xref: /webtrees/app/Factories/EncodingFactory.php (revision 18fd0859d876caec952296f28638ed0844e10712)
1<?php
2
3/**
4 * webtrees: online genealogy
5 * Copyright (C) 2023 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\Factories;
21
22use DomainException;
23use Fisharebest\Webtrees\Contracts\EncodingFactoryInterface;
24use Fisharebest\Webtrees\Encodings\ANSEL;
25use Fisharebest\Webtrees\Encodings\ASCII;
26use Fisharebest\Webtrees\Encodings\CP437;
27use Fisharebest\Webtrees\Encodings\CP850;
28use Fisharebest\Webtrees\Encodings\EncodingInterface;
29use Fisharebest\Webtrees\Encodings\ISO88591;
30use Fisharebest\Webtrees\Encodings\ISO88592;
31use Fisharebest\Webtrees\Encodings\MacRoman;
32use Fisharebest\Webtrees\Encodings\UTF16BE;
33use Fisharebest\Webtrees\Encodings\UTF16LE;
34use Fisharebest\Webtrees\Encodings\UTF8;
35use Fisharebest\Webtrees\Encodings\Windows1250;
36use Fisharebest\Webtrees\Encodings\Windows1251;
37use Fisharebest\Webtrees\Encodings\Windows1252;
38use Fisharebest\Webtrees\Exceptions\InvalidGedcomEncodingException;
39
40use function explode;
41use function ltrim;
42use function preg_match;
43use function str_contains;
44use function str_starts_with;
45use function strstr;
46
47/**
48 * Create an encoding object.
49 */
50class EncodingFactory implements EncodingFactoryInterface
51{
52    /**
53     * Detect an encoding from a GEDCOM header record.
54     *
55     * @throws InvalidGedcomEncodingException
56     */
57    public function detect(string $header): EncodingInterface|null
58    {
59        $utf_bom = [
60            '/^' . UTF8::BYTE_ORDER_MARK . '/'    => UTF8::NAME,
61            '/^' . UTF16BE::BYTE_ORDER_MARK . '/' => UTF16BE::NAME,
62            '/^' . UTF16LE::BYTE_ORDER_MARK . '/' => UTF16LE::NAME,
63        ];
64
65        foreach ($utf_bom as $regex => $encoding) {
66            if (preg_match($regex, $header) === 1) {
67                return $this->make($encoding);
68            }
69        }
70
71        $utf16 = [
72            "\x000" => UTF16BE::NAME,
73            "0\x00" => UTF16LE::NAME,
74        ];
75
76        foreach ($utf16 as $start => $encoding) {
77            if (str_starts_with($header, $start)) {
78                return $this->make($encoding);
79            }
80        }
81
82        // Standardize whitespace to simplify matching.
83        $header = strtr(ltrim($header), ["\r\n" => "\n", "\n\r" => "\n", "\r" => "\n"]);
84
85        while (str_contains($header, "\n ") || str_contains($header, " \n") || str_contains($header, '  ')) {
86            $header = strtr($header, ["\n " => "\n", " \n" => "\n", '  ' => ' ']);
87        }
88
89        // We need a complete header record
90        $header = strstr($header, "\n0", true);
91
92        if ($header === false) {
93            return null;
94        }
95
96        // Some of these come from Tamura Jones, the rest from webtrees users.
97        $character_sets = [
98            'ASCII'             => ASCII::NAME,
99            'ANSEL'             => ANSEL::NAME,
100            'UTF-8'             => UTF8::NAME,
101            'UNICODE'           => UTF8::NAME, // If the null byte test failed, this can't be UTF16
102            'ASCII/MacOS Roman' => MacRoman::NAME, // GEDitCOM
103            'ASCII/MACINTOSH'   => MacRoman::NAME, // MacFamilyTree < 8.3.5
104            'MACINTOSH'         => MacRoman::NAME, // MacFamilyTree >= 8.3.5
105            'CP437'             => CP437::NAME,
106            'IBMPC'             => CP437::NAME,
107            'IBM'               => CP437::NAME, // Reunion
108            'IBM-PC'            => CP437::NAME, // CumberlandFamilyTree
109            'OEM'               => CP437::NAME, // Généatique
110            'CP850'             => CP850::NAME,
111            'MSDOS'             => CP850::NAME,
112            'IBM-DOS'           => CP850::NAME, // Reunion, EasyTree
113            'MS-DOS'            => CP850::NAME, // AbrEdit FTM for Windows
114            'ANSI'              => CP850::NAME,
115            'WINDOWS'           => CP850::NAME, // Parentele
116            'IBM WINDOWS'       => CP850::NAME, // EasyTree, Généalogie, Reunion, TribalPages
117            'IBM_WINDOWS'       => CP850::NAME, // EasyTree
118            'CP1250'            => Windows1250::NAME,
119            'windows-1250'      => Windows1250::NAME, // GenoPro, Rodokmen Pro
120            'CP1251'            => Windows1251::NAME,
121            'WINDOWS-1251'      => Windows1251::NAME, // Rodovid
122            'CP1252'            => Windows1252::NAME, // Lifelines
123            'ISO-8859-1'        => ISO88591::NAME, // Cumberland Family Tree, Lifelines
124            'ISO8859-1'         => ISO88591::NAME, // Scion Genealogist
125            'ISO8859'           => ISO88591::NAME, // Genealogica Grafica
126            'LATIN-1'           => ISO88591::NAME,
127            'LATIN1'            => ISO88591::NAME, // GenealogyJ
128            'ISO-8859-2'        => ISO88592::NAME,
129            'ISO8859-2'         => ISO88592::NAME,
130            'LATIN-2'           => ISO88592::NAME,
131            'LATIN2'            => ISO88592::NAME,
132        ];
133
134        foreach ($character_sets as $pattern => $encoding) {
135            if (str_contains($pattern, '/')) {
136                [$char, $vers] = explode('/', $pattern);
137                $regex = "\n1 CHAR " . $char . "\n2 VERS " . $vers;
138            } else {
139                $regex = "\n1 CHAR(?:ACTER)? " . $pattern;
140            }
141
142            if (preg_match('/' . $regex . '/i', $header) === 1) {
143                return $this->make($encoding);
144            }
145        }
146
147        if (preg_match('/1 CHAR (.+)/', $header, $match) === 1) {
148            throw new InvalidGedcomEncodingException($match[1]);
149        }
150
151        return $this->make(UTF8::NAME);
152    }
153
154    /**
155     * Create a named encoding.
156     *
157     * @param string $name
158     *
159     * @return EncodingInterface
160     * @throws DomainException
161     */
162    public function make(string $name): EncodingInterface
163    {
164        switch ($name) {
165            case UTF8::NAME:
166                return new UTF8();
167
168            case UTF16BE::NAME:
169                return new UTF16BE();
170
171            case UTF16LE::NAME:
172                return new UTF16LE();
173
174            case ANSEL::NAME:
175                return new ANSEL();
176
177            case ASCII::NAME:
178                return new ASCII();
179
180            case CP437::NAME:
181                return new CP437();
182
183            case CP850::NAME:
184                return new CP850();
185
186            case Windows1250::NAME:
187                return new Windows1250();
188
189            case Windows1251::NAME:
190                return new Windows1251();
191
192            case Windows1252::NAME:
193                return new Windows1252();
194
195            case MacRoman::NAME:
196                return new MacRoman();
197
198            case ISO88591::NAME:
199                return new ISO88591();
200
201            case ISO88592::NAME:
202                return new ISO88592();
203
204            default:
205                throw new DomainException('Invalid encoding: ' . $name);
206        }
207    }
208
209    /**
210     * A list of supported encodings and their names.
211     *
212     * @return array<string,string>
213     */
214    public function list(): array
215    {
216        return [
217            UTF8::NAME        => 'UTF-8',
218            UTF16BE::NAME     => 'UTF-16BE',
219            UTF16LE::NAME     => 'UTF-16LE',
220            ANSEL::NAME       => 'ANSEL',
221            ASCII::NAME       => 'ASCII',
222            ISO88591::NAME    => 'ISO-8859-1',
223            ISO88592::NAME    => 'ISO-8859-2',
224            Windows1250::NAME => 'Windows 1250',
225            Windows1251::NAME => 'Windows 1251',
226            Windows1252::NAME => 'Windows 1252',
227            CP437::NAME       => 'CP437',
228            CP850::NAME       => 'CP850',
229            MacRoman::NAME    => 'MacOS Roman',
230        ];
231    }
232}
233