敏感詞檢測

過濾敏感詞，可以設定跳字長度，預設全形轉半形、忽略大小寫、跳詞、重復詞、黑名單。返回結果包含：關鍵字、關鍵字起始位置、結束位置、關鍵字序號等資訊。

string s = "中國|國人|zg人";string test = "我是中國人";StringSearch iwords = new StringSearch();iwords.SetKeywords(s.Split('|'));var b = iwords.ContainsAny(test);Assert.AreEqual(true, b);var f = iwords.FindFirst(test);Assert.AreEqual("中國", f);var all = iwords.FindAll(test);Assert.AreEqual("中國", all[0]);Assert.AreEqual("國人", all[1]);Assert.AreEqual(2, all.Count);var str = iwords.Replace(test, '*');Assert.AreEqual("我是***", str);

敏感詞通配符檢測

支持正規表式型別：.?[]|，透過正規表式可以進行模糊匹配，提升檢測精準度。

string s = ".[中美]國|國人|zg人";string test = "我是中國人";WordsMatch wordsSearch = new WordsMatch();wordsSearch.SetKeywords(s.Split('|'));var b = wordsSearch.ContainsAny(test);Assert.AreEqual(true, b);var f = wordsSearch.FindFirst(test);Assert.AreEqual("是中國", f.Keyword);var alls = wordsSearch.FindAll(test);Assert.AreEqual("是中國", alls[0].Keyword);Assert.AreEqual(".[中美]國", alls[0].MatchKeyword);Assert.AreEqual(1, alls[0].Start);Assert.AreEqual(3, alls[0].End);Assert.AreEqual(0, alls[0].Index);//返回索引Index,預設從0開始Assert.AreEqual("國人", alls[1].Keyword);Assert.AreEqual(2, alls.Count);var t = wordsSearch.Replace(test, '*');Assert.AreEqual("我****", t);

拼音轉換、繁簡轉換、數位轉大小寫操作

此工具箱，整合了繁體簡體互轉、拼音轉換、首字母提取、數位轉大小寫，使用例子如下：

// 轉成簡體WordsHelper.ToSimplifiedChinese("我愛中國");WordsHelper.ToSimplifiedChinese("我愛中國",1);// 港澳繁體轉簡體WordsHelper.ToSimplifiedChinese("我愛中國",2);// 台灣正體轉簡體// 轉成繁體WordsHelper.ToTraditionalChinese("我愛中國");WordsHelper.ToTraditionalChinese("我愛中國",1);// 簡體轉港澳繁體WordsHelper.ToTraditionalChinese("我愛中國",2);// 簡體轉台灣正體// 轉成全形WordsHelper.ToSBC("abcABC123");// 轉成半形WordsHelper.ToDBC("ａｂｃＡＢＣ１２３");// 數位轉成中文大寫WordsHelper.ToChineseRMB(12345678901.12);// 中文轉成數位WordsHelper.ToNumber("壹佰貳拾三億肆仟伍佰陸拾柒萬捌仟玖佰零壹元壹角貳分");// 獲取全拼WordsHelper.GetPinyin("我愛中國");//WoAiZhongGuo WordsHelper.GetPinyin("我愛中國",",");//Wo,Ai,Zhong,Guo WordsHelper.GetPinyin("我愛中國",true);//WǒÀiZhōngGuó// 獲取首字母WordsHelper.GetFirstPinyin("我愛中國");//WAZG// 獲取全部拼音WordsHelper.GetAllPinyin('傳');//Chuan,Zhuan// 獲取姓名WordsHelper.GetPinyinForName("單一一")//ShanYiYiWordsHelper.GetPinyinForName("單一一",",")//Shan,Yi,YiWordsHelper.GetPinyinForName("單一一",true)//ShànYīYī

效能對比

下面我們使用者1000字字串，進行10萬次效能對比，看看對比結果，測試程式碼如下：

ReadBadWord();var text = File.ReadAllText("Talk.txt");Console.Write("-------------------- FindFirst OR ContainsAny 100000次 --------------------Run("TrieFilter", () => { tf1.HasBadWord(text); });Run("FastFilter", () => { ff.HasBadWord(text); });Run("StringSearch（ContainsAny）", () => { stringSearch.ContainsAny(text); });Run("StringSearchEx（ContainsAny）--- WordsSearchEx（ContainsAny）程式碼相同", () => { stringSearchEx.ContainsAny(text); });Run("StringSearchEx2（ContainsAny）--- WordsSearchEx2（ContainsAny）程式碼相同", () => { stringSearchEx2.ContainsAny(text); });Run("StringSearchEx3（ContainsAny）--- WordsSearchEx3（ContainsAny）程式碼相同", () => { stringSearchEx3.ContainsAny(text); });Run("IllegalWordsSearch（ContainsAny）", () => { illegalWordsSearch.ContainsAny(text); });Run("StringSearch（FindFirst）", () => { stringSearch.FindFirst(text); });Run("StringSearchEx（FindFirst）", () => { stringSearchEx.FindFirst(text); });Run("StringSearchEx2（FindFirst）", () => { stringSearchEx2.FindFirst(text); });Run("StringSearchEx3（FindFirst）", () => { stringSearchEx3.FindFirst(text); });Run("WordsSearch（FindFirst）", () => { wordsSearch.FindFirst(text); });Run("WordsSearchEx（FindFirst）", () => { wordsSearchEx.FindFirst(text); });Run("WordsSearchEx2（FindFirst）", () => { wordsSearchEx2.FindFirst(text); });Run("WordsSearchEx3（FindFirst）", () => { wordsSearchEx3.FindFirst(text); });Run("IllegalWordsSearch（FindFirst）", () => { illegalWordsSearch.FindFirst(text); });Console.Write("-------------------- Find All 100000次 --------------------Run("TrieFilter（FindAll）", () => { tf1.FindAll(text); });Run("FastFilter（FindAll）", () => { ff.FindAll(text); });Run("StringSearch（FindAll）", () => { stringSearch.FindAll(text); });Run("StringSearchEx（FindAll）", () => { stringSearchEx.FindAll(text); });Run("StringSearchEx2（FindAll）", () => { stringSearchEx2.FindAll(text); });Run("StringSearchEx3（FindAll）", () => { stringSearchEx3.FindAll(text); });Run("WordsSearch（FindAll）", () => { wordsSearch.FindAll(text); });Run("WordsSearchEx（FindAll）", () => { wordsSearchEx.FindAll(text); });Run("WordsSearchEx2（FindAll）", () => { wordsSearchEx2.FindAll(text); });Run("WordsSearchEx3（FindAll）", () => { wordsSearchEx3.FindAll(text); });Run("IllegalWordsSearch（FindAll）", () => { illegalWordsSearch.FindAll(text); });Console.Write("-------------------- Replace 100000次 --------------------Run("TrieFilter（Replace）", () => { tf1.Replace(text); });Run("FastFilter（Replace）", () => { ff.Replace(text); });Run("StringSearch（Replace）", () => { stringSearch.Replace(text); });Run("WordsSearch（Replace）", () => { wordsSearch.Replace(text); });Run("StringSearchEx（Replace）--- WordsSearchEx（Replace）程式碼相同", () => { stringSearchEx.Replace(text); });Run("StringSearchEx2（Replace）--- WordsSearchEx2（Replace）程式碼相同", () => { stringSearchEx2.Replace(text); });Run("StringSearchEx3（Replace）--- WordsSearchEx3（Replace）程式碼相同", () => { stringSearchEx3.Replace(text); });Run("IllegalWordsSearch（Replace）", () => { illegalWordsSearch.Replace(text); });Console.Write("-------------------- Regex 100次 --------------------Run(100, "Regex.IsMatch", () => { re.IsMatch(text); });Run(100, "Regex.Match", () => { re.Match(text); });Run(100, "Regex.Matches", () => { re.Matches(text); });Console.Write("-------------------- Regex used Trie tree 100次 --------------------Run(100, "Regex.IsMatch", () => { re2.IsMatch(text); });Run(100, "Regex.Match", () => { re2.Match(text); });Run(100, "Regex.Matches", () => { re2.Matches(text); });