diff --git a/webapp/config/example.deploy.properties b/webapp/config/example.deploy.properties index b0a40eb72..abb6f1ad2 100644 --- a/webapp/config/example.deploy.properties +++ b/webapp/config/example.deploy.properties @@ -33,7 +33,7 @@ webapp.name = vitro # # The location where the Vitro application will store the data that it creates. -# This includes uploaded files (usually images) and the Lucene search index. +# This includes uploaded files (usually images) and the search index. # vitro.home.directory = /usr/local/vitro/data diff --git a/webapp/config/web.xml b/webapp/config/web.xml index f31538b32..e6dab1f40 100644 --- a/webapp/config/web.xml +++ b/webapp/config/web.xml @@ -155,12 +155,6 @@ edu.cornell.mannlib.vitro.webapp.auth.policy.RootUserPolicy$Setup - - edu.cornell.mannlib.vitro.webapp.search.solr.SolrSetup @@ -874,12 +868,6 @@ /listObjectPropertyStatements - IndividualListController edu.cornell.mannlib.vitro.webapp.controller.freemarker.SolrIndividualListController @@ -889,12 +877,6 @@ /individuallist - IndividualListRdf edu.cornell.mannlib.vitro.webapp.controller.IndividualListRdfController @@ -904,12 +886,6 @@ /listrdf/* - SearchController edu.cornell.mannlib.vitro.webapp.search.controller.SolrPagedSearchController @@ -933,12 +909,6 @@ /searchcontroller - AutocompleteController edu.cornell.mannlib.vitro.webapp.search.controller.SolrAutocompleteController @@ -988,12 +958,6 @@ /contact - JSON Service edu.cornell.mannlib.vitro.webapp.controller.SolrJsonServlet diff --git a/webapp/lib/lucene-analyzers-2.9.3.jar b/webapp/lib/lucene-analyzers-2.9.3.jar deleted file mode 100644 index 05bb2d576..000000000 Binary files a/webapp/lib/lucene-analyzers-2.9.3.jar and /dev/null differ diff --git a/webapp/lib/lucene-core-2.9.3.jar b/webapp/lib/lucene-core-2.9.3.jar deleted file mode 100644 index 4351f976b..000000000 Binary files a/webapp/lib/lucene-core-2.9.3.jar and /dev/null differ diff --git a/webapp/lib/lucene-highlighter-2.9.3.jar b/webapp/lib/lucene-highlighter-2.9.3.jar deleted file mode 100644 index 1b9cce4ec..000000000 Binary files a/webapp/lib/lucene-highlighter-2.9.3.jar and /dev/null differ diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/SolrJsonServlet.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/SolrJsonServlet.java index eaa7c4844..a6cadfbd3 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/SolrJsonServlet.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/SolrJsonServlet.java @@ -271,9 +271,7 @@ public class SolrJsonServlet extends VitroHttpServlet { return map; } - - //Factoring out to allow for results to be processed from query for both lucene and solr - //Map given to process method includes the actual individuals returned from the search + // Map given to process method includes the actual individuals returned from the search public static JSONObject processVClassResults(Map map, VitroRequest vreq, ServletContext context, boolean multipleVclasses) throws Exception{ JSONObject rObj = DataGetterUtils.processVclassResultsJSON(map, vreq, multipleVclasses); return rObj; @@ -331,7 +329,7 @@ public class SolrJsonServlet extends VitroHttpServlet { .getAttribute("displayOntModel"); if (displayOntModel != null) { ProhibitedFromSearch pfs = new ProhibitedFromSearch( - DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); + DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); editConfig.setProhibitedFromSearch(pfs); } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/edit/CloneEntityServlet.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/edit/CloneEntityServlet.java index a55afe93c..429116d3f 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/edit/CloneEntityServlet.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/controller/edit/CloneEntityServlet.java @@ -102,8 +102,6 @@ public class CloneEntityServlet extends BaseEditController { propertyInstanceDao.insertProp(currPI); } - // addIndividualToLuceneIndex( context, cloneURI ); - String encodedCloneURI = URLEncoder.encode(cloneURI, "UTF-8"); response.sendRedirect("entityEdit?uri="+encodedCloneURI); //response.sendRedirect("entity?home="+portalIdStr+"&id="+newEntityId); diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/DisplayVocabulary.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/DisplayVocabulary.java index cab2a0508..01fd1c2f8 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/DisplayVocabulary.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/DisplayVocabulary.java @@ -26,7 +26,7 @@ public class DisplayVocabulary { private static final String NS = DISPLAY_NS; /* Individuals */ - public static final String PRIMARY_LUCENE_INDEX_URI = NS + "PrimaryLuceneIndex"; + public static final String PRIMARY_SEARCH_INDEX_URI = NS + "PrimarySearchIndex"; //bk392 for extracting properties beyond context nodes. public static final String CONTEXT_NODES_URI = NS + "QueryForContextNodes"; diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/jena/VClassGroupDaoJena.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/jena/VClassGroupDaoJena.java index 9538e7837..05d29bc87 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/jena/VClassGroupDaoJena.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/dao/jena/VClassGroupDaoJena.java @@ -320,7 +320,7 @@ public class VClassGroupDaoJena extends JenaBaseDao implements VClassGroupDao { public void removeClassesHiddenFromSearch(List groups) { OntModel displayOntModel = getOntModelSelector().getDisplayModel(); ProhibitedFromSearch pfs = new ProhibitedFromSearch( - DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); + DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); for (VClassGroup group : groups) { List classList = new ArrayList(); for (VClass vclass : group.getVitroClassList()) { diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/DefaultObjectPropertyFormGenerator.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/DefaultObjectPropertyFormGenerator.java index 9d78d2523..47c7978d1 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/DefaultObjectPropertyFormGenerator.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/DefaultObjectPropertyFormGenerator.java @@ -266,7 +266,7 @@ public class DefaultObjectPropertyFormGenerator implements EditConfigurationGene // .getAttribute("displayOntModel"); // if (displayOntModel != null) { // ProhibitedFromSearch pfs = new ProhibitedFromSearch( -// DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); +// DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); // if( editConfiguration != null ) // editConfiguration.setProhibitedFromSearch(pfs); // } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/MenuEditingFormGenerator.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/MenuEditingFormGenerator.java index bc9bc3977..b47f8f097 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/MenuEditingFormGenerator.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/edit/n3editing/configuration/generators/MenuEditingFormGenerator.java @@ -476,7 +476,7 @@ public class MenuEditingFormGenerator implements EditConfigurationGenerator { .getAttribute("displayOntModel"); if (displayOntModel != null) { ProhibitedFromSearch pfs = new ProhibitedFromSearch( - DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); + DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); if( editConfiguration != null ) editConfiguration.setProhibitedFromSearch(pfs); } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/VitroSearchTermNames.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/VitroSearchTermNames.java index 7ccfb8b4d..f35586b77 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/VitroSearchTermNames.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/VitroSearchTermNames.java @@ -5,7 +5,7 @@ package edu.cornell.mannlib.vitro.webapp.search; public class VitroSearchTermNames { /** Id of entity, vclass or tab */ public static String URI = "URI"; - /** lucene document id */ + /** search document id */ public static String DOCID = "DocId"; /** java class of the object that the Doc represents. */ public static String JCLASS = "JCLASS"; diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/Searcher.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/Searcher.java deleted file mode 100755 index fdf5b716a..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/Searcher.java +++ /dev/null @@ -1,51 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.beans; - -import java.util.List; - -import edu.cornell.mannlib.vitro.webapp.search.SearchException; - -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroHighlighter; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQuery; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQueryFactory; - -/** - * This is used by the SearchController. Any search back end should - * implement this. - * - * Currently we use LuceneSearcher. It gets setup by LuceneSetup which - * is specified to run as a listener in the application's web.xml. - * - * @author bdc34 - * - * @ deprecated Use LuceneIndexFactory instead - */ -public interface Searcher { - - public VitroQueryFactory getQueryFactory(); - - /** - * return a list of object that are related to the query. - * The objects should be of type Entity or Tab, if not they - * will be ignored. - * @param query - * @return - * @throws SearchException - */ - public List search( VitroQuery query ) throws SearchException; - - /** - * The searcher may need to be used when making a highlighter. - * In Lucene the highlighter needs access to the index. - * @param q - * @return - */ - // public abstract VitroHighlighter getHighlighter(VitroQuery q); - - /** - * Used to close the searcher if the index that it was using gets - * deleted. - */ - public void close(); -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroHighlighter.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroHighlighter.java deleted file mode 100644 index 94817ded9..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroHighlighter.java +++ /dev/null @@ -1,134 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.beans; - -import java.io.IOException; -import java.io.Reader; -import java.io.StringReader; -import java.io.StringWriter; -import java.util.ArrayList; -import java.util.Iterator; -import java.util.List; - -import net.sf.jga.fn.UnaryFunctor; - -import org.apache.commons.logging.Log; -import org.apache.commons.logging.LogFactory; - -import edu.cornell.mannlib.vitro.webapp.beans.DataPropertyStatement; -import edu.cornell.mannlib.vitro.webapp.beans.Individual; -import edu.cornell.mannlib.vitro.webapp.beans.ObjectPropertyStatement; - -/** - * Interface for classes that highlight search results. - * All method must gracefully deal with null inputs. - * - * @author bdc34 - * - * @ deprecated there is no replacement - */ -public abstract class VitroHighlighter extends UnaryFunctor { - - private static final Log log = LogFactory.getLog(VitroHighlighter.class.getName()); - - public static String preTag = ""; - public static String postTag = ""; - - public abstract String highlight(String in ); - public abstract String getHighlightFragments(String in ); - - public String fn(String in){ - if( in == null || "".equals(in)) - return ""; - try{ - return highlight( in ); - }catch(Throwable th){ - return in; - } - } - - public void highlight(Individual ent){ - if( ent == null) - return; - - ent.setName( this.highlight(ent.getName())); - Iterator edIt = ent.getDataPropertyStatements().iterator(); - while (edIt.hasNext()) { - DataPropertyStatement dataPropertyStmt = (DataPropertyStatement)edIt.next(); - dataPropertyStmt.setData(this.highlight(dataPropertyStmt.getData())); - } - edIt = ent.getObjectPropertyStatements().iterator(); - /* works only if JSP doesn't escape the text - while (edIt.hasNext()) { - ObjectPropertyStatement objectPropertyStmt = (ObjectPropertyStatement)edIt.next(); - Individual object = objectPropertyStmt.getObject(); - object.setName(this.highlight(object.getName())); - } - */ - } - - /** - * Highlights the name and then replaces the description with - * highlighted fragments. - * @param ent - */ - public void fragmentHighlight(Individual ent){ - if( ent == null ) - return; - - //highlight the name, anchor and moniker and place back in entity object - if( ent.getName() != null ) - ent.setName( highlight( stripHtml(ent.getName() ))); - - //make a buffer of text to use the fragmenting hightlighter on - StringBuffer sb = new StringBuffer(""); - if(ent.getDataPropertyStatements() != null) { - Iterator edIt = ent.getDataPropertyStatements().iterator(); - while (edIt.hasNext()) { - sb.append(((DataPropertyStatement)edIt.next()).getData()); - sb.append(' '); - } - } - if(ent.getObjectPropertyStatements() != null) { - Iterator edIt = ent.getObjectPropertyStatements().iterator(); - while (edIt.hasNext()) { - String t; - try { - ObjectPropertyStatement stmt = (ObjectPropertyStatement) edIt.next(); - sb.append( ( (t = stmt.getProperty().getDomainPublic()) != null) ? t : "" ); - sb.append(' '); - sb.append( ( (t = stmt.getObject().getName()) != null) ? t : "" ); - sb.append(' '); - } catch (Exception e) { - log.info("Error highlighting object property statement for individual "+ent.getURI()); - } - } - } - } - - private final String stripHtml(String in){ - /* make a string with html stripped out */ - // ryounes 5/16/2011 Broken with upgrade to Solr 3.1: HTMLStripReader has been removed. - // According to change list, should use HTMLStripCharFilter, but it's not immediately clear how - // to migrate this code. Will enter Jira issue. -// Reader stripIn = new HTMLStripReader( new StringReader( in ) ); -// StringWriter stripOut = new StringWriter(in.length()); -// -// char bytes[] = new char[5000]; -// int bytesRead = 0; -// try { -// //this is a mess, there must be a better way to do this. -// while ( true ){ -// bytesRead = stripIn.read( bytes ); -// if( bytesRead == -1 ) break; -// stripOut.write(bytes, 0, bytesRead ); -// } -// } catch (IOException e1) { -// log.error("LuceneHighlighter.getHighlightFragments()" + -// " - unable to strip html" + e1); -// } -// return stripOut.toString(); - return in; - } -} - diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroQueryWrapper.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroQueryWrapper.java index 064118477..7507d37b5 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroQueryWrapper.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/beans/VitroQueryWrapper.java @@ -13,14 +13,12 @@ public class VitroQueryWrapper { private VitroQuery query = null; private int requestCount = 0; private long searchTime = 0; - private VitroHighlighter highlighter; - public VitroQueryWrapper(VitroQuery q, VitroHighlighter hi, int reqCount, long d){ + public VitroQueryWrapper(VitroQuery q, int reqCount, long d){ this.setSearchTime(d); this.setQuery(q); this.setRequestCount(reqCount); - this.highlighter = hi; } public long getSearchTime() { @@ -42,6 +40,4 @@ public class VitroQueryWrapper { this.requestCount = requestCount; } - public VitroHighlighter getHighlighter(){ return highlighter; } - } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/IndexController.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/IndexController.java index 4930b33a5..4924b558f 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/IndexController.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/IndexController.java @@ -24,8 +24,8 @@ import edu.cornell.mannlib.vitro.webapp.search.indexing.IndexBuilder; * * That IndexBuilder will be associated with a object that implements the IndexerIface. * - * An example of the IndexerIface is LuceneIndexer. - * An example of the IndexBuilder and LuceneIndexer getting setup is in LuceneSetup. + * An example of the IndexerIface is SolrIndexer. + * An example of the IndexBuilder and SolrIndexer setup is in SolrSetup. * * @author bdc34 */ diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/SolrPagedSearchController.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/SolrPagedSearchController.java index fe23dd67e..bebeb1441 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/SolrPagedSearchController.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/controller/SolrPagedSearchController.java @@ -47,7 +47,6 @@ import edu.cornell.mannlib.vitro.webapp.dao.VitroVocabulary; import edu.cornell.mannlib.vitro.webapp.search.IndexConstants; import edu.cornell.mannlib.vitro.webapp.search.SearchException; import edu.cornell.mannlib.vitro.webapp.search.VitroSearchTermNames; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroHighlighter; import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQuery; import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQueryFactory; import edu.cornell.mannlib.vitro.webapp.search.solr.SolrSetup; @@ -63,8 +62,6 @@ import freemarker.template.Configuration; * */ -// This will be renamed to PagedSearchController once everything is using Solr and we can -// delete the Lucene version. public class SolrPagedSearchController extends FreemarkerHttpServlet { private static final long serialVersionUID = 1L; @@ -615,10 +612,6 @@ public class SolrPagedSearchController extends FreemarkerHttpServlet { public static final int MAX_QUERY_LENGTH = 500; - public VitroHighlighter getHighlighter(VitroQuery q) { - throw new Error("PagedSearchController.getHighlighter() is unimplemented"); - } - public VitroQueryFactory getQueryFactory() { throw new Error("PagedSearchController.getQueryFactory() is unimplemented"); } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexBuilder.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexBuilder.java index 9deef835d..0e67fdf2a 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexBuilder.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexBuilder.java @@ -22,7 +22,7 @@ import edu.cornell.mannlib.vitro.webapp.dao.WebappDaoFactory; * The IndexBuilder is used to rebuild or update a search index. * There should only be one IndexBuilder in a vitro web application. * It uses an implementation of a back-end through an object that - * implements IndexerIface. An example of a back-end is LuceneIndexer. + * implements IndexerIface. An example of a back-end is SolrIndexer. * * See the class SearchReindexingListener for an example of how a model change * listener can use an IndexBuilder to keep the full text index in sncy with diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexerIface.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexerIface.java index 8c5ff126b..0fa5938bf 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexerIface.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/indexing/IndexerIface.java @@ -13,8 +13,8 @@ import edu.cornell.mannlib.vitro.webapp.search.docbuilder.Obj2DocIface; * IndexBuilder will manage getting lists of object to index and then use * an object that implements IndexerIface to stuff the backend index. * - * An example is LuceneIndexer which is set up and associated with a - * IndexBuilder in LuceneSetup. + * An example is SolrIndexer which is set up and associated with a + * IndexBuilder in SolrSetup. * * @author bdc34 * diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/CustomSimilarity.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/CustomSimilarity.java deleted file mode 100644 index 880fae449..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/CustomSimilarity.java +++ /dev/null @@ -1,65 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import org.apache.lucene.search.DefaultSimilarity; - -public class CustomSimilarity extends DefaultSimilarity { - - public CustomSimilarity(){} - - /** - * According to Lucene Javadoc, idf computes a score factor - * based on a term's document frequency (the number of documents - * that contain the term). - * - * idf = log(numDocs/(docFreq + 1)) - * - * From this formula we see that, the lower the value of docFreq - * higher the value of idf. In other words, rare terms have higher - * idf scores. - * - * Returning a value of 1.0f here for idf, since we wan't the - * rarity of a term not to effect the score of a document. - * - * bk392 3/29/2011 - */ - @Override - public float idf(int docFreq, int numDocs){ - return 1.0f; - } - - - /** - * Coord computes a score factor based on the fraction of all query terms - * that a document contains. The default implementation is - * - * coord = (overlap/ maxOverlap) - * - * overlap is the number of queryterms matched in the document and maxOverlap - * is the total number of terms present in the query. That means, more number of - * query terms matched in a document, higher the score. Here, we are returning a - * value of 1.0f to override this effect. - */ - @Override - public float coord(int overlap, int maxOverlap){ - return 1.0f; - } - - /** - * From Lucene Javadoc, lengthNorm computes the normalization value - * for a given field. These values together with the field boosts, are - * stored in an index and multiplied into scores for hits on each field by - * the search code. - * - * lengthNorm = 1 / sqrt(numTerms) - * - * In other words, the document score is inversely proportional to the number of terms - * contained in the field of interest. Higher the number, lower the doc score. We don't - * want this since most of our fields contain single value. (except ALLTEXT and type) - */ - @Override - public float lengthNorm(String fieldName, int numTerms){ - return 1.0f; - } -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/Entity2LuceneDoc.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/Entity2LuceneDoc.java deleted file mode 100644 index 3bc34697d..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/Entity2LuceneDoc.java +++ /dev/null @@ -1,375 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import java.util.HashMap; -import java.util.HashSet; -import java.util.Iterator; -import java.util.List; - -import org.apache.commons.logging.Log; -import org.apache.commons.logging.LogFactory; -import org.apache.lucene.document.Document; -import org.apache.lucene.document.Field; -import org.apache.lucene.index.Term; -import org.joda.time.DateTime; - -import com.hp.hpl.jena.vocabulary.OWL; - -import edu.cornell.mannlib.vitro.webapp.beans.DataPropertyStatement; -import edu.cornell.mannlib.vitro.webapp.beans.Individual; -import edu.cornell.mannlib.vitro.webapp.beans.IndividualImpl; -import edu.cornell.mannlib.vitro.webapp.beans.ObjectPropertyStatement; -import edu.cornell.mannlib.vitro.webapp.beans.VClass; -import edu.cornell.mannlib.vitro.webapp.dao.VitroVocabulary; -import edu.cornell.mannlib.vitro.webapp.search.IndexingException; - -import edu.cornell.mannlib.vitro.webapp.search.beans.IndividualProhibitedFromSearch; -import edu.cornell.mannlib.vitro.webapp.search.beans.ProhibitedFromSearch; -import edu.cornell.mannlib.vitro.webapp.search.docbuilder.Obj2DocIface; - -/** - * This class expect that Entities passed to it will have - * a VClass object and a list of keywords. The entity should - * be as full as possible. - */ -public class Entity2LuceneDoc implements Obj2DocIface{ - - /** These are the terms for the lucene index */ - public static class VitroLuceneTermNames{ - /** Id of entity, vclass or tab */ - public static String URI = "URI"; - /** lucene document id */ - public static String DOCID = "DocId"; - /** java class of the object that the Doc represents. */ - public static String JCLASS = "JCLASS"; - /** rdf:type */ - public static String RDFTYPE = "type"; - /** rdf:type */ - public static String CLASSGROUP_URI = "classgroup"; - /** Modtime from db */ - public static String MODTIME = "modTime"; - - /** time of index in msec since epoc */ - public static String INDEXEDTIME= "indexedTime"; - /** text for 'full text' search, this is stemmed */ - public static String ALLTEXT = "ALLTEXT"; - /** text for 'full text' search, this is unstemmed for - * use with wildcards and prefix queries */ - public static String ALLTEXTUNSTEMMED = "ALLTEXTUNSTEMMED"; - /** class name for storing context nodes **/ - public static final String CONTEXTNODE = "contextNode"; - /** Does the individual have a thumbnail image? 1=yes 0=no */ - public static final String THUMBNAIL = "THUMBNAIL"; - /** Should individual be included in full text search results? 1=yes 0=no */ - public static final String PROHIBITED_FROM_TEXT_RESULTS = "PROHIBITED_FROM_TEXT_RESULTS"; - /** class names in human readable form of an individual*/ - public static final String CLASSLOCALNAMELOWERCASE = "classLocalNameLowerCase"; - /** class names in human readable form of an individual*/ - public static final String CLASSLOCALNAME = "classLocalName"; - - // Fields derived from rdfs:label - /** Raw rdfs:label: no lowercasing, no tokenizing, no stop words, no stemming. - * Used only in retrieval rather than search. **/ - public static String NAME_RAW = "nameRaw"; // was NAMERAW - - /** rdfs:label lowercased, no tokenizing, no stop words, no stemming **/ - public static String NAME_LOWERCASE = "nameLowercase"; // was NAMELOWERCASE - - /** Same as NAME_LOWERCASE, but single-valued so it's sortable. **/ - // RY Need to control how indexing selects which of multiple values to copy. - public static String NAME_LOWERCASE_SINGLE_VALUED = "nameLowercaseSingleValued"; - - /** rdfs:label lowercased, tokenized, stop words, no stemming. - * Used for autocomplete matching on proper names. **/ - public static String NAME_UNSTEMMED = "nameUnstemmed"; // was NAMEUNSTEMMED - - /** rdfs:label lowercased, tokenized, stop words, stemmed. - * Used for autocomplete matching where stemming is desired (e.g., book titles) **/ - public static String NAME_STEMMED = "nameStemmed"; // was NAME - - } - - private static final Log log = LogFactory.getLog(Entity2LuceneDoc.class.getName()); - - public static String earliestTime = "16000101"; - public static String latestTime = "30000101"; - - /** a way to get to the term names for the lucene index */ - public static VitroLuceneTermNames term = new VitroLuceneTermNames(); - - private static String entClassName = Individual.class.getName(); - - private ProhibitedFromSearch classesProhibitedFromSearch; - - private IndividualProhibitedFromSearch individualProhibited; - - private static HashMap IndividualURIToObjectProperties = new HashMap(); - - private static HashSet objectProperties = new HashSet(); - - public Entity2LuceneDoc( - ProhibitedFromSearch classesProhibitedFromSearch, - IndividualProhibitedFromSearch individualProhibited){ - this.classesProhibitedFromSearch = classesProhibitedFromSearch; - this.individualProhibited = individualProhibited; - } - - public boolean canTranslate(Object obj) { - return (obj != null && obj instanceof Individual); - } - - @SuppressWarnings("static-access") - public Object translate(Object obj) throws IndexingException { - if(!( obj instanceof Individual)) - return null; - Individual ent = (Individual)obj; - String value; - Document doc = new Document(); - String classPublicNames = ""; - - //DocId - String id = ent.getURI(); - log.debug("translating " + id); - - if( id == null ){ - log.debug("cannot add individuals without URIs to lucene index"); - return null; - }else if( id.startsWith( VitroVocabulary.vitroURI ) - || id.startsWith( VitroVocabulary.VITRO_PUBLIC ) - || id.startsWith( VitroVocabulary.PSEUDO_BNODE_NS) - || id.startsWith( OWL.NS ) ){ - log.debug("not indxing because of namespace:" + id ); - return null; - } - - //filter out class groups, owl:ObjectProperties etc. - if( individualProhibited.isIndividualProhibited( id ) ){ - return null; - } - - /* Types and ClassGroup */ - boolean prohibited = false; - List vclasses = ent.getVClasses(false); - for( VClass clz : vclasses){ - if( clz.getURI() == null ){ - continue; - }else if( OWL.Thing.getURI().equals( clz.getURI()) ){ - //index individuals of type owl:Thing, just don't add owl:Thing the type field in the index - continue; - } else if ( clz.getURI().startsWith( OWL.NS ) ){ - log.debug("not indexing " + id + " because of type " + clz.getURI()); - return null; - }else{ - if( !prohibited && classesProhibitedFromSearch.isClassProhibitedFromSearch(clz.getURI()) ) - prohibited = true; - - if( clz.getSearchBoost() != null ) - doc.setBoost( doc.getBoost() + clz.getSearchBoost() ); - - Field typeField = new Field (term.RDFTYPE, clz.getURI(), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS); - doc.add( typeField); - - if(clz.getLocalName() != null){ - Field classLocalName = new Field(term.CLASSLOCALNAME, clz.getLocalName(), Field.Store.YES, Field.Index.ANALYZED); - Field classLocalNameLowerCase = new Field(term.CLASSLOCALNAMELOWERCASE, clz.getLocalName().toLowerCase(), Field.Store.YES, Field.Index.ANALYZED); - doc.add(classLocalName); - doc.add(classLocalNameLowerCase); - } - - if( clz.getName() != null ) - classPublicNames = classPublicNames + " " + clz.getName(); - - //Classgroup URI - if( clz.getGroupURI() != null ){ - Field classGroupField = new Field(term.CLASSGROUP_URI, clz.getGroupURI(), - Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS); - // classGroupField.setBoost(FIELD_BOOST); - doc.add(classGroupField); - } - } - } - doc.add( new Field(term.PROHIBITED_FROM_TEXT_RESULTS, prohibited?"1":"0", - Field.Store.NO,Field.Index.NOT_ANALYZED_NO_NORMS) ); - - /* lucene DOCID */ - doc.add( new Field(term.DOCID, entClassName + id, - Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - - - //vitro Id - doc.add( new Field(term.URI, id, Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - - - //java class - doc.add( new Field(term.JCLASS, entClassName, Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - - // Individual label - if( ent.getRdfsLabel() != null ) - value=ent.getRdfsLabel(); - else{ - //log.debug("Skipping individual without rdfs:label " + ent.getURI()); - //return null; - log.debug("Using local name for individual with rdfs:label " + ent.getURI()); - value = ent.getLocalName(); - } - Field nameRaw = new Field(term.NAME_RAW, value, Field.Store.YES, Field.Index.NOT_ANALYZED); - nameRaw.setBoost(NAME_BOOST); - doc.add(nameRaw); - - // RY Not sure if we need to store this. For Solr, see schema.xml field definition. - Field nameLowerCase = new Field(term.NAME_LOWERCASE, value.toLowerCase(), Field.Store.YES, Field.Index.NOT_ANALYZED); - nameLowerCase.setBoost(NAME_BOOST); - doc.add(nameLowerCase); - - Field nameUnstemmed = new Field(term.NAME_UNSTEMMED, value, Field.Store.NO, Field.Index.ANALYZED); - nameUnstemmed.setBoost(NAME_BOOST); - doc.add(nameUnstemmed); - - Field nameStemmed = new Field(term.NAME_STEMMED, value, Field.Store.NO, Field.Index.ANALYZED); - nameStemmed.setBoost(NAME_BOOST); - doc.add(nameStemmed); - - String contextNodePropertyValues; - -// if(ent.isVClass("http://xmlns.com/foaf/0.1/Person")){ - /*contextNodePropertyValues = searchQueryHandler.getPropertiesAssociatedWithEducationalTraining(ent.getURI()); - contextNodePropertyValues += searchQueryHandler.getPropertiesAssociatedWithRole(ent.getURI()); - contextNodePropertyValues += searchQueryHandler.getPropertiesAssociatedWithPosition(ent.getURI()); - contextNodePropertyValues += searchQueryHandler.getPropertiesAssociatedWithRelationship(ent.getURI()); - contextNodePropertyValues += searchQueryHandler.getPropertiesAssociatedWithAwardReceipt(ent.getURI()); - contextNodePropertyValues += searchQueryHandler.getPropertiesAssociatedWithInformationResource(ent.getURI()); */ - -// } - - /* Field contextNodeInformation = new Field(term.CONTEXTNODE, contextNodePropertyValues, Field.Store.YES, Field.Index.ANALYZED ); - doc.add(contextNodeInformation);*/ - - //boost for entity - if( ent.getSearchBoost() != null && ent.getSearchBoost() != 0 ) - doc.setBoost(ent.getSearchBoost()); - - //Modification time -// if( ent.getModTime() != null){ -// value = (new DateTime(ent.getModTime().getTime())) -// .toString(LuceneIndexer.MODTIME_DATE_FORMAT) ; -// } else { -// value= (new DateTime()).toString(LuceneIndexer.MODTIME_DATE_FORMAT) ; -// } -// doc.add( new Field(term.MODTIME, value , Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - - /* thumbnail */ - try{ - value = null; - if( ent.hasThumb() ) - doc.add(new Field(term.THUMBNAIL, "1", Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - else - doc.add(new Field(term.THUMBNAIL, "0", Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - }catch(Exception ex){ - log.debug("could not index thumbnail: " + ex); - } - - - //time of index in millis past epoc - Object anon[] = { new Long((new DateTime() ).getMillis()) }; - doc.add( new Field(term.INDEXEDTIME, String.format( "%019d", anon ), - Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS)); - - - if( ! prohibited ){ - //ALLTEXT, all of the 'full text' - String t=null; - value =""; - value+= " "+( ((t=ent.getName()) == null)?"":t ); - value+= " "+ getKeyterms(ent); - - value+= " " + classPublicNames; - - List dataPropertyStatements = ent.getDataPropertyStatements(); - if (dataPropertyStatements != null) { - Iterator dataPropertyStmtIter = dataPropertyStatements.iterator(); - while (dataPropertyStmtIter.hasNext()) { - DataPropertyStatement dataPropertyStmt = dataPropertyStmtIter.next(); - value+= " "+ ( ((t=dataPropertyStmt.getData()) == null)?"":t ); - } - } - - List objectPropertyStatements = ent.getObjectPropertyStatements(); - if (objectPropertyStatements != null) { - Iterator objectPropertyStmtIter = objectPropertyStatements.iterator(); - while (objectPropertyStmtIter.hasNext()) { - ObjectPropertyStatement objectPropertyStmt = objectPropertyStmtIter.next(); - if( "http://www.w3.org/2002/07/owl#differentFrom".equals(objectPropertyStmt.getPropertyURI()) ) - continue; - try { - value+= " "+ ( ((t=objectPropertyStmt.getObject().getName()) == null)?"":t ); - - if(ent.isVClass("http://xmlns.com/foaf/0.1/Person")){ - //IndividualURIToObjectProperties.put(ent.getURI(), ( ((t=objectPropertyStmt.getProperty().getURI()) == null)?"":t ) ); - objectProperties.add(( ((t=objectPropertyStmt.getProperty().getURI()) == null)?"":t )); - } - - } catch (Exception e) { - log.debug("could not index name of related object: " + e.getMessage()); - } - } - } - //stemmed terms - doc.add( new Field(term.ALLTEXT, value , Field.Store.NO, Field.Index.ANALYZED)); - //unstemmed terms - doc.add( new Field(term.ALLTEXTUNSTEMMED, value, Field.Store.NO, Field.Index.ANALYZED)); - } - - - // log.info("\n IndividualURItoObjectProperties " + IndividualURIToObjectProperties.toString() + " \n\n"); - log.info(" \n Object Properties " + objectProperties.toString() + "\n\n"); - - return doc; - } - - @SuppressWarnings("static-access") - public boolean canUnTranslate(Object result) { - if( result != null && result instanceof Document){ - Document hit = (Document) result; - if( entClassName.equalsIgnoreCase(hit.get(term.JCLASS)) ){ - return true; - } - } - return false; - } - - @SuppressWarnings("static-access") - public Object unTranslate(Object result) { - Individual ent = null; - if( result != null && result instanceof Document){ - Document hit = (Document) result; - String id = hit.get(term.URI); - ent = new IndividualImpl(); - ent.setURI(id); - } - return ent; - } - - @SuppressWarnings("static-access") - public Object getIndexId(Object obj) { - return new Term(term.DOCID, entClassName + ((Individual)obj).getURI() ) ; - } - - private String getKeyterms(Individual ent){ - /* bdc34: vitro:keywords are no longer being indexed */ - return ""; - } - - public ProhibitedFromSearch getClassesProhibitedFromSearch() { - return classesProhibitedFromSearch; - } - - public void setClassesProhibitedFromSearch( - ProhibitedFromSearch classesProhibitedFromSearch) { - this.classesProhibitedFromSearch = classesProhibitedFromSearch; - } - - public static float NAME_BOOST = 3.0F; - public static float MONIKER_BOOST = 2.0F; - public static float FIELD_BOOST = 1.0F; -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopAnalyzer.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopAnalyzer.java deleted file mode 100644 index e6a32bed7..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopAnalyzer.java +++ /dev/null @@ -1,121 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import java.io.Reader; -import java.util.Arrays; -import java.util.HashSet; -import java.util.List; -import java.util.Set; - -import org.apache.lucene.analysis.ASCIIFoldingFilter; -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.LowerCaseFilter; -import org.apache.lucene.analysis.StopFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.standard.StandardFilter; -import org.apache.lucene.analysis.standard.StandardTokenizer; -import org.apache.lucene.util.Version; - -public class HtmlLowerStopAnalyzer extends Analyzer { - /* much of this code is from - * http://www.onjava.com/pub/a/onjava/2003/01/15/lucene.html?page=2 - * bdc34 - */ - - private static Set _stopWords; - - /** - * An array containing some common English words - * that are usually not useful for searching. - */ - public static final String[] STOP_WORDS = - { - "0", "1", "2", "3", "4", "5", "6", "7", "8", - "9", "000", "$", - "about", "after", "all", "also", "an", "and", - "another", "any", "are", "as", "at", "be", - "because", "been", "before", "being", "between", - "both", "but", "by", "came", "can", "come", - "could", "did", "do", "does", "each", "else", - "for", "from", "get", "got", "has", "had", - "he", "have", "her", "here", "him", "himself", - "his", "how","if", "in", "into", "is", "it", - "its", "just", "like", "make", "many", "me", - "might", "more", "most", "much", "must", "my", - "never", "now", "of", "on", "only", "or", - "other", "our", "out", "over", "re", "said", - "same", "see", "should", "since", "so", "some", - "still", "such", "take", "than", "that", "the", - "their", "them", "then", "there", "these", - "they", "this", "those", "through", "to", "too", - "under", "up", "use", "very", "want", "was", - "way", "we", "well", "were", "what", "when", - "where", "which", "while", "who", "will", - "with", "would", "you", "your", - "a", "b", "c", "d", "e", "f", "g", "h", "i", - "j", "k", "l", "m", "n", "o", "p", "q", "r", - "s", "t", "u", "v", "w", "x", "y", "z" - }; - - public static final List stopWordsList = Arrays.asList(STOP_WORDS); - public static final Set STOP_WORDS_SET = new HashSet(stopWordsList); - - /** - * Builds an analyzer. - */ - public HtmlLowerStopAnalyzer() - { - this(STOP_WORDS_SET); - } - - /** - * Builds an analyzer with the given stop words. - * - * @param stopWords a String array of stop words - */ - public HtmlLowerStopAnalyzer(Set stopWords) - { - _stopWords = STOP_WORDS_SET; - } - - /** - * Processes the input by first converting it to - * lower case, then by eliminating stop words. - * - * @param reader the Reader that - * provides access to the input text - * @return an instance of TokenStream - */ - - public TokenStream tokenStream(String fieldName, Reader arg0) { - //ignore fieldName, tokenize all fields the same way. - - /* With this we are pipeing the output of the inner most - * Reader outwards. - * Input-> HtmlStrip-> LowerCase-> stopFilter-> StemFilter-> Output - */ -// TokenStream htmlStripAndLower = -// new LowerCaseTokenizer(arg0 ); -// -// -// boolean IGNORE_CASE = true; -// TokenFilter stopFilter = -// new StopFilter(htmlStripAndLower,STOP_WORDS , IGNORE_CASE) ; -// -// return stopFilter; -// - - TokenStream result = new StandardTokenizer(Version.LUCENE_29, arg0); - result = new StandardFilter(result); //break into tokens - result = new LowerCaseFilter(result); //lower case - result = new StopFilter(ENABLE_POSITION_INCREMENTS, result, STOP_WORDS_SET, IGNORE_CASE); //remove stop words - result = new ASCIIFoldingFilter(result); //this class converts alphabetic, symbolic and numerical characters into their ASCII equivalents. - return result; - - } - - private static final boolean IGNORE_CASE = true; - private static final boolean ENABLE_POSITION_INCREMENTS = false; - -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopStemAnalyzer.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopStemAnalyzer.java deleted file mode 100644 index 3abdfbecd..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/HtmlLowerStopStemAnalyzer.java +++ /dev/null @@ -1,47 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import java.io.Reader; -import java.util.Set; - -import org.apache.lucene.analysis.PorterStemFilter; -import org.apache.lucene.analysis.TokenStream; - -/** - * A Analyzer that strips html, lower cases, removes stops and - * then does porter stemming. - * - * @author bdc34 - * - */ -public class HtmlLowerStopStemAnalyzer extends HtmlLowerStopAnalyzer { - public HtmlLowerStopStemAnalyzer(){ - super(); - } - - public HtmlLowerStopStemAnalyzer(Set stopWords){ - super(stopWords); - } - - /** - * Processes the input by first converting it to - * lower case, then by eliminating stop words, and - * finally by performing Porter stemming on it. - * - * @param reader the Reader that - * provides access to the input text - * @return an instance of TokenStream - */ - - public TokenStream tokenStream(String fieldName, Reader arg0) { - //ignore fieldName, tokenize all fields the same way. - - /* With this we are pipeing the output of the inner most - * Reader outwards. - * Input-> HtmlStrip-> LowerCase-> stopFilter-> StemFilter-> Output - */ - return new PorterStemFilter(super.tokenStream(fieldName,arg0)); - } - -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQuery.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQuery.java deleted file mode 100644 index 230c7a2d7..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQuery.java +++ /dev/null @@ -1,123 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import javax.servlet.http.HttpServletRequest; - -import org.apache.commons.logging.Log; -import org.apache.commons.logging.LogFactory; -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.queryParser.QueryParser; -import org.apache.lucene.search.Query; - -import edu.cornell.mannlib.vitro.webapp.controller.VitroRequest; -import edu.cornell.mannlib.vitro.webapp.search.SearchException; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQuery; - -/** - * Creates a query that can be used to search a Lucene index. - * This class uses the Lucene class QueryParser to parse the - * text from the html text field input form. - * - * For information about how syntaxt and semantics of the - * QueryParser see: - * http://lucene.apache.org/java/docs/queryparsersyntax.html - * http://today.java.net/pub/a/today/2003/11/07/QueryParserRules.html - * - * This class is not thread safe, use one instance per request. - * @author bdc34 - * - */ -public class LuceneQuery extends VitroQuery { - private final String defaultSearchField = "ALLTEXT"; - - private final int SIMPLE = 1; - private final int ADVANCED =2; - private int queryType = SIMPLE; - - private Query query = null; - private Analyzer analyzer = null; - - private static final Log log = LogFactory.getLog(LuceneQuery.class.getName()); - - public LuceneQuery(VitroRequest request, - Analyzer analyzer, - String defaultField ){ - super(request); //the super class will stash the parameters for us. - this.analyzer = analyzer; - - if( isAdvancedQuery( request ) ){ - queryType = ADVANCED; - } - } - - @SuppressWarnings("static-access") - private QueryParser getQueryParser(){ - //defaultSearchField indicates which field search against when there is no term - //indicated in the query string. - //The analyzer is needed so that we use the same analyzer on the search queries as - //was used on the text that was indexed. - QueryParser qp = new QueryParser(defaultSearchField,analyzer); - //this sets the query parser to AND all of the query terms it finds. - qp.setDefaultOperator(QueryParser.AND_OPERATOR); - return qp; - } - - public Object getQuery() throws SearchException { - if( this.query != null ) - return this.query; - - String querystr = ""; - if( getParameters() != null && getParameters().get(VitroQuery.QUERY_PARAMETER_NAME)!=null ){ - Object obj= getParameters().get(VitroQuery.QUERY_PARAMETER_NAME); - if( obj instanceof String[]) - querystr = ((String[])obj)[0]; - else - log.debug("LuceneQquery.getQuery() querytext is of class " + - obj.getClass().getName()); - } - else - throw new SearchException(this.getClass().getName() + - ": There was no Parameter '"+VitroQuery.QUERY_PARAMETER_NAME+"' in the request."); - - try{ - if( SIMPLE == queryType ){ - QueryParser parser= getQueryParser(); - this.query = parser.parse(querystr); - } else if( ADVANCED == queryType ){ - this.query = null; - } - }catch (Exception ex){ - throw new SearchException(ex.getMessage()); - } - - return this.query; - } - - /** - * Check to see if the request came from some sort of advanced query page. - * - * @param request - * @return - */ - private boolean isAdvancedQuery(HttpServletRequest request){ - return false; - } - - @Override - public String getTerms() { - if( getParameters() != null && - getParameters().get(VitroQuery.QUERY_PARAMETER_NAME) != null) { - Object terms = getParameters().get(VitroQuery.QUERY_PARAMETER_NAME); - if( terms instanceof String[] ) { - return ((String[])terms)[0]; - } else { - log.debug("LuceneQuery.getTerms(): terms in a " + terms.getClass().getName() ); - return ""; - } - } else - return ""; - } - - public Analyzer getAnalyzer(){return analyzer;} -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQueryFactory.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQueryFactory.java deleted file mode 100644 index bee44c60b..000000000 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/lucene/LuceneQueryFactory.java +++ /dev/null @@ -1,40 +0,0 @@ -/* $This file is distributed under the terms of the license in /doc/license.txt$ */ - -package edu.cornell.mannlib.vitro.webapp.search.lucene; - -import org.apache.lucene.analysis.Analyzer; - -import edu.cornell.mannlib.vitro.webapp.controller.VitroRequest; -import edu.cornell.mannlib.vitro.webapp.search.SearchException; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQuery; -import edu.cornell.mannlib.vitro.webapp.search.beans.VitroQueryFactory; - -public class LuceneQueryFactory implements VitroQueryFactory { - - public static final int MAX_QUERY_LENGTH = 500; - private String defaultField; - private Analyzer analyzer = null; - - public LuceneQueryFactory(Analyzer analyzer, String defaultField ){ - this.analyzer = analyzer; - this.defaultField = defaultField; - } - - public VitroQuery getQuery(VitroRequest request) throws SearchException { - //there should be a better way to integrate this with LuceneQuery - //here we check that the request has the parameters that we need to - //make the query. If it does not then we return null. - String txt = request.getParameter(VitroQuery.QUERY_PARAMETER_NAME); - if( txt == null || txt.length() == 0 ) - return null; - if( txt.length() > MAX_QUERY_LENGTH ) - throw new SearchException("The search was too long. The maximum " + - "query length is " + MAX_QUERY_LENGTH ); - LuceneQuery query = new LuceneQuery(request, analyzer, defaultField ); - return query; - } - - public Analyzer getAnalyzer(){ - return analyzer; - } -} diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/IndividualToSolrDocument.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/IndividualToSolrDocument.java index 384a8fb4c..e1947f03d 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/IndividualToSolrDocument.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/IndividualToSolrDocument.java @@ -134,7 +134,7 @@ public class IndividualToSolrDocument { private void checkForSkipBasedOnNS(Individual ind) throws SkipIndividualException { String id = ind.getURI(); if(id == null){ - throw new SkipIndividualException("cannot add individuals without URIs to lucene Index"); + throw new SkipIndividualException("cannot add individuals without URIs to search index"); }else if( id.startsWith(VitroVocabulary.vitroURI) || id.startsWith(VitroVocabulary.VITRO_PUBLIC) || id.startsWith(VitroVocabulary.PSEUDO_BNODE_NS) || diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/SolrSetup.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/SolrSetup.java index 6a28feb72..6b1cf08b3 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/SolrSetup.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/search/solr/SolrSetup.java @@ -70,8 +70,7 @@ public class SolrSetup implements javax.servlet.ServletContextListener{ server.setMaxRetries(1); context.setAttribute(LOCAL_SOLR_SERVER, server); - /* setup the individual to solr doc translation */ - //first we need a ent2luceneDoc translator + /* set up the individual to solr doc translation */ OntModel displayOntModel = (OntModel) sce.getServletContext().getAttribute("displayOntModel"); OntModel abox = ModelContext.getBaseOntModelSelector(context).getABoxModel(); @@ -86,7 +85,7 @@ public class SolrSetup implements javax.servlet.ServletContextListener{ modifiers.add(new NameBoost()); IndividualToSolrDocument indToSolrDoc = new IndividualToSolrDocument( - new ProhibitedFromSearch(DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel), + new ProhibitedFromSearch(DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel), new IndividualProhibitedFromSearchImpl(context), modifiers); diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/web/jsptags/InputElementFormattingTag.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/web/jsptags/InputElementFormattingTag.java index ac110d4d6..8b82337c1 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/web/jsptags/InputElementFormattingTag.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/web/jsptags/InputElementFormattingTag.java @@ -449,7 +449,7 @@ public class InputElementFormattingTag extends TagSupport { .getAttribute("displayOntModel"); if (displayOntModel != null) { ProhibitedFromSearch pfs = new ProhibitedFromSearch( - DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); + DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); if( editConfig != null ) editConfig.setProhibitedFromSearch(pfs); } diff --git a/webapp/src/edu/cornell/mannlib/vitro/webapp/web/templatemodels/individual/ObjectPropertyStatementTemplateModel.java b/webapp/src/edu/cornell/mannlib/vitro/webapp/web/templatemodels/individual/ObjectPropertyStatementTemplateModel.java index 300a94184..718a4599c 100644 --- a/webapp/src/edu/cornell/mannlib/vitro/webapp/web/templatemodels/individual/ObjectPropertyStatementTemplateModel.java +++ b/webapp/src/edu/cornell/mannlib/vitro/webapp/web/templatemodels/individual/ObjectPropertyStatementTemplateModel.java @@ -30,7 +30,6 @@ public class ObjectPropertyStatementTemplateModel extends PropertyStatementTempl private final String objectUri; private final String templateName; - //Updating to include Vitro Request ObjectPropertyStatementTemplateModel(String subjectUri, String propertyUri, String objectKey, Map data, EditingPolicyHelper policyHelper, String templateName, VitroRequest vreq) { super(subjectUri, propertyUri, policyHelper, vreq); diff --git a/webapp/test/edu/cornell/mannlib/vitro/webapp/search/beans/ProhibitedFromSearchTest.java b/webapp/test/edu/cornell/mannlib/vitro/webapp/search/beans/ProhibitedFromSearchTest.java index 8e29ccb24..c2f3cafd8 100644 --- a/webapp/test/edu/cornell/mannlib/vitro/webapp/search/beans/ProhibitedFromSearchTest.java +++ b/webapp/test/edu/cornell/mannlib/vitro/webapp/search/beans/ProhibitedFromSearchTest.java @@ -110,7 +110,7 @@ public class ProhibitedFromSearchTest { @Test public void testPrimaryIndex(){ String primaryIndexN3 = - "" + + "" + "" + " . "; @@ -119,7 +119,7 @@ public class ProhibitedFromSearchTest { m.add( r.listStatements() ); Assert.assertTrue(m.size() == 1); - ProhibitedFromSearch pfs = new ProhibitedFromSearch( DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, m); + ProhibitedFromSearch pfs = new ProhibitedFromSearch( DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, m); Assert.assertNotNull(pfs.prohibitedClasses); Assert.assertEquals(1, pfs.prohibitedClasses.size() ); Assert.assertTrue(pfs.isClassProhibitedFromSearch("http://vivoweb.org/ontology/core#NonAcademic")); diff --git a/webapp/web/edit/forms/defaultObjPropForm.jsp b/webapp/web/edit/forms/defaultObjPropForm.jsp index 956f402c6..bf720e703 100644 --- a/webapp/web/edit/forms/defaultObjPropForm.jsp +++ b/webapp/web/edit/forms/defaultObjPropForm.jsp @@ -143,7 +143,7 @@ .getAttribute("displayOntModel"); if (displayOntModel != null) { ProhibitedFromSearch pfs = new ProhibitedFromSearch( - DisplayVocabulary.PRIMARY_LUCENE_INDEX_URI, displayOntModel); + DisplayVocabulary.PRIMARY_SEARCH_INDEX_URI, displayOntModel); if( editConfig != null ) editConfig.setProhibitedFromSearch(pfs); } diff --git a/webapp/web/themes/vitro/templates/page-home.ftl b/webapp/web/themes/vitro/templates/page-home.ftl index b6a97ebb8..58f90797b 100644 --- a/webapp/web/themes/vitro/templates/page-home.ftl +++ b/webapp/web/themes/vitro/templates/page-home.ftl @@ -24,7 +24,7 @@
  • Create or load ontologies in OWL format
  • Edit instances and relationships
  • Build a public web site to display your data
    • -
  • Search your data with Lucene
    • +
  • Search your data