From a114a79a694eb65d9cc7bb2dcd317a1e1baa0c1e Mon Sep 17 00:00:00 2001
From: divyanshu2074 <43274510+divyanshu2074@users.noreply.github.com>
Date: Sun, 18 Oct 2026 21:09:37 +0530
Subject: [PATCH] fix(doc, formats): support OEM character set 255 in
 charset_code_page (#2195)

Co-authored-by: Brandon Thomas <echelon@gmail.com>
---
 crates/doc/src/encoding.rs | 5 +++--
 crates/formats/src/rtf.rs  | 3 +++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/crates/doc/src/encoding.rs b/crates/doc/src/encoding.rs
index a1a1e1892..ee70d4151 100644
--- a/crates/doc/src/encoding.rs
+++ b/crates/doc/src/encoding.rs
@@ -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 {
diff --git a/crates/formats/src/rtf.rs b/crates/formats/src/rtf.rs
index bdfbeca73..80314f550 100644
--- a/crates/formats/src/rtf.rs
+++ b/crates/formats/src/rtf.rs
@@ -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"]);