#1629 - Drop LingPip

.github/workflows/maven.yml

@@ -14,6 +14,9 @@ on:
   pull_request:
     branches: [ "main", "release/**" ]
 
+permissions:
+  contents: read
+
 jobs:
   build:
     strategy:

dkpro-core-api-datasets-asl/src/main/java/org/dkpro/core/api/datasets/DatasetLoader.java

@@ -250,8 +250,8 @@ private void extract(File aArchive, ArchiveInputStream aArchiveStream, File aTar
                 throw new IllegalStateException("Filename must not contain line break");
             }
 
-            Path base = aTarget.toPath().toAbsolutePath();
-            Path out = base.resolve(name).toAbsolutePath();
+            Path base = aTarget.toPath().toAbsolutePath().normalize();
+            Path out = base.resolve(name).toAbsolutePath().normalize();
 
             if (!out.startsWith(base)) {
                 // Ignore attempts to write outside the base

dkpro-core-api-datasets-asl/src/main/java/org/dkpro/core/api/datasets/internal/actions/Explode.java

@@ -109,7 +109,8 @@ private void extract7z(ActionDescription aAction, Path aArchive, Path aTarget)
         throws IOException, RarException
     {
         // We always extract archives into a subfolder. Figure out the name of the folder.
-        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath();
+        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath()
+                .normalize();
 
         Map<String, Object> cfg = aAction.getConfiguration();
         int strip = cfg.containsKey("strip") ? (int) cfg.get("strip") : 0;
@@ -131,7 +132,7 @@ private void extract7z(ActionDescription aAction, Path aArchive, Path aTarget)
                 }
 
                 if (filter.accept(name)) {
-                    Path out = base.resolve(name).toAbsolutePath();
+                    Path out = base.resolve(name).toAbsolutePath().normalize();
                     if (!out.startsWith(base)) {
                         throw new IOException(
                                 "Archive tries to generate file outside target folder: [" + name
@@ -159,7 +160,8 @@ private void extractRar(ActionDescription aAction, Path aArchive, Path aTarget)
         throws IOException, RarException
     {
         // We always extract archives into a subfolder. Figure out the name of the folder.
-        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath();
+        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath()
+                .normalize();
 
         Map<String, Object> cfg = aAction.getConfiguration();
         int strip = cfg.containsKey("strip") ? (int) cfg.get("strip") : 0;
@@ -181,7 +183,7 @@ private void extractRar(ActionDescription aAction, Path aArchive, Path aTarget)
                 }
 
                 if (filter.accept(name)) {
-                    Path out = base.resolve(name).toAbsolutePath();
+                    Path out = base.resolve(name).toAbsolutePath().normalize();
                     if (!out.startsWith(base)) {
                         throw new IOException(
                                 "Archive tries to generate file outside target folder: [" + name
@@ -209,7 +211,8 @@ private void extract(ActionDescription aAction, Path aArchive, ArchiveInputStrea
         throws IOException
     {
         // We always extract archives into a subfolder. Figure out the name of the folder.
-        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath();
+        Path base = aTarget.resolve(getPathWithoutFileExtension(aArchive)).toAbsolutePath()
+                .normalize();
 
         Map<String, Object> cfg = aAction.getConfiguration();
         int strip = cfg.containsKey("strip") ? (int) cfg.get("strip") : 0;
@@ -230,7 +233,7 @@ private void extract(ActionDescription aAction, Path aArchive, ArchiveInputStrea
             }
 
             if (filter.accept(name)) {
-                Path out = base.resolve(name).toAbsolutePath();
+                Path out = base.resolve(name).toAbsolutePath().normalize();
                 if (!out.startsWith(base)) {
                     throw new IOException(
                             "Archive tries to generate file outside target folder: [" + name + "]");

dkpro-core-api-frequency-asl/src/main/java/org/dkpro/core/api/frequency/util/FrequencyDistribution.java

@@ -255,7 +255,7 @@ public void load(File file) throws IOException, ClassNotFoundException
         freqDist = (Object2LongOpenHashMap<T>) in.readObject();
         in.close();
 
-        int samples = 0;
+        long samples = 0;
 
         LongIterator sampleIter = freqDist.values().iterator();
 

dkpro-core-api-io-asl/src/main/java/org/dkpro/core/api/io/JCasFileWriter_ImplBase.java

@@ -27,6 +27,7 @@
 import java.net.URI;
 import java.net.URLDecoder;
 import java.net.URLEncoder;
+import java.nio.file.Paths;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
 
@@ -217,8 +218,13 @@ else if (targetLocation.startsWith(JAR_PREFIX)) {
             }
 
             // Begin new entry
-            ZipEntry entry = new ZipEntry(
-                    zipEntryPrefix + aRelativePath + aExtension + compression.getExtension());
+            String entryName = zipEntryPrefix + aRelativePath + aExtension
+                    + compression.getExtension();
+            if (Paths.get(entryName).normalize().startsWith("..")) {
+                throw new IOException(
+                        "ZIP entry name [" + entryName + "] would escape archive root");
+            }
+            ZipEntry entry = new ZipEntry(entryName);
             zipOutputStream.putNextEntry(entry);
 
             // We return an OutputStream for an individual entry. When this is closed by the

dkpro-core-api-parameter-asl/src/main/java/org/dkpro/core/api/parameter/MimeTypes.java

@@ -100,9 +100,6 @@ public final class MimeTypes
     public final static String APPLICATION_X_STANFORDNLP_NER = "application/x.org.dkpro.core.stanfordnlp.ner";
     public final static String APPLICATION_X_STANFORDNLP_TAGGER = "application/x.org.dkpro.core.stanfordnlp.tagger";
 
-    // LingPipe model types
-    public final static String APPLICATION_X_LINGPIPE_NER = "application/x.org.dkpro.core.lingpipe.ner";
-
     // ArkTweet model types
     public final static String APPLICATION_X_ARKTWEET_TAGGER = "application/x.org.dkpro.core.arktweet.tagger";
 

dkpro-core-api-parameter-asl/src/main/resources/META-INF/eu.openminted.share/mimeTypeMapping.map

@@ -5,7 +5,6 @@ application/vnd.xmi+xml=http://w3id.org/meta-share/omtd-share/Xmi
 #application/x.org.dkpro.ancora+xml
 application/x.org.dkpro.bnc+xml=http://w3id.org/meta-share/omtd-share/BncFormat
 application/x.org.dkpro.brat=http://w3id.org/meta-share/omtd-share/Brat
-#application/x.org.dkpro.core.lingpipe.ner
 #application/x.org.dkpro.core.opennlp.chunk
 #application/x.org.dkpro.core.opennlp.lemma
 #application/x.org.dkpro.core.opennlp.ner

dkpro-core-decompounding-asl/src/main/java/org/dkpro/core/decompounding/ranking/CompoundProbabilityRanker.java

@@ -76,9 +76,9 @@ public List<DecompoundedWord> rank(List<DecompoundedWord> aSplits)
     /**
      * Calculates the weight for a split
      */
-    private float calcRank(DecompoundedWord aSplit)
+    private double calcRank(DecompoundedWord aSplit)
     {
-        float result = 0;
+        double result = 0;
 
         for (Fragment elem : aSplit.getSplits()) {
             result += -1 * Math

dkpro-core-gpl/pom.xml

@@ -42,7 +42,6 @@
 
   <modules>
     <module>../dkpro-core-corenlp-gpl</module>
-    <module>../dkpro-core-lingpipe-gpl</module>
     <module>../dkpro-core-sfst-gpl</module>
     <module>../dkpro-core-io-tgrep-gpl</module>
   </modules>