yamadashy · yamadashy · Dec 14, 2025 · Dec 14, 2025 · Dec 14, 2025 · Dec 14, 2025
@@ -87,7 +87,7 @@
     "handlebars": "^4.7.8",
     "iconv-lite": "^0.7.0",
     "is-binary-path": "^3.0.0",
-    "isbinaryfile": "^6.0.0",
+    "isbinaryfile": "^5.0.2",
     "jiti": "^2.6.1",
     "jschardet": "^3.1.4",
     "json5": "^2.2.3",

@@ -43,16 +43,25 @@ export const readRawFile = async (filePath: string, maxFileSize: number): Promis
       return { content: null, skippedReason: 'binary-content' };
     }
 
-    const { encoding: detectedEncoding, confidence } = jschardet.detect(buffer) ?? {};
+    const { encoding: detectedEncoding } = jschardet.detect(buffer) ?? {};
     const encoding = detectedEncoding && iconv.encodingExists(detectedEncoding) ? detectedEncoding : 'utf-8';
 
     const content = iconv.decode(buffer, encoding, { stripBOM: true });
 
-    // Heuristics: U+FFFD indicates decode errors; very low confidence implies unreliable guess.
-    if (content.includes('\uFFFD') || (typeof confidence === 'number' && confidence < 0.2)) {
-      logger.debug(
-        `Skipping file due to encoding errors (${encoding}, confidence=${(confidence ?? 0).toFixed(2)}): ${filePath}`,
-      );
+    // Only skip if there are actual decode errors (U+FFFD replacement characters)
+    // Don't rely on jschardet confidence as it can return low values for valid UTF-8/ASCII files
+    if (content.includes('\uFFFD')) {
+      // For UTF-8, distinguish invalid byte sequences from a legitimate U+FFFD in the source
+      if (encoding.toLowerCase() === 'utf-8') {
+        try {
+          let utf8 = new TextDecoder('utf-8', { fatal: true }).decode(buffer);
+          if (utf8.charCodeAt(0) === 0xfeff) utf8 = utf8.slice(1); // strip UTF-8 BOM
+          return { content: utf8 };
+        } catch {
+          // fall through to skip below
+        }
+      }
+      logger.debug(`Skipping file due to encoding errors (detected: ${encoding}): ${filePath}`);
       return { content: null, skippedReason: 'encoding-error' };
     }
 

@@ -0,0 +1,125 @@
+import * as fs from 'node:fs/promises';
+import os from 'node:os';
+import path from 'node:path';
+import { afterEach, beforeEach, describe, expect, test } from 'vitest';
+import { readRawFile } from '../../../src/core/file/fileRead.js';
+
+describe('readRawFile', () => {
+  let testDir: string;
+
+  beforeEach(async () => {
+    testDir = await fs.mkdtemp(path.join(os.tmpdir(), 'repomix-fileRead-'));
+  });
+
+  afterEach(async () => {
+    await fs.rm(testDir, { recursive: true, force: true });
+  });
+
+  test('should read normal text file successfully', async () => {
+    const filePath = path.join(testDir, 'normal.txt');
+    const content = 'Hello World';
+    await fs.writeFile(filePath, content, 'utf-8');
+
+    const result = await readRawFile(filePath, 1024);
+
+    expect(result.content).toBe(content);
+    expect(result.skippedReason).toBeUndefined();
+  });
+
+  test('should read file with low jschardet confidence (Issue #869)', async () => {
+    // This tests that files with low confidence scores from jschardet
+    // are NOT skipped if they contain valid UTF-8 content
+    const filePath = path.join(testDir, 'server.py');
+    const content = `import json
+import time
+import uuid
+
+def hello():
+    print("Hello, World!")
+`;
+    await fs.writeFile(filePath, content, 'utf-8');
+
+    const result = await readRawFile(filePath, 1024 * 1024);
+
+    expect(result.content).toBe(content);
+    expect(result.skippedReason).toBeUndefined();
+  });
+
+  test('should read HTML file with Thymeleaf syntax (Issue #847)', async () => {
+    // This tests that HTML files with special syntax like Thymeleaf (~{})
+    // are NOT skipped even if jschardet returns low confidence
+    const filePath = path.join(testDir, 'thymeleaf.html');
+    const content = '<html lang="en" xmlns:th="http://www.thymeleaf.org" layout:decorate="~{layouts/default}"></html>';
+    await fs.writeFile(filePath, content, 'utf-8');
+
+    const result = await readRawFile(filePath, 1024);
+
+    expect(result.content).toBe(content);
+    expect(result.skippedReason).toBeUndefined();
+  });
+
+  test('should read empty file successfully', async () => {
+    // Empty files should not be skipped (jschardet may return 0 confidence for empty files)
+    const filePath = path.join(testDir, '__init__.py');
+    await fs.writeFile(filePath, '', 'utf-8');
+
+    const result = await readRawFile(filePath, 1024);
+
+    expect(result.content).toBe('');
+    expect(result.skippedReason).toBeUndefined();
+  });
+
+  test('should skip file with actual decode errors (U+FFFD)', async () => {
+    const filePath = path.join(testDir, 'invalid.txt');
+    // Create a file with a UTF-8 BOM followed by valid text and invalid UTF-8 sequences
+    // The BOM forces UTF-8 detection, and the invalid sequence will produce U+FFFD
+    const utf8Bom = Buffer.from([0xef, 0xbb, 0xbf]); // UTF-8 BOM
+    const validText = 'Hello World\n'.repeat(50);
+    // Invalid UTF-8: 0x80 is a continuation byte without a leading byte
+    const invalidSequence = Buffer.from([0x80, 0x81, 0x82]);
+    const buffer = Buffer.concat([utf8Bom, Buffer.from(validText), invalidSequence, Buffer.from(validText)]);
+    await fs.writeFile(filePath, buffer);
+
+    const result = await readRawFile(filePath, 1024 * 1024);
+
+    expect(result.content).toBeNull();
+    expect(result.skippedReason).toBe('encoding-error');
+  });
+
+  test('should skip file if it exceeds size limit', async () => {
+    const filePath = path.join(testDir, 'large.txt');
+    const content = 'x'.repeat(1000);
+    await fs.writeFile(filePath, content, 'utf-8');
+
+    const result = await readRawFile(filePath, 100);
+
+    expect(result.content).toBeNull();
+    expect(result.skippedReason).toBe('size-limit');
+  });
+
+  test('should skip binary file by extension', async () => {
+    const filePath = path.join(testDir, 'test.jpg');
+    const binaryData = Buffer.from([0xff, 0xd8, 0xff, 0xe0]);
+    await fs.writeFile(filePath, binaryData);
+
+    const result = await readRawFile(filePath, 1024);
+
+    expect(result.content).toBeNull();
+    expect(result.skippedReason).toBe('binary-extension');
+  });
+
+  test('should skip binary content in text extension file', async () => {
+    const filePath = path.join(testDir, 'binary.txt');
+    // Create file with binary content (null bytes and control characters)
+    const binaryData = Buffer.alloc(256);
+    for (let i = 0; i < 256; i++) {
+      binaryData[i] = i;
+    }
+    await fs.writeFile(filePath, binaryData);
+
+    const result = await readRawFile(filePath, 1024);
+
+    expect(result.content).toBeNull();
+    expect(result.skippedReason).toBe('binary-content');
+  });
+});