|
1
|
|
|
<?php |
|
2
|
|
|
/* |
|
3
|
|
|
* This file is part of dispositif/wikibot application (@github) |
|
4
|
|
|
* 2019-2023 © Philippe M./Irønie <[email protected]> |
|
5
|
|
|
* For the full copyright and MIT license information, view the license file. |
|
6
|
|
|
*/ |
|
7
|
|
|
|
|
8
|
|
|
declare(strict_types=1); |
|
9
|
|
|
|
|
10
|
|
|
namespace App\Domain\Publisher\Traits; |
|
11
|
|
|
|
|
12
|
|
|
trait AuthorConverterTrait |
|
13
|
|
|
{ |
|
14
|
|
|
protected function convertJsonLDAuthor(array $data, int $index): ?string |
|
15
|
|
|
{ |
|
16
|
|
|
// author=Bob |
|
17
|
|
|
// Why restricted to index 1 ?? |
|
18
|
|
|
if (1 === $index && $this->extractAuthorFromString($data)) { |
|
19
|
|
|
return $this->extractAuthorFromString($data); |
|
20
|
|
|
} |
|
21
|
|
|
|
|
22
|
|
|
if (isset($data['author']) && is_string($data['author']) && $index === 1) { |
|
23
|
|
|
return html_entity_decode($data['author']); |
|
24
|
|
|
} |
|
25
|
|
|
|
|
26
|
|
|
// author ['name'=>'Bob','@type'=>'Person'] |
|
27
|
|
|
$simpleAuthor = $this->extractFromSimpleArray($data, $index); |
|
28
|
|
|
if ($simpleAuthor) { |
|
29
|
|
|
return $simpleAuthor; |
|
30
|
|
|
} |
|
31
|
|
|
|
|
32
|
|
|
// author [ 0 => ['name'=>'Bob'], 1=> ...] |
|
33
|
|
|
$extractAuthorFromArray = $this->extractAuthorFromIndexedArray($data, $index); |
|
34
|
|
|
if ($extractAuthorFromArray) { |
|
35
|
|
|
return $extractAuthorFromArray; |
|
36
|
|
|
} |
|
37
|
|
|
|
|
38
|
|
|
return null; |
|
39
|
|
|
} |
|
40
|
|
|
|
|
41
|
|
|
/** |
|
42
|
|
|
* author=Bob |
|
43
|
|
|
*/ |
|
44
|
|
|
protected function extractAuthorFromString(array $data): ?string |
|
45
|
|
|
{ |
|
46
|
|
|
if (isset($data['author']) && is_string($data['author'])) { |
|
47
|
|
|
return html_entity_decode($data['author']); |
|
48
|
|
|
} |
|
49
|
|
|
|
|
50
|
|
|
return null; |
|
51
|
|
|
} |
|
52
|
|
|
|
|
53
|
|
|
/** |
|
54
|
|
|
* author ['name'=>'Bob','@type'=>'Person'] |
|
55
|
|
|
*/ |
|
56
|
|
|
protected function extractFromSimpleArray(array $data, int $index): ?string |
|
57
|
|
|
{ |
|
58
|
|
|
if (0 === $index |
|
59
|
|
|
&& isset($data['author']) |
|
60
|
|
|
&& isset($data['author']['name']) |
|
61
|
|
|
&& (!isset($data['author']['@type']) |
|
62
|
|
|
|| 'Person' === $data['author']['@type']) |
|
63
|
|
|
) { |
|
64
|
|
|
if (is_string($data['author']['name'])) { |
|
65
|
|
|
return html_entity_decode($data['author']['name']); |
|
66
|
|
|
} |
|
67
|
|
|
|
|
68
|
|
|
return html_entity_decode((string) $data['author']['name'][0]); |
|
69
|
|
|
} |
|
70
|
|
|
|
|
71
|
|
|
return null; |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
/** |
|
75
|
|
|
* author [ 0 => ['name'=>'Bob'], 1=> ...] |
|
76
|
|
|
*/ |
|
77
|
|
|
protected function extractAuthorFromIndexedArray(array $data, int $index): ?string |
|
78
|
|
|
{ |
|
79
|
|
|
if (isset($data['author']) && isset($data['author'][$index]) |
|
80
|
|
|
&& (!isset($data['author'][$index]['@type']) |
|
81
|
|
|
|| 'Person' === $data['author'][$index]['@type']) |
|
82
|
|
|
) { |
|
83
|
|
|
if (isset($data['author'][$index]['name']) && is_string($data['author'][$index]['name'])) { |
|
84
|
|
|
return html_entity_decode($data['author'][$index]['name']); |
|
85
|
|
|
} |
|
86
|
|
|
|
|
87
|
|
|
// "author" => [ "@type" => "Person", "name" => [] ] |
|
88
|
|
|
if (isset($data['author'][$index]['name'][0])) { |
|
89
|
|
|
return html_entity_decode((string) $data['author'][$index]['name'][0]); |
|
90
|
|
|
} |
|
91
|
|
|
} |
|
92
|
|
|
|
|
93
|
|
|
return null; |
|
94
|
|
|
} |
|
95
|
|
|
|
|
96
|
|
|
protected function convertInstitutionnel($data): ?string |
|
97
|
|
|
{ |
|
98
|
|
|
if (isset($data['author']) && isset($data['author'][0]) && isset($data['author'][0]['@type']) |
|
99
|
|
|
&& 'Person' !== $data['author'][0]['@type'] |
|
100
|
|
|
) { |
|
101
|
|
|
return html_entity_decode((string) $data['author'][0]['name']); |
|
102
|
|
|
} |
|
103
|
|
|
|
|
104
|
|
|
return null; |
|
105
|
|
|
} |
|
106
|
|
|
|
|
107
|
|
|
/** |
|
108
|
|
|
* Used by OpenGraphMapper (so also ExternMapper). |
|
109
|
|
|
* If more than 2 authors, reduce to the 2 first names. |
|
110
|
|
|
*/ |
|
111
|
|
|
protected function shrinkMultiAuthors(?string $authors): ?string |
|
112
|
|
|
{ |
|
113
|
|
|
if (empty($authors)) { |
|
114
|
|
|
return null; |
|
115
|
|
|
} |
|
116
|
|
|
// "Bob, Martin ; Yul, Bar ; ... ; ..." |
|
117
|
|
|
if (preg_match('#([^;]+;[^;]+);[^;]+;.+#', $authors, $matches)) { |
|
118
|
|
|
return $matches[1]; |
|
119
|
|
|
} |
|
120
|
|
|
// "Bob Martin, Yul Bar, ..., ...,..." |
|
121
|
|
|
if (preg_match('#([^,]+,[^,]+),[^,]+,.+#', $authors, $matches)) { |
|
122
|
|
|
return $matches[1]; |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
return $authors; |
|
126
|
|
|
} |
|
127
|
|
|
|
|
128
|
|
|
/** |
|
129
|
|
|
* If more than 2 authors, return "oui" for the bibliographic parameter "et al.". |
|
130
|
|
|
*/ |
|
131
|
|
|
protected function isAuthorsEtAl(?string $authors): bool |
|
132
|
|
|
{ |
|
133
|
|
|
if (empty($authors)) { |
|
134
|
|
|
return false; |
|
135
|
|
|
} |
|
136
|
|
|
return substr_count($authors, ',') >= 2 || substr_count($authors, ';') >= 1; |
|
137
|
|
|
} |
|
138
|
|
|
|
|
139
|
|
|
protected function cleanAuthor(?string $str = null): ?string |
|
140
|
|
|
{ |
|
141
|
|
|
if ($str === null) { |
|
142
|
|
|
return null; |
|
143
|
|
|
} |
|
144
|
|
|
// "https://www.facebook.com/search/top/?q=..." |
|
145
|
|
|
if (preg_match('#^https?://.+#i', $str)) { |
|
146
|
|
|
return null; |
|
147
|
|
|
} |
|
148
|
|
|
// "Par Bob" |
|
149
|
|
|
if (preg_match('#^Par (.+)$#i', $str, $matches)) { |
|
150
|
|
|
return $matches[1]; |
|
151
|
|
|
} |
|
152
|
|
|
|
|
153
|
|
|
return $str; |
|
154
|
|
|
} |
|
155
|
|
|
|
|
156
|
|
|
/** |
|
157
|
|
|
* Wikification des noms/acronymes d'agences de presse. |
|
158
|
|
|
* Note : utiliser APRES clean() et cleanAuthor() sinon bug "|" |
|
159
|
|
|
*/ |
|
160
|
|
|
protected function wikifyPressAgency(?string $str): ?string |
|
161
|
|
|
{ |
|
162
|
|
|
if (empty($str)) { |
|
163
|
|
|
return null; |
|
164
|
|
|
} |
|
165
|
|
|
// skip potential wikilinks |
|
166
|
|
|
if (str_contains($str, '[')) { |
|
167
|
|
|
return $str; |
|
168
|
|
|
} |
|
169
|
|
|
$str = preg_replace('#\b(AFP)\b#i', '[[Agence France-Presse|AFP]]', $str); |
|
170
|
|
|
$str = str_replace('Reuters', '[[Reuters]]', $str); |
|
171
|
|
|
$str = str_replace('Associated Press', '[[Associated Press]]', $str); |
|
172
|
|
|
$str = preg_replace('#\b(PA)\b#', '[[Press Association|PA]]', $str); |
|
173
|
|
|
$str = preg_replace('#\b(AP)\b#', '[[Associated Press|AP]]', $str); |
|
174
|
|
|
$str = str_replace('Xinhua', '[[Xinhua]]', $str); |
|
175
|
|
|
$str = preg_replace('#\b(ATS)\b#', '[[Agence télégraphique suisse|ATS]]', $str); |
|
176
|
|
|
|
|
177
|
|
|
return preg_replace('#\b(PC|CP)\b#', '[[La Presse canadienne|PC]]', $str); |
|
178
|
|
|
} |
|
179
|
|
|
} |
Dispositif /
Wikibot
