url.h

小型搜索引擎,用C/C++编写,属于全文搜索引擎

#ifndef _URL_H_030728_
#define _URL_H_030728_

#include <string>

const int URL_LEN               = 256;

using namespace std;


enum url_scheme {
	SCHEME_HTTP,
	SCHEME_FTP,
	SCHEME_INVALID
};

const int DEFAULT_HTTP_PORT = 80;
const int DEFAULT_FTP_PORT  = 21;

class CUrl
{
public:
	string m_sUrl;			/* Original URL */
	enum url_scheme m_eScheme;		/* URL scheme */

	string	m_sHost;		/* Extracted hostname */
	int	m_nPort;		/* Port number */

	/* URL components (URL-quoted). */
	string	m_sPath,
		m_sParams,
		m_sQuery,
		m_sFragment;

	/* Extracted path info (unquoted). */
	string	m_sDir,
		m_sFile;

	/* Username and password (unquoted). */
	string	m_sUser,
		m_sPasswd;

public:
	CUrl();
	~CUrl();

	bool ParseUrl(string strUrl);

private:
	void ParseScheme (const char *url);

};

#endif /* _URL_H_030728_ */