feat: tap random point in ocr text rect

internal/version/VERSION

@@ -1 +1 @@
-v5.0.0-beta-2503171509
+v5.0.0-beta-2503171536

uixt/ai/cv.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"image"
 	"math"
+	"math/rand/v2"
 	"regexp"
 
 	"github.com/pkg/errors"
@@ -96,6 +97,17 @@ func (t OCRText) Center() PointF {
 	return point
 }
 
+func (t OCRText) RandomPoint() PointF {
+	rect := t.Rect
+	x, y := float64(rect.Min.X), float64(rect.Min.Y)
+	width, height := float64(rect.Dx()), float64(rect.Dy())
+	point := PointF{
+		X: x + width*rand.Float64(),
+		Y: y + height*rand.Float64(),
+	}
+	return point
+}
+
 type OCRTexts []OCRText
 
 func (t OCRTexts) texts() (texts []string) {

uixt/driver_ext_tap.go

@@ -3,6 +3,7 @@ package uixt
 import (
 	"fmt"
 
+	"github.com/httprunner/httprunner/v5/uixt/ai"
 	"github.com/httprunner/httprunner/v5/uixt/option"
 )
 
@@ -19,7 +20,13 @@ func (dExt *XTDriver) TapByOCR(text string, opts ...option.ActionOption) error {
 		}
 		return err
 	}
-	point := textRect.Center()
+
+	var point ai.PointF
+	if actionOptions.TapRandom {
+		point = textRect.RandomPoint()
+	} else {
+		point = textRect.Center()
+	}
 
 	return dExt.TapAbsXY(point.X, point.Y, opts...)
 }

uixt/driver_ext_test.go

@@ -182,5 +182,6 @@ func TestDriverExt_Action_Risk(t *testing.T) {
 		option.WithSwipeOffset(-50, 50, -50, 50))
 	assert.Nil(t, err)
 
-	err = driver.TapByOCR("首页", option.WithTapOffset(-10, 10))
+	// tap random point in ocr text rect
+	err = driver.TapByOCR("首页", option.WithTapRandom(true))
 }

uixt/option/action.go

@@ -99,6 +99,10 @@ func (o *ActionOptions) Options() []ActionOption {
 		// for tap [x,y] offset
 		options = append(options, WithTapOffset(o.TapOffset[0], o.TapOffset[1]))
 	}
+	if o.TapRandom {
+		// tap random point in OCR/CV rectangle
+		options = append(options, WithTapRandom(true))
+	}
 	if len(o.SwipeOffset) == 4 {
 		// for swipe [fromX, fromY, toX, toY] offset
 		options = append(options, WithSwipeOffset(

uixt/option/screen.go

@@ -217,6 +217,7 @@ type ScreenFilterOptions struct {
 
 	Regex               bool  `json:"regex,omitempty" yaml:"regex,omitempty"`                             // use regex to match text
 	TapOffset           []int `json:"tap_offset,omitempty" yaml:"tap_offset,omitempty"`                   // tap with point offset
+	TapRandom           bool  `json:"tap_random,omitempty" yaml:"tap_random,omitempty"`                   // tap random point in text/image rectangle
 	SwipeOffset         []int `json:"swipe_offset,omitempty" yaml:"swipe_offset,omitempty"`               // swipe with direction offset
 	OffsetRandomRange   []int `json:"offset_random_range,omitempty" yaml:"offset_random_range,omitempty"` // set random range [min, max] for tap/swipe points
 	Index               int   `json:"index,omitempty" yaml:"index,omitempty"`                             // index of the target element
@@ -247,6 +248,14 @@ func WithTapOffset(offsetX, offsetY int) ActionOption {
 	}
 }
 
+// WithTapRandom is used with TapByOCR and TapByCV
+// when set true, tap random point in text/image rectangle
+func WithTapRandom(tapRandom bool) ActionOption {
+	return func(o *ActionOptions) {
+		o.TapRandom = tapRandom
+	}
+}
+
 func WithRegex(regex bool) ActionOption {
 	return func(o *ActionOptions) {
 		o.Regex = regex