fix(file_parser): handle non-UTF-8 encoded text files with automatic encoding detection

2026-01-22 18:28:37 +08:00
parent 0efd9352a0
commit 390c120fef
4 changed files with 64 additions and 6 deletions
--- a/backend/pyproject.toml
+++ b/backend/pyproject.toml
@@ -25,6 +25,9 @@ dependencies = [
    
    # 文件处理
    "PyMuPDF>=1.24.0",
+    # 编码检测（支持非UTF-8编码的文本文件）
+    "charset-normalizer>=3.0.0",
+    "chardet>=5.0.0",
    
    # 工具库
    "python-dotenv>=1.0.0",