+ * This configuration class is activated when the {@link MetadataExtractionConfiguration} class is present in the classpath. + *
+ *+ * By including this class, metadata extraction features are automatically configured without requiring explicit registration + * of the necessary components, simplifying integration into the application context. + *
+ * + * @author marcobelligoli + */ +@Configuration +@ConditionalOnClass(MetadataExtractionConfiguration.class) +@Import(MetadataExtractionConfiguration.class) +public class MetadataExtractionContentAutoConfiguration { + +} diff --git a/spring-content-autoconfigure/src/main/resources/META-INF/spring/org.springframework.boot.autoconfigure.AutoConfiguration.imports b/spring-content-autoconfigure/src/main/resources/META-INF/spring/org.springframework.boot.autoconfigure.AutoConfiguration.imports index 257eb9eee..c3ed82d7b 100644 --- a/spring-content-autoconfigure/src/main/resources/META-INF/spring/org.springframework.boot.autoconfigure.AutoConfiguration.imports +++ b/spring-content-autoconfigure/src/main/resources/META-INF/spring/org.springframework.boot.autoconfigure.AutoConfiguration.imports @@ -3,6 +3,7 @@ internal.org.springframework.content.fs.boot.autoconfigure.FilesystemContentAuto internal.org.springframework.content.jpa.boot.autoconfigure.JpaContentAutoConfiguration internal.org.springframework.content.mongo.boot.autoconfigure.MongoContentAutoConfiguration internal.org.springframework.content.renditions.boot.autoconfigure.RenditionsContentAutoConfiguration +internal.org.springframework.content.metadataextraction.boot.autoconfigure.MetadataExtractionContentAutoConfiguration internal.org.springframework.content.rest.boot.autoconfigure.ContentRestAutoConfiguration internal.org.springframework.content.rest.boot.autoconfigure.HypermediaAutoConfiguration internal.org.springframework.content.s3.boot.autoconfigure.S3ContentAutoConfiguration diff --git a/spring-content-autoconfigure/src/test/java/org/springframework/content/metadataextraction/boot/ContentMetadataExtractionAutoConfigurationTest.java b/spring-content-autoconfigure/src/test/java/org/springframework/content/metadataextraction/boot/ContentMetadataExtractionAutoConfigurationTest.java new file mode 100644 index 000000000..1d663b690 --- /dev/null +++ b/spring-content-autoconfigure/src/test/java/org/springframework/content/metadataextraction/boot/ContentMetadataExtractionAutoConfigurationTest.java @@ -0,0 +1,80 @@ +/* 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 org.springframework.content.metadataextraction.boot; + +import com.github.paulcwarren.ginkgo4j.Ginkgo4jConfiguration; +import com.github.paulcwarren.ginkgo4j.Ginkgo4jRunner; +import internal.org.springframework.content.s3.boot.autoconfigure.S3ContentAutoConfiguration; +import internal.org.springframework.content.solr.boot.autoconfigure.SolrAutoConfiguration; +import internal.org.springframework.content.solr.boot.autoconfigure.SolrExtensionAutoConfiguration; +import org.junit.runner.RunWith; +import org.springframework.boot.autoconfigure.AutoConfigurationPackage; +import org.springframework.boot.autoconfigure.EnableAutoConfiguration; +import org.springframework.content.commons.metadataextraction.MetadataExtractionService; +import org.springframework.content.commons.renditions.Renderable; +import org.springframework.content.commons.repository.ContentStore; +import org.springframework.content.metadataextraction.extractors.DefaultMetadataExtractor; +import org.springframework.context.annotation.AnnotationConfigApplicationContext; +import org.springframework.context.annotation.Configuration; +import org.springframework.context.annotation.EnableMBeanExport; +import org.springframework.jmx.support.RegistrationPolicy; +import org.springframework.support.TestEntity; + +import static com.github.paulcwarren.ginkgo4j.Ginkgo4jDSL.Context; +import static com.github.paulcwarren.ginkgo4j.Ginkgo4jDSL.Describe; +import static com.github.paulcwarren.ginkgo4j.Ginkgo4jDSL.It; +import static org.hamcrest.CoreMatchers.is; +import static org.hamcrest.CoreMatchers.not; +import static org.hamcrest.CoreMatchers.nullValue; +import static org.hamcrest.MatcherAssert.assertThat; + +/** + * Test class for verifying the functionality of the ContentMetadataExtractionAutoConfiguration. + * + * @author marcobelligoli + */ +@RunWith(Ginkgo4jRunner.class) +@Ginkgo4jConfiguration(threads = 1) +public class ContentMetadataExtractionAutoConfigurationTest { + + { + Describe("ContentMetadataExtractionAutoConfiguration", + () -> Context("given a default configuration", () -> It("should load the all metadata extractors", () -> { + + AnnotationConfigApplicationContext context = new AnnotationConfigApplicationContext(); + context.register(TestConfig.class); + context.refresh(); + + assertThat(context.getBean(MetadataExtractionService.class), is(not(nullValue()))); + assertThat(context.getBean(DefaultMetadataExtractor.class), is(not(nullValue()))); + + context.close(); + }))); + } + + @Configuration + @AutoConfigurationPackage + @EnableAutoConfiguration(exclude = { SolrAutoConfiguration.class, SolrExtensionAutoConfiguration.class, S3ContentAutoConfiguration.class }) + @EnableMBeanExport(registration = RegistrationPolicy.IGNORE_EXISTING) + public static class TestConfig { + + } + + public interface TestEntityContentStore extends ContentStore+ * The extracted metadata will be returned as a map where the keys represent + * the metadata property names and the values represent the respective metadata values. + *
+ *+ * This service retrieves all instances of {@link MetadataExtractor} present in the Spring context and, + * for each of them, performs metadata extraction from the provided file. + *
+ * + * @author marcobelligoli + */ +public interface MetadataExtractionService { + + /** + * Extracts metadata from the specified file. + * + * @param file the file from which metadata will be extracted + * @return a map containing the extracted metadata, where keys represent + * metadata property names, and values represent the respective metadata values + */ + Map+ * This exception is typically thrown by components that implement + * the {@link MetadataExtractor} + * interface when an error occurs while attempting to extract metadata from a file. + * Encapsulates the root cause of the error. + *
+ * + * @author marcobelligoli + */ +public class MetadataExtractionException extends RuntimeException { + + public MetadataExtractionException(Throwable cause) { + + super(cause); + } +} diff --git a/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/MetadataExtractionUtils.java b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/MetadataExtractionUtils.java new file mode 100644 index 000000000..a1275ad8e --- /dev/null +++ b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/MetadataExtractionUtils.java @@ -0,0 +1,112 @@ +/* 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 org.springframework.content.metadataextraction; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import org.springframework.core.io.ByteArrayResource; + +import java.io.ByteArrayOutputStream; +import java.io.File; +import java.io.FileInputStream; +import java.io.IOException; +import java.io.InputStream; + +/** + * Utility class for metadata extraction operations. + * This class provides methods for converting files or input streams + * into {@link ByteArrayResource} objects. + *+ * It is designed to be used as a utility class and therefore cannot be instantiated. + *
+ */ +public class MetadataExtractionUtils { + + private MetadataExtractionUtils() { + + throw new IllegalStateException("Utility class"); + } + + private static final Logger LOGGER = LoggerFactory.getLogger(MetadataExtractionUtils.class); + + /** + * Converts the contents of the given file into a {@link ByteArrayResource}. + * The method reads all data from the provided file and packages it + * into a {@link ByteArrayResource} for further use. + * + * @param file The file to be converted into a {@link ByteArrayResource}. + * Must not be null. The method will attempt to read the file's contents. + * @return A {@link ByteArrayResource} containing the file's byte data. + * Throws a {@link MetadataExtractionException} if the file cannot be read. + * @throws MetadataExtractionException If an I/O error occurs while accessing the file. + */ + public static ByteArrayResource getByteArrayResourceFromFile(File file) { + + try (InputStream inputStream = new FileInputStream(file)) { + return getByteArrayResource(inputStream, file.getName()); + } + catch (IOException e) { + throw new MetadataExtractionException(e); + } + } + + private static ByteArrayResource getByteArrayResource(InputStream inputStream, String fileName) { + + if (inputStream == null) { + return null; + } + + LOGGER.debug("Converting input stream in byte array resource..."); + + if (inputStream instanceof FileInputStream fileInputStream) { + File file; + try { + file = new File(fileInputStream.getFD().toString()); + fileName = file.getName(); + } + catch (IOException e) { + LOGGER.warn(e.getMessage()); + } + } + + byte[] fileBytes; + try (ByteArrayOutputStream baos = new ByteArrayOutputStream()) { + byte[] buffer = new byte[1024]; + int bytesRead; + while ((bytesRead = inputStream.read(buffer)) != -1) { + baos.write(buffer, 0, bytesRead); + } + fileBytes = baos.toByteArray(); + } + catch (IOException e) { + throw new MetadataExtractionException(e); + } + + String finalFileName = fileName; + var result = new ByteArrayResource(fileBytes) { + + @Override + public String getFilename() { + + return finalFileName; + } + }; + + LOGGER.debug("Conversion done"); + return result; + } +} diff --git a/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/config/MetadataExtractionConfiguration.java b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/config/MetadataExtractionConfiguration.java new file mode 100644 index 000000000..d15087683 --- /dev/null +++ b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/config/MetadataExtractionConfiguration.java @@ -0,0 +1,48 @@ +/* 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 org.springframework.content.metadataextraction.config; + +import internal.org.springframework.content.commons.metadataextraction.MetadataExtractionServiceImpl; +import org.springframework.content.commons.metadataextraction.MetadataExtractionService; +import org.springframework.content.commons.metadataextraction.MetadataExtractor; +import org.springframework.content.metadataextraction.extractors.DefaultMetadataExtractor; +import org.springframework.context.annotation.Bean; +import org.springframework.context.annotation.ComponentScan; +import org.springframework.context.annotation.Configuration; + +/** + * Spring configuration class for metadata extraction services. + *+ * This configuration enables component scanning to detect and register beans related to + * metadata extraction, including implementations of {@link MetadataExtractor}. + * It also defines a bean for the {@link MetadataExtractionService}, which aggregates + * various {@link MetadataExtractor} implementations to perform metadata extraction + * on a given file. + *
+ * + * @author marcobelligoli + */ +@Configuration +@ComponentScan(basePackageClasses = DefaultMetadataExtractor.class) +public class MetadataExtractionConfiguration { + + @Bean + public MetadataExtractionService metadataExtractionService(MetadataExtractor... metadataExtractors) { + + return new MetadataExtractionServiceImpl(metadataExtractors); + } +} diff --git a/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/extractors/AlfrescoTransformCoreMetadataExtractor.java b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/extractors/AlfrescoTransformCoreMetadataExtractor.java new file mode 100644 index 000000000..a9fcd0404 --- /dev/null +++ b/spring-content-metadata-extraction/src/main/java/org/springframework/content/metadataextraction/extractors/AlfrescoTransformCoreMetadataExtractor.java @@ -0,0 +1,102 @@ +/* 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 org.springframework.content.metadataextraction.extractors; + +import com.fasterxml.jackson.core.type.TypeReference; +import com.fasterxml.jackson.databind.ObjectMapper; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; +import org.springframework.beans.factory.annotation.Autowired; +import org.springframework.beans.factory.annotation.Value; +import org.springframework.boot.autoconfigure.condition.ConditionalOnProperty; +import org.springframework.content.commons.metadataextraction.MetadataExtractor; +import org.springframework.content.metadataextraction.MetadataExtractionException; +import org.springframework.content.metadataextraction.MetadataExtractionUtils; +import org.springframework.http.HttpEntity; +import org.springframework.http.HttpHeaders; +import org.springframework.http.HttpMethod; +import org.springframework.http.ResponseEntity; +import org.springframework.stereotype.Service; +import org.springframework.util.LinkedMultiValueMap; +import org.springframework.util.MultiValueMap; +import org.springframework.web.client.RestTemplate; + +import java.io.File; +import java.io.IOException; +import java.nio.file.Files; +import java.util.Collections; +import java.util.Map; + +/** + * Implementation of the {@link MetadataExtractor} interface for extracting metadata + * by leveraging Alfresco Transform Core service. This class communicates with the + * Alfresco Transform Core service to retrieve metadata for a given file. + *+ * This service is enabled conditionally based on the presence of the + * "alfresco.transform.core.url" property in the application configuration. + *
+ */ +@Service +@ConditionalOnProperty(name = "alfresco.transform.core.url") +public class AlfrescoTransformCoreMetadataExtractor implements MetadataExtractor { + + private static final Logger LOGGER = LoggerFactory.getLogger(AlfrescoTransformCoreMetadataExtractor.class); + private static final String ALFRESCO_TRANSFORM_CORE_TRANSFORM_URL = "/transform"; + private static final String TARGET_MIME_TYPE_METADATA_EXTRACTOR = "alfresco-metadata-extract"; + private final String alfrescoTransformCoreUrl; + private final RestTemplate restTemplate; + private final ObjectMapper objectMapper; + + @Autowired + public AlfrescoTransformCoreMetadataExtractor(@Value("${alfresco.transform.core.url}") String alfrescoTransformCoreUrl) { + + this.alfrescoTransformCoreUrl = alfrescoTransformCoreUrl; + this.restTemplate = new RestTemplate(); + this.objectMapper = new ObjectMapper(); + } + + @Override + public Map+ * This implementation retrieves detailed metadata using Java NIO's file attributes and utility + * classes. Metadata extracted by this class includes: + *
+ * If an error occurs during metadata extraction, a {@link MetadataExtractionException} is + * thrown, encapsulating the root cause of the error. This class also logs the extraction process + * for debugging purposes. + *
+ * + * @author marcobelligoli + */ +@Service +public class DefaultMetadataExtractor implements MetadataExtractor { + + private static final Logger LOGGER = LoggerFactory.getLogger(DefaultMetadataExtractor.class); + + @Override + public Map+ * It sets up a mock wire server to simulate the behavior of the Alfresco Transform Core service. + * Additionally, it verifies both successful metadata extraction and error scenarios. + *
+ */ +class AlfrescoTransformCoreMetadataExtractorTest { + + private static final String ALFRESCO_TRANSFORM_CORE_HOST = "localhost"; + private static WireMockServer wireMockServer; + private static AlfrescoTransformCoreMetadataExtractor metadataExtractor; + + @BeforeAll + static void setup() { + + wireMockServer = new WireMockServer(WireMockConfiguration.wireMockConfig().dynamicPort()); + wireMockServer.start(); + var port = wireMockServer.port(); + WireMock.configureFor(ALFRESCO_TRANSFORM_CORE_HOST, port); + var baseUrl = String.format("http://%s:%d", ALFRESCO_TRANSFORM_CORE_HOST, port); + metadataExtractor = new AlfrescoTransformCoreMetadataExtractor(baseUrl); + } + + @AfterAll + static void tearDown() { + + if (wireMockServer != null) { + wireMockServer.stop(); + } + } + + private static void mockAlfrescoTransformCoreResponse(String response) { + + stubFor(post(urlEqualTo("/transform")).willReturn(aResponse().withHeader("Content-Type", "application/json").withBody(response))); + } + + @Test + void testExtractMetadata() + throws URISyntaxException { + + File input = getFile(); + + mockAlfrescoTransformCoreResponse( + "{\"{http://www.alfresco.org/model/content/1.0}author\":\"John Doe\",\"{http://www.alfresco.org/model/content/1.0}created\":\"2024-04-16T07:39:22Z\",\"{http://www.alfresco.org/model/content/1.0}title\":null}"); + + var result = metadataExtractor.extractMetadata(input); + + assertNotNull(result); + assertEquals("John Doe", result.get("{http://www.alfresco.org/model/content/1.0}author")); + assertEquals("2024-04-16T07:39:22Z", result.get("{http://www.alfresco.org/model/content/1.0}created")); + assertNull(result.get("{http://www.alfresco.org/model/content/1.0}title")); + } + + @Test + void testExtractMetadataWithError() + throws URISyntaxException { + + File input = getFile(); + + mockAlfrescoTransformCoreResponse("{\"{http://www.alfresco.org/model/content/1.0}title:null}"); + + assertThrows(MetadataExtractionException.class, () -> metadataExtractor.extractMetadata(input)); + } + + private static File getFile() + throws URISyntaxException { + + ClassLoader classLoader = Thread.currentThread().getContextClassLoader(); + URL resource = classLoader.getResource("sample.jpeg"); + assert resource != null; + return new File(resource.toURI()); + } +} diff --git a/spring-content-metadata-extraction/src/test/java/org/springframework/content/metadataextraction/extractors/DefaultMetadataExtractorTest.java b/spring-content-metadata-extraction/src/test/java/org/springframework/content/metadataextraction/extractors/DefaultMetadataExtractorTest.java new file mode 100644 index 000000000..74a75efe9 --- /dev/null +++ b/spring-content-metadata-extraction/src/test/java/org/springframework/content/metadataextraction/extractors/DefaultMetadataExtractorTest.java @@ -0,0 +1,92 @@ +/* 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 org.springframework.content.metadataextraction.extractors; + +import org.junit.Test; +import org.springframework.content.metadataextraction.MetadataExtractionException; + +import java.io.File; +import java.io.IOException; +import java.net.URISyntaxException; +import java.net.URL; +import java.util.Map; + +import static org.junit.Assert.assertNotNull; +import static org.junit.Assert.assertThrows; +import static org.junit.Assert.assertTrue; + +/** + * Unit test class for the {@link DefaultMetadataExtractor}. + * + *This class contains test cases to validate the functionality of the + * {@link DefaultMetadataExtractor#extractMetadata(File)} method.
+ * + *The following test scenarios are covered:
+ *