Skip to content

Instantly share code, notes, and snippets.

@joeflack4

joeflack4/.py

Created May 31, 2024 22:00
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save joeflack4/c784a3dbdaf6d79e18a7f9bda5d3aba8 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save joeflack4/c784a3dbdaf6d79e18a7f9bda5d3aba8 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. joeflack4 created this gist May 31, 2024.
    47 changes: 47 additions & 0 deletions .py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,47 @@
    """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