Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/14008#discussion_r69264464
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
---
@@ -653,6 +655,128 @@ case class StringRPad(str: Expression, len:
Expression, pad: Expression)
}
/**
+ * Extracts a part from a URL
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(url, partToExtract[, key]) - extracts a part from a URL",
+ extended = "Parts: HOST, PATH, QUERY, REF, PROTOCOL, AUTHORITY, FILE,
USERINFO\n"
+ + "key specifies which query to extract\n"
+ + "Examples:\n"
+ + " > SELECT _FUNC_('http://spark.apache.org/path?query=1', "
+ + "'HOST') FROM src LIMIT 1;\n" + " 'spark.apache.org'\n"
+ + " > SELECT _FUNC_('http://spark.apache.org/path?query=1', "
+ + "'QUERY') FROM src LIMIT 1;\n" + " 'query=1'\n"
+ + " > SELECT _FUNC_('http://spark.apache.org/path?query=1', "
+ + "'QUERY', 'query') FROM src LIMIT 1;\n" + " '1'")
+case class ParseUrl(children: Expression*)
+ extends Expression with ImplicitCastInputTypes with CodegenFallback {
+
+ override def nullable: Boolean = true
+
+ override def inputTypes: Seq[DataType] =
Seq.fill(children.size)(StringType)
+ override def dataType: DataType = StringType
+
+ private lazy val stringExprs = children.toArray
+ @transient private var lastUrlStr: UTF8String = _
+ @transient private var lastUrl: URL = _
+ // last key in string, we will update the pattern if key value changed.
+ @transient private var lastKey: UTF8String = _
+ // last regex pattern, we cache it for performance concern
+ @transient private var pattern: Pattern = _
+ private lazy val HOST: UTF8String = UTF8String.fromString("HOST")
+ private lazy val PATH: UTF8String = UTF8String.fromString("PATH")
+ private lazy val QUERY: UTF8String = UTF8String.fromString("QUERY")
+ private lazy val REF: UTF8String = UTF8String.fromString("REF")
+ private lazy val PROTOCOL: UTF8String = UTF8String.fromString("PROTOCOL")
+ private lazy val FILE: UTF8String = UTF8String.fromString("FILE")
+ private lazy val AUTHORITY: UTF8String =
UTF8String.fromString("AUTHORITY")
+ private lazy val USERINFO: UTF8String = UTF8String.fromString("USERINFO")
+ private lazy val REGEXPREFIX: String = "[&^]?"
+ private lazy val REGEXSUBFIX: String = "=([^&]*)"
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (children.size > 3 || children.size < 2) {
+ TypeCheckResult.TypeCheckFailure("parse_url function requires two or
three arguments")
+ } else {
+ super[ImplicitCastInputTypes].checkInputDataTypes()
+ }
+ }
+
+ def parseUrlWithoutKey(url: Any, partToExtract: Any): Any = {
+ if (url == null || partToExtract == null) {
+ null
+ } else {
+ if (lastUrlStr == null || !url.equals(lastUrlStr)) {
+ try {
+ lastUrlStr = url.asInstanceOf[UTF8String].clone()
+ lastUrl = new URL(url.toString)
+ } catch {
+ case ex: MalformedURLException => return null
--- End diff --
We can use the following like Hive uses `Exception`. `SecurityException`
occurs possibly as a `RuntimeException`.
```
case NonFatal(_) =>
```
---
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
