API Docs for SAX and DOM                 XMLString.hpp Go to the documentation of this file. /* * The Apache Software License, Version 1.1 * * Copyright (c) 1999-2001 The Apache Software Foundation. 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. The end-user documentation included with the redistribution, * if any, must include the following acknowledgment: * "This product includes software developed by the * Apache Software Foundation (http://www.apache.org/)." * Alternately, this acknowledgment may appear in the software itself, * if and wherever such third-party acknowledgments normally appear. * * 4. The names "Xerces" and "Apache Software Foundation" must * not be used to endorse or promote products derived from this * software without prior written permission. For written * permission, please contact apache\@apache.org. * * 5. Products derived from this software may not be called "Apache", * nor may "Apache" appear in their name, without prior written * permission of the Apache Software Foundation. * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED 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 THE APACHE SOFTWARE FOUNDATION OR * ITS 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. * ==================================================================== * * This software consists of voluntary contributions made by many * individuals on behalf of the Apache Software Foundation, and was * originally based on software copyright (c) 1999, International * Business Machines, Inc., http://www.ibm.com . For more information * on the Apache Software Foundation, please see * <http://www.apache.org/>. */ /* * $Log: XMLString.hpp,v $ * Revision 1.23 2001/06/13 14:07:55 peiyongz * isValidaEncName() to validate an encoding name (EncName) * * Revision 1.22 2001/05/23 15:44:51 tng * Schema: NormalizedString fix. By Pei Yong Zhang. * * Revision 1.21 2001/05/11 13:26:31 tng * Copyright update. * * Revision 1.20 2001/05/09 18:43:30 tng * Add StringDatatypeValidator and BooleanDatatypeValidator. By Pei Yong Zhang. * * Revision 1.19 2001/05/03 20:34:35 tng * Schema: SchemaValidator update * * Revision 1.18 2001/05/03 19:17:35 knoaman * TraverseSchema Part II. * * Revision 1.17 2001/03/21 21:56:13 tng * Schema: Add Schema Grammar, Schema Validator, and split the DTDValidator into DTDValidator, DTDScanner, and DTDGrammar. * * Revision 1.16 2001/03/02 20:52:46 knoaman * Schema: Regular expression - misc. updates for error messages, * and additions of new functions to XMLString class. * * Revision 1.15 2001/01/15 21:26:34 tng * Performance Patches by David Bertoni. * * Details: (see xerces-c-dev mailing Jan 14) * XMLRecognizer.cpp: the internal encoding string XMLUni::fgXMLChEncodingString * was going through this function numerous times. As a result, the top hot-spot * for the parse was _wcsicmp(). The real problem is that the Microsofts wide string * functions are unbelievably slow. For things like encodings, it might be * better to use a special comparison function that only considers a-z and * A-Z as characters with case. This works since the character set for * encodings is limit to printable ASCII characters. * * XMLScanner2.cpp: This also has some case-sensitive vs. insensitive compares. * They are also much faster. The other tweak is to only make a copy of an attribute * string if it needs to be split. And then, the strategy is to try to use a * stack-based buffer, rather than a dynamically-allocated one. * * SAX2XMLReaderImpl.cpp: Again, more case-sensitive vs. insensitive comparisons. * * KVStringPair.cpp & hpp: By storing the size of the allocation, the storage can * likely be re-used many times, cutting down on dynamic memory allocations. * * XMLString.hpp: a more efficient implementation of stringLen(). * * DTDValidator.cpp: another case of using a stack-based buffer when possible * * These patches made a big difference in parse time in some of our test * files, especially the ones are very attribute-heavy. * * Revision 1.14 2000/10/13 22:47:57 andyh * Fix bug (failure to null-terminate result) in XMLString::trim(). * Patch contributed by Nadav Aharoni * * Revision 1.13 2000/04/12 18:42:15 roddey * Improved docs in terms of what 'max chars' means in the method * parameters. * * Revision 1.12 2000/04/06 19:42:51 rahulj * Clarified how big the target buffer should be in the API * documentation. * * Revision 1.11 2000/03/23 01:02:38 roddey * Updates to the XMLURL class to correct a lot of parsing problems * and to add support for the port number. Updated the URL tests * to test some of this new stuff. * * Revision 1.10 2000/03/20 23:00:46 rahulj * Moved the inline definition of stringLen before the first * use. This satisfied the HP CC compiler. * * Revision 1.9 2000/03/02 19:54:49 roddey * This checkin includes many changes done while waiting for the * 1.1.0 code to be finished. I can't list them all here, but a list is * available elsewhere. * * Revision 1.8 2000/02/24 20:05:26 abagchi * Swat for removing Log from API docs * * Revision 1.7 2000/02/16 18:51:52 roddey * Fixed some facts in the docs and reformatted the docs to stay within * a reasonable line width. * * Revision 1.6 2000/02/16 17:07:07 abagchi * Added API docs * * Revision 1.5 2000/02/06 07:48:06 rahulj * Year 2K copyright swat. * * Revision 1.4 2000/01/12 00:16:23 roddey * Changes to deal with multiply nested, relative pathed, entities and to deal * with the new URL class changes. * * Revision 1.3 1999/12/18 00:18:10 roddey * More changes to support the new, completely orthagonal support for * intrinsic encodings. * * Revision 1.2 1999/12/15 19:41:28 roddey * Support for the new transcoder system, where even intrinsic encodings are * done via the same transcoder abstraction as external ones. * * Revision 1.1.1.1 1999/11/09 01:05:52 twl * Initial checkin * * Revision 1.2 1999/11/08 20:45:21 rahul * Swat for adding in Product name and CVS comment log variable. * */ #if !defined(XMLSTRING_HPP) #define XMLSTRING_HPP #include <util/XercesDefs.hpp> #include <util/RefVectorOf.hpp> class XMLLCPTranscoder; class XMLString { public: /* Static methods for native character mode string manipulation */ static void binToText ( const unsigned int toFormat , char* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const unsigned int toFormat , XMLCh* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const unsigned long toFormat , char* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const unsigned long toFormat , XMLCh* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const long toFormat , char* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const long toFormat , XMLCh* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const int toFormat , char* const toFill , const unsigned int maxChars , const unsigned int radix ); static void binToText ( const int toFormat , XMLCh* const toFill , const unsigned int maxChars , const unsigned int radix ); static bool textToBin ( const XMLCh* const toConvert , unsigned int& toFill ); static int parseInt ( const XMLCh* const toConvert ); static void catString ( char* const target , const char* const src ); static void catString ( XMLCh* const target , const XMLCh* const src ); static int compareIString ( const char* const str1 , const char* const str2 ); static int compareIString ( const XMLCh* const str1 , const XMLCh* const str2 ); static int compareNString ( const char* const str1 , const char* const str2 , const unsigned int count ); static int compareNString ( const XMLCh* const str1 , const XMLCh* const str2 , const unsigned int count ); static int compareNIString ( const char* const str1 , const char* const str2 , const unsigned int count ); static int compareNIString ( const XMLCh* const str1 , const XMLCh* const str2 , const unsigned int count ); static int compareString ( const char* const str1 , const char* const str2 ); static int compareString ( const XMLCh* const str1 , const XMLCh* const str2 ); static bool regionMatches ( const XMLCh* const str1 , const int offset1 , const XMLCh* const str2 , const int offset2 , const unsigned int charCount ); static bool regionIMatches ( const XMLCh* const str1 , const int offset1 , const XMLCh* const str2 , const int offset2 , const unsigned int charCount ); static void copyString ( char* const target , const char* const src ); static void copyString ( XMLCh* const target , const XMLCh* const src ); static bool copyNString ( XMLCh* const target , const XMLCh* const src , const unsigned int maxChars ); static unsigned int hash ( const char* const tohash , const unsigned int hashModulus ); static unsigned int hash ( const XMLCh* const toHash , const unsigned int hashModulus ); static unsigned int hashN ( const XMLCh* const toHash , const unsigned int numChars , const unsigned int hashModulus ); static int indexOf(const char* const toSearch, const char ch); static int indexOf(const XMLCh* const toSearch, const XMLCh ch); static int indexOf ( const char* const toSearch , const char chToFind , const unsigned int fromIndex ); static int indexOf ( const XMLCh* const toSearch , const XMLCh chToFind , const unsigned int fromIndex ); static int lastIndexOf(const char* const toSearch, const char ch); static int lastIndexOf(const XMLCh* const toSearch, const XMLCh ch); static int lastIndexOf ( const char* const toSearch , const char chToFind , const unsigned int fromIndex ); static int lastIndexOf ( const XMLCh* const toSearch , const XMLCh ch , const unsigned int fromIndex ); static void moveChars ( XMLCh* const targetStr , const XMLCh* const srcStr , const unsigned int count ); static void subString ( char* const targetStr , const char* const srcStr , const int startIndex , const int endIndex ); static void subString ( XMLCh* const targetStr , const XMLCh* const srcStr , const int startIndex , const int endIndex ); static char* replicate(const char* const toRep); static XMLCh* replicate(const XMLCh* const toRep); static bool startsWith ( const char* const toTest , const char* const prefix ); static bool startsWith ( const XMLCh* const toTest , const XMLCh* const prefix ); static bool startsWithI ( const char* const toTest , const char* const prefix ); static bool startsWithI ( const XMLCh* const toTest , const XMLCh* const prefix ); static bool endsWith ( const XMLCh* const toTest , const XMLCh* const prefix ); static const XMLCh* findAny ( const XMLCh* const toSearch , const XMLCh* const searchList ); static XMLCh* findAny ( XMLCh* const toSearch , const XMLCh* const searchList ); static unsigned int stringLen(const char* const src); static unsigned int stringLen(const XMLCh* const src); static bool isValidNCName(const XMLCh* const name); static bool isValidEncName(const XMLCh* const name); static bool isAlpha(XMLCh const theChar); static bool isDigit(XMLCh const theChar); static void cut ( XMLCh* const toCutFrom , const unsigned int count ); static char* transcode ( const XMLCh* const toTranscode ); static bool transcode ( const XMLCh* const toTranscode , char* const toFill , const unsigned int maxChars ); static XMLCh* transcode ( const char* const toTranscode ); static bool transcode ( const char* const toTranscode , XMLCh* const toFill , const unsigned int maxChars ); static void trim(char* const toTrim); static void trim(XMLCh* const toTrim); static RefVectorOf<XMLCh>* tokenizeString(const XMLCh* const tokenizeSrc); static bool isInList(const XMLCh* const toFind, const XMLCh* const enumList); static XMLCh* makeUName ( const XMLCh* const pszURI , const XMLCh* const pszName ); static unsigned int replaceTokens ( XMLCh* const errText , const unsigned int maxChars , const XMLCh* const text1 , const XMLCh* const text2 , const XMLCh* const text3 , const XMLCh* const text4 ); static void upperCase(XMLCh* const toUpperCase); static void lowerCase(XMLCh* const toLowerCase); static bool isWSReplaced(const XMLCh* const toCheck); static bool isWSCollapsed(const XMLCh* const toCheck); static void replaceWS(XMLCh* const toConvert); static void collapseWS(XMLCh* const toConvert); private : XMLString(); ~XMLString(); static void initString(XMLLCPTranscoder* const defToUse); static void termString(); static bool validateRegion(const XMLCh* const str1, const int offset1, const XMLCh* const str2, const int offset2, const unsigned int charsCount); friend class XMLPlatformUtils; }; // --------------------------------------------------------------------------- // Inline some methods that are either just passthroughs to other string // methods, or which are key for performance. // --------------------------------------------------------------------------- inline void XMLString::moveChars( XMLCh* const targetStr , const XMLCh* const srcStr , const unsigned int count) { XMLCh* outPtr = targetStr; const XMLCh* inPtr = srcStr; for (unsigned int index = 0; index < count; index++) *outPtr++ = *inPtr++; } inline unsigned int XMLString::stringLen(const XMLCh* const src) { if (src == 0 || *src == 0) { return 0; } else { const XMLCh* pszTmp = src + 1; while (*pszTmp) ++pszTmp; return (unsigned int)(pszTmp - src); } } inline bool XMLString::startsWith( const XMLCh* const toTest , const XMLCh* const prefix) { return (compareNString(toTest, prefix, stringLen(prefix)) == 0); } inline bool XMLString::startsWithI( const XMLCh* const toTest , const XMLCh* const prefix) { return (compareNIString(toTest, prefix, stringLen(prefix)) == 0); } inline bool XMLString::endsWith(const XMLCh* const toTest, const XMLCh* const suffix) { unsigned int suffixLen = XMLString::stringLen(suffix); return regionMatches(toTest, XMLString::stringLen(toTest) - suffixLen, suffix, 0, suffixLen); } inline XMLCh* XMLString::replicate(const XMLCh* const toRep) { // If a null string, return a null string! XMLCh* ret = 0; if (toRep) { const unsigned int len = stringLen(toRep); ret = new XMLCh[len + 1]; XMLCh* outPtr = ret; const XMLCh* inPtr = toRep; for (unsigned int index = 0; index <= len; index++) *outPtr++ = *inPtr++; } return ret; } inline bool XMLString::validateRegion(const XMLCh* const str1, const int offset1, const XMLCh* const str2, const int offset2, const unsigned int charsCount) { if (offset1 < 0 || offset2 < 0 || (offset1 + charsCount) > XMLString::stringLen(str1) || (offset2 + charsCount) > XMLString::stringLen(str2) ) return false; return true; } #endif

Copyright © 2000 The Apache Software Foundation. All Rights Reserved.