From 63186a218e2e10848d4b014eacbc4ad3a51a20ca Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 29 Mar 2018 11:59:28 -0700
Subject: init repo

---
 .gitignore | 21 +++++++++++++++++++++
 README.md  |  9 +++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 README.md

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..81a4762
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,21 @@
+*.o
+*.a
+*.pyc
+#*#
+*~
+*.swp
+.*
+*.tmp
+*.old
+*.profile
+*.bkp
+*.bak
+[Tt]humbs.db
+*.DS_Store
+build/
+_build/
+src/build/
+*.log
+
+# Don't ignore this file itself
+!.gitignore
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..6ea387f
--- /dev/null
+++ b/README.md
@@ -0,0 +1,9 @@
+
+This repo contains hadoop tasks (mapreduce and pig), luigi jobs, and other
+scripts and code for the journal ingest pipeline.
+
+This repository is potentially public. Maybe we'll rename it "sandcrawler"?
+
+Archive-specific deployment/production guides and ansible scripts at:
+[journal-infra](https://git.archive.org/bnewbold/journal-infra)
+
-- 
cgit v1.2.3