SPARQL queries: Difference between revisions

From Qichwabase
Jump to navigation Jump to search
(Puno Quechua lexical entries query)
 
(4 intermediate revisions by one other user not shown)
Line 1: Line 1:
Here you find some SPARQL queries that you can use, and also modify or combine.
Here you find some SPARQL queries that you can use, and also modify or combine. To start a query from scratch, you may use this:
<sparql tryit="1">
PREFIX qwb: <https://qichwa.wikibase.cloud/entity/>
PREFIX qdp: <https://qichwa.wikibase.cloud/prop/direct/>
PREFIX qp: <https://qichwa.wikibase.cloud/prop/>
PREFIX qps: <https://qichwa.wikibase.cloud/prop/statement/>
PREFIX qpq: <https://qichwa.wikibase.cloud/prop/qualifier/>
PREFIX qpr: <https://qichwa.wikibase.cloud/prop/reference/>
PREFIX qno: <https://qichwa.wikibase.cloud/prop/novalue/>
 
SELECT * WHERE {}
</sparql>
=Lexical Entries=
=Lexical Entries=
==Puno Quechua Lexical entries ==
<sparql tryit="1">
#This is a list of Puno Quechua Lexical entries
PREFIX qwb: <https://qichwa.wikibase.cloud/entity/>
PREFIX qdp: <https://qichwa.wikibase.cloud/prop/direct/>
PREFIX qp: <https://qichwa.wikibase.cloud/prop/>
PREFIX qps: <https://qichwa.wikibase.cloud/prop/statement/>
PREFIX qpq: <https://qichwa.wikibase.cloud/prop/qualifier/>
PREFIX qpr: <https://qichwa.wikibase.cloud/prop/reference/>
PREFIX qno: <https://qichwa.wikibase.cloud/prop/novalue/>
SELECT ?entry ?lemma ?language ?lexical_category ?lex_cat_wikidata ?described_in
?form_representation ?spelling_variant
?sense_gloss_de ?sense_gloss_en ?sense_gloss_es ?sense_gloss_it
WHERE {
BIND("Q5218" AS ?language) #assigning Q5218 = Quechua Wikidata as the language
BIND("qu-x-Q7260479" AS ?spelling_variant) #Assigning the language-code for the form
BIND("Q24905" AS ?lex_cat_wikidata) #Assignning Q24905 = Verb Wikidata as the lexical category
?entry a ontolex:LexicalEntry;
      wikibase:lemma ?lemma;
      wikibase:lexicalCategory qwb:Q99 ; #Category Q99 = V.tr Qichwabase
      wikibase:lexicalCategory [rdfs:label ?lexical_category] ;     
      qp:P16 [qps:P16 ?form_representation;
              qpq:P17 qwb:Q116; #Q116 = Cusco-Collao (aiu) Qichwabase
            ].
OPTIONAL {
  ?entry ontolex:lexicalForm ?form1 .
  ?form1 ontolex:representation ?wform1;
        wikibase:grammaticalFeature [rdfs:label ?wf1_gram_feature_label] .
        FILTER(LANG(?featureLabel)="es")
}
OPTIONAL {
  ?entry ontolex:sense ?sense_de .
  ?sense_de skos:definition ?sense_gloss_de.
  FILTER(LANG(?sense_gloss_de)="de")
}
OPTIONAL {
  ?entry ontolex:sense ?sense_en .
  ?sense_en skos:definition ?sense_gloss_en.
  FILTER(LANG(?sense_gloss_en)="en")
}
#OPTIONAL {      # at least contains spanish gloss
  ?entry ontolex:sense ?sense_es .
  ?sense_es skos:definition ?sense_gloss_es.
  FILTER(LANG(?sense_gloss_es)="es")
#}
OPTIONAL {
  ?entry ontolex:sense ?sense_it .
  ?sense_it skos:definition ?sense_gloss_it.
  FILTER(LANG(?sense_gloss_it)="it")
}
}
LIMIT 10
==Lexical entries with lemma and pos==
<sparql tryit="1">
<sparql tryit="1">
# this lists all lexcial entries, with lemma and pos, ordered alphabetically by lemma
# this lists all lexcial entries, with lemma and pos, ordered alphabetically by lemma
Line 10: Line 75:
order by lcase(?lemma)
order by lcase(?lemma)
</sparql>
</sparql>
==Problematic lexical entries==
<sparql tryit="1">
# this lists all lexical entries with bracket, semicolon, or comma in the lemma sign
select ?entry ?lemma ?posLabel
where {?entry a ontolex:LexicalEntry;
                wikibase:lemma ?lemma;
                wikibase:lexicalCategory [rdfs:label ?posLabel].
                  filter(lang(?posLabel)="en")
                  filter(regex(?lemma,'[();,]'))}
order by lcase(?lemma)
</sparql>
=Senses and sense descriptions=
<sparql tryit="1">
#this lists entries that have senses and sense descriptions
select ?entry ?lemma ?posLabel (group_concat(concat(str(?sensegloss)," (",lang(?sensegloss),")");SEPARATOR="; ") as ?sense_descriptions)
where {
?entry a ontolex:LexicalEntry;
      wikibase:lemma ?lemma;
      wikibase:lexicalCategory [rdfs:label ?posLabel] . filter(lang(?posLabel)="en")
?entry ontolex:sense [skos:definition ?sensegloss].
} group by ?entry ?lemma ?posLabel ?sense_descriptions
limit 100 # remove the limit and get all entries that have sense descriptions
</sparql>
=Dialectal lemma variants=
=Dialectal lemma variants=
<sparql tryit="1">
<sparql tryit="1">

Latest revision as of 14:38, 20 April 2024

Here you find some SPARQL queries that you can use, and also modify or combine. To start a query from scratch, you may use this:

PREFIX qwb: <https://qichwa.wikibase.cloud/entity/>
PREFIX qdp: <https://qichwa.wikibase.cloud/prop/direct/>
PREFIX qp: <https://qichwa.wikibase.cloud/prop/>
PREFIX qps: <https://qichwa.wikibase.cloud/prop/statement/>
PREFIX qpq: <https://qichwa.wikibase.cloud/prop/qualifier/>
PREFIX qpr: <https://qichwa.wikibase.cloud/prop/reference/>
PREFIX qno: <https://qichwa.wikibase.cloud/prop/novalue/>

SELECT * WHERE {}

Try it!

Lexical Entries

Puno Quechua Lexical entries

#This is a list of Puno Quechua Lexical entries 
PREFIX qwb: <https://qichwa.wikibase.cloud/entity/>
PREFIX qdp: <https://qichwa.wikibase.cloud/prop/direct/>
PREFIX qp: <https://qichwa.wikibase.cloud/prop/>
PREFIX qps: <https://qichwa.wikibase.cloud/prop/statement/>
PREFIX qpq: <https://qichwa.wikibase.cloud/prop/qualifier/>
PREFIX qpr: <https://qichwa.wikibase.cloud/prop/reference/>
PREFIX qno: <https://qichwa.wikibase.cloud/prop/novalue/>

SELECT ?entry ?lemma ?language ?lexical_category ?lex_cat_wikidata ?described_in 
?form_representation ?spelling_variant 
?sense_gloss_de ?sense_gloss_en ?sense_gloss_es ?sense_gloss_it
WHERE {
BIND("Q5218" AS ?language) #assigning Q5218 = Quechua Wikidata as the language
BIND("qu-x-Q7260479" AS ?spelling_variant) #Assigning the language-code for the form
BIND("Q24905" AS ?lex_cat_wikidata) #Assignning Q24905 = Verb Wikidata as the lexical category
?entry a ontolex:LexicalEntry; 
       wikibase:lemma ?lemma;
       wikibase:lexicalCategory qwb:Q99 ; #Category Q99 = V.tr Qichwabase
       wikibase:lexicalCategory [rdfs:label ?lexical_category] ;       
       qp:P16 [qps:P16 ?form_representation;
               qpq:P17 qwb:Q116; #Q116 = Cusco-Collao (aiu) Qichwabase
             ]. 
OPTIONAL {
  ?entry ontolex:lexicalForm ?form1 .
  ?form1 ontolex:representation ?wform1;
         wikibase:grammaticalFeature [rdfs:label ?wf1_gram_feature_label] .
         FILTER(LANG(?featureLabel)="es")
}
OPTIONAL {
  ?entry ontolex:sense ?sense_de .
  ?sense_de skos:definition ?sense_gloss_de.
  FILTER(LANG(?sense_gloss_de)="de")
}
OPTIONAL {
  ?entry ontolex:sense ?sense_en .
  ?sense_en skos:definition ?sense_gloss_en.
  FILTER(LANG(?sense_gloss_en)="en")
}
#OPTIONAL {      # at least contains spanish gloss
  ?entry ontolex:sense ?sense_es .
  ?sense_es skos:definition ?sense_gloss_es.
  FILTER(LANG(?sense_gloss_es)="es")
#}
OPTIONAL {
  ?entry ontolex:sense ?sense_it .
  ?sense_it skos:definition ?sense_gloss_it.
  FILTER(LANG(?sense_gloss_it)="it")
}
}
LIMIT 10
==Lexical entries with lemma and pos==
<sparql tryit="1">
# this lists all lexcial entries, with lemma and pos, ordered alphabetically by lemma
select ?entry ?lemma ?posLabel 
where {?entry a ontolex:LexicalEntry; 
                wikibase:lemma ?lemma;
                wikibase:lexicalCategory [rdfs:label ?posLabel]. 
                  filter(lang(?posLabel)="en")}
order by lcase(?lemma)

Try it!

Problematic lexical entries

# this lists all lexical entries with bracket, semicolon, or comma in the lemma sign
select ?entry ?lemma ?posLabel 
where {?entry a ontolex:LexicalEntry; 
                wikibase:lemma ?lemma;
                wikibase:lexicalCategory [rdfs:label ?posLabel]. 
                  filter(lang(?posLabel)="en")
                  filter(regex(?lemma,'[();,]'))}
order by lcase(?lemma)

Try it!


Senses and sense descriptions

#this lists entries that have senses and sense descriptions
select ?entry ?lemma ?posLabel (group_concat(concat(str(?sensegloss)," (",lang(?sensegloss),")");SEPARATOR="; ") as ?sense_descriptions)
where {

?entry a ontolex:LexicalEntry; 
       wikibase:lemma ?lemma;
       wikibase:lexicalCategory [rdfs:label ?posLabel] . filter(lang(?posLabel)="en")
?entry ontolex:sense [skos:definition ?sensegloss].

} group by ?entry ?lemma ?posLabel ?sense_descriptions
limit 100 # remove the limit and get all entries that have sense descriptions

Try it!


Dialectal lemma variants

#defaultView:BarChart
#This shows the distribution of dialectal lemma variants
PREFIX qp: <https://qichwa.wikibase.cloud/prop/>
PREFIX qps: <https://qichwa.wikibase.cloud/prop/statement/>
PREFIX qpq: <https://qichwa.wikibase.cloud/prop/qualifier/>

SELECT ?dialect ?dialectLabel (count (?variant) as ?variants)
WHERE { ?lemma qp:P16 [ qps:P16 ?variant ; qpq:P17 ?dialect ] .
        SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
      }
GROUP BY ?dialect ?dialectLabel ?variants ORDER BY DESC(?variants)

Try it!

Part of speech (lexical category)

Course-grained (lexical category superclasses)

#defaultView:BarChart
PREFIX qdp: <https://qichwa.wikibase.cloud/prop/direct/>

select ?pos ?posLabel (count(?entry) as ?count)
where {
?entry a ontolex:LexicalEntry; 
       wikibase:lemma ?lemma;
       wikibase:lexicalCategory ?pos_finegrained.
       ?pos_finegrained qdp:P4 ?pos. ?pos rdfs:label ?posLabel . filter(lang(?posLabel)="en")
} group by ?pos ?posLabel ?count
order by desc(?count)

Try it!

Fine-grained (lexical categories as in Runasimi Dictionary)

#defaultView:BarChart
#this shows pos distribution (fine-grained categories as in Runasimi dictionary)
select ?pos ?posLabel (count(?entry) as ?count)
where {
?entry a ontolex:LexicalEntry; 
       wikibase:lemma ?lemma;
       wikibase:lexicalCategory ?pos. ?pos rdfs:label ?posLabel . filter(lang(?posLabel)="en")
} group by ?pos ?posLabel ?count
order by desc(?count)

Try it!