import re
from pathlib import Path
from urllib.parse import urlparse

# Define paths
input_file = Path("orig-inp.txt")
current_dir = Path(".")

if not input_file.exists():
    print(f"Error: {input_file} not found.")
    exit(1)

# Regex to find a URL at the end of a line
# Looks for http:// or https:// followed by non-whitespace characters until the end of the line
url_regex = re.compile(r"(https?://\S+)$")

print(f"{'Filename / URL Source':<40} | {'Status':<15} | {'Size (KB)':<10}")
print("-" * 72)

with open(input_file, "r", encoding="utf-8") as f:
    for line in f:
        line = line.strip()

        # Ignore blank lines
        if not line:
            continue

        # Extract the URL from the end of the line
        match = url_regex.search(line)
        if not match:
            print(f"{line[:40]:<40} | No URL Found   | -")
            continue

        url = match.group(1)

        try:
            # Extract the final segment (filename) from the URL
            parsed_url = urlparse(url)
            filename = Path(parsed_url.path).name

            # Sanity Check 1: Does the filename make sense?
            if not filename or not Path(filename).suffix or filename.startswith("."):
                print(f"{filename or url[:40]:<40} | Invalid Name   | -")
                continue

            local_file = current_dir / filename

            # Sanity Check 2: Does it exist?
            if not local_file.is_file():
                print(f"{filename:<40} | Missing        | -")
                continue

            # Sanity Check 3: Is it over 1 KB?
            file_size_kb = local_file.stat().st_size / 1024
            if file_size_kb <= 1:
                print(
                    f"{filename:<40} | Too Small      | {file_size_kb:.2f} KB"
                )
                continue

            # Passed all checks
            print(f"{filename:<40} | OK             | {file_size_kb:.2f} KB")

        except Exception as e:
            print(f"{url[:40]:<40} | Error: {str(e)[:10]} | -")