Java Sensitive word filtering

Sensitive word filtering is essential in website development. The general use of DFA, this relatively good algorithm to achieve.

Reference Link: http://cmsblogs.com/?p=1031

A better code implementation:

　　

1 Importjava.io.IOException;2 Importjava.util.ArrayList;3 ImportJava.util.HashMap;4 Importjava.util.List;5 6 /**7 * @title KeywordFilter8 * @description TODO9  * @author Ten * @date 2014-4-17 One  * @version1.0 A  */ -  Public classKeywordFilter { -     /**collection of sensitive words the * {FA ={isend=0, ={isend=1}}, Zhong ={isend=0, Guo ={isend=0, man ={isend=1}, male ={isend=0, man ={isend=1} }}} -      * */ -     PrivateHashMap Keysmap =NewHashMap (); -  +     /** - * Add sensitive words +      * @paramkeywords A      */ at      Public voidAddkeywords (list<string>keywords) { -          for(inti = 0; I < keywords.size (); i++) { -String key =Keywords.get (i). Trim (); -HashMap Nowhash = Keysmap;//initial traversal from the outermost layer -              for(intj = 0; J < Key.length (); J + +) { -                 CharWord =Key.charat (j); inObject Wordmap =nowhash.get (word); -                 if(Wordmap! =NULL) { toNowhash =(HASHMAP) wordmap; +}Else { -hashmap<string, string> Newwordhash =NewHashmap<string, string>(); theNewwordhash.put ("Isend", "0"); * nowhash.put (Word, newwordhash); $Nowhash =Newwordhash;Panax Notoginseng                 } -                 if(j = = Key.length ()-1) { theNowhash.put ("Isend", "1"); +                 } A             } the         } +     } -  $     /**  $ * Check if a string starts from the start position for keyword compliance, - * If not, return 0 - * If there is a conforming keyword value, continue traversing until Isend = 1 is encountered, returning the length of the matching keyword, the      */ -     Private intCheckkeywords (String txt,intbegin) {WuyiHashMap Nowhash =Keysmap; the         intres = 0; -          for(inti = begin; I < txt.length (); i++) { Wu             CharWord =Txt.charat (i); -Object Wordmap = Nowhash.get (word);//get the HashMap of the character corresponding About             if(Wordmap = =NULL) { $                 return0;//If the character does not have a corresponding Hashmap,return 0 -             } -  -res++;//if the character corresponding to the hashmap is not NULL, the description matches to a character, +1 ANowhash = (HashMap) wordmap;//points the traversed hashmap to the corresponding hashmap of the character +             if((String) nowhash.get ("Isend"). Equals ("1")) {//If the character is the end character of a sensitive word, return directly the                 returnRes; -}Else { $                 Continue; the             } the         } the         returnRes; the     } -  in     /**  the * Determine if there are any keywords in txt the      */ About      Public Booleaniscontentkeywords (String txt) { the          for(inti = 0; I < txt.length (); i++) { the             intLen =checkkeywords (TXT, i); the             if(Len > 0) { +                 return true; -             } the         }Bayi         return false; the     } the  -     /**  - * Returns a list of keywords in txt the      */ the      PublicList<string>gettxtkeywords (String txt) { thelist<string> list =NewArraylist<string>(); the         intL =txt.length (); -          for(inti = 0; I <l;) { the             intLen =checkkeywords (TXT, i); the             if(Len > 0) { theString TT = txt.substring (i, i +len);94 List.add (TT); thei + =Len; the}Else { thei++;98             } About         } -         returnlist;101     }102 103     /** 104 * Initialize the list of sensitive words the      * */106      Public voidInitfiltercode () {107list<string> keywords =NewArraylist<string>();108Keywords.add ("Chinese");109Keywords.add ("Chinese man")); theKeywords.add ("Falun");111          This. Addkeywords (keywords); the     }113  the      Public Static voidMain (string[] args)throwsIOException { theKeywordFilter filter =NewKeywordFilter (); the Filter.initfiltercode ();117String txt = "haha, but the Falun Gong, the Chinese,";118         BooleanBoo =filter.iscontentkeywords (TXT);119 System.out.println (boo); -List<string> set =filter.gettxtkeywords (TXT);121System.out.println ("contains the following sensitive words:" +set);122     }123     124      the     126     127}

Java Sensitive word filtering