Examples of org.apache.solr.handler.extraction.ExtractingRequestHandler

Package org.apache.solr.handler.extraction

Examples of org.apache.solr.handler.extraction.ExtractingRequestHandler

org.apache.solr.handler.extraction.ExtractingRequestHandler
Handler for rich documents like PDF or Word or any other file format that Tika handles that need the text to be extracted first from the document.

    assertU(commit());
  }


  @Test
  public void testExtraction() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    loadLocal("solr-word.pdf",
            "fmap.created", "extractedDate",
            "fmap.producer", "extractedProducer",
            "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",

View Full Code Here

  }




  @Test
  public void testDefaultField() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    try {
      ignoreException("unknown field 'a'");
      ignoreException("unknown field 'meta'");  // TODO: should this exception be happening?
      loadLocal("simple.html",

View Full Code Here

    assertQ(req("+id:simple2 +t_href:[* TO *]"), "//*[@numFound='1']");
  }


  @Test
  public void testLiterals() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    //test literal
    loadLocal("version_control.xml", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
            "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",
            "fmap.Author", "extractedAuthor",

View Full Code Here


  }


  @Test
  public void testPlainTextSpecifyingMimeType() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);


    // Load plain text specifying MIME type:
    loadLocal("version_control.txt", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
            "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",

View Full Code Here

    assertQ(req("extractedContent:Apache"), "//*[@numFound='1']");
  }


  @Test
  public void testPlainTextSpecifyingResourceName() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);


    // Load plain text specifying filename
    loadLocal("version_control.txt", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
            "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",

View Full Code Here

  // Note: If you load a plain text file specifying neither MIME type nor filename, extraction will silently fail. This is because Tika's
  // automatic MIME type detection will fail, and it will default to using an empty-string-returning default parser


  @Test
  public void testExtractOnly() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    SolrQueryResponse rsp = loadLocal("solr-word.pdf", ExtractingParams.EXTRACT_ONLY, "true");
    assertTrue("rsp is null and it shouldn't be", rsp != null);
    NamedList list = rsp.getValues();

View Full Code Here


  }


  @Test
  public void testXPath() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    SolrQueryResponse rsp = loadLocal("example.html",
            ExtractingParams.XPATH_EXPRESSION, "/xhtml:html/xhtml:body/xhtml:a/descendant:node()",
            ExtractingParams.EXTRACT_ONLY, "true"
    );

View Full Code Here

  }


  /** test arabic PDF extraction is functional */
  @Test
  public void testArabicPDF() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) 
      h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);


    loadLocal("arabic.pdf", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
        "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",

View Full Code Here

    assertQ(req("wdf_nocase:السلم"), "//result[@numFound=1]");
  }


  @Test
  public void testTikaExceptionHandling() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) 
      h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);


    try{
      loadLocal("password-is-solrcell.docx",

View Full Code Here

    return "solrconfig.xml";
  }




  public void testExtraction() throws Exception {
    ExtractingRequestHandler handler = (ExtractingRequestHandler) h.getCore().getRequestHandler("/update/extract");
    assertTrue("handler is null and it shouldn't be", handler != null);
    loadLocal("solr-word.pdf", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
            "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",
            "fmap.Author", "extractedAuthor",
            "fmap.content", "extractedContent",

View Full Code Here

0 1

TOP

Related Classes of org.apache.solr.handler.extraction.ExtractingRequestHandler

org.apache.solr.common.util.NamedList

org.apache.solr.handler.ExtractingRequestHandlerTest

org.apache.solr.handler.extraction.ExtractingRequestHandlerTest

org.apache.tika.config.TikaConfig

java.io.File

org.apache.solr.common.SolrException

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.