erraggy

class SiteMetricsTable extends HbaseTable[SiteMetricsTable, String, SiteMetricsRow](tableName = "site-metrics", rowKeyClass = classOf[String]) {
    def rowBuilder(result: DeserializedResult) = new SiteMetricsRow(this, result)

    val meta = family[String, String, Any]("meta")
    val name = column(meta, "name", classOf[String])

    val searchMetrics = family[String, DateMidnight, Long]("searchesByDay")
}

class SiteMetricsRow(table: SiteMetricsTable, result: DeserializedResult) extends HRow[SiteMetricsTable, String](result, table)

erraggy

WebCrawlingSchema.WebTable.query2.withKey("http://mycrawledsite.com/crawledpage.html")
            .withColumns(_.title, _.lastCrawled)
            .withFamilies(_.searchMetrics)
            .singleOption() match {
      case Some(pageRow) => {
        println("Title: " + pageRow.column(_.title).getOrElse("No Title"))
        println("Crawled on: " + pageRow.column(_.lastCrawled).getOrElse(new DateTime()))

        pageRow.family(_.searchMetrics).foreach {
          case (date: DateMidnight, views: Long) =>

erraggy

WebCrawlingSchema.WebTable
    .put("http://mycrawledsite.com/crawledpage.html")
    .value(_.title, "My Crawled Page Title")
    .value(_.lastCrawled, new DateTime())
    .value(_.article, "Jonsie went to the store.  She didn't notice the spinning of the Earth, nor did the Earth notice the expansion of the Universe.")
    .value(_.attributes, Map("foo" -> "bar", "custom" -> "data"))
    .valueMap(_.searchMetrics, Map(new DateMidnight(2011, 6, 5) -> 3l, new DateMidnight(2011, 6, 4) -> 34l))
  .execute()

erraggy

class WebTable extends HbaseTable[WebTable, String, WebPageRow](tableName = "pages", rowKeyClass = classOf[String]) {
    def rowBuilder(result: DeserializedResult) = new WebPageRow(this, result)

    val meta = family[String, String, Any]("meta")
    val title = column(meta, "title", classOf[String])
    val lastCrawled = column(meta, "lastCrawled", classOf[DateTime])

    val content = family[String, String, Any]("text", compressed = true)
    val article = column(content, "article", classOf[String])
    val attributes = column(content, "attrs", classOf[Map[String, String]])

erraggy

package object grvxml {
  private[grvxml] val entityRegex = """&\w+;""".r
  
  def forceHexEntities(input: String): String = entityRegex.replaceAllIn(input, m => {
    val matched = m.group(0)
    namedEntityToHexEntity.get(matched) match {
      case Some(replaceWithMe) => replaceWithMe
      case None => matched
    }
  })

erraggy

class SiteMetricsTable extends HbaseTable[SiteMetricsTable, String, SiteMetricsRow](tableName = "site-metrics", rowKeyClass = classOf[String]) {
    def rowBuilder(result: DeserializedResult) = new SiteMetricsRow(this, result)

    val meta = family[String, String, Any]("meta")
    val name = column(meta, "name", classOf[String])

    val searchMetrics = family[String, DateMidnight, Long]("searchesByDay")
}

class SiteMetricsRow(table: SiteMetricsTable, result: DeserializedResult) extends HRow[SiteMetricsTable, String](result, table)

erraggy

WebCrawlingSchema.WebTable.query2.withKey("http://mycrawledsite.com/crawledpage.html")
            .withColumns(_.title, _.lastCrawled)
            .withFamilies(_.searchMetrics)
            .singleOption() match {
      case Some(pageRow) => {
        println("Title: " + pageRow.column(_.title).getOrElse("No Title"))
        println("Crawled on: " + pageRow.column(_.lastCrawled).getOrElse(new DateTime()))

        pageRow.family(_.searchMetrics).foreach {
          case (date: DateMidnight, views: Long) =>

erraggy

WebCrawlingSchema.WebTable
            .put("http://mycrawledsite.com/crawledpage.html")
            .value(_.title, "My Crawled Page Title")
            .value(_.lastCrawled, new DateTime())
            .value(_.article, "Jonsie went to the store.  She didn't notice the spinning of the Earth, nor did the Earth notice the expansion of the Universe.")
            .value(_.attributes, Map("foo" -> "bar", "custom" -> "data"))
            .valueMap(_.searchMetrics, Map(new DateMidnight(2011, 6, 5) -> 3l, new DateMidnight(2011, 6, 4) -> 34l))
            .execute()

erraggy

class WebTable extends HbaseTable[WebTable, String, WebPageRow](tableName = "pages", rowKeyClass = classOf[String]) {
    def rowBuilder(result: DeserializedResult) = new WebPageRow(this, result)

    val meta = family[String, String, Any]("meta")
    val title = column(meta, "title", classOf[String])
    val lastCrawled = column(meta, "lastCrawled", classOf[DateTime])

    val content = family[String, String, Any]("text", compressed = true)
    val article = column(content, "article", classOf[String])
    val attributes = column(content, "attrs", classOf[Map[String, String]])

erraggy

<dependency>
  <groupId>com.gravity</groupId>
  <artifactId>gravity-hpaste</artifactId>
  <version>0.1.11</version>
</dependency>