Merge pull request #40 from scribe-org/english-verbs

Add English verbs query file

CHANGELOG.md

@@ -10,6 +10,16 @@ Scribe-Data tries to follow [semantic versioning](https://semver.org/), a MAJOR.
 
 Emojis for the following are chosen based on [gitmoji](https://gitmoji.dev/).
 
+# [Upcoming] Scribe-Data 3.2.0
+
+### ✨ Features
+
+- The data and process needed for an English keyboard has been added.
+  - The Wikidata queries for English have been updated to get all nouns and verbs.
+  <!-- - Formatting scripts have been written to prepare the queried data and load it into an SQLite database.
+  - English has been added to the data ETL process. -->
+- The data update process has been cleaned up in preparation for future changes to Scribe-Data and to implement better practices.
+
 # Scribe-Data 3.1.0
 
 ### ✨ Features

src/scribe_data/extract_transform/English/verbs/query_verbs.sparql

@@ -1,28 +1,53 @@
 # All English (Q1860) verbs and the currently implemented tenses for each.
 # Enter this query at https://query.wikidata.org/.
 
-SELECT DISTINCT ?verb ?simplePast ?pastParticiple WHERE {
+SELECT DISTINCT ?infinitive ?presFPS ?presTPS ?simpPast ?pastPart WHERE {
+  # Infinitive (required)
   ?lexeme a ontolex:LexicalEntry ;
     dct:language wd:Q1860 ;
     wikibase:lexicalCategory wd:Q24905 ;
-    wikibase:lemma ?lemma .
+    wikibase:lemma ?infinitive .
+
+  # Simple Present
+  OPTIONAL {
+    ?lexeme ontolex:lexicalForm ?presFPSForm .
+    ?presFPSForm ontolex:representation ?presFPS ;
+      wikibase:grammaticalFeature wd:Q3910936 ;
+      FILTER NOT EXISTS { ?presFPSForm wikibase:grammaticalFeature wd:Q51929074 . }
+      FILTER NOT EXISTS { ?presFPSForm wdt:P6191 wd:Q181970 . }
+      FILTER NOT EXISTS { ?presFPSForm wikibase:grammaticalFeature wd:Q126473 . }
+  } .
+
+  # Third-person Singular
+  OPTIONAL {
+    ?lexeme ontolex:lexicalForm ?presTPSForm .
+    ?presTPSForm ontolex:representation ?presTPS ;
+    wikibase:grammaticalFeature wd:Q51929074 ;
+    wikibase:grammaticalFeature wd:Q110786 ;
+    wikibase:grammaticalFeature wd:Q3910936 ;
+    FILTER NOT EXISTS { ?presFPSForm wdt:P6191 wd:Q181970 . }
+    FILTER NOT EXISTS { ?presFPSForm wikibase:grammaticalFeature wd:Q126473 . }
+  } .
 
   # Simple Past
   OPTIONAL {
-    ?lexeme ontolex:lexicalForm ?simplePastForm .
-    ?simplePastForm ontolex:representation ?simplePast ;
-      wikibase:grammaticalFeature wd:Q1392475 ;
+    ?lexeme ontolex:lexicalForm ?simpPastForm .
+    ?simpPastForm ontolex:representation ?simpPast ;
+    wikibase:grammaticalFeature wd:Q1392475 ;
+    FILTER NOT EXISTS { ?presFPSForm wdt:P6191 wd:Q181970 . }
+    FILTER NOT EXISTS { ?presFPSForm wikibase:grammaticalFeature wd:Q126473 . }
   } .
 
   # Past Participle
   OPTIONAL {
-    ?lexeme ontolex:lexicalForm ?pastParticipleForm .
-    ?pastParticipleForm ontolex:representation ?pastParticiple ;
-      wikibase:grammaticalFeature wd:Q1230649 ;
+    ?lexeme ontolex:lexicalForm ?pastPartForm .
+    ?pastPartForm ontolex:representation ?pastPart ;
+    wikibase:grammaticalFeature wd:Q1230649 ;
+    FILTER NOT EXISTS { ?presFPSForm wdt:P6191 wd:Q181970 . }
+    FILTER NOT EXISTS { ?presFPSForm wikibase:grammaticalFeature wd:Q126473 . }
   } .
 
   SERVICE wikibase:label {
     bd:serviceParam wikibase:language "[AUTO_LANGUAGE]".
-    ?lemma rdfs:label ?verb .
   }
 }