|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* (c) Kitodo. Key to digital objects e.V. <[email protected]> |
|
5
|
|
|
* |
|
6
|
|
|
* This file is part of the Kitodo and TYPO3 projects. |
|
7
|
|
|
* |
|
8
|
|
|
* @license GNU General Public License version 3 or later. |
|
9
|
|
|
* For the full copyright and license information, please read the |
|
10
|
|
|
* LICENSE.txt file that was distributed with this source code. |
|
11
|
|
|
*/ |
|
12
|
|
|
|
|
13
|
|
|
namespace Kitodo\Dlf\Format; |
|
14
|
|
|
|
|
15
|
|
|
use Kitodo\Dlf\Api\Orcid\Profile as OrcidProfile; |
|
16
|
|
|
use Kitodo\Dlf\Api\Viaf\Profile as ViafProfile; |
|
17
|
|
|
use Kitodo\Dlf\Common\MetadataInterface; |
|
18
|
|
|
use Slub\Mods\Element\Name; |
|
19
|
|
|
use Slub\Mods\ModsReader; |
|
20
|
|
|
|
|
21
|
|
|
/** |
|
22
|
|
|
* Metadata MODS format class for the 'dlf' extension |
|
23
|
|
|
* |
|
24
|
|
|
* @package TYPO3 |
|
25
|
|
|
* @subpackage dlf |
|
26
|
|
|
* |
|
27
|
|
|
* @access public |
|
28
|
|
|
*/ |
|
29
|
|
|
class Mods implements MetadataInterface |
|
30
|
|
|
{ |
|
31
|
|
|
/** |
|
32
|
|
|
* @access private |
|
33
|
|
|
* @var \SimpleXMLElement The metadata XML |
|
34
|
|
|
**/ |
|
35
|
|
|
private $xml; |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* @access private |
|
39
|
|
|
* @var ModsReader The metadata XML |
|
40
|
|
|
**/ |
|
41
|
|
|
private $modsReader; |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* @access private |
|
45
|
|
|
* @var array The metadata array |
|
46
|
|
|
**/ |
|
47
|
|
|
private $metadata; |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* @access private |
|
51
|
|
|
* @var bool The metadata array |
|
52
|
|
|
**/ |
|
53
|
|
|
private $useExternalApis; |
|
54
|
|
|
|
|
55
|
|
|
/** |
|
56
|
|
|
* This extracts the essential MODS metadata from XML |
|
57
|
|
|
* |
|
58
|
|
|
* @access public |
|
59
|
|
|
* |
|
60
|
|
|
* @param \SimpleXMLElement $xml The XML to extract the metadata from |
|
61
|
|
|
* @param array &$metadata The metadata array to fill |
|
62
|
|
|
* @param bool $useExternalApis true if external APIs should be called, false otherwise |
|
63
|
|
|
* |
|
64
|
|
|
* @return void |
|
65
|
|
|
*/ |
|
66
|
|
|
public function extractMetadata(\SimpleXMLElement $xml, array &$metadata, bool $useExternalApis): void |
|
67
|
|
|
{ |
|
68
|
|
|
$this->xml = $xml; |
|
69
|
|
|
$this->metadata = $metadata; |
|
70
|
|
|
$this->useExternalApis = $useExternalApis; |
|
71
|
|
|
|
|
72
|
|
|
$this->modsReader = new ModsReader($this->xml); |
|
73
|
|
|
|
|
74
|
|
|
$this->getAuthors(); |
|
75
|
|
|
$this->getHolders(); |
|
76
|
|
|
$this->getPlaces(); |
|
77
|
|
|
$this->getYears(); |
|
78
|
|
|
|
|
79
|
|
|
$metadata = $this->metadata; |
|
80
|
|
|
} |
|
81
|
|
|
|
|
82
|
|
|
/** |
|
83
|
|
|
* Get "author" and "author_sorting". |
|
84
|
|
|
* |
|
85
|
|
|
* @access private |
|
86
|
|
|
* |
|
87
|
|
|
* @return void |
|
88
|
|
|
*/ |
|
89
|
|
|
private function getAuthors(): void |
|
90
|
|
|
{ |
|
91
|
|
|
$authors = $this->modsReader->getNames('[./mods:role/mods:roleTerm[@type="code" and @authority="marcrelator"]="aut"]'); |
|
92
|
|
|
// Get "author" and "author_sorting" again if that was too sophisticated. |
|
93
|
|
|
if (empty($authors)) { |
|
94
|
|
|
// Get all names which do not have any role term assigned and assume these are authors. |
|
95
|
|
|
$authors = $this->modsReader->getNames('[not(./mods:role)]'); |
|
96
|
|
|
} |
|
97
|
|
|
if (!empty($authors)) { |
|
98
|
|
|
for ($i = 0, $j = count($authors); $i < $j; $i++) { |
|
99
|
|
|
$identifiers = $authors[$i]->getNameIdentifiers('[@type="orcid"]'); |
|
100
|
|
|
if ($this->useExternalApis && !empty($identifiers)) { |
|
101
|
|
|
$this->getAuthorFromOrcidApi($identifiers[0]->getValue(), $authors, $i); |
|
102
|
|
|
} else { |
|
103
|
|
|
$this->getAuthorFromXml($authors, $i); |
|
104
|
|
|
} |
|
105
|
|
|
} |
|
106
|
|
|
} |
|
107
|
|
|
} |
|
108
|
|
|
|
|
109
|
|
|
/** |
|
110
|
|
|
* Get author from ORCID API. |
|
111
|
|
|
* |
|
112
|
|
|
* @access private |
|
113
|
|
|
* |
|
114
|
|
|
* @param string $orcidId |
|
115
|
|
|
* @param array $authors |
|
116
|
|
|
* @param int $i |
|
117
|
|
|
* |
|
118
|
|
|
* @return void |
|
119
|
|
|
*/ |
|
120
|
|
|
private function getAuthorFromOrcidApi(string $orcidId, array $authors, int $i): void |
|
121
|
|
|
{ |
|
122
|
|
|
$profile = new OrcidProfile($orcidId); |
|
123
|
|
|
$name = $profile->getFullName(); |
|
124
|
|
|
if (!empty($name)) { |
|
125
|
|
|
$this->metadata['author'][$i] = [ |
|
126
|
|
|
'name' => $name, |
|
127
|
|
|
'url' => 'https://orcid.org/' . $orcidId |
|
128
|
|
|
]; |
|
129
|
|
|
} else { |
|
130
|
|
|
//fallback into display form |
|
131
|
|
|
$this->getAuthorFromXmlDisplayForm($authors, $i); |
|
132
|
|
|
} |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* Get author from XML. |
|
137
|
|
|
* |
|
138
|
|
|
* @access private |
|
139
|
|
|
* |
|
140
|
|
|
* @param array $authors |
|
141
|
|
|
* @param int $i |
|
142
|
|
|
* |
|
143
|
|
|
* @return void |
|
144
|
|
|
*/ |
|
145
|
|
|
private function getAuthorFromXml(array $authors, int $i): void |
|
146
|
|
|
{ |
|
147
|
|
|
$this->getAuthorFromXmlDisplayForm($authors, $i); |
|
148
|
|
|
|
|
149
|
|
|
$nameParts = $authors[$i]->getNameParts(); |
|
150
|
|
|
if (empty($this->metadata['author'][$i]) && $nameParts) { |
|
151
|
|
|
$name = []; |
|
152
|
|
|
$k = 4; |
|
153
|
|
|
foreach ($nameParts as $namePart) { |
|
154
|
|
|
if ( |
|
155
|
|
|
!empty($namePart->getType()) |
|
156
|
|
|
&& $namePart->getType() == 'family' |
|
157
|
|
|
) { |
|
158
|
|
|
$name[0] = $namePart->getValue(); |
|
159
|
|
|
} elseif ( |
|
160
|
|
|
!empty($namePart->getType()) |
|
161
|
|
|
&& $namePart->getType() == 'given' |
|
162
|
|
|
) { |
|
163
|
|
|
$name[1] = $namePart->getValue(); |
|
164
|
|
|
} elseif ( |
|
165
|
|
|
!empty($namePart->getType()) |
|
166
|
|
|
&& $namePart->getType() == 'termsOfAddress' |
|
167
|
|
|
) { |
|
168
|
|
|
$name[2] = $namePart->getValue(); |
|
169
|
|
|
} elseif ( |
|
170
|
|
|
!empty($namePart->getType()) |
|
171
|
|
|
&& $namePart->getType() == 'date' |
|
172
|
|
|
) { |
|
173
|
|
|
$name[3] = $namePart->getValue(); |
|
174
|
|
|
} else { |
|
175
|
|
|
$name[$k] = $namePart->getValue(); |
|
176
|
|
|
} |
|
177
|
|
|
$k++; |
|
178
|
|
|
} |
|
179
|
|
|
ksort($name); |
|
180
|
|
|
$this->metadata['author'][$i] = trim(implode(', ', $name)); |
|
181
|
|
|
} |
|
182
|
|
|
// Append "valueURI" to name using Unicode unit separator. |
|
183
|
|
|
if (!empty($authors[$i]->getValueURI())) { |
|
184
|
|
|
$this->metadata['author'][$i] .= pack('C', 31) . $authors[$i]->getValueURI(); |
|
185
|
|
|
} |
|
186
|
|
|
} |
|
187
|
|
|
|
|
188
|
|
|
/** |
|
189
|
|
|
* Get author from XML display form. |
|
190
|
|
|
* |
|
191
|
|
|
* @access private |
|
192
|
|
|
* |
|
193
|
|
|
* @param Name[] $authors |
|
194
|
|
|
* @param int $i |
|
195
|
|
|
* |
|
196
|
|
|
* @return void |
|
197
|
|
|
*/ |
|
198
|
|
|
private function getAuthorFromXmlDisplayForm(array $authors, int $i): void |
|
199
|
|
|
{ |
|
200
|
|
|
$displayForms = $authors[$i]->getDisplayForms(); |
|
201
|
|
|
if ($displayForms) { |
|
202
|
|
|
$this->metadata['author'][$i] = $displayForms[0]->getValue(); |
|
203
|
|
|
} |
|
204
|
|
|
} |
|
205
|
|
|
|
|
206
|
|
|
/** |
|
207
|
|
|
* Get holder. |
|
208
|
|
|
* |
|
209
|
|
|
* @access private |
|
210
|
|
|
* |
|
211
|
|
|
* @return void |
|
212
|
|
|
*/ |
|
213
|
|
|
private function getHolders(): void |
|
214
|
|
|
{ |
|
215
|
|
|
$holders = $this->modsReader->getNames('[./mods:role/mods:roleTerm[@type="code" and @authority="marcrelator"]="prv"]'); |
|
216
|
|
|
|
|
217
|
|
|
if (!empty($holders)) { |
|
218
|
|
|
for ($i = 0, $j = count($holders); $i < $j; $i++) { |
|
219
|
|
|
$identifiers = $holders[$i]->getNameIdentifiers('[@type="viaf"]'); |
|
220
|
|
|
if ($this->useExternalApis && !empty($identifiers)) { |
|
221
|
|
|
$this->getHolderFromViafApi($identifiers[0]->getValue(), $holders, $i); |
|
222
|
|
|
} else { |
|
223
|
|
|
$this->getHolderFromXml($holders, $i); |
|
224
|
|
|
} |
|
225
|
|
|
} |
|
226
|
|
|
} |
|
227
|
|
|
} |
|
228
|
|
|
|
|
229
|
|
|
/** |
|
230
|
|
|
* Get holder from VIAF API. |
|
231
|
|
|
* |
|
232
|
|
|
* @access private |
|
233
|
|
|
* |
|
234
|
|
|
* @param string $viafId |
|
235
|
|
|
* @param array $holders |
|
236
|
|
|
* @param int $i |
|
237
|
|
|
* |
|
238
|
|
|
* @return void |
|
239
|
|
|
*/ |
|
240
|
|
|
private function getHolderFromViafApi(string $viafId, array $holders, int $i): void |
|
241
|
|
|
{ |
|
242
|
|
|
$profile = new ViafProfile($viafId); |
|
243
|
|
|
$name = $profile->getFullName(); |
|
244
|
|
|
if (!empty($name)) { |
|
245
|
|
|
$this->metadata['holder'][$i] = [ |
|
246
|
|
|
'name' => $name, |
|
247
|
|
|
'url' => 'http://viaf.org/viaf/' . $viafId |
|
248
|
|
|
]; |
|
249
|
|
|
} else { |
|
250
|
|
|
//fallback into display form |
|
251
|
|
|
$this->getHolderFromXmlDisplayForm($holders, $i); |
|
252
|
|
|
} |
|
253
|
|
|
} |
|
254
|
|
|
|
|
255
|
|
|
/** |
|
256
|
|
|
* Get holder from XML. |
|
257
|
|
|
* |
|
258
|
|
|
* @access private |
|
259
|
|
|
* |
|
260
|
|
|
* @param array $holders |
|
261
|
|
|
* @param int $i |
|
262
|
|
|
* |
|
263
|
|
|
* @return void |
|
264
|
|
|
*/ |
|
265
|
|
|
private function getHolderFromXml(array $holders, int $i): void |
|
266
|
|
|
{ |
|
267
|
|
|
$this->getHolderFromXmlDisplayForm($holders, $i); |
|
268
|
|
|
// Append "valueURI" to name using Unicode unit separator. |
|
269
|
|
|
if (!empty($holders[$i]->getValueURI())) { |
|
270
|
|
|
$this->metadata['holder'][$i] .= pack('C', 31) . $holders[$i]->getValueURI(); |
|
271
|
|
|
} |
|
272
|
|
|
} |
|
273
|
|
|
|
|
274
|
|
|
/** |
|
275
|
|
|
* Get holder from XML display form. |
|
276
|
|
|
* |
|
277
|
|
|
* @access private |
|
278
|
|
|
* |
|
279
|
|
|
* @param array $holders |
|
280
|
|
|
* @param int $i |
|
281
|
|
|
* |
|
282
|
|
|
* @return void |
|
283
|
|
|
*/ |
|
284
|
|
|
private function getHolderFromXmlDisplayForm(array $holders, int $i): void |
|
285
|
|
|
{ |
|
286
|
|
|
// Check if there is a display form. |
|
287
|
|
|
$displayForms = $holders[$i]->getDisplayForm(); |
|
288
|
|
|
if ($displayForms) { |
|
289
|
|
|
$this->metadata['holder'][$i] = $displayForms[0]->getValue(); |
|
290
|
|
|
} |
|
291
|
|
|
} |
|
292
|
|
|
|
|
293
|
|
|
/** |
|
294
|
|
|
* Get "place" and "place_sorting". |
|
295
|
|
|
* |
|
296
|
|
|
* @access private |
|
297
|
|
|
* |
|
298
|
|
|
* @return void |
|
299
|
|
|
*/ |
|
300
|
|
|
private function getPlaces(): void |
|
301
|
|
|
{ |
|
302
|
|
|
$places = []; |
|
303
|
|
|
$originInfos = $this->modsReader->getOriginInfos('[not(./mods:edition="[Electronic ed.]")]'); |
|
304
|
|
|
foreach ($originInfos as $originInfo) { |
|
305
|
|
|
foreach ($originInfo->getPlaces() as $place) { |
|
306
|
|
|
foreach ($place->getPlaceTerms() as $placeTerm) { |
|
307
|
|
|
$places[] = $placeTerm->getValue(); |
|
308
|
|
|
} |
|
309
|
|
|
} |
|
310
|
|
|
} |
|
311
|
|
|
|
|
312
|
|
|
// Get "place" and "place_sorting" again if that was to sophisticated. |
|
313
|
|
|
if (empty($places)) { |
|
314
|
|
|
// Get all places and assume these are places of publication. |
|
315
|
|
|
$originInfos = $this->modsReader->getOriginInfos(); |
|
316
|
|
|
foreach ($originInfos as $originInfo) { |
|
317
|
|
|
foreach ($originInfo->getPlaces() as $place) { |
|
318
|
|
|
foreach ($place->getPlaceTerms() as $placeTerm) { |
|
319
|
|
|
$places[] = $placeTerm->getValue(); |
|
320
|
|
|
} |
|
321
|
|
|
} |
|
322
|
|
|
} |
|
323
|
|
|
} |
|
324
|
|
|
|
|
325
|
|
|
if (!empty($places)) { |
|
326
|
|
|
foreach ($places as $place) { |
|
327
|
|
|
$this->metadata['place'][] = $place; |
|
328
|
|
|
if (empty($this->metadata['place_sorting'][0])) { |
|
329
|
|
|
$this->metadata['place_sorting'][0] = preg_replace('/[[:punct:]]/', '', $place); |
|
330
|
|
|
} |
|
331
|
|
|
} |
|
332
|
|
|
} |
|
333
|
|
|
} |
|
334
|
|
|
|
|
335
|
|
|
/** |
|
336
|
|
|
* Get "year" and "year_sorting". |
|
337
|
|
|
* |
|
338
|
|
|
* @access private |
|
339
|
|
|
* |
|
340
|
|
|
* @return void |
|
341
|
|
|
*/ |
|
342
|
|
|
private function getYears(): void |
|
343
|
|
|
{ |
|
344
|
|
|
// Get "year_sorting". |
|
345
|
|
|
$yearsSorting = $this->modsReader->getOriginInfos('[not(./mods:edition="[Electronic ed.]")]/mods:dateOther[@type="order" and @encoding="w3cdtf"]'); |
|
346
|
|
|
if ($yearsSorting) { |
|
347
|
|
|
foreach ($yearsSorting as $yearSorting) { |
|
348
|
|
|
$otherDates = $yearSorting->getOtherDates(); |
|
349
|
|
|
if (!empty($otherDates)) { |
|
350
|
|
|
$this->metadata['year_sorting'][0] = $otherDates[0]->getValue(); |
|
351
|
|
|
} |
|
352
|
|
|
} |
|
353
|
|
|
} |
|
354
|
|
|
// Get "year" and "year_sorting" if not specified separately. |
|
355
|
|
|
$years = $this->modsReader->getOriginInfos('./mods:originInfo[not(./mods:edition="[Electronic ed.]")]/mods:dateIssued[@keyDate="yes"]'); |
|
356
|
|
|
// Get "year" and "year_sorting" again if that was to sophisticated. |
|
357
|
|
|
if (empty($years)) { |
|
358
|
|
|
// Get all dates and assume these are dates of publication. |
|
359
|
|
|
$years = $this->modsReader->getOriginInfos(); |
|
360
|
|
|
} |
|
361
|
|
|
if (!empty($years)) { |
|
362
|
|
|
foreach ($years as $year) { |
|
363
|
|
|
$issued = $year->getIssuedDates(); |
|
364
|
|
|
if (!empty($issued)) { |
|
365
|
|
|
$this->metadata['year'][] = $issued[0]->getValue(); |
|
366
|
|
|
if (empty($this->metadata['year_sorting'][0])) { |
|
367
|
|
|
$yearSorting = str_ireplace('x', '5', preg_replace('/[^\d.x]/i', '', $issued[0]->getValue())); |
|
368
|
|
|
if ( |
|
369
|
|
|
strpos($yearSorting, '.') |
|
|
|
|
|
|
370
|
|
|
|| strlen($yearSorting) < 3 |
|
|
|
|
|
|
371
|
|
|
) { |
|
372
|
|
|
$yearSorting = (((int) trim($yearSorting, '.') - 1) * 100) + 50; |
|
|
|
|
|
|
373
|
|
|
} |
|
374
|
|
|
$this->metadata['year_sorting'][0] = (int) $yearSorting; |
|
375
|
|
|
} |
|
376
|
|
|
} |
|
377
|
|
|
} |
|
378
|
|
|
} |
|
379
|
|
|
} |
|
380
|
|
|
} |
|
381
|
|
|
|