fix: errors

cmd/adb/install.go

@@ -47,7 +47,7 @@ var installCmd = &cobra.Command{
 			return err
 		}
 
-		err = driverExt.Install(args[0],
+		err = driverExt.GetDriver().GetDevice().Install(args[0],
 			option.WithReinstall(replace),
 			option.WithDowngrade(downgrade),
 			option.WithGrantPermission(grant),

examples/uitest/bili/android/cli.go

@@ -28,24 +28,24 @@ func init() {
 	fmt.Printf("=== start running cases, serial=%s, runTimes=%d ===\n", serial, runTimes)
 }
 
-func launchAppDriver(pkgName string) (driver *uixt.DriverExt, err error) {
+func launchAppDriver(pkgName string) (driver uixt.IDriverExt, err error) {
 	device, _ := uixt.NewAndroidDevice(option.WithSerialNumber(serial))
 	driver, err = device.NewDriver()
 	if err != nil {
 		return nil, err
 	}
 
-	_, err = driver.Driver.AppTerminate(pkgName)
+	_, err = driver.GetDriver().AppTerminate(pkgName)
 	if err != nil {
 		return nil, err
 	}
 
-	err = driver.Driver.Homescreen()
+	err = driver.GetDriver().Homescreen()
 	if err != nil {
 		return nil, err
 	}
 
-	err = driver.Driver.AppLaunch(pkgName)
+	err = driver.GetDriver().AppLaunch(pkgName)
 	if err != nil {
 		return nil, err
 	}
@@ -67,7 +67,7 @@ func launchAppDriver(pkgName string) (driver *uixt.DriverExt, err error) {
 	return driver, nil
 }
 
-func watchVideo(driver *uixt.DriverExt) (err error) {
+func watchVideo(driver uixt.IDriverExt) (err error) {
 	time.Sleep(3 * time.Second)
 	err = driver.SwipeRelative(0.7, 0.7, 0.7, 0.2)
 	if err != nil {
@@ -96,7 +96,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	if err != nil {
 		// 未找到横屏图标，该页面可能不是横版视频（直播|广告|Feed）
 		// 退出回到推荐页
-		driver.Driver.PressBack()
+		driver.GetDriver().PressBack()
 		return nil
 	}
 
@@ -104,7 +104,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	time.Sleep(10 * time.Second)
 
 	// 返回视频页面
-	err = driver.Driver.PressBack()
+	err = driver.GetDriver().PressBack()
 	if err != nil {
 		return err
 	}
@@ -112,7 +112,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	time.Sleep(1 * time.Second)
 
 	// 返回推荐页
-	err = driver.Driver.PressBack()
+	err = driver.GetDriver().PressBack()
 	if err != nil {
 		return err
 	}

examples/uitest/bili/ios/cli.go

@@ -28,7 +28,7 @@ func init() {
 	fmt.Printf("=== start running cases, serial=%s, runTimes=%d ===\n", serial, runTimes)
 }
 
-func launchAppDriver(pkgName string) (driver *uixt.DriverExt, err error) {
+func launchAppDriver(pkgName string) (driver uixt.IDriverExt, err error) {
 	device, _ := uixt.NewIOSDevice(option.WithUDID(serial))
 	driver, err = device.NewDriver()
 	if err != nil {
@@ -67,7 +67,7 @@ func launchAppDriver(pkgName string) (driver *uixt.DriverExt, err error) {
 	return driver, nil
 }
 
-func watchVideo(driver *uixt.DriverExt) (err error) {
+func watchVideo(driver uixt.IDriverExt) (err error) {
 	time.Sleep(3 * time.Second)
 	err = driver.SwipeRelative(0.7, 0.7, 0.7, 0.2)
 	if err != nil {
@@ -96,7 +96,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	if err != nil {
 		// 未找到横屏图标，该页面可能不是横版视频（直播|广告|Feed）
 		// 退出回到推荐页
-		driver.Driver.PressBack()
+		driver.GetDriver().PressBack()
 		return nil
 	}
 
@@ -104,7 +104,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	time.Sleep(10 * time.Second)
 
 	// 返回视频页面
-	err = driver.Driver.PressBack()
+	err = driver.GetDriver().PressBack()
 	if err != nil {
 		return err
 	}
@@ -112,7 +112,7 @@ func watchVideo(driver *uixt.DriverExt) (err error) {
 	time.Sleep(1 * time.Second)
 
 	// 返回推荐页
-	err = driver.Driver.PressBack()
+	err = driver.GetDriver().PressBack()
 	if err != nil {
 		return err
 	}

examples/worldcup/cli.go

@@ -8,6 +8,8 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/httprunner/httprunner/v5/pkg/uixt"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
 )
 
 var rootCmd = &cobra.Command{
@@ -15,21 +17,36 @@ var rootCmd = &cobra.Command{
 	Short:   "Monitor FIFA World Cup Live",
 	Version: "2022.12.03.0018",
 	RunE: func(cmd *cobra.Command, args []string) error {
-		var device uixt.IDevice
+		var driver uixt.IDriver
 		var bundleID string
 		if iosApp != "" {
 			log.Info().Str("bundleID", iosApp).Msg("init ios device")
-			device = initIOSDevice(uuid)
+			device, err := uixt.NewIOSDevice(option.WithUDID(uuid))
+			if err != nil {
+				log.Fatal().Err(err).Msg("failed to init ios device")
+			}
+			driver, _ = uixt.NewWDADriver(device)
 			bundleID = iosApp
 		} else if androidApp != "" {
 			log.Info().Str("bundleID", androidApp).Msg("init android device")
-			device = initAndroidDevice(uuid)
+			device, err := uixt.NewAndroidDevice(option.WithSerialNumber(uuid))
+			if err != nil {
+				log.Fatal().Err(err).Msg("failed to init android device")
+			}
+			driver, _ = uixt.NewADBDriver(device)
 			bundleID = androidApp
 		} else {
 			return errors.New("android or ios app bundldID is required")
 		}
 
-		wc := NewWorldCupLive(device, matchName, bundleID, duration, interval)
+		driverExt, err := uixt.NewDriverExt(driver,
+			ai.WithCVService(ai.CVServiceTypeVEDEM),
+		)
+		if err != nil {
+			return err
+		}
+
+		wc := NewWorldCupLive(driverExt, matchName, bundleID, duration, interval)
 
 		if auto {
 			wc.EnterLive(bundleID)

examples/worldcup/main.go

@@ -37,7 +37,7 @@ func convertTimeToSeconds(timeStr string) (int, error) {
 	return seconds, nil
 }
 
-func initIOSDevice(uuid string) uixt.IDevice {
+func initIOSDriver(uuid string) uixt.IDriverExt {
 	device, err := uixt.NewIOSDevice(
 		option.WithUDID(uuid),
 		option.WithWDAPort(8700), option.WithWDAMjpegPort(8800),
@@ -47,15 +47,17 @@ func initIOSDevice(uuid string) uixt.IDevice {
 	if err != nil {
 		log.Fatal().Err(err).Msg("failed to init ios device")
 	}
-	return device
+	driver, _ := device.NewDriver()
+	return driver
 }
 
-func initAndroidDevice(uuid string) uixt.IDevice {
+func initAndroidDriver(uuid string) uixt.IDriverExt {
 	device, err := uixt.NewAndroidDevice(option.WithSerialNumber(uuid))
 	if err != nil {
 		log.Fatal().Err(err).Msg("failed to init android device")
 	}
-	return device
+	driver, _ := device.NewDriver()
+	return driver
 }
 
 type timeLog struct {
@@ -66,10 +68,9 @@ type timeLog struct {
 }
 
 type WorldCupLive struct {
-	driver    *uixt.DriverExt
+	driver    uixt.IDriverExt
 	file      *os.File
 	resultDir string
-	UUID      string    `json:"uuid"`
 	MatchName string    `json:"matchName"`
 	BundleID  string    `json:"bundleID"`
 	StartTime string    `json:"startTime"`
@@ -80,12 +81,7 @@ type WorldCupLive struct {
 	PerfFile  string    `json:"perf"`
 }
 
-func NewWorldCupLive(device uixt.IDevice, matchName, bundleID string, duration, interval int) *WorldCupLive {
+func NewWorldCupLive(driver uixt.IDriverExt, matchName, bundleID string, duration, interval int) *WorldCupLive {
-	driverExt, err := device.NewDriver()
-	if err != nil {
-		log.Fatal().Err(err).Msg("failed to init driver")
-	}
-
 	if matchName == "" {
 		matchName = "unknown-match"
 	}
@@ -94,7 +90,7 @@ func NewWorldCupLive(device uixt.IDevice, matchName, bundleID string, duration,
 	matchName = fmt.Sprintf("%s-%s", startTime.Format("2006-01-02"), matchName)
 	resultDir := filepath.Join("worldcuplive", matchName, startTime.Format("15:04:05"))
 
-	if err = os.MkdirAll(filepath.Join(resultDir, "screenshot"), 0o755); err != nil {
+	if err := os.MkdirAll(filepath.Join(resultDir, "screenshot"), 0o755); err != nil {
 		log.Fatal().Err(err).Msg("failed to create result dir")
 	}
 
@@ -104,7 +100,7 @@ func NewWorldCupLive(device uixt.IDevice, matchName, bundleID string, duration,
 		log.Fatal().Err(err).Msg("failed to open file")
 	}
 	// write title
-	f.WriteString(fmt.Sprintf("%s\t%s\t%s\n", matchName, device.UUID(), bundleID))
+	f.WriteString(fmt.Sprintf("%s\t%s\t%s\n", matchName, driver.GetDriver().GetDevice().UUID(), bundleID))
 	f.WriteString("utc_time\tutc_timestamp\tlive_time\tlive_seconds\n")
 
 	if interval == 0 {
@@ -115,10 +111,9 @@ func NewWorldCupLive(device uixt.IDevice, matchName, bundleID string, duration,
 	}
 
 	return &WorldCupLive{
-		driver:    driverExt,
+		driver:    driver,
 		file:      f,
 		resultDir: resultDir,
-		UUID:      device.UUID(),
 		BundleID:  bundleID,
 		Duration:  duration,
 		Interval:  interval,
@@ -177,13 +172,13 @@ func (wc *WorldCupLive) EnterLive(bundleID string) error {
 	log.Info().Msg("enter world cup live")
 
 	// kill app
-	_, err := wc.driver.Driver.AppTerminate(bundleID)
+	_, err := wc.driver.GetDriver().AppTerminate(bundleID)
 	if err != nil {
 		log.Error().Err(err).Msg("terminate app failed")
 	}
 
 	// launch app
-	err = wc.driver.Driver.AppLaunch(bundleID)
+	err = wc.driver.GetDriver().AppLaunch(bundleID)
 	if err != nil {
 		log.Error().Err(err).Msg("launch app failed")
 		return err

examples/worldcup/main_test.go

@@ -33,17 +33,17 @@ func TestConvertTimeToSeconds(t *testing.T) {
 
 func TestMainIOS(t *testing.T) {
 	uuid := "00008030-00194DA421C1802E"
-	device := initIOSDevice(uuid)
+	driver := initIOSDriver(uuid)
 	bundleID := "com.ss.iphone.ugc.Aweme"
-	wc := NewWorldCupLive(device, "", bundleID, 30, 10)
+	wc := NewWorldCupLive(driver, "", bundleID, 30, 10)
 	wc.EnterLive(bundleID)
 	wc.Start()
 }
 
 func TestMainAndroid(t *testing.T) {
-	device := initAndroidDevice(uuid)
+	driver := initAndroidDriver(uuid)
 	bundleID := "com.ss.android.ugc.aweme"
-	wc := NewWorldCupLive(device, "", bundleID, 30, 10)
+	wc := NewWorldCupLive(driver, "", bundleID, 30, 10)
 	wc.EnterLive(bundleID)
 	wc.Start()
 }

internal/version/VERSION

@@ -1 +1 @@
-v5.0.0+2502081446
+v5.0.0+2502091051

pkg/uixt/ai/cv.go

@@ -9,13 +9,15 @@ import (
 
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 	"github.com/pkg/errors"
 )
 
 type ICVService interface {
 	// returns CV result including ocr texts, uploaded image url, etc
-	ReadFromBuffer(imageBuf *bytes.Buffer, opts ...ScreenShotOption) (*CVResult, error)
+	ReadFromBuffer(imageBuf *bytes.Buffer, opts ...option.ActionOption) (*CVResult, error)
-	ReadFromPath(imagePath string, opts ...ScreenShotOption) (*CVResult, error)
+	ReadFromPath(imagePath string, opts ...option.ActionOption) (*CVResult, error)
 }
 
 type CVResult struct {
@@ -75,8 +77,8 @@ type OCRText struct {
 	Rect    image.Rectangle `json:"-"`
 }
 
-func (t OCRText) Size() Size {
+func (t OCRText) Size() types.Size {
-	return Size{
+	return types.Size{
 		Width:  t.Rect.Dx(),
 		Height: t.Rect.Dy(),
 	}
@@ -105,7 +107,7 @@ func (t OCRTexts) texts() (texts []string) {
 	return texts
 }
 
-func (t OCRTexts) FilterScope(scope AbsScope) (results OCRTexts) {
+func (t OCRTexts) FilterScope(scope option.AbsScope) (results OCRTexts) {
 	for _, ocrText := range t {
 		rect := ocrText.Rect
 
@@ -127,8 +129,8 @@ func (t OCRTexts) FilterScope(scope AbsScope) (results OCRTexts) {
 
 // FindText returns matched text with options
 // Notice: filter scope should be specified with WithAbsScope
-func (t OCRTexts) FindText(text string, opts ...ScreenFilterOption) (result OCRText, err error) {
+func (t OCRTexts) FindText(text string, opts ...option.ActionOption) (result OCRText, err error) {
-	options := NewScreenFilterOptions(opts...)
+	options := option.NewActionOptions(opts...)
 
 	var results []OCRText
 	for _, ocrText := range t.FilterScope(options.AbsScope) {
@@ -172,8 +174,8 @@ func (t OCRTexts) FindText(text string, opts ...ScreenFilterOption) (result OCRT
 	return results[idx], nil
 }
 
-func (t OCRTexts) FindTexts(texts []string, opts ...ScreenFilterOption) (results OCRTexts, err error) {
+func (t OCRTexts) FindTexts(texts []string, opts ...option.ActionOption) (results OCRTexts, err error) {
-	options := NewScreenFilterOptions(opts...)
+	options := option.NewActionOptions(opts...)
 	for _, text := range texts {
 		ocrText, err := t.FindText(text, opts...)
 		if err != nil {
@@ -239,7 +241,7 @@ func (box Box) Center() PointF {
 
 type UIResults []UIResult
 
-func (u UIResults) FilterScope(scope AbsScope) (results UIResults) {
+func (u UIResults) FilterScope(scope option.AbsScope) (results UIResults) {
 	for _, uiResult := range u {
 		rect := image.Rectangle{
 			Min: image.Point{
@@ -267,8 +269,8 @@ func (u UIResults) FilterScope(scope AbsScope) (results UIResults) {
 	return
 }
 
-func (u UIResults) GetUIResult(opts ...ScreenFilterOption) (UIResult, error) {
+func (u UIResults) GetUIResult(opts ...option.ActionOption) (UIResult, error) {
-	options := NewScreenFilterOptions(opts...)
+	options := option.NewActionOptions(opts...)
 	uiResults := u.FilterScope(options.AbsScope)
 	if len(uiResults) == 0 {
 		return UIResult{}, errors.Wrap(code.CVResultNotFoundError,
@@ -315,16 +317,7 @@ func (p PointF) IsIdentical(p2 PointF) bool {
 	return math.Abs(p.X-p2.X) < 1 && math.Abs(p.Y-p2.Y) < 1
 }
 
-type Size struct {
-	Width  int `json:"width"`
-	Height int `json:"height"`
-}
-
-func (s Size) IsNil() bool {
-	return s.Width == 0 && s.Height == 0
-}
-
 type Screen struct {
-	StatusBarSize Size    `json:"statusBarSize"`
+	StatusBarSize types.Size `json:"statusBarSize"`
-	Scale         float64 `json:"scale"`
+	Scale         float64    `json:"scale"`
 }

pkg/uixt/ai/cv_vedem.go

@@ -16,6 +16,7 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/internal/json"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
 )
 
 var client = &http.Client{
@@ -46,7 +47,7 @@ func NewVEDEMImageService() (*vedemCVService, error) {
 //	ui - get ui position by type(s)
 type vedemCVService struct{}
 
-func (s *vedemCVService) ReadFromPath(imagePath string, opts ...ScreenShotOption) (
+func (s *vedemCVService) ReadFromPath(imagePath string, opts ...option.ActionOption) (
 	imageResult *CVResult, err error) {
 	imageBuf, err := os.ReadFile(imagePath)
 	if err != nil {
@@ -58,9 +59,9 @@ func (s *vedemCVService) ReadFromPath(imagePath string, opts ...ScreenShotOption
 	return
 }
 
-func (s *vedemCVService) ReadFromBuffer(imageBuf *bytes.Buffer, opts ...ScreenShotOption) (
+func (s *vedemCVService) ReadFromBuffer(imageBuf *bytes.Buffer, opts ...option.ActionOption) (
 	imageResult *CVResult, err error) {
-	actionOptions := NewScreenShotOptions(opts...)
+	actionOptions := option.NewActionOptions(opts...)
 	screenshotActions := actionOptions.List()
 	if len(screenshotActions) == 0 {
 		// skip

pkg/uixt/android_device.go

@@ -24,7 +24,9 @@ import (
 	"github.com/httprunner/httprunner/v5/internal/config"
 	"github.com/httprunner/httprunner/v5/internal/json"
 	"github.com/httprunner/httprunner/v5/pkg/gadb"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 const (
@@ -147,7 +149,7 @@ func (dev *AndroidDevice) LogEnabled() bool {
 	return dev.LogOn
 }
 
-func (dev *AndroidDevice) NewDriver(opts ...option.DriverOption) (driverExt *DriverExt, err error) {
+func (dev *AndroidDevice) NewDriver() (driverExt IDriverExt, err error) {
 	var driver IDriver
 	if dev.UIA2 || dev.LogOn {
 		driver, err = NewUIA2Driver(dev)
@@ -160,18 +162,21 @@ func (dev *AndroidDevice) NewDriver(opts ...option.DriverOption) (driverExt *Dri
 		return nil, errors.Wrap(err, "failed to init UIA driver")
 	}
 
-	driverExt, err = newDriverExt(dev, driver, opts...)
-	if err != nil {
-		return nil, err
-	}
-
 	if dev.LogOn {
-		err = driverExt.Driver.StartCaptureLog("hrp_adb_log")
+		err = driver.StartCaptureLog("hrp_adb_log")
 		if err != nil {
 			return nil, err
 		}
 	}
 
+	driverExt, err = NewDriverExt(driver, ai.WithCVService(ai.CVServiceTypeVEDEM))
+	if err != nil {
+		return nil, errors.Wrap(err, "init android driver ext failed")
+	}
+	// setup driver
+	if err := driverExt.GetDriver().Setup(); err != nil {
+		return nil, err
+	}
 	return driverExt, nil
 }
 
@@ -301,17 +306,17 @@ func (dev *AndroidDevice) Uninstall(packageName string) error {
 	return err
 }
 
-func (dev *AndroidDevice) GetCurrentWindow() (windowInfo WindowInfo, err error) {
+func (dev *AndroidDevice) GetCurrentWindow() (windowInfo types.WindowInfo, err error) {
 	// adb shell dumpsys window | grep -E 'mCurrentFocus|mFocusedApp'
 	output, err := dev.RunShellCommand("dumpsys", "window", "|", "grep", "-E", "'mCurrentFocus|mFocusedApp'")
 	if err != nil {
-		return WindowInfo{}, errors.Wrap(err, "get current window failed")
+		return types.WindowInfo{}, errors.Wrap(err, "get current window failed")
 	}
 	// mCurrentFocus=Window{a33bc55 u0 com.miui.home/com.miui.home.launcher.Launcher}
 	reFocus := regexp.MustCompile(`mCurrentFocus=Window{.*? (\S+)/(\S+)}`)
 	matches := reFocus.FindStringSubmatch(output)
 	if len(matches) == 3 {
-		windowInfo = WindowInfo{
+		windowInfo = types.WindowInfo{
 			PackageName: matches[1],
 			Activity:    matches[2],
 		}
@@ -321,7 +326,7 @@ func (dev *AndroidDevice) GetCurrentWindow() (windowInfo WindowInfo, err error)
 	reApp := regexp.MustCompile(`mFocusedApp=ActivityRecord{.*? (\S+)/(\S+?)\s`)
 	matches = reApp.FindStringSubmatch(output)
 	if len(matches) == 3 {
-		windowInfo = WindowInfo{
+		windowInfo = types.WindowInfo{
 			PackageName: matches[1],
 			Activity:    matches[2],
 		}
@@ -331,24 +336,24 @@ func (dev *AndroidDevice) GetCurrentWindow() (windowInfo WindowInfo, err error)
 	// adb shell dumpsys activity activities | grep mResumedActivity
 	output, err = dev.RunShellCommand("dumpsys", "activity", "activities", "|", "grep", "mResumedActivity")
 	if err != nil {
-		return WindowInfo{}, errors.Wrap(err, "get current activity failed")
+		return types.WindowInfo{}, errors.Wrap(err, "get current activity failed")
 	}
 	// mResumedActivity: ActivityRecord{2db504f u0 com.miui.home/.launcher.Launcher t2}
 	reActivity := regexp.MustCompile(`mResumedActivity: ActivityRecord{.*? (\S+)/(\S+?)\s`)
 	matches = reActivity.FindStringSubmatch(output)
 	if len(matches) == 3 {
-		windowInfo = WindowInfo{
+		windowInfo = types.WindowInfo{
 			PackageName: matches[1],
 			Activity:    matches[2],
 		}
 		return windowInfo, nil
 	}
 
-	return WindowInfo{}, errors.New("failed to extract current window")
+	return types.WindowInfo{}, errors.New("failed to extract current window")
 }
 
-func (dev *AndroidDevice) GetPackageInfo(packageName string) (AppInfo, error) {
+func (dev *AndroidDevice) GetPackageInfo(packageName string) (types.AppInfo, error) {
-	appInfo := AppInfo{
+	appInfo := types.AppInfo{
 		Name: packageName,
 	}
 	// get package version

pkg/uixt/android_driver_adb.go

@@ -23,8 +23,9 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/config"
 	"github.com/httprunner/httprunner/v5/internal/utf7"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 func NewADBDriver(device *AndroidDevice) (*ADBDriver, error) {
@@ -86,7 +87,7 @@ func (ad *ADBDriver) DeleteSession() (err error) {
 	return errDriverNotImplemented
 }
 
-func (ad *ADBDriver) Status() (deviceStatus DeviceStatus, err error) {
+func (ad *ADBDriver) Status() (deviceStatus types.DeviceStatus, err error) {
 	err = errDriverNotImplemented
 	return
 }
@@ -95,22 +96,22 @@ func (ad *ADBDriver) GetDevice() IDevice {
 	return ad.AndroidDevice
 }
 
-func (ad *ADBDriver) DeviceInfo() (deviceInfo DeviceInfo, err error) {
+func (ad *ADBDriver) DeviceInfo() (deviceInfo types.DeviceInfo, err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) Location() (location Location, err error) {
+func (ad *ADBDriver) Location() (location types.Location, err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) BatteryInfo() (batteryInfo BatteryInfo, err error) {
+func (ad *ADBDriver) BatteryInfo() (batteryInfo types.BatteryInfo, err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) getWindowSize() (size ai.Size, err error) {
+func (ad *ADBDriver) getWindowSize() (size types.Size, err error) {
 	// adb shell wm size
 	output, err := ad.runShellCommand("wm", "size")
 	if err != nil {
@@ -136,14 +137,14 @@ func (ad *ADBDriver) getWindowSize() (size ai.Size, err error) {
 			ss := strings.Split(resolution, "x")
 			width, _ := strconv.Atoi(ss[0])
 			height, _ := strconv.Atoi(ss[1])
-			return ai.Size{Width: width, Height: height}, nil
+			return types.Size{Width: width, Height: height}, nil
 		}
 	}
 	err = errors.New("physical window size not found by adb")
 	return
 }
 
-func (ad *ADBDriver) WindowSize() (size ai.Size, err error) {
+func (ad *ADBDriver) WindowSize() (size types.Size, err error) {
 	if !ad.windowSize.IsNil() {
 		// use cached window size
 		return ad.windowSize, nil
@@ -157,11 +158,11 @@ func (ad *ADBDriver) WindowSize() (size ai.Size, err error) {
 	orientation, err2 := ad.Orientation()
 	if err2 != nil {
 		// Notice: do not return err if get window orientation failed
-		orientation = OrientationPortrait
+		orientation = types.OrientationPortrait
 		log.Warn().Err(err2).Msgf(
 			"get window orientation failed, use default %s", orientation)
 	}
-	if orientation != OrientationPortrait {
+	if orientation != types.OrientationPortrait {
 		size.Width, size.Height = size.Height, size.Width
 	}
 
@@ -243,7 +244,7 @@ func (ad *ADBDriver) StopCamera() (err error) {
 	return
 }
 
-func (ad *ADBDriver) Orientation() (orientation Orientation, err error) {
+func (ad *ADBDriver) Orientation() (orientation types.Orientation, err error) {
 	output, err := ad.runShellCommand("dumpsys", "input", "|", "grep", "'SurfaceOrientation'")
 	if err != nil {
 		return
@@ -252,9 +253,9 @@ func (ad *ADBDriver) Orientation() (orientation Orientation, err error) {
 	matches := re.FindStringSubmatch(output)
 	if len(matches) > 1 { // 确保找到了匹配项
 		if matches[1] == "0" || matches[1] == "2" {
-			return OrientationPortrait, nil
+			return types.OrientationPortrait, nil
 		} else if matches[1] == "1" || matches[1] == "3" {
-			return OrientationLandscapeLeft, nil
+			return types.OrientationLandscapeLeft, nil
 		}
 	}
 	err = fmt.Errorf("not found SurfaceOrientation value")
@@ -490,12 +491,12 @@ func (ad *ADBDriver) ForceTouchFloat(x, y, pressure float64, second ...float64)
 	return
 }
 
-func (ad *ADBDriver) SetPasteboard(contentType PasteboardType, content string) (err error) {
+func (ad *ADBDriver) SetPasteboard(contentType types.PasteboardType, content string) (err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error) {
+func (ad *ADBDriver) GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error) {
 	err = errDriverNotImplemented
 	return
 }
@@ -618,17 +619,17 @@ func (ad *ADBDriver) Clear(packageName string) error {
 	return nil
 }
 
-func (ad *ADBDriver) PressButton(devBtn DeviceButton) (err error) {
+func (ad *ADBDriver) PressButton(devBtn types.DeviceButton) (err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) Rotation() (rotation Rotation, err error) {
+func (ad *ADBDriver) Rotation() (rotation types.Rotation, err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (ad *ADBDriver) SetRotation(rotation Rotation) (err error) {
+func (ad *ADBDriver) SetRotation(rotation types.Rotation) (err error) {
 	err = errDriverNotImplemented
 	return
 }
@@ -856,7 +857,7 @@ func (ad *ADBDriver) GetDriverResults() []*DriverRequests {
 	return nil
 }
 
-func (ad *ADBDriver) GetForegroundApp() (app AppInfo, err error) {
+func (ad *ADBDriver) GetForegroundApp() (app types.AppInfo, err error) {
 	packageInfo, err := ad.runShellCommand(
 		"CLASSPATH=/data/local/tmp/evalite", "app_process", "/",
 		"com.bytedance.iesqa.eval_process.PackageService", "2>/dev/null")

pkg/uixt/android_driver_stub.go

@@ -15,6 +15,7 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/json"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 const (
@@ -166,17 +167,17 @@ func (sad *StubAndroidDriver) close() error {
 	return nil
 }
 
-func (sad *StubAndroidDriver) Status() (DeviceStatus, error) {
+func (sad *StubAndroidDriver) Status() (types.DeviceStatus, error) {
 	app, err := sad.GetForegroundApp()
 	if err != nil {
-		return DeviceStatus{}, err
+		return types.DeviceStatus{}, err
 	}
 	res, err := sad.sendCommand(app.PackageName, "Hello", nil)
 	if err != nil {
-		return DeviceStatus{}, err
+		return types.DeviceStatus{}, err
 	}
 	log.Info().Msg(fmt.Sprintf("ping stub result :%v", res))
-	return DeviceStatus{}, nil
+	return types.DeviceStatus{}, nil
 }
 
 func (sad *StubAndroidDriver) Source(srcOpt ...option.SourceOption) (source string, err error) {

pkg/uixt/android_driver_uia2.go

@@ -16,8 +16,8 @@ import (
 
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/utf7"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 var errDriverNotImplemented = errors.New("driver method not implemented")
@@ -133,12 +133,12 @@ func (ud *UIA2Driver) DeleteSession() (err error) {
 	return err
 }
 
-func (ud *UIA2Driver) Status() (deviceStatus DeviceStatus, err error) {
+func (ud *UIA2Driver) Status() (deviceStatus types.DeviceStatus, err error) {
 	// register(getHandler, new Status("/wd/hub/status"))
 	var rawResp rawResponse
 	// Notice: use Driver.GET instead of httpGET to avoid loop calling
 	if rawResp, err = ud.GET("/status"); err != nil {
-		return DeviceStatus{Ready: false}, err
+		return types.DeviceStatus{Ready: false}, err
 	}
 	reply := new(struct {
 		Value struct {
@@ -147,34 +147,34 @@ func (ud *UIA2Driver) Status() (deviceStatus DeviceStatus, err error) {
 		}
 	})
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return DeviceStatus{Ready: false}, err
+		return types.DeviceStatus{Ready: false}, err
 	}
-	return DeviceStatus{Ready: true}, nil
+	return types.DeviceStatus{Ready: true}, nil
 }
 
-func (ud *UIA2Driver) DeviceInfo() (deviceInfo DeviceInfo, err error) {
+func (ud *UIA2Driver) DeviceInfo() (deviceInfo types.DeviceInfo, err error) {
 	// register(getHandler, new GetDeviceInfo("/wd/hub/session/:sessionId/appium/device/info"))
 	var rawResp rawResponse
 	if rawResp, err = ud.httpGET("/session", ud.sessionID, "appium/device/info"); err != nil {
-		return DeviceInfo{}, err
+		return types.DeviceInfo{}, err
 	}
-	reply := new(struct{ Value struct{ DeviceInfo } })
+	reply := new(struct{ Value struct{ types.DeviceInfo } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return DeviceInfo{}, err
+		return types.DeviceInfo{}, err
 	}
 	deviceInfo = reply.Value.DeviceInfo
 	return
 }
 
-func (ud *UIA2Driver) BatteryInfo() (batteryInfo BatteryInfo, err error) {
+func (ud *UIA2Driver) BatteryInfo() (batteryInfo types.BatteryInfo, err error) {
 	// register(getHandler, new GetBatteryInfo("/wd/hub/session/:sessionId/appium/device/battery_info"))
 	var rawResp rawResponse
 	if rawResp, err = ud.httpGET("/session", ud.sessionID, "appium/device/battery_info"); err != nil {
-		return BatteryInfo{}, err
+		return types.BatteryInfo{}, err
 	}
-	reply := new(struct{ Value struct{ BatteryInfo } })
+	reply := new(struct{ Value struct{ types.BatteryInfo } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return BatteryInfo{}, err
+		return types.BatteryInfo{}, err
 	}
 	if reply.Value.Level == -1 || reply.Value.Status == -1 {
 		return reply.Value.BatteryInfo, errors.New("cannot be retrieved from the system")
@@ -183,7 +183,7 @@ func (ud *UIA2Driver) BatteryInfo() (batteryInfo BatteryInfo, err error) {
 	return
 }
 
-func (ud *UIA2Driver) WindowSize() (size ai.Size, err error) {
+func (ud *UIA2Driver) WindowSize() (size types.Size, err error) {
 	// register(getHandler, new GetDeviceSize("/wd/hub/session/:sessionId/window/:windowHandle/size"))
 	if !ud.windowSize.IsNil() {
 		// use cached window size
@@ -192,11 +192,11 @@ func (ud *UIA2Driver) WindowSize() (size ai.Size, err error) {
 
 	var rawResp rawResponse
 	if rawResp, err = ud.httpGET("/session", ud.sessionID, "window/:windowHandle/size"); err != nil {
-		return ai.Size{}, errors.Wrap(err, "get window size failed by UIA2 request")
+		return types.Size{}, errors.Wrap(err, "get window size failed by UIA2 request")
 	}
-	reply := new(struct{ Value struct{ ai.Size } })
+	reply := new(struct{ Value struct{ types.Size } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return ai.Size{}, errors.Wrap(err, "get window size failed by UIA2 response")
+		return types.Size{}, errors.Wrap(err, "get window size failed by UIA2 response")
 	}
 	size = reply.Value.Size
 
@@ -204,9 +204,9 @@ func (ud *UIA2Driver) WindowSize() (size ai.Size, err error) {
 	orientation, err := ud.Orientation()
 	if err != nil {
 		log.Warn().Err(err).Msgf("window size get orientation failed, use default orientation")
-		orientation = OrientationPortrait
+		orientation = types.OrientationPortrait
 	}
-	if orientation != OrientationPortrait {
+	if orientation != types.OrientationPortrait {
 		size.Width, size.Height = size.Height, size.Width
 	}
 
@@ -244,13 +244,13 @@ func (ud *UIA2Driver) PressKeyCodes(keyCode KeyCode, metaState KeyMeta, flags ..
 	return
 }
 
-func (ud *UIA2Driver) Orientation() (orientation Orientation, err error) {
+func (ud *UIA2Driver) Orientation() (orientation types.Orientation, err error) {
 	// [[FBRoute GET:@"/orientation"] respondWithTarget:self action:@selector(handleGetOrientation:)]
 	var rawResp rawResponse
 	if rawResp, err = ud.httpGET("/session", ud.sessionID, "/orientation"); err != nil {
 		return "", err
 	}
-	reply := new(struct{ Value Orientation })
+	reply := new(struct{ Value types.Orientation })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
 		return "", err
 	}
@@ -418,7 +418,7 @@ func (ud *UIA2Driver) Swipe(fromX, fromY, toX, toY float64, opts ...option.Actio
 	return err
 }
 
-func (ud *UIA2Driver) SetPasteboard(contentType PasteboardType, content string) (err error) {
+func (ud *UIA2Driver) SetPasteboard(contentType types.PasteboardType, content string) (err error) {
 	lbl := content
 
 	const defaultLabelLen = 10
@@ -436,9 +436,9 @@ func (ud *UIA2Driver) SetPasteboard(contentType PasteboardType, content string)
 	return
 }
 
-func (ud *UIA2Driver) GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error) {
+func (ud *UIA2Driver) GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error) {
 	if len(contentType) == 0 {
-		contentType = PasteboardTypePlaintext
+		contentType = types.PasteboardTypePlaintext
 	}
 	// register(postHandler, new GetClipboard("/wd/hub/session/:sessionId/appium/device/get_clipboard"))
 	data := map[string]interface{}{
@@ -541,15 +541,15 @@ func (ud *UIA2Driver) Input(text string, opts ...option.ActionOption) (err error
 	return ud.SendKeys(text, opts...)
 }
 
-func (ud *UIA2Driver) Rotation() (rotation Rotation, err error) {
+func (ud *UIA2Driver) Rotation() (rotation types.Rotation, err error) {
 	// register(getHandler, new GetRotation("/wd/hub/session/:sessionId/rotation"))
 	var rawResp rawResponse
 	if rawResp, err = ud.httpGET("/session", ud.sessionID, "rotation"); err != nil {
-		return Rotation{}, err
+		return types.Rotation{}, err
 	}
-	reply := new(struct{ Value Rotation })
+	reply := new(struct{ Value types.Rotation })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return Rotation{}, err
+		return types.Rotation{}, err
 	}
 
 	rotation = reply.Value

pkg/uixt/android_test.go

@@ -10,9 +10,10 @@ import (
 
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
-var driverExt *DriverExt
+var driverExt IDriverExt
 
 func setupAndroidAdbDriver(t *testing.T) {
 	device, err := NewAndroidDevice()
@@ -91,7 +92,7 @@ func TestDriver_DeviceSize(t *testing.T) {
 func TestDriver_Source(t *testing.T) {
 	setupAndroidUIA2Driver(t)
 
-	source, err := driverExt.Driver.Source()
+	source, err := driverExt.GetDriver().Source()
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -140,7 +141,7 @@ func TestDriver_DeviceInfo(t *testing.T) {
 
 func TestDriver_Tap(t *testing.T) {
 	setupAndroidUIA2Driver(t)
-	driverExt.Driver.StartCaptureLog("")
+	driverExt.GetDriver().StartCaptureLog("")
 	err := driverExt.TapXY(0.5, 0.5,
 		option.WithIdentifier("test"),
 		option.WithPressDuration(4))
@@ -149,18 +150,18 @@ func TestDriver_Tap(t *testing.T) {
 	}
 	//time.Sleep(time.Second)
 	//
-	//err = driverExt.Driver.Tap(60.5, 125.5, WithIdentifier("test"))
+	//err = driverExt.GetDriver().Tap(60.5, 125.5, WithIdentifier("test"))
 	//if err != nil {
 	//	t.Fatal(err)
 	//}
 	//time.Sleep(time.Second)
-	//result, _ := driverExt.Driver.StopCaptureLog()
+	//result, _ := driverExt.GetDriver().StopCaptureLog()
 	//t.Log(result)
 }
 
 func TestDriver_Swipe(t *testing.T) {
 	setupAndroidUIA2Driver(t)
-	err := driverExt.Driver.Swipe(400, 1000, 400, 500,
+	err := driverExt.GetDriver().Swipe(400, 1000, 400, 500,
 		option.WithPressDuration(0.5))
 	if err != nil {
 		t.Fatal(err)
@@ -192,7 +193,7 @@ func TestDriver_Drag(t *testing.T) {
 func TestDriver_SendKeys(t *testing.T) {
 	setupAndroidUIA2Driver(t)
 
-	err := driverExt.Driver.SendKeys("辽宁省沈阳市新民市民族街36-4",
+	err := driverExt.GetDriver().SendKeys("辽宁省沈阳市新民市民族街36-4",
 		option.WithIdentifier("test"))
 	if err != nil {
 		t.Fatal(err)
@@ -222,7 +223,7 @@ func TestDriver_PressBack(t *testing.T) {
 
 func TestDriver_SetRotation(t *testing.T) {
 	// err = driver.SetRotation(Rotation{Z: 0})
-	err := driver.SetRotation(Rotation{Z: 270})
+	err := driver.SetRotation(types.Rotation{Z: 270})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -230,10 +231,10 @@ func TestDriver_SetRotation(t *testing.T) {
 
 func TestDriver_GetOrientation(t *testing.T) {
 	setupAndroidUIA2Driver(t)
-	_, _ = driverExt.Driver.AppTerminate("com.quark.browser")
+	_, _ = driverExt.GetDriver().AppTerminate("com.quark.browser")
-	_ = driverExt.Driver.AppLaunch("com.quark.browser")
+	_ = driverExt.GetDriver().AppLaunch("com.quark.browser")
 	time.Sleep(2 * time.Second)
-	_ = driverExt.Driver.Homescreen()
+	_ = driverExt.GetDriver().Homescreen()
 }
 
 func Test_getFreePort(t *testing.T) {
@@ -251,12 +252,12 @@ func TestDriver_AppLaunch(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	err = driver.Driver.AppLaunch("com.android.settings")
+	err = driver.GetDriver().AppLaunch("com.android.settings")
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	raw, err := driver.Driver.Screenshot()
+	raw, err := driver.GetDriver().Screenshot()
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -268,10 +269,10 @@ func TestDriver_IsAppInForeground(t *testing.T) {
 	setupAndroidUIA2Driver(t)
 	// setupAndroidAdbDriver(t)
 
-	err := driverExt.Driver.AppLaunch("com.android.settings")
+	err := driverExt.GetDriver().AppLaunch("com.android.settings")
 	checkErr(t, err)
 
-	app, err := driverExt.Driver.GetForegroundApp()
+	app, err := driverExt.GetDriver().GetForegroundApp()
 	checkErr(t, err)
 	if app.PackageName != "com.android.settings" {
 		t.FailNow()
@@ -280,18 +281,18 @@ func TestDriver_IsAppInForeground(t *testing.T) {
 		t.FailNow()
 	}
 
-	err = driverExt.Driver.AssertForegroundApp("com.android.settings")
+	err = driverExt.GetDriver().AssertForegroundApp("com.android.settings")
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	time.Sleep(2 * time.Second)
-	_, err = driverExt.Driver.AppTerminate("com.android.settings")
+	_, err = driverExt.GetDriver().AppTerminate("com.android.settings")
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	err = driverExt.Driver.AssertForegroundApp("com.android.settings")
+	err = driverExt.GetDriver().AssertForegroundApp("com.android.settings")
 	if err == nil {
 		t.Fatal(err)
 	}
@@ -304,19 +305,19 @@ func TestDriver_KeepAlive(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	err = driver.Driver.AppLaunch("com.android.settings")
+	err = driver.GetDriver().AppLaunch("com.android.settings")
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	_, err = driver.Driver.Screenshot()
+	_, err = driver.GetDriver().Screenshot()
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	time.Sleep(60 * time.Second)
 
-	_, err = driver.Driver.Screenshot()
+	_, err = driver.GetDriver().Screenshot()
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -329,7 +330,7 @@ func TestDriver_AppTerminate(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	_, err = driver.Driver.AppTerminate("tv.danmaku.bili")
+	_, err = driver.GetDriver().AppTerminate("tv.danmaku.bili")
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -391,7 +392,7 @@ func TestTapTexts(t *testing.T) {
 			},
 		},
 	}
-	err := driverExt.Driver.TapByTexts(actions...)
+	err := driverExt.GetDriver().TapByTexts(actions...)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -399,7 +400,7 @@ func TestTapTexts(t *testing.T) {
 
 func TestRecordVideo(t *testing.T) {
 	setupAndroidAdbDriver(t)
-	path, err := driverExt.Driver.(*ADBDriver).RecordScreen("", 5*time.Second)
+	path, err := driverExt.GetDriver().(*ADBDriver).RecordScreen("", 5*time.Second)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -409,7 +410,7 @@ func TestRecordVideo(t *testing.T) {
 func Test_Android_Backspace(t *testing.T) {
 	setupAndroidAdbDriver(t)
 
-	err := driverExt.Driver.Backspace(1)
+	err := driverExt.GetDriver().Backspace(1)
 	if err != nil {
 		t.Fatal(err)
 	}

pkg/uixt/demo/main_test.go

@@ -22,16 +22,14 @@ func TestIOSDemo(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	capabilities := option.NewCapabilities()
+	driverExt, err := device.NewDriver()
-	capabilities.WithDefaultAlertAction(option.AlertActionAccept) // or uixt.AlertActionDismiss
-	driverExt, err := device.NewDriver(option.WithDriverCapabilities(capabilities))
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// release session
 	defer func() {
-		driverExt.Driver.DeleteSession()
+		driverExt.GetDriver().DeleteSession()
 	}()
 
 	// 持续监测手机屏幕，直到出现青少年模式弹窗后，点击「我知道了」

pkg/uixt/device.go

@@ -2,6 +2,7 @@ package uixt
 
 import (
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 // current implemeted device: IOSDevice, AndroidDevice, HarmonyDevice
@@ -14,7 +15,7 @@ type IDevice interface {
 	Install(appPath string, opts ...option.InstallOption) error
 	Uninstall(packageName string) error
 
-	GetPackageInfo(packageName string) (AppInfo, error)
+	GetPackageInfo(packageName string) (types.AppInfo, error)
 
 	// TODO: remove?
 	LogEnabled() bool

pkg/uixt/driver.go

@@ -16,8 +16,9 @@ import (
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/internal/config"
 	"github.com/httprunner/httprunner/v5/internal/json"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 var (
@@ -40,10 +41,10 @@ type IDriver interface {
 	// GetSession returns session cache, including requests, screenshots, etc.
 	GetSession() *Session
 
-	Status() (DeviceStatus, error)
+	Status() (types.DeviceStatus, error)
 
 	GetDevice() IDevice
-	DeviceInfo() (DeviceInfo, error)
+	DeviceInfo() (types.DeviceInfo, error)
 
 	// Location Returns device location data.
 	//
@@ -56,13 +57,13 @@ type IDriver interface {
 	//
 	// The return value could be zero even if the permission is set to 'Always'
 	// since the location service needs some time to update the location data.
-	Location() (Location, error)
+	Location() (types.Location, error)
-	BatteryInfo() (BatteryInfo, error)
+	BatteryInfo() (types.BatteryInfo, error)
 
 	// WindowSize Return the width and height in portrait mode.
 	// when getting the window size in wda/ui2/adb, if the device is in landscape mode,
 	// the width and height will be reversed.
-	WindowSize() (ai.Size, error)
+	WindowSize() (types.Size, error)
 	Screen() (ai.Screen, error)
 	Scale() (float64, error)
 
@@ -78,7 +79,7 @@ type IDriver interface {
 	// Either `true` if the app has been successfully terminated or `false` if it was not running
 	AppTerminate(packageName string) (bool, error)
 	// GetForegroundApp returns current foreground app package name and activity name
-	GetForegroundApp() (app AppInfo, err error)
+	GetForegroundApp() (app types.AppInfo, err error)
 	// AssertForegroundApp returns nil if the given package and activity are in foreground
 	AssertForegroundApp(packageName string, activityType ...string) error
 
@@ -87,10 +88,10 @@ type IDriver interface {
 	// StopCamera Stops the camera for recording
 	StopCamera() error
 
-	Orientation() (orientation Orientation, err error)
+	Orientation() (orientation types.Orientation, err error)
 
-	SetRotation(rotation Rotation) (err error)
+	SetRotation(rotation types.Rotation) (err error)
-	Rotation() (rotation Rotation, err error)
+	Rotation() (rotation types.Rotation, err error)
 
 	// Tap Sends a tap event at the coordinate.
 	Tap(x, y float64, opts ...option.ActionOption) error
@@ -110,10 +111,10 @@ type IDriver interface {
 	Swipe(fromX, fromY, toX, toY float64, opts ...option.ActionOption) error
 
 	// SetPasteboard Sets data to the general pasteboard
-	SetPasteboard(contentType PasteboardType, content string) error
+	SetPasteboard(contentType types.PasteboardType, content string) error
 	// GetPasteboard Gets the data contained in the general pasteboard.
 	//  It worked when `WDA` was foreground. https://github.com/appium/WebDriverAgent/issues/330
-	GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error)
+	GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error)
 
 	SetIme(ime string) error
 
@@ -128,7 +129,7 @@ type IDriver interface {
 	Clear(packageName string) error
 
 	// PressButton Presses the corresponding hardware button on the device
-	PressButton(devBtn DeviceButton) error
+	PressButton(devBtn types.DeviceButton) error
 
 	// PressBack Presses the back button
 	PressBack(opts ...option.ActionOption) error
@@ -177,6 +178,13 @@ type IDriverExt interface {
 
 	GetScreenResult(opts ...option.ActionOption) (screenResult *ScreenResult, err error)
 	GetScreenTexts(opts ...option.ActionOption) (ocrTexts ai.OCRTexts, err error)
+	GetScreenShot(fileName string) (raw *bytes.Buffer, path string, err error)
+
+	TapByOCR(ocrText string, opts ...option.ActionOption) error
+	TapXY(x, y float64, opts ...option.ActionOption) error
+	TapAbsXY(x, y float64, opts ...option.ActionOption) error
+	TapOffset(param string, xOffset, yOffset float64, opts ...option.ActionOption) (err error)
+	TapByUIDetection(opts ...option.ActionOption) error
 
 	// swipe
 	SwipeRelative(fromX, fromY, toX, toY float64, opts ...option.ActionOption) error
@@ -184,15 +192,25 @@ type IDriverExt interface {
 	SwipeDown(opts ...option.ActionOption) error
 	SwipeLeft(opts ...option.ActionOption) error
 	SwipeRight(opts ...option.ActionOption) error
+
+	SwipeToTapApp(appName string, opts ...option.ActionOption) error
+
+	CheckPopup() (popup *PopupInfo, err error)
+	ClosePopupsHandler() error
+
+	DoAction(action MobileAction) (err error)
+	DoValidation(check, assert, expected string, message ...string) (err error)
 }
 
 func NewDriverExt(driver IDriver, opts ...ai.AIServiceOption) (IDriverExt, error) {
 	services := ai.NewAIService(opts...)
 	driverExt := &DriverExt{
-		Driver:       driver,
+		Driver:     driver,
-		ImageService: services.ImageService,
+		CVService:  services.ICVService,
+		LLMService: services.ILLMService,
 	}
 	// create results directory
+	// TODO: move to setup
 	if err := builtin.EnsureFolderExists(config.ResultsPath); err != nil {
 		return nil, errors.Wrap(err, "create results directory failed")
 	}
@@ -203,25 +221,9 @@ func NewDriverExt(driver IDriver, opts ...ai.AIServiceOption) (IDriverExt, error
 }
 
 type DriverExt struct {
-	Driver       IDriver
+	Driver     IDriver
-	ImageService ai.IImageService // used to extract image data
+	CVService  ai.ICVService  // OCR/CV
-}
+	LLMService ai.ILLMService // LLM
-
-func newDriverExt(device IDevice, driver IDriver, opts ...option.DriverOption) (dExt *DriverExt, err error) {
-	options := option.NewDriverOptions(opts...)
-
-	dExt = &DriverExt{
-		Driver: driver,
-	}
-
-	if options.WithImageService {
-		if dExt.ImageService, err = ai.NewVEDEMImageService(); err != nil {
-			return nil, err
-		}
-	}
-	if options.WithResultFolder {
-	}
-	return dExt, nil
 }
 
 func (dExt *DriverExt) GetDriver() IDriver {

pkg/uixt/driver_action.go

@@ -13,6 +13,7 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 type ActionMethod string
@@ -169,7 +170,7 @@ func (dExt *DriverExt) DoAction(action MobileAction) (err error) {
 			ACTION_AppLaunch, action.Params)
 	case ACTION_SwipeToTapApp:
 		if appName, ok := action.Params.(string); ok {
-			return dExt.swipeToTapApp(appName, action.GetOptions()...)
+			return dExt.SwipeToTapApp(appName, action.GetOptions()...)
 		}
 		return fmt.Errorf("invalid %s params, should be app name(string), got %v",
 			ACTION_SwipeToTapApp, action.Params)
@@ -201,7 +202,7 @@ func (dExt *DriverExt) DoAction(action MobileAction) (err error) {
 		return fmt.Errorf("app_terminate params should be bundleId(string), got %v", action.Params)
 	case ACTION_SetClipboard:
 		if text, ok := action.Params.(string); ok {
-			err := dExt.Driver.SetPasteboard(PasteboardTypePlaintext, text)
+			err := dExt.Driver.SetPasteboard(types.PasteboardTypePlaintext, text)
 			if err != nil {
 				return errors.Wrap(err, "failed to set clipboard")
 			}
@@ -280,7 +281,7 @@ func (dExt *DriverExt) DoAction(action MobileAction) (err error) {
 		return fmt.Errorf("invalid %s params: %v", ACTION_DoubleTap, action.Params)
 	case ACTION_Swipe:
 		params := action.Params
-		swipeAction := dExt.prepareSwipeAction(params, action.GetOptions()...)
+		swipeAction := prepareSwipeAction(dExt, params, action.GetOptions()...)
 		return swipeAction(dExt)
 	case ACTION_Input:
 		// input text on current active element
@@ -328,7 +329,7 @@ func (dExt *DriverExt) DoAction(action MobileAction) (err error) {
 	case ACTION_ScreenShot:
 		// take screenshot
 		log.Info().Msg("take screenshot for current screen")
-		_, err := dExt.GetScreenResult(action.GetOptions()...)
+		_, err := dExt.GetScreenResult(action.GetScreenOptions()...)
 		return err
 	case ACTION_StartCamera:
 		return dExt.Driver.StartCamera()

pkg/uixt/driver_popups.go

@@ -5,7 +5,7 @@ import (
 	"github.com/rs/zerolog/log"
 
 	"github.com/httprunner/httprunner/v5/code"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
 )
 

pkg/uixt/driver_screenshot.go

@@ -18,14 +18,15 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/internal/config"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 type ScreenResult struct {
 	bufSource   *bytes.Buffer  // raw image buffer bytes
 	ImagePath   string         `json:"image_path"` // image file path
-	Resolution  ai.Size        `json:"resolution"`
+	Resolution  types.Size     `json:"resolution"`
 	UploadedURL string         `json:"uploaded_url"` // uploaded image url
 	Texts       ai.OCRTexts    `json:"texts"`        // dumped raw OCRTexts
 	Icons       ai.UIResultMap `json:"icons"`        // CV 识别的图标
@@ -46,26 +47,26 @@ func (s *ScreenResult) FilterTextsByScope(x1, y1, x2, y2 float64) ai.OCRTexts {
 
 // GetScreenResult takes a screenshot, returns the image recognition result
 func (dExt *DriverExt) GetScreenResult(opts ...option.ActionOption) (screenResult *ScreenResult, err error) {
-	actionOptions := option.NewActionOptions(opts...)
+	screenshotOptions := option.NewActionOptions(opts...)
 
 	var fileName string
-	screenshotActions := actionOptions.ScreenshotActions()
+	optionsList := screenshotOptions.List()
-	if actionOptions.ScreenShotFileName != "" {
+	if screenshotOptions.ScreenShotFileName != "" {
-		fileName = builtin.GenNameWithTimestamp("%d_" + actionOptions.ScreenShotFileName)
+		fileName = builtin.GenNameWithTimestamp("%d_" + screenshotOptions.ScreenShotFileName)
-	} else if len(screenshotActions) != 0 {
+	} else if len(optionsList) != 0 {
-		fileName = builtin.GenNameWithTimestamp("%d_" + strings.Join(screenshotActions, "_"))
+		fileName = builtin.GenNameWithTimestamp("%d_" + strings.Join(optionsList, "_"))
 	} else {
 		fileName = builtin.GenNameWithTimestamp("%d_screenshot")
 	}
 
 	var bufSource *bytes.Buffer
-	var imageResult *ai.ImageResult
+	var imageResult *ai.CVResult
 	var imagePath string
-	var windowSize ai.Size
+	var windowSize types.Size
 	var lastErr error
 
 	// get screenshot info with retry
-	for i := 0; i <= actionOptions.MaxRetryTimes; i++ {
+	for i := 0; i < 3; i++ {
 		bufSource, imagePath, err = dExt.GetScreenShot(fileName)
 		if err != nil {
 			lastErr = err
@@ -85,9 +86,9 @@ func (dExt *DriverExt) GetScreenResult(opts ...option.ActionOption) (screenResul
 			Tags:       nil,
 			Resolution: windowSize,
 		}
-		imageResult, err = dExt.ImageService.GetImageFromBuffer(bufSource, opts...)
+		imageResult, err = dExt.CVService.ReadFromBuffer(bufSource, opts...)
 		if err != nil {
-			log.Error().Err(err).Msg("GetImageFromBuffer from ImageService failed")
+			log.Error().Err(err).Msg("ReadFromBuffer from ImageService failed")
 			lastErr = err
 			continue
 		}
@@ -107,7 +108,7 @@ func (dExt *DriverExt) GetScreenResult(opts ...option.ActionOption) (screenResul
 		screenResult.UploadedURL = imageResult.URL
 		screenResult.Icons = imageResult.UIResult
 
-		if actionOptions.ScreenShotWithClosePopups && imageResult.ClosePopupsResult != nil {
+		if screenshotOptions.ScreenShotWithClosePopups && imageResult.ClosePopupsResult != nil {
 			screenResult.Popup = &PopupInfo{
 				ClosePopupsResult: imageResult.ClosePopupsResult,
 				PicName:           imagePath,
@@ -129,8 +130,8 @@ func (dExt *DriverExt) GetScreenResult(opts ...option.ActionOption) (screenResul
 }
 
 func (dExt *DriverExt) GetScreenTexts(opts ...option.ActionOption) (ocrTexts ai.OCRTexts, err error) {
-	actionOptions := option.NewActionOptions(opts...)
+	options := option.NewActionOptions(opts...)
-	if actionOptions.ScreenShotFileName == "" {
+	if options.ScreenShotFileName == "" {
 		opts = append(opts, option.WithScreenShotFileName("get_screen_texts"))
 	}
 	opts = append(opts, option.WithScreenShotOCR(true), option.WithScreenShotUpload(true))
@@ -152,8 +153,8 @@ func (dExt *DriverExt) FindUIRectInUIKit(search string, opts ...option.ActionOpt
 }
 
 func (dExt *DriverExt) FindScreenText(text string, opts ...option.ActionOption) (point ai.PointF, err error) {
-	actionOptions := option.NewActionOptions(opts...)
+	options := option.NewActionOptions(opts...)
-	if actionOptions.ScreenShotFileName == "" {
+	if options.ScreenShotFileName == "" {
 		opts = append(opts, option.WithScreenShotFileName(fmt.Sprintf("find_screen_text_%s", text)))
 	}
 	ocrTexts, err := dExt.GetScreenTexts(opts...)
@@ -161,7 +162,7 @@ func (dExt *DriverExt) FindScreenText(text string, opts ...option.ActionOption)
 		return
 	}
 
-	result, err := ocrTexts.FindText(text, dExt.ParseActionOptions(opts...)...)
+	result, err := ocrTexts.FindText(text, opts...)
 	if err != nil {
 		log.Warn().Msgf("FindText failed: %s", err.Error())
 		return
@@ -174,10 +175,10 @@ func (dExt *DriverExt) FindScreenText(text string, opts ...option.ActionOption)
 }
 
 func (dExt *DriverExt) FindUIResult(opts ...option.ActionOption) (point ai.PointF, err error) {
-	actionOptions := option.NewActionOptions(opts...)
+	options := option.NewActionOptions(opts...)
-	if actionOptions.ScreenShotFileName == "" {
+	if options.ScreenShotFileName == "" {
 		opts = append(opts, option.WithScreenShotFileName(
-			fmt.Sprintf("find_ui_result_%s", strings.Join(actionOptions.ScreenShotWithUITypes, "_"))))
+			fmt.Sprintf("find_ui_result_%s", strings.Join(options.ScreenShotWithUITypes, "_"))))
 	}
 
 	screenResult, err := dExt.GetScreenResult(opts...)
@@ -185,14 +186,14 @@ func (dExt *DriverExt) FindUIResult(opts ...option.ActionOption) (point ai.Point
 		return
 	}
 
-	uiResults, err := screenResult.Icons.FilterUIResults(actionOptions.ScreenShotWithUITypes)
+	uiResults, err := screenResult.Icons.FilterUIResults(options.ScreenShotWithUITypes)
 	if err != nil {
 		return
 	}
-	uiResult, err := uiResults.GetUIResult(dExt.ParseActionOptions(opts...)...)
+	uiResult, err := uiResults.GetUIResult(opts...)
 	point = uiResult.Center()
 
-	log.Info().Interface("text", actionOptions.ScreenShotWithUITypes).
+	log.Info().Interface("text", options.ScreenShotWithUITypes).
 		Interface("point", point).Msg("FindUIResult success")
 	return
 }

pkg/uixt/driver_session.go

@@ -12,7 +12,7 @@ import (
 	"time"
 
 	"github.com/httprunner/httprunner/v5/internal/json"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
@@ -25,7 +25,7 @@ type Session struct {
 
 	// cache to avoid repeated query
 	scale      float64
-	windowSize ai.Size
+	windowSize types.Size
 
 	// cache uia2/wda request and response
 	requests []*DriverRequests

pkg/uixt/driver_swipe.go

@@ -10,7 +10,7 @@ import (
 
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
 )
 
@@ -86,7 +86,7 @@ func (dExt *DriverExt) LoopUntil(findAction, findCondition, foundAction Action,
 		fmt.Sprintf("loop %d times, match find condition failed", maxRetryTimes))
 }
 
-func (dExt *DriverExt) prepareSwipeAction(params interface{}, opts ...option.ActionOption) func(d *DriverExt) error {
+func prepareSwipeAction(dExt *DriverExt, params interface{}, opts ...option.ActionOption) func(d *DriverExt) error {
 	actionOptions := option.NewActionOptions(opts...)
 
 	var swipeDirection interface{}
@@ -177,11 +177,11 @@ func (dExt *DriverExt) swipeToTapTexts(texts []string, opts ...option.ActionOpti
 		return d.TapAbsXY(point.X, point.Y, opts...)
 	}
 
-	findAction := dExt.prepareSwipeAction(nil, optionsWithoutIdentifier...)
+	findAction := prepareSwipeAction(dExt, nil, optionsWithoutIdentifier...)
 	return dExt.LoopUntil(findAction, findTexts, foundTextAction, optionsWithoutIdentifier...)
 }
 
-func (dExt *DriverExt) swipeToTapApp(appName string, opts ...option.ActionOption) error {
+func (dExt *DriverExt) SwipeToTapApp(appName string, opts ...option.ActionOption) error {
 	// go to home screen
 	if err := dExt.Driver.Homescreen(); err != nil {
 		return errors.Wrap(err, "go to home screen failed")

pkg/uixt/driver_swipe_test.go

@@ -11,28 +11,30 @@ import (
 func TestAndroidSwipeAction(t *testing.T) {
 	setupAndroidAdbDriver(t)
 
-	swipeAction := driverExt.prepareSwipeAction("up", option.WithDirection("down"))
+	dExt := driverExt.(*DriverExt)
-	err := swipeAction(driverExt)
+	swipeAction := prepareSwipeAction(dExt, "up", option.WithDirection("down"))
+	err := swipeAction(dExt)
 	checkErr(t, err)
 
-	swipeAction = driverExt.prepareSwipeAction("up", option.WithCustomDirection(0.5, 0.5, 0.5, 0.9))
+	swipeAction = prepareSwipeAction(dExt, "up", option.WithCustomDirection(0.5, 0.5, 0.5, 0.9))
-	err = swipeAction(driverExt)
+	err = swipeAction(dExt)
 	checkErr(t, err)
 }
 
 func TestAndroidSwipeToTapApp(t *testing.T) {
 	setupAndroidAdbDriver(t)
 
-	err := driverExt.swipeToTapApp("抖音")
+	err := driverExt.SwipeToTapApp("抖音")
 	checkErr(t, err)
 }
 
 func TestAndroidSwipeToTapTexts(t *testing.T) {
 	setupAndroidAdbDriver(t)
 
-	err := driverExt.Driver.AppLaunch("com.ss.android.ugc.aweme")
+	err := driverExt.GetDriver().AppLaunch("com.ss.android.ugc.aweme")
 	checkErr(t, err)
 
-	err = driverExt.swipeToTapTexts([]string{"点击进入直播间", "直播中"}, option.WithDirection("up"))
+	dExt := driverExt.(*DriverExt)
+	err = dExt.swipeToTapTexts([]string{"点击进入直播间", "直播中"}, option.WithDirection("up"))
 	checkErr(t, err)
 }

pkg/uixt/driver_tap.go

@@ -51,11 +51,11 @@ func (dExt *DriverExt) TapByOCR(ocrText string, opts ...option.ActionOption) err
 }
 
 func (dExt *DriverExt) TapByUIDetection(opts ...option.ActionOption) error {
-	actionOptions := option.NewActionOptions(opts...)
+	options := option.NewActionOptions(opts...)
 
 	point, err := dExt.FindUIResult(opts...)
 	if err != nil {
-		if actionOptions.IgnoreNotFoundError {
+		if options.IgnoreNotFoundError {
 			return nil
 		}
 		return err
@@ -69,11 +69,11 @@ func (dExt *DriverExt) Tap(param string, opts ...option.ActionOption) error {
 }
 
 func (dExt *DriverExt) TapOffset(param string, xOffset, yOffset float64, opts ...option.ActionOption) (err error) {
-	actionOptions := option.NewActionOptions(opts...)
+	options := option.NewActionOptions(opts...)
 
 	point, err := dExt.FindUIRectInUIKit(param, opts...)
 	if err != nil {
-		if actionOptions.IgnoreNotFoundError {
+		if options.IgnoreNotFoundError {
 			return nil
 		}
 		return err

pkg/uixt/driver_test.go

@@ -3,20 +3,14 @@ package uixt
 import (
 	"testing"
 
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 )
 
 func TestNewDriverExt(t *testing.T) {
 	device, _ := NewAndroidDevice()
 	var driver IDriver
 	var err error
-	if device.UIA2 || device.LogOn {
+	driver, err = NewADBDriver(device)
-		driver, err = NewUIA2Driver(device)
-	} else if device.STUB {
-		driver, err = NewStubAndroidDriver(device)
-	} else {
-		driver, err = NewADBDriver(device)
-	}
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -24,6 +18,12 @@ func TestNewDriverExt(t *testing.T) {
 	driverExt, _ := NewDriverExt(driver,
 		ai.WithCVService(ai.CVServiceTypeVEDEM))
 
-	driverExt.GetDriver()
+	texts, _ := driverExt.GetScreenTexts()
-	t.Log(driverExt)
+	t.Log(texts)
+
+	// get original dirver
+	driver = driverExt.GetDriver().(*ADBDriver)
+
+	// get device
+	device = driver.GetDevice().(*AndroidDevice)
 }

pkg/uixt/harmony_device.go

@@ -1,19 +1,14 @@
 package uixt
 
 import (
-	"fmt"
-
 	"code.byted.org/iesqa/ghdc"
 	"github.com/pkg/errors"
 	"github.com/rs/zerolog/log"
 
 	"github.com/httprunner/httprunner/v5/code"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
-)
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
-
-var (
-	HdcServerHost = "localhost"
-	HdcServerPort = ghdc.HdcServerPort // 5037
 )
 
 type HarmonyDevice struct {
@@ -23,65 +18,53 @@ type HarmonyDevice struct {
 
 func NewHarmonyDevice(opts ...option.HarmonyDeviceOption) (device *HarmonyDevice, err error) {
 	deviceConfig := option.NewHarmonyDeviceOptions(opts...)
-	deviceList, err := GetHarmonyDevices(deviceConfig.ConnectKey)
+
+	// get all attached android devices
+	hdcClient, err := ghdc.NewClientWith(option.HdcServerHost, option.HdcServerPort)
 	if err != nil {
-		return nil, errors.Wrap(code.DeviceConnectionError, err.Error())
+		return nil, err
+	}
+	devices, err := hdcClient.DeviceList()
+	if err != nil {
+		return nil, err
+	}
+	if len(devices) == 0 {
+		return nil, errors.Wrapf(code.DeviceConnectionError,
+			"no attached harmony devices")
 	}
 
-	if deviceConfig.ConnectKey == "" && len(deviceList) > 1 {
+	// filter device by serial
-		return nil, errors.Wrap(code.DeviceConnectionError, "more than one device connected, please specify the serial")
+	var harmonyDevice *ghdc.Device
-	}
-
-	dev := deviceList[0]
 	if deviceConfig.ConnectKey == "" {
-		selectSerial := dev.Serial()
+		if len(devices) > 1 {
-		deviceConfig.ConnectKey = selectSerial
+			return nil, errors.Wrap(code.DeviceConnectionError,
-		log.Warn().
+				"more than one device connected, please specify the serial")
-			Str("connectKey", deviceConfig.ConnectKey).
+		}
-			Msg("harmony ConnectKey is not specified, select the first one")
+		harmonyDevice = &devices[0]
+		deviceConfig.ConnectKey = harmonyDevice.Serial()
+		log.Warn().Str("serial", deviceConfig.ConnectKey).
+			Msg("harmony ConnectKey is not specified, select the attached one")
+	} else {
+		for _, d := range devices {
+			if d.Serial() == deviceConfig.ConnectKey {
+				harmonyDevice = &d
+				break
+			}
+		}
+		if harmonyDevice == nil {
+			return nil, errors.Wrapf(code.DeviceConnectionError,
+				"harmony device %s not attached", harmonyDevice.Serial())
+		}
 	}
 
 	device = &HarmonyDevice{
 		HarmonyDeviceOptions: deviceConfig,
-		Device:               dev,
+		Device:               harmonyDevice,
 	}
 	log.Info().Str("connectKey", device.ConnectKey).Msg("init harmony device")
 	return device, nil
 }
 
-func GetHarmonyDevices(serial ...string) (devices []*ghdc.Device, err error) {
-	var hdcClient ghdc.Client
-	if hdcClient, err = ghdc.NewClientWith(HdcServerHost, HdcServerPort); err != nil {
-		return nil, err
-	}
-	var deviceList []ghdc.Device
-
-	if deviceList, err = hdcClient.DeviceList(); err != nil {
-		return nil, err
-	}
-
-	// filter by serial
-	for _, d := range deviceList {
-		for _, s := range serial {
-			if s != "" && s != d.Serial() {
-				continue
-			}
-			devices = append(devices, &d)
-		}
-	}
-
-	if len(devices) == 0 {
-		var err error
-		if serial == nil || (len(serial) == 1 && serial[0] == "") {
-			err = fmt.Errorf("no harmony device found")
-		} else {
-			err = fmt.Errorf("no harmony device found for serial %v", serial)
-		}
-		return nil, err
-	}
-	return devices, nil
-}
-
 func (dev *HarmonyDevice) Setup() error {
 	return nil
 }
@@ -106,7 +89,26 @@ func (dev *HarmonyDevice) Uninstall(packageName string) error {
 	return nil
 }
 
-func (dev *HarmonyDevice) GetPackageInfo(packageName string) (AppInfo, error) {
+func (dev *HarmonyDevice) GetPackageInfo(packageName string) (types.AppInfo, error) {
 	log.Warn().Msg("get package info not implemented for harmony device, skip")
-	return AppInfo{}, nil
+	return types.AppInfo{}, nil
+}
+
+func (dev *HarmonyDevice) NewDriver() (IDriverExt, error) {
+	// init harmony driver
+	driver, err := NewHDCDriver(dev)
+	if err != nil {
+		return nil, errors.Wrap(err, "init harmony driver failed")
+	}
+	driverExt, err := NewDriverExt(driver, ai.WithCVService(ai.CVServiceTypeVEDEM))
+	if err != nil {
+		return nil, errors.Wrap(err, "init harmony driver ext failed")
+	}
+
+	// setup driver
+	if err := driverExt.GetDriver().Setup(); err != nil {
+		return nil, err
+	}
+
+	return driverExt, nil
 }

pkg/uixt/harmony_driver_hdc.go

@@ -10,8 +10,9 @@ import (
 	"code.byted.org/iesqa/ghdc"
 	"github.com/rs/zerolog/log"
 
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 type HDCDriver struct {
@@ -58,31 +59,31 @@ func (hd *HDCDriver) GetSession() *Session {
 	return hd.Session
 }
 
-func (hd *HDCDriver) Status() (DeviceStatus, error) {
+func (hd *HDCDriver) Status() (types.DeviceStatus, error) {
-	return DeviceStatus{}, errDriverNotImplemented
+	return types.DeviceStatus{}, errDriverNotImplemented
 }
 
 func (hd *HDCDriver) GetDevice() IDevice {
 	return hd.HarmonyDevice
 }
 
-func (hd *HDCDriver) DeviceInfo() (DeviceInfo, error) {
+func (hd *HDCDriver) DeviceInfo() (types.DeviceInfo, error) {
-	return DeviceInfo{}, errDriverNotImplemented
+	return types.DeviceInfo{}, errDriverNotImplemented
 }
 
-func (hd *HDCDriver) Location() (Location, error) {
+func (hd *HDCDriver) Location() (types.Location, error) {
-	return Location{}, errDriverNotImplemented
+	return types.Location{}, errDriverNotImplemented
 }
 
-func (hd *HDCDriver) BatteryInfo() (BatteryInfo, error) {
+func (hd *HDCDriver) BatteryInfo() (types.BatteryInfo, error) {
-	return BatteryInfo{}, errDriverNotImplemented
+	return types.BatteryInfo{}, errDriverNotImplemented
 }
 
-func (hd *HDCDriver) WindowSize() (size ai.Size, err error) {
+func (hd *HDCDriver) WindowSize() (size types.Size, err error) {
 	display, err := hd.uiDriver.GetDisplaySize()
 	if err != nil {
 		log.Error().Err(err).Msg("failed to get window size")
-		return ai.Size{}, err
+		return types.Size{}, err
 	}
 	size.Width = display.Width
 	size.Height = display.Height
@@ -137,9 +138,9 @@ func (hd *HDCDriver) AppTerminate(packageName string) (bool, error) {
 	return true, nil
 }
 
-func (hd *HDCDriver) GetForegroundApp() (app AppInfo, err error) {
+func (hd *HDCDriver) GetForegroundApp() (app types.AppInfo, err error) {
 	// Todo
-	return AppInfo{}, errDriverNotImplemented
+	return types.AppInfo{}, errDriverNotImplemented
 }
 
 func (hd *HDCDriver) AssertForegroundApp(packageName string, activityType ...string) error {
@@ -155,8 +156,8 @@ func (hd *HDCDriver) StopCamera() error {
 	return errDriverNotImplemented
 }
 
-func (hd *HDCDriver) Orientation() (orientation Orientation, err error) {
+func (hd *HDCDriver) Orientation() (orientation types.Orientation, err error) {
-	return OrientationPortrait, nil
+	return types.OrientationPortrait, nil
 }
 
 func (hd *HDCDriver) Tap(x, y float64, opts ...option.ActionOption) error {
@@ -213,11 +214,11 @@ func (hd *HDCDriver) Swipe(fromX, fromY, toX, toY float64, opts ...option.Action
 	return hd.uiDriver.InjectGesture(ghdc.NewGesture().Start(ghdc.Point{X: int(fromX), Y: int(fromY)}).MoveTo(ghdc.Point{X: int(toX), Y: int(toY)}, duration))
 }
 
-func (hd *HDCDriver) SetPasteboard(contentType PasteboardType, content string) error {
+func (hd *HDCDriver) SetPasteboard(contentType types.PasteboardType, content string) error {
 	return errDriverNotImplemented
 }
 
-func (hd *HDCDriver) GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error) {
+func (hd *HDCDriver) GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error) {
 	return nil, errDriverNotImplemented
 }
 
@@ -237,7 +238,7 @@ func (hd *HDCDriver) Clear(packageName string) error {
 	return errDriverNotImplemented
 }
 
-func (hd *HDCDriver) PressButton(devBtn DeviceButton) error {
+func (hd *HDCDriver) PressButton(devBtn types.DeviceButton) error {
 	return errDriverNotImplemented
 }
 
@@ -343,12 +344,12 @@ func (hd *HDCDriver) TearDown() error {
 	return nil
 }
 
-func (hd *HDCDriver) Rotation() (rotation Rotation, err error) {
+func (hd *HDCDriver) Rotation() (rotation types.Rotation, err error) {
 	err = errDriverNotImplemented
 	return
 }
 
-func (hd *HDCDriver) SetRotation(rotation Rotation) (err error) {
+func (hd *HDCDriver) SetRotation(rotation types.Rotation) (err error) {
 	err = errDriverNotImplemented
 	return
 }

pkg/uixt/ios_device.go

@@ -28,7 +28,9 @@ import (
 
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 var tunnelManager *tunnel.TunnelManager = nil
@@ -207,10 +209,10 @@ func (dev *IOSDevice) LogEnabled() bool {
 	return dev.LogOn
 }
 
-func (dev *IOSDevice) getAppInfo(packageName string) (appInfo AppInfo, err error) {
+func (dev *IOSDevice) getAppInfo(packageName string) (appInfo types.AppInfo, err error) {
 	apps, err := dev.ListApps(ApplicationTypeAny)
 	if err != nil {
-		return AppInfo{}, err
+		return types.AppInfo{}, err
 	}
 	for _, app := range apps {
 		if app.CFBundleIdentifier == packageName {
@@ -222,27 +224,18 @@ func (dev *IOSDevice) getAppInfo(packageName string) (appInfo AppInfo, err error
 			return appInfo, err
 		}
 	}
-	return AppInfo{}, fmt.Errorf("not found App by bundle id: %s", packageName)
+	return types.AppInfo{}, fmt.Errorf("not found App by bundle id: %s", packageName)
 }
 
-func (dev *IOSDevice) NewDriver(opts ...option.DriverOption) (driverExt *DriverExt, err error) {
+func (dev *IOSDevice) NewDriver() (driverExt IDriverExt, err error) {
-	options := option.NewDriverOptions()
-
-	// init WDA driver
-	capabilities := options.Capabilities
-	if capabilities == nil {
-		capabilities = option.NewCapabilities()
-		capabilities.WithDefaultAlertAction(option.AlertActionAccept)
-	}
-
 	var driver IDriver
 	if dev.STUB {
-		driver, err = dev.NewStubDriver()
+		driver, err = NewStubIOSDriver(dev)
 		if err != nil {
 			return nil, errors.Wrap(err, "failed to init Stub driver")
 		}
 	} else {
-		driver, err = dev.NewHTTPDriver(capabilities)
+		driver, err := NewWDADriver(dev)
 		if err != nil {
 			return nil, errors.Wrap(err, "failed to init WDA driver")
 		}
@@ -264,12 +257,7 @@ func (dev *IOSDevice) NewDriver(opts ...option.DriverOption) (driverExt *DriverE
 		}
 	}
 
-	driverExt, err = newDriverExt(dev, driver, opts...)
+	settings, err := driver.SetAppiumSettings(map[string]interface{}{
-	if err != nil {
-		return nil, err
-	}
-
-	settings, err := driverExt.Driver.SetAppiumSettings(map[string]interface{}{
 		"snapshotMaxDepth":          dev.SnapshotMaxDepth,
 		"acceptAlertButtonSelector": dev.AcceptAlertButtonSelector,
 	})
@@ -279,12 +267,22 @@ func (dev *IOSDevice) NewDriver(opts ...option.DriverOption) (driverExt *DriverE
 	log.Info().Interface("appiumWDASettings", settings).Msg("set appium WDA settings")
 
 	if dev.LogOn {
-		err = driverExt.Driver.StartCaptureLog("hrp_wda_log")
+		err = driver.StartCaptureLog("hrp_wda_log")
 		if err != nil {
 			return nil, err
 		}
 	}
 
+	driverExt, err = NewDriverExt(driver, ai.WithCVService(ai.CVServiceTypeVEDEM))
+	if err != nil {
+		return nil, errors.Wrap(err, "init ios driver ext failed")
+	}
+
+	// setup driver
+	if err := driverExt.GetDriver().Setup(); err != nil {
+		return nil, err
+	}
+
 	return driverExt, nil
 }
 
@@ -587,52 +585,16 @@ func (dev *IOSDevice) NewHTTPDriver(capabilities option.Capabilities) (driver ID
 	return wd, nil
 }
 
-const (
+func (dev *IOSDevice) GetPackageInfo(packageName string) (types.AppInfo, error) {
-	defaultBightInsightPort = 8000
-	defaultDouyinServerPort = 32921
-)
-
-func (dev *IOSDevice) NewStubDriver() (driver IDriver, err error) {
-	localStubPort, err := builtin.GetFreePort()
-	if err != nil {
-		return nil, errors.Wrap(code.DeviceHTTPDriverError,
-			fmt.Sprintf("get free port failed: %v", err))
-	}
-
-	if err = dev.forward(localStubPort, defaultBightInsightPort); err != nil {
-		return nil, errors.Wrap(code.DeviceHTTPDriverError,
-			fmt.Sprintf("forward tcp port failed: %v", err))
-	}
-
-	localServerPort, err := builtin.GetFreePort()
-	if err != nil {
-		return nil, errors.Wrap(code.DeviceHTTPDriverError,
-			fmt.Sprintf("get free port failed: %v", err))
-	}
-	if err = dev.forward(localServerPort, defaultDouyinServerPort); err != nil {
-		return nil, errors.Wrap(code.DeviceHTTPDriverError,
-			fmt.Sprintf("forward tcp port failed: %v", err))
-	}
-	host := "localhost"
-	stubDriver, err := newStubIOSDriver(
-		fmt.Sprintf("http://%s:%d", host, localStubPort),
-		fmt.Sprintf("http://%s:%d", host, localServerPort), dev)
-	if err != nil {
-		return nil, err
-	}
-	return stubDriver, nil
-}
-
-func (dev *IOSDevice) GetPackageInfo(packageName string) (AppInfo, error) {
 	svc, err := installationproxy.New(dev.d)
 	if err != nil {
-		return AppInfo{}, errors.Wrap(code.DeviceGetInfoError, err.Error())
+		return types.AppInfo{}, errors.Wrap(code.DeviceGetInfoError, err.Error())
 	}
 	defer svc.Close()
 
 	apps, err := svc.BrowseAllApps()
 	if err != nil {
-		return AppInfo{}, errors.Wrap(code.DeviceGetInfoError, err.Error())
+		return types.AppInfo{}, errors.Wrap(code.DeviceGetInfoError, err.Error())
 	}
 
 	for _, app := range apps {
@@ -640,9 +602,9 @@ func (dev *IOSDevice) GetPackageInfo(packageName string) (AppInfo, error) {
 			continue
 		}
 
-		appInfo := AppInfo{
+		appInfo := types.AppInfo{
 			Name: app.CFBundleName,
-			AppBaseInfo: AppBaseInfo{
+			AppBaseInfo: types.AppBaseInfo{
 				BundleId:    app.CFBundleIdentifier,
 				PackageName: app.CFBundleIdentifier,
 				VersionName: app.CFBundleShortVersionString,
@@ -654,6 +616,6 @@ func (dev *IOSDevice) GetPackageInfo(packageName string) (AppInfo, error) {
 		log.Info().Interface("appInfo", appInfo).Msg("get package info")
 		return appInfo, nil
 	}
-	return AppInfo{}, errors.Wrap(code.DeviceAppNotInstalled,
+	return types.AppInfo{}, errors.Wrap(code.DeviceAppNotInstalled,
 		fmt.Sprintf("%s not found", packageName))
 }

pkg/uixt/ios_driver_stub.go

@@ -7,13 +7,58 @@ import (
 	"net/http"
 	"time"
 
+	"github.com/pkg/errors"
 	"github.com/rs/zerolog/log"
 
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/code"
+	"github.com/httprunner/httprunner/v5/internal/builtin"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
-type stubIOSDriver struct {
+const (
+	defaultBightInsightPort = 8000
+	defaultDouyinServerPort = 32921
+)
+
+func NewStubIOSDriver(device *IOSDevice) (driver *StubIOSDriver, err error) {
+	localStubPort, err := builtin.GetFreePort()
+	if err != nil {
+		return nil, errors.Wrap(code.DeviceHTTPDriverError,
+			fmt.Sprintf("get free port failed: %v", err))
+	}
+
+	if err = device.forward(localStubPort, defaultBightInsightPort); err != nil {
+		return nil, errors.Wrap(code.DeviceHTTPDriverError,
+			fmt.Sprintf("forward tcp port failed: %v", err))
+	}
+
+	localServerPort, err := builtin.GetFreePort()
+	if err != nil {
+		return nil, errors.Wrap(code.DeviceHTTPDriverError,
+			fmt.Sprintf("get free port failed: %v", err))
+	}
+	if err = device.forward(localServerPort, defaultDouyinServerPort); err != nil {
+		return nil, errors.Wrap(code.DeviceHTTPDriverError,
+			fmt.Sprintf("forward tcp port failed: %v", err))
+	}
+
+	host := "localhost"
+	timeout := 10 * time.Second
+	driver = &StubIOSDriver{}
+	driver.device = device
+	driver.bightInsightPrefix = fmt.Sprintf("http://%s:%d", host, localStubPort)
+	driver.serverPrefix = fmt.Sprintf("http://%s:%d", host, localServerPort)
+	driver.timeout = timeout
+	driver.client = &http.Client{
+		Timeout: time.Second * 10, // 设置超时时间为 10 秒
+	}
+
+	return driver, nil
+}
+
+type StubIOSDriver struct {
 	*WDADriver
 
 	bightInsightPrefix string
@@ -22,23 +67,7 @@ type stubIOSDriver struct {
 	device             *IOSDevice
 }
 
-func newStubIOSDriver(bightInsightAddr, serverAddr string, dev *IOSDevice, readTimeout ...time.Duration) (*stubIOSDriver, error) {
+func (s *StubIOSDriver) setUpWda() (err error) {
-	timeout := 10 * time.Second
-	if len(readTimeout) > 0 {
-		timeout = readTimeout[0]
-	}
-	driver := new(stubIOSDriver)
-	driver.device = dev
-	driver.bightInsightPrefix = bightInsightAddr
-	driver.serverPrefix = serverAddr
-	driver.timeout = timeout
-	driver.client = &http.Client{
-		Timeout: time.Second * 10, // 设置超时时间为 10 秒
-	}
-	return driver, nil
-}
-
-func (s *stubIOSDriver) setUpWda() (err error) {
 	if s.WDADriver == nil {
 		capabilities := option.NewCapabilities()
 		capabilities.WithDefaultAlertAction(option.AlertActionAccept)
@@ -53,7 +82,7 @@ func (s *stubIOSDriver) setUpWda() (err error) {
 }
 
 // NewSession starts a new session and returns the DriverSession.
-func (s *stubIOSDriver) NewSession(capabilities option.Capabilities) (Session, error) {
+func (s *StubIOSDriver) NewSession(capabilities option.Capabilities) (Session, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return Session{}, err
@@ -64,7 +93,7 @@ func (s *stubIOSDriver) NewSession(capabilities option.Capabilities) (Session, e
 // DeleteSession Kills application associated with that session and removes session
 //  1. alertsMonitor disable
 //  2. testedApplicationBundleId terminate
-func (s *stubIOSDriver) DeleteSession() error {
+func (s *StubIOSDriver) DeleteSession() error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -72,34 +101,34 @@ func (s *stubIOSDriver) DeleteSession() error {
 	return s.WDADriver.DeleteSession()
 }
 
-func (s *stubIOSDriver) Status() (DeviceStatus, error) {
+func (s *StubIOSDriver) Status() (types.DeviceStatus, error) {
 	err := s.setUpWda()
 	if err != nil {
-		return DeviceStatus{}, err
+		return types.DeviceStatus{}, err
 	}
 	return s.WDADriver.Status()
 }
 
-func (s *stubIOSDriver) DeviceInfo() (DeviceInfo, error) {
+func (s *StubIOSDriver) DeviceInfo() (types.DeviceInfo, error) {
 	err := s.setUpWda()
 	if err != nil {
-		return DeviceInfo{}, err
+		return types.DeviceInfo{}, err
 	}
 	return s.WDADriver.DeviceInfo()
 }
 
-func (s *stubIOSDriver) Location() (Location, error) {
+func (s *StubIOSDriver) Location() (types.Location, error) {
 	err := s.setUpWda()
 	if err != nil {
-		return Location{}, err
+		return types.Location{}, err
 	}
 	return s.WDADriver.Location()
 }
 
-func (s *stubIOSDriver) BatteryInfo() (BatteryInfo, error) {
+func (s *StubIOSDriver) BatteryInfo() (types.BatteryInfo, error) {
 	err := s.setUpWda()
 	if err != nil {
-		return BatteryInfo{}, err
+		return types.BatteryInfo{}, err
 	}
 	return s.WDADriver.BatteryInfo()
 }
@@ -107,15 +136,15 @@ func (s *stubIOSDriver) BatteryInfo() (BatteryInfo, error) {
 // WindowSize Return the width and height in portrait mode.
 // when getting the window size in wda/ui2/adb, if the device is in landscape mode,
 // the width and height will be reversed.
-func (s *stubIOSDriver) WindowSize() (ai.Size, error) {
+func (s *StubIOSDriver) WindowSize() (types.Size, error) {
 	err := s.setUpWda()
 	if err != nil {
-		return ai.Size{}, err
+		return types.Size{}, err
 	}
 	return s.WDADriver.WindowSize()
 }
 
-func (s *stubIOSDriver) Screen() (ai.Screen, error) {
+func (s *StubIOSDriver) Screen() (ai.Screen, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return ai.Screen{}, err
@@ -123,7 +152,7 @@ func (s *stubIOSDriver) Screen() (ai.Screen, error) {
 	return s.WDADriver.Screen()
 }
 
-func (s *stubIOSDriver) Scale() (float64, error) {
+func (s *StubIOSDriver) Scale() (float64, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return 0, err
@@ -132,7 +161,7 @@ func (s *stubIOSDriver) Scale() (float64, error) {
 }
 
 // Homescreen Forces the device under test to switch to the home screen
-func (s *stubIOSDriver) Homescreen() error {
+func (s *StubIOSDriver) Homescreen() error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -140,7 +169,7 @@ func (s *stubIOSDriver) Homescreen() error {
 	return s.WDADriver.Homescreen()
 }
 
-func (s *stubIOSDriver) Unlock() (err error) {
+func (s *StubIOSDriver) Unlock() (err error) {
 	err = s.setUpWda()
 	if err != nil {
 		return err
@@ -150,7 +179,7 @@ func (s *stubIOSDriver) Unlock() (err error) {
 
 // AppLaunch Launch an application with given bundle identifier in scope of current session.
 // !This method is only available since Xcode9 SDK
-func (s *stubIOSDriver) AppLaunch(packageName string) error {
+func (s *StubIOSDriver) AppLaunch(packageName string) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -160,7 +189,7 @@ func (s *stubIOSDriver) AppLaunch(packageName string) error {
 
 // AppTerminate Terminate an application with the given package name.
 // Either `true` if the app has been successfully terminated or `false` if it was not running
-func (s *stubIOSDriver) AppTerminate(packageName string) (bool, error) {
+func (s *StubIOSDriver) AppTerminate(packageName string) (bool, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return false, err
@@ -169,16 +198,16 @@ func (s *stubIOSDriver) AppTerminate(packageName string) (bool, error) {
 }
 
 // GetForegroundApp returns current foreground app package name and activity name
-func (s *stubIOSDriver) GetForegroundApp() (app AppInfo, err error) {
+func (s *StubIOSDriver) GetForegroundApp() (app types.AppInfo, err error) {
 	err = s.setUpWda()
 	if err != nil {
-		return AppInfo{}, err
+		return types.AppInfo{}, err
 	}
 	return s.WDADriver.GetForegroundApp()
 }
 
 // StartCamera Starts a new camera for recording
-func (s *stubIOSDriver) StartCamera() error {
+func (s *StubIOSDriver) StartCamera() error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -187,7 +216,7 @@ func (s *stubIOSDriver) StartCamera() error {
 }
 
 // StopCamera Stops the camera for recording
-func (s *stubIOSDriver) StopCamera() error {
+func (s *StubIOSDriver) StopCamera() error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -195,16 +224,16 @@ func (s *stubIOSDriver) StopCamera() error {
 	return s.WDADriver.StopCamera()
 }
 
-func (s *stubIOSDriver) Orientation() (orientation Orientation, err error) {
+func (s *StubIOSDriver) Orientation() (orientation types.Orientation, err error) {
 	err = s.setUpWda()
 	if err != nil {
-		return OrientationPortrait, err
+		return types.OrientationPortrait, err
 	}
 	return s.WDADriver.Orientation()
 }
 
 // Tap Sends a tap event at the coordinate.
-func (s *stubIOSDriver) Tap(x, y float64, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) Tap(x, y float64, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -213,7 +242,7 @@ func (s *stubIOSDriver) Tap(x, y float64, opts ...option.ActionOption) error {
 }
 
 // DoubleTap Sends a double tap event at the coordinate.
-func (s *stubIOSDriver) DoubleTap(x, y float64, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) DoubleTap(x, y float64, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -224,7 +253,7 @@ func (s *stubIOSDriver) DoubleTap(x, y float64, opts ...option.ActionOption) err
 // TouchAndHold Initiates a long-press gesture at the coordinate, holding for the specified duration.
 //
 //	second: The default value is 1
-func (s *stubIOSDriver) TouchAndHold(x, y float64, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) TouchAndHold(x, y float64, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -234,7 +263,7 @@ func (s *stubIOSDriver) TouchAndHold(x, y float64, opts ...option.ActionOption)
 
 // Drag Initiates a press-and-hold gesture at the coordinate, then drags to another coordinate.
 // WithPressDurationOption option can be used to set pressForDuration (default to 1 second).
-func (s *stubIOSDriver) Drag(fromX, fromY, toX, toY float64, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) Drag(fromX, fromY, toX, toY float64, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -243,7 +272,7 @@ func (s *stubIOSDriver) Drag(fromX, fromY, toX, toY float64, opts ...option.Acti
 }
 
 // SetPasteboard Sets data to the general pasteboard
-func (s *stubIOSDriver) SetPasteboard(contentType PasteboardType, content string) error {
+func (s *StubIOSDriver) SetPasteboard(contentType types.PasteboardType, content string) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -254,7 +283,7 @@ func (s *stubIOSDriver) SetPasteboard(contentType PasteboardType, content string
 // GetPasteboard Gets the data contained in the general pasteboard.
 //
 //	It worked when `WDA` was foreground. https://github.com/appium/WebDriverAgent/issues/330
-func (s *stubIOSDriver) GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error) {
+func (s *StubIOSDriver) GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error) {
 	err = s.setUpWda()
 	if err != nil {
 		return nil, err
@@ -262,7 +291,7 @@ func (s *stubIOSDriver) GetPasteboard(contentType PasteboardType) (raw *bytes.Bu
 	return s.WDADriver.GetPasteboard(contentType)
 }
 
-func (s *stubIOSDriver) SetIme(ime string) error {
+func (s *StubIOSDriver) SetIme(ime string) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -273,7 +302,7 @@ func (s *stubIOSDriver) SetIme(ime string) error {
 // SendKeys Types a string into active element. There must be element with keyboard focus,
 // otherwise an error is raised.
 // WithFrequency option can be used to set frequency of typing (letters per sec). The default value is 60
-func (s *stubIOSDriver) SendKeys(text string, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) SendKeys(text string, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -282,7 +311,7 @@ func (s *stubIOSDriver) SendKeys(text string, opts ...option.ActionOption) error
 }
 
 // Input works like SendKeys
-func (s *stubIOSDriver) Input(text string, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) Input(text string, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -290,7 +319,7 @@ func (s *stubIOSDriver) Input(text string, opts ...option.ActionOption) error {
 	return s.WDADriver.Input(text, opts...)
 }
 
-func (s *stubIOSDriver) Clear(packageName string) error {
+func (s *StubIOSDriver) Clear(packageName string) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -299,7 +328,7 @@ func (s *stubIOSDriver) Clear(packageName string) error {
 }
 
 // PressButton Presses the corresponding hardware button on the device
-func (s *stubIOSDriver) PressButton(devBtn DeviceButton) error {
+func (s *StubIOSDriver) PressButton(devBtn types.DeviceButton) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -308,7 +337,7 @@ func (s *stubIOSDriver) PressButton(devBtn DeviceButton) error {
 }
 
 // PressBack Presses the back button
-func (s *stubIOSDriver) PressBack(opts ...option.ActionOption) error {
+func (s *StubIOSDriver) PressBack(opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -316,7 +345,7 @@ func (s *stubIOSDriver) PressBack(opts ...option.ActionOption) error {
 	return s.WDADriver.PressBack(opts...)
 }
 
-func (s *stubIOSDriver) PressKeyCode(keyCode KeyCode) (err error) {
+func (s *StubIOSDriver) PressKeyCode(keyCode KeyCode) (err error) {
 	err = s.setUpWda()
 	if err != nil {
 		return err
@@ -324,7 +353,7 @@ func (s *stubIOSDriver) PressKeyCode(keyCode KeyCode) (err error) {
 	return s.WDADriver.PressKeyCode(keyCode)
 }
 
-func (s *stubIOSDriver) Screenshot() (*bytes.Buffer, error) {
+func (s *StubIOSDriver) Screenshot() (*bytes.Buffer, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return nil, err
@@ -345,7 +374,7 @@ func (s *stubIOSDriver) Screenshot() (*bytes.Buffer, error) {
 	//return bytes.NewBuffer(imageBytes), nil
 }
 
-func (s *stubIOSDriver) TapByText(text string, opts ...option.ActionOption) error {
+func (s *StubIOSDriver) TapByText(text string, opts ...option.ActionOption) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -353,7 +382,7 @@ func (s *stubIOSDriver) TapByText(text string, opts ...option.ActionOption) erro
 	return s.WDADriver.TapByText(text, opts...)
 }
 
-func (s *stubIOSDriver) TapByTexts(actions ...TapTextAction) error {
+func (s *StubIOSDriver) TapByTexts(actions ...TapTextAction) error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -362,7 +391,7 @@ func (s *stubIOSDriver) TapByTexts(actions ...TapTextAction) error {
 }
 
 // AccessibleSource Return application elements accessibility tree
-func (s *stubIOSDriver) AccessibleSource() (string, error) {
+func (s *StubIOSDriver) AccessibleSource() (string, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return "", err
@@ -375,7 +404,7 @@ func (s *stubIOSDriver) AccessibleSource() (string, error) {
 //	Checks health of XCTest by:
 //	1) Querying application for some elements,
 //	2) Triggering some device events.
-func (s *stubIOSDriver) HealthCheck() error {
+func (s *StubIOSDriver) HealthCheck() error {
 	err := s.setUpWda()
 	if err != nil {
 		return err
@@ -383,7 +412,7 @@ func (s *stubIOSDriver) HealthCheck() error {
 	return s.WDADriver.HealthCheck()
 }
 
-func (s *stubIOSDriver) GetAppiumSettings() (map[string]interface{}, error) {
+func (s *StubIOSDriver) GetAppiumSettings() (map[string]interface{}, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return nil, err
@@ -391,7 +420,7 @@ func (s *stubIOSDriver) GetAppiumSettings() (map[string]interface{}, error) {
 	return s.WDADriver.GetAppiumSettings()
 }
 
-func (s *stubIOSDriver) SetAppiumSettings(settings map[string]interface{}) (map[string]interface{}, error) {
+func (s *StubIOSDriver) SetAppiumSettings(settings map[string]interface{}) (map[string]interface{}, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return nil, err
@@ -399,7 +428,7 @@ func (s *stubIOSDriver) SetAppiumSettings(settings map[string]interface{}) (map[
 	return s.WDADriver.SetAppiumSettings(settings)
 }
 
-func (s *stubIOSDriver) IsHealthy() (bool, error) {
+func (s *StubIOSDriver) IsHealthy() (bool, error) {
 	err := s.setUpWda()
 	if err != nil {
 		return false, err
@@ -408,7 +437,7 @@ func (s *stubIOSDriver) IsHealthy() (bool, error) {
 }
 
 // triggers the log capture and returns the log entries
-func (s *stubIOSDriver) StartCaptureLog(identifier ...string) (err error) {
+func (s *StubIOSDriver) StartCaptureLog(identifier ...string) (err error) {
 	err = s.setUpWda()
 	if err != nil {
 		return err
@@ -416,7 +445,7 @@ func (s *stubIOSDriver) StartCaptureLog(identifier ...string) (err error) {
 	return s.WDADriver.StartCaptureLog(identifier...)
 }
 
-func (s *stubIOSDriver) StopCaptureLog() (result interface{}, err error) {
+func (s *StubIOSDriver) StopCaptureLog() (result interface{}, err error) {
 	err = s.setUpWda()
 	if err != nil {
 		return nil, err
@@ -424,7 +453,7 @@ func (s *stubIOSDriver) StopCaptureLog() (result interface{}, err error) {
 	return s.WDADriver.StopCaptureLog()
 }
 
-func (s *stubIOSDriver) GetDriverResults() []*DriverRequests {
+func (s *StubIOSDriver) GetDriverResults() []*DriverRequests {
 	err := s.setUpWda()
 	if err != nil {
 		return nil
@@ -432,7 +461,7 @@ func (s *stubIOSDriver) GetDriverResults() []*DriverRequests {
 	return s.WDADriver.GetDriverResults()
 }
 
-func (s *stubIOSDriver) Source(srcOpt ...option.SourceOption) (string, error) {
+func (s *StubIOSDriver) Source(srcOpt ...option.SourceOption) (string, error) {
 	resp, err := s.Request(http.MethodGet, fmt.Sprintf("%s/source?format=json&onlyWeb=false", s.bightInsightPrefix), []byte{})
 	if err != nil {
 		return "", err
@@ -440,7 +469,7 @@ func (s *stubIOSDriver) Source(srcOpt ...option.SourceOption) (string, error) {
 	return string(resp), nil
 }
 
-func (s *stubIOSDriver) LoginNoneUI(packageName, phoneNumber string, captcha, password string) (info AppLoginInfo, err error) {
+func (s *StubIOSDriver) LoginNoneUI(packageName, phoneNumber string, captcha, password string) (info AppLoginInfo, err error) {
 	params := map[string]interface{}{
 		"phone": phoneNumber,
 	}
@@ -478,7 +507,7 @@ func (s *stubIOSDriver) LoginNoneUI(packageName, phoneNumber string, captcha, pa
 	return info, nil
 }
 
-func (s *stubIOSDriver) LogoutNoneUI(packageName string) error {
+func (s *StubIOSDriver) LogoutNoneUI(packageName string) error {
 	resp, err := s.Request(http.MethodGet, fmt.Sprintf("%s/host/loginout/", s.serverPrefix), []byte{})
 	if err != nil {
 		return err
@@ -497,12 +526,12 @@ func (s *stubIOSDriver) LogoutNoneUI(packageName string) error {
 	return nil
 }
 
-func (s *stubIOSDriver) TearDown() error {
+func (s *StubIOSDriver) TearDown() error {
 	s.client.CloseIdleConnections()
 	return nil
 }
 
-func (s *stubIOSDriver) getLoginAppInfo(packageName string) (info AppLoginInfo, err error) {
+func (s *StubIOSDriver) getLoginAppInfo(packageName string) (info AppLoginInfo, err error) {
 	resp, err := s.Request(http.MethodGet, fmt.Sprintf("%s/host/app/info/", s.serverPrefix), []byte{})
 	if err != nil {
 		return info, err
@@ -524,6 +553,6 @@ func (s *stubIOSDriver) getLoginAppInfo(packageName string) (info AppLoginInfo,
 	return info, nil
 }
 
-func (s *stubIOSDriver) GetSession() *Session {
+func (s *StubIOSDriver) GetSession() *Session {
 	return s.Session
 }

pkg/uixt/ios_driver_stub_test.go

@@ -11,7 +11,7 @@ import (
 )
 
 var (
-	iOSStubDriver IDriver
+	iOSStubDriver IDriverExt
 	iOSDevice     *IOSDevice
 )
 
@@ -22,56 +22,56 @@ func setupiOSStubDriver(t *testing.T) {
 		option.WithWDAMjpegPort(8800),
 		option.WithIOSStub(false))
 	checkErr(t, err)
-	iOSStubDriver, err = iOSDevice.NewStubDriver()
+	iOSStubDriver, err = iOSDevice.NewDriver()
 	checkErr(t, err)
 }
 
 func TestIOSLogin(t *testing.T) {
 	setupiOSStubDriver(t)
-	info, err := iOSStubDriver.LoginNoneUI("", "12342316231", "8517", "")
+	info, err := iOSStubDriver.GetDriver().LoginNoneUI("", "12342316231", "8517", "")
 	checkErr(t, err)
 	t.Log(info)
 }
 
 func TestIOSLogout(t *testing.T) {
 	setupiOSStubDriver(t)
-	err := iOSStubDriver.LogoutNoneUI("")
+	err := iOSStubDriver.GetDriver().LogoutNoneUI("")
 	checkErr(t, err)
 }
 
 func TestIOSIsLogin(t *testing.T) {
 	setupiOSStubDriver(t)
-	err := iOSStubDriver.LogoutNoneUI("")
+	err := iOSStubDriver.GetDriver().LogoutNoneUI("")
 	checkErr(t, err)
 }
 
 func TestIOSSource(t *testing.T) {
 	setupiOSStubDriver(t)
-	source, err := iOSStubDriver.Source()
+	source, err := iOSStubDriver.GetDriver().Source()
 	checkErr(t, err)
 	t.Log(source)
 }
 
 func TestIOSForeground(t *testing.T) {
 	setupiOSStubDriver(t)
-	app, err := iOSStubDriver.GetForegroundApp()
+	app, err := iOSStubDriver.GetDriver().GetForegroundApp()
 	checkErr(t, err)
 	t.Log(app)
 }
 
 func TestIOSSwipe(t *testing.T) {
 	setupiOSStubDriver(t)
-	iOSStubDriver.Swipe(540, 0, 540, 1000)
+	iOSStubDriver.GetDriver().Swipe(540, 0, 540, 1000)
 }
 
 func TestIOSSave(t *testing.T) {
 	setupiOSStubDriver(t)
-	raw, err := iOSStubDriver.Screenshot()
+	raw, err := iOSStubDriver.GetDriver().Screenshot()
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	source, err := iOSStubDriver.Source()
+	source, err := iOSStubDriver.GetDriver().Source()
 	if err != nil {
 		t.Fatal(err)
 	}

pkg/uixt/ios_driver_wda.go

@@ -23,8 +23,9 @@ import (
 	"github.com/httprunner/httprunner/v5/code"
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 	"github.com/httprunner/httprunner/v5/internal/json"
-	"github.com/httprunner/httprunner/v5/pkg/ai"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/ai"
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 func NewWDADriver(device *IOSDevice) (*WDADriver, error) {
@@ -161,16 +162,16 @@ func (wd *WDADriver) DeleteSession() (err error) {
 	return
 }
 
-func (wd *WDADriver) Status() (deviceStatus DeviceStatus, err error) {
+func (wd *WDADriver) Status() (deviceStatus types.DeviceStatus, err error) {
 	// [[FBRoute GET:@"/status"].withoutSession respondWithTarget:self action:@selector(handleGetStatus:)]
 	var rawResp rawResponse
 	// Notice: use Driver.GET instead of httpGET to avoid loop calling
 	if rawResp, err = wd.GET("/status"); err != nil {
-		return DeviceStatus{}, err
+		return types.DeviceStatus{}, err
 	}
-	reply := new(struct{ Value struct{ DeviceStatus } })
+	reply := new(struct{ Value struct{ types.DeviceStatus } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return DeviceStatus{}, err
+		return types.DeviceStatus{}, err
 	}
 	deviceStatus = reply.Value.DeviceStatus
 	return
@@ -180,51 +181,51 @@ func (wd *WDADriver) GetDevice() IDevice {
 	return wd.IOSDevice
 }
 
-func (wd *WDADriver) DeviceInfo() (deviceInfo DeviceInfo, err error) {
+func (wd *WDADriver) DeviceInfo() (deviceInfo types.DeviceInfo, err error) {
 	// [[FBRoute GET:@"/wda/device/info"] respondWithTarget:self action:@selector(handleGetDeviceInfo:)]
 	// [[FBRoute GET:@"/wda/device/info"].withoutSession
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/wda/device/info"); err != nil {
-		return DeviceInfo{}, err
+		return types.DeviceInfo{}, err
 	}
-	reply := new(struct{ Value struct{ DeviceInfo } })
+	reply := new(struct{ Value struct{ types.DeviceInfo } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return DeviceInfo{}, err
+		return types.DeviceInfo{}, err
 	}
 	deviceInfo = reply.Value.DeviceInfo
 	return
 }
 
-func (wd *WDADriver) Location() (location Location, err error) {
+func (wd *WDADriver) Location() (location types.Location, err error) {
 	// [[FBRoute GET:@"/wda/device/location"] respondWithTarget:self action:@selector(handleGetLocation:)]
 	// [[FBRoute GET:@"/wda/device/location"].withoutSession
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/wda/device/location"); err != nil {
-		return Location{}, err
+		return types.Location{}, err
 	}
-	reply := new(struct{ Value struct{ Location } })
+	reply := new(struct{ Value struct{ types.Location } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return Location{}, err
+		return types.Location{}, err
 	}
 	location = reply.Value.Location
 	return
 }
 
-func (wd *WDADriver) BatteryInfo() (batteryInfo BatteryInfo, err error) {
+func (wd *WDADriver) BatteryInfo() (batteryInfo types.BatteryInfo, err error) {
 	// [[FBRoute GET:@"/wda/batteryInfo"] respondWithTarget:self action:@selector(handleGetBatteryInfo:)]
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/wda/batteryInfo"); err != nil {
-		return BatteryInfo{}, err
+		return types.BatteryInfo{}, err
 	}
-	reply := new(struct{ Value struct{ BatteryInfo } })
+	reply := new(struct{ Value struct{ types.BatteryInfo } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return BatteryInfo{}, err
+		return types.BatteryInfo{}, err
 	}
 	batteryInfo = reply.Value.BatteryInfo
 	return
 }
 
-func (wd *WDADriver) WindowSize() (size ai.Size, err error) {
+func (wd *WDADriver) WindowSize() (size types.Size, err error) {
 	// [[FBRoute GET:@"/window/size"] respondWithTarget:self action:@selector(handleGetWindowSize:)]
 	if !wd.windowSize.IsNil() {
 		// use cached window size
@@ -233,16 +234,16 @@ func (wd *WDADriver) WindowSize() (size ai.Size, err error) {
 
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/window/size"); err != nil {
-		return ai.Size{}, errors.Wrap(err, "get window size failed by WDA request")
+		return types.Size{}, errors.Wrap(err, "get window size failed by WDA request")
 	}
-	reply := new(struct{ Value struct{ ai.Size } })
+	reply := new(struct{ Value struct{ types.Size } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return ai.Size{}, errors.Wrap(err, "get window size failed by WDA response")
+		return types.Size{}, errors.Wrap(err, "get window size failed by WDA response")
 	}
 	size = reply.Value.Size
 	scale, err := wd.Scale()
 	if err != nil {
-		return ai.Size{}, errors.Wrap(err, "get window size scale failed")
+		return types.Size{}, errors.Wrap(err, "get window size scale failed")
 	}
 	size.Height = size.Height * int(scale)
 	size.Width = size.Width * int(scale)
@@ -281,28 +282,28 @@ func (wd *WDADriver) toScale(x float64) float64 {
 	return x / wd.scale
 }
 
-func (wd *WDADriver) ActiveAppInfo() (info AppInfo, err error) {
+func (wd *WDADriver) ActiveAppInfo() (info types.AppInfo, err error) {
 	// [[FBRoute GET:@"/wda/activeAppInfo"] respondWithTarget:self action:@selector(handleActiveAppInfo:)]
 	// [[FBRoute GET:@"/wda/activeAppInfo"].withoutSession
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/wda/activeAppInfo"); err != nil {
-		return AppInfo{}, err
+		return types.AppInfo{}, err
 	}
-	reply := new(struct{ Value struct{ AppInfo } })
+	reply := new(struct{ Value struct{ types.AppInfo } })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return AppInfo{}, err
+		return types.AppInfo{}, err
 	}
 	info = reply.Value.AppInfo
 	return
 }
 
-func (wd *WDADriver) ActiveAppsList() (appsList []AppBaseInfo, err error) {
+func (wd *WDADriver) ActiveAppsList() (appsList []types.AppBaseInfo, err error) {
 	// [[FBRoute GET:@"/wda/apps/list"] respondWithTarget:self action:@selector(handleGetActiveAppsList:)]
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/wda/apps/list"); err != nil {
 		return nil, err
 	}
-	reply := new(struct{ Value []AppBaseInfo })
+	reply := new(struct{ Value []types.AppBaseInfo })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
 		return nil, err
 	}
@@ -310,14 +311,14 @@ func (wd *WDADriver) ActiveAppsList() (appsList []AppBaseInfo, err error) {
 	return
 }
 
-func (wd *WDADriver) AppState(bundleId string) (runState AppState, err error) {
+func (wd *WDADriver) AppState(bundleId string) (runState types.AppState, err error) {
 	// [[FBRoute POST:@"/wda/apps/state"] respondWithTarget:self action:@selector(handleSessionAppState:)]
 	data := map[string]interface{}{"bundleId": bundleId}
 	var rawResp rawResponse
 	if rawResp, err = wd.httpPOST(data, "/session", wd.sessionID, "/wda/apps/state"); err != nil {
 		return 0, err
 	}
-	reply := new(struct{ Value AppState })
+	reply := new(struct{ Value types.AppState })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
 		return 0, err
 	}
@@ -471,7 +472,7 @@ func (wd *WDADriver) AppDeactivate(second float64) (err error) {
 	return
 }
 
-func (wd *WDADriver) GetForegroundApp() (appInfo AppInfo, err error) {
+func (wd *WDADriver) GetForegroundApp() (appInfo types.AppInfo, err error) {
 	activeAppInfo, err := wd.ActiveAppInfo()
 	appInfo.BundleId = activeAppInfo.BundleId
 	if err != nil {
@@ -611,7 +612,7 @@ func (wd *WDADriver) Swipe(fromX, fromY, toX, toY float64, opts ...option.Action
 	return wd.Drag(fromX, fromY, toX, toY, opts...)
 }
 
-func (wd *WDADriver) SetPasteboard(contentType PasteboardType, content string) (err error) {
+func (wd *WDADriver) SetPasteboard(contentType types.PasteboardType, content string) (err error) {
 	// [[FBRoute POST:@"/wda/setPasteboard"] respondWithTarget:self action:@selector(handleSetPasteboard:)]
 	data := map[string]interface{}{
 		"contentType": contentType,
@@ -621,7 +622,7 @@ func (wd *WDADriver) SetPasteboard(contentType PasteboardType, content string) (
 	return
 }
 
-func (wd *WDADriver) GetPasteboard(contentType PasteboardType) (raw *bytes.Buffer, err error) {
+func (wd *WDADriver) GetPasteboard(contentType types.PasteboardType) (raw *bytes.Buffer, err error) {
 	// [[FBRoute POST:@"/wda/getPasteboard"] respondWithTarget:self action:@selector(handleGetPasteboard:)]
 	data := map[string]interface{}{"contentType": contentType}
 	var rawResp rawResponse
@@ -713,7 +714,7 @@ func (wd *WDADriver) PressBack(opts ...option.ActionOption) (err error) {
 	return
 }
 
-func (wd *WDADriver) PressButton(devBtn DeviceButton) (err error) {
+func (wd *WDADriver) PressButton(devBtn types.DeviceButton) (err error) {
 	// [[FBRoute POST:@"/wda/pressButton"] respondWithTarget:self action:@selector(handlePressButtonCommand:)]
 	data := map[string]interface{}{"name": devBtn}
 	_, err = wd.httpPOST(data, "/session", wd.sessionID, "/wda/pressButton")
@@ -745,13 +746,13 @@ func (wd *WDADriver) StopCamera() (err error) {
 	return nil
 }
 
-func (wd *WDADriver) Orientation() (orientation Orientation, err error) {
+func (wd *WDADriver) Orientation() (orientation types.Orientation, err error) {
 	// [[FBRoute GET:@"/orientation"] respondWithTarget:self action:@selector(handleGetOrientation:)]
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/orientation"); err != nil {
 		return "", err
 	}
-	reply := new(struct{ Value Orientation })
+	reply := new(struct{ Value types.Orientation })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
 		return "", err
 	}
@@ -759,28 +760,28 @@ func (wd *WDADriver) Orientation() (orientation Orientation, err error) {
 	return
 }
 
-func (wd *WDADriver) SetOrientation(orientation Orientation) (err error) {
+func (wd *WDADriver) SetOrientation(orientation types.Orientation) (err error) {
 	// [[FBRoute POST:@"/orientation"] respondWithTarget:self action:@selector(handleSetOrientation:)]
 	data := map[string]interface{}{"orientation": orientation}
 	_, err = wd.httpPOST(data, "/session", wd.sessionID, "/orientation")
 	return
 }
 
-func (wd *WDADriver) Rotation() (rotation Rotation, err error) {
+func (wd *WDADriver) Rotation() (rotation types.Rotation, err error) {
 	// [[FBRoute GET:@"/rotation"] respondWithTarget:self action:@selector(handleGetRotation:)]
 	var rawResp rawResponse
 	if rawResp, err = wd.httpGET("/session", wd.sessionID, "/rotation"); err != nil {
-		return Rotation{}, err
+		return types.Rotation{}, err
 	}
-	reply := new(struct{ Value Rotation })
+	reply := new(struct{ Value types.Rotation })
 	if err = json.Unmarshal(rawResp, reply); err != nil {
-		return Rotation{}, err
+		return types.Rotation{}, err
 	}
 	rotation = reply.Value
 	return
 }
 
-func (wd *WDADriver) SetRotation(rotation Rotation) (err error) {
+func (wd *WDADriver) SetRotation(rotation types.Rotation) (err error) {
 	// [[FBRoute POST:@"/rotation"] respondWithTarget:self action:@selector(handleSetRotation:)]
 	_, err = wd.httpPOST(rotation, "/session", wd.sessionID, "/rotation")
 	return

pkg/uixt/ios_test.go

@@ -11,12 +11,13 @@ import (
 	"github.com/rs/zerolog/log"
 
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+	"github.com/httprunner/httprunner/v5/pkg/uixt/types"
 )
 
 var (
 	bundleId     = "com.apple.Preferences"
 	driver       IDriver
-	iOSDriverExt *DriverExt
+	iOSDriverExt IDriverExt
 )
 
 func setup(t *testing.T) {
@@ -29,11 +30,7 @@ func setup(t *testing.T) {
 	}
 	capabilities := option.NewCapabilities()
 	capabilities.WithDefaultAlertAction(option.AlertActionAccept)
-	driver, err = device.NewHTTPDriver(capabilities)
+	iOSDriverExt, err = device.NewDriver()
-	if err != nil {
-		t.Fatal(err)
-	}
-	iOSDriverExt, err = newDriverExt(device, driver)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -46,7 +43,7 @@ func TestViaUSB(t *testing.T) {
 
 func TestInstall(t *testing.T) {
 	setup(t)
-	err := iOSDriverExt.Install("xxx.ipa",
+	err := iOSDriverExt.GetDriver().GetDevice().Install("xxx.ipa",
 		option.WithRetryTimes(5))
 	log.Error().Err(err)
 	if err != nil {
@@ -320,7 +317,7 @@ func Test_remoteWD_SetPasteboard(t *testing.T) {
 	setup(t)
 
 	// err := driver.SetPasteboard(PasteboardTypePlaintext, "gwda")
-	err := driver.SetPasteboard(PasteboardTypeUrl, "Clock-stopwatch://")
+	err := driver.SetPasteboard(types.PasteboardTypeUrl, "Clock-stopwatch://")
 	// userHomeDir, _ := os.UserHomeDir()
 	// bytesImg, _ := ioutil.ReadFile(userHomeDir + "/Pictures/IMG_0806.jpg")
 	// err := driver.SetPasteboard(PasteboardTypeImage, string(bytesImg))
@@ -335,7 +332,7 @@ func Test_remoteWD_GetPasteboard(t *testing.T) {
 	var buffer *bytes.Buffer
 	var err error
 
-	buffer, err = driver.GetPasteboard(PasteboardTypePlaintext)
+	buffer, err = driver.GetPasteboard(types.PasteboardTypePlaintext)
 	// buffer, err = driver.GetPasteboard(PasteboardTypeUrl)
 	if err != nil {
 		t.Fatal(err)
@@ -367,17 +364,17 @@ func Test_remoteWD_SendKeys(t *testing.T) {
 func Test_remoteWD_PressButton(t *testing.T) {
 	setup(t)
 
-	err := driver.PressButton(DeviceButtonVolumeUp)
+	err := driver.PressButton(types.DeviceButtonVolumeUp)
 	if err != nil {
 		t.Fatal(err)
 	}
 	time.Sleep(time.Second * 1)
-	err = driver.PressButton(DeviceButtonVolumeDown)
+	err = driver.PressButton(types.DeviceButtonVolumeDown)
 	if err != nil {
 		t.Fatal(err)
 	}
 	time.Sleep(time.Second * 1)
-	err = driver.PressButton(DeviceButtonHome)
+	err = driver.PressButton(types.DeviceButtonHome)
 	if err != nil {
 		t.Fatal(err)
 	}

pkg/uixt/option/action.go

@@ -6,54 +6,24 @@ import (
 	"github.com/httprunner/httprunner/v5/internal/builtin"
 )
 
-// (x1, y1) is the top left corner, (x2, y2) is the bottom right corner
-// [x1, y1, x2, y2] in percentage of the screen
-type Scope []float64
-
-// [x1, y1, x2, y2] in absolute pixels
-type AbsScope []int
-
-func (s AbsScope) Option() ActionOption {
-	return WithAbsScope(s[0], s[1], s[2], s[3])
-}
-
 type ActionOptions struct {
 	// log
 	Identifier string `json:"identifier,omitempty" yaml:"identifier,omitempty"` // used to identify the action in log
 
 	// control related
-	MaxRetryTimes       int         `json:"max_retry_times,omitempty" yaml:"max_retry_times,omitempty"`           // max retry times
+	MaxRetryTimes int         `json:"max_retry_times,omitempty" yaml:"max_retry_times,omitempty"` // max retry times
-	IgnoreNotFoundError bool        `json:"ignore_NotFoundError,omitempty" yaml:"ignore_NotFoundError,omitempty"` // ignore error if target element not found
+	Interval      float64     `json:"interval,omitempty" yaml:"interval,omitempty"`               // interval between retries in seconds
-	Interval            float64     `json:"interval,omitempty" yaml:"interval,omitempty"`                         // interval between retries in seconds
+	Duration      float64     `json:"duration,omitempty" yaml:"duration,omitempty"`               // used to set duration of ios swipe action
-	Duration            float64     `json:"duration,omitempty" yaml:"duration,omitempty"`                         // used to set duration of ios swipe action
+	PressDuration float64     `json:"press_duration,omitempty" yaml:"press_duration,omitempty"`   // used to set duration of ios swipe action
-	PressDuration       float64     `json:"press_duration,omitempty" yaml:"press_duration,omitempty"`             // used to set duration of ios swipe action
+	Steps         int         `json:"steps,omitempty" yaml:"steps,omitempty"`                     // used to set steps of android swipe action
-	Steps               int         `json:"steps,omitempty" yaml:"steps,omitempty"`                               // used to set steps of android swipe action
+	Direction     interface{} `json:"direction,omitempty" yaml:"direction,omitempty"`             // used by swipe to tap text or app
-	Direction           interface{} `json:"direction,omitempty" yaml:"direction,omitempty"`                       // used by swipe to tap text or app
+	Timeout       int         `json:"timeout,omitempty" yaml:"timeout,omitempty"`                 // TODO: wait timeout in seconds for mobile action
-	Timeout             int         `json:"timeout,omitempty" yaml:"timeout,omitempty"`                           // TODO: wait timeout in seconds for mobile action
+	Frequency     int         `json:"frequency,omitempty" yaml:"frequency,omitempty"`
-	Frequency           int         `json:"frequency,omitempty" yaml:"frequency,omitempty"`
 
-	// scope related
+	ScreenOptions
-	Scope    Scope    `json:"scope,omitempty" yaml:"scope,omitempty"`
-	AbsScope AbsScope `json:"abs_scope,omitempty" yaml:"abs_scope,omitempty"`
-
-	Regex             bool  `json:"regex,omitempty" yaml:"regex,omitempty"`                             // use regex to match text
-	Offset            []int `json:"offset,omitempty" yaml:"offset,omitempty"`                           // used to tap offset of point
-	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
-	MatchOne          bool  `json:"match_one,omitempty" yaml:"match_one,omitempty"`                     // match one of the targets if existed
 
 	// set custiom options such as textview, id, description
 	Custom map[string]interface{} `json:"custom,omitempty" yaml:"custom,omitempty"`
-
-	// screenshot related
-	ScreenShotWithOCR            bool     `json:"screenshot_with_ocr,omitempty" yaml:"screenshot_with_ocr,omitempty"`
-	ScreenShotWithUpload         bool     `json:"screenshot_with_upload,omitempty" yaml:"screenshot_with_upload,omitempty"`
-	ScreenShotWithLiveType       bool     `json:"screenshot_with_live_type,omitempty" yaml:"screenshot_with_live_type,omitempty"`
-	ScreenShotWithLivePopularity bool     `json:"screenshot_with_live_popularity,omitempty" yaml:"screenshot_with_live_popularity,omitempty"`
-	ScreenShotWithUITypes        []string `json:"screenshot_with_ui_types,omitempty" yaml:"screenshot_with_ui_types,omitempty"`
-	ScreenShotWithClosePopups    bool     `json:"screenshot_with_close_popups,omitempty" yaml:"screenshot_with_close_popups,omitempty"`
-	ScreenShotWithOCRCluster     string   `json:"screenshot_with_ocr_cluster,omitempty" yaml:"screenshot_with_ocr_cluster,omitempty"`
-	ScreenShotFileName           string   `json:"screenshot_file_name,omitempty" yaml:"screenshot_file_name,omitempty"`
 }
 
 func (o *ActionOptions) Options() []ActionOption {
@@ -150,57 +120,11 @@ func (o *ActionOptions) Options() []ActionOption {
 		}
 	}
 
-	// screenshot options
-	if o.ScreenShotWithOCR {
-		options = append(options, WithScreenShotOCR(true))
-	}
-	if o.ScreenShotWithUpload {
-		options = append(options, WithScreenShotUpload(true))
-	}
-	if o.ScreenShotWithLiveType {
-		options = append(options, WithScreenShotLiveType(true))
-	}
-	if o.ScreenShotWithLivePopularity {
-		options = append(options, WithScreenShotLivePopularity(true))
-	}
-	if len(o.ScreenShotWithUITypes) > 0 {
-		options = append(options, WithScreenShotUITypes(o.ScreenShotWithUITypes...))
-	}
-	if o.ScreenShotWithClosePopups {
-		options = append(options, WithScreenShotClosePopups(true))
-	}
-	if o.ScreenShotWithOCRCluster != "" {
-		options = append(options, WithScreenOCRCluster(o.ScreenShotWithOCRCluster))
-	}
-	if o.ScreenShotFileName != "" {
-		options = append(options, WithScreenShotFileName(o.ScreenShotFileName))
-	}
-
 	return options
 }
 
-func (o *ActionOptions) ScreenshotActions() []string {
+func (o *ActionOptions) GetScreenOptions() []ActionOption {
-	actions := []string{}
+	return o.ScreenOptions.Options()
-	if o.ScreenShotWithUpload {
-		actions = append(actions, "upload")
-	}
-	if o.ScreenShotWithOCR {
-		actions = append(actions, "ocr")
-	}
-	if o.ScreenShotWithLiveType {
-		actions = append(actions, "liveType")
-	}
-	if o.ScreenShotWithLivePopularity {
-		actions = append(actions, "livePopularity")
-	}
-	// UI detection
-	if len(o.ScreenShotWithUITypes) > 0 {
-		actions = append(actions, "ui")
-	}
-	if o.ScreenShotWithClosePopups {
-		actions = append(actions, "close")
-	}
-	return actions
 }
 
 func (o *ActionOptions) GetRandomOffset() float64 {
@@ -283,12 +207,6 @@ func WithIdentifier(identifier string) ActionOption {
 	}
 }
 
-func WithIndex(index int) ActionOption {
-	return func(o *ActionOptions) {
-		o.Index = index
-	}
-}
-
 // set alias for compatibility
 var WithWaitTime = WithInterval
 
@@ -330,32 +248,6 @@ func WithCustomDirection(sx, sy, ex, ey float64) ActionOption {
 	}
 }
 
-// WithScope inputs area of [(x1,y1), (x2,y2)]
-// x1, y1, x2, y2 are all in [0, 1], which means the relative position of the screen
-func WithScope(x1, y1, x2, y2 float64) ActionOption {
-	return func(o *ActionOptions) {
-		o.Scope = Scope{x1, y1, x2, y2}
-	}
-}
-
-// WithAbsScope inputs area of [(x1,y1), (x2,y2)]
-// x1, y1, x2, y2 are all absolute position of the screen
-func WithAbsScope(x1, y1, x2, y2 int) ActionOption {
-	return func(o *ActionOptions) {
-		o.AbsScope = AbsScope{x1, y1, x2, y2}
-	}
-}
-
-// Deprecated: use WithTapOffset instead
-func WithOffset(offsetX, offsetY int) ActionOption {
-	return func(o *ActionOptions) {
-		o.Offset = []int{offsetX, offsetY}
-	}
-}
-
-// tap [x, y] with offset [offsetX, offsetY]
-var WithTapOffset = WithOffset
-
 // swipe [fromX, fromY, toX, toY] with offset [offsetFromX, offsetFromY, offsetToX, offsetToY]
 func WithSwipeOffset(offsetFromX, offsetFromY, offsetToX, offsetToY int) ActionOption {
 	return func(o *ActionOptions) {
@@ -369,18 +261,6 @@ func WithOffsetRandomRange(min, max int) ActionOption {
 	}
 }
 
-func WithRegex(regex bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.Regex = regex
-	}
-}
-
-func WithMatchOne(matchOne bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.MatchOne = matchOne
-	}
-}
-
 func WithFrequency(frequency int) ActionOption {
 	return func(o *ActionOptions) {
 		o.Frequency = frequency
@@ -404,51 +284,3 @@ func WithIgnoreNotFoundError(ignoreError bool) ActionOption {
 		o.IgnoreNotFoundError = ignoreError
 	}
 }
-
-func WithScreenShotOCR(ocrOn bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithOCR = ocrOn
-	}
-}
-
-func WithScreenShotUpload(uploadOn bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithUpload = uploadOn
-	}
-}
-
-func WithScreenShotLiveType(liveTypeOn bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithLiveType = liveTypeOn
-	}
-}
-
-func WithScreenShotLivePopularity(livePopularityOn bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithLivePopularity = livePopularityOn
-	}
-}
-
-func WithScreenShotUITypes(uiTypes ...string) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithUITypes = uiTypes
-	}
-}
-
-func WithScreenShotClosePopups(closeOn bool) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithClosePopups = closeOn
-	}
-}
-
-func WithScreenOCRCluster(ocrCluster string) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotWithOCRCluster = ocrCluster
-	}
-}
-
-func WithScreenShotFileName(fileName string) ActionOption {
-	return func(o *ActionOptions) {
-		o.ScreenShotFileName = fileName
-	}
-}

pkg/uixt/option/driver.go

@@ -1,49 +0,0 @@
-package option
-
-import (
-	"github.com/httprunner/funplugin"
-)
-
-type DriverOptions struct {
-	Capabilities     Capabilities
-	Plugin           funplugin.IPlugin
-	WithImageService bool
-	WithResultFolder bool
-}
-
-func NewDriverOptions(opts ...DriverOption) *DriverOptions {
-	driverOptions := &DriverOptions{
-		WithImageService: true,
-		WithResultFolder: true,
-	}
-	for _, option := range opts {
-		option(driverOptions)
-	}
-	return driverOptions
-}
-
-type DriverOption func(*DriverOptions)
-
-func WithDriverCapabilities(capabilities Capabilities) DriverOption {
-	return func(options *DriverOptions) {
-		options.Capabilities = capabilities
-	}
-}
-
-func WithDriverImageService(withImageService bool) DriverOption {
-	return func(options *DriverOptions) {
-		options.WithImageService = withImageService
-	}
-}
-
-func WithDriverResultFolder(withResultFolder bool) DriverOption {
-	return func(options *DriverOptions) {
-		options.WithResultFolder = withResultFolder
-	}
-}
-
-func WithDriverPlugin(plugin funplugin.IPlugin) DriverOption {
-	return func(options *DriverOptions) {
-		options.Plugin = plugin
-	}
-}

pkg/uixt/option/harmony.go

@@ -1,5 +1,12 @@
 package option
 
+import "code.byted.org/iesqa/ghdc"
+
+const (
+	HdcServerHost = "localhost"
+	HdcServerPort = ghdc.HdcServerPort // 5037
+)
+
 type HarmonyDeviceOptions struct {
 	ConnectKey string `json:"connect_key,omitempty" yaml:"connect_key,omitempty"`
 	LogOn      bool   `json:"log_on,omitempty" yaml:"log_on,omitempty"`

pkg/uixt/option/screen.go

@@ -1,11 +1,10 @@
-package ai
+package option
 
-func NewScreenShotOptions(opts ...ScreenShotOption) *ScreenShotOptions {
+import "github.com/httprunner/httprunner/v5/pkg/uixt/types"
-	options := &ScreenShotOptions{}
+
-	for _, option := range opts {
+type ScreenOptions struct {
-		option(options)
+	ScreenShotOptions
-	}
+	ScreenFilterOptions
-	return options
 }
 
 type ScreenShotOptions struct {
@@ -19,8 +18,8 @@ type ScreenShotOptions struct {
 	ScreenShotFileName           string   `json:"screenshot_file_name,omitempty" yaml:"screenshot_file_name,omitempty"`
 }
 
-func (o *ScreenShotOptions) Options() []ScreenShotOption {
+func (o *ScreenShotOptions) Options() []ActionOption {
-	options := make([]ScreenShotOption, 0)
+	options := make([]ActionOption, 0)
 	if o == nil {
 		return options
 	}
@@ -78,52 +77,50 @@ func (o *ScreenShotOptions) List() []string {
 	return options
 }
 
-type ScreenShotOption func(o *ScreenShotOptions)
+func WithScreenShotOCR(ocrOn bool) ActionOption {
-
+	return func(o *ActionOptions) {
-func WithScreenShotOCR(ocrOn bool) ScreenShotOption {
-	return func(o *ScreenShotOptions) {
 		o.ScreenShotWithOCR = ocrOn
 	}
 }
 
-func WithScreenShotUpload(uploadOn bool) ScreenShotOption {
+func WithScreenShotUpload(uploadOn bool) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithUpload = uploadOn
 	}
 }
 
-func WithScreenShotLiveType(liveTypeOn bool) ScreenShotOption {
+func WithScreenShotLiveType(liveTypeOn bool) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithLiveType = liveTypeOn
 	}
 }
 
-func WithScreenShotLivePopularity(livePopularityOn bool) ScreenShotOption {
+func WithScreenShotLivePopularity(livePopularityOn bool) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithLivePopularity = livePopularityOn
 	}
 }
 
-func WithScreenShotUITypes(uiTypes ...string) ScreenShotOption {
+func WithScreenShotUITypes(uiTypes ...string) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithUITypes = uiTypes
 	}
 }
 
-func WithScreenShotClosePopups(closeOn bool) ScreenShotOption {
+func WithScreenShotClosePopups(closeOn bool) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithClosePopups = closeOn
 	}
 }
 
-func WithScreenOCRCluster(ocrCluster string) ScreenShotOption {
+func WithScreenOCRCluster(ocrCluster string) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotWithOCRCluster = ocrCluster
 	}
 }
 
-func WithScreenShotFileName(fileName string) ScreenShotOption {
+func WithScreenShotFileName(fileName string) ActionOption {
-	return func(o *ScreenShotOptions) {
+	return func(o *ActionOptions) {
 		o.ScreenShotFileName = fileName
 	}
 }
@@ -132,7 +129,7 @@ func WithScreenShotFileName(fileName string) ScreenShotOption {
 // [x1, y1, x2, y2] in percentage of the screen
 type Scope []float64
 
-func (s Scope) ToAbs(windowSize Size) AbsScope {
+func (s Scope) ToAbs(windowSize types.Size) AbsScope {
 	x1, y1, x2, y2 := s[0], s[1], s[2], s[3]
 	// convert relative scope to absolute scope
 	absX1 := int(x1 * float64(windowSize.Width))
@@ -145,12 +142,12 @@ func (s Scope) ToAbs(windowSize Size) AbsScope {
 // [x1, y1, x2, y2] in absolute pixels
 type AbsScope []int
 
-func (s AbsScope) Option() ScreenFilterOption {
+func (s AbsScope) Option() ActionOption {
 	return WithAbsScope(s[0], s[1], s[2], s[3])
 }
 
-func NewScreenFilterOptions(opts ...ScreenFilterOption) *ScreenFilterOptions {
+func NewScreenFilterOptions(opts ...ActionOption) *ActionOptions {
-	options := &ScreenFilterOptions{}
+	options := &ActionOptions{}
 	for _, option := range opts {
 		option(options)
 	}
@@ -162,52 +159,51 @@ type ScreenFilterOptions struct {
 	Scope    Scope    `json:"scope,omitempty" yaml:"scope,omitempty"`
 	AbsScope AbsScope `json:"abs_scope,omitempty" yaml:"abs_scope,omitempty"`
 
-	Regex             bool  `json:"regex,omitempty" yaml:"regex,omitempty"`                             // use regex to match text
+	Regex               bool  `json:"regex,omitempty" yaml:"regex,omitempty"`                             // use regex to match text
-	Offset            []int `json:"offset,omitempty" yaml:"offset,omitempty"`                           // used to tap offset of point
+	Offset              []int `json:"offset,omitempty" yaml:"offset,omitempty"`                           // used to tap offset of point
-	OffsetRandomRange []int `json:"offset_random_range,omitempty" yaml:"offset_random_range,omitempty"` // set random range [min, max] for tap/swipe points
+	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
+	Index               int   `json:"index,omitempty" yaml:"index,omitempty"`                             // index of the target element
-	MatchOne          bool  `json:"match_one,omitempty" yaml:"match_one,omitempty"`                     // match one of the targets if existed
+	MatchOne            bool  `json:"match_one,omitempty" yaml:"match_one,omitempty"`
+	IgnoreNotFoundError bool  `json:"ignore_NotFoundError,omitempty" yaml:"ignore_NotFoundError,omitempty"` // ignore error if target element not found                  // match one of the targets if existed
 }
 
-type ScreenFilterOption func(o *ScreenFilterOptions)
-
 // WithScope inputs area of [(x1,y1), (x2,y2)]
 // x1, y1, x2, y2 are all in [0, 1], which means the relative position of the screen
-func WithScope(x1, y1, x2, y2 float64) ScreenFilterOption {
+func WithScope(x1, y1, x2, y2 float64) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.Scope = Scope{x1, y1, x2, y2}
 	}
 }
 
 // WithAbsScope inputs area of [(x1,y1), (x2,y2)]
 // x1, y1, x2, y2 are all absolute position of the screen
-func WithAbsScope(x1, y1, x2, y2 int) ScreenFilterOption {
+func WithAbsScope(x1, y1, x2, y2 int) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.AbsScope = AbsScope{x1, y1, x2, y2}
 	}
 }
 
 // tap [x, y] with offset [offsetX, offsetY]
-func WithTapOffset(offsetX, offsetY int) ScreenFilterOption {
+func WithTapOffset(offsetX, offsetY int) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.Offset = []int{offsetX, offsetY}
 	}
 }
 
-func WithRegex(regex bool) ScreenFilterOption {
+func WithRegex(regex bool) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.Regex = regex
 	}
 }
 
-func WithMatchOne(matchOne bool) ScreenFilterOption {
+func WithMatchOne(matchOne bool) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.MatchOne = matchOne
 	}
 }
 
-func WithIndex(index int) ScreenFilterOption {
+func WithIndex(index int) ActionOption {
-	return func(o *ScreenFilterOptions) {
+	return func(o *ActionOptions) {
 		o.Index = index
 	}
 }

pkg/uixt/types/app.go

@@ -0,0 +1,60 @@
+package types
+
+type AppInfo struct {
+	Name string `json:"name,omitempty"`
+	AppBaseInfo
+}
+
+type WindowInfo struct {
+	PackageName string `json:"packageName,omitempty"`
+	Activity    string `json:"activity,omitempty"`
+}
+
+type AppBaseInfo struct {
+	Pid            int         `json:"pid,omitempty"`
+	BundleId       string      `json:"bundleId,omitempty"`       // ios package name
+	ViewController string      `json:"viewController,omitempty"` // ios view controller
+	PackageName    string      `json:"packageName,omitempty"`    // android package name
+	Activity       string      `json:"activity,omitempty"`       // android activity
+	VersionName    string      `json:"versionName,omitempty"`
+	VersionCode    interface{} `json:"versionCode,omitempty"` // int or string
+	AppName        string      `json:"appName,omitempty"`
+	AppPath        string      `json:"appPath,omitempty"`
+	AppMD5         string      `json:"appMD5,omitempty"`
+	// AppIcon        string `json:"appIcon,omitempty"`
+}
+
+type AppState int
+
+const (
+	AppStateNotRunning AppState = 1 << iota
+	AppStateRunningBack
+	AppStateRunningFront
+)
+
+func (v AppState) String() string {
+	switch v {
+	case AppStateNotRunning:
+		return "Not Running"
+	case AppStateRunningBack:
+		return "Running (Back)"
+	case AppStateRunningFront:
+		return "Running (Front)"
+	default:
+		return "UNKNOWN"
+	}
+}
+
+// PasteboardType The type of the item on the pasteboard.
+type PasteboardType string
+
+const (
+	PasteboardTypePlaintext PasteboardType = "plaintext"
+	PasteboardTypeImage     PasteboardType = "image"
+	PasteboardTypeUrl       PasteboardType = "url"
+)
+
+const (
+	TextBackspace string = "\u0008"
+	TextDelete    string = "\u007F"
+)

pkg/uixt/types/device.go

@@ -1,8 +1,6 @@
-package uixt
+package types
 
-import (
+import "fmt"
-	"fmt"
-)
 
 type DeviceStatus struct {
 	Message string `json:"message"`
@@ -152,65 +150,6 @@ func (bs BatteryStatus) String() string {
 	}
 }
 
-type AppInfo struct {
-	Name string `json:"name,omitempty"`
-	AppBaseInfo
-}
-
-type WindowInfo struct {
-	PackageName string `json:"packageName,omitempty"`
-	Activity    string `json:"activity,omitempty"`
-}
-
-type AppBaseInfo struct {
-	Pid            int         `json:"pid,omitempty"`
-	BundleId       string      `json:"bundleId,omitempty"`       // ios package name
-	ViewController string      `json:"viewController,omitempty"` // ios view controller
-	PackageName    string      `json:"packageName,omitempty"`    // android package name
-	Activity       string      `json:"activity,omitempty"`       // android activity
-	VersionName    string      `json:"versionName,omitempty"`
-	VersionCode    interface{} `json:"versionCode,omitempty"` // int or string
-	AppName        string      `json:"appName,omitempty"`
-	AppPath        string      `json:"appPath,omitempty"`
-	AppMD5         string      `json:"appMD5,omitempty"`
-	// AppIcon        string `json:"appIcon,omitempty"`
-}
-
-type AppState int
-
-const (
-	AppStateNotRunning AppState = 1 << iota
-	AppStateRunningBack
-	AppStateRunningFront
-)
-
-func (v AppState) String() string {
-	switch v {
-	case AppStateNotRunning:
-		return "Not Running"
-	case AppStateRunningBack:
-		return "Running (Back)"
-	case AppStateRunningFront:
-		return "Running (Front)"
-	default:
-		return "UNKNOWN"
-	}
-}
-
-// PasteboardType The type of the item on the pasteboard.
-type PasteboardType string
-
-const (
-	PasteboardTypePlaintext PasteboardType = "plaintext"
-	PasteboardTypeImage     PasteboardType = "image"
-	PasteboardTypeUrl       PasteboardType = "url"
-)
-
-const (
-	TextBackspace string = "\u0008"
-	TextDelete    string = "\u007F"
-)
-
 // DeviceButton A physical button on an iOS device.
 type DeviceButton string
 
@@ -249,8 +188,6 @@ type Rotation struct {
 	Z int `json:"z"`
 }
 
-type Condition func(wd IDriver) (bool, error)
-
 type Direction string
 
 const (

pkg/uixt/types/ui.go

@@ -0,0 +1,10 @@
+package types
+
+type Size struct {
+	Width  int `json:"width"`
+	Height int `json:"height"`
+}
+
+func (s Size) IsNil() bool {
+	return s.Width == 0 && s.Height == 0
+}

runner.go

@@ -235,7 +235,7 @@ func (r *HRPRunner) Run(testcases ...ITestCase) (err error) {
 		// release UI driver session
 		defer func() {
 			for _, client := range caseRunner.uixtDrivers {
-				client.Driver.DeleteSession()
+				client.GetDriver().DeleteSession()
 			}
 		}()
 
@@ -281,7 +281,7 @@ func (r *HRPRunner) NewCaseRunner(testcase TestCase) (*CaseRunner, error) {
 		TestCase:    testcase,
 		hrpRunner:   r,
 		parser:      newParser(),
-		uixtDrivers: make(map[string]*uixt.DriverExt),
+		uixtDrivers: make(map[string]uixt.IDriverExt),
 	}
 	config := testcase.Config.Get()
 
@@ -336,7 +336,7 @@ type CaseRunner struct {
 	parametersIterator *ParametersIterator
 
 	// UI automation clients for iOS and Android, key is udid/serial
-	uixtDrivers map[string]*uixt.DriverExt
+	uixtDrivers map[string]uixt.IDriverExt
 }
 
 func (r *CaseRunner) GetParametersIterator() *ParametersIterator {
@@ -428,16 +428,14 @@ func (r *CaseRunner) parseConfig() (parsedConfig *TConfig, err error) {
 			return nil, errors.Wrap(err, "init android device failed")
 		}
 		if err := device.Setup(); err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "setup android device failed")
 		}
-		driver, err := device.NewDriver()
+		driverExt, err := device.NewDriver()
 		if err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "init android driver failed")
 		}
-		if err := driver.Setup(); err != nil {
+
-			return nil, err
+		r.uixtDrivers[androidDevice.SerialNumber] = driverExt
-		}
-		r.uixtDrivers[device.SerialNumber] = driver
 	}
 	// parse iOS devices config
 	for _, iosDevice := range parsedConfig.IOS {
@@ -446,21 +444,20 @@ func (r *CaseRunner) parseConfig() (parsedConfig *TConfig, err error) {
 			return nil, errors.Wrap(code.InvalidCaseError,
 				fmt.Sprintf("parse ios config failed: %v", err))
 		}
+
 		device, err := uixt.NewIOSDevice(iosDevice.Options()...)
 		if err != nil {
 			return nil, errors.Wrap(err, "init ios device failed")
 		}
 		if err := device.Setup(); err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "setup ios device failed")
 		}
-		driver, err := device.NewDriver()
+		driverExt, err := device.NewDriver()
 		if err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "init ios driver failed")
 		}
-		if err := driver.Setup(); err != nil {
+
-			return nil, err
+		r.uixtDrivers[iosDevice.UDID] = driverExt
-		}
-		r.uixtDrivers[device.UDID] = driver
 	}
 	// parse harmony devices config
 	for _, harmonyDevice := range parsedConfig.Harmony {
@@ -469,21 +466,20 @@ func (r *CaseRunner) parseConfig() (parsedConfig *TConfig, err error) {
 			return nil, errors.Wrap(code.InvalidCaseError,
 				fmt.Sprintf("parse harmony config failed: %v", err))
 		}
+
 		device, err := uixt.NewHarmonyDevice(harmonyDevice.Options()...)
 		if err != nil {
 			return nil, errors.Wrap(err, "init harmony device failed")
 		}
 		if err := device.Setup(); err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "setup harmony device failed")
 		}
-		driver, err := device.NewDriver()
+		driverExt, err := device.NewDriver()
 		if err != nil {
-			return nil, err
+			return nil, errors.Wrap(err, "init harmony driver failed")
 		}
-		if err := driver.Setup(); err != nil {
+
-			return nil, err
+		r.uixtDrivers[harmonyDevice.ConnectKey] = driverExt
-		}
-		r.uixtDrivers[device.ConnectKey] = driver
 	}
 
 	return parsedConfig, nil
@@ -525,7 +521,7 @@ func (r *CaseRunner) parseDeviceConfig(device interface{}, configVariables map[s
 	return nil
 }
 
-func (r *CaseRunner) GetUIXTDriver(serial string) (driver *uixt.DriverExt, err error) {
+func (r *CaseRunner) GetUIXTDriver(serial string) (driver uixt.IDriverExt, err error) {
 	for key, driver := range r.uixtDrivers {
 		// return the driver with the same serial
 		if key == serial {
@@ -604,8 +600,8 @@ func (r *SessionRunner) Start(givenVars map[string]interface{}) (summary *TestCa
 				"uuid": uuid,
 			}
 
-			if client.Device.LogEnabled() {
+			if client.GetDriver().GetDevice().LogEnabled() {
-				log, err1 := client.Driver.StopCaptureLog()
+				log, err1 := client.GetDriver().StopCaptureLog()
 				if err1 != nil {
 					if err == nil {
 						err = errors.Wrap(err1, "stop capture log failed")

server/context.go

@@ -13,7 +13,7 @@ import (
 	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
 )
 
-var uiClients = make(map[string]*uixt.DriverExt) // UI automation clients for iOS and Android, key is udid/serial
+var uiClients = make(map[string]uixt.IDriverExt) // UI automation clients for iOS and Android, key is udid/serial
 
 func handleDeviceContext() gin.HandlerFunc {
 	return func(c *gin.Context) {
@@ -54,9 +54,7 @@ func handleDeviceContext() gin.HandlerFunc {
 			}
 			device.Setup()
 
-			driver, err := device.NewDriver(
+			driver, err := device.NewDriver()
-				option.WithDriverImageService(true),
-				option.WithDriverResultFolder(true))
 			if err != nil {
 				log.Error().Err(err).Str("platform", platform).Str("serial", serial).
 					Msg("failed to init driver")

server/model.go

@@ -1,6 +1,8 @@
 package server
 
-import "github.com/httprunner/httprunner/v5/pkg/uixt/option"
+import (
+	"github.com/httprunner/httprunner/v5/pkg/uixt/option"
+)
 
 type HttpResponse struct {
 	Code    int         `json:"code"`
@@ -31,7 +33,7 @@ type InputRequest struct {
 }
 
 type ScreenRequest struct {
-	Options *option.ActionOptions `json:"options,omitempty"`
+	Options *option.ScreenOptions `json:"options,omitempty"`
 }
 
 type KeycodeRequest struct {

step_mobile_ui.go

@@ -684,7 +684,7 @@ func runStepMobileUI(s *SessionRunner, step IStep) (stepResult *StepResult, err
 				},
 				StartTime: startTime.Unix(),
 			}
-			if app, err1 := uiDriver.Driver.GetForegroundApp(); err1 == nil {
+			if app, err1 := uiDriver.GetDriver().GetForegroundApp(); err1 == nil {
 				attachments["foreground_app"] = app.AppBaseInfo
 			} else {
 				log.Warn().Err(err1).Msg("save foreground app failed, ignore")
@@ -711,7 +711,7 @@ func runStepMobileUI(s *SessionRunner, step IStep) (stepResult *StepResult, err
 		}
 
 		// save attachments
-		session := uiDriver.Driver.GetSession()
+		session := uiDriver.GetDriver().GetSession()
 		for key, value := range session.GetData(true) {
 			attachments[key] = value
 		}
@@ -780,7 +780,7 @@ func runStepMobileUI(s *SessionRunner, step IStep) (stepResult *StepResult, err
 	return stepResult, nil
 }
 
-func validateUI(ud *uixt.DriverExt, iValidators []interface{}) (validateResults []*ValidationResult, err error) {
+func validateUI(ud uixt.IDriverExt, iValidators []interface{}) (validateResults []*ValidationResult, err error) {
 	for _, iValidator := range iValidators {
 		validator, ok := iValidator.(Validator)
 		if !ok {