From eeb8a120d6d30f400fe7b3cd0d7c2ee0b30fc7a4 Mon Sep 17 00:00:00 2001 From: David Chang Date: Fri, 5 Jan 2024 15:20:47 +0800 Subject: [PATCH] ver Jan5th debugged --- .gitignore | 1 + branch-config/filelist | 1 + branch-config/ignorelist | 1 + desktop_env/controllers/python.py | 16 ++--- desktop_env/controllers/setup.py | 49 ++++++++------- desktop_env/envs/desktop_env.py | 36 +++++------ desktop_env/evaluators/getters/misc.py | 7 ++- desktop_env/evaluators/metrics/chrome.py | 11 ++-- desktop_env/evaluators/metrics/docs.py | 6 +- desktop_env/evaluators/metrics/general.py | 6 +- desktop_env/evaluators/metrics/table.py | 14 +++-- desktop_env/evaluators/metrics/utils.py | 3 + desktop_env/evaluators/metrics/vlc.py | 13 ++-- desktop_env/server/main.py | 10 ++-- .../7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json | 5 +- .../bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json | 5 +- main.py | 60 +++++++++++++++---- 17 files changed, 158 insertions(+), 86 deletions(-) diff --git a/.gitignore b/.gitignore index 490eebb..775592d 100644 --- a/.gitignore +++ b/.gitignore @@ -165,3 +165,4 @@ frontend/.idea tags tags-opts snapshots +*.syncthing.*.tmp diff --git a/branch-config/filelist b/branch-config/filelist index eb3b3a1..03e1bc0 100644 --- a/branch-config/filelist +++ b/branch-config/filelist @@ -2,3 +2,4 @@ desktop_env main.py requirements.txt evaluation_examples +logs diff --git a/branch-config/ignorelist b/branch-config/ignorelist index e69de29..c75dc7c 100644 --- a/branch-config/ignorelist +++ b/branch-config/ignorelist @@ -0,0 +1 @@ +logs/* diff --git a/desktop_env/controllers/python.py b/desktop_env/controllers/python.py index 2b0dfb7..55cdb2f 100644 --- a/desktop_env/controllers/python.py +++ b/desktop_env/controllers/python.py @@ -3,6 +3,8 @@ from typing import Any, Dict import requests from desktop_env.envs.actions import KEYBOARD_KEYS +import logging +logger = logging.getLogger("desktopenv.pycontroller") class PythonController: def __init__(self, http_server: str, pkgs_prefix: str = "python -c \"import pyautogui; {command}\""): @@ -17,7 +19,7 @@ class PythonController: if response.status_code == 200: return response.content else: - print("Failed to get screenshot. Status code:", response.status_code) + logger.error("Failed to get screenshot. Status code: %d", response.status_code) return None def get_file(self, file_path: str): @@ -26,10 +28,10 @@ class PythonController: """ response = requests.post(self.http_server + "/file", data={"file_path": file_path}) if response.status_code == 200: - print("File downloaded successfully") + logger.info("File downloaded successfully") return response.content else: - print("Failed to get file. Status code:", response.status_code) + logger.error("Failed to get file. Status code: %d", response.status_code) return None def execute_python_command(self, command: str) -> None: @@ -38,7 +40,7 @@ class PythonController: It can be used to execute the pyautogui commands, or... any other python command. who knows? """ command = self.pkgs_prefix.format(command=command) - payload = json.dumps({"command": command}) + payload = json.dumps({"command": command, "shell": True}) headers = { 'Content-Type': 'application/json' } @@ -46,12 +48,12 @@ class PythonController: try: response = requests.post(self.http_server + "/execute", headers=headers, data=payload) if response.status_code == 200: - print("Command executed successfully:", response.text) + logger.info("Command executed successfully: %s", response.text) else: - print("Failed to execute command. Status code:", response.status_code) + logger.error("Failed to execute command. Status code: %d", response.status_code) return response.json() except requests.exceptions.RequestException as e: - print("An error occurred while trying to execute the command:", e) + logger.error("An error occurred while trying to execute the command: %s", e) def execute_action(self, action: Dict[str, Any]): """ diff --git a/desktop_env/controllers/setup.py b/desktop_env/controllers/setup.py index 3c28d3f..aa12c43 100644 --- a/desktop_env/controllers/setup.py +++ b/desktop_env/controllers/setup.py @@ -8,6 +8,10 @@ import os.path from typing import Dict, List from typing import Any, Union +import logging +logger = logging.getLogger("desktopenv.setup") + +import traceback class SetupController: def __init__( self @@ -88,12 +92,12 @@ class SetupController: for chunk in response.iter_content(chunk_size=8192): if chunk: f.write(chunk) - print("File downloaded successfully") + logger.info("File downloaded successfully") downloaded = True break except requests.RequestException as e: - print(f"Failed to download {url}. Retrying... ({max_retries - i - 1} attempts left)") + logger.error(f"Failed to download {url}. Retrying... ({max_retries - i - 1} attempts left)") if not downloaded: raise requests.RequestException(f"Failed to download {url}. No retries left. Error: {e}") @@ -107,17 +111,18 @@ class SetupController: } ) headers = {"Content-Type": form.content_type} - print(form.content_type) + logger.debug(form.content_type) # send request to server to upload file try: + logger.debug("REQUEST ADDRESS: %s", self.http_server + "/upload") response = requests.post(self.http_server + "/upload", headers=headers, data=form) if response.status_code == 200: - print("Command executed successfully:", response.text) + logger.info("Command executed successfully: %s", response.text) else: - print("Failed to upload file. Status code:", response.text) + logger.error("Failed to upload file. Status code: %s", response.text) except requests.exceptions.RequestException as e: - print("An error occurred while trying to send the request:", e) + logger.error("An error occurred while trying to send the request: %s", e) def _change_wallpaper_setup(self, path: str): # if not config: @@ -138,11 +143,11 @@ class SetupController: try: response = requests.post(self.http_server + "/change_wallpaper", headers=headers, data=payload) if response.status_code == 200: - print("Command executed successfully:", response.text) + logger.info("Command executed successfully: %s", response.text) else: - print("Failed to change wallpaper. Status code:", response.text) + logger.error("Failed to change wallpaper. Status code: %s", response.text) except requests.exceptions.RequestException as e: - print("An error occurred while trying to send the request:", e) + logger.error("An error occurred while trying to send the request: %s", e) def _tidy_desktop_setup(self, **config): raise NotImplementedError() @@ -165,11 +170,11 @@ class SetupController: try: response = requests.post(self.http_server + "/open_file", headers=headers, data=payload) if response.status_code == 200: - print("Command executed successfully:", response.text) + logger.info("Command executed successfully: %s", response.text) else: - print("Failed to open file. Status code:", response.text) + logger.error("Failed to open file. Status code: %s", response.text) except requests.exceptions.RequestException as e: - print("An error occurred while trying to send the request:", e) + logger.error("An error occurred while trying to send the request: %s", e) def _launch_setup(self, command: List[str]): if not command: @@ -181,11 +186,11 @@ class SetupController: try: response = requests.post(self.http_server + "/launch", headers=headers, data=payload) if response.status_code == 200: - print("Command executed successfully:", response.text) + logger.info("Command executed successfully: %s", response.text) else: - print("Failed to launch application. Status code:", response.text) + logger.error("Failed to launch application. Status code: %s", response.text) except requests.exceptions.RequestException as e: - print("An error occurred while trying to send the request:", e) + logger.error("An error occurred while trying to send the request: %s", e) def _execute_setup(self, command: List[str], stdout: str = "", stderr: str = ""): if not command: @@ -195,7 +200,7 @@ class SetupController: headers = {"Content-Type": "application/json"} try: - response = requests.post(self.http_server + "/launch", headers=headers, data=payload) + response = requests.post(self.http_server + "/execute", headers=headers, data=payload) if response.status_code == 200: results: Dict[str, str] = response.json() if stdout: @@ -204,13 +209,15 @@ class SetupController: if stderr: with open(os.path.join(self.cache_dir, stderr), "w") as f: f.write(results["error"]) - print( "Command executed successfully: {:} ->".format(" ".join(command)) - , response.text - ) + logger.info( "Command executed successfully: %s -> %s" + , " ".join(command) + , response.text + ) else: - print("Failed to launch application. Status code:", response.text) + logger.error("Failed to launch application. Status code: %s", response.text) except requests.exceptions.RequestException as e: - print("An error occurred while trying to send the request:", e) + logger.error("An error occurred while trying to send the request: %s", e) + traceback.print_exc() def _act_setup(self, action_seq: List[Union[Dict[str, Any], str]]): # TODO diff --git a/desktop_env/envs/desktop_env.py b/desktop_env/envs/desktop_env.py index 1845f94..1a70b76 100644 --- a/desktop_env/envs/desktop_env.py +++ b/desktop_env/envs/desktop_env.py @@ -17,10 +17,12 @@ from desktop_env.controllers.setup import SetupController # from desktop_env.evaluators import eval_funcs from desktop_env.evaluators import metrics, getters +import logging +logger = logging.getLogger("desktopenv.env") + Metric = Callable[[Any, Any], float] Getter = Callable[[gym.Env, Dict[str, Any]], Any] - def _execute_command(command: List[str]) -> None: if command[:4] == ["vmrun", "-T", "ws", "start"]: p = subprocess.Popen(command) @@ -72,7 +74,7 @@ class DesktopEnv(gym.Env): self._set_task_info(task_config) # Initialize emulator and controller - print("Initializing...") + logger.info("Initializing...") self._start_emulator() self.host = f"http://{self._get_vm_ip()}:5000" self.controller = PythonController(http_server=self.host) @@ -98,26 +100,26 @@ class DesktopEnv(gym.Env): output: List[str] = output.splitlines() # if self.path_to_vm.lstrip("~/") in output: if self.path_to_vm in output: - print("VM is running.") + logger.info("VM is running.") break else: - print("Starting VM...") + logger.info("Starting VM...") _execute_command(["vmrun", "-T", "ws", "start", self.path_to_vm]) time.sleep(3) except subprocess.CalledProcessError as e: - print(f"Error executing command: {e.output.decode().strip()}") + logger.error(f"Error executing command: {e.output.decode().strip()}") def _get_vm_ip(self): max_retries = 10 - print("Getting IP Address...") + logger.info("Getting IP Address...") for _ in range(max_retries): try: output = _execute_command(["vmrun", "-T", "ws", "getGuestIPAddress", self.path_to_vm]).strip() - print(f"IP address: {output}") + logger.info(f"IP address: {output}") return output except: time.sleep(5) - print("Retrying...") + logger.info("Retrying...") raise Exception("Failed to get VM IP address!") def _save_state(self): @@ -156,38 +158,38 @@ class DesktopEnv(gym.Env): self.metric_options: Dict[str, Any] = self.evaluator.get("options", {}) def reset(self, task_config: Optional[Dict[str, Any]] = None, seed=None, options=None): - print("Resetting environment...") + logger.info("Resetting environment...") - print("Switching task...") + logger.info("Switching task...") if task_config is not None: self._set_task_info(task_config) self.setup_controller.reset_cache_dir(self.cache_dir) - print("Setting counters...") + logger.info("Setting counters...") self._traj_no += 1 self._step_no = 0 self.action_history.clear() - print("Setup new temp dir...") + logger.info("Setup new temp dir...") self.tmp_dir = tempfile.mkdtemp( prefix="{:d}.{:}.".format(self._traj_no, self.task_id), dir=self.tmp_dir_base ) os.makedirs(os.path.join(self.tmp_dir, "screenshots")) - print("Reverting to snapshot to {}...".format(self.snapshot_path)) + logger.info("Reverting to snapshot to {}...".format(self.snapshot_path)) _execute_command(["vmrun", "-T", "ws", "revertToSnapshot", self.path_to_vm, self.snapshot_path]) time.sleep(5) - print("Starting emulator...") + logger.info("Starting emulator...") self._start_emulator() - print("Emulator started.") + logger.info("Emulator started.") - print("Setting up environment...") + logger.info("Setting up environment...") self.setup_controller.setup(self.config) time.sleep(5) - print("Environment setup complete.") + logger.info("Environment setup complete.") observation = self._get_obs() return observation diff --git a/desktop_env/evaluators/getters/misc.py b/desktop_env/evaluators/getters/misc.py index 4f82666..f66322b 100644 --- a/desktop_env/evaluators/getters/misc.py +++ b/desktop_env/evaluators/getters/misc.py @@ -5,6 +5,9 @@ import subprocess import ctypes import os +import logging +logger = logging.getLogger("desktopenv.getters.misc") + R = TypeVar("Rule") def get_rule(env, config: R) -> R: """ @@ -40,7 +43,7 @@ def get_wallpaper(): process = subprocess.Popen(['osascript', '-e', script], stdout=subprocess.PIPE) output, error = process.communicate() if error: - print("Error:", error) + logger.error("Error: %s", error) else: return output.strip().decode('utf-8') @@ -49,7 +52,7 @@ def get_wallpaper(): output = subprocess.check_output(["gsettings", "get", "org.gnome.desktop.background", "picture-uri"]) return output.decode('utf-8').strip().replace('file://', '').replace("'", "") except Exception as e: - print("Error:", e) + logger.error("Error: %s", e) return None os_name = platform.system() diff --git a/desktop_env/evaluators/metrics/chrome.py b/desktop_env/evaluators/metrics/chrome.py index 360b28c..91cd38d 100644 --- a/desktop_env/evaluators/metrics/chrome.py +++ b/desktop_env/evaluators/metrics/chrome.py @@ -5,6 +5,9 @@ import sqlite3 from playwright.sync_api import sync_playwright +import logging +logger = logging.getLogger("desktopenv.metrics.chrome") + """ WARNING: 1. Functions from this script assume that no account is registered on Chrome, otherwise the default file path needs to be changed. @@ -36,7 +39,7 @@ def get_default_search_engine(): 'Google') return search_engine except Exception as e: - print(f"Error: {e}") + logger.error(f"Error: {e}") return "Google" @@ -61,7 +64,7 @@ def get_cookie_data(): return cookies except Exception as e: - print(f"Error: {e}") + logger.error(f"Error: {e}") return None @@ -85,7 +88,7 @@ def get_bookmarks(): return bookmarks except Exception as e: - print(f"Error: {e}") + logger.error(f"Error: {e}") return None @@ -117,7 +120,7 @@ def get_extensions_installed_from_shop(): manifest = json.load(file) manifests.append(manifest) except json.JSONDecodeError: - print(f"Error reading {manifest_path}") + logger.error(f"Error reading {manifest_path}") return manifests diff --git a/desktop_env/evaluators/metrics/docs.py b/desktop_env/evaluators/metrics/docs.py index 017ba1c..48d2c03 100644 --- a/desktop_env/evaluators/metrics/docs.py +++ b/desktop_env/evaluators/metrics/docs.py @@ -4,6 +4,8 @@ from typing import List, Dict, Any from docx import Document from docx.enum.text import WD_PARAGRAPH_ALIGNMENT +import logging +logger = logging.getLogger("desktopenv.metric.docs") def find_default_font(config_file_path, rules): """Find the default font in LibreOffice Writer.""" @@ -23,7 +25,7 @@ def find_default_font(config_file_path, rules): for value in prop.findall('value', namespace): default_font = value.text except Exception as e: - print(f"Error: {e}") + logger.error(f"Error: {e}") return 1 if default_font == expected_font else 0 @@ -192,4 +194,4 @@ def compare_contains_image(docx_file1, docx_file2): # print(result) # config_path = "/home/[username]/.config/libreoffice/4/user/registrymodifications.xcu" -# print(find_default_font("Ani", config_path)) \ No newline at end of file +# print(find_default_font("Ani", config_path)) diff --git a/desktop_env/evaluators/metrics/general.py b/desktop_env/evaluators/metrics/general.py index d0776eb..37a3bc0 100644 --- a/desktop_env/evaluators/metrics/general.py +++ b/desktop_env/evaluators/metrics/general.py @@ -18,13 +18,13 @@ def check_csv(result: str, rules: Dict[str, List[Dict[str, str]]]) -> float: float """ - expect_metrics = [False] * len(rules["except"]) + expect_metrics = [False] * len(rules.get("expect", [])) unexpect_metric = True with open(result) as f: reader = csv.DictReader(f) for rcd in reader: - for i, r in enumerate(rules["expect"]): + for i, r in enumerate(rules.get("expect", [])): expect_metrics[i] = expect_metrics[i] or _match_record(r, rcd) - unexpect_metric = unexpect_metric and all(_match_record(r, rcd) for r in rules["unexpect"]) + unexpect_metric = unexpect_metric and all(_match_record(r, rcd) for r in rules.get("unexpect", [])) return float(all(expect_metrics) and unexpect_metric) diff --git a/desktop_env/evaluators/metrics/table.py b/desktop_env/evaluators/metrics/table.py index 4cca1d7..34ef0b0 100644 --- a/desktop_env/evaluators/metrics/table.py +++ b/desktop_env/evaluators/metrics/table.py @@ -10,6 +10,8 @@ from typing import Dict, List from typing import Any, Union from numbers import Number +import logging +logger = logging.getLogger("desktopenv.metric.table") def compare_table(actual: str, expected: str, **options) -> float: """ @@ -32,7 +34,7 @@ def compare_table(actual: str, expected: str, **options) -> float: df1 = pd.read_excel(expected) df2 = pd.read_excel(actual) metric: bool = df1.equals(df2) - print("Normal Contents Metric: {:}".format(metric)) + logger.debug("Normal Contents Metric: {:}".format(metric)) features: List[str] = options.get("features", []) for ftr in features: @@ -43,12 +45,12 @@ def compare_table(actual: str, expected: str, **options) -> float: sp1 = load_sparklines(actual) sp2 = load_sparklines(expected) new_metric: bool = sp1 == sp2 - print("Sparkline Metric: {:}".format(new_metric)) + logger.debug("Sparkline Metric: {:}".format(new_metric)) elif ftr=="chart": charts1 = load_charts(workbook1, **options) charts2 = load_charts(workbook2, **options) new_metric: bool = charts1 == charts2 - print("Chart Metric: {:}".format(new_metric)) + logger.debug("Chart Metric: {:}".format(new_metric)) elif ftr=="number_format": number_formats1: List[str] = [ c.number_format.lower()\ for col in workbook1.active.iter_cols()\ @@ -61,7 +63,7 @@ def compare_table(actual: str, expected: str, **options) -> float: if c.data_type=="n" ] new_metric: bool = number_formats1==number_formats2 - print("Number Format Metric: {:}".format(new_metric)) + logger.debug("Number Format Metric: {:}".format(new_metric)) else: raise NotImplementedError("Unsupported xlsx feature: {:}".format(ftr)) metric = metric and new_metric @@ -79,7 +81,7 @@ def check_sheet_list(result: str, rules: List[Dict[str, Any]]) -> float: expected_name: str = worksheet_names[r["sheet_idx"]] actual_name: str = r["sheet_name"] metric: bool = expected_name == actual_name - print("Assertion: {:d}.{:} is {:} - {:}".format(r["sheet_idx"], actual_name, expected_name, metric)) + logger.debug("Assertion: {:d}.{:} is {:} - {:}".format(r["sheet_idx"], actual_name, expected_name, metric)) passes = passes and metric elif r["type"] == "sheet_data": if isinstance(r["sheet_idx0"], int): @@ -99,7 +101,7 @@ def check_sheet_list(result: str, rules: List[Dict[str, Any]]) -> float: sheet_idx: int = int(sheet_idx) df2: pd.DataFrame = pd.read_excel(file_name, sheet_idx) metric: bool = df1.equals(df2) - print("Assertion: {:} == {:} - {:}".format(r["sheet_idx0"], r["sheet_idx1"], metric)) + logger.debug("Assertion: {:} == {:} - {:}".format(r["sheet_idx0"], r["sheet_idx1"], metric)) passes = passes and metric else: raise NotImplementedError("Unimplemented sheet check: {:}".format(r["type"])) diff --git a/desktop_env/evaluators/metrics/utils.py b/desktop_env/evaluators/metrics/utils.py index b826d87..93bc778 100644 --- a/desktop_env/evaluators/metrics/utils.py +++ b/desktop_env/evaluators/metrics/utils.py @@ -11,6 +11,9 @@ from openpyxl.chart._chart import ChartBase from typing import Dict, List, Set from typing import Any +import logging +logger = logging.getLogger("desktopenv.metrics.utils") + _xlsx_namespaces = [ ("x14", "http://schemas.microsoft.com/office/spreadsheetml/2009/9/main") , ("xm", "http://schemas.microsoft.com/office/excel/2006/main") ] diff --git a/desktop_env/evaluators/metrics/vlc.py b/desktop_env/evaluators/metrics/vlc.py index d3083c2..2f5a9ff 100644 --- a/desktop_env/evaluators/metrics/vlc.py +++ b/desktop_env/evaluators/metrics/vlc.py @@ -5,6 +5,9 @@ from xml.etree import ElementTree import pygetwindow as gw import pyautogui +import logging +logger = logging.getLogger("desktopenv.metrics.vlc") + def read_vlc_config(setting_name): """ Reads the VLC configuration file to check for a specific setting. @@ -24,7 +27,7 @@ def read_vlc_config(setting_name): config_path = paths.get(os_type) if not config_path or not os.path.exists(config_path): - print("VLC config file not found for this operating system.") + logger.warning("VLC config file not found for this operating system.") return None try: @@ -33,7 +36,7 @@ def read_vlc_config(setting_name): if line.startswith(setting_name): return line.strip() except IOError as e: - print(f"Error reading config file: {e}") + logger.error(f"Error reading config file: {e}") return None @@ -53,7 +56,7 @@ def get_vlc_playing_info(host='localhost', port=8080, password='password'): return status, file_info return status, None except Exception as e: - print(f"Error: {e}") + logger.error(f"Error: {e}") return None, None @@ -78,10 +81,10 @@ def is_vlc_fullscreen(): except IndexError: # VLC window not found - print("VLC window not found.") + logger.error("VLC window not found.") return False except Exception as e: - print(f"An error occurred: {e}") + logger.error(f"An error occurred: {e}") return False diff --git a/desktop_env/server/main.py b/desktop_env/server/main.py index e565787..26fc2a4 100644 --- a/desktop_env/server/main.py +++ b/desktop_env/server/main.py @@ -16,17 +16,19 @@ app = Flask(__name__) pyautogui.PAUSE = 0 pyautogui.DARWIN_CATCH_UP_TIME = 0 +logger = app.logger @app.route('/setup/execute', methods=['POST']) @app.route('/execute', methods=['POST']) def execute_command(): data = request.json # The 'command' key in the JSON request should contain the command to be executed. - command = data.get('command', []) + shell = data.get('shell', False) + command = data.get('command', "" if shell else []) # Execute the command without any safety checks. try: - result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True) + result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=shell, text=True) return jsonify({ 'status': 'success', 'output': result.stdout, @@ -94,7 +96,7 @@ def capture_screen_with_cursor(): # Use the screencapture utility to capture the screen with the cursor subprocess.run(["screencapture", "-C", file_path]) else: - print(f"The platform you're using ({user_platform}) is not currently supported") + logger.warning(f"The platform you're using ({user_platform}) is not currently supported") return send_file(file_path, mimetype='image/png') @@ -190,7 +192,7 @@ def download_file(): return "File downloaded successfully" except requests.RequestException as e: - print(f"Failed to download {url}. Retrying... ({max_retries - i - 1} attempts left)") + logger.error(f"Failed to download {url}. Retrying... ({max_retries - i - 1} attempts left)") return f"Failed to download {url}. No retries left. Error: {e}", 500 diff --git a/evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json b/evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json index 21adb0d..449fa26 100644 --- a/evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json +++ b/evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json @@ -25,7 +25,7 @@ "-f", "/home/david/thunderbird-profile.tar.gz", "-C", - "$HOME/" + "/home/david/" ] } }, @@ -61,7 +61,7 @@ "command": [ "python3", "/home/david/firefox_decrypt.py", - "$HOME/.thunderbird", + "/home/david/.thunderbird", "-n", "-c", "2", @@ -80,6 +80,7 @@ "path": "thunderbird-accounts.csv" }, "expected": { + "type": "rule", "rules": { "expect": [ { diff --git a/evaluation_examples/examples/thunderbird/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json b/evaluation_examples/examples/thunderbird/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json index e659ede..7e977de 100644 --- a/evaluation_examples/examples/thunderbird/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json +++ b/evaluation_examples/examples/thunderbird/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json @@ -25,7 +25,7 @@ "-f", "/home/david/thunderbird-profile.tar.gz", "-C", - "$HOME/" + "/home/david/" ] } }, @@ -61,7 +61,7 @@ "command": [ "python3", "/home/david/firefox_decrypt.py", - "$HOME/.thunderbird", + "/home/david/.thunderbird", "-n", "-c", "2", @@ -80,6 +80,7 @@ "path": "thunderbird-accounts.csv" }, "expected": { + "type": "rule", "rules": { "unexpect": [ { diff --git a/main.py b/main.py index 806ca28..cebb934 100644 --- a/main.py +++ b/main.py @@ -1,21 +1,57 @@ import json from desktop_env.envs.desktop_env import DesktopEnv +import logging +import os +import sys +import datetime + +# Logger Configs {{{ # +logger = logging.getLogger() +logger.setLevel(logging.DEBUG) + +datetime_str: str = datetime.datetime.now().strftime("%Y%m%d@%H%M%S") + +file_handler = logging.FileHandler(os.path.join("logs", "normal-{:}.log".format(datetime_str))) +debug_handler = logging.FileHandler(os.path.join("logs", "debug-{:}.log".format(datetime_str))) +stdout_handler = logging.StreamHandler(sys.stdout) +sdebug_handler = logging.FileHandler(os.path.join("logs", "sdebug-{:}.log".format(datetime_str))) + +file_handler.setLevel(logging.INFO) +debug_handler.setLevel(logging.DEBUG) +stdout_handler.setLevel(logging.INFO) +sdebug_handler.setLevel(logging.DEBUG) + +formatter = logging.Formatter(fmt="\x1b[1;33m[%(asctime)s \x1b[31m%(levelname)s \x1b[32m%(module)s/%(lineno)d-%(processName)s\x1b[1;33m] \x1b[0m%(message)s") +file_handler.setFormatter(formatter) +debug_handler.setFormatter(formatter) +stdout_handler.setFormatter(formatter) +sdebug_handler.setFormatter(formatter) + +stdout_handler.addFilter(logging.Filter("desktopenv")) +sdebug_handler.addFilter(logging.Filter("desktopenv")) + +logger.addHandler(file_handler) +logger.addHandler(debug_handler) +logger.addHandler(stdout_handler) +logger.addHandler(sdebug_handler) +# }}} Logger Configs # + +logger = logging.getLogger("desktopenv.main") def human_agent(): """ Runs the Gym environment with human input. """ - with open("evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json", "r") as f: + with open("evaluation_examples/examples/thunderbird/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json", "r") as f: example = json.load(f) - example["snapshot"] = "Snapshot 10" + example["snapshot"] = "Snapshot 13" env = DesktopEnv( path_to_vm="/home/david/vmware/KUbuntu 64-bit/KUbuntu 64-bit.vmx" , action_space="computer_13" , task_config=example ) - # reset the environment to certain snapshot observation = env.reset() done = False @@ -38,24 +74,26 @@ def human_agent(): # "action_type": 0, # "click_type": 3, # } - print(trajectory[i]) + logger.info(trajectory[i]) observation, reward, done, info = env.step(trajectory[i], pause=5) - print("Observation:", observation) - print("Reward:", reward) - print("Info:", info) + logger.info("Observation: %s", observation) + logger.info("Reward: %.2f", reward) + logger.info("Info: %s", info) - print("================================\n") + logger.info("================================\n") if done: - print("The episode is done.") + logger.info("The episode is done.") break result = env.evaluate() - print("Result:", result) + logger.info("Result: %.2f", result) + + #input("PAUSING") env.close() - print("Environment closed.") + logger.info("Environment closed.") if __name__ == "__main__":