MediaWiki
Difference between revisions of "LexemeQueriesGenerator.js"
Line 1: | Line 1: | ||
+ | // SOURCE: https://github.com/sinaahmadi/sinaahmadi.github.io/blob/master/_posts/2021-10-04-sparql-query-generator-for-lexicographical-data.md | ||
+ | // Author: Sina Ahmadi @sinaahmadi | ||
+ | // Revamp: @hugolpz | ||
+ | // LICENSE: MIT | ||
/* TODO | /* TODO | ||
1) List of languages with recordings AND number of speakers | 1) List of languages with recordings AND number of speakers |
Revision as of 20:26, 6 January 2022
// SOURCE: https://github.com/sinaahmadi/sinaahmadi.github.io/blob/master/_posts/2021-10-04-sparql-query-generator-for-lexicographical-data.md
// Author: Sina Ahmadi @sinaahmadi
// Revamp: @hugolpz
// LICENSE: MIT
/* TODO
1) List of languages with recordings AND number of speakers
See base : https://lingualibre.org/wiki/LinguaLibre:List_of_languages
See nbSp : https://w.wiki/4ZB3
Finish hacking based on https://jsfiddle.net/hugolpz/rygo9s5b/
[x] getData from elements
[x] Identify suitable query
[x] Edit suitable query
[x] Run/Open Query
Improve
[ ] Query with federate SPARQL including LinguaLibre
[ ] Factorize SPARQL codes.
Add to LinguaLibre
[x] Add to [[User:Yug/OOUI]], [[Help:SPARQL 2]]
[x] Migrate to general space. : MediaWiki:LexemeQueriesGenerator.js ; MediaWiki:Common.js
Translate
[ ] Find a way to translate ?
MediaWiki Extension ?
- [x] Explore -> Nope.
*/
// Toolbox
/* ********************************************************************** */
/* QUERIES BASIS ******************************************************** */
// Current: Wikidata, Dbnary.
var queries = {
// Queries for Wikidata
wikidata :
{
values :`VALUES ?word {'book'@GLWSSA}`,
basic: `SELECT * WHERE {
VALUESTOBEADDEDHERE
?l a ontolex:LexicalEntry ;
dct:language wd:LNGCDE ;
ontolex:lexicalForm ?form ; #test
wikibase:lexicalCategory wd:POSTAG ;
wikibase:lemma ?lemma .
?form ontolex:representation ?word .
}`,
senses: `SELECT * WHERE {
VALUESTOBEADDEDHERE
?l a ontolex:LexicalEntry ;
dct:language wd:LNGCDE ;
ontolex:lexicalForm ?form ;
wikibase:lexicalCategory wd:POSTAG ;
wikibase:lemma ?lemma ;
ontolex:sense ?sense .
?form ontolex:representation ?word .
}`,
sensesDefinitions : `SELECT * WHERE {
VALUESTOBEADDEDHERE
?l a ontolex:LexicalEntry ;
dct:language wd:LNGCDE ;
wikibase:lemma ?lemma ;
ontolex:lexicalForm ?form ;
wikibase:lexicalCategory ?category ;
ontolex:sense ?sense .
?form ontolex:representation ?word .
?language wdt:P218 "GLWSSA" .
?sense skos:definition ?gloss .
FILTER EXISTS {?l ontolex:sense ?sense }
FILTER(LANG(?gloss) = "GLWSSA")
}`,
sensesDefinitionsExamples: `SELECT * WHERE {
VALUESTOBEADDEDHERE
?l a ontolex:LexicalEntry ;
dct:language wd:LNGCDE ;
wikibase:lemma ?lemma ;
ontolex:lexicalForm ?form ;
wikibase:lexicalCategory ?category ;
ontolex:sense ?sense .
?language wdt:P218 "GLWSSA" .
?form ontolex:representation ?word .
?sense skos:definition ?gloss .
OPTIONAL{
?l p:P5831 ?statement .
?statement ps:P5831 ?example .
}
FILTER EXISTS {?l ontolex:sense ?sense }
FILTER(LANG(?gloss) = "GLWSSA")
}`,
translation: `SELECT DISTINCT * WHERE {
?source dct:language wd:LNGCDE;
wikibase:lemma ?sourceLemma;
ontolex:sense [ wdt:P5137 ?sense ].
?target dct:language wd:LNGCDETRG;
wikibase:lemma ?targetLemma;
ontolex:sense [ wdt:P5137 ?sense ].
} ORDER BY ASC(UCASE(str(?sourceLemma)))`,
translationLemma : `SELECT DISTINCT * WHERE {
VALUESTOBEADDEDHERE
?source dct:language wd:LNGCDE;
wikibase:lemma ?sourceLemma;
ontolex:lexicalForm ?form ;
wikibase:lexicalCategory wd:POSTAG ;
ontolex:sense [ wdt:P5137 ?sense ].
?target dct:language wd:LNGCDETRG;
wikibase:lemma ?targetLemma;
ontolex:sense [ wdt:P5137 ?sense ].
?form ontolex:representation ?word .
} ORDER BY ASC(UCASE(str(?sourceLemma)))`
},
// Queries for Dbnary
dbnary : {
values: `VALUES ?label {'book'@GLWSSA}
VALUES ?pos {<http://www.lexinfo.net/ontology/2.0/lexinfo#POSTAGNM>}`,
basic: `SELECT * WHERE {VALUESTOBEADDEDHERE
?lexeme a ontolex:LexicalEntry ;
rdfs:label ?label ;
ontolex:canonicalForm ?form ;
lime:language ?lang ;
lexinfo:partOfSpeech ?pos .
FILTER(?lang = "GLWSSA")
}`,
senses: `SELECT * WHERE {
VALUESTOBEADDEDHERE
?lexeme a ontolex:LexicalEntry ;
rdfs:label ?label ;
ontolex:canonicalForm ?form ;
lime:language ?lang ;
lexinfo:partOfSpeech ?pos ;
ontolex:sense ?sense .
FILTER(?lang = "GLWSSA")
}`,
sensesDefinitions: `SELECT ?lexeme ?label ?pos ?sense ?definition
WHERE {
?sense a ontolex:LexicalSense ;
skos:definition ?def .
?def rdf:value ?definition .
FILTER(lang(?definition) = "GLWSSA")
{
SELECT * WHERE {VALUESTOBEADDEDHERE
?lexeme a ontolex:LexicalEntry ;
rdfs:label ?label ;
ontolex:canonicalForm ?form ;
lime:language ?lang ;
lexinfo:partOfSpeech ?pos ;
ontolex:sense ?sense .
FILTER(?lang = "GLWSSA")
}
}
}`,
sensesDefinitionsExamples: ``,
translation: ``,
translationLemma: ``
}
};
/* ********************************************************************** */
/* OOJS / OOUI ********************************************************** */
// Data & options
var baseLanguages = [ //Major languages: cmn, spa, eng, fra, ara, rus, hin, swa
// data https://w.wiki/4ZB3
{ data:'Q13955', ll:'', label:'ara — Arabic' },
{ data:'Q9610', ll:'', label:'ben — Bengali' },
{ data:'Q9192', ll:'Q113', label:'cmn — MandarinChinese' } ,
{ data:'Q188', ll:'', label:'deu — German' },
{ data:'Q1860', ll:'', label:'eng — English' },
{ data:'Q150', ll:'', label:'fra — French' },
{ data:'Q1568', ll:'', label:'hin — Hindi' },
{ data:'Q5287', ll:'', label:'jpn — Japanese' },
{ data:'Q1571', ll:'Q34', label:'mar — Marathi' },
{ data:'Q58635', ll:'', label:'pan — Punjabi' },
{ data:'Q5146', ll:'', label:'por — Portuguese' },
{ data:'Q7737', ll:'', label:'rus — Russian' },
{ data:'Q1321', ll:'', label:'spa — Spanish' },
],
availableLanguages = [
{ data:'Q13955',ll:'', iso1:'ar', label:'ara — Arabic' },
{ data:'Q9610',ll:'', iso1:'bn', label:'ben — Bengali' },
{ data:'Q12107', ll:'Q209', iso1:'br', label: 'bre: Breton' }, // lili
{ data:'Q9192', ll:'Q113', iso1:'zh', label:'cmn — MandarinChinese' } ,
{ data:'Q188',ll:'', iso1:'de', label:'deu — German' },
{ data:'Q1860',ll:'', iso1:'en', label:'eng — English' },
{ data:'Q150',ll:'', iso1:'fr', label:'fra — French' },
{ data:'Q33454',ll:'', iso1:'ff', label:'ful — Fula' },
{ data:'Q56475',ll:'', iso1:'ha', label:'hau — Hausa' },
{ data:'Q1568',ll:'', iso1:'hi', label:'hin — Hindi' },
{ data:'Q9240',ll:'', iso1:'id', label:'ind — Indonesian' },
{ data:'Q652',ll:'', iso1:'it', label:'ita — Italian' },
{ data:'Q33549',ll:'', iso1:'jv', label:'jav — Javanese' },
{ data:'Q5287',ll:'', iso1:'ja', label:'jpn — Japanese' },
{ data:'Q9176',ll:'', iso1:'ko', label:'kor — Korean' },
{ data:'Q1571',ll:'', iso1:'mr', label:'mar — Marathi' },
{ data:'Q9237',ll:'', iso1:'ms', label:'msa — Malay' },
{ data:'Q58635',ll:'', iso1:'pa', label:'pan — Punjabi' },
{ data:'Q5146',ll:'', iso1:'pt', label:'por — Portuguese' },
{ data:'Q7737',ll:'', iso1:'ru', label:'rus — Russian' },
{ data:'Q1321',ll:'', iso1:'es', label:'spa — Spanish' },
{ data:'Q5885',ll:'', iso1:'ta', label:'tam — Tamil' },
{ data:'Q8097',ll:'', iso1:'te', label:'tel — Telugu' },
{ data:'Q256',ll:'', iso1:'tr', label:'tur — Turkish' },
{ data:'Q1617',ll:'', iso1:'ur', label:'urd — Urdu' },
{ data:'Q9199',ll:'', iso1:'vi', label:'vie — Vietnamese' },
],
languagesArray = [ ...availableLanguages ],
posArray = [
{ data: 'Q1084', label: 'noun' },
{ data: 'Q36224', label: 'pronoun' },
{ data: 'Q24905', label: 'verb' },
{ data: 'Q380057', label: 'adverb' },
{ data: 'Q34698', label: 'adjective' },
{ data: 'Q21087400', label: 'quantitative'},
{ data: 'Q83034', label: 'interjection' },
{ data: 'Q4833830', label: 'preposition' },
{ data: 'Q103184', label: 'article' },
{ data: 'Q36484', label: 'conjunction' },
].map(o => new OO.ui.MenuOptionWidget({ data: o.data, label: o.label })),
infoTypesArray = [
{ data: 'basic', label: 'Just look !' },
{ data: 'senses', label: 'Sense' },
{ data: 'sensesDefinitions', label: 'Sense, definition' },
{ data: 'sensesDefinitionsExamples', label: 'Sense, definition and examples'},
].map(o => new OO.ui.MenuOptionWidget({ data: o.data, label: o.label })),
languagesArrayT = [ ...baseLanguages, ],
endpointsArray = [
{ data: 'wikidata', label: 'Wikidata', selected: true },
{ data: 'Dbnary', label: 'Dbnary' },
//{ data: 'LinguaLibre', label: 'LinguaLibre' },
];
// Elements
var lemma = new OO.ui.TextInputWidget({
id: 'lqg-lemma',
icon: 'search',
placeholder: 'books',
value: 'books',
label: 'Word to search',
}),
languages = new OO.ui.ComboBoxInputWidget({ // ComboBox
id: 'lqg-languages',
placeholder : 'Target language',
options: languagesArray,
menu: { filterFromInput: true, filterMode : 'substring' }
// value: 'Q34',
}),
pos = new OO.ui.DropdownWidget( {
id: 'lqg-pos',
label: 'Part-of-speech',
menu: { items: posArray }
}),
infoTypes = new OO.ui.DropdownWidget({
id: 'lqg-infoTypes',
label: 'Information to fetch ... (if any)',
menu: { items: infoTypesArray }
}),
translations = new OO.ui.ComboBoxInputWidget({ // ComboBox
id: 'lqg-translations',
placeholder : 'Translations to fetch ... (if any)',
options: languagesArrayT,
menu: { filterFromInput: true, filterMode : 'substring' }
}),
endpoints = new OO.ui.RadioSelectInputWidget( {
id: 'lqg-endpoints',
label: 'Radios buttons',
options: endpointsArray,
} ),
limit = new OO.ui.CheckboxInputWidget({ id: 'lqg-limit', selected: true, }),
limitLabel = new OO.ui.LabelWidget( { label: 'Limit to 100 (faster)' }),
queryDisplay = new OO.ui.MultilineTextInputWidget( {
id: 'lqg-queryDisplay',
//value: `# Query will appear here.\n\n\n\n\n\n`,
placeholder: `# Query will appear here.\n\n\n\n\n\n`,
multiline: true,
autosize: true,
minRows: 10,
maxRows: 20
} ),
generate = new OO.ui.ButtonWidget({
id: 'lqg-generate',
label: 'Generate',
}),
run = new OO.ui.ButtonWidget({
id: 'lqg-run',
label:'Run !',
});
// An example of a fieldset with horizontal layout.
var fieldset = new OO.ui.FieldsetLayout( {
label: 'Queries Generator for Wikidata Lexemes'
} );
fieldset.addItems( [
new OO.ui.FieldLayout(
new OO.ui.Widget( {
content: [
new OO.ui.HorizontalLayout( { items: [
lemma,
pos,
languages,
infoTypes,
translations,
]}),
new OO.ui.HorizontalLayout( { items: [
generate,
run,
limit,
limitLabel,
endpoints,
]}),
queryDisplay
]
}),{
label: 'Select the suitable values to build your Wikidata Lexemes Query.',
align: 'top'
})
]
);
$( "#lqg" ).append( fieldset.$element );
// Check data
var checkAvailableData = function(identity,element){
// console.log('2',languages)
console.log(identity+'a getElementId(): ',element.getElementId())
console.log(identity+'b getData(): ',element.getData())
console.log(identity+'c getValue(): ',element.getValue())
}
$('#lqg-lemma').on('focusout',function() {checkAvailableData(1,lemma);})
$('#lqg-languages').on('focusout',function() { checkAvailableData(2,languages);});
checkAvailableData(2,languages);
/* ********************************************************************** */
/* GENERATE QUERY STRING ************************************************ */
// Current: Wikidata, Dbnary.
var generateQuery = function () {
// getData from elements
var selectedDropdown = function (group){
var items = group.getMenu().items.filter(item=> item.selected==true )
return items[0]?items[0].data:null;
}
var selectedRadio = function (group){
var items = group.getMenu().items.filter(item=> item.selected==true )
return items[0]?items[0].data:null;
}
var qid2value = function (arr,qid,field){
field = field || 'label'
var match = arr.filter(item=> item.data==qid);
return match[0]?match[0][field]:null;
}
var form = {
lemma: lemma.getValue(),//string
pos: selectedDropdown(pos),//Qid
posLabel: qid2value(posArray,selectedDropdown(pos)),//noun
languages: languages.getValue(),//Qid
languagesISO1: qid2value(availableLanguages,languages.getValue(),'iso1'),//en
infoTypes: selectedDropdown(infoTypes),//string
translations: translations.getValue(),//Qid
limit: limit.isSelected(),//boolean
endpoints: endpoints.getValue(),//wikidata|dbnary
queryDisplay: queryDisplay.getValue(),//string
};
console.log(form)
// console.log(form);
var query = form.queryDisplay;
// Identify suitable query
if (form.endpoints == 'wikidata' && form.translations != "null") {
form.infoTypes = form.lemma? 'translationLemma': 'translation';
}
if (form.endpoints == 'dbnary' && form.infoTypes == 'sensesDefinitionsExamples') {
form.infoTypes = 'sensesDefinitions';
}
query = queries[form.endpoints][form.infoTypes];
// Edit suitable query
val = form.lemma ? queries[form.endpoints].values : '# no lemma provided';
query = query
.replace("VALUESTOBEADDEDHERE", val.replace("book", form.lemma))
.replace("WORD", form.lemma)
.replace("LNGCDE", form.languages)// Q
.replaceAll("GLWSSA", form.languagesISO1)// en
.replaceAll("LNGCDETRG", form.translations)// Q
.replace("POSTAGNM", form.posLabel) // noun
.replace("POSTAG", form.pos)// Q
.concat(form.limit?`\nLIMIT 100`:'');
// Inject query
queryDisplay.setValue(query);
}
/* ********************************************************************** */
/* OPENS EXTERNAL QUERY SERVICE ***************************************** */
// Current: Wikidata, Dbnary. Broken: lingualibre.
var runQuery = function () {
var endpointLabel = endpoints.getValue(),
queryText = queryDisplay.getValue(),
queryEncoded = encodeURIComponent(queryText),
baseEndpointUrl =
endpointLabel == 'wikidata'? 'https://query.wikidata.org/#'
:'http://kaiko.getalp.org/sparql?default-graph-uri=&query=';
if (queryText) {
window.open(baseEndpointUrl.concat(queryEncoded), '_blank');
}
}
$('#lqg-run').on('click',function(){ runQuery(); });
$('#lqg-generate').on('click',function(){ generateQuery(); });