python-count-word-freq

Answer

The function reads a text file, extracts words using regex (sequences of [a-zA-Z']+), strips leading/trailing apostrophes, lowercases, counts with collections.Counter, and returns results sorted by frequency (descending) then alphabetically.

word_freq.py:

#!/usr/bin/env python3
"""Count word frequency in a text file using collections.Counter."""

import sys
from collections import Counter
import re


def count_word_frequency(file_path: str, encoding: str = "utf-8") -> list[tuple[str, int]]:
    """
    Read a text file, count word frequencies using collections.Counter,
    and return results sorted by frequency (descending), then alphabetically.
    """
    try:
        with open(file_path, "r", encoding=encoding) as f:
            text = f.read()
    except FileNotFoundError:
        print(f"Error: File '{file_path}' not found.", file=sys.stderr)
        sys.exit(1)
    except IOError as e:
        print(f"Error reading file '{file_path}': {e}", file=sys.stderr)
        sys.exit(1)

    # Extract words using regex, strip surrounding apostrophes, lowercase
    words = re.findall(r"[a-zA-Z']+", text)
    words = [w.strip("'").lower() for w in words if w.strip("'")]

    counter = Counter(words)
    # Sort by frequency descending, then alphabetically ascending
    sorted_words = sorted(counter.items(), key=lambda x: (-x[1], x[0]))
    return sorted_words


def main() -> None:
    if len(sys.argv) != 2:
        print(f"Usage: {sys.argv[0]} <file>", file=sys.stderr)
        sys.exit(1)

    result = count_word_frequency(sys.argv[1])
    for word, freq in result:
        print(f"{word}: {freq}")


if __name__ == "__main__":
    main()

Usage:

python3 word_freq.py <file>