aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-29 11:01:14 -0700
committerBryan Newbold <bnewbold@archive.org>2018-05-29 11:01:14 -0700
commitc14676635f39dd1bc0345e4df2d1fa06c298bfd7 (patch)
tree4fcdfc2aa27f56973b68a9cad32f4a0120b9a756 /scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
parent62bfc9d5f40ccd690b4b070d64d046fb6b1e3e8a (diff)
downloadsandcrawler-c14676635f39dd1bc0345e4df2d1fa06c298bfd7.tar.gz
sandcrawler-c14676635f39dd1bc0345e4df2d1fa06c298bfd7.zip
HBaseRowCountJob actually counts rows
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala13
1 files changed, 2 insertions, 11 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))
}