spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From janplus <...@git.apache.org>
Subject [GitHub] spark pull request #14008: [SPARK-16281][SQL] Implement parse_url SQL functi...
Date Fri, 08 Jul 2016 05:56:09 GMT
Github user janplus commented on a diff in the pull request:

    https://github.com/apache/spark/pull/14008#discussion_r70028094
  
    --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
---
    @@ -652,6 +654,152 @@ 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 = children(0) match {
    +    case Literal(url: UTF8String, _) => if (url ne null) getUrl(url) else null
    +    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 = children(2) match {
    +    case Literal(key: UTF8String, _) => if (key ne null) getPattern(key) else null
    +    case _ => null
    +  }
    +
    +  // If the partToExtract is a constant, cache the Extract part function so that we don't
need
    +  // to check the partToExtract for every row.
    +  @transient private lazy val cachedExtractPartFunc = children(1) match {
    +    case Literal(part: UTF8String, _) => getExtractPartFunc(part)
    +    case _ => null
    +  }
    +
    +  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 = {
    +    Pattern.compile(REGEXPREFIX + key.toString + REGEXSUBFIX)
    +  }
    +
    +  private def getUrl(url: UTF8String): URL = {
    +    try {
    +      new URL(url.toString)
    +    } catch {
    +      case e: MalformedURLException => null
    +    }
    +  }
    +
    +  private def getExtractPartFunc(partToExtract: UTF8String): (URL) => String = {
    +    partToExtract match {
    +      case HOST => (url: URL) => url.getHost
    +      case PATH => (url: URL) => url.getPath
    +      case QUERY => (url: URL) => url.getQuery
    +      case REF => (url: URL) => url.getRef
    +      case PROTOCOL => (url: URL) => url.getProtocol
    +      case FILE => (url: URL) => url.getFile
    +      case AUTHORITY => (url: URL) => url.getAuthority
    +      case USERINFO => (url: URL) => url.getUserInfo
    +      case _ => (url: URL) => 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 (cachedExtractPartFunc ne null) {
    +      UTF8String.fromString(cachedExtractPartFunc.apply(url))
    +    } else {
    +      UTF8String.fromString(getExtractPartFunc(partToExtract).apply(url))
    +    }
    +  }
    +
    +  private def parseUrlWithoutKey(url: UTF8String, partToExtract: UTF8String): UTF8String
= {
    +    if (cachedUrl ne null) {
    +      extractFromUrl(cachedUrl, partToExtract)
    +    } else {
    +      val currentUrl = getUrl(url)
    +      if (currentUrl ne null) {
    +        extractFromUrl(currentUrl, partToExtract)
    +      } else {
    +        null
    +      }
    +    }
    +  }
    +
    +  override def eval(input: InternalRow): Any = {
    --- End diff --
    
    Make sense, 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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message