This is an automated email from the ASF dual-hosted git repository.
jin pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-hugegraph.git
The following commit(s) were added to refs/heads/master by this push:
new 19ef0ac20 remove word dependency to remove GPL license (#1998)
19ef0ac20 is described below
commit 19ef0ac203b06e2d5324927f970da133636be38f
Author: zyxxoo <[email protected]>
AuthorDate: Mon Oct 31 12:05:22 2022 +0800
remove word dependency to remove GPL license (#1998)
---
hugegraph-core/pom.xml | 20 ------
.../baidu/hugegraph/analyzer/AnalyzerFactory.java | 2 -
.../com/baidu/hugegraph/analyzer/WordAnalyzer.java | 74 ----------------------
.../com/baidu/hugegraph/config/CoreOptions.java | 9 +--
.../baidu/hugegraph/unit/core/AnalyzerTest.java | 21 ------
5 files changed, 1 insertion(+), 125 deletions(-)
diff --git a/hugegraph-core/pom.xml b/hugegraph-core/pom.xml
index bb1d3646d..ded15fda5 100644
--- 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
index ab84dba63..3d6ead94c 100644
---
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
deleted file mode 100644
index 48ba66d95..000000000
---
a/hugegraph-core/src/main/java/com/baidu/hugegraph/analyzer/WordAnalyzer.java
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
- * Copyright 2017 HugeGraph Authors
- *
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements. See the NOTICE file distributed with this
- * work for additional information regarding copyright ownership. The ASF
- * licenses this file to You under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
- * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
- * License for the specific language governing permissions and limitations
- * under the License.
- */
-
-package com.baidu.hugegraph.analyzer;
-
-import java.util.List;
-import java.util.Set;
-
-import org.apdplat.word.WordSegmenter;
-import org.apdplat.word.segmentation.SegmentationAlgorithm;
-import org.apdplat.word.segmentation.Word;
-
-import com.baidu.hugegraph.config.ConfigException;
-import com.baidu.hugegraph.util.InsertionOrderUtil;
-import com.google.common.collect.ImmutableList;
-
-/**
- * Reference from https://my.oschina.net/apdplat/blog/412921
- */
-public class WordAnalyzer implements Analyzer {
-
- public static final List<String> SUPPORT_MODES =
- ImmutableList.<String>builder()
- .add("MaximumMatching")
- .add("ReverseMaximumMatching")
- .add("MinimumMatching")
- .add("ReverseMinimumMatching")
- .add("BidirectionalMaximumMatching")
- .add("BidirectionalMinimumMatching")
- .add("BidirectionalMaximumMinimumMatching")
- .add("FullSegmentation")
- .add("MinimalWordCount")
- .add("MaxNgramScore")
- .add("PureEnglish")
- .build();
-
- private final SegmentationAlgorithm algorithm;
-
- public WordAnalyzer(String mode) {
- try {
- this.algorithm = SegmentationAlgorithm.valueOf(mode);
- } catch (Exception e) {
- throw new ConfigException(
- "Unsupported segment mode '%s' for word analyzer, " +
- "the available values are %s", e, mode, SUPPORT_MODES);
- }
- }
-
- @Override
- public Set<String> segment(String text) {
- Set<String> result = InsertionOrderUtil.newSet();
- List<Word> words = WordSegmenter.segWithStopWords(text,
this.algorithm);
- for (Word word : words) {
- result.add(word.getText());
- }
- return result;
- }
-}
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
index a20d4798b..c2596cbc4 100644
--- 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 class CoreOptions extends OptionHolder {
"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 class CoreOptions extends OptionHolder {
"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
index 3674ee83f..c88488890 100644
---
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 class AnalyzerTest {
// 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
