Mercurial > hg
view i18n/posplit @ 47123:d8ac62374943
dirstate-tree: Make `DirstateMap` borrow from a bytes buffer
… that has the contents of the `.hg/dirstate` file.
This only applies to the tree-based flavor of `DirstateMap`.
For now only the entire `&[u8]` slice is stored, so this is not useful yet.
Adding a lifetime parameter to the `DirstateMap` struct (in hg-core) makes
Python bindings non-trivial because we keep that struct in a Python object
that has a dynamic lifetime tied to Python’s reference-counting and GC.
As long as we keep the `PyBytes` that owns the borrowed bytes buffer next to
the borrowing struct, the buffer will live long enough for the borrows to stay
valid. However this relationship cannot be expressed in safe Rust code in a
way that would statisfy they borrow-checker. We use `unsafe` code to erase
that lifetime parameter, and encapsulate it in a safe abstraction similar to
the owning-ref crate: https://docs.rs/owning_ref/
Differential Revision: https://phab.mercurial-scm.org/D10557
author | Simon Sapin <simon.sapin@octobus.net> |
---|---|
date | Fri, 30 Apr 2021 18:24:54 +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()