From 3361fa2a1b2a4245bd75845f096db7f4664ff404 Mon Sep 17 00:00:00 2001
From: Justin Reese <justaddcoffee+github@gmail.com>
Date: Tue, 29 Sep 2020 14:54:59 -0700
Subject: [PATCH] Add template READMEs to the repo, and actually add them to
 builds in Jenkinsfile

---
 Jenkinsfile               |  2 ++
 templates/README.build    | 13 +++++++++++++
 templates/README.toplevel |  6 ++++++
 3 files changed, 21 insertions(+)
 create mode 100644 templates/README.build
 create mode 100644 templates/README.toplevel

diff --git a/Jenkinsfile b/Jenkinsfile
index 42671d32..c1f677c2 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -167,9 +167,11 @@ pipeline {
                                 // stats dir
                                 sh 'mkdir $BUILDSTARTDATE/stats/'
                                 sh 'cp -p *_stats.yaml $BUILDSTARTDATE/stats/'
+                                sh 'cp templates/README.build $BUILDSTARTDATE/README'
 
                                 // make local $S3PROJECTDIR
                                 sh 'mkdir $S3PROJECTDIR'
+                                sh 'cp templates/README.toplevel $S3PROJECTDIR/README'
                                 // add dir for existing builds so they are indexed
                                 // do an s3cmd ls for our project subdir, for each existing build make a local dir in $S3PROJECTDIR
                                 sh "for dir in `s3cmd ls s3://kg-hub-public-data/kg-covid-19/ | grep '\\/\$' | awk '{print \$NF}' | grep -w -v -E 'raw|current' | xargs -n1 basename`; do mkdir -p $S3PROJECTDIR/\$dir; done"
diff --git a/templates/README.build b/templates/README.build
new file mode 100644
index 00000000..99537b7c
--- /dev/null
+++ b/templates/README.build
@@ -0,0 +1,13 @@
+The files in this directory represent a build of the KG-COVID-19 knowledge graph.
+
+These file include:
+	•	Jenkinsfile - the exact command run to produce this build of the KG
+	•	kg-covid-19.jnl.gz - a blazegraph journal that can be loaded to produce a Blazegraph endpoint
+	•	kg-covid-19.nt.gz - an ntriples/RDF version of the KG
+	•	kg-covid-19.tar.gz - a tar.gz file containing the KG in KGX TSV format
+
+The subdirectories in this directory are:
+
+	•	raw - the raw data that was downloaded and transformed to produce this KG
+	•	stats - statistics about this build of the KG in yaml format
+	•	transformed - the transformed subgraphs for each source we ingest
diff --git a/templates/README.toplevel b/templates/README.toplevel
new file mode 100644
index 00000000..06e1b6d9
--- /dev/null
+++ b/templates/README.toplevel
@@ -0,0 +1,6 @@
+The subdirectories here each contain a build of the KG-COVID-19 knowledge graph.
+The directories are named with a timestamp (YYYYMMDD) according to when the build
+was produced. The current/ directory is the most recent build.
+
+See the README in the build directory for a detailed explanation of each file
+contained in that directory.