词性标注修改

ruoyi-admin/src/main/resources/application-druid.yml

@@ -23,12 +23,12 @@ spring:
         druid:
             # 主库数据源
             master:
-                url: jdbc:mysql://120.78.220.29:3306/makesoft?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
-                username: root
-                password: Biemo123
-#                url: jdbc:mysql://39.108.144.227:1637/makesoft?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
+#                url: jdbc:mysql://120.78.220.29:3306/makesoft?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
 #                username: root
 #                password: Biemo123
+                url: jdbc:mysql://39.108.144.227:1637/makesoft?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
+                username: root
+                password: Biemo123
 #                url: jdbc:mysql://118.31.7.2:3306/makesoft?useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&useSSL=true&serverTimezone=GMT%2B8
 #                username: root
 #                password: sztzjy2017

ruoyi-biemo/src/main/java/com/ruoyi/biemo/business/controller/DocInfoController.java

@@ -83,7 +83,7 @@ public class DocInfoController extends BaseController {
     }
 
     @GetMapping("/getEmotionAnalysisByCateId/{categoryId}")
-        public AjaxResult getEmotionAnalysis(@PathVariable String categoryId){
+        public AjaxResult getEmotionAnalysis(@PathVariable String categoryId) throws IOException {
         EmotionResult emotionResult = docInfoService.getEmotionAnalysis(categoryId);
         return AjaxResult.success(emotionResult);
     }

ruoyi-biemo/src/main/java/com/ruoyi/biemo/nlp/SentimentAnalysisUtils.java

@@ -16,8 +16,10 @@ import java.util.List;
  * 情感分析
  */
 public class SentimentAnalysisUtils {
-    public static final String CORPUS_FOLDER = TestUtility.ensureTestData("ChnSentiCorp", "http://hanlp.linrunsoft.com/release/corpus/ChnSentiCorp.zip");
-    public static final String MODEL_PATH = "D:\\code\\TextBigData\\data\\test\\sentiment-classification-model.ser";
+    public static final String CORPUS_FOLDER = TestUtility.ensureTest2Data("ChnSentiCorp", "http://hanlp.linrunsoft.com/release/corpus/ChnSentiCorp.zip");
+//    public static final String MODEL_PATH = "D:\\code\\TextBigData\\data\\test\\sentiment-classification-model.ser";
+    public static final String MODEL_PATH = "/usr/local/textjar/analysis-hanlp/data/test/sentiment-classification-model.ser";
+
 
     public static String analysis(String text){
         String result = "";

ruoyi-biemo/src/main/java/com/ruoyi/biemo/utils/FormatUtil.java

@@ -0,0 +1,58 @@
+package com.ruoyi.biemo.utils;
+
+
+import com.hankcs.hanlp.HanLP;
+import com.hankcs.hanlp.seg.common.Term;
+
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+public class FormatUtil {
+ 
+    /**
+     * 去除停用词
+     * @param oldString：原中文文本
+     * @return 去除停用词之后的中文文本
+     * @throws IOException
+     */
+    public static String RemovalOfStopWords(String oldString) throws IOException {
+        String newString = oldString;
+ 
+        // 分词
+        List<Term> termList = HanLP.segment(newString);
+
+ 
+        // 中文 停用词 .txt 文件路径
+        String filePath = "/usr/local/textjar/analysis-hanlp/data/test/stop.txt";
+        File file = new File(filePath);
+ 
+        BufferedReader bufferedReader = new BufferedReader(new FileReader(file));
+        List<String> stopWords = new ArrayList<>();
+        String temp = null;
+        while ((temp = bufferedReader.readLine()) != null) {
+            //System.out.println("*" + temp+ "*");
+            stopWords.add(temp.trim());
+        }
+ 
+        List<String> termStringList = new ArrayList<>();
+        for(Term term:termList) {
+            termStringList.add(term.word);
+            //System.out.println("*" + term.word + "*");
+        }
+ 
+        termStringList.removeAll(stopWords);
+ 
+        newString = "";
+        for (String string:termStringList) {
+            newString += string;
+        }
+ 
+        return newString;
+    }
+ 
+}

ruoyi-biemo/src/main/java/com/ruoyi/biemo/utils/TestUtility.java

@@ -30,7 +30,7 @@ public class TestUtility
     {
 //        ensureData("data/model/crf", "http://nlp.hankcs.com/download.php?file=data", ".", false);
 //        ensureData("D:\\tianze\\文本大数据\\analysis-hanlp\\data\\model\\crf", "http://nlp.hankcs.com/download.php?file=data", ".", false);
-        ensureData("/usr/local/textjar/analysis-hanlp/data/model/crf", "http://nlp.hankcs.com/download.php?file=data", ".", false);
+        ensureData("/usr/local/textjar/analysis-hanlp/data//model/crf", "http://nlp.hankcs.com/download.php?file=data", ".", false);
     }
 
     /**