kallithea Files · scripts/docs-headings.py

Files @ 3dbb625d5f9c

Branch filter:

Location: kallithea/scripts/docs-headings.py

3dbb625d5f9c 2.6 KiB text/x-python Show Annotation Show as Raw Download as Raw

mads

vcs: introduce 'branches' attribute on changesets, making it possible for Git to show multiple branches for a changeset

Mercurial changesets will always have have exactly one branch (which might be
"default"). The VCS data model was the same.

Git allows for a changeset to have 0 or more branches ... and possibly one of
them as active. The right data model is thus to have an enumerable of branches.

We thus add a 'branches' attribute and use it where applicable.

The existing 'branch' attribute used some heuristics to decide which branch use
as "the" branch ... and in some places code (and tests) rely on that. We thus
keep that old method, knowing that some of its uses probably should move to
'branches'.

The code for retrieving Git branches is based on work by Dominik Ruf.

#!/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 = 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', fn])
        print

if __name__ == '__main__':
    main()