view i18n/posplit @ 29334:ecc9b788fd69

sslutil: per-host config option to define certificates

Recent work has introduced the [hostsecurity] config section for
defining per-host security settings. This patch builds on top
of this foundation and implements the ability to define a per-host
path to a file containing certificates used for verifying the server
certificate. It is logically a per-host web.cacerts setting.

This patch also introduces a warning when both per-host
certificates and fingerprints are defined. These are mutually
exclusive for host verification and I think the user should be
alerted when security settings are ambiguous because, well,
security is important.

Tests validating the new behavior have been added.

I decided against putting "ca" in the option name because a
non-CA certificate can be specified and used to validate the server
certificate (commonly this will be the exact public certificate
used by the server). It's worth noting that the underlying
Python API used is load_verify_locations(cafile=X) and it calls
into OpenSSL's SSL_CTX_load_verify_locations(). Even OpenSSL's
documentation seems to omit that the file can contain a non-CA
certificate if it matches the server's certificate exactly. I
thought a CA certificate was a special kind of x509 certificate.
Perhaps I'm wrong and any x509 certificate can be used as a
CA certificate [as far as OpenSSL is concerned]. In any case,
I thought it best to drop "ca" from the name because this reflects
reality.

#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

from __future__ import absolute_import, print_function

import polib
import re
import sys

def addentry(po, entry, cache):
    e = cache.get(entry.msgid)
    if e:
        e.occurrences.extend(entry.occurrences)
    else:
        po.append(entry)
        cache[entry.msgid] = entry

def mkentry(orig, delta, msgid, msgstr):
    entry = polib.POEntry()
    entry.merge(orig)
    entry.msgid = msgid or orig.msgid
    entry.msgstr = msgstr or orig.msgstr
    entry.occurrences = [(p, int(l) + delta) for (p, l) in orig.occurrences]
    return entry

if __name__ == "__main__":
    po = polib.pofile(sys.argv[1])

    cache = {}
    entries = po[:]
    po[:] = []
    findd = re.compile(r' *\.\. (\w+)::') # for finding directives
    for entry in entries:
        msgids = entry.msgid.split(u'\n\n')
        if entry.msgstr:
            msgstrs = entry.msgstr.split(u'\n\n')
        else:
            msgstrs = [u''] * len(msgids)

        if len(msgids) != len(msgstrs):
            # places the whole existing translation as a fuzzy
            # translation for each paragraph, to give the
            # translator a chance to recover part of the old
            # translation - erasing extra paragraphs is
            # probably better than retranslating all from start
            if 'fuzzy' not in entry.flags:
                entry.flags.append('fuzzy')
            msgstrs = [entry.msgstr] * len(msgids)

        delta = 0
        for msgid, msgstr in zip(msgids, msgstrs):
            if msgid and msgid != '::':
                newentry = mkentry(entry, delta, msgid, msgstr)
                mdirective = findd.match(msgid)
                if mdirective:
                    if not msgid[mdirective.end():].rstrip():
                        # only directive, nothing to translate here
                        delta += 2
                        continue
                    directive = mdirective.group(1)
                    if directive in ('container', 'include'):
                        if msgid.rstrip('\n').count('\n') == 0:
                            # only rst syntax, nothing to translate
                            delta += 2
                            continue
                        else:
                            # lines following directly, unexpected
                            print('Warning: text follows line with directive' \
                                  ' %s' % directive)
                    comment = 'do not translate: .. %s::' % directive
                    if not newentry.comment:
                        newentry.comment = comment
                    elif comment not in newentry.comment:
                        newentry.comment += '\n' + comment
                addentry(po, newentry, cache)
            delta += 2 + msgid.count('\n')
    po.save()