remove word dependency to remove GPL license (#1998)

apache · Oct 31, 2022 · 19ef0ac · 19ef0ac
1 parent 66b1674
commit 19ef0ac
Show file tree

Hide file tree

Showing 5 changed files with 1 addition and 125 deletions.
diff --git a/hugegraph-core/pom.xml b/hugegraph-core/pom.xml
@@ -32,7 +32,6 @@
         <jraft.version>1.3.11</jraft.version>
         <ohc.version>0.7.4</ohc.version>
         <lz4.version>1.8.0</lz4.version>
-        <apdplat-word.version>1.3.1</apdplat-word.version>
         <mmseg4j-core.version>1.10.0</mmseg4j-core.version>
         <jcseg.version>2.6.2</jcseg.version>
         <hanlp.version>portable-1.8.3</hanlp.version>
@@ -125,25 +124,6 @@
             </exclusions>
         </dependency>
 
-        <dependency>
-            <groupId>org.apdplat</groupId>
-            <artifactId>word</artifactId>
-            <version>${apdplat-word.version}</version>
-            <exclusions>
-                <exclusion>
-                    <groupId>ch.qos.logback</groupId>
-                    <artifactId>logback-classic</artifactId>
-                </exclusion>
-                <exclusion>
-                    <groupId>org.apache.lucene</groupId>
-                    <artifactId>lucene-core</artifactId>
-                </exclusion>
-                <exclusion>
-                    <groupId>org.apache.lucene</groupId>
-                    <artifactId>lucene-analyzers-common</artifactId>
-                </exclusion>
-            </exclusions>
-        </dependency>
         <dependency>
             <groupId>org.ansj</groupId>
             <artifactId>ansj_seg</artifactId>

diff --git a/hugegraph-core/src/main/java/com/baidu/hugegraph/analyzer/AnalyzerFactory.java b/hugegraph-core/src/main/java/com/baidu/hugegraph/analyzer/AnalyzerFactory.java
@@ -36,8 +36,6 @@ public class AnalyzerFactory {
     public static Analyzer analyzer(String name, String mode) {
         name = name.toLowerCase();
         switch (name) {
-            case "word":
-                return new WordAnalyzer(mode);
             case "ansj":
                 return new AnsjAnalyzer(mode);
             case "hanlp":

diff --git a/hugegraph-core/src/main/java/com/baidu/hugegraph/analyzer/WordAnalyzer.java b/hugegraph-core/src/main/java/com/baidu/hugegraph/analyzer/WordAnalyzer.java
diff --git a/hugegraph-core/src/main/java/com/baidu/hugegraph/config/CoreOptions.java b/hugegraph-core/src/main/java/com/baidu/hugegraph/config/CoreOptions.java
@@ -571,7 +571,7 @@ public static synchronized CoreOptions instance() {
                     "search.text_analyzer",
                     "Choose a text analyzer for searching the " +
                     "vertex/edge properties, available type are " +
-                    "[word, ansj, hanlp, smartcn, jieba, jcseg, " +
+                    "[ansj, hanlp, smartcn, jieba, jcseg, " +
                     "mmseg4j, ikanalyzer].",
                     disallowEmpty(),
                     "ikanalyzer"
@@ -582,13 +582,6 @@ public static synchronized CoreOptions instance() {
                     "search.text_analyzer_mode",
                     "Specify the mode for the text analyzer, " +
                     "the available mode of analyzer are " +
-                    "{word: [MaximumMatching, ReverseMaximumMatching, " +
-                            "MinimumMatching, ReverseMinimumMatching, " +
-                            "BidirectionalMaximumMatching, " +
-                            "BidirectionalMinimumMatching, " +
-                            "BidirectionalMaximumMinimumMatching, " +
-                            "FullSegmentation, MinimalWordCount, " +
-                            "MaxNgramScore, PureEnglish], " +
                     "ansj: [BaseAnalysis, IndexAnalysis, ToAnalysis, " +
                            "NlpAnalysis], " +
                     "hanlp: [standard, nlp, index, nShort, shortest, speed], " +

diff --git a/hugegraph-test/src/main/java/com/baidu/hugegraph/unit/core/AnalyzerTest.java b/hugegraph-test/src/main/java/com/baidu/hugegraph/unit/core/AnalyzerTest.java
@@ -47,27 +47,6 @@ public void teardown() {
         // pass
     }
 
-    @Test
-    public void testWordAnalyzer() {
-        // MaximumMatching mode
-        Analyzer analyzer = AnalyzerFactory.analyzer("word", "MaximumMatching");
-        Assert.assertEquals(setOf("england", "wins", "world", "cup"),
-                            analyzer.segment(TEXT_1));
-        Assert.assertEquals(setOf("英格兰", "世界杯", "夺冠", "中华人民共和国",
-                                  "国歌", "百度", "科技园", "位于", "北京市",
-                                  "海淀区", "西北旺", "东路", "10号", "院"),
-                            analyzer.segment(TEXT_2));
-
-        // ReverseMaximumMatching mode
-        analyzer = AnalyzerFactory.analyzer("word", "ReverseMaximumMatching");
-        Assert.assertEquals(setOf("england", "wins", "world", "cup"),
-                            analyzer.segment(TEXT_1));
-        Assert.assertEquals(setOf("英格兰", "世界杯", "夺冠", "中华人民共和国",
-                                  "国歌", "百度", "科技园", "位于", "北京市",
-                                  "海淀区", "西北旺", "东路", "10号", "院"),
-                            analyzer.segment(TEXT_2));
-    }
-
     @Test
     public void testAnsjAnalyzer() {
         // BaseAnalysis mode