mirror of
https://github.com/sxyazi/yazi.git
synced 2026-07-21 23:01:05 +00:00
refactor: prefer WriteConsoleW for Windows console output (#2464)
This commit is contained in:
三咲雅 · Misaki Masa
GitHub
parent
22980cf000
commit
c8bf2c507a
16 changed files with 283 additions and 71 deletions
31
Cargo.lock
generated
31
Cargo.lock
generated
|
|
@ -299,12 +299,6 @@ version = "1.22.0"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6b1fc10dbac614ebc03540c9dbd60e83887fda27794998c6528f1782047d540"
|
||||
|
||||
[[package]]
|
||||
name = "byteorder"
|
||||
version = "1.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
|
||||
|
||||
[[package]]
|
||||
name = "byteorder-lite"
|
||||
version = "0.1.0"
|
||||
|
|
@ -1913,9 +1907,9 @@ checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
|
|||
|
||||
[[package]]
|
||||
name = "ppv-lite86"
|
||||
version = "0.2.20"
|
||||
version = "0.2.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
|
||||
checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
|
||||
dependencies = [
|
||||
"zerocopy",
|
||||
]
|
||||
|
|
@ -2252,9 +2246,9 @@ checksum = "56e6fa9c48d24d85fb3de5ad847117517440f6beceb7798af16b4a87d616b8d0"
|
|||
|
||||
[[package]]
|
||||
name = "serde"
|
||||
version = "1.0.218"
|
||||
version = "1.0.219"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e8dfc9d19bdbf6d17e22319da49161d5d0108e4188e8b680aef6299eed22df60"
|
||||
checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
|
||||
dependencies = [
|
||||
"serde_derive",
|
||||
]
|
||||
|
|
@ -2271,9 +2265,9 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "serde_derive"
|
||||
version = "1.0.218"
|
||||
version = "1.0.219"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f09503e191f4e797cb8aac08e9a4a4695c5edf6a2e70e376d961ddd5c969f82b"
|
||||
checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
|
@ -2452,9 +2446,9 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "2.0.99"
|
||||
version = "2.0.100"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e02e925281e18ffd9d640e234264753c43edc62d64b2d4cf898f1bc5e75f3fc2"
|
||||
checksum = "b09a44accad81e1ba1cd74a32461ba89dee89095ba17b32f5d03683b1b1fc2a0"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
|
@ -3661,19 +3655,18 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "zerocopy"
|
||||
version = "0.7.35"
|
||||
version = "0.8.23"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0"
|
||||
checksum = "fd97444d05a4328b90e75e503a34bad781f14e28a823ad3557f0750df1ebcbc6"
|
||||
dependencies = [
|
||||
"byteorder",
|
||||
"zerocopy-derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy-derive"
|
||||
version = "0.7.35"
|
||||
version = "0.8.23"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
|
||||
checksum = "6352c01d0edd5db859a63e2605f4ea3183ddbd15e2c4a9e7d32184df75e4f154"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ parking_lot = "0.12.3"
|
|||
ratatui = { version = "0.29.0", features = [ "unstable-rendered-line-info" ] }
|
||||
regex = "1.11.1"
|
||||
scopeguard = "1.2.0"
|
||||
serde = { version = "1.0.218", features = [ "derive" ] }
|
||||
serde = { version = "1.0.219", features = [ "derive" ] }
|
||||
serde_json = "1.0.140"
|
||||
tokio = { version = "1.44.0", features = [ "full" ] }
|
||||
tokio-stream = "0.1.17"
|
||||
|
|
|
|||
|
|
@ -1 +1 @@
|
|||
{"version":"0.2","language":"en","flagWords":[],"words":["Punct","KEYMAP","splitn","crossterm","YAZI","peekable","ratatui","syntect","pbpaste","pbcopy","oneshot","Posix","Lsar","XADDOS","zoxide","cands","Deque","precache","imageops","IFBLK","IFCHR","IFDIR","IFIFO","IFLNK","IFMT","IFSOCK","IRGRP","IROTH","IRUSR","ISGID","ISUID","ISVTX","IWGRP","IWOTH","IWUSR","IXGRP","IXOTH","IXUSR","libc","winsize","TIOCGWINSZ","xpixel","ypixel","ioerr","appender","Catppuccin","macchiato","gitmodules","Dotfiles","bashprofile","vimrc","flac","webp","exiftool","mediainfo","ripgrep","indexmap","indexmap","unwatch","canonicalize","serde","fsevent","Ueberzug","iterm","wezterm","sixel","chafa","ueberzugpp","Konsole","Überzug","pkgs","pdftoppm","poppler","prebuild","singlefile","jpegopt","EXIF","rustfmt","mktemp","nanos","xclip","xsel","natord","Mintty","nixos","nixpkgs","SIGTSTP","SIGCONT","SIGCONT","mlua","nonstatic","userdata","metatable","natsort","backstack","luajit","Succ","Succ","cand","fileencoding","foldmethod","lightgreen","darkgray","lightred","lightyellow","lightcyan","nushell","msvc","aarch","linemode","sxyazi","rsplit","ZELLIJ","bitflags","bitflags","USERPROFILE","Neovim","vergen","gitcl","Renderable","preloaders","prec","Upserting","prio","Ghostty","Catmull","Lanczos","cmds","unyank","scrolloff","headsup","unsub","uzers","scopeguard","SPDLOG","globset","filetime","magick","magick","prefetcher","Prework","prefetchers","PREWORKERS","conds","translit","rxvt","Urxvt","realpath","realname","REPARSE","hardlink","hardlinking","nlink","nlink","linemodes","SIGSTOP","sevenzip","rsplitn","replacen","DECSET","DECRQM","repeek","cwds","tcsi","Hyprland","Wayfire","SWAYSOCK","btime","nsec","codegen","gethostname","fchmod","fdfind","Rustc","rustc","ffprobe","vframes","luma","obase","outln","errln","tmtheme","twox","cfgs","fstype","objc","rdev","runloop","exfat","rclone","DECRQSS","DECSCUSR","libvterm","Uninit","lockin"]}
|
||||
{"version":"0.2","language":"en","words":["Punct","KEYMAP","splitn","crossterm","YAZI","peekable","ratatui","syntect","pbpaste","pbcopy","oneshot","Posix","Lsar","XADDOS","zoxide","cands","Deque","precache","imageops","IFBLK","IFCHR","IFDIR","IFIFO","IFLNK","IFMT","IFSOCK","IRGRP","IROTH","IRUSR","ISGID","ISUID","ISVTX","IWGRP","IWOTH","IWUSR","IXGRP","IXOTH","IXUSR","libc","winsize","TIOCGWINSZ","xpixel","ypixel","ioerr","appender","Catppuccin","macchiato","gitmodules","Dotfiles","bashprofile","vimrc","flac","webp","exiftool","mediainfo","ripgrep","indexmap","indexmap","unwatch","canonicalize","serde","fsevent","Ueberzug","iterm","wezterm","sixel","chafa","ueberzugpp","Konsole","Überzug","pkgs","pdftoppm","poppler","prebuild","singlefile","jpegopt","EXIF","rustfmt","mktemp","nanos","xclip","xsel","natord","Mintty","nixos","nixpkgs","SIGTSTP","SIGCONT","SIGCONT","mlua","nonstatic","userdata","metatable","natsort","backstack","luajit","Succ","Succ","cand","fileencoding","foldmethod","lightgreen","darkgray","lightred","lightyellow","lightcyan","nushell","msvc","aarch","linemode","sxyazi","rsplit","ZELLIJ","bitflags","bitflags","USERPROFILE","Neovim","vergen","gitcl","Renderable","preloaders","prec","Upserting","prio","Ghostty","Catmull","Lanczos","cmds","unyank","scrolloff","headsup","unsub","uzers","scopeguard","SPDLOG","globset","filetime","magick","magick","prefetcher","Prework","prefetchers","PREWORKERS","conds","translit","rxvt","Urxvt","realpath","realname","REPARSE","hardlink","hardlinking","nlink","nlink","linemodes","SIGSTOP","sevenzip","rsplitn","replacen","DECSET","DECRQM","repeek","cwds","tcsi","Hyprland","Wayfire","SWAYSOCK","btime","nsec","codegen","gethostname","fchmod","fdfind","Rustc","rustc","ffprobe","vframes","luma","obase","outln","errln","tmtheme","twox","cfgs","fstype","objc","rdev","runloop","exfat","rclone","DECRQSS","DECSCUSR","libvterm","Uninit","lockin","rposition"],"flagWords":[]}
|
||||
|
|
@ -55,10 +55,10 @@ impl Chafa {
|
|||
|
||||
Adapter::Chafa.image_hide()?;
|
||||
Adapter::shown_store(area);
|
||||
Emulator::move_lock((max.x, max.y), |stderr| {
|
||||
Emulator::move_lock((max.x, max.y), |w| {
|
||||
for (i, line) in lines.into_iter().enumerate() {
|
||||
stderr.write_all(line)?;
|
||||
queue!(stderr, MoveTo(max.x, max.y + i as u16 + 1))?;
|
||||
w.write_all(line)?;
|
||||
queue!(w, MoveTo(max.x, max.y + i as u16 + 1))?;
|
||||
}
|
||||
Ok(area)
|
||||
})
|
||||
|
|
@ -66,10 +66,10 @@ impl Chafa {
|
|||
|
||||
pub(crate) fn image_erase(area: Rect) -> Result<()> {
|
||||
let s = " ".repeat(area.width as usize);
|
||||
Emulator::move_lock((0, 0), |stderr| {
|
||||
Emulator::move_lock((0, 0), |w| {
|
||||
for y in area.top()..area.bottom() {
|
||||
queue!(stderr, MoveTo(area.x, y))?;
|
||||
write!(stderr, "{s}")?;
|
||||
queue!(w, MoveTo(area.x, y))?;
|
||||
write!(w, "{s}")?;
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
|
|
|
|||
|
|
@ -19,18 +19,18 @@ impl Iip {
|
|||
|
||||
Adapter::Iip.image_hide()?;
|
||||
Adapter::shown_store(area);
|
||||
Emulator::move_lock((max.x, max.y), |stderr| {
|
||||
stderr.write_all(&b)?;
|
||||
Emulator::move_lock((max.x, max.y), |w| {
|
||||
w.write_all(&b)?;
|
||||
Ok(area)
|
||||
})
|
||||
}
|
||||
|
||||
pub(crate) fn image_erase(area: Rect) -> Result<()> {
|
||||
let s = " ".repeat(area.width as usize);
|
||||
Emulator::move_lock((0, 0), |stderr| {
|
||||
Emulator::move_lock((0, 0), |w| {
|
||||
for y in area.top()..area.bottom() {
|
||||
queue!(stderr, MoveTo(area.x, y))?;
|
||||
write!(stderr, "{s}")?;
|
||||
queue!(w, MoveTo(area.x, y))?;
|
||||
write!(w, "{s}")?;
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
|
|
|
|||
|
|
@ -321,22 +321,22 @@ impl Kgp {
|
|||
|
||||
Adapter::Kgp.image_hide()?;
|
||||
Adapter::shown_store(area);
|
||||
Emulator::move_lock((area.x, area.y), |stderr| {
|
||||
stderr.write_all(&b1)?;
|
||||
stderr.write_all(&b2)?;
|
||||
Emulator::move_lock((area.x, area.y), |w| {
|
||||
w.write_all(&b1)?;
|
||||
w.write_all(&b2)?;
|
||||
Ok(area)
|
||||
})
|
||||
}
|
||||
|
||||
pub(crate) fn image_erase(area: Rect) -> Result<()> {
|
||||
let s = " ".repeat(area.width as usize);
|
||||
Emulator::move_lock((0, 0), |stderr| {
|
||||
Emulator::move_lock((0, 0), |w| {
|
||||
for y in area.top()..area.bottom() {
|
||||
queue!(stderr, MoveTo(area.x, y))?;
|
||||
write!(stderr, "{s}")?;
|
||||
queue!(w, MoveTo(area.x, y))?;
|
||||
write!(w, "{s}")?;
|
||||
}
|
||||
|
||||
write!(stderr, "{START}_Gq=2,a=d,d=A{ESCAPE}\\{CLOSE}")?;
|
||||
write!(w, "{START}_Gq=2,a=d,d=A{ESCAPE}\\{CLOSE}")?;
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
|
|
|||
|
|
@ -19,8 +19,8 @@ impl KgpOld {
|
|||
|
||||
Adapter::KgpOld.image_hide()?;
|
||||
Adapter::shown_store(area);
|
||||
Emulator::move_lock((area.x, area.y), |stderr| {
|
||||
stderr.write_all(&b)?;
|
||||
Emulator::move_lock((area.x, area.y), |w| {
|
||||
w.write_all(&b)?;
|
||||
Ok(area)
|
||||
})
|
||||
}
|
||||
|
|
|
|||
|
|
@ -19,18 +19,18 @@ impl Sixel {
|
|||
|
||||
Adapter::Sixel.image_hide()?;
|
||||
Adapter::shown_store(area);
|
||||
Emulator::move_lock((area.x, area.y), |stderr| {
|
||||
stderr.write_all(&b)?;
|
||||
Emulator::move_lock((area.x, area.y), |w| {
|
||||
w.write_all(&b)?;
|
||||
Ok(area)
|
||||
})
|
||||
}
|
||||
|
||||
pub(crate) fn image_erase(area: Rect) -> Result<()> {
|
||||
let s = " ".repeat(area.width as usize);
|
||||
Emulator::move_lock((0, 0), |stderr| {
|
||||
Emulator::move_lock((0, 0), |w| {
|
||||
for y in area.top()..area.bottom() {
|
||||
queue!(stderr, MoveTo(area.x, y))?;
|
||||
write!(stderr, "{s}")?;
|
||||
queue!(w, MoveTo(area.x, y))?;
|
||||
write!(w, "{s}")?;
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
|
|
|
|||
|
|
@ -13,5 +13,5 @@ proc-macro = true
|
|||
|
||||
[dependencies]
|
||||
# External dependencies
|
||||
syn = { version = "2.0.99", features = [ "full" ] }
|
||||
syn = { version = "2.0.100", features = [ "full" ] }
|
||||
quote = "1.0.39"
|
||||
|
|
|
|||
|
|
@ -66,8 +66,8 @@ impl Mgr {
|
|||
|
||||
{
|
||||
let mut w = TTY.lockout();
|
||||
for (o, n) in &todo {
|
||||
writeln!(w, "{} -> {}", o.display(), n.display())?;
|
||||
for (old, new) in &todo {
|
||||
writeln!(w, "{} -> {}", old.display(), new.display())?;
|
||||
}
|
||||
write!(w, "Continue to rename? (y/N): ")?;
|
||||
w.flush()?;
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
yazi_macro::mod_pub!(errors event shell theme translit tty url);
|
||||
|
||||
yazi_macro::mod_flat!(chars condition debounce either env id layer natsort number os rand ro_cell sync_cell terminal throttle time);
|
||||
yazi_macro::mod_flat!(chars condition debounce either env id layer natsort number os rand ro_cell sync_cell terminal throttle time utf8);
|
||||
|
||||
pub fn init() {
|
||||
tty::init();
|
||||
|
|
|
|||
|
|
@ -2,10 +2,14 @@ use std::{io::{Error, ErrorKind, Read, Write}, time::Duration};
|
|||
|
||||
pub struct Handle {
|
||||
#[cfg(unix)]
|
||||
inner: std::os::fd::RawFd,
|
||||
inner: std::os::fd::RawFd,
|
||||
#[cfg(windows)]
|
||||
inner: std::os::windows::io::RawHandle,
|
||||
close: bool,
|
||||
inner: std::os::windows::io::RawHandle,
|
||||
close: bool,
|
||||
#[cfg(windows)]
|
||||
out_utf8: bool,
|
||||
#[cfg(windows)]
|
||||
incomplete_utf8: super::IncompleteUtf8,
|
||||
}
|
||||
|
||||
impl Drop for Handle {
|
||||
|
|
@ -49,16 +53,20 @@ impl Write for Handle {
|
|||
use std::os::{fd::IntoRawFd, unix::io::FromRawFd};
|
||||
let mut f = unsafe { std::fs::File::from_raw_fd(self.inner) };
|
||||
let result = f.write(buf);
|
||||
self.inner = f.into_raw_fd();
|
||||
_ = f.into_raw_fd();
|
||||
result
|
||||
}
|
||||
#[cfg(windows)]
|
||||
{
|
||||
use std::os::windows::io::{FromRawHandle, IntoRawHandle};
|
||||
let mut f = unsafe { std::fs::File::from_raw_handle(self.inner) };
|
||||
let result = f.write(buf);
|
||||
self.inner = f.into_raw_handle();
|
||||
result
|
||||
if self.out_utf8 {
|
||||
let mut f = unsafe { std::fs::File::from_raw_handle(self.inner) };
|
||||
let result = f.write(buf);
|
||||
_ = f.into_raw_handle();
|
||||
result
|
||||
} else {
|
||||
super::write_console_utf16(buf, &mut self.incomplete_utf8, self.inner)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -114,7 +122,7 @@ impl Handle {
|
|||
#[cfg(windows)]
|
||||
impl Handle {
|
||||
pub(super) fn new(out: bool) -> std::io::Result<Self> {
|
||||
use windows_sys::Win32::{Foundation::{GENERIC_READ, GENERIC_WRITE, INVALID_HANDLE_VALUE}, Storage::FileSystem::{CreateFileW, FILE_SHARE_READ, FILE_SHARE_WRITE, OPEN_EXISTING}};
|
||||
use windows_sys::Win32::{Foundation::{GENERIC_READ, GENERIC_WRITE, INVALID_HANDLE_VALUE}, Globalization::CP_UTF8, Storage::FileSystem::{CreateFileW, FILE_SHARE_READ, FILE_SHARE_WRITE, OPEN_EXISTING}, System::Console::GetConsoleOutputCP};
|
||||
|
||||
let name: Vec<u16> = if out { "CONOUT$\0" } else { "CONIN$\0" }.encode_utf16().collect();
|
||||
let result = unsafe {
|
||||
|
|
@ -132,7 +140,12 @@ impl Handle {
|
|||
if result == INVALID_HANDLE_VALUE {
|
||||
Err(std::io::Error::last_os_error())
|
||||
} else {
|
||||
Ok(Self { inner: result, close: true })
|
||||
Ok(Self {
|
||||
inner: result,
|
||||
close: true,
|
||||
out_utf8: unsafe { GetConsoleOutputCP() } == CP_UTF8,
|
||||
incomplete_utf8: Default::default(),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,4 +1,7 @@
|
|||
yazi_macro::mod_flat!(tty handle);
|
||||
yazi_macro::mod_flat!(handle tty);
|
||||
|
||||
#[cfg(windows)]
|
||||
yazi_macro::mod_flat!(windows);
|
||||
|
||||
pub static TTY: crate::RoCell<Tty> = crate::RoCell::new();
|
||||
|
||||
|
|
|
|||
|
|
@ -11,9 +11,6 @@ pub struct Tty {
|
|||
|
||||
impl Default for Tty {
|
||||
fn default() -> Self {
|
||||
#[cfg(windows)]
|
||||
Self::set_code_page().expect("failed to set terminal code page");
|
||||
|
||||
let stdin = Handle::new(false).expect("failed to open stdin");
|
||||
let stdout = Handle::new(true).expect("failed to open stdout");
|
||||
Self { stdin: Mutex::new(stdin), stdout: Mutex::new(BufWriter::new(stdout)) }
|
||||
|
|
@ -58,13 +55,6 @@ impl Tty {
|
|||
let result = read();
|
||||
(buf, result)
|
||||
}
|
||||
|
||||
#[cfg(windows)]
|
||||
fn set_code_page() -> std::io::Result<()> {
|
||||
use windows_sys::Win32::{Globalization::CP_UTF8, System::Console::SetConsoleOutputCP};
|
||||
|
||||
if unsafe { SetConsoleOutputCP(CP_UTF8) } == 0 { Err(Error::last_os_error()) } else { Ok(()) }
|
||||
}
|
||||
}
|
||||
|
||||
// --- Reader
|
||||
|
|
|
|||
160
yazi-shared/src/tty/windows.rs
Normal file
160
yazi-shared/src/tty/windows.rs
Normal file
|
|
@ -0,0 +1,160 @@
|
|||
// Copied from https://github.com/rust-lang/rust/blob/master/library/std/src/sys/pal/windows/stdio.rs
|
||||
|
||||
use std::{mem::MaybeUninit, os::windows::io::RawHandle, str};
|
||||
|
||||
use windows_sys::Win32::{Globalization::{CP_UTF8, MB_ERR_INVALID_CHARS, MultiByteToWideChar}, System::Console::WriteConsoleW};
|
||||
|
||||
use crate::{floor_char_boundary, utf8_char_width};
|
||||
|
||||
// Apparently Windows doesn't handle large reads on stdin or writes to
|
||||
// stdout/stderr well (see #13304 for details).
|
||||
//
|
||||
// From MSDN (2011): "The storage for this buffer is allocated from a shared
|
||||
// heap for the process that is 64 KB in size. The maximum size of the buffer
|
||||
// will depend on heap usage."
|
||||
//
|
||||
// We choose the cap at 8 KiB because libuv does the same, and it seems to be
|
||||
// acceptable so far.
|
||||
const MAX_BUFFER_SIZE: usize = 8192;
|
||||
|
||||
#[derive(Default)]
|
||||
pub(super) struct IncompleteUtf8 {
|
||||
bytes: [u8; 4],
|
||||
len: u8,
|
||||
}
|
||||
|
||||
pub(super) fn write_console_utf16(
|
||||
data: &[u8],
|
||||
incomplete_utf8: &mut IncompleteUtf8,
|
||||
handle: RawHandle,
|
||||
) -> std::io::Result<usize> {
|
||||
if incomplete_utf8.len > 0 {
|
||||
assert!(incomplete_utf8.len < 4, "Unexpected number of bytes for incomplete UTF-8 codepoint.");
|
||||
if data[0] >> 6 != 0b10 {
|
||||
// not a continuation byte - reject
|
||||
incomplete_utf8.len = 0;
|
||||
return Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidData,
|
||||
"Windows stdio in console mode does not support writing non-UTF-8 byte sequences",
|
||||
));
|
||||
}
|
||||
incomplete_utf8.bytes[incomplete_utf8.len as usize] = data[0];
|
||||
incomplete_utf8.len += 1;
|
||||
let char_width = utf8_char_width(incomplete_utf8.bytes[0]);
|
||||
if (incomplete_utf8.len as usize) < char_width {
|
||||
// more bytes needed
|
||||
return Ok(1);
|
||||
}
|
||||
let s = str::from_utf8(&incomplete_utf8.bytes[0..incomplete_utf8.len as usize]);
|
||||
incomplete_utf8.len = 0;
|
||||
match s {
|
||||
Ok(s) => {
|
||||
assert_eq!(char_width, s.len());
|
||||
let written = write_valid_utf8_to_console(handle, s)?;
|
||||
assert_eq!(written, s.len()); // guaranteed by write_valid_utf8_to_console() for single codepoint writes
|
||||
return Ok(1);
|
||||
}
|
||||
Err(_) => {
|
||||
return Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidData,
|
||||
"Windows stdio in console mode does not support writing non-UTF-8 byte sequences",
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// As the console is meant for presenting text, we assume bytes of `data` are
|
||||
// encoded as UTF-8, which needs to be encoded as UTF-16.
|
||||
//
|
||||
// If the data is not valid UTF-8 we write out as many bytes as are valid.
|
||||
// If the first byte is invalid it is either first byte of a multi-byte sequence
|
||||
// but the provided byte slice is too short or it is the first byte of an
|
||||
// invalid multi-byte sequence.
|
||||
let len = std::cmp::min(data.len(), MAX_BUFFER_SIZE / 2);
|
||||
let utf8 = match str::from_utf8(&data[..len]) {
|
||||
Ok(s) => s,
|
||||
Err(ref e) if e.valid_up_to() == 0 => {
|
||||
let first_byte_char_width = utf8_char_width(data[0]);
|
||||
if first_byte_char_width > 1 && data.len() < first_byte_char_width {
|
||||
incomplete_utf8.bytes[0] = data[0];
|
||||
incomplete_utf8.len = 1;
|
||||
return Ok(1);
|
||||
} else {
|
||||
return Err(std::io::Error::new(
|
||||
std::io::ErrorKind::InvalidData,
|
||||
"Windows stdio in console mode does not support writing non-UTF-8 byte sequences",
|
||||
));
|
||||
}
|
||||
}
|
||||
Err(e) => str::from_utf8(&data[..e.valid_up_to()]).unwrap(),
|
||||
};
|
||||
|
||||
write_valid_utf8_to_console(handle, utf8)
|
||||
}
|
||||
|
||||
fn write_valid_utf8_to_console(handle: RawHandle, utf8: &str) -> std::io::Result<usize> {
|
||||
debug_assert!(!utf8.is_empty());
|
||||
|
||||
let mut utf16 = [MaybeUninit::<u16>::uninit(); MAX_BUFFER_SIZE / 2];
|
||||
let utf8 = &utf8[..floor_char_boundary(utf8, utf16.len())];
|
||||
|
||||
let utf16: &[u16] = unsafe {
|
||||
// Note that this theoretically checks validity twice in the (most common) case
|
||||
// where the underlying byte sequence is valid utf-8 (given the check in
|
||||
// `write()`).
|
||||
let result = MultiByteToWideChar(
|
||||
CP_UTF8,
|
||||
MB_ERR_INVALID_CHARS,
|
||||
utf8.as_ptr(),
|
||||
utf8.len() as i32,
|
||||
utf16.as_mut_ptr() as *mut _,
|
||||
utf16.len() as i32,
|
||||
);
|
||||
assert!(result != 0, "Unexpected error in MultiByteToWideChar");
|
||||
|
||||
// Safety: MultiByteToWideChar initializes `result` values.
|
||||
&*(&utf16[..result as usize] as *const [MaybeUninit<u16>] as *const [u16])
|
||||
};
|
||||
|
||||
let mut written = write_u16s(handle, utf16)?;
|
||||
|
||||
// Figure out how many bytes of as UTF-8 were written away as UTF-16.
|
||||
if written == utf16.len() {
|
||||
Ok(utf8.len())
|
||||
} else {
|
||||
// Make sure we didn't end up writing only half of a surrogate pair (even though
|
||||
// the chance is tiny). Because it is not possible for user code to re-slice
|
||||
// `data` in such a way that a missing surrogate can be produced (and also
|
||||
// because of the UTF-8 validation above), write the missing surrogate out
|
||||
// now. Buffering it would mean we have to lie about the number of bytes
|
||||
// written.
|
||||
let first_code_unit_remaining = utf16[written];
|
||||
if matches!(first_code_unit_remaining, 0xdcee..=0xdfff) {
|
||||
// low surrogate
|
||||
// We just hope this works, and give up otherwise
|
||||
let _ = write_u16s(handle, &utf16[written..written + 1]);
|
||||
written += 1;
|
||||
}
|
||||
// Calculate the number of bytes of `utf8` that were actually written.
|
||||
let mut count = 0;
|
||||
for ch in utf16[..written].iter() {
|
||||
count += match ch {
|
||||
0x0000..=0x007f => 1,
|
||||
0x0080..=0x07ff => 2,
|
||||
0xdcee..=0xdfff => 1, // Low surrogate. We already counted 3 bytes for the other.
|
||||
_ => 3,
|
||||
};
|
||||
}
|
||||
debug_assert!(String::from_utf16(&utf16[..written]).unwrap() == utf8[..count]);
|
||||
Ok(count)
|
||||
}
|
||||
}
|
||||
|
||||
fn write_u16s(handle: RawHandle, data: &[u16]) -> std::io::Result<usize> {
|
||||
debug_assert!(data.len() < u32::MAX as usize);
|
||||
let mut written = 0;
|
||||
let result = unsafe {
|
||||
WriteConsoleW(handle, data.as_ptr(), data.len() as u32, &mut written, std::ptr::null_mut())
|
||||
};
|
||||
if result == 0 { Err(std::io::Error::last_os_error()) } else { Ok(written as usize) }
|
||||
}
|
||||
53
yazi-shared/src/utf8.rs
Normal file
53
yazi-shared/src/utf8.rs
Normal file
|
|
@ -0,0 +1,53 @@
|
|||
// https://tools.ietf.org/html/rfc3629
|
||||
const UTF8_CHAR_WIDTH: &[u8; 256] = &[
|
||||
// 1 2 3 4 5 6 7 8 9 A B C D E F
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 1
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 2
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 3
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 4
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 5
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 6
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 7
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 8
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 9
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // A
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // B
|
||||
0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // C
|
||||
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // D
|
||||
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // E
|
||||
4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // F
|
||||
];
|
||||
|
||||
/// Given a first byte, determines how many bytes are in this UTF-8 character.
|
||||
#[must_use]
|
||||
#[inline]
|
||||
pub const fn utf8_char_width(b: u8) -> usize { UTF8_CHAR_WIDTH[b as usize] as usize }
|
||||
|
||||
/// Finds the closest `x` not exceeding `index` where [`is_char_boundary(x)`] is
|
||||
/// `true`.
|
||||
///
|
||||
/// This method can help you truncate a string so that it's still valid UTF-8,
|
||||
/// but doesn't exceed a given number of bytes. Note that this is done purely at
|
||||
/// the character level and can still visually split graphemes, even though the
|
||||
/// underlying characters aren't split. For example, the emoji 🧑🔬 (scientist)
|
||||
/// could be split so that the string only includes 🧑 (person) instead.
|
||||
#[inline]
|
||||
pub fn floor_char_boundary(s: &str, index: usize) -> usize {
|
||||
if index >= s.len() {
|
||||
s.len()
|
||||
} else {
|
||||
let lower_bound = index.saturating_sub(3);
|
||||
let new_index =
|
||||
s.as_bytes()[lower_bound..=index].iter().rposition(|&b| is_utf8_char_boundary(b));
|
||||
|
||||
// SAFETY: we know that the character boundary will be within four bytes
|
||||
unsafe { lower_bound + new_index.unwrap_unchecked() }
|
||||
}
|
||||
}
|
||||
|
||||
#[inline]
|
||||
const fn is_utf8_char_boundary(b: u8) -> bool {
|
||||
// This is bit magic equivalent to: b < 128 || b >= 192
|
||||
(b as i8) >= -0x40
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue