61yao commented on code in PR #9265:
URL: https://github.com/apache/pinot/pull/9265#discussion_r953221591
##########
pinot-plugins/pinot-batch-ingestion/pinot-batch-ingestion-spark-3.2/src/main/java/org/apache/pinot/plugin/ingestion/batch/spark3/SparkSegmentGenerationJobRunner.java:
##########
@@ -128,14 +126,6 @@ public void run()
for (PinotFSSpec pinotFSSpec : pinotFSSpecs) {
PinotFSFactory.register(pinotFSSpec.getScheme(),
pinotFSSpec.getClassName(), new PinotConfiguration(pinotFSSpec));
}
-
- //Get pinotFS for input
Review Comment:
Done
##########
pinot-common/src/main/java/org/apache/pinot/common/segment/generation/SegmentGenerationUtils.java:
##########
@@ -229,4 +233,63 @@ private static String fetchUrl(URL url, String authToken)
}
return IOUtils.toString(connection.getInputStream(),
StandardCharsets.UTF_8);
}
+
+
+ /**
+ * Find matching files from root directory specified in fileUri.
+ * If includePattern and excludePattern are not null, get all the files that
match includePattern and exclude files
+ * that match excludePattern.
+ * If
+ *
+ * @param pinotFs root directly fs
+ * @param fileUri root directly uri
+ * @param includePattern optional glob patterns for files to include
+ * @param excludePattern optional glob patterns for files to exclude
+ * @param searchRecrusively if ture, search files recursively from directory
specified in fileUri
+ * @return list of matching files.
+ * @throws IOException on IO failure for list files in root directory.
+ * @throws URISyntaxException for matching file URIs
+ * @throws RuntimeException if there is no matching file.
+ */
+ public static List<String> listMatchedFilesWithRecursiveOption(PinotFS
pinotFs, URI fileUri, String includePattern,
Review Comment:
Done
##########
pinot-spi/src/main/java/org/apache/pinot/spi/ingestion/batch/BatchConfig.java:
##########
@@ -32,6 +32,7 @@ public class BatchConfig {
private final FileFormat _inputFormat;
private final String _inputDirURI;
+ private final boolean _searchRecursively;
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]
