in src/main/java/com/uber/uberscriptquery/util/SparkUtils.java [57:65]
public static void writeParquet(Dataset<Row> df, String outputPath, SaveMode saveMode, int numPartitions) {
logger.info(String.format("Saving parquet file %s, saveMode: %s, numPartitions: %s", outputPath, saveMode, numPartitions));
String hdfsOutputPath = outputPath;
if (hdfsOutputPath.toLowerCase().startsWith(HDFS_PREFIX_LOWERCASE)) {
hdfsOutputPath = hdfsOutputPath.substring(HDFS_PREFIX_LOWERCASE.length());
}
df.coalesce(numPartitions).write().mode(saveMode).parquet(hdfsOutputPath);
logger.info(String.format("Saved parquet file %s, saveMode: %s, numPartitions: %s", outputPath, saveMode, numPartitions));
}