kallithea Files · scripts/docs-headings.py

Files @ 6353b5e87091

Branch filter:

Location: kallithea/scripts/docs-headings.py

6353b5e87091 2.6 KiB text/x-python Show Annotation Show as Raw Download as Raw

Mads Kiilerich

ini: specify utf8 for sample MySQL connection strings

By default, the MySQL stack will store unicode as UTF-8 encoded data in string
fields, thus without using any unicode capabilities in the database.

As described in
http://docs.sqlalchemy.org/en/latest/dialects/mysql.html#mysql-unicode , set
charset=utf8 to actually put unicode in the database.

Existing databases that already store utf8 in the database should keep using
the old url.

This will only support 16 bit code points, but utf8mb4 will double the key size
and make them too big for MySQL.

#!/usr/bin/env python2

"""
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():
    for fn in subprocess.check_output(['hg', 'loc', 'set:**.rst+kallithea/i18n/how_to']).splitlines():
        print 'processing %s:' % fn
        s = file(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)

        file(fn, 'w').write(s)
        print subprocess.check_output(['hg', 'diff', fn])
        print

if __name__ == '__main__':
    main()