kallithea Files · scripts/docs-headings.py

Files @ e54ddaa52fee

Branch filter:

Location: kallithea/scripts/docs-headings.py

e54ddaa52fee 2.6 KiB text/x-python Show Annotation Show as Raw Download as Raw

Andrew Shadura

hooks: parse incoming git refs correctly

Hooks receive a line of the following format on standard input:

<old-value> SP <new-value> SP <ref-name> LF

where <old-value> is the old object name stored in the ref,
<new-value> is the new object name to be stored in the ref
and <ref-name> is the full name of the ref.

This means, we have to strip at least the LF in order to have a
correct version of the ref name after the split. Also, when
parsing the ref name itself, use all components but first instead
of just second, as a ref name may have slashes in it.

Previously, failure to parse ref name correctly would lead to the
following behaviour. A newly created repository with no commits pushed
has HEAD set to refs/heads/master by default, even though there's no
such ref in the repository yet. Upon first push, Kallithea rewrites
this symbolic reference with a reference to a real branch.

However, due to a bug in ref name parsing, if a ref name had a slash,
Kallithea would update HEAD to an invalid reference:

git push origin feature/branch

would rewrite HEAD to refs/heads/feature. All future attempts to work
with this repository would fail because dulwich would complain it can't
read HEAD as it is a directory.

#!/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()