Resolves "Reviewer feedback for 2.0.0 RC1" (#283)

dkpro · Nov 20, 2023 · 0917eec · 0917eec
1 parent 47deef4
commit 0917eec
Show file tree

Hide file tree

Showing 32 changed files with 126 additions and 184 deletions.
diff --git a/dkpro-jwpl-api/pom.xml b/dkpro-jwpl-api/pom.xml
@@ -182,13 +182,6 @@
           <include>**/*</include>
         </includes>
       </resource>
-      <resource>
-        <directory>src/it/resources</directory>
-        <filtering>true</filtering>
-        <includes>
-          <include>**/*</include>
-        </includes>
-      </resource>
     </resources>
     <plugins>
       <plugin>
@@ -270,24 +263,6 @@
           </execution>
         </executions>
       </plugin>
-      <plugin>
-        <artifactId>maven-assembly-plugin</artifactId>
-        <executions>
-          <execution>
-            <id>create-executable-jar</id>
-            <phase>package</phase>
-            <goals>
-              <goal>single</goal>
-            </goals>
-            <configuration>
-              <attach>false</attach>
-              <descriptorRefs>
-                <descriptor>jar-with-dependencies</descriptor>
-              </descriptorRefs>
-            </configuration>
-          </execution>
-        </executions>
-      </plugin>
     </plugins>
   </build>
 </project>
diff --git a/dkpro-jwpl-api/src/it/java/org/dkpro/jwpl/api/PerformanceTest.java b/dkpro-jwpl-api/src/it/java/org/dkpro/jwpl/api/PerformanceTest.java
@@ -26,7 +26,7 @@
 import java.util.Set;
 
 import org.dkpro.jwpl.api.exception.WikiApiException;
-import org.dkpro.jwpl.util.GraphUtilities;
+import org.dkpro.jwpl.api.util.GraphUtilities;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/CategoryGraph.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/CategoryGraph.java
@@ -39,10 +39,10 @@
 import org.dkpro.jwpl.api.exception.WikiApiException;
 import org.dkpro.jwpl.api.exception.WikiPageNotFoundException;
 import org.dkpro.jwpl.api.exception.WikiTitleParsingException;
+import org.dkpro.jwpl.api.util.ApiUtilities;
+import org.dkpro.jwpl.api.util.CommonUtilities;
 import org.dkpro.jwpl.api.util.GraphSerialization;
-import org.dkpro.jwpl.util.ApiUtilities;
-import org.dkpro.jwpl.util.CommonUtilities;
-import org.dkpro.jwpl.util.OS;
+import org.dkpro.jwpl.api.util.OS;
 import org.jgrapht.GraphPath;
 import org.jgrapht.alg.connectivity.ConnectivityInspector;
 import org.jgrapht.alg.shortestpath.DijkstraShortestPath;

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/Page.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/Page.java
@@ -25,14 +25,14 @@
 import org.dkpro.jwpl.api.exception.WikiTitleParsingException;
 import org.dkpro.jwpl.api.hibernate.PageDAO;
 import org.dkpro.jwpl.api.sweble.PlainTextConverter;
-import org.dkpro.jwpl.util.UnmodifiableArraySet;
+import org.dkpro.jwpl.api.util.UnmodifiableArraySet;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.PageId;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.PageTitle;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.WtEngineImpl;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.nodes.EngProcessedPage;
 import org.hibernate.LockOptions;
 import org.hibernate.Session;
 import org.hibernate.type.StandardBasicTypes;
-import org.sweble.wikitext.engine.PageId;
-import org.sweble.wikitext.engine.PageTitle;
-import org.sweble.wikitext.engine.WtEngineImpl;
-import org.sweble.wikitext.engine.nodes.EngProcessedPage;
 
 import de.fau.cs.osr.ptk.common.AstVisitor;
 

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/PageQueryIterable.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/PageQueryIterable.java
@@ -24,8 +24,8 @@
 
 import org.dkpro.jwpl.api.exception.WikiApiException;
 import org.dkpro.jwpl.api.exception.WikiPageNotFoundException;
-import org.dkpro.jwpl.util.ApiUtilities;
-import org.dkpro.jwpl.util.StringUtils;
+import org.dkpro.jwpl.api.util.ApiUtilities;
+import org.dkpro.jwpl.api.util.StringUtils;
 import org.hibernate.Session;
 import org.hibernate.query.Query;
 import org.slf4j.Logger;

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/WikiConstants.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/WikiConstants.java
@@ -22,9 +22,9 @@
 
 import javax.xml.parsers.ParserConfigurationException;
 
-import org.sweble.wikitext.engine.config.WikiConfig;
-import org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
-import org.sweble.wikitext.engine.utils.LanguageConfigGenerator;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.config.WikiConfig;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.utils.LanguageConfigGenerator;
 import org.xml.sax.SAXException;
 
 import com.neovisionaries.i18n.LanguageCode;

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/Wikipedia.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/Wikipedia.java
@@ -34,13 +34,13 @@
 import org.dkpro.jwpl.api.exception.WikiPageNotFoundException;
 import org.dkpro.jwpl.api.exception.WikiTitleParsingException;
 import org.dkpro.jwpl.api.hibernate.WikiHibernateUtil;
-import org.dkpro.jwpl.util.distance.LevenshteinStringDistance;
+import org.dkpro.jwpl.api.util.distance.LevenshteinStringDistance;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.config.WikiConfig;
 import org.hibernate.Session;
 import org.hibernate.query.NativeQuery;
 import org.hibernate.type.StandardBasicTypes;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
-import org.sweble.wikitext.engine.config.WikiConfig;
 
 /**
  * Provides access to Wikipedia articles and categories.

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/WikipediaInfo.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/WikipediaInfo.java
@@ -28,7 +28,7 @@
 
 import org.dkpro.jwpl.api.exception.WikiApiException;
 import org.dkpro.jwpl.api.exception.WikiPageNotFoundException;
-import org.dkpro.jwpl.util.ApiUtilities;
+import org.dkpro.jwpl.api.util.ApiUtilities;
 import org.hibernate.Session;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/sweble/PlainTextConverter.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/sweble/PlainTextConverter.java
@@ -23,11 +23,11 @@
 import java.util.List;
 import java.util.regex.Pattern;
 
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.PageTitle;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.config.WikiConfig;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
-import org.sweble.wikitext.engine.PageTitle;
-import org.sweble.wikitext.engine.config.WikiConfig;
-import org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
 import org.sweble.wikitext.parser.nodes.WtBold;
 import org.sweble.wikitext.parser.nodes.WtExternalLink;
 import org.sweble.wikitext.parser.nodes.WtHorizontalRule;

diff --git a/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/sweble/TemplateNameExtractor.java b/dkpro-jwpl-api/src/main/java/org/dkpro/jwpl/api/sweble/TemplateNameExtractor.java
@@ -29,8 +29,8 @@
 import java.util.LinkedList;
 import java.util.List;
 
-import org.sweble.wikitext.engine.config.WikiConfig;
-import org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.config.WikiConfig;
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.utils.DefaultConfigEnWp;
 import org.sweble.wikitext.parser.nodes.WtNode;
 import org.sweble.wikitext.parser.nodes.WtTemplate;
 

diff --git a/...ava/org/dkpro/jwpl/util/ApiUtilities.java → ...org/dkpro/jwpl/api/util/ApiUtilities.java b/...ava/org/dkpro/jwpl/util/ApiUtilities.java → ...org/dkpro/jwpl/api/util/ApiUtilities.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.lang.invoke.MethodHandles;
 

diff --git a/.../org/dkpro/jwpl/util/CommonUtilities.java → .../dkpro/jwpl/api/util/CommonUtilities.java b/.../org/dkpro/jwpl/util/CommonUtilities.java → .../dkpro/jwpl/api/util/CommonUtilities.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.util.Arrays;
 import java.util.Map;

diff --git a/...java/org/dkpro/jwpl/util/DbUtilities.java → .../org/dkpro/jwpl/api/util/DbUtilities.java b/...java/org/dkpro/jwpl/util/DbUtilities.java → .../org/dkpro/jwpl/api/util/DbUtilities.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.lang.invoke.MethodHandles;
 import java.sql.Connection;

diff --git a/...a/org/dkpro/jwpl/util/GraphUtilities.java → ...g/dkpro/jwpl/api/util/GraphUtilities.java b/...a/org/dkpro/jwpl/util/GraphUtilities.java → ...g/dkpro/jwpl/api/util/GraphUtilities.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.lang.invoke.MethodHandles;
 import java.util.HashSet;

diff --git a/...g/dkpro/jwpl/util/HibernateUtilities.java → ...pro/jwpl/api/util/HibernateUtilities.java b/...g/dkpro/jwpl/util/HibernateUtilities.java → ...pro/jwpl/api/util/HibernateUtilities.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.util.HashMap;
 import java.util.Map;

diff --git a/...src/main/java/org/dkpro/jwpl/util/OS.java → ...main/java/org/dkpro/jwpl/api/util/OS.java b/...src/main/java/org/dkpro/jwpl/util/OS.java → ...main/java/org/dkpro/jwpl/api/util/OS.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 public class OS
 {

diff --git a/...java/org/dkpro/jwpl/util/StringUtils.java → .../org/dkpro/jwpl/api/util/StringUtils.java b/...java/org/dkpro/jwpl/util/StringUtils.java → .../org/dkpro/jwpl/api/util/StringUtils.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.util.Collection;
 import java.util.Iterator;

diff --git a/...dkpro/jwpl/util/UnmodifiableArraySet.java → ...o/jwpl/api/util/UnmodifiableArraySet.java b/...dkpro/jwpl/util/UnmodifiableArraySet.java → ...o/jwpl/api/util/UnmodifiableArraySet.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util;
+package org.dkpro.jwpl.api.util;
 
 import java.util.Arrays;
 import java.util.Collection;

diff --git a/...l/distance/LevenshteinStringDistance.java → ...l/distance/LevenshteinStringDistance.java b/...l/distance/LevenshteinStringDistance.java → ...l/distance/LevenshteinStringDistance.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util.distance;
+package org.dkpro.jwpl.api.util.distance;
 
 public class LevenshteinStringDistance
     implements StringDistance

diff --git a/...ro/jwpl/util/distance/StringDistance.java → ...wpl/api/util/distance/StringDistance.java b/...ro/jwpl/util/distance/StringDistance.java → ...wpl/api/util/distance/StringDistance.java
@@ -15,7 +15,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package org.dkpro.jwpl.util.distance;
+package org.dkpro.jwpl.api.util.distance;
 
 public interface StringDistance
 {

diff --git a/dkpro-jwpl-api/src/test/java/org/dkpro/jwpl/api/WikiConfigTest.java b/dkpro-jwpl-api/src/test/java/org/dkpro/jwpl/api/WikiConfigTest.java
@@ -19,8 +19,8 @@
 
 import static org.junit.jupiter.api.Assertions.assertSame;
 
+import org.dkpro.jwpl.shade.org.sweble.wikitext.engine.config.WikiConfig;
 import org.junit.jupiter.api.Test;
-import org.sweble.wikitext.engine.config.WikiConfig;
 
 public class WikiConfigTest
 {

diff --git a/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/NOTICE.txt b/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/NOTICE.txt
@@ -0,0 +1,8 @@
+All classes from this module are taken from third parties.
+
+The classes were published by the Sweble project provided
+via https://github.com/sweble/sweble-wikitext
+by the Open Source Research Group, University of Erlangen-Nürnberg
+
+under the Apache License, Version 2.0
+(http://www.apache.org/licenses/LICENSE-2.0)
diff --git a/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/pom.xml b/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/pom.xml
@@ -124,6 +124,10 @@
                   <pattern>javax.xml.bind</pattern>
                   <shadedPattern>jakarta.xml.bind</shadedPattern>
                 </relocation>
+                <relocation>
+                  <pattern>org.sweble.wikitext.engine</pattern>
+                  <shadedPattern>org.dkpro.jwpl.shade.org.sweble.wikitext.engine</shadedPattern>
+                </relocation>
               </relocations>
             </configuration>
           </execution>
@@ -146,7 +150,6 @@
         -->
         <groupId>org.codehaus.mojo</groupId>
         <artifactId>build-helper-maven-plugin</artifactId>
-        <version>3.4.0</version>
         <executions>
           <execution>
             <id>workaround-makeItVisibleOnIntellij</id>

diff --git a/dkpro-jwpl-revisionmachine/README b/dkpro-jwpl-revisionmachine/README
@@ -1,17 +1,73 @@
-Known Issues
+# Config Examples
 
-Please also see the issues on Google Code 
-http://code.google.com/p/jwpl/issues/list
+## Diff Tool Config
 
+```xml
+<config>
+	<values>
+		<VALUE_MINIMUM_LONGEST_COMMON_SUBSTRING>12</VALUE_MINIMUM_LONGEST_COMMON_SUBSTRING>
+		<COUNTER_FULL_REVISION>1000</COUNTER_FULL_REVISION>
+	</values>
+	<externals>
+		<sevenzip>"D:\Programme\Utilities\7-Zip\7z.exe"</sevenzip>
+	</externals>
+	<input>
+		<MODE_SURROGATES>DISCARD_REVISION</MODE_SURROGATES>
+		<WIKIPEDIA_ENCODING>UTF-8</WIKIPEDIA_ENCODING>
+		<archive>
+			<type>SEVENZIP</type>
+			<path>"D:\simplewiki.7z"</path>
+			<start>0</start>
+		</archive>
+	</input>
+	<output>
+		<OUTPUT_MODE>SQL</OUTPUT_MODE>
+		<PATH>""</PATH>
+		<LIMIT_SQL_FILE_SIZE>1000000000</LIMIT_SQL_FILE_SIZE>
+		<MODE_ZIP_COMPRESSION_ENABLED>true</MODE_ZIP_COMPRESSION_ENABLED>
+	</output>
+	<cache>
+		<LIMIT_TASK_SIZE_REVISIONS>5000000</LIMIT_TASK_SIZE_REVISIONS>
+		<LIMIT_TASK_SIZE_DIFFS>1000000</LIMIT_TASK_SIZE_DIFFS>
+		<LIMIT_SQLSERVER_MAX_ALLOWED_PACKET>1000000</LIMIT_SQLSERVER_MAX_ALLOWED_PACKET>
+	</cache>
+	<logging>
+		<root_folder>""</root_folder>
+		<diff_tool>
+			<level>INFO</level>
+		</diff_tool>
+	</logging>
+	<debug>
+		<verification_diff>false</verification_diff>
+		<verification_encoding>false</verification_encoding>
+		<statistical_output>false</statistical_output>
+		<debug_output>
+			<enabled>false</enabled>
+			<path>""</path>
+		</debug_output>
+	</debug>
+	<filter>
+		<namespaces>
+			<!-- White list of namespaces; if nothing here then all namespaces are allowed -->
+			<ns>0</ns>
+			<ns>1</ns>
+		</namespaces>
+	</filter>
+</config>
 
-I) 
-Handling of surrogate characters
+```
 
-There are 4 possible modes of handling UTF8 surrogate characters.
-Currently, the only reliable mode is "Discard Revision", in which any revision that contains surrogate characters is discarded.
-The other three modes in "org.dkpro.jwpl.revisionmachine.difftool.data.SurrogateModes" have been disabled for now.
-The corresponding config-section in the config tool has also been made invisible (org.dkpro.jwpl.revisionmachine.difftool.config.gui.panels.InputPanel)
-The disabled parts are marked with TODO-markers
+## Index Generator Config
 
-In order to use the other three surrogate modes, which try to handle surrogate characters differently,
-the corresponding code has to be checked. Afterwards, the modes can be reenables in the config tool (InputPanel.java) and the SurrogateModes-class
+```
+host=localhost
+db=wiki_en_20110405_rev
+user=student
+password=student
+output=target
+outputDatabase=false
+outputDatafile=false
+charset=UTF8
+buffer=15000
+maxAllowedPackets=16760832
+```