jmdict: skip inserting duplicate xrefs

lib/_data_ingestion/jmdict/seed_data.dart

@@ -5,6 +5,8 @@ import 'package:jadb/_data_ingestion/jmdict/objects.dart';
 import 'package:jadb/table_names/jmdict.dart';
 import 'package:sqflite_common/sqlite_api.dart';
 
+/// A wrapper for the result of resolving an xref, which includes the resolved entry and a flag
+/// indicating whether the xref was ambiguous (i.e. could refer to multiple entries).
 class ResolvedXref {
   Entry entry;
   bool ambiguous;
@@ -12,6 +14,13 @@ class ResolvedXref {
   ResolvedXref(this.entry, this.ambiguous);
 }
 
+/// Resolves an xref (pair of kanji, optionally reading, and optionally sense number) to an a specific
+/// JMdict entry, if possible.
+///
+/// If the xref is ambiguous (i.e. it could refer to multiple entries), the
+/// first entry is returned, and the returned value is marked as ambiguous.
+///
+/// If the xref cannot be resolved to any entry at all, an exception is thrown.
 ResolvedXref resolveXref(
   SplayTreeMap<String, Set<Entry>> entriesByKanji,
   SplayTreeMap<String, Set<Entry>> entriesByReading,
@@ -181,24 +190,17 @@ Future<void> seedJMDictData(List<Entry> entries, Database db) async {
 
   print('  [JMdict] Building xref trees');
   final SplayTreeMap<String, Set<Entry>> entriesByKanji = SplayTreeMap();
+  final SplayTreeMap<String, Set<Entry>> entriesByReading = SplayTreeMap();
 
   for (final entry in entries) {
     for (final kanji in entry.kanji) {
-      if (entriesByKanji.containsKey(kanji.reading)) {
+      entriesByKanji.putIfAbsent(kanji.reading, () => {});
-        entriesByKanji.update(kanji.reading, (list) => list..add(entry));
+      entriesByKanji.update(kanji.reading, (set) => set..add(entry));
-      } else {
-        entriesByKanji.putIfAbsent(kanji.reading, () => {entry});
-      }
     }
-  }
+
-  final SplayTreeMap<String, Set<Entry>> entriesByReading = SplayTreeMap();
-  for (final entry in entries) {
     for (final reading in entry.readings) {
-      if (entriesByReading.containsKey(reading.reading)) {
+      entriesByReading.putIfAbsent(reading.reading, () => {});
-        entriesByReading.update(reading.reading, (list) => list..add(entry));
+      entriesByReading.update(reading.reading, (set) => set..add(entry));
-      } else {
-        entriesByReading.putIfAbsent(reading.reading, () => {entry});
-      }
     }
   }
 
@@ -207,6 +209,7 @@ Future<void> seedJMDictData(List<Entry> entries, Database db) async {
 
   for (final e in entries) {
     for (final s in e.senses) {
+      final seenSeeAlsoXrefs = <int>{};
       for (final xref in s.seeAlso) {
         final resolvedEntry = resolveXref(
           entriesByKanji,
@@ -214,6 +217,15 @@ Future<void> seedJMDictData(List<Entry> entries, Database db) async {
           xref,
         );
 
+        if (seenSeeAlsoXrefs.contains(resolvedEntry.entry.entryId)) {
+          print(
+            'WARNING: Skipping duplicate seeAlso xref from sense ${s.senseId} to entry ${resolvedEntry.entry.entryId}\n'
+            '  (kanjiRef: ${xref.kanjiRef}, readingRef: ${xref.readingRef}, senseOrderNum: ${xref.senseOrderNum})',
+          );
+          continue;
+        }
+        seenSeeAlsoXrefs.add(resolvedEntry.entry.entryId);
+
         b.insert(JMdictTableNames.senseSeeAlso, {
           'senseId': s.senseId,
           'xrefEntryId': resolvedEntry.entry.entryId,
@@ -224,6 +236,7 @@ Future<void> seedJMDictData(List<Entry> entries, Database db) async {
         });
       }
 
+      final seenAntonymXrefs = <int>{};
       for (final ant in s.antonyms) {
         final resolvedEntry = resolveXref(
           entriesByKanji,
@@ -231,6 +244,15 @@ Future<void> seedJMDictData(List<Entry> entries, Database db) async {
           ant,
         );
 
+        if (seenAntonymXrefs.contains(resolvedEntry.entry.entryId)) {
+          print(
+            'WARNING: Skipping duplicate antonym xref from sense ${s.senseId} to entry ${resolvedEntry.entry.entryId}\n'
+            '  (kanjiRef: ${ant.kanjiRef}, readingRef: ${ant.readingRef}, senseOrderNum: ${ant.senseOrderNum})',
+          );
+          continue;
+        }
+        seenAntonymXrefs.add(resolvedEntry.entry.entryId);
+
         b.insert(JMdictTableNames.senseAntonyms, {
           'senseId': s.senseId,
           'xrefEntryId': resolvedEntry.entry.entryId,