lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #8 from xlang-ai/xiaochuanli/addChromeExtensions

Browse Source 
finish the rest part of chrome examples and verify them on mac arm64
This commit is contained in:
Tianbao Xie
2024-02-25 00:59:11 +08:00
committed by GitHub
parent 792d8844c7 0a6b5b3f57
commit cc1f0e2dff
26 changed files with 1993 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
desktop_env/evaluators/getters/__init__.py
View File

@@ -17,14 +17,21 @@ from .chrome import (
get_enable_do_not_track,
get_enable_enhanced_safety_browsing,
get_new_startup_page,
get_find_unpacked_extension_path
get_find_unpacked_extension_path,
get_data_delete_automacally,
get_active_tab_html_parse,
get_active_tab_html_parse_accTree,
get_active_tab_url_parse,
get_gotoRecreationPage_and_get_html_content,
get_url_dashPart,
get_active_url_from_accessTree
)
from .file import get_cloud_file, get_vm_file, get_cache_file
from .general import get_vm_command_line, get_vm_terminal_output
from .gimp import get_gimp_config_file
from .impress import get_audio_in_slide
from .info import get_vm_screen_size, get_vm_window_size, get_vm_wallpaper, get_list_directory
from .misc import get_rule, get_accessibility_tree
from .misc import get_rule, get_accessibility_tree, get_rule_relativeTime
from .replay import get_replay
from .vlc import get_vlc_playing_info, get_vlc_config, get_default_video_player
from .vscode import get_vscode_config

304
desktop_env/evaluators/getters/chrome.py
View File

@@ -1,12 +1,27 @@
import json
import logging
import os
import time
import sqlite3
from typing import Dict, Any
from playwright.sync_api import sync_playwright
from typing import Dict, Any, List
from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive, GoogleDriveFileList, GoogleDriveFile
from playwright.sync_api import sync_playwright
from urllib.parse import urlparse, parse_qs
import lxml.etree
from lxml.cssselect import CSSSelector
from lxml.etree import _Element
_accessibility_ns_map = {"st": "uri:deskat:state.at-spi.gnome.org"
, "attr": "uri:deskat:attributes.at-spi.gnome.org"
, "cp": "uri:deskat:component.at-spi.gnome.org"
, "doc": "uri:deskat:document.at-spi.gnome.org"
, "docattr": "uri:deskat:attributes.document.at-spi.gnome.org"
, "txt": "uri:deskat:text.at-spi.gnome.org"
, "val": "uri:deskat:value.at-spi.gnome.org"
, "act": "uri:deskat:action.at-spi.gnome.org"
}
logger = logging.getLogger("desktopenv.getters.chrome")
@@ -371,7 +386,58 @@ def get_open_tabs_info(env, config: Dict[str, str]):
return tabs_info
def get_active_url_from_accessTree(env, config):
"""
Playwright cannot get the url of active tab directly,
so we need to use accessibility tree to get the active tab info.
This function is used to get the active tab url from the accessibility tree.
config:
Dict[str, str]{
'xpath':
the same as in metrics.general.accessibility_tree.
'selectors':
the same as in metrics.general.accessibility_tree.
'goto_prefix':
the prefix you want to add to the beginning of the url to be opened, default is "https://",
(the url we get from accTree does not have prefix)
...(other keys, not used in this function)
}
Return
url: str
"""
accessibility_tree: str = env.controller.get_accessibility_tree()
# download accessibility tree to "/home/user/Desktop"
logger.debug("AT@eval: %s", accessibility_tree)
# first, use accessibility API to get the active tab URL
at: _Element = lxml.etree.fromstring(accessibility_tree)
if "xpath" in config:
elements: List[_Element] = at.xpath(config["xpath"], namespaces=_accessibility_ns_map)
elif "selectors" in config:
selector = CSSSelector(", ".join(config["selectors"]), namespaces=_accessibility_ns_map)
elements: List[_Element] = selector(at)
else:
raise ValueError("At least one of xpath and selectors is required")
if len(elements) == 0:
print("no elements found")
return 0.
active_tab_url = config["goto_prefix"]+elements[0].text if "goto_prefix" in config.keys() else "https://" + elements[0].text
print("active tab url now: {}".format(active_tab_url))
return active_tab_url
def get_active_tab_info(env, config: Dict[str, str]):
"""
This function is used to get all info about active tab.
Warning! This function will reload the target-url page
If the tartget url has cache or cookie, this function may reload to another page.
If you have tested the url will not pop up to another page (check in incongnito mode yourself first),
you can use this function.
config: Dict[str, str]{
# Keys used in get_active_url_from_accessTree: "xpath", "selectors"
}
"""
active_tab_url = get_active_url_from_accessTree(env, config)
host = env.vm_ip
port = 9222 # fixme: this port is hard-coded, need to be changed from config file
@@ -379,24 +445,21 @@ def get_active_tab_info(env, config: Dict[str, str]):
with sync_playwright() as p:
# connect to remote Chrome instance
browser = p.chromium.connect_over_cdp(remote_debugging_url)
active_tab_info = {}
for context in browser.contexts:
for page in context.pages:
if page.is_visible("body"): # check the visibility of the page body to determine the active status
active_tab_info = {
'title': page.title(),
'url': page.url,
'content': page.content() # get the HTML content of the page
}
break
if active_tab_info:
break
# go to the target URL page
page = browser.new_page()
page.goto(active_tab_url)
page.wait_for_load_state('load') # Wait for the 'load' event to complete
active_tab_info = {
'title': page.title(),
'url': page.url,
'content': page.content() # get the HTML content of the page
}
browser.close()
print("active_tab_title: {}".format(active_tab_info.get('title', 'None')))
print("active_tab_url: {}".format(active_tab_info.get('url', 'None')))
print("active_tab_content: {}".format(active_tab_info.get('content', 'None')))
# print("active_tab_title: {}".format(active_tab_info.get('title', 'None')))
# print("active_tab_url: {}".format(active_tab_info.get('url', 'None')))
# print("active_tab_content: {}".format(active_tab_info.get('content', 'None')))
return active_tab_info
@@ -683,3 +746,208 @@ def get_find_unpacked_extension_path(env, config: Dict[str, str]):
except Exception as e:
logger.error(f"Error: {e}")
return "Google"
def get_data_delete_automacally(env, config: Dict[str, str]):
"""
This function is used to open th "auto-delete" mode of chromium
"""
os_type = env.vm_platform
if os_type == 'Windows':
preference_file_path = env.controller.execute_python_command("""import os; print(os.path.join(os.getenv('LOCALAPPDATA'),
'Google\\Chrome\\User Data\\Default\\Preferences'))""")['output'].strip()
elif os_type == 'Darwin':
preference_file_path = env.controller.execute_python_command(
"import os; print(os.path.join(os.getenv('HOME'), 'Library/Application Support/Google/Chrome/Default/Preferences'))")[
'output'].strip()
elif os_type == 'Linux':
# preference_file_path = env.controller.execute_python_command(
# "import os; print(os.path.join(os.getenv('HOME'), '.config/google-chrome/Default/Preferences'))")[
# 'output'].strip()
preference_file_path = env.controller.execute_python_command(
"import os; print(os.path.join(os.getenv('HOME'), 'snap/chromium/common/chromium/Default/Preferences'))")[
'output'].strip()
else:
raise Exception('Unsupported operating system')
try:
content = env.controller.get_file(preference_file_path)
data = json.loads(content)
data_delete_state = data["profile"]["exit_type"]
return data_delete_state
except Exception as e:
logger.error(f"Error: {e}")
return "Google"
def get_active_tab_html_parse(env, config: Dict[str, Any]):
"""
This function is used to get the specific element's text content from the active tab's html.
config:
Dict[str, str]{
# Keys used in get_active_url_from_accessTree: "xpath", "selectors"
'category':
choose from ["class", "label", "xpath", "input"], used to indicate how to find the element
'labelObject':
only exists when category is "label",
a dict like { "labelSelector": "the key you want to store the text content of this label's ee=lement"}
'class_singleObject':
only exists when category is "class", a dict with keys as the class name,
like { "class name" : "the key you want to store the text content of this element" }
'class_multiObject':
only exists when category is "class", used for elements with same class name.
Two layer of dict, like
( {
"class name": {
"rank in this class" : "the key you want to store the text content of this element"
...
}
} )
'xpathObject':
only exists when category is "xpath", a dict with keys as the xpath,
like { "full xpath" : "the key you want to store the text content of this element" }
'inputObject':
only exists when category is "input",
a dict with keys as the input element's xpath, like { "full xpath" : "the key you want to store the text content of this element" }
}
"""
active_tab_url = get_active_url_from_accessTree(env, config)
host = env.vm_ip
port = 9222 # fixme: this port is hard-coded, need to be changed from config file
remote_debugging_url = f"http://{host}:{port}"
with sync_playwright() as p:
# connect to remote Chrome instance
browser = p.chromium.connect_over_cdp(remote_debugging_url)
target_page = None
for context in browser.contexts:
for page in context.pages:
page.wait_for_load_state("load")
if page.url == active_tab_url:
target_page = page
break
return_json = {}
if config["category"] == "class":
#find the text of elements in html with specific class name
class_multiObject = config["class_multiObject"]
for key in class_multiObject.keys():
object_dict = class_multiObject[key]
for order_key in object_dict.keys():
return_json[object_dict[order_key]] = target_page.query_selector_all("."+key)[int(order_key)].text_content().strip()
class_singleObject = config["class_singleObject"]
for key in class_singleObject.keys():
return_json[class_singleObject[key]] = target_page.query_selector("."+key).text_content().strip()
elif config['category'] == "label":
#find the text of elements in html with specific label name
labelObject = config["labelObject"]
for key in labelObject.keys():
return_json[labelObject[key]] = target_page.get_by_label(key).text_content().strip()
elif config["category"] == "xpath":
#find the text of elements in html with specific xpath
xpathObject = config["xpathObject"]
for key in xpathObject.keys():
return_json[xpathObject[key]] = target_page.locator("xpath="+key).text_content().strip()
elif config["category"] == "input":
inputObject = config["inputObject"]
for key in inputObject.keys():
return_json[inputObject[key]] = target_page.locator("xpath="+key).input_value().strip()
browser.close()
return return_json
def get_gotoRecreationPage_and_get_html_content(env, config: Dict[str, Any]):
"""
especially used for www.recreation.gov examples
"""
host = env.vm_ip
port = 9222 # fixme: this port is hard-coded, need to be changed from config file
remote_debugging_url = f"http://{host}:{port}"
with sync_playwright() as p:
browser = p.chromium.connect_over_cdp(remote_debugging_url)
page = browser.new_page()
page.goto("https://www.recreation.gov/")
page.fill("input#hero-search-input", "Albion Basin")
page.click("button.nav-search-button")
print("after first click")
time.sleep(2)
# Assuming .search-result-highlight--success leads to a new page or requires page load
with page.expect_popup() as popup_info:
page.click(".search-result-highlight--success")
print("after second click")
newpage = popup_info.value
newpage.wait_for_load_state()
print("go to newpage: ")
print(newpage.title())
time.sleep(2)
newpage.click("button.next-available")
print("after third click")
return_json = {}
return_json["expected"]={}
#find the text of elements in html with specific class name
if config["selector"] == "class":
if "order" in config.keys():
className = config["class"]
return_json["expected"][className]=newpage.query_selector_all("."+className)[int(config["order"])].text_content().strip()
else:
className = config["class"]
return_json["expected"][className] = newpage.query_selector("."+className).text_content().strip()
browser.close()
return return_json
def get_active_tab_url_parse(env, config:Dict[str, Any]):
"""
This function is used to parse the url according to config["parse_keys"].
config:
'parse_keys': must exist,
a list of keys to extract from the query parameters of the url.
'replace': optional,
a dict, used to replace the original key with the new key.
( { "original key": "new key" } )
"""
active_tab_url = get_active_url_from_accessTree(env, config)
# connect to remote Chrome instance
# parse in a hard-coded way to find the specific info about task
parsed_url = urlparse(active_tab_url)
# Extract the query parameters
query_params = parse_qs(parsed_url.query)
# Define the keys of interest
keys_of_interest = [key for key in config["parse_keys"]]
# Extract the parameters of interest
extracted_params = {key: query_params.get(key, [''])[0] for key in keys_of_interest}
if "replace" in config:
for key in config["replace"].keys():
# change original key to new key, keep value unchange
value = extracted_params.pop(key)
extracted_params[config["replace"][key]] = value
return extracted_params
def get_url_dashPart(env, config: Dict[str, str]):
"""
This function is used to extract one of the dash-separated part of the URL.
config
'partIndex': must exist,
the index of the dash-separated part to extract, starting from 0.
'needDeleteId': optional,
a boolean, used to indicate whether to delete the "id" part ( an example: "/part-you-want?id=xxx" )
'returnType': must exist,
a string, used to indicate the return type, "string" or "json".
"""
active_tab_url = get_active_url_from_accessTree(env, config)
# extract the last dash-separated part of the URL, and delete all the characters after "id"
dash_part = active_tab_url.split("/")[config["partIndex"]]
if config["needDeleteId"]:
dash_part = dash_part.split("?")[0]
# print("active_tab_title: {}".format(active_tab_info.get('title', 'None')))
# print("active_tab_url: {}".format(active_tab_info.get('url', 'None')))
# print("active_tab_content: {}".format(active_tab_info.get('content', 'None')))
if config["returnType"] == "string":
return dash_part
elif config["returnType"] == "json":
return {config["key"]: dash_part}

175
desktop_env/evaluators/getters/misc.py
View File

@@ -1,10 +1,78 @@
import logging
from typing import TypeVar
from datetime import datetime, timedelta
logger = logging.getLogger("desktopenv.getters.misc")
R = TypeVar("Rule")
day_of_week_mapping = {
0: 'Mon',
1: 'Tue',
2: 'Wed',
3: 'Thu',
4: 'Fri',
5: 'Sat',
6: 'Sun'
}
month_mapping = {
1: 'Jan',
2: 'Feb',
3: 'Mar',
4: 'Apr',
5: 'May',
6: 'Jun',
7: 'Jul',
8: 'Aug',
9: 'Sep',
10: 'Oct',
11: 'Nov',
12: 'Dec'
}
Month_Mapping_Full = {
1: "January",
2: "February",
3: "March",
4: "April",
5: "May",
6: "June",
7: "July",
8: "August",
9: "September",
10: "October",
11: "November",
12: "December"
}
month_mapping_full = {
1: 'january',
2: 'february',
3:'march',
4: 'april',
5:'may',
6: 'june',
7: 'july',
8: 'august',
9:'september',
10: 'october',
11: 'november',
12: 'december'
}
relativeTime_to_IntDay = {
"tomorrow": 1,
"5th next month": "special",
"10th next month": "special",
"11th next month": "special",
"this month": "special",
"this Saturday": "special",
"this Sunday": "special",
"next Monday": "special",
"next Friday": "special",
"first monday four months later": "special"
}
def get_rule(env, config: R) -> R:
"""
@@ -12,6 +80,113 @@ def get_rule(env, config: R) -> R:
"""
return config["rules"]
def get_rule_relativeTime(env, config: R) -> R:
"""
According to the rule definded in funciton "apply_rules_to_timeFormat", convert the relative time to absolute time.
config:
'relativeTime': {
"from": must exist; indicates the relativeTime.
"to": optional; indicates the relativeTime.
}
If relativeTime only has key "from", then the key of time in "expected" dict must be "time".
If relativeTime has key "to", then the key of time in "expected" dict must be "from" and "to".
"""
relativeRules = config["rules"]
relativeTime = relativeRules["relativeTime"] # int, "+" means future, "-" means past
# get the date now
now = datetime.now()
# calculate the relative time
if "to" not in relativeTime.keys():
start_relative_time = relativeTime["from"]
if relativeTime_to_IntDay[start_relative_time] != "special":
# relativeTime can be represented by actual int days
start_relative_time_IntDat = relativeTime_to_IntDay[start_relative_time]
timediff = timedelta(days=start_relative_time_IntDat)
absoluteDay = now + timediff
else:
# special case, you can add more special cases here
if start_relative_time == "5th next month":
next_year = now.year + 1 if now.month == 12 else now.year
next_month = now.month + 1 if now.month < 12 else 1
next_day = 5
absoluteDay = datetime(next_year, next_month, next_day)
elif start_relative_time == "10th next month":
next_year = now.year + 1 if now.month == 12 else now.year
next_month = now.month + 1 if now.month < 12 else 1
next_day = 10
absoluteDay = datetime(next_year, next_month, next_day)
elif start_relative_time == "this month":
absoluteDay = now
elif start_relative_time == "next Monday":
absoluteDay = now + timedelta(days=((6-now.weekday())+1))
elif start_relative_time == "first monday four months later":
next_year = now.year + 1 if now.month >=9 else now.year
next_month = (now.month + 4)%12
# get the first monday of the next_month
temp_date = datetime(next_year, next_month, 1)
absoluteDay = temp_date + timedelta(days=((6-temp_date.weekday())+1)%7)
regular_time = apply_rules_to_timeFormat(relativeRules["expected"]["time"], absoluteDay)
config["rules"]["expected"]["time"] = regular_time
else:
from_time = relativeTime["from"]
to_time = relativeTime["to"]
# deal with from_time first
if relativeTime_to_IntDay[from_time] != "special":
from_time_IntDat = relativeTime_to_IntDay[from_time]
from_timediff = timedelta(days=from_time_IntDat)
from_absoluteDay = now + from_timediff
else:
if from_time == "this Saturday":
from_absoluteDay = now + timedelta(days=(5-now.weekday()))
elif from_time == "10th next month":
next_year = now.year + 1 if now.month == 12 else now.year
next_month = now.month + 1 if now.month < 12 else 1
next_day = 10
from_absoluteDay = datetime(next_year, next_month, next_day)
elif from_time == "next Monday":
from_absoluteDay = now + timedelta(days=((6-now.weekday())+1))
else:
pass # more rules here
regular_from_time = apply_rules_to_timeFormat(relativeRules["expected"]["from"], from_absoluteDay)
config["rules"]["expected"]["from"] = regular_from_time
# deal with to_time
if relativeTime_to_IntDay[to_time] != "special":
to_time_IntDat = relativeTime_to_IntDay[to_time]
to_timediff = timedelta(days=to_time_IntDat)
to_absoluteDay = now + to_timediff
else:
if to_time == "this Sunday":
to_absoluteDay = now + timedelta(days=(6-now.weekday()))
elif to_time == "11th next month":
next_year = now.year + 1 if now.month == 12 else now.year
next_month = now.month + 1 if now.month < 12 else 1
next_day = 11
to_absoluteDay = datetime(next_year, next_month, next_day)
elif to_time == "next Friday":
to_absoluteDay = now + timedelta(days=((4-now.weekday()) if now.weekday() < 4 else (6-now.weekday()) + 5))
else:
pass # more rules here
regular_to_time = apply_rules_to_timeFormat(relativeRules["expected"]["to"], to_absoluteDay)
config["rules"]["expected"]["to"] = regular_to_time
return config["rules"]
def apply_rules_to_timeFormat(timeFormat: str, absoluteDay: datetime):
timeFormat = timeFormat.replace("{DoW}", day_of_week_mapping[absoluteDay.weekday()], 1)
timeFormat = timeFormat.replace("{Month}", month_mapping[absoluteDay.month], 1)
timeFormat = timeFormat.replace("{DayD}", str(absoluteDay.day), 1)
timeFormat = timeFormat.replace("{Year}", str(absoluteDay.year), 1)
timeFormat = timeFormat.replace("{Month0D}", "0"+str(absoluteDay.month) if absoluteDay.month < 10 else str(absoluteDay.month), 1)
timeFormat = timeFormat.replace("{month}", month_mapping_full[absoluteDay.month], 1)
timeFormat = timeFormat.replace("{MonthFull}", Month_Mapping_Full[absoluteDay.month], 1)
timeFormat = timeFormat.replace("{Day0D}", "0"+str(absoluteDay.day) if absoluteDay.day < 10 else str(absoluteDay.day), 1)
# you can add other replace rules here
return timeFormat
def get_accessibility_tree(env, *args) -> str:
accessibility_tree: str = env.controller.get_accessibility_tree()

4
desktop_env/evaluators/metrics/__init__.py
View File

@@ -17,6 +17,7 @@ from .chrome import (
check_history_deleted,
is_expected_search_query,
is_expected_active_tab,
is_expected_url_pattern_match,
is_added_to_steam_cart
)
from .docs import (
@@ -55,7 +56,8 @@ from .general import (
exact_match,
is_in_list,
fuzzy_match,
check_include_exclude
check_include_exclude,
check_direct_json_object
)
from .gimp import (
check_brightness_decrease_and_structure_sim,

21
desktop_env/evaluators/metrics/chrome.py
View File

@@ -29,6 +29,27 @@ def is_expected_active_tab(active_tab_info: Dict[str, str], rule: Dict[str, Any]
logger.error(f"Unknown type: {match_type}")
return 0
# rules[expected] is a string-formatted regex
def is_expected_url_pattern_match(result, rules) -> float:
"""
This function is used to search the expected pattern in the url using regex.
result is the return value of function "activte_tab_info" or return value of function "get_active_url_from_accessTree"
"""
if type(result)== dict:
result_url = result["url"]
print("result url: {}".format(result_url))
else:
result_url = result
# expect_regex = re.compile(rules["expected"])
patterns = rules["expected"]
print("expected_regex: {}".format(patterns))
for pattern in patterns:
match = re.search(pattern, result_url)
print(match)
if not match:
return 0.
return 1.
def is_expected_tabs(open_tabs: List[Dict[str, str]], rule: Dict[str, Any]) -> float:
"""

23
desktop_env/evaluators/metrics/general.py
View File

@@ -44,7 +44,9 @@ def is_in_list(result, rules) -> float:
return 1.
else:
return 0.
def fuzzy_match(result, rules) -> float:
expect = rules["expected"]
@@ -135,7 +137,7 @@ def check_accessibility_tree(result: str, rules: Dict[str, Any]) -> float:
needed. If both are present, `xpath` takes the priority.
"text": str as the expected text content of the selected element.
"exact": bool specifying whether exact match or fuzzy match should
be performed. defaults to True
be performed. defaults to True.
}
Returns:
@@ -152,6 +154,7 @@ def check_accessibility_tree(result: str, rules: Dict[str, Any]) -> float:
raise ValueError("At least one of xpath and selectors is required")
if len(elements) == 0:
print("no elements")
return 0.
if "text" in rules:
@@ -217,3 +220,19 @@ def check_json(result: str, rules: Dict[str, List[Dict[str, Union[List[str], str
value = value[k]
metric = metric and not _match_value_to_rule(value, r)
return metric
def check_direct_json_object(result, rules)->float:
"""
One of the most commonly used function to evalute.
Compare two json objects directly.
"""
print("result: ")
print(result)
print("expected: ")
print(rules["expected"])
expected_json = rules["expected"]
for key in expected_json.keys():
if expected_json[key] != result[key]:
return 0.
return 1.0

93
evaluation_examples/examples/chrome/1704f00f-79e6-43a7-961b-cedd3724d5fd.json Normal file
View File

@@ -0,0 +1,93 @@
{
"id": "1704f00f-79e6-43a7-961b-cedd3724d5fd",
"snapshot": "chrome",
"instruction": "Find a large car with lowest price from next Monday to next Friday in Zurich.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.rentalcars.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["check_direct_json_object", "check_direct_json_object"],
"result": [{
"type": "active_tab_url_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"parse_keys": ["locationName", "dropLocationName", "filterCriteria_carCategory", "filterCriteria_sortBy"]
},
{
"type": "active_tab_html_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject":{
"/html/body/main/div/div/div/section/div/div/div/div[1]/div[1]/p": "from",
"/html/body/main/div/div/div/section/div/div/div/div[1]/div[3]/p": "to"
}
}],
"expected":[{
"type": "rule",
"rules":{
"expected": {
"locationName": "Zurich Airport",
"dropLocationName": "Zurich Airport",
"filterCriteria_carCategory": "large",
"filterCriteria_sortBy": "PRICE"
}
}
},
{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from":"next Monday",
"to":"next Friday"
},
"expected": {
"from": "{DoW}, {DayD} {Month} {Year}, 10:00",
"to": "{DoW}, {DayD} {Month} {Year}, 10:00"
}
}}
]
}
}

66
evaluation_examples/examples/chrome/2888b4e6-5b47-4b57-8bf5-c73827890774.json Normal file
View File

@@ -0,0 +1,66 @@
{
"id": "2888b4e6-5b47-4b57-8bf5-c73827890774",
"snapshot": "chrome",
"instruction": "Find a men's T-Shirt that is in large size with a stripe pattern, short sleeve and under the Sales&Discount.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.macys.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"exact_match",
"result": {
"type": "url_dashPart",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": true,
"returnType": "string"
},
"expected":{
"type": "rule",
"rules":{
"expected": "Stripe,Men,L,Short%20Sleeve,Sales%20%26%20Discounts"
}
}
}
}

95
evaluation_examples/examples/chrome/368d9ba4-203c-40c1-9fa3-da2f1430ce63.json
View File

@@ -1,18 +1,85 @@
{
"id": "368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"snapshot": "chrome",
"instruction": "find the Monthly forecast for Manchester, GB for January",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
"id": "368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"snapshot": "chrome",
"instruction": "find the Monthly forecast for Manchester, GB for this month",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.accuweather.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["check_direct_json_object", "is_expected_url_pattern_match"],
"result": [{
"type": "url_dashPart",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"partIndex": -2,
"needDeleteId": false,
"returnType": "json",
"key":"time"
},
{
"type": "active_tab_info",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
}],
"expected":[
{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "this month"
},
"expected": {
"time": "{month}-weather"
}
}
},
{
"type": "rule",
"rules":{
"expected": ["\/manchester\/"]
}
}]
}
}
}

120
evaluation_examples/examples/chrome/47543840-672a-467d-80df-8f7c3b9788c9.json Normal file
View File

@@ -0,0 +1,120 @@
{
"id": "47543840-672a-467d-80df-8f7c3b9788c9",
"snapshot": "chrome",
"instruction": "Find and select the car with the most number of seats to pick up in Boston Logan Intl Airport from 10th next month to 11th next month.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.budget.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["is_expected_url_pattern_match", "check_direct_json_object", "check_direct_json_object"],
"conj": "and",
"result": [
{
"type": "active_url_from_accessTree",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
{
"type": "active_tab_html_parse",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject":{},
"class_multiObject":{
"location-info":{
"0": "start_location",
"1": "end_location"
},
"day-time-info":{
"0": "from",
"1": "to"
}
}
},
{
"type": "active_tab_html_parse",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject":{
"/html/body/div[6]/div[2]/div[1]/div/div/div[2]/div[1]/section[1]/div/form/div[1]/div[2]/div/a": "rank"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["reservation#\/vehicles"]
}
},
{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from":"10th next month",
"to": "11th next month"
},
"expected": {
"start_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t Pick-Up",
"end_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS",
"from": "{DoW}, {Month} {Day0D}, 12:00 PM",
"to": "{DoW}, {Month} {Day0D}, 12:00 PM"
}
}
},
{
"type": "rule",
"rules":{
"expected": {
"rank": "Number of Seats (High to Low)"
}
}
}
]
}
}

81
evaluation_examples/examples/chrome/6c4c23a1-42a4-43cc-9db1-2f86ff3738cc.json Normal file
View File

@@ -0,0 +1,81 @@
{
"id": "6c4c23a1-42a4-43cc-9db1-2f86ff3738cc",
"snapshot": "chrome",
"instruction": "Find flights from Seattle to New York on 5th next month and only show those that can be purchased with miles.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.delta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject":{
"search-date": "time",
"price-in-tabs__nav--selected": "category"
},
"class_multiObject":{
"search-segment-cities__city": {
"0": "start",
"1": "end"
}
}
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "5th next month"
},
"expected": {
"start": "SEA",
"end": "NYC",
"time": "{DoW}, {Month} {DayD}, {Year}",
"category": "Miles"
}
}
}
}
}

66
evaluation_examples/examples/chrome/7f52cab9-535c-4835-ac8c-391ee64dc930.json Normal file
View File

@@ -0,0 +1,66 @@
{
"id": "7f52cab9-535c-4835-ac8c-391ee64dc930",
"snapshot": "chrome",
"instruction": "Create a list of drip coffee makers that are on sale and within $25-60 and have a black finish.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://shopping.google.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"parse_keys": ["q", "tbs"]
},
"expected":{
"type": "rule",
"rules":{
"expected": {
"q": "drip coffee maker",
"tbs": "mr:1,price:1,ppr_min:25,ppr_max:60,pdtr0:1825161|1825162"
}
}
}
}
}

68
evaluation_examples/examples/chrome/82279c77-8fc6-46f6-9622-3ba96f61b477.json Normal file
View File

@@ -0,0 +1,68 @@
{
"id": "82279c77-8fc6-46f6-9622-3ba96f61b477",
"snapshot": "chrome",
"instruction": "Find electric cars with a maximum price of $50,000 within 50 miles of 10001.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.cars.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"parse_keys": ["list_price_max", "maximum_distance", "zip","fuel_slugs[]"]
},
"expected":{
"type": "rule",
"rules":{
"expected": {
"list_price_max": "50000",
"maximum_distance": "50",
"zip":"10001",
"fuel_slugs[]":"electric"
}
}
}
}
}

73
evaluation_examples/examples/chrome/82bc8d6a-36eb-4d2d-8801-ef714fb1e55a.json Normal file
View File

@@ -0,0 +1,73 @@
{
"id": "82bc8d6a-36eb-4d2d-8801-ef714fb1e55a",
"snapshot": "chrome",
"instruction": "On April 21, look up a flight from Mumbai to Stockholm.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.qatarairways.com/en-hk/homepage.html"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"parse_keys": ["fromStation", "toStation", "departing"],
"replace":{
"departing": "time"
}
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from": "next Monday"
},
"expected": {
"fromStation": "BOM",
"toStation": "STO",
"time": "{Year}-{Month0D}-{DayD}"
}
}
}
}
}

84
evaluation_examples/examples/chrome/9f3f70fc-5afc-4958-a7b7-3bb4fcb01805.json Normal file
View File

@@ -0,0 +1,84 @@
{
"id": "9f3f70fc-5afc-4958-a7b7-3bb4fcb01805",
"snapshot": "chrome",
"instruction": "Browse the list of women's Nike jerseys over $60.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.nba.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["is_expected_url_pattern_match", "check_direct_json_object"],
"conj": "and",
"result": [
{
"type": "active_tab_info",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
]
},
{
"type": "active_tab_html_parse",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"category": "xpath",
"xpathObject":{
"/html/body/div[2]/div/div[6]/div[2]/div[2]/div/div[1]/div[4]/ul/li[2]": "money"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["\/women-jerseys\/"]
}
},
{
"type": "rule",
"rules":{
"expected": {
"money": "over $60"
}
}
}
]
}
}

72
evaluation_examples/examples/chrome/9f935cce-0a9f-435f-8007-817732bfc0a5.json
View File

@@ -1,18 +1,62 @@
{
"id": "9f935cce-0a9f-435f-8007-817732bfc0a5",
"snapshot": "chrome",
"instruction": "Browse list of Civil Division forms.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
"id": "9f935cce-0a9f-435f-8007-817732bfc0a5",
"snapshot": "chrome",
"instruction": "Browse list of Civil Division forms.",
"source": "online_tasks",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.justice.gov/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_tab_info",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": ["forms\\?title=&field_component_target_id=431"]
}
}
}
}
}

70
evaluation_examples/examples/chrome/a96b564e-dbe9-42c3-9ccf-b4498073438a.json
View File

@@ -1,4 +1,74 @@
{
"id": "a96b564e-dbe9-42c3-9ccf-b4498073438a",
"snapshot": "chrome",
"instruction": "Find discussions of community and open one with most replies.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.flightaware.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('alt', 'f10'); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_active_tab",
"result": {
"type": "active_tab_info",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"type": "url",
"url": "https://discussions.flightaware.com/t/graphs-for-dump1090-my-version-with-install-script/46263"
}
}
=======
"id": "a96b564e-dbe9-42c3-9ccf-b4498073438a",
"snapshot": "chrome",
"instruction": "Find discussions of community and open one with most replies.",

77
evaluation_examples/examples/chrome/b070486d-e161-459b-aa2b-ef442d973b92.json
View File

@@ -1,18 +1,65 @@
{
"id": "b070486d-e161-459b-aa2b-ef442d973b92",
"snapshot": "chrome",
"instruction": "Show side effects of Tamiflu.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
"id": " b070486d-e161-459b-aa2b-ef442d973b92",
"snapshot": "chrome",
"instruction": "Show side effects of Tamiflu.",
"source": "online_tasks",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.drugs.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"exact_match",
"result": {
"type": "url_dashPart",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected":{
"type": "rule",
"rules":{
"expected": "tamiflu.html#side-effects"
}
}
}
}
}
}

70
evaluation_examples/examples/chrome/b4f95342-463e-4179-8c3f-193cd7241fb2.json Normal file
View File

@@ -0,0 +1,70 @@
{
"id": "b4f95342-463e-4179-8c3f-193cd7241fb2",
"snapshot": "chrome",
"instruction": "Find the next available date for Albion Basin.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.recreation.gov/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category":"class",
"class_singleObject":{},
"class_multiObject":{
"camp-sortable-column-header":{
"2":"camp-sortable-column-header"
}
}
},
"expected":{
"type":"gotoRecreationPage_and_get_html_content",
"selector": "class",
"class": "camp-sortable-column-header",
"order": "2"
}
}
}

81
evaluation_examples/examples/chrome/b7895e80-f4d1-4648-bee0-4eb45a6f1fa8.json Normal file
View File

@@ -0,0 +1,81 @@
{
"id": "b7895e80-f4d1-4648-bee0-4eb45a6f1fa8",
"snapshot": "chrome",
"instruction": "Find a Hotel in New York City with lowest price possible for 2 adults this weekend.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.tripadvisor.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject":{
"/html/body/div[1]/main/div[3]/div/div[1]/div[2]/div[1]/div[2]/div/div/div/div/div[1]/div/button/div[3]":"from",
"/html/body/div[1]/main/div[3]/div/div[1]/div[2]/div[1]/div[2]/div/div/div/div/div[2]/button/div[3]":"to",
"/html/body/div[1]/main/div[3]/div/div[1]/div[2]/div[1]/div[1]/div/h1":"city",
"/html/body/div[1]/main/div[3]/div/div[1]/div[2]/div[1]/div[2]/div/div/div/div/div[3]/button/div[3]/span/span[2]":"adult",
"/html/body/div[1]/main/div[3]/div/div[2]/div/div[1]/div/div[2]/div[1]/div/div[1]/div/div[1]/div[2]/div/div[2]/div/button/div/div":"rank"
}
},
"expected":
{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "this Saturday",
"to": "this Sunday"
},
"expected": {
"from": "{DoW}, {Month} {DayD}",
"to": "{DoW}, {Month} {DayD}",
"city": "New York City Hotels",
"adult": "2 adults",
"rank": "Price (low to high)"
}
}
}
}
}

72
evaluation_examples/examples/chrome/c1fa57f3-c3db-4596-8f09-020701085416.json Normal file
View File

@@ -0,0 +1,72 @@
{
"id": "c1fa57f3-c3db-4596-8f09-020701085416",
"snapshot": "chrome",
"instruction": "Open the baggage fee calculator.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.united.com/en/us"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('alt', 'f10'); time.sleep(0.5);"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_tab_info",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": ["baggage-calculator"]
}
}
}
}

74
evaluation_examples/examples/chrome/cabb3bae-cccb-41bd-9f5d-0f3a9fecd825.json
View File

@@ -1,18 +1,62 @@
{
"id": "cabb3bae-cccb-41bd-9f5d-0f3a9fecd825",
"snapshot": "chrome",
"instruction": "Browse spider-man toys for kids and sort by lowest price.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
"id": "cabb3bae-cccb-41bd-9f5d-0f3a9fecd825",
"snapshot": "chrome",
"instruction": "Browse spider-man toys for kids and sort by lowest price.",
"source": "online_tasks",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.kohls.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_url_from_accessTree",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": ["AgeAppropriate:Kids", "search=spider-man%20toys", "S=4"]
}
}
}
}
}
}

112
evaluation_examples/examples/chrome/da46d875-6b82-4681-9284-653b0c7ae241.json Normal file
View File

@@ -0,0 +1,112 @@
{
"id": "da46d875-6b82-4681-9284-653b0c7ae241",
"snapshot": "chrome",
"instruction": "Schedule an appointment to apply for transportation access pass in the Charlie Card store on the first Monday four months later, 10:15 am, fill in my details (James Smith, james.smith@gmail.com), and book.",
"source": "test_task_2",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.mbta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["is_expected_url_pattern_match", "check_direct_json_object", "check_direct_json_object"],
"conj": "and",
"result": [
{
"type": "active_tab_info",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
]
},
{
"type": "active_tab_html_parse",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"category": "class",
"class_singleObject":{},
"class_multiObject":{
"breakword":{
"1": "content",
"2": "time"
}
}
},
{
"type": "active_tab_html_parse",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"category": "input",
"inputObject":{
"/html/body/div/div/form/div[7]/div/div/div[1]/input[1]": "name",
"/html/body/div/div/form/div[7]/div/div/div[1]/input[2]": "mail"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["CharlieCardStoreAppointments@mbta.com\/bookings\/"]
}
},
{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from":"first monday four months later"
},
"expected": {
"content": "Apply for Transportation Access Pass (TAP) CharlieCard non-auto approval",
"time": "{MonthFull} {Day0D}, 10:15 am"
}
}
},
{
"type": "rule",
"rules":{
"expected": {
"name": "James Smith",
"mail": "james.smith@gmail.com"
}
}
}
]
}
}

8
evaluation_examples/examples/chrome/f3b19d1e-2d48-44e9-b4e1-defcae1a0197.json
View File

@@ -31,12 +31,16 @@
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_tab_info"
"type": "active_tab_info",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www."
},
"expected":{
"type": "rule",
"rules":{
"expected": "https://seatgeek\\.com/help/articles/\\d+-Buying-Tickets"
"expected": ["https://seatgeek\\.com/help/articles/\\d+-Buying-Tickets"]
}
}
}

77
evaluation_examples/examples/chrome/f79439ad-3ee8-4f99-a518-0eb60e5652b0.json Normal file
View File

@@ -0,0 +1,77 @@
{
"id": "f79439ad-3ee8-4f99-a518-0eb60e5652b0",
"snapshot": "chrome",
"instruction": "Search for a one way flight from Dublin to Vienna on 10th next month for 2 adults.",
"source": "test_task_2",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.ryanair.com/gb/en"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"parse_keys":["originIata", "destinationIata", "tpAdults", "tpTeens", "tpChildren", "tpStartDate", "isReturn"],
"replace":{
"tpStartDate": "time"
}
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "10th next month"
},
"expected": {
"originIata": "DUB",
"destinationIata": "VIE",
"tpAdults": "2",
"tpTeens": "0",
"tpChildren": "0",
"time": "{Year}-{Month0D}-{DayD}",
"isReturn":"false"
}
}
}
}
}

79
evaluation_examples/examples/chrome/fc6d8143-9452-4171-9459-7f515143419a.json Normal file
View File

@@ -0,0 +1,79 @@
{
"id": "fc6d8143-9452-4171-9459-7f515143419a",
"snapshot": "chrome",
"instruction": "Find the status of tomorrow flights from New York airports to Columbus in Ohio.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.delta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"selectors":[
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject":{
"search-date": "time"
},
"class_multiObject":{
"search-segment-cities__city": {
"0": "start",
"1": "end"
}
}
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "tomorrow"
},
"expected": {
"start": "NYC",
"end": "CMH",
"time": "{DoW}, {Month} {DayD}, {Year}"
}
}
}
}
}