python · agiudiceandrea · Dec 10, 2020 · Dec 10, 2020 · Jun 8, 2021 · Jun 8, 2021
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
@@ -314,6 +314,22 @@ def _EndRecData(fpin):
     # Unable to find a valid end of central directory structure
     return None
 
+def _sanitize_filename(filename):
+    """Terminate the file name at the first null byte and
+    ensure paths always use forward slashes as the directory separator."""
+
+    # Terminate the file name at the first null byte.  Null bytes in file
+    # names are used as tricks by viruses in archives.
+    null_byte = filename.find(chr(0))
+    if null_byte >= 0:
+        filename = filename[0:null_byte]
+    # This is used to ensure paths in generated ZIP files always use
+    # forward slashes as the directory separator, as required by the
+    # ZIP format specification.
+    if os.sep != "/" and os.sep in filename:
+        filename = filename.replace(os.sep, "/")
+    return filename
+
 
 class ZipInfo (object):
     """Class with attributes describing each file in the ZIP archive."""
@@ -336,6 +352,7 @@ class ZipInfo (object):
         'external_attr',
         'header_offset',
         'CRC',
+        'orig_filename_crc',
         'compress_size',
         'file_size',
         '_raw_time',
@@ -344,16 +361,9 @@ class ZipInfo (object):
     def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)):
         self.orig_filename = filename   # Original file name in archive
 
-        # Terminate the file name at the first null byte.  Null bytes in file
-        # names are used as tricks by viruses in archives.
-        null_byte = filename.find(chr(0))
-        if null_byte >= 0:
-            filename = filename[0:null_byte]
-        # This is used to ensure paths in generated ZIP files always use
-        # forward slashes as the directory separator, as required by the
-        # ZIP format specification.
-        if os.sep != "/" and os.sep in filename:
-            filename = filename.replace(os.sep, "/")
+        # Terminate the file name at the first null byte and
+        # ensure paths always use forward slashes as the directory separator.
+        filename = _sanitize_filename(filename)
 
         self.filename = filename        # Normalized file name
         self.date_time = date_time      # year, month, day, hour, min, sec
@@ -484,6 +494,24 @@ def _decodeExtra(self):
                 except struct.error:
                     raise BadZipFile(f"Corrupt zip64 extra field. "
                                      f"{field} not found.") from None
+            elif tp == 0x7075:
+                data = extra[4:ln+4]
+                # Unicode Path Extra Field
+                try:
+                    up_version, up_name_crc = unpack('<BL', data[:5])
+                    if up_version == 1 and up_name_crc == self.orig_filename_crc:
+                        up_unicode_name = data[5:].decode('utf-8')
+                        if up_unicode_name:
+                            self.filename = _sanitize_filename(up_unicode_name)
+                        else:
+                            import warnings
+                            warnings.warn("Empty unicode path extra field (0x7075)", stacklevel=2)
+                except struct.error:
+                    import warnings
+                    warnings.warn("Corrupt unicode path extra field (0x7075)", stacklevel=2)
+                except UnicodeDecodeError:
+                    import warnings
+                    warnings.warn('Corrupt unicode path extra field (0x7075): invalid utf-8 bytes', stacklevel=2)
 
             extra = extra[ln+4:]
 
@@ -1354,6 +1382,7 @@ def _RealGetContents(self):
             if self.debug > 2:
                 print(centdir)
             filename = fp.read(centdir[_CD_FILENAME_LENGTH])
+            orig_filename_crc = crc32(filename)
             flags = centdir[5]
             if flags & 0x800:
                 # UTF-8 file names extension
@@ -1378,6 +1407,7 @@ def _RealGetContents(self):
             x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
                             t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )
 
+            x.orig_filename_crc = orig_filename_crc
             x._decodeExtra()
             x.header_offset = x.header_offset + concat
             self.filelist.append(x)

diff --git a/Misc/NEWS.d/next/Library/2020-12-10-19-48-31.bpo-41928.9TH76z.rst b/Misc/NEWS.d/next/Library/2020-12-10-19-48-31.bpo-41928.9TH76z.rst
@@ -0,0 +1 @@
+Add support for Unicode Path Extra Field in ZipFile.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Add support for Unicode Path Extra Field in ZipFile.