More internal refinements of the ascii splitting algorithm.

_encode_chunks(): Pass maxlinelen in instead of always using
self._maxlinelen, so we can adjust for shorter initial lines.
Pass this value through to _max_append().

encode(): Weave maxlinelen through to the _encode_chunks() call.

_split_ascii(): When recursively splitting a line on spaces
(i.e. lower level syntactic split), don't append the whole returned
string.  Instead, split it on linejoiners and extend the lines up to
the last line (for proper packing).  Calculate the linelen based on
the last element in the this list.

1 files changed, 10 insertions, 7 deletions

diff --git a/Lib/email/Header.py b/Lib/email/Header.py
index cef734c..afd815f 100644
--- a/Lib/email/Header.py
+++ b/Lib/email/Header.py
@@ -342,7 +342,7 @@ class Header:
         lines = line.splitlines()
         return zip(lines, [charset]*len(lines))
 
-    def _encode_chunks(self, newchunks):
+    def _encode_chunks(self, newchunks, maxlinelen):
         # MIME-encode a header with many different charsets and/or encodings.
         #
         # Given a list of pairs (string, charset), return a MIME-encoded
@@ -367,7 +367,7 @@ class Header:
                 s = header
             else:
                 s = charset.header_encode(header)
-            _max_append(chunks, s, self._maxlinelen, ' ')
+            _max_append(chunks, s, maxlinelen, ' ')
         joiner = NL + self._continuation_ws
         return joiner.join(chunks)
 
@@ -407,11 +407,12 @@ class Header:
             newchunks += self._split(s, charset, targetlen, splitchars)
             lastchunk, lastcharset = newchunks[-1]
             lastlen = lastcharset.encoded_header_len(lastchunk)
-        return self._encode_chunks(newchunks)
+        return self._encode_chunks(newchunks, maxlinelen)
 
 
 
 def _split_ascii(s, firstlen, restlen, continuation_ws, splitchars):
+    linejoiner = '\n' + continuation_ws
     lines = []
     maxlen = firstlen
     for line in s.splitlines():
@@ -460,11 +461,14 @@ def _split_ascii(s, firstlen, restlen, continuation_ws, splitchars):
                 # splitting on whitespace, try to recursively split this line
                 # on whitespace.
                 if partlen > maxlen and ch <> ' ':
-                    this = [_split_ascii(part, maxlen, restlen,
-                                         continuation_ws, ' ')]
+                    subs = _split_ascii(part, maxlen, restlen,
+                                        continuation_ws, ' ')
+                    subl = re.split(linejoiner, subs)
+                    lines.extend(subl[:-1])
+                    this = [subl[-1]]
                 else:
                     this = [part]
-                linelen = wslen + partlen
+                linelen = wslen + len(this[-1])
                 maxlen = restlen
             else:
                 this.append(part)
@@ -472,7 +476,6 @@ def _split_ascii(s, firstlen, restlen, continuation_ws, splitchars):
         # Put any left over parts on a line by themselves
         if this:
             lines.append(joiner.join(this))
-    linejoiner = '\n' + continuation_ws
     return linejoiner.join(lines)