|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* This file is part of dispositif/wikibot application (@github) |
|
4
|
|
|
* 2019/2020 © Philippe M. <[email protected]> |
|
5
|
|
|
* For the full copyright and MIT license information, please view the license file. |
|
6
|
|
|
*/ |
|
7
|
|
|
|
|
8
|
|
|
declare(strict_types=1); |
|
9
|
|
|
|
|
10
|
|
|
|
|
11
|
|
|
namespace App\Domain\Publisher; |
|
12
|
|
|
|
|
13
|
|
|
use App\Domain\Enums\Language; |
|
14
|
|
|
use DateTime; |
|
15
|
|
|
use Exception; |
|
16
|
|
|
|
|
17
|
|
|
trait ExternConverterTrait |
|
18
|
|
|
{ |
|
19
|
|
|
protected function isAnArticle(?string $str): bool |
|
20
|
|
|
{ |
|
21
|
|
|
if (in_array($str, ['article', 'journalArticle'])) { |
|
22
|
|
|
return true; |
|
23
|
|
|
} |
|
24
|
|
|
|
|
25
|
|
|
return false; |
|
26
|
|
|
} |
|
27
|
|
|
|
|
28
|
|
|
protected function convertURLaccess($data): ?string |
|
29
|
|
|
{ |
|
30
|
|
|
// NYT, Figaro |
|
31
|
|
|
if (isset($data['isAccessibleForFree'])) { |
|
32
|
|
|
return $data['isAccessibleForFree'] ? 'ouvert' : 'limité'; |
|
33
|
|
|
} |
|
34
|
|
|
if (isset($data['DC.rights'])) { |
|
35
|
|
|
return (in_array($data['DC.rights'], ['free', 'public domain'])) ? 'ouvert' : 'limité'; |
|
36
|
|
|
} |
|
37
|
|
|
if (isset($data['og:article:content_tier'])) { |
|
38
|
|
|
return ($data['og:article:content_tier'] === 'free') ? 'ouvert' : 'limité'; |
|
39
|
|
|
} |
|
40
|
|
|
|
|
41
|
|
|
return null; |
|
42
|
|
|
} |
|
43
|
|
|
|
|
44
|
|
|
/** |
|
45
|
|
|
* Réduit le nombre d'auteurs si > 3. |
|
46
|
|
|
* En $modeEtAll=true vérification pour "et al.=oui". |
|
47
|
|
|
* TODO : wikifyPressAgency() |
|
48
|
|
|
* |
|
49
|
|
|
* @param string|null $authors |
|
50
|
|
|
* @param bool $modeEtAl |
|
51
|
|
|
* |
|
52
|
|
|
* @return string|null |
|
53
|
|
|
*/ |
|
54
|
|
|
protected function authorsEtAl(?string $authors, $modeEtAl = false): ?string |
|
55
|
|
|
{ |
|
56
|
|
|
if (empty($authors)) { |
|
57
|
|
|
return null; |
|
58
|
|
|
} |
|
59
|
|
|
// conserve juste les 3 premiers auteurs TODO : refactor |
|
60
|
|
|
// Bob, Martin ; Yul, Bar ; ... ; ... |
|
61
|
|
|
if (preg_match('#([^;]+;[^;]+);[^;]+;.+#', $authors, $matches)) { |
|
62
|
|
|
return ($modeEtAl) ? 'oui' : $matches[1]; |
|
63
|
|
|
} |
|
64
|
|
|
// Bob Martin, Yul Bar, ..., ...,... |
|
65
|
|
|
if (preg_match('#([^,]+,[^,]+),[^,]+,.+#', $authors, $matches)) { |
|
66
|
|
|
return ($modeEtAl) ? 'oui' : $matches[1]; |
|
67
|
|
|
} |
|
68
|
|
|
|
|
69
|
|
|
return ($modeEtAl) ? null : $authors; |
|
70
|
|
|
} |
|
71
|
|
|
|
|
72
|
|
|
protected function convertDCpage(array $meta): ?string |
|
73
|
|
|
{ |
|
74
|
|
|
if (isset($meta['citation_firstpage'])) { |
|
75
|
|
|
$page = $meta['citation_firstpage']; |
|
76
|
|
|
if (isset($meta['citation_lastpage'])) { |
|
77
|
|
|
$page .= '–'.$meta['citation_lastpage']; |
|
78
|
|
|
} |
|
79
|
|
|
|
|
80
|
|
|
return (string)$page; |
|
81
|
|
|
} |
|
82
|
|
|
|
|
83
|
|
|
return null; |
|
84
|
|
|
} |
|
85
|
|
|
|
|
86
|
|
|
// TODO encodage + normalizer |
|
87
|
|
|
public function clean(?string $str = null): ?string |
|
88
|
|
|
{ |
|
89
|
|
|
if ($str === null) { |
|
90
|
|
|
return null; |
|
91
|
|
|
} |
|
92
|
|
|
$str = str_replace( |
|
93
|
|
|
[''', ''', ''', "\n", " ", "|", "é"], |
|
94
|
|
|
[ |
|
95
|
|
|
"'", |
|
96
|
|
|
"'", |
|
97
|
|
|
"'", |
|
98
|
|
|
'', |
|
99
|
|
|
' ', |
|
100
|
|
|
'/', |
|
101
|
|
|
"é", |
|
102
|
|
|
], |
|
103
|
|
|
$str |
|
104
|
|
|
); |
|
105
|
|
|
|
|
106
|
|
|
return html_entity_decode($str); |
|
107
|
|
|
} |
|
108
|
|
|
|
|
109
|
|
|
protected function convertOGtype2format(?string $ogType): ?string |
|
110
|
|
|
{ |
|
111
|
|
|
if (empty($ogType)) { |
|
112
|
|
|
return null; |
|
113
|
|
|
} |
|
114
|
|
|
// og:type = default: website / video.movie / video.tv_show video.other / article, book, profile |
|
115
|
|
|
if (strpos($ogType, 'video') !== false) { |
|
116
|
|
|
return 'vidéo'; |
|
117
|
|
|
} |
|
118
|
|
|
if (strpos($ogType, 'book') !== false) { |
|
119
|
|
|
return 'livre'; |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
|
|
return null; |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
/** |
|
126
|
|
|
* https://developers.facebook.com/docs/internationalization#locales |
|
127
|
|
|
* @param string|null $lang |
|
128
|
|
|
* |
|
129
|
|
|
* @return string|null |
|
130
|
|
|
*/ |
|
131
|
|
|
protected function convertLangue(?string $lang = null): ?string |
|
132
|
|
|
{ |
|
133
|
|
|
if (empty($lang)) { |
|
134
|
|
|
return null; |
|
135
|
|
|
} |
|
136
|
|
|
// en_GB |
|
137
|
|
|
if (preg_match('#^([a-z]{2})_[A-Z]{2}$#', $lang, $matches)) { |
|
138
|
|
|
return $matches[1]; |
|
139
|
|
|
} |
|
140
|
|
|
|
|
141
|
|
|
return Language::all2wiki($lang); |
|
142
|
|
|
} |
|
143
|
|
|
|
|
144
|
|
|
protected function convertAuteur($data, $indice) |
|
145
|
|
|
{ |
|
146
|
|
|
// author=Bob |
|
147
|
|
|
if (isset($data['author']) && is_string($data['author']) && $indice === 1) { |
|
148
|
|
|
return html_entity_decode($data['author']); |
|
149
|
|
|
} |
|
150
|
|
|
|
|
151
|
|
|
// author ['name'=>'Bob','@type'=>'Person'] |
|
152
|
|
|
if (0 === $indice |
|
153
|
|
|
&& isset($data['author']) |
|
154
|
|
|
&& isset($data['author']['name']) |
|
155
|
|
|
&& (!isset($data['author']['@type']) |
|
156
|
|
|
|| 'Person' === $data['author']['@type']) |
|
157
|
|
|
) { |
|
158
|
|
|
if (is_string($data['author']['name'])) { |
|
159
|
|
|
return html_entity_decode($data['author']['name']); |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
|
|
return html_entity_decode($data['author']['name'][0]); |
|
163
|
|
|
} |
|
164
|
|
|
|
|
165
|
|
|
// author [ 0 => ['name'=>'Bob'], 1=> ...] |
|
166
|
|
|
if (isset($data['author']) && isset($data['author'][$indice]) |
|
167
|
|
|
&& (!isset($data['author'][$indice]['@type']) |
|
168
|
|
|
|| 'Person' === $data['author'][$indice]['@type']) |
|
169
|
|
|
) { |
|
170
|
|
|
if (isset($data['author'][$indice]['name']) && is_string($data['author'][$indice]['name'])) { |
|
171
|
|
|
return html_entity_decode($data['author'][$indice]['name']); |
|
172
|
|
|
} |
|
173
|
|
|
|
|
174
|
|
|
// "author" => [ "@type" => "Person", "name" => [] ] |
|
175
|
|
|
return html_entity_decode($data['author'][$indice]['name'][0]); |
|
176
|
|
|
} |
|
177
|
|
|
|
|
178
|
|
|
return null; |
|
179
|
|
|
} |
|
180
|
|
|
|
|
181
|
|
|
protected function convertInstitutionnel($data) |
|
182
|
|
|
{ |
|
183
|
|
|
if (isset($data['author']) && isset($data['author'][0]) && isset($data['author'][0]['@type']) |
|
184
|
|
|
&& 'Person' !== $data['author'][0]['@type'] |
|
185
|
|
|
) { |
|
186
|
|
|
return html_entity_decode($data['author'][0]['name']); |
|
187
|
|
|
} |
|
188
|
|
|
|
|
189
|
|
|
return null; |
|
190
|
|
|
} |
|
191
|
|
|
|
|
192
|
|
|
/** |
|
193
|
|
|
* @param string $str |
|
194
|
|
|
* |
|
195
|
|
|
* @return string |
|
196
|
|
|
* @throws Exception |
|
197
|
|
|
*/ |
|
198
|
|
|
protected function convertDate(?string $str): ?string |
|
199
|
|
|
{ |
|
200
|
|
|
if (empty($str)) { |
|
201
|
|
|
return null; |
|
202
|
|
|
} |
|
203
|
|
|
|
|
204
|
|
|
// "2012" |
|
205
|
|
|
if (preg_match('#^[12][0-9]{3}$#', $str)) { |
|
206
|
|
|
return $str; |
|
207
|
|
|
} |
|
208
|
|
|
|
|
209
|
|
|
try { |
|
210
|
|
|
$date = new DateTime($str); |
|
211
|
|
|
} catch (Exception $e) { |
|
212
|
|
|
dump('EXCEPTION DATE'); |
|
213
|
|
|
|
|
214
|
|
|
return $str; |
|
215
|
|
|
} |
|
216
|
|
|
|
|
217
|
|
|
return $date->format('d-m-Y'); |
|
218
|
|
|
} |
|
219
|
|
|
|
|
220
|
|
|
/** |
|
221
|
|
|
* Wikification des noms/acronymes d'agences de presse. |
|
222
|
|
|
* |
|
223
|
|
|
* @param string $str |
|
224
|
|
|
* |
|
225
|
|
|
* @return string |
|
226
|
|
|
*/ |
|
227
|
|
|
protected function wikifyPressAgency(?string $str): ?string |
|
228
|
|
|
{ |
|
229
|
|
|
if (empty($str)) { |
|
230
|
|
|
return null; |
|
231
|
|
|
} |
|
232
|
|
|
// skip potential wikilinks |
|
233
|
|
|
if (strpos($str, '[') !== false) { |
|
234
|
|
|
return $str; |
|
235
|
|
|
} |
|
236
|
|
|
$str = preg_replace('#\b(AFP)\b#i', '[[Agence France-Presse|AFP]]', $str); |
|
237
|
|
|
$str = str_replace('Reuters', '[[Reuters]]', $str); |
|
238
|
|
|
$str = str_replace('Associated Press', '[[Associated Press]]', $str); |
|
239
|
|
|
$str = preg_replace('#\b(PA)\b#', '[[Press Association|PA]]', $str); |
|
240
|
|
|
$str = preg_replace('#\b(AP)\b#', '[[Associated Press|AP]]', $str); |
|
241
|
|
|
$str = str_replace('Xinhua', '[[Xinhua]]', $str); |
|
242
|
|
|
$str = preg_replace('#\b(ATS)\b#', '[[Agence télégraphique suisse|ATS]]', $str); |
|
243
|
|
|
$str = preg_replace('#\b(PC|CP)\b#', '[[La Presse canadienne|PC]]', $str); |
|
244
|
|
|
|
|
245
|
|
|
return $str; |
|
246
|
|
|
} |
|
247
|
|
|
|
|
248
|
|
|
} |
|
249
|
|
|
|