Help

Difference between revisions of "SPARQL"

Help:SPARQL gathers a list of SPARQL queries in the context of Lingua Libre, ready to use, alongside with beginner-friendly inline-comments, introductions to concepts, code snippets and a few tools. To dive into it, first check the content's structure visible in the outline. This page allows users not familiar with SPARQL to easily query the LinguaLibre knowledge graph, and to download or directly feed that data into an application. To fit with most frequent uses, the page focuses towards web development.
 
(9 intermediate revisions by the same user not shown)
Line 362: Line 362:
 
|style="padding: 0 3em;width:60%"|
 
|style="padding: 0 3em;width:60%"|
 
<syntaxhighlight lang="sparql">
 
<syntaxhighlight lang="sparql">
 +
#defaultEndpoint:Lingualibre
 
SELECT ?genderLabel (count(?speaker) AS ?nb)
 
SELECT ?genderLabel (count(?speaker) AS ?nb)
 
WHERE {
 
WHERE {
Line 374: Line 375:
 
||
 
||
 
<query _pagination="5" >
 
<query _pagination="5" >
 +
#defaultEndpoint:Lingualibre
 
SELECT ?genderLabel (count(?speaker) AS ?nb)
 
SELECT ?genderLabel (count(?speaker) AS ?nb)
 
WHERE {
 
WHERE {
Line 491: Line 493:
  
 
== Languages ==
 
== Languages ==
 +
=== 🇶 LL Language (Q930) → List of words recorded ===
 +
''This query could be run on Wikimedia Commons MediaWiki API. See [[Help:APIs]].''
 +
<!-- Q: Change exact match by CONTAINS() -->
 +
{| style="width:100%"
 +
|- style="vertical-align:top;"
 +
|style="padding: 0 3em;width:60%"|
 +
<syntaxhighlight lang="sparql">
 +
#defaultEndpoint:Wikidata
 +
PREFIX prop: <https://lingualibre.org/prop/direct/>
 +
PREFIX entity: <https://lingualibre.org/entity/>
 +
SELECT ?writing WHERE {
 +
  SERVICE <https://lingualibre.org/sparql> {
 +
    SELECT ?writing WHERE {
 +
      ?record prop:P2 entity:Q2;
 +
        prop:P4 entity:Q930, ?language;
 +
        prop:P3 ?url;
 +
        prop:P7 ?writing.
 +
    # FILTER(CONTAINS(STR(?audio), "LL-Q35735")) # occitan
 +
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
 +
    }
 +
  }
 +
}
 +
</syntaxhighlight>
 +
||
 +
<query _pagination="5">
 +
#defaultEndpoint:Wikidata
 +
PREFIX prop: <https://lingualibre.org/prop/direct/>
 +
PREFIX entity: <https://lingualibre.org/entity/>
 +
SELECT ?writing WHERE {
 +
  SERVICE <https://lingualibre.org/sparql> {
 +
    SELECT ?writing WHERE {
 +
      ?record prop:P2 entity:Q2;
 +
        prop:P4 entity:Q930, ?language;
 +
        prop:P3 ?url;
 +
        prop:P7 ?writing.
 +
    # FILTER(CONTAINS(STR(?audio), "LL-Q35735")) # occitan
 +
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
 +
    }
 +
  }
 +
}
 +
</query>
 +
|}
 +
 
=== 🇶 Language name(s) in English → Language LL Qid(s) ===
 
=== 🇶 Language name(s) in English → Language LL Qid(s) ===
 
''This query has been UPDATED to work on Commons SPARQL Endpoint. ''
 
''This query has been UPDATED to work on Commons SPARQL Endpoint. ''
Line 1,090: Line 1,135:
 
|style="padding: 0 3em;width:60%"|
 
|style="padding: 0 3em;width:60%"|
 
<syntaxhighlight lang="sparql">
 
<syntaxhighlight lang="sparql">
 +
#defaultEndpoint:Lingualibre
 
SELECT ?languageQidLabel ?wdQid ?languageQid ?isoCode  
 
SELECT ?languageQidLabel ?wdQid ?languageQid ?isoCode  
 
(COUNT(DISTINCT(?record)) AS ?recordCount)
 
(COUNT(DISTINCT(?record)) AS ?recordCount)
Line 1,115: Line 1,161:
 
||
 
||
 
<pre>
 
<pre>
 +
#defaultEndpoint:Lingualibre
 
languageQidLabel wdQid languageQid isoCode recordCount speakerM speakerF
 
languageQidLabel wdQid languageQid isoCode recordCount speakerM speakerF
 
French Q150 Q21 fra 16761 0 18
 
French Q150 Q21 fra 16761 0 18
Line 1,125: Line 1,172:
 
=== ❌ Is Language ([[Q3]]) → list all languages with number of unique words and speakers ===
 
=== ❌ Is Language ([[Q3]]) → list all languages with number of unique words and speakers ===
 
<syntaxhighlight lang="sparql">
 
<syntaxhighlight lang="sparql">
 +
#defaultEndpoint:Lingualibre
 
SELECT ?language (COUNT(?audio) AS ?nbAudio) (COUNT(?speaker) AS ?nbSpeaker) WHERE {
 
SELECT ?language (COUNT(?audio) AS ?nbAudio) (COUNT(?speaker) AS ?nbSpeaker) WHERE {
 
   ?language prop:P2 entity:Q4 .
 
   ?language prop:P2 entity:Q4 .
Line 1,141: Line 1,189:
 
|style="padding: 0 3em;width:60%"|
 
|style="padding: 0 3em;width:60%"|
 
<syntaxhighlight lang="sparql">
 
<syntaxhighlight lang="sparql">
 +
#defaultEndpoint:Lingualibre
 
select ?record ?recordLabel ?speakerLabel ?languageLabel ?languageLevelLabel
 
select ?record ?recordLabel ?speakerLabel ?languageLabel ?languageLevelLabel
 
where {
 
where {
Line 1,159: Line 1,208:
 
||
 
||
 
<query _pagination="5">
 
<query _pagination="5">
 +
#defaultEndpoint:Lingualibre
 
select ?record ?recordLabel ?speakerLabel ?languageLabel ?languageLevelLabel
 
select ?record ?recordLabel ?speakerLabel ?languageLabel ?languageLevelLabel
 
where {
 
where {
Line 1,220: Line 1,270:
 
#defaultEndpoint:Lingualibre
 
#defaultEndpoint:Lingualibre
 
SELECT
 
SELECT
 +
(COUNT(DISTINCT ?record) AS ?records)
 
(COUNT(DISTINCT ?speaker) AS ?speakers)
 
(COUNT(DISTINCT ?speaker) AS ?speakers)
−
(COUNT(DISTINCT ?record) AS ?records)
+
(COUNT(DISTINCT ?language) AS ?languages)
 
WHERE {
 
WHERE {
 
   ?record prop:P2 entity:Q2 .
 
   ?record prop:P2 entity:Q2 .
 
   ?record prop:P6 ?date .
 
   ?record prop:P6 ?date .
 
   ?record prop:P5 ?speaker .
 
   ?record prop:P5 ?speaker .
 +
  ?record prop:P4 ?language .
 
   # Filters:
 
   # Filters:
−
   FILTER(?date >= "2018-07-01T00:00:00Z"^^xsd:dateTime)
+
   FILTER(?date >= "2018-07-01T00:00:00Z"^^xsd:dateTime  
−
  FILTER(?date < "2019-01-01T00:00:00Z"^^xsd:dateTime)
+
      && ?date < "2019-01-01T00:00:00Z"^^xsd:dateTime)
 
}
 
}
 
</syntaxhighlight>
 
</syntaxhighlight>
Line 1,235: Line 1,287:
 
#defaultEndpoint:Lingualibre
 
#defaultEndpoint:Lingualibre
 
SELECT
 
SELECT
 +
(COUNT(DISTINCT ?record) AS ?records)
 
(COUNT(DISTINCT ?speaker) AS ?speakers)
 
(COUNT(DISTINCT ?speaker) AS ?speakers)
−
(COUNT(DISTINCT ?record) AS ?records)
+
(COUNT(DISTINCT ?language) AS ?languages)
 
WHERE {
 
WHERE {
 
   ?record prop:P2 entity:Q2 .
 
   ?record prop:P2 entity:Q2 .
 
   ?record prop:P6 ?date .
 
   ?record prop:P6 ?date .
 
   ?record prop:P5 ?speaker .
 
   ?record prop:P5 ?speaker .
 +
  ?record prop:P4 ?language .
 
   # Filters:
 
   # Filters:
−
   FILTER(?date >= "2018-07-01T00:00:00Z"^^xsd:dateTime)
+
   FILTER(?date >= "2018-07-01T00:00:00Z"^^xsd:dateTime  
−
  FILTER(?date < "2019-01-01T00:00:00Z"^^xsd:dateTime)
+
      && ?date < "2019-01-01T00:00:00Z"^^xsd:dateTime)
 
}
 
}
 
</query>
 
</query>
Line 1,256: Line 1,310:
 
* [[:mw:Manual:Developing extensions]] — PHP-based modules enhancing wikis, can pull data via SPARQL queries.
 
* [[:mw:Manual:Developing extensions]] — PHP-based modules enhancing wikis, can pull data via SPARQL queries.
  
−
{{Lingua Libre scripts}}
+
{{Technicals}}
  
 
[[Category:Lingua Libre:Help{{#translation:}}]]
 
[[Category:Lingua Libre:Help{{#translation:}}]]

Latest revision as of 11:23, 28 April 2024


Draft
Twemoji12 1f3d7.svg
Twemoji12 1f3d7.svg

December 2021 rewriting : work in progress, please do not translate yet.
  1. NOW/Opened: General content review. You may help by: a) reading and copy-editing the page's English, b) testing queries on LLQS, edit in or discuss improvements, 3) increase comments' concistency.
  2. Legend: 🇶 minor aspects to improve, see hidden comment ; ❌ query too heavy to run in this page.
  3. Later/not yet: translations.

Help welcome.

Base

Useful elements

... Loading ...

Tools

On Wikidata, the WDQS allows to practice SPARQL queries creation in an intuitive way.

References

Code snippets

Fetch data using SPARQL

LinguaLibre data can be fetched using various coding languages such as Python, Javascript, R and others, returning JSON or other formats.

  • For code snippet in your language : open query.wikidata.org (WikiData Query Service, aka WDQS), run your SPARQL query, click "Code" : a pop up window appears with various implementations.
  • For downloading data, click "Download".

Javascript:
At least 3 methods exists (code snippet), example:

Query Result's basic unit
SPARQL:
SELECT ?item WHERE { ?item prop:P2 entity:Q5 } LIMIT 10

{ … },
{
  "item": {
    "type": "uri",
    "value": "https://lingualibre.org/entity/Q12"
  },
  "itemLabel": {
    "xml:lang": "en",
    "type": "literal",
    "value": "beginner"
  }
},
{ … }
Javascript: 
var endpoint = 'https://lingualibre.org/sparql';
var sparql = 'SELECT ?item WHERE { ?item prop:P2 entity:Q5 } LIMIT 10';
$.getJSON(endpoint,
	{ query: sparql, format: 'json' },
	function(data){ console.log('JQuery: ',data)}
);

Merging data

Advanced SPARQL queries with COUNT() and others are often slow (>3secs, sometime >100secs). You are encouraged to do multiple smaller SPARQL queries to then merge their responded data. By example, the complementary Javascript snippet below would help web developers to do so. 

// Data from 3 sparql queries.
// Important: One key must be similar in all datasets, here: 'qid'
const langs = [{ qid: 'Q209', label: 'Breton', iso:'bre' }, { qid: 'Q34', label: 'Marathi', iso: 'mar' }],
    speakersFemales = [{ qid: 'Q209', genderF: 3, recordsF: 60 }, { qid: 'Q34', genderF: 21, recordsF:5046 }],
    speakersMales = [{ qid: 'Q209', genderM: 7, recordsM: 218 }, { qid: 'Q34', genderM: 85, recordsM:32964 }];
// Toolbox for merging data by same id
var merge2ArraysBySameId = function(arr1,arr2,id1){
	return arr1.map( item1 => { 
  	var identical = arr2.find(obj => obj[id1] === item1[id1]); 
  	return Object.assign(identical, item1) 
  } );
}
// Mergings
var step1 = merge2ArraysBySameId(langs,speakersFemales,'qid');
var step2 = merge2ArraysBySameId(step1,speakersMales,'qid');
alert(JSON.stringify(step2))

Lingualibre's ground

Is Language (d:Q34770) → List existing languages with: LL Qid, ISO 639-3, Name

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?lang ?iso ?langLabel
WHERE {
  # First get the relevant languages by first looking up all records
  {
    SELECT DISTINCT ?lang WHERE {
      _:record wdt:P31 wd:Q108167708 ; # Filter to get wd:Q108167708 (pronunciation file)
               wdt:P407 ?lang .        # For each pronunciation file, fetch the language
    }
  }
  
  # From this point on, ?lang is bound. Get the label and ISO code on Wikidata
  SERVICE <https://query.wikidata.org/sparql> {
    ?lang wdt:P31 wd:Q34770 .  # Filter: P31 'instance of' is Q1193409 'language or dialect'.
    ?lang wdt:P220 ?iso .      # Assign value: P220 'ISO-639-3' into ?iso.
  }

  SERVICE wikibase:label {
    # Add label to each variable used.
    # ?lang now has twin variable ?langLabel
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Is Speaker (speaker (Q3)) → List existing speakers

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?speaker ?speakerLabel
WHERE {
  ?speaker prop:P2 entity:Q3 .  # Filter: P2 'instance of' is Q3 'speaker'.
  # Add labels to each variable used.
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Is Language level (language level (Q5)) → List existing levels

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?item ?itemLabel
WHERE {
  ?item prop:P2 entity:Q5    # Filter: P2 'instance of' is Q5 'language level'.
  # Add labels to each variable used.
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Is Sex or Gender (sex or gender (Q7)) → List existing sexes or genders

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?item ?itemLabel
WHERE {
  ?item prop:P2 entity:Q7    # Filter: P2 'instance of' is Q7 'sex or gender'.
  # Add labels to each variable used.
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Speaker

🇶 Speaker name(s) → Speaker Qid(s)

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?speakerName ?speakerId
WHERE {
  VALUES ?speakerName { "Yug" "VIGNERON" } # Assign value: one or multiple values
  # note: need to comment BIND
  BIND ( STRLANG(?speakerName, "en") AS ?speakerLabel )
  # Grammatical note: ';' allows to chain actions 
  ?speakerId prop:P2 entity:Q3 ;        # Filter: P2 'instance of' is Q3 'speaker'.
             rdfs:label ?speakerLabel . # Filter by value: label equal ?speakerLabel's value
}
... Loading ...

🇶 Speaker Qid (SangeetaRH (Q445757)) → Speaker data, all

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
# Get Q445757 (User:SangeetaRH‎)'s data
SELECT ?anyProperty ?anyValue ?anyValueLabel
WHERE {
  entity:Q445757 ?anyProperty ?anyValue .  # Filter: of Q445757 'SangeetaRH‎', get any property and any values
  # Add labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

🇶 Speaker Qid (SangeetaRH (Q445757)) → Speaker languages (P4)

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?languages ?languagesLabel
WHERE {
  entity:Q445757 prop:P4 ?languages . # Assign value: for Q445757 'SangeetaRH‎', P4 'language' into ?languages
  # Add labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

🇶 Count speaker gender (P8)

#defaultEndpoint:Lingualibre
SELECT ?genderLabel (count(?speaker) AS ?nb)
WHERE {
  ?speaker prop:P2 entity:Q3 ;
           prop:P8 ?gender .
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
GROUP BY ?genderLabel
... Loading ...

Speaker Qid (speakers/1 ???) + Language LL Qid (d:Q1571) → List records

This query is IN WORK for Commons SPARQL Endpoint. One Wikidata property is missing; please update this query with the right property URI. 

#defaultEndpoint:Commons
SELECT ?audio ?audioLabel
WHERE {
  ?audio wdt:SPEAKER_PROPERTY_MISSING <http://lingualibre.org/speakers/1> ; # Filter: ??? 'speaker' P5 Speaker is User:SangeetaRH
         wdt:P407 wd:Q1571 .   # Filter: P407 'language' is Q1571 'Marathi'
  
  # Add labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Speaker Qid (speakers/1 ???) + Language LL Qid (d:Q1571) → Count records

This query is IN WORK for Commons SPARQL Endpoint. One Wikidata property is missing; please update this query with the right property URI. 

#defaultEndpoint:Commons
SELECT ?language ?speaker (COUNT(?audio) AS ?audio)
WHERE {
  # Comment out the below pattern to filter by language, e.g. Q1571 or others
  # VALUES ?language { wd:Q1571 }  # Bind value: Q1571 'Marathi' into ?language
  VALUES ?speaker { <http://lingualibre.org/speakers/1> }   # Assign value: ll.org/speakers/1 (for 'SangeetaRH') into ?speaker
  
  ?audio wdt:SPEAKER_PROPERTY_MISSING ?speaker ; # Filter: ??? 'speaker' is ?speaker
         wdt:P407 ?language ;                    # Filter: P407 'language' bound to ?language
         wdt:P31 wd:Q108167708 .                 # Filter: P31 'instance of' is Q108167708 'pronunciation file'
}
GROUP BY ?language ?speaker  # Sorting first groups per language and speaker
... Loading ...

Is Speaker (speaker (Q3)) → List of accounts and associated speakers

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?linkedUser ?speakerLabel (SUBSTR(STR(?speaker),32) AS ?speakerQid)
WHERE {
  ?speaker prop:P2 entity:Q3 .  # Filter: P2 'instance of' is Q3 'speaker'.
  ?speaker prop:P11 ?linkedUser . # Assign value: P11 'linked users' into ?linkedUser.
  # Add labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
} ORDER BY DESC (?speakerLabel)
... Loading ...

Languages

🇶 LL Language (Q930) → List of words recorded

This query could be run on Wikimedia Commons MediaWiki API. See Help:APIs. 

#defaultEndpoint:Wikidata
PREFIX prop: <https://lingualibre.org/prop/direct/>
PREFIX entity: <https://lingualibre.org/entity/>
SELECT ?writing WHERE {
  SERVICE <https://lingualibre.org/sparql> {
    SELECT ?writing WHERE {
      ?record prop:P2 entity:Q2;
        prop:P4 entity:Q930, ?language;
        prop:P3 ?url;
        prop:P7 ?writing.
    # FILTER(CONTAINS(STR(?audio), "LL-Q35735")) # occitan
      SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
    }
  }
}
... Loading ...

🇶 Language name(s) in English → Language LL Qid(s)

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?languageId ?languageName 
WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    VALUES ?languageName { "Marathi" "Atikamekw" "Central Bikol" } # Target values
    
    BIND ( STRLANG(?languageName, "en") AS ?languageLabel ) # Bind filter by English
    
    ?languageId rdfs:label ?languageLabel ;  # Assign value label into ?languageLabel
                wdt:P31 wd:Q34770 .          # Filter: P2 'instance of' is Q4 'language' AND
    
  }
}
... Loading ...

Language ISO-639-3 → Language LL Qid(s), Wikidata Qid, Label

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?langIso ?langId ?langIdLabel
WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    VALUES ?langIso { "mar" "bre" "bcl" "atj" "ban" } # Target ISO values
    ?langId 
      wdt:P220 ?langIso ;    # Assign value: P13 'Iso-639-3' to ?langIso AND
      wdt:P31 wd:Q34770 ;    # Filter: P2 'instance of' is Q4 'language' 

  }

  # Labels
  SERVICE wikibase:label {bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en"}
}
... Loading ...

Language LL All Languages → Count records

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?language ?languageLabel ?audios WHERE {
  { 
    SELECT ?language (COUNT(?audio) AS ?audios) WHERE {
    # Comment out the below statement to filter to only certain languages (e.g. Q34 or others)
    # VALUES ?language { entity:Q34 }

    ?audio wdt:P31 wd:Q108167708 ;  # Filter: P2 'instance of' is Q2 'record'
           wdt:P407 ?language .
  }
   GROUP BY ?language
  }

  SERVICE <https://query.wikidata.org/sparql> {
    SERVICE wikibase:label { 
      bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en".
      ?language rdfs:label ?languageLabel .
    }
  }
}
... Loading ...

🇶 Language LL All Languages → Count unique words, audios, ratio

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?language ?languageLabel ?words ?audios ?percent
WHERE {
  {
    SELECT ?language
           (COUNT(DISTINCT(?itemLabel)) AS ?words)  # Count and assign value to ?Audio
           (COUNT(?audio) as ?audios) 
           (ROUND(10000*?words/?audios)/100 AS ?percent)
           WHERE {
             # Uncomment the below line to filter languages (e.g Q34 or others)
             # VALUES ?language { wd:Q34 }
             ?audio wdt:P407 ?language ;      # Bind property P407 'language' to ?language
                    wdt:P31 wd:Q108167708 ;   # Filter: P31 'instance of' Q108167708 (pronunciation file)
                    wdt:P9533 ?itemLabel .   # Bind P9533 'transcription' to ?itemLabel.
           }
    GROUP BY ?language ?languageLabel
  }

 
    SERVICE <https://query.wikidata.org/sparql> {
      SERVICE wikibase:label { 
        bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en".
        ?language rdfs:label ?languageLabel .
      }
  }
}
... Loading ...

Language LL All Languages → Count speakers

This query is IN WORK for Commons SPARQL Endpoint. One Wikidata property is missing; please update this query with the right property URI. 

#defaultEndpoint:Commons
SELECT ?language ?languageLabel ?speakers WHERE {
  {
    SELECT ?language (COUNT(?speaker) AS ?speakers) WHERE {

      # Uncomment the below line to filter to specific languages
      # E.g Q34 and others
      # VALUES ?language { wd:Q34 }

      ?record wdt:P407 ?language ;                    # Bind P407 'language' to ?language (if unbound)
              wdt:P31 wd:Q108167708 ;                 # P31 'instance of' Q108167708 'pronunciation file'
              wdt:SPEAKER_PROPERTY_MISSING ?speaker ; # Bind ??? 'speaker' to ?speaker
    } GROUP BY ?language
  }
  
  SERVICE <https://query.wikidata.org/sparql> {
    SERVICE wikibase:label { 
      bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". 
      ?language rdfs:label ?languageLabel
    }
  }
}
... Loading ...

Language LL Qid (Q209) → List speakers

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT ?language ?speaker ?speakerLabel WHERE {
  VALUES ?language { entity:Q209 }
  ?speaker prop:P2 entity:Q3 .  # P2 'instance of' is Q3 'speaker'
  ?speaker prop:P4 ?language .  # P4 'language' is Q34 'Marathi'
  # Labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Language LL Qid (d:Q12107) → Language data, all

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?predicate ?object WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    # Given Q12107 language, get all properties and values
    wd:Q12107 ?predicate ?object .
  }
}
... Loading ...

Language LL Qid (d:Q12107) → Language data, Literals

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT * WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    # Given Q12107 'Breton language', get only literals
    wd:Q12107 ?predicate ?object .
    ?predicate rdf:type owl:DatatypeProperty .
  }
}
... Loading ...

Language LL Qid (d:Q12107) → Property P220 (ISO 639-3)

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT * WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    wd:Q12107 wdt:P220 ?iso . # Assign value : Q209 'Breton', P13 'ISO 639-3', value into ?iso
  }
}
... Loading ...

Languages → List existing languages' iso-639-3

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT * WHERE {
  SERVICE <https://query.wikidata.org/sparql> {
    ?lang wdt:P220 ?code .
  }
}
... Loading ...

🇶 Language WD Qid → Language data, core

This query is going to be DEPRECATED as the queried data will no longer be available. 

#defaultEndpoint:Lingualibre
SELECT * WHERE {
  ?lang prop:P12 "Q12107" .  # Filter: P12 'Wikidata id' is Wikidata's "Q12107"
  ?lang ?predicate ?object . # 
  ?predicate rdf:type owl:DatatypeProperty .
}
... Loading ...

Records

Record LL Qid (sdc:M69288741) → Record data, all

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT * WHERE {
  sdc:M69288741 ?predicate ?object .
}
... Loading ...

Record LL Qid (sdc:M69288741) → Record data, core

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT * WHERE {
  sdc:M69288741 ?predicate ?object .

  SERVICE <https://query.wikidata.org/sparql> {
    ?predicate rdf:type owl:DatatypeProperty . 
  } 
}
... Loading ...

Language (d:Q1860) + String → Record LL Qid(s)

This query has been UPDATED to work on Commons SPARQL Endpoint. 

#defaultEndpoint:Commons
SELECT ?item
WHERE { 
  ?item wdt:P31 wd:Q108167708 . # Filter: P31 'instance of' Q108167708 'record'
  ?item wdt:P407 wd:Q1860 .     # Filter: P407 'language' is Q1860 'English'
  ?item wdt:P9533 "apple"@en.   # Filter: P9533 'transcription' is "apple"
}
... Loading ...

Language (d:Q12107) + Speaker (/speakers/1 ??) + String (ni) → Record LL Qid

This query is IN WORK for Commons SPARQL Endpoint. One Wikidata property is missing; please update this query with the right property URI.

Case: Search in Breton language, with speaker 'ThonyVezbe', 

SELECT ?audio ?urlPointer
WHERE {
  ?audio wdt:P407 wd:Q12107 ;                                                # P407 'language' is Q12107 'Breton'
         wdt:SPEAKER_PROPERTY_MISSING <https://lingualibre.org/speakers/1> ; # ??? 'speaker' is ll.org/speakers/1 'ThonyVezbe'
         wdt:P9533 "ni"@br ;
         schema:url ?urlPointer .
}
... Loading ...

Language (d:Q150) + Speaker (/speakers/1 ??) + String → URL pointer, filename

This query is IN WORK for Commons SPARQL Endpoint. One Wikidata property is missing; please update this query with the right property URI. 

SELECT ?audio ?urlPointer
  (REPLACE(REPLACE(REPLACE(SUBSTR(STR(?urlPointer),52),"%20","_"),"%28","("),"%29",")") AS ?filename)
WHERE {
  ?audio wdt:P407 wd:Q150 ;                                                   # Filter: P407 'language' is Q150 'French'
         wdt:SPEARKER_PROPERTY_MISSING <https://lingualibre.org/speakers/1> ; # Filter: ??? 'speaker' is ll.org/speakers/1 'Aemines1'
         wdt:P9533 "pomme"@fr ; # Filter: P9533 'audio transcription' of "pomme" in French
         schema:url ?urlPointer # Bind the URI to the file to ?urlPointer
}
... Loading ...

Files on Commons about records in Punjabi with transcription and LinguaLibre identifier

#defaultEndpoint:Commons
SELECT * WHERE {
  ?m wdt:P31 wd:Q108167708 ; #record
     wdt:P407 wd:Q58635 ; #in Punjabi
     wdt:P9533 ?transcription ; #with transcription
     wdt:P10369 ?idLili . #with LinguaLibre identifier
}
LIMIT 100

🇶 Count records by gender of the speaker (P8)

SELECT ?genderLabel (count(?record) AS ?nb)
WHERE {
  ?record prop:P2 entity:Q2 ;
          prop:P5 ?speaker .
  ?speaker prop:P2 entity:Q3 ;
           prop:P8 ?gender .
  # Add labels to each variable used.
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" . } 
}
GROUP BY ?genderLabel
... Loading ...

Heavy queries

Queries below are too large to run on LinguaLibre's wikipages, or even on Lingualibre Query Service).
To do: do smaller sub-queries, with one COUNT() function.

❌ Languages → Name, Wikidata Qid, LLQid, Iso-639-3, and genders

Query Result 
#defaultEndpoint:Lingualibre
SELECT ?languageQidLabel ?wdQid ?languageQid ?isoCode 
(COUNT(DISTINCT(?record)) AS ?recordCount)
(COUNT(DISTINCT(?speakerLangM)) AS ?speakerM) 
(COUNT(DISTINCT(?speakerLangF)) AS ?speakerF)
wWHERE{
  ?record prop:P2 entity:Q2 .     # Filter: items where P2 'instance of' is Q2 'record'
  ?record prop:P4 ?languageQid .  # Assign value: P4 'language' into variable ?language
  ?languageQid prop:P12 ?wdQid .  # Assign value: P12 'wikidata id' into variable ?WD
  ?languageQid prop:P13 ?isoCode. # Assign value: P13 'iso639-3' into ?isoCode
  
  #?record prop:P5 ?speakerQidM .   # Assign value: P5 'speaker' into variable ?speakerQidM
  #?speakerQidM prop:P8 entity:Q16 .   # Filter: P8 'sex or gender' is Q16 'male
  #?speakerQidM prop:P4 ?speakerLangM .  # Assign value: P4 'language' into variable ?spakerLangM
  
  ?record prop:P5 ?speakerQidF .   # Assign value: P5 'speaker' into variable ?speakerQidF
  ?speakerQidF prop:P8 entity:Q17 .   # Filter: P8 'sex or gender' is Q17 'female
  ?speakerQidF prop:P4 ?speakerLangF .  # Assign value: P4 'language' into variable ?spakerLangF
  
  SERVICE wikibase:label { bd:serviceParam wikibase:language "en" . } 
}
GROUP BY ?languageQidLabel ?languageQid ?wdQid ?isoCode
ORDER BY DESC(?recordCount)

#defaultEndpoint:Lingualibre
languageQidLabel	wdQid	languageQid	isoCode	recordCount	speakerM	speakerF
French	Q150	Q21	fra	16761	0	18
Marathi	Q1571	Q34	mar	13153	0	5
Polish	Q809	Q298	pol	11686	0	1
…

❌ Is Language (speaker (Q3)) → list all languages with number of unique words and speakers

#defaultEndpoint:Lingualibre
SELECT ?language (COUNT(?audio) AS ?nbAudio) (COUNT(?speaker) AS ?nbSpeaker) WHERE {
  ?language prop:P2 entity:Q4 .
  ?audio prop:P4 ?language .
  ?speaker prop:P4 ?language .
}
GROUP BY ?language

Others

(These old queries are not assessed yet.)

Language (Breton (Q209)) → Record, speaker's language level

#defaultEndpoint:Lingualibre
select ?record ?recordLabel ?speakerLabel ?languageLabel ?languageLevelLabel
where {
  ?record prop:P2 entity:Q2   # Filter: P2 'instance of' is Q2 'record' AND P4
	; prop:P4 entity:Q209 .   # AND P4 'language' is Q209 'Breton'
  ?record prop:P5 ?speaker .  # Assign value: record's P5 'speaker' into ?speaker
  ?record prop:P4 ?language . # Assign value: record's P4 'language' into ?language
  
  ?speaker llp:P4 ?languageStatement .    # P4 'language'
  ?languageStatement llv:P4 ?language .   # P4 'language'
  ?languageStatement llq:P16 ?languageLevel . # P16 'language level'
  # Adds labels
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
} ORDER BY ?languageLabel ?languageLevelLabel
... Loading ...

Language (Marathi (Q34)) → Records of Wikidata concepts with WD Qid (P12)

Those items were proposed to Lingualibre's recorder at step 3 via a SPARQL query upon Wikidata, so those words have WD's Qids.
#defaultEndpoint:Lingualibre
SELECT ?languageLabel ?recordLabel ?record ?wid
WHERE {
  ?record prop:P2 entity:Q2 .    # Filter: P2 'instance of' is Q2 'record'
  ?record prop:P4 entity:Q34 .  # Filter: P4 'language' is Q34 'Marathi'
  ?record prop:P4 ?language .    # Assign value: record's P4 'language' to variable ?language
  ?record prop:P12 ?wid .        # Assign value: record's P12 'wikidata id' to variable ?wid
  # Add labels capability
  SERVICE wikibase:label {
    bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en" .
  } 
}
... Loading ...

Records → Filter by date: late 2018

#defaultEndpoint:Lingualibre
SELECT
(COUNT(DISTINCT ?record) AS ?records)
(COUNT(DISTINCT ?speaker) AS ?speakers)
(COUNT(DISTINCT ?language) AS ?languages)
WHERE {
  ?record prop:P2 entity:Q2 .
  ?record prop:P6 ?date .
  ?record prop:P5 ?speaker .
  ?record prop:P4 ?language .
  # Filters:
  FILTER(?date >= "2018-07-01T00:00:00Z"^^xsd:dateTime 
       && ?date < "2019-01-01T00:00:00Z"^^xsd:dateTime)
}
... Loading ...

See also

Lingua Libre technical helps
Template {{Speakers category}} • {{Recommended lists}} • {{To iso 639-2}} • {{To iso 639-3}} • {{Userbox-records}} • {{Bot steps}}
Audio files How to create a frequency list? • Convert files formats • Denoise files with SoX • Rename and mass rename
Bots Help:Bots • LinguaLibre:Bot • Help:Log in to Lingua Libre with Pywikibot • Lingua Libre Bot (gh) • Olafbot • PamputtBot • Dragons Bot (gh)
MediaWiki MediaWiki: Help:Documentation opérationelle Mediawiki • Help:Database structure • Help:CSS • Help:Rename • Help:OAuth • LinguaLibre:User rights (rate limit) • Module:Lingua Libre record & {{Lingua Libre record}} • JS scripts: MediaWiki:Common.js • LastAudios.js • SoundLibrary.js • ItemsSugar.js • LexemeQueriesGenerator.js (pad) • Sparql2data.js (pad) • LanguagesGallery.js (pad) • Gadgets: Gadget-LinguaImporter.js • Gadget-Demo.js • Gadget-RecentNonAudio.js • LiLiZip.js
Queries Help:APIs • Help:SPARQL • SPARQL (intermediate) (stub) • SPARQL for lexemes (stub) • SPARQL for maintenance • Lingualibre:Wikidata (stub) • Help:SPARQL (HAL)
Reuses Help:Download datasets • Help:Embed audio in HTML
Unstable & tests Help:SPARQL/test
Categories Category:Technical reports
Retrieved from "https://lingualibre.org/index.php?title=Help:SPARQL&oldid=1348851"