parser: implement initial tokeniser

only logging position, errors and non-whitespace elements

Signed-off-by: Alejandro Mery <amery@jpi.io>

parser/lexer.go

@@ -1,11 +1,73 @@
 package parser
 
-import "asciigoat.org/core/lexer"
+import (
+	"asciigoat.org/core/lexer"
+)
 
 // Run parses the source
 func (p *Parser) Run() error {
 	p.setDefaults()
 	p.pos.Reset()
 
-	return lexer.Run(nil)
+	return lexer.Run(p.lexStart)
+}
+
+func (p *Parser) lexStart() (lexer.StateFn, error) {
+	for {
+		r, _, err := p.src.ReadRune()
+		switch {
+		case err != nil:
+			// read error
+			return p.emitError("", err)
+		case IsNewLine(r):
+			// new line
+			p.lexNewLine(r)
+			p.stepLine()
+		case IsSpace(r):
+			// whitespace
+			p.stepRune()
+		default:
+			// token
+			p.src.UnreadRune()
+			return p.lexToken, nil
+		}
+	}
+}
+
+func (p *Parser) lexToken() (lexer.StateFn, error) {
+	p.src.AcceptAll(IsNotSpace)
+
+	p.pushString(TokenUnknown)
+
+	return p.lexStart, nil
+}
+
+func (p *Parser) lexNewLine(r1 rune) {
+	// r1 is warrantied to be either \n or \r
+	r2, _, err := p.src.ReadRune()
+
+	switch r1 {
+	case '\r':
+		switch {
+		case r2 == '\n':
+			// CR LN
+		case err == nil:
+			// CR
+			p.src.UnreadRune()
+		default:
+			// CR EOF
+		}
+	case '\n':
+		switch {
+		case r2 == '\r':
+			// LN CR
+		case err == nil:
+			// LN
+			p.src.UnreadRune()
+		default:
+			// LN EOF
+		}
+	default:
+		panic("unreachable")
+	}
 }

parser/lexer_runes.go

@@ -0,0 +1,19 @@
+package parser
+
+import "asciigoat.org/core/lexer"
+
+var (
+	// IsNewLine tells if a rune represents a line break or the start of one
+	IsNewLine = lexer.NewIsIn("\n\r")
+	// IsSpace tells if a rune is considered whitespace by unicode
+	IsSpace = lexer.IsSpace
+	// IsNotNewLine tells if a rune is anything other than line breaks
+	IsNotNewLine = lexer.NewIsNot(IsNewLine)
+	// IsNotSpace tells if a rune is anything other than whitespace
+	IsNotSpace = lexer.NewIsNot(IsSpace)
+)
+
+// IsSpaceNotNewLine indicates a rune is whitespace but not a new line
+func IsSpaceNotNewLine(r rune) bool {
+	return IsSpace(r) && !IsNewLine(r)
+}