aboutsummaryrefslogtreecommitdiffstatshomepage
diff options
context:
space:
mode:
-rw-r--r--Doc/library/email.header.rst34
-rw-r--r--Lib/email/header.py17
-rw-r--r--Lib/test/test_email/test_email.py12
3 files changed, 54 insertions, 9 deletions
diff --git a/Doc/library/email.header.rst b/Doc/library/email.header.rst
index 219fad0d2f6..c3392a62b8e 100644
--- a/Doc/library/email.header.rst
+++ b/Doc/library/email.header.rst
@@ -178,16 +178,36 @@ The :mod:`email.header` module also provides the following convenient functions.
Decode a message header value without converting the character set. The header
value is in *header*.
- This function returns a list of ``(decoded_string, charset)`` pairs containing
- each of the decoded parts of the header. *charset* is ``None`` for non-encoded
- parts of the header, otherwise a lower case string containing the name of the
- character set specified in the encoded string.
+ For historical reasons, this function may return either:
- Here's an example::
+ 1. A list of pairs containing each of the decoded parts of the header,
+ ``(decoded_bytes, charset)``, where *decoded_bytes* is always an instance of
+ :class:`bytes`, and *charset* is either:
+
+ - A lower case string containing the name of the character set specified.
+
+ - ``None`` for non-encoded parts of the header.
+
+ 2. A list of length 1 containing a pair ``(string, None)``, where
+ *string* is always an instance of :class:`str`.
+
+ An :exc:`email.errors.HeaderParseError` may be raised when certain decoding
+ errors occur (e.g. a base64 decoding exception).
+
+ Here are examples:
>>> from email.header import decode_header
>>> decode_header('=?iso-8859-1?q?p=F6stal?=')
[(b'p\xf6stal', 'iso-8859-1')]
+ >>> decode_header('unencoded_string')
+ [('unencoded_string', None)]
+ >>> decode_header('bar =?utf-8?B?ZsOzbw==?=')
+ [(b'bar ', None), (b'f\xc3\xb3o', 'utf-8')]
+
+ .. note::
+
+ This function exists for for backwards compatibility only. For
+ new code, we recommend using :class:`email.headerregistry.HeaderRegistry`.
.. function:: make_header(decoded_seq, maxlinelen=None, header_name=None, continuation_ws=' ')
@@ -203,3 +223,7 @@ The :mod:`email.header` module also provides the following convenient functions.
:class:`Header` instance. Optional *maxlinelen*, *header_name*, and
*continuation_ws* are as in the :class:`Header` constructor.
+ .. note::
+
+ This function exists for for backwards compatibility only, and is
+ not recommended for use in new code.
diff --git a/Lib/email/header.py b/Lib/email/header.py
index 113a81f4131..220a84a7454 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -59,16 +59,22 @@ _max_append = email.quoprimime._max_append
def decode_header(header):
"""Decode a message header value without converting charset.
- Returns a list of (string, charset) pairs containing each of the decoded
- parts of the header. Charset is None for non-encoded parts of the header,
- otherwise a lower-case string containing the name of the character set
- specified in the encoded string.
+ For historical reasons, this function may return either:
+
+ 1. A list of length 1 containing a pair (str, None).
+ 2. A list of (bytes, charset) pairs containing each of the decoded
+ parts of the header. Charset is None for non-encoded parts of the header,
+ otherwise a lower-case string containing the name of the character set
+ specified in the encoded string.
header may be a string that may or may not contain RFC2047 encoded words,
or it may be a Header object.
An email.errors.HeaderParseError may be raised when certain decoding error
occurs (e.g. a base64 decoding exception).
+
+ This function exists for backwards compatibility only. For new code, we
+ recommend using email.headerregistry.HeaderRegistry instead.
"""
# If it is a Header object, we can just return the encoded chunks.
if hasattr(header, '_chunks'):
@@ -161,6 +167,9 @@ def make_header(decoded_seq, maxlinelen=None, header_name=None,
This function takes one of those sequence of pairs and returns a Header
instance. Optional maxlinelen, header_name, and continuation_ws are as in
the Header constructor.
+
+ This function exists for backwards compatibility only, and is not
+ recommended for use in new code.
"""
h = Header(maxlinelen=maxlinelen, header_name=header_name,
continuation_ws=continuation_ws)
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 8765d121fd0..b8116d073a2 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -2568,6 +2568,18 @@ Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?=
self.assertEqual(str(make_header(decode_header(s))),
'"Müller T" <T.Mueller@xxx.com>')
+ def test_unencoded_ascii(self):
+ # bpo-22833/gh-67022: returns [(str, None)] rather than [(bytes, None)]
+ s = 'header without encoded words'
+ self.assertEqual(decode_header(s),
+ [('header without encoded words', None)])
+
+ def test_unencoded_utf8(self):
+ # bpo-22833/gh-67022: returns [(str, None)] rather than [(bytes, None)]
+ s = 'header with unexpected non ASCII caract\xe8res'
+ self.assertEqual(decode_header(s),
+ [('header with unexpected non ASCII caract\xe8res', None)])
+
# Test the MIMEMessage class
class TestMIMEMessage(TestEmailBase):