Add description to documents interface and indexation. Prepare #0025746
--- a/server/src/app/Console/Commands/IndexDocuments.php Mon Feb 06 10:03:33 2017 +0100
+++ b/server/src/app/Console/Commands/IndexDocuments.php Mon Feb 06 13:23:39 2017 +0100
@@ -103,6 +103,15 @@
]
]
],
+ 'description' => [
+ 'type' => 'string',
+ 'fields' => [
+ 'french' => [
+ 'type' => 'string',
+ 'analyzer' => 'french'
+ ]
+ ]
+ ],
'date' => [ 'type' => 'date', 'index' => 'not_analyzed'],
'geonames_hierarchy' => [ 'type' => 'string', 'index' => 'not_analyzed'],
'geonames_country' => ['type' => 'string', 'index' => 'not_analyzed'],
@@ -524,6 +533,21 @@
}, []);
}
+ private function getDescriptions($doc) {
+ return array_reduce($doc->getDescriptions(), function($res, $desc) {
+ $val = null;
+ if(is_string($desc)) {
+ $val = $desc;
+ } elseif($desc instanceof Literal) {
+ $val = $desc->getValue();
+ }
+ if(!empty($val)) {
+ array_push($res, $val);
+ }
+ return $res;
+ }, []);
+ }
+
private function getDocBody($doc) {
list($geonamesCountry, $geonamesHierarchy) = $this->getGeonamesHierarchy($doc);
return [
@@ -537,6 +561,7 @@
'geonames_country' => $geonamesCountry,
'geonames_hierarchy' => $geonamesHierarchy,
'subject' => $this->getSubjects($doc),
+ 'description' => $this->getDescriptions($doc),
];
}
--- a/server/src/app/Models/Document.php Mon Feb 06 10:03:33 2017 +0100
+++ b/server/src/app/Models/Document.php Mon Feb 06 13:23:39 2017 +0100
@@ -30,6 +30,7 @@
private $contributors = null;
private $subjects = null;
private $types = null;
+ private $descriptions = null;
private $geoInfo = false;
protected function clearMemoizationCache() {
@@ -39,6 +40,7 @@
$this->contributors = null;
$this->subjects = null;
$this->types = null;
+ $this->descriptions = null;
$this->transcript = false;
$this->geoInfo = false;
}
@@ -310,6 +312,19 @@
}
+ /**
+ * Get subjects list
+ */
+ public function getDescriptions() {
+ if(is_null($this->descriptions)) {
+ $this->descriptions = [];
+ $this->descriptions = array_merge($this->descriptions, $this->getProvidedCHO()->all('<http://purl.org/dc/elements/1.1/description>'));
+ $this->descriptions = array_merge($this->descriptions, $this->getProvidedCHO()->all('<http://purl.org/dc/terms/abstract>'));
+ $this->descriptions = array_merge($this->descriptions, $this->getProvidedCHO()->all('<http://purl.org/dc/terms/tableOfContents>'));
+ }
+ return $this->descriptions;
+ }
+
public function isIsomorphic($doc) {
return Isomorphic::isomorphic($this->graph, $doc->graph);
@@ -359,6 +374,10 @@
function($s) { return Utils::processLiteralResourceOrString($s); },
$this->getTypes()
);
+ $descriptions = array_map(
+ function($s) { return Utils::processLiteralResourceOrString($s); },
+ $this->getDescriptions()
+ );
$res = array_merge($res, [
'publishers' => $publishers,
@@ -367,7 +386,8 @@
'types' => $types,
'transcript' => $transcript,
'mediaArray'=> $mediaArray,
- 'geoInfo' => $geoInfo
+ 'geoInfo' => $geoInfo,
+ 'descriptions' => $descriptions
]);
}
--- a/server/src/tests/Models/DocumentTest.php Mon Feb 06 10:03:33 2017 +0100
+++ b/server/src/tests/Models/DocumentTest.php Mon Feb 06 13:23:39 2017 +0100
@@ -13,6 +13,7 @@
const TEST_INPUT_DOCS = [
'TEST' => __DIR__.'/files/DocumentTest/test_doc.ttl',
'TEST_NO_GEOINFO' => __DIR__.'/files/DocumentTest/test_no_geoinfo.ttl',
+ 'TEST_NO_DESCRIPTION' => __DIR__.'/files/DocumentTest/test_doc_no_description.ttl',
];
private $inputGraphes = [];
@@ -427,7 +428,9 @@
$this->assertTrue(is_array($json), 'Returned json must be an array');
$this->assertEquals(
- ["id", "uri", "title", "languages", "modified", "issued", "created", "publishers", "contributors", "subjects", "types", "transcript", "mediaArray", "geoInfo"],
+ [ "id", "uri", "title", "languages", "modified", "issued",
+ "created", "publishers", "contributors", "subjects", "types",
+ "transcript", "mediaArray", "geoInfo", "descriptions" ],
array_keys($json)
);
$this->assertEquals(sprintf('%1$s/crdo-CFPP2000_35_SOUNDid', config('corpusparole.handle_prefix')), $json['id']);
@@ -501,5 +504,26 @@
$this->assertEquals(9, $res->getCurrentDelta()->getAddedGraph()->countTriples(), "Added graph must have 7 triples");
}
+ public function testDescriptions() {
+ $doc = new Document(config('corpusparole.corpus_doc_id_base_uri')."crdo-CFPP2000_35_SOUND", $this->inputGraphes['TEST']);
+
+ $descriptions = $doc->getDescriptions();
+
+ $this->assertTrue(is_array($descriptions));
+
+ $this->assertCount(4, $descriptions);
+ }
+
+ public function testNoDescription() {
+ $doc = new Document(config('corpusparole.corpus_doc_id_base_uri')."crdo-CFPP2000_35_SOUND", $this->inputGraphes['TEST_NO_DESCRIPTION']);
+
+ $descriptions = $doc->getDescriptions();
+
+ $this->assertTrue(is_array($descriptions));
+
+ $this->assertCount(0, $descriptions);
+ }
+
+
}
--- a/server/src/tests/Models/files/DocumentTest/test_doc.ttl Mon Feb 06 10:03:33 2017 +0100
+++ b/server/src/tests/Models/files/DocumentTest/test_doc.ttl Mon Feb 06 13:23:39 2017 +0100
@@ -22,6 +22,8 @@
<http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
<http://purl.org/dc/elements/1.1/contributor> <http://viaf.org/viaf/93752300> , "Tanguy, Noalig" , "Chevrier, Michel" , "Kiliç, Ozgur" , "Salvegas, Etienne" , "du-Breuil-de-Pont-en-Auge, Augustin" , "du-Breuil-de-Pont-en-Auge, Benoît" ;
<http://purl.org/dc/elements/1.1/description> "Enregistrement issu du Corpus de Français Parlé Parisien des années 2000 (CFPP2000)"@fr , "Quartier(s) concerné(s) : Paris 3e, et 20e (pour l'âge adulte); Anonymisation : Noalig TANGUY;"@fr ;
+ <http://purl.org/dc/terms/tableOfContents> "2- ech'cratcheu"@pcd;
+ <http://purl.org/dc/terms/abstract> "Participants : deux employées. Enregistré par James Mallinson. Contenu : JSM se renseigne sur billet."@fr;
<http://purl.org/dc/elements/1.1/identifier> "ark:/87895/1.17-375004" , "%2$scrdo-CFPP2000_35_SOUNDid" , "oai:crdo.vjf.cnrs.fr:crdo-CFPP2000_35" , "Cote producteur: [03-01] Ozgur_Kilic_H_32_alii_3e"@fr , "ark:/87895/1.17-372593" , "oai:crdo.vjf.cnrs.fr:crdo-CFPP2000_35_SOUND" ;
<http://purl.org/dc/elements/1.1/language> <http://lexvo.org/id/iso639-3/fra> ;
<http://purl.org/dc/elements/1.1/publisher> <http://viaf.org/viaf/142432638>;
@@ -77,4 +79,4 @@
<http://purl.org/dc/terms/extent> "PT48M26S" ;
<http://purl.org/dc/terms/issued> "2013-10-12T14:35:57+02:00"^^<http://purl.org/dc/terms/W3CDTF> ;
<http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
- <http://www.europeana.eu/schemas/edm/isDerivativeOf> <http://cocoon.huma-num.fr/data/archi/masters/372593.wav> .
\ No newline at end of file
+ <http://www.europeana.eu/schemas/edm/isDerivativeOf> <http://cocoon.huma-num.fr/data/archi/masters/372593.wav> .
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/server/src/tests/Models/files/DocumentTest/test_doc_no_description.ttl Mon Feb 06 13:23:39 2017 +0100
@@ -0,0 +1,79 @@
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix sesame: <http://www.openrdf.org/schema/sesame#> .
+@prefix owl: <http://www.w3.org/2002/07/owl#> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+@prefix fn: <http://www.w3.org/2005/xpath-functions#> .
+
+<%1$scrdo-CFPP2000_35_SOUND> a <http://www.openarchives.org/ore/terms/Aggregation> ;
+ <http://www.europeana.eu/schemas/edm/aggregatedCHO> <http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-CFPP2000_35_SOUND> ;
+ <http://www.europeana.eu/schemas/edm/dataProvider> "Langage et langues : description, théorisation, transmission" ;
+ <http://www.europeana.eu/schemas/edm/hasView> <http://cocoon.huma-num.fr/exist/crdo/cfpp2000/fra/Ozgur_Kilic_H_32_alii_3e-2.xml> , <http://cocoon.huma-num.fr/data/cfpp2000/Ozgur_Kilic_H_32_alii_3e-2.mp3> , <http://cocoon.huma-num.fr/data/cfpp2000/Ozgur_Kilic_H_32_alii_3e-2.wav> ;
+ <http://www.europeana.eu/schemas/edm/isShownAt> <http://corpusdelaparole.huma-num.fr/corpus-app#/detail/crdo-CFPP2000_35_SOUND> ;
+ <http://www.europeana.eu/schemas/edm/isShownBy> <http://cocoon.huma-num.fr/data/archi/masters/372593.wav> ;
+ <http://www.europeana.eu/schemas/edm/provider> "Corpus de la Parole"@fr ;
+ <http://www.europeana.eu/schemas/edm/rights> <http://creativecommons.org/licenses/by-nc-sa/4.0/> .
+
+<http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-CFPP2000_35_SOUND> a <http://www.europeana.eu/schemas/edm/ProvidedCHO> ;
+ <http://purl.org/dc/terms/accessRights> "Freely available for non-commercial use" ;
+ <http://purl.org/dc/terms/created> "2010-11-17"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/extent> "PT48M26S" ;
+ <http://purl.org/dc/terms/issued> "2013-10-12T14:35:57+02:00"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
+ <http://purl.org/dc/elements/1.1/contributor> <http://viaf.org/viaf/93752300> , "Tanguy, Noalig" , "Chevrier, Michel" , "Kiliç, Ozgur" , "Salvegas, Etienne" , "du-Breuil-de-Pont-en-Auge, Augustin" , "du-Breuil-de-Pont-en-Auge, Benoît" ;
+ <http://purl.org/dc/elements/1.1/identifier> "ark:/87895/1.17-375004" , "%2$scrdo-CFPP2000_35_SOUNDid" , "oai:crdo.vjf.cnrs.fr:crdo-CFPP2000_35" , "Cote producteur: [03-01] Ozgur_Kilic_H_32_alii_3e"@fr , "ark:/87895/1.17-372593" , "oai:crdo.vjf.cnrs.fr:crdo-CFPP2000_35_SOUND" ;
+ <http://purl.org/dc/elements/1.1/language> <http://lexvo.org/id/iso639-3/fra> ;
+ <http://purl.org/dc/elements/1.1/publisher> <http://viaf.org/viaf/142432638>;
+ <http://purl.org/dc/elements/1.1/subject> <http://ark.bnf.fr/ark:/12148/cb13318415c> , "anthropological_linguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "lexicography"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "phonetics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , <http://lexvo.org/id/iso639-3/fra> , <http://ark.bnf.fr/ark:/12148/cb133188907> , <http://ark.bnf.fr/ark:/12148/cb11932762f> , "general_linguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , <http://ark.bnf.fr/ark:/12148/cb133183660> , "text_and_corpus_linguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "Français"@fr , <http://ark.bnf.fr/ark:/12148/cb122368540> , "phonology"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "semantics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "sociolinguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "syntax"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "typology"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , <http://ark.bnf.fr/ark:/12148/cb119418302> , <http://ark.bnf.fr/ark:/12148/cb135540729> , "discourse_analysis"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "historical_linguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , "language_documentation"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> , <http://ark.bnf.fr/ark:/12148/cb133192210> , <http://ark.bnf.fr/ark:/12148/cb119377452> , <http://ark.bnf.fr/ark:/12148/cb13320451h> , <http://ark.bnf.fr/ark:/12148/cb13318422n> , <http://ark.bnf.fr/ark:/12148/cb11975823c> , "mathematical_linguistics"^^<http://www.language-archives.org/OLAC/1.1/linguistic-field> ;
+ <http://purl.org/dc/elements/1.1/title> "Entretien de Ozgur Kiliç 2"@fr ;
+ <http://purl.org/dc/elements/1.1/type> <http://ark.bnf.fr/ark:/12148/cb11932135w> , <http://ark.bnf.fr/ark:/12148/cb12481481z> , <http://purl.org/dc/dcmitype/Sound> , "primary_text"^^<http://www.language-archives.org/OLAC/1.1/linguistic-type> , <http://purl.org/dc/dcmitype/Text> , "narrative"^^<http://www.language-archives.org/OLAC/1.1/discourse-type> , "report"^^<http://www.language-archives.org/OLAC/1.1/discourse-type> , "unintelligible_speech"^^<http://www.language-archives.org/OLAC/1.1/discourse-type> ;
+ <http://purl.org/dc/terms/available> "2013-10-12"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/spatial> [
+ a <http://www.europeana.eu/schemas/edm/Place> ;
+ owl:sameAs <http://sws.geonames.org/6618626/> ;
+ <http://www.w3.org/2003/01/geo/wgs84_pos#lat> "48.73194"^^xsd:float;
+ <http://www.w3.org/2003/01/geo/wgs84_pos#long> "7.70833"^^xsd:float;
+ <http://www.w3.org/2004/02/skos/core#note> "FR"^^<http://purl.org/dc/terms/ISO3166> , "France, Île-de-France, Paris, Université Sorbonne Nouvelle Paris 3, site Censier"@fr , "Domicile de Ozgur Kiliç"@fr , "France, Île-de-France, Paris 20"@fr
+ ];
+ <http://www.europeana.eu/schemas/edm/isGatheredInto> <http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-COLLECTION_LANGUESDEFRANCE> , <http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-COLLECTION_CFPP2000> ;
+ <http://www.language-archives.org/OLAC/1.1/depositor> <http://viaf.org/viaf/93752300> ;
+ <http://www.language-archives.org/OLAC/1.1/interviewer> <http://viaf.org/viaf/93752300> ;
+ <http://www.language-archives.org/OLAC/1.1/transcriber> "Tanguy, Noalig" ;
+ <http://purl.org/dc/elements/1.1/coverage> "Quartier concerné : 3e"@fr ;
+ <http://www.language-archives.org/OLAC/1.1/responder> "Chevrier, Michel" , "Kiliç, Ozgur" , "Salvegas, Etienne" , "du-Breuil-de-Pont-en-Auge, Augustin" , "du-Breuil-de-Pont-en-Auge, Benoît" ;
+ <http://purl.org/dc/elements/1.1/relation> <http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-CFPP2000_31_SOUND> .
+
+
+<http://cocoon.huma-num.fr/exist/crdo/cfpp2000/fra/Ozgur_Kilic_H_32_alii_3e-2.xml> a <http://www.europeana.eu/schemas/edm/WebResource> ;
+ <http://purl.org/dc/elements/1.1/format> "application/xml"^^<http://purl.org/dc/terms/IMT> ;
+ <http://purl.org/dc/terms/accessRights> "Freely available for non-commercial use" ;
+ <http://purl.org/dc/terms/created> "2010-11-17"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/issued> "2013-11-04T22:20:07+01:00"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
+ <http://purl.org/dc/terms/conformsTo> <http://purl.org/poi/crdo.vjf.cnrs.fr/crdo-dtd_transcriber> .
+
+<http://cocoon.huma-num.fr/data/archi/masters/372593.wav> a <http://www.europeana.eu/schemas/edm/WebResource> ;
+ <http://purl.org/dc/elements/1.1/format> "audio/x-wav"^^<http://purl.org/dc/terms/IMT> ;
+ <http://purl.org/dc/terms/accessRights> "Freely available for non-commercial use" ;
+ <http://purl.org/dc/terms/created> "2010-11-17"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/extent> "PT48M26S" ;
+ <http://purl.org/dc/terms/issued> "2013-10-12T14:35:57+02:00"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> .
+
+<http://cocoon.huma-num.fr/data/cfpp2000/Ozgur_Kilic_H_32_alii_3e-2.mp3> a <http://www.europeana.eu/schemas/edm/WebResource> ;
+ <http://purl.org/dc/elements/1.1/format> "audio/mpeg"^^<http://purl.org/dc/terms/IMT> ;
+ <http://purl.org/dc/terms/accessRights> "Freely available for non-commercial use" ;
+ <http://purl.org/dc/terms/created> "2010-11-17"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/extent> "PT48M26S" ;
+ <http://purl.org/dc/terms/issued> "2013-10-12T14:35:57+02:00"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
+ <http://www.europeana.eu/schemas/edm/isDerivativeOf> <http://cocoon.huma-num.fr/data/archi/masters/372593.wav> .
+
+<http://cocoon.huma-num.fr/data/cfpp2000/Ozgur_Kilic_H_32_alii_3e-2.wav> a <http://www.europeana.eu/schemas/edm/WebResource> ;
+ <http://purl.org/dc/elements/1.1/format> "audio/x-wav"^^<http://purl.org/dc/terms/IMT> ;
+ <http://purl.org/dc/terms/accessRights> "Freely available for non-commercial use" ;
+ <http://purl.org/dc/terms/created> "2010-11-17"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/extent> "PT48M26S" ;
+ <http://purl.org/dc/terms/issued> "2013-10-12T14:35:57+02:00"^^<http://purl.org/dc/terms/W3CDTF> ;
+ <http://purl.org/dc/terms/license> <http://creativecommons.org/licenses/by-nc-sa/3.0/> ;
+ <http://www.europeana.eu/schemas/edm/isDerivativeOf> <http://cocoon.huma-num.fr/data/archi/masters/372593.wav> .