Github user denalex commented on a diff in the pull request: https://github.com/apache/incubator-hawq/pull/1209#discussion_r109265306 --- Diff: pxf/pxf-hive/src/main/java/org/apache/hawq/pxf/plugins/hive/HiveORCAccessor.java --- @@ -213,4 +237,40 @@ private boolean buildArgument(SearchArgument.Builder builder, Object filterObj) return true; } + /** + * Fetches file-level statistics from an ORC file. + */ + @Override + public void retrieveStats() throws Exception { + FragmentMetadata fragmentMetadata = Utilities.parseFragmentMetadata(inputData); + /* + * We are using file-level stats therefore if file has multiple splits, + * it's enough to return count for a first split in file. + * In case file has multiple splits - we don't want to duplicate counts. + */ + if (inputData.getFragmentIndex() == 0) + this.count = this.orcReader.getNumberOfRows(); + } + + /** + * Emits tuple without reading from disk, currently supports COUNT + */ + @Override + public OneRow emitAggObject() { + OneRow row = null; + switch (inputData.getAggType()) { + case COUNT: + if (objectsEmitted < count) { + objectsEmitted++; + row = new OneRow(key, data); --- End diff -- as this is likely a dummy object, can you reuse a single object and return it multiple times rather than creating multiple dummy objects ?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---