diff options
Diffstat (limited to 'lib-python/3/email/charset.py')
| -rw-r--r-- | lib-python/3/email/charset.py | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/lib-python/3/email/charset.py b/lib-python/3/email/charset.py index f22be2c52c..e999472355 100644 --- a/lib-python/3/email/charset.py +++ b/lib-python/3/email/charset.py @@ -194,7 +194,7 @@ class Charset: header encoding. Charset.SHORTEST is not allowed for body_encoding. - output_charset: Some character sets must be converted before the can be + output_charset: Some character sets must be converted before they can be used in email headers or bodies. If the input_charset is one of them, this attribute will contain the name of the charset output will be converted to. Otherwise, it will @@ -386,12 +386,22 @@ class Charset: string using the ascii codec produces the correct string version of the content. """ - # 7bit/8bit encodings return the string unchanged (module conversions) + if not string: + return string if self.body_encoding is BASE64: if isinstance(string, str): string = string.encode(self.output_charset) return email.base64mime.body_encode(string) elif self.body_encoding is QP: + # quopromime.body_encode takes a string, but operates on it as if + # it were a list of byte codes. For a (minimal) history on why + # this is so, see changeset 0cf700464177. To correctly encode a + # character set, then, we must turn it into pseudo bytes via the + # latin1 charset, which will encode any byte as a single code point + # between 0 and 255, which is what body_encode is expecting. + if isinstance(string, str): + string = string.encode(self.output_charset) + string = string.decode('latin1') return email.quoprimime.body_encode(string) else: if isinstance(string, str): |