summaryrefslogtreecommitdiffstats
path: root/svtools/source/svrtf/rtfout.cxx
blob: b06a04eedfa0aed2f91384ac707e43f14210a6aa (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
/* -*- 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/.
 *
 * This file incorporates work covered by the following license notice:
 *
 *   Licensed to the Apache Software Foundation (ASF) under one or more
 *   contributor license agreements. See the NOTICE file distributed
 *   with this work for additional information regarding copyright
 *   ownership. The ASF licenses this file to you under the Apache
 *   License, Version 2.0 (the "License"); you may not use this file
 *   except in compliance with the License. You may obtain a copy of
 *   the License at http://www.apache.org/licenses/LICENSE-2.0 .
 */

#include <tools/debug.hxx>
#include <tools/stream.hxx>
#include <tools/solar.h>
#include <rtl/string.hxx>
#include <svtools/rtfkeywd.hxx>
#include <svtools/rtfout.hxx>

namespace {

SvStream& Out_Hex( SvStream& rStream, sal_uLong nHex, sal_uInt8 nLen )
{
    char aNToABuf[] = "0000000000000000";

    DBG_ASSERT( nLen < sizeof(aNToABuf), "too many places" );
    if( nLen >= sizeof(aNToABuf) )
        nLen = (sizeof(aNToABuf)-1);

    // set pointer to end of buffer
    char* pStr = aNToABuf + (sizeof(aNToABuf)-1);
    for( sal_uInt8 n = 0; n < nLen; ++n )
    {
        *(--pStr) = static_cast<char>(nHex & 0xf ) + 48;
        if( *pStr > '9' )
            *pStr += 39;
        nHex >>= 4;
    }
    return rStream.WriteCharPtr( pStr );
}

// Ideally, this function should work on (sal_uInt32) Unicode scalar values
// instead of (sal_Unicode) UTF-16 code units.  However, at least "Rich Text
// Format (RTF) Specification Version 1.9.1" available at
// <https://www.microsoft.com/en-us/download/details.aspx?id=10725> does not
// look like it allows non-BMP Unicode characters >= 0x10000 in the \uN notation
// (it only talks about "Unicode character", but then explains how values of N
// greater than 32767 will be expressed as negative signed 16-bit numbers, so
// that smells like \uN is limited to BMP).
// However the "Mathematics" section has an example that shows the code point
// U+1D44E being encoded as UTF-16 surrogate pair "\u-10187?\u-9138?", so
// sal_Unicode actually works fine here.
SvStream& Out_Char(SvStream& rStream, sal_Unicode c,
    int *pUCMode, rtl_TextEncoding eDestEnc)
{
    const char* pStr = nullptr;
    switch (c)
    {
    case 0x1:
    case 0x2:
        // this are control character of our textattributes and will never be
        // written
        break;
    case 0xA0:
        rStream.WriteCharPtr( "\\~" );
        break;
    case 0xAD:
        rStream.WriteCharPtr( "\\-" );
        break;
    case 0x2011:
        rStream.WriteCharPtr( "\\_" );
        break;
    case '\n':
        pStr = OOO_STRING_SVTOOLS_RTF_LINE;
        break;
    case '\t':
        pStr = OOO_STRING_SVTOOLS_RTF_TAB;
        break;
    default:
        switch(c)
        {
            case 149:
                pStr = OOO_STRING_SVTOOLS_RTF_BULLET;
                break;
            case 150:
                pStr = OOO_STRING_SVTOOLS_RTF_ENDASH;
                break;
            case 151:
                pStr = OOO_STRING_SVTOOLS_RTF_EMDASH;
                break;
            case 145:
                pStr = OOO_STRING_SVTOOLS_RTF_LQUOTE;
                break;
            case 146:
                pStr = OOO_STRING_SVTOOLS_RTF_RQUOTE;
                break;
            case 147:
                pStr = OOO_STRING_SVTOOLS_RTF_LDBLQUOTE;
                break;
            case 148:
                pStr = OOO_STRING_SVTOOLS_RTF_RDBLQUOTE;
                break;
        }

        if (pStr)
            break;

        switch (c)
        {
            case '\\':
            case '}':
            case '{':
                rStream.WriteChar( '\\' ).WriteChar( char(c) );
                break;
            default:
                if (c >= ' ' && c <= '~')
                    rStream.WriteChar( char(c) );
                else
                {
                    //If we can't convert to the dest encoding, or if
                    //it's an uncommon multibyte sequence which most
                    //readers won't be able to handle correctly, then
                    //export as unicode
                    OUString sBuf(&c, 1);
                    OString sConverted;
                    sal_uInt32 const nFlags =
                        RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR |
                        RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR;
                    bool bWriteAsUnicode = !(sBuf.convertToString(&sConverted,
                                         eDestEnc, nFlags))
                                            || (RTL_TEXTENCODING_UTF8==eDestEnc); // #i43933# do not export UTF-8 chars in RTF;
                    if (bWriteAsUnicode)
                    {
                        (void)sBuf.convertToString(&sConverted,
                            eDestEnc, OUSTRING_TO_OSTRING_CVTFLAGS);
                    }
                    const sal_Int32 nLen = sConverted.getLength();

                    if (bWriteAsUnicode && pUCMode)
                    {
                        // then write as unicode - character
                        if (*pUCMode != nLen)
                        {
                            // #i47831# add an additional whitespace, so that
                            // "document whitespaces" are not ignored.;
                            rStream.WriteCharPtr( "\\uc" )
                               .WriteOString( OString::number(nLen) ).WriteCharPtr( " " );
                            *pUCMode = nLen;
                        }
                        rStream.WriteCharPtr( "\\u" )
                           .WriteCharPtr( OString::number(
                                static_cast<sal_Int32>(c)).getStr() );
                    }

                    for (sal_Int32 nI = 0; nI < nLen; ++nI)
                    {
                        rStream.WriteCharPtr( "\\'" );
                        Out_Hex(rStream, sConverted[nI], 2);
                    }
                }
                break;
        }
        break;
    }

    if (pStr)
        rStream.WriteCharPtr( pStr ).WriteChar( ' ' );

    return rStream;
}

}

SvStream& RTFOutFuncs::Out_String( SvStream& rStream, const OUString& rStr,
    rtl_TextEncoding eDestEnc)
{
    int nUCMode = 1;
    for (sal_Int32 n = 0; n < rStr.getLength(); ++n)
        Out_Char(rStream, rStr[n], &nUCMode, eDestEnc);
    if (nUCMode != 1)
      rStream.WriteCharPtr( "\\uc1" ).WriteCharPtr( " " ); // #i47831# add an additional whitespace, so that "document whitespaces" are not ignored.;
    return rStream;
}

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