phantop
/
doukutsu-rs
mirror of https://github.com/doukutsu-rs/doukutsu-rs
1
0
Fork 0
Code Issues Releases Wiki Activity

feat: support GBK encoding for 'zh' locale

This commit is contained in:
poly000 2024-03-22 11:20:48 +08:00
parent 7630a9b60e
commit 1ff222bee4
No known key found for this signature in database
4 changed files with 24 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Cargo.toml
View File

@ -65,6 +65,7 @@ cpal = { git = "https://github.com/doukutsu-rs/cpal", rev = "9d269d8724102404e73
directories = "3"
discord-rich-presence = { version = "0.2", optional = true }
downcast = "0.11"
encoding_rs = "0.8.33"
fern = "0.6.2"
glutin = { git = "https://github.com/doukutsu-rs/glutin.git", rev = "2dd95f042e6e090d36f577cbea125560dd99bd27", optional = true, default_features = false, features = ["x11"] }
imgui = "0.8"

27
src/game/scripting/tsc/bytecode_utils.rs
View File

@ -3,7 +3,6 @@ use std::io::{Cursor, Read};
use crate::framework::error::GameError::ParseError;
use crate::framework::error::GameResult;
use crate::game::scripting::tsc::text_script::TextScriptEncoding;
use crate::util::encoding::{read_cur_shift_jis, read_cur_wtf8};
pub fn put_varint(val: i32, out: &mut Vec<u8>) {
let mut x = ((val as u32) >> 31) ^ ((val as u32) << 1);
@ -43,7 +42,7 @@ pub fn read_cur_varint(cursor: &mut Cursor<&[u8]>) -> GameResult<i32> {
}
#[allow(unused)]
pub fn read_varint<I: Iterator<Item=u8>>(iter: &mut I) -> GameResult<i32> {
pub fn read_varint<I: Iterator<Item = u8>>(iter: &mut I) -> GameResult<i32> {
let mut result = 0u32;
for o in 0..5 {
@ -62,27 +61,25 @@ pub fn put_string(buffer: &mut Vec<u8>, out: &mut Vec<u8>, encoding: TextScriptE
if buffer.is_empty() {
return;
}
let mut chars_count = 0;
let mut cursor: Cursor<&Vec<u8>> = Cursor::new(buffer);
let mut tmp_buf = Vec::new();
let mut remaining = buffer.len() as u32;
let mut chars = 0;
while remaining > 0 {
let (consumed, chr) = match encoding {
TextScriptEncoding::UTF8 => read_cur_wtf8(&mut cursor, remaining),
TextScriptEncoding::ShiftJIS => read_cur_shift_jis(&mut cursor, remaining),
};
let encoding = match encoding {
TextScriptEncoding::UTF8 => encoding_rs::UTF_8,
TextScriptEncoding::ShiftJIS => encoding_rs::SHIFT_JIS,
TextScriptEncoding::GBK => encoding_rs::GBK,
};
remaining -= consumed;
chars += 1;
put_varint(chr as i32, &mut tmp_buf);
let decoded_text = encoding.decode_without_bom_handling(&buffer).0;
for chr in decoded_text.chars() {
chars_count += 1;
put_varint(chr as _, &mut tmp_buf);
}
buffer.clear();
put_varint(chars, out);
put_varint(chars_count, out);
out.append(&mut tmp_buf);
}

14
src/game/scripting/tsc/text_script.rs
View File

@ -48,12 +48,15 @@ bitfield! {
pub enum TextScriptEncoding {
UTF8 = 0,
ShiftJIS,
GBK,
}
impl From<&str> for TextScriptEncoding {
fn from(s: &str) -> Self {
match s {
"utf-8" => Self::UTF8,
// GBK is a superset to GB2312
"gbk" | "gb2312" => Self::GBK,
_ => Self::ShiftJIS,
}
}
@ -64,7 +67,10 @@ impl TextScriptEncoding {
let required_encoding = if (state.loc.code == "jp" || state.loc.code == "en") && state.constants.is_base() {
TextScriptEncoding::ShiftJIS
} else {
TextScriptEncoding::UTF8
match state.loc.code.as_str() {
"zh" => TextScriptEncoding::GBK,
_ => TextScriptEncoding::UTF8,
}
};
encoding != required_encoding
@ -798,8 +804,10 @@ impl TextScriptVM {
// The vanilla game treats this as a 1-byte value lol
//if npc.event_num == (new_direction & 0xFF) as u16 {
if npc.event_num == new_direction as u16 {
game_scene.player1.direction = if game_scene.player1.x > npc.x { Direction::Left } else { Direction::Right };
game_scene.player2.direction = if game_scene.player2.x > npc.x { Direction::Left } else { Direction::Right };
game_scene.player1.direction =
if game_scene.player1.x > npc.x { Direction::Left } else { Direction::Right };
game_scene.player2.direction =
if game_scene.player2.x > npc.x { Direction::Left } else { Direction::Right };
}
}
}

42
src/util/encoding.rs
View File

@ -2,48 +2,6 @@ use std::io::Cursor;
use byteorder::ReadBytesExt;
/// Decodes UTF-8 character in a less strict way.
/// http://simonsapin.github.io/wtf-8/#decoding-wtf-8
pub fn read_cur_wtf8<T: AsRef<[u8]>>(cursor: &mut Cursor<T>, max_bytes: u32) -> (u32, char) {
let result: u32;
let consumed: u32;
if max_bytes == 0 {
return (0, '\u{fffd}');
}
match cursor.read_u8() {
Ok(byte @ 0x00..=0x7f) => {
consumed = 1;
result = byte as u32;
}
Ok(byte @ 0xc2..=0xdf) if max_bytes >= 2 => {
let byte2 = { if let Ok(n) = cursor.read_u8() { n } else { return (1, '\u{fffd}'); } };
consumed = 2;
result = (byte as u32 & 0x1f) << 6 | (byte2 as u32 & 0x3f);
}
Ok(byte @ 0xe0..=0xef) if max_bytes >= 3 => {
let byte2 = { if let Ok(n) = cursor.read_u8() { n } else { return (1, '\u{fffd}'); } };
let byte3 = { if let Ok(n) = cursor.read_u8() { n } else { return (2, '\u{fffd}'); } };
consumed = 3;
result = (byte as u32 & 0x0f) << 12 | (byte2 as u32 & 0x3f) << 6 | (byte3 as u32 & 0x3f);
}
Ok(byte @ 0xf0..=0xf4) if max_bytes >= 4 => {
let byte2 = { if let Ok(n) = cursor.read_u8() { n } else { return (1, '\u{fffd}'); } };
let byte3 = { if let Ok(n) = cursor.read_u8() { n } else { return (2, '\u{fffd}'); } };
let byte4 = { if let Ok(n) = cursor.read_u8() { n } else { return (3, '\u{fffd}'); } };
consumed = 4;
result = (byte as u32 & 0x07) << 18 | (byte2 as u32 & 0x3f) << 12 | (byte3 as u32 & 0x3f) << 6 | (byte4 as u32 & 0x3f);
}
_ => { return (1, '\u{fffd}'); }
}
(consumed, std::char::from_u32(result).unwrap_or('\u{fffd}'))
}
/// Shift-JIS -> Unicode converter.
pub fn read_cur_shift_jis<T: AsRef<[u8]>>(cursor: &mut Cursor<T>, max_bytes: u32) -> (u32, char) {
let result: u32;