OPENNLP-1753: Switch to pre-trained Model binaries v1.3

mawiesne · mawiesne · commit c865e77de4f9 · 2025-06-27T20:05:31.000+02:00
- adjusts version strings
- adjusts index.html template to latest v1.3 copy for DownloadParserTest
- adjusts examples in Dev manual
diff --git a/opennlp-api/src/main/java/opennlp/tools/monitoring/StopCriteria.java b/opennlp-api/src/main/java/opennlp/tools/monitoring/StopCriteria.java
@@ -26,7 +26,7 @@
  */
 public interface StopCriteria<T extends Number> extends Predicate<T> {
 
-  String FINISHED = "Training Finished after completing %s Iterations successfully.";
+  String FINISHED = "Training finished after completing %s iterations successfully.";
 
   /**
    * @return A detailed message captured upon hitting the {@link StopCriteria} during model training.
diff --git a/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/AbstractModelLoaderTest.java b/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/AbstractModelLoaderTest.java
@@ -38,7 +38,7 @@ public abstract class AbstractModelLoaderTest {
   private static final String BASE_URL_MODELS_V183 = "https://dlcdn.apache.org/opennlp/models/langdetect/1.8.3/";
   protected static final Path OPENNLP_DIR = Paths.get(System.getProperty("OPENNLP_DOWNLOAD_HOME",
           System.getProperty("user.home"))).resolve(".opennlp");
-  protected static final String VER = "1.2-2.5.0";
+  protected static final String VER = "1.3-2.5.4";
   protected static final String BIN = ".bin";
   protected static List<String> SUPPORTED_LANG_CODES = List.of(
           "en", "fr", "de", "it", "nl", "bg", "ca", "cs", "da", "el",
diff --git a/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java b/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java
@@ -56,7 +56,7 @@ public void setup() {
 
   @ParameterizedTest(name = "Verify \"{0}\" tokenizer model loading")
   @ValueSource(strings = {"en-ud-ewt", "fr-ud-gsd", "de-ud-gsd", "it-ud-vit", "nl-ud-alpino",
-      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdt", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
+      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdtc", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
       "eu-ud-bdt", "fi-ud-tdt", "hr-ud-set", "hy-ud-bsut", "is-ud-icepahc", "ka-ud-glc", "kk-ud-ktb",
       "ko-ud-kaist", "lv-ud-lvtb", "no-ud-bokmaal", "pl-ud-pdb", "pt-ud-gsd", "ro-ud-rrt", "ru-ud-gsd",
       "sr-ud-set", "sk-ud-snk", "sl-ud-ssj", "sv-ud-talbanken", "tr-ud-boun", "uk-ud-iu"})
diff --git a/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java b/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java
@@ -56,7 +56,7 @@ public void setup() {
 
   @ParameterizedTest(name = "Verify \"{0}\" POS model loading")
   @ValueSource(strings = {"en-ud-ewt", "fr-ud-gsd", "de-ud-gsd", "it-ud-vit", "nl-ud-alpino",
-      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdt", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
+      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdtc", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
       "eu-ud-bdt", "fi-ud-tdt", "hr-ud-set", "hy-ud-bsut", "is-ud-icepahc", "ka-ud-glc", "kk-ud-ktb",
       "ko-ud-kaist", "lv-ud-lvtb", "no-ud-bokmaal", "pl-ud-pdb", "pt-ud-gsd", "ro-ud-rrt", "ru-ud-gsd",
       "sr-ud-set", "sk-ud-snk", "sl-ud-ssj", "sv-ud-talbanken", "tr-ud-boun", "uk-ud-iu"})
diff --git a/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java b/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java
@@ -56,7 +56,7 @@ public void setup() {
 
   @ParameterizedTest(name = "Verify \"{0}\" sentence model loading")
   @ValueSource(strings = {"en-ud-ewt", "fr-ud-gsd", "de-ud-gsd", "it-ud-vit", "nl-ud-alpino",
-      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdt", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
+      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdtc", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
       "eu-ud-bdt", "fi-ud-tdt", "hr-ud-set", "hy-ud-bsut", "is-ud-icepahc", "ka-ud-glc", "kk-ud-ktb",
       "ko-ud-kaist", "lv-ud-lvtb", "no-ud-bokmaal", "pl-ud-pdb", "pt-ud-gsd", "ro-ud-rrt", "ru-ud-gsd",
       "sr-ud-set", "sk-ud-snk", "sl-ud-ssj", "sv-ud-talbanken", "tr-ud-boun", "uk-ud-iu"})
diff --git a/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java b/opennlp-core/opennlp-cli/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java
@@ -56,7 +56,7 @@ public void setup() {
 
   @ParameterizedTest(name = "Verify \"{0}\" tokenizer model loading")
   @ValueSource(strings = {"en-ud-ewt", "fr-ud-gsd", "de-ud-gsd", "it-ud-vit", "nl-ud-alpino",
-      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdt", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
+      "bg-ud-btb", "ca-ud-ancora", "cs-ud-pdtc", "da-ud-ddt", "el-ud-gdt", "es-ud-gsd", "et-ud-edt",
       "eu-ud-bdt", "fi-ud-tdt", "hr-ud-set", "hy-ud-bsut", "is-ud-icepahc", "ka-ud-glc", "kk-ud-ktb",
       "ko-ud-kaist", "lv-ud-lvtb", "no-ud-bokmaal", "pl-ud-pdb", "pt-ud-gsd", "ro-ud-rrt", "ru-ud-gsd",
       "sr-ud-set", "sk-ud-snk", "sl-ud-ssj", "sv-ud-talbanken", "tr-ud-boun", "uk-ud-iu"})
diff --git a/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java b/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java
@@ -49,7 +49,7 @@ public class TwentyNewsgroupSampleStreamFactoryTest extends
 
   private static final Path OPENNLP_DIR = Paths.get(System.getProperty("OPENNLP_DOWNLOAD_HOME",
           System.getProperty("user.home"))).resolve(".opennlp");
-  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin";
+  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin";
 
   // SUT
   private TwentyNewsgroupSampleStreamFactory factory;
diff --git a/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java b/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java
@@ -52,7 +52,7 @@ public class BratNameSampleStreamFactoryTest extends
 
   private static final Path OPENNLP_DIR = Paths.get(System.getProperty("OPENNLP_DOWNLOAD_HOME",
           System.getProperty("user.home"))).resolve(".opennlp");
-  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin";
+  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin";
 
   // SUT
   private BratNameSampleStreamFactory factory;
diff --git a/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java b/opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java
@@ -48,7 +48,7 @@ public class Muc6NameSampleStreamFactoryTest extends
 
   private static final Path OPENNLP_DIR = Paths.get(System.getProperty("OPENNLP_DOWNLOAD_HOME",
           System.getProperty("user.home"))).resolve(".opennlp");
-  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin";
+  private static final String TOKENIZER_MODEL_NAME = "opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin";
 
   // SUT
   private Muc6NameSampleStreamFactory factory;
diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/DownloadUtil.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/DownloadUtil.java
@@ -58,7 +58,7 @@ public class DownloadUtil {
   private static final String BASE_URL =
       System.getProperty("OPENNLP_DOWNLOAD_BASE_URL", "https://dlcdn.apache.org/opennlp/");
   private static final String MODEL_URI_PATH =
-      System.getProperty("OPENNLP_DOWNLOAD_MODEL_PATH", "models/ud-models-1.2/");
+      System.getProperty("OPENNLP_DOWNLOAD_MODEL_PATH", "models/ud-models-1.3/");
   private static final String OPENNLP_DOWNLOAD_HOME = "OPENNLP_DOWNLOAD_HOME";
 
   private static Map<String, Map<ModelType, String>> availableModels;
diff --git a/opennlp-docs/src/docbkx/lemmatizer.xml b/opennlp-docs/src/docbkx/lemmatizer.xml
@@ -41,7 +41,7 @@
 			<para>
 				<screen>
 		   <![CDATA[
-$ opennlp LemmatizerME opennlp-en-ud-ewt-lemmas-1.2-2.5.0.bin < sentences]]>
+$ opennlp LemmatizerME opennlp-en-ud-ewt-lemmas-1.3-2.5.4.bin < sentences]]>
 		  </screen>
 				The Lemmatizer now reads a pos tagged sentence(s) per line from
 				standard input. For example, you can copy this sentence to the
@@ -89,7 +89,7 @@ signed	VERB	sign
 				<programlisting language="java">
 		<![CDATA[
 LemmatizerModel model = null;
-try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-lemmas-1.2-2.5.0.bin"))) {
+try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-lemmas-1.3-2.5.4.bin"))) {
   model = new LemmatizerModel(modelIn);
 }
 ]]>
diff --git a/opennlp-docs/src/docbkx/postagger.xml b/opennlp-docs/src/docbkx/postagger.xml
@@ -41,7 +41,7 @@ under the License.
 		Download the English maxent pos model and start the POS Tagger Tool with this command:
 		<screen>
 			<![CDATA[
-$ opennlp POSTagger opennlp-en-ud-ewt-pos-1.2-2.5.0.bin]]>
+$ opennlp POSTagger opennlp-en-ud-ewt-pos-1.3-2.5.4.bin]]>
 		 </screen>
 		The POS Tagger now reads a tokenized sentence per line from stdin.
 		Copy these two sentences to the console:
@@ -69,7 +69,7 @@ Mr._PROPN Vinken_PROPN is_AUX chairman_NOUN of_ADP Elsevier_ADJ N.V._PROPN ,_PUN
 			In the sample below it is loaded from disk.
 			<programlisting language="java">
 				<![CDATA[
-try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-pos-1.2-2.5.0.bin"){
+try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-pos-1.3-2.5.4.bin"){
   POSModel model = new POSModel(modelIn);
 }]]>
 			</programlisting>
@@ -343,7 +343,7 @@ Arrays.stream(tags).forEach(k -> System.out.print(k + " "));]]>
 				    POS Tags using the custom model (en-custom-pos-maxent.bin): PROPN OTHER PRON ADJ NOUN PUNCT
 
 				Output with the default model
-				    POS Tags using the default model (opennlp-en-ud-ewt-pos-1.2-2.5.0.bin):	NOUN AUX PRON ADJ NOUN PUNCT
+				    POS Tags using the default model (opennlp-en-ud-ewt-pos-1.3-2.5.4.bin):	NOUN AUX PRON ADJ NOUN PUNCT
 			</literallayout>
 		</para>
 		</section>
diff --git a/opennlp-docs/src/docbkx/sentdetect.xml b/opennlp-docs/src/docbkx/sentdetect.xml
@@ -63,13 +63,13 @@ Rudolph Agnew, 55 years old and former chairman of Consolidated Gold Fields PLC,
 		Download the english sentence detector model and start the Sentence Detector Tool with this command:
         <screen>
         <![CDATA[
-$ opennlp SentenceDetector opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin]]>
+$ opennlp SentenceDetector opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin]]>
 		</screen>
 		Just copy the sample text from above to the console. The Sentence Detector will read it and echo one sentence per line to the console.
 		Usually the input is read from a file and the output is redirected to another file. This can be achieved with the following command.
 		<screen>
 				<![CDATA[
-$ opennlp SentenceDetector opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin < input.txt > output.txt]]>
+$ opennlp SentenceDetector opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin < input.txt > output.txt]]>
 		</screen>
 		For the english sentence model from the website the input text should not be tokenized.
 		</para>
@@ -81,7 +81,7 @@ $ opennlp SentenceDetector opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin < input.txt
 		To instantiate the Sentence Detector the sentence model must be loaded first.
 		<programlisting language="java">
 				<![CDATA[
-try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin")) {
+try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin")) {
   SentenceModel model = new SentenceModel(modelIn);
 }]]>
 		</programlisting>
diff --git a/opennlp-docs/src/docbkx/tokenizer.xml b/opennlp-docs/src/docbkx/tokenizer.xml
@@ -97,7 +97,7 @@ $ opennlp SimpleTokenizer]]>
 			our website.
 			<screen>
 			<![CDATA[
-$ opennlp TokenizerME opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin]]>
+$ opennlp TokenizerME opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin]]>
 		    </screen>
 			To test the tokenizer copy the sample from above to the console. The
 			whitespace separated tokens will be written back to the
@@ -107,7 +107,7 @@ $ opennlp TokenizerME opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin]]>
 			Usually the input is read from a file and written to a file.
 			<screen>
 			<![CDATA[
-$ opennlp TokenizerME opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin < article.txt > article-tokenized.txt]]>
+$ opennlp TokenizerME opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin < article.txt > article-tokenized.txt]]>
 		    </screen>
 			It can be done in the same way for the Simple Tokenizer.
 		</para>
@@ -151,7 +151,7 @@ London share prices were bolstered largely by continued gains on Wall Street and
 			can be loaded.
 			<programlisting language="java">
 			<![CDATA[
-try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin")) {
+try (InputStream modelIn = new FileInputStream("opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin")) {
   TokenizerModel model = new TokenizerModel(modelIn);
 }]]>
 		 </programlisting>
diff --git a/opennlp-extensions/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java b/opennlp-extensions/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java
@@ -82,7 +82,7 @@ void testSerializeInvalid2() {
   }
 
   @ParameterizedTest
-  @ValueSource(strings = {"opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin"})
+  @ValueSource(strings = {"opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin"})
   void testLoadBytes(String file) {
     try {
       byte[] data = OpennlpUtil.loadBytes(OPENNLP_DIR.resolve(file).toFile());
diff --git a/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/OpenNlpTextAnalyzer.xml b/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/OpenNlpTextAnalyzer.xml
@@ -118,15 +118,15 @@
 			<externalResource>
 				<name>SentenceModel</name>
 				<fileResourceSpecifier>
-					<fileUrl>file:opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin</fileUrl>
+					<fileUrl>file:opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin</fileUrl>
 				</fileResourceSpecifier>
 				<implementationName>opennlp.uima.sentdetect.SentenceModelResourceImpl</implementationName>
 			</externalResource>
 
 			<externalResource>
 				<name>TokenModel</name>
 				<fileResourceSpecifier>
-					<fileUrl>file:opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin</fileUrl>
+					<fileUrl>file:opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin</fileUrl>
 				</fileResourceSpecifier>
 				<implementationName>opennlp.uima.tokenize.TokenizerModelResourceImpl</implementationName>
 			</externalResource>
@@ -190,7 +190,7 @@
 			<externalResource>
 				<name>PosModel</name>
 				<fileResourceSpecifier>
-					<fileUrl>file:opennlp-en-ud-ewt-pos-1.2-2.5.0.bin</fileUrl>
+					<fileUrl>file:opennlp-en-ud-ewt-pos-1.3-2.5.4.bin</fileUrl>
 				</fileResourceSpecifier>
 				<implementationName>opennlp.uima.postag.POSModelResourceImpl</implementationName>
 			</externalResource>
diff --git a/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/PosTagger.xml b/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/PosTagger.xml
@@ -117,7 +117,7 @@
       <externalResource>
         <name>PosModel</name>
         <fileResourceSpecifier>
-          <fileUrl>file:opennlp-en-ud-ewt-pos-1.2-2.5.0.bin</fileUrl>
+          <fileUrl>file:opennlp-en-ud-ewt-pos-1.3-2.5.4.bin</fileUrl>
         </fileResourceSpecifier>
         <implementationName>opennlp.uima.postag.POSModelResourceImpl</implementationName>
       </externalResource>
diff --git a/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/SentenceDetector.xml b/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/SentenceDetector.xml
@@ -93,7 +93,7 @@
       <externalResource>
         <name>SentenceModel</name>
         <fileResourceSpecifier>
-          <fileUrl>file:opennlp-en-ud-ewt-sentence-1.2-2.5.0.bin</fileUrl>
+          <fileUrl>file:opennlp-en-ud-ewt-sentence-1.3-2.5.4.bin</fileUrl>
         </fileResourceSpecifier>
         <implementationName>opennlp.uima.sentdetect.SentenceModelResourceImpl</implementationName>
       </externalResource>
diff --git a/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/Tokenizer.xml b/opennlp-extensions/opennlp-uima/src/test/resources/test-descriptors/Tokenizer.xml
@@ -110,7 +110,7 @@
       <externalResource>
 				<name>TokenModel</name>
 				<fileResourceSpecifier>
-					<fileUrl>file:opennlp-en-ud-ewt-tokens-1.2-2.5.0.bin</fileUrl>
+					<fileUrl>file:opennlp-en-ud-ewt-tokens-1.3-2.5.4.bin</fileUrl>
 				</fileResourceSpecifier>
 				<implementationName>opennlp.uima.tokenize.TokenizerModelResourceImpl</implementationName>
 			</externalResource>
diff --git a/opennlp-tools/src/test/java/opennlp/tools/monitoring/DefaultTrainingProgressMonitorTest.java b/opennlp-tools/src/test/java/opennlp/tools/monitoring/DefaultTrainingProgressMonitorTest.java
@@ -79,7 +79,7 @@ void testFinishedTrainingWithoutStopCriteria() {
 
       //Assert that the logs captured the training completion message when all iterations are exhausted.
       List<String> actual = logCaptor.getInfoLogs();
-      List<String> expected = List.of("Training Finished after completing 150 Iterations successfully.");
+      List<String> expected = List.of("Training finished after completing 150 iterations successfully.");
       assertArrayEquals(expected.toArray(), actual.toArray());
     }
   }
diff --git a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java
@@ -84,7 +84,7 @@ private URL fromClasspath(String file) {
   private static final String MODEL_SENT = "sentence-";
   private static final String MODEL_TOK = "tokens-";
   private static final String MODEL_POS = "pos-";
-  private static final String VER = "1.2-2.5.0";
+  private static final String VER = "1.3-2.5.4";
   private static final String BIN = ".bin";
 
   // Note: This needs to be public as JUnit 5 requires it like this.
@@ -116,9 +116,9 @@ public static Stream<Arguments> expectedModels() {
         ModelType.TOKENIZER, OPENNLP + "bg-ud-btb-" + MODEL_TOK + VER + BIN,
         ModelType.POS, OPENNLP + "bg-ud-btb-" + MODEL_POS + VER + BIN)),
       Arguments.of("cs", Map.of(
-        ModelType.SENTENCE_DETECTOR, OPENNLP + "cs-ud-pdt-" + MODEL_SENT + VER + BIN,
-        ModelType.TOKENIZER, OPENNLP + "cs-ud-pdt-" + MODEL_TOK + VER + BIN,
-        ModelType.POS, OPENNLP + "cs-ud-pdt-" + MODEL_POS + VER + BIN)),
+        ModelType.SENTENCE_DETECTOR, OPENNLP + "cs-ud-pdtc-" + MODEL_SENT + VER + BIN,
+        ModelType.TOKENIZER, OPENNLP + "cs-ud-pdtc-" + MODEL_TOK + VER + BIN,
+        ModelType.POS, OPENNLP + "cs-ud-pdtc-" + MODEL_POS + VER + BIN)),
       Arguments.of("da", Map.of(
         ModelType.SENTENCE_DETECTOR, OPENNLP + "da-ud-ddt-" + MODEL_SENT + VER + BIN,
         ModelType.TOKENIZER, OPENNLP + "da-ud-ddt-" + MODEL_TOK + VER + BIN,
diff --git a/opennlp-tools/src/test/resources/opennlp/tools/util/index.html b/opennlp-tools/src/test/resources/opennlp/tools/util/index.html
diff --git a/pom.xml b/pom.xml
