From 05b56466e746e074ce8aa7d000cf62b3f5819637 Mon Sep 17 00:00:00 2001
From: h7x4 <h7x4@nani.wtf>
Date: Sat, 21 Feb 2026 00:46:24 +0900
Subject: [PATCH] tanos-jlpt: fix breaking changes for csv parser

---
 .../tanos-jlpt/csv_parser.dart                | 72 ++++++++++---------
 1 file changed, 40 insertions(+), 32 deletions(-)

diff --git a/lib/_data_ingestion/tanos-jlpt/csv_parser.dart b/lib/_data_ingestion/tanos-jlpt/csv_parser.dart
index c0ab10a..dfdab0a 100644
--- a/lib/_data_ingestion/tanos-jlpt/csv_parser.dart
+++ b/lib/_data_ingestion/tanos-jlpt/csv_parser.dart
@@ -3,12 +3,20 @@ import 'dart:io';
 
 import 'package:csv/csv.dart';
 import 'package:jadb/_data_ingestion/tanos-jlpt/objects.dart';
+import 'package:xml/xml_events.dart';
 
 Future<List<JLPTRankedWord>> parseJLPTRankedWords(
   Map<String, File> files,
 ) async {
   final List<JLPTRankedWord> result = [];
 
+  final codec = CsvCodec(
+    fieldDelimiter: ',',
+    lineDelimiter: '\n',
+    quoteMode: QuoteMode.strings,
+    escapeCharacter: '\\',
+  );
+
   for (final entry in files.entries) {
     final jlptLevel = entry.key;
     final file = entry.value;
@@ -17,42 +25,42 @@ Future<List<JLPTRankedWord>> parseJLPTRankedWords(
       throw Exception('File $jlptLevel does not exist');
     }
 
-    final rows = await file
+    final words = await file
         .openRead()
         .transform(utf8.decoder)
-        .transform(CsvToListConverter())
+        .transform(codec.decoder)
+        .flatten()
+        .map((row) {
+          if (row.length != 3) {
+            throw Exception('Invalid line in $jlptLevel: $row');
+          }
+          return row;
+        })
+        .map((row) => row.map((e) => e as String).toList())
+        .map((row) {
+          final kanji = row[0].isEmpty
+              ? null
+              : row[0]
+                    .replaceFirst(RegExp('^お・'), '')
+                    .replaceAll(RegExp(r'（.*）'), '');
+
+          final readings = row[1]
+              .split(RegExp('[・/、(:?s+)]'))
+              .map((e) => e.trim())
+              .toList();
+
+          final meanings = row[2].split(',').expand(cleanMeaning).toList();
+
+          return JLPTRankedWord(
+            readings: readings,
+            kanji: kanji,
+            jlptLevel: jlptLevel,
+            meanings: meanings,
+          );
+        })
         .toList();
 
-    for (final row in rows) {
-      if (row.length != 3) {
-        throw Exception('Invalid line in $jlptLevel: $row');
-      }
-
-      final kanji = (row[0] as String).isEmpty
-          ? null
-          : (row[0] as String)
-                .replaceFirst(RegExp('^お・'), '')
-                .replaceAll(RegExp(r'（.*）'), '');
-
-      final readings = (row[1] as String)
-          .split(RegExp('[・/、(:?s+)]'))
-          .map((e) => e.trim())
-          .toList();
-
-      final meanings = (row[2] as String)
-          .split(',')
-          .expand(cleanMeaning)
-          .toList();
-
-      result.add(
-        JLPTRankedWord(
-          readings: readings,
-          kanji: kanji,
-          jlptLevel: jlptLevel,
-          meanings: meanings,
-        ),
-      );
-    }
+    result.addAll(words);
   }
 
   return result;