Extract and print directives from files in a software project

extract_directives.py

# -*- coding: utf-8 -*-
""" Purpose: Extract and print directives from a software project.

Created: 2017-09-24
Contact: [email protected]

Usage::
    python extract_directives.py
    python extract_directives.py -d=/path/to/ -i=FIXME -e=js
    
Notes:

* The `extract_directives` function is taken directly from:
  https://github.com/follnoob/extract-todo

LICENSE:
extract_directives.py is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

extract_directives.py is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with extract_directives.py.  If not, see <http://www.gnu.org/licenses/>.
"""

__author__ = "Derek Hohls"
__version__ = "0.0.1"

import os
import codecs
import argparse

# GLOBALS
_FILES = {
    # Dict with supported files and their comment chars
    ".tex": '%',
    ".py": '#',
    ".h": "//",
    ".c": "//",
    ".hpp": "//",
    ".cpp": "//",
    ".js": "//"
}
_EXCLUSIONS = [
    # List of directories to ignore
    'tests', 'migrations'
]


def extract_directives(fname, directive='TODO'):
    """Method for directive extraction.
    Parameters
    ----------
    fname : str
        Path to file.
    Returns
    -------
    list of str
        List with directives.
    """
    global _FILES
    ext = os.path.splitext(fname)
    comm_char = _FILES[ext[1]]
    todos = []
    with codecs.open(fname, "r", "utf-8") as f:
        lineCount = 0
        for line in f:
            lineCount += 1
            if comm_char not in line:
                continue
            try:
                line = line.split(comm_char, 1)[1].strip()
            except IndexError:
                pass
            if line.startswith(directive):
                todo = line.split(directive, 1)[1].strip()
                todos.append("%s:%d\n\t%s" %
                             (os.path.basename(fname), lineCount, todo))
    return todos
        

def main(args):
    directory = args.directory or "."
    directive = args.directive or "TODO"
    extension = args.extension or "py"
    header = 'All %s in "%s" files under %s' % (directive, extension, directory)
    print('='*len(header))
    print(header)
    print('='*len(header))
    for root, dirs, files in os.walk(directory):
        path = root.split(os.sep)
        exclude = False
        for exc in _EXCLUSIONS:
            if exc in path:
                exclude = True
        if not exclude:
            for the_file in files:
                full_file = os.path.join(root, the_file)
                if the_file.endswith('.%s' % extension):
                     items = extract_directives(
                        fname=full_file, directive=directive)
                     if items:
                         print('\n%s' % full_file)
                         print('-'*len(full_file))
                         for item in items:
                            print(item)


if __name__ == '__main__':
    PARSER = argparse.ArgumentParser()
    PARSER.add_argument(
        '-d', '--directory',
        help="Specify directory (default: current)")
    PARSER.add_argument(
        '-i', '--directive',
        help="Specify the directive (default: TODO)")
    PARSER.add_argument(
        '-e', '--extension',
        help="Specify the extension (default: py)")
    PARSER.add_argument(
        '-ll', '--loglevel', default='WARNING',
        choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'],
        help="Set log level for service (default: WARNING)")
    ARGS = PARSER.parse_args()
    LOG_LEVEL = ARGS.loglevel
    main(ARGS)