Files
@ 6f9970a36190
Branch filter:
Location: kallithea/scripts/docs-headings.py - annotation
6f9970a36190
2.6 KiB
text/x-python
auth_ldap: fix interpretation of LDAP attributes in Python 3
The python-ldap module returns the LDAP attribute names as strings, and the
attribute values as arrays of bytes, e.g. for email:
'mail': [b'john.doe@example.com'],
See https://www.python-ldap.org/en/latest/bytes_mode.html, particularly:
https://www.python-ldap.org/en/latest/bytes_mode.html#what-s-text-and-what-s-bytes
Due to a missing conversion from bytes to unicode for the attribute values
obtained from LDAP, storing the values in a unicode field in the database would
fail. It would apparently either store a repr of the bytes or store them in
some other way.
Upon user login, SQLAlchemy warned about this:
.../sqlalchemy/sql/sqltypes.py:269: SAWarning: Unicode type received non-unicode bind param value b'John'. (this warning may be suppressed after 10 occurrences)
.../sqlalchemy/sql/sqltypes.py:269: SAWarning: Unicode type received non-unicode bind param value b'Doe'. (this warning may be suppressed after 10 occurrences)
In PostgreSQL, this would result in 'weird' values for first name, last
name, and email fields, both in the database and the web UI, e.g.
firstname: \x4a6f686e
lastname: \x446f65
email: \x6a6f686e406578616d706c652e636f6d
These values represent the actual values in hexadecimal, e.g.
\x4a6f686e = 0x4a 0x6f 0x68 0x6e = J o h n
In SQLite, the problem initially shows differently, as an exception in
gravatar_url():
File "_base_root_html", line 207, in render_body
File "_index_html", line 78, in render_header_menu
File "_base_base_html", line 479, in render_menu
File ".../kallithea/lib/helpers.py", line 908, in gravatar_div
gravatar(email_address, cls=cls, size=size)))
File ".../kallithea/lib/helpers.py", line 923, in gravatar
src = gravatar_url(email_address, size * 2)
File ".../kallithea/lib/helpers.py", line 956, in gravatar_url
.replace('{email}', email_address) \
TypeError: replace() argument 2 must be str, not bytes
but nevertheless the root cause of the problem is the same.
Fix the problem by converting the LDAP attributes from bytes to strings.
The python-ldap module returns the LDAP attribute names as strings, and the
attribute values as arrays of bytes, e.g. for email:
'mail': [b'john.doe@example.com'],
See https://www.python-ldap.org/en/latest/bytes_mode.html, particularly:
https://www.python-ldap.org/en/latest/bytes_mode.html#what-s-text-and-what-s-bytes
Due to a missing conversion from bytes to unicode for the attribute values
obtained from LDAP, storing the values in a unicode field in the database would
fail. It would apparently either store a repr of the bytes or store them in
some other way.
Upon user login, SQLAlchemy warned about this:
.../sqlalchemy/sql/sqltypes.py:269: SAWarning: Unicode type received non-unicode bind param value b'John'. (this warning may be suppressed after 10 occurrences)
.../sqlalchemy/sql/sqltypes.py:269: SAWarning: Unicode type received non-unicode bind param value b'Doe'. (this warning may be suppressed after 10 occurrences)
In PostgreSQL, this would result in 'weird' values for first name, last
name, and email fields, both in the database and the web UI, e.g.
firstname: \x4a6f686e
lastname: \x446f65
email: \x6a6f686e406578616d706c652e636f6d
These values represent the actual values in hexadecimal, e.g.
\x4a6f686e = 0x4a 0x6f 0x68 0x6e = J o h n
In SQLite, the problem initially shows differently, as an exception in
gravatar_url():
File "_base_root_html", line 207, in render_body
File "_index_html", line 78, in render_header_menu
File "_base_base_html", line 479, in render_menu
File ".../kallithea/lib/helpers.py", line 908, in gravatar_div
gravatar(email_address, cls=cls, size=size)))
File ".../kallithea/lib/helpers.py", line 923, in gravatar
src = gravatar_url(email_address, size * 2)
File ".../kallithea/lib/helpers.py", line 956, in gravatar_url
.replace('{email}', email_address) \
TypeError: replace() argument 2 must be str, not bytes
but nevertheless the root cause of the problem is the same.
Fix the problem by converting the LDAP attributes from bytes to strings.
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 a188803df37e 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([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\2{2,}\n+''', flags=re.MULTILINE)
def main():
filenames = subprocess.check_output(['hg', 'loc', 'set:**.rst+kallithea/i18n/how_to']).splitlines()
for fn in filenames:
fn = fn.decode()
print('processing %s' % fn)
s = open(fn).read()
# find levels and their styles
lastpos = 0
styles = []
for markup in headermatch.findall(s):
style = markup[1]
if style in styles:
stylepos = styles.index(style)
if stylepos > lastpos + 1:
print('bad style %r with level %s - was at %s' % (style, stylepos, lastpos))
else:
stylepos = len(styles)
if stylepos > lastpos + 1:
print('bad new style %r - expected %r' % (style, styles[lastpos + 1]))
else:
styles.append(style)
lastpos = stylepos
# remove superfluous spacing (may however be restored by header spacing)
s = re.sub(r'''(\n\n)\n*''', r'\1', s, flags=re.MULTILINE)
if styles:
newstyles = pystyles[pystyles.index(styles[0]):]
def subf(m):
title, style = m.groups()
level = styles.index(style)
before, after = spaces[level]
newstyle = newstyles[level]
return '\n' * (before + 1) + title + '\n' + newstyle * len(title) + '\n' * (after + 1)
s = headermatch.sub(subf, s)
# remove superfluous spacing when headers are adjacent
s = re.sub(r'''(\n.+\n([][!"#$%&'()*+,./:;<=>?@\\^_`{|}~-])\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()
|