Changeset 1936

Timestamp:

05/15/12 13:35:42 (12 years ago)

Author:

herste

Message:

started adding type of thing described code, based on the cmdi profile used

Location:

vlo/trunk

Files:

• vlo_solr/src/main/solr_conf/solr/conf/schema.xml (modified) (14 diffs)
• vlo_webapp/src/main/java/eu/clarin/cmdi/vlo/FacetConstants.java (modified) (1 diff)
• vlo_webapp/src/main/java/eu/clarin/cmdi/vlo/importer/MetadataImporter.java (modified) (2 diffs)
• vlo_webapp/src/main/resources/facetConcepts.xml (modified) (1 diff)

vlo/trunk/vlo_solr/src/main/solr_conf/solr/conf/schema.xml

@@ -1 @@
-<?xml version="1.0" encoding="UTF-8" ?>
+itu<?xml version="1.0" encoding="UTF-8" ?>
 <!--
  Licensed to the Apache Software Foundation (ASF) under one or more
@@ -17 +17 @@
 -->
 
-<!--  
+<!--
  This is the Solr schema file. This file should be named "schema.xml" and
  should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default) 
+ (i.e. ./solr/conf/schema.xml by default)
  or located where the classloader for the Solr webapp can find it.
 
@@ -52 +52 @@
        not normally be changed by applications.
        1.0: multiValued attribute did not exist, all fields are multiValued by nature
-       1.1: multiValued attribute introduced, false by default 
+       1.1: multiValued attribute introduced, false by default
        1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
      -->
@@ -65 +65 @@
     -->
 
-    <!-- The StrField type is not analyzed, but indexed/stored verbatim.  
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
        - StrField and TextField support an optional compressThreshold which
        limits compression (if enabled in the derived fields) to values which
@@ -91 +91 @@
          then default lucene sorting will be used which places docs without the
          field first in an ascending sort and last in a descending sort.
-    -->    
+    -->
 
     <!--
@@ -118 +118 @@
     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
          is a more restricted form of the canonical representation of dateTime
-         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         http://www.w3.org/TR/xmlschema-2/#dateTime
          The trailing "Z" designates UTC time and is mandatory.
          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
@@ -133 +133 @@
                   ... 6 months and 3 days in the future from the start of
                       the current day
-                      
+
          Consult the DateField javadocs for more information.
 
@@ -178 +178 @@
     <!-- The "RandomSortField" is not used to store or search any
          data.  You can declare fields of this type it in your schema
-         to generate pseudo-random orderings of your docs for sorting 
-         purposes.  The ordering is generated based on the field name 
+         to generate pseudo-random orderings of your docs for sorting
+         purposes.  The ordering is generated based on the field name
          and the version of the index, As long as the index version
          remains unchanged, and the same field name is reused,
-         the ordering of the docs will be consistent.  
+         the ordering of the docs will be consistent.
          If you want different psuedo-random orderings of documents,
          for the same version of the index, use a dynamicField and
@@ -294 +294 @@
 
     <!-- A general unstemmed text field that indexes tokens normally and also
-         reversed (via ReversedWildcardFilterFactory), to enable more efficient 
+         reversed (via ReversedWildcardFilterFactory), to enable more efficient
          leading wildcard queries. -->
     <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
@@ -346 +346 @@
         <!-- The PatternReplaceFilter gives you the flexibility to use
              Java Regular expression to replace any sequence of characters
-             matching a pattern with an arbitrary replacement string, 
+             matching a pattern with an arbitrary replacement string,
              which may include back references to portions of the original
              string matched by the pattern.
-             
+
              See the Java Regular Expression documentation for more
              information on pattern and replacement string syntax.
-             
+
              http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
           -->
@@ -360 +360 @@
       </analyzer>
     </fieldType>
-    
+
     <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
       <analyzer>
@@ -374 +374 @@
         The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
         a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
-        Attributes of the DelimitedPayloadTokenFilterFactory : 
+        Attributes of the DelimitedPayloadTokenFilterFactory :
          "delimiter" - a one character delimiter. Default is | (pipe)
          "encoder" - how to encode the following value into a playload
@@ -396 +396 @@
 
     <!-- since fields of this type are by default not stored or indexed,
-         any data added to them will be ignored outright.  --> 
-    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" /> 
+         any data added to them will be ignored outright.  -->
+    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
 
  </types>
@@ -437 +437 @@
    <field name="_fileName" type="string" indexed="true" stored="true" multiValued="false" />
    <field name="_resourceRef" type="string" indexed="true" stored="true" multiValued="true" />
+   <field name="_componentProfile" type="string" indexed="true" stored="true" multiValued="false" />
    <field name="metadataSource" type="metadataSource" indexed="false" stored="true" multiValued="true" />
    <field name="languages" type="string" indexed="true" stored="true" multiValued="true" />

vlo/trunk/vlo_webapp/src/main/java/eu/clarin/cmdi/vlo/FacetConstants.java

@@ -24 +24 @@
     public static final String FIELD_FILENAME = "_fileName";
     public static final String FIELD_RESOURCE = "_resourceRef";
+    public static final String FIELD_CLARIN_PROFILE = "_componentProfile";
 
     // PREFIX URL for the language-link

vlo/trunk/vlo_webapp/src/main/java/eu/clarin/cmdi/vlo/importer/MetadataImporter.java

@@ -42 +42 @@
         POST_PROCESSORS.put(FacetConstants.FIELD_LANGUAGES, new LanguageLinkPostProcessor());
         POST_PROCESSORS.put(FacetConstants.FIELD_NATIONAL_PROJECT, new NationalProjectPostProcessor());
+        // TODO: Define tools postprocessor and create input file and so on. Maybe do this dynamicly?
     }
 
@@ -232 +233 @@
         metadataSourceUrl += file.getAbsolutePath().substring(dataOrigin.getTostrip().length());
 
-        solrDocument.addField(FacetConstants.FIELD_COMPLETE_METADATA, metadataSourceUrl); // TODO: add the contents of the metadata file here
+        solrDocument.addField(FacetConstants.FIELD_COMPLETE_METADATA, metadataSourceUrl);
 
         addResourceData(solrDocument, cmdiData);

vlo/trunk/vlo_webapp/src/main/resources/facetConcepts.xml

@@ -71 +71 @@
     <pattern>/c:CMD/c:Header/c:MdCollectionDisplayName/text()</pattern>
   </facetConcept>
+    <facetConcept name="_componentProfile">
+        <pattern>/c:CMD/c:Header/c:MdProfile/text()</pattern>
+    </facetConcept>
 </facetConcepts>