format.py

#!/usr/bin/env python

import glob
import re

from itertools import islice, zip_longest


OUTPUT_FILE = 'exam/report.md'
INPUT_FILE = 'exam/report-base.md'
EXAM_DIR = 'exam/writeup/'
FULL_DIR = 'exam/writeup/'

IMG_PATTERN = re.compile(r'!\[(.+?)\]\((.+?)\s=.+?\)')

WRAPAT = 92


def in_ignore_list(s, hs):
    for i in hs:
        if i in s:
            return True
    return False


def batched(iterable, n):
    "Batch data into lists of length n. The last batch may be shorter."
    # batched('ABCDEFG', 3) --> ABC DEF G
    it = iter(iterable)
    while True:
        batch = list(islice(it, n))
        if not batch:
            return
        yield batch


def format_it(input_filename, output_filename, exam_dir, full_dir):
    # Get original data
    data = open(input_filename, 'rb').read()

    # Get the sections.
    md_parts = []
    md_data = b'\n'
    for i in md_parts:
        md_data += open('{}/{}.md'.format(exam_dir, i), 'rb').read()
        md_data += b'\n\n'
    lab_md = IMG_PATTERN.sub('![\g<1>]({}\g<2>)'.format(full_dir),
                             md_data.decode('utf-8')).encode('utf-8')

    # Transform the data.
    data = data.replace(b'{{REPORT_REPLACE}}', lab_md)

    # Replace unicode.
    data = data.replace('│'.encode(), b'|')
    data = re.sub(r"[^\x00-\x7F]+", "-", data.decode()).encode()

    # Automatically add newlines to overly long lines in code blocks.
    lines = data.split(b'\n')
    processed_lines = []
    in_code_block = False
    for line in lines:
        if line.startswith(b'```'):
            # Never allow naked code blocks. Always default to console.
            if not in_code_block and line == b'```':
                line = b'```console'
            in_code_block = not in_code_block
        if in_code_block and len(line) > WRAPAT:
            # First line
            processed_lines.append(line[:WRAPAT])
            # Rest of the lines are indented.
            indented_lines = batched(line[WRAPAT:], WRAPAT-2)
            for i in indented_lines:
                processed_lines.append(b'  ' + bytes(i))
        else:
            processed_lines.append(line)
    data = b'\n'.join(processed_lines)

    # Output the modified data
    with open(output_filename, 'wb') as outfile:
        outfile.write(data)


def main():
    '''Main function'''
    format_it(INPUT_FILE, OUTPUT_FILE, EXAM_DIR, FULL_DIR)


if __name__ == '__main__':
    main()