summaryrefslogtreecommitdiffstats
path: root/devscripts/prepare_manpage.py
blob: 9b12e71e5f9d4b65efc0243a95e7cf9acbcbc5d7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
#!/usr/bin/env python3

# Allow direct execution
import os
import sys

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))


import os.path
import re

from devscripts.utils import (
    compose_functions,
    get_filename_args,
    read_file,
    write_file,
)

ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
README_FILE = os.path.join(ROOT_DIR, 'README.md')

PREFIX = r'''%yt-dlp(1)

# NAME

yt\-dlp \- A youtube-dl fork with additional features and patches

# SYNOPSIS

**yt-dlp** \[OPTIONS\] URL [URL...]

# DESCRIPTION

'''


def filter_excluded_sections(readme):
    EXCLUDED_SECTION_BEGIN_STRING = re.escape('<!-- MANPAGE: BEGIN EXCLUDED SECTION -->')
    EXCLUDED_SECTION_END_STRING = re.escape('<!-- MANPAGE: END EXCLUDED SECTION -->')
    return re.sub(
        rf'(?s){EXCLUDED_SECTION_BEGIN_STRING}.+?{EXCLUDED_SECTION_END_STRING}\n',
        '', readme)


def move_sections(readme):
    MOVE_TAG_TEMPLATE = '<!-- MANPAGE: MOVE "%s" SECTION HERE -->'
    sections = re.findall(r'(?m)^%s$' % (
        re.escape(MOVE_TAG_TEMPLATE).replace(r'\%', '%') % '(.+)'), readme)

    for section_name in sections:
        move_tag = MOVE_TAG_TEMPLATE % section_name
        if readme.count(move_tag) > 1:
            raise Exception(f'There is more than one occurrence of "{move_tag}". This is unexpected')

        sections = re.findall(rf'(?sm)(^# {re.escape(section_name)}.+?)(?=^# )', readme)
        if len(sections) < 1:
            raise Exception(f'The section {section_name} does not exist')
        elif len(sections) > 1:
            raise Exception(f'There are multiple occurrences of section {section_name}, this is unhandled')

        readme = readme.replace(sections[0], '', 1).replace(move_tag, sections[0], 1)
    return readme


def filter_options(readme):
    section = re.search(r'(?sm)^# USAGE AND OPTIONS\n.+?(?=^# )', readme).group(0)
    options = '# OPTIONS\n'
    for line in section.split('\n')[1:]:
        mobj = re.fullmatch(r'''(?x)
                \s{4}(?P<opt>-(?:,\s|[^\s])+)
                (?:\s(?P<meta>(?:[^\s]|\s(?!\s))+))?
                (\s{2,}(?P<desc>.+))?
            ''', line)
        if not mobj:
            options += f'{line.lstrip()}\n'
            continue
        option, metavar, description = mobj.group('opt', 'meta', 'desc')

        # Pandoc's definition_lists. See http://pandoc.org/README.html
        option = f'{option} *{metavar}*' if metavar else option
        description = f'{description}\n' if description else ''
        options += f'\n{option}\n:   {description}'
        continue

    return readme.replace(section, options, 1)


TRANSFORM = compose_functions(filter_excluded_sections, move_sections, filter_options)


def main():
    write_file(get_filename_args(), PREFIX + TRANSFORM(read_file(README_FILE)))


if __name__ == '__main__':
    main()