Dataloader move to universal from gpii-ops/gpii-dataloader

Dockerfile

@@ -4,6 +4,7 @@ WORKDIR /app
 COPY . /app
 
 RUN apk add --no-cache --virtual build-dependencies python make git g++ && \
+    apk add --no-cache curl jq && \
     npm install && \
     chown -R node:node . && \
     npm cache clean --force && \

documentation/DataLoader.md

@@ -0,0 +1,66 @@
+# CouchDB Data Loader
+
+(`scripts/deleteAndLoadSnapsets.sh`)
+
+This script is used to setup CouchDB database and is executed as a Kubernetes batch Job every time new version of the
+universal image is deployed to the cluster (also when cluster is initially created).
+
+It does following:
+
+- Converts the preferences in universal into `snapset` Prefs Safes and GPII Keys,
+- Optionally deletes existing database,
+- Creates a CouchDB database if none exits,
+- Updates the database with respect to its `design/views` document, as required,
+- Loads the latest snapsets created into the database.
+
+## Environment Variables
+
+- `COUCHDB_URL`: URL of the CouchDB database. (required)
+- `CLEAR_INDEX`: If set to `true`, the database at $COUCHDB_URL will be deleted and recreated. (optional)
+- `STATIC_DATA_DIR`: The directory where the static data to be loaded into CouchDB resides. (optional)
+- `BUILD_DATA_DIR`: The directory where the data built from the conversion step resides. (optional)
+
+The use of environment variables for data directories is useful if you want to mount the database data using a Docker
+volume and point the data loader at it.
+
+Note that since [the docker doesn't support the environment variable type of
+array](https://github.com/moby/moby/issues/20169), two separate environment variables are used for inputting data
+directories instead of one array that holds these directories.
+
+## Running
+
+Example using containers:
+
+```bash
+$ docker run -d -p 5984:5984 --name couchdb couchdb
+$ docker run --rm --link couchdb -e COUCHDB_URL=http://couchdb:5984/gpii \
+    -e CLEAR_INDEX=true vagrant-universal scripts/deleteAndLoadSnapsets.sh
+$ docker run -d -p 8081:8081 --name preferences --link couchdb \
+    -e NODE_ENV=gpii.config.preferencesServer.standalone.production \
+    -e PREFERENCESSERVER_LISTEN_PORT=8081 -e DATASOURCE_HOSTNAME=http://couchdb \
+    -e DATASOURCE_PORT=5984 vagrant-universal
+```
+
+Below are two versions of loading couchdb data from a different location (e.g.
+/home/vagrant/sync/universal/testData/dbData for static data directory and /home/vagrant/sync/universal/build/dbData for
+build data directory).  The first version has the optional `CLEAR_INDEX` set to true to erase and reset the database
+prior to other database changes:
+
+```bash
+$ docker run --name dataloader --link couchdb \
+    -v /home/vagrant/sync/universal/testData/dbData:/static_data -e STATIC_DATA_DIR=/static_data \
+    -v /home/vagrant/sync/universal/build/dbData:/build_data -e BUILD_DATA_DIR=/build_data \
+    -e COUCHDB_URL=http://couchdb:5984/gpii \
+    -e CLEAR_INDEX=true vagrant-universal scripts/deleteAndLoadSnapsets.sh
+```
+
+The second version does not set `CLEAR_INDEX` such that any existing database is left intact prior to subsequent changes
+to it (e.g., deleting the snapsets):
+
+```bash
+$ docker run --name dataloader --link couchdb \
+    -v /home/vagrant/sync/universal/testData/dbData:/static_data -e STATIC_DATA_DIR=/static_data \
+    -v /home/vagrant/sync/universal/build/dbData:/build_data -e BUILD_DATA_DIR=/build_data \
+    -e COUCHDB_URL=http://couchdb:5984/gpii \
+    vagrant-universal scripts/deleteAndLoadSnapsets.sh
+```

documentation/README.md

@@ -9,6 +9,7 @@
   * [Preferences Server](PreferencesServer.md)
 * [Data Model for Preferences and OAuth Data](DataModel.md)
   * [Pouch Manager](PouchManager.md)
+  * [Data Loader](DataLoader.md)
 * [MatchMakerFramework](MatchMakerFramework.md)
   * [Flat Match Maker](FlatMatchMaker.md)
   * [Apptology](Apptology.md)

scripts/convertPrefs.js

@@ -45,7 +45,7 @@ rimraf(targetDir, function () {
         filenames.forEach(function (filename) {
             if (filename.endsWith(".json5")) {
                 var gpiiKey = filename.substr(0, filename.length - 6);
-                var preferences = fs.readFileSync(inputDir + filename, "utf-8");
+                var preferences = fs.readFileSync(inputDir + "/" + filename, "utf-8");
                 var currentTime = new Date().toISOString();
                 var prefsSafeId = "prefsSafe-" + gpiiKey;
 
@@ -80,11 +80,11 @@ rimraf(targetDir, function () {
         });
 
         // Write the target files
-        var prefsSafesFile = targetDir + "prefsSafes.json";
+        var prefsSafesFile = targetDir + "/prefsSafes.json";
         console.log("prefsSafesFile: " + prefsSafesFile);
         fs.writeFileSync(prefsSafesFile, JSON.stringify(prefsSafes, null, 4));
 
-        var gpiiKeysFile = targetDir + "gpiiKeys.json";
+        var gpiiKeysFile = targetDir + "/gpiiKeys.json";
         fs.writeFileSync(gpiiKeysFile, JSON.stringify(gpiiKeys, null, 4));
 
         console.log("Finished converting preferences data in the source directory " + inputDir + " to the target directory " + targetDir);

scripts/deleteAndLoadSnapsets.sh

@@ -0,0 +1,86 @@
+#!/bin/sh
+APP_DIR=${APP_DIR:-"/app"}
+
+STATIC_DATA_DIR=${STATIC_DATA_DIR:-"${APP_DIR}/testData/dbData"}
+PREFERENCES_DATA_DIR=${PREFERENCES_DATA_DIR:-"${APP_DIR}/testData/preferences"}
+BUILD_DATA_DIR=${BUILD_DATA_DIR:-'/tmp/build/dbData'}
+
+DATALOADER_JS="${APP_DIR}/scripts/deleteAndLoadSnapsets.js"
+CONVERT_JS="${APP_DIR}/scripts/convertPrefs.js"
+
+log() {
+  echo "$(date +'%Y-%m-%d %H:%M:%S') - $1"
+}
+
+warm_indices(){
+  log "Warming indices..."
+
+  for view in $(curl -s "${COUCHDB_URL}/_design/views/" | jq -r '.views | keys[]'); do
+    curl -fsS "${COUCHDB_URL}/_design/views/_view/${view}" >/dev/null
+  done
+
+  log "Finished warming indices..."
+}
+
+# Verify variables
+if [ -z "${COUCHDB_URL}" ]; then
+  echo "COUCHDB_URL environment variable must be defined"
+  exit 1
+fi
+
+COUCHDB_URL_SANITIZED=$(echo "${COUCHDB_URL}" | sed -e 's,\(://\)[^/]*\(@\),\1<SENSITIVE>\2,g')
+
+log 'Starting'
+log "CouchDB: ${COUCHDB_URL_SANITIZED}"
+log "Clear index: ${CLEAR_INDEX}"
+log "Static: ${STATIC_DATA_DIR}"
+log "Build: ${BUILD_DATA_DIR}"
+log "Working directory: $(pwd)"
+
+# Check we can connect to CouchDB
+COUCHDB_URL_ROOT=$(echo "${COUCHDB_URL}" | sed 's/[^\/]*$//g')
+RET_CODE=$(curl --write-out '%{http_code}' --silent --output /dev/null "${COUCHDB_URL_ROOT}/_up")
+if [ "$RET_CODE" != '200' ]; then
+  log "[ERROR] Failed to connect to CouchDB: ${COUCHDB_URL_SANITIZED}"
+  exit 1
+fi
+
+# Create build dir if it does not exist
+if [ ! -d "${BUILD_DATA_DIR}" ]; then
+  mkdir -p "${BUILD_DATA_DIR}"
+fi
+
+# Convert preferences json5 to GPII keys and preferences safes
+if [ -d "${PREFERENCES_DATA_DIR}" ]; then
+  node "${CONVERT_JS}" "${PREFERENCES_DATA_DIR}" "${BUILD_DATA_DIR}" snapset
+  if [ "$?" != '0' ]; then
+    log "[ERROR] ${CONVERT_JS} failed (exit code: $?)"
+    exit 1
+  fi
+else
+  log "PREFERENCES_DATA_DIR ($PREFERENCES_DATA_DIR) does not exist, nothing to convert"
+fi
+
+# Initialize (possibly clear) data base
+if [ "${CLEAR_INDEX}" == 'true' ]; then
+  log "Deleting database at ${COUCHDB_URL_SANITIZED}"
+  if ! curl -fsS -X DELETE "${COUCHDB_URL}"; then
+    log "Error deleting database"
+  fi
+fi
+
+log "Creating database at ${COUCHDB_URL_SANITIZED}"
+if ! curl -fsS -X PUT "${COUCHDB_URL}"; then
+  log "Database already exists at ${COUCHDB_URL_SANITIZED}"
+fi
+
+# Submit data
+node "${DATALOADER_JS}" "${COUCHDB_URL}" "${STATIC_DATA_DIR}" "${BUILD_DATA_DIR}"
+err=$?
+if [ "${err}" != '0' ]; then
+  log "${DATALOADER_JS} failed with ${err}, exiting"
+  exit "${err}"
+fi
+
+# Warm Data
+warm_indices

scripts/vagrantCloudBasedContainers.sh

@@ -6,7 +6,7 @@
 # It builds a Docker image for GPII/universal and uses it to start two
 # components: the Preferences Server and the Flow Manager.
 #
-# It also starts a CouchDB container and loads the CouchDB data into
+# It also starts a CouchDB container and data into
 # it, so tests running against the GPII components will have access to the
 # latest test data.
 #
@@ -35,16 +35,16 @@ COUCHDB_HEALTHCHECK_TIMEOUT=30
 if [ "$NO_REBUILD" == "true" ] ; then
     CLEAR_INDEX=
 else
-    CLEAR_INDEX=1
+    CLEAR_INDEX='true'
 fi
 
 UNIVERSAL_DIR="/home/vagrant/sync/universal"
 STATIC_DATA_DIR="$UNIVERSAL_DIR/testData/dbData"
 BUILD_DATA_DIR="$UNIVERSAL_DIR/build/dbData/snapset"
 
-DATALOADER_IMAGE="herrclown/gpii-dataloader"
 DATALOADER_COUCHDB_URL="http://couchdb:${COUCHDB_PORT}/gpii"
 DATASOURCE_HOSTNAME="http://couchdb"
+DATALOADER_CMD='/app/scripts/deleteAndLoadSnapsets.sh'
 
 GPII_PREFERENCES_CONFIG="gpii.config.preferencesServer.standalone.production"
 GPII_PREFERENCES_PORT=9081
@@ -82,7 +82,7 @@ docker run -d -p $COUCHDB_PORT:$COUCHDB_PORT --name couchdb $COUCHDB_IMAGE
 wget -O /dev/null --retry-connrefused --waitretry=$COUCHDB_HEALTHCHECK_DELAY --read-timeout=20 --timeout=1 --tries=$COUCHDB_HEALTHCHECK_TIMEOUT http://localhost:$COUCHDB_PORT
 
 # Load the CouchDB data
-docker run --rm --link couchdb -v $STATIC_DATA_DIR:/static_data -e STATIC_DATA_DIR=/static_data -v $BUILD_DATA_DIR:/build_data -e BUILD_DATA_DIR=/build_data -e COUCHDB_URL=$DATALOADER_COUCHDB_URL -e CLEAR_INDEX=$CLEAR_INDEX $DATALOADER_IMAGE
+docker run --rm --link couchdb -v $STATIC_DATA_DIR:/static_data -e STATIC_DATA_DIR=/static_data -v $BUILD_DATA_DIR:/build_data -e BUILD_DATA_DIR=/build_data -e COUCHDB_URL=$DATALOADER_COUCHDB_URL -e CLEAR_INDEX=$CLEAR_INDEX $UNIVERSAL_IMAGE $DATALOADER_CMD
 
 # Wait for the CouchDB views become accessible. Accessing the view URL forced the view index to build which take time.
 # The URL returns 500 when the index is not ready, so use "--retry-on-http-error" option to continue retries at 500 response code.