1 /**************************************************************
2 *
3 * Licensed to the Apache Software Foundation (ASF) under one
4 * or more contributor license agreements. See the NOTICE file
5 * distributed with this work for additional information
6 * regarding copyright ownership. The ASF licenses this file
7 * to you under the Apache License, Version 2.0 (the
8 * "License"); you may not use this file except in compliance
9 * with the License. You may obtain a copy of the License at
10 *
11 * http://www.apache.org/licenses/LICENSE-2.0
12 *
13 * Unless required by applicable law or agreed to in writing,
14 * software distributed under the License is distributed on an
15 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16 * KIND, either express or implied. See the License for the
17 * specific language governing permissions and limitations
18 * under the License.
19 *
20 *************************************************************/
21
22
23
24 // MARKER(update_precomp.py): autogen include statement, do not remove
25 #include "precompiled_lingucomponent.hxx"
26
27 #if defined(WNT)
28 #include <tools/prewin.h>
29 #endif
30
31 #if defined(WNT)
32 #include <Windows.h>
33 #endif
34
35 #if defined(WNT)
36 #include <tools/postwin.h>
37 #endif
38
39
40 #include <osl/thread.h>
41 #include <osl/file.hxx>
42 #include <tools/debug.hxx>
43 #include <tools/urlobj.hxx>
44 #include <i18npool/mslangid.hxx>
45 #include <unotools/lingucfg.hxx>
46 #include <unotools/pathoptions.hxx>
47 #include <rtl/ustring.hxx>
48 #include <rtl/string.hxx>
49 #include <rtl/tencinfo.h>
50 #include <linguistic/misc.hxx>
51
52 #include <set>
53 #include <vector>
54 #include <string.h>
55
56 #include <lingutil.hxx>
57
58
59
60
61 using ::com::sun::star::lang::Locale;
62 using namespace ::com::sun::star;
63
64 #if 0
65 //////////////////////////////////////////////////////////////////////
66
67 String GetDirectoryPathFromFileURL( const String &rFileURL )
68 {
69 // get file URL
70 INetURLObject aURLObj;
71 aURLObj.SetSmartProtocol( INET_PROT_FILE );
72 aURLObj.SetSmartURL( rFileURL );
73 aURLObj.removeSegment();
74 DBG_ASSERT( !aURLObj.HasError(), "invalid URL" );
75 String aRes = aURLObj.GetMainURL( INetURLObject::DECODE_TO_IURI );
76 return aRes;
77 }
78 #endif
79
80 #if defined(WNT)
Win_GetShortPathName(const rtl::OUString & rLongPathName)81 rtl::OString Win_GetShortPathName( const rtl::OUString &rLongPathName )
82 {
83 rtl::OString aRes;
84
85 sal_Unicode aShortBuffer[1024] = {0};
86 sal_Int32 nShortBufSize = sizeof( aShortBuffer ) / sizeof( aShortBuffer[0] );
87
88 // use the version of 'GetShortPathName' that can deal with Unicode...
89 sal_Int32 nShortLen = GetShortPathNameW(
90 reinterpret_cast<LPCWSTR>( rLongPathName.getStr() ),
91 reinterpret_cast<LPWSTR>( aShortBuffer ),
92 nShortBufSize );
93
94 if (nShortLen < nShortBufSize) // conversion successful?
95 aRes = rtl::OString( OU2ENC( rtl::OUString( aShortBuffer, nShortLen ), osl_getThreadTextEncoding()) );
96 else
97 DBG_ERROR( "Win_GetShortPathName: buffer to short" );
98
99 return aRes;
100 }
101 #endif //defined(WNT)
102
103 //////////////////////////////////////////////////////////////////////
104
105 // build list of old style diuctionaries (not as extensions) to use.
106 // User installed dictionaries (the ones residing in the user paths)
107 // will get precedence over system installed ones for the same language.
GetOldStyleDics(const char * pDicType)108 std::vector< SvtLinguConfigDictionaryEntry > GetOldStyleDics( const char *pDicType )
109 {
110 std::vector< SvtLinguConfigDictionaryEntry > aRes;
111
112 if (!pDicType)
113 return aRes;
114
115 rtl::OUString aFormatName;
116 String aDicExtension;
117 #ifdef SYSTEM_DICTS
118 rtl::OUString aSystemDir;
119 rtl::OUString aSystemPrefix;
120 rtl::OUString aSystemSuffix;
121 #endif
122 if (strcmp( pDicType, "DICT" ) == 0)
123 {
124 aFormatName = A2OU("DICT_SPELL");
125 aDicExtension = String::CreateFromAscii( ".dic" );
126 #ifdef SYSTEM_DICTS
127 aSystemDir = A2OU( DICT_SYSTEM_DIR );
128 aSystemSuffix = aDicExtension;
129 #endif
130 }
131 else if (strcmp( pDicType, "HYPH" ) == 0)
132 {
133 aFormatName = A2OU("DICT_HYPH");
134 aDicExtension = String::CreateFromAscii( ".dic" );
135 #ifdef SYSTEM_DICTS
136 aSystemDir = A2OU( HYPH_SYSTEM_DIR );
137 aSystemPrefix = A2OU( "hyph_" );
138 aSystemSuffix = aDicExtension;
139 #endif
140 }
141 else if (strcmp( pDicType, "THES" ) == 0)
142 {
143 aFormatName = A2OU("DICT_THES");
144 aDicExtension = String::CreateFromAscii( ".dat" );
145 #ifdef SYSTEM_DICTS
146 aSystemDir = A2OU( THES_SYSTEM_DIR );
147 aSystemPrefix = A2OU( "th_" );
148 aSystemSuffix = A2OU( "_v2.dat" );
149 #endif
150 }
151
152
153 if (aFormatName.getLength() == 0 || aDicExtension.Len() == 0)
154 return aRes;
155
156 // set of languages to remember the language where it is already
157 // decided to make use of the dictionary.
158 std::set< LanguageType > aDicLangInUse;
159
160 #ifdef SYSTEM_DICTS
161 osl::Directory aSystemDicts(aSystemDir);
162 if (aSystemDicts.open() == osl::FileBase::E_None)
163 {
164 osl::DirectoryItem aItem;
165 osl::FileStatus aFileStatus(FileStatusMask_FileURL);
166 while (aSystemDicts.getNextItem(aItem) == osl::FileBase::E_None)
167 {
168 aItem.getFileStatus(aFileStatus);
169 rtl::OUString sPath = aFileStatus.getFileURL();
170 if (sPath.lastIndexOf(aSystemSuffix) == sPath.getLength()-aSystemSuffix.getLength())
171 {
172 sal_Int32 nStartIndex = sPath.lastIndexOf(sal_Unicode('/')) + 1;
173 if (!sPath.match(aSystemPrefix, nStartIndex))
174 continue;
175 rtl::OUString sChunk = sPath.copy(0, sPath.getLength() - aSystemSuffix.getLength());
176 sal_Int32 nIndex = nStartIndex + aSystemPrefix.getLength();
177 rtl::OUString sLang = sChunk.getToken( 0, '_', nIndex );
178 if (!sLang.getLength())
179 continue;
180 rtl::OUString sRegion;
181 if (nIndex != -1)
182 sRegion = sChunk.copy( nIndex, sChunk.getLength() - nIndex );
183
184 // Thus we first get the language of the dictionary
185 LanguageType nLang = MsLangId::convertIsoNamesToLanguage(
186 sLang, sRegion );
187
188 if (aDicLangInUse.count( nLang ) == 0)
189 {
190 // remember the new language in use
191 aDicLangInUse.insert( nLang );
192
193 // add the dictionary to the resulting vector
194 SvtLinguConfigDictionaryEntry aDicEntry;
195 aDicEntry.aLocations.realloc(1);
196 aDicEntry.aLocaleNames.realloc(1);
197 rtl::OUString aLocaleName( MsLangId::convertLanguageToIsoString( nLang ) );
198 aDicEntry.aLocations[0] = sPath;
199 aDicEntry.aFormatName = aFormatName;
200 aDicEntry.aLocaleNames[0] = aLocaleName;
201 aRes.push_back( aDicEntry );
202 }
203 }
204 }
205 }
206
207 #endif
208
209 return aRes;
210 }
211
212
MergeNewStyleDicsAndOldStyleDics(std::list<SvtLinguConfigDictionaryEntry> & rNewStyleDics,const std::vector<SvtLinguConfigDictionaryEntry> & rOldStyleDics)213 void MergeNewStyleDicsAndOldStyleDics(
214 std::list< SvtLinguConfigDictionaryEntry > &rNewStyleDics,
215 const std::vector< SvtLinguConfigDictionaryEntry > &rOldStyleDics )
216 {
217 // get list of languages supported by new style dictionaries
218 std::set< LanguageType > aNewStyleLanguages;
219 std::list< SvtLinguConfigDictionaryEntry >::const_iterator aIt;
220 for (aIt = rNewStyleDics.begin() ; aIt != rNewStyleDics.end(); ++aIt)
221 {
222 const uno::Sequence< rtl::OUString > aLocaleNames( aIt->aLocaleNames );
223 sal_Int32 nLocaleNames = aLocaleNames.getLength();
224 for (sal_Int32 k = 0; k < nLocaleNames; ++k)
225 {
226 LanguageType nLang = MsLangId::convertIsoStringToLanguage( aLocaleNames[k] );
227 aNewStyleLanguages.insert( nLang );
228 }
229 }
230
231 // now check all old style dictionaries if they will add a not yet
232 // added language. If so add them to the resulting vector
233 std::vector< SvtLinguConfigDictionaryEntry >::const_iterator aIt2;
234 for (aIt2 = rOldStyleDics.begin(); aIt2 != rOldStyleDics.end(); ++aIt2)
235 {
236 sal_Int32 nOldStyleDics = aIt2->aLocaleNames.getLength();
237
238 // old style dics should only have one language listed...
239 DBG_ASSERT( nOldStyleDics, "old style dictionary with more then one language found!");
240 if (nOldStyleDics > 0)
241 {
242 LanguageType nLang = MsLangId::convertIsoStringToLanguage( aIt2->aLocaleNames[0] );
243
244 if (nLang == LANGUAGE_DONTKNOW || nLang == LANGUAGE_NONE)
245 {
246 DBG_ERROR( "old style dictionary with invalid language found!" );
247 continue;
248 }
249
250 // language not yet added?
251 if (aNewStyleLanguages.count( nLang ) == 0)
252 rNewStyleDics.push_back( *aIt2 );
253 }
254 else
255 {
256 DBG_ERROR( "old style dictionary with no language found!" );
257 }
258 }
259 }
260
261
getTextEncodingFromCharset(const sal_Char * pCharset)262 rtl_TextEncoding getTextEncodingFromCharset(const sal_Char* pCharset)
263 {
264 // default result: used to indicate that we failed to get the proper encoding
265 rtl_TextEncoding eRet = RTL_TEXTENCODING_DONTKNOW;
266
267 if (pCharset)
268 {
269 eRet = rtl_getTextEncodingFromMimeCharset(pCharset);
270 if (eRet == RTL_TEXTENCODING_DONTKNOW)
271 eRet = rtl_getTextEncodingFromUnixCharset(pCharset);
272 if (eRet == RTL_TEXTENCODING_DONTKNOW)
273 {
274 if (strcmp("ISCII-DEVANAGARI", pCharset) == 0)
275 eRet = RTL_TEXTENCODING_ISCII_DEVANAGARI;
276 }
277 }
278 return eRet;
279 }
280
281 //////////////////////////////////////////////////////////////////////
282
283