kip

#!/usr/bin/env python3

import os
import sys
import re
import subprocess
import requests
import time
from typing import Set, Tuple, List, Dict

# List of Python built-in modules
BUILTIN_MODULES = {
    'abc', 'aifc', 'argparse', 'array', 'ast', 'asynchat', 'asyncio', 'asyncore', 'atexit',
    'audioop', 'base64', 'bdb', 'binascii', 'binhex', 'bisect', 'builtins', 'bz2', 'calendar',
    'cgi', 'cgitb', 'chunk', 'cmath', 'cmd', 'code', 'codecs', 'codeop', 'collections', 'colorsys',
    'compileall', 'concurrent', 'configparser', 'contextlib', 'copy', 'copyreg', 'crypt', 'csv',
    'ctypes', 'curses', 'dataclasses', 'datetime', 'dbm', 'decimal', 'difflib', 'dis', 'distutils',
    'doctest', 'dummy_threading', 'email', 'encodings', 'ensurepip', 'enum', 'errno', 'faulthandler',
    'fcntl', 'filecmp', 'fileinput', 'fnmatch', 'formatter', 'fractions', 'ftplib', 'functools',
    'gc', 'getopt', 'getpass', 'gettext', 'glob', 'gzip', 'hashlib', 'heapq', 'hmac', 'html', 'http',
    'imaplib', 'imghdr', 'imp', 'importlib', 'inspect', 'io', 'ipaddress', 'itertools', 'json',
    'keyword', 'lib2to3', 'linecache', 'locale', 'logging', 'lzma', 'mailbox', 'mailcap', 'marshal',
    'math', 'mimetypes', 'modulefinder', 'multiprocessing', 'netrc', 'nntplib', 'numbers', 'operator',
    'optparse', 'os', 'ossaudiodev', 'parser', 'pathlib', 'pdb', 'pickle', 'pickletools', 'pipes',
    'pkgutil', 'platform', 'plistlib', 'poplib', 'posix', 'pprint', 'profile', 'pstats', 'pty',
    'pwd', 'py_compile', 'pyclbr', 'pydoc', 'queue', 'quopri', 'random', 're', 'readline',
    'reprlib', 'resource', 'rlcompleter', 'runpy', 'sched', 'secrets', 'select', 'selectors', 'shelve',
    'shlex', 'shutil', 'signal', 'site', 'smtpd', 'smtplib', 'sndhdr', 'socket', 'socketserver',
    'spwd', 'sqlite3', 'ssl', 'stat', 'statistics', 'string', 'stringprep', 'struct', 'subprocess',
    'sunau', 'symtable', 'sys', 'sysconfig', 'syslog', 'tabnanny', 'tarfile', 'telnetlib', 'tempfile',
    'termios', 'test', 'textwrap', 'threading', 'time', 'timeit', 'token', 'tokenize', 'trace',
    'traceback', 'tracemalloc', 'tty', 'turtle', 'types', 'typing', 'unicodedata', 'unittest',
    'urllib', 'uu', 'uuid', 'venv', 'warnings', 'wave', 'weakref', 'webbrowser', 'xdrlib', 'xml',
    'xmlrpc', 'zipapp', 'zipfile', 'zipimport', 'zlib'
}

# Known corrections for PyPI package names
KNOWN_CORRECTIONS = {
    'dateutil': 'python-dateutil',
    'dotenv': 'python-dotenv',
    'docx': 'python-docx',
    'tesseract': 'pytesseract',
    'magic': 'python-magic',
    'multipart': 'python-multipart',
    'newspaper': 'newspaper3k',
    'srtm': 'elevation',
    'yaml': 'pyyaml',
    'zoneinfo': 'backports.zoneinfo'
}

# List of generic names to exclude
EXCLUDED_NAMES = {'models', 'data', 'convert', 'example', 'tests'}

def run_command(command: List[str]) -> Tuple[int, str, str]:
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    stdout, stderr = process.communicate()
    return process.returncode, stdout.decode(), stderr.decode()

def is_package_installed(package: str) -> bool:
    returncode, stdout, _ = run_command(["mamba", "list"])
    if returncode == 0:
        if re.search(f"^{package}\\s", stdout, re.MULTILINE):
            return True
    returncode, stdout, _ = run_command(["pip", "list"])
    return re.search(f"^{package}\\s", stdout, re.MULTILINE) is not None

def install_package(package: str):
    if is_package_installed(package):
        print(f"Package '{package}' is already installed.")
        return

    print(f"Installing package '{package}'.")
    returncode, _, _ = run_command(["mamba", "install", "-y", "-c", "conda-forge", package])
    if returncode != 0:
        returncode, _, _ = run_command(["pip", "install", package])
    
    if returncode != 0:
        print(f"Failed to install package '{package}'.")
    else:
        print(f"Successfully installed package '{package}'.")

def process_python_file(file_path: str) -> Set[str]:
    with open(file_path, 'r') as file:
        content = file.read()

    imports = set()
    for line in content.split('\n'):
        line = line.strip()
        if line.startswith(('import ', 'from ')) and not line.startswith('#'):
            if line.startswith('import '):
                modules = line.replace('import ', '').split(',')
                for mod in modules:
                    mod = re.sub(r'\s+as\s+\w+', '', mod).split('.')[0].strip()
                    if mod and not mod.isupper() and mod not in EXCLUDED_NAMES and mod not in BUILTIN_MODULES:
                        imports.add(KNOWN_CORRECTIONS.get(mod, mod))
            elif line.startswith('from '):
                mod = line.split(' ')[1].split('.')[0].strip()
                if mod and not mod.isupper() and mod not in EXCLUDED_NAMES and mod not in BUILTIN_MODULES:
                    imports.add(KNOWN_CORRECTIONS.get(mod, mod))

    return imports

def process_requirements_file(file_path: str) -> Set[str]:
    with open(file_path, 'r') as file:
        return {line.strip() for line in file if line.strip() and not line.startswith('#')}

def main():
    if len(sys.argv) < 2:
        print("Usage: kip <package1> [<package2> ...] or kip <script.py> or kip -r <requirements.txt>")
        sys.exit(1)

    packages_to_install = set()

    i = 1
    while i < len(sys.argv):
        arg = sys.argv[i]
        if arg == '-r':
            if i + 1 < len(sys.argv):
                requirements_file = sys.argv[i + 1]
                if os.path.isfile(requirements_file):
                    packages_to_install.update(process_requirements_file(requirements_file))
                else:
                    print(f"Requirements file {requirements_file} not found.")
                    sys.exit(1)
                i += 2
            else:
                print("Error: -r flag requires a file path.")
                sys.exit(1)
        elif arg.endswith('.py'):
            if os.path.isfile(arg):
                packages_to_install.update(process_python_file(arg))
            else:
                print(f"File {arg} not found.")
                sys.exit(1)
            i += 1
        else:
            packages_to_install.add(arg)
            i += 1

    for package in packages_to_install:
        install_package(package)

if __name__ == "__main__":
    main()