Files @ 9d3ac5963e4e
Branch filter:

Location: kallithea/scripts/docs-headings.py - annotation

Thomas De Schampheleire
diff: fix two-way diff for added or removed files

Viewing the two-way diff of an added file gives following exception:

File "_base_root_html", line 211, in render_body

File "_base_base_html", line 42, in render_body

File "files_diff_2way_html", line 197, in render_main

File ".../kallithea/lib/vcs/nodes.py", line 411, in is_binary
return b'\0' in self.content
TypeError: 'in <string>' requires string as left operand, not bytes

At this point, self.content was '' (empty string).

Commit 9203621cae03a03bbf8cfb4b667daa656780a93e made that node content is
always bytes, but this also had to be reflected in EmptyChangeset.

Add a basic test that catches this behavior.
#!/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()