muse-dev[bot] commented on a change in pull request #2247:
URL: https://github.com/apache/lucene-solr/pull/2247#discussion_r572484392
##########
File path:
lucene/facet/src/java/org/apache/lucene/facet/taxonomy/directory/DirectoryTaxonomyReader.java
##########
@@ -353,12 +349,137 @@ 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 (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);
+
+ // this check is only needed once to confirm that the index uses
BinaryDocValues
+ boolean success = values.advanceExact(ordinals[i] -
leafReaderDocBase);
+ if (success == false) {
+ return getBulkPathForOlderIndexes(ordinals);
+ }
+ }
+ boolean success = values.advanceExact(ordinals[i] - leafReaderDocBase);
+ assert success;
+ bulkPath[originalPosition[i]] =
+ new
FacetLabel(FacetsConfig.stringToPath(values.binaryValue().utf8ToString()));
+ }
+ }
+
+ for (int i = 0; i < ordinalsLength; i++) {
+ synchronized (categoryCache) {
Review comment:
*THREAD_SAFETY_VIOLATION:* Read/Write race. Non-private method
`DirectoryTaxonomyReader.getBulkPath(...)` reads without synchronization from
`this.categoryCache`. Potentially races with write in method
`DirectoryTaxonomyReader.doClose()`.
Reporting because this access may occur on a background thread.
##########
File path:
lucene/facet/src/java/org/apache/lucene/facet/taxonomy/directory/DirectoryTaxonomyReader.java
##########
@@ -320,23 +323,16 @@ public FacetLabel getPath(int ordinal) throws IOException
{
// doOpenIfChanged, we need to ensure that the ordinal is one that this DTR
// instance recognizes. Therefore we do this check up front, before we hit
// the cache.
- if (ordinal < 0 || ordinal >= indexReader.maxDoc()) {
- return null;
- }
+ int indexReaderMaxDoc = indexReader.maxDoc();
+ checkOrdinalBounds(ordinal, indexReaderMaxDoc);
- // TODO: can we use an int-based hash impl, such as IntToObjectMap,
- // wrapped as LRU?
- Integer catIDInteger = Integer.valueOf(ordinal);
- synchronized (categoryCache) {
- FacetLabel res = categoryCache.get(catIDInteger);
- if (res != null) {
- return res;
- }
+ FacetLabel ordinalPath = getPathFromCache(ordinal);
Review comment:
*THREAD_SAFETY_VIOLATION:* Read/Write race. Non-private method
`DirectoryTaxonomyReader.getPath(...)` indirectly reads without synchronization
from `this.categoryCache`. Potentially races with write in method
`DirectoryTaxonomyReader.doClose()`.
Reporting because this access may occur on a background thread.
----------------------------------------------------------------
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.
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
