dongjoon-hyun commented on code in PR #2601:
URL: https://github.com/apache/orc/pull/2601#discussion_r3119703792
##########
java/tools/src/java/org/apache/orc/tools/MergeFiles.java:
##########
@@ -56,27 +60,60 @@ public static void main(Configuration conf, String[] args)
throws Exception {
}
boolean ignoreExtension = cli.hasOption("ignoreExtension");
- List<Path> inputFiles = new ArrayList<>();
- OrcFile.WriterOptions writerOptions = OrcFile.writerOptions(conf);
+ long maxSizeBytes = 0;
+ if (cli.hasOption("maxSize")) {
+ try {
+ maxSizeBytes = Long.parseLong(cli.getOptionValue("maxSize"));
+ } catch (NumberFormatException e) {
+ System.err.println("--maxSize requires a numeric value in bytes.");
+ System.exit(1);
+ }
+ if (maxSizeBytes <= 0) {
+ System.err.println("--maxSize must be a positive number of bytes.");
+ System.exit(1);
+ }
+ }
+ List<LocatedFileStatus> inputStatuses = new ArrayList<>();
String[] files = cli.getArgs();
for (String root : files) {
Path rootPath = new Path(root);
FileSystem fs = rootPath.getFileSystem(conf);
for (RemoteIterator<LocatedFileStatus> itr = fs.listFiles(rootPath,
true); itr.hasNext(); ) {
LocatedFileStatus status = itr.next();
if (status.isFile() && (ignoreExtension ||
status.getPath().getName().endsWith(".orc"))) {
- inputFiles.add(status.getPath());
+ inputStatuses.add(status);
}
}
}
- if (inputFiles.isEmpty()) {
+ if (inputStatuses.isEmpty()) {
System.err.println("No files found.");
System.exit(1);
}
- List<Path> mergedFiles = OrcFile.mergeFiles(
- new Path(outputFilename), writerOptions, inputFiles);
+ List<Path> inputFiles = new ArrayList<>(inputStatuses.size());
+ for (LocatedFileStatus s : inputStatuses) {
+ inputFiles.add(s.getPath());
+ }
Review Comment:
Shall we sort `inputFiles` here by path to be more deterministic?
--
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]
