Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/14008#discussion_r69850899
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
---
@@ -652,6 +654,160 @@ case class StringRPad(str: Expression, len:
Expression, pad: Expression)
override def prettyName: String = "rpad"
}
+object ParseUrl {
+ private val HOST = UTF8String.fromString("HOST")
+ private val PATH = UTF8String.fromString("PATH")
+ private val QUERY = UTF8String.fromString("QUERY")
+ private val REF = UTF8String.fromString("REF")
+ private val PROTOCOL = UTF8String.fromString("PROTOCOL")
+ private val FILE = UTF8String.fromString("FILE")
+ private val AUTHORITY = UTF8String.fromString("AUTHORITY")
+ private val USERINFO = UTF8String.fromString("USERINFO")
+ private val REGEXPREFIX = "(&|^)"
+ private val REGEXSUBFIX = "=([^&]*)"
+}
+
+/**
+ * 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.
+ Key specifies which query to extract.
+ Examples:
+ > SELECT _FUNC_('http://spark.apache.org/path?query=1', 'HOST')
+ 'spark.apache.org'
+ > SELECT _FUNC_('http://spark.apache.org/path?query=1', 'QUERY')
+ 'query=1'
+ > SELECT _FUNC_('http://spark.apache.org/path?query=1', 'QUERY',
'query')
+ '1'""")
+case class ParseUrl(children: Seq[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
+ override def prettyName: String = "parse_url"
+
+ // If the url is a constant, cache the URL object so that we don't need
to convert url
+ // from UTF8String to String to URL for every row.
+ @transient private lazy val cachedUrl = stringExprs(0) match {
+ case Literal(url: UTF8String, _) => getUrl(url)
+ case _ => null
+ }
+
+ // If the key is a constant, cache the Pattern object so that we don't
need to convert key
+ // from UTF8String to String to StringBuilder to String to Pattern for
every row.
+ @transient private lazy val cachedPattern = stringExprs(2) match {
+ case Literal(key: UTF8String, _) => getPattern(key)
+ case _ => null
+ }
+
+ private lazy val stringExprs = children.toArray
+ import ParseUrl._
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (children.size > 3 || children.size < 2) {
+ TypeCheckResult.TypeCheckFailure(s"$prettyName function requires two
or three arguments")
+ } else {
+ super[ImplicitCastInputTypes].checkInputDataTypes()
+ }
+ }
+
+ private def getPattern(key: UTF8String): Pattern = {
+ if (key != null) {
+ Pattern.compile(REGEXPREFIX + key.toString + REGEXSUBFIX)
+ } else {
+ null
+ }
+ }
+
+ private def getUrl(url: UTF8String): URL = {
+ try {
+ new URL(url.toString)
+ } catch {
+ case e: MalformedURLException => null
+ }
+ }
+
+ private def extractValueFromQuery(query: UTF8String, pattern: Pattern):
UTF8String = {
+ val m = pattern.matcher(query.toString)
+ if (m.find()) {
+ UTF8String.fromString(m.group(2))
+ } else {
+ null
+ }
+ }
+
+ private def extractFromUrl(url: URL, partToExtract: UTF8String):
UTF8String = {
+ if (partToExtract.equals(HOST)) {
+ UTF8String.fromString(url.getHost)
+ } else if (partToExtract.equals(PATH)) {
+ UTF8String.fromString(url.getPath)
+ } else if (partToExtract.equals(QUERY)) {
+ UTF8String.fromString(url.getQuery)
+ } else if (partToExtract.equals(REF)) {
+ UTF8String.fromString(url.getRef)
+ } else if (partToExtract.equals(PROTOCOL)) {
+ UTF8String.fromString(url.getProtocol)
+ } else if (partToExtract.equals(FILE)) {
+ UTF8String.fromString(url.getFile)
+ } else if (partToExtract.equals(AUTHORITY)) {
+ UTF8String.fromString(url.getAuthority)
+ } else if (partToExtract.equals(USERINFO)) {
+ UTF8String.fromString(url.getUserInfo)
+ } else {
+ null
+ }
+ }
+
+ private def parseUrlWithoutKey(url: UTF8String, partToExtract:
UTF8String): UTF8String = {
+ if (url != null && partToExtract != null) {
+ if (cachedUrl ne null) {
+ extractFromUrl(cachedUrl, partToExtract)
+ } else {
+ val currentUrl = getUrl(url)
+ if (currentUrl ne null) {
+ extractFromUrl(currentUrl, partToExtract)
+ } else {
+ null
+ }
+ }
+ } else {
+ null
+ }
+ }
+
+ override def eval(input: InternalRow): Any = {
+ val url = stringExprs(0).eval(input).asInstanceOf[UTF8String]
+ val partToExtract = stringExprs(1).eval(input).asInstanceOf[UTF8String]
+ if (stringExprs.size == 2) {
+ parseUrlWithoutKey(url, partToExtract)
+ } else { // QUERY with key
+ if (QUERY.equals(partToExtract)) {
--- End diff --
in scala we can just use `==`, it's same with equals
---
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
