本文轉自淺析敏感詞過濾算法(C++),本身也在其基礎上根據本身的狀況作了一點修改。html
https://blog.csdn.net/u012755940/article/details/51689401?utm_source=appios
爲了提升查找效率,這裏將敏感詞用樹形結構存儲,每一個節點有一個map成員,其映射關係爲一個string對應一個WordNode。
好比敏感詞庫裏面有槍手、手槍這幾個詞,讀入後就變成了以下圖所示的樹狀結構。
算法
STL::map是按照operator<比較判斷元素是否相同,以及比較元素的大小,而後選擇合適的位置插入到樹中。
下面主要實現了WordNode類,進行節點的插入以及查詢。windows
WordNode.happ
#ifndef __WORDNODE_H__ #define __WORDNODE_H__ #define PACE 1 #include <string> #include <map> #include <stdio.h> class CWordNode { public: CWordNode(std::string character); CWordNode(){ m_character = ""; }; ~CWordNode(); std::string getCharacter() const{ return m_character; }; CWordNode* findChild(std::string& nextCharacter); CWordNode* insertChild(std::string& nextCharacter); private: friend class CWordTree; typedef std::map<std::string, CWordNode> _TreeMap; typedef std::map<std::string, CWordNode>::iterator _TreeMapIterator; std::string m_character; _TreeMap m_map; CWordNode* m_parent; }; #endif
WordNode.cpp函數
#include "WordNode.h" using namespace std; CWordNode::~CWordNode() { } CWordNode::CWordNode(std::string character) { if (character.size() == PACE) { m_character.assign(character); } } CWordNode* CWordNode::findChild(std::string& nextCharacter) { _TreeMapIterator TreeMapIt = m_map.find(nextCharacter); if (TreeMapIt == m_map.end()) { return NULL; } else { return &TreeMapIt->second; } } CWordNode* CWordNode::insertChild(std::string& nextCharacter) { if (!findChild(nextCharacter)) { m_map.insert(pair<std::string, CWordNode>(nextCharacter, CWordNode(nextCharacter))); return &(m_map.find(nextCharacter)->second); } return NULL; }
另外,編碼
#define PACE 1
這裏的PACE本來是2,由於一個GBK漢字佔兩個字符,並且原文中也說了若是須要考慮英文或中英文結合的狀況,將PACE改成1。
不過我試過以後,以爲無論是中文、英文仍是中英文,PACE爲 1 都適用,結果都沒錯,只不過中文的狀況下每一個節點的string都再也不是一個完整的漢字,而是漢字的一個字符。lua
接下來實現這個tree,在創建WordNode樹時,以parent爲根節點創建,一開始parent爲m_emptyRoot,而後keyword按照規則添加到樹中,假設一開始m_emptyRoot爲空,keyword爲」敏感詞」,則會以」敏感詞」爲一條分支創建成爲一顆樹枝’敏’->’感’->’詞’,此後,若想再添加」敏感度」,因爲」敏感詞」與」敏感度」的前兩個字相同,則會在’敏’->’感’->’詞’的基礎上,從字’感’開始新生長出一顆分支,即’敏’->’感’->’度’,這兩顆分支共用’敏’->’感’。spa
下面代碼實現了WordTree類,進行樹的構成及查詢。.net
WordTree.h
#ifndef __WORDTREE_H__ #define __WORDTREE_H__ #include "WordNode.h" class CWordTree { public: CWordTree(); ~CWordTree(); int nCount; CWordNode* insert(std::string &keyWord); CWordNode* insert(const char* keyword); CWordNode* find(std::string& keyword); private: CWordNode m_emptyRoot; int m_pace; CWordNode* insert(CWordNode* parent, std::string& keyword); CWordNode* insertBranch(CWordNode* parent, std::string& keyword); CWordNode* find(CWordNode* parent, std::string& keyword); }; #endif // __WORDTREE_H__
WordTree.cpp
#include "WordTree.h" CWordTree::CWordTree() :nCount(0) { } CWordTree::~CWordTree() { } CWordNode* CWordTree::insert(std::string &keyWord) { return insert(&m_emptyRoot, keyWord); } CWordNode* CWordTree::insert(const char* keyWord) { std::string wordstr(keyWord); return insert(wordstr); } CWordNode* CWordTree::insert(CWordNode* parent, std::string& keyWord) { if (keyWord.size() == 0) { return NULL; } std::string firstChar = keyWord.substr(0, PACE); CWordNode* firstNode = parent->findChild(firstChar); if (firstNode == NULL) { return insertBranch(parent, keyWord); } std::string restChar = keyWord.substr(PACE, keyWord.size()); return insert(firstNode, restChar); } CWordNode* CWordTree::find(std::string& keyWord) { return find(&m_emptyRoot, keyWord); } CWordNode* CWordTree::find(CWordNode* parent, std::string& keyWord) { std::string firstChar = keyWord.substr(0, PACE); CWordNode* firstNode = parent->findChild(firstChar); if (firstNode == NULL) { nCount = 0; return NULL; } std::string restChar = keyWord.substr(PACE, keyWord.size()); if (firstNode->m_map.empty()) { return firstNode; } if (keyWord.size() == PACE) { return NULL; } nCount++; return find(firstNode, restChar); } CWordNode* CWordTree::insertBranch(CWordNode* parent, std::string& keyWord) { std::string firstChar = keyWord.substr(0, PACE); CWordNode* firstNode = parent->insertChild(firstChar); if (firstNode != NULL) { std::string restChar = keyWord.substr(PACE, keyWord.size()); if (!restChar.empty()) { return insertBranch(firstNode, restChar); } } return NULL; }
最後就是利用上述的Tree來實現敏感詞過濾,WordFilter::censor(string &source) 函數用來進行敏感詞過濾,source即輸入的字符串,若是source包含敏感詞,則用「**」替代掉。
WordFilter::load(const char* filepath) 函數經過文件載入敏感詞,並構建WordTree,這裏我用的是txt文件。
下面實現了WordFilter類。
WordFilter.h
#ifndef __WORDFILTER_H__ #define __WORDFILTER_H__ #include "WordTree.h" #include "base/CCRef.h" USING_NS_CC; class CWordFilter : public Ref { public: ~CWordFilter(); bool loadFile(const char* filepath); bool censorStr(std::string &source); bool censorStrWithOutSymbol(const std::string &source); static CWordFilter* getInstance(); static void release(); private: std::string string_To_UTF8(const std::string & str); std::string UTF8_To_string(const std::string & str); CWordFilter(); static CWordFilter* m_pInstance; CWordTree m_WordTree; }; #endif // __WORDFILTER_H__
WordFilter.cpp
#include "WordFilter.h" #include <ctype.h> #include <algorithm> #include <iostream> #include <fstream> #include <istream> using namespace std; USING_NS_CC; CWordFilter* CWordFilter::m_pInstance = nullptr; CWordFilter::CWordFilter() { } CWordFilter::~CWordFilter() { } CWordFilter* CWordFilter::getInstance() { if (m_pInstance == NULL) { m_pInstance = new CWordFilter(); } return m_pInstance; } void CWordFilter::release() { if (m_pInstance) { delete m_pInstance; } m_pInstance = NULL; } bool CWordFilter::loadFile(const char* filepath) { ifstream infile(filepath, ios::in); if (!infile) { return false; } else { string read; while (getline(infile, read)) { #if (CC_TARGET_PLATFORM == CC_PLATFORM_ANDROID || CC_TARGET_PLATFORM == CC_PLATFORM_IOS) string s; s = read.substr(0, read.length() - 1); m_WordTree.insert(s); #else m_WordTree.insert(read); #endif } } infile.close(); return true; } bool CWordFilter::censorStr(string &source) { int lenght = source.size(); for (int i = 0; i < lenght; i += 1) { string substring = source.substr(i, lenght - i); if (m_WordTree.find(substring) != NULL) { source.replace(i, (m_WordTree.nCount + 1), "**"); lenght = source.size(); return true; } } return false; } bool CWordFilter::censorStrWithOutSymbol(const std::string &source) { string sourceWithOutSymbol; int i = 0; while (source[i] != 0) { if (source[i] & 0x80 && source[i] & 0x40 && source[i] & 0x20) { int byteCount = 0; if (source[i] & 0x10) { byteCount = 4; } else { byteCount = 3; } for (int a = 0; a < byteCount; a++) { sourceWithOutSymbol += source[i]; i++; } } else if (source[i] & 0x80 && source[i] & 0x40) { i += 2; } else { i += 1; } } return censorStr(sourceWithOutSymbol); }
這裏說明一點,本人是作Cocos2d-x手遊客戶端開發的,程序是要移植到安卓或者iOS平臺上。當逐行讀取txt文件中的敏感詞並構成樹的時候,getline(infile, read)函數獲得的read字符串後面帶有結束符,好比「槍手\0」,這時跟咱們須要檢測的字符串「…槍手…」就明顯不符合,這是檢測不出來的。這種狀況我如今只知道在安卓或者iOS平臺存在,而在windows環境下VS中是不會出現這種問題的。因此我對讀取到的字符串作了處理,把最後一個字符也就是結束符去掉,再進行下一步操做。
而我使用的是lua,lua發送給C++的字符串都是用utf-8編碼的,因此再去除字符串的時候並不能簡答的使用(a & 0x80)來判斷