Analyzing which files changed in various build PRs

.py

"""Count file name appearances"""
import os
from collections import defaultdict
from glob import glob

# Path to the Desktop
desktop_path = os.path.expanduser("~/Desktop")

# Filenames
filenames = glob(os.path.join(desktop_path, "*.txt"))
# Print
print('Analyzing which files changed in various build PRs, and how many times they appeared in multiple PRs')
print('Reading: ' + ','.join(os.path.basename(x) for x in filenames) + '\n')

# Initialize a defaultdict to store the counts
line_counts = defaultdict(int)

# Read each file and count the occurrences of each line
for filename in filenames:
    file_path = os.path.join(desktop_path, filename)
    with open(file_path, 'r') as file:
        for line in file:
            line = line.strip()  # Remove any leading/trailing whitespace
            line_counts[line] += 1

# Convert defaultdict to a regular dictionary (optional)
line_counts = dict(line_counts)

grouped_by_n_times = {}
for k, v in line_counts.items():
    if v not in grouped_by_n_times:
        grouped_by_n_times[v] = []
    grouped_by_n_times[v].append(k)

# Print report
print('Results: ')
print('Each number header represents the number of times a file appeared in multiple PRs')
highest_count = max(grouped_by_n_times.keys())
i = highest_count
while i > 0:
    v = grouped_by_n_times.get(i, [])
    if v:
        print(str(i) + ' -------------------')
        for filename in v:
            print(filename)
        print('')
    i -= 1

Was thinking about attaching inputs, but looks like gists don't allow attaching of input files, like .txt even, nor even .zip.