[SPARK-16281][SQL] Implement parse_url SQL function

## What changes were proposed in this pull request?

This PR adds parse_url SQL functions in order to remove Hive fallback.

A new implementation of #13999

## How was this patch tested?

Pass the exist tests including new testcases.

Author: wujian <jan.chou.wu@gmail.com>

Closes #14008 from janplus/SPARK-16281.

1 files changed, 15 insertions, 0 deletions

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
index 044ac22328..f509551b1e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
@@ -228,6 +228,21 @@ class StringFunctionsSuite extends QueryTest with SharedSQLContext {
       Row("???hi", "hi???", "h", "h"))
   }
 
+  test("string parse_url function") {
+    val df = Seq[String](("http://userinfo@spark.apache.org/path?query=1#Ref"))
+      .toDF("url")
+
+    checkAnswer(
+      df.selectExpr(
+        "parse_url(url, 'HOST')", "parse_url(url, 'PATH')",
+        "parse_url(url, 'QUERY')", "parse_url(url, 'REF')",
+        "parse_url(url, 'PROTOCOL')", "parse_url(url, 'FILE')",
+        "parse_url(url, 'AUTHORITY')", "parse_url(url, 'USERINFO')",
+        "parse_url(url, 'QUERY', 'query')"),
+      Row("spark.apache.org", "/path", "query=1", "Ref",
+        "http", "/path?query=1", "userinfo@spark.apache.org", "userinfo", "1"))
+  }
+
   test("string repeat function") {
     val df = Seq(("hi", 2)).toDF("a", "b")