Files
lambda/pkg/saccharine/tokenizer.go

73 lines
1.9 KiB
Go

package saccharine
import (
"errors"
"fmt"
"unicode"
"git.maximhutz.com/max/lambda/pkg/iterator"
)
// isVariables determines whether a rune can be a valid variable.
func isVariable(r rune) bool {
return unicode.IsLetter(r) || unicode.IsNumber(r)
}
// Pulls the next token from an iterator over runes. If it cannot, it will
// return nil. If an error occurs, it will return that.
func getToken(i *iterator.Iterator[rune]) (*Token, error) {
index := i.Index()
if i.IsDone() {
return nil, nil
}
letter, err := i.Pop()
if err != nil {
return nil, fmt.Errorf("cannot produce next token: %w", err)
}
switch {
case letter == '(':
// The opening deliminator of an application.
return &Token{Type: TokenOpenParen, Index: index, Value: string(letter)}, nil
case letter == ')':
// The terminator of an application.
return &Token{Type: TokenCloseParen, Index: index, Value: string(letter)}, nil
case letter == '.':
// The terminator of the parameters in an abstraction.
return &Token{Type: TokenDot, Index: index, Value: string(letter)}, nil
case letter == '\\':
// The opening deliminator of an abstraction.
return &Token{Type: TokenSlash, Index: index, Value: string(letter)}, nil
case unicode.IsSpace(letter):
// If there is a space character, ignore it.
return nil, nil
case isVariable(letter):
rest := i.PopWhile(isVariable)
atom := string(append([]rune{letter}, rest...))
return &Token{Index: index, Type: TokenVariable, Value: atom}, nil
}
return nil, fmt.Errorf("unknown character '%v'", letter)
}
// Parses a list of runes into tokens. All error encountered are returned, as well.
func GetTokens(input []rune) ([]Token, error) {
i := iterator.New(input)
tokens := []Token{}
errorList := []error{}
for !i.IsDone() {
token, err := getToken(i)
if err != nil {
errorList = append(errorList, err)
} else if token != nil {
tokens = append(tokens, *token)
}
}
return tokens, errors.Join(errorList...)
}