aleleba/wordcraft
1
0
Fork 0
mirror of https://github.com/storytold/wordcraft.git synced 2026-10-29 04:47:10 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix(doc, formats): support OEM character set 255 in charset_code_page (#2195)

Browse Source 
Co-authored-by: Brandon Thomas <echelon@gmail.com>
This commit is contained in:
divyanshu2074
2026-10-18 11:39:37 -04:00
committed by GitHub
co-authored by Brandon Thomas
parent 61a626820e
commit a114a79a69
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/doc/src/encoding.rs
+3 -2
View File
@@ -287,12 +287,12 @@ pub fn code_page_byte(code_page: u16, b: u8) -> char {
}
/// The code page of an RTF or Word font charset (`\fcharset`): 204 Russian → 1251, 238 Eastern
/// European → 1250, 77 Mac → 10000, 254 PC → 437… `None` for the ANSI and default charsets (the
/// European → 1250, 77 Mac → 10000, 254 PC / 255 OEM → 437… `None` for the ANSI and default charsets (the
/// document's code page applies), symbol fonts and the double-byte East Asian charsets.
pub fn charset_code_page(charset: i32) -> Option<u16> {
Some(match charset {
77 => MAC_ROMAN_CODE_PAGE,
254 => 437,
254 | 255 => 437,
161 => 1253,
162 => 1254,
163 => 1258,
@@ -323,6 +323,7 @@ mod tests {
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 {
crates/formats/src/rtf.rs
+3
View File
@@ -2839,6 +2839,9 @@ mod tests {
assert_eq!(texts(&f), ["Normal:ÒÚÛ"]);
let f = parse(br"{\rtf1\ansi\deff0{\fonttbl{\f0 Arial;}{\f1\fcharset77 Geneva;}}caf\'e9 {\f1 caf\'8e \'d2ok\'d3}\par}").unwrap();
assert_eq!(texts(&f), ["Normal:café café “ok”"]);
// \fcharset255 is the standard OEM character set (CP437).
let f = parse(br"{\rtf1\ansi\deff0{\fonttbl{\f0 Arial;}{\f1\fcharset255 Terminal;}}caf\'e9 {\f1 caf\'82}\par}").unwrap();
assert_eq!(texts(&f), ["Normal:café café"]);
// DOS documents: `\pc` is code page 437, `\pca` 850; a font can name one with `\cpg`.
let f = parse(br"{\rtf1\pc\deff0{\fonttbl{\f0 Courier;}}caf\'82 \'a0 la carte\par}").unwrap();
assert_eq!(texts(&f), ["Normal:café á la carte"]);