1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace PubPeerFoundation\PublicationDataExtractor\Resources\Extractors; |
4
|
|
|
|
5
|
|
|
use PubPeerFoundation\PublicationDataExtractor\Support\UpdateTypesStandardiser; |
6
|
|
|
use PubPeerFoundation\PublicationDataExtractor\Exceptions\UnparseableApiException; |
7
|
|
|
use PubPeerFoundation\PublicationDataExtractor\Exceptions\JournalTitleNotFoundException; |
8
|
|
|
|
9
|
|
|
class Crossref extends Extractor implements ProvidesPublicationData, ProvidesIdentifiersData, ProvidesJournalData, ProvidesAuthorsData, ProvidesUpdatesData |
10
|
|
|
{ |
11
|
|
|
/** |
12
|
|
|
* @throws UnparseableApiException |
13
|
|
|
*/ |
14
|
|
|
protected function getDataFromDocument() |
15
|
|
|
{ |
16
|
|
|
if ('ok' !== $this->document['status']) { |
17
|
24 |
|
throw new UnparseableApiException(); |
18
|
|
|
} |
19
|
24 |
|
|
20
|
24 |
|
$this->searchTree = $this->document['message']; |
21
|
|
|
} |
22
|
11 |
|
|
23
|
|
|
/** |
24
|
11 |
|
* Extract and format data needed for the Publication Model. |
25
|
|
|
*/ |
26
|
9 |
|
public function extractPublicationData() |
27
|
9 |
|
{ |
28
|
9 |
|
$date = $this->extractDateFrom(['published-print', 'published-online', 'issued']); |
29
|
9 |
|
|
30
|
9 |
|
$this->output['publication'] = [ |
31
|
9 |
|
'title' => get_string($this->searchTree, 'title'), |
32
|
9 |
|
'abstract' => get_string($this->searchTree, 'abstract'), |
33
|
|
|
'url' => $this->searchTree['URL'] ?? null, |
34
|
9 |
|
'published_at' => $date, |
35
|
|
|
]; |
36
|
|
|
} |
37
|
7 |
|
|
38
|
|
|
/** |
39
|
7 |
|
* Extract and format data needed for the Identifiers Relationship |
40
|
2 |
|
* on the Publication Model. |
41
|
|
|
*/ |
42
|
|
|
public function extractIdentifiersData() |
43
|
5 |
|
{ |
44
|
5 |
|
if (! empty($this->searchTree['DOI'])) { |
45
|
|
|
$this->output['identifiers'][] = [ |
46
|
|
|
'value' => $this->searchTree['DOI'], |
47
|
|
|
'type' => 'doi', |
48
|
|
|
]; |
49
|
11 |
|
} |
50
|
|
|
|
51
|
11 |
|
foreach (get_array($this->searchTree, 'ISSN') as $issn) { |
52
|
|
|
$this->output['identifiers'][] = [ |
53
|
11 |
|
'value' => $issn, |
54
|
11 |
|
'type' => 'issn', |
55
|
11 |
|
]; |
56
|
11 |
|
} |
57
|
11 |
|
} |
58
|
|
|
|
59
|
11 |
|
/** |
60
|
|
|
* Extract and format data needed for the Journal Relationship |
61
|
|
|
* on the Publication Model. |
62
|
|
|
* |
63
|
|
|
* @throws JournalTitleNotFoundException |
64
|
11 |
|
*/ |
65
|
|
|
public function extractJournalData() |
66
|
11 |
|
{ |
67
|
|
|
$this->output['journal'] = [ |
68
|
|
|
'title' => get_string($this->searchTree, 'container-title'), |
69
|
|
|
'issn' => get_array($this->searchTree, 'ISSN'), |
70
|
|
|
'publisher' => get_string($this->searchTree, 'publisher'), |
71
|
|
|
]; |
72
|
|
|
|
73
|
17 |
|
if (empty($this->searchTree['container-title']) && empty($this->searchTree['ISSN'])) { |
74
|
|
|
throw new JournalTitleNotFoundException(); |
75
|
17 |
|
} |
76
|
9 |
|
} |
77
|
9 |
|
|
78
|
9 |
|
/** |
79
|
|
|
* Extract and format data needed for the Authors Relationship |
80
|
|
|
* on the Publication Model. |
81
|
|
|
*/ |
82
|
17 |
|
public function extractAuthorsData() |
83
|
12 |
|
{ |
84
|
11 |
|
foreach (get_array($this->searchTree, 'author') as $author) { |
85
|
11 |
|
if (isset($author['family'])) { |
86
|
11 |
|
$this->output['authors'][] = [ |
87
|
11 |
|
'first_name' => get_string($author, 'given'), |
88
|
|
|
'last_name' => get_string($author, 'family'), |
89
|
|
|
'orcid' => get_string($author, 'ORCID'), |
90
|
|
|
'affiliation' => get_array($author, 'affiliation'), |
91
|
1 |
|
]; |
92
|
1 |
|
} |
93
|
1 |
|
} |
94
|
|
|
} |
95
|
|
|
|
96
|
|
|
/** |
97
|
17 |
|
* Extract and format data needed for the Types Relationship |
98
|
|
|
* on the Publication Model. |
99
|
|
|
*/ |
100
|
|
|
public function extractTypesData() |
101
|
|
|
{ |
102
|
|
|
$this->output['types'][] = [ |
103
|
12 |
|
'name' => get_string($this->searchTree, 'type'), |
104
|
|
|
]; |
105
|
12 |
|
} |
106
|
1 |
|
|
107
|
|
|
/** |
108
|
|
|
* Extract and format data needed for the tags Relationship |
109
|
12 |
|
* on the Publication Model. |
110
|
12 |
|
*/ |
111
|
12 |
|
public function extractTagsData() |
112
|
12 |
|
{ |
113
|
|
|
foreach (get_array($this->searchTree, 'subject') as $tag) { |
114
|
12 |
|
$this->output['tags'][] = [ |
115
|
|
|
'name' => $tag, |
116
|
|
|
]; |
117
|
|
|
} |
118
|
|
|
} |
119
|
|
|
|
120
|
9 |
|
/** |
121
|
|
|
* Extract and format data needed for the Updates Relationship |
122
|
9 |
|
* on the Publication Model. |
123
|
9 |
|
*/ |
124
|
9 |
|
public function extractUpdatesData() |
125
|
9 |
|
{ |
126
|
9 |
|
foreach (get_array($this->searchTree, 'update-to') as $update) { |
127
|
9 |
|
$this->output['updates'][] = [ |
128
|
9 |
|
'timestamp' => $update['updated']['timestamp'], |
129
|
9 |
|
'identifier' => [ |
130
|
|
|
'doi' => get_string($update, 'DOI'), |
131
|
|
|
], |
132
|
|
|
'type' => UpdateTypesStandardiser::getType($update['type']), |
133
|
|
|
]; |
134
|
9 |
|
} |
135
|
|
|
} |
136
|
|
|
|
137
|
|
|
/** |
138
|
|
|
* @param $array |
139
|
|
|
* @return mixed |
140
|
9 |
|
*/ |
141
|
|
|
protected function extractDateFrom($array) |
142
|
9 |
|
{ |
143
|
9 |
|
$datePartsContainer = array_values(array_filter($array, function ($string) { |
144
|
|
|
return isset($this->searchTree[$string]); |
145
|
9 |
|
}))[0]; |
146
|
|
|
|
147
|
|
|
return date_from_parts($this->searchTree[$datePartsContainer]['date-parts'][0]); |
148
|
|
|
} |
149
|
|
|
} |
150
|
|
|
|