Package edu.stanford.nlp.pipeline

Examples of edu.stanford.nlp.pipeline.CoreNLPProtos$Document

194
195
196
197
198
199
200
201
202
203
204
    // Construct a raw surrogate pair character and confirm it outputs hex escaped, when UTF-8 too
    @Test
    public void test_RawSurrogatePairUTF8() throws JDOMException, IOException {
      SAXBuilder builder = new SAXBuilder();
      builder.setExpandEntities(true);
      Document doc = builder.build(new StringReader("<?xml version=\"1.0\"?><root>\uD800\uDC00</root>"));
      Format format = Format.getCompactFormat().setEncoding("UTF-8");
      XMLOutputter outputter = new XMLOutputter(format);
      ByteArrayOutputStream baos = new ByteArrayOutputStream();
      outputter.output(doc, baos);
      String xml = baos.toString();
View Full Code Here
209
210
211
212
213
214
215
216
217
218
219
220
221
    // Construct illegal XML and check if the parser notices
    @Test
    public void test_ErrorSurrogatePair() throws JDOMException, IOException {
      SAXBuilder builder = new SAXBuilder();
      builder.setExpandEntities(true);
      Document doc = builder.build(new StringReader("<?xml version=\"1.0\"?><root></root>"));
      try {
        doc.getRootElement().setText("\uD800\uDBFF");
        fail("Illegal surrogate pair should have thrown an exception");
      }
      catch (IllegalDataException e) {
        // do nothing
      } catch (Exception e) {
View Full Code Here
226
227
228
229
230
231
232
233
234
235
236
237
238
    // Manually construct illegal XML and make sure the outputter notices
    @Test
    public void test_ErrorSurrogatePairOutput() throws JDOMException, IOException {
      SAXBuilder builder = new SAXBuilder();
      builder.setExpandEntities(true);
      Document doc = builder.build(new StringReader("<?xml version=\"1.0\"?><root></root>"));
      Text t = new UncheckedJDOMFactory().text("\uD800\uDBFF");
      doc.getRootElement().setContent(t);
      Format format = Format.getCompactFormat().setEncoding("ISO-8859-1");
      XMLOutputter outputter = new XMLOutputter(format);
      ByteArrayOutputStream baos = new ByteArrayOutputStream();
      try {
        outputter.output(doc, baos);
View Full Code Here
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
    assertNotNull(out.toString());
  }
 
  @Test
  public void testCRNLEscaping() {
    Document doc = new Document();
    Element root = new Element("root");
    Element child1 = new Element("child1");
    Element child2 = new Element("child2");
    Text stuff = new Text("foo");
    root.addContent(child1);
    root.addContent(stuff);
    root.addContent(child2);
    doc.setRootElement(root);
    XMLOutputter xout = new XMLOutputter(Format.getPrettyFormat());
    String actual = xout.outputString(doc);
    String expect = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\r\n"
        + "<root>\r\n"
        + "  <child1 />\r\n"
View Full Code Here
584
585
586
587
588
589
590
591
592
593
594
        outputString(ftfw,     root));
  }
 
  @Test
  public void testDocumentSimple() {
    Document content = new Document();
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
        outputString(fraw,     content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
        outputString(fcompact, content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
View Full Code Here
599
600
601
602
603
604
605
606
607
608
609
610
        outputString(ftfw,     content));
  }
 
  @Test
  public void testDocumentDocType() {
    Document content = new Document();
    content.setDocType(new DocType("root"));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE root>\n",
        outputString(fraw,     content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE root>\n",
        outputString(fcompact, content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE root>\n",
View Full Code Here
615
616
617
618
619
620
621
622
623
624
625
626
        outputString(ftfw,     content));
  }
 
  @Test
  public void testDocumentComment() {
    Document content = new Document();
    content.addContent(new Comment("comment"));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!--comment-->\n",
        outputString(fraw,     content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!--comment-->\n",
        outputString(fcompact, content));
    assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!--comment-->\n",
View Full Code Here
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
    checkOutput(new DocType("root", "publicID", "systemID"), dec, dec, dec, dec, dec);
  }

  @Test
  public void testOutputDocumentSimple() {
    Document doc = new Document();
    doc.addContent(new Element("root"));
    String xmldec = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
    String rtdec = "<root />";
    checkOutput(doc,
        xmldec + "\n" + rtdec + "\n",
        xmldec + "\n" + rtdec + "\n",
View Full Code Here
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
        xmldec + "\n" + rtdec + "\n");
  }

  @Test
  public void testOutputDocumentOmitEncoding() {
    Document doc = new Document();
    doc.addContent(new Element("root"));
    String xmldec = "<?xml version=\"1.0\"?>";
    FormatSetup setup = new FormatSetup() {
      @Override
      public void setup(Format fmt) {
        fmt.setOmitEncoding(true);
View Full Code Here
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
        xmldec + "\n" + rtdec + "\n");
  }

  @Test
  public void testOutputDocumentOmitDeclaration() {
    Document doc = new Document();
    doc.addContent(new Element("root"));
    FormatSetup setup = new FormatSetup() {
      @Override
      public void setup(Format fmt) {
        fmt.setOmitDeclaration(true);
      }
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.pipeline.CoreNLPProtos$Document

  • ca.uhn.fhir.model.dstu.composite.ResourceReferenceDt
  • ca.uhn.fhir.model.primitive.StringDt
  • ch.rotscher.maven.plugins.InstallWithVersionOverrideMojo
  • classes.GeometricRecognizer
  • com.atlassian.maven.plugins.jgitflow.helper.DefaultProjectHelper
  • com.atlassian.maven.plugins.jgitflow.manager.AbstractFlowReleaseManager
  • com.cisco.oss.foundation.logging.FoundationLogger
  • com.cisco.oss.foundation.logging.structured.AbstractFoundationLoggingMarker
  • com.danhaywood.isis.wicket.gmap3.service.LocationLookupService
  • com.jakehorsfield.platformer.objects.tiles.TileGrid
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.