Analyze xunit test run

xunit_testrun_da.py

import pandas as pd
from bs4 import BeautifulSoup

# Update: Ensure file path handling is robust
file_path = "C:/Users/jskal/OneDrive/Plocha/tests.txt"

try:
    # Load the HTML file
    with open(file_path, 'r') as file:
        html_content = file.read()
except FileNotFoundError:
    raise FileNotFoundError(f"The file at {file_path} was not found. Please ensure the path is correct and the file exists.")

# Parse the HTML using BeautifulSoup
soup = BeautifulSoup(html_content, 'html.parser')

# Extract the table
table = soup.find('table')
if table is None:
    raise ValueError("No <table> element found in the HTML file. Please check the file content.")

# Extract headers
headers = [th.text.strip() for th in table.find_all('th')]
if not headers:
    raise ValueError("No headers found in the table. Ensure the table has a proper <thead> section.")

# Extract rows
rows = []
for tr in table.find_all('tr')[1:]:  # Skip the header row
    cells = [td.text.strip() for td in tr.find_all('td')]
    rows.append(cells)

# Create a DataFrame
if headers and rows:
    df = pd.DataFrame(rows, columns=headers)
else:
    raise ValueError("No rows found in the table. Ensure the table has valid data rows.")

# Clean and process the DataFrame
# Extract Section from 'Test suite' column
def extract_section(test_suite):
    parts = test_suite.split('.')
    return parts[4] if len(parts) > 4 else None

df['Section'] = df['Test suite'].apply(extract_section)

# Convert time strings to milliseconds
def convert_time_to_ms(time_str):
    if 'ms' in time_str:
        return float(time_str.replace('ms', ''))
    elif 's' in time_str:
        return float(time_str.replace('s', '')) * 1000
    else:
        return 0

df['Time_ms'] = df['Time'].apply(convert_time_to_ms)

# Sum time by section
section_summary = df.groupby('Section')['Time_ms'].sum().reset_index().sort_values(by='Time_ms', ascending=False)

# Rename columns for clarity
section_summary.rename(columns={'Time_ms': 'Total Time (ms)'}, inplace=True)

import pandas as pd

# Display the summarized data to the user
print("Test Duration Summary by Section:")
print(section_summary)