docs.
+ * The field must have at most one indexed token per document.
+ */
+ public static NamedList getFieldCacheCounts(SolrIndexSearcher searcher, DocSet docs, String fieldName, int limit, boolean zeros, boolean missing) throws IOException {
+ // TODO: If the number of terms is high compared to docs.size(), and zeros==false,
+ // we should use an alternate strategy to avoid
+ // 1) creating another huge int[] for the counts
+ // 2) looping over that huge int[] looking for the rare non-zeros.
+ //
+ // Yet another variation: if docs.size() is small and termvectors are stored,
+ // then use them instead of the FieldCache.
+ //
+
+ FieldCache.StringIndex si = FieldCache.DEFAULT.getStringIndex(searcher.getReader(), fieldName);
+ int[] count = new int[si.lookup.length];
+ DocIterator iter = docs.iterator();
+ while (iter.hasNext()) {
+ count[si.order[iter.nextDoc()]]++;
+ }
+
+ FieldType ft = searcher.getSchema().getFieldType(fieldName);
+ NamedList res = new NamedList();
+
+ // IDEA: we could also maintain a count of "other"... everything that fell outside
+ // of the top 'N'
+
+ BoundedTreeSetdocs
+ * and the DocSet for each term in the filter.
*
* @see SolrParams#FACET_LIMIT
* @see SolrParams#FACET_ZEROS
+ * @see SolrParams#FACET_MISSING
*/
- public NamedList getFacetTermEnumCounts(String fieldName)
+ public NamedList getFacetTermEnumCounts(SolrIndexSearcher searcher, DocSet docs, String field, int limit, boolean zeros, boolean missing)
throws IOException {
-
+
/* :TODO: potential optimization...
- * cache the Terms with the highest docFreq and try them first
- * don't enum if we get our max from them
- */
-
+ * cache the Terms with the highest docFreq and try them first
+ * don't enum if we get our max from them
+ */
+
IndexSchema schema = searcher.getSchema();
IndexReader r = searcher.getReader();
- FieldType ft = schema.getFieldType(fieldName);
+ FieldType ft = schema.getFieldType(field);
- SetContainer for a request to execute a query.
+ *SolrQueryRequest is not thread safe.