Mercurial > hg
view i18n/posplit @ 36958:644a02f6b34f
util: prefer "bytesio" to "stringio"
The io.BytesIO and io.StringIO types enforce the type of
data being operated on. On Python 2, we use cStringIO.StringIO(),
which is lax about mixing types. On Python 3, we actually use
io.BytesIO. Ideally, we'd use io.BytesIO on Python 2. But I believe
its performance is poor compared to cString.StringIO().
Anyway, we canonically define our pycompat type as "stringio."
That name is misleading, especially on Python 3.
This commit renames the canonical symbols to "bytesio."
"stringio" is preserved as an alias for API compatibility. There
are a lot of callers in the repo and I hesitate to take away the
old name. I also don't feel like changing everything at this time.
But at least new callers can use a "proper" name.
Differential Revision: https://phab.mercurial-scm.org/D2868
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Wed, 14 Mar 2018 11:52:35 -0700 |
parents | 90d84e1e427a |
children | d0e8933d6dad |
line wrap: on
line source
#!/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()