Github user janplus commented on a diff in the pull request: https://github.com/apache/spark/pull/14008#discussion_r69385193 --- Diff: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala --- @@ -725,4 +725,51 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper { checkEvaluation(FindInSet(Literal("abf"), Literal("abc,b,ab,c,def")), 0) checkEvaluation(FindInSet(Literal("ab,"), Literal("abc,b,ab,c,def")), 0) } + + test("ParseUrl") { + def checkParseUrl(expected: String, urlStr: String, partToExtract: String): Unit = { + checkEvaluation( + ParseUrl(Seq(Literal.create(urlStr, StringType), + Literal.create(partToExtract, StringType))), expected) + } + def checkParseUrlWithKey( + expected: String, urlStr: String, + partToExtract: String, key: String): Unit = { + checkEvaluation( + ParseUrl(Seq(Literal.create(urlStr, StringType), Literal.create(partToExtract, StringType), + Literal.create(key, StringType))), expected) + } + + checkParseUrl("spark.apache.org", "http://spark.apache.org/path?query=1", "HOST") + checkParseUrl("/path", "http://spark.apache.org/path?query=1", "PATH") + checkParseUrl("query=1", "http://spark.apache.org/path?query=1", "QUERY") + checkParseUrl("Ref", "http://spark.apache.org/path?query=1#Ref", "REF") + checkParseUrl("http", "http://spark.apache.org/path?query=1", "PROTOCOL") + checkParseUrl("/path?query=1", "http://spark.apache.org/path?query=1", "FILE") + checkParseUrl("spark.apache.org:8080", "http://spark.apache.org:8080/path?query=1", "AUTHORITY") + checkParseUrl("userinfo", "http://useri...@spark.apache.org/path?query=1", "USERINFO") + checkParseUrlWithKey("1", "http://spark.apache.org/path?query=1", "QUERY", "query") + + // Null checking + checkParseUrl(null, null, "HOST") + checkParseUrl(null, "http://spark.apache.org/path?query=1", null) + checkParseUrl(null, null, null) + checkParseUrl(null, "test", "HOST") + checkParseUrl(null, "http://spark.apache.org/path?query=1", "NO") + checkParseUrlWithKey(null, "http://spark.apache.org/path?query=1", "HOST", "query") + checkParseUrlWithKey(null, "http://spark.apache.org/path?query=1", "QUERY", "quer") + checkParseUrlWithKey(null, "http://spark.apache.org/path?query=1", "QUERY", null) + checkParseUrlWithKey(null, "http://spark.apache.org/path?query=1", "QUERY", "") + + // exceptional cases + intercept[java.util.regex.PatternSyntaxException] { --- End diff -- Hi, @dongjoon-hyun It seems only when `url`, `partToExtract` and `key` is all `Literal`, then hive may give a `SemanticException`. > hive> select * from url_parse_data; OK http://spark/path? QUERY ??? Time taken: 0.054 seconds, Fetched: 1 row(s) > hive> select parse_url("http://spark/path?", "QUERY", "???") from url_parse_data; FAILED: SemanticException [Error 10014]: Line 1:7 Wrong arguments '"???"': org.apache.hadoop.hive.ql.metadata.HiveException: Unable to execute method public java.lang.String org.apache.hadoop.hive.ql.udf.UDFParseUrl.evaluate(java.lang.String,java.lang.String,java.lang.String) on object org.apache.hadoop.hive.ql.udf.UDFParseUrl@59e082f8 of class org.apache.hadoop.hive.ql.udf.UDFParseUrl with arguments {http://spark/path?:java.lang.String, QUERY:java.lang.String, ???:java.lang.String} of size 3 > hive> select parse_url(url, "QUERY", "???") from url_parse_data; OK Failed with exception java.io.IOException:org.apache.hadoop.hive.ql.metadata.HiveException: Unable to execute method public java.lang.String org.apache.hadoop.hive.ql.udf.UDFParseUrl.evaluate(java.lang.String,java.lang.String,java.lang.String) on object org.apache.hadoop.hive.ql.udf.UDFParseUrl@7d1f3fe9 of class org.apache.hadoop.hive.ql.udf.UDFParseUrl with arguments {http://spark/path?:java.lang.String, QUERY:java.lang.String, ???:java.lang.String} of size 3 > hive> select parse_url("http://spark/path?", part, "???") from url_parse_data; OK Failed with exception java.io.IOException:org.apache.hadoop.hive.ql.metadata.HiveException: Unable to execute method public java.lang.String org.apache.hadoop.hive.ql.udf.UDFParseUrl.evaluate(java.lang.String,java.lang.String,java.lang.String) on object org.apache.hadoop.hive.ql.udf.UDFParseUrl@37fef327 of class org.apache.hadoop.hive.ql.udf.UDFParseUrl with arguments {http://spark/path?:java.lang.String, QUERY:java.lang.String, ???:java.lang.String} of size 3 > hive> select parse_url("http://spark/path?", "QUERY", key) from url_parse_data; OK Failed with exception java.io.IOException:org.apache.hadoop.hive.ql.metadata.HiveException: Unable to execute method public java.lang.String org.apache.hadoop.hive.ql.udf.UDFParseUrl.evaluate(java.lang.String,java.lang.String,java.lang.String) on object org.apache.hadoop.hive.ql.udf.UDFParseUrl@1d944fc0 of class org.apache.hadoop.hive.ql.udf.UDFParseUrl with arguments {http://spark/path?:java.lang.String, QUERY:java.lang.String, ???:java.lang.String} of size 3 Given that, it seems not that valuable to do this optimization.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org