List of usage examples for org.apache.commons.io FileUtils toFile
public static File toFile(URL url)
URL to a File. From source file:nl.strohalm.cyclos.utils.lucene.IndexHandler.java
/** * Returns the root directory where indexes are stored *///from w w w. j a va 2 s. c o m public static File resolveIndexRoot() { // Setup the Lucene index directory to WEB-INF/indexes directory final File bin = FileUtils.toFile(IndexHandler.class.getResource("/")); // WEB-INF/classes File root = bin.getParentFile(); // WEB-INF // When running on the standalone server, the bin is root/bin, not root/web/WEB-INF/classes if (!bin.getAbsolutePath().contains("WEB-INF") && new File(root, "web").exists()) { root = new File(root, "web/WEB-INF"); } return new File(root, "indexes"); // WEB-INF/indexes }
From source file:org.ambraproject.rhino.RhinoTestHelper.java
/** * Parses an XML file.//w w w.ja va 2 s.c o m * * @param xmlDataResource The XML URL data resource * * @return The {@link org.w3c.dom.Document Document} * * @throws ParserConfigurationException if a DocumentBuilder cannot be created which satisfies the * configuration requested * @throws IOException if cannot process file * @throws SAXException if any parse errors occur */ public static Document loadXMLFromString(URL xmlDataResource) throws ParserConfigurationException, IOException, SAXException { final File xmlFile = FileUtils.toFile(xmlDataResource); final Document document = loadXMLFromString(xmlFile); return document; }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test successful processing of <b>manifest.xml</b> file. * * @param entryNames The list of entry names. * * @throws IOException if manifest file cannot be processed *///from ww w . jav a 2 s . c o m @Test(dataProvider = "getPackageEntryNames") public void testGetManifestXmlShouldSucceed(Collection<String> entryNames) throws IOException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, MANIFEST_XML); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, entryNames); final ManifestXml actualManifest = ingestionService.getManifestXml(testArchive); final Asset articleAsset = actualManifest.getArticleAsset(); assertThat(articleAsset.getRepresentations()).hasSize(2); final Optional<Representation> printable = articleAsset.getRepresentation("printable"); assertThat(printable.isPresent()).isTrue(); final Representation printablePresentation = printable.get(); assertThat(printablePresentation.getType()).isEqualTo("printable"); final ManifestFile presentationManifest = printablePresentation.getFile(); assertThat(presentationManifest.getEntry()).isEqualTo("dupp.0000001.pdf"); assertThat(presentationManifest.getCrepoKey()).isEqualTo("10.1111/dupp.0000001.pdf"); final ImmutableList<Asset> assets = actualManifest.getAssets(); assertThat(assets).hasSize(8); final MutableInt supplementary_count = new MutableInt(); assets.forEach(asset -> { final AssetTagName assetTag = asset.getAssetTagName(); final AssetType assetType = asset.getType(); if (assetTag.equals(ManifestXml.AssetTagName.ARTICLE)) { assertThat(assetType).isEqualTo(AssetType.ARTICLE); assertThat(asset).isEqualTo(articleAsset); } else if (assetTag.equals(ManifestXml.AssetTagName.OBJECT)) { assertThat(asset.getRepresentations()).hasSize(1); assertThat(assetType).isEqualTo(AssetType.SUPPLEMENTARY_MATERIAL); supplementary_count.increment(); final String expectedUri = String.format("info:doi/10.1111/dupp.0000001.s%03d", supplementary_count.intValue()); assertThat(asset.getUri()).isEqualTo(expectedUri); if (supplementary_count.intValue() == 1) { // First asset will have "strkImage" set to True. assertThat(asset.isStrikingImage()).isTrue(); } else { assertThat(asset.isStrikingImage()).isFalse(); } } else { assert false : String.format("Unexpected test case for asset tag: '%s'", assetTag); } }); final ImmutableList<String> expectedEntries = ImmutableList.of(MANIFEST_XML, MANIFEST_DTD); final ImmutableList<ManifestFile> ancillaryFiles = actualManifest.getAncillaryFiles(); assertThat(ancillaryFiles).hasSize(2); ancillaryFiles.forEach(ancillary -> { final String entry = ancillary.getEntry(); assertThat(expectedEntries).contains(entry); if (entry.equals(MANIFEST_XML)) { assertThat(ancillary.getCrepoKey()).isEqualTo("10.1111/dupp.0000001.manifest.xml"); assertThat(ancillary.getMimetype()).isEqualTo("application/xml"); } else if (entry.equals(MANIFEST_DTD)) { assertThat(ancillary.getCrepoKey()).isEqualTo("10.1111/dupp.0000001.manifest.dtd"); assertThat(ancillary.getMimetype()).isEqualTo("application/xml-dtd"); } else { assert false : String.format("Unexpected test case for entry: '%s'", entry); } }); }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test exception handling with an <b>empty</b> manifest.xml file. * * @param entryNames The list of entries in the test archive. * * @throws IOException if manifest file cannot be processed */// w w w . ja v a2 s.c om @Test(dataProvider = "getPackageEntryNames") public void testEmptyManifestXmlShouldFail(Collection<String> entryNames) throws IOException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, "empty_manifest.xml"); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, entryNames); final ManifestXml actualManifest = ingestionService.getManifestXml(testArchive); assertThat(actualManifest).isNotNull(); try { actualManifest.getArticleAsset(); fail("Expecting exception, but nothing was thrown."); } catch (Exception exception) { assertThat(exception).isInstanceOf(ManifestDataException.class); assertThat(exception).hasMessageThat().isEqualTo("'article' node must have 'uri' attribute"); } }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test exception handling with an <b>duplicate URI</b> in manifest.xml file. * * @param entryNames The list of entries in the test archive. * * @throws IOException if manifest file cannot be processed *///from w w w. j a v a 2s . c o m @Test(dataProvider = "getPackageEntryNames") public void testDuplicateUriManifestXmlShouldFail(Collection<String> entryNames) throws IOException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, "duplicate_assets_manifest.xml"); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, entryNames); final ManifestXml actualManifest = ingestionService.getManifestXml(testArchive); assertThat(actualManifest).isNotNull(); try { actualManifest.getArticleAsset(); fail("Expecting exception, but nothing was thrown."); } catch (Exception exception) { assertThat(exception).isInstanceOf(ManifestDataException.class); assertThat(exception).hasMessageThat() .isEqualTo("Manifest has assets with duplicate uri: info:doi/10.1111/dupp.0000001.s001"); } }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test successful article ingestion./*from w ww. j a va 2 s. c om*/ * * @throws IOException if archive file cannot be processed * @throws SAXException if any XML parsing errors * @throws ParserConfigurationException if a DocumentBuilder cannot be created */ @Test @DirtiesContext() public void testArticleIngestShouldSucceed() throws IOException, ParserConfigurationException, SAXException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, MANIFEST_XML); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, ARTICLE_INGEST_ENTRIES); final Optional<String> bucketName = Optional.empty(); final String manuscriptEntry = "dupp.0000001.xml"; final URL manuscriptResource = Resources.getResource(IngestionServiceTest.class, manuscriptEntry); final Document manuscript = RhinoTestHelper.loadXMLFromString(manuscriptResource); final Article expectedArticle = new Article(); expectedArticle.setDoi("10.1111/dupp.0000001"); final ArticleIngestion expectedIngestion = new ArticleIngestion(); expectedIngestion.setArticle(expectedArticle); expectedIngestion.setIngestionNumber(1); final Doi expectedArticleDoi = Doi.create(INGESTED_DOI_URI); final HibernatePersistenceService mockPersistenceService = applicationContext .getBean(HibernatePersistenceService.class); when(mockPersistenceService.persistArticle(expectedArticleDoi)).thenReturn(expectedArticle); when(mockPersistenceService.persistIngestion(any(Article.class), any(IngestPackage.class))) .thenReturn(expectedIngestion); final IngestionService mockIngestionService = applicationContext.getBean(IngestionService.class); doReturn(manuscript).when(mockIngestionService).getDocument(testArchive, manuscriptEntry); final ArticleIngestion actualIngestion = mockIngestionService.ingest(testArchive, bucketName); assertThat(actualIngestion).isNotNull(); assertThat(actualIngestion).isEqualTo(expectedIngestion); assertThat(actualIngestion.getArticle()).isEqualTo(expectedArticle); final CustomMetadataExtractor.Factory mockMetadataExtractorFactory = applicationContext .getBean(CustomMetadataExtractor.Factory.class); final ArticleCrudService mockArticleCrudService = applicationContext.getBean(ArticleCrudService.class); verify(mockIngestionService).getDocument(testArchive, manuscriptEntry); verify(mockMetadataExtractorFactory).parse(manuscript); final ImmutableList<String> expectedDois = ImmutableList.of(INGESTED_DOI_URI, "info:doi/10.1111/dupp.0000001.s001", "info:doi/10.1111/dupp.0000001.s002", "info:doi/10.1111/dupp.0000001.s003", "info:doi/10.1111/dupp.0000001.s004", "info:doi/10.1111/dupp.0000001.s005", "info:doi/10.1111/dupp.0000001.s006", "info:doi/10.1111/dupp.0000001.s007"); final int callCount = mockingDetails(mockArticleCrudService).getInvocations().size(); assertThat(callCount).isEqualTo(expectedDois.size()); expectedDois.forEach(doiUri -> { final Doi assetDoi = Doi.create(doiUri); verify(mockArticleCrudService).getAllArticleItems(assetDoi); }); verify(mockPersistenceService).persistArticle(expectedArticleDoi); verify(mockPersistenceService).persistIngestion(any(Article.class), any(IngestPackage.class)); }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test successful article ingestion into a bucket. * /*ww w .java 2 s . co m*/ * @throws IOException if archive file cannot be processed * @throws SAXException if any XML parsing errors * @throws ParserConfigurationException if a DocumentBuilder cannot be created */ @Test @DirtiesContext public void testIngestIntoBucketShouldSucceed() throws IOException, ParserConfigurationException, SAXException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, MANIFEST_XML); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, ARTICLE_INGEST_ENTRIES); final Optional<String> bucketName = Optional.of("corpus"); final RuntimeConfiguration.MultiBucketContentRepoEndpoint mockRepoEndpoint = new RhinoTestHelper.TestMultiBucketContentRepoEndpoint( bucketName.get()); final RuntimeConfiguration mockRuntimeConfiguration = applicationContext .getBean(RuntimeConfiguration.class); doReturn(mockRepoEndpoint).when(mockRuntimeConfiguration).getCorpusStorage(); final String manuscriptEntry = "dupp.0000001.xml"; final URL manuscriptResource = Resources.getResource(IngestionServiceTest.class, manuscriptEntry); final Document manuscript = RhinoTestHelper.loadXMLFromString(manuscriptResource); final IngestionService mockIngestionService = applicationContext.getBean(IngestionService.class); doReturn(manuscript).when(mockIngestionService).getDocument(testArchive, manuscriptEntry); final ArticleIngestion expectedIngestion = new ArticleIngestion(); doReturn(expectedIngestion).when(mockIngestionService).processIngestPackage(any(IngestPackage.class)); mockIngestionService.ingest(testArchive, bucketName); // Ingest the archive to the bucket. verify(mockIngestionService).processIngestPackage(any(IngestPackage.class)); }
From source file:org.ambraproject.rhino.service.impl.IngestionServiceTest.java
/** * Test exception handling for article ingestion into an unknown bucket. * //w w w.ja va 2 s .c o m * @throws IOException if archive file cannot be processed * @throws SAXException if any XML parsing errors * @throws ParserConfigurationException if a DocumentBuilder cannot be created */ @Test @DirtiesContext public void testIngestIntoUnknownBucketShouldFail() throws IOException, ParserConfigurationException, SAXException { final URL xmlDataResource = Resources.getResource(IngestionServiceTest.class, MANIFEST_XML); final File manifestFile = FileUtils.toFile(xmlDataResource); final byte[] manifestData = FileUtils.readFileToByteArray(manifestFile); final Archive testArchive = createStubArchive(manifestData, ARTICLE_INGEST_ENTRIES); final Optional<String> bucketName = Optional.of("unknown"); final String manuscriptEntry = "dupp.0000001.xml"; final URL manuscriptResource = Resources.getResource(IngestionServiceTest.class, manuscriptEntry); final Document manuscript = RhinoTestHelper.loadXMLFromString(manuscriptResource); final IngestionService mockIngestionService = applicationContext.getBean(IngestionService.class); doReturn(manuscript).when(mockIngestionService).getDocument(testArchive, manuscriptEntry); try { mockIngestionService.ingest(testArchive, bucketName); fail("Expecting exception, but nothing was thrown."); } catch (Exception exception) { assertThat(exception).isInstanceOf(RestClientException.class); final String message = NO_SPACE_JOINER.join("Invalid bucket name: ", bucketName.get(), ". Allowed values are: ", "[bucket_name, secondary_bucket]. ", "(Allowed values are specified by rhino.yaml.)"); assertThat(exception).hasMessageThat().isEqualTo(message); } verify(mockIngestionService, times(0)).processIngestPackage(any(IngestPackage.class)); }
From source file:org.anc.gate.GrafDocument.java
@Override public Resource init() throws ResourceInstantiationException { // Out.prln("Initializing GrafDocument."); super.init(); IGraph graph;/* ww w . j a v a2 s. c o m*/ File fullPath; //from the gate gui URL url = super.getSourceUrl(); if (url != null) { fullPath = FileUtils.toFile(url); } else { Out.println("No file found: sourceUrl = " + url); return null; } // Load a DocumentHeader object to query the data it contains. DocumentHeader docHeader = null; try { docHeader = new DocumentHeader(fullPath); } catch (FileNotFoundException e) { throw new ResourceInstantiationException("Error loading document header.", e); } // Discard the XML from the header AnnotationSet originalMarkups = getAnnotations("Original markups"); if (originalMarkups != null) { originalMarkups.clear(); } // Get the text for the document String filename = null; try { filename = docHeader.getContentLocation(); } catch (GrafException e) { throw new ResourceInstantiationException("Unable to locate the primary data.", e); } //file should be there... if (filename == null) { throw new ResourceInstantiationException("Document content not specified in the headern."); } //get the original text, see getContent below File txtFile = new File(fullPath.getParentFile(), filename); if (!txtFile.exists()) { throw new ResourceInstantiationException("Primary data not found: " + txtFile.getPath()); } // Out.prln("Loading text from " + txtFile.getPath()); String theContent = null; try { theContent = getContent(new File(fullPath.getParentFile(), filename)); } catch (IOException e) { throw new ResourceInstantiationException("Unable to load text content.", e); } endOfContent = theContent.length(); if (endOfContent == 0) { throw new ResourceInstantiationException("Text file is empty"); } // Replace the DocumentContent. The current DocumentContent contains the // ANC header file, which not what we want the user to see. //make a new gate Document Content object with the original text DocumentContent docContent = new DocumentContentImpl(theContent); //set it to this object, and move on, nothing to see here... this.setContent(docContent); // Get a parser for the standoff annotations //AnnotationParser parser = new AnnotationParser(); try { ResourceHeader header = new ResourceHeader(resourceHeader.openStream()); GrafParser graphParser = new GrafParser(header); //This is a gate Annotation set made using standoffASName, that comes from the //gate GUI, Gate uses the setStandoffASName above to fill it, getAnnotations is a gate method, not ours gateAnnotations = this.getAnnotations(standoffASName); //get an iterator from the standoffAnnotations; ie iterate through the stand off file names if (standoffAnnotations == null || standoffAnnotations.size() == 0) { standoffAnnotations = docHeader.getAnnotationTypes(); } for (String type : standoffAnnotations) { //ok get the file name for each standoff file type, remember we are working with a *.anc file here.. filename = docHeader.getAnnotationLocation(type); Out.prln("Loading annotation " + type + " from " + filename); // System.out.println("filename is " + filename); if (filename != null) { try { //get the file name from this iteration, call the parser for that file now... //and pull out the annotations from this iterations standoff file. // newAnnotations = parser.parse(basePath + System.getProperty("file.separator") + filename); graph = graphParser.parse(new File(fullPath.getParentFile(), filename)); } catch (Exception e) { Out.println("Could not load graph from " + filename); throw new ResourceInstantiationException(e); } //cycle through the nodes only here, making it look easy for (INode node : graph.nodes()) { //this is where the magic happens...see comments in addAnnotations addAnnotation(node); } } } } catch (SAXException e) { Out.println("Could not create GraphParser"); } catch (Exception e) { Out.prln("Unable to load GrafDocument"); e.printStackTrace(); } return this; }
From source file:org.anc.gate.LoadGrafStandoff.java
@Override public Resource init() throws ResourceInstantiationException { if (resourceHeader == null) { throw new ResourceInstantiationException("The resource header has not been set."); }/* w w w . ja v a 2 s. c o m*/ try { super.init(); // parser = new GrafParser(); File headerFile = FileUtils.toFile(resourceHeader); header = new ResourceHeader(headerFile); // for (IAnnotationSpace aspace : header.getAnnotationSpaces()) // { // parser.addAnnotationSpace(aspace); // } } catch (Exception ex) { throw new ResourceInstantiationException("Unable to initialize the GraphParser", ex); } return this; }