v0.17.3

Author: danielteberian

Cargo.lock

@@ -5,6 +5,21 @@ Version History
 ## 0.17.3
  - Added "better-error-messages" (ideas/better-error-messages.md).
  - Added a section to the README to explain how people can contribute to the kernel's development (README.md).
+ - Added the data::utf8 module (src/data/utf8).
+ - Created mod.rs (src/data/utf8/mod.rs).
+ - Added the data::utf8::types module (src/data/utf8/types.rs).
+ - Added data::utf8::types module to mod.rs (src/data/utf8/mod.rs).
+ - Added data::utf8 module to mod.rs (src/data/mod.rs).
+ - Added data::parse::utf8 module (src/data/parse/utf8.rs).
+ - Added data::parse::utf8 module to mod.rs (src/data/parse/mod.rs).
+ - Merged pull-request 5c65ff3.
+ 	- Updated Rust nightly version to 1.68.0(2023-01-21).
+ 	- Updated bootloader crate to v0.9.23 (Cargo.toml).
+ - Removed the "abi_efiapi" feature (src/main.rs).
+ - Removed the "asm_sym" feature (src/lib.rs).
+ - Removed the "const_fn_fn_ptr_basics" feature (src/lib.rs).
+ - Updated kernel version number (src/main.rs).
+ - Updated version number (Cargo.toml).
 
 ## 0.17.2
  - Created the data::parser module (src/data/parse).

VERSIONHISTORY.md

@@ -12,3 +12,6 @@ pub mod parse;
 
 // UCS-2
 pub mod ucs2;
+
+// UTF-8
+pub mod utf8;

src/data/mod.rs

@@ -2,3 +2,5 @@
 
 
 //pub mod json;
+
+pub mod utf8;

src/data/parse/mod.rs

@@ -0,0 +1,109 @@
+// src/data/parse/utf8.rs
+//
+// Parser for UTF-8 data.
+// Thank you to Alacritty!
+
+
+use core::char;
+use crate::data::utf8::types::{Action, State};
+
+
+pub trait Receiver
+{
+	fn codepoint(&mut self, _: char);
+	fn invalidseq(&mut self);
+}
+
+
+#[derive(Clone, Default, PartialEq, Eq, Debug)]
+pub struct Parse
+{
+	point: u32,
+	state: State,
+}
+
+
+const CONTINUATION_MASK: u8 = 0b0011_1111;
+
+
+impl Parse
+{
+	// Create a parser
+	pub fn new() -> Parse
+	{
+		Parse
+		{
+			point: 0,
+			// Set state to the default value
+			state: State::Ground,
+		}
+	}
+
+	// Advance the parser
+	pub fn adv<R>(&mut self, receiver: &mut R, byte: u8)
+	where
+		R: Receiver,
+	{
+		let (state, action) = self.state.adv(byte);
+		self.perform_action(receiver, byte, action);
+		self.state = state;
+	}
+
+	fn perform_action<R>(&mut self, receiver: &mut R, byte: u8, action: Action)
+	where
+		R: Receiver,
+	{
+		match action
+		{
+			Action::InvalidSeq =>
+			{
+				self.point = 0;
+				receiver.invalidseq();
+			},
+
+			Action::EmitByte =>
+			{
+				receiver.codepoint(byte as char);
+			},
+
+			Action::SetByte1 =>
+			{
+				let point = self.point | ((byte & CONTINUATION_MASK) as u32);
+				let c = unsafe
+				{
+					char::from_u32_unchecked(point)
+				};
+
+				self.point = 0;
+
+				receiver.codepoint(c);
+			},
+
+			Action::SetByte2 =>
+			{
+				self.point |= ((byte & CONTINUATION_MASK) as u32) << 6;
+			},
+
+			Action::SetByte2Top =>
+			{
+				self.point |= ((byte & 0b0001_1111) as u32) << 6;
+			},
+
+			Action::SetByte3 =>
+			{
+				self.point |= ((byte & CONTINUATION_MASK) as u32) << 12;
+			},
+
+			Action::SetByte3Top =>
+			{
+				self.point |= ((byte & 0b0000_1111) as u32) << 12;
+			},
+
+			Action::SetByte4 =>
+			{
+				self.point |= ((byte & 0b0000_0111) as u32) << 18;
+			},
+		}
+	}
+}
+

src/data/parse/utf8.rs

@@ -0,0 +1,4 @@
+// src/data/utf8/mod.rs
+
+
+pub mod types;

src/data/utf8/mod.rs

@@ -0,0 +1,105 @@
+// src/data/utf8/types.rs
+//
+// UTF-8 types.
+// Thank you to Alacritty for their crate "utf8parse"!
+
+
+
+// What to do when byte is received
+#[derive(Debug, Copy, Clone)]
+pub enum Action
+{
+	InvalidSeq 	= 		0,
+	EmitByte 	= 		1,
+	SetByte1 	= 		2,
+	SetByte2 	= 		3,
+	SetByte2Top 	= 		4,
+	SetByte3 	= 		5,
+	SetByte3Top 	= 		6,
+	SetByte4 	= 		7,
+}
+
+
+// These are the states that the parser can be in
+#[allow(non_camel_case_types)]
+#[derive(Debug, Default, Copy, Clone, PartialEq, Eq)]
+pub enum State
+{
+	#[default]
+	Ground 		=		0,
+	Tail3 		=		1,
+	Tail2 		=		2,
+	Tail1 		= 		3,
+	U3_2_e0 	= 		4,
+	U3_2_ed 	= 		5,
+	UTF8_4_3_f0 	= 		6,
+	UTF8_4_3_f4 	= 		7,
+}
+
+
+impl State
+{
+	#[inline]
+	pub fn adv(self, byte: u8) -> (State, Action)
+	{
+		match self
+		{
+			State::Ground => match byte
+			{
+				0x00..=0x7f => (State::Ground, Action::EmitByte),
+				0xc2..=0xdf => (State::Tail1, Action::SetByte2Top),
+				0xe0 => (State::U3_2_e0, Action::SetByte2Top),
+				0xe1..=0xec => (State::Tail2, Action::SetByte3Top),
+				0xed => (State::U3_2_ed, Action::SetByte3Top),
+				0xee..=0xef => (State::Tail2, Action::SetByte3Top),
+				0xf0 => (State::UTF8_4_3_f0, Action::SetByte4),
+				0xf1..=0xf3 => (State::Tail3, Action::SetByte4),
+				0xf4 => (State::UTF8_4_3_f4, Action::SetByte4),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::U3_2_e0 => match byte
+			{
+				0xa0..=0xbf => (State::Tail1, Action::SetByte2),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::U3_2_ed => match byte
+			{
+				0x80..=0x9f => (State::Tail1, Action::SetByte2),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::UTF8_4_3_f0 => match byte
+			{
+				0x90..=0xbf => (State::Tail2, Action::SetByte3),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::UTF8_4_3_f4 => match byte
+			{
+				0x80..=0x8f => (State::Tail2, Action::SetByte3),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::Tail3 => match byte
+			{
+				0x80..=0xbf => (State::Tail2, Action::SetByte3),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+
+			State::Tail2 => match byte
+			{
+				0x80..=0xbf => (State::Tail1, Action::SetByte2),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+
+			State::Tail1 => match byte
+			{
+				0x80..=0xbf => (State::Ground, Action::SetByte1),
+				_ => (State::Ground, Action::InvalidSeq),
+			},
+		}
+	}
+}

src/data/utf8/types.rs

@@ -7,8 +7,6 @@
 #![allow(unused_variables)]
 #![feature(abi_x86_interrupt)]
 #![feature(alloc_error_handler)]
-#![feature(asm_sym)]
-#![feature(const_fn_fn_ptr_basics)]
 #![feature(const_mut_refs)]
 #![feature(core_intrinsics)]
 #![feature(custom_test_frameworks)]

src/lib.rs

@@ -1,6 +1,5 @@
 #![no_std]
 #![no_main]
-#![feature(abi_efiapi)]
 #![feature(custom_test_frameworks)]
 #![feature(type_ascription)]
 #![test_runner(libertyos_kernel::testexec)]
@@ -36,7 +35,7 @@ fn kernel_main(bootinfo: &'static BootInfo) -> !
 
 
 	libertyos_kernel::init::start(bootinfo);
-	println!("LIBERTYOS v0.17.2");
+	println!("LIBERTYOS v0.17.3");
 	print!("\x1b[?25h");
 	println!();