xgboost

.old/extract.ts

@@ -0,0 +1,49 @@
+import { parseTja } from './parse';
+import { factorize } from './factorize';
+import { readdirSync, readFileSync, writeFileSync, existsSync, mkdirSync } from 'fs';
+import { join, dirname } from 'path';
+import iconv from 'iconv-lite';
+
+const [,, workingDir, dataDir] = process.argv;
+
+const featurePath = join(workingDir, 'factors.json');
+
+if (existsSync(featurePath)) {
+    console.log('factors.json already exists. Skipping extraction.');
+    process.exit(0);
+}
+
+// 작업 디렉토리 존재 확인 및 생성
+if (!existsSync(workingDir)) {
+    mkdirSync(workingDir, { recursive: true });
+}
+
+const tjaDir = join(dataDir, 'tja');
+const results: any[] = [];
+
+for (const file of readdirSync(tjaDir)) {
+    if (!file.endsWith('.tja')) continue;
+    
+    const songno = file.replace(/\D/g, '');
+    const buffer = readFileSync(join(tjaDir, file));
+    
+    let content = iconv.decode(buffer, 'shift-jis', { stripBOM: true });
+    content = content.replace(/\uFFFD/g, '').replace(/[\u{0080}-\u{FFFF}]/gu, '').replace(/\r\n/g, '\n');
+    let parsed = parseTja(content);
+
+    if (!parsed) {
+        content = iconv.decode(buffer, 'utf-8', { stripBOM: true });
+        content = content.replace(/\uFFFD/g, '').replace(/[\u{0080}-\u{FFFF}]/gu, '').replace(/\r\n/g, '\n');
+        parsed = parseTja(content);
+    }
+    
+    if (!parsed) continue;
+
+    for (const diff of ['oni', 'edit'] as const) {
+        if (!parsed[diff]) continue;
+        const factors = factorize(parsed[diff]!);
+        results.push({ songno, diff: diff === 'oni' ? 'oni' : 'ura', ...factors });
+    }
+}
+writeFileSync(featurePath, JSON.stringify(results, null, 2));
+console.log(`Features extracted to ${featurePath}`);