erraggy

SELECT  [Subject], PostDate, FormattedBody, 
          dbo.old_url(PostDate, [Subject]) AS old_url, 
          dbo.make_slug([Subject]) AS slug
FROM  dbo.cs_Posts
WHERE   UserID = 2102 
  AND   SectionID = 4 
  AND   PostLevel = 1 
  AND   IsApproved = 1 
  AND   IsLocked = 0

erraggy

CREATE FUNCTION [dbo].[make_slug]
(
	@post_title nvarchar(256)
)
RETURNS nvarchar(500)
AS
BEGIN
	-- Declare the return variable here
	DECLARE @slug nvarchar(500)
	DECLARE @clean_title nvarchar(500)

erraggy

CREATE FUNCTION [dbo].[old_url]
(
	@post_date datetime,
	@post_title nvarchar(256)
)
RETURNS nvarchar(500)
AS
BEGIN
	-- Declare the return variable here
	DECLARE @url nvarchar(500)

erraggy

CREATE FUNCTION [dbo].[removePunctuation] 
(
	@input nvarchar(500)
)
RETURNS nvarchar(500)
AS
BEGIN
	/**
	 *  Based on Nigel Rivett's SQL script found: 
	 *    http://www.nigelrivett.net/SQLTsql/RemoveNonNumericCharacters.html 

erraggy

CREATE FUNCTION [dbo].[deDupeSpaces] 
(
	@input nvarchar(500)
)
RETURNS nvarchar(500)
AS
BEGIN
    /**
    *  Based on Nigel Rivett's SQL script found: 
    *    http://www.nigelrivett.net/SQLTsql/RemoveNonNumericCharacters.html 

erraggy

INSERT INTO wp_xxxxx_posts 
	(post_author, 
	post_date, 
	post_date_gmt, 
	post_content, 
	post_title, 
	post_status, 
	post_name, 
	post_modified, 
	post_modified_gmt, 

erraggy

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

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

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

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) =>