#12586: add provisional email policy with new header parsing and folding.

When the new policies are used (and only when the new policies are explicitly
used) headers turn into objects that have attributes based on their parsed
values, and can be set using objects that encapsulate the values, as well as
set directly from unicode strings.  The folding algorithm then takes care of
encoding unicode where needed, and folding according to the highest level
syntactic objects.

With this patch only date and time headers are parsed as anything other than
unstructured, but that is all the helper methods in the existing API handle.
I do plan to add more parsers, and complete the set specified in the RFC
before the package becomes stable.

1 files changed, 40 insertions, 3 deletions

diff --git a/Lib/email/errors.py b/Lib/email/errors.py
index c04deb4..f916229 100644
--- a/Lib/email/errors.py
+++ b/Lib/email/errors.py
@@ -5,7 +5,6 @@
 """email package exception classes."""
 
 
-
 class MessageError(Exception):
     """Base class for errors in the email package."""
 
@@ -30,9 +29,8 @@ class CharsetError(MessageError):
     """An illegal charset was given."""
 
 
-
 # These are parsing defects which the parser was able to work around.
-class MessageDefect(Exception):
+class MessageDefect(ValueError):
     """Base class for a message defect."""
 
     def __init__(self, line=None):
@@ -58,3 +56,42 @@ class MultipartInvariantViolationDefect(MessageDefect):
 
 class InvalidMultipartContentTransferEncodingDefect(MessageDefect):
     """An invalid content transfer encoding was set on the multipart itself."""
+
+class UndecodableBytesDefect(MessageDefect):
+    """Header contained bytes that could not be decoded"""
+
+class InvalidBase64PaddingDefect(MessageDefect):
+    """base64 encoded sequence had an incorrect length"""
+
+class InvalidBase64CharactersDefect(MessageDefect):
+    """base64 encoded sequence had characters not in base64 alphabet"""
+
+# These errors are specific to header parsing.
+
+class HeaderDefect(MessageDefect):
+    """Base class for a header defect."""
+
+class InvalidHeaderDefect(HeaderDefect):
+    """Header is not valid, message gives details."""
+
+class HeaderMissingRequiredValue(HeaderDefect):
+    """A header that must have a value had none"""
+
+class NonPrintableDefect(HeaderDefect):
+    """ASCII characters outside the ascii-printable range found"""
+
+    def __init__(self, non_printables):
+        super().__init__(non_printables)
+        self.non_printables = non_printables
+
+    def __str__(self):
+        return ("the following ASCII non-printables found in header: "
+            "{}".format(self.non_printables))
+
+class ObsoleteHeaderDefect(HeaderDefect):
+    """Header uses syntax declared obsolete by RFC 5322"""
+
+class NonASCIILocalPartDefect(HeaderDefect):
+    """local_part contains non-ASCII characters"""
+    # This defect only occurs during unicode parsing, not when
+    # parsing messages decoded from binary.