bpo-33497: Add errors param to cgi.parse_multipart and make an encoding in FieldStorage use the given errors (GH-6804)

3 files changed, 27 insertions, 7 deletions

diff --git a/Doc/library/cgi.rst b/Doc/library/cgi.rst
index 17386b8..0b1aead 100644
--- a/Doc/library/cgi.rst
+++ b/Doc/library/cgi.rst
@@ -296,7 +296,7 @@ algorithms implemented in this module in other circumstances.
    instead. It is maintained here only for backward compatibility.
 
 
-.. function:: parse_multipart(fp, pdict, encoding="utf-8")
+.. function:: parse_multipart(fp, pdict, encoding="utf-8", errors="replace")
 
    Parse input of type :mimetype:`multipart/form-data` (for  file uploads).
    Arguments are *fp* for the input file, *pdict* for a dictionary containing
@@ -312,8 +312,8 @@ algorithms implemented in this module in other circumstances.
    which is much more flexible.
 
    .. versionchanged:: 3.7
-      Added the *encoding* parameter.  For non-file fields, the value is now
-      a list of strings, not bytes.
+      Added the *encoding* and *errors* parameters.  For non-file fields, the
+      value is now a list of strings, not bytes.
 
 
 .. function:: parse_header(string)
diff --git a/Lib/cgi.py b/Lib/cgi.py
index f5e85aa..f82cc6c 100755
--- a/Lib/cgi.py
+++ b/Lib/cgi.py
@@ -198,13 +198,14 @@ def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
          DeprecationWarning, 2)
     return urllib.parse.parse_qsl(qs, keep_blank_values, strict_parsing)
 
-def parse_multipart(fp, pdict, encoding="utf-8"):
+def parse_multipart(fp, pdict, encoding="utf-8", errors="replace"):
     """Parse multipart input.
 
     Arguments:
     fp   : input file
     pdict: dictionary containing other parameters of content-type header
-    encoding: request encoding
+    encoding, errors: request encoding and error handler, passed to
+        FieldStorage
 
     Returns a dictionary just like parse_qs(): keys are the field names, each
     value is a list of values for that field. For non-file fields, the value
@@ -217,7 +218,7 @@ def parse_multipart(fp, pdict, encoding="utf-8"):
     headers = Message()
     headers.set_type(ctype)
     headers['Content-Length'] = pdict['CONTENT-LENGTH']
-    fs = FieldStorage(fp, headers=headers, encoding=encoding,
+    fs = FieldStorage(fp, headers=headers, encoding=encoding, errors=errors,
         environ={'REQUEST_METHOD': 'POST'})
     return {k: fs.getlist(k) for k in fs}
 
@@ -458,7 +459,8 @@ class FieldStorage:
         self.type = ctype
         self.type_options = pdict
         if 'boundary' in pdict:
-            self.innerboundary = pdict['boundary'].encode(self.encoding)
+            self.innerboundary = pdict['boundary'].encode(self.encoding,
+                                                          self.errors)
         else:
             self.innerboundary = b""
 
diff --git a/Lib/test/test_cgi.py b/Lib/test/test_cgi.py
index 903d073..4f2bba1 100644
--- a/Lib/test/test_cgi.py
+++ b/Lib/test/test_cgi.py
@@ -130,6 +130,24 @@ class CgiTests(unittest.TestCase):
                     'file': [b'Testing 123.\n'], 'title': ['']}
         self.assertEqual(result, expected)
 
+    def test_parse_multipart_invalid_encoding(self):
+        BOUNDARY = "JfISa01"
+        POSTDATA = """--JfISa01
+Content-Disposition: form-data; name="submit-name"
+Content-Length: 3
+
+\u2603
+--JfISa01"""
+        fp = BytesIO(POSTDATA.encode('utf8'))
+        env = {'boundary': BOUNDARY.encode('latin1'),
+               'CONTENT-LENGTH': str(len(POSTDATA.encode('utf8')))}
+        result = cgi.parse_multipart(fp, env, encoding="ascii",
+                                     errors="surrogateescape")
+        expected = {'submit-name': ["\udce2\udc98\udc83"]}
+        self.assertEqual(result, expected)
+        self.assertEqual("\u2603".encode('utf8'),
+                         result["submit-name"][0].encode('utf8', 'surrogateescape'))
+
     def test_fieldstorage_properties(self):
         fs = cgi.FieldStorage()
         self.assertFalse(fs)