1 //! Convert a string in IBM codepage 437 to UTF-8
2 
3 /// Trait to convert IBM codepage 437 to the target type
4 pub trait FromCp437 {
5     /// Target type
6     type Target;
7 
8     /// Function that does the conversion from cp437.
9     /// Generally allocations will be avoided if all data falls into the ASCII range.
10     #[allow(clippy::wrong_self_convention)]
from_cp437(self) -> Self::Target11     fn from_cp437(self) -> Self::Target;
12 }
13 
14 impl<'a> FromCp437 for &'a [u8] {
15     type Target = ::std::borrow::Cow<'a, str>;
16 
from_cp437(self) -> Self::Target17     fn from_cp437(self) -> Self::Target {
18         if self.iter().all(|c| *c < 0x80) {
19             ::std::str::from_utf8(self).unwrap().into()
20         } else {
21             self.iter().map(|c| to_char(*c)).collect::<String>().into()
22         }
23     }
24 }
25 
26 impl FromCp437 for Vec<u8> {
27     type Target = String;
28 
from_cp437(self) -> Self::Target29     fn from_cp437(self) -> Self::Target {
30         if self.iter().all(|c| *c < 0x80) {
31             String::from_utf8(self).unwrap()
32         } else {
33             self.into_iter().map(to_char).collect()
34         }
35     }
36 }
37 
to_char(input: u8) -> char38 fn to_char(input: u8) -> char {
39     let output = match input {
40         0x00..=0x7f => input as u32,
41         0x80 => 0x00c7,
42         0x81 => 0x00fc,
43         0x82 => 0x00e9,
44         0x83 => 0x00e2,
45         0x84 => 0x00e4,
46         0x85 => 0x00e0,
47         0x86 => 0x00e5,
48         0x87 => 0x00e7,
49         0x88 => 0x00ea,
50         0x89 => 0x00eb,
51         0x8a => 0x00e8,
52         0x8b => 0x00ef,
53         0x8c => 0x00ee,
54         0x8d => 0x00ec,
55         0x8e => 0x00c4,
56         0x8f => 0x00c5,
57         0x90 => 0x00c9,
58         0x91 => 0x00e6,
59         0x92 => 0x00c6,
60         0x93 => 0x00f4,
61         0x94 => 0x00f6,
62         0x95 => 0x00f2,
63         0x96 => 0x00fb,
64         0x97 => 0x00f9,
65         0x98 => 0x00ff,
66         0x99 => 0x00d6,
67         0x9a => 0x00dc,
68         0x9b => 0x00a2,
69         0x9c => 0x00a3,
70         0x9d => 0x00a5,
71         0x9e => 0x20a7,
72         0x9f => 0x0192,
73         0xa0 => 0x00e1,
74         0xa1 => 0x00ed,
75         0xa2 => 0x00f3,
76         0xa3 => 0x00fa,
77         0xa4 => 0x00f1,
78         0xa5 => 0x00d1,
79         0xa6 => 0x00aa,
80         0xa7 => 0x00ba,
81         0xa8 => 0x00bf,
82         0xa9 => 0x2310,
83         0xaa => 0x00ac,
84         0xab => 0x00bd,
85         0xac => 0x00bc,
86         0xad => 0x00a1,
87         0xae => 0x00ab,
88         0xaf => 0x00bb,
89         0xb0 => 0x2591,
90         0xb1 => 0x2592,
91         0xb2 => 0x2593,
92         0xb3 => 0x2502,
93         0xb4 => 0x2524,
94         0xb5 => 0x2561,
95         0xb6 => 0x2562,
96         0xb7 => 0x2556,
97         0xb8 => 0x2555,
98         0xb9 => 0x2563,
99         0xba => 0x2551,
100         0xbb => 0x2557,
101         0xbc => 0x255d,
102         0xbd => 0x255c,
103         0xbe => 0x255b,
104         0xbf => 0x2510,
105         0xc0 => 0x2514,
106         0xc1 => 0x2534,
107         0xc2 => 0x252c,
108         0xc3 => 0x251c,
109         0xc4 => 0x2500,
110         0xc5 => 0x253c,
111         0xc6 => 0x255e,
112         0xc7 => 0x255f,
113         0xc8 => 0x255a,
114         0xc9 => 0x2554,
115         0xca => 0x2569,
116         0xcb => 0x2566,
117         0xcc => 0x2560,
118         0xcd => 0x2550,
119         0xce => 0x256c,
120         0xcf => 0x2567,
121         0xd0 => 0x2568,
122         0xd1 => 0x2564,
123         0xd2 => 0x2565,
124         0xd3 => 0x2559,
125         0xd4 => 0x2558,
126         0xd5 => 0x2552,
127         0xd6 => 0x2553,
128         0xd7 => 0x256b,
129         0xd8 => 0x256a,
130         0xd9 => 0x2518,
131         0xda => 0x250c,
132         0xdb => 0x2588,
133         0xdc => 0x2584,
134         0xdd => 0x258c,
135         0xde => 0x2590,
136         0xdf => 0x2580,
137         0xe0 => 0x03b1,
138         0xe1 => 0x00df,
139         0xe2 => 0x0393,
140         0xe3 => 0x03c0,
141         0xe4 => 0x03a3,
142         0xe5 => 0x03c3,
143         0xe6 => 0x00b5,
144         0xe7 => 0x03c4,
145         0xe8 => 0x03a6,
146         0xe9 => 0x0398,
147         0xea => 0x03a9,
148         0xeb => 0x03b4,
149         0xec => 0x221e,
150         0xed => 0x03c6,
151         0xee => 0x03b5,
152         0xef => 0x2229,
153         0xf0 => 0x2261,
154         0xf1 => 0x00b1,
155         0xf2 => 0x2265,
156         0xf3 => 0x2264,
157         0xf4 => 0x2320,
158         0xf5 => 0x2321,
159         0xf6 => 0x00f7,
160         0xf7 => 0x2248,
161         0xf8 => 0x00b0,
162         0xf9 => 0x2219,
163         0xfa => 0x00b7,
164         0xfb => 0x221a,
165         0xfc => 0x207f,
166         0xfd => 0x00b2,
167         0xfe => 0x25a0,
168         0xff => 0x00a0,
169     };
170     ::std::char::from_u32(output).unwrap()
171 }
172 
173 #[cfg(test)]
174 mod test {
175     #[test]
to_char_valid()176     fn to_char_valid() {
177         for i in 0x00_u32..0x100 {
178             super::to_char(i as u8);
179         }
180     }
181 
182     #[test]
ascii()183     fn ascii() {
184         for i in 0x00..0x80 {
185             assert_eq!(super::to_char(i), i as char);
186         }
187     }
188 
189     #[test]
example_slice()190     fn example_slice() {
191         use super::FromCp437;
192         let data = b"Cura\x87ao";
193         assert!(::std::str::from_utf8(data).is_err());
194         assert_eq!(data.from_cp437(), "Curaçao");
195     }
196 
197     #[test]
example_vec()198     fn example_vec() {
199         use super::FromCp437;
200         let data = vec![0xCC, 0xCD, 0xCD, 0xB9];
201         assert!(String::from_utf8(data.clone()).is_err());
202         assert_eq!(&data.from_cp437(), "╠══╣");
203     }
204 }
205