Changed merge_xml.py

David Bruce Borenstein · David Bruce Borenstein · commit 4d79557a2f45 · 2017-11-29T19:50:14.000Z
diff --git a/python/merge_xml.py b/python/merge_xml.py
@@ -18,7 +18,7 @@
 ### Handle command line arguments
 
 parser = argparse.ArgumentParser()
-parser.add_argument("--input", action="store", help="Path to Parquet file containing xpath-value pairs.", default = "990_long/parsed")
+parser.add_argument("--input", action="append", help="Path to Parquet file containing xpath-value pairs.")
 parser.add_argument("--output", action="store", help="Path in which to store result. Can be local or S3.")
 parser.add_argument("--timestamp", action="store_true", help="If true, append the timestamp to the output path.")
 parser.add_argument("--partitions", type=int, action="store", help="Number of partitions to use for the join.", default=400)
@@ -42,7 +42,7 @@
                 col("location_code").alias("location"))
 
 standardize = udf(lambda xpath : "/Return/" + xpath.strip(), StringType())
-df = spark.read.parquet(args.input) \
+df = spark.read.parquet(*args.input) \
         .repartition(args.partitions) \
         .withColumn("xpath", standardize(col("xpath"))) \
 
