commit 81925096b645bf17cf688d1311bce002b5a9418f
author Marc Kupietz <kupietz@ids-mannheim.de> Mon Sep 07 15:16:51 2020 +0200
committer Marc K <morckx@gmail.com> Mon Sep 07 15:25:28 2020 +0200
tree 72e8930b1290ff3567cd9987d7e425d9b5e4c580
parent 478632eb7e133969531f3b401576564783183707

Use original Span class and implement Tokenizer interface from OpenNLP

Using maven assembly plugin to include the required classes into a jar
for binary distribution.

This makes it possible to use KorAPTokenizerImpl as tokenizer in OpenNLP
applications.

Change-Id: I627dcdd046334db1b1ae9dd60cf7104fd3a3c518

src/assembly/bin-distribution.xml

diff --git a/src/assembly/bin-distribution.xml b/src/assembly/bin-distribution.xml
new file mode 100644
index 0000000..5b4aca9
--- /dev/null
+++ b/src/assembly/bin-distribution.xml
@@ -0,0 +1,40 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<assembly xmlns="http://maven.apache.org/ASSEMBLY/2.1.0"
+          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+          xsi:schemaLocation="http://maven.apache.org/ASSEMBLY/2.1.0 http://maven.apache.org/xsd/assembly-2.1.0.xsd">
+    <id>jar-with-dependencies-and-exclude-classes</id>
+    <formats>
+        <format>jar</format>
+    </formats>
+    <includeBaseDirectory>false</includeBaseDirectory>
+    <dependencySets>
+        <dependencySet>
+            <outputDirectory>/</outputDirectory>
+            <useProjectArtifact>false</useProjectArtifact>
+            <unpack>true</unpack>
+            <unpackOptions>
+                <includes>
+                    <include>opennlp/tools/util/Span.class</include>
+                    <include>opennlp/tools/tokenize/Tokenizer.class</include>
+                </includes>
+            </unpackOptions>
+            <scope>runtime</scope>
+        </dependencySet>
+    </dependencySets>
+    <fileSets>
+        <fileSet>
+            <directory>${project.basedir}</directory>
+            <outputDirectory>META-INF/</outputDirectory>
+            <includes>
+                <include>README*</include>
+                <include>Readme*</include>
+                <include>LICENSE*</include>
+            </includes>
+            <useDefaultExcludes>true</useDefaultExcludes>
+        </fileSet>
+        <fileSet>
+            <outputDirectory>/</outputDirectory>
+            <directory>${project.build.outputDirectory}</directory>
+        </fileSet>
+    </fileSets>
+</assembly>
\ No newline at end of file

src/assembly/src-distribution.xml

diff --git a/src/assembly/src-distribution.xml b/src/assembly/src-distribution.xml
new file mode 100644
index 0000000..675c51e
--- /dev/null
+++ b/src/assembly/src-distribution.xml
@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<assembly xmlns="http://maven.apache.org/ASSEMBLY/2.1.0"
+          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+          xsi:schemaLocation="http://maven.apache.org/ASSEMBLY/2.1.0 http://maven.apache.org/xsd/assembly-2.1.0.xsd">
+    <id>src</id>
+    <formats>
+        <format>zip</format>
+    </formats>
+    <fileSets>
+        <fileSet>
+            <directory>${project.basedir}</directory>
+            <includes>
+                <include>README*</include>
+                <include>Readme*</include>
+                <include>LICENSE*</include>
+                <include>NOTICE*</include>
+                <include>pom.xml</include>
+            </includes>
+            <useDefaultExcludes>true</useDefaultExcludes>
+        </fileSet>
+        <fileSet>
+            <directory>${project.build.sourceDirectory}/src</directory>
+            <useDefaultExcludes>true</useDefaultExcludes>
+        </fileSet>
+    </fileSets>
+</assembly>