和楼上电脑同步了下。

Merge branch 'master' of https://gitee.com/DetaChina/DetaParser.git Conflicts: .project README.md wordSegment/org/tinos/engine/nlp/imp/NLPControllerImp.java wordSegment/org/tinos/engine/pos/POSController.java wordSegment/org/tinos/engine/pos/imp/POSControllerImp.java wordSegment/org/tinos/ortho/fhmm/imp/poscc.lyg wordSegment/org/tinos/ortho/fhmm/imp/poscj.lyg wordSegment/org/tinos/ortho/fhmm/imp/postt.lyg
yaoguangluo · Jun 7, 2019 · e34d2f3 · e34d2f3
2 parents e1859fb + d9dfc2e
commit e34d2f3
Show file tree

Hide file tree

Showing 17 changed files with 85 additions and 23 deletions.
diff --git a/.gitee/ISSUE_TEMPLATE.zh-CN.md b/.gitee/ISSUE_TEMPLATE.zh-CN.md
@@ -0,0 +1,13 @@
+### 该问题是怎么引起的？
+
+
+
+### 重现步骤
+
+
+
+### 报错信息
+
+
+
+
diff --git a/.gradle/5.0/fileChanges/last-build.bin b/.gradle/5.0/fileChanges/last-build.bin
diff --git a/.gradle/5.0/fileHashes/fileHashes.bin b/.gradle/5.0/fileHashes/fileHashes.bin
diff --git a/.gradle/5.0/fileHashes/fileHashes.lock b/.gradle/5.0/fileHashes/fileHashes.lock
diff --git a/.gradle/5.0/gc.properties b/.gradle/5.0/gc.properties
diff --git a/.gradle/vcs-1/gc.properties b/.gradle/vcs-1/gc.properties
diff --git a/.project b/.project
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<projectDescription>
-	<name>Deta_Parser</name>
+<projectDescription>
+	<name>Deta_Parser</name>
 	<comment></comment>
 	<projects>
 	</projects>

diff --git a/.settings/org.eclipse.buildship.core.prefs b/.settings/org.eclipse.buildship.core.prefs
@@ -1,3 +1,7 @@
+<<<<<<< HEAD
+connection.project.dir=
+eclipse.preferences.version=1
+=======
 arguments=
 auto.sync=false
 build.scans.enabled=false
@@ -11,3 +15,4 @@ offline.mode=false
 override.workspace.settings=true
 show.console.view=true
 show.executions.view=true
+>>>>>>> branch 'master' of https://gitee.com/DetaChina/DetaParser.git
diff --git a/README.en.md b/README.en.md
@@ -0,0 +1,36 @@
+# 德塔中文分词分析word segementation
+
+#### Description
+电脑偶尔登不上 https://github.com/yaoguangluo/DetaParser,就在码云上2选1发布.
+
+#### Software Architecture
+Software architecture description
+
+#### Installation
+
+1. xxxx
+2. xxxx
+3. xxxx
+
+#### Instructions
+
+1. xxxx
+2. xxxx
+3. xxxx
+
+#### Contribution
+
+1. Fork the repository
+2. Create Feat_xxx branch
+3. Commit your code
+4. Create Pull Request
+
+
+#### Gitee Feature
+
+1. You can use Readme\_XXX.md to support different languages, such as Readme\_en.md, Readme\_zh.md
+2. Gitee blog [blog.gitee.com](https://blog.gitee.com)
+3. Explore open source project [https://gitee.com/explore](https://gitee.com/explore)
+4. The most valuable open source project [GVP](https://gitee.com/gvp)
+5. The manual of Gitee [https://gitee.com/help](https://gitee.com/help)
+6. The most popular members  [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)
diff --git a/README.md b/README.md
@@ -1,7 +1,6 @@
 # <<100%(首创)个人著作权开源项目 软著登字第3951366号>>🔥26,000/ms word segment for text mining of NLP, POS, AI and Deep learning/每秒中文混合分词2200~3000万词汇的高精准确率快速神经网络分词包. 训练词意分析, 词感分析, 词境分析, 词灵分析并自由扩充词库 免费的官方互动展示页地址: http://tinos.qicp.vip/data.html 
 ###### 项目使用说明书 10.6.1版本地址:
 https://github.com/yaoguangluo/AOPM_VPCS_Theroy/blob/master/%E6%B5%8F%E9%98%B3%E5%BE%B7%E5%A1%94%E8%BD%AF%E4%BB%B6%E5%BC%80%E5%8F%91%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%20%E8%AF%AD%E8%A8%80%E5%9B%BE%E7%81%B5%E5%B7%A5%E7%A8%8BAPI%E8%AF%B4%E6%98%8E%E4%B9%A6_10_6_1_5.doc
-
 ![实例](https://github.com/yaoguangluo/Deta_Parser/blob/master/DETA%2020190524.jpg)
 ## 版本号：11.1.1 : 4字词卷积催化函数 准备整体卡诺图化简, 和PCA阀门优化. 2019-05-23 字长卷积小表 已经 应用了(新增4表). 2019-05-27 0:11 M
 ## 版本号：11.1.0: 随机测试文章来自 360八卦新闻推荐, 腾讯门户, 163门户等,总计110多篇文章, 约5万字, 算法问题导致错误分词1个(错误率十万分之三),词库缺少导致错误7个(错误率万分之三), <中文分析错误率小于亿分之一> 是一个艰巨的主题. 算法问题的扩充 时时更新在 HUB上.2019-05-25 22:48 M

diff --git a/build.gradle b/build.gradle
@@ -1,4 +1,8 @@
+<<<<<<< HEAD
+group 'DetaNLP'
+=======
 group 'Deta_Parser'
+>>>>>>> branch 'master' of https://gitee.com/DetaChina/DetaParser.git
 version '1.0-SNAPSHOT'
 apply plugin: 'java'
 sourceCompatibility = 1.8

diff --git a/settings.gradle b/settings.gradle
@@ -7,4 +7,8 @@
  * in the user guide at https://docs.gradle.org/4.10.3/userguide/multi_project_builds.html
  */
 
+<<<<<<< HEAD
+rootProject.name = 'DetaNLP'
+=======
 rootProject.name = 'Deta_Parser'
+>>>>>>> branch 'master' of https://gitee.com/DetaChina/DetaParser.git
diff --git a/wordSegment/org/tinos/engine/nlp/imp/NLPControllerImp.java b/wordSegment/org/tinos/engine/nlp/imp/NLPControllerImp.java
@@ -11,9 +11,9 @@ public class NLPControllerImp implements NLPController{
 	public int doSlangPartAndPOSCheckForTwoChar(int countInputStringLength, List<String> outputList
 			, StringBuilder stringBuilder, Map<String, String> wordsForest, StringBuilder[] prefixWord
 			, POSController posUtils, int charPosition, String textInputString){
-		String countWordNode= stringBuilder.toString();
+		String countWordNode= stringBuilder.toString();
 		if (StableData.INT_ZERO== prefixWord[StableData.INT_ZERO].length()){
-			if(StableMaps.CiTwo.containsKey(countWordNode)) {
+			if(StableMaps.CiTwo.containsKey(countWordNode)) {
 				prefixWord[StableData.INT_ZERO].delete(StableData.INT_ZERO, prefixWord[StableData.INT_ZERO].length());
 				prefixWord[StableData.INT_ZERO].append(countWordNode);
 				outputList.add(countWordNode);
@@ -44,8 +44,8 @@ public int doSlangPartAndPOSCheckForTwoChar(int countInputStringLength, List<Str
 					return countInputStringLength;
 				}
 			}
-		}
-		if (StableMaps.CiTwo.containsKey(countWordNode)){
+		}
+		if (StableMaps.CiTwo.containsKey(countWordNode)){
 			prefixWord[StableData.INT_ZERO].delete(StableData.INT_ZERO, prefixWord[StableData.INT_ZERO].length());
 			prefixWord[StableData.INT_ZERO].append(countWordNode);
 			outputList.add(countWordNode);
@@ -170,10 +170,10 @@ public int doSlangCheck(int countInputStringLength, List<String> output, StringB
 		+ prefixWord[StableData.INT_ONE].charAt(StableData.INT_ZERO))) {
 			countInputStringLength= doPOSAndEMMCheckOfThree(--countInputStringLength, output, wordsForest
 					, stringBuilder.delete(StableData.INT_THREE, StableData.INT_FOUR), prefixWord, posUtils, charPosition, textInputString);
-			return countInputStringLength;
+			return countInputStringLength;
 		}	
 		if (StableMaps.CiTwo.containsKey(preRegister)){
-			if (StableMaps.CiTwo.containsKey(postRegister)){
+			if (StableMaps.CiTwo.containsKey(postRegister)){
 				String string= StableData.EMPTY_STRING+ inputString.charAt(StableData.INT_ZERO);
 				if(StableMaps.xingWeiCi.containsKey(prefixWord[StableData.INT_ZERO].toString())
 						&&StableMaps.shiTaiCi.containsKey(string)) {
@@ -198,8 +198,8 @@ public int doSlangCheck(int countInputStringLength, List<String> output, StringB
 				prefixWord[StableData.INT_ZERO].append(preRegister);
 				return countInputStringLength-StableData.INT_TWO;
 			}
-		}
-		if(StableMaps.CiThree.containsKey(preRegister+ inputString.charAt(StableData.INT_TWO))&& !StableMaps.CiTwo.containsKey(postRegister)) {
+		}
+		if(StableMaps.CiThree.containsKey(preRegister+ inputString.charAt(StableData.INT_TWO))&& !StableMaps.CiTwo.containsKey(postRegister)) {
 			prefixWord[StableData.INT_ZERO].delete(StableData.INT_ZERO, prefixWord[StableData.INT_ZERO].length());
 			prefixWord[StableData.INT_ZERO].append(preRegister+ inputString.charAt(StableData.INT_TWO));
 			output.add(preRegister+ inputString.charAt(StableData.INT_TWO));

diff --git a/wordSegment/org/tinos/engine/pos/POSController.java b/wordSegment/org/tinos/engine/pos/POSController.java
@@ -76,6 +76,6 @@ void didNotFindFirstCharForMap(Map<String, WordFrequency> outputList, String[] s
 			, Map<String, String> wordsForest);
 
 	int parserFirstCharOfThreeForMap(int countInputStringLength, Map<String, WordFrequency> outputList, String[] strings
-			, StringBuilder[] fixWord, Map<String, String> wordsForest);
+			, StringBuilder[] fixWord, Map<String, String> wordsForest);
 }
 
diff --git a/wordSegment/org/tinos/engine/pos/imp/POSControllerImp.java b/wordSegment/org/tinos/engine/pos/imp/POSControllerImp.java
@@ -288,8 +288,8 @@ public int chuLiLianCiPostFixOfThree(Map<String, String> wordsForest, List<Strin
 		if (StableMaps.lianCi.containsKey(strings[StableData.INT_TWO])){
 			countInputLength= parserFirstCharOfThree(countInputLength, outputList, strings, prefixWord);
 			return countInputLength;
-		}
-		if (StableMaps.CiTwo.containsKey(strings[StableData.INT_ONE])){
+		}
+		if (StableMaps.CiTwo.containsKey(strings[StableData.INT_ONE])){
 			countInputLength= parserFirstTwoCharOfThree(countInputLength, outputList, strings, prefixWord);
 			return countInputLength;
 		}
@@ -401,8 +401,8 @@ public int chuLiZhuCiOfThree(Map<String, String> wordsForest, List<String> outpu
 			return countInputStringLength;
 		}
 		if (wordsForest.containsKey(fixWord[StableData.INT_ZERO].toString())){
-			if (StableMaps.dongCi.containsKey(fixWord[StableData.INT_ZERO].toString())){
-				if(StableMaps.CiTwo.containsKey(strings[StableData.INT_TWO])) {
+			if (StableMaps.dongCi.containsKey(fixWord[StableData.INT_ZERO].toString())){
+				if(StableMaps.CiTwo.containsKey(strings[StableData.INT_TWO])) {
 					countInputStringLength = parserFirstCharOfThree(countInputStringLength, outputList, strings, fixWord);
 					return countInputStringLength;
 				}
@@ -476,8 +476,8 @@ public int chuLiJieCiOfThree(Map<String, String> wordsForest, List<String> outpu
 					outputList.add(strings[StableData.INT_TWO]);
 					fixWord[StableData.INT_ZERO].delete(StableData.INT_ZERO, fixWord[StableData.INT_ZERO].length());
 					fixWord[StableData.INT_ZERO].append(strings[StableData.INT_TWO]);
-					return countInputStringLength;
-				}else if (StableMaps.CiTwo.containsKey(strings[StableData.INT_ONE])){
+					return countInputStringLength;
+				}else if (StableMaps.CiTwo.containsKey(strings[StableData.INT_ONE])){
 					if(StableMaps.jieCi.containsKey(strings[StableData.INT_ONE])) {
 						countInputStringLength= parserFirstTwoCharOfThree(countInputStringLength, outputList, strings, fixWord);
 						return countInputStringLength;
@@ -499,7 +499,7 @@ public int chuLiJieCiOfThree(Map<String, String> wordsForest, List<String> outpu
 		if(StableMaps.jieCi.containsKey(strings[StableData.INT_ONE])) {
 			countInputStringLength= parserFirstTwoCharOfThree(countInputStringLength, outputList, strings, fixWord);
 			return countInputStringLength;
-		}
+		}
 		outputList.add(strings[StableData.INT_ZERO]);
 		if(StableMaps.CiTwo.containsKey(strings[StableData.INT_TWO])) {
 			outputList.add(strings[StableData.INT_TWO]);
@@ -509,7 +509,7 @@ public int chuLiJieCiOfThree(Map<String, String> wordsForest, List<String> outpu
 		}
 		fixWord[StableData.INT_ZERO].delete(StableData.INT_ZERO, fixWord[StableData.INT_ZERO].length());
 		fixWord[StableData.INT_ZERO].append(strings[StableData.INT_ZERO]);
-		return countInputStringLength= StableData.INT_ONE;
+		return countInputStringLength= StableData.INT_ONE;
 	}
 
 	public int chuLiLiangCiOfThree(Map<String, String> wordsForest, List<String> outputList, int countInputStringLength
@@ -848,5 +848,5 @@ public int parserFirstCharOfThreeForMap(int countInputStringLength, Map<String,
 			return countInputStringLength;
 		}
 		return countInputStringLength;
-	}
+	}
 }
diff --git a/wordSegment/org/tinos/ortho/fhmm/imp/symbol.lyg b/wordSegment/org/tinos/ortho/fhmm/imp/symbol.lyg
@@ -0,0 +1 @@
+ộ
diff --git a/wordSegment/org/tinos/test/DemoPOSforSpecial.java b/wordSegment/org/tinos/test/DemoPOSforSpecial.java
@@ -14,7 +14,7 @@ public static void main(String[] args) throws IOException {
 		Map<String, String> nlp = analyzer.getPosCnToCn();
 		List<String> sets = new ArrayList<>();
 		String[] ss = new String[1];
-		String[] ss1 = new String[1];
+		String[] ss1 = new String[1];
 		ss[0] = "存在这是非常常是非常愚蠢的为主要求知不断的提高自身的知识的不锻炼改变化";
 		ss1[0] = "나는 일을 준비 하고 있다 ";
 		for (int i = 0; i < ss.length; i++) {
@@ -34,7 +34,7 @@ public static void main(String[] args) throws IOException {
 					out.println(sets.get(k) + "/" + nlp.get(sets.get(k)) + "  ");
 				}
 			}
-			out.println("");
+			out.println("");
 		}
 	}
 }