Created
November 2, 2017 16:33
-
-
Save onastavchuk/42bd7bdd9d368f74ac5676a03e3fbe91 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| fun castDf(df: Dataset<Row>) = | |
| df.withColumn("_tmp", split(col("request"), " ")).select( | |
| col("host"), | |
| unix_timestamp( | |
| col("request_time"), "dd/MMM/yyyy:HH:mm:ss" | |
| ).cast("timestamp").alias("time"), | |
| col("_tmp").getItem(0).alias("verb"), | |
| col("_tmp").getItem(1).alias("resource"), | |
| col("status").cast("short"), | |
| col("bytes") | |
| ).drop("_tmp")!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment