Incorporates reviewer feedback of 2.0.0 RC2 (#285)

* Only add the log4j2.xml to the fat-jar for CLI-like modules, so it does not leak into Maven attached artifacts * Move configuration samples into README files * Fix some warning regarding the shaded artifact
dkpro · Nov 22, 2023 · 4ab7b9d · 4ab7b9d
1 parent 0917eec
commit 4ab7b9d
Show file tree

Hide file tree

Showing 13 changed files with 160 additions and 363 deletions.
diff --git a/dkpro-jwpl-datamachine/pom.xml b/dkpro-jwpl-datamachine/pom.xml
@@ -56,6 +56,26 @@
   </dependencies>
   <build>
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-source-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-jar-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
       <plugin>
         <artifactId>maven-assembly-plugin</artifactId>
         <executions>

diff --git a/dkpro-jwpl-datamachine/src/main/assembly/assembly.xml b/dkpro-jwpl-datamachine/src/main/assembly/assembly.xml
@@ -39,4 +39,13 @@
             <handlerName>metaInf-services</handlerName>
         </containerDescriptorHandler>
     </containerDescriptorHandlers>
+    <fileSets>
+        <fileSet>
+            <directory>${project.basedir}/src/main/resources</directory>
+            <includes>
+                <include>log4j2.xml</include>
+            </includes>
+            <outputDirectory>/</outputDirectory>
+        </fileSet>
+    </fileSets>
 </assembly>
diff --git a/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/pom.xml b/dkpro-jwpl-deps/dkpro-jwpl-swc-engine-shade/pom.xml
@@ -115,9 +115,18 @@
                   <include>org.sweble.wikitext:swc-engine:*</include> 
                 </includes>
               </artifactSet>
+              <filters>
+                <filter>
+                  <artifact>*:*</artifact>
+                  <excludes>
+                    <exclude>META-INF/MANIFEST.MF</exclude>
+                    <exclude>META-INF/maven/**</exclude>
+                    <exclude>org.sweble.wikitext/swc-engine/git.properties</exclude>
+                  </excludes>
+                </filter>
+              </filters>
               <transformers>
-                <transformer
-                  implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
+                <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
               </transformers>
               <relocations>
                 <relocation>

diff --git a/dkpro-jwpl-revisionmachine/pom.xml b/dkpro-jwpl-revisionmachine/pom.xml
@@ -84,6 +84,26 @@
 
   <build>
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-source-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-jar-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
       <plugin>
         <artifactId>maven-assembly-plugin</artifactId>
         <executions>

diff --git a/dkpro-jwpl-revisionmachine/src/main/assembly/assembly.xml b/dkpro-jwpl-revisionmachine/src/main/assembly/assembly.xml
@@ -39,4 +39,13 @@
             <handlerName>metaInf-services</handlerName>
         </containerDescriptorHandler>
     </containerDescriptorHandlers>
+    <fileSets>
+        <fileSet>
+            <directory>${project.basedir}/src/main/resources</directory>
+            <includes>
+                <include>log4j2.xml</include>
+            </includes>
+            <outputDirectory>/</outputDirectory>
+        </fileSet>
+    </fileSets>
 </assembly>
diff --git a/dkpro-jwpl-timemachine/README.TXT → dkpro-jwpl-timemachine/README.md b/dkpro-jwpl-timemachine/README.TXT → dkpro-jwpl-timemachine/README.md
@@ -1,11 +1,12 @@
-JWPLTimeMachine
+# JWPLTimeMachine
 
 USAGE:
 
 StartDBMapping <configuration.xml>
 
 EXAMPLE FILE:
 
+```xml
 <?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
 <properties>
@@ -22,6 +23,7 @@ EXAMPLE FILE:
   <entry key="outputDirectory">/home/zesch/wiki_data/elwiki_test</entry>
   <entry key="removeInputFilesAfterProcessing">false</entry>
 </properties>
+```
 
  * language - The used language. The language string must correspond to one of the values enumerated in WikiConstants.Language in the JWPL. Examples: english, german, frensh, arabic.
  * mainCategory - The title of the main category of the Wikipedia language version used. For example, "Categories" for the English Wikipedia or "!Hauptkategorie" for the German Wikipedia.
@@ -34,3 +36,47 @@ EXAMPLE FILE:
  * categoryLinksFile - The absolute path to the categorylinks file only .sql and .sql.gz extensions are supported.
  * outputDirectory - The absolute path to the directory to which the transformed files will be written. The outputDirectory will be created if it does not exist. However its parent directory must exist.
  * removeInputFilesAfterProcessing - A boolean that specifies whether the meta-history file, the pagelinks file and the categorylinks file should be removed after the processing.
+
+# Config Examples
+
+## Greek
+
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
+<properties>
+  <comment>This a configuration formular for the JWPL TimeMachine</comment>
+  <entry key="language">greek</entry>
+  <entry key="mainCategory">Κατηγορίες</entry>
+  <entry key="disambiguationCategory">Αποσαφήνιση</entry>
+  <entry key="fromTimestamp">20060101000000</entry>
+  <entry key="toTimestamp">20060102000000</entry>
+  <entry key="each">1</entry>
+  <entry key="metaHistoryFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-pages-meta-history.xml.bz2</entry>
+  <entry key="categoryLinksFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-categorylinks.sql.gz</entry>
+  <entry key="pageLinksFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-pagelinks.sql.gz</entry>
+  <entry key="outputDirectory">/home/zesch/wiki_data/elwiki_test</entry>
+  <entry key="removeInputFilesAfterProcessing">false</entry>
+</properties>
+```
+
+## Arabic
+
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
+<properties>
+    <comment>This a configuration formular for the JWPL TimeMachine</comment>
+    <entry key="language">greek</entry>
+    <entry key="mainCategory">Κατηγορίες</entry>
+    <entry key="disambiguationCategory">Αποσαφήνιση</entry>
+    <entry key="fromTimestamp">20060101000000</entry>
+    <entry key="toTimestamp">20060102000000</entry>
+    <entry key="each">1</entry>
+    <entry key="metaHistoryFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-pages-meta-history.xml.bz2</entry>
+    <entry key="categoryLinksFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-categorylinks.sql.gz</entry>
+    <entry key="pageLinksFile">/home/zesch/wiki_data/elwiki/elwiki-20080205-pagelinks.sql.gz</entry>
+    <entry key="outputDirectory">/home/zesch/wiki_data/elwiki_test</entry>
+    <entry key="removeInputFilesAfterProcessing">false</entry>
+</properties>
+```
diff --git a/dkpro-jwpl-timemachine/config_file_arabic_one_snapshot.xml b/dkpro-jwpl-timemachine/config_file_arabic_one_snapshot.xml
diff --git a/dkpro-jwpl-timemachine/config_file_greek_one_snapshot.xml b/dkpro-jwpl-timemachine/config_file_greek_one_snapshot.xml
diff --git a/dkpro-jwpl-timemachine/pom.xml b/dkpro-jwpl-timemachine/pom.xml
@@ -62,6 +62,26 @@
 
   <build>
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-source-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-jar-plugin</artifactId>
+        <configuration>
+          <excludes>
+            <!-- exclude it here as we only want to add it to the fat jar -->
+            <exclude>**/log4j2.xml</exclude>
+          </excludes>
+        </configuration>
+      </plugin>
       <plugin>
         <artifactId>maven-assembly-plugin</artifactId>
         <executions>

diff --git a/dkpro-jwpl-timemachine/src/main/assembly/assembly.xml b/dkpro-jwpl-timemachine/src/main/assembly/assembly.xml
@@ -39,4 +39,13 @@
             <handlerName>metaInf-services</handlerName>
         </containerDescriptorHandler>
     </containerDescriptorHandlers>
+    <fileSets>
+        <fileSet>
+            <directory>${project.basedir}/src/main/resources</directory>
+            <includes>
+                <include>log4j2.xml</include>
+            </includes>
+            <outputDirectory>/</outputDirectory>
+        </fileSet>
+    </fileSets>
 </assembly>
diff --git a/...n/resources/templategen.properties.sample → dkpro-jwpl-util/README.md b/...n/resources/templategen.properties.sample → dkpro-jwpl-util/README.md
@@ -1,3 +1,16 @@
+# JWPL Util
+
+## Template Schema
+
+```sql
+CREATE TABLE IF NOT EXISTS templateId_pageId (templateId INTEGER UNSIGNED NOT NULL,pageId INTEGER UNSIGNED NOT NULL, UNIQUE(templateId, pageId)) ENGINE = MYISAM;
+CREATE TABLE IF NOT EXISTS templates (templateId INTEGER NOT NULL AUTO_INCREMENT,templateName TEXT NOT NULL,PRIMARY KEY(templateId)) ENGINE = MYISAM;
+CREATE TABLE IF NOT EXISTS templateId_revisionId(templateId INTEGER UNSIGNED NOT NULL,revisionId INTEGER UNSIGNED NOT NULL, UNIQUE(templateId, revisionId)) ENGINE = MYISAM;
+```
+
+## Properties Sample
+
+```
 #host=dbhost
 #db=revisiondb
 #user=username
@@ -33,4 +46,5 @@ pages_black_list=
 revisions_white_list=official_schprooche
 revisions_white_prefix_list=
 revisions_black_prefix_list=
-revisions_black_list=
+revisions_black_list=
+```
diff --git a/dkpro-jwpl-util/src/main/resources/create_tpltables_simplegenerator.sql b/dkpro-jwpl-util/src/main/resources/create_tpltables_simplegenerator.sql