summaryrefslogtreecommitdiff
path: root/l10ntools/source/propmerge.cxx
blob: d3b6314ba0af94ae6c4c62a26160b7634276031a (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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
 * This file is part of the LibreOffice project.
 *
 * This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/.
 */

#include <rtl/ustring.hxx>
#include <o3tl/string_view.hxx>

#include <memory>
#include <cstdlib>
#include <cassert>
#include <iostream>
#include <iomanip>
#include <string_view>

#include <export.hxx>
#include <common.hxx>
#include <propmerge.hxx>
#include <utility>

namespace
{
    //Find ascii escaped unicode
    sal_Int32 lcl_IndexOfUnicode(
        std::string_view rSource, const sal_Int32 nFrom = 0 )
    {
        static constexpr std::string_view sHexDigits = "0123456789abcdefABCDEF";
        size_t nIndex = rSource.find( "\\u", nFrom );
        if( nIndex == std::string_view::npos )
        {
            return -1;
        }
        bool bIsUnicode = true;
        for( short nDist = 2; nDist <= 5; ++nDist )
        {
            if( sHexDigits.find( rSource[nIndex + nDist] ) == std::string_view::npos )
            {
                bIsUnicode = false;
            }
        }
        return bIsUnicode ? nIndex : -1;
    }

    //Convert ascii escaped unicode to utf-8
    OString lcl_ConvertToUTF8( const OString& rText )
    {
        OString sResult = rText;
        sal_Int32 nIndex = lcl_IndexOfUnicode( sResult );
        while( nIndex != -1 && nIndex < rText.getLength() )
        {
            const OString sHex = sResult.copy( nIndex + 2, 4 );
            const sal_Unicode cDec =
                static_cast<sal_Unicode>( strtol( sHex.getStr(), nullptr, 16 ) );
            const OString sNewChar( &cDec, 1, RTL_TEXTENCODING_UTF8 );
            sResult = sResult.replaceAll( "\\u" + sHex, sNewChar );
            nIndex = lcl_IndexOfUnicode( sResult, nIndex );
        }
        return sResult;
    }

    //Escape unicode characters
    void lcl_PrintJavaStyle( std::string_view rText, std::ofstream &rOfstream )
    {
        const OUString sTemp =
            OStringToOUString( rText, RTL_TEXTENCODING_UTF8 );
        for ( sal_Int32 nIndex = 0; nIndex < sTemp.getLength(); ++nIndex )
        {
            sal_Unicode cUniCode = sTemp[nIndex];
            if( cUniCode < 128 )
            {
                rOfstream << static_cast<char>( cUniCode );
            }
            else
            {
                rOfstream
                    << "\\u"
                    << std::setfill('0') << std::setw(2) << std::uppercase
                    << std::hex << (cUniCode >> 8)
                    << std::setfill('0') << std::setw(2) << std::uppercase
                    << std::hex << (cUniCode & 0xFF);
            }
        }
    }
}

//Open source file and store its lines
PropParser::PropParser(
    OString _sInputFile, OString _sLang,
    const bool bMergeMode )
    : m_sSource(std::move( _sInputFile ))
    , m_sLang(std::move( _sLang ))
    , m_bIsInitialized( false )
{
    std::ifstream aIfstream( m_sSource.getStr() );
    if( aIfstream.is_open() )
    {
        std::string s;
        while( std::getline( aIfstream, s ) )
        {
            OString sLine( s.data(), s.length() );
            if( bMergeMode ||
                ( !sLine.startsWith(" *") && !sLine.startsWith("/*") ) )
            {
                m_vLines.push_back( sLine );
            }
        }
    }
    else
    {
        std::cerr
            << "Propex error: Cannot open source file: "
            << m_sSource << std::endl;
        return;
    }
    m_bIsInitialized = true;
}

PropParser::~PropParser()
{
}

//Extract strings form source file
void PropParser::Extract( const OString& rPOFile )
{
    assert( m_bIsInitialized );
    PoOfstream aPOStream( rPOFile, PoOfstream::APP );
    if( !aPOStream.isOpen() )
    {
        std::cerr
            << "Propex error: Cannot open pofile for extract: "
            << rPOFile << std::endl;
        return;
    }

    for( size_t nIndex = 0; nIndex < m_vLines.size(); ++nIndex )
    {
        const OString sLine = m_vLines[nIndex];
        const sal_Int32 nEqualSign = sLine.indexOf('=');
        if( nEqualSign != -1 )
        {
            std::string_view sID = o3tl::trim(sLine.subView( 0, nEqualSign ));
            OString sText = lcl_ConvertToUTF8( OString(o3tl::trim(sLine.subView( nEqualSign + 1 ))) );

            common::writePoEntry(
                "Propex"_ostr, aPOStream, m_sSource, "property",
                OString(sID), OString(), OString(), sText);
        }
    }

    aPOStream.close();
}

//Merge strings to source file
void PropParser::Merge( const OString &rMergeSrc, const OString &rDestinationFile )
{
    assert( m_bIsInitialized );
    std::ofstream aDestination(
        rDestinationFile.getStr(), std::ios_base::out | std::ios_base::trunc );
    if( !aDestination.is_open() ) {
        std::cerr
            << "Propex error: Cannot open source file for merge: "
            << rDestinationFile << std::endl;
        return;
    }

    std::unique_ptr<MergeDataFile> pMergeDataFile;
    if( m_sLang != "qtz" )
    {
        pMergeDataFile.reset( new MergeDataFile( rMergeSrc, m_sSource, false, false ) );

        const std::vector<OString> vLanguages = pMergeDataFile->GetLanguages();
        if( !vLanguages.empty() && vLanguages[0] != m_sLang )
        {
            std::cerr
                << ("Propex error: given language conflicts with language of"
                    " Mergedata file: ")
                << m_sLang << " - "
                << vLanguages[0] << std::endl;
            return;
        }
    }

    for( size_t nIndex = 0; nIndex < m_vLines.size(); ++nIndex )
    {
        const OString sLine = m_vLines[nIndex];
        const sal_Int32 nEqualSign = sLine.indexOf('=');
        if( !sLine.startsWith(" *") && !sLine.startsWith("/*") &&
            nEqualSign != -1 )
        {
            const OString sID( o3tl::trim(sLine.subView( 0, sLine.indexOf('=') )) );
            ResData  aResData( sID, m_sSource );
            aResData.sResTyp = "property"_ostr;
            OString sNewText;
            if( m_sLang == "qtz" )
            {
                const OString sOriginText = lcl_ConvertToUTF8(OString(o3tl::trim(sLine.subView( nEqualSign + 1 ))));
                sNewText = MergeEntrys::GetQTZText(aResData, sOriginText);
            }
            else if( pMergeDataFile )
            {
                MergeEntrys* pEntrys = pMergeDataFile->GetMergeEntrys( &aResData );
                if( pEntrys )
                {
                    pEntrys->GetText( sNewText, m_sLang );
                }
            }
            if( !sNewText.isEmpty() )
            {
                aDestination << OString(sID + "=");
                lcl_PrintJavaStyle( sNewText, aDestination );
                aDestination << std::endl;
            }
            else
            {
                aDestination << sLine << std::endl;
            }
        }
        else
        {
            aDestination << sLine << std::endl;
        }
    }
    aDestination.close();
}

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