gg: rename Walk to Iter, and implement Disjoin

gg/gg.go

@@ -8,22 +8,6 @@ import (
 	"strings"
 )
 
-// TODO it's a bit unfortunate that it's possible to create disjointed graphs
-// within the same graph instance. That's not really something that would be
-// possible with any other type of datastructure. I think all that would be
-// needed to get rid of this is to remove the Null instance and instead do a
-// New(value) function. This would allow a graph to be just a single value with
-// no edges, but I _think_ that's fine?
-//
-// Actually, that's kinda bogus, it really messes with how I conceptualized
-// ginger being used. Which is maybe fine. I should do some research on the
-// typical way that graphs and other structures are defined.
-//
-// It seems that disjoint unions, as they're called, are an accepted thing... if
-// I need it for gim a Disjoin method might be the best bet, which would walk
-// through the Graph and compute each disjointed Graph and return them
-// individually.
-
 // Value wraps a go value in a way such that it will be uniquely identified
 // within any Graph and between Graphs. Use NewValue to create a Value instance.
 // You can create an instance manually as long as ID is globally unique.
@@ -173,7 +157,7 @@ func (g *Graph) cp() *Graph {
 ////////////////////////////////////////////////////////////////////////////////
 // Graph creation
 
-func mkVertex(typ VertexType, val Value, ins []OpenEdge) vertex {
+func mkVertex(typ VertexType, val Value, ins ...OpenEdge) vertex {
 	v := vertex{VertexType: typ, in: ins}
 	switch typ {
 	case ValueVertex:
@@ -199,7 +183,7 @@ func mkVertex(typ VertexType, val Value, ins []OpenEdge) vertex {
 // multiple ValueOut OpenEdges constructed with the same val will be leaving the
 // same Vertex instance in the constructed Graph.
 func ValueOut(val, edgeVal Value) OpenEdge {
-	return OpenEdge{fromV: mkVertex(ValueVertex, val, nil), val: edgeVal}
+	return OpenEdge{fromV: mkVertex(ValueVertex, val), val: edgeVal}
 }
 
 // JunctionOut creates a OpenEdge which, when used to construct a Graph,
@@ -209,9 +193,9 @@ func ValueOut(val, edgeVal Value) OpenEdge {
 // When constructing Graphs Junction vertices are de-duplicated on their input
 // edges. So multiple Junction OpenEdges constructed with the same set of input
 // edges will be leaving the same Junction instance in the constructed Graph.
-func JunctionOut(in []OpenEdge, edgeVal Value) OpenEdge {
+func JunctionOut(ins []OpenEdge, edgeVal Value) OpenEdge {
 	return OpenEdge{
-		fromV: mkVertex(JunctionVertex, Value{}, in),
+		fromV: mkVertex(JunctionVertex, Value{}, ins...),
 		val:   edgeVal,
 	}
 }
@@ -221,7 +205,7 @@ func JunctionOut(in []OpenEdge, edgeVal Value) OpenEdge {
 // referenced within toe OpenEdge which do not yet exist in the Graph will also
 // be created in this step.
 func (g *Graph) AddValueIn(oe OpenEdge, val Value) *Graph {
-	to := mkVertex(ValueVertex, val, nil)
+	to := mkVertex(ValueVertex, val)
 	toID := to.id
 
 	// if to is already in the graph, pull it out, as it might have existing in
@@ -269,7 +253,7 @@ func (g *Graph) AddValueIn(oe OpenEdge, val Value) *Graph {
 // OpenEdge, no changes are made. Any vertices referenced by toe OpenEdge for
 // which that edge is their only outgoing edge will be removed from the Graph.
 func (g *Graph) DelValueIn(oe OpenEdge, val Value) *Graph {
-	to := mkVertex(ValueVertex, val, nil)
+	to := mkVertex(ValueVertex, val)
 	toID := to.id
 
 	// pull to out of the graph. if it's not there then bail
@@ -343,6 +327,8 @@ func (g *Graph) DelValueIn(oe OpenEdge, val Value) *Graph {
 // Union takes in another Graph and returns a new one which is the union of the
 // two. Value vertices which are shared between the two will be merged so that
 // the new vertex has the input edges of both.
+//
+// TODO it bothers me that the opposite of Disjoin is Union and not "Join"
 func (g *Graph) Union(g2 *Graph) *Graph {
 	g = g.cp()
 	for vID, v2 := range g2.vM {
@@ -361,6 +347,80 @@ func (g *Graph) Union(g2 *Graph) *Graph {
 	return g
 }
 
+// Disjoin splits the Graph into as many independently connected Graphs as it
+// contains. Each Graph returned will have vertices connected only within itself
+// and not across to the other Graphs, and the Union of all returned Graphs will
+// be the original again.
+//
+// The order of the Graphs returned is not deterministic.
+//
+// Null.Disjoin() returns empty slice.
+func (g *Graph) Disjoin() []*Graph {
+	m := map[string]*Graph{}    // maps each id to the Graph it belongs to
+	mG := map[*Graph]struct{}{} // tracks unique Graphs created
+
+	var connectedTo func(vertex) *Graph
+	connectedTo = func(v vertex) *Graph {
+		if v.VertexType == ValueVertex {
+			if g := m[v.id]; g != nil {
+				return g
+			}
+		}
+		for _, oe := range v.in {
+			if g := connectedTo(oe.fromV); g != nil {
+				return g
+			}
+		}
+		return nil
+	}
+
+	// used upon finding out that previously-thought-to-be disconnected vertices
+	// aren't. Merges the two graphs they're connected into together into one
+	// and updates all state internal to this function accordingly.
+	rejoin := func(gDst, gSrc *Graph) {
+		for id, v := range gSrc.vM {
+			gDst.vM[id] = v
+			m[id] = gDst
+		}
+		delete(mG, gSrc)
+	}
+
+	var connectTo func(vertex, *Graph)
+	connectTo = func(v vertex, g *Graph) {
+		if v.VertexType == ValueVertex {
+			if g2, ok := m[v.id]; ok && g != g2 {
+				rejoin(g, g2)
+			}
+			m[v.id] = g
+		}
+		for _, oe := range v.in {
+			connectTo(oe.fromV, g)
+		}
+	}
+
+	for id, v := range g.vM {
+		gV := connectedTo(v)
+
+		// if gV is nil it means this vertex is part of a new Graph which
+		// nothing else has been connected to yet.
+		if gV == nil {
+			gV = Null.cp()
+			mG[gV] = struct{}{}
+		}
+		gV.vM[id] = v
+
+		// do this no matter what, because we want to descend in to the in edges
+		// and mark all of those as being part of this graph too
+		connectTo(v, gV)
+	}
+
+	gg := make([]*Graph, 0, len(mG))
+	for g := range mG {
+		gg = append(gg, g)
+	}
+	return gg
+}
+
 ////////////////////////////////////////////////////////////////////////////////
 // Graph traversal
 
@@ -454,12 +514,10 @@ func Equal(g1, g2 *Graph) bool {
 // TODO Walk, but by edge
 // TODO Walk, but without end. AKA FSM
 
-// Walk will traverse the Graph, calling the callback on every Vertex in the
-// Graph once. If startWith is non-nil then that Vertex will be the first one
-// passed to the callback and used as the starting point of the traversal. If
-// the callback returns false the traversal is stopped.
-func (g *Graph) Walk(startWith *Vertex, callback func(*Vertex) bool) {
-	// TODO figure out how to make Walk deterministic?
+// Iter will iterate through the Graph's vertices, calling the callback on every
+// Vertex in the Graph once. The vertex order used is non-deterministic.  If the
+// callback returns false the iteration is stopped.
+func (g *Graph) Iter(callback func(*Vertex) bool) {
 	g.makeView()
 	if len(g.byVal) == 0 {
 		return
@@ -482,12 +540,6 @@ func (g *Graph) Walk(startWith *Vertex, callback func(*Vertex) bool) {
 		return true
 	}
 
-	if startWith != nil {
-		if !innerWalk(startWith) {
-			return
-		}
-	}
-
 	for _, v := range g.byVal {
 		if !innerWalk(v) {
 			return

gg/gg_test.go

@@ -1,6 +1,9 @@
 package gg
 
 import (
+	"fmt"
+	"sort"
+	"strings"
 	. "testing"
 
 	"github.com/stretchr/testify/assert"
@@ -54,10 +57,10 @@ func assertVertexEqual(t *T, exp, got *Vertex, msgAndArgs ...interface{}) bool {
 	return assertInner(exp, got, map[*Vertex]bool{})
 }
 
-func assertWalk(t *T, expVals, expJuncs int, g *Graph, msgAndArgs ...interface{}) {
+func assertIter(t *T, expVals, expJuncs int, g *Graph, msgAndArgs ...interface{}) {
 	seen := map[*Vertex]bool{}
 	var gotVals, gotJuncs int
-	g.Walk(nil, func(v *Vertex) bool {
+	g.Iter(func(v *Vertex) bool {
 		assert.NotContains(t, seen, v, msgAndArgs...)
 		seen[v] = true
 		if v.VertexType == ValueVertex {
@@ -277,8 +280,8 @@ func TestGraph(t *T) {
 		// sanity check that graphs are equal to themselves
 		assert.True(t, Equal(out, out), msgAndArgs...)
 
-		// test the Walk method in here too
-		assertWalk(t, tests[i].numVals, tests[i].numJuncs, out, msgAndArgs...)
+		// test the Iter method in here too
+		assertIter(t, tests[i].numVals, tests[i].numJuncs, out, msgAndArgs...)
 	}
 }
 
@@ -407,6 +410,61 @@ func TestGraphDelValueIn(t *T) {
 	}
 }
 
+// deterministically hashes a Graph
+func graphStr(g *Graph) string {
+	var vStr func(vertex) string
+	var oeStr func(OpenEdge) string
+	vStr = func(v vertex) string {
+		if v.VertexType == ValueVertex {
+			return fmt.Sprintf("v:%q\n", v.val.V.(string))
+		}
+		s := fmt.Sprintf("j:%d\n", len(v.in))
+		ssOE := make([]string, len(v.in))
+		for i := range v.in {
+			ssOE[i] = oeStr(v.in[i])
+		}
+		sort.Strings(ssOE)
+		return s + strings.Join(ssOE, "")
+	}
+	oeStr = func(oe OpenEdge) string {
+		s := fmt.Sprintf("oe:%q\n", oe.val.V.(string))
+		return s + vStr(oe.fromV)
+	}
+	sVV := make([]string, 0, len(g.vM))
+	for _, v := range g.vM {
+		sVV = append(sVV, vStr(v))
+	}
+	sort.Strings(sVV)
+	return strings.Join(sVV, "")
+}
+
+func assertEqualSets(t *T, exp, got []*Graph) bool {
+	if !assert.Equal(t, len(exp), len(got)) {
+		return false
+	}
+
+	m := map[*Graph]string{}
+	for _, g := range exp {
+		m[g] = graphStr(g)
+	}
+	for _, g := range got {
+		m[g] = graphStr(g)
+	}
+
+	sort.Slice(exp, func(i, j int) bool {
+		return m[exp[i]] < m[exp[j]]
+	})
+	sort.Slice(got, func(i, j int) bool {
+		return m[got[i]] < m[got[j]]
+	})
+
+	b := true
+	for i := range exp {
+		b = b || assert.True(t, Equal(exp[i], got[i]), "i:%d exp:%q got:%q", i, m[exp[i]], m[got[i]])
+	}
+	return b
+}
+
 func TestGraphUnion(t *T) {
 	assertUnion := func(g1, g2 *Graph) *Graph {
 		ga := g1.Union(g2)
@@ -415,6 +473,11 @@ func TestGraphUnion(t *T) {
 		return ga
 	}
 
+	assertDisjoin := func(g *Graph, exp ...*Graph) {
+		ggDisj := g.Disjoin()
+		assertEqualSets(t, exp, ggDisj)
+	}
+
 	v0 := NewValue("v0")
 	v1 := NewValue("v1")
 	e0 := NewValue("e0")
@@ -423,6 +486,8 @@ func TestGraphUnion(t *T) {
 
 		g := Null.AddValueIn(ValueOut(v0, e0), v1)
 		assert.True(t, Equal(g, assertUnion(g, Null)))
+
+		assertDisjoin(g, g)
 	}
 
 	v2 := NewValue("v2")
@@ -436,6 +501,8 @@ func TestGraphUnion(t *T) {
 		assertVertexEqual(t, value(v1, edge(e0, value(v0))), g.ValueVertex(v1))
 		assertVertexEqual(t, value(v2), g.ValueVertex(v2))
 		assertVertexEqual(t, value(v3, edge(e1, value(v2))), g.ValueVertex(v3))
+
+		assertDisjoin(g, g0, g1)
 	}
 
 	va0, vb0 := NewValue("va0"), NewValue("vb0")
@@ -470,6 +537,8 @@ func TestGraphUnion(t *T) {
 				edge(eb1, value(vb1)))),
 			g.ValueVertex(vb2),
 		)
+
+		assertDisjoin(g, ga, gb)
 	}
 
 	{ // Two partially overlapping graphs
@@ -485,6 +554,8 @@ func TestGraphUnion(t *T) {
 			),
 			g.ValueVertex(v2),
 		)
+
+		assertDisjoin(g, g)
 	}
 
 	ej0 := NewValue("ej0")
@@ -508,6 +579,8 @@ func TestGraphUnion(t *T) {
 			),
 			g.ValueVertex(v2),
 		)
+
+		assertDisjoin(g, g)
 	}
 
 	{ // Two equal graphs

gg/json.go

@@ -172,7 +172,7 @@ func (jm jsonUnmarshaler) UnmarshalJSON(b []byte) error {
 				return vertex{}, err
 			}
 		}
-		return mkVertex(vJ.Type, val, ins), nil
+		return mkVertex(vJ.Type, val, ins...), nil
 	}
 
 	for _, v := range gJ.ValueVertices {

gim/constraint/constraint.go

@@ -87,7 +87,7 @@ func (e *Engine) Solve() map[string]int {
 	// first the roots are determined to be the elements with no In edges, which
 	// _must_ exist since the graph presumably has no loops
 	var roots []*gg.Vertex
-	e.g.Walk(nil, func(v *gg.Vertex) bool {
+	e.g.Iter(func(v *gg.Vertex) bool {
 		if len(v.In) == 0 {
 			roots = append(roots, v)
 			m[vElem(v)] = 0