org.apache.solr.util.TestHarness Java Examples

@Test
public void testTermVecMultiValuedHighlight2() throws Exception {

  // do summarization using term vectors on multivalued field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_mv_text");
  args.put("hl.snippets", "2");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "",0,200,args);

  String shortText = "short";
  assertU(adoc("tv_mv_text", shortText,
               "tv_mv_text", LONG_TEXT,
               "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("tv_mv_text:long"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='tv_mv_text']/str[.='a <em>long</em> days night this should be a piece of text which']",
          "//arr[@name='tv_mv_text']/str[.=' <em>long</em> fragments.']"
          );
}
 

@Test
public void testMultiValueAnalysisHighlight() {

  // do summarization using re-analysis of the field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "textgap");
  args.put("df", "textgap");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("textgap", "first entry hasnt queryword",
      "textgap", "second entry has queryword long",
      "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("long"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='textgap']/str"
          );

}
 

@Test
public void testMultiValueBestFragmentHighlight() {
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "textgap");
  args.put("df", "textgap");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
      "", 0, 200, args);
  
  assertU(adoc("textgap", "first entry has one word foo", 
      "textgap", "second entry has both words foo bar",
      "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Best fragment summarization",
      sumLRF.makeRequest("foo bar"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1']/arr[@name='textgap']/str[.=\'second entry has both words <em>foo</em> <em>bar</em>\']"
  );
}
 

@Test
public void testDefaultFieldHighlight() {

  // do summarization using re-analysis of the field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("df", "t_text");
  args.put("hl.fl", "");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
      sumLRF.makeRequest("long"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1']/arr[@name='t_text']/str"
  );

}
 

@Test
public void testHighlightDisabled() {

  // ensure highlighting can be explicitly disabled
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "false");
  args.put("hl.fl", "t_text");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("t_text:long"), "not(//lst[@name='highlighting'])");

}
 

@Test
public void testTwoFieldHighlight() {

  // do summarization using re-analysis of the field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "t_text tv_text");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long day's night", "id", "1",
               "tv_text", "a long night's day"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("t_text:long"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='t_text']/str",
          "//lst[@name='1']/arr[@name='tv_text']/str"
          );
}
 

@Test
public void testTermVecHighlight() {

  // do summarization using term vectors
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_text");
  args.put("hl.snippets", "2");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "",0,200,args);
  
  assertU(adoc("tv_text", LONG_TEXT, 
               "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("tv_text:long"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='tv_text']/str[.='a <em>long</em> days night this should be a piece of text which']",
          "//arr[@name='tv_text']/str[.=' <em>long</em> fragments.']"
          );
}
 

@Test
public void testLongFragment() {

  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_text");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  

  String text = 
    "junit: [mkdir] Created dir: /home/klaas/worio/backend/trunk/build-src/solr-nightly/build/test-results [junit] Running org.apache.solr.BasicFunctionalityTest [junit] Tests run: 7, Failures: 0, Errors: 0, Time elapsed: 5.36 sec [junit] Running org.apache.solr.ConvertedLegacyTest [junit] Tests run: 1, Failures: 0, Errors: 0, Time elapsed: 8.268 sec [junit] Running org.apache.solr.DisMaxRequestHandlerTest [junit] Tests run: 1, Failures: 0, Errors: 0, Time elapsed: 1.56 sec [junit] Running org.apache.solr.HighlighterTest [junit] Tests run: 7, Failures: 0, Errors: 0, Time elapsed: 4.979 sec [junit] Running org.apache.solr.OutputWriterTest [junit] Tests run: 2, Failures: 0, Errors: 0, Time elapsed: 0.797 sec [junit] Running org.apache.solr.SampleTest [junit] Tests run: 2, Failures: 0, Errors: 0, Time elapsed: 1.021 sec [junit] Running org.apache.solr.analysis.TestBufferedTokenStream [junit] Tests run: 2, Failures: 0, Errors: 0, Time elapsed: 0.05 sec [junit] Running org.apache.solr.analysis.TestRemoveDuplicatesTokenFilter [junit] Tests run: 3, Failures: 0, Errors: 0, Time elapsed: 0.054 sec [junit] Running org.apache.solr.analysis.TestSynonymFilter [junit] Tests run: 6, Failures: 0, Errors: 0, Time elapsed: 0.081 sec [junit] Running org.apache.solr.analysis.TestWordDelimiterFilter [junit] Tests run: 1, Failures: 0, Errors: 0, Time elapsed: 1.714 sec [junit] Running org.apache.solr.search.TestDocSet [junit] Tests run: 1, Failures: 0, Errors: 0, Time elapsed: 0.788 sec [junit] Running org.apache.solr.util.SolrPluginUtilsTest [junit] Tests run: 5, Failures: 0, Errors: 0, Time elapsed: 3.519 sec [junit] Running org.apache.solr.util.TestOpenBitSet [junit] Tests run: 2, Failures: 0, Errors: 0, Time elapsed: 0.533 sec";
  assertU(adoc("tv_text", text, "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("tv_text:dir"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='tv_text']/str"
          );
}
 

@Test
public void testTermVectorWithoutOffsetsHighlight() {

  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_no_off_text");

  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory("", 0, 200, args);

  assertU(adoc("tv_no_off_text", "Crackerjack Cameron", "id", "1"));
  assertU(commit());
  assertU(optimize());

  assertQ("Fields with term vectors switched on but no offsets should be correctly highlighted",
          sumLRF.makeRequest("tv_no_off_text:cameron"),
          "//arr[@name='tv_no_off_text']/str[.='Crackerjack <em>Cameron</em>']");

}
 

public void testCatchAllCopyField() throws Exception {
  deleteCore();
  initCore("solrconfig.xml", "schema-copyfield-test.xml");
  
  IndexSchema schema = h.getCore().getLatestSchema();
  
  assertNull("'*' should not be (or match) a dynamic field", schema.getDynamicPattern("*"));
  
  boolean foundCatchAllCopyField = false;
  for (IndexSchema.DynamicCopy dcf : schema.getDynamicCopyFields()) {
    foundCatchAllCopyField = dcf.getRegex().equals("*") && dcf.getDestFieldName().equals("catchall_t");
    if (foundCatchAllCopyField) {
      break;
    }
  }
  assertTrue("<copyField source=\"*\" dest=\"catchall_t\"/> is missing from the schema", foundCatchAllCopyField);

  SolrQueryRequest req = req("qt", "/admin/luke", "show", "schema", "indent", "on");
  String xml = h.query(req);
  String result = TestHarness.validateXPath(xml, field("bday") + "/arr[@name='copyDests']/str[.='catchall_t']");
  assertNull(xml, result);

  // Put back the configuration expected by the rest of the tests in this suite
  deleteCore();
  initCore("solrconfig.xml", "schema12.xml");
}
 

@Test
public void testDefaultFieldPrefixWildcardHighlight() {

  // do summarization using re-analysis of the field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("df", "t_text");
  args.put("hl.fl", "");
  args.put("hl.usePhraseHighlighter", "true");
  args.put("hl.highlightMultiTerm", "true");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("lon*"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='t_text']/str"
          );

}
 

/**
 * Pass "null" for the client to query to the local server.
 * Fetches response in xml format and matches with the given set of xpaths
 */
public static void assertQ(SolrClient client, SolrParams args, String... tests) throws Exception {
  String resp;
  resp = getQueryResponse(client, "xml", args);
  try {
    String results = TestHarness.validateXPath(resp, tests);
    if (null != results) {
      String msg = "REQUEST FAILED: xpath=" + results
          + "\n\txml response was: " + resp
          + "\n\tparams were:" + args.toQueryString();

      log.error(msg);
      throw new RuntimeException(msg);
    }
  } catch (XPathExpressionException e1) {
    throw new RuntimeException("XPath is invalid", e1);
  } catch (Exception e2) {
    SolrException.log(log,"REQUEST FAILED for params: " + args.toQueryString(), e2);
    throw new RuntimeException("Exception during query", e2);
  }
}
 

@Test
public void testDefaultFieldNonPrefixWildcardHighlight() {

  // do summarization using re-analysis of the field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("df", "t_text");
  args.put("hl.fl", "");
  args.put("hl.usePhraseHighlighter", "true");
  args.put("hl.highlightMultiTerm", "true");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("l*g"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='t_text']/str"
          );

}
 

public void testConfig()
{
        SolrHighlighter highlighter = HighlightComponent.getHighlighter(h.getCore());
  log.info( "highlighter" );

  assertTrue( highlighter instanceof DummyHighlighter );

  // check to see that doHighlight is called from the DummyHighlighter
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("df", "t_text");
  args.put("hl.fl", "");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);

  assertU(adoc("t_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("long"),
          "//lst[@name='highlighting']/str[@name='dummy']"
          );
  }
 

@Test
public void test() {
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_text");
  args.put("hl.snippets", "2");
  args.put("hl.tag.pre", "<fvpre>"); //... and let post default to </em>. This is just a test.
  if (random().nextBoolean()) {
    args.put("hl.useFastVectorHighlighter", "true"); // old way
  } else {
    args.put("hl.method", "fastVector"); // the new way
  }
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "",0,200,args);
  
  assertU(adoc("tv_text", "basic fast vector highlighter test", 
               "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("tv_text:vector"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='tv_text']/str[.='basic fast <fvpre>vector</em> highlighter test']"
          );
}
 

public void testScoreChanges() throws Exception {
  assertU(adoc(
      "id", "1",
      "str_field", "foo",
      RANK_1, "1"
      ));
  assertU(commit());
  ModifiableSolrParams params = params("q", "foo",
      "defType", "dismax",
      "qf", "str_field^10",
      "fl", "id,score",
      "wt", "xml");
  
  double scoreBefore = (Double) TestHarness.evaluateXPath(h.query(req(params)), "//result/doc[1]/float[@name='score']", XPathConstants.NUMBER);
  params.add("bq", "{!rank f='" + RANK_1 + "' function='log' scalingFactor='1'}");
  double scoreAfter = (Double) TestHarness.evaluateXPath(h.query(req(params)), "//result/doc[1]/float[@name='score']", XPathConstants.NUMBER);
  assertNotEquals("Expecting score to change", scoreBefore, scoreAfter, 0f);

}
 

@Test
public void testTermVecMultiValuedHighlight() throws Exception {

  // do summarization using term vectors on multivalued field
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_mv_text");
  args.put("hl.snippets", "2");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "",0,200,args);
  
  assertU(adoc("tv_mv_text", LONG_TEXT, 
               "tv_mv_text", LONG_TEXT, 
               "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
          sumLRF.makeRequest("tv_mv_text:long"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[@name='tv_mv_text']/str[.='a <em>long</em> days night this should be a piece of text which']",
          "//arr[@name='tv_mv_text']/str[.=' <em>long</em> fragments.']"
          );
}
 

private static void withNewRawReader(TestHarness h, DirectoryReaderConsumer consumer) {
  try (SolrCore core = h.getCoreInc()) {
    final RefCounted<SolrIndexSearcher> searcherRef = core.openNewSearcher(true, true);
    final SolrIndexSearcher searcher = searcherRef.get();
    try {
      try {
        consumer.accept(searcher.getRawReader());
      } catch (Exception e) {
        fail(e.toString());
      }
    } finally {
      searcherRef.decref();
    }
  }
}
 

public void testCopyFieldLists() throws Exception {
  SolrQueryRequest req = req("qt", "/admin/luke", "show", "schema");

  String xml = h.query(req);
  String r = TestHarness.validateXPath
    (xml,
     field("text") + "/arr[@name='copySources']/str[.='title']",
     field("text") + "/arr[@name='copySources']/str[.='subject']",
     field("title") + "/arr[@name='copyDests']/str[.='text']",
     field("title") + "/arr[@name='copyDests']/str[.='title_stemmed']",
     dynfield("bar_copydest_*") + "/arr[@name='copySources']/str[.='foo_copysource_*']",
     dynfield("foo_copysource_*") + "/arr[@name='copyDests']/str[.='bar_copydest_*']");
  assertEquals(xml, null, r);
}
 

private static void implUpdateSchemaField(TestHarness h, String fieldName, IntUnaryOperator propertiesModifier) {
  try (SolrCore core = h.getCoreInc()) {

    // Add docvalues to the field type
    IndexSchema schema = core.getLatestSchema();
    SchemaField oldSchemaField = schema.getField(fieldName);
    SchemaField newSchemaField = new SchemaField(
        fieldName,
        oldSchemaField.getType(),
        propertiesModifier.applyAsInt(oldSchemaField.getProperties()),
        oldSchemaField.getDefaultValue());
    schema.getFields().put(fieldName, newSchemaField);
  }
}
 

/**
 * @deprecated as testHarness is used
 * Creates a Solr Alfresco test harness.
 * @param schema
 * @throws Exception
 */
@Deprecated
public static void initAlfrescoCore(String schema) throws Exception
{

    LOG.info("##################################### init Alfresco core ##############");
    LOG.info("####initCore");
    System.setProperty("solr.solr.home", TEST_FILES_LOCATION);
    System.setProperty("solr.directoryFactory","solr.RAMDirectoryFactory");
    System.setProperty("solr.tests.maxBufferedDocs", "1000");
    System.setProperty("solr.tests.maxIndexingThreads", "10");
    System.setProperty("solr.tests.ramBufferSizeMB", "1024");
    // other  methods like starting a jetty instance need these too
    System.setProperty("solr.test.sys.prop1", "propone");
    System.setProperty("solr.test.sys.prop2", "proptwo");
    System.setProperty("alfresco.test", "true");
    System.setProperty("solr.tests.mergeScheduler", "org.apache.lucene.index.ConcurrentMergeScheduler");
    System.setProperty("solr.tests.mergePolicy", "org.apache.lucene.index.TieredMergePolicy");

    if (CORE_NOT_YET_CREATED)
    {

        testExecutionSolrHome = TEST_EXECUTION_FOLDER + "/" + Time.now() + "/solrhome";
        testSolrCollection = testExecutionSolrHome + "/collection1";
        testSolrConf = testSolrCollection + "/conf/";
        templateConf = testExecutionSolrHome + "/templates/%s/conf/";

        copyTestFiles();
        createAlfrescoCore(schema);
    }
    LOG.info("####initCore end");



    admin = of(h).map(TestHarness::getCoreContainer)
                .map(CoreContainer::getMultiCoreHandler)
                .map(AlfrescoCoreAdminHandler.class::cast)
                .orElseThrow(RuntimeException::new);
}
 

@Test
public void testDisMaxHighlight() {

  // same test run through dismax handler
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "tv_text");
  args.put("qf", "tv_text");
  args.put("q.alt", "*:*");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "/dismax",0,200,args);
  
  assertU(adoc("tv_text", "a long day's night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
      sumLRF.makeRequest("long"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1']/arr[@name='tv_text']/str"
  );
  
  // try the same thing without a q param
  assertQ("Should not explode...", // q.alt should return everything
      sumLRF.makeRequest( new String[] { null } ), // empty query
      "//result[@numFound='1']"
      );
}
 

@Test
public void testCustomSimpleFormatterHighlight() {

  // do summarization using a custom formatter
  HashMap<String,String> args = new HashMap<>();
  args.put("hl", "true");
  args.put("hl.fl", "t_text");
  args.put("hl.simple.pre","<B>");
  args.put("hl.simple.post", "</B>");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  assertU(adoc("t_text", "a long days night", "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("Basic summarization",
      sumLRF.makeRequest("t_text:long"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1']/arr[@name='t_text']/str[.='a <B>long</B> days night']"
  );
  
  // test a per-field override
  args.put("f.t_text.hl.simple.pre", "<I>");
  args.put("f.t_text.hl.simple.post", "</I>");
  sumLRF = h.getRequestFactory(
        "", 0, 200, args);
  assertQ("Basic summarization",
        sumLRF.makeRequest("t_text:long"),
        "//lst[@name='highlighting']/lst[@name='1']",
        "//lst[@name='1']/arr[@name='t_text']/str[.='a <I>long</I> days night']"
        );
  
}
 

@Test
public void testMaxChars() {
  HashMap<String,String> args = new HashMap<>();
  args.put("fl", "id score");
  args.put("hl", "true");
  args.put("hl.snippets", "10");
  final String field = random().nextBoolean() ? "t_text" : "tv_text";
  args.put("hl.fl", field);
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  

  assertU(adoc(field, LONG_TEXT, "id", "1"));
  assertU(commit());

  assertQ("token at start of text",
          sumLRF.makeRequest(field + ":disjoint"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//lst[@name='1']/arr[count(str)=1]"
          );
  args.put("hl.maxAnalyzedChars", "20");
  sumLRF = h.getRequestFactory("", 0, 200, args);
  assertQ("token at end of text",
      sumLRF.makeRequest(field + ":disjoint"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1'][not(*)]"
  );
  args.put("hl.maxAnalyzedChars", "-1");
  sumLRF = h.getRequestFactory("", 0, 200, args);
  assertQ("token at start of text",
      sumLRF.makeRequest(field + ":disjoint"),
      "//lst[@name='highlighting']/lst[@name='1']",
      "//lst[@name='1']/arr[count(str)=1]"
  );

}
 

@Test
public void testRegexFragmenter() {
  HashMap<String,String> args = new HashMap<>();
  args.put("fl", "id score");
  args.put("hl", "true");
  args.put("hl.snippets", "10");
  args.put("hl.fl", "t_text");
  args.put("hl.fragmenter", "regex");
  args.put("hl.regex.pattern", "[-\\w ,\"']{20,200}");
  args.put("hl.regex.slop", ".9");
  TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
    "", 0, 200, args);
  
  String t = "This is an example of a sentence. Another example \"sentence\" with " +
    "special characters\nand a line-break! Miscellaneous character like ^ are " +
    "unknowns and end up being bad example s of sentences? I wonder how " +
    "slashes/other punctuation fare in these examples?";
  assertU(adoc("t_text", t, "id", "1"));
  assertU(commit());
  assertU(optimize());
  assertQ("regex fragmenter",
          sumLRF.makeRequest("t_text:example"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//arr/str[.='This is an <em>example</em> of a sentence']",
          "//arr/str[.='. Another <em>example</em> \"sentence\" with special characters\nand a line-break']",
          "//arr/str[.=' ^ are unknowns and end up being bad <em>example</em> s of sentences']",
          "//arr/str[.='/other punctuation fare in these <em>examples</em>?']"
          );
  // try with some punctuation included
  args.put("hl.regex.pattern", "[-\\w ,^/\\n\"']{20,200}");
  sumLRF = h.getRequestFactory("", 0, 200, args);
  assertQ("regex fragmenter 2",
          sumLRF.makeRequest("t_text:example"),
          "//lst[@name='highlighting']/lst[@name='1']",
          "//arr/str[.='This is an <em>example</em> of a sentence']",
          "//arr/str[.='. Another <em>example</em> \"sentence\" with special characters\nand a line-break']",
          "//arr/str[.='! Miscellaneous character like ^ are unknowns and end up being bad <em>example</em> s of sentences']",
          "//arr/str[.='? I wonder how slashes/other punctuation fare in these <em>examples</em>?']"
          );
}
 

@Test
public void testVariableFragsize() {
   assertU(adoc("tv_text", "a long days night this should be a piece of text which is is is is is is is is is is is is is is is is is is is is is is is is isis is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is sufficiently lengthly to produce multiple fragments which are not concatenated at all", 
         "id", "1"));
   assertU(commit());
   assertU(optimize());

   // default length
   HashMap<String,String> args = new HashMap<>();
   args.put("hl", "true");
   args.put("hl.fl", "tv_text");
   TestHarness.LocalRequestFactory sumLRF = h.getRequestFactory(
     "", 0, 200, args);
   assertQ("Basic summarization",
         sumLRF.makeRequest("tv_text:long"),
         "//lst[@name='highlighting']/lst[@name='1']",
         "//lst[@name='1']/arr[@name='tv_text']/str[.='a <em>long</em> days night this should be a piece of text which']"
         );
   
   // 25
   args.put("hl.fragsize","25");
   sumLRF = h.getRequestFactory(
         "", 0, 200, args);
   assertQ("Basic summarization",
         sumLRF.makeRequest("tv_text:long"),
         "//lst[@name='highlighting']/lst[@name='1']",
         "//lst[@name='1']/arr[@name='tv_text']/str[.='a <em>long</em> days night']"
         );
   
   // 0 - NullFragmenter
   args.put("hl.fragsize","0");
   sumLRF = h.getRequestFactory(
         "", 0, 200, args);
   assertQ("Basic summarization",
         sumLRF.makeRequest("tv_text:long"),
         "//lst[@name='highlighting']/lst[@name='1']",
         "//lst[@name='1']/arr[@name='tv_text']/str[.='a <em>long</em> days night this should be a piece of text which is is is is is is is is is is is is is is is is is is is is is is is is isis is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is is sufficiently lengthly to produce multiple fragments which are not concatenated at all']"
         );
}
 

public void testCompressionModeDefault() throws IOException {
  assertEquals("Default Solr compression mode changed. Is this expected?", 
      SchemaCodecFactory.SOLR_DEFAULT_COMPRESSION_MODE, Mode.valueOf("BEST_SPEED"));

  String previousCoreName = h.coreName;
  String newCoreName = "core_with_default_compression";
  SolrCore c = null;
  
  SolrConfig config = TestHarness.createConfig(testSolrHome, previousCoreName, "solrconfig_codec2.xml");
  assertEquals("Unexpected codec factory for this test.", "solr.SchemaCodecFactory", config.get("codecFactory/@class"));
  assertNull("Unexpected configuration of codec factory for this test. Expecting empty element", 
      config.getNode("codecFactory", false).getFirstChild());
  IndexSchema schema = IndexSchemaFactory.buildIndexSchema("schema_codec.xml", config);

  CoreContainer coreContainer = h.getCoreContainer();
  
  try {
    CoreDescriptor cd = new CoreDescriptor(newCoreName, testSolrHome.resolve(newCoreName), coreContainer);
    c = new SolrCore(coreContainer, cd,
        new ConfigSet("fakeConfigset", config, schema, null, true));
    assertNull(coreContainer.registerCore(cd, c, false, false));
    h.coreName = newCoreName;
    assertEquals("We are not using the correct core", "solrconfig_codec2.xml", h.getCore().getConfigResource());
    assertU(add(doc("string_f", "foo")));
    assertU(commit());
    assertCompressionMode(SchemaCodecFactory.SOLR_DEFAULT_COMPRESSION_MODE.name(), h.getCore());
  } finally {
    h.coreName = previousCoreName;
    coreContainer.unload(newCoreName);
  }
  
}
 

public TestDataProvider(final TestHarness testHarness) throws Exception
{
    this.core = testHarness.getCore();
    dataModel.getNamespaceDAO().removePrefix("");
    dataModel.setCMDefaultUri();

    rootNodeRef = newNodeRef();
    addStoreRoot(core, dataModel, rootNodeRef, 1, 1, 1, 1);
}
 

@Test
public void testIndexHeapUsageBytes() throws Exception {
  try (SolrQueryRequest req = req("qt", "/admin/luke")) {
    String response = h.query(req);
    String xpath = "//long[@name='indexHeapUsageBytes']";
    Double num = (Double) TestHarness.evaluateXPath(response, xpath, XPathConstants.NUMBER);
    //with docs in the index, indexHeapUsageBytes should be greater than 0
    Assert.assertTrue("indexHeapUsageBytes should be > 0, but was " + num.intValue(), num.intValue() > 0);
  }
}
 

/**
 * Generates a simple <doc>... XML String with no options
 *
 * @param fieldsAndValues 0th and Even numbered args are fields names, Odds are field values.
 * @see TestHarness#makeSimpleDoc
 */
public static XmlDoc doc(String... fieldsAndValues)
{
    XmlDoc d = new XmlDoc();
    d.xml = TestHarness.makeSimpleDoc(fieldsAndValues);
    return d;
}