#4661: add bytes parsing and generation to email (email version bump to 5.1.0)

The work on this is not 100% complete, but everything is present to
allow real-world testing of the code.  The only remaining major todo
item is to (hopefully!) enhance the handling of non-ASCII bytes in headers
converted to unicode by RFC2047 encoding them rather than replacing them with
'?'s.

1 files changed, 45 insertions, 1 deletions

diff --git a/Lib/email/parser.py b/Lib/email/parser.py
index 06014e2..b83e0f7 100644
--- a/Lib/email/parser.py
+++ b/Lib/email/parser.py
@@ -7,7 +7,7 @@
 __all__ = ['Parser', 'HeaderParser']
 
 import warnings
-from io import StringIO
+from io import StringIO, TextIOWrapper
 
 from email.feedparser import FeedParser
 from email.message import Message
@@ -89,3 +89,47 @@ class HeaderParser(Parser):
 
     def parsestr(self, text, headersonly=True):
         return Parser.parsestr(self, text, True)
+
+
+class BytesParser:
+
+    def __init__(self, *args, **kw):
+        """Parser of binary RFC 2822 and MIME email messages.
+
+        Creates an in-memory object tree representing the email message, which
+        can then be manipulated and turned over to a Generator to return the
+        textual representation of the message.
+
+        The input must be formatted as a block of RFC 2822 headers and header
+        continuation lines, optionally preceeded by a `Unix-from' header.  The
+        header block is terminated either by the end of the input or by a
+        blank line.
+
+        _class is the class to instantiate for new message objects when they
+        must be created.  This class must have a constructor that can take
+        zero arguments.  Default is Message.Message.
+        """
+        self.parser = Parser(*args, **kw)
+
+    def parse(self, fp, headersonly=False):
+        """Create a message structure from the data in a binary file.
+
+        Reads all the data from the file and returns the root of the message
+        structure.  Optional headersonly is a flag specifying whether to stop
+        parsing after reading the headers or not.  The default is False,
+        meaning it parses the entire contents of the file.
+        """
+        fp = TextIOWrapper(fp, encoding='ascii', errors='surrogateescape')
+        return self.parser.parse(fp, headersonly)
+
+
+    def parsebytes(self, text, headersonly=False):
+        """Create a message structure from a byte string.
+
+        Returns the root of the message structure.  Optional headersonly is a
+        flag specifying whether to stop parsing after reading the headers or
+        not.  The default is False, meaning it parses the entire contents of
+        the file.
+        """
+        text = text.decode('ASCII', errors='surrogateescape')
+        return self.parser.parsestr(text, headersonly)