From 7c49fecd01cbd89bb5987442b89a4aafc1186ff9 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Mon, 20 Aug 2018 18:50:07 -0700
Subject: make col counter generic

---
 please                                             | 28 ++++++++++++++++
 .../scala/sandcrawler/GrobidMetadataCountJob.scala | 36 ---------------------
 .../main/scala/sandcrawler/HBaseColCountJob.scala  | 37 ++++++++++++++++++++++
 3 files changed, 65 insertions(+), 36 deletions(-)
 delete mode 100644 scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala
 create mode 100644 scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala

diff --git a/please b/please
index 0cc4b72..8a46978 100755
--- a/please
+++ b/please
@@ -165,6 +165,30 @@ def run_grobidscorabledump(args):
             env=args.env)
     subprocess.call(cmd, shell=True)
 
+def run_colcount(args):
+    if args.rebuild:
+        rebuild_scalding()
+    print("Starting colcount job...")
+    output = "{}/output-{}/{}-colcount-{}".format(
+        HDFS_DIR,
+        args.env,
+        datetime.strftime(datetime.now(), "%Y-%m-%d-%H%M.%S"),
+        args.column)
+    cmd = """hadoop jar \
+        scalding/target/scala-2.11/sandcrawler-assembly-0.2.0-SNAPSHOT.jar \
+        com.twitter.scalding.Tool sandcrawler.HBaseColCountJob \
+        --hdfs \
+        --app.conf.path scalding/ia_cluster.conf \
+        --hbase-table wbgrp-journal-extract-0-{env} \
+        --zookeeper-hosts {zookeeper_hosts} \
+        --column {column} \
+        --output {output}""".format(
+            column=args.column,
+            output=output,
+            zookeeper_hosts=ZOOKEEPER_HOSTS,
+            env=args.env)
+    subprocess.call(cmd, shell=True)
+
 def main():
     parser = argparse.ArgumentParser()
 
@@ -206,6 +230,10 @@ def main():
     sub_grobidscorabledump = subparsers.add_parser('grobid-scorable-dump')
     sub_grobidscorabledump.set_defaults(func=run_grobidscorabledump)
 
+    sub_colcount = subparsers.add_parser('col-count')
+    sub_colcount.set_defaults(func=run_colcount)
+    sub_colcount.add_argument('column',
+        help="column name to use in count")
 
     args = parser.parse_args()
     if not args.__dict__.get("func"):
diff --git a/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala b/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala
deleted file mode 100644
index 08f3340..0000000
--- a/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala
+++ /dev/null
@@ -1,36 +0,0 @@
-package sandcrawler
-
-import java.util.Properties
-
-import cascading.property.AppProps
-import cascading.tuple.Fields
-import com.twitter.scalding._
-import parallelai.spyglass.base.JobBase
-import parallelai.spyglass.hbase.HBaseConstants.SourceMode
-import parallelai.spyglass.hbase.HBasePipeConversions
-import parallelai.spyglass.hbase.HBaseSource
-
-class GrobidMetadataCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
-
-  val output = args("output")
-
-  GrobidMetadataCountJob.getHBaseSource(
-    args("hbase-table"),
-    args("zookeeper-hosts"))
-    .read
-    .debug
-    .groupAll { _.size('count) }
-    .write(Tsv(output))
-}
-
-object GrobidMetadataCountJob {
-
-  // eg, "wbgrp-journal-extract-0-qa",7 "mtrcs-zk1.us.archive.org:2181"
-  def getHBaseSource(hbaseTable: String, zookeeperHosts: String) : HBaseSource = {
-    HBaseBuilder.build(
-      hbaseTable,
-      zookeeperHosts,
-      List("grobid0:metadata"),
-      SourceMode.SCAN_ALL)
-  }
-}
diff --git a/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala
new file mode 100644
index 0000000..a007339
--- /dev/null
+++ b/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala
@@ -0,0 +1,37 @@
+package sandcrawler
+
+import java.util.Properties
+
+import cascading.property.AppProps
+import cascading.tuple.Fields
+import com.twitter.scalding._
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+import parallelai.spyglass.hbase.HBasePipeConversions
+import parallelai.spyglass.hbase.HBaseSource
+
+class HBaseColCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
+
+  val output = args("output")
+
+  HBaseColCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"),
+    args("column")
+    .read
+    .debug
+    .groupAll { _.size('count) }
+    .write(Tsv(output))
+}
+
+object HBaseColCountJob {
+
+  // eg, "wbgrp-journal-extract-0-qa",7 "mtrcs-zk1.us.archive.org:2181"
+  def getHBaseSource(hbaseTable: String, zookeeperHosts: String, col: String) : HBaseSource = {
+    HBaseBuilder.build(
+      hbaseTable,
+      zookeeperHosts,
+      List(col),
+      SourceMode.SCAN_ALL)
+  }
+}
-- 
cgit v1.2.3