| LEFT | RIGHT |
|---|
| 1 #!/usr/bin/env python | 1 #!/usr/bin/env python |
| 2 # -*- coding: utf-8 -*- | 2 # -*- coding: utf-8 -*- |
| 3 # | 3 # |
| 4 # Copyright 2002-2007 Zuza Software Foundation | 4 # Copyright 2002-2007 Zuza Software Foundation |
| 5 # | 5 # |
| 6 # This file is part of translate. | 6 # This file is part of translate. |
| 7 # | 7 # |
| 8 # translate is free software; you can redistribute it and/or modify | 8 # translate is free software; you can redistribute it and/or modify |
| 9 # it under the terms of the GNU General Public License as published by | 9 # it under the terms of the GNU General Public License as published by |
| 10 # the Free Software Foundation; either version 2 of the License, or | 10 # the Free Software Foundation; either version 2 of the License, or |
| 11 # (at your option) any later version. | 11 # (at your option) any later version. |
| 12 # | 12 # |
| 13 # translate is distributed in the hope that it will be useful, | 13 # translate is distributed in the hope that it will be useful, |
| 14 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 16 # GNU General Public License for more details. | 16 # GNU General Public License for more details. |
| 17 # | 17 # |
| 18 # You should have received a copy of the GNU General Public License | 18 # You should have received a copy of the GNU General Public License |
| 19 # along with translate; if not, write to the Free Software | 19 # along with translate; if not, write to the Free Software |
| 20 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA | 20 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
| 21 | 21 |
| 22 """Classes that hold units of .po files (pounit) or entire files (pofile). | 22 """Classes that hold units of .po files (pounit) or entire files (pofile). |
| 23 | 23 |
| 24 Gettext-style .po (or .pot) files are used in translations for KDE, GNOME and | 24 Gettext-style .po (or .pot) files are used in translations for KDE, GNOME and |
| 25 many other projects. | 25 many other projects. |
| 26 | 26 |
| 27 This uses libgettextpo from the gettext package. Any version before 0.17 will | 27 This uses libgettextpo from the gettext package. Any version before 0.17 will |
| 28 at least cause some subtle bugs or may not work at all. Developers might want | 28 at least cause some subtle bugs or may not work at all. Developers might want |
| 29 to have a look at gettext-tools/libgettextpo/gettext-po.h from the gettext | 29 to have a look at gettext-tools/libgettextpo/gettext-po.h from the gettext |
| 30 package for the public API of the library. | 30 package for the public API of the library. |
| 31 """ | 31 """ |
| 32 | 32 |
| 33 from translate.misc.multistring import multistring | 33 from translate.misc.multistring import multistring |
| 34 from translate.storage import pocommon | 34 from translate.storage import pocommon |
| 35 from translate.misc import quote | 35 from translate.misc import quote |
| 36 from translate.lang import data | 36 from translate.lang import data |
| 37 from ctypes import * | 37 from ctypes import * |
| 38 import ctypes.util | 38 import ctypes.util |
| 39 try: | 39 try: |
| 40 import cStringIO as StringIO | 40 import cStringIO as StringIO |
| 41 except ImportError: | 41 except ImportError: |
| 42 import StringIO | 42 import StringIO |
| 43 import os | 43 import os |
| 44 import pypo | 44 import pypo |
| 45 import re | 45 import re |
| 46 import sys | 46 import sys |
| 47 import tempfile | 47 import tempfile |
| 48 | 48 |
| 49 lsep = " " | 49 lsep = " " |
| 50 """Seperator for #: entries""" | 50 """Seperator for #: entries""" |
| (...skipping 273 matching lines...) Show 10 above Show 10 below |
| 324 else: | 324 else: |
| 325 raise ValueError("Comment type not valid") | 325 raise ValueError("Comment type not valid") |
| 326 | 326 |
| 327 if comments and get_libgettextpo_version() < (0, 17, 0): | 327 if comments and get_libgettextpo_version() < (0, 17, 0): |
| 328 comments = "\n".join([line.strip() for line in comments.split("\n")]
) | 328 comments = "\n".join([line.strip() for line in comments.split("\n")]
) |
| 329 # Let's drop the last newline | 329 # Let's drop the last newline |
| 330 return comments[:-1].decode(self._encoding) | 330 return comments[:-1].decode(self._encoding) |
| 331 | 331 |
| 332 def addnote(self, text, origin=None, position="append"): | 332 def addnote(self, text, origin=None, position="append"): |
| 333 # ignore empty strings and strings without non-space characters | 333 # ignore empty strings and strings without non-space characters |
| 334 if (not text) or (not text.strip()): | 334 if (not text) or (not text.strip()): |
| 335 return | 335 return |
| 336 text = data.forceunicode(text) | 336 text = data.forceunicode(text) |
| 337 oldnotes = self.getnotes(origin) | 337 oldnotes = self.getnotes(origin) |
| 338 newnotes = None | 338 newnotes = None |
| 339 if oldnotes: | 339 if oldnotes: |
| 340 if position == "append": | 340 if position == "append": |
| 341 newnotes = oldnotes + "\n" + text | 341 newnotes = oldnotes + "\n" + text |
| 342 elif position == "merge": | 342 elif position == "merge": |
| 343 if oldnotes != text: | 343 if oldnotes != text: |
| 344 oldnoteslist = oldnotes.split("\n") | 344 oldnoteslist = oldnotes.split("\n") |
| 345 for newline in text.split("\n"): | 345 for newline in text.split("\n"): |
| 346 newline = newline.rstrip() | 346 newline = newline.rstrip() |
| 347 # avoid duplicate comment lines (this might cause some p
roblems) | 347 # avoid duplicate comment lines (this might cause some p
roblems) |
| 348 if newline not in oldnotes or len(newline) < 5: | 348 if newline not in oldnotes or len(newline) < 5: |
| 349 oldnoteslist.append(newline) | 349 oldnoteslist.append(newline) |
| 350 newnotes = "\n".join(oldnoteslist) | 350 newnotes = "\n".join(oldnoteslist) |
| 351 else: | 351 else: |
| 352 newnotes = text + '\n' + oldnotes | 352 newnotes = text + '\n' + oldnotes |
| 353 else: | 353 else: |
| 354 newnotes = "\n".join([line.rstrip() for line in text.split("\n")]) | 354 newnotes = "\n".join([line.rstrip() for line in text.split("\n")]) |
| 355 | 355 |
| 356 if newnotes: | 356 if newnotes: |
| 357 newlines = [] | 357 newlines = [] |
| 358 needs_space = get_libgettextpo_version() < (0, 17, 0) | 358 needs_space = get_libgettextpo_version() < (0, 17, 0) |
| 359 for line in newnotes.split("\n"): | 359 for line in newnotes.split("\n"): |
| 360 if line and needs_space: | 360 if line and needs_space: |
| 361 newlines.append(" " + line) | 361 newlines.append(" " + line) |
| 362 else: | 362 else: |
| 363 newlines.append(line) | 363 newlines.append(line) |
| 364 newnotes = "\n".join(newlines) | 364 newnotes = "\n".join(newlines) |
| 365 if origin in ["programmer", "developer", "source code"]: | 365 if origin in ["programmer", "developer", "source code"]: |
| 366 gpo.po_message_set_extracted_comments(self._gpo_message, newnote
s) | 366 gpo.po_message_set_extracted_comments(self._gpo_message, newnote
s) |
| 367 else: | 367 else: |
| 368 gpo.po_message_set_comments(self._gpo_message, newnotes) | 368 gpo.po_message_set_comments(self._gpo_message, newnotes) |
| 369 | 369 |
| 370 def removenotes(self): | 370 def removenotes(self): |
| 371 gpo.po_message_set_comments(self._gpo_message, "") | 371 gpo.po_message_set_comments(self._gpo_message, "") |
| 372 | 372 |
| 373 def copy(self): | 373 def copy(self): |
| 374 unit = self.buildfromunit(self) | 374 """Returns a copy of the this unit that can be used independently. |
| 375 #XXX: adding missing data | 375 """ |
| 376 unit = pounit() |
| 377 unit.source = self.source |
| 378 unit.target = self.target |
| 379 unit.markfuzzy(self.isfuzzy()) |
| 376 if self.isobsolete(): | 380 if self.isobsolete(): |
| 377 unit.makeobsolete() | 381 unit.makeobsolete() |
| 382 for location in self.getlocations(): |
| 383 unit.addlocation(location) |
| 384 notes = [] |
| 385 origins = ['translator', 'developer', 'programmer', 'source code'] |
| 386 for origin in origins: |
| 387 note = self.getnotes(origin=origin) |
| 388 if note in notes: |
| 389 continue |
| 390 if note: |
| 391 unit.addnote(note, origin=origin) |
| 392 notes.append(note) |
| 378 context = gpo.po_message_msgctxt(self._gpo_message) | 393 context = gpo.po_message_msgctxt(self._gpo_message) |
| 379 if context: | 394 if context: |
| 380 unit.setcontext(context) | 395 unit.setcontext(context) |
| 381 comments = self._extract_msgidcomments() | 396 comments = self._extract_msgidcomments() |
| 382 if comments: | 397 if comments: |
| 383 print 'HAS COMMENTS', comments | |
| 384 unit.setmsgidcomment(comments) | 398 unit.setmsgidcomment(comments) |
| 385 return unit | 399 return unit |
| 386 | 400 |
| 387 def merge(self, otherpo, overwrite=False, comments=True, authoritative=False
): | 401 def merge(self, otherpo, overwrite=False, comments=True, authoritative=False
): |
| 388 """Merges the otherpo (with the same msgid) into this one. | 402 """Merges the otherpo (with the same msgid) into this one. |
| 389 | 403 |
| 390 Overwrite non-blank self.msgstr only if overwrite is True | 404 Overwrite non-blank self.msgstr only if overwrite is True |
| 391 merge comments only if comments is True | 405 merge comments only if comments is True |
| 392 | 406 |
| 393 """ | 407 """ |
| 394 | 408 |
| 395 if not isinstance(otherpo, pounit): | 409 if not isinstance(otherpo, pounit): |
| 396 super(pounit, self).merge(otherpo, overwrite, comments) | 410 super(pounit, self).merge(otherpo, overwrite, comments) |
| 397 return | 411 return |
| 398 if comments: | 412 if comments: |
| 399 self.addnote(otherpo.getnotes("translator"), origin="translator", po
sition="merge") | 413 self.addnote(otherpo.getnotes("translator"), origin="translator", po
sition="merge") |
| 400 # FIXME mergelists(self.typecomments, otherpo.typecomments) | 414 # FIXME mergelists(self.typecomments, otherpo.typecomments) |
| 401 if not authoritative: | 415 if not authoritative: |
| 402 # We don't bring across otherpo.automaticcomments as we consider
ourself | 416 # We don't bring across otherpo.automaticcomments as we consider
ourself |
| 403 # to be the the authority. Same applies to otherpo.msgidcomment
s | 417 # to be the the authority. Same applies to otherpo.msgidcomment
s |
| 404 self.addnote(otherpo.getnotes("developer"), origin="developer",
position="merge") | 418 self.addnote(otherpo.getnotes("developer"), origin="developer",
position="merge") |
| 405 self.msgidcomment = otherpo._extract_msgidcomments() or None | 419 self.msgidcomment = otherpo._extract_msgidcomments() or None |
| 406 self.addlocations(otherpo.getlocations()) | 420 self.addlocations(otherpo.getlocations()) |
| 407 if not self.istranslated() or overwrite: | 421 if not self.istranslated() or overwrite: |
| 408 # Remove kde-style comments from the translation (if any). | 422 # Remove kde-style comments from the translation (if any). |
| 409 if self._extract_msgidcomments(otherpo.target): | 423 if self._extract_msgidcomments(otherpo.target): |
| 410 otherpo.target = otherpo.target.replace('_: ' + otherpo._extract
_msgidcomments()+ '\n', '') | 424 otherpo.target = otherpo.target.replace('_: ' + otherpo._extract
_msgidcomments()+ '\n', '') |
| 411 self.target = otherpo.target | 425 self.target = otherpo.target |
| 412 if self.source != otherpo.source: | 426 if self.source != otherpo.source: |
| 413 self.markfuzzy() | 427 self.markfuzzy() |
| 414 else: | 428 else: |
| 415 self.markfuzzy(otherpo.isfuzzy()) | 429 self.markfuzzy(otherpo.isfuzzy()) |
| 416 elif not otherpo.istranslated(): | 430 elif not otherpo.istranslated(): |
| 417 if self.source != otherpo.source: | 431 if self.source != otherpo.source: |
| 418 self.markfuzzy() | 432 self.markfuzzy() |
| 419 else: | 433 else: |
| 420 if self.target != otherpo.target: | 434 if self.target != otherpo.target: |
| 421 self.markfuzzy() | 435 self.markfuzzy() |
| 422 | 436 |
| 423 def isheader(self): | 437 def isheader(self): |
| 424 #return self.source == u"" and self.target != u"" | 438 #return self.source == u"" and self.target != u"" |
| 425 # we really want to make sure that there is no msgidcomment or msgctxt | 439 # we really want to make sure that there is no msgidcomment or msgctxt |
| 426 return self.getid() == "" and len(self.target) > 0 | 440 return self.getid() == "" and len(self.target) > 0 |
| 427 | 441 |
| 428 def isblank(self): | 442 def isblank(self): |
| 429 return len(self.source) == 0 and len(self.target) == 0 | 443 return len(self.source) == 0 and len(self.target) == 0 |
| 430 | 444 |
| 431 def hastypecomment(self, typecomment): | 445 def hastypecomment(self, typecomment): |
| 432 return gpo.po_message_is_format(self._gpo_message, typecomment) | 446 return gpo.po_message_is_format(self._gpo_message, typecomment) |
| 433 | 447 |
| (...skipping 199 matching lines...) Show 10 above Show 10 below |
| 633 # Skip the first unit if it is a header. | 647 # Skip the first unit if it is a header. |
| 634 if self.units[0].isheader(): | 648 if self.units[0].isheader(): |
| 635 units = self.units[1:] | 649 units = self.units[1:] |
| 636 else: | 650 else: |
| 637 units = self.units | 651 units = self.units |
| 638 | 652 |
| 639 for unit in units: | 653 for unit in units: |
| 640 if not unit.isblank() and not unit.isobsolete(): | 654 if not unit.isblank() and not unit.isobsolete(): |
| 641 return False | 655 return False |
| 642 return True | 656 return True |
| 643 | 657 |
| 644 def parse(self, input): | 658 def parse(self, input): |
| 645 if hasattr(input, 'name'): | 659 if hasattr(input, 'name'): |
| 646 self.filename = input.name | 660 self.filename = input.name |
| 647 elif not getattr(self, 'filename', ''): | 661 elif not getattr(self, 'filename', ''): |
| 648 self.filename = '' | 662 self.filename = '' |
| 649 | 663 |
| 650 if hasattr(input, "read"): | 664 if hasattr(input, "read"): |
| 651 posrc = input.read() | 665 posrc = input.read() |
| 652 input.close() | 666 input.close() |
| 653 input = posrc | 667 input = posrc |
| 654 | 668 |
| 655 needtmpfile = not os.path.isfile(input) | 669 needtmpfile = not os.path.isfile(input) |
| 656 if needtmpfile: | 670 if needtmpfile: |
| 657 # This is not a file - we write the string to a temporary file | 671 # This is not a file - we write the string to a temporary file |
| 658 fd, fname = tempfile.mkstemp(prefix='translate', suffix='.po') | 672 fd, fname = tempfile.mkstemp(prefix='translate', suffix='.po') |
| 659 os.write(fd, input) | 673 os.write(fd, input) |
| 660 input = fname | 674 input = fname |
| 661 os.close(fd) | 675 os.close(fd) |
| 662 | 676 |
| 663 self._gpo_memory_file = gpo.po_file_read_v3(input, xerror_handler) | 677 self._gpo_memory_file = gpo.po_file_read_v3(input, xerror_handler) |
| 664 if self._gpo_memory_file is None: | 678 if self._gpo_memory_file is None: |
| 665 print >> sys.stderr, "Error:" | 679 print >> sys.stderr, "Error:" |
| 666 | 680 |
| 667 if needtmpfile: | 681 if needtmpfile: |
| 668 os.remove(input) | 682 os.remove(input) |
| 669 | 683 |
| 670 # Handle xerrors here | 684 # Handle xerrors here |
| 671 self._header = gpo.po_file_domain_header(self._gpo_memory_file, None) | 685 self._header = gpo.po_file_domain_header(self._gpo_memory_file, None) |
| 672 if self._header: | 686 if self._header: |
| 673 charset = gpo.po_header_field(self._header, "Content-Type") | 687 charset = gpo.po_header_field(self._header, "Content-Type") |
| 674 if charset: | 688 if charset: |
| 675 charset = re.search("charset=([^\\s]+)", charset).group(1) | 689 charset = re.search("charset=([^\\s]+)", charset).group(1) |
| 676 self._encoding = encodingToUse(charset) | 690 self._encoding = encodingToUse(charset) |
| 677 self._gpo_message_iterator = gpo.po_message_iterator(self._gpo_memory_fi
le, None) | 691 self._gpo_message_iterator = gpo.po_message_iterator(self._gpo_memory_fi
le, None) |
| 678 newmessage = gpo.po_next_message(self._gpo_message_iterator) | 692 newmessage = gpo.po_next_message(self._gpo_message_iterator) |
| 679 while newmessage: | 693 while newmessage: |
| 680 newunit = pounit(gpo_message=newmessage) | 694 newunit = pounit(gpo_message=newmessage) |
| 681 self.units.append(newunit) | 695 self.units.append(newunit) |
| 682 newmessage = gpo.po_next_message(self._gpo_message_iterator) | 696 newmessage = gpo.po_next_message(self._gpo_message_iterator) |
| 683 #self._free_iterator() | |
| 684 | 697 |
| 685 def __del__(self): | 698 def __del__(self): |
| 686 #print 'DELL CALLED', id(self) | |
| 687 # We currently disable this while we still get segmentation faults. | 699 # We currently disable this while we still get segmentation faults. |
| 688 # Note that this is definitely leaking memory because of this. | 700 # Note that this is definitely leaking memory because of this. |
| 689 #return | |
| 690 self._free_iterator() | 701 self._free_iterator() |
| 691 if self._gpo_memory_file is not None: | 702 if self._gpo_memory_file is not None: |
| 692 gpo.po_file_free(self._gpo_memory_file) | 703 gpo.po_file_free(self._gpo_memory_file) |
| 693 self._gpo_memory_file = None | 704 self._gpo_memory_file = None |
| 694 | 705 |
| 695 def _free_iterator(self): | 706 def _free_iterator(self): |
| 696 #print 'ITERATOR CALLED', id(self) | |
| 697 # We currently disable this while we still get segmentation faults. | 707 # We currently disable this while we still get segmentation faults. |
| 698 # Note that this is definitely leaking memory because of this. | 708 # Note that this is definitely leaking memory because of this. |
| 699 #return | |
| 700 if self._gpo_message_iterator is not None: | 709 if self._gpo_message_iterator is not None: |
| 701 gpo.po_message_iterator_free(self._gpo_message_iterator) | 710 gpo.po_message_iterator_free(self._gpo_message_iterator) |
| 702 self._gpo_message_iterator = None | 711 self._gpo_message_iterator = None |
| LEFT | RIGHT |
|---|
