3 use RT::Test nodb => 1, tests => 14;
7 diag q{'=' char in a leading part before an encoded part};
9 my $str = 'key="plain"; key="=?UTF-8?B?0LzQvtC5X9GE0LDQudC7LmJpbg==?="';
11 RT::I18N::DecodeMIMEWordsToUTF8($str),
12 'key="plain"; key="мой_файл.bin"',
17 diag q{not compliant with standards, but MUAs send such field when attachment has non-ascii in name};
19 my $str = 'attachment; filename="=?UTF-8?B?0LzQvtC5X9GE0LDQudC7LmJpbg==?="';
21 RT::I18N::DecodeMIMEWordsToUTF8($str),
22 'attachment; filename="мой_файл.bin"',
27 diag q{'=' char in a trailing part after an encoded part};
29 my $str = 'attachment; filename="=?UTF-8?B?0LzQvtC5X9GE0LDQudC7LmJpbg==?="; some_prop="value"';
31 RT::I18N::DecodeMIMEWordsToUTF8($str),
32 'attachment; filename="мой_файл.bin"; some_prop="value"',
37 diag q{adding quotes around mime words containing specials when word is already quoted};
40 Content-Disposition: attachment; filename="=?iso-8859-1?Q?foobar,_?=
41 =?iso-8859-1?Q?barfoo.docx?="
43 my $decoded = 'Content-Disposition: attachment; filename="foobar, barfoo.docx"';
44 is( RT::I18N::DecodeMIMEWordsToUTF8($str), $decoded, "No added quotes" );
47 diag q{regression test for #5248 from rt3.fsck.com};
49 my $str = qq{Subject: =?ISO-8859-1?Q?Re=3A_=5BXXXXXX=23269=5D_=5BComment=5D_Frag?=}
50 . qq{\n =?ISO-8859-1?Q?e_zu_XXXXXX--xxxxxx_/_Xxxxx=FCxxxxxxxxxx?=};
52 RT::I18N::DecodeMIMEWordsToUTF8($str),
53 qq{Subject: Re: [XXXXXX#269] [Comment] Frage zu XXXXXX--xxxxxx / Xxxxxüxxxxxxxxxx},
58 diag q{newline and encoded file name};
60 my $str = qq{application/vnd.ms-powerpoint;\n\tname="=?ISO-8859-1?Q?Main_presentation.ppt?="};
62 RT::I18N::DecodeMIMEWordsToUTF8($str),
63 qq{application/vnd.ms-powerpoint;\tname="Main presentation.ppt"},
71 "attachment; filename*=ISO-8859-1''%74%E9%73%74%2E%74%78%74";
73 RT::I18N::DecodeMIMEWordsToEncoding( $str, 'utf-8', 'Content-Disposition' ),
74 'attachment; filename="tést.txt"',
79 diag q{rfc2231 param continuations};
81 # XXX TODO: test various forms of the continuation stuff
82 # quotes around the values
85 filename*0*=ISO-2022-JP'ja'%1b$B%3f7$7$$%25F%25%2d%259%25H%1b%28B;
87 filename*2*=%1b$B%25I%25%2d%25e%25a%25s%25H%1b%28B;
91 RT::I18N::DecodeMIMEWordsToEncoding( $hdr, 'utf-8', 'Content-Disposition' ),
92 'inline; filename="新しいテキスト ドキュメント.txt"',
93 'decoded continuations as one string'
97 diag q{canonicalize mime word encodings like gb2312};
99 my $str = qq{Subject: =?gb2312?B?1NrKwL3nuPe12Lmy09CzrN9eX1NpbXBsaWZpZWRfQ05fR0IyMzEyYQ==?=
100 =?gb2312?B?dHRhY2hlbWVudCB0ZXN0IGluIENOIHNpbXBsaWZpZWQ=?=};
103 RT::I18N::DecodeMIMEWordsToUTF8($str),
104 qq{Subject: 在世界各地共有超過_Simplified_CN_GB2312attachement test in CN simplified},
110 diag q{Whitespace between encoded words should be removed};
112 my $str = "=?utf-8?Q?=E3=82=AD?= =?utf-8?Q?=E3=83=A3?=";
114 RT::I18N::DecodeMIMEWordsToUTF8($str),
116 "whitespace between encoded words is removed",
119 $str = "=?utf-8?Q?=E3=82=AD?= \n =?utf-8?Q?=E3=83=A3?=";
121 RT::I18N::DecodeMIMEWordsToUTF8($str),
123 "newlines between encoded words also removed",
127 diag q{Multiple octets split across QP hunks are correctly reassembled};
129 # This passes even without explicit code to handle it because utf8
130 # is perl's internal string encoding.
131 my $str = "=?utf-8?Q?=E3?= =?utf-8?Q?=82?= =?utf-8?Q?=AD?=";
133 RT::I18N::DecodeMIMEWordsToUTF8($str),
135 "UTF8 character split in three is successfully reassembled",
138 # Non-utf8 encodings thus also must be checked
139 $str = <<EOT; chomp $str;
140 =?gb2312?q?Chinese(gb2312)=20=20=C3=C0=B9=FA=C7=B0=CB=BE=B7=A8=B2=BF=B3?=
141 =?gb2312?q?=A4=C3=E6=BC=FB=C8=F8=B4=EF=C4=B7=BA=F3=B3=C6=C6=E4=D7=B4=CC=AC?=
142 =?gb2312?q?=BA=DC=BA=C3=20=20Chinese=20(gb2312)?=
145 RT::I18N::DecodeMIMEWordsToUTF8($str),
146 "Chinese(gb2312) 美国前司法部长面见萨达姆后称其状态很好 Chinese (gb2312)",
147 "gb2312 character is successfully reassembled",