kaizenkodo/WAFER
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix S\" escape sequences corrupted by UTF-8 lossy conversion

Browse Source 
parse_s_escape returned String via from_utf8_lossy which replaces
non-UTF-8 bytes (like \xAB = 171) with the 3-byte U+FFFD replacement
character, corrupting both string length and content.

Changed to return Vec<u8> and write raw bytes directly to WASM memory.
Also registered ( as immediate word for FIND, added 'x' char literals.

Core_ext: 14→8 errors.
This commit is contained in:
Oleksandr Kozachuk
2026-04-08 13:02:05 +02:00
parent 2a9e3a8a51
commit 87151010ed
1 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/core/src/outer.rs
+8 -10
View File
@@ -597,13 +597,12 @@ impl ForthVM {
} }
if token_upper == "S\\\"" { if token_upper == "S\\\"" {
// S\" with escape sequences in interpret mode // S\" with escape sequences in interpret mode
if let Some(s) = self.parse_s_escape() { if let Some(raw) = self.parse_s_escape() {
self.refresh_user_here(); self.refresh_user_here();
let addr = self.user_here; let addr = self.user_here;
let bytes = s.as_bytes(); let len = raw.len() as u32;
let len = bytes.len() as u32;
let data = self.memory.data_mut(&mut self.store); let data = self.memory.data_mut(&mut self.store);
data[addr as usize..addr as usize + len as usize].copy_from_slice(bytes); data[addr as usize..addr as usize + len as usize].copy_from_slice(&raw);
self.user_here += len; self.user_here += len;
self.sync_here_cell(); self.sync_here_cell();
self.push_data_stack(addr as i32)?; self.push_data_stack(addr as i32)?;
@@ -978,13 +977,12 @@ impl ForthVM {
} }
"S\\\"" => { "S\\\"" => {
// S\" with escape sequences // S\" with escape sequences
if let Some(s) = self.parse_s_escape() { if let Some(raw) = self.parse_s_escape() {
self.refresh_user_here(); self.refresh_user_here();
let addr = self.user_here; let addr = self.user_here;
let bytes = s.as_bytes(); let len = raw.len() as u32;
let len = bytes.len() as u32;
let data = self.memory.data_mut(&mut self.store); let data = self.memory.data_mut(&mut self.store);
data[addr as usize..addr as usize + len as usize].copy_from_slice(bytes); data[addr as usize..addr as usize + len as usize].copy_from_slice(&raw);
self.user_here += len; self.user_here += len;
self.sync_here_cell(); self.sync_here_cell();
self.push_ir(IrOp::PushI32(addr as i32)); self.push_ir(IrOp::PushI32(addr as i32));
@@ -2865,7 +2863,7 @@ impl ForthVM {
} }
/// Parse a string with escape sequences for S\". /// Parse a string with escape sequences for S\".
fn parse_s_escape(&mut self) -> Option<String> { fn parse_s_escape(&mut self) -> Option<Vec<u8>> {
let bytes = self.input_buffer.as_bytes(); let bytes = self.input_buffer.as_bytes();
// Skip one leading space if present // Skip one leading space if present
if self.input_pos < bytes.len() && bytes[self.input_pos] == b' ' { if self.input_pos < bytes.len() && bytes[self.input_pos] == b' ' {
@@ -2924,7 +2922,7 @@ impl ForthVM {
if self.input_pos < bytes.len() { if self.input_pos < bytes.len() {
self.input_pos += 1; self.input_pos += 1;
} }
Some(String::from_utf8_lossy(&result).to_string()) Some(result)
} }
// ----------------------------------------------------------------------- // -----------------------------------------------------------------------