chore: import original project baseline

Import the pre-repair source tree as the history baseline.
Runtime data (data/), virtualenvs, bytecode caches and logs are
gitignored so local secrets and user state stay out of the repo.

tests/test_file_attach.py

@@ -0,0 +1,87 @@
+# -*- coding: utf-8 -*-
+"""
+file_reader 单元测试（标准库 unittest，零额外依赖）
+运行：在项目根目录执行  python -m unittest discover tests -v
+      或直接  python tests/test_file_attach.py
+"""
+import os
+import sys
+import tempfile
+import unittest
+
+# 保证直接运行（python tests/xxx.py）时也能 import 到项目根下的包
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."))
+
+from ui.views.system_tools.file_reader import BINARY_EXTS, read_text_file  # noqa: E402
+
+
+class ReadTextFileTest(unittest.TestCase):
+    """read_text_file：编码探测 / 二进制探测 / 大小守卫"""
+
+    def _write(self, data: bytes, suffix: str = ".txt") -> str:
+        fd, path = tempfile.mkstemp(suffix=suffix)
+        with os.fdopen(fd, "wb") as f:
+            f.write(data)
+        self.addCleanup(os.remove, path)
+        return path
+
+    def test_utf8_file(self):
+        path = self._write("你好，世界\nhello".encode("utf-8"))
+        content, enc, size_kb, lines = read_text_file(path)
+        self.assertIn("你好，世界", content)
+        self.assertIn("hello", content)
+        self.assertEqual(lines, 2)
+        self.assertIn(enc, ("utf-8-sig", "utf-8"))
+        self.assertGreater(size_kb, 0)
+
+    def test_utf8_bom_file(self):
+        path = self._write(b"\xef\xbb\xbf" + "带BOM".encode("utf-8"))
+        content, enc, _, _ = read_text_file(path)
+        self.assertEqual(content, "带BOM")  # utf-8-sig 会吃掉 BOM
+        self.assertEqual(enc, "utf-8-sig")
+
+    def test_gbk_file_falls_back_to_gb18030(self):
+        path = self._write("中文GBK内容".encode("gbk"))
+        content, enc, _, _ = read_text_file(path)
+        self.assertEqual(content, "中文GBK内容")
+        self.assertEqual(enc, "gb18030")
+
+    def test_binary_file_rejected(self):
+        path = self._write(b"\x00\x01\x02\x03binary-payload")
+        with self.assertRaises(ValueError):
+            read_text_file(path)
+
+    def test_oversize_file_rejected(self):
+        path = self._write(b"a" * 100)
+        with self.assertRaises(ValueError):
+            read_text_file(path, max_bytes=10)
+
+    def test_latin1_fallback_never_fails(self):
+        # 0xFF 既非合法 UTF-8 也非合法 GB18030 引导字节，应由 latin-1 兜底
+        path = self._write(b"\xff\xfe\xfd plain text")
+        content, enc, _, _ = read_text_file(path)
+        self.assertEqual(enc, "latin-1")
+        self.assertIn("plain text", content)
+
+
+class BinaryExtBlacklistTest(unittest.TestCase):
+    """黑名单分类：Word/Excel 等被拒，常见代码/文本文件放行"""
+
+    def test_office_and_binary_blocked(self):
+        for ext in (".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx",
+                    ".zip", ".exe", ".dll", ".mp4", ".ttf", ".db", ".psd"):
+            self.assertIn(ext, BINARY_EXTS, f"{ext} 应在黑名单中")
+
+    def test_pdf_not_blacklisted(self):
+        # PDF 改由专用分支（pdf_reader）处理，不再走二进制黑名单
+        self.assertNotIn(".pdf", BINARY_EXTS, ".pdf 应由 PDF 专用分支处理，不应在黑名单中")
+
+    def test_text_and_code_allowed(self):
+        for ext in (".py", ".js", ".ts", ".java", ".c", ".cpp", ".go", ".rs",
+                    ".md", ".txt", ".json", ".yaml", ".html", ".css", ".sql",
+                    ".sh", ".csv", ".log", ".ipynb", ""):
+            self.assertNotIn(ext, BINARY_EXTS, f"{ext} 不应在黑名单中")
+
+
+if __name__ == "__main__":
+    unittest.main()