1*40df464eSAndrew Rist /**************************************************************
2cdf0e10cSrcweir *
3*40df464eSAndrew Rist * Licensed to the Apache Software Foundation (ASF) under one
4*40df464eSAndrew Rist * or more contributor license agreements. See the NOTICE file
5*40df464eSAndrew Rist * distributed with this work for additional information
6*40df464eSAndrew Rist * regarding copyright ownership. The ASF licenses this file
7*40df464eSAndrew Rist * to you under the Apache License, Version 2.0 (the
8*40df464eSAndrew Rist * "License"); you may not use this file except in compliance
9*40df464eSAndrew Rist * with the License. You may obtain a copy of the License at
10*40df464eSAndrew Rist *
11*40df464eSAndrew Rist * http://www.apache.org/licenses/LICENSE-2.0
12*40df464eSAndrew Rist *
13*40df464eSAndrew Rist * Unless required by applicable law or agreed to in writing,
14*40df464eSAndrew Rist * software distributed under the License is distributed on an
15*40df464eSAndrew Rist * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16*40df464eSAndrew Rist * KIND, either express or implied. See the License for the
17*40df464eSAndrew Rist * specific language governing permissions and limitations
18*40df464eSAndrew Rist * under the License.
19*40df464eSAndrew Rist *
20*40df464eSAndrew Rist *************************************************************/
21*40df464eSAndrew Rist
22*40df464eSAndrew Rist
23cdf0e10cSrcweir
24cdf0e10cSrcweir // MARKER(update_precomp.py): autogen include statement, do not remove
25cdf0e10cSrcweir #include "precompiled_svl.hxx"
26cdf0e10cSrcweir #include <svl/lngmisc.hxx>
27cdf0e10cSrcweir #include <tools/solar.h>
28cdf0e10cSrcweir #include <tools/string.hxx>
29cdf0e10cSrcweir #include <tools/debug.hxx>
30cdf0e10cSrcweir #include <rtl/ustrbuf.hxx>
31cdf0e10cSrcweir #include <rtl/ustring.hxx>
32cdf0e10cSrcweir
33cdf0e10cSrcweir using namespace rtl;
34cdf0e10cSrcweir
35cdf0e10cSrcweir namespace linguistic
36cdf0e10cSrcweir {
37cdf0e10cSrcweir
38cdf0e10cSrcweir ///////////////////////////////////////////////////////////////////////////
39cdf0e10cSrcweir
GetNumControlChars(const OUString & rTxt)40cdf0e10cSrcweir sal_Int32 GetNumControlChars( const OUString &rTxt )
41cdf0e10cSrcweir {
42cdf0e10cSrcweir sal_Int32 nCnt = 0;
43cdf0e10cSrcweir sal_Int32 nLen = rTxt.getLength();
44cdf0e10cSrcweir for (sal_Int32 i = 0; i < nLen; ++i)
45cdf0e10cSrcweir {
46cdf0e10cSrcweir if (IsControlChar( rTxt[i] ))
47cdf0e10cSrcweir ++nCnt;
48cdf0e10cSrcweir }
49cdf0e10cSrcweir return nCnt;
50cdf0e10cSrcweir }
51cdf0e10cSrcweir
52cdf0e10cSrcweir
RemoveHyphens(OUString & rTxt)53cdf0e10cSrcweir sal_Bool RemoveHyphens( OUString &rTxt )
54cdf0e10cSrcweir {
55cdf0e10cSrcweir sal_Bool bModified = sal_False;
56cdf0e10cSrcweir if (HasHyphens( rTxt ))
57cdf0e10cSrcweir {
58cdf0e10cSrcweir String aTmp( rTxt );
59cdf0e10cSrcweir aTmp.EraseAllChars( SVT_SOFT_HYPHEN );
60cdf0e10cSrcweir aTmp.EraseAllChars( SVT_HARD_HYPHEN );
61cdf0e10cSrcweir rTxt = aTmp;
62cdf0e10cSrcweir bModified = sal_True;
63cdf0e10cSrcweir }
64cdf0e10cSrcweir return bModified;
65cdf0e10cSrcweir }
66cdf0e10cSrcweir
67cdf0e10cSrcweir
RemoveControlChars(OUString & rTxt)68cdf0e10cSrcweir sal_Bool RemoveControlChars( OUString &rTxt )
69cdf0e10cSrcweir {
70cdf0e10cSrcweir sal_Bool bModified = sal_False;
71cdf0e10cSrcweir sal_Int32 nCtrlChars = GetNumControlChars( rTxt );
72cdf0e10cSrcweir if (nCtrlChars)
73cdf0e10cSrcweir {
74cdf0e10cSrcweir sal_Int32 nLen = rTxt.getLength();
75cdf0e10cSrcweir sal_Int32 nSize = nLen - nCtrlChars;
76cdf0e10cSrcweir OUStringBuffer aBuf( nSize );
77cdf0e10cSrcweir aBuf.setLength( nSize );
78cdf0e10cSrcweir sal_Int32 nCnt = 0;
79cdf0e10cSrcweir for (sal_Int32 i = 0; i < nLen; ++i)
80cdf0e10cSrcweir {
81cdf0e10cSrcweir sal_Unicode cChar = rTxt[i];
82cdf0e10cSrcweir if (!IsControlChar( cChar ))
83cdf0e10cSrcweir {
84cdf0e10cSrcweir DBG_ASSERT( nCnt < nSize, "index out of range" );
85cdf0e10cSrcweir aBuf.setCharAt( nCnt++, cChar );
86cdf0e10cSrcweir }
87cdf0e10cSrcweir }
88cdf0e10cSrcweir DBG_ASSERT( nCnt == nSize, "wrong size" );
89cdf0e10cSrcweir rTxt = aBuf.makeStringAndClear();
90cdf0e10cSrcweir bModified = sal_True;
91cdf0e10cSrcweir }
92cdf0e10cSrcweir return bModified;
93cdf0e10cSrcweir }
94cdf0e10cSrcweir
95cdf0e10cSrcweir
96cdf0e10cSrcweir // non breaking field character
97cdf0e10cSrcweir #define CH_TXTATR_INWORD ((sal_Char) 0x02)
98cdf0e10cSrcweir
ReplaceControlChars(rtl::OUString & rTxt,sal_Char)99cdf0e10cSrcweir sal_Bool ReplaceControlChars( rtl::OUString &rTxt, sal_Char /*aRplcChar*/ )
100cdf0e10cSrcweir {
101cdf0e10cSrcweir // the resulting string looks like this:
102cdf0e10cSrcweir // 1. non breaking field characters get removed
103cdf0e10cSrcweir // 2. remaining control characters will be replaced by ' '
104cdf0e10cSrcweir
105cdf0e10cSrcweir sal_Bool bModified = sal_False;
106cdf0e10cSrcweir sal_Int32 nCtrlChars = GetNumControlChars( rTxt );
107cdf0e10cSrcweir if (nCtrlChars)
108cdf0e10cSrcweir {
109cdf0e10cSrcweir sal_Int32 nLen = rTxt.getLength();
110cdf0e10cSrcweir OUStringBuffer aBuf( nLen );
111cdf0e10cSrcweir sal_Int32 nCnt = 0;
112cdf0e10cSrcweir for (sal_Int32 i = 0; i < nLen; ++i)
113cdf0e10cSrcweir {
114cdf0e10cSrcweir sal_Unicode cChar = rTxt[i];
115cdf0e10cSrcweir if (CH_TXTATR_INWORD != cChar)
116cdf0e10cSrcweir {
117cdf0e10cSrcweir if (IsControlChar( cChar ))
118cdf0e10cSrcweir cChar = ' ';
119cdf0e10cSrcweir DBG_ASSERT( nCnt < nLen, "index out of range" );
120cdf0e10cSrcweir aBuf.setCharAt( nCnt++, cChar );
121cdf0e10cSrcweir }
122cdf0e10cSrcweir }
123cdf0e10cSrcweir aBuf.setLength( nCnt );
124cdf0e10cSrcweir rTxt = aBuf.makeStringAndClear();
125cdf0e10cSrcweir bModified = sal_True;
126cdf0e10cSrcweir }
127cdf0e10cSrcweir return bModified;
128cdf0e10cSrcweir }
129cdf0e10cSrcweir
130cdf0e10cSrcweir
GetThesaurusReplaceText(const String & rText)131cdf0e10cSrcweir String GetThesaurusReplaceText( const String &rText )
132cdf0e10cSrcweir {
133cdf0e10cSrcweir // The strings for synonyms returned by the thesaurus sometimes have some
134cdf0e10cSrcweir // explanation text put in between '(' and ')' or a trailing '*'.
135cdf0e10cSrcweir // These parts should not be put in the ReplaceEdit Text that may get
136cdf0e10cSrcweir // inserted into the document. Thus we strip them from the text.
137cdf0e10cSrcweir
138cdf0e10cSrcweir String aText( rText );
139cdf0e10cSrcweir
140cdf0e10cSrcweir xub_StrLen nPos = aText.Search( sal_Unicode('(') );
141cdf0e10cSrcweir while (STRING_NOTFOUND != nPos)
142cdf0e10cSrcweir {
143cdf0e10cSrcweir xub_StrLen nEnd = aText.Search( sal_Unicode(')'), nPos );
144cdf0e10cSrcweir if (STRING_NOTFOUND != nEnd)
145cdf0e10cSrcweir aText.Erase( nPos, nEnd-nPos+1 );
146cdf0e10cSrcweir else
147cdf0e10cSrcweir break;
148cdf0e10cSrcweir nPos = aText.Search( sal_Unicode('(') );
149cdf0e10cSrcweir }
150cdf0e10cSrcweir
151cdf0e10cSrcweir nPos = aText.Search( sal_Unicode('*') );
152cdf0e10cSrcweir if (STRING_NOTFOUND != nPos)
153cdf0e10cSrcweir aText.Erase( nPos );
154cdf0e10cSrcweir
155cdf0e10cSrcweir // remove any possible remaining ' ' that may confuse the thesaurus
156cdf0e10cSrcweir // when it gets called with the text
157cdf0e10cSrcweir aText.EraseLeadingAndTrailingChars( sal_Unicode(' ') );
158cdf0e10cSrcweir
159cdf0e10cSrcweir return aText;
160cdf0e10cSrcweir }
161cdf0e10cSrcweir
162cdf0e10cSrcweir ///////////////////////////////////////////////////////////////////////////
163cdf0e10cSrcweir
164cdf0e10cSrcweir } // namespace linguistic
165cdf0e10cSrcweir
166