From bd9c6564a07eb1b5d9c6a25942a198dc3800281b Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 21 Aug 2018 17:14:25 -0700
Subject: add please for keysmissingcolumn

---
 please | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'please')

diff --git a/please b/please
index b32dd79..a5e7f15 100755
--- a/please
+++ b/please
@@ -215,6 +215,30 @@ def run_colcount(args):
             env=args.env)
     subprocess.call(cmd, shell=True)
 
+def run_keysmissingcol(args):
+    if args.rebuild:
+        rebuild_scalding()
+    print("Starting keysmissingcol job...")
+    output = "{}/output-{}/{}-keysmissingcol-{}".format(
+        HDFS_DIR,
+        args.env,
+        datetime.strftime(datetime.now(), "%Y-%m-%d-%H%M.%S"),
+        args.column.replace(":", "_"))
+    cmd = """hadoop jar \
+        scalding/target/scala-2.11/sandcrawler-assembly-0.2.0-SNAPSHOT.jar \
+        com.twitter.scalding.Tool sandcrawler.MissingColDumpJob \
+        --hdfs \
+        --app.conf.path scalding/ia_cluster.conf \
+        --hbase-table wbgrp-journal-extract-0-{env} \
+        --zookeeper-hosts {zookeeper_hosts} \
+        --column {column} \
+        --output {output}""".format(
+            output=output,
+            zookeeper_hosts=ZOOKEEPER_HOSTS,
+            column=args.column,
+            env=args.env)
+    subprocess.call(cmd, shell=True)
+
 def main():
     parser = argparse.ArgumentParser()
 
@@ -264,6 +288,11 @@ def main():
     sub_colcount.add_argument('column',
         help="column name to use in count")
 
+    sub_keysmissingcol = subparsers.add_parser('keys-missing-col')
+    sub_keysmissingcol.set_defaults(func=run_matchcrossref)
+    sub_keysmissingcol.add_argument('column',
+        help="column to SCAN for missing keys")
+
     args = parser.parse_args()
     if not args.__dict__.get("func"):
         print("tell me what to do! (try --help)")
-- 
cgit v1.2.3


From 9557323addb8ab0b7f84dc404e8ef3d76243f13f Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 22 Aug 2018 03:02:06 +0000
Subject: fixes to please keys-missing-col

---
 please | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'please')

diff --git a/please b/please
index a5e7f15..023eeac 100755
--- a/please
+++ b/please
@@ -226,7 +226,7 @@ def run_keysmissingcol(args):
         args.column.replace(":", "_"))
     cmd = """hadoop jar \
         scalding/target/scala-2.11/sandcrawler-assembly-0.2.0-SNAPSHOT.jar \
-        com.twitter.scalding.Tool sandcrawler.MissingColDumpJob \
+        com.twitter.scalding.Tool sandcrawler.MissingColumnDumpJob \
         --hdfs \
         --app.conf.path scalding/ia_cluster.conf \
         --hbase-table wbgrp-journal-extract-0-{env} \
@@ -289,7 +289,7 @@ def main():
         help="column name to use in count")
 
     sub_keysmissingcol = subparsers.add_parser('keys-missing-col')
-    sub_keysmissingcol.set_defaults(func=run_matchcrossref)
+    sub_keysmissingcol.set_defaults(func=run_keysmissingcol)
     sub_keysmissingcol.add_argument('column',
         help="column to SCAN for missing keys")
 
-- 
cgit v1.2.3