From c14676635f39dd1bc0345e4df2d1fa06c298bfd7 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 29 May 2018 11:01:14 -0700 Subject: HBaseRowCountJob actually counts rows --- scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala | 13 ++----------- scalding/src/test/scala/sandcrawler/HBaseRowCountTest.scala | 8 ++++++-- 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala index 5df6b2e..98da239 100644 --- a/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala +++ b/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala @@ -27,15 +27,6 @@ class HBaseRowCountJob(args: Args) extends JobBase(args) with HBasePipeConversio sourceMode = SourceMode.GET_LIST, keyList = List("sha1:K2DKSSVTXWPRMFDTWSTCQW3RVWRIOV3Q", "sha1:C3YNNEGH5WAG5ZAAXWAEBNXJWT6CZ3WU")) .read .debug - .fromBytesWritable(new Fields("key")) - .write(Tsv(output format "get_list")) - - /* - List("column_family"), - sourceMode = SourceMode.SCAN_ALL) - .read - .debug - .fromBytesWritable(new Fields("key")) - .write(Tsv(output format "get_list")) - */ + .groupAll { _.size('count) } + .write(Tsv(output)) } diff --git a/scalding/src/test/scala/sandcrawler/HBaseRowCountTest.scala b/scalding/src/test/scala/sandcrawler/HBaseRowCountTest.scala index 598f45d..ac7cf18 100644 --- a/scalding/src/test/scala/sandcrawler/HBaseRowCountTest.scala +++ b/scalding/src/test/scala/sandcrawler/HBaseRowCountTest.scala @@ -46,11 +46,15 @@ class HBaseRowCountTest extends FunSpec with TupleConversions { sampleData.map(l => new Tuple(l.map(s => {new ImmutableBytesWritable(Bytes.toBytes(s))}):_*))) .sink[Tuple](Tsv(output format "get_list")) { outputBuffer => - log.debug("Output => " + outputBuffer) it("should return the test data provided.") { println("outputBuffer.size => " + outputBuffer.size) - assert(outputBuffer.size === 2) + assert(outputBuffer.size === 1) + } + + it("should return the correct count") { + println("raw output => " + outputBuffer) + assert(outputBuffer(0).getObject(0) === 2) } } .run -- cgit v1.2.3