init commit

nobaksan · Apr 10, 2018 · 308d801 · 308d801
1 parent c3576d2
commit 308d801
Show file tree

Hide file tree

Showing 10 changed files with 462 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,63 @@
+# Created by .ignore support plugin (hsz.mobi)
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+.idea/**
+
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# CMake
+cmake-build-debug/
+cmake-build-release/
+
+# Mongo Explorer plugin:
+.idea/**/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+.idea/compiler.xml
+.idea/copyright/
+.idea/libraries/
+.idea/markdown-navigator/
+.idea/misc.xml
+.idea/modules.xml
+.idea/preferred-vcs.xml
+.idea/workspace.xml
+elasticsearch-merge-token-filter.iml
diff --git a/.ignore b/.ignore
@@ -0,0 +1,65 @@
+# Created by .ignore support plugin (hsz.mobi)
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/dictionaries
+.idea/**
+
+
+# Sensitive or high-churn files:
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+
+# Gradle:
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# CMake
+cmake-build-debug/
+cmake-build-release/
+
+# Mongo Explorer plugin:
+.idea/**/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+.idea/compiler.xml
+.idea/copyright/
+.idea/libraries/
+.idea/markdown-navigator/
+.idea/misc.xml
+.idea/modules.xml
+.idea/preferred-vcs.xml
+.idea/workspace.xml
+.idea/encodings.xml
+.idea/vcs.xml
+elasticsearch-merge-token-filter.iml
diff --git a/plugin-descriptor.properties b/plugin-descriptor.properties
@@ -0,0 +1,6 @@
+description=Merge token filter
+version=${elasticsearch.version}
+name=elasticsearch-merge-token-filter
+classname=org.elasticsearch.plugin.analysis.starstory.AnalysisMergeFilterPlugin
+java.version=1.8
+elasticsearch.version=${elasticsearch.version}
diff --git a/pom.xml b/pom.xml
@@ -0,0 +1,138 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<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>
+
+    <groupId>org.elasticsearch</groupId>
+    <artifactId>elasticsearch-merge-token-filter</artifactId>
+    <version>6.1.0</version>
+
+    <packaging>jar</packaging>
+
+    <properties>
+        <lucene.version>7.2.1</lucene.version>
+        <elasticsearch.version>6.1.1</elasticsearch.version>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    </properties>
+
+    <licenses>
+        <license>
+            <name>The Apache Software License, Version 2.0</name>
+            <url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
+            <distribution>repo</distribution>
+        </license>
+    </licenses>
+
+    <dependencies>
+    <dependency>
+        <groupId>org.elasticsearch</groupId>
+        <artifactId>elasticsearch</artifactId>
+        <version>${elasticsearch.version}</version>
+        <scope>compile</scope>
+    </dependency>
+        <!-- https://mvnrepository.com/artifact/org.elasticsearch.test/framework -->
+        <dependency>
+            <groupId>org.elasticsearch.test</groupId>
+            <artifactId>framework</artifactId>
+            <version>6.1.1</version>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-api</artifactId>
+            <version>1.7.5</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-simple</artifactId>
+            <version>1.6.4</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.apache.lucene</groupId>
+            <artifactId>lucene-test-framework</artifactId>
+            <version>${lucene.version}</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>4.12</version>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-core</artifactId>
+            <version>2.8.2</version>
+            <scope>test</scope>
+        </dependency>
+
+
+        <dependency>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-api</artifactId>
+            <version>2.8.2</version>
+            <scope>test</scope>
+        </dependency>
+
+        <dependency>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-core</artifactId>
+            <version>2.8.2</version>
+        </dependency>
+
+
+    </dependencies>
+
+    <build>
+        <testResources>
+            <testResource>
+                <directory>${project.basedir}/src/test/resources</directory>
+            </testResource>
+        </testResources>
+        <plugins>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
+                <version>3.2</version>
+                <configuration>
+                    <source>1.8</source>
+                    <target>1.8</target>
+                </configuration>
+            </plugin>
+            <plugin>
+                <artifactId>maven-assembly-plugin</artifactId>
+                <version>2.3</version>
+                <configuration>
+                    <outputDirectory>${project.build.directory}/releases/</outputDirectory>
+                    <descriptors>
+                        <descriptor>${basedir}/src/main/assemblies/plugin.xml</descriptor>
+                    </descriptors>
+                </configuration>
+                <executions>
+                    <execution>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>single</goal>
+                        </goals>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>2.14</version>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-install-plugin</artifactId>
+                <version>2.4</version>
+            </plugin>
+        </plugins>
+    </build>
+
+</project>
diff --git a/src/main/assemblies/plugin.xml b/src/main/assemblies/plugin.xml
@@ -0,0 +1,34 @@
+<?xml version="1.0"?>
+<assembly>
+    <id>plugin</id>
+    <formats>
+        <format>zip</format>
+    </formats>
+    <includeBaseDirectory>false</includeBaseDirectory>
+    <dependencySets>
+        <dependencySet>
+            <outputDirectory>elasticsearch/</outputDirectory>
+            <useProjectArtifact>true</useProjectArtifact>
+            <useTransitiveFiltering>true</useTransitiveFiltering>
+            <excludes>
+                <exclude>org.elasticsearch:elasticsearch</exclude>
+            </excludes>
+        </dependencySet>
+        <dependencySet>
+            <outputDirectory>elasticsearch/</outputDirectory>
+            <useProjectArtifact>true</useProjectArtifact>
+            <useTransitiveFiltering>true</useTransitiveFiltering>
+            <includes>
+                <include>org.slf4j:slf4j-api</include>
+                <include>org.slf4j:slf4j-simple</include>
+            </includes>
+        </dependencySet>
+    </dependencySets>
+    <files>
+        <file>
+            <source>plugin-descriptor.properties</source>
+            <outputDirectory>elasticsearch/</outputDirectory>
+            <filtered>true</filtered>
+        </file>
+    </files>
+</assembly>
diff --git a/src/main/java/elasticsearch/merge/MergeTokenFilter.java b/src/main/java/elasticsearch/merge/MergeTokenFilter.java
@@ -0,0 +1,64 @@
+package elasticsearch.merge;
+
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.util.AttributeSource;
+
+import java.io.IOException;
+
+/**
+ * Created by nobaksan on 2018. 4. 9..
+ */
+public class MergeTokenFilter extends TokenFilter {
+    private final CharTermAttribute termAtt = (CharTermAttribute)addAttribute(CharTermAttribute.class);
+    private final PositionIncrementAttribute posIncrAtt = (PositionIncrementAttribute)addAttribute(PositionIncrementAttribute.class);
+    private String tokenSeparator = null;
+    private int incrementGap = 100;
+    private StringBuilder builder = new StringBuilder();
+    private AttributeSource.State previousState = null;
+    private boolean recheckPrevious = false;
+
+    public MergeTokenFilter(TokenStream input, String tokenSeparator)
+    {
+        super(input);
+        this.tokenSeparator = (tokenSeparator != null ? tokenSeparator : "_");
+    }
+
+    @Override
+    public boolean incrementToken() throws IOException
+    {
+        boolean empty = false;
+        this.builder.setLength(0);
+        if (this.recheckPrevious)
+        {
+            restoreState(this.previousState);
+
+            this.builder.append(this.termAtt.buffer(), 0, this.termAtt.length());
+            this.recheckPrevious = false;
+        }
+        while (this.input.incrementToken()) {
+            if (this.posIncrAtt.getPositionIncrement() <= this.incrementGap)
+            {
+                if (this.builder.length() > 0) {
+                    this.builder.append(this.tokenSeparator);
+                }
+                this.builder.append(this.termAtt.buffer(), 0, this.termAtt.length());
+            }
+            else
+            {
+                this.recheckPrevious = true;
+                this.previousState = captureState();
+            }
+        }
+        if (this.builder.length() > 0)
+        {
+            this.termAtt.setEmpty().append(this.builder);
+            if (!this.recheckPrevious) {
+                empty = true;
+            }
+        }
+        return empty;
+    }
+}