pathScripts/import-finder

145 lines
6.6 KiB
Text
Raw Normal View History

#!/usr/bin/env python3
import os
import re
import requests
import time
import pkg_resources
# 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 find_imports(root_dir):
imports_by_file = {}
for dirpath, _, filenames in os.walk(root_dir):
for filename in filenames:
if filename.endswith('.py'):
filepath = os.path.join(dirpath, filename)
with open(filepath, 'r') as file:
import_lines = []
for line in file:
line = line.strip()
if line.startswith(('import ', 'from ')) and not line.startswith('#'):
import_lines.append(line)
imports_by_file[filepath] = import_lines
return imports_by_file
def process_import_lines(import_lines):
processed_lines = set() # Use a set to remove duplicates
for line in import_lines:
# Handle 'import xyz' and 'import abc, def, geh'
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:
processed_lines.add(mod)
# Handle 'from abc import def, geh'
elif line.startswith('from '):
mod = line.split(' ')[1].split('.')[0].strip()
if mod and not mod.isupper() and mod not in EXCLUDED_NAMES:
processed_lines.add(mod)
return processed_lines
def check_pypi_availability(libraries):
available = set()
unavailable = set()
for lib in libraries:
if lib in BUILTIN_MODULES: # Skip built-in modules
continue
corrected_lib = KNOWN_CORRECTIONS.get(lib, lib)
try:
if check_library_on_pypi(corrected_lib):
available.add(corrected_lib)
else:
unavailable.add(corrected_lib)
except requests.exceptions.RequestException:
print(f"Warning: Unable to check {corrected_lib} on PyPI due to network error.")
unavailable.add(corrected_lib)
return available, unavailable
def check_library_on_pypi(library):
max_retries = 3
for attempt in range(max_retries):
try:
response = requests.get(f"https://pypi.org/pypi/{library}/json", timeout=5)
return response.status_code == 200
except requests.exceptions.RequestException:
if attempt < max_retries - 1:
time.sleep(1) # Wait for 1 second before retrying
else:
raise
def save_to_requirements_file(available, output_file='requirements.txt'):
existing_requirements = set()
if os.path.isfile(output_file):
with open(output_file, 'r') as file:
existing_requirements = set(line.strip() for line in file)
with open(output_file, 'a') as file:
for pkg in sorted(available - existing_requirements):
print(f"Adding to requirements.txt: {pkg}")
file.write(pkg + '\n')
def save_to_missing_file(unavailable, output_file='missing-packages.txt'):
existing_missing = set()
if os.path.isfile(output_file):
with open(output_file, 'r') as file:
existing_missing = set(line.strip() for line in file)
with open(output_file, 'a') as file:
for pkg in sorted(unavailable - existing_missing):
print(f"Adding to missing-packages.txt: {pkg}")
file.write(pkg + '\n')
if __name__ == "__main__":
root_dir = os.getcwd() # Get the current working directory
imports_by_file = find_imports(root_dir)
for filepath, import_lines in imports_by_file.items():
print(f"# Processing {filepath}")
processed_lines = process_import_lines(import_lines)
available, unavailable = check_pypi_availability(processed_lines)
save_to_requirements_file(available)
save_to_missing_file(unavailable)
print(f"Processed import statements have been saved to requirements.txt and missing-packages.txt")