diff options
Diffstat (limited to 'lingucomponent')
40 files changed, 1152 insertions, 2130 deletions
diff --git a/lingucomponent/prj/build.lst b/lingucomponent/prj/build.lst index 138e5858f70e..15ee595c67c0 100644 --- a/lingucomponent/prj/build.lst +++ b/lingucomponent/prj/build.lst @@ -1,9 +1,8 @@ -lc lingucomponent : linguistic libtextcat svl HYPHEN:hyphen HUNSPELL:hunspell NULL +lc lingucomponent : linguistic LIBTEXTCAT:libtextcat LIBTEXTCATDATA:libtextcat svl HYPHEN:hyphen HUNSPELL:hunspell MYTHES:mythes NULL lc lingucomponent usr1 - all lc_mkout NULL lc lingucomponent\inc nmake - all lc_inc NULL lc lingucomponent\source\lingutil nmake - all lc_util lc_inc NULL -lc lingucomponent\source\thesaurus\mythes nmake - all lc_mythes lc_util lc_inc NULL -lc lingucomponent\source\thesaurus\libnth nmake - all lc_libnth lc_mythes lc_util lc_inc NULL +lc lingucomponent\source\thesaurus\libnth nmake - all lc_libnth lc_util lc_inc NULL lc lingucomponent\source\spellcheck\spell nmake - all lc_libspell lc_util lc_inc NULL lc lingucomponent\source\hyphenator\altlinuxhyph\hyphen nmake - all lc_libhyphen lc_util lc_inc NULL lc lingucomponent\source\languageguessing nmake - all lc_languageguessing lc_util lc_inc NULL diff --git a/lingucomponent/prj/d.lst b/lingucomponent/prj/d.lst index 666ee38d5b1d..4760a299c84d 100644 --- a/lingucomponent/prj/d.lst +++ b/lingucomponent/prj/d.lst @@ -46,3 +46,8 @@ mkdir: %_DEST%\xml%_EXT%\registry\data\org\openoffice mkdir: %_DEST%\xml%_EXT%\registry\data\org\openoffice\Office ..\config\*.xcu %_DEST%\xml%_EXT%\registry\data\org\openoffice\Office\*.xcu +..\%__SRC%\misc\MacOSXSpell.component %_DEST%\xml%_EXT%\MacOSXSpell.component +..\%__SRC%\misc\guesslang.component %_DEST%\xml%_EXT%\guesslang.component +..\%__SRC%\misc\hyphen.component %_DEST%\xml%_EXT%\hyphen.component +..\%__SRC%\misc\lnth.component %_DEST%\xml%_EXT%\lnth.component +..\%__SRC%\misc\spell.component %_DEST%\xml%_EXT%\spell.component diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/exports.dxp b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/exports.dxp index b0f85bf7bebf..a9861e3ffc0c 100644 --- a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/exports.dxp +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/exports.dxp @@ -1,3 +1,2 @@ component_getFactory component_getImplementationEnvironment -component_writeInfo diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hreg.cxx b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hreg.cxx index 448ecc529bf0..9d975a83b8ef 100644 --- a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hreg.cxx +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hreg.cxx @@ -42,9 +42,6 @@ using namespace com::sun::star::registry; // declaration of external RegEntry-functions defined by the service objects // -extern sal_Bool SAL_CALL Hyphenator_writeInfo( - void * /*pServiceManager*/, XRegistryKey * pRegistryKey ); - extern void * SAL_CALL Hyphenator_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, @@ -57,12 +54,6 @@ extern void * SAL_CALL Hyphenator_getFactory( extern "C" { -sal_Bool SAL_CALL component_writeInfo( - void * pServiceManager, XRegistryKey * pRegistryKey ) -{ - return Hyphenator_writeInfo( pServiceManager, pRegistryKey ); -} - void SAL_CALL component_getImplementationEnvironment( const sal_Char ** ppEnvTypeName, uno_Environment ** /*ppEnv*/ ) { diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphen.component b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphen.component new file mode 100644 index 000000000000..aeae4c577b98 --- /dev/null +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphen.component @@ -0,0 +1,34 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!--********************************************************************** +* +* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +* +* Copyright 2000, 2010 Oracle and/or its affiliates. +* +* OpenOffice.org - a multi-platform office productivity suite +* +* This file is part of OpenOffice.org. +* +* OpenOffice.org is free software: you can redistribute it and/or modify +* it under the terms of the GNU Lesser General Public License version 3 +* only, as published by the Free Software Foundation. +* +* OpenOffice.org is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU Lesser General Public License version 3 for more details +* (a copy is included in the LICENSE file that accompanied this code). +* +* You should have received a copy of the GNU Lesser General Public License +* version 3 along with OpenOffice.org. If not, see +* <http://www.openoffice.org/license.html> +* for a copy of the LGPLv3 License. +* +**********************************************************************--> + +<component loader="com.sun.star.loader.SharedLibrary" + xmlns="http://openoffice.org/2010/uno-components"> + <implementation name="org.openoffice.lingu.LibHnjHyphenator"> + <service name="com.sun.star.linguistic2.Hyphenator"/> + </implementation> +</component> diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.cxx b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.cxx index 3b0871cc36b6..5d040be72cb9 100755 --- a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.cxx +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.cxx @@ -32,7 +32,6 @@ #include <com/sun/star/uno/Reference.h> #include <com/sun/star/linguistic2/XSearchableDictionaryList.hpp> -//#include <com/sun/star/linguistic2/SpellFailure.hpp> #include <cppuhelper/factory.hxx> // helper for factories #include <com/sun/star/registry/XRegistryKey.hpp> #include <i18npool/mslangid.hxx> @@ -43,15 +42,12 @@ #include <osl/mutex.hxx> #include <hyphen.h> - -#ifndef _HYPHENIMP_HXX #include <hyphenimp.hxx> -#endif #include <linguistic/hyphdta.hxx> #include <rtl/ustring.hxx> - #include <rtl/ustrbuf.hxx> +#include <rtl/textenc.h> #include <linguistic/lngprops.hxx> #include <unotools/pathoptions.hxx> @@ -97,9 +93,8 @@ Hyphenator::Hyphenator() : { bDisposing = FALSE; pPropHelper = NULL; - aDicts = NULL; - numdict = 0; - + aDicts = NULL; + numdict = 0; } @@ -108,21 +103,22 @@ Hyphenator::~Hyphenator() if (pPropHelper) pPropHelper->RemoveAsPropListener(); - if ((numdict) && (aDicts)) { - for (int i=0; i < numdict; i++) { + if ((numdict) && (aDicts)) + { + for (int i=0; i < numdict; i++) + { if (aDicts[i].apCC) delete aDicts[i].apCC; aDicts[i].apCC = NULL; - } + } } - if (aDicts) delete[] aDicts; + if (aDicts) delete[] aDicts; aDicts = NULL; - numdict = 0; + numdict = 0; } PropertyHelper_Hyphen & Hyphenator::GetPropHelper_Impl() { - if (!pPropHelper) { Reference< XPropertySet > xPropSet( GetLinguProperties(), UNO_QUERY ); @@ -212,12 +208,7 @@ Sequence< Locale > SAL_CALL Hyphenator::getLocales() // add dictionary information aDicts = new HDInfo[numdict]; -/* - aTEncs = new rtl_TextEncoding [numdict]; - aTLocs = new Locale [numdict]; - aTNames = new OUString [numdict]; - aCharSetInfo = new CharClass* [numdict]; -*/ + k = 0; for (aDictIt = aDics.begin(); aDictIt != aDics.end(); ++aDictIt) { @@ -233,7 +224,7 @@ Sequence< Locale > SAL_CALL Hyphenator::getLocales() for (sal_Int32 i = 0; i < nLocales; ++i) { aDicts[k].aPtr = NULL; - aDicts[k].aEnc = 0; + aDicts[k].eEnc = RTL_TEXTENCODING_DONTKNOW; aDicts[k].aLoc = MsLangId::convertLanguageToLocale( MsLangId::convertIsoStringToLanguage( aDictIt->aLocaleNames[i] )); aDicts[k].apCC = new CharClass( aDicts[k].aLoc ); @@ -288,240 +279,268 @@ sal_Bool SAL_CALL Hyphenator::hasLocale(const Locale& rLocale) } -Reference< XHyphenatedWord > SAL_CALL -Hyphenator::hyphenate( const ::rtl::OUString& aWord, - const ::com::sun::star::lang::Locale& aLocale, - sal_Int16 nMaxLeading, - const ::com::sun::star::beans::PropertyValues& aProperties ) - throw (com::sun::star::uno::RuntimeException, - com::sun::star::lang::IllegalArgumentException) +Reference< XHyphenatedWord > SAL_CALL Hyphenator::hyphenate( const ::rtl::OUString& aWord, + const ::com::sun::star::lang::Locale& aLocale, + sal_Int16 nMaxLeading, + const ::com::sun::star::beans::PropertyValues& aProperties ) + throw (com::sun::star::uno::RuntimeException, com::sun::star::lang::IllegalArgumentException) { int nHyphenationPos = -1; - int nHyphenationPosAlt = -1; - int nHyphenationPosAltHyph = -1; + int nHyphenationPosAlt = -1; + int nHyphenationPosAltHyph = -1; int wordlen; char *hyphens; - char *lcword; - int k = 0; + char *lcword; + int k = 0; - PropertyHelper_Hyphen & rHelper = GetPropHelper(); - rHelper.SetTmpPropVals(aProperties); + PropertyHelper_Hyphen & rHelper = GetPropHelper(); + rHelper.SetTmpPropVals(aProperties); sal_Int16 minTrail = rHelper.GetMinTrailing(); sal_Int16 minLead = rHelper.GetMinLeading(); sal_Int16 minLen = rHelper.GetMinWordLength(); HyphenDict *dict = NULL; - rtl_TextEncoding aEnc = 0; - CharClass * pCC = NULL; + rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW; + CharClass * pCC = NULL; Reference< XHyphenatedWord > xRes; - k = -1; - for (int j = 0; j < numdict; j++) - if (aLocale == aDicts[j].aLoc) k = j; - - - // if we have a hyphenation dictionary matching this locale - if (k != -1) { + k = -1; + for (int j = 0; j < numdict; j++) + { + if (aLocale == aDicts[j].aLoc) + k = j; + } + // if we have a hyphenation dictionary matching this locale + if (k != -1) + { // if this dictinary has not been loaded yet do that - if (!aDicts[k].aPtr) { - - OUString DictFN = aDicts[k].aName + A2OU(".dic"); - OUString dictpath; + if (!aDicts[k].aPtr) + { + OUString DictFN = aDicts[k].aName + A2OU(".dic"); + OUString dictpath; - osl::FileBase::getSystemPathFromFileURL( DictFN, dictpath ); - OString sTmp( OU2ENC( dictpath, osl_getThreadTextEncoding() ) ); + osl::FileBase::getSystemPathFromFileURL( DictFN, dictpath ); + OString sTmp( OU2ENC( dictpath, osl_getThreadTextEncoding() ) ); #if defined(WNT) - // workaround for Windows specifc problem that the - // path length in calls to 'fopen' is limted to somewhat - // about 120+ characters which will usually be exceed when - // using dictionaries as extensions. - sTmp = Win_GetShortPathName( dictpath ); + // workaround for Windows specifc problem that the + // path length in calls to 'fopen' is limted to somewhat + // about 120+ characters which will usually be exceed when + // using dictionaries as extensions. + sTmp = Win_GetShortPathName( dictpath ); #endif - if ( ( dict = hnj_hyphen_load ( sTmp.getStr()) ) == NULL ) - { - fprintf(stderr, "Couldn't find file %s\n", OU2ENC(dictpath, osl_getThreadTextEncoding()) ); - return NULL; - } - aDicts[k].aPtr = dict; - aDicts[k].aEnc = rtl_getTextEncodingFromUnixCharset(dict->cset); - if (aDicts[k].aEnc == RTL_TEXTENCODING_DONTKNOW) { - if (strcmp("ISCII-DEVANAGARI", dict->cset) == 0) { - aDicts[k].aEnc = RTL_TEXTENCODING_ISCII_DEVANAGARI; - } else if (strcmp("UTF-8", dict->cset) == 0) { - aDicts[k].aEnc = RTL_TEXTENCODING_UTF8; - } - } + if ( ( dict = hnj_hyphen_load ( sTmp.getStr()) ) == NULL ) + { + fprintf(stderr, "Couldn't find file %s\n", OU2ENC(dictpath, osl_getThreadTextEncoding()) ); + return NULL; + } + aDicts[k].aPtr = dict; + aDicts[k].eEnc = getTextEncodingFromCharset(dict->cset); } - // other wise hyphenate the word with that dictionary - dict = aDicts[k].aPtr; - aEnc = aDicts[k].aEnc; - pCC = aDicts[k].apCC; + // other wise hyphenate the word with that dictionary + dict = aDicts[k].aPtr; + eEnc = aDicts[k].eEnc; + pCC = aDicts[k].apCC; - sal_uInt16 ct = CAPTYPE_UNKNOWN; - ct = capitalType(aWord, pCC); + // we don't want to work with a default text encoding since following incorrect + // results may occur only for specific text and thus may be hard to notice. + // Thus better always make a clean exit here if the text encoding is in question. + // Hopefully something not working at all will raise proper attention quickly. ;-) + DBG_ASSERT( eEnc != RTL_TEXTENCODING_DONTKNOW, "failed to get text encoding! (maybe incorrect encoding string in file)" ); + if (eEnc == RTL_TEXTENCODING_DONTKNOW) + return NULL; - // first convert any smart quotes or apostrophes to normal ones + sal_uInt16 ct = CAPTYPE_UNKNOWN; + ct = capitalType(aWord, pCC); + + // first convert any smart quotes or apostrophes to normal ones OUStringBuffer rBuf(aWord); - sal_Int32 nc = rBuf.getLength(); - sal_Unicode ch; - for (sal_Int32 ix=0; ix < nc; ix++) { + sal_Int32 nc = rBuf.getLength(); + sal_Unicode ch; + for (sal_Int32 ix=0; ix < nc; ix++) + { ch = rBuf.charAt(ix); - if ((ch == 0x201C) || (ch == 0x201D)) rBuf.setCharAt(ix,(sal_Unicode)0x0022); - if ((ch == 0x2018) || (ch == 0x2019)) rBuf.setCharAt(ix,(sal_Unicode)0x0027); - } - OUString nWord(rBuf.makeStringAndClear()); + if ((ch == 0x201C) || (ch == 0x201D)) + rBuf.setCharAt(ix,(sal_Unicode)0x0022); + if ((ch == 0x2018) || (ch == 0x2019)) + rBuf.setCharAt(ix,(sal_Unicode)0x0027); + } + OUString nWord(rBuf.makeStringAndClear()); - // now convert word to all lowercase for pattern recognition - OUString nTerm(makeLowerCase(nWord, pCC)); + // now convert word to all lowercase for pattern recognition + OUString nTerm(makeLowerCase(nWord, pCC)); - // now convert word to needed encoding - OString encWord(OU2ENC(nTerm,aEnc)); + // now convert word to needed encoding + OString encWord(OU2ENC(nTerm,eEnc)); wordlen = encWord.getLength(); - lcword = new char[wordlen + 1]; + lcword = new char[wordlen + 1]; hyphens = new char[wordlen + 5]; - char ** rep = NULL; // replacements of discretionary hyphenation - int * pos = NULL; // array of [hyphenation point] minus [deletion position] - int * cut = NULL; // length of deletions in original word - - // copy converted word into simple char buffer - strcpy(lcword,encWord.getStr()); - - // now strip off any ending periods - int n = wordlen-1; - while((n >=0) && (lcword[n] == '.')) n--; - n++; - if (n > 0) { - if (hnj_hyphen_hyphenate3(dict, lcword, n, hyphens, NULL, &rep, &pos, &cut, - minLead, minTrail, Max(dict->clhmin, Max(dict->clhmin, 2) + Max(0, minLead - Max(dict->lhmin, 2))), - Max(dict->crhmin, Max(dict->crhmin, 2) + Max(0, minTrail - Max(dict->rhmin, 2))))) - { - //whoops something did not work - delete[] hyphens; - delete[] lcword; - if (rep) { - for(int j = 0; j < n; j++) { + char ** rep = NULL; // replacements of discretionary hyphenation + int * pos = NULL; // array of [hyphenation point] minus [deletion position] + int * cut = NULL; // length of deletions in original word + + // copy converted word into simple char buffer + strcpy(lcword,encWord.getStr()); + + // now strip off any ending periods + int n = wordlen-1; + while((n >=0) && (lcword[n] == '.')) + n--; + n++; + if (n > 0) + { + const bool bFailed = 0 != hnj_hyphen_hyphenate3( dict, lcword, n, hyphens, NULL, + &rep, &pos, &cut, minLead, minTrail, + Max(dict->clhmin, Max(dict->clhmin, 2) + Max(0, minLead - Max(dict->lhmin, 2))), + Max(dict->crhmin, Max(dict->crhmin, 2) + Max(0, minTrail - Max(dict->rhmin, 2))) ); + if (bFailed) + { + //whoops something did not work + delete[] hyphens; + delete[] lcword; + if (rep) + { + for(int j = 0; j < n; j++) + { if (rep[j]) free(rep[j]); } free(rep); - } - if (pos) free(pos); - if (cut) free(cut); - return NULL; - } + } + if (pos) free(pos); + if (cut) free(cut); + return NULL; } + } - // now backfill hyphens[] for any removed trailing periods - for (int c = n; c < wordlen; c++) hyphens[c] = '0'; - hyphens[wordlen] = '\0'; + // now backfill hyphens[] for any removed trailing periods + for (int c = n; c < wordlen; c++) hyphens[c] = '0'; + hyphens[wordlen] = '\0'; INT32 Leading = GetPosInWordToCheck( aWord, nMaxLeading ); for (INT32 i = 0; i < n; i++) { - int leftrep = 0; - BOOL hit = (n >= minLen); - if (!rep || !rep[i] || (i >= n)) { - hit = hit && (hyphens[i]&1) && (i < Leading); - hit = hit && (i >= (minLead-1) ); - hit = hit && ((n - i - 1) >= minTrail); - } else { - // calculate change character length before hyphenation point signed with '=' - for (char * c = rep[i]; *c && (*c != '='); c++) { - if (aEnc == RTL_TEXTENCODING_UTF8) { - if (((unsigned char) *c) >> 6 != 2) leftrep++; - } else leftrep++; + int leftrep = 0; + BOOL hit = (n >= minLen); + if (!rep || !rep[i] || (i >= n)) + { + hit = hit && (hyphens[i]&1) && (i < Leading); + hit = hit && (i >= (minLead-1) ); + hit = hit && ((n - i - 1) >= minTrail); + } + else + { + // calculate change character length before hyphenation point signed with '=' + for (char * c = rep[i]; *c && (*c != '='); c++) + { + if (eEnc == RTL_TEXTENCODING_UTF8) + { + if (((unsigned char) *c) >> 6 != 2) + leftrep++; } - hit = hit && (hyphens[i]&1) && ((i + leftrep - pos[i]) < Leading); - hit = hit && ((i + leftrep - pos[i]) >= (minLead-1) ); - hit = hit && ((n - i - 1 + sal::static_int_cast< sal_sSize >(strlen(rep[i])) - leftrep - 1) >= minTrail); + else + leftrep++; } - if (hit) { - nHyphenationPos = i; - if (rep && (i < n) && rep[i]) { - nHyphenationPosAlt = i - pos[i]; - nHyphenationPosAltHyph = i + leftrep - pos[i]; - } + hit = hit && (hyphens[i]&1) && ((i + leftrep - pos[i]) < Leading); + hit = hit && ((i + leftrep - pos[i]) >= (minLead-1) ); + hit = hit && ((n - i - 1 + sal::static_int_cast< sal_sSize >(strlen(rep[i])) - leftrep - 1) >= minTrail); + } + if (hit) + { + nHyphenationPos = i; + if (rep && (i < n) && rep[i]) + { + nHyphenationPosAlt = i - pos[i]; + nHyphenationPosAltHyph = i + leftrep - pos[i]; } - } - - if (nHyphenationPos == -1) { - xRes = NULL; - } else { - if (rep && rep[nHyphenationPos]) { - // remove equal sign - char * s = rep[nHyphenationPos]; - int eq = 0; - for (; *s; s++) { - if (*s == '=') eq = 1; - if (eq) *s = *(s + 1); - } - OUString repHyphlow(rep[nHyphenationPos], strlen(rep[nHyphenationPos]), aEnc); - OUString repHyph; - switch (ct) { - case CAPTYPE_ALLCAP: - { - repHyph = makeUpperCase(repHyphlow, pCC); - break; - } - case CAPTYPE_INITCAP: - { - if (nHyphenationPosAlt == 0) { - repHyph = makeInitCap(repHyphlow, pCC); - } else { - repHyph = repHyphlow; - } - break; - } - default: - { - repHyph = repHyphlow; - break; - } } + } + + if (nHyphenationPos == -1) + { + xRes = NULL; + } + else + { + if (rep && rep[nHyphenationPos]) + { + // remove equal sign + char * s = rep[nHyphenationPos]; + int eq = 0; + for (; *s; s++) + { + if (*s == '=') eq = 1; + if (eq) *s = *(s + 1); + } + OUString repHyphlow(rep[nHyphenationPos], strlen(rep[nHyphenationPos]), eEnc); + OUString repHyph; + switch (ct) + { + case CAPTYPE_ALLCAP: + { + repHyph = makeUpperCase(repHyphlow, pCC); + break; + } + case CAPTYPE_INITCAP: + { + if (nHyphenationPosAlt == 0) + repHyph = makeInitCap(repHyphlow, pCC); + else + repHyph = repHyphlow; + break; + } + default: + { + repHyph = repHyphlow; + break; + } + } - // handle shortening - INT16 nPos = (INT16) ((nHyphenationPosAltHyph < nHyphenationPos) ? - nHyphenationPosAltHyph : nHyphenationPos); - // dicretionary hyphenation + // handle shortening + INT16 nPos = (INT16) ((nHyphenationPosAltHyph < nHyphenationPos) ? + nHyphenationPosAltHyph : nHyphenationPos); + // dicretionary hyphenation xRes = new HyphenatedWord( aWord, LocaleToLanguage( aLocale ), nPos, - aWord.replaceAt(nHyphenationPosAlt + 1, cut[nHyphenationPos], repHyph), - (INT16) nHyphenationPosAltHyph); - } else { + aWord.replaceAt(nHyphenationPosAlt + 1, cut[nHyphenationPos], repHyph), + (INT16) nHyphenationPosAltHyph); + } + else + { xRes = new HyphenatedWord( aWord, LocaleToLanguage( aLocale ), - (INT16)nHyphenationPos, aWord, (INT16) nHyphenationPos); - } + (INT16)nHyphenationPos, aWord, (INT16) nHyphenationPos); + } } - delete[] lcword; + delete[] lcword; delete[] hyphens; - if (rep) { - for(int j = 0; j < n; j++) { - if (rep[j]) free(rep[j]); - } - free(rep); + if (rep) + { + for(int j = 0; j < n; j++) + { + if (rep[j]) free(rep[j]); } - if (pos) free(pos); - if (cut) free(cut); + free(rep); + } + if (pos) free(pos); + if (cut) free(cut); return xRes; } - return NULL; + return NULL; } -Reference < XHyphenatedWord > SAL_CALL - Hyphenator::queryAlternativeSpelling( const ::rtl::OUString& /*aWord*/, - const ::com::sun::star::lang::Locale& /*aLocale*/, - sal_Int16 /*nIndex*/, - const ::com::sun::star::beans::PropertyValues& /*aProperties*/ ) - throw(::com::sun::star::lang::IllegalArgumentException, - ::com::sun::star::uno::RuntimeException) +Reference < XHyphenatedWord > SAL_CALL Hyphenator::queryAlternativeSpelling( + const ::rtl::OUString& /*aWord*/, + const ::com::sun::star::lang::Locale& /*aLocale*/, + sal_Int16 /*nIndex*/, + const ::com::sun::star::beans::PropertyValues& /*aProperties*/ ) + throw(::com::sun::star::lang::IllegalArgumentException, ::com::sun::star::uno::RuntimeException) { /* alternative spelling isn't supported by tex dictionaries */ /* XXX: OOo's extended libhjn algorithm can support alternative spellings with extended TeX dic. */ @@ -529,251 +548,262 @@ Reference < XHyphenatedWord > SAL_CALL return NULL; } -Reference< XPossibleHyphens > SAL_CALL - Hyphenator::createPossibleHyphens( const ::rtl::OUString& aWord, - const ::com::sun::star::lang::Locale& aLocale, - const ::com::sun::star::beans::PropertyValues& aProperties ) - throw(::com::sun::star::lang::IllegalArgumentException, - ::com::sun::star::uno::RuntimeException) - +Reference< XPossibleHyphens > SAL_CALL Hyphenator::createPossibleHyphens( const ::rtl::OUString& aWord, + const ::com::sun::star::lang::Locale& aLocale, + const ::com::sun::star::beans::PropertyValues& aProperties ) + throw(::com::sun::star::lang::IllegalArgumentException, ::com::sun::star::uno::RuntimeException) { - int wordlen; - char *hyphens; - char *lcword; - int k; + int wordlen; + char *hyphens; + char *lcword; + int k; - PropertyHelper_Hyphen & rHelper = GetPropHelper(); - rHelper.SetTmpPropVals(aProperties); - sal_Int16 minTrail = rHelper.GetMinTrailing(); - sal_Int16 minLead = rHelper.GetMinLeading(); + PropertyHelper_Hyphen & rHelper = GetPropHelper(); + rHelper.SetTmpPropVals(aProperties); + sal_Int16 minTrail = rHelper.GetMinTrailing(); + sal_Int16 minLead = rHelper.GetMinLeading(); - HyphenDict *dict = NULL; - rtl_TextEncoding aEnc = 0; - CharClass* pCC = NULL; + HyphenDict *dict = NULL; + rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW; + CharClass* pCC = NULL; - Reference< XPossibleHyphens > xRes; + Reference< XPossibleHyphens > xRes; - k = -1; - for (int j = 0; j < numdict; j++) - if (aLocale == aDicts[j].aLoc) k = j; + k = -1; + for (int j = 0; j < numdict; j++) + { + if (aLocale == aDicts[j].aLoc) k = j; + } + // if we have a hyphenation dictionary matching this locale + if (k != -1) + { + // if this dictioanry has not been loaded yet do that + if (!aDicts[k].aPtr) + { + OUString DictFN = aDicts[k].aName + A2OU(".dic"); + OUString dictpath; - // if we have a hyphenation dictionary matching this locale - if (k != -1) { + osl::FileBase::getSystemPathFromFileURL( DictFN, dictpath ); + OString sTmp( OU2ENC( dictpath, osl_getThreadTextEncoding() ) ); - // if this dictioanry has not been loaded yet do that - if (!aDicts[k].aPtr) { +#if defined(WNT) + // workaround for Windows specifc problem that the + // path length in calls to 'fopen' is limted to somewhat + // about 120+ characters which will usually be exceed when + // using dictionaries as extensions. + sTmp = Win_GetShortPathName( dictpath ); +#endif - OUString DictFN = aDicts[k].aName + A2OU(".dic"); - OUString dictpath; + if ( ( dict = hnj_hyphen_load ( sTmp.getStr()) ) == NULL ) + { + fprintf(stderr, "Couldn't find file %s and %s\n", sTmp.getStr(), OU2ENC(dictpath, osl_getThreadTextEncoding()) ); + return NULL; + } + aDicts[k].aPtr = dict; + aDicts[k].eEnc = getTextEncodingFromCharset(dict->cset); + } - osl::FileBase::getSystemPathFromFileURL( DictFN, dictpath ); - OString sTmp( OU2ENC( dictpath, osl_getThreadTextEncoding() ) ); + // other wise hyphenate the word with that dictionary + dict = aDicts[k].aPtr; + eEnc = aDicts[k].eEnc; + pCC = aDicts[k].apCC; -#if defined(WNT) - // workaround for Windows specifc problem that the - // path length in calls to 'fopen' is limted to somewhat - // about 120+ characters which will usually be exceed when - // using dictionaries as extensions. - sTmp = Win_GetShortPathName( dictpath ); -#endif + // we don't want to work with a default text encoding since following incorrect + // results may occur only for specific text and thus may be hard to notice. + // Thus better always make a clean exit here if the text encoding is in question. + // Hopefully something not working at all will raise proper attention quickly. ;-) + DBG_ASSERT( eEnc != RTL_TEXTENCODING_DONTKNOW, "failed to get text encoding! (maybe incorrect encoding string in file)" ); + if (eEnc == RTL_TEXTENCODING_DONTKNOW) + return NULL; - if ( ( dict = hnj_hyphen_load ( sTmp.getStr()) ) == NULL ) + // first handle smart quotes both single and double + OUStringBuffer rBuf(aWord); + sal_Int32 nc = rBuf.getLength(); + sal_Unicode ch; + for (sal_Int32 ix=0; ix < nc; ix++) { - fprintf(stderr, "Couldn't find file %s and %s\n", sTmp.getStr(), OU2ENC(dictpath, osl_getThreadTextEncoding()) ); - return NULL; + ch = rBuf.charAt(ix); + if ((ch == 0x201C) || (ch == 0x201D)) + rBuf.setCharAt(ix,(sal_Unicode)0x0022); + if ((ch == 0x2018) || (ch == 0x2019)) + rBuf.setCharAt(ix,(sal_Unicode)0x0027); } - aDicts[k].aPtr = dict; - aDicts[k].aEnc = rtl_getTextEncodingFromUnixCharset(dict->cset); - if (aDicts[k].aEnc == RTL_TEXTENCODING_DONTKNOW) { - if (strcmp("ISCII-DEVANAGARI", dict->cset) == 0) { - aDicts[k].aEnc = RTL_TEXTENCODING_ISCII_DEVANAGARI; - } else if (strcmp("UTF-8", dict->cset) == 0) { - aDicts[k].aEnc = RTL_TEXTENCODING_UTF8; + OUString nWord(rBuf.makeStringAndClear()); + + // now convert word to all lowercase for pattern recognition + OUString nTerm(makeLowerCase(nWord, pCC)); + + // now convert word to needed encoding + OString encWord(OU2ENC(nTerm,eEnc)); + + wordlen = encWord.getLength(); + lcword = new char[wordlen+1]; + hyphens = new char[wordlen+5]; + char ** rep = NULL; // replacements of discretionary hyphenation + int * pos = NULL; // array of [hyphenation point] minus [deletion position] + int * cut = NULL; // length of deletions in original word + + // copy converted word into simple char buffer + strcpy(lcword,encWord.getStr()); + + // first remove any trailing periods + int n = wordlen-1; + while((n >=0) && (lcword[n] == '.')) + n--; + n++; + // fprintf(stderr,"hyphenate... %s\n",lcword); fflush(stderr); + if (n > 0) + { + const bool bFailed = 0 != hnj_hyphen_hyphenate3(dict, lcword, n, hyphens, NULL, + &rep, &pos, &cut, minLead, minTrail, + Max(dict->clhmin, Max(dict->clhmin, 2) + Max(0, minLead - Max(dict->lhmin, 2))), + Max(dict->crhmin, Max(dict->crhmin, 2) + Max(0, minTrail - Max(dict->rhmin, 2))) ); + if (bFailed) + { + delete[] hyphens; + delete[] lcword; + + if (rep) + { + for(int j = 0; j < n; j++) + { + if (rep[j]) free(rep[j]); + } + free(rep); + } + if (pos) free(pos); + if (cut) free(cut); + + return NULL; } - } - } - - // other wise hyphenate the word with that dictionary - dict = aDicts[k].aPtr; - aEnc = aDicts[k].aEnc; - pCC = aDicts[k].apCC; - - // first handle smart quotes both single and double - OUStringBuffer rBuf(aWord); - sal_Int32 nc = rBuf.getLength(); - sal_Unicode ch; - for (sal_Int32 ix=0; ix < nc; ix++) { - ch = rBuf.charAt(ix); - if ((ch == 0x201C) || (ch == 0x201D)) rBuf.setCharAt(ix,(sal_Unicode)0x0022); - if ((ch == 0x2018) || (ch == 0x2019)) rBuf.setCharAt(ix,(sal_Unicode)0x0027); - } - OUString nWord(rBuf.makeStringAndClear()); - - // now convert word to all lowercase for pattern recognition - OUString nTerm(makeLowerCase(nWord, pCC)); - - // now convert word to needed encoding - OString encWord(OU2ENC(nTerm,aEnc)); - - wordlen = encWord.getLength(); - lcword = new char[wordlen+1]; - hyphens = new char[wordlen+5]; - char ** rep = NULL; // replacements of discretionary hyphenation - int * pos = NULL; // array of [hyphenation point] minus [deletion position] - int * cut = NULL; // length of deletions in original word - - // copy converted word into simple char buffer - strcpy(lcword,encWord.getStr()); - - // first remove any trailing periods - int n = wordlen-1; - while((n >=0) && (lcword[n] == '.')) n--; - n++; - // fprintf(stderr,"hyphenate... %s\n",lcword); fflush(stderr); - if (n > 0) { - if (hnj_hyphen_hyphenate3(dict, lcword, n, hyphens, NULL, &rep, &pos, &cut, - minLead, minTrail, Max(dict->clhmin, Max(dict->clhmin, 2) + Max(0, minLead - Max(dict->lhmin, 2))), - Max(dict->crhmin, Max(dict->crhmin, 2) + Max(0, minTrail - Max(dict->rhmin, 2))))) - { - delete[] hyphens; - delete[] lcword; - - if (rep) { - for(int j = 0; j < n; j++) { - if (rep[j]) free(rep[j]); - } - free(rep); - } - if (pos) free(pos); - if (cut) free(cut); - - return NULL; - } - } - // now backfill hyphens[] for any removed periods - for (int c = n; c < wordlen; c++) hyphens[c] = '0'; - hyphens[wordlen] = '\0'; - // fprintf(stderr,"... %s\n",hyphens); fflush(stderr); - - INT16 nHyphCount = 0; - INT16 i; - - for ( i = 0; i < encWord.getLength(); i++) - if (hyphens[i]&1 && (!rep || !rep[i])) - nHyphCount++; - - Sequence< INT16 > aHyphPos(nHyphCount); - INT16 *pPos = aHyphPos.getArray(); - OUStringBuffer hyphenatedWordBuffer; - OUString hyphenatedWord; - nHyphCount = 0; - - for (i = 0; i < nWord.getLength(); i++) { - hyphenatedWordBuffer.append(aWord[i]); - // hyphenation position (not alternative) - if (hyphens[i]&1 && (!rep || !rep[i])) { - pPos[nHyphCount] = i; - hyphenatedWordBuffer.append(sal_Unicode('=')); - nHyphCount++; - } - } - - hyphenatedWord = hyphenatedWordBuffer.makeStringAndClear(); - //fprintf(stderr,"result is %s\n",OU2A(hyphenatedWord)); - //fflush(stderr); - - xRes = new PossibleHyphens( aWord, LocaleToLanguage( aLocale ), - hyphenatedWord, aHyphPos ); - - delete[] hyphens; - delete[] lcword; - - if (rep) { - for(int j = 0; j < n; j++) { - if (rep[j]) free(rep[j]); - } - free(rep); - } - if (pos) free(pos); - if (cut) free(cut); - - return xRes; - } + } + // now backfill hyphens[] for any removed periods + for (int c = n; c < wordlen; c++) + hyphens[c] = '0'; + hyphens[wordlen] = '\0'; + // fprintf(stderr,"... %s\n",hyphens); fflush(stderr); - return NULL; + INT16 nHyphCount = 0; + INT16 i; + + for ( i = 0; i < encWord.getLength(); i++) + { + if (hyphens[i]&1 && (!rep || !rep[i])) + nHyphCount++; + } + + Sequence< INT16 > aHyphPos(nHyphCount); + INT16 *pPos = aHyphPos.getArray(); + OUStringBuffer hyphenatedWordBuffer; + OUString hyphenatedWord; + nHyphCount = 0; + + for (i = 0; i < nWord.getLength(); i++) + { + hyphenatedWordBuffer.append(aWord[i]); + // hyphenation position (not alternative) + if (hyphens[i]&1 && (!rep || !rep[i])) + { + pPos[nHyphCount] = i; + hyphenatedWordBuffer.append(sal_Unicode('=')); + nHyphCount++; + } + } + + hyphenatedWord = hyphenatedWordBuffer.makeStringAndClear(); + //fprintf(stderr,"result is %s\n",OU2A(hyphenatedWord)); + //fflush(stderr); + + xRes = new PossibleHyphens( aWord, LocaleToLanguage( aLocale ), + hyphenatedWord, aHyphPos ); + + delete[] hyphens; + delete[] lcword; + + if (rep) + { + for(int j = 0; j < n; j++) + { + if (rep[j]) free(rep[j]); + } + free(rep); + } + if (pos) free(pos); + if (cut) free(cut); + return xRes; + } + + return NULL; } sal_uInt16 SAL_CALL Hyphenator::capitalType(const OUString& aTerm, CharClass * pCC) { - sal_Int32 tlen = aTerm.getLength(); - if ((pCC) && (tlen)) { - String aStr(aTerm); - sal_Int32 nc = 0; - for (xub_StrLen tindex = 0; tindex < tlen; tindex++) { - if (pCC->getCharacterType(aStr,tindex) & - ::com::sun::star::i18n::KCharacterType::UPPER) nc++; - } - - if (nc == 0) return (sal_uInt16) CAPTYPE_NOCAP; - - if (nc == tlen) return (sal_uInt16) CAPTYPE_ALLCAP; + sal_Int32 tlen = aTerm.getLength(); + if ((pCC) && (tlen)) + { + String aStr(aTerm); + sal_Int32 nc = 0; + for (xub_StrLen tindex = 0; tindex < tlen; tindex++) + { + if (pCC->getCharacterType(aStr,tindex) & ::com::sun::star::i18n::KCharacterType::UPPER) + nc++; + } - if ((nc == 1) && (pCC->getCharacterType(aStr,0) & - ::com::sun::star::i18n::KCharacterType::UPPER)) - return (sal_uInt16) CAPTYPE_INITCAP; + if (nc == 0) + return (sal_uInt16) CAPTYPE_NOCAP; + if (nc == tlen) + return (sal_uInt16) CAPTYPE_ALLCAP; + if ((nc == 1) && (pCC->getCharacterType(aStr,0) & ::com::sun::star::i18n::KCharacterType::UPPER)) + return (sal_uInt16) CAPTYPE_INITCAP; - return (sal_uInt16) CAPTYPE_MIXED; + return (sal_uInt16) CAPTYPE_MIXED; } - return (sal_uInt16) CAPTYPE_UNKNOWN; + return (sal_uInt16) CAPTYPE_UNKNOWN; } OUString SAL_CALL Hyphenator::makeLowerCase(const OUString& aTerm, CharClass * pCC) { - if (pCC) - return pCC->toLower_rtl(aTerm, 0, aTerm.getLength()); - return aTerm; + if (pCC) + return pCC->toLower_rtl(aTerm, 0, aTerm.getLength()); + return aTerm; } OUString SAL_CALL Hyphenator::makeUpperCase(const OUString& aTerm, CharClass * pCC) { - if (pCC) - return pCC->toUpper_rtl(aTerm, 0, aTerm.getLength()); - return aTerm; + if (pCC) + return pCC->toUpper_rtl(aTerm, 0, aTerm.getLength()); + return aTerm; } OUString SAL_CALL Hyphenator::makeInitCap(const OUString& aTerm, CharClass * pCC) { - sal_Int32 tlen = aTerm.getLength(); - if ((pCC) && (tlen)) { - OUString bTemp = aTerm.copy(0,1); - if (tlen > 1) - return ( pCC->toUpper_rtl(bTemp, 0, 1) - + pCC->toLower_rtl(aTerm,1,(tlen-1)) ); - - return pCC->toUpper_rtl(bTemp, 0, 1); + sal_Int32 tlen = aTerm.getLength(); + if ((pCC) && (tlen)) + { + OUString bTemp = aTerm.copy(0,1); + if (tlen > 1) + return ( pCC->toUpper_rtl(bTemp, 0, 1) + pCC->toLower_rtl(aTerm,1,(tlen-1)) ); + + return pCC->toUpper_rtl(bTemp, 0, 1); } - return aTerm; + return aTerm; } - - Reference< XInterface > SAL_CALL Hyphenator_CreateInstance( - const Reference< XMultiServiceFactory > & /*rSMgr*/ ) + const Reference< XMultiServiceFactory > & /*rSMgr*/ ) throw(Exception) { - Reference< XInterface > xService = (cppu::OWeakObject*) new Hyphenator; return xService; } -sal_Bool SAL_CALL - Hyphenator::addLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) +sal_Bool SAL_CALL Hyphenator::addLinguServiceEventListener( + const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -787,9 +817,8 @@ sal_Bool SAL_CALL } -sal_Bool SAL_CALL - Hyphenator::removeLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) +sal_Bool SAL_CALL Hyphenator::removeLinguServiceEventListener( + const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -804,8 +833,7 @@ sal_Bool SAL_CALL } -OUString SAL_CALL - Hyphenator::getServiceDisplayName( const Locale& /*rLocale*/ ) +OUString SAL_CALL Hyphenator::getServiceDisplayName( const Locale& /*rLocale*/ ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -813,8 +841,7 @@ OUString SAL_CALL } -void SAL_CALL - Hyphenator::initialize( const Sequence< Any >& rArguments ) +void SAL_CALL Hyphenator::initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -836,16 +863,15 @@ void SAL_CALL xPropHelper = pPropHelper; pPropHelper->AddAsPropListener(); //! after a reference is established } - else { + else + { DBG_ERROR( "wrong number of arguments in sequence" ); } - } } -void SAL_CALL - Hyphenator::dispose() +void SAL_CALL Hyphenator::dispose() throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -859,8 +885,7 @@ void SAL_CALL } -void SAL_CALL - Hyphenator::addEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL Hyphenator::addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -870,8 +895,7 @@ void SAL_CALL } -void SAL_CALL - Hyphenator::removeEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL Hyphenator::removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -927,32 +951,6 @@ Sequence< OUString > Hyphenator::getSupportedServiceNames_Static() return aSNS; } - -sal_Bool SAL_CALL Hyphenator_writeInfo( - void * /*pServiceManager*/, registry::XRegistryKey * pRegistryKey ) -{ - - try - { - String aImpl( '/' ); - aImpl += Hyphenator::getImplementationName_Static().getStr(); - aImpl.AppendAscii( "/UNO/SERVICES" ); - Reference< registry::XRegistryKey > xNewKey = - pRegistryKey->createKey( aImpl ); - Sequence< OUString > aServices = - Hyphenator::getSupportedServiceNames_Static(); - for( INT32 i = 0; i < aServices.getLength(); i++ ) - xNewKey->createKey( aServices.getConstArray()[i] ); - - return sal_True; - } - catch(Exception &) - { - return sal_False; - } -} - - void * SAL_CALL Hyphenator_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, void * ) { diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.hxx b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.hxx index 031217914754..e20b4f58f589 100644 --- a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.hxx +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/hyphenimp.hxx @@ -65,7 +65,7 @@ struct HDInfo { HyphenDict * aPtr; OUString aName; Locale aLoc; - rtl_TextEncoding aEnc; + rtl_TextEncoding eEnc; CharClass * apCC; }; @@ -83,12 +83,12 @@ class Hyphenator : > { Sequence< Locale > aSuppLocales; - HDInfo * aDicts; - sal_Int32 numdict; + HDInfo * aDicts; + sal_Int32 numdict; ::cppu::OInterfaceContainerHelper aEvtListeners; Reference< XPropertyChangeListener > xPropHelper; - Reference< XMultiServiceFactory > rSMgr; + Reference< XMultiServiceFactory > rSMgr; linguistic::PropertyHelper_Hyphen * pPropHelper; BOOL bDisposing; @@ -108,88 +108,38 @@ public: virtual ~Hyphenator(); // XSupportedLocales (for XHyphenator) - virtual Sequence< Locale > SAL_CALL getLocales() - throw(RuntimeException); - virtual sal_Bool SAL_CALL hasLocale( const Locale& rLocale ) - throw(RuntimeException); + virtual Sequence< Locale > SAL_CALL getLocales() throw(RuntimeException); + virtual sal_Bool SAL_CALL hasLocale( const Locale& rLocale ) throw(RuntimeException); // XHyphenator - virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XHyphenatedWord > SAL_CALL - hyphenate( const ::rtl::OUString& aWord, - const ::com::sun::star::lang::Locale& aLocale, - sal_Int16 nMaxLeading, - const ::com::sun::star::beans::PropertyValues& aProperties ) - throw(::com::sun::star::lang::IllegalArgumentException, - ::com::sun::star::uno::RuntimeException); - - virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XHyphenatedWord > SAL_CALL - queryAlternativeSpelling( const ::rtl::OUString& aWord, - const ::com::sun::star::lang::Locale& aLocale, - sal_Int16 nIndex, - const ::com::sun::star::beans::PropertyValues& aProperties ) - throw(::com::sun::star::lang::IllegalArgumentException, - ::com::sun::star::uno::RuntimeException); - - virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XPossibleHyphens > SAL_CALL - createPossibleHyphens( const ::rtl::OUString& aWord, - const ::com::sun::star::lang::Locale& aLocale, - const ::com::sun::star::beans::PropertyValues& aProperties ) - throw(::com::sun::star::lang::IllegalArgumentException, - ::com::sun::star::uno::RuntimeException); + virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XHyphenatedWord > SAL_CALL hyphenate( const ::rtl::OUString& aWord, const ::com::sun::star::lang::Locale& aLocale, sal_Int16 nMaxLeading, const ::com::sun::star::beans::PropertyValues& aProperties ) throw(::com::sun::star::lang::IllegalArgumentException, ::com::sun::star::uno::RuntimeException); + virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XHyphenatedWord > SAL_CALL queryAlternativeSpelling( const ::rtl::OUString& aWord, const ::com::sun::star::lang::Locale& aLocale, sal_Int16 nIndex, const ::com::sun::star::beans::PropertyValues& aProperties ) throw(::com::sun::star::lang::IllegalArgumentException, ::com::sun::star::uno::RuntimeException); + virtual ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XPossibleHyphens > SAL_CALL createPossibleHyphens( const ::rtl::OUString& aWord, const ::com::sun::star::lang::Locale& aLocale, const ::com::sun::star::beans::PropertyValues& aProperties ) throw(::com::sun::star::lang::IllegalArgumentException, ::com::sun::star::uno::RuntimeException); // XLinguServiceEventBroadcaster - virtual sal_Bool SAL_CALL - addLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); - virtual sal_Bool SAL_CALL - removeLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); + virtual sal_Bool SAL_CALL addLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); + virtual sal_Bool SAL_CALL removeLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); // XServiceDisplayName - virtual OUString SAL_CALL - getServiceDisplayName( const Locale& rLocale ) - throw(RuntimeException); + virtual OUString SAL_CALL getServiceDisplayName( const Locale& rLocale ) throw(RuntimeException); // XInitialization - virtual void SAL_CALL - initialize( const Sequence< Any >& rArguments ) - throw(Exception, RuntimeException); + virtual void SAL_CALL initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException); // XComponent - virtual void SAL_CALL - dispose() - throw(RuntimeException); - virtual void SAL_CALL - addEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - virtual void SAL_CALL - removeEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - - //////////////////////////////////////////////////////////// - // Service specific part - // + virtual void SAL_CALL dispose() throw(RuntimeException); + virtual void SAL_CALL addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); + virtual void SAL_CALL removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); // XServiceInfo - virtual OUString SAL_CALL - getImplementationName() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - supportsService( const OUString& rServiceName ) - throw(RuntimeException); - virtual Sequence< OUString > SAL_CALL - getSupportedServiceNames() - throw(RuntimeException); - - - static inline OUString - getImplementationName_Static() throw(); - static Sequence< OUString > - getSupportedServiceNames_Static() throw(); + virtual OUString SAL_CALL getImplementationName() throw(RuntimeException); + virtual sal_Bool SAL_CALL supportsService( const OUString& rServiceName ) throw(RuntimeException); + virtual Sequence< OUString > SAL_CALL getSupportedServiceNames() throw(RuntimeException); + static inline OUString getImplementationName_Static() throw(); + static Sequence< OUString > getSupportedServiceNames_Static() throw(); + private: sal_uInt16 SAL_CALL capitalType(const OUString&, CharClass *); diff --git a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/makefile.mk b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/makefile.mk index f3626c70312b..6f767d8bfa9e 100644 --- a/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/makefile.mk +++ b/lingucomponent/source/hyphenator/altlinuxhyph/hyphen/makefile.mk @@ -91,3 +91,11 @@ DEF1EXPORTFILE= exports.dxp .INCLUDE : target.mk + +ALLTAR : $(MISC)/hyphen.component + +$(MISC)/hyphen.component .ERRREMOVE : $(SOLARENV)/bin/createcomponent.xslt \ + hyphen.component + $(XSLTPROC) --nonet --stringparam uri \ + '$(COMPONENTPREFIX_BASIS_NATIVE)$(SHL1TARGETN:f)' -o $@ \ + $(SOLARENV)/bin/createcomponent.xslt hyphen.component diff --git a/lingucomponent/source/languageguessing/guesslang.component b/lingucomponent/source/languageguessing/guesslang.component new file mode 100644 index 000000000000..633a489c38fa --- /dev/null +++ b/lingucomponent/source/languageguessing/guesslang.component @@ -0,0 +1,34 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!--********************************************************************** +* +* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +* +* Copyright 2000, 2010 Oracle and/or its affiliates. +* +* OpenOffice.org - a multi-platform office productivity suite +* +* This file is part of OpenOffice.org. +* +* OpenOffice.org is free software: you can redistribute it and/or modify +* it under the terms of the GNU Lesser General Public License version 3 +* only, as published by the Free Software Foundation. +* +* OpenOffice.org is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU Lesser General Public License version 3 for more details +* (a copy is included in the LICENSE file that accompanied this code). +* +* You should have received a copy of the GNU Lesser General Public License +* version 3 along with OpenOffice.org. If not, see +* <http://www.openoffice.org/license.html> +* for a copy of the LGPLv3 License. +* +**********************************************************************--> + +<component loader="com.sun.star.loader.SharedLibrary" + xmlns="http://openoffice.org/2010/uno-components"> + <implementation name="com.sun.star.lingu2.LanguageGuessing"> + <service name="com.sun.star.linguistic2.LanguageGuessing"/> + </implementation> +</component> diff --git a/lingucomponent/source/languageguessing/guesslang.cxx b/lingucomponent/source/languageguessing/guesslang.cxx index c8486c1bc471..baac0fd7e856 100644 --- a/lingucomponent/source/languageguessing/guesslang.cxx +++ b/lingucomponent/source/languageguessing/guesslang.cxx @@ -465,13 +465,6 @@ void SAL_CALL component_getImplementationEnvironment( *ppEnvTypeName = CPPU_CURRENT_LANGUAGE_BINDING_NAME; } -sal_Bool SAL_CALL component_writeInfo( - XMultiServiceFactory * xMgr, registry::XRegistryKey * xRegistry ) -{ - return ::cppu::component_writeInfoHelper( - xMgr, xRegistry, s_component_entries ); -} - void * SAL_CALL component_getFactory( sal_Char const * implName, lang::XMultiServiceFactory * xMgr, registry::XRegistryKey * xRegistry ) diff --git a/lingucomponent/source/languageguessing/makefile.mk b/lingucomponent/source/languageguessing/makefile.mk index ebad4076b3ed..624ccba3c334 100644 --- a/lingucomponent/source/languageguessing/makefile.mk +++ b/lingucomponent/source/languageguessing/makefile.mk @@ -78,3 +78,11 @@ DEF1NAME =$(SHL1TARGET) .INCLUDE : target.mk + +ALLTAR : $(MISC)/guesslang.component + +$(MISC)/guesslang.component .ERRREMOVE : $(SOLARENV)/bin/createcomponent.xslt \ + guesslang.component + $(XSLTPROC) --nonet --stringparam uri \ + '$(COMPONENTPREFIX_BASIS_NATIVE)$(SHL1TARGETN:f)' -o $@ \ + $(SOLARENV)/bin/createcomponent.xslt guesslang.component diff --git a/lingucomponent/source/lingutil/lingutil.cxx b/lingucomponent/source/lingutil/lingutil.cxx index ee7d71de4435..14253fca5cd3 100644 --- a/lingucomponent/source/lingutil/lingutil.cxx +++ b/lingucomponent/source/lingutil/lingutil.cxx @@ -50,6 +50,7 @@ #include <unotools/pathoptions.hxx> #include <rtl/ustring.hxx> #include <rtl/string.hxx> +#include <rtl/tencinfo.h> #include <linguistic/misc.hxx> #include <set> @@ -268,5 +269,25 @@ void MergeNewStyleDicsAndOldStyleDics( } } + +rtl_TextEncoding getTextEncodingFromCharset(const sal_Char* pCharset) +{ + // default result: used to indicate that we failed to get the proper encoding + rtl_TextEncoding eRet = RTL_TEXTENCODING_DONTKNOW; + + if (pCharset) + { + eRet = rtl_getTextEncodingFromMimeCharset(pCharset); + if (eRet == RTL_TEXTENCODING_DONTKNOW) + eRet = rtl_getTextEncodingFromUnixCharset(pCharset); + if (eRet == RTL_TEXTENCODING_DONTKNOW) + { + if (strcmp("ISCII-DEVANAGARI", pCharset) == 0) + eRet = RTL_TEXTENCODING_ISCII_DEVANAGARI; + } + } + return eRet; +} + ////////////////////////////////////////////////////////////////////// diff --git a/lingucomponent/source/lingutil/lingutil.hxx b/lingucomponent/source/lingutil/lingutil.hxx index 8b45b1f509ad..82d2e646edfc 100644 --- a/lingucomponent/source/lingutil/lingutil.hxx +++ b/lingucomponent/source/lingutil/lingutil.hxx @@ -101,5 +101,13 @@ void MergeNewStyleDicsAndOldStyleDics( std::list< SvtLinguConfigDictionaryEntry /////////////////////////////////////////////////////////////////////////// + +//Find an encoding from a charset string, using +//rtl_getTextEncodingFromMimeCharset and falling back to +//rtl_getTextEncodingFromUnixCharset with the addition of +//ISCII-DEVANAGARI. On failure will return final fallback of +//RTL_TEXTENCODING_ISO_8859_1 +rtl_TextEncoding getTextEncodingFromCharset(const sal_Char* pCharset); + #endif diff --git a/lingucomponent/source/spellcheck/macosxspell/MacOSXSpell.component b/lingucomponent/source/spellcheck/macosxspell/MacOSXSpell.component new file mode 100644 index 000000000000..2f2f9e102087 --- /dev/null +++ b/lingucomponent/source/spellcheck/macosxspell/MacOSXSpell.component @@ -0,0 +1,34 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!--********************************************************************** +* +* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +* +* Copyright 2000, 2010 Oracle and/or its affiliates. +* +* OpenOffice.org - a multi-platform office productivity suite +* +* This file is part of OpenOffice.org. +* +* OpenOffice.org is free software: you can redistribute it and/or modify +* it under the terms of the GNU Lesser General Public License version 3 +* only, as published by the Free Software Foundation. +* +* OpenOffice.org is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU Lesser General Public License version 3 for more details +* (a copy is included in the LICENSE file that accompanied this code). +* +* You should have received a copy of the GNU Lesser General Public License +* version 3 along with OpenOffice.org. If not, see +* <http://www.openoffice.org/license.html> +* for a copy of the LGPLv3 License. +* +**********************************************************************--> + +<component loader="com.sun.star.loader.SharedLibrary" + xmlns="http://openoffice.org/2010/uno-components"> + <implementation name="org.openoffice.lingu.MacOSXSpellChecker"> + <service name="com.sun.star.linguistic2.SpellChecker"/> + </implementation> +</component> diff --git a/lingucomponent/source/spellcheck/macosxspell/macreg.cxx b/lingucomponent/source/spellcheck/macosxspell/macreg.cxx index b60ffffe42e9..9df90f79cca7 100644 --- a/lingucomponent/source/spellcheck/macosxspell/macreg.cxx +++ b/lingucomponent/source/spellcheck/macosxspell/macreg.cxx @@ -42,9 +42,6 @@ using namespace com::sun::star::registry; // declaration of external RegEntry-functions defined by the service objects // -extern sal_Bool SAL_CALL MacSpellChecker_writeInfo( - void * /*pServiceManager*/, XRegistryKey * pRegistryKey ); - extern void * SAL_CALL MacSpellChecker_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, @@ -57,12 +54,6 @@ extern void * SAL_CALL MacSpellChecker_getFactory( extern "C" { -sal_Bool SAL_CALL component_writeInfo( - void * pServiceManager, XRegistryKey * pRegistryKey ) -{ - return MacSpellChecker_writeInfo( pServiceManager, pRegistryKey ); -} - void SAL_CALL component_getImplementationEnvironment( const sal_Char ** ppEnvTypeName, uno_Environment ** /*ppEnv*/ ) { diff --git a/lingucomponent/source/spellcheck/macosxspell/macspellimp.cxx b/lingucomponent/source/spellcheck/macosxspell/macspellimp.cxx index 70996793c186..002f1dec0b36 100644 --- a/lingucomponent/source/spellcheck/macosxspell/macspellimp.cxx +++ b/lingucomponent/source/spellcheck/macosxspell/macspellimp.cxx @@ -644,32 +644,6 @@ Sequence< OUString > MacSpellChecker::getSupportedServiceNames_Static() return aSNS; } - -sal_Bool SAL_CALL MacSpellChecker_writeInfo( - void * /*pServiceManager*/, registry::XRegistryKey * pRegistryKey ) -{ - - try - { - String aImpl( '/' ); - aImpl += MacSpellChecker::getImplementationName_Static().getStr(); - aImpl.AppendAscii( "/UNO/SERVICES" ); - Reference< registry::XRegistryKey > xNewKey = - pRegistryKey->createKey( aImpl ); - Sequence< OUString > aServices = - MacSpellChecker::getSupportedServiceNames_Static(); - for( INT32 i = 0; i < aServices.getLength(); i++ ) - xNewKey->createKey( aServices.getConstArray()[i] ); - - return sal_True; - } - catch(Exception &) - { - return sal_False; - } -} - - void * SAL_CALL MacSpellChecker_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, void * ) { diff --git a/lingucomponent/source/spellcheck/macosxspell/macspellimp.hxx b/lingucomponent/source/spellcheck/macosxspell/macspellimp.hxx index b3cfce92fd8b..fc1906e18025 100644 --- a/lingucomponent/source/spellcheck/macosxspell/macspellimp.hxx +++ b/lingucomponent/source/spellcheck/macosxspell/macspellimp.hxx @@ -75,14 +75,14 @@ class MacSpellChecker : XServiceDisplayName > { - Sequence< Locale > aSuppLocales; + Sequence< Locale > aSuppLocales; // Hunspell ** aDicts; - rtl_TextEncoding * aDEncs; - Locale * aDLocs; - OUString * aDNames; - sal_Int32 numdict; - NSSpellChecker * macSpell; - int macTag; //unique tag for this doc + rtl_TextEncoding * aDEncs; + Locale * aDLocs; + OUString * aDNames; + sal_Int32 numdict; + NSSpellChecker * macSpell; + int macTag; //unique tag for this doc ::cppu::OInterfaceContainerHelper aEvtListeners; Reference< XPropertyChangeListener > xPropHelper; @@ -100,84 +100,43 @@ class MacSpellChecker : } INT16 GetSpellFailure( const OUString &rWord, const Locale &rLocale ); - Reference< XSpellAlternatives > - GetProposals( const OUString &rWord, const Locale &rLocale ); + Reference< XSpellAlternatives > GetProposals( const OUString &rWord, const Locale &rLocale ); public: MacSpellChecker(); virtual ~MacSpellChecker(); // XSupportedLocales (for XSpellChecker) - virtual Sequence< Locale > SAL_CALL - getLocales() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - hasLocale( const Locale& rLocale ) - throw(RuntimeException); + virtual Sequence< Locale > SAL_CALL getLocales() throw(RuntimeException); + virtual sal_Bool SAL_CALL hasLocale( const Locale& rLocale ) throw(RuntimeException); // XSpellChecker - virtual sal_Bool SAL_CALL - isValid( const OUString& rWord, const Locale& rLocale, - const PropertyValues& rProperties ) - throw(IllegalArgumentException, - RuntimeException); - virtual Reference< XSpellAlternatives > SAL_CALL - spell( const OUString& rWord, const Locale& rLocale, - const PropertyValues& rProperties ) - throw(IllegalArgumentException, - RuntimeException); + virtual sal_Bool SAL_CALL isValid( const OUString& rWord, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException); + virtual Reference< XSpellAlternatives > SAL_CALL spell( const OUString& rWord, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException); // XLinguServiceEventBroadcaster - virtual sal_Bool SAL_CALL - addLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); - virtual sal_Bool SAL_CALL - removeLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); + virtual sal_Bool SAL_CALL addLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); + virtual sal_Bool SAL_CALL removeLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); // XServiceDisplayName - virtual OUString SAL_CALL - getServiceDisplayName( const Locale& rLocale ) - throw(RuntimeException); + virtual OUString SAL_CALL getServiceDisplayName( const Locale& rLocale ) throw(RuntimeException); // XInitialization - virtual void SAL_CALL - initialize( const Sequence< Any >& rArguments ) - throw(Exception, RuntimeException); + virtual void SAL_CALL initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException); // XComponent - virtual void SAL_CALL - dispose() - throw(RuntimeException); - virtual void SAL_CALL - addEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - virtual void SAL_CALL - removeEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - - //////////////////////////////////////////////////////////// - // Service specific part - // + virtual void SAL_CALL dispose() throw(RuntimeException); + virtual void SAL_CALL addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); + virtual void SAL_CALL removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); // XServiceInfo - virtual OUString SAL_CALL - getImplementationName() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - supportsService( const OUString& rServiceName ) - throw(RuntimeException); - virtual Sequence< OUString > SAL_CALL - getSupportedServiceNames() - throw(RuntimeException); - - - static inline OUString - getImplementationName_Static() throw(); - static Sequence< OUString > - getSupportedServiceNames_Static() throw(); + virtual OUString SAL_CALL getImplementationName() throw(RuntimeException); + virtual sal_Bool SAL_CALL supportsService( const OUString& rServiceName ) throw(RuntimeException); + virtual Sequence< OUString > SAL_CALL getSupportedServiceNames() throw(RuntimeException); + + + static inline OUString getImplementationName_Static() throw(); + static Sequence< OUString > getSupportedServiceNames_Static() throw(); }; inline OUString MacSpellChecker::getImplementationName_Static() throw() diff --git a/lingucomponent/source/spellcheck/macosxspell/makefile.mk b/lingucomponent/source/spellcheck/macosxspell/makefile.mk index 6414560e0f4a..4e88b808ddc0 100644 --- a/lingucomponent/source/spellcheck/macosxspell/makefile.mk +++ b/lingucomponent/source/spellcheck/macosxspell/makefile.mk @@ -91,3 +91,11 @@ SHL1VERSIONMAP=$(SOLARENV)/src/component.map dummy: @echo " Nothing to build for GUIBASE=$(GUIBASE)" .ENDIF + +ALLTAR : $(MISC)/MacOSXSpell.component + +$(MISC)/MacOSXSpell.component .ERRREMOVE : \ + $(SOLARENV)/bin/createcomponent.xslt MacOSXSpell.component + $(XSLTPROC) --nonet --stringparam uri \ + '$(COMPONENTPREFIX_BASIS_NATIVE)$(SHL1TARGETN:f)' -o $@ \ + $(SOLARENV)/bin/createcomponent.xslt MacOSXSpell.component diff --git a/lingucomponent/source/spellcheck/spell/exports.dxp b/lingucomponent/source/spellcheck/spell/exports.dxp index b0f85bf7bebf..a9861e3ffc0c 100644 --- a/lingucomponent/source/spellcheck/spell/exports.dxp +++ b/lingucomponent/source/spellcheck/spell/exports.dxp @@ -1,3 +1,2 @@ component_getFactory component_getImplementationEnvironment -component_writeInfo diff --git a/lingucomponent/source/spellcheck/spell/makefile.mk b/lingucomponent/source/spellcheck/spell/makefile.mk index 4173d4dbae22..56dd79939b40 100644 --- a/lingucomponent/source/spellcheck/spell/makefile.mk +++ b/lingucomponent/source/spellcheck/spell/makefile.mk @@ -85,3 +85,11 @@ DEF1EXPORTFILE= exports.dxp .INCLUDE : target.mk + +ALLTAR : $(MISC)/spell.component + +$(MISC)/spell.component .ERRREMOVE : $(SOLARENV)/bin/createcomponent.xslt \ + spell.component + $(XSLTPROC) --nonet --stringparam uri \ + '$(COMPONENTPREFIX_BASIS_NATIVE)$(SHL1TARGETN:f)' -o $@ \ + $(SOLARENV)/bin/createcomponent.xslt spell.component diff --git a/lingucomponent/source/spellcheck/spell/spell.component b/lingucomponent/source/spellcheck/spell/spell.component new file mode 100644 index 000000000000..9f951a8a8f76 --- /dev/null +++ b/lingucomponent/source/spellcheck/spell/spell.component @@ -0,0 +1,34 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!--********************************************************************** +* +* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +* +* Copyright 2000, 2010 Oracle and/or its affiliates. +* +* OpenOffice.org - a multi-platform office productivity suite +* +* This file is part of OpenOffice.org. +* +* OpenOffice.org is free software: you can redistribute it and/or modify +* it under the terms of the GNU Lesser General Public License version 3 +* only, as published by the Free Software Foundation. +* +* OpenOffice.org is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU Lesser General Public License version 3 for more details +* (a copy is included in the LICENSE file that accompanied this code). +* +* You should have received a copy of the GNU Lesser General Public License +* version 3 along with OpenOffice.org. If not, see +* <http://www.openoffice.org/license.html> +* for a copy of the LGPLv3 License. +* +**********************************************************************--> + +<component loader="com.sun.star.loader.SharedLibrary" + xmlns="http://openoffice.org/2010/uno-components"> + <implementation name="org.openoffice.lingu.MySpellSpellChecker"> + <service name="com.sun.star.linguistic2.SpellChecker"/> + </implementation> +</component> diff --git a/lingucomponent/source/spellcheck/spell/sreg.cxx b/lingucomponent/source/spellcheck/spell/sreg.cxx index bd97403c89d6..4c6375698de6 100644 --- a/lingucomponent/source/spellcheck/spell/sreg.cxx +++ b/lingucomponent/source/spellcheck/spell/sreg.cxx @@ -42,9 +42,6 @@ using namespace com::sun::star::registry; // declaration of external RegEntry-functions defined by the service objects // -extern sal_Bool SAL_CALL SpellChecker_writeInfo( - void * /*pServiceManager*/, XRegistryKey * pRegistryKey ); - extern void * SAL_CALL SpellChecker_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, @@ -56,12 +53,6 @@ extern void * SAL_CALL SpellChecker_getFactory( extern "C" { -sal_Bool SAL_CALL component_writeInfo( - void * pServiceManager, XRegistryKey * pRegistryKey ) -{ - return SpellChecker_writeInfo( pServiceManager, pRegistryKey ); -} - void SAL_CALL component_getImplementationEnvironment( const sal_Char ** ppEnvTypeName, uno_Environment ** /*ppEnv*/ ) { diff --git a/lingucomponent/source/spellcheck/spell/sspellimp.cxx b/lingucomponent/source/spellcheck/spell/sspellimp.cxx index 8486f4fb38fd..577d105afcde 100644 --- a/lingucomponent/source/spellcheck/spell/sspellimp.cxx +++ b/lingucomponent/source/spellcheck/spell/sspellimp.cxx @@ -27,6 +27,7 @@ // MARKER(update_precomp.py): autogen include statement, do not remove #include "precompiled_lingucomponent.hxx" + #include <com/sun/star/uno/Reference.h> #include <com/sun/star/linguistic2/XSearchableDictionaryList.hpp> @@ -37,12 +38,10 @@ #include <unotools/processfactory.hxx> #include <osl/mutex.hxx> +#include <lingutil.hxx> #include <hunspell.hxx> #include <dictmgr.hxx> - -#ifndef _SPELLIMP_HXX #include <sspellimp.hxx> -#endif #include <linguistic/lngprops.hxx> #include <linguistic/spelldta.hxx> @@ -52,8 +51,7 @@ #include <unotools/useroptions.hxx> #include <osl/file.hxx> #include <rtl/ustrbuf.hxx> - -#include <lingutil.hxx> +#include <rtl/textenc.h> #include <list> #include <set> @@ -77,35 +75,37 @@ using namespace linguistic; SpellChecker::SpellChecker() : aEvtListeners ( GetLinguMutex() ) { - aDicts = NULL; + aDicts = NULL; aDEncs = NULL; aDLocs = NULL; aDNames = NULL; bDisposing = FALSE; pPropHelper = NULL; - numdict = 0; + numdict = 0; } SpellChecker::~SpellChecker() { - if (aDicts) { - for (int i = 0; i < numdict; i++) { + if (aDicts) + { + for (int i = 0; i < numdict; i++) + { if (aDicts[i]) delete aDicts[i]; aDicts[i] = NULL; - } - delete[] aDicts; - } - aDicts = NULL; - numdict = 0; - if (aDEncs) delete[] aDEncs; - aDEncs = NULL; - if (aDLocs) delete[] aDLocs; - aDLocs = NULL; - if (aDNames) delete[] aDNames; - aDNames = NULL; - if (pPropHelper) - pPropHelper->RemoveAsPropListener(); + } + delete[] aDicts; + } + aDicts = NULL; + numdict = 0; + if (aDEncs) delete[] aDEncs; + aDEncs = NULL; + if (aDLocs) delete[] aDLocs; + aDLocs = NULL; + if (aDNames) delete[] aDNames; + aDNames = NULL; + if (pPropHelper) + pPropHelper->RemoveAsPropListener(); } @@ -217,7 +217,7 @@ Sequence< Locale > SAL_CALL SpellChecker::getLocales() for (sal_Int32 i = 0; i < nLocales; ++i) { aDicts[k] = NULL; - aDEncs[k] = 0; + aDEncs[k] = RTL_TEXTENCODING_DONTKNOW; aDLocs[k] = MsLangId::convertLanguageToLocale( MsLangId::convertIsoStringToLanguage( aLocaleNames[i] )); // also both files have to be in the same directory and the @@ -272,84 +272,86 @@ sal_Bool SAL_CALL SpellChecker::hasLocale(const Locale& rLocale) return bRes; } + INT16 SpellChecker::GetSpellFailure( const OUString &rWord, const Locale &rLocale ) { - Hunspell * pMS; - rtl_TextEncoding aEnc; + Hunspell * pMS = NULL; + rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW; // initialize a myspell object for each dictionary once - // (note: mutex is held higher up in isValid) - + // (note: mutex is held higher up in isValid) INT16 nRes = -1; - // first handle smart quotes both single and double + // first handle smart quotes both single and double OUStringBuffer rBuf(rWord); - sal_Int32 n = rBuf.getLength(); - sal_Unicode c; - for (sal_Int32 ix=0; ix < n; ix++) { + sal_Int32 n = rBuf.getLength(); + sal_Unicode c; + for (sal_Int32 ix=0; ix < n; ix++) + { c = rBuf.charAt(ix); - if ((c == 0x201C) || (c == 0x201D)) rBuf.setCharAt(ix,(sal_Unicode)0x0022); - if ((c == 0x2018) || (c == 0x2019)) rBuf.setCharAt(ix,(sal_Unicode)0x0027); - } - OUString nWord(rBuf.makeStringAndClear()); + if ((c == 0x201C) || (c == 0x201D)) + rBuf.setCharAt(ix,(sal_Unicode)0x0022); + if ((c == 0x2018) || (c == 0x2019)) + rBuf.setCharAt(ix,(sal_Unicode)0x0027); + } + OUString nWord(rBuf.makeStringAndClear()); if (n) { - for (sal_Int32 i = 0; i < numdict; ++i) { + for (sal_Int32 i = 0; i < numdict; ++i) + { pMS = NULL; - aEnc = 0; + eEnc = RTL_TEXTENCODING_DONTKNOW; if (rLocale == aDLocs[i]) { - if (!aDicts[i]) - { - OUString dicpath = aDNames[i] + A2OU(".dic"); - OUString affpath = aDNames[i] + A2OU(".aff"); - OUString dict; - OUString aff; - osl::FileBase::getSystemPathFromFileURL(dicpath,dict); - osl::FileBase::getSystemPathFromFileURL(affpath,aff); - OString aTmpaff(OU2ENC(aff,osl_getThreadTextEncoding())); - OString aTmpdict(OU2ENC(dict,osl_getThreadTextEncoding())); + if (!aDicts[i]) + { + OUString dicpath = aDNames[i] + A2OU(".dic"); + OUString affpath = aDNames[i] + A2OU(".aff"); + OUString dict; + OUString aff; + osl::FileBase::getSystemPathFromFileURL(dicpath,dict); + osl::FileBase::getSystemPathFromFileURL(affpath,aff); + OString aTmpaff(OU2ENC(aff,osl_getThreadTextEncoding())); + OString aTmpdict(OU2ENC(dict,osl_getThreadTextEncoding())); #if defined(WNT) - // workaround for Windows specifc problem that the - // path length in calls to 'fopen' is limted to somewhat - // about 120+ characters which will usually be exceed when - // using dictionaries as extensions. - aTmpaff = Win_GetShortPathName( aff ); - aTmpdict = Win_GetShortPathName( dict ); + // workaround for Windows specifc problem that the + // path length in calls to 'fopen' is limted to somewhat + // about 120+ characters which will usually be exceed when + // using dictionaries as extensions. + aTmpaff = Win_GetShortPathName( aff ); + aTmpdict = Win_GetShortPathName( dict ); #endif - aDicts[i] = new Hunspell(aTmpaff.getStr(),aTmpdict.getStr()); - aDEncs[i] = 0; - if (aDicts[i]) { - char * dic_encoding = aDicts[i]->get_dic_encoding(); - aDEncs[i] = rtl_getTextEncodingFromUnixCharset(aDicts[i]->get_dic_encoding()); - if (aDEncs[i] == RTL_TEXTENCODING_DONTKNOW) { - if (strcmp("ISCII-DEVANAGARI", dic_encoding) == 0) { - aDEncs[i] = RTL_TEXTENCODING_ISCII_DEVANAGARI; - } else if (strcmp("UTF-8", dic_encoding) == 0) { - aDEncs[i] = RTL_TEXTENCODING_UTF8; - } - } - } - } - pMS = aDicts[i]; - aEnc = aDEncs[i]; - } + aDicts[i] = new Hunspell(aTmpaff.getStr(),aTmpdict.getStr()); + aDEncs[i] = RTL_TEXTENCODING_DONTKNOW; + if (aDicts[i]) + aDEncs[i] = getTextEncodingFromCharset(aDicts[i]->get_dic_encoding()); + } + pMS = aDicts[i]; + eEnc = aDEncs[i]; + } + if (pMS) - { - OString aWrd(OU2ENC(nWord,aEnc)); + { + // we don't want to work with a default text encoding since following incorrect + // results may occur only for specific text and thus may be hard to notice. + // Thus better always make a clean exit here if the text encoding is in question. + // Hopefully something not working at all will raise proper attention quickly. ;-) + DBG_ASSERT( eEnc != RTL_TEXTENCODING_DONTKNOW, "failed to get text encoding! (maybe incorrect encoding string in file)" ); + if (eEnc == RTL_TEXTENCODING_DONTKNOW) + return -1; + + OString aWrd(OU2ENC(nWord,eEnc)); int rVal = pMS->spell((char*)aWrd.getStr()); - if (rVal != 1) - { - nRes = SpellFailure::SPELLING_ERROR; - } else { - return -1; - } - pMS = NULL; + if (rVal != 1) + nRes = SpellFailure::SPELLING_ERROR; + else + return -1; + pMS = NULL; } } } @@ -358,8 +360,7 @@ INT16 SpellChecker::GetSpellFailure( const OUString &rWord, const Locale &rLocal } -sal_Bool SAL_CALL - SpellChecker::isValid( const OUString& rWord, const Locale& rLocale, +sal_Bool SAL_CALL SpellChecker::isValid( const OUString& rWord, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException) { @@ -375,6 +376,9 @@ sal_Bool SAL_CALL return TRUE; #endif + // return FALSE to process SPELLML requests (they are longer than the header) + if (rWord.match(A2OU(SPELLML_HEADER), 0) && (rWord.getLength() > 10)) return FALSE; + // Get property values to be used. // These are be the default values set in the SN_LINGU_PROPERTIES // PropertySet which are overridden by the supplied ones from the @@ -390,11 +394,11 @@ sal_Bool SAL_CALL { INT16 nLang = LocaleToLanguage( rLocale ); // postprocess result for errors that should be ignored - if ( (!rHelper.IsSpellUpperCase() && IsUpper( rWord, nLang )) - || (!rHelper.IsSpellWithDigits() && HasDigits( rWord )) - || (!rHelper.IsSpellCapitalization() - && nFailure == SpellFailure::CAPTION_ERROR) - ) + const bool bIgnoreError = + (!rHelper.IsSpellUpperCase() && IsUpper( rWord, nLang )) || + (!rHelper.IsSpellWithDigits() && HasDigits( rWord )) || + (!rHelper.IsSpellCapitalization() && nFailure == SpellFailure::CAPTION_ERROR); + if (bIgnoreError) nFailure = -1; } @@ -410,23 +414,26 @@ Reference< XSpellAlternatives > // Especially it may give a list of suggested (correct) words: Reference< XSpellAlternatives > xRes; - // note: mutex is held by higher up by spell which covers both + // note: mutex is held by higher up by spell which covers both - Hunspell* pMS; - rtl_TextEncoding aEnc; - int count; - int numsug = 0; + Hunspell* pMS = NULL; + rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW; + int count = 0; + int numsug = 0; - // first handle smart quotes (single and double) + // first handle smart quotes (single and double) OUStringBuffer rBuf(rWord); - sal_Int32 n = rBuf.getLength(); - sal_Unicode c; - for (sal_Int32 ix=0; ix < n; ix++) { - c = rBuf.charAt(ix); - if ((c == 0x201C) || (c == 0x201D)) rBuf.setCharAt(ix,(sal_Unicode)0x0022); - if ((c == 0x2018) || (c == 0x2019)) rBuf.setCharAt(ix,(sal_Unicode)0x0027); - } - OUString nWord(rBuf.makeStringAndClear()); + sal_Int32 n = rBuf.getLength(); + sal_Unicode c; + for (sal_Int32 ix=0; ix < n; ix++) + { + c = rBuf.charAt(ix); + if ((c == 0x201C) || (c == 0x201D)) + rBuf.setCharAt(ix,(sal_Unicode)0x0022); + if ((c == 0x2018) || (c == 0x2019)) + rBuf.setCharAt(ix,(sal_Unicode)0x0027); + } + OUString nWord(rBuf.makeStringAndClear()); if (n) { @@ -434,59 +441,55 @@ Reference< XSpellAlternatives > Sequence< OUString > aStr( 0 ); - for (int i =0; i < numdict; i++) { + for (int i =0; i < numdict; i++) + { pMS = NULL; - aEnc = 0; - count = 0; + eEnc = RTL_TEXTENCODING_DONTKNOW; + count = 0; if (rLocale == aDLocs[i]) { - pMS = aDicts[i]; - aEnc = aDEncs[i]; - } + pMS = aDicts[i]; + eEnc = aDEncs[i]; + } if (pMS) { char ** suglst = NULL; - OString aWrd(OU2ENC(nWord,aEnc)); - count = pMS->suggest(&suglst, (const char *) aWrd.getStr()); - - if (count) { - - aStr.realloc( numsug + count ); - OUString *pStr = aStr.getArray(); - for (int ii=0; ii < count; ii++) - { - // if needed add: if (suglst[ii] == NULL) continue; - OUString cvtwrd(suglst[ii],strlen(suglst[ii]),aEnc); - pStr[numsug + ii] = cvtwrd; - free(suglst[ii]); - } - free(suglst); - numsug += count; + OString aWrd(OU2ENC(nWord,eEnc)); + count = pMS->suggest(&suglst, (const char *) aWrd.getStr()); + + if (count) + { + aStr.realloc( numsug + count ); + OUString *pStr = aStr.getArray(); + for (int ii=0; ii < count; ++ii) + { + OUString cvtwrd(suglst[ii],strlen(suglst[ii]),eEnc); + pStr[numsug + ii] = cvtwrd; } - } + pMS->free_list(&suglst, count); + numsug += count; + } + } } - // now return an empty alternative for no suggestions or the list of alternatives if some found + // now return an empty alternative for no suggestions or the list of alternatives if some found SpellAlternatives *pAlt = new SpellAlternatives; - String aTmp(rWord); + String aTmp(rWord); pAlt->SetWordLanguage( aTmp, nLang ); pAlt->SetFailureType( SpellFailure::SPELLING_ERROR ); pAlt->SetAlternatives( aStr ); xRes = pAlt; - return xRes; - - } return xRes; + } + return xRes; } - - -Reference< XSpellAlternatives > SAL_CALL - SpellChecker::spell( const OUString& rWord, const Locale& rLocale, - const PropertyValues& rProperties ) +Reference< XSpellAlternatives > SAL_CALL SpellChecker::spell( + const OUString& rWord, const Locale& rLocale, + const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -511,7 +514,7 @@ Reference< XSpellAlternatives > SAL_CALL Reference< XInterface > SAL_CALL SpellChecker_CreateInstance( - const Reference< XMultiServiceFactory > & /*rSMgr*/ ) + const Reference< XMultiServiceFactory > & /*rSMgr*/ ) throw(Exception) { @@ -520,9 +523,8 @@ Reference< XInterface > SAL_CALL SpellChecker_CreateInstance( } -sal_Bool SAL_CALL - SpellChecker::addLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) +sal_Bool SAL_CALL SpellChecker::addLinguServiceEventListener( + const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -536,9 +538,8 @@ sal_Bool SAL_CALL } -sal_Bool SAL_CALL - SpellChecker::removeLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) +sal_Bool SAL_CALL SpellChecker::removeLinguServiceEventListener( + const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -553,8 +554,7 @@ sal_Bool SAL_CALL } -OUString SAL_CALL - SpellChecker::getServiceDisplayName( const Locale& /*rLocale*/ ) +OUString SAL_CALL SpellChecker::getServiceDisplayName( const Locale& /*rLocale*/ ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -562,8 +562,7 @@ OUString SAL_CALL } -void SAL_CALL - SpellChecker::initialize( const Sequence< Any >& rArguments ) +void SAL_CALL SpellChecker::initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -585,16 +584,15 @@ void SAL_CALL xPropHelper = pPropHelper; pPropHelper->AddAsPropListener(); //! after a reference is established } - else { + else + { DBG_ERROR( "wrong number of arguments in sequence" ); } - } } -void SAL_CALL - SpellChecker::dispose() +void SAL_CALL SpellChecker::dispose() throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -608,8 +606,7 @@ void SAL_CALL } -void SAL_CALL - SpellChecker::addEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL SpellChecker::addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -619,8 +616,7 @@ void SAL_CALL } -void SAL_CALL - SpellChecker::removeEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL SpellChecker::removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -676,32 +672,6 @@ Sequence< OUString > SpellChecker::getSupportedServiceNames_Static() return aSNS; } - -sal_Bool SAL_CALL SpellChecker_writeInfo( - void * /*pServiceManager*/, registry::XRegistryKey * pRegistryKey ) -{ - - try - { - String aImpl( '/' ); - aImpl += SpellChecker::getImplementationName_Static().getStr(); - aImpl.AppendAscii( "/UNO/SERVICES" ); - Reference< registry::XRegistryKey > xNewKey = - pRegistryKey->createKey( aImpl ); - Sequence< OUString > aServices = - SpellChecker::getSupportedServiceNames_Static(); - for( INT32 i = 0; i < aServices.getLength(); i++ ) - xNewKey->createKey( aServices.getConstArray()[i] ); - - return sal_True; - } - catch(Exception &) - { - return sal_False; - } -} - - void * SAL_CALL SpellChecker_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, void * ) { diff --git a/lingucomponent/source/spellcheck/spell/sspellimp.hxx b/lingucomponent/source/spellcheck/spell/sspellimp.hxx index 94c57fa8b742..9bcbdec5250b 100644 --- a/lingucomponent/source/spellcheck/spell/sspellimp.hxx +++ b/lingucomponent/source/spellcheck/spell/sspellimp.hxx @@ -69,11 +69,11 @@ class SpellChecker : > { Sequence< Locale > aSuppLocales; - Hunspell ** aDicts; - rtl_TextEncoding * aDEncs; - Locale * aDLocs; - OUString * aDNames; - sal_Int32 numdict; + Hunspell ** aDicts; + rtl_TextEncoding * aDEncs; + Locale * aDLocs; + OUString * aDNames; + sal_Int32 numdict; ::cppu::OInterfaceContainerHelper aEvtListeners; Reference< XPropertyChangeListener > xPropHelper; @@ -91,84 +91,43 @@ class SpellChecker : } INT16 GetSpellFailure( const OUString &rWord, const Locale &rLocale ); - Reference< XSpellAlternatives > - GetProposals( const OUString &rWord, const Locale &rLocale ); + Reference< XSpellAlternatives > GetProposals( const OUString &rWord, const Locale &rLocale ); public: SpellChecker(); virtual ~SpellChecker(); // XSupportedLocales (for XSpellChecker) - virtual Sequence< Locale > SAL_CALL - getLocales() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - hasLocale( const Locale& rLocale ) - throw(RuntimeException); + virtual Sequence< Locale > SAL_CALL getLocales() throw(RuntimeException); + virtual sal_Bool SAL_CALL hasLocale( const Locale& rLocale ) throw(RuntimeException); // XSpellChecker - virtual sal_Bool SAL_CALL - isValid( const OUString& rWord, const Locale& rLocale, - const PropertyValues& rProperties ) - throw(IllegalArgumentException, - RuntimeException); - virtual Reference< XSpellAlternatives > SAL_CALL - spell( const OUString& rWord, const Locale& rLocale, - const PropertyValues& rProperties ) - throw(IllegalArgumentException, - RuntimeException); + virtual sal_Bool SAL_CALL isValid( const OUString& rWord, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException); + virtual Reference< XSpellAlternatives > SAL_CALL spell( const OUString& rWord, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException); // XLinguServiceEventBroadcaster - virtual sal_Bool SAL_CALL - addLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); - virtual sal_Bool SAL_CALL - removeLinguServiceEventListener( - const Reference< XLinguServiceEventListener >& rxLstnr ) - throw(RuntimeException); + virtual sal_Bool SAL_CALL addLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); + virtual sal_Bool SAL_CALL removeLinguServiceEventListener( const Reference< XLinguServiceEventListener >& rxLstnr ) throw(RuntimeException); // XServiceDisplayName - virtual OUString SAL_CALL - getServiceDisplayName( const Locale& rLocale ) - throw(RuntimeException); + virtual OUString SAL_CALL getServiceDisplayName( const Locale& rLocale ) throw(RuntimeException); // XInitialization - virtual void SAL_CALL - initialize( const Sequence< Any >& rArguments ) - throw(Exception, RuntimeException); + virtual void SAL_CALL initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException); // XComponent - virtual void SAL_CALL - dispose() - throw(RuntimeException); - virtual void SAL_CALL - addEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - virtual void SAL_CALL - removeEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - - //////////////////////////////////////////////////////////// - // Service specific part - // + virtual void SAL_CALL dispose() throw(RuntimeException); + virtual void SAL_CALL addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); + virtual void SAL_CALL removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); // XServiceInfo - virtual OUString SAL_CALL - getImplementationName() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - supportsService( const OUString& rServiceName ) - throw(RuntimeException); - virtual Sequence< OUString > SAL_CALL - getSupportedServiceNames() - throw(RuntimeException); - - - static inline OUString - getImplementationName_Static() throw(); - static Sequence< OUString > - getSupportedServiceNames_Static() throw(); + virtual OUString SAL_CALL getImplementationName() throw(RuntimeException); + virtual sal_Bool SAL_CALL supportsService( const OUString& rServiceName ) throw(RuntimeException); + virtual Sequence< OUString > SAL_CALL getSupportedServiceNames() throw(RuntimeException); + + + static inline OUString getImplementationName_Static() throw(); + static Sequence< OUString > getSupportedServiceNames_Static() throw(); }; inline OUString SpellChecker::getImplementationName_Static() throw() @@ -177,7 +136,6 @@ inline OUString SpellChecker::getImplementationName_Static() throw() } - /////////////////////////////////////////////////////////////////////////// #endif diff --git a/lingucomponent/source/thesaurus/libnth/exports.dxp b/lingucomponent/source/thesaurus/libnth/exports.dxp index b0f85bf7bebf..a9861e3ffc0c 100644 --- a/lingucomponent/source/thesaurus/libnth/exports.dxp +++ b/lingucomponent/source/thesaurus/libnth/exports.dxp @@ -1,3 +1,2 @@ component_getFactory component_getImplementationEnvironment -component_writeInfo diff --git a/lingucomponent/source/thesaurus/libnth/lnth.component b/lingucomponent/source/thesaurus/libnth/lnth.component new file mode 100644 index 000000000000..bea91b94c1fe --- /dev/null +++ b/lingucomponent/source/thesaurus/libnth/lnth.component @@ -0,0 +1,34 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!--********************************************************************** +* +* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +* +* Copyright 2000, 2010 Oracle and/or its affiliates. +* +* OpenOffice.org - a multi-platform office productivity suite +* +* This file is part of OpenOffice.org. +* +* OpenOffice.org is free software: you can redistribute it and/or modify +* it under the terms of the GNU Lesser General Public License version 3 +* only, as published by the Free Software Foundation. +* +* OpenOffice.org is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU Lesser General Public License version 3 for more details +* (a copy is included in the LICENSE file that accompanied this code). +* +* You should have received a copy of the GNU Lesser General Public License +* version 3 along with OpenOffice.org. If not, see +* <http://www.openoffice.org/license.html> +* for a copy of the LGPLv3 License. +* +**********************************************************************--> + +<component loader="com.sun.star.loader.SharedLibrary" + xmlns="http://openoffice.org/2010/uno-components"> + <implementation name="org.openoffice.lingu.new.Thesaurus"> + <service name="com.sun.star.linguistic2.Thesaurus"/> + </implementation> +</component> diff --git a/lingucomponent/source/thesaurus/libnth/makefile.mk b/lingucomponent/source/thesaurus/libnth/makefile.mk index 58e4d97e5561..91d39d2d3eeb 100644 --- a/lingucomponent/source/thesaurus/libnth/makefile.mk +++ b/lingucomponent/source/thesaurus/libnth/makefile.mk @@ -105,3 +105,11 @@ DEF1EXPORTFILE= exports.dxp .INCLUDE : target.mk + +ALLTAR : $(MISC)/lnth.component + +$(MISC)/lnth.component .ERRREMOVE : $(SOLARENV)/bin/createcomponent.xslt \ + lnth.component + $(XSLTPROC) --nonet --stringparam uri \ + '$(COMPONENTPREFIX_BASIS_NATIVE)$(SHL1TARGETN:f)' -o $@ \ + $(SOLARENV)/bin/createcomponent.xslt lnth.component diff --git a/lingucomponent/source/thesaurus/libnth/nthesdta.hxx b/lingucomponent/source/thesaurus/libnth/nthesdta.hxx index 259bf5454359..23804d54f60f 100644 --- a/lingucomponent/source/thesaurus/libnth/nthesdta.hxx +++ b/lingucomponent/source/thesaurus/libnth/nthesdta.hxx @@ -48,11 +48,11 @@ class Meaning : { ::com::sun::star::uno::Sequence< ::rtl::OUString > aSyn; // list of synonyms, may be empty. ::rtl::OUString aTerm; - INT16 nLanguage; + INT16 nLanguage; #if 0 // this is for future use by a German thesaurus - BOOL bIsGermanPreReform; + BOOL bIsGermanPreReform; #endif // disallow copy-constructor and assignment-operator for now @@ -68,22 +68,12 @@ public: virtual ~Meaning(); // XMeaning - virtual ::rtl::OUString SAL_CALL - getMeaning() - throw(::com::sun::star::uno::RuntimeException); - - virtual ::com::sun::star::uno::Sequence< ::rtl::OUString > SAL_CALL - querySynonyms() - throw(::com::sun::star::uno::RuntimeException); + virtual ::rtl::OUString SAL_CALL getMeaning() throw(::com::sun::star::uno::RuntimeException); + virtual ::com::sun::star::uno::Sequence< ::rtl::OUString > SAL_CALL querySynonyms() throw(::com::sun::star::uno::RuntimeException); // non-interface specific functions - void SetSynonyms( - const ::com::sun::star::uno::Sequence< ::rtl::OUString > - &rSyn ); - - void SetMeaning(const ::rtl::OUString &rTerm ); - - + void SetSynonyms( const ::com::sun::star::uno::Sequence< ::rtl::OUString > &rSyn ); + void SetMeaning( const ::rtl::OUString &rTerm ); }; diff --git a/lingucomponent/source/thesaurus/libnth/nthesimp.cxx b/lingucomponent/source/thesaurus/libnth/nthesimp.cxx index bd6afffdbd6a..02d469514593 100644 --- a/lingucomponent/source/thesaurus/libnth/nthesimp.cxx +++ b/lingucomponent/source/thesaurus/libnth/nthesimp.cxx @@ -28,9 +28,7 @@ // MARKER(update_precomp.py): autogen include statement, do not remove #include "precompiled_lingucomponent.hxx" -// include <stdio.h> #include <com/sun/star/uno/Reference.h> - #include <cppuhelper/factory.hxx> // helper for factories #include <com/sun/star/registry/XRegistryKey.hpp> #include <com/sun/star/beans/XPropertySet.hpp> @@ -43,6 +41,8 @@ #include <rtl/string.hxx> #include <rtl/ustrbuf.hxx> +#include <rtl/textenc.h> + #include "nthesimp.hxx" #include <linguistic/misc.hxx> #include <linguistic/lngprops.hxx> @@ -100,23 +100,27 @@ Thesaurus::Thesaurus() : aTEncs = NULL; aTLocs = NULL; aTNames = NULL; - numthes = 0; + numthes = 0; } Thesaurus::~Thesaurus() { - if (aThes) { - for (int i = 0; i < numthes; i++) { + if (aThes) + { + for (int i = 0; i < numthes; i++) + { if (aThes[i]) delete aThes[i]; aThes[i] = NULL; } delete[] aThes; } aThes = NULL; - if (aCharSetInfo) { - for (int i = 0; i < numthes; i++) { + if (aCharSetInfo) + { + for (int i = 0; i < numthes; i++) + { if (aCharSetInfo[i]) delete aCharSetInfo[i]; aCharSetInfo[i] = NULL; } @@ -244,7 +248,7 @@ Sequence< Locale > SAL_CALL Thesaurus::getLocales() for (sal_Int32 i = 0; i < nLocales; ++i) { aThes[k] = NULL; - aTEncs[k] = 0; + aTEncs[k] = RTL_TEXTENCODING_DONTKNOW; aTLocs[k] = MsLangId::convertLanguageToLocale( MsLangId::convertIsoStringToLanguage( aDictIt->aLocaleNames[i] )); aCharSetInfo[k] = new CharClass( aTLocs[k] ); @@ -302,28 +306,28 @@ sal_Bool SAL_CALL Thesaurus::hasLocale(const Locale& rLocale) } -Sequence < Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL - Thesaurus::queryMeanings( const OUString& qTerm, const Locale& rLocale, - const PropertyValues& rProperties) - throw(IllegalArgumentException, RuntimeException) +Sequence < Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL Thesaurus::queryMeanings( + const OUString& qTerm, const Locale& rLocale, + const PropertyValues& rProperties) + throw(IllegalArgumentException, RuntimeException) { - MutexGuard aGuard( GetLinguMutex() ); + MutexGuard aGuard( GetLinguMutex() ); - uno::Sequence< Reference< XMeaning > > aMeanings( 1 ); - uno::Sequence< Reference< XMeaning > > noMeanings( 0 ); - uno::Reference< XLinguServiceManager > xLngSvcMgr( GetLngSvcMgr_Impl() ); - uno::Reference< XSpellChecker1 > xSpell; + uno::Sequence< Reference< XMeaning > > aMeanings( 1 ); + uno::Sequence< Reference< XMeaning > > noMeanings( 0 ); + uno::Reference< XLinguServiceManager > xLngSvcMgr( GetLngSvcMgr_Impl() ); + uno::Reference< XSpellChecker1 > xSpell; - OUString rTerm(qTerm); - OUString pTerm(qTerm); - sal_uInt16 ct = CAPTYPE_UNKNOWN; - sal_Int32 stem = 0; - sal_Int32 stem2 = 0; + OUString rTerm(qTerm); + OUString pTerm(qTerm); + sal_uInt16 ct = CAPTYPE_UNKNOWN; + sal_Int32 stem = 0; + sal_Int32 stem2 = 0; - INT16 nLanguage = LocaleToLanguage( rLocale ); + INT16 nLanguage = LocaleToLanguage( rLocale ); - if (nLanguage == LANGUAGE_NONE || !rTerm.getLength()) - return noMeanings; + if (nLanguage == LANGUAGE_NONE || !rTerm.getLength()) + return noMeanings; if (!hasLocale( rLocale )) #ifdef LINGU_EXCEPTIONS @@ -332,195 +336,202 @@ Sequence < Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL return noMeanings; #endif - if (prevTerm == qTerm && prevLocale == nLanguage) return prevMeanings; + if (prevTerm == qTerm && prevLocale == nLanguage) + return prevMeanings; - mentry * pmean = NULL; + mentry * pmean = NULL; sal_Int32 nmean = 0; - PropertyHelper_Thes &rHelper = GetPropHelper(); - rHelper.SetTmpPropVals( rProperties ); + PropertyHelper_Thes &rHelper = GetPropHelper(); + rHelper.SetTmpPropVals( rProperties ); - MyThes * pTH = NULL; - rtl_TextEncoding aEnc = 0; - CharClass * pCC = NULL; + MyThes * pTH = NULL; + rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW; + CharClass * pCC = NULL; - // find the first thesaurus that matches the locale - for (int i =0; i < numthes; i++) { - if (rLocale == aTLocs[i]) + // find the first thesaurus that matches the locale + for (int i =0; i < numthes; i++) + { + if (rLocale == aTLocs[i]) + { + // open up and intialize this thesaurus if need be + if (!aThes[i]) { - // open up and intialize this thesaurus if need be - if (!aThes[i]) - { - OUString datpath = aTNames[i] + A2OU(".dat"); - OUString idxpath = aTNames[i] + A2OU(".idx"); - OUString ndat; - OUString nidx; - osl::FileBase::getSystemPathFromFileURL(datpath,ndat); - osl::FileBase::getSystemPathFromFileURL(idxpath,nidx); - OString aTmpidx(OU2ENC(nidx,osl_getThreadTextEncoding())); - OString aTmpdat(OU2ENC(ndat,osl_getThreadTextEncoding())); + OUString datpath = aTNames[i] + A2OU(".dat"); + OUString idxpath = aTNames[i] + A2OU(".idx"); + OUString ndat; + OUString nidx; + osl::FileBase::getSystemPathFromFileURL(datpath,ndat); + osl::FileBase::getSystemPathFromFileURL(idxpath,nidx); + OString aTmpidx(OU2ENC(nidx,osl_getThreadTextEncoding())); + OString aTmpdat(OU2ENC(ndat,osl_getThreadTextEncoding())); #if defined(WNT) - // workaround for Windows specifc problem that the - // path length in calls to 'fopen' is limted to somewhat - // about 120+ characters which will usually be exceed when - // using dictionaries as extensions. - aTmpidx = Win_GetShortPathName( nidx ); - aTmpdat = Win_GetShortPathName( ndat ); + // workaround for Windows specifc problem that the + // path length in calls to 'fopen' is limted to somewhat + // about 120+ characters which will usually be exceed when + // using dictionaries as extensions. + aTmpidx = Win_GetShortPathName( nidx ); + aTmpdat = Win_GetShortPathName( ndat ); #endif - aThes[i] = new MyThes(aTmpidx.getStr(),aTmpdat.getStr()); - if (aThes[i]) { - const char * enc_string = aThes[i]->get_th_encoding(); - if (!enc_string) { - aTEncs[i] = rtl_getTextEncodingFromUnixCharset("ISO8859-1"); - } else { - aTEncs[i] = rtl_getTextEncodingFromUnixCharset(enc_string); - if (aTEncs[i] == RTL_TEXTENCODING_DONTKNOW) { - if (strcmp("ISCII-DEVANAGARI", enc_string) == 0) { - aTEncs[i] = RTL_TEXTENCODING_ISCII_DEVANAGARI; - } else if (strcmp("UTF-8", enc_string) == 0) { - aTEncs[i] = RTL_TEXTENCODING_UTF8; - } - } - } - } - } - pTH = aThes[i]; - aEnc = aTEncs[i]; - pCC = aCharSetInfo[i]; - - if (pTH) - break; + aThes[i] = new MyThes(aTmpidx.getStr(),aTmpdat.getStr()); + if (aThes[i]) + aTEncs[i] = getTextEncodingFromCharset(aThes[i]->get_th_encoding()); + } + pTH = aThes[i]; + eEnc = aTEncs[i]; + pCC = aCharSetInfo[i]; + + if (pTH) + break; } } - while (pTH) { - // convert word to all lower case for searching - if (!stem) ct = capitalType(rTerm, pCC); - OUString nTerm(makeLowerCase(rTerm, pCC)); - OString aTmp( OU2ENC(nTerm, aEnc) ); - nmean = pTH->Lookup(aTmp.getStr(),aTmp.getLength(),&pmean); + // we don't want to work with a default text encoding since following incorrect + // results may occur only for specific text and thus may be hard to notice. + // Thus better always make a clean exit here if the text encoding is in question. + // Hopefully something not working at all will raise proper attention quickly. ;-) + DBG_ASSERT( eEnc != RTL_TEXTENCODING_DONTKNOW, "failed to get text encoding! (maybe incorrect encoding string in file)" ); + if (eEnc == RTL_TEXTENCODING_DONTKNOW) + return noMeanings; - if (nmean) aMeanings.realloc( nmean ); + while (pTH) + { + // convert word to all lower case for searching + if (!stem) + ct = capitalType(rTerm, pCC); + OUString nTerm(makeLowerCase(rTerm, pCC)); + OString aTmp( OU2ENC(nTerm, eEnc) ); + nmean = pTH->Lookup(aTmp.getStr(),aTmp.getLength(),&pmean); - mentry * pe = pmean; - OUString codeTerm = qTerm; - Reference< XSpellAlternatives > xTmpRes2; + if (nmean) + aMeanings.realloc( nmean ); - if (stem) { - xTmpRes2 = xSpell->spell( A2OU("<?xml?><query type='analyze'><word>") + + mentry * pe = pmean; + OUString codeTerm = qTerm; + Reference< XSpellAlternatives > xTmpRes2; + + if (stem) + { + xTmpRes2 = xSpell->spell( A2OU("<?xml?><query type='analyze'><word>") + pTerm + A2OU("</word></query>"), nLanguage, rProperties ); - if (xTmpRes2.is()) { - Sequence<OUString>seq = xTmpRes2->getAlternatives(); - if (seq.getLength() > 0) { + if (xTmpRes2.is()) + { + Sequence<OUString>seq = xTmpRes2->getAlternatives(); + if (seq.getLength() > 0) + { codeTerm = seq[0]; stem2 = 1; - } + } #if 0 - OString o = OUStringToOString(codeTerm, rtl_getTextEncodingFromUnixCharset("UTF-8")); - fprintf(stderr, "CODETERM: %s\n", o.pData->buffer); + OString o = OUStringToOString(codeTerm, RTL_TEXTENCODING_UTF8); + fprintf(stderr, "CODETERM: %s\n", o.pData->buffer); #endif - } - } - - for (int j = 0; j < nmean; j++) { - int count = pe->count; - if (count) { - Sequence< OUString > aStr( count ); - OUString *pStr = aStr.getArray(); - - for (int i=0; i < count; i++) { - OUString sTerm(pe->psyns[i],strlen(pe->psyns[i]),aEnc ); - sal_Int32 catpos = sTerm.indexOf('('); - sal_Int32 catpos2 = 0; - OUString catst; - OUString catst2; - if (catpos > 2) { - // remove category name for affixation and casing - catst = A2OU(" ") + sTerm.copy(catpos); - sTerm = sTerm.copy(0, catpos); - sTerm = sTerm.trim(); - } - // generate synonyms with affixes - if (stem && stem2) { - Reference< XSpellAlternatives > xTmpRes; - xTmpRes = xSpell->spell( A2OU("<?xml?><query type='generate'><word>") + - sTerm + A2OU("</word>") + codeTerm + A2OU("</query>"), nLanguage, rProperties ); - if (xTmpRes.is()) { - Sequence<OUString>seq = xTmpRes->getAlternatives(); - for (int k = 0; k < seq.getLength(); k++) { - OString o = OUStringToOString(seq[k], rtl_getTextEncodingFromUnixCharset("UTF-8")); - } - if (seq.getLength() > 0) sTerm = seq[0]; - } - } - if (catpos2) sTerm = catst2 + sTerm; - - sal_uInt16 ct1 = capitalType(sTerm, pCC); - if (CAPTYPE_MIXED == ct1) - ct = ct1; - OUString cTerm; - switch (ct) { - case CAPTYPE_ALLCAP: - { - cTerm = makeUpperCase(sTerm, pCC); - break; - } - case CAPTYPE_INITCAP: - { - cTerm = makeInitCap(sTerm, pCC); - break; - } - default: - { - cTerm = sTerm; - break; - } - } - OUString aAlt( cTerm + catst); - pStr[i] = aAlt; - } + } + } + + for (int j = 0; j < nmean; j++) + { + int count = pe->count; + if (count) + { + Sequence< OUString > aStr( count ); + OUString *pStr = aStr.getArray(); + + for (int i=0; i < count; i++) + { + OUString sTerm(pe->psyns[i],strlen(pe->psyns[i]),eEnc ); + sal_Int32 catpos = sTerm.indexOf('('); + sal_Int32 catpos2 = 0; + OUString catst; + OUString catst2; + if (catpos > 2) + { + // remove category name for affixation and casing + catst = A2OU(" ") + sTerm.copy(catpos); + sTerm = sTerm.copy(0, catpos); + sTerm = sTerm.trim(); + } + // generate synonyms with affixes + if (stem && stem2) + { + Reference< XSpellAlternatives > xTmpRes; + xTmpRes = xSpell->spell( A2OU("<?xml?><query type='generate'><word>") + + sTerm + A2OU("</word>") + codeTerm + A2OU("</query>"), nLanguage, rProperties ); + if (xTmpRes.is()) + { + Sequence<OUString>seq = xTmpRes->getAlternatives(); + if (seq.getLength() > 0) + sTerm = seq[0]; + } + } + if (catpos2) + sTerm = catst2 + sTerm; + + sal_uInt16 ct1 = capitalType(sTerm, pCC); + if (CAPTYPE_MIXED == ct1) + ct = ct1; + OUString cTerm; + switch (ct) + { + case CAPTYPE_ALLCAP: + cTerm = makeUpperCase(sTerm, pCC); + break; + case CAPTYPE_INITCAP: + cTerm = makeInitCap(sTerm, pCC); + break; + default: + cTerm = sTerm; + break; + } + OUString aAlt( cTerm + catst); + pStr[i] = aAlt; + } #if 0 - Meaning * pMn = new Meaning(rTerm,nLanguage,rHelper); + Meaning * pMn = new Meaning(rTerm,nLanguage,rHelper); #endif - Meaning * pMn = new Meaning(rTerm,nLanguage); - OUString dTerm(pe->defn,strlen(pe->defn),aEnc ); - pMn->SetMeaning(dTerm); - pMn->SetSynonyms(aStr); - Reference<XMeaning>* pMeaning = aMeanings.getArray(); - pMeaning[j] = pMn; - } - pe++; - } - pTH->CleanUpAfterLookup(&pmean,nmean); - - if (nmean) { + Meaning * pMn = new Meaning(rTerm,nLanguage); + OUString dTerm(pe->defn,strlen(pe->defn),eEnc ); + pMn->SetMeaning(dTerm); + pMn->SetSynonyms(aStr); + Reference<XMeaning>* pMeaning = aMeanings.getArray(); + pMeaning[j] = pMn; + } + pe++; + } + pTH->CleanUpAfterLookup(&pmean,nmean); + + if (nmean) + { prevTerm = qTerm; prevMeanings = aMeanings; prevLocale = nLanguage; return aMeanings; - } + } - if (stem || !xLngSvcMgr.is()) return noMeanings; + if (stem || !xLngSvcMgr.is()) + return noMeanings; stem = 1; xSpell = uno::Reference< XSpellChecker1 >( xLngSvcMgr->getSpellChecker(), UNO_QUERY ); - if (!xSpell.is() || !xSpell->isValid( A2OU(SPELLML_SUPPORT), nLanguage, rProperties )) { + if (!xSpell.is() || !xSpell->isValid( A2OU(SPELLML_SUPPORT), nLanguage, rProperties )) return noMeanings; - } Reference< XSpellAlternatives > xTmpRes; xTmpRes = xSpell->spell( A2OU("<?xml?><query type='stem'><word>") + rTerm + A2OU("</word></query>"), nLanguage, rProperties ); - if (xTmpRes.is()) { + if (xTmpRes.is()) + { Sequence<OUString>seq = xTmpRes->getAlternatives(); #if 0 - for (int i = 0; i < seq.getLength(); i++) { - OString o = OUStringToOString(seq[i], rtl_getTextEncodingFromUnixCharset("UTF-8")); + for (int i = 0; i < seq.getLength(); i++) + { + OString o = OUStringToOString(seq[i], RTL_TEXTENCODING_UTF8); fprintf(stderr, "%d: %s\n", i + 1, o.pData->buffer); } #endif - if (seq.getLength() > 0) { + if (seq.getLength() > 0) + { rTerm = seq[0]; // XXX Use only the first stem continue; } @@ -529,17 +540,21 @@ Sequence < Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL // stem the last word of the synonym (for categories after affixation) rTerm = rTerm.trim(); sal_Int32 pos = rTerm.lastIndexOf(' '); - if (!pos) return noMeanings; + if (!pos) + return noMeanings; xTmpRes = xSpell->spell( A2OU("<?xml?><query type='stem'><word>") + rTerm.copy(pos + 1) + A2OU("</word></query>"), nLanguage, rProperties ); - if (xTmpRes.is()) { + if (xTmpRes.is()) + { Sequence<OUString>seq = xTmpRes->getAlternatives(); - if (seq.getLength() > 0) { + if (seq.getLength() > 0) + { pTerm = rTerm.copy(pos + 1); rTerm = rTerm.copy(0, pos + 1) + seq[0]; -#if 0 - for (int i = 0; i < seq.getLength(); i++) { - OString o = OUStringToOString(seq[i], rtl_getTextEncodingFromUnixCharset("UTF-8")); +#if 0 + for (int i = 0; i < seq.getLength(); i++) + { + OString o = OUStringToOString(seq[i], RTL_TEXTENCODING_UTF8); fprintf(stderr, "%d: %s\n", i + 1, o.pData->buffer); } #endif @@ -547,12 +562,11 @@ Sequence < Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL } } break; - } + } return noMeanings; } - Reference< XInterface > SAL_CALL Thesaurus_CreateInstance( const Reference< XMultiServiceFactory > & /*rSMgr*/ ) throw(Exception) @@ -562,8 +576,7 @@ Reference< XInterface > SAL_CALL Thesaurus_CreateInstance( } -OUString SAL_CALL - Thesaurus::getServiceDisplayName( const Locale& /*rLocale*/ ) +OUString SAL_CALL Thesaurus::getServiceDisplayName( const Locale& /*rLocale*/ ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -571,8 +584,7 @@ OUString SAL_CALL } -void SAL_CALL - Thesaurus::initialize( const Sequence< Any >& rArguments ) +void SAL_CALL Thesaurus::initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -603,24 +615,26 @@ void SAL_CALL sal_uInt16 SAL_CALL Thesaurus::capitalType(const OUString& aTerm, CharClass * pCC) { sal_Int32 tlen = aTerm.getLength(); - if ((pCC) && (tlen)) { - String aStr(aTerm); - sal_Int32 nc = 0; - for (USHORT tindex = 0; tindex < tlen; tindex++) { - if (pCC->getCharacterType(aStr,tindex) & - ::com::sun::star::i18n::KCharacterType::UPPER) nc++; - } - - if (nc == 0) return (sal_uInt16) CAPTYPE_NOCAP; - - if (nc == tlen) return (sal_uInt16) CAPTYPE_ALLCAP; + if ((pCC) && (tlen)) + { + String aStr(aTerm); + sal_Int32 nc = 0; + for (USHORT tindex = 0; tindex < tlen; tindex++) + { + if (pCC->getCharacterType(aStr,tindex) & + ::com::sun::star::i18n::KCharacterType::UPPER) nc++; + } - if ((nc == 1) && (pCC->getCharacterType(aStr,0) & - ::com::sun::star::i18n::KCharacterType::UPPER)) - return (sal_uInt16) CAPTYPE_INITCAP; + if (nc == 0) + return (sal_uInt16) CAPTYPE_NOCAP; + if (nc == tlen) + return (sal_uInt16) CAPTYPE_ALLCAP; + if ((nc == 1) && (pCC->getCharacterType(aStr,0) & + ::com::sun::star::i18n::KCharacterType::UPPER)) + return (sal_uInt16) CAPTYPE_INITCAP; - return (sal_uInt16) CAPTYPE_MIXED; - } + return (sal_uInt16) CAPTYPE_MIXED; + } return (sal_uInt16) CAPTYPE_UNKNOWN; } @@ -628,38 +642,40 @@ sal_uInt16 SAL_CALL Thesaurus::capitalType(const OUString& aTerm, CharClass * pC OUString SAL_CALL Thesaurus::makeLowerCase(const OUString& aTerm, CharClass * pCC) { - if (pCC) - return pCC->toLower_rtl(aTerm, 0, aTerm.getLength()); - return aTerm; + if (pCC) + return pCC->toLower_rtl(aTerm, 0, aTerm.getLength()); + return aTerm; } OUString SAL_CALL Thesaurus::makeUpperCase(const OUString& aTerm, CharClass * pCC) { - if (pCC) - return pCC->toUpper_rtl(aTerm, 0, aTerm.getLength()); - return aTerm; + if (pCC) + return pCC->toUpper_rtl(aTerm, 0, aTerm.getLength()); + return aTerm; } OUString SAL_CALL Thesaurus::makeInitCap(const OUString& aTerm, CharClass * pCC) { - sal_Int32 tlen = aTerm.getLength(); - if ((pCC) && (tlen)) { - OUString bTemp = aTerm.copy(0,1); - if (tlen > 1) - return ( pCC->toUpper_rtl(bTemp, 0, 1) - + pCC->toLower_rtl(aTerm,1,(tlen-1)) ); + sal_Int32 tlen = aTerm.getLength(); + if ((pCC) && (tlen)) + { + OUString bTemp = aTerm.copy(0,1); + if (tlen > 1) + { + return ( pCC->toUpper_rtl(bTemp, 0, 1) + + pCC->toLower_rtl(aTerm,1,(tlen-1)) ); + } - return pCC->toUpper_rtl(bTemp, 0, 1); + return pCC->toUpper_rtl(bTemp, 0, 1); } - return aTerm; + return aTerm; } -void SAL_CALL - Thesaurus::dispose() +void SAL_CALL Thesaurus::dispose() throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -673,8 +689,7 @@ void SAL_CALL } -void SAL_CALL - Thesaurus::addEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL Thesaurus::addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -684,8 +699,7 @@ void SAL_CALL } -void SAL_CALL - Thesaurus::removeEventListener( const Reference< XEventListener >& rxListener ) +void SAL_CALL Thesaurus::removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException) { MutexGuard aGuard( GetLinguMutex() ); @@ -739,31 +753,6 @@ Sequence< OUString > Thesaurus::getSupportedServiceNames_Static() return aSNS; } - -sal_Bool SAL_CALL Thesaurus_writeInfo( - void * /*pServiceManager*/, registry::XRegistryKey * pRegistryKey ) -{ - try - { - String aImpl( '/' ); - aImpl += Thesaurus::getImplementationName_Static().getStr(); - aImpl.AppendAscii( "/UNO/SERVICES" ); - Reference< registry::XRegistryKey > xNewKey = - pRegistryKey->createKey( aImpl ); - Sequence< OUString > aServices = - Thesaurus::getSupportedServiceNames_Static(); - for( INT32 i = 0; i < aServices.getLength(); i++ ) - xNewKey->createKey( aServices.getConstArray()[i] ); - - return sal_True; - } - catch(Exception &) - { - return sal_False; - } -} - - void * SAL_CALL Thesaurus_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, void * ) { diff --git a/lingucomponent/source/thesaurus/libnth/nthesimp.hxx b/lingucomponent/source/thesaurus/libnth/nthesimp.hxx index 94bbb6fb3ea6..e6d447879701 100644 --- a/lingucomponent/source/thesaurus/libnth/nthesimp.hxx +++ b/lingucomponent/source/thesaurus/libnth/nthesimp.hxx @@ -116,55 +116,27 @@ public: virtual ~Thesaurus(); // XSupportedLocales (for XThesaurus) - virtual Sequence< Locale > SAL_CALL - getLocales() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - hasLocale( const Locale& rLocale ) - throw(RuntimeException); + virtual Sequence< Locale > SAL_CALL getLocales() throw(RuntimeException); + virtual sal_Bool SAL_CALL hasLocale( const Locale& rLocale ) throw(RuntimeException); // XThesaurus - virtual Sequence< Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL - queryMeanings( const OUString& rTerm, const Locale& rLocale, - const PropertyValues& rProperties ) - throw(IllegalArgumentException, - RuntimeException); + virtual Sequence< Reference < ::com::sun::star::linguistic2::XMeaning > > SAL_CALL queryMeanings( const OUString& rTerm, const Locale& rLocale, const PropertyValues& rProperties ) throw(IllegalArgumentException, RuntimeException); // XServiceDisplayName - virtual OUString SAL_CALL - getServiceDisplayName( const Locale& rLocale ) - throw(RuntimeException); + virtual OUString SAL_CALL getServiceDisplayName( const Locale& rLocale ) throw(RuntimeException); // XInitialization - virtual void SAL_CALL - initialize( const Sequence< Any >& rArguments ) - throw(Exception, RuntimeException); + virtual void SAL_CALL initialize( const Sequence< Any >& rArguments ) throw(Exception, RuntimeException); // XComponent - virtual void SAL_CALL - dispose() - throw(RuntimeException); - virtual void SAL_CALL - addEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - virtual void SAL_CALL - removeEventListener( const Reference< XEventListener >& rxListener ) - throw(RuntimeException); - - //////////////////////////////////////////////////////////// - // Service specific part - // + virtual void SAL_CALL dispose() throw(RuntimeException); + virtual void SAL_CALL addEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); + virtual void SAL_CALL removeEventListener( const Reference< XEventListener >& rxListener ) throw(RuntimeException); // XServiceInfo - virtual OUString SAL_CALL - getImplementationName() - throw(RuntimeException); - virtual sal_Bool SAL_CALL - supportsService( const OUString& rServiceName ) - throw(RuntimeException); - virtual Sequence< OUString > SAL_CALL - getSupportedServiceNames() - throw(RuntimeException); + virtual OUString SAL_CALL getImplementationName() throw(RuntimeException); + virtual sal_Bool SAL_CALL supportsService( const OUString& rServiceName ) throw(RuntimeException); + virtual Sequence< OUString > SAL_CALL getSupportedServiceNames() throw(RuntimeException); static inline OUString @@ -183,8 +155,7 @@ private: static ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XSpellChecker1 > xSpell; */ - static ::com::sun::star::uno::Reference< - ::com::sun::star::linguistic2::XLinguServiceManager > GetLngSvcMgr(); + static ::com::sun::star::uno::Reference< ::com::sun::star::linguistic2::XLinguServiceManager > GetLngSvcMgr(); }; diff --git a/lingucomponent/source/thesaurus/libnth/ntreg.cxx b/lingucomponent/source/thesaurus/libnth/ntreg.cxx index 14b3b3c896d4..f622e1e094c8 100644 --- a/lingucomponent/source/thesaurus/libnth/ntreg.cxx +++ b/lingucomponent/source/thesaurus/libnth/ntreg.cxx @@ -41,9 +41,6 @@ using namespace com::sun::star::registry; // declaration of external RegEntry-functions defined by the service objects // -extern sal_Bool SAL_CALL Thesaurus_writeInfo( - void * /*pServiceManager*/, XRegistryKey * pRegistryKey ); - extern void * SAL_CALL Thesaurus_getFactory( const sal_Char * pImplName, XMultiServiceFactory * pServiceManager, @@ -56,12 +53,6 @@ extern void * SAL_CALL Thesaurus_getFactory( extern "C" { -sal_Bool SAL_CALL component_writeInfo( - void * pServiceManager, XRegistryKey * pRegistryKey ) -{ - return Thesaurus_writeInfo( pServiceManager, pRegistryKey ); -} - void SAL_CALL component_getImplementationEnvironment( const sal_Char ** ppEnvTypeName, uno_Environment ** /*ppEnv*/ ) { diff --git a/lingucomponent/source/thesaurus/mythes/Makefile b/lingucomponent/source/thesaurus/mythes/Makefile deleted file mode 100644 index b1d811296714..000000000000 --- a/lingucomponent/source/thesaurus/mythes/Makefile +++ /dev/null @@ -1,39 +0,0 @@ - -CXX=g++ - -CXXFLAGS= -O2 -Wall -ansi -pedantic -I. - -LDFLAGS=-L. -lmythes - -LIBS=libmythes.a - -AR=ar rc -RANLIB=ranlib - -OBJS = mythes.o - -all: example - -libmythes.a: $(OBJS) - $(AR) $@ $(OBJS) - -@ ($(RANLIB) $@ || true) >/dev/null 2>&1 - -example: example.o $(LIBS) - $(CXX) $(CXXFLAGS) -o $@ example.o $(LDFLAGS) - -%.o: %.cxx - $(CXX) $(CXXFLAGS) -c $< - -clean: - rm -f *.o *~ example libthes.a - -distclean: clean - -depend: - makedepend -- $(CXXFLAGS) -- *.[ch]xx - -# DO NOT DELETE THIS LINE -- make depend depends on it. - -mythes.o: mythes.hxx -example.o: mythes.hxx - diff --git a/lingucomponent/source/thesaurus/mythes/README b/lingucomponent/source/thesaurus/mythes/README deleted file mode 100644 index 421f16a712fe..000000000000 --- a/lingucomponent/source/thesaurus/mythes/README +++ /dev/null @@ -1,60 +0,0 @@ -MyThes is a simple thesaurus that uses a structured -text data file and an index file with binary search -to lookup words and phrases and return information -on part of speech, meanings, and synonyms - -MyThes was written to provide a thesaurus for the -OpenOffice.org project - -The Main features of MyThes are: - -1. written in C++ to make it easier to interface with - Pspell, OpenOffice, AbiWord, etc - -2. it is stateless, uses no static variables and - should be completely reentrant with no ifdefs - -3. it compiles with -ansi and -pedantic and -Wall - with no warnings so it should be quite portable - -4. it uses a perl program to read the structured - text file and create the index needed for bianry - searching (see dictionaries/en_US/th_gen_idx.pl) - -5. it is very simple with *lots* of comments. - The main "smarts" are in the structure of the - text file that makes up the thesaurus data - -6. It comes with a ready-to-go structured thesaurus - data file for en_US extracted from the WordNet-2.0 data. - (see dictioanries/en_US/th_en_US_new.dat) - - Please see WordNet_license.txt and WordNet_readme.txt - for more information on the very useful project! - (found in dictionaries/en_US/) - -7. The source code has a BSD license (and no advertising clause) - - -MyThes has the world's simplest Makefile and no -configure support. It does come with a simple example -program that looks up some words and returns meanings -and synonyms. - -To build it simply do the following: - -unzip mythes.zip -cd mythes -make - -To run the example program: -./example th_en_US_new.idx th_en_US_new.dat checkme.lst - -Please play around with it and let me know -what you think. - -Thanks, - -Kevin Hendricks -kevin.hendricks@sympatico.ca - diff --git a/lingucomponent/source/thesaurus/mythes/checkme.lst b/lingucomponent/source/thesaurus/mythes/checkme.lst deleted file mode 100644 index 120d343a9e0f..000000000000 --- a/lingucomponent/source/thesaurus/mythes/checkme.lst +++ /dev/null @@ -1,4 +0,0 @@ -simple -complex -junk -jhjhjh diff --git a/lingucomponent/source/thesaurus/mythes/data_layout.txt b/lingucomponent/source/thesaurus/mythes/data_layout.txt deleted file mode 100644 index ef4bc255d96a..000000000000 --- a/lingucomponent/source/thesaurus/mythes/data_layout.txt +++ /dev/null @@ -1,131 +0,0 @@ -Description of the Structure of the Data needed by MyThes --------------------------------------------------------- - -MyThes is very simple. Almost all of the "smarts" are really -in the thesaurus data file itself. - -The format for this file is at follows: - -- no binary data - -- line ending is a newline '\n' and not carriage return/linefeeds - -- Line 1 is a character string that describes the encoding -used for the file. It is up to the calling program to convert -to and from this encoding if necessary. - - ISO8859-1 is used by the th_en_US_new.dat file. - - Strings currently recognized by OpenOffice.org are: - - UTF-8 - ISO8859-1 - ISO8859-2 - ISO8859-3 - ISO8859-4 - ISO8859-5 - ISO8859-6 - ISO8859-7 - ISO8859-8 - ISO8859-9 - ISO8859-10 - KOI8-R - CP-1251 - ISO8859-14 - ISCII-DEVANAGARI - - -- All of the remaning lines of the file follow this structure - -entry|num_mean -pos|syn1_mean|syn2|... -. -. -. -pos|mean_syn1|syn2|... - - -where: - - entry - all lowercase version of the word or phrase being described - num_mean - number of meanings for this entry - - There is one meaning per line and each meaning is comprised of - - pos - part of speech or other meaning specific description - syn1_mean - synonym 1 also used to describe the meaning itself - syn2 - synonym 2 for that meaning etc. - - -To make this even more clearer, here is actual data for the -entry "simple". - -simple|9 -(adj)|simple |elemental|ultimate|oversimplified|simplistic|simplex|simplified|unanalyzable| -undecomposable|uncomplicated|unsophisticated|easy|plain|unsubdivided -(adj)|elementary|uncomplicated|unproblematic|easy -(adj)|bare|mere|plain -(adj)|childlike|wide-eyed|dewy-eyed|naive |naif -(adj)|dim-witted|half-witted|simple-minded|retarded -(adj)|simple |unsubdivided|unlobed|smooth -(adj)|plain -(noun)|herb|herbaceous plant -(noun)|simpleton|person|individual|someone|somebody|mortal|human|soul - - -It says that "simple" has 9 different meanings and each -meaning will have its part of speech and at least 1 synonym -with other if presetn following on the same line. - - - -Once you ahve created your own structured text file you can use -the perl program "th_gen_idx.pl" which can be found in this -directory to create an index file that is used to seek into -your data file by the MyThes code. - -The correct way to run the perl program is as follows: - -cat th_en_US_new.dat | ./th_gen_idx.pl > th_en_US_new.idx - - - -Then if you head the resulting index file you should see the -following: - -ISO8859-1 -142689 -'hood|10 -'s gravenhage|88 -'tween|173 -'tween decks|196 -.22|231 -.22 caliber|319 -.22 calibre|365 -.38 caliber|411 -.38 calibre|457 -.45 caliber|503 -.45 calibre|549 -0|595 -1|666 -1 chronicles|6283 -1 esdras|6336 - - -Line 1 is the same encoding string taken from the -structured thesaurus data file. - -Line 2 is a count of the total number of entries -in your thesaurus. - -All of the remaining lines are of the form - -entry|byte_offset_into_data_file_where_entry_is_found - - -That's all there is too it. - - -Kevin -kevin.hendricks@sympatico.ca - diff --git a/lingucomponent/source/thesaurus/mythes/example.cxx b/lingucomponent/source/thesaurus/mythes/example.cxx deleted file mode 100644 index 31c85989cf26..000000000000 --- a/lingucomponent/source/thesaurus/mythes/example.cxx +++ /dev/null @@ -1,128 +0,0 @@ -/************************************************************************* - * - * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. - * - * Copyright 2000, 2010 Oracle and/or its affiliates. - * - * OpenOffice.org - a multi-platform office productivity suite - * - * This file is part of OpenOffice.org. - * - * OpenOffice.org is free software: you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License version 3 - * only, as published by the Free Software Foundation. - * - * OpenOffice.org is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License version 3 for more details - * (a copy is included in the LICENSE file that accompanied this code). - * - * You should have received a copy of the GNU Lesser General Public License - * version 3 along with OpenOffice.org. If not, see - * <http://www.openoffice.org/license.html> - * for a copy of the LGPLv3 License. - * - ************************************************************************/ - - -// MARKER(update_precomp.py): autogen include statement, do not remove -#include "precompiled_lingucomponent.hxx" -#include <cstring> -#include <cstdlib> -#include <cstdio> - -#include "mythes.hxx" - -extern char * mystrdup(const char * s); - -using namespace std; - -int -main(int argc, char** argv) -{ - - char * af; - char * df; - char * wtc; - FILE* wtclst; - - /* first parse the command line options */ - /* arg1 - index file, arg2 thesaurus data file, arg3 - file of words to check */ - - if (argv[1]) { - af = mystrdup(argv[1]); - } else { - fprintf(stderr,"correct syntax is:\n"); - fprintf(stderr,"example index_file thesaurus_file file_of_words_to_check\n"); - exit(1); - } - if (argv[2]) { - df = mystrdup(argv[2]); - } else { - fprintf(stderr,"correct syntax is:\n"); - fprintf(stderr,"example index_file thesaurus_file file_of_words_to_check\n"); - exit(1); - } - if (argv[3]) { - wtc = mystrdup(argv[3]); - } else { - fprintf(stderr,"correct syntax is:\n"); - fprintf(stderr,"example index_file thesaurus_file file_of_words_to_check\n"); - exit(1); - } - - - /* open the words to check list */ - wtclst = fopen(wtc,"r"); - if (!wtclst) { - fprintf(stderr,"Error - could not open file of words to check\n"); - exit(1); - } - - // open a new thesaurus object - MyThes * pMT= new MyThes(af,df); - - // get the encoding used for the thesaurus data - char * encoding = pMT->get_th_encoding(); - fprintf(stdout,"Thesaurus uses encoding %s\n\n",encoding); - - int k; - char buf[101]; - mentry * pmean; - - while(fgets(buf,100,wtclst)) { - k = strlen(buf); - *(buf + k - 1) = '\0'; - int len = strlen(buf); - int count = pMT->Lookup(buf,len,&pmean); - // don't change value of pmean - // or count since needed for CleanUpAfterLookup routine - mentry* pm = pmean; - if (count) { - fprintf(stdout,"%s has %d meanings\n",buf,count); - for (int i=0; i < count; i++) { - fprintf(stdout," meaning %d: %s\n",i,pm->defn); - for (int j=0; j < pm->count; j++) { - fprintf(stdout," %s\n",pm->psyns[j]); - } - fprintf(stdout,"\n"); - pm++; - } - fprintf(stdout,"\n\n"); - // now clean up all allocated memory - pMT->CleanUpAfterLookup(&pmean,count); - } else { - fprintf(stdout,"\"%s\" is not in thesaurus!\n",buf); - } - } - - delete pMT; - fclose(wtclst); - free(wtc); - free(df); - free(af); - - return 0; -} - diff --git a/lingucomponent/source/thesaurus/mythes/license.readme b/lingucomponent/source/thesaurus/mythes/license.readme deleted file mode 100644 index b6bf70a0c7fe..000000000000 --- a/lingucomponent/source/thesaurus/mythes/license.readme +++ /dev/null @@ -1,34 +0,0 @@ -/* - * Copyright 2003 Kevin B. Hendricks, Stratford, Ontario, Canada - * And Contributors. All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * - * 3. All modifications to the source code must be clearly marked as - * such. Binary redistributions based on modified source code - * must be clearly marked as modified versions in the documentation - * and/or other materials provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY KEVIN B. HENDRICKS AND CONTRIBUTORS - * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS - * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL - * KEVIN B. HENDRICKS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, - * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - * - */ diff --git a/lingucomponent/source/thesaurus/mythes/makefile.mk b/lingucomponent/source/thesaurus/mythes/makefile.mk deleted file mode 100644 index ac45219b97a0..000000000000 --- a/lingucomponent/source/thesaurus/mythes/makefile.mk +++ /dev/null @@ -1,59 +0,0 @@ -#************************************************************************* -# -# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. -# -# Copyright 2000, 2010 Oracle and/or its affiliates. -# -# OpenOffice.org - a multi-platform office productivity suite -# -# This file is part of OpenOffice.org. -# -# OpenOffice.org is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License version 3 -# only, as published by the Free Software Foundation. -# -# OpenOffice.org is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License version 3 for more details -# (a copy is included in the LICENSE file that accompanied this code). -# -# You should have received a copy of the GNU Lesser General Public License -# version 3 along with OpenOffice.org. If not, see -# <http://www.openoffice.org/license.html> -# for a copy of the LGPLv3 License. -# -#************************************************************************* - -PRJ = ..$/..$/.. - -PRJNAME = lingucomponent -TARGET = mythes -LIBTARGET=NO - -#----- Settings --------------------------------------------------------- - -.INCLUDE : settings.mk - -# --- Files -------------------------------------------------------- - -.IF "$(SYSTEM_MYTHES)" == "YES" -@all: - @echo "Using system mythes..." -.ENDIF - -all_target: ALLTAR - - - -SLOFILES= \ - $(SLO)$/mythes.obj - -LIB1TARGET= $(SLB)$/lib$(TARGET).lib -LIB1ARCHIV= $(LB)/lib$(TARGET).a -LIB1OBJFILES= $(SLOFILES) - -# --- Targets ------------------------------------------------------ - -.INCLUDE : target.mk - diff --git a/lingucomponent/source/thesaurus/mythes/mythes.cxx b/lingucomponent/source/thesaurus/mythes/mythes.cxx deleted file mode 100644 index ebb224d92140..000000000000 --- a/lingucomponent/source/thesaurus/mythes/mythes.cxx +++ /dev/null @@ -1,403 +0,0 @@ -/************************************************************************* - * - * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. - * - * Copyright 2000, 2010 Oracle and/or its affiliates. - * - * OpenOffice.org - a multi-platform office productivity suite - * - * This file is part of OpenOffice.org. - * - * OpenOffice.org is free software: you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License version 3 - * only, as published by the Free Software Foundation. - * - * OpenOffice.org is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License version 3 for more details - * (a copy is included in the LICENSE file that accompanied this code). - * - * You should have received a copy of the GNU Lesser General Public License - * version 3 along with OpenOffice.org. If not, see - * <http://www.openoffice.org/license.html> - * for a copy of the LGPLv3 License. - * - ************************************************************************/ - - -// MARKER(update_precomp.py): autogen include statement, do not remove -#include "precompiled_lingucomponent.hxx" -#include "license.readme" -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <errno.h> - -#include "mythes.hxx" - - - -MyThes::MyThes(const char* idxpath, const char * datpath) -{ - nw = 0; - encoding = NULL; - list = NULL; - offst = NULL; - - if (thInitialize(idxpath, datpath) != 1) { - fprintf(stderr,"Error - can't open %s or %s\n",idxpath, datpath); - fflush(stderr); - thCleanup(); - // did not initialize properly - throw exception? - } -} - - -MyThes::~MyThes() -{ - thCleanup(); -} - - -int MyThes::thInitialize(const char* idxpath, const char* datpath) -{ - - // open the index file - FILE * pifile = fopen(idxpath,"r"); - if (!pifile) { - return 0; - } - - // parse in encoding and index size */ - char * wrd; - wrd = (char *)calloc(1, MAX_WD_LEN); - if (!wrd) { - fprintf(stderr,"Error - bad memory allocation\n"); - fflush(stderr); - fclose(pifile); - return 0; - } - int len = readLine(pifile,wrd,MAX_WD_LEN); - encoding = mystrdup(wrd); - len = readLine(pifile,wrd,MAX_WD_LEN); - int idxsz = atoi(wrd); - - - // now allocate list, offst for the given size - list = (char**) calloc(idxsz,sizeof(char*)); - offst = (unsigned int*) calloc(idxsz,sizeof(unsigned int)); - - if ( (!(list)) || (!(offst)) ) { - fprintf(stderr,"Error - bad memory allocation\n"); - fflush(stderr); - fclose(pifile); - return 0; - } - - // now parse the remaining lines of the index - len = readLine(pifile,wrd,MAX_WD_LEN); - while (len > 0) - { - int np = mystr_indexOfChar(wrd,'|'); - if (nw < idxsz) { - if (np >= 0) { - *(wrd+np) = '\0'; - list[nw] = (char *)calloc(1,(np+1)); - if (!list[nw]) { - fprintf(stderr,"Error - bad memory allocation\n"); - fflush(stderr); - fclose(pifile); - return 0; - } - memcpy((list[nw]),wrd,np); - offst[nw] = atoi(wrd+np+1); - nw++; - } - } - len = readLine(pifile,wrd,MAX_WD_LEN); - } - - free((void *)wrd); - fclose(pifile); - - /* next open the data file */ - pdfile = fopen(datpath,"r"); - if (!pdfile) { - return 0; - } - - return 1; -} - - -void MyThes::thCleanup() -{ - /* first close the data file */ - if (pdfile) { - fclose(pdfile); - pdfile=NULL; - } - - if (list) - { - /* now free up all the allocated strings on the list */ - for (int i=0; i < nw; i++) - { - if (list[i]) { - free(list[i]); - list[i] = 0; - } - } - free((void*)list); - } - - if (encoding) free((void*)encoding); - if (offst) free((void*)offst); - - encoding = NULL; - list = NULL; - offst = NULL; - nw = 0; -} - - - -// lookup text in index and count of meanings and a list of meaning entries -// with each entry having a synonym count and pointer to an -// array of char * (i.e the synonyms) -// -// note: calling routine should call CleanUpAfterLookup with the original -// meaning point and count to properly deallocate memory - -int MyThes::Lookup(const char * pText, int len, mentry** pme) -{ - - *pme = NULL; - - // handle the case of missing file or file related errors - if (! pdfile) return 0; - - long offset = 0; - - /* copy search word and make sure null terminated */ - char * wrd = (char *) calloc(1,(len+1)); - memcpy(wrd,pText,len); - - /* find it in the list */ - int idx = nw > 0 ? binsearch(wrd,list,nw) : -1; - free(wrd); - if (idx < 0) return 0; - - // now seek to the offset - offset = (long) offst[idx]; - int rc = fseek(pdfile,offset,SEEK_SET); - if (rc) { - return 0; - } - - // grab the count of the number of meanings - // and allocate a list of meaning entries - char * buf = NULL; - buf = (char *) malloc( MAX_LN_LEN ); - if (!buf) return 0; - readLine(pdfile, buf, (MAX_LN_LEN-1)); - int np = mystr_indexOfChar(buf,'|'); - if (np < 0) { - free(buf); - return 0; - } - int nmeanings = atoi(buf+np+1); - *pme = (mentry*) malloc( nmeanings * sizeof(mentry) ); - if (!(*pme)) { - free(buf); - return 0; - } - - // now read in each meaning and parse it to get defn, count and synonym lists - mentry* pm = *(pme); - char dfn[MAX_WD_LEN]; - - for (int j = 0; j < nmeanings; j++) { - readLine(pdfile, buf, (MAX_LN_LEN-1)); - - pm->count = 0; - pm->psyns = NULL; - pm->defn = NULL; - - // store away the part of speech for later use - char * p = buf; - char * pos = NULL; - np = mystr_indexOfChar(p,'|'); - if (np >= 0) { - *(buf+np) = '\0'; - pos = mystrdup(p); - p = p + np + 1; - } else { - pos = mystrdup(""); - } - - // count the number of fields in the remaining line - int nf = 1; - char * d = p; - np = mystr_indexOfChar(d,'|'); - while ( np >= 0 ) { - nf++; - d = d + np + 1; - np = mystr_indexOfChar(d,'|'); - } - pm->count = nf; - pm->psyns = (char **) malloc(nf*sizeof(char*)); - - // fill in the synonym list - d = p; - for (int jj = 0; jj < nf; jj++) - { - np = mystr_indexOfChar(d,'|'); - if (np > 0) - { - *(d+np) = '\0'; - pm->psyns[jj] = mystrdup(d); - d = d + np + 1; - } - else - { - pm->psyns[jj] = mystrdup(d); - } - } - - // add pos to first synonym to create the definition - int k = strlen(pos); - int m = strlen(pm->psyns[0]); - if ((k+m) < (MAX_WD_LEN - 1)) { - strncpy(dfn,pos,k); - *(dfn+k) = ' '; - strncpy((dfn+k+1),(pm->psyns[0]),m+1); - pm->defn = mystrdup(dfn); - } else { - pm->defn = mystrdup(pm->psyns[0]); - } - free(pos); - pm++; - - } - free(buf); - - return nmeanings; -} - - - -void MyThes::CleanUpAfterLookup(mentry ** pme, int nmeanings) -{ - - if (nmeanings == 0) return; - if ((*pme) == NULL) return; - - mentry * pm = *pme; - - for (int i = 0; i < nmeanings; i++) { - int count = pm->count; - for (int j = 0; j < count; j++) { - if (pm->psyns[j]) free(pm->psyns[j]); - pm->psyns[j] = NULL; - } - if (pm->psyns) free(pm->psyns); - pm->psyns = NULL; - if (pm->defn) free(pm->defn); - pm->defn = NULL; - pm->count = 0; - pm++; - } - pm = *pme; - free(pm); - *pme = NULL; - return; -} - - -// read a line of text from a text file stripping -// off the line terminator and replacing it with -// a null string terminator. -// returns: -1 on error or the number of characters in -// in the returning string - -// A maximum of nc characters will be returned - -int MyThes::readLine(FILE * pf, char * buf, int nc) -{ - - if (fgets(buf,nc,pf)) { - mychomp(buf); - return strlen(buf); - } - return -1; -} - - - -// performs a binary search on null terminated character -// strings -// -// returns: -1 on not found -// index of wrd in the list[] - -int MyThes::binsearch(char * sw, char* _list[], int nlst) -{ - int lp, up, mp, j, indx; - lp = 0; - up = nlst-1; - indx = -1; - if (strcmp(sw,_list[lp]) < 0) return -1; - if (strcmp(sw,_list[up]) > 0) return -1; - while (indx < 0 ) { - mp = (int)((lp+up) >> 1); - j = strcmp(sw,_list[mp]); - if ( j > 0) { - lp = mp + 1; - } else if (j < 0 ) { - up = mp - 1; - } else { - indx = mp; - } - if (lp > up) return -1; - } - return indx; -} - -char * MyThes::get_th_encoding() -{ - if (encoding) return encoding; - return NULL; -} - - -// string duplication routine -char * MyThes::mystrdup(const char * p) -{ - int sl = strlen(p) + 1; - char * d = (char *)malloc(sl); - if (d) { - memcpy(d,p,sl); - return d; - } - return NULL; -} - -// remove cross-platform text line end characters -void MyThes::mychomp(char * s) -{ - int k = strlen(s); - if ((k > 0) && ((*(s+k-1)=='\r') || (*(s+k-1)=='\n'))) *(s+k-1) = '\0'; - if ((k > 1) && (*(s+k-2) == '\r')) *(s+k-2) = '\0'; -} - - -// return index of char in string -int MyThes::mystr_indexOfChar(const char * d, int c) -{ - char * p = strchr((char *)d,c); - if (p) return (int)(p-d); - return -1; -} - diff --git a/lingucomponent/source/thesaurus/mythes/mythes.hxx b/lingucomponent/source/thesaurus/mythes/mythes.hxx deleted file mode 100644 index 539e6723c42d..000000000000 --- a/lingucomponent/source/thesaurus/mythes/mythes.hxx +++ /dev/null @@ -1,76 +0,0 @@ -#ifndef _MYTHES_HXX_ -#define _MYTHES_HXX_ - -// some maximum sizes for buffers -#define MAX_WD_LEN 200 -#define MAX_LN_LEN 16384 - - -// a meaning with definition, count of synonyms and synonym list -struct mentry { - char* defn; - int count; - char** psyns; -}; - - -class MyThes -{ - - int nw; /* number of entries in thesaurus */ - char** list; /* stores word list */ - unsigned int* offst; /* stores offset list */ - char * encoding; /* stores text encoding; */ - - FILE *pdfile; - - // disallow copy-constructor and assignment-operator for now - MyThes(); - MyThes(const MyThes &); - MyThes & operator = (const MyThes &); - -public: - MyThes(const char* idxpath, const char* datpath); - ~MyThes(); - - // lookup text in index and return number of meanings - // each meaning entry has a defintion, synonym count and pointer - // when complete return the *original* meaning entry and count via - // CleanUpAfterLookup to properly handle memory deallocation - - int Lookup(const char * pText, int len, mentry** pme); - - void CleanUpAfterLookup(mentry** pme, int nmean); - - char* get_th_encoding(); - -private: - // Open index and dat files and load list array - int thInitialize (const char* indxpath, const char* datpath); - - // internal close and cleanup dat and idx files - void thCleanup (); - - // read a text line (\n terminated) stripping off line terminator - int readLine(FILE * pf, char * buf, int nc); - - // binary search on null terminated character strings - int binsearch(char * wrd, char* list[], int nlst); - - // string duplication routine - char * mystrdup(const char * p); - - // remove cross-platform text line end characters - void mychomp(char * s); - - // return index of char in string - int mystr_indexOfChar(const char * d, int c); - -}; - -#endif - - - - - |