view i18n/posplit @ 37338:cbc4425e81b5

tests: conditionalize tests based on presence of revlogs for files

~85 tests don't like our non-revlog file store for various reasons.

This commit introduces hghave functionality for declaring and querying
repository features. By default, we assume repositories have
revlog-based file storage. But if the HGREPOFEATURES environment
variable is set, we can override the default set of repository
features. If you run the test harness with our simplestorerepo
extension and an environment variable set to the proper value, you
can override the hghave defaults to agree with simplestorerepo's
version of reality.

Various tests have been modified so behavior dependent on revlog-based
file storage is marked as such.

This fixes a handful of test failures with our custom file storage
extension. But dozens remain. The point of this commit is to demonstrate
how tests will need to be modified to account for custom storage
implementations.

TBH, I'm not convinced hghave is the proper layer for repository
feature detection. I /think/ we'll eventually want something in
run-tests.py itself. But that would require inventing a new primitive
in the test harness. This is all very alpha at the moment. So I think
hghave is an acceptable place to hang this feature detection. I think
the right time to be thinking about integrating this into run-tests.py
is *after* we have a stable alternate storage implementation in core.
For now, let's try to make progress towards the idea of an alternate
storage backend.

Differential Revision: https://phab.mercurial-scm.org/D3030

#!/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()