skoppu22 commented on code in PR #220:
URL:
https://github.com/apache/cassandra-analytics/pull/220#discussion_r3530505903
##########
cassandra-analytics-core/src/main/java/org/apache/cassandra/spark/bulkwriter/TableSchema.java:
##########
@@ -308,6 +300,47 @@ private static void
validateDataframeFieldsInTable(TableInfoProvider tableInfo,
Preconditions.checkArgument(unknownFields.isEmpty(), "Unknown fields
in data frame => " + unknownFields);
}
+ /**
+ * Validates secondary index constraints for bulk write operations.
+ * <p>
+ * When the cluster is Cassandra 5.0+ and ALL indexes are SAI, the write
is allowed because
+ * SAI index components are generated alongside SSTables and are
immediately queryable after import.
+ * <p>
+ * When any index is non-SAI (legacy 2i), the write is blocked unless
SKIP_SECONDARY_INDEX_CHECK is set.
+ *
+ * @param tableInfo the table info provider
+ * @param skipSecondaryIndexCheck whether the user explicitly opted out
of the check
+ * @param indexStatements the CREATE INDEX statements for the
table
+ * @param lowestCassandraVersion the lowest Cassandra version in the
cluster
+ */
+ static void validateSecondaryIndexes(TableInfoProvider tableInfo,
+ boolean skipSecondaryIndexCheck,
+ Set<String> indexStatements,
+ String lowestCassandraVersion)
+ {
+ if (!tableInfo.hasSecondaryIndex())
+ {
+ return; // No indexes — nothing to validate
+ }
+
+ if (isSaiWrite(indexStatements, lowestCassandraVersion))
+ {
+ LOGGER.info("Table has SAI indexes on Cassandra 5.0+. SAI index
components will be generated "
+ + "alongside SSTables. indexCount={}",
indexStatements.size());
+ return;
+ }
+
+ if (skipSecondaryIndexCheck)
+ {
+ LOGGER.warn("Bulk writing to tables with SecondaryIndexes will
have an asynchronous index rebuild "
+ + "take place automatically after writing. Reads against
the index during this time "
+ + "window will produce inconsistent or stale results
until index rebuild is complete.");
+ return;
+ }
+
+ throw new UnsupportedAnalyticsOperationException("Bulkwriter doesn't
support secondary indexes");
Review Comment:
Done
##########
cassandra-analytics-core/src/main/java/org/apache/cassandra/spark/bulkwriter/TableSchema.java:
##########
@@ -308,6 +300,47 @@ private static void
validateDataframeFieldsInTable(TableInfoProvider tableInfo,
Preconditions.checkArgument(unknownFields.isEmpty(), "Unknown fields
in data frame => " + unknownFields);
}
+ /**
+ * Validates secondary index constraints for bulk write operations.
+ * <p>
+ * When the cluster is Cassandra 5.0+ and ALL indexes are SAI, the write
is allowed because
+ * SAI index components are generated alongside SSTables and are
immediately queryable after import.
+ * <p>
+ * When any index is non-SAI (legacy 2i), the write is blocked unless
SKIP_SECONDARY_INDEX_CHECK is set.
+ *
+ * @param tableInfo the table info provider
+ * @param skipSecondaryIndexCheck whether the user explicitly opted out
of the check
+ * @param indexStatements the CREATE INDEX statements for the
table
+ * @param lowestCassandraVersion the lowest Cassandra version in the
cluster
+ */
+ static void validateSecondaryIndexes(TableInfoProvider tableInfo,
Review Comment:
Done
--
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]
