This is an automated email from the ASF dual-hosted git repository. mawiesne pushed a commit to branch OPENNLP-1729-Provide-easier-loading-of-Models-for-given-model-lang-and-type in repository https://gitbox.apache.org/repos/asf/opennlp.git
commit cdfe0aca78e6d4f8644994d4bcde7cc104bbdbf3 Author: Martin Wiesner <[email protected]> AuthorDate: Mon Apr 28 22:29:16 2025 +0200 OPENNLP-1729: Provide easier loading of Models for given model lang and type - extracts ModelType from DownloadUtil - adds new methods to ClassPathModelLoader to obtain actual model instances easily - adds ClassPathModelProvider interface - adds DefaultClassPathModelProvider which combines existing classes to achieve easier access to model objects via classpath loading - adds JUnit tests for the new classes - adds and improves JavaDoc --- opennlp-tools-models/pom.xml | 12 ++ .../tools/models/ClassPathLoaderException.java | 38 ++++++ .../opennlp/tools/models/ClassPathModelLoader.java | 84 +++++++++++- .../tools/models/ClassPathModelProvider.java | 77 +++++++++++ .../models/DefaultClassPathModelProvider.java | 90 +++++++++++++ .../models/classgraph/ClassgraphModelFinder.java | 1 + .../tools/models/AbstractClassPathFinderTest.java | 3 +- .../tools/models/ClassPathModelLoaderTest.java | 77 +++++++++++ .../models/DefaultClassPathModelProviderTest.java | 96 +++++++++++++ .../main/java/opennlp/tools/chunker/ChunkerME.java | 3 +- .../main/java/opennlp/tools/models/ModelType.java | 42 ++++++ .../java/opennlp/tools/postag/POSTaggerME.java | 3 +- .../tools/postag/ThreadSafePOSTaggerME.java | 3 +- .../tools/sentdetect/SentenceDetectorME.java | 3 +- .../sentdetect/ThreadSafeSentenceDetectorME.java | 3 +- .../tools/tokenize/ThreadSafeTokenizerME.java | 3 +- .../java/opennlp/tools/tokenize/TokenizerME.java | 3 +- .../main/java/opennlp/tools/util/DownloadUtil.java | 28 +--- .../lemmatizer/LemmatizerModelLoaderIT.java | 3 +- .../tools/cmdline/postag/POSModelLoaderIT.java | 3 +- .../cmdline/sentdetect/SentenceModelLoaderIT.java | 3 +- .../cmdline/tokenizer/TokenizerModelLoaderIT.java | 3 +- .../TwentyNewsgroupSampleStreamFactoryTest.java | 3 +- .../brat/BratNameSampleStreamFactoryTest.java | 3 +- .../muc/Muc6NameSampleStreamFactoryTest.java | 3 +- .../opennlp/tools/util/DownloadParserTest.java | 150 +++++++++++---------- .../tools/util/DownloadUtilDownloadTwiceTest.java | 3 +- .../java/opennlp/tools/util/DownloadUtilTest.java | 11 +- .../src/test/java/opennlp/uima/AbstractIT.java | 7 +- .../uima/util/AnnotationComparatorTest.java | 3 +- .../java/opennlp/uima/util/AnnotatorUtilTest.java | 3 +- .../java/opennlp/uima/util/OpennlpUtilTest.java | 3 +- .../test/java/opennlp/uima/util/UimaUtilTest.java | 3 +- 33 files changed, 644 insertions(+), 129 deletions(-) diff --git a/opennlp-tools-models/pom.xml b/opennlp-tools-models/pom.xml index dd403d83..3d1f9188 100644 --- a/opennlp-tools-models/pom.xml +++ b/opennlp-tools-models/pom.xml @@ -76,6 +76,18 @@ <version>${opennlp.models.version}</version> <scope>test</scope> </dependency> + <dependency> + <groupId>org.apache.opennlp</groupId> + <artifactId>opennlp-models-tokenizer-en</artifactId> + <version>${opennlp.models.version}</version> + <scope>test</scope> + </dependency> + <dependency> + <groupId>org.apache.opennlp</groupId> + <artifactId>opennlp-models-pos-en</artifactId> + <version>${opennlp.models.version}</version> + <scope>test</scope> + </dependency> <dependency> <groupId>org.apache.opennlp</groupId> <artifactId>opennlp-models-langdetect</artifactId> diff --git a/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathLoaderException.java b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathLoaderException.java new file mode 100644 index 00000000..eec5cd09 --- /dev/null +++ b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathLoaderException.java @@ -0,0 +1,38 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +import java.io.Serial; + +public class ClassPathLoaderException extends RuntimeException { + + @Serial + private static final long serialVersionUID = 8858291914366114032L; + + public ClassPathLoaderException(String message) { + super(message); + } + + public ClassPathLoaderException(Throwable cause) { + super(cause); + } + + public ClassPathLoaderException(String message, Throwable cause) { + super(message, cause); + } +} diff --git a/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelLoader.java b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelLoader.java index 2e51b664..e00c280a 100644 --- a/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelLoader.java +++ b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelLoader.java @@ -16,14 +16,21 @@ */ package opennlp.tools.models; +import java.io.BufferedInputStream; +import java.io.ByteArrayInputStream; import java.io.IOException; import java.io.InputStream; +import java.lang.reflect.InvocationTargetException; import java.util.Objects; import java.util.Properties; +import java.util.Set; + +import opennlp.tools.util.model.BaseModel; /** * Responsible for loading OpenNLP models from the classpath via {@link ClassPathModelEntry entries}. - * If models could be loaded successfully, those are provided as {@link ClassPathModel model references}. + * If models could be loaded successfully, those are provided as {@link ClassPathModel model references} + * or as instances of the specified {@link ModelType}. * * @see ClassPathModel * @see ClassPathModelEntry @@ -37,7 +44,7 @@ public class ClassPathModelLoader { * Moreover, it is validated that the {@link ClassPathModelEntry#model() binary data} * and {@link ClassPathModelEntry#properties() meta-data} are not {@code null}. * @return A {@link ClassPathModel} containing the model resources. - * @throws IOException thrown if something went wrong during reading resources from the classpath. + * @throws IOException Thrown if something went wrong during reading resources from the classpath. */ public ClassPathModel load(ClassPathModelEntry entry) throws IOException { Objects.requireNonNull(entry, "entry must not be null"); @@ -47,7 +54,7 @@ public class ClassPathModelLoader { final Properties properties = new Properties(); if (entry.properties().isPresent()) { - try (InputStream inputStream = entry.properties().get().toURL().openStream()) { + try (InputStream inputStream = new BufferedInputStream(entry.properties().get().toURL().openStream())) { properties.load(inputStream); } } @@ -59,4 +66,75 @@ public class ClassPathModelLoader { return new ClassPathModel(properties, model); } + + /** + * Restores a {@link T model} among a set {@link ClassPathModelEntry classpath entries} + * according to the specified parameters {@code lang} and {@code type}. + * + * @param classPathEntries A non-empty set of {@link ClassPathModelEntry candidates} to find a matching + * model in. Must not be {@code null}. If it is empty, the result will + * be {@code null}. + * @param lang The language code of the requested model. If {@code null}, the result will + * be {@code null} as well. + * @param type The {@link ModelType} to select the model variant. + * @param modelType The class of model type parameter {@link T} to create an instance of. + * + * @return An model instance of type {@link T}, or {@code null} if no match was found + * for the specified parameters. + * + * @throws IllegalArgumentException Thrown if parameters were invalid. + * @throws ClassPathLoaderException Thrown if {@link T} could not be instantiated correctly. + * @throws IOException Thrown if something went wrong during reading resources from the classpath. + */ + <T extends BaseModel> T load(Set<ClassPathModelEntry> classPathEntries, String lang, + ModelType type, Class<T> modelType) throws IOException { + return load(classPathEntries, lang, type.getName(), modelType); + } + + /** + * Restores a {@link T model} among a set {@link ClassPathModelEntry classpath entries} + * according to the specified parameters {@code lang} and {@code type}. + * + * @param classPathEntries A non-empty set of {@link ClassPathModelEntry candidates} to find a matching + * model in. Must not be {@code null}. If it is empty, the result will + * be {@code null}. + * @param lang The language code of the requested model. If {@code null}, the result will + * be {@code null} as well. + * @param type The type string to narrow down the model variant. Note: Custom naming patterns + * can be applied here, as the {@code type} fragment will be used for a 'contains' + * check internally. + * @param modelType The class of model type parameter {@link T} to create an instance of. + * + * @return An model instance of type {@link T}, or {@code null} if no match was found + * for the specified parameters. + * + * @throws IllegalArgumentException Thrown if parameters were invalid. + * @throws ClassPathLoaderException Thrown if {@link T} could not be instantiated correctly. + * @throws IOException Thrown if something went wrong during reading resources from the classpath. + */ + <T extends BaseModel> T load(Set<ClassPathModelEntry> classPathEntries, String lang, + String type, Class<T> modelType) throws IOException { + if (classPathEntries == null) { + throw new IllegalArgumentException("The provided ClassPath entries must not be null!"); + } + T result = null; + if (classPathEntries.isEmpty()) { + return result; + } + try { + for (ClassPathModelEntry entry : classPathEntries) { + final ClassPathModel cpm = load(entry); + if (cpm != null && cpm.getModelLanguage().equals(lang) && cpm.getModelName().contains(type)) { + try (InputStream is = new BufferedInputStream(new ByteArrayInputStream(cpm.model()))) { + result = modelType.getConstructor(InputStream.class).newInstance(is); + break; // found a match + } + } + } + } catch (InstantiationException | IllegalAccessException | + InvocationTargetException | NoSuchMethodException e) { + throw new ClassPathLoaderException(e); + } + return result; + } } diff --git a/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelProvider.java b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelProvider.java new file mode 100644 index 00000000..9640299a --- /dev/null +++ b/opennlp-tools-models/src/main/java/opennlp/tools/models/ClassPathModelProvider.java @@ -0,0 +1,77 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +import java.io.IOException; + +import opennlp.tools.util.model.BaseModel; + +/** + * A provider for obtaining pre-trained OpenNLP {@link BaseModel models} from + * an application's classpath. + * <p> + * Providing models available in the classpath requires a {@link ClassPathModelFinder finder} + * and a {@link ClassPathModelLoader} at runtime. Depending on the environment, + * a custom {@code finder} can be used. + * + * @see BaseModel + * @see ClassPathModelFinder + * @see ClassPathModelLoader + */ +public interface ClassPathModelProvider { + + /** + * Restores a {@link T model} among all classpath models at runtime + * according to the specified parameters {@code lang} and {@code type}. + * + * @param lang The ISO language code of the requested model. If {@code null}, the result will + * be {@code null} as well. + * @param type The type string to narrow down the model variant. Note: Custom naming patterns + * can be applied here, as the {@code type} fragment will be used for a 'contains' + * check internally. + * @param modelType The class of model type parameter {@link T} to create an instance of. + * + * @return An model instance of type {@link T}, or {@code null} if no match was found + * for the specified parameters. + * @throws IllegalArgumentException Thrown if parameters were invalid. + * @throws IOException Thrown if something went wrong during reading resources from the classpath. + */ + <T extends BaseModel> T load(String lang, ModelType type, Class<T> modelType) + throws IOException; + + /** + * Restores a {@link T model} among all classpath models at runtime + * according to the specified parameters {@code lang} and {@code type}. + * + * @param lang The ISO language code of the requested model. If {@code null}, the result will + * be {@code null} as well. + * @param type The type string to narrow down the model variant. Note: Custom naming patterns + * can be applied here, as the {@code type} fragment will be used for a 'contains' + * check internally. + * @param modelType The class of model type parameter {@link T} to create an instance of. + * @param reloadCache {@code true}, if the internal cache of the {@link ClassPathModelFinder} + * should explicitly be reloaded, {@code false} otherwise. + * + * @return An model instance of type {@link T}, or {@code null} if no match was found + * for the specified parameters. + * @throws IllegalArgumentException Thrown if parameters were invalid. + * @throws IOException Thrown if something went wrong during reading resources from the classpath. + */ + <T extends BaseModel> T load(String lang, ModelType type, Class<T> modelType, + boolean reloadCache) throws IOException; +} diff --git a/opennlp-tools-models/src/main/java/opennlp/tools/models/DefaultClassPathModelProvider.java b/opennlp-tools-models/src/main/java/opennlp/tools/models/DefaultClassPathModelProvider.java new file mode 100644 index 00000000..ee923e6c --- /dev/null +++ b/opennlp-tools-models/src/main/java/opennlp/tools/models/DefaultClassPathModelProvider.java @@ -0,0 +1,90 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +import java.io.IOException; + +import opennlp.tools.models.simple.SimpleClassPathModelFinder; +import opennlp.tools.util.model.BaseModel; + +/** + * A default implementation of {@link ClassPathModelProvider} which by default relies on + * {@link SimpleClassPathModelFinder} to scan for models in the current classpath. + * + * @see ClassPathModelFinder + * @see ClassPathModelLoader + */ +public class DefaultClassPathModelProvider implements ClassPathModelProvider { + + private final ClassPathModelFinder finder; + private final ClassPathModelLoader loader; + + /** + * Instantiates a {@link DefaultClassPathModelProvider} with a {@link SimpleClassPathModelFinder} + * and uses a default {@link ClassPathModelLoader}. + * By default, it scans for the {@link ClassPathModelFinder#OPENNLP_MODEL_JAR_PREFIX} pattern for + * available model jars. + * + * @implNote If you require a different model jar prefix pattern for your environment and or + * model file naming strategy, please use + * {@link #DefaultClassPathModelProvider(ClassPathModelFinder, ClassPathModelLoader) + * constructor} with two arguments. + */ + public DefaultClassPathModelProvider() { + this(new SimpleClassPathModelFinder(), new ClassPathModelLoader()); + } + + /** + * Instantiates a {@link DefaultClassPathModelProvider} with the specified {@code modelJarPattern}, + * a {@link ClassPathModelFinder model finder} and a {@link ClassPathModelLoader model loader} instance. + * + * @param finder The {@link ClassPathModelFinder} instance to use for this provider. + * It must not be {@code null}. + * @param loader The {@link ClassPathModelLoader} instance to use for this provider. + * It must not be {@code null}. + * @throws IllegalArgumentException Thrown if one of the specified parameters were invalid. + */ + public DefaultClassPathModelProvider(ClassPathModelFinder finder, ClassPathModelLoader loader) { + if (finder == null) { + throw new IllegalArgumentException("ClassPathModelFinder cannot be null."); + } + if (loader == null) { + throw new IllegalArgumentException("ClassPathModelLoader cannot be null."); + } + this.finder = finder; + this.loader = loader; + } + + /** + * {@inheritDoc} + */ + @Override + public <T extends BaseModel> T load(String lang, ModelType type, Class<T> modelType) + throws IOException { + return load(lang, type, modelType, false); + } + + /** + * {@inheritDoc} + */ + @Override + public <T extends BaseModel> T load(String lang, ModelType type, Class<T> modelType, + boolean reloadCache) throws IOException { + return loader.load(finder.findModels(reloadCache), lang, type, modelType); + } +} diff --git a/opennlp-tools-models/src/main/java/opennlp/tools/models/classgraph/ClassgraphModelFinder.java b/opennlp-tools-models/src/main/java/opennlp/tools/models/classgraph/ClassgraphModelFinder.java index c440945c..b413f6ee 100644 --- a/opennlp-tools-models/src/main/java/opennlp/tools/models/classgraph/ClassgraphModelFinder.java +++ b/opennlp-tools-models/src/main/java/opennlp/tools/models/classgraph/ClassgraphModelFinder.java @@ -14,6 +14,7 @@ * See the License for the specific language governing permissions and * limitations under the License. */ + package opennlp.tools.models.classgraph; import java.net.URI; diff --git a/opennlp-tools-models/src/test/java/opennlp/tools/models/AbstractClassPathFinderTest.java b/opennlp-tools-models/src/test/java/opennlp/tools/models/AbstractClassPathFinderTest.java index e03f08ce..a9da5e8e 100644 --- a/opennlp-tools-models/src/test/java/opennlp/tools/models/AbstractClassPathFinderTest.java +++ b/opennlp-tools-models/src/test/java/opennlp/tools/models/AbstractClassPathFinderTest.java @@ -26,14 +26,13 @@ import static org.junit.jupiter.api.Assertions.assertNotNull; public abstract class AbstractClassPathFinderTest extends AbstractClassPathModelTest { - @Test public void testFindOpenNLPModels() { final ClassPathModelFinder finder = getModelFinder(); final Set<ClassPathModelEntry> models = finder.findModels(false); assertNotNull(models); - assertEquals(2, models.size()); + assertEquals(4, models.size()); for (ClassPathModelEntry entry : models) { assertNotNull(entry.model()); diff --git a/opennlp-tools-models/src/test/java/opennlp/tools/models/ClassPathModelLoaderTest.java b/opennlp-tools-models/src/test/java/opennlp/tools/models/ClassPathModelLoaderTest.java new file mode 100644 index 00000000..cc979efd --- /dev/null +++ b/opennlp-tools-models/src/test/java/opennlp/tools/models/ClassPathModelLoaderTest.java @@ -0,0 +1,77 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +import java.io.IOException; +import java.util.Collections; + +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; + +import opennlp.tools.models.simple.SimpleClassPathModelFinder; +import opennlp.tools.postag.POSModel; +import opennlp.tools.tokenize.TokenizerModel; + +import static org.junit.jupiter.api.Assertions.assertNull; +import static org.junit.jupiter.api.Assertions.assertThrows; + +public class ClassPathModelLoaderTest { + + // SUT + private ClassPathModelLoader loader; + + @BeforeEach + void setUp() { + loader = new ClassPathModelLoader(); + } + + @Test + void testLoadModelWithEmptyClassPathEntriesShouldReturnNull() throws IOException { + assertNull(loader.load(Collections.emptySet(), "en", "pos", POSModel.class)); + } + + @Test + void testLoadModelWithUnsupportedLanguageCodeShouldReturnNull() throws IOException { + assertNull(loader.load(Collections.emptySet(), "xy", "pos", POSModel.class)); + } + + @Test + void testLoadModelWithIllegalModelTypeShouldReturnNull() throws IOException { + assertNull(loader.load(Collections.emptySet(), "en", "xyz", POSModel.class)); + } + + @Test + void testLoadModelWithInconsistentClassTypeShouldTrow() { + SimpleClassPathModelFinder finder = new SimpleClassPathModelFinder(); + // Check if a mismatch is correctly detected and thrown + assertThrows(ClassPathLoaderException.class, () -> + loader.load(finder.findModels(true), "en", "pos", TokenizerModel.class)); + } + + @Test + void testLoadModelWithIllegalArguments1() { + assertThrows(IllegalArgumentException.class, () + -> loader.load(null, "en", "pos", POSModel.class)); + } + + @Test + void testLoadModelWithIllegalArguments2() { + assertThrows(IllegalArgumentException.class, () + -> loader.load(null, "en", ModelType.POS_GENERIC, POSModel.class)); + } +} diff --git a/opennlp-tools-models/src/test/java/opennlp/tools/models/DefaultClassPathModelProviderTest.java b/opennlp-tools-models/src/test/java/opennlp/tools/models/DefaultClassPathModelProviderTest.java new file mode 100644 index 00000000..f8a027ca --- /dev/null +++ b/opennlp-tools-models/src/test/java/opennlp/tools/models/DefaultClassPathModelProviderTest.java @@ -0,0 +1,96 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +import java.io.IOException; + +import org.junit.jupiter.api.BeforeAll; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; + +import opennlp.tools.models.simple.SimpleClassPathModelFinder; +import opennlp.tools.postag.POSModel; +import opennlp.tools.sentdetect.SentenceModel; +import opennlp.tools.tokenize.TokenizerModel; + +import static org.junit.jupiter.api.Assertions.assertNotNull; +import static org.junit.jupiter.api.Assertions.assertThrows; +import static org.junit.jupiter.api.Assertions.assertTrue; +import static org.junit.jupiter.api.Assertions.fail; + +public class DefaultClassPathModelProviderTest { + + private static SimpleClassPathModelFinder finder; + private static ClassPathModelLoader loader; + + // SUT + private DefaultClassPathModelProvider provider; + + @BeforeAll + public static void initEnv() { + finder = new SimpleClassPathModelFinder(); + loader = new ClassPathModelLoader(); + } + + @BeforeEach + void setup() { + provider = new DefaultClassPathModelProvider(finder, loader); + } + + @Test + void testLoadSentenceModel() throws IOException { + SentenceModel m = provider.load("en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); + assertNotNull(m); + assertTrue(m.isLoadedFromSerialized()); + } + + @Test + void testLoadTokenizerModel() throws IOException { + TokenizerModel m = provider.load("en", ModelType.TOKENIZER, TokenizerModel.class); + assertNotNull(m); + assertTrue(m.isLoadedFromSerialized()); + } + + @Test + void testLoadPOSModel() throws IOException { + POSModel m = provider.load("en", ModelType.POS_GENERIC, POSModel.class); + assertNotNull(m); + assertTrue(m.isLoadedFromSerialized()); + } + + @Test + void testCreateInstance() { + try { + new DefaultClassPathModelProvider(); + } catch (RuntimeException e) { + fail(e.getLocalizedMessage(), e); + } + } + + @Test + void testCreateInstanceWithIllegalParameters1() { + assertThrows(IllegalArgumentException.class, () -> + new DefaultClassPathModelProvider(finder, null)); + } + + @Test + void testCreateInstanceWithIllegalParameters2() { + assertThrows(IllegalArgumentException.class, () -> + new DefaultClassPathModelProvider(null, loader)); + } +} diff --git a/opennlp-tools/src/main/java/opennlp/tools/chunker/ChunkerME.java b/opennlp-tools/src/main/java/opennlp/tools/chunker/ChunkerME.java index e036742e..d0daf86b 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/chunker/ChunkerME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/chunker/ChunkerME.java @@ -30,6 +30,7 @@ import opennlp.tools.ml.TrainerFactory.TrainerType; import opennlp.tools.ml.model.Event; import opennlp.tools.ml.model.MaxentModel; import opennlp.tools.ml.model.SequenceClassificationModel; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.ObjectStream; import opennlp.tools.util.Sequence; @@ -63,7 +64,7 @@ public class ChunkerME implements Chunker { * @throws IOException Thrown if the model cannot be downloaded or saved. */ public ChunkerME(String language) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.CHUNKER, ChunkerModel.class)); + this(DownloadUtil.downloadModel(language, ModelType.CHUNKER, ChunkerModel.class)); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/models/ModelType.java b/opennlp-tools/src/main/java/opennlp/tools/models/ModelType.java new file mode 100644 index 00000000..6e863157 --- /dev/null +++ b/opennlp-tools/src/main/java/opennlp/tools/models/ModelType.java @@ -0,0 +1,42 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package opennlp.tools.models; + +/** + * A model type to pattern enumeration. + */ +public enum ModelType { + LEMMATIZER("lemma"), + TOKENIZER("token"), + SENTENCE_DETECTOR("sent"), + POS("pos-perceptron"), + POS_GENERIC("pos"), + NAME_FINDER("ner"), + CHUNKER("chunker"), + PARSER("parser-chunking"); + + private final String name; + + ModelType(String name) { + this.name = name; + } + + public String getName() { + return name; + } +} diff --git a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java index a85ceb55..c3c03a12 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java @@ -39,6 +39,7 @@ import opennlp.tools.ml.TrainerFactory.TrainerType; import opennlp.tools.ml.model.Event; import opennlp.tools.ml.model.MaxentModel; import opennlp.tools.ml.model.SequenceClassificationModel; +import opennlp.tools.models.ModelType; import opennlp.tools.ngram.NGramModel; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.ObjectStream; @@ -115,7 +116,7 @@ public class POSTaggerME implements POSTagger { * @throws IOException Thrown if the model could not be downloaded or saved. */ public POSTaggerME(String language, POSTagFormat format) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.POS, POSModel.class), format); + this(DownloadUtil.downloadModel(language, ModelType.POS, POSModel.class), format); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/postag/ThreadSafePOSTaggerME.java b/opennlp-tools/src/main/java/opennlp/tools/postag/ThreadSafePOSTaggerME.java index a1e29283..39ad425e 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/postag/ThreadSafePOSTaggerME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/postag/ThreadSafePOSTaggerME.java @@ -20,6 +20,7 @@ package opennlp.tools.postag; import java.io.IOException; import opennlp.tools.commons.ThreadSafe; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.Sequence; @@ -68,7 +69,7 @@ public class ThreadSafePOSTaggerME implements POSTagger, AutoCloseable { * @throws IOException Thrown if the model could not be downloaded or saved. */ public ThreadSafePOSTaggerME(String language, POSTagFormat format) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.POS, POSModel.class), format); + this(DownloadUtil.downloadModel(language, ModelType.POS, POSModel.class), format); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java index 1908b02f..5fbf9de6 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java @@ -31,6 +31,7 @@ import opennlp.tools.ml.EventTrainer; import opennlp.tools.ml.TrainerFactory; import opennlp.tools.ml.model.Event; import opennlp.tools.ml.model.MaxentModel; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.lang.Factory; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.ObjectStream; @@ -91,7 +92,7 @@ public class SentenceDetectorME implements SentenceDetector { */ public SentenceDetectorME(String language) throws IOException { this(DownloadUtil.downloadModel(language, - DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class)); + ModelType.SENTENCE_DETECTOR, SentenceModel.class)); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/ThreadSafeSentenceDetectorME.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/ThreadSafeSentenceDetectorME.java index 6cff0a0a..dae891c4 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/ThreadSafeSentenceDetectorME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/ThreadSafeSentenceDetectorME.java @@ -21,6 +21,7 @@ import java.io.IOException; import opennlp.tools.commons.ThreadSafe; import opennlp.tools.dictionary.Dictionary; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.Span; @@ -56,7 +57,7 @@ public class ThreadSafeSentenceDetectorME implements SentenceDetector, AutoClose * @throws IOException Thrown if the model could not be downloaded or saved. */ public ThreadSafeSentenceDetectorME(String language) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class)); + this(DownloadUtil.downloadModel(language, ModelType.SENTENCE_DETECTOR, SentenceModel.class)); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/tokenize/ThreadSafeTokenizerME.java b/opennlp-tools/src/main/java/opennlp/tools/tokenize/ThreadSafeTokenizerME.java index 2f105fb1..6915f5fb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/tokenize/ThreadSafeTokenizerME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/tokenize/ThreadSafeTokenizerME.java @@ -21,6 +21,7 @@ import java.io.IOException; import opennlp.tools.commons.ThreadSafe; import opennlp.tools.dictionary.Dictionary; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.Span; @@ -56,7 +57,7 @@ public class ThreadSafeTokenizerME implements Tokenizer, AutoCloseable { * @throws IOException Thrown if the model could not be downloaded or saved. */ public ThreadSafeTokenizerME(String language) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class)); + this(DownloadUtil.downloadModel(language, ModelType.TOKENIZER, TokenizerModel.class)); } /** diff --git a/opennlp-tools/src/main/java/opennlp/tools/tokenize/TokenizerME.java b/opennlp-tools/src/main/java/opennlp/tools/tokenize/TokenizerME.java index a617108f..3fcb6a0d 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/tokenize/TokenizerME.java +++ b/opennlp-tools/src/main/java/opennlp/tools/tokenize/TokenizerME.java @@ -30,6 +30,7 @@ import opennlp.tools.ml.EventTrainer; import opennlp.tools.ml.TrainerFactory; import opennlp.tools.ml.model.Event; import opennlp.tools.ml.model.MaxentModel; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.ObjectStream; import opennlp.tools.util.Span; @@ -120,7 +121,7 @@ public class TokenizerME extends AbstractTokenizer { * @throws IOException Thrown if the model cannot be downloaded or saved. */ public TokenizerME(String language) throws IOException { - this(DownloadUtil.downloadModel(language, DownloadUtil.ModelType.TOKENIZER, + this(DownloadUtil.downloadModel(language, ModelType.TOKENIZER, TokenizerModel.class)); } diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/DownloadUtil.java b/opennlp-tools/src/main/java/opennlp/tools/util/DownloadUtil.java index cd80792f..7a6244fb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/DownloadUtil.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/DownloadUtil.java @@ -45,6 +45,7 @@ import org.slf4j.Logger; import org.slf4j.LoggerFactory; import opennlp.tools.commons.Internal; +import opennlp.tools.models.ModelType; import opennlp.tools.util.model.BaseModel; /** @@ -54,25 +55,6 @@ public class DownloadUtil { private static final Logger logger = LoggerFactory.getLogger(DownloadUtil.class); - /** - * The type of model. - */ - public enum ModelType { - LEMMATIZER("lemma"), - TOKENIZER("token"), - SENTENCE_DETECTOR("sent"), - POS("pos-perceptron"), - NAME_FINDER("ner"), - CHUNKER("chunker"), - PARSER("parser-chunking"); - - private final String name; - - ModelType(String name) { - this.name = name; - } - } - private static final String BASE_URL = System.getProperty("OPENNLP_DOWNLOAD_BASE_URL", "https://dlcdn.apache.org/opennlp/";); private static final String MODEL_URI_PATH = @@ -86,7 +68,7 @@ public class DownloadUtil { * for a particular {@code language}. * * @param language The ISO language code of the requested model. - * @param modelType The {@link DownloadUtil.ModelType type} of model. + * @param modelType The {@link ModelType type} of model. * @return {@code true} if a model exists locally, {@code false} otherwise. * @throws IOException Thrown if IO errors occurred or the computed hash sum * of an associated, local model file was incorrect. @@ -117,10 +99,10 @@ public class DownloadUtil { } /** - * Triggers a download for the specified {@link DownloadUtil.ModelType}. + * Triggers a download for the specified {@link ModelType}. * * @param language The ISO language code of the requested model. - * @param modelType The {@link DownloadUtil.ModelType type} of model. + * @param modelType The {@link ModelType type} of model. * @param type The class of the resulting model. * @param <T> The generic type which is a subclass of {@link BaseModel}. * @return A model instance of type {@link T}. @@ -136,7 +118,7 @@ public class DownloadUtil { } } - throw new IOException("There is no model available: " + language + " " + modelType.name); + throw new IOException("There is no model available: " + language + " " + modelType.getName()); } /** diff --git a/opennlp-tools/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java b/opennlp-tools/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java index c34d186a..da19b5e9 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java +++ b/opennlp-tools/src/test/java/opennlp/tools/cmdline/lemmatizer/LemmatizerModelLoaderIT.java @@ -29,6 +29,7 @@ import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.AbstractModelLoaderTest; import opennlp.tools.EnabledWhenCDNAvailable; import opennlp.tools.lemmatizer.LemmatizerModel; +import opennlp.tools.models.ModelType; import opennlp.tools.util.DownloadUtil; @EnabledWhenCDNAvailable(hostname = "dlcdn.apache.org") @@ -41,7 +42,7 @@ public class LemmatizerModelLoaderIT extends AbstractModelLoaderTest { public static void initResources() { SUPPORTED_LANG_CODES.forEach(lang -> { try { - DownloadUtil.downloadModel(lang, DownloadUtil.ModelType.LEMMATIZER, LemmatizerModel.class); + DownloadUtil.downloadModel(lang, ModelType.LEMMATIZER, LemmatizerModel.class); } catch (IOException e) { throw new RuntimeException(e); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java b/opennlp-tools/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java index 06ae24d7..65793232 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java +++ b/opennlp-tools/src/test/java/opennlp/tools/cmdline/postag/POSModelLoaderIT.java @@ -28,6 +28,7 @@ import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.AbstractModelLoaderTest; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.postag.POSModel; import opennlp.tools.util.DownloadUtil; @@ -41,7 +42,7 @@ public class POSModelLoaderIT extends AbstractModelLoaderTest { public static void initResources() { SUPPORTED_LANG_CODES.forEach(lang -> { try { - DownloadUtil.downloadModel(lang, DownloadUtil.ModelType.POS, POSModel.class); + DownloadUtil.downloadModel(lang, ModelType.POS, POSModel.class); } catch (IOException e) { throw new RuntimeException(e); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java b/opennlp-tools/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java index 7440b6fe..a061bda6 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java +++ b/opennlp-tools/src/test/java/opennlp/tools/cmdline/sentdetect/SentenceModelLoaderIT.java @@ -28,6 +28,7 @@ import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.AbstractModelLoaderTest; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.util.DownloadUtil; @@ -41,7 +42,7 @@ public class SentenceModelLoaderIT extends AbstractModelLoaderTest { public static void initResources() { SUPPORTED_LANG_CODES.forEach(lang -> { try { - DownloadUtil.downloadModel(lang, DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + DownloadUtil.downloadModel(lang, ModelType.SENTENCE_DETECTOR, SentenceModel.class); } catch (IOException e) { throw new RuntimeException(e); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java b/opennlp-tools/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java index e482dd65..7c3067bf 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java +++ b/opennlp-tools/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerModelLoaderIT.java @@ -28,6 +28,7 @@ import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.AbstractModelLoaderTest; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.tokenize.TokenizerModel; import opennlp.tools.util.DownloadUtil; @@ -41,7 +42,7 @@ public class TokenizerModelLoaderIT extends AbstractModelLoaderTest { public static void initResources() { SUPPORTED_LANG_CODES.forEach(lang -> { try { - DownloadUtil.downloadModel(lang, DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class); + DownloadUtil.downloadModel(lang, ModelType.TOKENIZER, TokenizerModel.class); } catch (IOException e) { throw new RuntimeException(e); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java b/opennlp-tools/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java index d07f1ece..7b12a705 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/formats/TwentyNewsgroupSampleStreamFactoryTest.java @@ -33,6 +33,7 @@ import opennlp.tools.cmdline.ObjectStreamFactory; import opennlp.tools.cmdline.StreamFactoryRegistry; import opennlp.tools.cmdline.TerminateToolException; import opennlp.tools.doccat.DocumentSample; +import opennlp.tools.models.ModelType; import opennlp.tools.tokenize.TokenizerModel; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.ObjectStream; @@ -72,7 +73,7 @@ public class TwentyNewsgroupSampleStreamFactoryTest extends TwentyNewsgroupSampleStreamFactory.registerFactory(); try { // ensure, the model is available locally for later test purposes - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class); + DownloadUtil.downloadModel("en", ModelType.TOKENIZER, TokenizerModel.class); } catch (IOException e) { fail(e.getLocalizedMessage()); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java b/opennlp-tools/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java index edfbd844..8f9eb50a 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/formats/brat/BratNameSampleStreamFactoryTest.java @@ -34,6 +34,7 @@ import opennlp.tools.cmdline.StreamFactoryRegistry; import opennlp.tools.cmdline.TerminateToolException; import opennlp.tools.formats.AbstractSampleStreamFactory; import opennlp.tools.formats.AbstractSampleStreamFactoryTest; +import opennlp.tools.models.ModelType; import opennlp.tools.namefind.NameSample; import opennlp.tools.tokenize.TokenizerModel; import opennlp.tools.util.DownloadUtil; @@ -76,7 +77,7 @@ public class BratNameSampleStreamFactoryTest extends BratNameSampleStreamFactory.registerFactory(); try { // ensure, the model is available locally for later test purposes - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class); + DownloadUtil.downloadModel("en", ModelType.TOKENIZER, TokenizerModel.class); } catch (IOException e) { fail(e.getLocalizedMessage()); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java b/opennlp-tools/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java index ffe1c0a6..f2857302 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/formats/muc/Muc6NameSampleStreamFactoryTest.java @@ -31,6 +31,7 @@ import opennlp.tools.cmdline.StreamFactoryRegistry; import opennlp.tools.cmdline.TerminateToolException; import opennlp.tools.formats.AbstractSampleStreamFactory; import opennlp.tools.formats.AbstractSampleStreamFactoryTest; +import opennlp.tools.models.ModelType; import opennlp.tools.namefind.NameSample; import opennlp.tools.tokenize.TokenizerModel; import opennlp.tools.util.DownloadUtil; @@ -70,7 +71,7 @@ public class Muc6NameSampleStreamFactoryTest extends Muc6NameSampleStreamFactory.registerFactory(); try { // ensure, the model is available locally for later test purposes - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class); + DownloadUtil.downloadModel("en", ModelType.TOKENIZER, TokenizerModel.class); } catch (IOException e) { fail(e.getLocalizedMessage()); } diff --git a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java index 6276d272..dfff59c5 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadParserTest.java @@ -27,6 +27,8 @@ import org.junit.jupiter.params.ParameterizedTest; import org.junit.jupiter.params.provider.Arguments; import org.junit.jupiter.params.provider.MethodSource; +import opennlp.tools.models.ModelType; + import static org.junit.jupiter.api.Assertions.assertEquals; import static org.junit.jupiter.api.Assertions.assertNotNull; import static org.junit.jupiter.api.Assertions.assertThrows; @@ -35,22 +37,22 @@ public class DownloadParserTest { @ParameterizedTest(name = "Verify \"{0}\" available models") @MethodSource(value = "expectedModels") - void testAvailableModels(String language, Map<DownloadUtil.ModelType, String> expectedModels) { + void testAvailableModels(String language, Map<ModelType, String> expectedModels) { final URL baseUrl = fromClasspath("opennlp/tools/util/index.html"); assertNotNull(baseUrl); final DownloadUtil.DownloadParser downloadParser = new DownloadUtil.DownloadParser(baseUrl); - Map<String, Map<DownloadUtil.ModelType, String>> result = downloadParser.getAvailableModels(); + Map<String, Map<ModelType, String>> result = downloadParser.getAvailableModels(); assertNotNull(result); assertEquals(32, result.size()); - final Map<DownloadUtil.ModelType, String> availableModels = result.get(language); + final Map<ModelType, String> availableModels = result.get(language); assertNotNull(availableModels); - for (Map.Entry<DownloadUtil.ModelType, String> e : expectedModels.entrySet()) { + for (Map.Entry<ModelType, String> e : expectedModels.entrySet()) { final String url = availableModels.get(e.getKey()); final String expectedUrl = baseUrl + "/" + e.getValue(); @@ -69,7 +71,7 @@ public class DownloadParserTest { void testInvalidUrl() throws MalformedURLException { final DownloadUtil.DownloadParser downloadParser = new DownloadUtil.DownloadParser(new URL("file:/this/does/not/exist")); - Map<String, Map<DownloadUtil.ModelType, String>> result = downloadParser.getAvailableModels(); + Map<String, Map<ModelType, String>> result = downloadParser.getAvailableModels(); assertNotNull(result); assertEquals(0, result.size()); } @@ -90,97 +92,97 @@ public class DownloadParserTest { // Data as defined in "test/resources/opennlp/tools/util/index.html" return Stream.of( Arguments.of("en",Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "en-ud-ewt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "en-ud-ewt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "en-ud-ewt-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "en-ud-ewt-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "en-ud-ewt-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "en-ud-ewt-" + MODEL_POS + VER + BIN)), Arguments.of("fr", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "fr-ud-gsd-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "fr-ud-gsd-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "fr-ud-gsd-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "fr-ud-gsd-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "fr-ud-gsd-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "fr-ud-gsd-" + MODEL_POS + VER + BIN)), Arguments.of("de", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "de-ud-gsd-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "de-ud-gsd-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "de-ud-gsd-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "de-ud-gsd-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "de-ud-gsd-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "de-ud-gsd-" + MODEL_POS + VER + BIN)), Arguments.of("it", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "it-ud-vit-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "it-ud-vit-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "it-ud-vit-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "it-ud-vit-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "it-ud-vit-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "it-ud-vit-" + MODEL_POS + VER + BIN)), Arguments.of("nl", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "nl-ud-alpino-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "nl-ud-alpino-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "nl-ud-alpino-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "nl-ud-alpino-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "nl-ud-alpino-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "nl-ud-alpino-" + MODEL_POS + VER + BIN)), Arguments.of("bg", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "bg-ud-btb-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "bg-ud-btb-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "bg-ud-btb-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "bg-ud-btb-" + MODEL_SENT + VER + BIN, + 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( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "cs-ud-pdt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "cs-ud-pdt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "cs-ud-pdt-" + MODEL_POS + VER + BIN)), + 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)), Arguments.of("da", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "da-ud-ddt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "da-ud-ddt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "da-ud-ddt-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "da-ud-ddt-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "da-ud-ddt-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "da-ud-ddt-" + MODEL_POS + VER + BIN)), Arguments.of("es", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "es-ud-gsd-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "es-ud-gsd-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "es-ud-gsd-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "es-ud-gsd-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "es-ud-gsd-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "es-ud-gsd-" + MODEL_POS + VER + BIN)), Arguments.of("et", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "et-ud-edt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "et-ud-edt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "et-ud-edt-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "et-ud-edt-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "et-ud-edt-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "et-ud-edt-" + MODEL_POS + VER + BIN)), Arguments.of("fi", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "fi-ud-tdt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "fi-ud-tdt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "fi-ud-tdt-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "fi-ud-tdt-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "fi-ud-tdt-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "fi-ud-tdt-" + MODEL_POS + VER + BIN)), Arguments.of("hr", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "hr-ud-set-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "hr-ud-set-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "hr-ud-set-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "hr-ud-set-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "hr-ud-set-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "hr-ud-set-" + MODEL_POS + VER + BIN)), Arguments.of("lv", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "lv-ud-lvtb-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "lv-ud-lvtb-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "lv-ud-lvtb-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "lv-ud-lvtb-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "lv-ud-lvtb-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "lv-ud-lvtb-" + MODEL_POS + VER + BIN)), Arguments.of("no", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "no-ud-bokmaal-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "no-ud-bokmaal-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "no-ud-bokmaal-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "no-ud-bokmaal-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "no-ud-bokmaal-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "no-ud-bokmaal-" + MODEL_POS + VER + BIN)), Arguments.of("pl", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "pl-ud-pdb-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "pl-ud-pdb-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "pl-ud-pdb-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "pl-ud-pdb-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "pl-ud-pdb-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "pl-ud-pdb-" + MODEL_POS + VER + BIN)), Arguments.of("pt", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "pt-ud-gsd-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "pt-ud-gsd-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "pt-ud-gsd-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "pt-ud-gsd-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "pt-ud-gsd-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "pt-ud-gsd-" + MODEL_POS + VER + BIN)), Arguments.of("ro", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "ro-ud-rrt-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "ro-ud-rrt-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "ro-ud-rrt-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "ro-ud-rrt-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "ro-ud-rrt-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "ro-ud-rrt-" + MODEL_POS + VER + BIN)), Arguments.of("ru", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "ru-ud-gsd-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "ru-ud-gsd-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "ru-ud-gsd-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "ru-ud-gsd-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "ru-ud-gsd-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "ru-ud-gsd-" + MODEL_POS + VER + BIN)), Arguments.of("sr", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "sr-ud-set-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "sr-ud-set-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "sr-ud-set-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "sr-ud-set-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "sr-ud-set-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "sr-ud-set-" + MODEL_POS + VER + BIN)), Arguments.of("sk", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "sk-ud-snk-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "sk-ud-snk-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "sk-ud-snk-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "sk-ud-snk-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "sk-ud-snk-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "sk-ud-snk-" + MODEL_POS + VER + BIN)), Arguments.of("sl", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "sl-ud-ssj-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "sl-ud-ssj-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "sl-ud-ssj-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "sl-ud-ssj-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "sl-ud-ssj-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "sl-ud-ssj-" + MODEL_POS + VER + BIN)), Arguments.of("sv", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "sv-ud-talbanken-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "sv-ud-talbanken-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "sv-ud-talbanken-" + MODEL_POS + VER + BIN)), + ModelType.SENTENCE_DETECTOR, OPENNLP + "sv-ud-talbanken-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "sv-ud-talbanken-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "sv-ud-talbanken-" + MODEL_POS + VER + BIN)), Arguments.of("uk", Map.of( - DownloadUtil.ModelType.SENTENCE_DETECTOR, OPENNLP + "uk-ud-iu-" + MODEL_SENT + VER + BIN, - DownloadUtil.ModelType.TOKENIZER, OPENNLP + "uk-ud-iu-" + MODEL_TOK + VER + BIN, - DownloadUtil.ModelType.POS, OPENNLP + "uk-ud-iu-" + MODEL_POS + VER + BIN)) + ModelType.SENTENCE_DETECTOR, OPENNLP + "uk-ud-iu-" + MODEL_SENT + VER + BIN, + ModelType.TOKENIZER, OPENNLP + "uk-ud-iu-" + MODEL_TOK + VER + BIN, + ModelType.POS, OPENNLP + "uk-ud-iu-" + MODEL_POS + VER + BIN)) ); } } diff --git a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilDownloadTwiceTest.java b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilDownloadTwiceTest.java index 24bad516..a9982ecc 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilDownloadTwiceTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilDownloadTwiceTest.java @@ -30,6 +30,7 @@ import org.junit.jupiter.api.Test; import org.slf4j.LoggerFactory; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import static org.junit.jupiter.api.Assertions.assertEquals; @@ -61,7 +62,7 @@ public class DownloadUtilDownloadTwiceTest { @Test public void testDownloadModelTwice() throws IOException { String lang = "de"; - DownloadUtil.ModelType type = DownloadUtil.ModelType.SENTENCE_DETECTOR; + ModelType type = ModelType.SENTENCE_DETECTOR; try (LogCaptor logCaptor = LogCaptor.forClass(DownloadUtil.class)) { boolean alreadyDownloaded = DownloadUtil.existsModel(lang, type); diff --git a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilTest.java b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilTest.java index c5355601..f92ada9c 100644 --- a/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilTest.java +++ b/opennlp-tools/src/test/java/opennlp/tools/util/DownloadUtilTest.java @@ -29,6 +29,7 @@ import org.junit.jupiter.params.provider.NullAndEmptySource; import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.tokenize.TokenizerModel; @@ -48,7 +49,7 @@ public class DownloadUtilTest { @EnabledWhenCDNAvailable(hostname = "dlcdn.apache.org") public void testDownloadModelByLanguage(String lang) throws IOException { SentenceModel model = DownloadUtil.downloadModel(lang, - DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + ModelType.SENTENCE_DETECTOR, SentenceModel.class); assertNotNull(model); assertEquals(lang, model.getLanguage()); assertTrue(model.isLoadedFromSerialized()); @@ -68,7 +69,7 @@ public class DownloadUtilTest { @EnabledWhenCDNAvailable(hostname = "dlcdn.apache.org") public void testExistsModel() throws IOException { final String lang = "en"; - final DownloadUtil.ModelType type = DownloadUtil.ModelType.SENTENCE_DETECTOR; + final ModelType type = ModelType.SENTENCE_DETECTOR; // Prepare SentenceModel model = DownloadUtil.downloadModel(lang, type, SentenceModel.class); assertNotNull(model); @@ -82,7 +83,7 @@ public class DownloadUtilTest { @ValueSource(strings = {"xy", "\t", "\n"}) @EnabledWhenCDNAvailable(hostname = "dlcdn.apache.org") public void testExistsModelInvalid(String input) throws IOException { - assertFalse(DownloadUtil.existsModel(input, DownloadUtil.ModelType.SENTENCE_DETECTOR)); + assertFalse(DownloadUtil.existsModel(input, ModelType.SENTENCE_DETECTOR)); } @ParameterizedTest(name = "Detect invalid input: \"{0}\"") @@ -90,10 +91,10 @@ public class DownloadUtilTest { @ValueSource(strings = {" ", "\t", "\n"}) public void testDownloadModelInvalid(String input) { assertThrows(IOException.class, () -> DownloadUtil.downloadModel(input, - DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class), "Invalid model"); + ModelType.SENTENCE_DETECTOR, SentenceModel.class), "Invalid model"); } - private static final DownloadUtil.ModelType MT_TOKENIZER = DownloadUtil.ModelType.TOKENIZER; + private static final ModelType MT_TOKENIZER = ModelType.TOKENIZER; // Note: This needs to be public as JUnit 5 requires it like this. public static Stream<Arguments> provideURLs() { diff --git a/opennlp-uima/src/test/java/opennlp/uima/AbstractIT.java b/opennlp-uima/src/test/java/opennlp/uima/AbstractIT.java index 1295dead..39c27387 100644 --- a/opennlp-uima/src/test/java/opennlp/uima/AbstractIT.java +++ b/opennlp-uima/src/test/java/opennlp/uima/AbstractIT.java @@ -41,6 +41,7 @@ import org.junit.jupiter.api.BeforeAll; import org.slf4j.Logger; import org.slf4j.LoggerFactory; +import opennlp.tools.models.ModelType; import opennlp.tools.postag.POSModel; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.tokenize.TokenizerModel; @@ -57,9 +58,9 @@ abstract class AbstractIT extends AbstractUimaTest { @BeforeAll public static void initEnv() throws IOException { // ensure referenced UD models are present in download home - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.TOKENIZER, TokenizerModel.class); - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.POS, POSModel.class); + DownloadUtil.downloadModel("en", ModelType.TOKENIZER, TokenizerModel.class); + DownloadUtil.downloadModel("en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); + DownloadUtil.downloadModel("en", ModelType.POS, POSModel.class); // ensure referenced classic model files are present in download home for (String modelName: List.of("en-ner-organization", "en-ner-location", "en-ner-person", diff --git a/opennlp-uima/src/test/java/opennlp/uima/util/AnnotationComparatorTest.java b/opennlp-uima/src/test/java/opennlp/uima/util/AnnotationComparatorTest.java index bcab5d01..2366355a 100644 --- a/opennlp-uima/src/test/java/opennlp/uima/util/AnnotationComparatorTest.java +++ b/opennlp-uima/src/test/java/opennlp/uima/util/AnnotationComparatorTest.java @@ -32,6 +32,7 @@ import org.junit.jupiter.api.BeforeEach; import org.junit.jupiter.api.Test; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.util.DownloadUtil; import opennlp.uima.AbstractUimaTest; @@ -56,7 +57,7 @@ class AnnotationComparatorTest extends AbstractUimaTest { @BeforeAll public static void initEnv() throws IOException { // ensure referenced UD models are present in download home - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + DownloadUtil.downloadModel("en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); } @BeforeEach diff --git a/opennlp-uima/src/test/java/opennlp/uima/util/AnnotatorUtilTest.java b/opennlp-uima/src/test/java/opennlp/uima/util/AnnotatorUtilTest.java index 0aeba0b6..66a0b48f 100644 --- a/opennlp-uima/src/test/java/opennlp/uima/util/AnnotatorUtilTest.java +++ b/opennlp-uima/src/test/java/opennlp/uima/util/AnnotatorUtilTest.java @@ -38,6 +38,7 @@ import org.junit.jupiter.params.provider.NullAndEmptySource; import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.util.DownloadUtil; import opennlp.uima.AbstractUimaTest; @@ -62,7 +63,7 @@ class AnnotatorUtilTest extends AbstractUimaTest { @BeforeAll public static void initEnv() throws IOException { // ensure referenced UD models are present in download home - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + DownloadUtil.downloadModel("en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); } @BeforeEach diff --git a/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java b/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java index 332784a1..b5a93c05 100644 --- a/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java +++ b/opennlp-uima/src/test/java/opennlp/uima/util/OpennlpUtilTest.java @@ -30,6 +30,7 @@ import org.junit.jupiter.params.provider.EmptySource; import org.junit.jupiter.params.provider.ValueSource; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.util.DownloadUtil; import opennlp.tools.util.TrainingParameters; @@ -53,7 +54,7 @@ public class OpennlpUtilTest extends AbstractTest { @BeforeAll public static void initEnv() throws IOException { sentModel = DownloadUtil.downloadModel( - "en", DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + "en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); } @Test diff --git a/opennlp-uima/src/test/java/opennlp/uima/util/UimaUtilTest.java b/opennlp-uima/src/test/java/opennlp/uima/util/UimaUtilTest.java index d101a76b..084083f8 100644 --- a/opennlp-uima/src/test/java/opennlp/uima/util/UimaUtilTest.java +++ b/opennlp-uima/src/test/java/opennlp/uima/util/UimaUtilTest.java @@ -33,6 +33,7 @@ import org.junit.jupiter.api.BeforeEach; import org.junit.jupiter.api.Test; import opennlp.tools.EnabledWhenCDNAvailable; +import opennlp.tools.models.ModelType; import opennlp.tools.sentdetect.SentenceModel; import opennlp.tools.util.DownloadUtil; import opennlp.uima.AbstractUimaTest; @@ -59,7 +60,7 @@ class UimaUtilTest extends AbstractUimaTest { @BeforeAll public static void initEnv() throws IOException { // ensure referenced UD models are present in download home - DownloadUtil.downloadModel("en", DownloadUtil.ModelType.SENTENCE_DETECTOR, SentenceModel.class); + DownloadUtil.downloadModel("en", ModelType.SENTENCE_DETECTOR, SentenceModel.class); } @BeforeEach
