[incubator-ponymail-foal] branch master updated: Canonicalisation of 'From ' quoting variations

[sebb]

This is an automated email from the ASF dual-hosted git repository.

sebb pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-ponymail-foal.git


The following commit(s) were added to refs/heads/master by this push:
     new c80e784  Canonicalisation of 'From ' quoting variations
c80e784 is described below

commit c80e7842ae274c22afefa817e18bd936c981ee8f
Author: Sebb <s...@apache.org>
AuthorDate: Fri Oct 8 20:26:33 2021 +0100

    Canonicalisation of 'From ' quoting variations
    
    This fixes #115
    
    (Unit tests will be added shortly)
---
 tools/plugins/dkim_id.py | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/tools/plugins/dkim_id.py b/tools/plugins/dkim_id.py
index 27c6e79..8925c3e 100644
--- a/tools/plugins/dkim_id.py
+++ b/tools/plugins/dkim_id.py
@@ -21,6 +21,7 @@ DKIM-ID Generator Code
 
 import base64
 import hmac
+import re
 from typing import List, Optional, Set, Tuple
 
 # Types
@@ -253,9 +254,27 @@ def rfc6376_split_canon(
         # Which makes this function polymorphic really
         # This is not reflected in its type signature
         headers, body = rfc6376_simple_holistic(headers, body)
-
+        body = _strip_gt_from(body)
     return (headers, body)
 
+def _strip_gt_from(body: bytes) -> bytes:
+    r"""
+    Convert all escaped '>+From ' back to 'From '
+
+    >>> _strip_gt_from(b'> From ')
+    b'> From '
+    >>> _strip_gt_from(b' >From ')
+    b' >From '
+    >>> _strip_gt_from(b'>From_')
+    b'>From_'
+    >>> _strip_gt_from(b'>From ')
+    b'From '
+    >>> _strip_gt_from(b'>>>From ')
+    b'From '
+    >>> _strip_gt_from(b'\r\n>From x\r\n>From y')
+    b'\r\nFrom x\r\nFrom y'
+    """
+    return re.sub(b'^>+From ', b'From ', body, flags = re.MULTILINE)
 
 def rfc6376_join(headers: Headers, body: Optional[bytes] = None) -> bytes:
     r"""