]> gitweb.factorcode.org Git - factor.git/blob - extra/punycode/punycode-tests.factor
punycode: adding basic support for Punycode (RFC 3492).
[factor.git] / extra / punycode / punycode-tests.factor
1
2 USING: arrays assocs fry kernel punycode tools.test ;
3
4 {
5     ! Wikipedia Examples
6
7     { "" "" }
8     { "A" "A-" }
9     { "3" "3-" }
10     { "-" "--" }
11     { "--" "---" }
12     { "abc" "abc-" }
13     { "London" "London-" }
14     { "Lloyd-Atkinson" "Lloyd-Atkinson-" }
15     { "This has spaces" "This has spaces-" }
16     { "ü" "tda" }
17     { "αβγ" "mxacd" }
18     { "München" "Mnchen-3ya" }
19     { "Mnchen-3ya" "Mnchen-3ya-" }
20     { "München-Ost" "Mnchen-Ost-9db" }
21     { "Bahnhof München-Ost" "Bahnhof Mnchen-Ost-u6b" }
22
23     ! (A) Arabic (Egyptian):
24     {
25         "\u{0644}\u{064A}\u{0647}\u{0645}\u{0627}\u{0628}\u{062A}\u{0643}\u{0644}\u{0645}\u{0648}\u{0634}\u{0639}\u{0631}\u{0628}\u{064A}\u{061F}"
26         "egbpdaj6bu4bxfgehfvwxn"
27     }
28
29     ! (B) Chinese (simplified):
30     {
31         "\u{4ED6}\u{4EEC}\u{4E3A}\u{4EC0}\u{4E48}\u{4E0D}\u{8BF4}\u{4E2D}\u{6587}"
32         "ihqwcrb4cv8a8dqg056pqjye"
33     }
34
35     ! (C) Chinese (traditional):
36     {
37         "\u{4ED6}\u{5011}\u{7232}\u{4EC0}\u{9EBD}\u{4E0D}\u{8AAA}\u{4E2D}\u{6587}"
38         "ihqwctvzc91f659drss3x8bo0yb"
39     }
40
41     ! (D) Czech:
42     {
43        "\u{0050}\u{0072}\u{006F}\u{010D}\u{0070}\u{0072}\u{006F}\u{0073}\u{0074}\u{011B}\u{006E}\u{0065}\u{006D}\u{006C}\u{0075}\u{0076}\u{00ED}\u{010D}\u{0065}\u{0073}\u{006B}\u{0079}"
44        "Proprostnemluvesky-uyb24dma41a"
45     }
46
47     ! (E) Hebrew:
48     {
49         "\u{05DC}\u{05DE}\u{05D4}\u{05D4}\u{05DD}\u{05E4}\u{05E9}\u{05D5}\u{05D8}\u{05DC}\u{05D0}\u{05DE}\u{05D3}\u{05D1}\u{05E8}\u{05D9}\u{05DD}\u{05E2}\u{05D1}\u{05E8}\u{05D9}\u{05EA}"
50         "4dbcagdahymbxekheh6e0a7fei0b"
51     }
52
53     ! (F) Hindi (Devanagari):
54     {
55         "\u{092F}\u{0939}\u{0932}\u{094B}\u{0917}\u{0939}\u{093F}\u{0928}\u{094D}\u{0926}\u{0940}\u{0915}\u{094D}\u{092F}\u{094B}\u{0902}\u{0928}\u{0939}\u{0940}\u{0902}\u{092C}\u{094B}\u{0932}\u{0938}\u{0915}\u{0924}\u{0947}\u{0939}\u{0948}\u{0902}"
56         "i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd"
57     }
58
59     ! (G) Japanese (kanji and hiragana):
60     {
61         "\u{306A}\u{305C}\u{307F}\u{3093}\u{306A}\u{65E5}\u{672C}\u{8A9E}\u{3092}\u{8A71}\u{3057}\u{3066}\u{304F}\u{308C}\u{306A}\u{3044}\u{306E}\u{304B}"
62         "n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa"
63     }
64
65     ! (H) Korean (Hangul syllables):
66     {
67         "\u{C138}\u{ACC4}\u{C758}\u{BAA8}\u{B4E0}\u{C0AC}\u{B78C}\u{B4E4}\u{C774}\u{D55C}\u{AD6D}\u{C5B4}\u{B97C}\u{C774}\u{D574}\u{D55C}\u{B2E4}\u{BA74}\u{C5BC}\u{B9C8}\u{B098}\u{C88B}\u{C744}\u{AE4C}"
68         "989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5jpsd879ccm6fea98c"
69     }
70
71     ! (I) Russian (Cyrillic):
72     {
73         "\u{043F}\u{043E}\u{0447}\u{0435}\u{043C}\u{0443}\u{0436}\u{0435}\u{043E}\u{043D}\u{0438}\u{043D}\u{0435}\u{0433}\u{043E}\u{0432}\u{043E}\u{0440}\u{044F}\u{0442}\u{043F}\u{043E}\u{0440}\u{0443}\u{0441}\u{0441}\u{043A}\u{0438}"
74         ! FIXME: example has upper-case? "b1abfaaepdrnnbgefbaDotcwatmq2g4l"
75         "b1abfaaepdrnnbgefbadotcwatmq2g4l"
76     }
77
78     ! (J) Spanish:
79     {
80         "\u{0050}\u{006F}\u{0072}\u{0071}\u{0075}\u{00E9}\u{006E}\u{006F}\u{0070}\u{0075}\u{0065}\u{0064}\u{0065}\u{006E}\u{0073}\u{0069}\u{006D}\u{0070}\u{006C}\u{0065}\u{006D}\u{0065}\u{006E}\u{0074}\u{0065}\u{0068}\u{0061}\u{0062}\u{006C}\u{0061}\u{0072}\u{0065}\u{006E}\u{0045}\u{0073}\u{0070}\u{0061}\u{00F1}\u{006F}\u{006C}"
81         "PorqunopuedensimplementehablarenEspaol-fmd56a"
82     }
83
84     ! (K) Vietnamese:
85     {
86         "\u{0054}\u{1EA1}\u{0069}\u{0073}\u{0061}\u{006F}\u{0068}\u{1ECD}\u{006B}\u{0068}\u{00F4}\u{006E}\u{0067}\u{0074}\u{0068}\u{1EC3}\u{0063}\u{0068}\u{1EC9}\u{006E}\u{00F3}\u{0069}\u{0074}\u{0069}\u{1EBF}\u{006E}\u{0067}\u{0056}\u{0069}\u{1EC7}\u{0074}"
87         "TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g"
88     }
89
90     ! (L) 3<nen>B<gumi><kinpachi><sensei>
91     {
92         "\u{0033}\u{5E74}\u{0042}\u{7D44}\u{91D1}\u{516B}\u{5148}\u{751F}"
93         "3B-ww4c5e180e575a65lsy2b"
94     }
95
96     ! (M) <amuro><namie>-with-SUPER-MONKEYS
97     {
98         "\u{5B89}\u{5BA4}\u{5948}\u{7F8E}\u{6075}\u{002D}\u{0077}\u{0069}\u{0074}\u{0068}\u{002D}\u{0053}\u{0055}\u{0050}\u{0045}\u{0052}\u{002D}\u{004D}\u{004F}\u{004E}\u{004B}\u{0045}\u{0059}\u{0053}"
99         "-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n"
100     }
101
102     ! (N) Hello-Another-Way-<sorezore><no><basho>
103     {
104         "\u{0048}\u{0065}\u{006C}\u{006C}\u{006F}\u{002D}\u{0041}\u{006E}\u{006F}\u{0074}\u{0068}\u{0065}\u{0072}\u{002D}\u{0057}\u{0061}\u{0079}\u{002D}\u{305D}\u{308C}\u{305E}\u{308C}\u{306E}\u{5834}\u{6240}"
105        "Hello-Another-Way--fc4qua05auwb3674vfr0b"
106     }
107
108     ! (O) <hitotsu><yane><no><shita>2
109     {
110         "\u{3072}\u{3068}\u{3064}\u{5C4B}\u{6839}\u{306E}\u{4E0B}\u{0032}"
111         "2-u9tlzr9756bt3uc0v"
112     }
113
114     ! (P) Maji<de>Koi<suru>5<byou><mae>
115     {
116        "\u{004D}\u{0061}\u{006A}\u{0069}\u{3067}\u{004B}\u{006F}\u{0069}\u{3059}\u{308B}\u{0035}\u{79D2}\u{524D}"
117        "MajiKoi5-783gue6qz075azm5e"
118     }
119
120     ! (Q) <pafii>de<runba>
121     {
122        "\u{30D1}\u{30D5}\u{30A3}\u{30FC}\u{0064}\u{0065}\u{30EB}\u{30F3}\u{30D0}"
123        "de-jg4avhby1noc0d"
124     }
125
126     ! (R) <sono><supiido><de>
127     {
128         "\u{305D}\u{306E}\u{30B9}\u{30D4}\u{30FC}\u{30C9}\u{3067}"
129         "d9juau41awczczp"
130     }
131
132     ! (S) -> $1.00 <-
133     {
134        "\u{002D}\u{003E}\u{0020}\u{0024}\u{0031}\u{002E}\u{0030}\u{0030}\u{0020}\u{003C}\u{002D}"
135         "-> $1.00 <--"
136     }
137 } [
138     [ [ 1array ] dip '[ _ punycode> ] unit-test ]
139     [ 1array swap '[ _ >punycode ] unit-test ] 2bi
140 ] assoc-each
141
142 {
143     { "😉.com" "xn--n28h.com" }
144     { "💩.la" "xn--ls8h.la" }
145     { "са.com" "xn--80a7a.com" } ! phishing
146 } [
147     [ [ 1array ] dip '[ _ idna> ] unit-test ]
148     [ 1array swap '[ _ >idna ] unit-test ] 2bi
149 ] assoc-each