-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
7 changed files
with
320 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
/target/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
[package] | ||
name = "lelwel-oberon0" | ||
version = "1.0.0" | ||
edition = "2021" | ||
|
||
[dependencies] | ||
logos = "0.13.0" | ||
codespan-reporting = "0.11.1" | ||
|
||
[build-dependencies] | ||
lelwel = { path = "../.." } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
# lelwel-oberon0 | ||
An example for an acceptor of the [Oberon-0 programming language](https://en.wikipedia.org/wiki/PL/0#Oberon-0). |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
fn main() { | ||
lelwel::build("src/oberon0.llw"); | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,31 @@ | ||
use codespan_reporting::diagnostic::Severity; | ||
use codespan_reporting::files::SimpleFile; | ||
use codespan_reporting::term::termcolor::{ColorChoice, StandardStream}; | ||
use codespan_reporting::term::{self, Config}; | ||
use logos::Logos; | ||
use parser::*; | ||
|
||
mod parser; | ||
|
||
fn main() -> std::io::Result<()> { | ||
let args: Vec<String> = std::env::args().collect(); | ||
if args.len() != 2 { | ||
std::process::exit(1); | ||
} | ||
let contents = std::fs::read_to_string(&args[1])?; | ||
|
||
let mut tokens = TokenStream::new(Token::lexer(&contents)); | ||
let mut diags = vec![]; | ||
Parser::parse(&mut tokens, &mut diags); | ||
|
||
let writer = StandardStream::stderr(ColorChoice::Auto); | ||
let config = Config::default(); | ||
let file = SimpleFile::new(&args[1], &contents); | ||
for diag in diags.iter() { | ||
term::emit(&mut writer.lock(), &config, &file, &diag).unwrap(); | ||
} | ||
if diags.iter().any(|d| d.severity == Severity::Error) { | ||
std::process::exit(1); | ||
} | ||
Ok(()) | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,92 @@ | ||
/// keyword | ||
token Const='CONST' Var='VAR' Procedure='PROCEDURE' Begin='BEGIN' | ||
End='END' If='IF' Then='THEN' While='WHILE' Do='DO' Elsif='ELSIF' Else='ELSE' | ||
Type='TYPE' DivKw='DIV' ModKw='MOD' OrKw='OR' Array='ARRAY' Record='RECORD' | ||
Of='OF' Module='MODULE' Repeat='REPEAT' Until='UNTIL'; | ||
/// punctuator | ||
token Dot='.' Eq='=' Comma=',' Semi=';' Asn=':=' Hash='#' | ||
Lt='<' Leq='<=' Gt='>' Geq='>=' Add='+' Sub='-' Mul='*' LPar='(' | ||
RPar=')' LBrak='[' RBrak=']' Not='~' And='&' Colon=':'; | ||
token Ident='<identifier>' Number='<number>'; | ||
|
||
start: | ||
module | ||
; | ||
|
||
selector: | ||
('.' Ident | '[' (expression !) ']')* | ||
; | ||
factor: | ||
Ident selector | Number | '(' (expression !) ')' | '~' factor | ||
; | ||
term: | ||
factor (('*' | 'DIV' | 'MOD' | '&') factor)* | ||
; | ||
simple_expression: | ||
['+' | '-'] term (('+' | '-' | 'OR') term)* | ||
; | ||
expression: | ||
simple_expression [('=' | '#' | '<' | '<=' | '>' | '>=') simple_expression] | ||
; | ||
assignment_or_procedure_call: | ||
Ident selector (':=' expression | [actual_parameters]) | ||
; | ||
actual_parameters: | ||
'(' [expression (',' expression !)* !] ')' | ||
; | ||
if_statement: | ||
'IF' (expression !) 'THEN' statement_sequence | ||
('ELSIF' (expression !) 'THEN' statement_sequence)* | ||
['ELSE' statement_sequence] 'END' | ||
; | ||
while_statement: | ||
'WHILE' (expression !) 'DO' statement_sequence 'END' | ||
; | ||
repeat_statement: | ||
'REPEAT' statement_sequence 'UNTIL' expression | ||
; | ||
statement: | ||
[assignment_or_procedure_call | if_statement | while_statement | repeat_statement | !] | ||
; | ||
statement_sequence: | ||
statement (';' statement)* | ||
; | ||
ident_list: | ||
Ident (',' Ident !)* | ||
; | ||
array_type: | ||
'ARRAY' (expression !) 'OF' type | ||
; | ||
field_list: | ||
[ident_list ':' type] | ||
; | ||
record_type: | ||
'RECORD' (field_list (';' field_list !)* !) 'END' | ||
; | ||
type: | ||
Ident | array_type | record_type | ! | ||
; | ||
fp_section: | ||
['VAR'] ident_list ':' type | ||
; | ||
formal_parameters: | ||
'(' [fp_section (';' fp_section !)* !] ')' | ||
; | ||
procedure_heading: | ||
'PROCEDURE' Ident [formal_parameters] | ! | ||
; | ||
procedure_body: | ||
declarations ['BEGIN' statement_sequence] 'END' Ident | ! | ||
; | ||
procedure_declaration: | ||
procedure_heading ';' procedure_body | ||
; | ||
declarations: | ||
['CONST' (Ident '=' expression ';' !)*] | ||
['TYPE' (Ident '=' type ';' !)*] | ||
['VAR' (ident_list ':' type ';' !)*] | ||
(procedure_declaration ';' !)* | ||
; | ||
module: | ||
'MODULE' Ident ';' declarations ['BEGIN' statement_sequence] 'END' Ident '.' | ||
; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,180 @@ | ||
use codespan_reporting::diagnostic::Label; | ||
use logos::{Lexer, Logos}; | ||
|
||
pub type Span = core::ops::Range<usize>; | ||
pub type Diagnostic = codespan_reporting::diagnostic::Diagnostic<()>; | ||
|
||
pub struct TokenStream<'a> { | ||
lexer: Lexer<'a, Token>, | ||
} | ||
|
||
impl<'a> TokenStream<'a> { | ||
pub fn new(lexer: Lexer<'a, Token>) -> Self { | ||
Self { lexer } | ||
} | ||
#[inline] | ||
pub fn next_token(&mut self) -> Result<Token, LexerError> { | ||
if let Some(token) = Iterator::next(&mut self.lexer) { | ||
return token; | ||
} | ||
Ok(Token::EOF) | ||
} | ||
#[inline] | ||
fn span(&self) -> Span { | ||
self.lexer.span() | ||
} | ||
} | ||
|
||
macro_rules! check_limit { | ||
($input:expr, $current:expr, $depth:expr) => { | ||
if $depth > 128 { | ||
*$current = Token::EOF; | ||
return Err(Diagnostic::error() | ||
.with_message("exceeded recursion depth limit") | ||
.with_labels(vec![Label::primary((), $input.span())])); | ||
} | ||
}; | ||
} | ||
|
||
macro_rules! err { | ||
[$input:expr, $($tk:literal),*] => { | ||
{ | ||
let expected = [$($tk),*]; | ||
let mut msg = "invalid syntax, expected".to_string(); | ||
if expected.len() > 1 { | ||
msg.push_str(" one of: "); | ||
} else { | ||
msg.push_str(": "); | ||
} | ||
let mut count = 0; | ||
for e in expected { | ||
count += 1; | ||
let s = format!("{}", e); | ||
let s = if s.starts_with('<') && s.ends_with('>') && s.len() > 2 { | ||
s | ||
} else { | ||
format!("'{}'", s) | ||
}; | ||
msg.push_str(&s); | ||
if count < expected.len() { | ||
msg.push_str(", "); | ||
} | ||
} | ||
Err(Diagnostic::error() | ||
.with_message(msg) | ||
.with_labels(vec![Label::primary((), $input.span())])) | ||
} | ||
} | ||
} | ||
|
||
#[derive(Debug, Clone, PartialEq, Default)] | ||
pub enum LexerError { | ||
#[default] | ||
Invalid, | ||
} | ||
|
||
impl LexerError { | ||
pub fn into_diagnostic(self, span: Span) -> Diagnostic { | ||
match self { | ||
Self::Invalid => Diagnostic::error() | ||
.with_message("invalid token") | ||
.with_labels(vec![Label::primary((), span)]), | ||
} | ||
} | ||
} | ||
|
||
#[derive(Logos, Debug, PartialEq, Clone)] | ||
#[logos(skip r"\s+")] | ||
#[logos(skip r"\(\*[^*]*\*+([^)*][^*]*\*+)*\)")] | ||
#[logos(error = LexerError)] | ||
pub enum Token { | ||
EOF, | ||
#[token("CONST")] | ||
Const, | ||
#[token("VAR")] | ||
Var, | ||
#[token("PROCEDURE")] | ||
Procedure, | ||
#[token("BEGIN")] | ||
Begin, | ||
#[token("END")] | ||
End, | ||
#[token("IF")] | ||
If, | ||
#[token("THEN")] | ||
Then, | ||
#[token("WHILE")] | ||
While, | ||
#[token("DO")] | ||
Do, | ||
#[token("ELSIF")] | ||
Elsif, | ||
#[token("ELSE")] | ||
Else, | ||
#[token("TYPE")] | ||
Type, | ||
#[token("DIV")] | ||
DivKw, | ||
#[token("MOD")] | ||
ModKw, | ||
#[token("OR")] | ||
OrKw, | ||
#[token("ARRAY")] | ||
Array, | ||
#[token("RECORD")] | ||
Record, | ||
#[token("OF")] | ||
Of, | ||
#[token("MODULE")] | ||
Module, | ||
#[token("REPEAT")] | ||
Repeat, | ||
#[token("UNTIL")] | ||
Until, | ||
#[token(".")] | ||
Dot, | ||
#[token("=")] | ||
Eq, | ||
#[token(",")] | ||
Comma, | ||
#[token(";")] | ||
Semi, | ||
#[token(":=")] | ||
Asn, | ||
#[token("#")] | ||
Hash, | ||
#[token("<")] | ||
Lt, | ||
#[token("<=")] | ||
Leq, | ||
#[token(">")] | ||
Gt, | ||
#[token(">=")] | ||
Geq, | ||
#[token("+")] | ||
Add, | ||
#[token("-")] | ||
Sub, | ||
#[token("*")] | ||
Mul, | ||
#[token("(")] | ||
LPar, | ||
#[token(")")] | ||
RPar, | ||
#[token("[")] | ||
LBrak, | ||
#[token("]")] | ||
RBrak, | ||
#[token("~")] | ||
Not, | ||
#[token("&")] | ||
And, | ||
#[token(":")] | ||
Colon, | ||
#[regex("[[:alpha:]][[:alnum:]]*")] | ||
Ident, | ||
#[regex(r"\d+")] | ||
Number, | ||
} | ||
|
||
include!(concat!(env!("OUT_DIR"), "/generated.rs")); |