Python script to gather all of the code in an `RMarkdown` file's code chunks and print it to stdout

getcode.py

import re
import argparse


START_PATT = re.compile(r'^```\{r([ \w]*).*\}$')
END_PATT = re.compile(r'^```$')

HEADER_PATT = re.compile(r'^(?P<level>#+) (?P<name>.+)$')


def get_chunk(file) -> str:
    def lines():
        for line in file:
            if re.match(END_PATT, line):
                return
            yield line

    return ''.join(lines())


def get_code(file) -> str:
    def chunks():
        for line in file:
            header_match = re.match(HEADER_PATT, line)
            if header_match:
                name = header_match.group('name')
                level = len(header_match.group('level'))
                side = '-'*(5*(5 - level))
                sep = '\n'*(4 if level <= 2 else 2)
                yield sep
                yield f'# {side} {name if level > 2 else name.upper()} {side}\n'

            chunk_match = re.match(START_PATT, line)
            if chunk_match:
                yield '\n'
                yield get_chunk(file)

    return ''.join(chunks())


def file_type(filename: str):
    return open(filename, 'r')


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('file', type=file_type)
    args = parser.parse_args()
    code = get_code(args.file)
    print(code)


if __name__ == '__main__':
    main()