| 1 |
# Copyright (C) 2002 Python Software Foundation |
| 2 |
# Contact: [email protected] |
| 3 |
# email package unit tests for (optional) Asian codecs |
| 4 |
|
| 5 |
import unittest |
| 6 |
|
| 7 |
from test.test_email import TestEmailBase |
| 8 |
from email.charset import Charset |
| 9 |
from email.header import Header, decode_header |
| 10 |
from email.message import Message |
| 11 |
|
| 12 |
# We're compatible with Python 2.3, but it doesn't have the built-in Asian |
| 13 |
# codecs, so we have to skip all these tests. |
| 14 |
try: |
| 15 |
str(b'foo', 'euc-jp') |
| 16 |
except LookupError: |
| 17 |
raise unittest.SkipTest |
| 18 |
|
| 19 |
|
| 20 |
|
| 21 |
class TestEmailAsianCodecs(TestEmailBase): |
| 22 |
def test_japanese_codecs(self): |
| 23 |
eq = self.ndiffAssertEqual |
| 24 |
jcode = "euc-jp" |
| 25 |
gcode = "iso-8859-1" |
| 26 |
j = Charset(jcode) |
| 27 |
g = Charset(gcode) |
| 28 |
h = Header("Hello World!") |
| 29 |
jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' |
| 30 |
b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode) |
| 31 |
ghello = str(b'Gr\xfc\xdf Gott!', gcode) |
| 32 |
h.append(jhello, j) |
| 33 |
h.append(ghello, g) |
| 34 |
# BAW: This used to -- and maybe should -- fold the two iso-8859-1 |
| 35 |
# chunks into a single encoded word. However it doesn't violate the |
| 36 |
# standard to have them as two encoded chunks and maybe it's |
| 37 |
# reasonable <wink> for each .append() call to result in a separate |
| 38 |
# encoded word. |
| 39 |
eq(h.encode(), """\ |
| 40 |
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?= |
| 41 |
=?iso-8859-1?q?Gr=FC=DF_Gott!?=""") |
| 42 |
eq(decode_header(h.encode()), |
| 43 |
[(b'Hello World! ', None), |
| 44 |
(b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'), |
| 45 |
(b'Gr\xfc\xdf Gott!', gcode)]) |
| 46 |
subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5' |
| 47 |
b'\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2' |
| 48 |
b'\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3' |
| 49 |
b'\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9') |
| 50 |
subject = str(subject_bytes, jcode) |
| 51 |
h = Header(subject, j, header_name="Subject") |
| 52 |
# test a very long header |
| 53 |
enc = h.encode() |
| 54 |
# TK: splitting point may differ by codec design and/or Header encoding |
| 55 |
eq(enc , """\ |
| 56 |
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?= |
| 57 |
=?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""") |
| 58 |
# TK: full decode comparison |
| 59 |
eq(str(h).encode(jcode), subject_bytes) |
| 60 |
|
| 61 |
h = Header("Japanese") |
| 62 |
s = '\u65e5\u672c\u8a9e' # 日本語 |
| 63 |
h.append(s, Charset('euc-jp')) |
| 64 |
h.append(s, Charset('iso-2022-jp')) |
| 65 |
h.append(s, Charset('shift_jis')) |
| 66 |
eq(h.encode(), """\ |
| 67 |
Japanese =?iso-2022-jp?b?GyRCRnxLXDhsGyhC?= =?iso-2022-jp?b?GyRCRnxLXDhsGyhC?= |
| 68 |
=?iso-2022-jp?b?GyRCRnxLXDhsGyhC?=""") |
| 69 |
eq(decode_header(h.encode()), |
| 70 |
[(b'Japanese ', None), |
| 71 |
(b'\x1b$BF|K\\8l\x1b(B\x1b$BF|K\\8l\x1b(B\x1b$BF|K\\8l\x1b(B', 'iso-2022-jp'), |
| 72 |
]) |
| 73 |
|
| 74 |
def test_chinese_codecs(self): |
| 75 |
eq = self.ndiffAssertEqual |
| 76 |
h = Header("Chinese") |
| 77 |
s = '\u4e2d\u6587' # 中文 |
| 78 |
h.append(s, Charset('gb2312')) |
| 79 |
h.append(s, Charset('gbk')) |
| 80 |
h.append(s, Charset('gb18030')) |
| 81 |
h.append(s, Charset('hz')) |
| 82 |
h.append(s, Charset('big5')) |
| 83 |
h.append(s, Charset('big5hkscs')) |
| 84 |
eq(h.encode(), """\ |
| 85 |
Chinese =?gb2312?b?1tDOxA==?= =?gbk?b?1tDOxA==?= =?gb18030?b?1tDOxA==?= |
| 86 |
=?hz?b?fntWUE5Efn0=?= =?big5?b?pKSk5Q==?= =?big5hkscs?b?pKSk5Q==?=""") |
| 87 |
eq(decode_header(h.encode()), |
| 88 |
[(b'Chinese ', None), |
| 89 |
(b'\xd6\xd0\xce\xc4', 'gb2312'), |
| 90 |
(b'\xd6\xd0\xce\xc4', 'gbk'), |
| 91 |
(b'\xd6\xd0\xce\xc4', 'gb18030'), |
| 92 |
(b'~{VPND~}', 'hz'), |
| 93 |
(b'\xa4\xa4\xa4\xe5', 'big5'), |
| 94 |
(b'\xa4\xa4\xa4\xe5', 'big5hkscs'), |
| 95 |
]) |
| 96 |
|
| 97 |
def test_korean_codecs(self): |
| 98 |
eq = self.ndiffAssertEqual |
| 99 |
h = Header("Korean") |
| 100 |
s = '\ud55c\uad6d\uc5b4' # 한국어 |
| 101 |
h.append(s, Charset('euc-kr')) |
| 102 |
h.append(s, Charset('ks_c_5601-1987')) |
| 103 |
h.append(s, Charset('cp949')) |
| 104 |
h.append(s, Charset('iso-2022-kr')) |
| 105 |
h.append(s, Charset('johab')) |
| 106 |
eq(h.encode(), """\ |
| 107 |
Korean =?euc-kr?b?x9Gxub7u?= =?ks_c_5601-1987?b?x9Gxub7uIMfRsbm+7g==?= |
| 108 |
=?iso-2022-kr?b?GyQpQw5HUTE5Pm4P?= =?johab?b?0GWKgrTh?=""") |
| 109 |
eq(decode_header(h.encode()), |
| 110 |
[(b'Korean ', None), |
| 111 |
(b'\xc7\xd1\xb1\xb9\xbe\xee', 'euc-kr'), |
| 112 |
(b'\xc7\xd1\xb1\xb9\xbe\xee \xc7\xd1\xb1\xb9\xbe\xee', 'ks_c_5601-1987'), |
| 113 |
(b'\x1b$)C\x0eGQ19>n\x0f', 'iso-2022-kr'), |
| 114 |
(b'\xd0e\x8a\x82\xb4\xe1', 'johab'), |
| 115 |
]) |
| 116 |
|
| 117 |
def test_payload_encoding_utf8(self): |
| 118 |
jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' |
| 119 |
b'\xa5\xeb\xa5\xc9\xa1\xaa', 'euc-jp') |
| 120 |
msg = Message() |
| 121 |
msg.set_payload(jhello, 'utf-8') |
| 122 |
ustr = msg.get_payload(decode=True).decode(msg.get_content_charset()) |
| 123 |
self.assertEqual(jhello, ustr) |
| 124 |
|
| 125 |
def test_payload_encoding(self): |
| 126 |
jcode = 'euc-jp' |
| 127 |
jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc' |
| 128 |
b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode) |
| 129 |
msg = Message() |
| 130 |
msg.set_payload(jhello, jcode) |
| 131 |
ustr = msg.get_payload(decode=True).decode(msg.get_content_charset()) |
| 132 |
self.assertEqual(jhello, ustr) |
| 133 |
|
| 134 |
|
| 135 |
|
| 136 |
if __name__ == '__main__': |
| 137 |
unittest.main() |