Regular-Expresso Changeset

Changeset - 68c16b6d84f3

Parent rev.

Child rev.

[Not reviewed]

default

0 3 0

Laman - 10 months ago 2024-06-20 13:49:15

added the lambda transition

3 files changed with 51 insertions and 0 deletions:

regexp.py

src/regexp/token.rs

tests/test_regexp.rs

0 comments (0 inline, 0 general)

regexp.py

➞

Show inline comments

@@ @@ -21,6 +21,19 @@ class Token: @@
 		pass
 class Lambda(Token):
 	is_skippable = True
 	def list_first(self):
 		yield from []
 	def list_last(self):
 		yield from []
 	def list_neighbours(self):
 		yield from []
 class Symbol(Token):
 	def __init__(self, position, value):
 		self.position = position
@@ @@ -188,6 +201,9 @@ def parse(pattern, offset=0): @@
 			is_alternative = True
 			res.append(AlternativeSeparator())
 			i += 1
 		elif c == "_":
 			res.append(Lambda())
 			i += 1
 		else:
 			res.append(Symbol(i+offset, c))
 			i += 1

src/regexp/token.rs

➞

Show inline comments

@@ @@ -52,6 +52,7 @@ pub struct Chain { @@
+}
 pub enum Token {
 	Lambda,
 	Symbol(Symbol),
 	Asterisk(Asterisk),
 	Plus(Plus),
@@ @@ -225,6 +226,7 @@ impl Chain { @@
 impl Token {
 	pub fn is_skippable(&self) -> bool {
 		match self {
 			Token::Lambda => true,
 			Token::Symbol(_) => false,
 			Token::Asterisk(_) => true,
 			Token::Plus(_) => false,
@@ @@ -236,6 +238,7 @@ impl Token { @@
 	pub fn list_first(&self) -> Vec<usize> {
 		match self {
 			Token::Lambda => vec![],
 			Token::Symbol(t) => t.list_first(),
 			Token::Asterisk(t) => t.list_first(),
 			Token::Plus(t) => t.list_first(),
@@ @@ -247,6 +250,7 @@ impl Token { @@
 	pub fn list_last(&self) -> Vec<usize> {
 		match self {
 			Token::Lambda => vec![],
 			Token::Symbol(t) => t.list_last(),
 			Token::Asterisk(t) => t.list_last(),
 			Token::Plus(t) => t.list_last(),
@@ @@ -258,6 +262,7 @@ impl Token { @@
 	pub fn list_neighbours(&self) -> Vec<(usize, usize)> {
 		match self {
 			Token::Lambda => vec![],
 			Token::Symbol(t) => t.list_neighbours(),
 			Token::Asterisk(t) => t.list_neighbours(),
 			Token::Plus(t) => t.list_neighbours(),
@@ @@ -313,6 +318,10 @@ pub fn parse(pattern: &String, offset: u @@
 				res.push(Box::new(Token::AlternativeSeparator));
 				i += 1;
+			}
 			'_' => {
 				res.push(Box::new(Token::Lambda));
 				i += 1;
+			}
 			_c => {
 				res.push(Box::new(Token::Symbol(Symbol{position: i+offset})));
 				i += 1;

tests/test_regexp.rs

➞

Show inline comments

@@ @@ -89,6 +89,32 @@ fn test_eval_alternative_dfa() { @@
+}
 #[test]
 fn test_eval_lambda_nfa() {
 	let r = Regexp::new(&String::from("a_")).unwrap();
 	assert!(r.eval(String::from("a")));
 	assert!(!r.eval(String::from("")));
 	assert!(!r.eval(String::from("ab")));
 	let r = Regexp::new(&String::from("a|_")).unwrap();
 	assert!(r.eval(String::from("a")));
 	assert!(r.eval(String::from("")));
 	assert!(!r.eval(String::from("b")));
+}
 #[test]
 fn test_eval_lambda_dfa() {
 	let r = Regexp::new(&String::from("a_")).unwrap().determinize();
 	assert!(r.eval(String::from("a")));
 	assert!(!r.eval(String::from("")));
 	assert!(!r.eval(String::from("ab")));
 	let r = Regexp::new(&String::from("a|_")).unwrap().determinize();
 	assert!(r.eval(String::from("a")));
 	assert!(r.eval(String::from("")));
 	assert!(!r.eval(String::from("b")));
+}
 #[test]
 fn test_invalid_asterisk() {
 	let x = Regexp::new(&String::from("*"));
 	assert!(matches!(x, Err(ParsingError::Asterisk{s: _, pos: 0})));

0 comments (0 inline, 0 general)