gh-153426: Raise BadZipFile for invalid UTF-8 filenames- #1

Lib/zipfile/__init__.py

@@ -2084,7 +2084,10 @@
             flags = centdir[_CD_FLAG_BITS]
             if flags & _MASK_UTF_FILENAME:
                 # UTF-8 file names extension
-                filename = filename.decode('utf-8')
+                try:
+                    filename = filename.decode('utf-8')
+                except UnicodeDecodeError as e:
+                    raise BadZipFile("Invalid UTF-8 filename in central directory") from e                                                 
             else:
                 # Historical ZIP filename encoding
                 filename = filename.decode(self.metadata_encoding or 'cp437')
@@ -2264,8 +2267,11 @@
 
             if fheader[_FH_GENERAL_PURPOSE_FLAG_BITS] & _MASK_UTF_FILENAME:
                 # UTF-8 filename
+                try:
                 fname_str = fname.decode("utf-8")
+        except UnicodeDecodeError as e:
+            raise BadZipFile("Invalid UTF-8 filename in local file header") from e
             else:
                 fname_str = fname.decode(self.metadata_encoding or "cp437")
 
             if fname_str != zinfo.orig_filename:
@@ -2299,11 +2305,11 @@
                 pwd = None
 
             return ZipExtFile(zef_file, mode + 'b', zinfo, pwd, True)
         except:
             zef_file.close()
             raise
 
     def _open_to_write(self, zinfo, force_zip64=False):
         if force_zip64 and not self._allowZip64:
             raise ValueError(
                 "force_zip64 is True, but allowZip64 was False when opening "
@@ -2780,7 +2786,7 @@
             fp.close()
 
 
 class PyZipFile(ZipFile):
     """Class to create ZIP archives with Python library files and packages."""
 
     def __init__(self, file, mode="r", compression=ZIP_STORED,