mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-14 06:22:24 +00:00
Dylan M. Taylor
c516452b47
craft-rtf and craft-dxf each carried tables for DOS 437, 737, 850, 852 and 857 (and craft-rtf one for 866). They are now one set in craft-codepage, which takes craft-rtf's codepage module (Windows and Mac tables, OEM glyphs, font charsets) and craft-dxf's DOS tables. craft_rtf::codepage re-exports it unchanged; craft-dxf keeps its $DWGCODEPAGE names and Decoder and looks the DOS tables up there. Every byte of every code page either crate decodes is unchanged: the public decoders of both crates were dumped over all 256 bytes of each page (and the East Asian pairs) before and after, and the dumps are identical. craft-mime now reads the DOS pages by their IANA names (IBM437, cp850, ibm-852, 857...), which it read as UTF-8 before.
441 lines
26 KiB
Rust
441 lines
26 KiB
Rust
#![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)]
|
||
//! Legacy 8-bit code pages, one table each, for every reader of old text: Windows-1252 and the other single-byte Windows
|
||
//! code pages RTF files name with `\ansicpg` or a font's `\fcharset` (Cyrillic 1251, Central
|
||
//! European 1250, Greek, Turkish, Hebrew, Arabic, Baltic, Vietnamese, Thai), Mac OS Roman
|
||
//! (10000, RTF `\mac`), and the East Asian multibyte code pages (932 Shift-JIS, 936 GBK, 949 UHC,
|
||
//! 950 Big5), whose bytes decode as runs rather than one at a time (by `encoding_rs`, see
|
||
//! [`multibyte_encoding_name`]), and the DOS (OEM) code pages ([`dos_upper`], [`oem_byte`]).
|
||
//!
|
||
//! Keyed by Windows code page number. Readers that name code pages otherwise (a DXF file's
|
||
//! `$DWGCODEPAGE`, a MIME charset label) map their names to these numbers.
|
||
|
||
#[cfg(doctest)]
|
||
#[doc = include_str!("../README.md")]
|
||
struct ReadmeExamples;
|
||
|
||
pub mod dos;
|
||
|
||
/// Windows-1252 code points for 0x80..=0x9F.
|
||
const CP1252: [u16; 32] = [
|
||
0x20AC, 0x0081, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x008D, 0x017D, 0x008F, 0x0090, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x009D, 0x017E, 0x0178,
|
||
];
|
||
|
||
/// One Windows-1252 byte as a char.
|
||
pub fn cp1252(b: u8) -> char {
|
||
if (0x80..0xA0).contains(&b) {
|
||
CP1252.get((b - 0x80) as usize).and_then(|u| char::from_u32(u32::from(*u))).unwrap_or('\u{FFFD}')
|
||
} else {
|
||
b as char
|
||
}
|
||
}
|
||
|
||
/// Windows-874 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP874: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2026, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x00A0, 0x0E01, 0x0E02, 0x0E03,
|
||
0x0E04, 0x0E05, 0x0E06, 0x0E07, 0x0E08, 0x0E09, 0x0E0A, 0x0E0B, 0x0E0C, 0x0E0D, 0x0E0E, 0x0E0F, 0x0E10, 0x0E11, 0x0E12, 0x0E13, 0x0E14, 0x0E15,
|
||
0x0E16, 0x0E17, 0x0E18, 0x0E19, 0x0E1A, 0x0E1B, 0x0E1C, 0x0E1D, 0x0E1E, 0x0E1F, 0x0E20, 0x0E21, 0x0E22, 0x0E23, 0x0E24, 0x0E25, 0x0E26, 0x0E27,
|
||
0x0E28, 0x0E29, 0x0E2A, 0x0E2B, 0x0E2C, 0x0E2D, 0x0E2E, 0x0E2F, 0x0E30, 0x0E31, 0x0E32, 0x0E33, 0x0E34, 0x0E35, 0x0E36, 0x0E37, 0x0E38, 0x0E39,
|
||
0x0E3A, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x0E3F, 0x0E40, 0x0E41, 0x0E42, 0x0E43, 0x0E44, 0x0E45, 0x0E46, 0x0E47, 0x0E48, 0x0E49, 0x0E4A, 0x0E4B,
|
||
0x0E4C, 0x0E4D, 0x0E4E, 0x0E4F, 0x0E50, 0x0E51, 0x0E52, 0x0E53, 0x0E54, 0x0E55, 0x0E56, 0x0E57, 0x0E58, 0x0E59, 0x0E5A, 0x0E5B, 0xFFFD, 0xFFFD,
|
||
0xFFFD, 0xFFFD,
|
||
];
|
||
|
||
/// Windows-1250 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1250: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0xFFFD, 0x201E, 0x2026, 0x2020, 0x2021, 0xFFFD, 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0x0161, 0x203A, 0x015B, 0x0165, 0x017E, 0x017A, 0x00A0, 0x02C7, 0x02D8, 0x0141,
|
||
0x00A4, 0x0104, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x017B, 0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E, 0x017C, 0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7,
|
||
0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E, 0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7, 0x0158, 0x016E,
|
||
0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF, 0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7, 0x010D, 0x00E9, 0x0119, 0x00EB,
|
||
0x011B, 0x00ED, 0x00EE, 0x010F, 0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD,
|
||
0x0163, 0x02D9,
|
||
];
|
||
|
||
/// Windows-1251 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1251: [u16; 128] = [
|
||
0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021, 0x20AC, 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F, 0x0452, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0x0459, 0x203A, 0x045A, 0x045C, 0x045B, 0x045F, 0x00A0, 0x040E, 0x045E, 0x0408,
|
||
0x00A4, 0x0490, 0x00A6, 0x00A7, 0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x0407, 0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5,
|
||
0x00B6, 0x00B7, 0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455, 0x0457, 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
|
||
0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F, 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429,
|
||
0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F, 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043A, 0x043B,
|
||
0x043C, 0x043D, 0x043E, 0x043F, 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D,
|
||
0x044E, 0x044F,
|
||
];
|
||
|
||
/// Windows-1253 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1253: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0xFFFD, 0x2030, 0xFFFD, 0x2039, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0xFFFD, 0x203A, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x00A0, 0x0385, 0x0386, 0x00A3,
|
||
0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0xFFFD, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x2015, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x00B5,
|
||
0x00B6, 0x00B7, 0x0388, 0x0389, 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E, 0x038F, 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
|
||
0x0398, 0x0399, 0x039A, 0x039B, 0x039C, 0x039D, 0x039E, 0x039F, 0x03A0, 0x03A1, 0xFFFD, 0x03A3, 0x03A4, 0x03A5, 0x03A6, 0x03A7, 0x03A8, 0x03A9,
|
||
0x03AA, 0x03AB, 0x03AC, 0x03AD, 0x03AE, 0x03AF, 0x03B0, 0x03B1, 0x03B2, 0x03B3, 0x03B4, 0x03B5, 0x03B6, 0x03B7, 0x03B8, 0x03B9, 0x03BA, 0x03BB,
|
||
0x03BC, 0x03BD, 0x03BE, 0x03BF, 0x03C0, 0x03C1, 0x03C2, 0x03C3, 0x03C4, 0x03C5, 0x03C6, 0x03C7, 0x03C8, 0x03C9, 0x03CA, 0x03CB, 0x03CC, 0x03CD,
|
||
0x03CE, 0xFFFD,
|
||
];
|
||
|
||
/// Windows-1254 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1254: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0xFFFD, 0xFFFD, 0x0178, 0x00A0, 0x00A1, 0x00A2, 0x00A3,
|
||
0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF, 0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
||
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF, 0x011E, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7, 0x00D8, 0x00D9,
|
||
0x00DA, 0x00DB, 0x00DC, 0x0130, 0x015E, 0x00DF, 0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7, 0x00E8, 0x00E9, 0x00EA, 0x00EB,
|
||
0x00EC, 0x00ED, 0x00EE, 0x00EF, 0x011F, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7, 0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0131,
|
||
0x015F, 0x00FF,
|
||
];
|
||
|
||
/// Windows-1255 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1255: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0xFFFD, 0x2039, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0xFFFD, 0x203A, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x00A0, 0x00A1, 0x00A2, 0x00A3,
|
||
0x20AA, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF, 0x05B0, 0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7,
|
||
0x05B8, 0x05B9, 0x05BA, 0x05BB, 0x05BC, 0x05BD, 0x05BE, 0x05BF, 0x05C0, 0x05C1, 0x05C2, 0x05C3, 0x05F0, 0x05F1, 0x05F2, 0x05F3, 0x05F4, 0xFFFD,
|
||
0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8, 0x05D9, 0x05DA, 0x05DB,
|
||
0x05DC, 0x05DD, 0x05DE, 0x05DF, 0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7, 0x05E8, 0x05E9, 0x05EA, 0xFFFD, 0xFFFD, 0x200E,
|
||
0x200F, 0xFFFD,
|
||
];
|
||
|
||
/// Windows-1256 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1256: [u16; 128] = [
|
||
0x20AC, 0x067E, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0x0679, 0x2039, 0x0152, 0x0686, 0x0698, 0x0688, 0x06AF, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x06A9, 0x2122, 0x0691, 0x203A, 0x0153, 0x200C, 0x200D, 0x06BA, 0x00A0, 0x060C, 0x00A2, 0x00A3,
|
||
0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x06BE, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x061B, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x061F, 0x06C1, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627,
|
||
0x0628, 0x0629, 0x062A, 0x062B, 0x062C, 0x062D, 0x062E, 0x062F, 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x00D7, 0x0637, 0x0638,
|
||
0x0639, 0x063A, 0x0640, 0x0641, 0x0642, 0x0643, 0x00E0, 0x0644, 0x00E2, 0x0645, 0x0646, 0x0647, 0x0648, 0x00E7, 0x00E8, 0x00E9, 0x00EA, 0x00EB,
|
||
0x0649, 0x064A, 0x00EE, 0x00EF, 0x064B, 0x064C, 0x064D, 0x064E, 0x00F4, 0x064F, 0x0650, 0x00F7, 0x0651, 0x00F9, 0x0652, 0x00FB, 0x00FC, 0x200E,
|
||
0x200F, 0x06D2,
|
||
];
|
||
|
||
/// Windows-1257 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1257: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0xFFFD, 0x201E, 0x2026, 0x2020, 0x2021, 0xFFFD, 0x2030, 0xFFFD, 0x2039, 0xFFFD, 0x00A8, 0x02C7, 0x00B8, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0xFFFD, 0x2122, 0xFFFD, 0x203A, 0xFFFD, 0x00AF, 0x02DB, 0xFFFD, 0x00A0, 0xFFFD, 0x00A2, 0x00A3,
|
||
0x00A4, 0xFFFD, 0x00A6, 0x00A7, 0x00D8, 0x00A9, 0x0156, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00C6, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00F8, 0x00B9, 0x0157, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00E6, 0x0104, 0x012E, 0x0100, 0x0106, 0x00C4, 0x00C5, 0x0118, 0x0112,
|
||
0x010C, 0x00C9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012A, 0x013B, 0x0160, 0x0143, 0x0145, 0x00D3, 0x014C, 0x00D5, 0x00D6, 0x00D7, 0x0172, 0x0141,
|
||
0x015A, 0x016A, 0x00DC, 0x017B, 0x017D, 0x00DF, 0x0105, 0x012F, 0x0101, 0x0107, 0x00E4, 0x00E5, 0x0119, 0x0113, 0x010D, 0x00E9, 0x017A, 0x0117,
|
||
0x0123, 0x0137, 0x012B, 0x013C, 0x0161, 0x0144, 0x0146, 0x00F3, 0x014D, 0x00F5, 0x00F6, 0x00F7, 0x0173, 0x0142, 0x015B, 0x016B, 0x00FC, 0x017C,
|
||
0x017E, 0x02D9,
|
||
];
|
||
|
||
/// Windows-1258 code points for 0x80..=0xFF (U+FFFD where the byte is unassigned).
|
||
const CP1258: [u16; 128] = [
|
||
0x20AC, 0xFFFD, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0xFFFD, 0x2039, 0x0152, 0xFFFD, 0xFFFD, 0xFFFD, 0xFFFD, 0x2018,
|
||
0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0xFFFD, 0x203A, 0x0153, 0xFFFD, 0xFFFD, 0x0178, 0x00A0, 0x00A1, 0x00A2, 0x00A3,
|
||
0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
|
||
0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF, 0x00C0, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
|
||
0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x0300, 0x00CD, 0x00CE, 0x00CF, 0x0110, 0x00D1, 0x0309, 0x00D3, 0x00D4, 0x01A0, 0x00D6, 0x00D7, 0x00D8, 0x00D9,
|
||
0x00DA, 0x00DB, 0x00DC, 0x01AF, 0x0303, 0x00DF, 0x00E0, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x00E5, 0x00E6, 0x00E7, 0x00E8, 0x00E9, 0x00EA, 0x00EB,
|
||
0x0301, 0x00ED, 0x00EE, 0x00EF, 0x0111, 0x00F1, 0x0323, 0x00F3, 0x00F4, 0x01A1, 0x00F6, 0x00F7, 0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x01B0,
|
||
0x20AB, 0x00FF,
|
||
];
|
||
|
||
/// Mac OS Roman (code page 10000, RTF `\mac`) code points for 0x80..=0xFF, with the euro sign at
|
||
/// 0xDB (Mac OS 8.5 and later).
|
||
const MAC_ROMAN: [u16; 128] = [
|
||
0x00C4, 0x00C5, 0x00C7, 0x00C9, 0x00D1, 0x00D6, 0x00DC, 0x00E1, 0x00E0, 0x00E2, 0x00E4, 0x00E3, 0x00E5, 0x00E7, 0x00E9, 0x00E8, 0x00EA, 0x00EB,
|
||
0x00ED, 0x00EC, 0x00EE, 0x00EF, 0x00F1, 0x00F3, 0x00F2, 0x00F4, 0x00F6, 0x00F5, 0x00FA, 0x00F9, 0x00FB, 0x00FC, 0x2020, 0x00B0, 0x00A2, 0x00A3,
|
||
0x00A7, 0x2022, 0x00B6, 0x00DF, 0x00AE, 0x00A9, 0x2122, 0x00B4, 0x00A8, 0x2260, 0x00C6, 0x00D8, 0x221E, 0x00B1, 0x2264, 0x2265, 0x00A5, 0x00B5,
|
||
0x2202, 0x2211, 0x220F, 0x03C0, 0x222B, 0x00AA, 0x00BA, 0x03A9, 0x00E6, 0x00F8, 0x00BF, 0x00A1, 0x00AC, 0x221A, 0x0192, 0x2248, 0x2206, 0x00AB,
|
||
0x00BB, 0x2026, 0x00A0, 0x00C0, 0x00C3, 0x00D5, 0x0152, 0x0153, 0x2013, 0x2014, 0x201C, 0x201D, 0x2018, 0x2019, 0x00F7, 0x25CA, 0x00FF, 0x0178,
|
||
0x2044, 0x20AC, 0x2039, 0x203A, 0xFB01, 0xFB02, 0x2021, 0x00B7, 0x201A, 0x201E, 0x2030, 0x00C2, 0x00CA, 0x00C1, 0x00CB, 0x00C8, 0x00CD, 0x00CE,
|
||
0x00CF, 0x00CC, 0x00D3, 0x00D4, 0xF8FF, 0x00D2, 0x00DA, 0x00DB, 0x00D9, 0x0131, 0x02C6, 0x02DC, 0x00AF, 0x02D8, 0x02D9, 0x02DA, 0x00B8, 0x02DD,
|
||
0x02DB, 0x02C7,
|
||
];
|
||
|
||
/// The glyphs the OEM code pages show for 0x01..=0x1F (smileys, card suits, arrows), as
|
||
/// Windows' Alt+numpad entry produces them rather than the control characters.
|
||
const OEM_GLYPHS: [u16; 31] = [
|
||
0x263A, 0x263B, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022, 0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x266B, 0x263C, 0x25BA, 0x25C4, 0x2195,
|
||
0x203C, 0x00B6, 0x00A7, 0x25AC, 0x21A8, 0x2191, 0x2193, 0x2192, 0x2190, 0x221F, 0x2194, 0x25B2, 0x25BC,
|
||
];
|
||
|
||
/// The OEM code pages [`oem_byte`] decodes.
|
||
pub const OEM_CODE_PAGES: [u16; 6] = [437, 737, 850, 852, 857, 866];
|
||
|
||
/// One byte of an OEM code page in [`OEM_CODE_PAGES`] (any other code page reads as 437) as a
|
||
/// char, with the graphic glyphs for 0x01..=0x1F and 0x7F (⌂); 0x00 stays NUL.
|
||
pub fn oem_byte(code_page: u16, b: u8) -> char {
|
||
if b >= 0x80 {
|
||
let table = dos_upper(code_page).filter(|_| OEM_CODE_PAGES.contains(&code_page)).unwrap_or(&dos::DOS437);
|
||
return table.get(usize::from(b - 0x80)).copied().unwrap_or('\u{FFFD}');
|
||
}
|
||
let u = match b {
|
||
0x01..=0x1F => OEM_GLYPHS.get(usize::from(b - 1)).copied(),
|
||
0x7F => Some(0x2302),
|
||
_ => Some(u16::from(b)),
|
||
};
|
||
u.and_then(|u| char::from_u32(u32::from(u))).unwrap_or('\u{FFFD}')
|
||
}
|
||
|
||
/// The DOS (OEM) code pages [`dos_upper`] has a table for.
|
||
pub const DOS_CODE_PAGES: [u16; 15] = [437, 720, 737, 775, 850, 852, 855, 857, 860, 861, 863, 864, 865, 866, 869];
|
||
|
||
/// The upper half (bytes 0x80–0xFF, U+FFFD where unassigned) of a DOS code page in
|
||
/// [`DOS_CODE_PAGES`]; its lower half is ASCII, except that DOS 864 has U+066A (ARABIC PERCENT
|
||
/// SIGN) at 0x25.
|
||
pub fn dos_upper(code_page: u16) -> Option<&'static [char; 128]> {
|
||
Some(match code_page {
|
||
437 => &dos::DOS437,
|
||
720 => &dos::DOS720,
|
||
737 => &dos::DOS737,
|
||
775 => &dos::DOS775,
|
||
850 => &dos::DOS850,
|
||
852 => &dos::DOS852,
|
||
855 => &dos::DOS855,
|
||
857 => &dos::DOS857,
|
||
860 => &dos::DOS860,
|
||
861 => &dos::DOS861,
|
||
863 => &dos::DOS863,
|
||
864 => &dos::DOS864,
|
||
865 => &dos::DOS865,
|
||
866 => &dos::DOS866,
|
||
869 => &dos::DOS869,
|
||
_ => return None,
|
||
})
|
||
}
|
||
|
||
/// The single-byte Windows code pages [`windows_byte`] decodes (1252 included).
|
||
pub const SINGLE_BYTE_CODE_PAGES: [u16; 10] = [874, 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, 1258];
|
||
|
||
/// Mac OS Roman, RTF's `\mac` character set.
|
||
pub const MAC_ROMAN_CODE_PAGE: u16 = 10000;
|
||
|
||
/// One byte of a single-byte code page as a char: a Windows one in [`SINGLE_BYTE_CODE_PAGES`] or
|
||
/// Mac OS Roman ([`MAC_ROMAN_CODE_PAGE`]); any other code page reads as Windows-1252.
|
||
pub fn windows_byte(code_page: u16, b: u8) -> char {
|
||
let table: &[u16; 128] = match code_page {
|
||
874 => &CP874,
|
||
1250 => &CP1250,
|
||
1251 => &CP1251,
|
||
1253 => &CP1253,
|
||
1254 => &CP1254,
|
||
1255 => &CP1255,
|
||
1256 => &CP1256,
|
||
1257 => &CP1257,
|
||
1258 => &CP1258,
|
||
MAC_ROMAN_CODE_PAGE => &MAC_ROMAN,
|
||
_ => return cp1252(b),
|
||
};
|
||
if b < 0x80 {
|
||
return b as char;
|
||
}
|
||
table.get(usize::from(b - 0x80)).and_then(|u| char::from_u32(u32::from(*u))).unwrap_or('\u{FFFD}')
|
||
}
|
||
|
||
/// Whether [`code_page_byte`] decodes `code_page`: a Windows one ([`SINGLE_BYTE_CODE_PAGES`]), an
|
||
/// OEM (DOS) one ([`OEM_CODE_PAGES`]) or Mac OS Roman. Document formats (RTF) name all three.
|
||
pub fn is_byte_code_page(code_page: u16) -> bool {
|
||
SINGLE_BYTE_CODE_PAGES.contains(&code_page) || OEM_CODE_PAGES.contains(&code_page) || code_page == MAC_ROMAN_CODE_PAGE
|
||
}
|
||
|
||
/// Windows' symbol code page (`CP_SYMBOL`), the charset of symbol fonts (`\fcharset2`): a byte is
|
||
/// the font's own code, not a letter. [`code_page_byte`] reads one from 0x80 as U+F000 + the byte,
|
||
/// the form a Word symbol character takes (`w:sym w:char="F0D8"`).
|
||
pub const SYMBOL_CODE_PAGE: u16 = 42;
|
||
|
||
/// A byte of 8-bit document text in `code_page` (see [`is_byte_code_page`], and
|
||
/// [`SYMBOL_CODE_PAGE`] for a symbol font) as a char. Below 0x80 it is ASCII in every code page
|
||
/// (text, so an OEM page's glyphs for control codes don't apply).
|
||
pub fn code_page_byte(code_page: u16, b: u8) -> char {
|
||
if b >= 0x80 && code_page == SYMBOL_CODE_PAGE {
|
||
return char::from_u32(0xF000 + u32::from(b)).unwrap_or('\u{FFFD}');
|
||
}
|
||
if b >= 0x80 && OEM_CODE_PAGES.contains(&code_page) { oem_byte(code_page, b) } else { windows_byte(code_page, b) }
|
||
}
|
||
|
||
/// The East Asian multibyte code pages a document format names with `\ansicpg` or a font's `\cpg`:
|
||
/// 932 Shift-JIS (Japanese), 936 GBK (Simplified Chinese), 949 UHC (Korean) and 950 Big5
|
||
/// (Traditional Chinese).
|
||
pub const MULTIBYTE_CODE_PAGES: [u16; 4] = [932, 936, 949, 950];
|
||
|
||
/// Whether `code_page` is one of the East Asian multibyte code pages ([`MULTIBYTE_CODE_PAGES`]):
|
||
/// its bytes decode as a run, a lead byte together with its trail byte.
|
||
pub fn is_multibyte_code_page(code_page: u16) -> bool {
|
||
multibyte_encoding_name(code_page).is_some()
|
||
}
|
||
|
||
/// The WHATWG encoding name of an East Asian multibyte code page (see [`MULTIBYTE_CODE_PAGES`]),
|
||
/// for `encoding_rs::Encoding::for_label`; `None` for the single-byte code pages, whose bytes
|
||
/// decode one at a time, and anything else.
|
||
pub fn multibyte_encoding_name(code_page: u16) -> Option<&'static str> {
|
||
Some(match code_page {
|
||
932 => "shift_jis",
|
||
936 => "gbk",
|
||
949 => "euc-kr",
|
||
950 => "big5",
|
||
_ => return None,
|
||
})
|
||
}
|
||
|
||
/// Whether a document format can name `code_page` for its text: a single-byte Windows, DOS or Mac
|
||
/// one ([`is_byte_code_page`]) or an East Asian multibyte one ([`is_multibyte_code_page`]).
|
||
pub fn is_text_code_page(code_page: u16) -> bool {
|
||
is_byte_code_page(code_page) || is_multibyte_code_page(code_page)
|
||
}
|
||
|
||
/// The code page of an RTF or Word font charset (`\fcharset`): 204 Russian → 1251, 238 Eastern
|
||
/// European → 1250, 77 Mac → 10000, 254 PC / 255 OEM → 437, 128 Japanese → 932, 129 Korean → 949,
|
||
/// 134 Simplified Chinese → 936, 136 Traditional Chinese → 950, 2 Symbol → [`SYMBOL_CODE_PAGE`]…
|
||
/// `None` for the ANSI and default charsets (the document's code page applies).
|
||
pub fn charset_code_page(charset: i32) -> Option<u16> {
|
||
Some(match charset {
|
||
2 => SYMBOL_CODE_PAGE,
|
||
77 => MAC_ROMAN_CODE_PAGE,
|
||
128 => 932,
|
||
129 => 949,
|
||
134 => 936,
|
||
136 => 950,
|
||
161 => 1253,
|
||
162 => 1254,
|
||
163 => 1258,
|
||
177 => 1255,
|
||
178 => 1256,
|
||
186 => 1257,
|
||
204 => 1251,
|
||
222 => 874,
|
||
238 => 1250,
|
||
254 | 255 => 437,
|
||
_ => return None,
|
||
})
|
||
}
|
||
|
||
#[cfg(test)]
|
||
mod tests {
|
||
use super::*;
|
||
|
||
#[test]
|
||
fn single_byte_code_pages() {
|
||
let decode = |cp: u16, bytes: &[u8]| bytes.iter().map(|&b| windows_byte(cp, b)).collect::<String>();
|
||
assert_eq!(decode(1251, &[0xD1, 0xF7, 0xE5, 0xF2, 0x20, 0xB9]), "Счет №");
|
||
assert_eq!(decode(1251, &[0xA8, 0xB8]), "Ёё");
|
||
assert_eq!(decode(1250, &[0xA3, 0xF3, 0x9F]), "Łóź");
|
||
assert_eq!(decode(1253, &[0xC1, 0xE2]), "Αβ");
|
||
assert_eq!(decode(1252, &[0x80, 0xE9]), "ێ");
|
||
assert_eq!(decode(9999, &[0xE9]), "é");
|
||
// Mac OS Roman: accents, the euro sign at 0xDB, typographic quotes.
|
||
assert_eq!(decode(10000, &[0x80, 0x8E, 0xDB, 0xF1, 0xF2, 0xF3, 0xD2, 0xD3, 0x41]), "Äé€ÒÚÛ“”A");
|
||
assert_eq!(charset_code_page(77), Some(10000));
|
||
assert_eq!(charset_code_page(254), Some(437));
|
||
assert_eq!(charset_code_page(255), Some(437));
|
||
assert_eq!(charset_code_page(204), Some(1251));
|
||
assert_eq!(charset_code_page(0), None);
|
||
for cp in SINGLE_BYTE_CODE_PAGES {
|
||
for b in 0..=255u8 {
|
||
let _ = windows_byte(cp, b);
|
||
}
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn windows_1255_holam_haser_for_vav() {
|
||
assert_eq!(windows_byte(1255, 0xCA), '\u{05BA}');
|
||
}
|
||
|
||
/// One decoder for document text in any code page RTF names: Windows, DOS or Mac.
|
||
#[test]
|
||
fn document_text_in_windows_dos_and_mac_code_pages() {
|
||
let decode = |cp: u16, bytes: &[u8]| bytes.iter().map(|&b| code_page_byte(cp, b)).collect::<String>();
|
||
assert_eq!(decode(437, &[0x82, 0xA0, 0x41, 0x01]), "éáA\u{1}", "DOS text; ASCII stays ASCII");
|
||
assert_eq!(decode(850, &[0x9D, 0xE9]), "ØÚ");
|
||
assert_eq!(decode(10000, &[0x8E]), "é");
|
||
assert_eq!(decode(1251, &[0xC4]), "Д");
|
||
// A symbol font's bytes are its own codes, from 0x80 the private-use form; ASCII stays ASCII.
|
||
assert_eq!(charset_code_page(2), Some(SYMBOL_CODE_PAGE));
|
||
assert_eq!(decode(SYMBOL_CODE_PAGE, &[0x4A, 0x93, 0xD8, 0xFC]), "J\u{F093}\u{F0D8}\u{F0FC}");
|
||
for cp in [437, 850, 866, 1250, 1252, 10000] {
|
||
assert!(is_byte_code_page(cp), "{cp}");
|
||
}
|
||
assert!(!is_byte_code_page(932) && !is_byte_code_page(0) && !SINGLE_BYTE_CODE_PAGES.contains(&10000));
|
||
}
|
||
|
||
/// The East Asian charsets and code pages RTF names are multibyte: their bytes decode
|
||
/// as runs (a lead byte and its trail byte together), not one at a time.
|
||
#[test]
|
||
fn east_asian_code_pages_are_multibyte() {
|
||
assert_eq!(charset_code_page(128), Some(932), "Japanese");
|
||
assert_eq!(charset_code_page(129), Some(949), "Korean");
|
||
assert_eq!(charset_code_page(134), Some(936), "Simplified Chinese");
|
||
assert_eq!(charset_code_page(136), Some(950), "Traditional Chinese");
|
||
assert_eq!(charset_code_page(255), Some(437), "OEM is single-byte");
|
||
assert_eq!(MULTIBYTE_CODE_PAGES, [932, 936, 949, 950]);
|
||
for cp in MULTIBYTE_CODE_PAGES {
|
||
assert!(is_multibyte_code_page(cp) && is_text_code_page(cp), "{cp}");
|
||
assert!(!is_byte_code_page(cp) && !SINGLE_BYTE_CODE_PAGES.contains(&cp), "{cp}");
|
||
assert!(multibyte_encoding_name(cp).is_some(), "{cp}");
|
||
}
|
||
assert!(is_text_code_page(1251) && is_text_code_page(437) && is_text_code_page(10000));
|
||
assert!(!is_text_code_page(0) && !is_text_code_page(9999));
|
||
}
|
||
|
||
/// The Windows and Mac tables are the WHATWG Encoding Standard's single-byte indexes, except
|
||
/// that a byte the code page leaves unassigned is U+FFFD here (outside Windows-1252) where the
|
||
/// standard gives the C1 control of the same number.
|
||
#[test]
|
||
fn windows_tables_agree_with_the_encoding_standard() {
|
||
for cp in SINGLE_BYTE_CODE_PAGES.into_iter().chain([MAC_ROMAN_CODE_PAGE]) {
|
||
let label = if cp == MAC_ROMAN_CODE_PAGE { "macintosh".to_string() } else { format!("windows-{cp}") };
|
||
let enc = encoding_rs::Encoding::for_label(label.as_bytes()).unwrap();
|
||
for b in 0..=255u8 {
|
||
let standard = enc.decode_without_bom_handling(&[b]).0.chars().next().unwrap();
|
||
let ours = windows_byte(cp, b);
|
||
let hole = cp != 1252 && ours == '\u{FFFD}' && standard == char::from(b) && (0x80..0xA0).contains(&b);
|
||
assert!(ours == standard || hole, "{cp} {b:#x}: {ours:?} {standard:?}");
|
||
}
|
||
}
|
||
}
|
||
|
||
/// DOS 866 is also the standard's IBM866.
|
||
#[test]
|
||
fn dos_866_agrees_with_the_encoding_standard() {
|
||
for b in 0x80..=0xFFu8 {
|
||
let standard = encoding_rs::IBM866.decode_without_bom_handling(&[b]).0.chars().next().unwrap();
|
||
assert_eq!(dos::DOS866[usize::from(b - 0x80)], standard, "{b:#x}");
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn every_dos_page_has_a_table_and_oem_byte_uses_it() {
|
||
for cp in DOS_CODE_PAGES {
|
||
let t = dos_upper(cp).unwrap();
|
||
assert!(t.iter().all(|c| !c.is_ascii()), "{cp}");
|
||
}
|
||
for cp in OEM_CODE_PAGES {
|
||
for b in 0x80..=0xFFu8 {
|
||
assert_eq!(oem_byte(cp, b), dos_upper(cp).unwrap()[usize::from(b - 0x80)], "{cp} {b:#x}");
|
||
}
|
||
}
|
||
// 437 and 850 differ on 0x9B (¢ / ø); 864 is DOS Arabic.
|
||
assert_eq!((dos_upper(437).unwrap()[0x1B], dos_upper(850).unwrap()[0x1B]), ('¢', 'ø'));
|
||
assert_eq!(dos_upper(864).unwrap()[0], '\u{00B0}');
|
||
assert_eq!(dos_upper(1252), None);
|
||
assert_eq!(oem_byte(720, 0xE9), oem_byte(437, 0xE9), "a page oem_byte doesn't list reads as 437");
|
||
}
|
||
|
||
#[test]
|
||
fn oem_code_pages() {
|
||
let decode = |cp: u16, bytes: &[u8]| bytes.iter().map(|&b| oem_byte(cp, b)).collect::<String>();
|
||
assert_eq!(decode(437, &[0x82, 0xE9, 0x01, 0x7F]), "éΘ☺⌂");
|
||
assert_eq!(decode(850, &[0x9B, 0xE9]), "øÚ");
|
||
assert_eq!(decode(852, &[0xA5, 0x88, 0xBE, 0xA9]), "ąłżę");
|
||
assert_eq!(decode(866, &[0x8F, 0xE0, 0xA8, 0xA2, 0xA5, 0xE2, 0xF0, 0xFC]), "ПриветЁ№");
|
||
assert_eq!(decode(737, &[0x80, 0x99, 0xE0]), "Αβω");
|
||
assert_eq!(decode(857, &[0x8D, 0x98, 0xA6, 0x9F]), "ıİĞş");
|
||
assert_eq!(oem_byte(857, 0xD5), '\u{FFFD}', "unassigned in 857");
|
||
assert_eq!(decode(9999, &[0xE9]), "Θ", "unknown pages read as 437");
|
||
for cp in OEM_CODE_PAGES {
|
||
for b in 0..=255u8 {
|
||
let _ = oem_byte(cp, b);
|
||
}
|
||
}
|
||
}
|
||
}
|