Merge branch 'master' into fix-violation-step-attribution

internal/driver/chrome/driver.go

@@ -193,6 +193,23 @@ func (d *Driver) InputText(_ context.Context, text string) error {
 	)
 }
 
+// EraseText clears the focused field. InputText above already replaces via
+// select-all, so the character count is not needed to bound the deletion.
+func (d *Driver) EraseText(_ context.Context, _ int) error {
+	return chromedp.Run(d.tabCtx,
+		chromedp.ActionFunc(func(ctx context.Context) error {
+			if err := chromedp.Evaluate(`
+				(function() {
+					const el = document.activeElement;
+					if (el && typeof el.select === 'function') el.select();
+				})()`, nil).Do(ctx); err != nil {
+				return err
+			}
+			return input.InsertText("").Do(ctx)
+		}),
+	)
+}
+
 func (d *Driver) Swipe(_ context.Context, fromX, fromY, toX, toY int, duration time.Duration) error {
 	millis := max(duration.Milliseconds(), 50)
 	script := fmt.Sprintf(`

internal/driver/driver.go

@@ -20,6 +20,10 @@ type DeviceDriver interface {
 	DoubleTap(ctx context.Context, x, y int) error
 	DoubleTapSelector(ctx context.Context, selector string) error
 	InputText(ctx context.Context, text string) error
+	// EraseText deletes characterCount characters from the focused field.
+	// The runner calls it before InputText so the verb replaces existing
+	// content instead of appending to it.
+	EraseText(ctx context.Context, characterCount int) error
 	Swipe(ctx context.Context, fromX, fromY, toX, toY int, duration time.Duration) error
 	PressKey(ctx context.Context, key string) error
 	LongPress(ctx context.Context, x, y int) error

internal/driver/mock/mock.go

@@ -19,6 +19,7 @@ const (
 	ActionDoubleTap         ActionKind = "double_tap"
 	ActionDoubleTapSelector ActionKind = "double_tap_selector"
 	ActionInputText         ActionKind = "input_text"
+	ActionEraseText         ActionKind = "erase_text"
 	ActionSwipe             ActionKind = "swipe"
 	ActionPressKey          ActionKind = "press_key"
 	ActionLongPress         ActionKind = "long_press"
@@ -32,19 +33,20 @@ const (
 )
 
 type Action struct {
-	Kind         ActionKind
-	BundleID     string
-	ClearState   bool
-	X, Y         int
-	FromX, FromY int
-	ToX, ToY     int
-	Duration     time.Duration
-	Selector     string
-	Text         string
-	Key          string
-	LogLevel     string
-	LogSince     time.Time
-	Idle         time.Duration
+	Kind           ActionKind
+	BundleID       string
+	ClearState     bool
+	X, Y           int
+	FromX, FromY   int
+	ToX, ToY       int
+	Duration       time.Duration
+	Selector       string
+	Text           string
+	CharacterCount int
+	Key            string
+	LogLevel       string
+	LogSince       time.Time
+	Idle           time.Duration
 }
 
 // Driver is an in-memory Driver implementation for unit tests.
@@ -210,6 +212,14 @@ func (d *Driver) InputText(ctx context.Context, text string) error {
 	return nil
 }
 
+func (d *Driver) EraseText(ctx context.Context, characterCount int) error {
+	if err := d.failure(ActionEraseText); err != nil {
+		return err
+	}
+	d.record(Action{Kind: ActionEraseText, CharacterCount: characterCount})
+	return nil
+}
+
 func (d *Driver) Swipe(ctx context.Context, fromX, fromY, toX, toY int, duration time.Duration) error {
 	if err := d.failure(ActionSwipe); err != nil {
 		return err

internal/driver/sidecar/client.go

@@ -104,14 +104,18 @@ func (c *Client) TapSelector(ctx context.Context, selector string) error {
 	return err
 }
 
-// doubleTapGap is the inter-tap delay for DoubleTap: short enough to land both
-// events inside a sub-100 ms race window, long enough for the sidecar to
-// serialize two MotionEvent streams. The sidecar exposes no native double-tap
-// RPC, so the gesture is two Taps with this gap.
+// doubleTapGap is the inter-tap delay for the selector fallback: short enough
+// to land both events inside a sub-100 ms race window, long enough for the
+// sidecar to serialize two MotionEvent streams.
 const doubleTapGap = 50 * time.Millisecond
 
+// DoubleTap dispatches the native RPC so the backend can land both taps as
+// close together as the platform allows. Composing two Tap round trips from
+// here spreads them by hundreds of milliseconds on iOS, wide enough for
+// navigation to interleave between the taps.
 func (c *Client) DoubleTap(ctx context.Context, x, y int) error {
-	return doubleTap(ctx, func() error { return c.Tap(ctx, x, y) })
+	_, err := c.stub.DoubleTap(ctx, &driverpb.Point{X: int32(x), Y: int32(y)})
+	return err
 }
 
 func (c *Client) DoubleTapSelector(ctx context.Context, selector string) error {
@@ -137,6 +141,11 @@ func (c *Client) InputText(ctx context.Context, text string) error {
 	return err
 }
 
+func (c *Client) EraseText(ctx context.Context, characterCount int) error {
+	_, err := c.stub.EraseText(ctx, &driverpb.EraseTextRequest{CharacterCount: int32(characterCount)})
+	return err
+}
+
 func (c *Client) Swipe(ctx context.Context, fromX, fromY, toX, toY int, duration time.Duration) error {
 	_, err := c.stub.Swipe(ctx, &driverpb.SwipeRequest{
 		From:           &driverpb.Point{X: int32(fromX), Y: int32(fromY)},

internal/hierarchy/hierarchy.go

@@ -75,6 +75,7 @@ type Element struct {
 type Node struct {
 	Element
 	Children []*Node `json:"-"`
+	tree     *Tree
 }
 
 // Tree is a flat collection of every node in a hierarchy dump, in pre-order.
@@ -180,7 +181,7 @@ func Parse(text string) (*Tree, error) {
 }
 
 func walkNode(node *treeNodeJSON, tree *Tree) *Node {
-	n := &Node{Element: *elementFromNode(node)}
+	n := &Node{Element: *elementFromNode(node), tree: tree}
 	tree.Elements = append(tree.Elements, &n.Element)
 	for i := range node.Children {
 		n.Children = append(n.Children, walkNode(&node.Children[i], tree))
@@ -333,69 +334,50 @@ func (t *Tree) FindAllBySelectorPath(path []Selector) []*Node {
 	return t.Root.FindAllBySelectorPath(path)
 }
 
-// Find returns the first Node in this node's subtree (descendants only) matching
-// the string selector. Path queries within the selector are not supported here.
+// Find returns the first Node scoped to this node (descendants, with spatial
+// fallback) matching the string selector. Path queries within the selector are
+// not supported here.
 func (n *Node) Find(selector string) *Node {
-	kind, value, ok := parseSelector(selector)
-	if !ok {
-		return nil
-	}
-	for _, child := range n.Children {
-		if nodes := searchSubtree(child, kind, value); len(nodes) > 0 {
-			return nodes[0]
-		}
-	}
-	return nil
+	return firstNode(n.FindAll(selector))
 }
 
-// FindAll returns all Nodes in this node's subtree (descendants only) matching
-// the string selector.
+// FindAll returns all Nodes scoped to this node (descendants, with spatial
+// fallback) matching the string selector.
 func (n *Node) FindAll(selector string) []*Node {
 	kind, value, ok := parseSelector(selector)
 	if !ok {
 		return nil
 	}
-	var result []*Node
-	for _, child := range n.Children {
-		result = append(result, searchSubtree(child, kind, value)...)
-	}
-	return result
+	return n.scopedNodes(func(element *Element) bool {
+		return match(element, kind, value)
+	})
 }
 
-// FindBySelector returns the first Node in this node's subtree matching sel (AND semantics).
+// FindBySelector returns the first Node scoped to this node matching sel (AND semantics).
 func (n *Node) FindBySelector(sel Selector) *Node {
-	for _, child := range n.Children {
-		if nodes := searchSubtreeBySelector(child, sel); len(nodes) > 0 {
-			return nodes[0]
-		}
-	}
-	return nil
+	return firstNode(n.FindAllBySelector(sel))
 }
 
-// FindAllBySelector returns all Nodes in this node's subtree matching sel (AND semantics).
+// FindAllBySelector returns all Nodes scoped to this node matching sel (AND semantics).
 func (n *Node) FindAllBySelector(sel Selector) []*Node {
-	var result []*Node
-	for _, child := range n.Children {
-		result = append(result, searchSubtreeBySelector(child, sel)...)
-	}
-	return result
+	return n.scopedNodes(func(element *Element) bool {
+		return matchSelector(element, sel)
+	})
 }
 
 // FindBySelectorPath walks a chain of selectors. The first selector is matched
-// against descendants of the receiver; each subsequent selector is matched
-// against descendants of the previous match. Returns the deepest match or nil.
+// in the receiver's scope; each subsequent selector is matched in the scope of
+// the previous match. Returns the deepest match or nil.
 func (n *Node) FindBySelectorPath(path []Selector) *Node {
 	if len(path) == 0 {
 		return nil
 	}
-	for _, child := range n.Children {
-		for _, candidate := range searchSubtreeBySelector(child, path[0]) {
-			if len(path) == 1 {
-				return candidate
-			}
-			if deeper := candidate.FindBySelectorPath(path[1:]); deeper != nil {
-				return deeper
-			}
+	for _, candidate := range n.FindAllBySelector(path[0]) {
+		if len(path) == 1 {
+			return candidate
+		}
+		if deeper := candidate.FindBySelectorPath(path[1:]); deeper != nil {
+			return deeper
 		}
 	}
 	return nil
@@ -407,19 +389,86 @@ func (n *Node) FindAllBySelectorPath(path []Selector) []*Node {
 	if len(path) == 0 {
 		return nil
 	}
+	var result []*Node
+	for _, candidate := range n.FindAllBySelector(path[0]) {
+		if len(path) == 1 {
+			result = append(result, candidate)
+			continue
+		}
+		result = append(result, candidate.FindAllBySelectorPath(path[1:])...)
+	}
+	return result
+}
+
+func firstNode(nodes []*Node) *Node {
+	if len(nodes) == 0 {
+		return nil
+	}
+	return nodes[0]
+}
+
+// scopedNodes returns this node's descendants matching accept, in pre-order.
+// When no descendant matches, nodes spatially contained in this node's bounds
+// are matched instead. Compose on iOS emits a testTag node as an empty leaf
+// sibling of the content it labels rather than as an ancestor, so descendant
+// search under the tagged node finds nothing; bounds containment recovers the
+// intended scope.
+func (n *Node) scopedNodes(accept func(*Element) bool) []*Node {
 	var result []*Node
 	for _, child := range n.Children {
-		for _, candidate := range searchSubtreeBySelector(child, path[0]) {
-			if len(path) == 1 {
-				result = append(result, candidate)
-				continue
-			}
-			result = append(result, candidate.FindAllBySelectorPath(path[1:])...)
+		collectMatches(child, accept, &result)
+	}
+	if len(result) > 0 {
+		return result
+	}
+	for _, candidate := range n.spatialScope() {
+		if accept(&candidate.Element) {
+			result = append(result, candidate)
 		}
 	}
 	return result
 }
 
+func collectMatches(node *Node, accept func(*Element) bool, result *[]*Node) {
+	if accept(&node.Element) {
+		*result = append(*result, node)
+	}
+	for _, child := range node.Children {
+		collectMatches(child, accept, result)
+	}
+}
+
+// spatialScope returns every node in the tree, in pre-order, whose positive
+// bounds lie fully inside this node's bounds, excluding the node itself.
+func (n *Node) spatialScope() []*Node {
+	if n.tree == nil || n.tree.Root == nil {
+		return nil
+	}
+	if n.Bounds.Width() <= 0 || n.Bounds.Height() <= 0 {
+		return nil
+	}
+	var result []*Node
+	var walk func(*Node)
+	walk = func(candidate *Node) {
+		if candidate != n &&
+			candidate.Bounds.Width() > 0 && candidate.Bounds.Height() > 0 &&
+			containsBounds(n.Bounds, candidate.Bounds) {
+			result = append(result, candidate)
+		}
+		for _, child := range candidate.Children {
+			walk(child)
+		}
+	}
+	walk(n.tree.Root)
+	return result
+}
+
+// containsBounds reports whether outer fully contains inner (inclusive).
+func containsBounds(outer, inner Bounds) bool {
+	return inner.Left >= outer.Left && inner.Top >= outer.Top &&
+		inner.Right <= outer.Right && inner.Bottom <= outer.Bottom
+}
+
 func findPathNode(root *Node, segments []string) *Node {
 	if root == nil || len(segments) == 0 {
 		return nil
@@ -440,18 +489,12 @@ func findPathNode(root *Node, segments []string) *Node {
 }
 
 func findPathDescendantsNode(root *Node, segments []string) *Node {
-	kind, value, ok := parseSelector(segments[0])
-	if !ok {
-		return nil
-	}
-	for _, child := range root.Children {
-		for _, node := range searchSubtree(child, kind, value) {
-			if len(segments) == 1 {
-				return node
-			}
-			if result := findPathDescendantsNode(node, segments[1:]); result != nil {
-				return result
-			}
+	for _, node := range root.FindAll(segments[0]) {
+		if len(segments) == 1 {
+			return node
+		}
+		if result := findPathDescendantsNode(node, segments[1:]); result != nil {
+			return result
 		}
 	}
 	return nil
@@ -477,19 +520,13 @@ func findPathAllNodes(root *Node, segments []string) []*Node {
 }
 
 func findPathAllDescendantsNodes(root *Node, segments []string) []*Node {
-	kind, value, ok := parseSelector(segments[0])
-	if !ok {
-		return nil
-	}
 	var result []*Node
-	for _, child := range root.Children {
-		for _, node := range searchSubtree(child, kind, value) {
-			if len(segments) == 1 {
-				result = append(result, node)
-				continue
-			}
-			result = append(result, findPathAllDescendantsNodes(node, segments[1:])...)
+	for _, node := range root.FindAll(segments[0]) {
+		if len(segments) == 1 {
+			result = append(result, node)
+			continue
 		}
+		result = append(result, findPathAllDescendantsNodes(node, segments[1:])...)
 	}
 	return result
 }

internal/hierarchy/hierarchy_test.go

@@ -730,3 +730,145 @@ func TestExplicitPackageAttributeWins(t *testing.T) {
 		t.Errorf("package = %q, want app.folio (explicit attr should win)", got)
 	}
 }
+
+// iosFlatDump mirrors the Compose-on-iOS accessibility shape: the testTag node
+// surfaces as an empty leaf SIBLING of the container holding the content it
+// labels, with equal bounds, instead of as an ancestor.
+const iosFlatDump = `{
+  "attributes": {"bounds": "[0,0][402,874]"},
+  "children": [
+    {
+      "attributes": {"accessibilityText": "Folio", "bounds": "[0,0][402,874]"},
+      "children": [
+        {
+          "attributes": {"resource-id": "LoginScreen", "bounds": "[0,62][402,840]"},
+          "children": []
+        },
+        {
+          "attributes": {"bounds": "[0,62][402,840]"},
+          "children": [
+            {
+              "attributes": {"accessibilityText": "EMAIL", "bounds": "[20,106][60,120]"},
+              "children": []
+            },
+            {
+              "attributes": {"resource-id": "LoginEmail", "accessibilityText": "Email", "bounds": "[34,125][368,173]"},
+              "children": [
+                {"attributes": {"bounds": "[34,125][368,173]"}, "children": []}
+              ]
+            },
+            {
+              "attributes": {"resource-id": "LoginPassword", "accessibilityText": "Password", "bounds": "[34,205][368,253]"},
+              "children": []
+            },
+            {
+              "attributes": {"text": "Sign in", "bounds": "[20,297][382,345]"},
+              "children": []
+            },
+            {
+              "attributes": {"resource-id": "LoginSubmit", "accessibilityText": "Sign in", "bounds": "[20,297][382,345]"},
+              "children": [
+                {"attributes": {"text": "Sign in", "resource-id": "SubmitLabel", "bounds": "[168,312][233,330]"}, "children": []}
+              ]
+            }
+          ]
+        }
+      ]
+    },
+    {
+      "attributes": {"bounds": "[0,0][402,54]"},
+      "children": [
+        {
+          "attributes": {"resource-id": "StatusClock", "accessibilityText": "3:24 PM", "bounds": "[55,22][92,42]"},
+          "children": []
+        }
+      ]
+    }
+  ]
+}`
+
+func TestIOSFlatSelectorPathFallsBackToBounds(t *testing.T) {
+	tree, err := Parse(iosFlatDump)
+	if err != nil {
+		t.Fatalf("Parse: %v", err)
+	}
+	path := []Selector{
+		{Filters: []AttrFilter{{Attr: "testTag", Value: "LoginScreen"}}},
+		{Filters: []AttrFilter{{Attr: "testTag", Value: "LoginEmail"}}},
+	}
+	node := tree.FindBySelectorPath(path)
+	if node == nil {
+		t.Fatal("expected LoginEmail via bounds containment under leaf LoginScreen")
+	}
+	if node.ResourceID != "LoginEmail" {
+		t.Fatalf("got %q, want LoginEmail", node.ResourceID)
+	}
+}
+
+func TestIOSFlatStringPathFallsBackToBounds(t *testing.T) {
+	tree, _ := Parse(iosFlatDump)
+	element := tree.Find("id:LoginScreen > id:LoginSubmit")
+	if element == nil {
+		t.Fatal("expected LoginSubmit via bounds containment under leaf LoginScreen")
+	}
+	if element.ResourceID != "LoginSubmit" {
+		t.Fatalf("got %q, want LoginSubmit", element.ResourceID)
+	}
+}
+
+func TestIOSFlatScopedNodeFindFallsBackToBounds(t *testing.T) {
+	tree, _ := Parse(iosFlatDump)
+	screen := tree.FindNode("id:LoginScreen")
+	if screen == nil {
+		t.Fatal("expected LoginScreen node")
+	}
+	node := screen.Find("id:LoginPassword")
+	if node == nil {
+		t.Fatal("expected LoginPassword via bounds containment")
+	}
+	if node.ResourceID != "LoginPassword" {
+		t.Fatalf("got %q, want LoginPassword", node.ResourceID)
+	}
+}
+
+func TestIOSFlatFindAllBySelectorPathReturnsEachField(t *testing.T) {
+	tree, _ := Parse(iosFlatDump)
+	path := []Selector{
+		{Filters: []AttrFilter{{Attr: "testTag", Value: "LoginScreen"}}},
+		{Filters: []AttrFilter{{Attr: "label", Value: "word"}}},
+	}
+	// label "word" substring-matches "Password" only.
+	nodes := tree.FindAllBySelectorPath(path)
+	if len(nodes) != 1 {
+		t.Fatalf("got %d nodes, want 1", len(nodes))
+	}
+	if nodes[0].ResourceID != "LoginPassword" {
+		t.Fatalf("got %q, want LoginPassword", nodes[0].ResourceID)
+	}
+}
+
+func TestIOSFlatSpatialScopeExcludesOutsideBounds(t *testing.T) {
+	tree, _ := Parse(iosFlatDump)
+	// StatusClock sits in the status bar above LoginScreen's bounds; the
+	// spatial fallback must not leak it into the screen's scope.
+	if tree.Find("id:LoginScreen > id:StatusClock") != nil {
+		t.Fatal("StatusClock is outside LoginScreen bounds, expected nil")
+	}
+}
+
+func TestIOSFlatStructuralChildStillPreferred(t *testing.T) {
+	tree, _ := Parse(iosFlatDump)
+	submit := tree.FindNode("id:LoginSubmit")
+	if submit == nil {
+		t.Fatal("expected LoginSubmit node")
+	}
+	// "Sign in" exists as the structural child of LoginSubmit and as an
+	// equal-bounds sibling decoration; the structural child must win.
+	node := submit.Find("text:Sign in")
+	if node == nil {
+		t.Fatal("expected structural child match")
+	}
+	if node.ResourceID != "SubmitLabel" {
+		t.Fatalf("expected the structural child SubmitLabel, got id=%q", node.ResourceID)
+	}
+}

internal/runner/runner.go

@@ -497,6 +497,15 @@ func applyAction(ctx context.Context, drv driver.DeviceDriver, action verifier.A
 				return err
 			}
 		}
+		// InputText replaces the field's content: erase what the target
+		// holds before typing. Appending instead lets repeated draws grow
+		// the field without bound (e.g. into a max-length validation error
+		// the fuzzer can never escape) and makes retried typing land twice.
+		if count := existingTextLength(action, tree); count > 0 {
+			if err := drv.EraseText(ctx, count); err != nil {
+				return err
+			}
+		}
 		return drv.InputText(ctx, action.Text)
 	case verifier.ActionKindSwipe:
 		duration := time.Duration(action.DurationMillis) * time.Millisecond
@@ -547,6 +556,20 @@ func collectLogs(ctx context.Context, drv driver.DeviceDriver, since time.Time)
 	return result
 }
 
+// existingTextLength returns the character count of the InputText target's
+// current text, so the runner can erase it before typing. Zero when the
+// target cannot be resolved or holds no text.
+func existingTextLength(action verifier.Action, tree *hierarchy.Tree) int {
+	if action.On == "" || tree == nil {
+		return 0
+	}
+	element := tree.Find(action.On)
+	if element == nil {
+		return 0
+	}
+	return len([]rune(element.Text))
+}
+
 func resolveCoordinates(action verifier.Action, tree *hierarchy.Tree) (int, int, bool) {
 	// When On is empty, X/Y are authoritative (web V8 path emits coordinates
 	// directly from getBoundingClientRect; the runtime nullifies unresolved

internal/runner/runner_test.go

@@ -550,6 +550,52 @@ func TestRunner_LogsWaitForIdleDriverErrors(t *testing.T) {
 	}
 }
 
+func TestApplyAction_InputTextErasesExistingTextBeforeTyping(t *testing.T) {
+	tree, err := hierarchy.Parse(`{"attributes":{"resource-id":"root","bounds":"[0,0,1080,2340]"},"children":[
+		{"attributes":{"resource-id":"username","text":"stale-value","bounds":"[10,10,500,100]"},"children":[]}
+	]}`)
+	if err != nil {
+		t.Fatalf("Parse: %v", err)
+	}
+	driverMock := mockdriver.New()
+	action := verifier.Action{Kind: verifier.ActionKindInputText, On: "id:username", Text: "alice"}
+
+	if err := applyAction(context.Background(), driverMock, action, tree); err != nil {
+		t.Fatalf("applyAction: %v", err)
+	}
+	actions := driverMock.Actions()
+	if len(actions) != 3 {
+		t.Fatalf("want tap, erase, input; got %v", actions)
+	}
+	if actions[0].Kind != mockdriver.ActionTap {
+		t.Errorf("first action = %v, want tap", actions[0].Kind)
+	}
+	if actions[1].Kind != mockdriver.ActionEraseText || actions[1].CharacterCount != len("stale-value") {
+		t.Errorf("second action = %+v, want erase_text of %d characters", actions[1], len("stale-value"))
+	}
+	if actions[2].Kind != mockdriver.ActionInputText || actions[2].Text != "alice" {
+		t.Errorf("third action = %+v, want input_text alice", actions[2])
+	}
+}
+
+func TestApplyAction_InputTextSkipsEraseWhenTargetEmpty(t *testing.T) {
+	tree, err := hierarchy.Parse(`{"attributes":{"resource-id":"root","bounds":"[0,0,1080,2340]"},"children":[
+		{"attributes":{"resource-id":"username","bounds":"[10,10,500,100]"},"children":[]}
+	]}`)
+	if err != nil {
+		t.Fatalf("Parse: %v", err)
+	}
+	driverMock := mockdriver.New()
+	action := verifier.Action{Kind: verifier.ActionKindInputText, On: "id:username", Text: "alice"}
+
+	if err := applyAction(context.Background(), driverMock, action, tree); err != nil {
+		t.Fatalf("applyAction: %v", err)
+	}
+	if containsAction(driverMock.Actions(), mockdriver.ActionEraseText, "") {
+		t.Errorf("empty field must not be erased: %v", driverMock.Actions())
+	}
+}
+
 func TestApplyAction_InputTextSurfacesFocusTapError(t *testing.T) {
 	t.Run("selector focus tap fails", func(t *testing.T) {
 		driverMock := mockdriver.New()