M.V. Hutz
da3da70855
## Description Both the `saccharine` and `lambda` packages need tokenizing and parsing primitives. This PR extracts shared token infrastructure into a new `pkg/token` package, then wires both languages up to use it. - Add `pkg/token` with a generic `Token[T]` type, `Scan`, `ScanAtom`, `ScanRune`, `ScanCharacter`, `IsVariable`, `ParseRawToken`, and `ParseList`. - Refactor `pkg/saccharine` to delegate to `pkg/token`, removing duplicated scanning and parsing helpers. - Implement `Codec.Decode` for `pkg/lambda` (scanner + parser) using the shared token package. - Add `iterator.While` for predicate-driven iteration. - Rename `iterator.Do` to `iterator.Try` to better describe its rollback semantics. ### Decisions - The `Type` constraint (`comparable` + `Name() string`) keeps the generic token flexible while ensuring every token type can produce readable error messages. - `iterator.Do` was renamed to `iterator.Try` since it describes a try/rollback operation, not a side-effecting "do". ## Benefits - Eliminates duplicated token, scanning, and parsing code between languages. - Enables the `lambda` package to decode (parse) lambda calculus strings, which was previously unimplemented. - Makes it straightforward to add new languages by reusing `pkg/token` primitives. ## Checklist - [x] Code follows conventional commit format. - [x] Branch follows naming convention (`<type>/<description>`). Always use underscores. - [x] Tests pass (if applicable). - [ ] Documentation updated (if applicable). Reviewed-on: #46 Co-authored-by: M.V. Hutz <git@maximhutz.me> Co-committed-by: M.V. Hutz <git@maximhutz.me>
75 lines
2.2 KiB
Go
75 lines
2.2 KiB
Go
package token
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"unicode"
|
|
|
|
"git.maximhutz.com/max/lambda/pkg/iterator"
|
|
)
|
|
|
|
// IsVariable determines whether a rune can be a valid variable character.
|
|
func IsVariable(r rune) bool {
|
|
return unicode.IsLetter(r) || unicode.IsNumber(r) || r == '_'
|
|
}
|
|
|
|
// ScanRune consumes the next rune from the iterator if it satisfies the
|
|
// predicate.
|
|
// Returns an error if the iterator is exhausted or the rune does not match.
|
|
func ScanRune(i *iterator.Iterator[rune], expected func(rune) bool) (rune, error) {
|
|
return iterator.Try(i, func(i *iterator.Iterator[rune]) (rune, error) {
|
|
if r, err := i.Next(); err != nil {
|
|
return r, err
|
|
} else if !expected(r) {
|
|
return r, fmt.Errorf("got unexpected rune %v'", r)
|
|
} else {
|
|
return r, nil
|
|
}
|
|
})
|
|
}
|
|
|
|
// ScanCharacter consumes the next rune from the iterator if it matches the
|
|
// expected rune exactly.
|
|
// Returns an error if the iterator is exhausted or the rune does not match.
|
|
func ScanCharacter(i *iterator.Iterator[rune], expected rune) (rune, error) {
|
|
return ScanRune(i, func(r rune) bool { return r == expected })
|
|
}
|
|
|
|
// ScanAtom scans a contiguous sequence of variable characters into a single
|
|
// atom token.
|
|
// The first rune has already been consumed and is passed in.
|
|
func ScanAtom[T Type](i *iterator.Iterator[rune], first rune, typ T, column int) *Token[T] {
|
|
atom := []rune{first}
|
|
|
|
for {
|
|
if r, err := ScanRune(i, IsVariable); err != nil {
|
|
break
|
|
} else {
|
|
atom = append(atom, r)
|
|
}
|
|
}
|
|
|
|
return NewAtom(typ, string(atom), column)
|
|
}
|
|
|
|
// Scan tokenizes an input string using a language-specific scanToken function.
|
|
// The scanToken function is called repeatedly until the input is exhausted.
|
|
// It returns nil (no token, no error) for skippable input like whitespace.
|
|
// Errors are accumulated and returned joined at the end.
|
|
func Scan[T Type](input string, scanToken func(*iterator.Iterator[rune]) (*Token[T], error)) ([]Token[T], error) {
|
|
i := iterator.Of([]rune(input))
|
|
tokens := []Token[T]{}
|
|
errorList := []error{}
|
|
|
|
for !i.Done() {
|
|
token, err := scanToken(i)
|
|
if err != nil {
|
|
errorList = append(errorList, err)
|
|
} else if token != nil {
|
|
tokens = append(tokens, *token)
|
|
}
|
|
}
|
|
|
|
return tokens, errors.Join(errorList...)
|
|
}
|