view scripts/docs-headings.py @ 8588:210e76d69b62

mysql: bump charset to to 'utf8mb4' to get full UTF-8 support We used to use 'utf8', but in MySQL, this is just an alias for 'utf8mb3' which isn't full unicode. 'utf8mb4' has less surprises (especially if used with the 'utf8mb4_unicode_ci' collation). MySQL character sets for server, database, tables, and connection are set independently. Until now, we have specified 'utf8' when creating tables to overrule the database charset and in the default MySQL connection URL. For existing databases, it is recommended to change encoding (and collation) by altering the each of the tables inside it as described on https://stackoverflow.com/questions/6115612/how-to-convert-an-entire-mysql-database-characterset-and-collation-to-utf-8 .
author Mads Kiilerich <mads@kiilerich.com>
date Mon, 15 Jun 2020 16:57:20 +0200
parents 4b68fbe195b6
children 0a84ef075575
line wrap: on
line source

#!/usr/bin/env python3

"""
Consistent formatting of rst section titles
"""

import re
import subprocess


spaces = [
    (0, 1), # we assume this is a over-and-underlined header
    (2, 1),
    (1, 1),
    (1, 0),
    (1, 0),
    ]

# http://sphinx-doc.org/rest.html :
#   for the Python documentation, this convention is used which you may follow:
#   # with overline, for parts
#   * with overline, for chapters
#   =, for sections
#   -, for subsections
#   ^, for subsubsections
#   ", for paragraphs
pystyles = ['#', '*', '=', '-', '^', '"']

# match on a header line underlined with one of the valid characters
headermatch = re.compile(r'''\n*(.+)\n([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\2{2,}\n+''', flags=re.MULTILINE)


def main():
    filenames = subprocess.check_output(['hg', 'loc', 'set:**.rst+kallithea/i18n/how_to']).splitlines()
    for fn in filenames:
        fn = fn.decode()
        print('processing %s' % fn)
        s = open(fn).read()

        # find levels and their styles
        lastpos = 0
        styles = []
        for markup in headermatch.findall(s):
            style = markup[1]
            if style in styles:
                stylepos = styles.index(style)
                if stylepos > lastpos + 1:
                    print('bad style %r with level %s - was at %s' % (style, stylepos, lastpos))
            else:
                stylepos = len(styles)
                if stylepos > lastpos + 1:
                    print('bad new style %r - expected %r' % (style, styles[lastpos + 1]))
                else:
                    styles.append(style)
            lastpos = stylepos

        # remove superfluous spacing (may however be restored by header spacing)
        s = re.sub(r'''(\n\n)\n*''', r'\1', s, flags=re.MULTILINE)

        if styles:
            newstyles = pystyles[pystyles.index(styles[0]):]

            def subf(m):
                title, style = m.groups()
                level = styles.index(style)
                before, after = spaces[level]
                newstyle = newstyles[level]
                return '\n' * (before + 1) + title + '\n' + newstyle * len(title) + '\n' * (after + 1)
            s = headermatch.sub(subf, s)

        # remove superfluous spacing when headers are adjacent
        s = re.sub(r'''(\n.+\n([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\2{2,}\n\n\n)\n*''', r'\1', s, flags=re.MULTILINE)
        # fix trailing space and spacing before link sections
        s = s.strip() + '\n'
        s = re.sub(r'''\n+((?:\.\. _[^\n]*\n)+)$''', r'\n\n\n\1', s)

        open(fn, 'w').write(s)

    print(subprocess.check_output(['hg', 'diff'] + filenames))

if __name__ == '__main__':
    main()