all premade tests pass

src/lexer/c1.rs

@@ -3,9 +3,106 @@ use logos::Logos;
 #[derive(Logos, Debug, PartialEq)]
 pub enum C1Token {
     // TODO: Define variants and their token/regex
+    //// Tokens can be literal strings, of any length.
+    //#[token("fast")]
+    //Fast,
+    //// Or regular expressions.
+    //#[regex("[a-zA-Z]+")]
+    //Text,
+    #[token("bool")]
+    KwBoolean,
+    #[token("do")]
+    KwDo,	
+    #[token("else")]
+    KwElse,	
+    #[token("float")]
+    KwFloat,	
+    #[token("for")]
+    KwFor,	
+    #[token("if")]
+    KwIf,	
+    #[token("int")]
+    KwInt,	
+    #[token("printf")]
+    KwPrintf,	
+    #[token("return")]
+    KwReturn,	
+    #[token("void")]
+    KwVoid,	
+    #[token("while")]
+    KwWhile,
+
+    #[token("+")]
+    Plus,
+    #[token("-")]
+    Minus,
+    #[token("*")]
+    Asterisk,
+    #[token("/")]
+    Slash,
+    #[token("=")]
+    Assign,
+    #[token("==")]
+    Eq,
+    #[token("!=")]
+    Neq,
+    #[token("<")]
+    Lss,
+    #[token(">")]
+    Grt,
+    #[token("<=")]
+    Leq,
+    #[token(">=")]
+    Geq,
+    #[token("&&")]
+    And,
+    #[token("||")]
+    Or,
+
+    #[token(",")]
+    Comma,
+    #[token(";")]
+    Semicolon,
+    #[token("(")]
+    LParen,
+    #[token(")")]
+    RParen,
+    #[token("{")]
+    LBrace,
+    #[token("}")]
+    RBrace,
+
+    #[regex("[0-9]+")]
+    ConstInt,
+    #[regex(r"[0-9]*\.[0-9]+([eE]([+-])?[0-9]+)?")]
+    #[regex("[0-9]+[eE]([+-])?[0-9]+")]
+    ConstFloat,
+    #[regex("true")]
+    #[regex("false")]
+    ConstBoolean,
+    #[regex("\"[^\\n\"]*\"")] // ???????????????	 
+    ConstString,
+    #[regex("([a-zA-Z])+([0-9]|[a-zA-Z])*")]
+    Id,
+
+    //#[regex("[0-9]")]
+    //DIGIT,
+    //#[regex("[0-9]+")]
+    //INTEGER,
+    //#[regex("[0-9]+ \".\" [0-9]+ | \".\" [0-9]+")]
+    //FLOAT,
+    //#[regex("[a-zA-Z]")]
+    //LETTER,
+
+    #[regex(r"\s", logos::skip)]
+    #[regex(r"/\*([^*])*\*/", logos::skip)] //
+    #[regex("//[^\\n]*", logos::skip)]
+    Ignore,
 
-    // Logos requires one token variant to handle errors,
-    // it can be named anything you wish.
     #[error]
     Error,
+
+    // Logos requires one token variant to handle errors,
+    // it can be named anything you wish.
+    
 }

src/lexer/url.rs

@@ -27,9 +27,15 @@ impl Display for LinkText {
 #[derive(Logos, Debug, PartialEq)]
 pub enum URLToken {
     // TODO: Capture link definitions
+    //wasnt able to look for href="[^"]" even with escape char, so href= must do the trick
+    #[regex(r"<a[^>]+href=[^>]*>[^<]*</a(\s)*>", extract_link_info)]//<a[^>]*>[^<]*</a[^>]*>
     Link((LinkUrl, LinkText)),
 
     // TODO: Ignore all characters that do not belong to a link definition
+    //#[regex("", logos::skip)] //<[^a][^*]*>[^(<a)]*
+    #[regex("((<[^a])|[^<])*", logos::skip)]
+    //this works because it has a lower priority i guess...
+    #[regex("<a[^>]*>", logos::skip)]
     Ignored,
 
     // Catch any error
@@ -40,5 +46,35 @@ pub enum URLToken {
 /// Extracts the URL and text from a string that matched a Link token
 fn extract_link_info(lex: &mut Lexer<URLToken>) -> (LinkUrl, LinkText) {
     // TODO: Implement extraction from link definition
-    todo!()
+    //println!("{}", lex.slice());
+    let mut s = String::from(lex.slice());
+    
+    // this is sooo dirty, but i cant code in rust... :/
+    let pos = s.find("href=");
+    match pos {
+        None => (),
+        Some(p) => s = s[p+6..].to_string(),
+    }
+    let pos = s.find("\"");
+    let mut url = String::from("");
+    match pos {
+        None => (),
+        Some(p) => url.push_str(&s[..p].to_string()),
+    }
+    let pos = s.find(">");
+    match pos {
+        None => (),
+        Some(p) => s = s[p+1..].to_string(),
+    }
+    let pos = s.find("<");
+    let mut text = String::from("");
+    match pos {
+        None => (),
+        Some(p) => text.push_str(&s[..p].to_string()),
+    }
+    //println!("{}", s);
+    //println!("{}", url);
+    //println!("{}", text);
+
+    (LinkUrl(String::from(url)),LinkText(String::from(text)))
 }