please support for grobid-scorable-dump

1 files changed, 24 insertions, 0 deletions

diff --git a/please b/please
index 1a992f2..0cc4b72 100755
--- a/please
+++ b/please
@@ -144,6 +144,27 @@ def run_matchcrossref(args):
             crossref_input=args.crossref_input)
     subprocess.call(cmd, shell=True)
 
+def run_grobidscorabledump(args):
+    if args.rebuild:
+        rebuild_scalding()
+    print("Starting grobid-scorable-dump job...")
+    output = "{}/output-{}/{}-grobidscorabledump".format(
+        HDFS_DIR,
+        args.env,
+        datetime.strftime(datetime.now(), "%Y-%m-%d-%H%M.%S"))
+    cmd = """hadoop jar \
+        scalding/target/scala-2.11/sandcrawler-assembly-0.2.0-SNAPSHOT.jar \
+        com.twitter.scalding.Tool sandcrawler.GrobidScorableDumpJob \
+        --hdfs \
+        --app.conf.path scalding/ia_cluster.conf \
+        --hbase-table wbgrp-journal-extract-0-{env} \
+        --zookeeper-hosts {zookeeper_hosts} \
+        --output {output}""".format(
+            output=output,
+            zookeeper_hosts=ZOOKEEPER_HOSTS,
+            env=args.env)
+    subprocess.call(cmd, shell=True)
+
 def main():
     parser = argparse.ArgumentParser()
 
@@ -182,6 +203,9 @@ def main():
         help="number of reducers to run",
         type=int, default=30)
 
+    sub_grobidscorabledump = subparsers.add_parser('grobid-scorable-dump')
+    sub_grobidscorabledump.set_defaults(func=run_grobidscorabledump)
+
 
     args = parser.parse_args()
     if not args.__dict__.get("func"):