Files
lambda/pkg/saccharine/tokenizer.go

117 lines
2.6 KiB
Go

package saccharine
import (
"errors"
"fmt"
"unicode"
"git.maximhutz.com/max/lambda/pkg/iterator"
"git.maximhutz.com/max/lambda/pkg/saccharine/token"
"git.maximhutz.com/max/lambda/pkg/trace"
)
// isVariables determines whether a rune can be a valid variable.
func isVariable(r rune) bool {
return unicode.IsLetter(r) || unicode.IsNumber(r)
}
func parseRune(i *iterator.Iterator[rune], expected func(rune) bool) (rune, error) {
i2 := i.Copy()
if r, err := i2.Next(); err != nil {
return r, err
} else if !expected(r) {
return r, fmt.Errorf("got unexpected rune %v'", r)
} else {
i.Sync(i2)
return r, nil
}
}
func parseCharacter(i *iterator.Iterator[rune], expected rune) (rune, error) {
i2 := i.Copy()
if r, err := i2.Next(); err != nil {
return r, err
} else if r != expected {
return r, fmt.Errorf("got unexpected rune %v'", r)
} else {
i.Sync(i2)
return r, nil
}
}
// 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.Token, error) {
index := i.Index()
if i.Done() {
return nil, nil
}
letter, err := i.Next()
if err != nil {
return nil, trace.WrapError(fmt.Errorf("cannot produce next token"), err)
}
switch {
case letter == '(':
return token.NewOpenParen(index), nil
case letter == ')':
return token.NewCloseParen(index), nil
case letter == '.':
return token.NewDot(index), nil
case letter == '\\':
return token.NewSlash(index), nil
case letter == '\n':
return token.NewNewline(index), nil
case letter == '{':
return token.NewNewline(index), nil
case letter == '}':
return token.NewNewline(index), nil
case letter == ':':
if _, err := parseCharacter(i, '='); err != nil {
return nil, err
} else {
return token.NewAssign(index), nil
}
case letter == ';':
return token.NewEnd(index), nil
case unicode.IsSpace(letter):
return nil, nil
case isVariable(letter):
atom := []rune{letter}
for {
if r, err := parseRune(i, isVariable); err != nil {
break
} else {
atom = append(atom, r)
}
}
return token.NewAtom(string(atom), index), nil
}
return nil, fmt.Errorf("unknown character '%v'", string(letter))
}
// Parses a list of runes into tokens. All error encountered are returned, as well.
func GetTokens(input string) ([]token.Token, error) {
i := iterator.Of([]rune(input))
tokens := []token.Token{}
errorList := []error{}
for !i.Done() {
token, err := getToken(i)
if err != nil {
errorList = append(errorList, err)
} else if token != nil {
tokens = append(tokens, *token)
}
}
return tokens, errors.Join(errorList...)
}