可检测中文名文件的文件类型

tests/test_data/中文名测试.txt

@@ -0,0 +1 @@
+测试中文名称文件的文件类型识别

tests/test_filetype.py

@@ -0,0 +1,19 @@
+# coding:utf8
+
+from pathlib import Path
+from xanalyzer.file import FileAnalyzer
+
+cur_dir_path = Path(__file__).parent
+
+
+def test_common_filetype():
+    upxed_path = cur_dir_path / 'test_data' / 'Hello_upx.exe_'
+    file_analyzer = FileAnalyzer(upxed_path)
+    assert file_analyzer.get_type() == 'PE32 executable (console) Intel 80386, for MS Windows, UPX compressed'
+
+
+def test_chinese_name_filetype():
+    chinese_name_path = cur_dir_path / 'test_data' / '中文名测试.txt'
+    file_analyzer = FileAnalyzer(chinese_name_path)
+    file_analyzer.get_type()
+    assert file_analyzer.get_type() == 'UTF-8 Unicode text, with no line terminators'

xanalyzer/file.py

@@ -23,7 +23,12 @@ def __init__(self, file_path):
         self.file_type = self.get_type()
 
     def get_type(self):
-        return magic.from_file(self.file_path)
+        # return magic.from_file(self.file_path)
+        # magic.from_file不能通过中文路径读取文件，暂时使用magic.from_buffer
+        the_file = open(self.file_path, 'rb')
+        the_content = the_file.read()
+        the_file.close()
+        return magic.from_buffer(the_content)
 
     @staticmethod
     def get_windows_style_file_size(tmp_size):