amousavigourabi commented on code in PR #1170:
URL: https://github.com/apache/parquet-mr/pull/1170#discussion_r1359433148
##########
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java:
##########
@@ -314,32 +315,32 @@ public void testParquetFileWithBloomFilterWithFpp()
throws IOException {
.withConf(conf)
.withDictionaryEncoding(false)
.withBloomFilterEnabled("name", true)
- .withBloomFilterNDV("name", totalCount)
- .withBloomFilterFPP("name", testFpp[i])
+ .withBloomFilterNDV("name", buildBloomFilterCount)
+ .withBloomFilterFPP("name", testFpp)
.build()) {
- java.util.Iterator<String> iterator = distinctStrings.iterator();
- while (iterator.hasNext()) {
- writer.write(factory.newGroup().append("name", iterator.next()));
+ for (String str : distinctStringsForFileGenerate) {
+ writer.write(factory.newGroup().append("name", str));
}
}
- distinctStrings.clear();
try (ParquetFileReader reader =
ParquetFileReader.open(HadoopInputFile.fromPath(path, new Configuration()))) {
BlockMetaData blockMetaData = reader.getFooter().getBlocks().get(0);
BloomFilter bloomFilter =
reader.getBloomFilterDataReader(blockMetaData)
.readBloomFilter(blockMetaData.getColumns().get(0));
- // The exist counts the number of times FindHash returns true.
- int exist = 0;
- while (distinctStrings.size() < totalCount) {
- String str = RandomStringUtils.randomAlphabetic(randomStrLen - 2);
- if (distinctStrings.add(str) &&
+ // The false positive counts the number of times FindHash returns true.
+ int falsePositive = 0;
+ Set<String> distinctStringsForProbe = new HashSet<>();
+ while (distinctStringsForProbe.size() < testBloomFilterCount) {
+ String str = RandomStringUtils.randomAlphabetic(randomStrLen - 1);
Review Comment:
Is there any reason this cannot be `randomStrLen` by the way?
--
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]
