This commit is contained in:
Brian Picciano 2023-10-21 17:42:31 +02:00
parent 21c91731e9
commit e113e96f1f
6 changed files with 847 additions and 0 deletions

73
gg/v2/decoder.go Normal file
View File

@ -0,0 +1,73 @@
package gg
import (
"bufio"
"fmt"
"io"
)
// Decoder reads Value's off of a byte stream.
type Decoder struct {
br *bufio.Reader
brNextLoc Location
unread []locatableRune
lastRead locatableRune
}
// NewDecoder returns a Decoder which will decode the given stream as a gg
// formatted stream of a Values.
func NewDecoder(r io.Reader) *Decoder {
return &Decoder{
br: bufio.NewReader(r),
brNextLoc: Location{Row: 1, Col: 1},
}
}
func (d *Decoder) readRune() (locatableRune, error) {
if len(d.unread) > 0 {
d.lastRead = d.unread[len(d.unread)-1]
d.unread = d.unread[:len(d.unread)-1]
return d.lastRead, nil
}
loc := d.brNextLoc
r, _, err := d.br.ReadRune()
if err != nil {
return d.lastRead, err
}
if r == '\n' {
d.brNextLoc.Row++
d.brNextLoc.Col = 1
} else {
d.brNextLoc.Col++
}
d.lastRead = locatableRune{loc, r}
return d.lastRead, nil
}
func (d *Decoder) unreadRune(lr locatableRune) {
if d.lastRead != lr {
panic(fmt.Sprintf(
"unreading rune %#v, but last read rune was %#v", lr, d.lastRead,
))
}
d.unread = append(d.unread, lr)
}
func (d *Decoder) nextLoc() Location {
if len(d.unread) > 0 {
return d.unread[len(d.unread)-1].Location
}
return d.brNextLoc
}
// Next returns the next top-level value in the stream, or io.EOF.
func (d *Decoder) Next() (Value, error) {
panic("TODO")
}

24
gg/v2/gg.bnf Normal file
View File

@ -0,0 +1,24 @@
<digit> ::= "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
<positive-number> ::= <digit>+
<negative-number> ::= "-" <positive-number>
<number> ::= <negative-number> | <positive-number>
<name> ::= (<letter> | <mark>) (<letter> | <mark> | <digit>)*
<value> ::= <name> | <number> | <tuple> | <graph>
<tuple> ::= "(" <tuple-tail>
<tuple-tail> ::= ")" | <value> <tuple-post-value>
<tuple-post-value> ::= ")"
| "," <tuple-tail>
| "<" <value> <tuple-post-value>
<graph> ::= "{" <graph-tail>
<graph-tail> ::= "}" | <name> "=" <graph-open-edge>
<graph-open-edge> ::= <value> <graph-open-edge-tail>
<graph-open-edge-tail> ::= "}"
| ";" <graph-tail>
| "<" <graph-open-edge>
<top-level-value> ::= <name> | <number> | <graph>
<gg> ::= <eof> | <top-level-value> <gg>

116
gg/v2/gg.go Normal file
View File

@ -0,0 +1,116 @@
// Package gg implements graph serialization to/from the gg text format.
package gg
import (
"fmt"
"github.com/mediocregopher/ginger/graph"
)
// Type aliases for convenience
type (
Graph = graph.Graph[OptionalValue, Value]
OpenEdge = graph.OpenEdge[OptionalValue, Value]
)
// Value represents a value which can be serialized by the gg text format.
type Value struct {
Location
// Only one of these fields may be set
Name *string
Number *int64
Graph *Graph
}
// Name returns a name Value.
func Name(name string) Value {
return Value{Name: &name}
}
// Number returns a number Value.
func Number(n int64) Value {
return Value{Number: &n}
}
// Equal returns true if the passed in Value is equivalent, ignoring the
// LexerToken on either Value.
//
// Will panic if the passed in v2 is not a Value from this package.
func (v Value) Equal(v2g graph.Value) bool {
v2 := v2g.(Value)
switch {
case v.Name != nil && v2.Name != nil && *v.Name == *v2.Name:
return true
case v.Number != nil && v2.Number != nil && *v.Number == *v2.Number:
return true
case v.Graph != nil && v2.Graph != nil && v.Graph.Equal(v2.Graph):
return true
default:
return false
}
}
func (v Value) String() string {
switch {
case v.Name != nil:
return *v.Name
case v.Number != nil:
return fmt.Sprint(*v.Number)
case v.Graph != nil:
return v.Graph.String()
default:
panic("no fields set on Value")
}
}
// OptionalValue is a Value which may be unset. This is used for edge values,
// since edges might not have a value.
type OptionalValue struct {
Value
Valid bool
}
// None is the zero OptionalValue (hello rustaceans).
var None OptionalValue
// Some wraps a Value to be an OptionalValue.
func Some(v Value) OptionalValue {
return OptionalValue{Valid: true, Value: v}
}
func (v OptionalValue) String() string {
if !v.Valid {
return "<none>"
}
return v.Value.String()
}
func (v OptionalValue) Equal(v2g graph.Value) bool {
var v2 OptionalValue
if v2Val, ok := v2g.(Value); ok {
v2 = Some(v2Val)
} else {
v2 = v2g.(OptionalValue)
}
if v.Valid != v2.Valid {
return false
} else if !v.Valid {
return true
}
return v.Value.Equal(v2.Value)
}

49
gg/v2/location.go Normal file
View File

@ -0,0 +1,49 @@
package gg
import "fmt"
// Location indicates a position in a stream of bytes identified by column
// within newline-separated rows.
type Location struct {
Row, Col int
}
func (l Location) errf(str string, args ...any) LocatedError {
return LocatedError{l, fmt.Errorf(str, args...)}
}
func (l Location) locate() Location { return l }
// LocatedError is an error related to a specific point within a decode gg
// stream.
type LocatedError struct {
Location
Err error
}
func (e LocatedError) Error() string {
return fmt.Sprintf("%d:%d: %v", e.Row, e.Col, e.Err)
}
type locatable interface {
locate() Location
}
type locatableRune struct {
Location
r rune
}
type locatableString struct {
Location
str string
}
type locatableSlice[T locatable] []T
func (s locatableSlice[T]) locate() Location {
if len(s) == 0 {
panic("can't locate empty locatableSlice")
}
return s[0].locate()
}

365
gg/v2/term.go Normal file
View File

@ -0,0 +1,365 @@
package gg
import (
"errors"
"fmt"
"io"
"strconv"
"strings"
"unicode"
"github.com/mediocregopher/ginger/graph"
)
var (
errNoMatch = errors.New("not found")
)
type stringerFn func() string
func (fn stringerFn) String() string {
return fn()
}
type stringerStr string
func (str stringerStr) String() string {
return string(str)
}
type term[T locatable] struct {
name fmt.Stringer
decodeFn func(d *Decoder) (T, error)
}
func (t term[T]) String() string {
return t.name.String()
}
func firstOf[T locatable](terms ...*term[T]) *term[T] {
if len(terms) < 2 {
panic("firstOfTerms requires at least 2 terms")
}
return &term[T]{
name: stringerFn(func() string {
descrs := make([]string, len(terms))
for i := range terms {
descrs[i] = terms[i].String()
}
return strings.Join(descrs, " or ")
}),
decodeFn: func(d *Decoder) (T, error) {
var zero T
for _, t := range terms {
v, err := t.decodeFn(d)
if errors.Is(err, errNoMatch) {
continue
} else if err != nil {
return zero, err
}
return v, nil
}
return zero, errNoMatch
},
}
}
func seq[Ta, Tb, Tc locatable](
name fmt.Stringer,
termA *term[Ta],
termB *term[Tb],
fn func(Ta, Tb) (Tc, error),
) *term[Tc] {
return &term[Tc]{
name: name,
decodeFn: func(d *Decoder) (Tc, error) {
var zero Tc
va, err := termA.decodeFn(d)
if err != nil {
return zero, err
}
vb, err := termB.decodeFn(d)
if errors.Is(err, errNoMatch) {
return zero, d.nextLoc().errf("expected %v", termB)
} else if err != nil {
return zero, err
}
vc, err := fn(va, vb)
if err != nil {
return zero, err
}
return vc, nil
},
}
}
func matchAndSkip[Ta, Tb locatable](
termA *term[Ta], termB *term[Tb],
) *term[Tb] {
return seq(termA, termA, termB, func(_ Ta, b Tb) (Tb, error) {
return b, nil
})
}
func oneOrMore[T locatable](t *term[T]) *term[locatableSlice[T]] {
return &term[locatableSlice[T]]{
name: stringerFn(func() string {
return fmt.Sprintf("one or more %v", t)
}),
decodeFn: func(d *Decoder) (locatableSlice[T], error) {
var vv []T
for {
v, err := t.decodeFn(d)
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
},
}
}
func zeroOrMore[T locatable](t *term[T]) *term[locatableSlice[T]] {
return &term[locatableSlice[T]]{
name: stringerFn(func() string {
return fmt.Sprintf("zero or more %v", t)
}),
decodeFn: func(d *Decoder) (locatableSlice[T], error) {
var vv []T
for {
v, err := t.decodeFn(d)
if errors.Is(err, errNoMatch) {
break
} else if err != nil {
return nil, err
}
vv = append(vv, v)
}
return vv, nil
},
}
}
func mapTerm[Ta locatable, Tb locatable](
name fmt.Stringer, t *term[Ta], fn func(Ta) Tb,
) *term[Tb] {
return &term[Tb]{
name: name,
decodeFn: func(d *Decoder) (Tb, error) {
var zero Tb
va, err := t.decodeFn(d)
if err != nil {
return zero, err
}
return fn(va), nil
},
}
}
func runePredTerm(
name fmt.Stringer, pred func(rune) bool,
) *term[locatableRune] {
return &term[locatableRune]{
name: name,
decodeFn: func(d *Decoder) (locatableRune, error) {
lr, err := d.readRune()
if errors.Is(err, io.EOF) {
return locatableRune{}, errNoMatch
} else if err != nil {
return locatableRune{}, err
}
if !pred(lr.r) {
d.unreadRune(lr)
return locatableRune{}, errNoMatch
}
return lr, nil
},
}
}
func runeTerm(r rune) *term[locatableRune] {
return runePredTerm(
stringerStr(fmt.Sprintf("'%c'", r)),
func(r2 rune) bool { return r2 == r },
)
}
func locatableRunesToString(rr locatableSlice[locatableRune]) string {
str := make([]rune, len(rr))
for i := range rr {
str[i] = rr[i].r
}
return string(str)
}
func runesToStringTerm(
t *term[locatableSlice[locatableRune]],
) *term[locatableString] {
return mapTerm(
t, t, func(rr locatableSlice[locatableRune]) locatableString {
return locatableString{rr.locate(), locatableRunesToString(rr)}
},
)
}
var (
digitTerm = runePredTerm(
stringerStr("digit"),
func(r rune) bool { return '0' <= r && r <= '9' },
)
positiveNumberTerm = runesToStringTerm(oneOrMore(digitTerm))
negativeNumberTerm = seq(
stringerStr("negative-number"),
runeTerm('-'),
positiveNumberTerm,
func(neg locatableRune, posNum locatableString) (locatableString, error) {
return locatableString{
neg.locate(), string(neg.r) + posNum.str,
}, nil
},
)
numberTerm = mapTerm(
stringerStr("number"),
firstOf(negativeNumberTerm, positiveNumberTerm),
func(str locatableString) Value {
i, err := strconv.ParseInt(str.str, 10, 64)
if err != nil {
panic(fmt.Errorf("parsing %q as int: %w", str, err))
}
return Value{Number: &i, Location: str.locate()}
},
)
)
var (
letterTerm = runePredTerm(
stringerStr("letter"),
func(r rune) bool {
return unicode.In(r, unicode.Letter, unicode.Mark)
},
)
letterTailTerm = zeroOrMore(firstOf(letterTerm, digitTerm))
nameTerm = seq(
stringerStr("name"),
letterTerm,
letterTailTerm,
func(head locatableRune, tail locatableSlice[locatableRune]) (Value, error) {
name := string(head.r) + locatableRunesToString(tail)
return Value{Name: &name, Location: head.locate()}, nil
},
)
)
var graphTerm = func() *term[Value] {
type graphState struct {
Location // location of last place graphState was updated
g *Graph
oe *OpenEdge
}
var (
// pre-define these, and then fill in the pointers after, in order to
// deal with recursive dependencies between them.
graphTerm = new(term[Value])
graphTailTerm = new(term[graphState])
graphOpenEdgeTerm = new(term[graphState])
graphOpenEdgeTailTerm = new(term[graphState])
valueTerm = new(term[Value])
rightCurlyBrace = runeTerm('}')
graphEndTerm = mapTerm(
rightCurlyBrace,
rightCurlyBrace, func(lr locatableRune) graphState {
// if '}', then map that to an empty state. This acts as a
// sentinel value to indicate "end of graph".
return graphState{Location: lr.locate()}
},
)
)
*graphTerm = *seq(
stringerStr("graph"),
runeTerm('{'),
graphTailTerm,
func(lr locatableRune, gs graphState) (Value, error) {
if gs.g == nil {
gs.g = new(Graph)
}
return Value{Graph: gs.g, Location: lr.locate()}, nil
},
)
*graphTailTerm = *firstOf(
graphEndTerm,
seq(
nameTerm,
nameTerm,
matchAndSkip(runeTerm('='), graphOpenEdgeTailTerm),
func(name Value, gs graphState) (graphState, error) {
if gs.g == nil {
gs.g = new(Graph)
}
gs.g = gs.g.AddValueIn(name, gs.oe)
gs.oe = nil
gs.Location = name.locate()
return gs, nil
},
),
)
*graphOpenEdgeTerm = *firstOf(
graphEndTerm,
matchAndSkip(runeTerm(';'), graphTailTerm),
matchAndSkip(runeTerm('<'), graphOpenEdgeTailTerm),
)
*graphOpenEdgeTailTerm = *seq(
valueTerm,
valueTerm,
graphOpenEdgeTerm,
func(val Value, gs graphState) (graphState, error) {
if gs.oe == nil {
gs.oe = graph.ValueOut(None, val)
} else if !gs.oe.EdgeValue().Valid {
gs.oe = gs.oe.WithEdgeValue(Some(val))
} else {
gs.oe = graph.TupleOut(Some(val), gs.oe)
}
gs.Location = val.locate()
return gs, nil
},
)
*valueTerm = *firstOf(nameTerm, numberTerm, graphTerm)
return graphTerm
}()

220
gg/v2/term_test.go Normal file
View File

@ -0,0 +1,220 @@
package gg
import (
"bytes"
"io"
"strconv"
"testing"
"github.com/mediocregopher/ginger/graph"
"github.com/stretchr/testify/assert"
)
func decoderLeftover(d *Decoder) string {
unread := make([]rune, len(d.unread))
for i := range unread {
unread[i] = d.unread[i].r
}
rest, err := io.ReadAll(d.br)
if err != nil {
panic(err)
}
return string(unread) + string(rest)
}
func TestTermDecoding(t *testing.T) {
type test struct {
in string
exp Value
expErr string
leftover string
}
runTests := func(
t *testing.T, name string, term *term[Value], tests []test,
) {
t.Run(name, func(t *testing.T) {
for i, test := range tests {
t.Run(strconv.Itoa(i), func(t *testing.T) {
dec := NewDecoder(bytes.NewBufferString(test.in))
got, err := term.decodeFn(dec)
if test.expErr != "" {
assert.Error(t, err)
assert.Equal(t, test.expErr, err.Error())
} else if assert.NoError(t, err) {
assert.True(t,
test.exp.Equal(got),
"\nexp:%v\ngot:%v", test.exp, got,
)
assert.Equal(t, test.leftover, decoderLeftover(dec))
}
})
}
})
}
expNum := func(row, col int, n int64) Value {
return Value{Number: &n, Location: Location{row, col}}
}
runTests(t, "number", numberTerm, []test{
{in: `0`, exp: expNum(1, 1, 0)},
{in: `100`, exp: expNum(1, 1, 100)},
{in: `-100`, exp: expNum(1, 1, -100)},
{in: `0foo`, exp: expNum(1, 1, 0), leftover: "foo"},
{in: `100foo`, exp: expNum(1, 1, 100), leftover: "foo"},
})
expName := func(row, col int, name string) Value {
return Value{Name: &name, Location: Location{row, col}}
}
expGraph := func(row, col int, g *Graph) Value {
return Value{Graph: g, Location: Location{row, col}}
}
runTests(t, "name", nameTerm, []test{
{in: `a`, exp: expName(1, 1, "a")},
{in: `ab`, exp: expName(1, 1, "ab")},
{in: `ab2c`, exp: expName(1, 1, "ab2c")},
})
runTests(t, "graph", graphTerm, []test{
{in: `{}`, exp: expGraph(1, 1, new(Graph))},
{in: `{`, expErr: `1:2: expected '}' or name`},
{in: `{a}`, expErr: `1:3: expected '='`},
{in: `{a=}`, expErr: `1:4: expected name or number or graph`},
{
in: `{foo=a}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(None, expName(6, 1, "a")),
),
),
},
{in: `{1=a}`, expErr: `1:2: expected '}' or name`},
{in: `{foo=a,}`, expErr: `1:7: expected '}' or ';' or '<'`},
{in: `{foo=a`, expErr: `1:7: expected '}' or ';' or '<'`},
{
in: `{foo=a<b}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(
Some(expName(6, 1, "a")),
expName(8, 1, "b"),
),
),
),
},
{
in: `{foo=a<b<c}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.TupleOut(
Some(expName(6, 1, "a")),
graph.ValueOut(
Some(expName(8, 1, "b")),
expName(10, 1, "c"),
),
),
),
),
},
{
in: `{foo=a<b<c<1}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.TupleOut(
Some(expName(6, 1, "a")),
graph.TupleOut(
Some(expName(8, 1, "b")),
graph.ValueOut(
Some(expName(10, 1, "c")),
expNum(12, 1, 1),
),
),
),
),
),
},
{
in: `{foo=a<b;}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(
Some(expName(6, 1, "a")),
expName(8, 1, "b"),
),
),
),
},
{
in: `{foo=a<b;bar=c}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(
Some(expName(6, 1, "a")),
expName(8, 1, "b"),
),
).
AddValueIn(
expName(10, 1, "bar"),
graph.ValueOut(None, expName(15, 1, "c")),
),
),
},
{
in: `{foo=a<{baz=1};bar=c}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(
Some(expName(6, 1, "a")),
expGraph(8, 1, new(Graph).AddValueIn(
expName(9, 1, "baz"),
graph.ValueOut(None, expNum(13, 1, 1)),
)),
),
).
AddValueIn(
expName(16, 1, "bar"),
graph.ValueOut(None, expName(20, 1, "c")),
),
),
},
{
in: `{foo={baz=1}<a;bar=c}`,
exp: expGraph(
1, 1, new(Graph).
AddValueIn(
expName(2, 1, "foo"),
graph.ValueOut(
Some(expGraph(8, 1, new(Graph).AddValueIn(
expName(9, 1, "baz"),
graph.ValueOut(None, expNum(13, 1, 1)),
))),
expName(6, 1, "a"),
),
).
AddValueIn(
expName(16, 1, "bar"),
graph.ValueOut(None, expName(20, 1, "c")),
),
),
},
})
}