From 14e06f870b8f3cced4f5d153eb4a08099830e5a7 Mon Sep 17 00:00:00 2001
From: Paul <der.paul.ammann@gmail.com>
Date: Tue, 14 Jun 2022 14:42:18 +0200
Subject: [PATCH] Init
---
src/C1_parser.rs | 289 +++++++++++++++++++++++++++++++++++++++++++++++
src/lexer.rs | 4 +
src/lib.rs | 2 +
tests/parser.rs | 3 +
4 files changed, 298 insertions(+)
create mode 100644 src/C1_parser.rs
diff --git a/src/C1_parser.rs b/src/C1_parser.rs
new file mode 100644
index 0000000..127809a
--- /dev/null
+++ b/src/C1_parser.rs
@@ -0,0 +1,289 @@
+use std::fs::File;
+use crate::{C1Lexer, C1Token, lexer, ParseResult};
+
+pub struct C1Parser<'a> {
+ lx: C1Lexer<'a>,
+}
+
+impl<'a> C1Parser<'a> {
+ fn new(text: &str) -> C1Parser {
+ C1Parser {
+ lx: C1Lexer::new(text),
+ }
+ }
+
+ pub fn parse(text: &str) -> ParseResult {
+ let mut instance = C1Parser::new(text);
+
+ println!("Starting parsing");
+
+ instance.program().unwrap();
+
+ Ok(())
+ }
+
+ fn program(&mut self) -> ParseResult {
+ self.functiondefinition().unwrap();
+ Ok(())
+ }
+
+ fn functiondefinition(&mut self) -> ParseResult {
+ if self.lx.current_token() == Some(C1Token::KwInt) || self.lx.current_token() == Some(C1Token::KwVoid) || self.lx.current_token() == Some(C1Token::KwBoolean) || self.lx.current_token() == Some(C1Token::KwFloat) {
+ self.lx.eat();
+
+ self.check_and_eat_token(C1Token::Identifier).unwrap();
+ self.check_and_eat_token(C1Token::LeftParenthesis).unwrap();
+ self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ self.check_and_eat_token(C1Token::LeftBrace).unwrap();
+ self.statementlist().unwrap();
+ self.check_and_eat_token(C1Token::RightBrace).unwrap();
+
+ return Ok(());
+ }
+ return Err(format!("Expected token group 'type' but found {:?}", self.lx.current_token()));
+ }
+
+ fn statementlist(&mut self) -> ParseResult {
+ print!("statementlist->");
+ //self.block().unwrap(); //TODO: While loop
+
+ /*if self.lx.current_token() == Some(C1Token::LeftBrace) && self.lx.peek_token() == Some(C1Token::RightBrace) {
+ self.lx.eat();
+ self.lx.eat();
+ println!("eat");
+ return Ok(());
+ }
+
+
+ if self.lx.current_token() == Some(C1Token::LeftBrace){
+ self.check_and_eat_token(C1Token::LeftBrace).unwrap();
+
+ while !(self.lx.current_token() == Some(C1Token::RightBrace)) {
+ println!("r");
+
+ if self.lx.current_token() == Some(C1Token::LeftBrace){
+ self.statementlist().unwrap();
+ }
+
+ self.statement().unwrap();
+ }
+ println!("block finished!!!");
+
+ self.check_and_eat_token(C1Token::RightBrace).unwrap();
+ }*/
+
+ while !(self.lx.current_token() == Some(C1Token::RightBrace)) {
+ self.block().unwrap();
+ }
+
+ Ok(())
+ }
+
+ fn block(&mut self) -> ParseResult {
+ print!("block->");
+ if self.lx.current_token() == Some(C1Token::LeftBrace){
+ self.check_and_eat_token(C1Token::LeftBrace).unwrap();
+ self.statementlist().unwrap();
+ self.check_and_eat_token(C1Token::RightBrace).unwrap();
+ }else{
+ self.statement().unwrap();
+ }
+ Ok(())
+ }
+
+ fn statement(&mut self) -> ParseResult {
+ print!("statement->");
+ match self.lx.current_token() {
+ Some(C1Token::KwIf) => {
+ self.ifstatement().unwrap();
+ Ok(())
+ },
+ Some(C1Token::KwReturn) => {
+ self.returnstatement().unwrap();
+ self.check_and_eat_token(C1Token::Semicolon).unwrap();
+ Ok(())
+ },
+ Some(C1Token::KwPrintf) => {
+ self.printfstatement().unwrap();
+ self.check_and_eat_token(C1Token::Semicolon).unwrap();
+ Ok(())
+ },
+ Some(C1Token::Identifier) => {
+ if self.lx.peek_token() == Some(C1Token::Assign) {
+ self.statassignment().unwrap();
+ self.check_and_eat_token(C1Token::Semicolon).unwrap();
+ }else{
+ self.functioncall().unwrap();
+ self.check_and_eat_token(C1Token::Semicolon).unwrap();
+ }
+ Ok(())
+ },
+ _ => Err(format!("Expected token group 'statement' but found {:?}", self.lx.current_token().unwrap())),
+ }
+ }
+
+ fn functioncall(&mut self) -> ParseResult {
+ print!("functioncall->");
+ self.check_and_eat_token(C1Token::Identifier).unwrap();
+ self.check_and_eat_token(C1Token::LeftParenthesis).unwrap();
+ self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ Ok(())
+ }
+
+ fn statassignment(&mut self) -> ParseResult {
+ print!("statassignment->");
+ self.check_and_eat_token(C1Token::Identifier).unwrap();
+ self.check_and_eat_token(C1Token::Assign).unwrap();
+ self.assignment().unwrap();
+ Ok(())
+ }
+
+
+ fn returnstatement(&mut self) -> ParseResult {
+ print!("returnstatement->");
+ self.check_and_eat_token(C1Token::KwReturn).unwrap();
+ self.assignment(); //TODO: Maybe?
+ Ok(())
+ }
+
+ fn printfstatement(&mut self) -> ParseResult {
+ print!("printfstatement->");
+ self.check_and_eat_token(C1Token::KwPrintf).unwrap();
+ self.check_and_eat_token(C1Token::LeftParenthesis).unwrap();
+ self.assignment().unwrap();
+ self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ Ok(())
+ }
+
+ fn ifstatement(&mut self) -> ParseResult {
+ print!("ifstatement->");
+ self.check_and_eat_token(C1Token::KwIf).unwrap();
+ self.check_and_eat_token(C1Token::LeftParenthesis).unwrap();
+ self.assignment().unwrap();
+ //TODO: self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ self.block().unwrap();
+ Ok(())
+ }
+
+ fn assignment(&mut self) -> ParseResult {
+ print!("assignment->");
+ println!("test: {:?} {:?}", self.lx.current_text(), self.lx.peek_text());
+ if self.lx.current_token() == Some(C1Token::Identifier) && self.lx.peek_token() == Some(C1Token::Assign) {
+ self.check_and_eat_token(C1Token::Identifier).unwrap();
+ self.check_and_eat_token(C1Token::Assign).unwrap();
+ self.assignment().unwrap();
+ return Ok(());
+ }else{
+ println!("assignment: Not Identifier");
+ self.expr().unwrap();
+ return Ok(());
+ }
+ }
+
+ fn expr(&mut self) -> ParseResult {
+ print!("expr->");
+ self.simpexpr().unwrap();
+
+ let tk = self.lx.current_token();
+ if tk == Some(C1Token::Equal) || tk == Some(C1Token::NotEqual) || tk == Some(C1Token::Less) || tk == Some(C1Token::LessEqual) || tk == Some(C1Token::Greater) || tk == Some(C1Token::GreaterEqual) {
+ self.lx.eat();
+ self.simpexpr().unwrap();
+ }else{
+ return Ok(());
+ }
+ self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ Ok(())
+ }
+
+ fn simpexpr(&mut self) -> ParseResult {
+ print!("simpexpr->");
+ if self.lx.current_token() == Some(C1Token::Minus){
+ self.check_and_eat_token(C1Token::Minus).unwrap();
+ }
+ self.term().unwrap();
+
+ while self.lx.current_token() == Some(C1Token::Plus) || self.lx.current_token() == Some(C1Token::Minus) || self.lx.current_token() == Some(C1Token::Or) {
+ self.lx.eat();
+ self.term().unwrap();
+ }
+ Ok(())
+ }
+
+ fn term(&mut self) -> ParseResult {
+ print!("term->");
+ self.factor().unwrap();
+
+ while self.lx.current_token() == Some(C1Token::Asterisk) || self.lx.current_token() == Some(C1Token::Slash) || self.lx.current_token() == Some(C1Token::And) {
+ self.lx.eat();
+ self.factor().unwrap();
+ }
+ Ok(())
+ }
+
+ fn factor(&mut self) -> ParseResult {
+ print!("factor->");
+
+
+
+ match self.lx.current_token() {
+ Some(C1Token::ConstInt) => {
+ self.check_and_eat_token(C1Token::ConstInt).unwrap();
+ Ok(())
+ },
+ Some(C1Token::ConstFloat) => {
+ self.check_and_eat_token(C1Token::ConstFloat).unwrap();
+ Ok(())
+ },
+ Some(C1Token::ConstBoolean) => {
+ self.check_and_eat_token(C1Token::ConstBoolean).unwrap();
+ Ok(())
+ },
+ Some(C1Token::Identifier) => {
+
+ if self.lx.peek_token() == Some(C1Token::LeftParenthesis) {
+ self.functioncall().unwrap();
+ }else{
+ self.check_and_eat_token(C1Token::Identifier).unwrap();
+ }
+
+ Ok(())
+ },
+ Some(C1Token::LeftParenthesis) => {
+
+ print!("factor left parenthesis->");
+
+ self.check_and_eat_token(C1Token::LeftParenthesis).unwrap();
+ self.assignment().unwrap();
+ self.check_and_eat_token(C1Token::RightParenthesis).unwrap();
+ Ok(())
+ },
+ _ => Err(format!("Expected token group 'factor' but found {:?}", self.lx.current_token().unwrap())),
+ }
+
+ }
+
+
+ fn current_matches(&self, token: C1Token) -> ParseResult {
+ if self.lx.current_token() == Some(token) {
+ Ok(())
+ } else {
+ Err(format!("Expected token {:?}", token))
+ }
+ }
+
+ fn check_and_eat_token(&mut self, token: C1Token) -> ParseResult{
+ println!("Checking token: {:?} with text {:?} in line {:?}", token, self.lx.current_text().unwrap(), self.lx.current_line_number().unwrap());
+ match self.lx.current_token() {
+ Some(x) => {
+ if x == token {
+ println!("Correct: {:?}", x);
+ self.lx.eat();
+ return Ok(());
+ }
+ println!("Wrong: {:?}", x);
+ return Err(format!("Expected token {:?} but found {:?}", token, x));
+ },
+ None => Err("No token".to_owned()),
+ }
+ }
+}
\ No newline at end of file
diff --git a/src/lexer.rs b/src/lexer.rs
index a955a4d..e56101b 100644
--- a/src/lexer.rs
+++ b/src/lexer.rs
@@ -126,6 +126,10 @@ pub enum C1Token {
#[regex("//[^\n]*(\n)?", logos::skip)]
CPPComment,
+ #[regex(r"\r", logos::skip)] //NEW
+ carriagereturn,
+
+
// We can also use this variant to define whitespace,
// or any other matches we wish to skip.
#[regex(r"[ \t\f]+", logos::skip)]
diff --git a/src/lib.rs b/src/lib.rs
index 82c0db8..4de0c7a 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -10,3 +10,5 @@ pub use lexer::C1Token;
// You will need a re-export of your C1Parser definition. Here is an example:
// mod parser;
// pub use parser::C1Parser;
+mod C1_parser;
+pub use C1_parser::C1Parser;
diff --git a/tests/parser.rs b/tests/parser.rs
index a627444..883b222 100644
--- a/tests/parser.rs
+++ b/tests/parser.rs
@@ -4,6 +4,9 @@ use std::fs;
#[test]
fn run_example() {
let text = fs::read_to_string("tests/data/beispiel.c-1").unwrap();
+
+ println!("test1");
+
let result = C1Parser::parse(text.as_str());
assert!(result.is_ok(), "Parse result: {}", result.err().unwrap());
}
--
GitLab