summaryrefslogtreecommitdiff
path: root/l10ntools/source/lngmerge.cxx
blob: 7af3293775f70a5596d94d1803cd06fccc9ac0a3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*************************************************************************
 *
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * Copyright 2000, 2010 Oracle and/or its affiliates.
 *
 * OpenOffice.org - a multi-platform office productivity suite
 *
 * This file is part of OpenOffice.org.
 *
 * OpenOffice.org is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License version 3
 * only, as published by the Free Software Foundation.
 *
 * OpenOffice.org is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License version 3 for more details
 * (a copy is included in the LICENSE file that accompanied this code).
 *
 * You should have received a copy of the GNU Lesser General Public License
 * version 3 along with OpenOffice.org.  If not, see
 * <http://www.openoffice.org/license.html>
 * for a copy of the LGPLv3 License.
 *
 ************************************************************************/

// MARKER(update_precomp.py): autogen include statement, do not remove
#include "precompiled_l10ntools.hxx"
#include <tools/fsys.hxx>

// local includes
#include "lngmerge.hxx"
#include <iostream>
using namespace std;
//
// class LngParser
//
/*****************************************************************************/
LngParser::LngParser( const ByteString &rLngFile, sal_Bool bUTF8, sal_Bool bULFFormat )
/*****************************************************************************/
                :
                nError( LNG_OK ),
                pLines( NULL ),
                sSource( rLngFile ),
                bDBIsUTF8( bUTF8 ),
                bULF( bULFFormat )
{
    pLines = new LngLineList();
    DirEntry aEntry( String( sSource, RTL_TEXTENCODING_ASCII_US ));
    if ( aEntry.Exists()) {
        SvFileStream aStream( String( sSource, RTL_TEXTENCODING_ASCII_US ), STREAM_STD_READ );
        if ( aStream.IsOpen()) {
            ByteString sLine;
            bool bFirstLine = true;
            while ( !aStream.IsEof()) {
                aStream.ReadLine( sLine );

                if( bFirstLine ){       // Always remove UTF8 BOM from the first line
                    Export::RemoveUTF8ByteOrderMarker( sLine );
                    bFirstLine = false;
                }

                pLines->push_back( new ByteString( sLine ) );
            }
        }
        else
            nError = LNG_COULD_NOT_OPEN;
    }
    else
        nError = LNG_FILE_NOTFOUND;
}

/*****************************************************************************/
LngParser::~LngParser()
/*****************************************************************************/
{
    for ( size_t i = 0, n = pLines->size(); i < n; i++ )
        delete (*pLines)[ i ];
    pLines->clear();
    delete pLines;
}

/*****************************************************************************/
void LngParser::FillInFallbacks( ByteStringHashMap Text )
/*****************************************************************************/
{
    ByteString sCur;
    for( unsigned int n = 0; n < aLanguages.size(); n++ ){
        sCur = aLanguages[ n ];

        if( Export::isAllowed( sCur ) ){
            ByteString sFallbackLang = Export::GetFallbackLanguage( sCur );
            if( sFallbackLang.Len() ){
                Text[ sCur ] = Text[ sFallbackLang ];
            }
        }
    }
}

/*****************************************************************************/
sal_Bool LngParser::CreateSDF(
    const ByteString &rSDFFile, const ByteString &rPrj,
    const ByteString &rRoot )
/*****************************************************************************/
{

    Export::InitLanguages( false );
    aLanguages = Export::GetLanguages();
    SvFileStream aSDFStream( String( rSDFFile, RTL_TEXTENCODING_ASCII_US ),
        STREAM_STD_WRITE | STREAM_TRUNC );
    if ( !aSDFStream.IsOpen()) {
        nError = SDF_COULD_NOT_OPEN;
    }
    aSDFStream.SetStreamCharSet( RTL_TEXTENCODING_UTF8 );
    nError = SDF_OK;
    DirEntry aEntry( String( sSource, RTL_TEXTENCODING_ASCII_US ));
    aEntry.ToAbs();
    String sFullEntry = aEntry.GetFull();
    aEntry += DirEntry( String( "..", RTL_TEXTENCODING_ASCII_US ));
    aEntry += DirEntry( rRoot );
    ByteString sPrjEntry( aEntry.GetFull(), gsl_getSystemTextEncoding());
    ByteString sActFileName(
        sFullEntry.Copy( sPrjEntry.Len() + 1 ), gsl_getSystemTextEncoding());
    sActFileName.SearchAndReplaceAll( "/", "\\" );

    size_t nPos  = 0;
    sal_Bool bStart = true;
    ByteString sGroup;
    ByteStringHashMap Text;
    ByteString sID;
    ByteString sLine;

    while( nPos < pLines->size() ) {
        sLine = *(*pLines)[ nPos++ ];
        while( nPos < pLines->size() && !isNextGroup( sGroup , sLine ) ) {
            ReadLine( sLine , Text );
            sID = sGroup;
            sLine = *(*pLines)[ nPos++ ];
        };
        if( bStart ) {
            bStart = false;
            sID = sGroup;
        }
        else {
            WriteSDF( aSDFStream , Text , rPrj , rRoot , sActFileName , sID );
        }
    }
    aSDFStream.Close();
    return true;
}

 void LngParser::WriteSDF( SvFileStream &aSDFStream , ByteStringHashMap &rText_inout ,
     const ByteString &rPrj , const ByteString &rRoot ,
     const ByteString &sActFileName , const ByteString &sID )
 {

    sal_Bool bExport = true;
    if ( bExport ) {
           ByteString sTimeStamp( Export::GetTimeStamp());
        ByteString sCur;
        FillInFallbacks( rText_inout );
        for( unsigned int n = 0; n < aLanguages.size(); n++ ){
            sCur = aLanguages[ n ];
            ByteString sAct = rText_inout[ sCur ];
            if ( !sAct.Len() && sCur.Len() )
                sAct = rText_inout[ ByteString("en-US") ];

            ByteString sOutput( rPrj ); sOutput += "\t";
            if ( rRoot.Len())
                sOutput += sActFileName;
            sOutput += "\t0\t";
            sOutput += "LngText\t";
            sOutput += sID; sOutput += "\t\t\t\t0\t";
            sOutput += sCur; sOutput += "\t";
            sOutput += sAct; sOutput += "\t\t\t\t";
            sOutput += sTimeStamp;
            aSDFStream.WriteLine( sOutput );
        }
    }
 }
 bool LngParser::isNextGroup( ByteString &sGroup_out , ByteString &sLine_in ){
    sLine_in.EraseLeadingChars( ' ' );
    sLine_in.EraseTrailingChars( ' ' );
    if (( sLine_in.GetChar( 0 ) == '[' ) &&
            ( sLine_in.GetChar( sLine_in.Len() - 1 ) == ']' )){
        sGroup_out = sLine_in.GetToken( 1, '[' ).GetToken( 0, ']' );
        sGroup_out.EraseLeadingChars( ' ' );
        sGroup_out.EraseTrailingChars( ' ' );
        return true;
    }
    return false;
 }
 void LngParser::ReadLine( const ByteString &sLine_in , ByteStringHashMap &rText_inout){
    ByteString sLang = sLine_in.GetToken( 0, '=' );
    sLang.EraseLeadingChars( ' ' );
    sLang.EraseTrailingChars( ' ' );
    ByteString sText = sLine_in.GetToken( 1, '\"' ).GetToken( 0, '\"' );
    if( sLang.Len() )
        rText_inout[ sLang ] = sText;
 }

/*****************************************************************************/
sal_Bool LngParser::Merge(
    const ByteString &rSDFFile, const ByteString &rDestinationFile , const ByteString& rPrj )
/*****************************************************************************/
{
    (void) rPrj;
    Export::InitLanguages( true );
    SvFileStream aDestination(
        String( rDestinationFile, RTL_TEXTENCODING_ASCII_US ),
        STREAM_STD_WRITE | STREAM_TRUNC );
    if ( !aDestination.IsOpen()) {
        nError = LNG_COULD_NOT_OPEN;
    }
    nError = LNG_OK;

    MergeDataFile aMergeDataFile( rSDFFile, sSource , sal_False, RTL_TEXTENCODING_MS_1252);//, bDBIsUTF8 );
    ByteString sTmp( Export::sLanguages );
    if( sTmp.ToUpperAscii().Equals("ALL") )
        Export::SetLanguages( aMergeDataFile.GetLanguages() );
    aLanguages = Export::GetLanguages();

    size_t nPos = 0;
    sal_Bool bGroup = sal_False;
    ByteString sGroup;

    // seek to next group
    while ( nPos < pLines->size() && !bGroup ) {
        ByteString sLine( *(*pLines)[ nPos ] );
        sLine.EraseLeadingChars( ' ' );
        sLine.EraseTrailingChars( ' ' );
        if (( sLine.GetChar( 0 ) == '[' ) &&
            ( sLine.GetChar( sLine.Len() - 1 ) == ']' ))
        {
            sGroup = sLine.GetToken( 1, '[' ).GetToken( 0, ']' );
            sGroup.EraseLeadingChars( ' ' );
            sGroup.EraseTrailingChars( ' ' );
            bGroup = sal_True;
        }
        nPos ++;
    }

    while ( nPos < pLines->size()) {
        ByteStringHashMap Text;
        ByteString sID( sGroup );
        sal_uLong nLastLangPos = 0;

        ResData  *pResData = new ResData( "", sID , sSource );
        pResData->sResTyp = "LngText";
        PFormEntrys *pEntrys = aMergeDataFile.GetPFormEntrys( pResData );
        // read languages
        bGroup = sal_False;

        ByteString sLanguagesDone;

        while ( nPos < pLines->size() && !bGroup ) {
            ByteString sLine( *(*pLines)[ nPos ] );
            sLine.EraseLeadingChars( ' ' );
            sLine.EraseTrailingChars( ' ' );
            if (( sLine.GetChar( 0 ) == '[' ) &&
                ( sLine.GetChar( sLine.Len() - 1 ) == ']' ))
            {
                sGroup = sLine.GetToken( 1, '[' ).GetToken( 0, ']' );
                sGroup.EraseLeadingChars( ' ' );
                sGroup.EraseTrailingChars( ' ' );
                bGroup = sal_True;
                nPos ++;
                sLanguagesDone = "";
            }
            else if ( sLine.GetTokenCount( '=' ) > 1 ) {
                ByteString sLang = sLine.GetToken( 0, '=' );
                sLang.EraseLeadingChars( ' ' );
                sLang.EraseTrailingChars( ' ' );

                ByteString sSearch( ";" );
                sSearch += sLang;
                sSearch += ";";

                if (( sLanguagesDone.Search( sSearch ) != STRING_NOTFOUND )) {
                    LngLineList::iterator it = pLines->begin();
                    ::std::advance( it, nPos );
                    pLines->erase( it );
                }
                if( bULF && pEntrys )
                {
                    // this is a valid text line
                    ByteString sText = sLine.GetToken( 1, '\"' ).GetToken( 0, '\"' );
                    if( sLang.Len() ){
                        ByteString sNewText;
                        pEntrys->GetText( sNewText, STRING_TYP_TEXT, sLang, sal_True );

                        if ( sNewText.Len()) {
                            ByteString *pLine = (*pLines)[ nPos ];

                            ByteString sText1( sLang );
                            sText1 += " = \"";
                            sText1 += sNewText;
                            sText1 += "\"";
                            *pLine = sText1;
                            Text[ sLang ] = sNewText;
                        }
                    }
                    nLastLangPos = nPos;
                    nPos ++;
                    sLanguagesDone += sSearch;
                }
                else {
                    nLastLangPos = nPos;
                    nPos ++;
                    sLanguagesDone += sSearch;
                }
            }
            else
                nPos++;
        }
        ByteString sCur;
        if ( nLastLangPos )
        {
            for(size_t n = 0; n < aLanguages.size(); ++n)
            {
                sCur = aLanguages[ n ];
                if( !sCur.EqualsIgnoreCaseAscii("en-US") && Text[sCur].isEmpty() && pEntrys )
                {

                    ByteString sNewText;
                    pEntrys->GetText( sNewText, STRING_TYP_TEXT, sCur, sal_True );
                    if (( sNewText.Len()) &&
                        !(( sCur.Equals("x-comment") ) && ( sNewText == "-" )))
                    {
                        ByteString sLine;
                        sLine += sCur;
                        sLine += " = \"";
                        sLine += sNewText;
                        sLine += "\"";

                        nLastLangPos++;
                        nPos++;

                        if ( nLastLangPos < pLines->size() ) {
                            LngLineList::iterator it = pLines->begin();
                            ::std::advance( it, nLastLangPos );
                            pLines->insert( it, new ByteString( sLine ) );
                        } else {
                            pLines->push_back( new ByteString( sLine ) );
                        }
                    }
                }
            }
        }

        delete pResData;
    }

    for ( size_t i = 0; i < pLines->size(); i++ )
        aDestination.WriteLine( *(*pLines)[ i ] );

    aDestination.Close();
    return sal_True;
}

/* vim:set shiftwidth=4 softtabstop=4 expandtab: */