Examples with DocumentFactory org.icij.extract.document.DocumentFactory used on opensource projects

Example 1 with DocumentFactory

use of org.icij.extract.document.DocumentFactory in project datashare by ICIJ.

the class IndexerHelper method indexEmbeddedFile.

File indexEmbeddedFile(String project, String docPath) throws IOException {
    Path path = get(getClass().getResource(docPath).getPath());
    Extractor extractor = new Extractor(new DocumentFactory().withIdentifier(new DigestIdentifier("SHA-384", Charset.defaultCharset())));
    extractor.setDigester(new UpdatableDigester(project, Entity.HASHER.toString()));
    TikaDocument document = extractor.extract(path);
    ElasticsearchSpewer elasticsearchSpewer = new ElasticsearchSpewer(client, l -> ENGLISH, new FieldNames(), mock(Publisher.class), new PropertiesProvider()).withRefresh(IMMEDIATE).withIndex("test-datashare");
    elasticsearchSpewer.write(document);
    return path.toFile();
}

Example 2 with DocumentFactory

use of org.icij.extract.document.DocumentFactory in project datashare by ICIJ.

the class DatashareExtractIntegrationTest method createExtractor.

Extractor createExtractor() {
    Extractor extractor = new Extractor(new DocumentFactory().withIdentifier(new DigestIdentifier("SHA-384", Charset.defaultCharset())));
    extractor.setDigester(new UpdatableDigester("test", Entity.HASHER.toString()));
    return extractor;
}

Example 3 with DocumentFactory

use of org.icij.extract.document.DocumentFactory in project datashare by ICIJ.

the class ElasticsearchSpewerTest method test_duplicate_file.

@Test
public void test_duplicate_file() throws Exception {
    DocumentFactory tikaFactory = new DocumentFactory().configure(Options.from(new HashMap<String, String>() {

        {
            put("idDigestMethod", Document.HASHER.toString());
        }
    }));
    Extractor extractor = new Extractor(tikaFactory);
    extractor.setDigester(new UpdatableDigester("project", Document.HASHER.toString()));
    final TikaDocument document = extractor.extract(get(Objects.requireNonNull(getClass().getResource("/docs/doc.txt")).getPath()));
    final TikaDocument document2 = extractor.extract(get(Objects.requireNonNull(getClass().getResource("/docs/doc-duplicate.txt")).getPath()));
    spewer.write(document);
    spewer.write(document2);
    GetResponse actualDocument = es.client.get(new GetRequest(TEST_INDEX, document.getId()), RequestOptions.DEFAULT);
    GetResponse actualDocument2 = es.client.get(new GetRequest(TEST_INDEX, new Duplicate(document2.getPath(), document.getId()).getId()), RequestOptions.DEFAULT);
    assertThat(actualDocument.isExists()).isTrue();
    assertThat(actualDocument.getSourceAsMap()).includes(entry("type", "Document"));
    assertThat(actualDocument2.isExists()).isTrue();
    assertThat(actualDocument2.getSourceAsMap()).includes(entry("type", "Duplicate"));
}

Example 4 with DocumentFactory

use of org.icij.extract.document.DocumentFactory in project datashare by ICIJ.

the class ElasticsearchSpewerTest method test_truncated_content.

@Test
public void test_truncated_content() throws Exception {
    ElasticsearchSpewer limitedContentSpewer = new ElasticsearchSpewer(es.client, text -> Language.ENGLISH, new FieldNames(), publisher, new PropertiesProvider(new HashMap<String, String>() {

        {
            put("maxContentLength", "20");
        }
    })).withRefresh(IMMEDIATE).withIndex("test-datashare");
    final TikaDocument document = new DocumentFactory().withIdentifier(new PathIdentifier()).create(get("fake-file.txt"));
    final ParsingReader reader = new ParsingReader(new ByteArrayInputStream("this content should be truncated".getBytes()));
    document.setReader(reader);
    limitedContentSpewer.write(document);
    GetResponse documentFields = es.client.get(new GetRequest(TEST_INDEX, document.getId()), RequestOptions.DEFAULT);
    assertThat(documentFields.getSourceAsMap()).includes(entry("content", "this content should"));
}

Example 5 with DocumentFactory

use of org.icij.extract.document.DocumentFactory in project datashare by ICIJ.

the class ElasticsearchSpewerTest method test_extract_id_should_be_equal_to_datashare_id.

@Test
public void test_extract_id_should_be_equal_to_datashare_id() throws IOException {
    DocumentFactory tikaFactory = new DocumentFactory().configure(Options.from(new HashMap<String, String>() {

        {
            put("idDigestMethod", Document.HASHER.toString());
        }
    }));
    Extractor extractor = new Extractor(tikaFactory);
    extractor.setDigester(new UpdatableDigester("project", Document.HASHER.toString()));
    final TikaDocument extractDocument = extractor.extract(get(Objects.requireNonNull(getClass().getResource("/docs/embedded_doc.eml")).getPath()));
    Document document = new Document(Project.project("project"), get(Objects.requireNonNull(getClass().getResource("/docs/embedded_doc.eml")).getPath()), "This is a document to be parsed by datashare.", Language.FRENCH, Charset.defaultCharset(), "text/plain", convert(extractDocument.getMetadata()), Document.Status.INDEXED, 45L);
    assertThat(document.getId()).isEqualTo(extractDocument.getId());
}