C++ 敏感字符过滤 - c++编程基础

TOP

C++ 敏感字符过滤(一)

2015-11-21 01:02:27 来源: 作者: 【大中小】浏览:4次

WordNode.h
#ifndef __TOOLS_WORDNODE_H_INCLUDE__
#define __TOOLS_WORDNODE_H_INCLUDE__

#include

class CWordNode
{
typedef std::map umap;
public:
CWordNode(const std::string& word) { Reset(word); }
~CWordNode()
{
umap::iterator Ite = this->m_mapWordNodes.begin();
while (Ite != this->m_mapWordNodes.end())
{
CWordNode* pTmp = Ite->second;
delete pTmp;
pTmp = NULL;
++Ite;
}

this->m_mapWordNodes.clear();
this->m_nEndTag = 0;
}

void Reset(const std::string& word)
{
this->m_cWord = word;
this->m_nEndTag = 0;
this->m_mapWordNodes.clear();
}

public:
std::string m_cWord;
int m_nEndTag;
umap m_mapWordNodes;
};

#endif // __TOOLS_WORDNODE_H_INCLUDE__

WordsFilter.h
#ifndef __TOOLS_WORDSFILTER_H_INCLUDE__
#define __TOOLS_WORDSFILTER_H_INCLUDE__

#include
#include "WordNode.h"

class CWordsFilter
{
typedef std::map umap;
private:
std::list m_lsAllSensitiveWords; // 所有敏感词列表
CWordNode* m_rootWordNode;
bool m_bIsInit;

public:
CWordsFilter();
~CWordsFilter();

static CWordsFilter& GetInstance(); // 获取共享实例

void InitSensitiveWords(std::string strWord); // 初始化敏感词集
void InitSensitiveWords(std::list lsAllSensitiveWords); // 初始化敏感词集
std::string FilterSensitiveWords(const std::string& strContent); // 过滤敏感词

private:
void BuildWordTree(); // 构建敏感词树
void InsertNode(CWordNode* pNode, const std::string& strContent, int nIndex);
CWordNode* FindNode(CWordNode* pNode, const std::string& word);
int GetFirstBytes(const std::string& str); // 获取字符串中的第一个字符字节长度

};

#endif // __TOOLS_WORDSFILTER_H_INCLUDE__

WordsFilter.cpp
#include
#include
#include
#include
#include "WordsFilter.h"

int nStep = 2;

typedef std::vector Tokens;
Tokens StrSplit(const std::string &src, const std::string &sep)
{
Tokens r;
std::string s;

for (std::string::const_iterator i = src.begin(); i != src.end(); i++)
{
if (sep.find((*i)) != std::string::npos)
{
if (s.length())
{
r.push_back(s);
}
s = "";
}
else
{
s += (*i);
}
}

if (s.length())
{
r.push_back(s);
}
return r;
};

int CWordsFilter::GetFirstBytes(const std::string& str)
{
for (int i = 0; i < (int)str.size(); ++i)
{

unsigned char chr = (unsigned char)str.at(i);

// 如果是该字节是 0XXX XXXX 样式，说明其是一个英文文字，占1字节
if ((chr >> 7) == 0)
{
return 1;
}
// 如果该字节是 1111 110X 样式，说明其是一个文字的头，且该文字占6字节
else if ((chr >> 1) == 126)
{
return 6;
}
// 如果该字节是 1111 10XX 样式，说明其是一个文字的头，且该文字占5字节
else if ((chr >> 2) == 62)
{
return 5;
}
// 如果该字节是 1111 0XXX 样式，说明其是一个文字的头，且该文字占4字节
else if ((chr >> 3) == 30)
{
return 4;
}
// 如果该字节是 1110 XXXX 样式，说明其是一个文字的头，且该文字占3字节
else if ((chr >> 4) == 14)
{
return 3;
}
// 如果该字节是 110X XXXX 样式，说明其是一个文字的头，且该文字占2字节
else if ((chr >> 5) == 6)
{
return 2;
}
else
{
continue;
}
}
return 1;
}

CWordsFilter::CWordsFilter():
m_bIsInit(false),
m_rootWordNode(NULL)
{
m_lsAllSensitiveWords.clear();
}

CWordsFilter::~CWordsFilter()
{
this->m_lsAllSensitiveWords.clear();
delete this->m_rootWordNode;
this->m_rootWordNode = NULL;
}

void CWordsFilter::InitSensitiveWords(std::string strWord)
{
Tokens token = StrSplit(strWord, ",");
std::list lsAllSensitiveWords;
Tokens::iterator Ite = token.begin();
while (Ite != token.end())
{
lsAllSensitiveWords.push_back(*Ite);
++Ite;
}
InitSensitiveWords(lsAllSensitiveWords);
}

void CWordsFilter::InitSensitiveWords(std::lis

首页上一页 1 2 下一页尾页 1/2/2
【大中小】【打印】【繁体】【投稿】【收藏】【推荐】【举报】【评论】【关闭】【返回顶部】
分享到:
上一篇：POJ 1028 Web Navigation	下一篇：BZOJ 4025 二分图分治+并查集

帐　　号:

密码: (新用户注册)

验证码:

表　　情:

内　　容: