ginger/gg/grammar/symbol.go

package grammar

import (
	"errors"
	"fmt"
	"io"
	"strings"
)

// ErrNoMatch is used by Symbol's Decode method, see that method's docs for more
// details.
var ErrNoMatch = errors.New("no match")

// Symbol represents a symbol in the grammar. A Symbol is expected to be
// stateless, and is usually constructed from other Symbols using functions in
// this package.
type Symbol[T any] interface {
	fmt.Stringer // Used when generating errors related to this Symbol, e.g. "number"

	// Decode reads and parses a value represented by this Symbol off the
	// Reader.
	//
	// This may return ErrNoMatch to indicate that the upcoming data on the
	// Reader is rejected by this Symbol. In this case the Symbol should leave
	// the Reader in the same state it was passed.
	Decode(Reader) (T, error)
}

type symbol[T any] struct {
	fmt.Stringer
	decodeFn func(Reader) (T, error)
}

func (s *symbol[T]) Decode(r Reader) (T, error) { return s.decodeFn(r) }

// SymbolPtr wraps a Symbol in a such a way as to make lazily initializing a
// Symbol variable possible. This allows for recursion amongst different
// Symbols.
//
// Example:
//
//	a := new(SymbolPtr)
//	b := new(SymbolPtr)
//	a.Symbol = FirstOf(Rune('a'), b)
//	b.Symbol = FirstOf(Rune('b'), a)
type SymbolPtr[T any] struct {
	Symbol[T]
}

func named[T any](stringer fmt.Stringer, sym Symbol[T]) Symbol[T] {
	return &symbol[T]{
		stringer,
		sym.Decode,
	}
}

// Named wraps the given Symbol such that its String method returns the given
// name.
func Named[T any](name string, sym Symbol[T]) Symbol[T] {
	return named(Stringer{S: name}, sym)
}

// RuneFunc matches and produces any rune for which the given function returns
// true.
func RuneFunc(name string, fn func(rune) bool) Symbol[Located[rune]] {
	return &symbol[Located[rune]]{
		Stringer{S: name},
		func(rr Reader) (Located[rune], error) {
			var zero Located[rune]

			r, err := rr.ReadRune()
			if errors.Is(err, io.EOF) {
				return zero, ErrNoMatch
			} else if err != nil {
				return zero, err
			}

			if !fn(r.Value) {
				rr.UnreadRune(r)
				return zero, ErrNoMatch
			}

			return r, nil
		},
	}
}

// Rune matches and produces the given rune.
func Rune(r rune) Symbol[Located[rune]] {
	return RuneFunc(
		fmt.Sprintf("'%c'", r),
		func(r2 rune) bool { return r == r2 },
	)
}

// StringFromRunes produces a string from the slice of runes produced by the
// given Symbol. The slice must not be empty. StringFromRunes does not match if
// the given Symbol does not match.
func StringFromRunes(sym Symbol[[]Located[rune]]) Symbol[Located[string]] {
	return Mapping(sym, func(runes []Located[rune]) Located[string] {
		if len(runes) == 0 {
			panic("StringFromRunes used on empty set of runes")
		}

		str := make([]rune, len(runes))
		for i := range runes {
			str[i] = runes[i].Value
		}
		return Located[string]{runes[0].Location, string(str)}
	})
}

// Mapping produces a value of type Tb by decoding a value from the given
// Symbol and passing it through the given mapping function. If the given Symbol
// doesn't match then neither does Map.
func Mapping[Ta, Tb any](
	sym Symbol[Ta], fn func(Ta) Tb,
) Symbol[Tb] {
	return &symbol[Tb]{
		sym,
		func(rr Reader) (Tb, error) {
			var zero Tb
			va, err := sym.Decode(rr)
			if err != nil {
				return zero, err
			}
			return fn(va), nil
		},
	}
}

// OneOrMore will produce as many of the given Symbol's value as can be found
// sequentially, up until a non-matching value is encountered. If no matches are
// found then OneOrMore does not match.
func OneOrMore[T any](sym Symbol[T]) Symbol[[]T] {
	return &symbol[[]T]{
		Stringer{F: func() string {
			return fmt.Sprintf("one or more %v", sym)
		}},
		func(rr Reader) ([]T, error) {
			var vv []T
			for {
				v, err := sym.Decode(rr)
				if errors.Is(err, ErrNoMatch) {
					break
				} else if err != nil {
					return nil, err
				}

				vv = append(vv, v)
			}

			if len(vv) == 0 {
				return nil, ErrNoMatch
			}

			return vv, nil
		},
	}
}

// ZeroOrMore will produce as many of the given Symbol's value as can be found
// sequentially, up until a non-matching value is encountered. If no matches are
// found then an empty slice is produced.
func ZeroOrMore[T any](sym Symbol[T]) Symbol[[]T] {
	return &symbol[[]T]{
		Stringer{F: func() string {
			return fmt.Sprintf("zero or more %v", sym)
		}},
		func(rr Reader) ([]T, error) {
			var vv []T
			for {
				v, err := sym.Decode(rr)
				if errors.Is(err, ErrNoMatch) {
					break
				} else if err != nil {
					return nil, err
				}

				vv = append(vv, v)
			}

			return vv, nil
		},
	}
}

func firstOf[T any](stringer fmt.Stringer, syms ...Symbol[T]) Symbol[T] {
	return &symbol[T]{
		stringer,
		func(rr Reader) (T, error) {
			var zero T
			for _, sym := range syms {
				v, err := sym.Decode(rr)
				if errors.Is(err, ErrNoMatch) {
					continue
				} else if err != nil {
					return zero, err
				}

				return v, nil
			}

			return zero, ErrNoMatch
		},
	}
}

// FirstOf matches and produces the value for the first Symbol in the list which
// matches. FirstOf does not match if none of the given Symbols match.
func FirstOf[T any](syms ...Symbol[T]) Symbol[T] {
	return firstOf(
		Stringer{F: func() string {
			descrs := make([]string, len(syms))
			for i := range syms {
				descrs[i] = syms[i].String()
			}
			return strings.Join(descrs, " or ")
		}},
		syms...,
	)
}

// Reduction produces a value of type Tc by first reading a value from symA,
// then symB, and then running those through the given function.
//
// If symA does not match then Reduction does not match. If symA matches but
// symB does not then also match then Reduction produces a LocatedError.
func Reduction[Ta, Tb, Tc any](
	symA Symbol[Ta],
	symB Symbol[Tb],
	fn func(Ta, Tb) Tc,
) Symbol[Tc] {
	return &symbol[Tc]{
		symA,
		func(rr Reader) (Tc, error) {
			var zero Tc

			va, err := symA.Decode(rr)
			if err != nil {
				return zero, err
			}

			vb, err := symB.Decode(rr)
			if errors.Is(err, ErrNoMatch) {
				return zero, rr.NextLocation().errf("expected %v", symB)
			} else if err != nil {
				return zero, err
			}

			return fn(va, vb), nil

		},
	}
}

// Prefixed matches on prefixSym, discards its value, then produces the value
// produced by sym.
//
// If prefixSym does not match then Prefixed does not match. If prefixSym
// matches but sym does not also match then Prefixed produces a LocatedError.
func Prefixed[Ta, Tb any](prefixSym Symbol[Ta], sym Symbol[Tb]) Symbol[Tb] {
	return named(prefixSym, Reduction(prefixSym, sym, func(_ Ta, b Tb) Tb {
		return b
	}))
}

// PrefixDiscarded is similar to Prefixed, except that if sym does not match
// then PrefixDiscarded does not match, whereas Prefixed produces a LocatedError
// in that case.
//
// NOTE PrefixDiscarded does not fully honor the contract of Symbol. If
// prefixSym matches, but sym does not, then only sym will restore Reader to its
// prior state; prefixSym cannot return whatever data it read back onto the
// Reader. Therefore ErrNoMatch can be returned without Reader being fully back
// in its original state. In practice this isn't a big deal, given the common
// use-cases of PrefixDiscarded, but it may prove tricky.
func PrefixDiscarded[Ta, Tb any](prefixSym Symbol[Ta], sym Symbol[Tb]) Symbol[Tb] {
	return &symbol[Tb]{
		sym,
		func(rr Reader) (Tb, error) {
			var zero Tb
			if _, err := prefixSym.Decode(rr); err != nil {
				return zero, err
			}
			return sym.Decode(rr)
		},
	}
}

// Suffixed matchs on sym and then suffixSym, returning the value produced by
// sym and discarding the one produced by suffixSym.
//
// If sym does not match then Suffixed does not match. If sym matches but
// suffixSym does not also match then Suffixed produces a LocatedError.
func Suffixed[Ta, Tb any](sym Symbol[Ta], suffixSym Symbol[Tb]) Symbol[Ta] {
	return named(sym, Reduction(sym, suffixSym, func(a Ta, _ Tb) Ta {
		return a
	}))
}

// Discard matches if the given Symbol does, but discards the value it produces,
// producing an empty value instead.
func Discard[T any](sym Symbol[T]) Symbol[struct{}] {
	return Mapping(sym, func(T) struct{} { return struct{}{} })
}