slfan1989 commented on code in PR #12568:
URL: https://github.com/apache/iceberg/pull/12568#discussion_r2002601412
##########
spark/v3.4/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteTablePathsAction.java:
##########
@@ -932,23 +1093,40 @@ protected void checkFileNum(
int manifestFileCount,
int totalCount,
RewriteTablePath.Result result) {
+ checkFileNum(versionFileCount, manifestListCount, manifestFileCount, 0,
totalCount, result);
+ }
+
+ protected void checkFileNum(
+ int versionFileCount,
+ int manifestListCount,
+ int manifestFileCount,
+ int statisticsFileCount,
+ int totalCount,
+ RewriteTablePath.Result result) {
List<String> filesToMove =
spark
.read()
.format("text")
.load(result.fileListLocation())
.as(Encoders.STRING())
.collectAsList();
- assertThat(filesToMove.stream().filter(f ->
f.endsWith(".metadata.json")).count())
- .withFailMessage("Wrong rebuilt version file count")
+ Predicate<String> isManifest = f -> f.endsWith("-m0.avro") ||
f.endsWith("-m1.avro");
+ Predicate<String> isManifestList = f -> f.contains("snap-") &&
f.endsWith(".avro");
+ Predicate<String> isMetadataJSON = f -> f.endsWith(".metadata.json");
+
+ assertThat(filesToMove.stream().filter(isMetadataJSON).count())
+ .as("Wrong rebuilt version file count")
.isEqualTo(versionFileCount);
- assertThat(filesToMove.stream().filter(f -> f.contains("snap-")).count())
- .withFailMessage("Wrong rebuilt Manifest list file count")
+ assertThat(filesToMove.stream().filter(isManifestList).count())
+ .as("Wrong rebuilt Manifest list file count")
.isEqualTo(manifestListCount);
- assertThat(filesToMove.stream().filter(f ->
f.endsWith("-m0.avro")).count())
- .withFailMessage("Wrong rebuilt Manifest file file count")
+ assertThat(filesToMove.stream().filter(isManifest).count())
+ .as("Wrong rebuilt Manifest file file count")
.isEqualTo(manifestFileCount);
- assertThat(filesToMove.size()).withFailMessage("Wrong total file
count").isEqualTo(totalCount);
+ assertThat(filesToMove.stream().filter(f -> f.endsWith(".stats")).count())
+ .withFailMessage("Wrong rebuilt Statistic file count")
Review Comment:
@nastra Thank you for reviewing and providing valuable feedback! I can wait
until your PR is merged, and then further improve this PR based on your changes.
--
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...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
