Package translate :: Package storage :: Module qm
[hide private]
[frames] | no frames]

Source Code for Module translate.storage.qm

  1  #!/usr/bin/env python 
  2  # -*- coding: utf-8 -*- 
  3  # 
  4  # Copyright 2007 Zuza Software Foundation 
  5  # 
  6  # This file is part of translate. 
  7  # 
  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 
 10  # the Free Software Foundation; either version 2 of the License, or 
 11  # (at your option) any later version. 
 12  # 
 13  # translate is distributed in the hope that it will be useful, 
 14  # but WITHOUT ANY WARRANTY; without even the implied warranty of 
 15  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
 16  # GNU General Public License for more details. 
 17  # 
 18  # You should have received a copy of the GNU General Public License 
 19  # along with translate; if not, write to the Free Software 
 20  # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA 
 21  # 
 22   
 23  """Module for parsing Qt .qm files 
 24   
 25  @note: based on documentation from Gettext's .qm implementation (see write-qt.c) and on observation 
 26  of the output of lrelease. 
 27  @note: Certain deprecated section tags are not implemented.  These will break and print out 
 28  the missing tag.  They are easy to implement and should follow the structure in 03  
 29  (Translation).  We could find no examples that use these so we'd rather leave it  
 30  unimplemented until we actually have test data. 
 31  @note: Many .qm files are unable to be parsed as they do not have the source text.  We assume 
 32  that since they use a hash table to lookup the data there is actually no need for the  
 33  source text.  It seems however that in Qt4's lrelease all data is included in the resultant .qm 
 34  file. 
 35  @todo: We can only parse, not create, a .qm file.  The main issue is that we need to  
 36  implement the hashing algorithm (which seems to be identical to the Gettext hash algorithm).  Unlike 
 37  Gettext it seems that the hash is required, but that has not been validated. 
 38  @todo: The code can parse files correctly.  But it could be cleaned up to be more readable, especially  
 39  the part that breaks the file into sections. 
 40  """ 
 41   
 42  from translate.storage import base 
 43  from translate.misc.multistring import multistring 
 44  import codecs 
 45  import struct 
 46  import sys 
 47   
 48  QM_MAGIC_NUMBER = (0x3CB86418L, 0xCAEF9C95L, 0xCD211CBFL, 0x60A1BDDDL) 
 49   
50 -def qmunpack(qmfile='messages.mo'):
51 """Helper to unpack Qt .qm files into a Python string""" 52 f = open(qmfile) 53 s = f.read() 54 print "\\x%02x"*len(s) % tuple(map(ord, s)) 55 f.close()
56
57 -class qmunit(base.TranslationUnit):
58 """A class representing a .qm translation message."""
59 - def __init__(self, source=None):
60 super(qmunit, self).__init__(source)
61
62 -class qmfile(base.TranslationStore):
63 """A class representing a .qm file.""" 64 UnitClass = qmunit 65 Mimetypes = ["application/x-qm"] 66 Extensions = ["qm"]
67 - def __init__(self, inputfile=None, unitclass=qmunit):
68 self.UnitClass = unitclass 69 base.TranslationStore.__init__(self, unitclass=unitclass) 70 self.units = [] 71 self.filename = '' 72 if inputfile is not None: 73 self.parsestring(inputfile)
74
75 - def __str__(self):
76 """Output a string representation of the .qm data file""" 77 return ""
78
79 - def parse(self, input):
80 """parses the given file or file source string""" 81 if hasattr(input, 'name'): 82 self.filename = input.name 83 elif not getattr(self, 'filename', ''): 84 self.filename = '' 85 if hasattr(input, "read"): 86 qmsrc = input.read() 87 input.close() 88 input = qmsrc 89 if len(input) < 16: 90 raise ValueError("This is not a .qm file: file empty or to small") 91 magic = struct.unpack(">4L", input[:16]) 92 if magic != QM_MAGIC_NUMBER: 93 raise ValueError("This is not a .qm file: invalid magic number") 94 startsection = 16 95 sectionheader = 5 96 while startsection < len(input): 97 section_type, length = struct.unpack(">bL", input[startsection:startsection+sectionheader]) 98 if section_type == 0x42: 99 #print "Section: hash" 100 hashash = True 101 hash_start = startsection+sectionheader 102 hash_data = struct.unpack(">%db" % length, input[startsection+sectionheader:startsection+sectionheader+length]) 103 elif section_type == 0x69: 104 #print "Section: messages" 105 hasmessages = True 106 messages_start = startsection+sectionheader 107 messages_data = struct.unpack(">%db" % length, input[startsection+sectionheader:startsection+sectionheader+length]) 108 elif section_type == 0x2f: 109 #print "Section: contexts" 110 hascontexts = True 111 contexts_start = startsection+sectionheader 112 contexts_data = struct.unpack(">%db" % length, input[startsection+sectionheader:startsection+sectionheader+length]) 113 startsection = startsection+sectionheader+length 114 pos = messages_start 115 source = target = None 116 while pos < messages_start + len(messages_data): 117 subsection, = struct.unpack(">b", input[pos:pos+1]) 118 if subsection == 0x01: # End 119 #print "End" 120 pos = pos+1 121 if not source is None and not target is None: 122 newunit = self.addsourceunit(source) 123 newunit.target = target 124 source = target = None 125 else: 126 raise ValueError("Old .qm format with no source defined") 127 continue 128 #print pos, subsection 129 pos = pos+1 130 length, = struct.unpack(">l", input[pos:pos+4]) 131 if subsection == 0x03: # Translation 132 if length != -1: 133 raw, = struct.unpack(">%ds" % length, input[pos+4:pos+4+length]) 134 string, templen = codecs.utf_16_be_decode(raw) 135 if target: 136 target.strings.append(string) 137 else: 138 target = multistring(string) 139 pos = pos+4+length 140 else: 141 target = "" 142 pos = pos+4 143 #print "Translation: %s" % target.encode('utf-8') 144 elif subsection == 0x06: # SourceText 145 source = input[pos+4:pos+4+length].decode('iso-8859-1') 146 #print "SourceText: %s" % source 147 pos = pos+4+length 148 elif subsection == 0x07: # Context 149 context = input[pos+4:pos+4+length].decode('iso-8859-1') 150 #print "Context: %s" % context 151 pos = pos+4+length 152 elif subsection == 0x08: # Disambiguating-comment 153 comment = input[pos+4:pos+4+length] 154 #print "Disambiguating-comment: %s" % comment 155 pos = pos+4+length 156 elif subsection == 0x05: # hash 157 hash = input[pos:pos+4] 158 #print "Hash: %s" % hash 159 pos = pos+4 160 else: 161 if subsection == 0x02: # SourceText16 162 subsection_name = "SourceText16" 163 elif subsection == 0x04: # Context16 164 subsection_name = "Context16" 165 else: 166 subsection_name = "Unkown" 167 print >> sys.stderr, "Unimplemented: %s %s" % (subsection, subsection_name) 168 return
169