WIP

migrations/0001_JMDict.sql

@@ -1,3 +1,5 @@
+SELECT icu_load_collation('ja_JP', 'japanese');
+
 CREATE TABLE "JMdict_Version" (
   "version" VARCHAR(10) PRIMARY KEY NOT NULL,
   "date" DATE NOT NULL,
@@ -55,13 +57,13 @@ CREATE TABLE "JMdict_KanjiElement" (
   "elementId" INTEGER PRIMARY KEY,
   "entryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("entryId"),
   "orderNum" INTEGER NOT NULL,
-  "reading" TEXT NOT NULL,
+  "reading" TEXT NOT NULL COLLATE japanese,
   "news" INTEGER CHECK ("news" BETWEEN 1 AND 2),
   "ichi" INTEGER CHECK ("ichi" BETWEEN 1 AND 2),
   "spec" INTEGER CHECK ("spec" BETWEEN 1 AND 2),
   "gai" INTEGER CHECK ("gai" BETWEEN 1 AND 2),
   "nf" INTEGER CHECK ("nf" BETWEEN 1 AND 48),
-  UNIQUE("entryId", "reading"),
+  -- UNIQUE("entryId", "reading"),
   UNIQUE("entryId", "orderNum")
 ) WITHOUT ROWID;
 
@@ -80,14 +82,14 @@ CREATE TABLE "JMdict_ReadingElement" (
   "elementId" INTEGER PRIMARY KEY,
   "entryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("entryId"),
   "orderNum" INTEGER NOT NULL,
-  "reading" TEXT NOT NULL,
+  "reading" TEXT NOT NULL COLLATE japanese,
   "readingDoesNotMatchKanji" BOOLEAN NOT NULL DEFAULT FALSE,
   "news" INTEGER CHECK ("news" BETWEEN 1 AND 2),
   "ichi" INTEGER CHECK ("ichi" BETWEEN 1 AND 2),
   "spec" INTEGER CHECK ("spec" BETWEEN 1 AND 2),
   "gai" INTEGER CHECK ("gai" BETWEEN 1 AND 2),
   "nf" INTEGER CHECK ("nf" BETWEEN 1 AND 48),
-  UNIQUE("entryId", "reading"),
+  -- UNIQUE("entryId", "reading"),
   UNIQUE("entryId", "orderNum")
 ) WITHOUT ROWID;
 
@@ -120,17 +122,17 @@ CREATE INDEX "JMdict_Sense_byEntryId_byOrderNum" ON "JMdict_Sense"("entryId", "o
 CREATE TABLE "JMdict_SenseRestrictedToKanji" (
   "entryId" INTEGER NOT NULL,
   "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("senseId"),
-  "kanji" TEXT NOT NULL,
-  FOREIGN KEY ("entryId", "kanji") REFERENCES "JMdict_KanjiElement"("entryId", "reading"),
-  PRIMARY KEY ("entryId", "senseId", "kanji")
+  "kanjiOrderNum" INTEGER NOT NULL CHECK ("kanjiOrderNum" > 0),
+  FOREIGN KEY ("entryId", "kanjiOrderNum") REFERENCES "JMdict_KanjiElement"("entryId", "orderNum"),
+  PRIMARY KEY ("entryId", "senseId", "kanjiOrderNum")
 ) WITHOUT ROWID;
 
 CREATE TABLE "JMdict_SenseRestrictedToReading" (
   "entryId" INTEGER NOT NULL,
   "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("senseId"),
-  "reading" TEXT NOT NULL,
-  FOREIGN KEY ("entryId", "reading") REFERENCES "JMdict_ReadingElement"("entryId", "reading"),
-  PRIMARY KEY ("entryId", "senseId", "reading")
+  "readingOrderNum" INTEGER NOT NULL CHECK ("readingOrderNum" > 0),
+  FOREIGN KEY ("entryId", "readingOrderNum") REFERENCES "JMdict_ReadingElement"("entryId", "orderNum"),
+  PRIMARY KEY ("entryId", "senseId", "readingOrderNum")
 ) WITHOUT ROWID;
 
 -- In order to add xrefs, you will need to have added the entry to xref to.
@@ -145,32 +147,23 @@ CREATE TABLE "JMdict_SenseRestrictedToReading" (
 
 CREATE TABLE "JMdict_SenseSeeAlso" (
   "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("senseId"),
-  "xrefEntryId" INTEGER NOT NULL,
-  "seeAlsoReading" TEXT,
-  "seeAlsoKanji" TEXT,
-  "seeAlsoSense" INTEGER,
+  "xrefEntryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("entryId"),
+  -- Sometimes the cross reference is to a specific sense
+  "xrefSenseOrderNum" INTEGER,
   -- For some entries, the cross reference is ambiguous. This means that while the ingestion
   -- has determined some xrefEntryId, it is not guaranteed to be the correct one.
   "ambiguous" BOOLEAN NOT NULL DEFAULT FALSE,
-  FOREIGN KEY ("xrefEntryId", "seeAlsoKanji") REFERENCES "JMdict_KanjiElement"("entryId", "reading"),
-  FOREIGN KEY ("xrefEntryId", "seeAlsoReading") REFERENCES "JMdict_ReadingElement"("entryId", "reading"),
-  FOREIGN KEY ("xrefEntryId", "seeAlsoSense") REFERENCES "JMdict_Sense"("entryId", "orderNum"),
-  UNIQUE("senseId", "xrefEntryId", "seeAlsoReading", "seeAlsoKanji", "seeAlsoSense")
+  FOREIGN KEY ("xrefEntryId", "xrefSenseOrderNum") REFERENCES "JMdict_Sense"("entryId", "orderNum"),
+  UNIQUE("senseId", "xrefEntryId", "xrefSenseOrderNum")
 );
 
 CREATE TABLE "JMdict_SenseAntonym" (
   "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("senseId"),
-  "xrefEntryId" INTEGER NOT NULL,
-  "antonymReading" TEXT,
-  "antonymKanji" TEXT,
-  "antonymSense" INTEGER,
+  "xrefEntryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("entryId"),
   -- For some entries, the cross reference is ambiguous. This means that while the ingestion
   -- has determined some xrefEntryId, it is not guaranteed to be the correct one.
   "ambiguous" BOOLEAN NOT NULL DEFAULT FALSE,
-  FOREIGN KEY ("xrefEntryId", "antonymKanji") REFERENCES "JMdict_KanjiElement"("entryId", "reading"),
-  FOREIGN KEY ("xrefEntryId", "antonymReading") REFERENCES "JMdict_ReadingElement"("entryId", "reading"),
-  FOREIGN KEY ("xrefEntryId", "antonymSense") REFERENCES "JMdict_Sense"("entryId", "orderNum"),
-  UNIQUE("senseId", "xrefEntryId", "antonymReading", "antonymKanji", "antonymSense")
+  UNIQUE("senseId", "xrefEntryId")
 );
 
 -- These cross references are going to be mostly accessed from a sense