shubhamvishu commented on code in PR #12183:
URL: https://github.com/apache/lucene/pull/12183#discussion_r1259261938
##########
lucene/core/src/java/org/apache/lucene/index/TermStates.java:
##########
@@ -211,4 +242,40 @@ public String toString() {
return sb.toString();
}
+
+ /** Wrapper over TermState, ordinal value, term doc frequency and total term
frequency */
+ public static final class TermStateInfo {
Review Comment:
Sure
##########
lucene/core/src/java/org/apache/lucene/index/TermStates.java:
##########
@@ -86,19 +91,45 @@ public TermStates(
* @param needsStats if {@code true} then all leaf contexts will be visited
up-front to collect
* term statistics. Otherwise, the {@link TermState} objects will be
built only when requested
*/
- public static TermStates build(IndexReaderContext context, Term term,
boolean needsStats)
+ public static TermStates build(IndexSearcher indexSearcher, Term term,
boolean needsStats)
throws IOException {
- assert context != null && context.isTopLevel;
+ IndexReaderContext context = indexSearcher.getTopReaderContext();
+ assert context != null;
final TermStates perReaderTermState = new TermStates(needsStats ? null :
term, context);
if (needsStats) {
- for (final LeafReaderContext ctx : context.leaves()) {
- // if (DEBUG) System.out.println(" r=" + leaves[i].reader);
- TermsEnum termsEnum = loadTermsEnum(ctx, term);
- if (termsEnum != null) {
- final TermState termState = termsEnum.termState();
- // if (DEBUG) System.out.println(" found");
- perReaderTermState.register(
- termState, ctx.ord, termsEnum.docFreq(),
termsEnum.totalTermFreq());
+ Executor executor = indexSearcher.getExecutor();
+ if (executor == null) {
+ executor = Runnable::run;
+ }
+ List<FutureTask<TermStateInfo>> tasks =
+ context.leaves().stream()
+ .map(
+ ctx ->
+ new FutureTask<>(
+ () -> {
+ TermsEnum termsEnum = loadTermsEnum(ctx, term);
+ if (termsEnum != null) {
+ return new TermStateInfo(
+ termsEnum.termState(),
+ ctx.ord,
+ termsEnum.docFreq(),
+ termsEnum.totalTermFreq());
+ }
+ return null;
+ }))
+ .toList();
+ for (FutureTask<TermStateInfo> task : tasks) {
+ executor.execute(task);
+ }
+ for (FutureTask<TermStateInfo> task : tasks) {
+ try {
+ TermStateInfo wrapper = task.get();
+ if (wrapper != null) {
+ perReaderTermState.register(
+ wrapper.state, wrapper.ordinal, wrapper.docFreq,
wrapper.totalTermFreq);
+ }
+ } catch (InterruptedException | ExecutionException e) {
+ throw new RuntimeException(e.getMessage());
Review Comment:
I'll change in next revision
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
