xref: /webtrees/app/Encodings/Windows1252.php (revision f3ee9488f9ef10a7691b4e6efa7708170e4de3a6)
1<?php
2
3/**
4 * webtrees: online genealogy
5 * Copyright (C) 2021 webtrees development team
6 * This program is free software: you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation, either version 3 of the License, or
9 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
14 * You should have received a copy of the GNU General Public License
15 * along with this program. If not, see <https://www.gnu.org/licenses/>.
16 */
17
18declare(strict_types=1);
19
20namespace Fisharebest\Webtrees\Encodings;
21
22/**
23 * Convert between Windows Code Page 1252 and UTF-8.
24 *
25 * @link https://en.wikipedia.org/wiki/Windows-1252
26 */
27class Windows1252 extends AbstractEncoding
28{
29    public const NAME = 'CP1252';
30
31    protected const TO_UTF8 = [
32        "\x80" => UTF8::EURO_SIGN,
33        "\x81" => UTF8::REPLACEMENT_CHARACTER,
34        "\x82" => UTF8::SINGLE_LOW_9_QUOTATION_MARK,
35        "\x83" => UTF8::LATIN_SMALL_LETTER_F_WITH_HOOK,
36        "\x84" => UTF8::DOUBLE_LOW_9_QUOTATION_MARK,
37        "\x85" => UTF8::HORIZONTAL_ELLIPSIS,
38        "\x86" => UTF8::DAGGER,
39        "\x87" => UTF8::DOUBLE_DAGGER,
40        "\x88" => UTF8::MODIFIER_LETTER_CIRCUMFLEX_ACCENT,
41        "\x89" => UTF8::PER_MILLE_SIGN,
42        "\x8A" => UTF8::LATIN_CAPITAL_LETTER_S_WITH_CARON,
43        "\x8B" => UTF8::SINGLE_LEFT_POINTING_ANGLE_QUOTATION_MARK,
44        "\x8C" => UTF8::LATIN_CAPITAL_LIGATURE_OE,
45        "\x8D" => UTF8::REPLACEMENT_CHARACTER,
46        "\x8E" => UTF8::LATIN_CAPITAL_LETTER_Z_WITH_CARON,
47        "\x8F" => UTF8::REPLACEMENT_CHARACTER,
48        "\x90" => UTF8::REPLACEMENT_CHARACTER,
49        "\x91" => UTF8::LEFT_SINGLE_QUOTATION_MARK,
50        "\x92" => UTF8::RIGHT_SINGLE_QUOTATION_MARK,
51        "\x93" => UTF8::LEFT_DOUBLE_QUOTATION_MARK,
52        "\x94" => UTF8::RIGHT_DOUBLE_QUOTATION_MARK,
53        "\x95" => UTF8::BULLET,
54        "\x96" => UTF8::EN_DASH,
55        "\x97" => UTF8::EM_DASH,
56        "\x98" => UTF8::SMALL_TILDE,
57        "\x99" => UTF8::TRADE_MARK_SIGN,
58        "\x9A" => UTF8::LATIN_SMALL_LETTER_S_WITH_CARON,
59        "\x9B" => UTF8::SINGLE_RIGHT_POINTING_ANGLE_QUOTATION_MARK,
60        "\x9C" => UTF8::LATIN_SMALL_LIGATURE_OE,
61        "\x9D" => UTF8::REPLACEMENT_CHARACTER,
62        "\x9E" => UTF8::LATIN_SMALL_LETTER_Z_WITH_CARON,
63        "\x9F" => UTF8::LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS,
64        "\xA0" => UTF8::NO_BREAK_SPACE,
65        "\xA1" => UTF8::INVERTED_EXCLAMATION_MARK,
66        "\xA2" => UTF8::CENT_SIGN,
67        "\xA3" => UTF8::POUND_SIGN,
68        "\xA4" => UTF8::CURRENCY_SIGN,
69        "\xA5" => UTF8::YEN_SIGN,
70        "\xA6" => UTF8::BROKEN_BAR,
71        "\xA7" => UTF8::SECTION_SIGN,
72        "\xA8" => UTF8::DIAERESIS,
73        "\xA9" => UTF8::COPYRIGHT_SIGN,
74        "\xAA" => UTF8::FEMININE_ORDINAL_INDICATOR,
75        "\xAB" => UTF8::LEFT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK,
76        "\xAC" => UTF8::NOT_SIGN,
77        "\xAD" => UTF8::SOFT_HYPHEN,
78        "\xAE" => UTF8::REGISTERED_SIGN,
79        "\xAF" => UTF8::MACRON,
80        "\xB0" => UTF8::DEGREE_SIGN,
81        "\xB1" => UTF8::PLUS_MINUS_SIGN,
82        "\xB2" => UTF8::SUPERSCRIPT_TWO,
83        "\xB3" => UTF8::SUPERSCRIPT_THREE,
84        "\xB4" => UTF8::ACUTE_ACCENT,
85        "\xB5" => UTF8::MICRO_SIGN,
86        "\xB6" => UTF8::PILCROW_SIGN,
87        "\xB7" => UTF8::MIDDLE_DOT,
88        "\xB8" => UTF8::CEDILLA,
89        "\xB9" => UTF8::SUPERSCRIPT_ONE,
90        "\xBA" => UTF8::MASCULINE_ORDINAL_INDICATOR,
91        "\xBB" => UTF8::RIGHT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK,
92        "\xBC" => UTF8::VULGAR_FRACTION_ONE_QUARTER,
93        "\xBD" => UTF8::VULGAR_FRACTION_ONE_HALF,
94        "\xBE" => UTF8::VULGAR_FRACTION_THREE_QUARTERS,
95        "\xBF" => UTF8::INVERTED_QUESTION_MARK,
96        "\xC0" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_GRAVE,
97        "\xC1" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_ACUTE,
98        "\xC2" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_CIRCUMFLEX,
99        "\xC3" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_TILDE,
100        "\xC4" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_DIAERESIS,
101        "\xC5" => UTF8::LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE,
102        "\xC6" => UTF8::LATIN_CAPITAL_LETTER_AE,
103        "\xC7" => UTF8::LATIN_CAPITAL_LETTER_C_WITH_CEDILLA,
104        "\xC8" => UTF8::LATIN_CAPITAL_LETTER_E_WITH_GRAVE,
105        "\xC9" => UTF8::LATIN_CAPITAL_LETTER_E_WITH_ACUTE,
106        "\xCA" => UTF8::LATIN_CAPITAL_LETTER_E_WITH_CIRCUMFLEX,
107        "\xCB" => UTF8::LATIN_CAPITAL_LETTER_E_WITH_DIAERESIS,
108        "\xCC" => UTF8::LATIN_CAPITAL_LETTER_I_WITH_GRAVE,
109        "\xCD" => UTF8::LATIN_CAPITAL_LETTER_I_WITH_ACUTE,
110        "\xCE" => UTF8::LATIN_CAPITAL_LETTER_I_WITH_CIRCUMFLEX,
111        "\xCF" => UTF8::LATIN_CAPITAL_LETTER_I_WITH_DIAERESIS,
112        "\xD0" => UTF8::LATIN_CAPITAL_LETTER_ETH,
113        "\xD1" => UTF8::LATIN_CAPITAL_LETTER_N_WITH_TILDE,
114        "\xD2" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_GRAVE,
115        "\xD3" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_ACUTE,
116        "\xD4" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_CIRCUMFLEX,
117        "\xD5" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_TILDE,
118        "\xD6" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_DIAERESIS,
119        "\xD7" => UTF8::MULTIPLICATION_SIGN,
120        "\xD8" => UTF8::LATIN_CAPITAL_LETTER_O_WITH_STROKE,
121        "\xD9" => UTF8::LATIN_CAPITAL_LETTER_U_WITH_GRAVE,
122        "\xDA" => UTF8::LATIN_CAPITAL_LETTER_U_WITH_ACUTE,
123        "\xDB" => UTF8::LATIN_CAPITAL_LETTER_U_WITH_CIRCUMFLEX,
124        "\xDC" => UTF8::LATIN_CAPITAL_LETTER_U_WITH_DIAERESIS,
125        "\xDD" => UTF8::LATIN_CAPITAL_LETTER_Y_WITH_ACUTE,
126        "\xDE" => UTF8::LATIN_CAPITAL_LETTER_THORN,
127        "\xDF" => UTF8::LATIN_SMALL_LETTER_SHARP_S,
128        "\xE0" => UTF8::LATIN_SMALL_LETTER_A_WITH_GRAVE,
129        "\xE1" => UTF8::LATIN_SMALL_LETTER_A_WITH_ACUTE,
130        "\xE2" => UTF8::LATIN_SMALL_LETTER_A_WITH_CIRCUMFLEX,
131        "\xE3" => UTF8::LATIN_SMALL_LETTER_A_WITH_TILDE,
132        "\xE4" => UTF8::LATIN_SMALL_LETTER_A_WITH_DIAERESIS,
133        "\xE5" => UTF8::LATIN_SMALL_LETTER_A_WITH_RING_ABOVE,
134        "\xE6" => UTF8::LATIN_SMALL_LETTER_AE,
135        "\xE7" => UTF8::LATIN_SMALL_LETTER_C_WITH_CEDILLA,
136        "\xE8" => UTF8::LATIN_SMALL_LETTER_E_WITH_GRAVE,
137        "\xE9" => UTF8::LATIN_SMALL_LETTER_E_WITH_ACUTE,
138        "\xEA" => UTF8::LATIN_SMALL_LETTER_E_WITH_CIRCUMFLEX,
139        "\xEB" => UTF8::LATIN_SMALL_LETTER_E_WITH_DIAERESIS,
140        "\xEC" => UTF8::LATIN_SMALL_LETTER_I_WITH_GRAVE,
141        "\xED" => UTF8::LATIN_SMALL_LETTER_I_WITH_ACUTE,
142        "\xEE" => UTF8::LATIN_SMALL_LETTER_I_WITH_CIRCUMFLEX,
143        "\xEF" => UTF8::LATIN_SMALL_LETTER_I_WITH_DIAERESIS,
144        "\xF0" => UTF8::LATIN_SMALL_LETTER_ETH,
145        "\xF1" => UTF8::LATIN_SMALL_LETTER_N_WITH_TILDE,
146        "\xF2" => UTF8::LATIN_SMALL_LETTER_O_WITH_GRAVE,
147        "\xF3" => UTF8::LATIN_SMALL_LETTER_O_WITH_ACUTE,
148        "\xF4" => UTF8::LATIN_SMALL_LETTER_O_WITH_CIRCUMFLEX,
149        "\xF5" => UTF8::LATIN_SMALL_LETTER_O_WITH_TILDE,
150        "\xF6" => UTF8::LATIN_SMALL_LETTER_O_WITH_DIAERESIS,
151        "\xF7" => UTF8::DIVISION_SIGN,
152        "\xF8" => UTF8::LATIN_SMALL_LETTER_O_WITH_STROKE,
153        "\xF9" => UTF8::LATIN_SMALL_LETTER_U_WITH_GRAVE,
154        "\xFA" => UTF8::LATIN_SMALL_LETTER_U_WITH_ACUTE,
155        "\xFB" => UTF8::LATIN_SMALL_LETTER_U_WITH_CIRCUMFLEX,
156        "\xFC" => UTF8::LATIN_SMALL_LETTER_U_WITH_DIAERESIS,
157        "\xFD" => UTF8::LATIN_SMALL_LETTER_Y_WITH_ACUTE,
158        "\xFE" => UTF8::LATIN_SMALL_LETTER_THORN,
159        "\xFF" => UTF8::LATIN_SMALL_LETTER_Y_WITH_DIAERESIS,
160    ];
161}
162