ginger/gg/decoder.go

package gg

import (
	"fmt"
	"io"
	"strconv"
	"unicode"

	. "code.betamike.com/mediocregopher/ginger/gg/grammar"
	"code.betamike.com/mediocregopher/ginger/graph"
	"golang.org/x/exp/slices"
)

var (
	notNewline = RuneFunc(
		"not-newline", func(r rune) bool { return r != '\n' },
	)

	comment = Prefixed(
		Prefixed(Rune('*'), ZeroOrMore(notNewline)), Rune('\n'),
	)

	whitespace = ZeroOrMore(FirstOf(
		Discard(RuneFunc("whitespace", unicode.IsSpace)),
		Discard(comment),
	))
)

func trimmed[T any](sym Symbol[T]) Symbol[T] {
	sym = PrefixDiscarded(whitespace, sym)
	sym = Suffixed(sym, whitespace)
	return sym
}

func trimmedRune(r rune) Symbol[Located[rune]] {
	return trimmed(Rune(r))
}

var (
	digit = RuneFunc(
		"digit", func(r rune) bool { return '0' <= r && r <= '9' },
	)

	positiveNumber = StringFromRunes(OneOrMore(digit))

	negativeNumber = Reduction(
		Rune('-'),
		positiveNumber,
		func(neg Located[rune], posNum Located[string]) Located[string] {
			return Locate(neg.Location, string(neg.Value)+posNum.Value)
		},
	)

	number = Named(
		"number",
		Mapping(
			FirstOf(negativeNumber, positiveNumber),
			func(str Located[string]) Located[Value] {
				i, err := strconv.ParseInt(str.Value, 10, 64)
				if err != nil {
					panic(fmt.Errorf("parsing %q as int: %w", str, err))
				}

				return Locate(str.Location, Number(i))
			},
		),
	)
)

var (
	nameHead = FirstOf(
		RuneFunc("letter", unicode.IsLetter),
		RuneFunc("mark", unicode.IsMark),
		Rune('!'),
	)

	nameTail = ZeroOrMore(FirstOf(nameHead, digit))

	name = Named(
		"name",
		Reduction(
			nameHead,
			nameTail,
			func(head Located[rune], tail []Located[rune]) Located[Value] {
				name := make([]rune, 0, len(tail)+1)
				name = append(name, head.Value)
				for _, r := range tail {
					name = append(name, r.Value)
				}
				return Locate(head.Location, Name(string(name)))
			},
		),
	)
)

func openEdgeIntoValue(val Value, oe *OpenEdge) *OpenEdge {
	switch {
	case oe == nil:
		return graph.ValueOut(None, val)
	case !oe.EdgeValue().Valid:
		return oe.WithEdgeValue(Some(val))
	default:
		return graph.TupleOut(Some(val), oe)
	}
}

var graphSym, value = func() (
	Symbol[Located[Value]], Symbol[Located[Value]],
) {

	type tupleState struct {
		ins []*OpenEdge
		oe  *OpenEdge
	}

	type graphState struct {
		g  *Graph
		oe *OpenEdge
	}

	var (
		tupleEnd = Mapping(
			trimmedRune(')'),
			func(Located[rune]) tupleState {
				// if ')', then map that to an empty state. This acts as a
				// sentinel value to indicate "end of tuple".
				return tupleState{}
			},
		)

		graphEnd = Mapping(
			trimmedRune('}'),
			func(Located[rune]) graphState {
				// if '}', then map that to an empty state. This acts as a
				// sentinel value to indicate "end of graph".
				return graphState{}
			},
		)
	)

	var (
		// pre-define these, and then fill in the pointers after, in order to
		// deal with recursive dependencies between them.
		value = new(SymbolPtr[Located[Value]])

		tuple                  = new(SymbolPtr[*OpenEdge])
		tupleTail              = new(SymbolPtr[tupleState])
		tupleOpenEdge          = new(SymbolPtr[tupleState])
		tupleOpenEdgeTail      = new(SymbolPtr[tupleState])
		tupleOpenEdgeValueTail = new(SymbolPtr[tupleState])

		graphSym               = new(SymbolPtr[Located[Value]])
		graphTail              = new(SymbolPtr[graphState])
		graphOpenEdge          = new(SymbolPtr[graphState])
		graphOpenEdgeTail      = new(SymbolPtr[graphState])
		graphOpenEdgeValueTail = new(SymbolPtr[graphState])
	)

	tuple.Symbol = Named(
		"tuple",
		Reduction[Located[rune], tupleState, *OpenEdge](
			trimmedRune('('),
			tupleTail,
			func(_ Located[rune], ts tupleState) *OpenEdge {
				slices.Reverse(ts.ins)
				return graph.TupleOut(None, ts.ins...)
			},
		),
	)

	tupleTail.Symbol = FirstOf(
		tupleEnd,
		Mapping[tupleState, tupleState](
			tupleOpenEdge,
			func(ts tupleState) tupleState {
				ts.ins = append(ts.ins, ts.oe)
				ts.oe = nil
				return ts
			},
		),
	)

	tupleOpenEdge.Symbol = FirstOf(
		Reduction[Located[Value], tupleState, tupleState](
			value,
			tupleOpenEdgeValueTail,
			func(val Located[Value], ts tupleState) tupleState {
				ts.oe = openEdgeIntoValue(val.Value, ts.oe)
				return ts
			},
		),
		Reduction[*OpenEdge, tupleState, tupleState](
			tuple,
			tupleOpenEdgeTail,
			func(oe *OpenEdge, ts tupleState) tupleState {
				ts.oe = oe
				return ts
			},
		),
	)

	tupleOpenEdgeTail.Symbol = FirstOf(
		tupleEnd,
		Prefixed[Located[rune], tupleState](trimmedRune(','), tupleTail),
	)

	tupleOpenEdgeValueTail.Symbol = FirstOf[tupleState](
		tupleOpenEdgeTail,
		Prefixed[Located[rune], tupleState](trimmedRune('<'), tupleOpenEdge),
	)

	graphSym.Symbol = Named(
		"graph",
		Reduction[Located[rune], graphState, Located[Value]](
			trimmedRune('{'),
			graphTail,
			func(r Located[rune], gs graphState) Located[Value] {
				if gs.g == nil {
					gs.g = new(Graph)
				}

				return Locate(r.Location, Value{Graph: gs.g})
			},
		),
	)

	graphTail.Symbol = FirstOf(
		graphEnd,
		Reduction(
			name,
			Prefixed[Located[rune], graphState](
				trimmedRune('='), graphOpenEdge,
			),
			func(name Located[Value], gs graphState) graphState {
				if gs.g == nil {
					gs.g = new(Graph)
				}

				gs.g = gs.g.AddValueIn(name.Value, gs.oe)
				gs.oe = nil
				return gs
			},
		),
	)

	graphOpenEdge.Symbol = FirstOf(
		Reduction[Located[Value], graphState, graphState](
			value,
			graphOpenEdgeValueTail,
			func(val Located[Value], gs graphState) graphState {
				gs.oe = openEdgeIntoValue(val.Value, gs.oe)
				return gs
			},
		),
		Reduction[*OpenEdge, graphState, graphState](
			tuple,
			graphOpenEdgeTail,
			func(oe *OpenEdge, gs graphState) graphState {
				gs.oe = oe
				return gs
			},
		),
	)

	graphOpenEdgeTail.Symbol = FirstOf(
		graphEnd,
		Prefixed[Located[rune], graphState](trimmedRune(';'), graphTail),
	)

	graphOpenEdgeValueTail.Symbol = FirstOf[graphState](
		graphOpenEdgeTail,
		Prefixed[Located[rune], graphState](trimmedRune('<'), graphOpenEdge),
	)

	value.Symbol = trimmed(FirstOf[Located[Value]](name, number, graphSym))

	return graphSym, value
}()

// Decoder reads Values off of an io.Reader, or return io.EOF.
type Decoder interface {
	Next() (Located[Value], error)
}

type decoder struct {
	r Reader
}

// NewDecoder returns a Decoder which reads off the given io.Reader. The
// io.Reader should not be read from after this call.
func NewDecoder(r io.Reader) Decoder {
	return &decoder{r: NewReader(r)}
}

func (d *decoder) Next() (Located[Value], error) {
	return value.Decode(d.r)
}