PREFIX dct: <http://purl.org/dc/terms/>
PREFIX ontolex: <http://www.w3.org/ns/lemon/ontolex#>
PREFIX p: <http://www.wikidata.org/prop/>
PREFIX pq: <http://www.wikidata.org/prop/qualifier/>
PREFIX prov: <http://www.w3.org/ns/prov#>
PREFIX ps: <http://www.wikidata.org/prop/statement/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdno: <http://www.wikidata.org/prop/novalue/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
# Danish lexeme
# SELECT ?lexeme { ?lexeme dct:language wd:Q9035 }
START = @<danish-lexeme>
<danish-lexeme> {
dct:language [ wd:Q9035 ]
// rdf:label "language"
// rdf:comment "The language of a Danish lexeme must be Danish." ;
wikibase:lemma [ @da ]
// rdf:label "lemma"
// rdf:comment "The lemma must be Danish." ;
# Lexical category should be noun, verb, adjective, adverb,
wikibase:lexicalCategory [
wd:Q1084
wd:Q24905
wd:Q34698
wd:Q36224 # pronoun
wd:Q36484 # conjunction
wd:Q62155 # affix
wd:Q63116 # numeral
wd:Q103184 # article
wd:Q380057
wd:Q4833830 # preposition
wd:Q55064750 # formal subject
] ;
wdt:P31 IRI *
// rdf:label "instance of"
// rdf:comment "zero or more instance of" ;
wdt:P5187 [ @da ] *
// rdf:label "word stem"
// rdf:comment "zero or more word stems" ;
wdt:P1343 IRI *
// rdf:label "described in"
// rdf:comment "zero or more described in" ;
wdt:P5323 IRI *
// rdf:label "attested in"
// rdf:comment "zero or more attested in" ;
wdt:P5238 IRI {0,4}
// rdf:label "compound parts"
// rdf:comment "zero or up to four compound parts" ;
p:P5912 @<#oqaasileriffik-statement> +
// rdf:label "Oqaasileriffik ID"
// rdf:comment "Danish lexeme must have one or more Oqaasileriffik statement" ;
p:P6140 @<#dannet-statement>
// rdf:label "DanNet identifier"
// rdf:comment "Danish lexeme must have novalue or one DanNet statement" ;
p:P5831 @<#danish-usage-example-statement> +
// rdf:label "Usage example"
// rdf:comment "Danish lexeme must have one or more usage examples" ;
}
AND (
# If the lexeme is a compound then it must have a 'combines' proper
# with at least two parts
NOT { wdt:P31 wd:Q245423 }
OR { wdt:P5238 IRI {2,} }
)
<#danish-form> EXTRA a {
a [ ontolex:Form ] ;
wikibase:grammaticalFeature IRI * ;
ontolex:representation [ @da ] ;
p:P5279 @<#danish-hyphenation-statement> +
// rdf:label "Hyphenation"
// rdf:comment "Danish form most have novalue, or one or more value statements" ;
}
<#dannet-statement> EXTRA rdf:type {
a [ wdno:P6140 ] | ps:P6140 /^[0-9]{8}(-[1-9][0-9]*)?$/
// rdf:label "DanNet identifier"
// rdf:comment "DanNet identifier should either be novalue or a 8 digit string with possible suffix" ;
}
<#oqaasileriffik-statement> EXTRA a {
a [ wdno:P5912 ] | ps:P5912 /[1-9][0-9]*/
// rdf:label "Oqaasileriffik ID"
// rdf:comment "Must have novalue or one identifier for Oqaasileriffik online dictionary" ;
}
<#danish-usage-example-statement> EXTRA a {
ps:P5831 [ @da ] ;
pq:P5830 @<#danish-form> ;
prov:wasDerivedFrom IRI + ;
}
<#danish-hyphenation-statement> EXTRA a {
a [ wdno:P5279 ] | ps:P5279 /.+‧.+/ ;
}
