '\x8d'
- 142: 173, # '\x8e'
- 143: 174, # '\x8f'
- 144: 175, # '\x90'
- 145: 176, # '\x91'
- 146: 177, # '\x92'
- 147: 178, # '\x93'
- 148: 179, # '\x94'
- 149: 180, # '\x95'
- 150: 181, # '\x96'
- 151: 182, # '\x97'
- 152: 183, # '\x98'
- 153: 184, # '\x99'
- 154: 185, # '\x9a'
- 155: 186, # '\x9b'
- 156: 187, # '\x9c'
- 157: 188, # '\x9d'
- 158: 189, # '\x9e'
- 159: 190, # '\x9f'
- 160: 191, # '\xa0'
- 161: 192, # 'Ą'
- 162: 193, # '˘'
- 163: 194, # 'Ł'
- 164: 195, # '¤'
- 165: 196, # 'Ľ'
- 166: 197, # 'Ś'
- 167: 75, # '§'
- 168: 198, # '¨'
- 169: 199, # 'Š'
- 170: 200, # 'Ş'
- 171: 201, # 'Ť'
- 172: 202, # 'Ź'
- 173: 203, # '\xad'
- 174: 204, # 'Ž'
- 175: 205, # 'Ż'
- 176: 79, # '°'
- 177: 206, # 'ą'
- 178: 207, # '˛'
- 179: 208, # 'ł'
- 180: 209, # '´'
- 181: 210, # 'ľ'
- 182: 211, # 'ś'
- 183: 212, # 'ˇ'
- 184: 213, # '¸'
- 185: 214, # 'š'
- 186: 215, # 'ş'
- 187: 216, # 'ť'
- 188: 217, # 'ź'
- 189: 218, # '˝'
- 190: 219, # 'ž'
- 191: 220, # 'ż'
- 192: 221, # 'Ŕ'
- 193: 51, # 'Á'
- 194: 81, # 'Â'
- 195: 222, # 'Ă'
- 196: 78, # 'Ä'
- 197: 223, # 'Ĺ'
- 198: 224, # 'Ć'
- 199: 225, # 'Ç'
- 200: 226, # 'Č'
- 201: 44, # 'É'
- 202: 227, # 'Ę'
- 203: 228, # 'Ë'
- 204: 229, # 'Ě'
- 205: 61, # 'Í'
- 206: 230, # 'Î'
- 207: 231, # 'Ď'
- 208: 232, # 'Đ'
- 209: 233, # 'Ń'
- 210: 234, # 'Ň'
- 211: 58, # 'Ó'
- 212: 235, # 'Ô'
- 213: 66, # 'Ő'
- 214: 59, # 'Ö'
- 215: 236, # '×'
- 216: 237, # 'Ř'
- 217: 238, # 'Ů'
- 218: 60, # 'Ú'
- 219: 69, # 'Ű'
- 220: 63, # 'Ü'
- 221: 239, # 'Ý'
- 222: 240, # 'Ţ'
- 223: 241, # 'ß'
- 224: 82, # 'ŕ'
- 225: 14, # 'á'
- 226: 74, # 'â'
- 227: 242, # 'ă'
- 228: 70, # 'ä'
- 229: 80, # 'ĺ'
- 230: 243, # 'ć'
- 231: 72, # 'ç'
- 232: 244, # 'č'
- 233: 15, # 'é'
- 234: 83, # 'ę'
- 235: 77, # 'ë'
- 236: 84, # 'ě'
- 237: 30, # 'í'
- 238: 76, # 'î'
- 239: 85, # 'ď'
- 240: 245, # 'đ'
- 241: 246, # 'ń'
- 242: 247, # 'ň'
- 243: 25, # 'ó'
- 244: 73, # 'ô'
- 245: 42, # 'ő'
- 246: 24, # 'ö'
- 247: 248, # '÷'
- 248: 249, # 'ř'
- 249: 250, # 'ů'
- 250: 31, # 'ú'
- 251: 56, # 'ű'
- 252: 29, # 'ü'
- 253: 251, # 'ý'
- 254: 252, # 'ţ'
- 255: 253, # '˙'
+ 0: 255, # '\x00'
+ 1: 255, # '\x01'
+ 2: 255, # '\x02'
+ 3: 255, # '\x03'
+ 4: 255, # '\x04'
+ 5: 255, # '\x05'
+ 6: 255, # '\x06'
+ 7: 255, # '\x07'
+ 8: 255, # '\x08'
+ 9: 255, # '\t'
+ 10: 254, # '\n'
+ 11: 255, # '\x0b'
+ 12: 255, # '\x0c'
+ 13: 254, # '\r'
+ 14: 255, # '\x0e'
+ 15: 255, # '\x0f'
+ 16: 255, # '\x10'
+ 17: 255, # '\x11'
+ 18: 255, # '\x12'
+ 19: 255, # '\x13'
+ 20: 255, # '\x14'
+ 21: 255, # '\x15'
+ 22: 255, # '\x16'
+ 23: 255, # '\x17'
+ 24: 255, # '\x18'
+ 25: 255, # '\x19'
+ 26: 255, # '\x1a'
+ 27: 255, # '\x1b'
+ 28: 255, # '\x1c'
+ 29: 255, # '\x1d'
+ 30: 255, # '\x1e'
+ 31: 255, # '\x1f'
+ 32: 253, # ' '
+ 33: 253, # '!'
+ 34: 253, # '"'
+ 35: 253, # '#'
+ 36: 253, # '$'
+ 37: 253, # '%'
+ 38: 253, # '&'
+ 39: 253, # "'"
+ 40: 253, # '('
+ 41: 253, # ')'
+ 42: 253, # '*'
+ 43: 253, # '+'
+ 44: 253, # ','
+ 45: 253, # '-'
+ 46: 253, # '.'
+ 47: 253, # '/'
+ 48: 252, # '0'
+ 49: 252, # '1'
+ 50: 252, # '2'
+ 51: 252, # '3'
+ 52: 252, # '4'
+ 53: 252, # '5'
+ 54: 252, # '6'
+ 55: 252, # '7'
+ 56: 252, # '8'
+ 57: 252, # '9'
+ 58: 253, # ':'
+ 59: 253, # ';'
+ 60: 253, # '<'
+ 61: 253, # '='
+ 62: 253, # '>'
+ 63: 253, # '?'
+ 64: 253, # '@'
+ 65: 28, # 'A'
+ 66: 40, # 'B'
+ 67: 54, # 'C'
+ 68: 45, # 'D'
+ 69: 32, # 'E'
+ 70: 50, # 'F'
+ 71: 49, # 'G'
+ 72: 38, # 'H'
+ 73: 39, # 'I'
+ 74: 53, # 'J'
+ 75: 36, # 'K'
+ 76: 41, # 'L'
+ 77: 34, # 'M'
+ 78: 35, # 'N'
+ 79: 47, # 'O'
+ 80: 46, # 'P'
+ 81: 71, # 'Q'
+ 82: 43, # 'R'
+ 83: 33, # 'S'
+ 84: 37, # 'T'
+ 85: 57, # 'U'
+ 86: 48, # 'V'
+ 87: 64, # 'W'
+ 88: 68, # 'X'
+ 89: 55, # 'Y'
+ 90: 52, # 'Z'
+ 91: 253, # '['
+ 92: 253, # '\\'
+ 93: 253, # ']'
+ 94: 253, # '^'
+ 95: 253, # '_'
+ 96: 253, # '`'
+ 97: 2, # 'a'
+ 98: 18, # 'b'
+ 99: 26, # 'c'
+ 100: 17, # 'd'
+ 101: 1, # 'e'
+ 102: 27, # 'f'
+ 103: 12, # 'g'
+ 104: 20, # 'h'
+ 105: 9, # 'i'
+ 106: 22, # 'j'
+ 107: 7, # 'k'
+ 108: 6, # 'l'
+ 109: 13, # 'm'
+ 110: 4, # 'n'
+ 111: 8, # 'o'
+ 112: 23, # 'p'
+ 113: 67, # 'q'
+ 114: 10, # 'r'
+ 115: 5, # 's'
+ 116: 3, # 't'
+ 117: 21, # 'u'
+ 118: 19, # 'v'
+ 119: 65, # 'w'
+ 120: 62, # 'x'
+ 121: 16, # 'y'
+ 122: 11, # 'z'
+ 123: 253, # '{'
+ 124: 253, # '|'
+ 125: 253, # '}'
+ 126: 253, # '~'
+ 127: 253, # '\x7f'
+ 128: 159, # '\x80'
+ 129: 160, # '\x81'
+ 130: 161, # '\x82'
+ 131: 162, # '\x83'
+ 132: 163, # '\x84'
+ 133: 164, # '\x85'
+ 134: 165, # '\x86'
+ 135: 166, # '\x87'
+ 136: 167, # '\x88'
+ 137: 168, # '\x89'
+ 138: 169, # '\x8a'
+ 139: 170, # '\x8b'
+ 140: 171, # '\x8c'
+ 141: 172, # '\x8d'
+ 142: 173, # '\x8e'
+ 143: 174, # '\x8f'
+ 144: 175, # '\x90'
+ 145: 176, # '\x91'
+ 146: 177, # '\x92'
+ 147: 178, # '\x93'
+ 148: 179, # '\x94'
+ 149: 180, # '\x95'
+ 150: 181, # '\x96'
+ 151: 182, # '\x97'
+ 152: 183, # '\x98'
+ 153: 184, # '\x99'
+ 154: 185, # '\x9a'
+ 155: 186, # '\x9b'
+ 156: 187, # '\x9c'
+ 157: 188, # '\x9d'
+ 158: 189, # '\x9e'
+ 159: 190, # '\x9f'
+ 160: 191, # '\xa0'
+ 161: 192, # 'Ą'
+ 162: 193, # '˘'
+ 163: 194, # 'Ł'
+ 164: 195, # '¤'
+ 165: 196, # 'Ľ'
+ 166: 197, # 'Ś'
+ 167: 75, # '§'
+ 168: 198, # '¨'
+ 169: 199, # 'Š'
+ 170: 200, # 'Ş'
+ 171: 201, # 'Ť'
+ 172: 202, # 'Ź'
+ 173: 203, # '\xad'
+ 174: 204, # 'Ž'
+ 175: 205, # 'Ż'
+ 176: 79, # '°'
+ 177: 206, # 'ą'
+ 178: 207, # '˛'
+ 179: 208, # 'ł'
+ 180: 209, # '´'
+ 181: 210, # 'ľ'
+ 182: 211, # 'ś'
+ 183: 212, # 'ˇ'
+ 184: 213, # '¸'
+ 185: 214, # 'š'
+ 186: 215, # 'ş'
+ 187: 216, # 'ť'
+ 188: 217, # 'ź'
+ 189: 218, # '˝'
+ 190: 219, # 'ž'
+ 191: 220, # 'ż'
+ 192: 221, # 'Ŕ'
+ 193: 51, # 'Á'
+ 194: 81, # 'Â'
+ 195: 222, # 'Ă'
+ 196: 78, # 'Ä'
+ 197: 223, # 'Ĺ'
+ 198: 224, # 'Ć'
+ 199: 225, # 'Ç'
+ 200: 226, # 'Č'
+ 201: 44, # 'É'
+ 202: 227, # 'Ę'
+ 203: 228, # 'Ë'
+ 204: 229, # 'Ě'
+ 205: 61, # 'Í'
+ 206: 230, # 'Î'
+ 207: 231, # 'Ď'
+ 208: 232, # 'Đ'
+ 209: 233, # 'Ń'
+ 210: 234, # 'Ň'
+ 211: 58, # 'Ó'
+ 212: 235, # 'Ô'
+ 213: 66, # 'Ő'
+ 214: 59, # 'Ö'
+ 215: 236, # '×'
+ 216: 237, # 'Ř'
+ 217: 238, # 'Ů'
+ 218: 60, # 'Ú'
+ 219: 69, # 'Ű'
+ 220: 63, # 'Ü'
+ 221: 239, # 'Ý'
+ 222: 240, # 'Ţ'
+ 223: 241, # 'ß'
+ 224: 82, # 'ŕ'
+ 225: 14, # 'á'
+ 226: 74, # 'â'
+ 227: 242, # 'ă'
+ 228: 70, # 'ä'
+ 229: 80, # 'ĺ'
+ 230: 243, # 'ć'
+ 231: 72, # 'ç'
+ 232: 244, # 'č'
+ 233: 15, # 'é'
+ 234: 83, # 'ę'
+ 235: 77, # 'ë'
+ 236: 84, # 'ě'
+ 237: 30, # 'í'
+ 238: 76, # 'î'
+ 239: 85, # 'ď'
+ 240: 245, # 'đ'
+ 241: 246, # 'ń'
+ 242: 247, # 'ň'
+ 243: 25, # 'ó'
+ 244: 73, # 'ô'
+ 245: 42, # 'ő'
+ 246: 24, # 'ö'
+ 247: 248, # '÷'
+ 248: 249, # 'ř'
+ 249: 250, # 'ů'
+ 250: 31, # 'ú'
+ 251: 56, # 'ű'
+ 252: 29, # 'ü'
+ 253: 251, # 'ý'
+ 254: 252, # 'ţ'
+ 255: 253, # '˙'
}
-ISO_8859_2_HUNGARIAN_MODEL = SingleByteCharSetModel(charset_name='ISO-8859-2',
- language='Hungarian',
- char_to_order_map=ISO_8859_2_HUNGARIAN_CHAR_TO_ORDER,
- language_model=HUNGARIAN_LANG_MODEL,
- typical_positive_ratio=0.947368,
- keep_ascii_letters=True,
- alphabet='ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű')
-
+ISO_8859_2_HUNGARIAN_MODEL = SingleByteCharSetModel(
+ charset_name="ISO-8859-2",
+ language="Hungarian",
+ char_to_order_map=ISO_8859_2_HUNGARIAN_CHAR_TO_ORDER,
+ language_model=HUNGARIAN_LANG_MODEL,
+ typical_positive_ratio=0.947368,
+ keep_ascii_letters=True,
+ alphabet="ABCDEFGHIJKLMNOPRSTUVZabcdefghijklmnoprstuvzÁÉÍÓÖÚÜáéíóöúüŐőŰű",
+)