#![no_std]
//! Convert strings to and from IBM-1047.
//!
//! ```rust
//! # #[cfg(feature = "alloc")]
//! # {
//! use ibm1047::Encode;
//! // Warning: flatten will discard characters that cannot be encoded as IBM-1047.
//! let ebcdic: Vec<u8> = "Hello, World!\n".encode_ibm1047().flatten().collect();
//! let string: String = ibm1047::decode(&ebcdic).collect();
//!
//! assert_eq!(string, "Hello, World!\n");
//! # }
//! ```
#[cfg(feature = "alloc")]
extern crate alloc;
#[cfg(feature = "alloc")]
use alloc::string::String;
const UNICODE_TO_IBM1047: [u8; 256] = [
0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x06, 0x17, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x09, 0x0A, 0x1B,
0x30, 0x31, 0x1A, 0x33, 0x34, 0x35, 0x36, 0x08, 0x38, 0x39, 0x3A, 0x3B, 0x04, 0x14, 0x3E, 0xFF,
0x41, 0xAA, 0x4A, 0xB1, 0x9F, 0xB2, 0x6A, 0xB5, 0xBB, 0xB4, 0x9A, 0x8A, 0xB0, 0xCA, 0xAF, 0xBC,
0x90, 0x8F, 0xEA, 0xFA, 0xBE, 0xA0, 0xB6, 0xB3, 0x9D, 0xDA, 0x9B, 0x8B, 0xB7, 0xB8, 0xB9, 0xAB,
0x64, 0x65, 0x62, 0x66, 0x63, 0x67, 0x9E, 0x68, 0x74, 0x71, 0x72, 0x73, 0x78, 0x75, 0x76, 0x77,
0xAC, 0x69, 0xED, 0xEE, 0xEB, 0xEF, 0xEC, 0xBF, 0x80, 0xFD, 0xFE, 0xFB, 0xFC, 0xBA, 0xAE, 0x59,
0x44, 0x45, 0x42, 0x46, 0x43, 0x47, 0x9C, 0x48, 0x54, 0x51, 0x52, 0x53, 0x58, 0x55, 0x56, 0x57,
0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF,
];
const IBM1047_TO_UNICODE: [char; 256] = [
'\u{00}', '\u{01}', '\u{02}', '\u{03}', '\u{9C}', '\u{09}', '\u{86}', '\u{7F}', '\u{97}',
'\u{8D}', '\u{8E}', '\u{0B}', '\u{0C}', '\u{0D}', '\u{0E}', '\u{0F}', '\u{10}', '\u{11}',
'\u{12}', '\u{13}', '\u{9D}', '\u{0A}', '\u{08}', '\u{87}', '\u{18}', '\u{19}', '\u{92}',
'\u{8F}', '\u{1C}', '\u{1D}', '\u{1E}', '\u{1F}', '\u{80}', '\u{81}', '\u{82}', '\u{83}',
'\u{84}', '\u{85}', '\u{17}', '\u{1B}', '\u{88}', '\u{89}', '\u{8A}', '\u{8B}', '\u{8C}',
'\u{05}', '\u{06}', '\u{07}', '\u{90}', '\u{91}', '\u{16}', '\u{93}', '\u{94}', '\u{95}',
'\u{96}', '\u{04}', '\u{98}', '\u{99}', '\u{9A}', '\u{9B}', '\u{14}', '\u{15}', '\u{9E}',
'\u{1A}', '\u{20}', '\u{A0}', '\u{E2}', '\u{E4}', '\u{E0}', '\u{E1}', '\u{E3}', '\u{E5}',
'\u{E7}', '\u{F1}', '\u{A2}', '\u{2E}', '\u{3C}', '\u{28}', '\u{2B}', '\u{7C}', '\u{26}',
'\u{E9}', '\u{EA}', '\u{EB}', '\u{E8}', '\u{ED}', '\u{EE}', '\u{EF}', '\u{EC}', '\u{DF}',
'\u{21}', '\u{24}', '\u{2A}', '\u{29}', '\u{3B}', '\u{5E}', '\u{2D}', '\u{2F}', '\u{C2}',
'\u{C4}', '\u{C0}', '\u{C1}', '\u{C3}', '\u{C5}', '\u{C7}', '\u{D1}', '\u{A6}', '\u{2C}',
'\u{25}', '\u{5F}', '\u{3E}', '\u{3F}', '\u{F8}', '\u{C9}', '\u{CA}', '\u{CB}', '\u{C8}',
'\u{CD}', '\u{CE}', '\u{CF}', '\u{CC}', '\u{60}', '\u{3A}', '\u{23}', '\u{40}', '\u{27}',
'\u{3D}', '\u{22}', '\u{D8}', '\u{61}', '\u{62}', '\u{63}', '\u{64}', '\u{65}', '\u{66}',
'\u{67}', '\u{68}', '\u{69}', '\u{AB}', '\u{BB}', '\u{F0}', '\u{FD}', '\u{FE}', '\u{B1}',
'\u{B0}', '\u{6A}', '\u{6B}', '\u{6C}', '\u{6D}', '\u{6E}', '\u{6F}', '\u{70}', '\u{71}',
'\u{72}', '\u{AA}', '\u{BA}', '\u{E6}', '\u{B8}', '\u{C6}', '\u{A4}', '\u{B5}', '\u{7E}',
'\u{73}', '\u{74}', '\u{75}', '\u{76}', '\u{77}', '\u{78}', '\u{79}', '\u{7A}', '\u{A1}',
'\u{BF}', '\u{D0}', '\u{5B}', '\u{DE}', '\u{AE}', '\u{AC}', '\u{A3}', '\u{A5}', '\u{B7}',
'\u{A9}', '\u{A7}', '\u{B6}', '\u{BC}', '\u{BD}', '\u{BE}', '\u{DD}', '\u{A8}', '\u{AF}',
'\u{5D}', '\u{B4}', '\u{D7}', '\u{7B}', '\u{41}', '\u{42}', '\u{43}', '\u{44}', '\u{45}',
'\u{46}', '\u{47}', '\u{48}', '\u{49}', '\u{AD}', '\u{F4}', '\u{F6}', '\u{F2}', '\u{F3}',
'\u{F5}', '\u{7D}', '\u{4A}', '\u{4B}', '\u{4C}', '\u{4D}', '\u{4E}', '\u{4F}', '\u{50}',
'\u{51}', '\u{52}', '\u{B9}', '\u{FB}', '\u{FC}', '\u{F9}', '\u{FA}', '\u{FF}', '\u{5C}',
'\u{F7}', '\u{53}', '\u{54}', '\u{55}', '\u{56}', '\u{57}', '\u{58}', '\u{59}', '\u{5A}',
'\u{B2}', '\u{D4}', '\u{D6}', '\u{D2}', '\u{D3}', '\u{D5}', '\u{30}', '\u{31}', '\u{32}',
'\u{33}', '\u{34}', '\u{35}', '\u{36}', '\u{37}', '\u{38}', '\u{39}', '\u{B3}', '\u{DB}',
'\u{DC}', '\u{D9}', '\u{DA}', '\u{9F}',
];
pub struct EncodeIbm1047<'a> {
chars: core::str::Chars<'a>,
}
impl<'a> Iterator for EncodeIbm1047<'a> {
type Item = Result<u8, char>;
fn next(&mut self) -> Option<Self::Item> {
let c = self.chars.next()?;
if c as u32 >= UNICODE_TO_IBM1047.len().try_into().unwrap() {
Some(Err(c))
} else {
Some(Ok(UNICODE_TO_IBM1047[c as usize]))
}
}
}
pub struct DecodeIbm1047<'a> {
bytes: core::slice::Iter<'a, u8>,
}
impl<'a> Iterator for DecodeIbm1047<'a> {
type Item = char;
fn next(&mut self) -> Option<Self::Item> {
self.bytes.next().map(|&i| IBM1047_TO_UNICODE[i as usize])
}
}
pub trait Encode {
fn encode_ibm1047(&self) -> EncodeIbm1047;
}
#[cfg(feature = "alloc")]
pub trait Decode {
fn from_ibm1047(bytes: &[u8]) -> String;
}
pub fn decode(bytes: &[u8]) -> DecodeIbm1047 {
DecodeIbm1047 { bytes: bytes.iter() }
}
impl Encode for str {
fn encode_ibm1047(&self) -> EncodeIbm1047 {
EncodeIbm1047 {
chars: self.chars(),
}
}
}
#[cfg(feature = "alloc")]
impl Decode for String {
fn from_ibm1047(bytes: &[u8]) -> String {
let mut str = String::with_capacity(bytes.len());
for &b in bytes {
str.push(IBM1047_TO_UNICODE[b as usize])
}
str
}
}
#[cfg(test)]
mod test {
use crate::Encode;
#[cfg(feature = "alloc")]
use crate::Decode;
const UTF8: &str = "\u{10}\u{89}\u{8}\u{84}\u{1d}»¸¬\u{95}7Bôú|Ëk$Zíîhó5f\u{17} ¡\u{94}\u{9c}/y%\u{8c}Þ,X\u{9d}ßħ\u{5}\u{a0}\u{e}\u{88}vÊ\u{80}\u{1e}x×r\u{3}JõFæ\u{9e}t\u{15}.\u{92}W¹!ÁÖ\u{16}\u{9a}nÌ\u{1b}ý¾Åzì\u{7f}cLÿ¦w\u{2}oE\u{4}¯\u{f}\u{14}\u{98}[º`ãK\u{96}\u{9b}\u{87}Ã\n¤\u{81}ÒS\u{18}Çë8\u{ad}TU:+ép\u{1}¼2<V½Ï\"\u{c}³Y\u{13}Éa\u{8a}²\u{19}~¶µ?e\u{90}\u{8f}Güs\u{86}ø\u{97}Îq=i\u{9f}Õ\u{85}bÍ\u{83}\u{6}#{;_ä\u{11}\u{91}]¥mèRÀÑâ±^Ø\u{1c}\u{99}ûÈ*\u{8e}Qê\u{82}þM\u{8d}}¨O\u{1f}çÐ1ò\u{b}Ô\\\tÛ\u{93}áPà9·ï®Aù«Âª\0÷\u{8b}\u{12}>0ÚCÙ&ñl\u{7}@\rð)Ü-(4¿3£©´åÝ6Dd'öÓ\u{1a}jgH¢uÆIN°";
const IBM1047: &[u8] = &[
0x10, 0x29, 0x16, 0x24, 0x1d, 0x8b, 0x9d, 0xb0, 0x35, 0xf7, 0xc2, 0xcb, 0xde, 0x4f, 0x73,
0x92, 0x5b, 0xe9, 0x55, 0x56, 0x88, 0xce, 0xf5, 0x86, 0x26, 0x40, 0xaa, 0x34, 0x04, 0x61,
0xa8, 0x6c, 0x2c, 0xae, 0x6b, 0xe7, 0x14, 0x59, 0x63, 0xb5, 0x2d, 0x41, 0x0e, 0x28, 0xa5,
0x72, 0x20, 0x1e, 0xa7, 0xbf, 0x99, 0x03, 0xd1, 0xcf, 0xc6, 0x9c, 0x3e, 0xa3, 0x3d, 0x4b,
0x1a, 0xe6, 0xda, 0x5a, 0x65, 0xec, 0x32, 0x3a, 0x95, 0x78, 0x27, 0x8d, 0xb9, 0x67, 0xa9,
0x58, 0x07, 0x83, 0xd3, 0xdf, 0x6a, 0xa6, 0x02, 0x96, 0xc5, 0x37, 0xbc, 0x0f, 0x3c, 0x38,
0xad, 0x9b, 0x79, 0x46, 0xd2, 0x36, 0x3b, 0x17, 0x66, 0x15, 0x9f, 0x21, 0xed, 0xe2, 0x18,
0x68, 0x53, 0xf8, 0xca, 0xe3, 0xe4, 0x7a, 0x4e, 0x51, 0x97, 0x01, 0xb7, 0xf2, 0x4c, 0xe5,
0xb8, 0x77, 0x7f, 0x0c, 0xfa, 0xe8, 0x13, 0x71, 0x81, 0x2a, 0xea, 0x19, 0xa1, 0xb6, 0xa0,
0x6f, 0x85, 0x30, 0x1b, 0xc7, 0xdc, 0xa2, 0x06, 0x70, 0x08, 0x76, 0x98, 0x7e, 0x89, 0xff,
0xef, 0x25, 0x82, 0x75, 0x23, 0x2e, 0x7b, 0xc0, 0x5e, 0x6d, 0x43, 0x11, 0x31, 0xbd, 0xb2,
0x94, 0x54, 0xd9, 0x64, 0x69, 0x42, 0x8f, 0x5f, 0x80, 0x1c, 0x39, 0xdb, 0x74, 0x5c, 0x0a,
0xd8, 0x52, 0x22, 0x8e, 0xd4, 0x09, 0xd0, 0xbb, 0xd6, 0x1f, 0x48, 0xac, 0xf1, 0xcd, 0x0b,
0xeb, 0xe0, 0x05, 0xfb, 0x33, 0x45, 0xd7, 0x44, 0xf9, 0xb3, 0x57, 0xaf, 0xc1, 0xdd, 0x8a,
0x62, 0x9a, 0x00, 0xe1, 0x2b, 0x12, 0x6e, 0xf0, 0xfe, 0xc3, 0xfd, 0x50, 0x49, 0x93, 0x2f,
0x7c, 0x0d, 0x8c, 0x5d, 0xfc, 0x60, 0x4d, 0xf4, 0xab, 0xf3, 0xb1, 0xb4, 0xbe, 0x47, 0xba,
0xf6, 0xc4, 0x84, 0x7d, 0xcc, 0xee, 0x3f, 0x91, 0x87, 0xc8, 0x4a, 0xa4, 0x9e, 0xc9, 0xd5,
0x90,
];
#[test]
fn encode() {
assert!(UTF8.encode_ibm1047().flatten().eq(IBM1047.iter().copied()))
}
#[test]
fn decode() {
assert!(super::decode(IBM1047).eq(UTF8.chars()))
}
#[cfg(feature = "alloc")]
#[test]
fn decode_string() {
assert_eq!(alloc::string::String::from_ibm1047(IBM1047), UTF8)
}
}