devscripts/prepare_manpage.py

   1 #!/usr/bin/env python3
   2 from __future__ import unicode_literals
   3
   4 import io
   5 import optparse
   6 import os.path
   7 import re
   8
   9 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
  10 README_FILE = os.path.join(ROOT_DIR, 'README.md')
  11
  12 PREFIX = r'''%yt-dlp(1)
  13
  14 # NAME
  15
  16 yt\-dlp \- A youtube-dl fork with additional features and patches
  17
  18 # SYNOPSIS
  19
  20 **yt-dlp** \[OPTIONS\] URL [URL...]
  21
  22 # DESCRIPTION
  23
  24 '''
  25
  26
  27 def main():
  28     parser = optparse.OptionParser(usage='%prog OUTFILE.md')
  29     options, args = parser.parse_args()
  30     if len(args) != 1:
  31         parser.error('Expected an output filename')
  32
  33     outfile, = args
  34
  35     with io.open(README_FILE, encoding='utf-8') as f:
  36         readme = f.read()
  37
  38     readme = filter_excluded_sections(readme)
  39     readme = move_sections(readme)
  40     readme = filter_options(readme)
  41
  42     with io.open(outfile, 'w', encoding='utf-8') as outf:
  43         outf.write(PREFIX + readme)
  44
  45
  46 def filter_excluded_sections(readme):
  47     EXCLUDED_SECTION_BEGIN_STRING = re.escape('<!-- MANPAGE: BEGIN EXCLUDED SECTION -->')
  48     EXCLUDED_SECTION_END_STRING = re.escape('<!-- MANPAGE: END EXCLUDED SECTION -->')
  49     return re.sub(
  50         rf'(?s){EXCLUDED_SECTION_BEGIN_STRING}.+?{EXCLUDED_SECTION_END_STRING}\n',
  51         '', readme)
  52
  53
  54 def move_sections(readme):
  55     MOVE_TAG_TEMPLATE = '<!-- MANPAGE: MOVE "%s" SECTION HERE -->'
  56     sections = re.findall(rf'(?m)^{re.escape(MOVE_TAG_TEMPLATE) % "(.+)"}$', readme)
  57
  58     for section_name in sections:
  59         move_tag = MOVE_TAG_TEMPLATE % section_name
  60         if readme.count(move_tag) > 1:
  61             raise Exception(f'There is more than one occurrence of "{move_tag}". This is unexpected')
  62
  63         sections = re.findall(rf'(?sm)(^# {re.escape(section_name)}.+?)(?=^# )', readme)
  64         if len(sections) < 1:
  65             raise Exception(f'The section {section_name} does not exist')
  66         elif len(sections) > 1:
  67             raise Exception(f'There are multiple occurrences of section {section_name}, this is unhandled')
  68
  69         readme = readme.replace(sections[0], '', 1).replace(move_tag, sections[0], 1)
  70     return readme
  71
  72
  73 def filter_options(readme):
  74     section = re.search(r'(?sm)^# USAGE AND OPTIONS\n.+?(?=^# )', readme).group(0)
  75     options = '# OPTIONS\n'
  76     for line in section.split('\n')[1:]:
  77         if line.lstrip().startswith('-'):
  78             split = re.split(r'\s{2,}', line.lstrip())
  79             # Description string may start with `-` as well. If there is
  80             # only one piece then it's a description bit not an option.
  81             if len(split) > 1:
  82                 option, description = split
  83                 split_option = option.split(' ')
  84
  85                 if not split_option[-1].startswith('-'):  # metavar
  86                     option = ' '.join(split_option[:-1] + [f'*{split_option[-1]}*'])
  87
  88                 # Pandoc's definition_lists. See http://pandoc.org/README.html
  89                 options += f'\n{option}\n:   {description}\n'
  90                 continue
  91         options += line.lstrip() + '\n'
  92
  93     return readme.replace(section, options, 1)
  94
  95
  96 if __name__ == '__main__':
  97     main()