zacharymorn commented on a change in pull request #128:
URL: https://github.com/apache/lucene/pull/128#discussion_r696248395
##########
File path: lucene/core/src/java/org/apache/lucene/index/CheckIndex.java
##########
@@ -843,6 +825,258 @@ public Status checkIndex(List<String> onlySegments)
throws IOException {
return result;
}
+ private void updateMaxSegmentName(Status result, SegmentCommitInfo info) {
+ long segmentName = Long.parseLong(info.info.name.substring(1),
Character.MAX_RADIX);
+ if (segmentName > result.maxSegmentName) {
+ result.maxSegmentName = segmentName;
+ }
+ }
+
+ private void processSegmentInfoStatusResult(
+ Status result, SegmentCommitInfo info, Status.SegmentInfoStatus
segmentInfoStatus) {
+ result.segmentInfos.add(segmentInfoStatus);
+ if (segmentInfoStatus.error != null) {
+ result.totLoseDocCount += segmentInfoStatus.toLoseDocCount;
+ result.numBadSegments++;
+ } else {
+ // Keeper
+ result.newSegments.add(info.clone());
+ }
+ }
+
+ private <R> CompletableFuture<R> runAsyncSegmentCheck(
+ Callable<R> asyncCallable, ExecutorService executorService) {
+ return CompletableFuture.supplyAsync(callableToSupplier(asyncCallable),
executorService);
+ }
+
+ private <T> Supplier<T> callableToSupplier(Callable<T> callable) {
+ return () -> {
+ try {
+ return callable.call();
+ } catch (RuntimeException | Error e) {
+ throw e;
+ } catch (Throwable e) {
+ throw new CompletionException(e);
+ }
+ };
+ }
+
+ private Status.SegmentInfoStatus testSegment(
+ SegmentInfos sis, SegmentCommitInfo info, PrintStream infoStream) throws
IOException {
+ Status.SegmentInfoStatus segInfoStat = new Status.SegmentInfoStatus();
+ segInfoStat.name = info.info.name;
+ segInfoStat.maxDoc = info.info.maxDoc();
+
+ final Version version = info.info.getVersion();
+ if (info.info.maxDoc() <= 0) {
+ throw new CheckIndexException(" illegal number of documents: maxDoc=" +
info.info.maxDoc());
+ }
+
+ int toLoseDocCount = info.info.maxDoc();
+
+ SegmentReader reader = null;
+
+ try {
+ msg(infoStream, " version=" + (version == null ? "3.0" : version));
+ msg(infoStream, " id=" + StringHelper.idToString(info.info.getId()));
+ final Codec codec = info.info.getCodec();
+ msg(infoStream, " codec=" + codec);
+ segInfoStat.codec = codec;
+ msg(infoStream, " compound=" + info.info.getUseCompoundFile());
+ segInfoStat.compound = info.info.getUseCompoundFile();
+ msg(infoStream, " numFiles=" + info.files().size());
+ Sort indexSort = info.info.getIndexSort();
+ if (indexSort != null) {
+ msg(infoStream, " sort=" + indexSort);
+ }
+ segInfoStat.numFiles = info.files().size();
+ segInfoStat.sizeMB = info.sizeInBytes() / (1024. * 1024.);
+ // nf#format is not thread-safe, and would generate random non valid
results in concurrent
+ // setting
+ synchronized (nf) {
+ msg(infoStream, " size (MB)=" + nf.format(segInfoStat.sizeMB));
+ }
+ Map<String, String> diagnostics = info.info.getDiagnostics();
+ segInfoStat.diagnostics = diagnostics;
+ if (diagnostics.size() > 0) {
+ msg(infoStream, " diagnostics = " + diagnostics);
+ }
+
+ if (!info.hasDeletions()) {
+ msg(infoStream, " no deletions");
+ segInfoStat.hasDeletions = false;
+ } else {
+ msg(infoStream, " has deletions [delGen=" + info.getDelGen() + "]");
+ segInfoStat.hasDeletions = true;
+ segInfoStat.deletionsGen = info.getDelGen();
+ }
+
+ long startOpenReaderNS = System.nanoTime();
+ if (infoStream != null) infoStream.print(" test: open
reader.........");
+ reader = new SegmentReader(info, sis.getIndexCreatedVersionMajor(),
IOContext.DEFAULT);
+ msg(
+ infoStream,
+ String.format(
+ Locale.ROOT, "OK [took %.3f sec]", nsToSec(System.nanoTime() -
startOpenReaderNS)));
+
+ segInfoStat.openReaderPassed = true;
+
+ long startIntegrityNS = System.nanoTime();
+ if (infoStream != null) infoStream.print(" test: check
integrity.....");
+ reader.checkIntegrity();
+ msg(
+ infoStream,
+ String.format(
+ Locale.ROOT, "OK [took %.3f sec]", nsToSec(System.nanoTime() -
startIntegrityNS)));
+
+ if (reader.maxDoc() != info.info.maxDoc()) {
+ throw new CheckIndexException(
+ "SegmentReader.maxDoc() "
+ + reader.maxDoc()
+ + " != SegmentInfo.maxDoc "
+ + info.info.maxDoc());
+ }
+
+ final int numDocs = reader.numDocs();
+ toLoseDocCount = numDocs;
+
+ if (reader.hasDeletions()) {
+ if (reader.numDocs() != info.info.maxDoc() - info.getDelCount()) {
+ throw new CheckIndexException(
+ "delete count mismatch: info="
+ + (info.info.maxDoc() - info.getDelCount())
+ + " vs reader="
+ + reader.numDocs());
+ }
+ if ((info.info.maxDoc() - reader.numDocs()) > reader.maxDoc()) {
+ throw new CheckIndexException(
+ "too many deleted docs: maxDoc()="
+ + reader.maxDoc()
+ + " vs del count="
+ + (info.info.maxDoc() - reader.numDocs()));
+ }
+ if (info.info.maxDoc() - reader.numDocs() != info.getDelCount()) {
+ throw new CheckIndexException(
+ "delete count mismatch: info="
+ + info.getDelCount()
+ + " vs reader="
+ + (info.info.maxDoc() - reader.numDocs()));
+ }
+ } else {
+ if (info.getDelCount() != 0) {
+ throw new CheckIndexException(
+ "delete count mismatch: info="
+ + info.getDelCount()
+ + " vs reader="
+ + (info.info.maxDoc() - reader.numDocs()));
+ }
+ }
+
+ if (checksumsOnly == false) {
+ // This redundant assignment is done to make compiler happy
+ SegmentReader finalReader = reader;
Review comment:
Ah yes this is left over when I was previously using lambda for each
test. I've removed this.
--
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
