Files
@ 8993d401575b
Branch filter:
Location: kallithea/scripts/docs-headings.py - annotation
8993d401575b
2.6 KiB
text/x-python
files: fix raw download of repo files with names with unicode points above 256 in name
Raw download had apparently only been tested with non-ascii characters that
were latin1. That was apparently a (too) simple case that worked without
crashing.
Files with unicode code points above 256 in their name would fail to download,
when Waitress failed like this, trying to get a real byte string by encoding
WSGI headers to latin1:
UnicodeEncodeError: 'latin-1' codec can't encode characters in position 84-85: ordinal not in range(256)
HTTP headers are of course byte strings on the network, but Python3 WSGI does
unfortunately neither expose it as bytes nor as unicode strings to be encoded
as utf-8. Instead, it uses unicode strings with byte values encoded as code
points 0-255. That is achieved by decoding the utf-8 encoded bytes as latin1.
For raw downloads, the recommended download filename is provided in the
Content-Disposition header. The problem is that it was provided as a real
unicode string.
Fixed by applying the "proper" latin1-decoding of a utf8-encoding.
Raw download had apparently only been tested with non-ascii characters that
were latin1. That was apparently a (too) simple case that worked without
crashing.
Files with unicode code points above 256 in their name would fail to download,
when Waitress failed like this, trying to get a real byte string by encoding
WSGI headers to latin1:
UnicodeEncodeError: 'latin-1' codec can't encode characters in position 84-85: ordinal not in range(256)
HTTP headers are of course byte strings on the network, but Python3 WSGI does
unfortunately neither expose it as bytes nor as unicode strings to be encoded
as utf-8. Instead, it uses unicode strings with byte values encoded as code
points 0-255. That is achieved by decoding the utf-8 encoded bytes as latin1.
For raw downloads, the recommended download filename is provided in the
Content-Disposition header. The problem is that it was provided as a real
unicode string.
Fixed by applying the "proper" latin1-decoding of a utf8-encoding.
aa6f17a53b49 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 0a277465fddf f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 0a84ef075575 a188803df37e 01aca0a4f876 a8e6bb9ee9ea 665dfa112f2c f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 a8e6bb9ee9ea f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 a8e6bb9ee9ea f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 ed2fb6e84a02 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 665dfa112f2c a188803df37e a8e6bb9ee9ea f38b50f8a6a6 f38b50f8a6a6 f38b50f8a6a6 | #!/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([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\2{2,}\n+''', flags=re.MULTILINE)
def main():
filenames = subprocess.check_output(['hg', 'files', 'set:**.rst+kallithea/i18n/how_to']).splitlines()
for fn in filenames:
fn = fn.decode()
print('processing %s' % fn)
s = open(fn).read()
# find levels and their styles
lastpos = 0
styles = []
for markup in headermatch.findall(s):
style = markup[1]
if style in styles:
stylepos = styles.index(style)
if stylepos > lastpos + 1:
print('bad style %r with level %s - was at %s' % (style, stylepos, lastpos))
else:
stylepos = len(styles)
if stylepos > lastpos + 1:
print('bad new style %r - expected %r' % (style, styles[lastpos + 1]))
else:
styles.append(style)
lastpos = stylepos
# remove superfluous spacing (may however be restored by header spacing)
s = re.sub(r'''(\n\n)\n*''', r'\1', s, flags=re.MULTILINE)
if styles:
newstyles = pystyles[pystyles.index(styles[0]):]
def subf(m):
title, style = m.groups()
level = styles.index(style)
before, after = spaces[level]
newstyle = newstyles[level]
return '\n' * (before + 1) + title + '\n' + newstyle * len(title) + '\n' * (after + 1)
s = headermatch.sub(subf, s)
# remove superfluous spacing when headers are adjacent
s = re.sub(r'''(\n.+\n([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\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()
|