修改添加词性标注功能

conf/user.dict

@@ -9,5 +9,5 @@ utf-8 3 nz
 簡體字 53 n
 簡體字典 53 n
 矿泉水瓶盖 53 n
-点赞 3 nz
-
+点赞 3 userDict
+普顿思   3   userDict

conf/user.dict.bak

@@ -0,0 +1,12 @@
+小清新 3
+百搭 3
+显瘦 3
+又拍云 3
+iphone 3
+鲜芋仙 3
+UTF-8 3 nz
+utf-8 3 nz
+簡體字 53 n
+簡體字典 53 n
+矿泉水瓶盖 53 n
+点赞 3 nz

pom.xml

@@ -1,17 +1,13 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
     xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
     <modelVersion>4.0.0</modelVersion>
-    <parent>
-        <groupId>org.sonatype.oss</groupId>
-        <artifactId>oss-parent</artifactId>
-        <version>7</version>
-    </parent>
-    <groupId>com.huaban</groupId>
+
+    <groupId>org.xm</groupId>
     <artifactId>jieba-analysis</artifactId>
-    <version>1.0.3-SNAPSHOT</version>
+    <version>1.0.4-SNAPSHOT</version>
     <packaging>jar</packaging>
 
-    <name>结巴分词工具(jieba for java)</name>
+    <name>分词工具(java)</name>
     <url>http://maven.apache.org</url>
     <inceptionYear>2013</inceptionYear>
     <licenses>
@@ -29,8 +25,12 @@
     </scm>
 
     <properties>
+        <java.version>1.8</java.version>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-        <maven.compiler.target>1.7</maven.compiler.target>
+        <maven.compiler.target>1.8</maven.compiler.target>
+        <slf4j-api.version>1.6.4</slf4j-api.version>
+        <logback-classic.version>0.9.28</logback-classic.version>
+
     </properties>
 
     <developers>
@@ -49,14 +49,35 @@
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
-            <version>4.8</version>
+            <version>4.11</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-lang3</artifactId>
-            <version>3.3.1</version>
+            <version>3.3.2</version>
+        </dependency>
+
+        <!-- SLF4J日志框架API -->
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-api</artifactId>
+            <version>${slf4j-api.version}</version>
+        </dependency>
+        <!-- LOGBACK日志实现提供者 -->
+        <dependency>
+            <groupId>ch.qos.logback</groupId>
+            <artifactId>logback-classic</artifactId>
+            <version>${logback-classic.version}</version>
+            <exclusions>
+                <exclusion>
+                    <groupId>commons-logging</groupId>
+                    <artifactId>commons-logging</artifactId>
+                </exclusion>
+            </exclusions>
+            <scope>runtime</scope>
         </dependency>
+
     </dependencies>
 
     <build>
@@ -66,8 +87,8 @@
                 <artifactId>maven-compiler-plugin</artifactId>
                 <version>2.3.2</version>
                 <configuration>
-                    <source>1.7</source>
-                    <target>1.7</target>
+                    <source>1.8</source>
+                    <target>1.8</target>
                 </configuration>
             </plugin>
             <plugin>

src/main/java/com/huaban/analysis/jieba/JiebaSegmenter.java

@@ -99,7 +99,7 @@ public List<SegToken> process(String paragraph, SegMode mode) {
                                 int j = 0;
                                 for (; j < token.length() - 1; ++j) {
                                     gram2 = token.substring(j, j + 2);
-                                    if (wordDict.containsWord(gram2))
+                                    if (wordDict.containsWord(gram2)) //wordDict is the core.txt ; if the gram2 in resources/core.txt
                                         tokens.add(new SegToken(gram2, offset + j, offset + j + 2, wordDict.getNature(gram2)));
                                 }
                             }

src/main/java/com/huaban/analysis/jieba/WordDictionary.java

@@ -63,7 +63,6 @@ public void init(Path configFile) {
         synchronized (WordDictionary.class) {
             if (loadedPath.contains(abspath))
                 return;
-
             DirectoryStream<Path> stream;
             try {
                 stream = Files.newDirectoryStream(configFile, String.format(Locale.getDefault(), "*%s", USER_DICT_SUFFIX));
@@ -73,8 +72,6 @@ public void init(Path configFile) {
                 }
                 loadedPath.add(abspath);
             } catch (IOException e) {
-                // TODO Auto-generated catch block
-                // e.printStackTrace();
                 System.err.println(String.format(Locale.getDefault(), "%s: load user dict failure!", configFile.toString()));
             }
         }

src/main/java/com/huaban/analysis/jieba/viterbi/FinalSeg.java

@@ -1,21 +1,16 @@
 package com.huaban.analysis.jieba.viterbi;
 
+import com.huaban.analysis.jieba.CharacterUtil;
+import com.huaban.analysis.jieba.Node;
+import com.huaban.analysis.jieba.Pair;
+
 import java.io.BufferedReader;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.InputStreamReader;
 import java.nio.charset.Charset;
-import java.util.HashMap;
-import java.util.List;
-import java.util.Locale;
-import java.util.Map;
-import java.util.Vector;
+import java.util.*;
 import java.util.regex.Matcher;
-import java.util.Collections;
-
-import com.huaban.analysis.jieba.CharacterUtil;
-import com.huaban.analysis.jieba.Pair;
-import com.huaban.analysis.jieba.Node;
 
 
 public class FinalSeg {
@@ -26,7 +21,7 @@ public class FinalSeg {
     private static Map<Character, Double> start;
     private static Map<Character, Map<Character, Double>> trans;
     private static Map<Character, char[]> prevStatus;
-    private static Double MIN_FLOAT = -3.14e100;;
+    private static Double MIN_FLOAT = -3.14e100;
 
 
     private FinalSeg() {