build: Fix staging deployment

- Changed default bucket from concordqa-report-data to concord-staging-report-data
- Upgraded from node 12 to node 14

functions/README.md

@@ -18,14 +18,14 @@ Then install the dependencies
 
 ### Configuring AWS credentials
 
-First we need a bucket to write to, e.g. `concordqa-report-data`. We need to set this as an environment variable
+First we need a bucket to write to, e.g. `concord-staging-report-data`. We need to set this as an environment variable
 for the auto_update function:
 
-`firebase functions:config:set aws.s3_bucket=concordqa-report-data`
+`firebase functions:config:set aws.s3_bucket=concord-staging-report-data`
 
 In order to write to S3, a user needs to be created in AWS IAM with permission to write to the S3 bucket.
 For instance there exists a user, `report-service-qa`, within the AminConcordQA role, with permission to write
-to the `concordqa-report-data` S3 bucket.
+to the `concord-staging-report-data` S3 bucket.
 
 We can download the AWS key and Secret Key for this user (check 1Password), and then push it up to Firebase with
 

query-creator/README.md

@@ -219,7 +219,7 @@ You can change the behavior of the query-creator using the following query param
 ## AWS Glue/Athena Setup
 
 1. Create a `report-service` database in AWS Glue.
-2. If running on production, replace all instances of `concordqa-report-data` below with `concord-report-data`, or
+2. If running on production, replace all instances of `concord-staging-report-data` below with `concord-report-data`, or
    any other location as appropriate
 2. In Athena with the `report-service` database selected run the following:
 
@@ -233,12 +233,12 @@ You can change the behavior of the query-creator using the following query param
         structure_id STRING
     )
     ROW FORMAT SERDE 'org.openx.data.jsonserde.JsonSerDe'
-    LOCATION "s3://concordqa-report-data/activity-structure/"
+    LOCATION "s3://concord-staging-report-data/activity-structure/"
     TBLPROPERTIES
     (
         "projection.enabled" = "true",
         "projection.structure_id.type" = "injected",
-        "storage.location.template" = "s3://concordqa-report-data/activity-structure/${structure_id}"
+        "storage.location.template" = "s3://concord-staging-report-data/activity-structure/${structure_id}"
     )
 
     CREATE EXTERNAL TABLE IF NOT EXISTS learners (
@@ -262,12 +262,12 @@ You can change the behavior of the query-creator using the following query param
         query_id STRING
     )
     ROW FORMAT SERDE 'org.openx.data.jsonserde.JsonSerDe'
-    LOCATION "s3://concordqa-report-data/learners/"
+    LOCATION "s3://concord-staging-report-data/learners/"
     TBLPROPERTIES
     (
         "projection.enabled" = "true",
         "projection.query_id.type" = "injected",
-        "storage.location.template" = "s3://concordqa-report-data/learners/${query_id}"
+        "storage.location.template" = "s3://concord-staging-report-data/learners/${query_id}"
     )
 
     CREATE EXTERNAL TABLE IF NOT EXISTS partitioned_answers (
@@ -296,11 +296,11 @@ You can change the behavior of the query-creator using the following query param
         escaped_url STRING
     )
     ROW FORMAT SERDE 'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
-    LOCATION "s3://concordqa-report-data/partitioned-answers/"
+    LOCATION "s3://concord-staging-report-data/partitioned-answers/"
     TBLPROPERTIES
     (
         "projection.enabled" = "true",
         "projection.escaped_url.type" = "injected",
-        "storage.location.template" = "s3://concordqa-report-data/partitioned-answers/${escaped_url}"
+        "storage.location.template" = "s3://concord-staging-report-data/partitioned-answers/${escaped_url}"
     )
     ```

query-creator/env.sample.json

@@ -1,6 +1,6 @@
 {
   "Parameters": {
-    "OUTPUT_BUCKET": "concordqa-report-data",
+    "OUTPUT_BUCKET": "concord-staging-report-data",
     "REPORT_SERVICE_TOKEN": "replace_me_with_the_real_report_service_dev_token",
     "REPORT_SERVICE_URL": "https://us-central1-report-service-dev.cloudfunctions.net/api",
     "PORTAL_REPORT_URL": "https://portal-report.concord.org/branch/master/index.html",

query-creator/samconfig.toml

@@ -9,7 +9,7 @@ s3_prefix = "report-service-query-creator"
 region = "us-east-1"
 confirm_changeset = true
 capabilities = "CAPABILITY_IAM"
-parameter_overrides = "OutputBucket=\"concordqa-report-data\" LogInputBucket=\"log-ingester-qa\"  ReportServiceUrl=\"https://us-central1-report-service-dev.cloudfunctions.net/api\" ResearcherReportsUrl=\"https://researcher-reports.concord.org/branch/master/\" FirebaseApp=\"report-service-dev\" PortalReportUrl=\"https://portal-report.concord.org/branch/master/index.html\" LogAthenaDBName=\"log_ingester_qa\""
+parameter_overrides = "OutputBucket=\"concord-staging-report-data\" LogInputBucket=\"log-ingester-qa\"  ReportServiceUrl=\"https://us-central1-report-service-dev.cloudfunctions.net/api\" ResearcherReportsUrl=\"https://researcher-reports.concord.org/branch/master/\" FirebaseApp=\"report-service-dev\" PortalReportUrl=\"https://portal-report.concord.org/branch/master/index.html\" LogAthenaDBName=\"log_ingester_qa\""
 image_repositories = []
 
 [production]

query-creator/template.yaml

@@ -50,7 +50,7 @@ Resources:
     Properties:
       CodeUri: create-query/
       Handler: app.lambdaHandler
-      Runtime: nodejs12.x
+      Runtime: nodejs14.x
       Events:
         CreateQuery:
           Type: Api # More info about API Event Source: https://github.com/awslabs/serverless-application-model/blob/master/versions/2016-10-31.md#api

scripts/README.md

@@ -23,7 +23,7 @@ https://console.cloud.google.com/apis/credentials?project=report-service-pro&org
 Run the script by passing in the destination S3 bucket and the source key for the Firestore database. e.g.
 
 ```
-node export-answers.js concordqa-report-data authoring.staging.concord.org
+node export-answers.js concord-staging-report-data authoring.staging.concord.org
 ```
 
 the script accepts up to three arguments:

scripts/export-answers.js

@@ -7,7 +7,7 @@ const util = require('util');
 const parquet = require('parquetjs');
 const { parquetInfo, getSyncDocId, hasLTIMetadata, getHash, schema } = require('../functions/src/shared/s3-answers')
 
-const BUCKET = process.argv[2];     // e.g. concordqa-report-data
+const BUCKET = process.argv[2];     // e.g. concord-staging-report-data
 const SOURCE =  process.argv[3];    // e.g. authoring.staging.concord.org
 const DATE_REGEX  = process.argv[4] // optional, e.g. `2021-(04|05)`
                                     // if a regex is included, it will *only* be used if there is a `created` field in the answer.