mirror/computer
1
0
Fork 0
mirror of https://github.com/trycua/computer.git synced 2026-01-04 20:40:15 -06:00
Code Issues Packages Projects Releases Wiki Activity

Added reference documentation for: libs/python/computer-server/computer_server/handlers/linux.py

Browse Source
This commit is contained in:
Andrei Onel
2025-09-01 22:51:56 +03:00
parent 1b4c04c553
commit 890fcfdeb3
1 changed files with 233 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

237
libs/python/computer-server/computer_server/handlers/linux.py
View File

@@ -38,7 +38,12 @@ class LinuxAccessibilityHandler(BaseAccessibilityHandler):
"""Linux implementation of accessibility handler."""
async def get_accessibility_tree(self) -> Dict[str, Any]:
"""Get the accessibility tree of the current window."""
"""Get the accessibility tree of the current window.
Returns:
Dict[str, Any]: A dictionary containing success status and a simulated tree structure
since Linux doesn't have equivalent accessibility API like macOS.
"""
# Linux doesn't have equivalent accessibility API like macOS
# Return a minimal dummy tree
logger.info("Getting accessibility tree (simulated, no accessibility API available on Linux)")
@@ -56,7 +61,16 @@ class LinuxAccessibilityHandler(BaseAccessibilityHandler):
async def find_element(self, role: Optional[str] = None,
title: Optional[str] = None,
value: Optional[str] = None) -> Dict[str, Any]:
"""Find an element in the accessibility tree by criteria."""
"""Find an element in the accessibility tree by criteria.
Args:
role: The role of the element to find.
title: The title of the element to find.
value: The value of the element to find.
Returns:
Dict[str, Any]: A dictionary indicating that element search is not supported on Linux.
"""
logger.info(f"Finding element with role={role}, title={title}, value={value} (not supported on Linux)")
return {
"success": False,
@@ -64,7 +78,12 @@ class LinuxAccessibilityHandler(BaseAccessibilityHandler):
}
def get_cursor_position(self) -> Tuple[int, int]:
"""Get the current cursor position."""
"""Get the current cursor position.
Returns:
Tuple[int, int]: The x and y coordinates of the cursor position.
Returns (0, 0) if pyautogui is not available.
"""
try:
pos = pyautogui.position()
return pos.x, pos.y
@@ -75,7 +94,12 @@ class LinuxAccessibilityHandler(BaseAccessibilityHandler):
return 0, 0
def get_screen_size(self) -> Tuple[int, int]:
"""Get the screen size."""
"""Get the screen size.
Returns:
Tuple[int, int]: The width and height of the screen in pixels.
Returns (1920, 1080) if pyautogui is not available.
"""
try:
size = pyautogui.size()
return size.width, size.height
@@ -91,6 +115,16 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Mouse Actions
async def mouse_down(self, x: Optional[int] = None, y: Optional[int] = None, button: str = "left") -> Dict[str, Any]:
"""Press and hold a mouse button at the specified coordinates.
Args:
x: The x coordinate to move to before pressing. If None, uses current position.
y: The y coordinate to move to before pressing. If None, uses current position.
button: The mouse button to press ("left", "right", or "middle").
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -100,6 +134,16 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def mouse_up(self, x: Optional[int] = None, y: Optional[int] = None, button: str = "left") -> Dict[str, Any]:
"""Release a mouse button at the specified coordinates.
Args:
x: The x coordinate to move to before releasing. If None, uses current position.
y: The y coordinate to move to before releasing. If None, uses current position.
button: The mouse button to release ("left", "right", or "middle").
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -109,6 +153,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def move_cursor(self, x: int, y: int) -> Dict[str, Any]:
"""Move the cursor to the specified coordinates.
Args:
x: The x coordinate to move to.
y: The y coordinate to move to.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.moveTo(x, y)
return {"success": True}
@@ -116,6 +169,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def left_click(self, x: Optional[int] = None, y: Optional[int] = None) -> Dict[str, Any]:
"""Perform a left mouse click at the specified coordinates.
Args:
x: The x coordinate to click at. If None, clicks at current position.
y: The y coordinate to click at. If None, clicks at current position.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -125,6 +187,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def right_click(self, x: Optional[int] = None, y: Optional[int] = None) -> Dict[str, Any]:
"""Perform a right mouse click at the specified coordinates.
Args:
x: The x coordinate to click at. If None, clicks at current position.
y: The y coordinate to click at. If None, clicks at current position.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -134,6 +205,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def double_click(self, x: Optional[int] = None, y: Optional[int] = None) -> Dict[str, Any]:
"""Perform a double click at the specified coordinates.
Args:
x: The x coordinate to double click at. If None, clicks at current position.
y: The y coordinate to double click at. If None, clicks at current position.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -143,6 +223,16 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def click(self, x: Optional[int] = None, y: Optional[int] = None, button: str = "left") -> Dict[str, Any]:
"""Perform a mouse click with the specified button at the given coordinates.
Args:
x: The x coordinate to click at. If None, clicks at current position.
y: The y coordinate to click at. If None, clicks at current position.
button: The mouse button to click ("left", "right", or "middle").
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if x is not None and y is not None:
pyautogui.moveTo(x, y)
@@ -152,6 +242,17 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def drag_to(self, x: int, y: int, button: str = "left", duration: float = 0.5) -> Dict[str, Any]:
"""Drag from the current position to the specified coordinates.
Args:
x: The x coordinate to drag to.
y: The y coordinate to drag to.
button: The mouse button to use for dragging.
duration: The time in seconds to take for the drag operation.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.dragTo(x, y, duration=duration, button=button)
return {"success": True}
@@ -159,6 +260,18 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def drag(self, start_x: int, start_y: int, end_x: int, end_y: int, button: str = "left") -> Dict[str, Any]:
"""Drag from start coordinates to end coordinates.
Args:
start_x: The starting x coordinate.
start_y: The starting y coordinate.
end_x: The ending x coordinate.
end_y: The ending y coordinate.
button: The mouse button to use for dragging.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.moveTo(start_x, start_y)
pyautogui.dragTo(end_x, end_y, duration=0.5, button=button)
@@ -167,6 +280,16 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def drag_path(self, path: List[Tuple[int, int]], button: str = "left", duration: float = 0.5) -> Dict[str, Any]:
"""Drag along a path defined by a list of coordinates.
Args:
path: A list of (x, y) coordinate tuples defining the drag path.
button: The mouse button to use for dragging.
duration: The time in seconds to take for each segment of the drag.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
if not path:
return {"success": False, "error": "Path is empty"}
@@ -179,6 +302,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Keyboard Actions
async def key_down(self, key: str) -> Dict[str, Any]:
"""Press and hold a key.
Args:
key: The key to press down.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.keyDown(key)
return {"success": True}
@@ -186,6 +317,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def key_up(self, key: str) -> Dict[str, Any]:
"""Release a key.
Args:
key: The key to release.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.keyUp(key)
return {"success": True}
@@ -193,6 +332,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def type_text(self, text: str) -> Dict[str, Any]:
"""Type the specified text using the keyboard.
Args:
text: The text to type.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
# use pynput for Unicode support
self.keyboard.type(text)
@@ -201,6 +348,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def press_key(self, key: str) -> Dict[str, Any]:
"""Press and release a key.
Args:
key: The key to press.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.press(key)
return {"success": True}
@@ -208,6 +363,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def hotkey(self, keys: List[str]) -> Dict[str, Any]:
"""Press a combination of keys simultaneously.
Args:
keys: A list of keys to press together as a hotkey combination.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.hotkey(*keys)
return {"success": True}
@@ -216,6 +379,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Scrolling Actions
async def scroll(self, x: int, y: int) -> Dict[str, Any]:
"""Scroll the mouse wheel.
Args:
x: The horizontal scroll amount.
y: The vertical scroll amount.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.scroll(x, y)
return {"success": True}
@@ -223,6 +395,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def scroll_down(self, clicks: int = 1) -> Dict[str, Any]:
"""Scroll down by the specified number of clicks.
Args:
clicks: The number of scroll clicks to perform downward.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.scroll(-clicks)
return {"success": True}
@@ -230,6 +410,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def scroll_up(self, clicks: int = 1) -> Dict[str, Any]:
"""Scroll up by the specified number of clicks.
Args:
clicks: The number of scroll clicks to perform upward.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
pyautogui.scroll(clicks)
return {"success": True}
@@ -238,6 +426,12 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Screen Actions
async def screenshot(self) -> Dict[str, Any]:
"""Take a screenshot of the current screen.
Returns:
Dict[str, Any]: A dictionary containing success status and base64-encoded image data,
or error message if failed.
"""
try:
from PIL import Image
screenshot = pyautogui.screenshot()
@@ -252,6 +446,12 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": f"Screenshot error: {str(e)}"}
async def get_screen_size(self) -> Dict[str, Any]:
"""Get the size of the screen.
Returns:
Dict[str, Any]: A dictionary containing success status and screen dimensions,
or error message if failed.
"""
try:
size = pyautogui.size()
return {"success": True, "size": {"width": size.width, "height": size.height}}
@@ -259,6 +459,12 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def get_cursor_position(self) -> Dict[str, Any]:
"""Get the current position of the cursor.
Returns:
Dict[str, Any]: A dictionary containing success status and cursor coordinates,
or error message if failed.
"""
try:
pos = pyautogui.position()
return {"success": True, "position": {"x": pos.x, "y": pos.y}}
@@ -267,6 +473,12 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Clipboard Actions
async def copy_to_clipboard(self) -> Dict[str, Any]:
"""Get the current content of the clipboard.
Returns:
Dict[str, Any]: A dictionary containing success status and clipboard content,
or error message if failed.
"""
try:
import pyperclip
content = pyperclip.paste()
@@ -275,6 +487,14 @@ class LinuxAutomationHandler(BaseAutomationHandler):
return {"success": False, "error": str(e)}
async def set_clipboard(self, text: str) -> Dict[str, Any]:
"""Set the clipboard content to the specified text.
Args:
text: The text to copy to the clipboard.
Returns:
Dict[str, Any]: A dictionary with success status and error message if failed.
"""
try:
import pyperclip
pyperclip.copy(text)
@@ -284,6 +504,15 @@ class LinuxAutomationHandler(BaseAutomationHandler):
# Command Execution
async def run_command(self, command: str) -> Dict[str, Any]:
"""Execute a shell command asynchronously.
Args:
command: The shell command to execute.
Returns:
Dict[str, Any]: A dictionary containing success status, stdout, stderr,
and return code, or error message if failed.
"""
try:
# Create subprocess
process = await asyncio.create_subprocess_shell(