284 lines
7.7 KiB
Python
284 lines
7.7 KiB
Python
import copy
|
|
import importlib.util
|
|
import json
|
|
import sys
|
|
import re
|
|
from typing import Dict
|
|
|
|
|
|
def check_json_keybindings(actual: str, expected: str, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): path to result text file
|
|
expected (str): expected dict{}
|
|
|
|
Return:
|
|
float: the score
|
|
"""
|
|
|
|
def direct_load_json(fp):
|
|
try:
|
|
with open(fp, 'r') as f:
|
|
data = json.load(f)
|
|
return data
|
|
except:
|
|
return None
|
|
|
|
def skip_first_line_load_json(fp):
|
|
try:
|
|
with open(fp, 'r') as f:
|
|
f.readline()
|
|
data = json.load(f)
|
|
return data
|
|
except:
|
|
return None
|
|
|
|
for func in [direct_load_json, skip_first_line_load_json]:
|
|
data = func(actual)
|
|
if data is not None and type(data) == list:
|
|
break
|
|
else:
|
|
return 0.0
|
|
expected = expected['expected']
|
|
if expected in data:
|
|
return 1.0
|
|
else:
|
|
return 0.0
|
|
|
|
|
|
def check_json_settings(actual: str, expected: str, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): path to result text file
|
|
expected (dict): expected dict{}, containing key "expect"
|
|
|
|
Return:
|
|
float: the score
|
|
"""
|
|
if not actual:
|
|
return 0.
|
|
|
|
try:
|
|
with open(actual, 'r') as f:
|
|
data = json.load(f)
|
|
except Exception as e:
|
|
return 0.0
|
|
|
|
expect = expected['expected']
|
|
|
|
# Check if all expected key-value pairs are in the actual data
|
|
for key, value in expect.items():
|
|
if key not in data or data[key] != value:
|
|
return 0.0
|
|
|
|
return 1.0
|
|
|
|
|
|
def compare_text_file(actual: str, expected: str, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): path to result text file
|
|
expected (str): path to gold text file
|
|
|
|
Return:
|
|
float: the score
|
|
"""
|
|
if not actual:
|
|
return 0.
|
|
|
|
with open(actual) as f1:
|
|
actual_text = f1.read()
|
|
with open(expected) as f2:
|
|
expected_text = f2.read()
|
|
|
|
ignore_blanks = options.get('ignore_blanks', False)
|
|
if ignore_blanks:
|
|
actual_text = re.sub(r'[\t\n]', ' ', actual_text).strip()
|
|
actual_text = re.sub(r'\s+', ' ', actual_text)
|
|
expected_text = re.sub(r'[\t\n]', ' ', expected_text).strip()
|
|
expected_text = re.sub(r'\s+', ' ', expected_text)
|
|
|
|
ignore_case = options.get('ignore_case', False)
|
|
if ignore_case:
|
|
actual_text = actual_text.lower()
|
|
expected_text = expected_text.lower()
|
|
|
|
if actual_text == expected_text:
|
|
return 1.0
|
|
return 0.0
|
|
|
|
import zipfile
|
|
from difflib import SequenceMatcher
|
|
import PyPDF2
|
|
|
|
def compare_pdf_content(content1, content2, text_similarity_threshold):
|
|
def extract_text_from_pdf(content):
|
|
with open("temp.pdf", "wb") as temp_pdf:
|
|
temp_pdf.write(content)
|
|
with open("temp.pdf", "rb") as temp_pdf:
|
|
pdf_reader = PyPDF2.PdfReader(temp_pdf)
|
|
text = ''
|
|
for page_num in range(len(pdf_reader.pages)):
|
|
page = pdf_reader.pages[page_num]
|
|
text += page.extract_text()
|
|
return text
|
|
|
|
text1 = extract_text_from_pdf(content1)
|
|
text2 = extract_text_from_pdf(content2)
|
|
|
|
similarity_ratio = SequenceMatcher(None, text1, text2).ratio()
|
|
|
|
return similarity_ratio >= text_similarity_threshold
|
|
|
|
def compare_zip_files(actual: str, expected: str, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): path to result zip file
|
|
expected (str): path to gold zip file
|
|
|
|
Return:
|
|
float: the score
|
|
"""
|
|
if not actual:
|
|
return 0.
|
|
|
|
with zipfile.ZipFile(actual, 'r') as zip_file1, zipfile.ZipFile(expected, 'r') as zip_file2:
|
|
file_list1 = set(zip_file1.namelist())
|
|
file_list2 = set(zip_file2.namelist())
|
|
|
|
if file_list1 != file_list2:
|
|
return 0.0
|
|
|
|
for file_name in file_list1:
|
|
content1 = zip_file1.read(file_name)
|
|
content2 = zip_file2.read(file_name)
|
|
|
|
if file_name.lower().endswith('.pdf'):
|
|
if compare_pdf_content(content1, content2, 0.95):
|
|
continue
|
|
else:
|
|
return 0.0
|
|
elif content1 != content2:
|
|
return 0.0
|
|
return 1.0
|
|
|
|
|
|
def compare_config(actual: str, rules: Dict, **options) -> float:
|
|
if not actual:
|
|
return 0.
|
|
|
|
with open(actual) as f1:
|
|
actual_text = f1.read()
|
|
|
|
if actual_text == rules['expected']:
|
|
return 1.0
|
|
return 0.0
|
|
|
|
|
|
def compare_answer(actual: str, rules: Dict, **options) -> float:
|
|
"""
|
|
Args:
|
|
actual (str): result string
|
|
expected (str): gold string
|
|
|
|
Return:
|
|
float: the score
|
|
"""
|
|
if not actual:
|
|
return 0.
|
|
|
|
if actual == rules['expected']:
|
|
return 1.0
|
|
|
|
# TODO: can use text embedding to get non-zero return
|
|
return 0.0
|
|
|
|
|
|
def is_extension_installed(actual: str, rules: Dict, **options):
|
|
if rules['type'] == 'contain':
|
|
if rules['expected'] in actual:
|
|
return 1.0
|
|
return 0.0
|
|
elif rules['type'] == 'not_contain':
|
|
if rules['expected'] not in actual:
|
|
return 1.0
|
|
return 0.0
|
|
else:
|
|
raise NotImplementedError
|
|
|
|
|
|
def check_python_file_by_test_suite(actual_files, test_file, **options) -> float:
|
|
"""Check the python file by running the test suite in the given test file."""
|
|
|
|
test_function_name = options.get('test_function_name', 'test')
|
|
# Create a unique module name, it can be arbitrary but must be unique in the current runtime environment
|
|
module_name = 'dynamic_module'
|
|
|
|
# Load the module from the given file path
|
|
spec = importlib.util.spec_from_file_location(module_name, test_file)
|
|
module = importlib.util.module_from_spec(spec)
|
|
sys.modules[module_name] = module # Add the loaded module to sys.modules
|
|
spec.loader.exec_module(module) # Execute the module to make its content available
|
|
|
|
# Retrieve the function by name from the loaded module and execute it
|
|
test_function = getattr(module, test_function_name)
|
|
try:
|
|
if test_function():
|
|
return 1.0
|
|
else:
|
|
return 0.0
|
|
except Exception as e:
|
|
return 0.0
|
|
|
|
|
|
def check_python_file_by_gold_file(actual_files, gold_file: str, **options) -> float:
|
|
pass
|
|
|
|
|
|
def check_html_background_image(src_path: str, rule: Dict = None) -> float:
|
|
"""
|
|
Check if the background image is correctly set.
|
|
multi-app:bb7db4c2-30b5-4be7-8dd7-b8c4ec7d3108
|
|
"""
|
|
if not src_path:
|
|
return 0.0
|
|
|
|
from bs4 import BeautifulSoup
|
|
with open(src_path, 'r') as f:
|
|
html_content = f.read()
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|
styles = soup.find_all('style')
|
|
for style in styles:
|
|
if f'background-image: url(\'{rule["value"]}\')' in style.text:
|
|
return 1.0
|
|
return 0.0
|
|
|
|
|
|
def compare_result_files(src_path, tgt_path):
|
|
"""
|
|
Compare whether the content of two files are the same.
|
|
multi-app:7f35355e-02a6-45b5-b140-f0be698bcf85
|
|
"""
|
|
if not src_path or not tgt_path:
|
|
return 0.0
|
|
|
|
with open(src_path, 'r') as f:
|
|
src_content = f.read().strip()
|
|
with open(tgt_path, 'r') as f:
|
|
tgt_content = f.read().strip()
|
|
try:
|
|
# Compare the content as numbers
|
|
tgt_content_num = float(tgt_content)
|
|
if tgt_content in src_content:
|
|
# If the content of tgt is in src, return 1.0 since output src might be
|
|
# a superset(language description+number) of tgt
|
|
return 1.0
|
|
src_content_num = float(src_content)
|
|
if abs(src_content_num - tgt_content_num) < 1e-4:
|
|
return 1.0
|
|
return 0.0
|
|
except:
|
|
if src_content == tgt_content:
|
|
return 1.0
|
|
return 0.0
|