gautamworah96 commented on a change in pull request #179:
URL: https://github.com/apache/lucene/pull/179#discussion_r696969300
##########
File path:
lucene/facet/src/java/org/apache/lucene/facet/taxonomy/directory/DirectoryTaxonomyReader.java
##########
@@ -351,12 +349,139 @@ public FacetLabel getPath(int ordinal) throws
IOException {
}
synchronized (categoryCache) {
- categoryCache.put(catIDInteger, ret);
+ categoryCache.put(ordinal, ret);
}
return ret;
}
+ private FacetLabel getPathFromCache(int ordinal) {
+ // TODO: can we use an int-based hash impl, such as IntToObjectMap,
+ // wrapped as LRU?
+ synchronized (categoryCache) {
+ return categoryCache.get(ordinal);
+ }
+ }
+
+ private void checkOrdinalBounds(int ordinal, int indexReaderMaxDoc)
+ throws IllegalArgumentException {
+ if (ordinal < 0 || ordinal >= indexReaderMaxDoc) {
+ throw new IllegalArgumentException(
+ "ordinal "
+ + ordinal
+ + " is out of the range of the indexReader "
+ + indexReader.toString());
+ }
+ }
+
+ /**
+ * Returns an array of FacetLabels for a given array of ordinals.
+ *
+ * <p>This API is generally faster than iteratively calling {@link
#getPath(int)} over an array of
+ * ordinals. It uses the {@link #getPath(int)} method iteratively when it
detects that the index
+ * was created using StoredFields (with no performance gains) and uses
DocValues based iteration
+ * when the index is based on DocValues.
+ *
+ * @param ordinals Array of ordinals that are assigned to categories
inserted into the taxonomy
+ * index
+ */
+ public FacetLabel[] getBulkPath(int... ordinals) throws IOException {
+ ensureOpen();
+
+ int ordinalsLength = ordinals.length;
+ FacetLabel[] bulkPath = new FacetLabel[ordinalsLength];
+ // remember the original positions of ordinals before they are sorted
+ int[] originalPosition = new int[ordinalsLength];
+ Arrays.setAll(originalPosition, IntUnaryOperator.identity());
+ int indexReaderMaxDoc = indexReader.maxDoc();
+
+ for (int i = 0; i < ordinalsLength; i++) {
+ // check whether the ordinal is valid before accessing the cache
+ checkOrdinalBounds(ordinals[i], indexReaderMaxDoc);
+ // check the cache before trying to find it in the index
+ FacetLabel ordinalPath = getPathFromCache(ordinals[i]);
+ if (ordinalPath != null) {
+ bulkPath[i] = ordinalPath;
+ }
+ }
+
+ /* parallel sort the ordinals and originalPosition array based on the
values in the ordinals array */
+ new InPlaceMergeSorter() {
+ @Override
+ protected void swap(int i, int j) {
+ int x = ordinals[i];
+ ordinals[i] = ordinals[j];
+ ordinals[j] = x;
+
+ x = originalPosition[i];
+ originalPosition[i] = originalPosition[j];
+ originalPosition[j] = x;
+ }
+ ;
+
+ @Override
+ public int compare(int i, int j) {
+ return Integer.compare(ordinals[i], ordinals[j]);
+ }
+ }.sort(0, ordinalsLength);
+
+ int readerIndex;
+ int leafReaderMaxDoc = 0;
+ int leafReaderDocBase = 0;
+ LeafReader leafReader;
+ LeafReaderContext leafReaderContext;
+ BinaryDocValues values = null;
+
+ for (int i = 0; i < ordinalsLength; i++) {
+ if (bulkPath[originalPosition[i]] == null) {
+ /*
+ If ordinals[i] >= leafReaderMaxDoc then we find the next leaf that
contains our ordinal
+ */
+ if (values == null || ordinals[i] >= leafReaderMaxDoc) {
+
+ readerIndex = ReaderUtil.subIndex(ordinals[i], indexReader.leaves());
+ leafReaderContext = indexReader.leaves().get(readerIndex);
+ leafReader = leafReaderContext.reader();
+ leafReaderMaxDoc = leafReader.maxDoc();
+ leafReaderDocBase = leafReaderContext.docBase;
+ values = leafReader.getBinaryDocValues(Consts.FULL);
+
+ /*
+ If the index is constructed with the older StoredFields it will not
have any BinaryDocValues field and will return null
+ */
+ if (values == null) {
+ return getBulkPathForOlderIndexes(ordinals);
+ }
+ }
+ boolean success = values.advanceExact(ordinals[i] - leafReaderDocBase);
+ assert success;
+ bulkPath[originalPosition[i]] =
+ new
FacetLabel(FacetsConfig.stringToPath(values.binaryValue().utf8ToString()));
+
+ // add the value to the categoryCache after computation
+ synchronized (categoryCache) {
Review comment:
Sure. I've implemented this in the next iteration where the
`uncachedOrdinalPositions` array stores the positions of ordinals that were not
cached.
We later on use these positions in one go to bulk insert paths into the
cache.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
