migrations/JMDict: add extra constraints, clean up pkeys, etc.

migrations/0001_JMDict.sql

@@ -40,7 +40,7 @@ CREATE TABLE "JMdict_Entry" (
 
 CREATE TABLE "JMdict_KanjiElement" (
   "entryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("id"),
-  "orderNum" INTEGER,
+  "orderNum" INTEGER NOT NULL,
   "reading" TEXT NOT NULL,
   "news" INTEGER CHECK ("news" BETWEEN 1 AND 2),
   "ichi" INTEGER CHECK ("ichi" BETWEEN 1 AND 2),
@@ -65,7 +65,7 @@ CREATE TABLE "JMdict_KanjiElementInfo" (
 
 CREATE TABLE "JMdict_ReadingElement" (
   "entryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("id"),
-  "orderNum" INTEGER,
+  "orderNum" INTEGER NOT NULL,
   "reading" TEXT NOT NULL,
   "readingDoesNotMatchKanji" BOOLEAN NOT NULL DEFAULT FALSE,
   "news" INTEGER CHECK ("news" BETWEEN 1 AND 2),
@@ -99,29 +99,29 @@ CREATE TABLE "JMdict_ReadingElementInfo" (
 -- Sense
 
 CREATE TABLE "JMdict_Sense" (
-  "id" INTEGER PRIMARY KEY AUTOINCREMENT,
-  "entryId" INTEGER REFERENCES "JMdict_Entry"("id"),
-  "orderNum" INTEGER,
+  "id" INTEGER PRIMARY KEY,
+  "entryId" INTEGER NOT NULL REFERENCES "JMdict_Entry"("id"),
+  "orderNum" INTEGER NOT NULL,
   UNIQUE("entryId", "orderNum")
 );
 
 CREATE INDEX "JMdict_Sense_byEntryId_byOrderNum" ON "JMdict_Sense"("entryId", "orderNum");
 
 CREATE TABLE "JMdict_SenseRestrictedToKanji" (
-  "entryId" INTEGER,
-  "senseId" INTEGER REFERENCES "JMdict_Sense"("id"),
-  "kanji" TEXT,
+  "entryId" INTEGER NOT NULL,
+  "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("id"),
+  "kanji" TEXT NOT NULL,
   FOREIGN KEY ("entryId", "kanji") REFERENCES "JMdict_KanjiElement"("entryId", "reading"),
   PRIMARY KEY ("entryId", "senseId", "kanji")
-);
+) WITHOUT ROWID;
 
 CREATE TABLE "JMdict_SenseRestrictedToReading" (
-  "entryId" INTEGER,
-  "senseId" INTEGER REFERENCES "JMdict_Sense"("id"),
-  "reading" TEXT,
+  "entryId" INTEGER NOT NULL,
+  "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("id"),
+  "reading" TEXT NOT NULL,
   FOREIGN KEY ("entryId", "reading") REFERENCES "JMdict_ReadingElement"("entryId", "reading"),
   PRIMARY KEY ("entryId", "senseId", "reading")
-);
+) WITHOUT ROWID;
 
 -- In order to add xrefs, you will need to have added the entry to xref to.
 -- These should be added in a second pass of the dictionary file.
@@ -134,37 +134,34 @@ CREATE TABLE "JMdict_SenseRestrictedToReading" (
 -- These two things also concern "SenseAntonym"
 
 CREATE TABLE "JMdict_SenseSeeAlso" (
-  "senseId" INTEGER REFERENCES "JMdict_Sense"("id"),
-  "xrefEntryId" INTEGER,
+  "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("id"),
+  "xrefEntryId" INTEGER NOT NULL,
   "seeAlsoReading" TEXT,
   "seeAlsoKanji" TEXT,
   "seeAlsoSense" 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,
-  CHECK ("seeAlsoReading" = NULL <> "seeAlsoKanji" = NULL),
-  -- CHECK("seeAlsoSense" = NULL OR "seeAlsoSense")
+  "ambiguous" BOOLEAN NOT NULL DEFAULT FALSE,
   --  TODO: Check that if seeAlsoSense is present, it refers to a sense connected to xrefEntryId.
   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"),
-  PRIMARY KEY ("senseId", "xrefEntryId", "seeAlsoReading", "seeAlsoKanji", "seeAlsoSense")
+  UNIQUE("senseId", "xrefEntryId", "seeAlsoReading", "seeAlsoKanji", "seeAlsoSense")
 );
 
 CREATE TABLE "JMdict_SenseAntonym" (
-  "senseId" INTEGER REFERENCES "JMdict_Sense"("id"),
-  "xrefEntryId" INTEGER,
+  "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("id"),
+  "xrefEntryId" INTEGER NOT NULL,
   "antonymReading" TEXT,
   "antonymKanji" TEXT,
   "antonymSense" 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,
-  CHECK ("antonymReading" = NULL <> "antonymKanji" = NULL),
+  "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"),
-  PRIMARY KEY ("senseId", "xrefEntryId", "antonymReading", "antonymKanji", "antonymSense")
+  UNIQUE("senseId", "xrefEntryId", "antonymReading", "antonymKanji", "antonymSense")
 );
 
 -- These cross references are going to be mostly accessed from a sense
@@ -198,7 +195,7 @@ CREATE TABLE "JMdict_SenseLanguageSource" (
   "phrase" TEXT,
   "fullyDescribesSense" BOOLEAN NOT NULL DEFAULT TRUE,
   "constructedFromSmallerWords" BOOLEAN NOT NULL DEFAULT FALSE,
-  PRIMARY KEY ("senseId", "language", "phrase")
+  UNIQUE("senseId", "language", "phrase")
 );
 
 CREATE TABLE "JMdict_SenseDialect" (
@@ -232,8 +229,7 @@ CREATE TABLE "JMdict_SenseInfo" (
 -- the Tanaka Corpus, so I will leave the type out for now.
 
 CREATE TABLE "JMdict_ExampleSentence" (
-  "id" INTEGER PRIMARY KEY,
-  "senseId" INTEGER REFERENCES "JMdict_Sense"("id"),
+  "senseId" INTEGER NOT NULL REFERENCES "JMdict_Sense"("id"),
   "word" TEXT NOT NULL,
   "source" TEXT NOT NULL,
   "sourceLanguage" CHAR(3) NOT NULL DEFAULT "eng",