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
|
|
|
|
18
|
|
|
declare(strict_types=1); |
19
|
|
|
|
20
|
|
|
namespace Fisharebest\Webtrees\Factories; |
21
|
|
|
|
22
|
|
|
use DomainException; |
23
|
|
|
use Fisharebest\Webtrees\Contracts\EncodingFactoryInterface; |
24
|
|
|
use Fisharebest\Webtrees\Encodings\ANSEL; |
25
|
|
|
use Fisharebest\Webtrees\Encodings\ASCII; |
26
|
|
|
use Fisharebest\Webtrees\Encodings\CP437; |
27
|
|
|
use Fisharebest\Webtrees\Encodings\CP850; |
28
|
|
|
use Fisharebest\Webtrees\Encodings\EncodingInterface; |
29
|
|
|
use Fisharebest\Webtrees\Encodings\ISO88591; |
30
|
|
|
use Fisharebest\Webtrees\Encodings\ISO88592; |
31
|
|
|
use Fisharebest\Webtrees\Encodings\MacRoman; |
32
|
|
|
use Fisharebest\Webtrees\Encodings\UTF16BE; |
33
|
|
|
use Fisharebest\Webtrees\Encodings\UTF16LE; |
34
|
|
|
use Fisharebest\Webtrees\Encodings\UTF8; |
35
|
|
|
use Fisharebest\Webtrees\Encodings\Windows1250; |
36
|
|
|
use Fisharebest\Webtrees\Encodings\Windows1251; |
37
|
|
|
use Fisharebest\Webtrees\Encodings\Windows1252; |
38
|
|
|
use Fisharebest\Webtrees\Exceptions\InvalidGedcomEncodingException; |
39
|
|
|
|
40
|
|
|
use function explode; |
41
|
|
|
use function ltrim; |
42
|
|
|
use function preg_match; |
43
|
|
|
use function str_contains; |
44
|
|
|
use function str_starts_with; |
45
|
|
|
use function strstr; |
46
|
|
|
|
47
|
|
|
/** |
48
|
|
|
* Create an encoding object. |
49
|
|
|
*/ |
50
|
|
|
class EncodingFactory implements EncodingFactoryInterface |
51
|
|
|
{ |
52
|
|
|
/** |
53
|
|
|
* Detect an encoding from a GEDCOM header record. |
54
|
|
|
* |
55
|
|
|
* @param string $header |
56
|
|
|
* |
57
|
|
|
* @return EncodingInterface|null |
58
|
|
|
* @throws InvalidGedcomEncodingException |
59
|
|
|
*/ |
60
|
|
|
public function detect(string $header): ?EncodingInterface |
61
|
|
|
{ |
62
|
|
|
$utf_bom = [ |
63
|
|
|
'/^' . UTF8::BYTE_ORDER_MARK . '/' => UTF8::NAME, |
64
|
|
|
'/^' . UTF16BE::BYTE_ORDER_MARK . '/' => UTF16BE::NAME, |
65
|
|
|
'/^' . UTF16LE::BYTE_ORDER_MARK . '/' => UTF16LE::NAME, |
66
|
|
|
]; |
67
|
|
|
|
68
|
|
|
foreach ($utf_bom as $regex => $encoding) { |
69
|
|
|
if (preg_match($regex, $header) === 1) { |
70
|
|
|
return $this->make($encoding); |
71
|
|
|
} |
72
|
|
|
} |
73
|
|
|
|
74
|
|
|
$utf16 = [ |
75
|
|
|
"\x000" => UTF16BE::NAME, |
76
|
|
|
"0\x00" => UTF16LE::NAME, |
77
|
|
|
]; |
78
|
|
|
|
79
|
|
|
foreach ($utf16 as $start => $encoding) { |
80
|
|
|
if (str_starts_with($header, $start)) { |
81
|
|
|
return $this->make($encoding); |
82
|
|
|
} |
83
|
|
|
} |
84
|
|
|
|
85
|
|
|
// Standardize whitespace to simplify matching. |
86
|
|
|
$header = strtr(ltrim($header), ["\r\n" => "\n", "\n\r" => "\n", "\r" => "\n"]); |
87
|
|
|
|
88
|
|
|
while (str_contains($header, "\n ") || str_contains($header, " \n") || str_contains($header, ' ')) { |
89
|
|
|
$header = strtr($header, ["\n " => "\n", " \n" => "\n", ' ' => ' ']); |
90
|
|
|
} |
91
|
|
|
|
92
|
|
|
// We need a complete header record |
93
|
|
|
$header = strstr($header, "\n0", true); |
94
|
|
|
|
95
|
|
|
if ($header === false) { |
96
|
|
|
return null; |
97
|
|
|
} |
98
|
|
|
|
99
|
|
|
// Some of these come from Tamura Jones, the rest from webtrees users. |
100
|
|
|
$character_sets = [ |
101
|
|
|
'ASCII' => ASCII::NAME, |
102
|
|
|
'ANSEL' => ANSEL::NAME, |
103
|
|
|
'UTF-8' => UTF8::NAME, |
104
|
|
|
'UNICODE' => UTF8::NAME, // If the null byte test failed, this can't be UTF16 |
105
|
|
|
'ASCII/MacOS Roman' => MacRoman::NAME, // GEDitCOM |
106
|
|
|
'ASCII/MACINTOSH' => MacRoman::NAME, // MacFamilyTree < 8.3.5 |
107
|
|
|
'MACINTOSH' => MacRoman::NAME, // MacFamilyTree >= 8.3.5 |
108
|
|
|
'CP437' => CP437::NAME, |
109
|
|
|
'IBMPC' => CP437::NAME, |
110
|
|
|
'IBM' => CP437::NAME, // Reunion |
111
|
|
|
'IBM-PC' => CP437::NAME, // CumberlandFamilyTree |
112
|
|
|
'OEM' => CP437::NAME, // Généatique |
113
|
|
|
'CP850' => CP850::NAME, |
114
|
|
|
'MSDOS' => CP850::NAME, |
115
|
|
|
'IBM-DOS' => CP850::NAME, // Reunion, EasyTree |
116
|
|
|
'MS-DOS' => CP850::NAME, // AbrEdit FTM for Windows |
117
|
|
|
'ANSI' => CP850::NAME, |
118
|
|
|
'WINDOWS' => CP850::NAME, // Parentele |
119
|
|
|
'IBM WINDOWS' => CP850::NAME, // EasyTree, Généalogie, Reunion, TribalPages |
120
|
|
|
'IBM_WINDOWS' => CP850::NAME, // EasyTree |
121
|
|
|
'CP1250' => Windows1250::NAME, |
122
|
|
|
'windows-1250' => Windows1250::NAME, // GenoPro, Rodokmen Pro |
123
|
|
|
'CP1251' => Windows1251::NAME, |
124
|
|
|
'WINDOWS-1251' => Windows1251::NAME, // Rodovid |
125
|
|
|
'CP1252' => Windows1252::NAME, // Lifelines |
126
|
|
|
'ISO-8859-1' => ISO88591::NAME, // Cumberland Family Tree, Lifelines |
127
|
|
|
'ISO8859-1' => ISO88591::NAME, // Scion Genealogist |
128
|
|
|
'ISO8859' => ISO88591::NAME, // Genealogica Grafica |
129
|
|
|
'LATIN-1' => ISO88591::NAME, |
130
|
|
|
'LATIN1' => ISO88591::NAME, // GenealogyJ |
131
|
|
|
'ISO-8859-2' => ISO88592::NAME, |
132
|
|
|
'ISO8859-2' => ISO88592::NAME, |
133
|
|
|
'LATIN-2' => ISO88592::NAME, |
134
|
|
|
'LATIN2' => ISO88592::NAME, |
135
|
|
|
]; |
136
|
|
|
|
137
|
|
|
foreach ($character_sets as $pattern => $encoding) { |
138
|
|
|
if (str_contains($pattern, '/')) { |
139
|
|
|
[$char, $vers] = explode('/', $pattern); |
140
|
|
|
$regex = "\n1 CHAR " . $char . "\n2 VERS " . $vers; |
141
|
|
|
} else { |
142
|
|
|
$regex = "\n1 CHAR(?:ACTER)? " . $pattern; |
143
|
|
|
} |
144
|
|
|
|
145
|
|
|
if (preg_match("/" . $regex . "/i", $header) === 1) { |
146
|
|
|
return $this->make($encoding); |
147
|
|
|
} |
148
|
|
|
} |
149
|
|
|
|
150
|
|
|
if (preg_match('/1 CHAR (.+)/', $header, $match) === 1) { |
151
|
|
|
$charset = $match[1]; |
152
|
|
|
} else { |
153
|
|
|
$charset = '???'; |
154
|
|
|
} |
155
|
|
|
|
156
|
|
|
throw new InvalidGedcomEncodingException($charset); |
157
|
|
|
} |
158
|
|
|
|
159
|
|
|
/** |
160
|
|
|
* Create a named encoding. |
161
|
|
|
* |
162
|
|
|
* @param string $name |
163
|
|
|
* |
164
|
|
|
* @return EncodingInterface |
165
|
|
|
* @thorws DomainException |
166
|
|
|
*/ |
167
|
|
|
public function make(string $name): EncodingInterface |
168
|
|
|
{ |
169
|
|
|
switch ($name) { |
170
|
|
|
case UTF8::NAME: |
171
|
|
|
return new UTF8(); |
172
|
|
|
|
173
|
|
|
case UTF16BE::NAME: |
174
|
|
|
return new UTF16BE(); |
175
|
|
|
|
176
|
|
|
case UTF16LE::NAME: |
177
|
|
|
return new UTF16LE(); |
178
|
|
|
|
179
|
|
|
case ANSEL::NAME: |
180
|
|
|
return new ANSEL(); |
181
|
|
|
|
182
|
|
|
case ASCII::NAME: |
183
|
|
|
return new ASCII(); |
184
|
|
|
|
185
|
|
|
case CP437::NAME: |
186
|
|
|
return new CP437(); |
187
|
|
|
|
188
|
|
|
case CP850::NAME: |
189
|
|
|
return new CP850(); |
190
|
|
|
|
191
|
|
|
case Windows1250::NAME: |
192
|
|
|
return new Windows1250(); |
193
|
|
|
|
194
|
|
|
case Windows1251::NAME: |
195
|
|
|
return new Windows1251(); |
196
|
|
|
|
197
|
|
|
case Windows1252::NAME: |
198
|
|
|
return new Windows1252(); |
199
|
|
|
|
200
|
|
|
case MacRoman::NAME: |
201
|
|
|
return new MacRoman(); |
202
|
|
|
|
203
|
|
|
case ISO88591::NAME: |
204
|
|
|
return new ISO88591(); |
205
|
|
|
|
206
|
|
|
case ISO88592::NAME: |
207
|
|
|
return new ISO88592(); |
208
|
|
|
|
209
|
|
|
default: |
210
|
|
|
throw new DomainException('Invalid encoding: ' . $name); |
211
|
|
|
} |
212
|
|
|
} |
213
|
|
|
|
214
|
|
|
/** |
215
|
|
|
* A list of supported encodings and their names. |
216
|
|
|
* |
217
|
|
|
* @return array<string,string> |
218
|
|
|
*/ |
219
|
|
|
public function list(): array |
220
|
|
|
{ |
221
|
|
|
return [ |
222
|
|
|
UTF8::NAME => 'UTF-8', |
223
|
|
|
UTF16BE::NAME => 'UTF-16BE', |
224
|
|
|
UTF16LE::NAME => 'UTF-16LE', |
225
|
|
|
ANSEL::NAME => 'ANSEL', |
226
|
|
|
ASCII::NAME => 'ASCII', |
227
|
|
|
ISO88591::NAME => 'ISO-8859-1', |
228
|
|
|
ISO88592::NAME => 'ISO-8859-2', |
229
|
|
|
Windows1250::NAME => 'Windows 1250', |
230
|
|
|
Windows1251::NAME => 'Windows 1251', |
231
|
|
|
Windows1252::NAME => 'Windows 1252', |
232
|
|
|
CP437::NAME => 'CP437', |
233
|
|
|
CP850::NAME => 'CP850', |
234
|
|
|
MacRoman::NAME => 'MacOS Roman', |
235
|
|
|
]; |
236
|
|
|
} |
237
|
|
|
} |
238
|
|
|
|