devscripts/prepare_manpage.py

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