Github user janplus commented on a diff in the pull request: https://github.com/apache/spark/pull/14008#discussion_r69264274 --- 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") --- End diff -- Yes, you are right. I'll fix this.
--- 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