summaryrefslogtreecommitdiff
path: root/filter/source/msfilter/rtfutil.cxx
blob: 3ffb053e2f15f641e2d0537c071ec10b62ae99f2 (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
/* -*- 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 <filter/msfilter/rtfutil.hxx>
#include <rtl/strbuf.hxx>
#include <svtools/rtfkeywd.hxx>

namespace msfilter {
namespace rtfutil {

OString OutHex(sal_uLong nHex, sal_uInt8 nLen)
{
    sal_Char aNToABuf[] = "0000000000000000";

    OSL_ENSURE( nLen < sizeof(aNToABuf), "nLen is too big" );
    if( nLen >= sizeof(aNToABuf) )
        nLen = (sizeof(aNToABuf)-1);

    // Set pointer to the buffer end
    sal_Char* pStr = aNToABuf + (sizeof(aNToABuf)-1);
    for( sal_uInt8 n = 0; n < nLen; ++n )
    {
        *(--pStr) = (sal_Char)(nHex & 0xf ) + 48;
        if( *pStr > '9' )
            *pStr += 39;
        nHex >>= 4;
    }
    return OString(pStr);
}

OString OutChar(sal_Unicode c, int *pUCMode, rtl_TextEncoding eDestEnc, bool* pSuccess, bool bUnicode)
{
    if (pSuccess)
        *pSuccess = true;
    OStringBuffer aBuf;
    const sal_Char* pStr = 0;
    // 0x0b instead of \n, etc because of the replacements in SwWW8AttrIter::GetSnippet()
    switch (c)
    {
        case 0x0b:
            // hard line break
            pStr = OOO_STRING_SVTOOLS_RTF_LINE;
            break;
        case '\t':
            pStr = OOO_STRING_SVTOOLS_RTF_TAB;
            break;
        case '\\':
        case '}':
        case '{':
            aBuf.append('\\');
            aBuf.append((sal_Char)c);
            break;
        case 0xa0:
            // non-breaking space
            pStr = "\\~";
            break;
        case 0x1e:
            // non-breaking hyphen
            pStr = "\\_";
            break;
        case 0x1f:
            // optional hyphen
            pStr = "\\-";
            break;
        default:
            if (c >= ' ' && c <= '~')
                aBuf.append((sal_Char)c);
            else {
                OUString sBuf(&c, 1);
                OString sConverted;
                if (pSuccess)
                    *pSuccess &= sBuf.convertToString(&sConverted, eDestEnc, RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR | RTL_UNICODETOTEXT_FLAGS_INVALID_ERROR);
                else
                    sBuf.convertToString(&sConverted, eDestEnc, OUSTRING_TO_OSTRING_CVTFLAGS);
                const sal_Int32 nLen = sConverted.getLength();

                if (pUCMode && bUnicode)
                {
                    if (*pUCMode != nLen)
                    {
                        aBuf.append("\\uc");
                        aBuf.append((sal_Int32)nLen);
                        // #i47831# add an additional whitespace, so that "document whitespaces" are not ignored.
                        aBuf.append(' ');
                        *pUCMode = nLen;
                    }
                    aBuf.append("\\u");
                    aBuf.append((sal_Int32)c);
                }

                for (sal_Int32 nI = 0; nI < nLen; ++nI)
                {
                    aBuf.append("\\'");
                    aBuf.append(OutHex(sConverted.getStr()[nI], 2));
                }
            }
    }
    if (pStr) {
        aBuf.append(pStr);
        switch (c)
        {
            case 0xa0:
            case 0x1e:
            case 0x1f:
                break;
            default:
                aBuf.append(' ');
        }
    }
    return aBuf.makeStringAndClear();
}

OString OutString(const String &rStr, rtl_TextEncoding eDestEnc, bool bUnicode)
{
    SAL_INFO("filter.ms", OSL_THIS_FUNC << ", rStr = '" << OUString(rStr) << "'");
    OStringBuffer aBuf;
    int nUCMode = 1;
    for (xub_StrLen n = 0; n < rStr.Len(); ++n)
        aBuf.append(OutChar(rStr.GetChar(n), &nUCMode, eDestEnc, 0, bUnicode));
    if (nUCMode != 1) {
        aBuf.append(OOO_STRING_SVTOOLS_RTF_UC);
        aBuf.append((sal_Int32)1);
        aBuf.append(" "); // #i47831# add an additional whitespace, so that "document whitespaces" are not ignored.;
    }
    return aBuf.makeStringAndClear();
}

/// Checks if lossless conversion of the string to eDestEnc is possible or not.
static bool TryOutString(const String &rStr, rtl_TextEncoding eDestEnc)
{
    int nUCMode = 1;
    for (xub_StrLen n = 0; n < rStr.Len(); ++n)
    {
        bool bRet;
        OutChar(rStr.GetChar(n), &nUCMode, eDestEnc, &bRet);
        if (!bRet)
            return false;
    }
    return true;
}

OString OutStringUpr(const sal_Char *pToken, const String &rStr, rtl_TextEncoding eDestEnc)
{
    if (TryOutString(rStr, eDestEnc))
        return OString("{") + pToken + " " + OutString(rStr, eDestEnc) + "}";

    OStringBuffer aRet;
    aRet.append("{" OOO_STRING_SVTOOLS_RTF_UPR "{");
    aRet.append(pToken);
    aRet.append(" ");
    aRet.append(OutString(rStr, eDestEnc, /*bUnicode =*/ false));
    aRet.append("}{" OOO_STRING_SVTOOLS_RTF_IGNORE OOO_STRING_SVTOOLS_RTF_UD "{");
    aRet.append(pToken);
    aRet.append(" ");
    aRet.append(OutString(rStr, eDestEnc));
    aRet.append("}}}");
    return aRet.makeStringAndClear();
}
}
}

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