#5265 - Extract paragraph structure from PDF files

.github/workflows/maven.yml

@@ -70,18 +70,6 @@ jobs:
       with:
         maven-version: 3.9.9
 
-    - name: Set up cache date
-      run: echo "CACHE_DATE=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
-
-    - name: Cache Maven repository
-      id: maven-cache
-      uses: actions/cache@1bd1e32a3bdc45362d1e726936510720a7c30a57 # v4.2.0
-      with:
-        path: ~/.m2/repository
-        key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}-${{ env.CACHE_DATE }}
-        restore-keys: |
-          ${{ runner.os }}-maven-
-
     - name: Cache Docker layers
       uses: actions/cache@1bd1e32a3bdc45362d1e726936510720a7c30a57 # v4.2.0
       with:

inception/inception-io-xml/src/main/java/de/tudarmstadt/ukp/inception/io/xml/dkprocore/CasXmlHandler.java

@@ -57,6 +57,7 @@ public class CasXmlHandler
     private XmlDocument docNode;
     private boolean captureText = true;
     private boolean splitSentencesInBlockElements = true;
+    private boolean commitText = true;
 
     private final Set<ElementListener> listeners = new LinkedHashSet<>();
 
@@ -67,6 +68,11 @@ public CasXmlHandler(JCas aJCas)
         stack = new ArrayDeque<>();
     }
 
+    public void setCommitText(boolean aCommitText)
+    {
+        commitText = aCommitText;
+    }
+
     public void addListener(ElementListener aListener)
     {
         listeners.add(aListener);
@@ -125,7 +131,9 @@ public void endDocument() throws SAXException
             l.endDocument(docNode);
         }
 
-        jcas.setDocumentText(text.toString());
+        if (commitText) {
+            jcas.setDocumentText(text.toString());
+        }
 
         if (!blockElements.isEmpty()) {
             if (splitSentencesInBlockElements) {
@@ -213,7 +221,7 @@ public void endElement(String aUri, String aLocalName, String aQName) throws SAX
     }
 
     @Override
-    public void characters(char[] aCh, int aStart, int aLength) throws SAXException
+    public void characters(char[] aCh, int aStart, int aLength)
     {
         if (stack.isEmpty()) {
             // We ignore any characters outside the root elements. These could include e.g.
@@ -241,7 +249,7 @@ public void characters(char[] aCh, int aStart, int aLength) throws SAXException
     }
 
     @Override
-    public void ignorableWhitespace(char[] aCh, int aStart, int aLength) throws SAXException
+    public void ignorableWhitespace(char[] aCh, int aStart, int aLength)
     {
         characters(aCh, aStart, aLength);
     }

inception/inception-pdf-editor2/pom.xml

@@ -73,6 +73,10 @@
       <groupId>de.tudarmstadt.ukp.inception.app</groupId>
       <artifactId>inception-external-editor</artifactId>
     </dependency>
+    <dependency>
+      <groupId>de.tudarmstadt.ukp.inception.app</groupId>
+      <artifactId>inception-io-xml</artifactId>
+    </dependency>
 
     <dependency>
       <groupId>org.apache.commons</groupId>