Mercurial > hg
view i18n/posplit @ 47927:b81f52ca8075
dirstate-item: keep the full information in memory (for pure form)
This changeset is finally reaching the area where we have been headed this whole
time. Since all implementation details are contained inside de DirstateItem
logic, we can change the way it is implemented.
So we store the information that are passed to the object and use them to
dynamically compute the "legacy" value.
For now we only do this for the Pure implementation, as this is a good
demonstration for the logic is fully insulated.
The next step will be the update the C code too, to implement the various method
with the new attribute (instead of the legacy one) and then start seriously
thinking about the parameters we feed into DirstateItem.
Differential Revision: https://phab.mercurial-scm.org/D11364
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Fri, 27 Aug 2021 15:10:21 +0200 |
parents | c102b704edb5 |
children | 6000f5b25c9b |
line wrap: on
line source
#!/usr/bin/env python3 # # 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) # merge comments from entry for comment in entry.comment.split('\n'): if comment and comment not in e.comment: if not e.comment: e.comment = comment else: e.comment += '\n' + comment 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()