⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 page.h

📁 小型搜索引擎,用C/C++编写,属于全文搜索引擎
💻 H
字号:
#ifndef _Page_H_030728_#define _Page_H_030728_#include <string>#include <map>#include <vector>#include "Url.h"//large enough to hold sina's 437 links const int ANCHOR_TEXT_LEN       = 256;const int MAX_URL_REFERENCES    = 1000;const int URL_REFERENCE_LEN     = (URL_LEN+ANCHOR_TEXT_LEN)*MAX_URL_REFERENCES*1/2 ;using namespace std;// plain text or otherenum page_type {	PLAIN_TEXT,	OTHER	};struct RefLink4SE	// <href src...>, <area src...>{	char *link;	char *anchor_text;	string strCharset;};struct RefLink4History	// <img src...>,<script src...>{	char *link;};class CPage{public:	string m_sUrl;			string m_sLocation;		/* Location URL */	string m_sHeader;	int m_nLenHeader;	string m_sCharset;	string m_sContentEncoding;	string m_sContentType;	string m_sContent;	int m_nLenContent;	string m_sContentLinkInfo;	string m_sLinkInfo4SE;	int m_nLenLinkInfo4SE;	string m_sLinkInfo4History;	int m_nLenLinkInfo4History;	string m_sContentNoTags;	int m_nRefLink4SENum;	int m_nRefLink4HistoryNum;	enum page_type m_eType;	RefLink4SE m_RefLink4SE[MAX_URL_REFERENCES];	RefLink4History m_RefLink4History[MAX_URL_REFERENCES/2];	map<string,string,less<string> > m_mapLink4SE;	vector<string > m_vecLink4History;public:	CPage();	CPage::CPage(string strUrl, string strLocation, char* header, char* body, int nLenBody);	~CPage();	int GetCharset();	int GetContentEncoding();	int GetContentType();	int GetContentLinkInfo();	int GetLinkInfo4SE();	int GetLinkInfo4History();	void FindRefLink4SE();	void FindRefLink4History();private:	int NormallizeUrl(string& strUrl);	bool IsFilterLink(string plink);};#endif /* _Page_H_030728_ */

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -