saxfilehandlers.h

基于径向基函数的神经网络文本自动分类系统。

// SAXFileHandlers.h: interface for the CSAXFileHandlers class.
//
//////////////////////////////////////////////////////////////////////

#if !defined(AFX_SAXFILEHANDLERS_H__8CDD50B2_F407_472F_9392_1B19DECE62E9__INCLUDED_)
#define AFX_SAXFILEHANDLERS_H__8CDD50B2_F407_472F_9392_1B19DECE62E9__INCLUDED_

#if _MSC_VER > 1000
#pragma once
#endif // _MSC_VER > 1000

#include <xercesc/sax2/Attributes.hpp>
#include <xercesc/sax2/DefaultHandler.hpp>

XERCES_CPP_NAMESPACE_USE

class CSAXFileHandlers : public DefaultHandler
{
public:
	CSAXFileHandlers();
	virtual ~CSAXFileHandlers();
	bool Convert();
    // -----------------------------------------------------------------------
    //  Handlers for the SAX DocumentHandler interface
    // -----------------------------------------------------------------------
    void startElement(const XMLCh* const uri, const XMLCh* const localname, const XMLCh* const qname, const Attributes& attrs);
	void endElement(const XMLCh *const uri, const XMLCh* const localname, const XMLCh* const qname);
    void characters(const XMLCh* const chars, const unsigned int length);
    // -----------------------------------------------------------------------
    //  Handlers for the SAX ErrorHandler interface
    // -----------------------------------------------------------------------
	void warning(const SAXParseException& exception);
    void error(const SAXParseException& exception);
    void fatalError(const SAXParseException& exception);
    void resetErrors();
private:
	int m_nStatus;
	bool m_bInAuthor;
	bool m_bInDateLine;
	bool m_bInTitle;
	CStringArray m_astrTop10Category;
private:
	short GetTopicString(CStringArray &astrToipics, CString &strTopic, bool bTop10=false);
	bool IsInTop10Category(char *);
	void clear();
	char m_pDocID[15];
	CStringArray m_astrTopics;
	char m_pTitle[1024];
	char m_pContent[1024*128];
public:
	void writeContent();
	FILE *m_pStream;
	char m_pTarget[MAX_PATH];
	char m_pSource[MAX_PATH];
	int m_nSourceFormat;
	int m_nTargetFormat;
	bool m_bShowErrors;
	int m_nSplitType;
	int m_nDocsSetType;
	int m_nCategoryNum;
};
extern CSAXFileHandlers theSaxFileHandler;

#endif // !defined(AFX_SAXFILEHANDLERS_H__8CDD50B2_F407_472F_9392_1B19DECE62E9__INCLUDED_)