Backfills & deprecating legacy tables

.github/workflows/linter.yaml

@@ -30,5 +30,6 @@ jobs:
         env:
           DEFAULT_BRANCH: main
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VALIDATE_JSCPD: false
           VALIDATE_JAVASCRIPT_PRETTIER: false
           VALIDATE_MARKDOWN_PRETTIER: false

README.md

@@ -8,11 +8,11 @@ The pipelines are run in Dataform service in Google Cloud Platform (GCP) and are
 
 ### Crawl results
 
-Tag: `crawl_results_all`
+Tag: `crawl_complete`
 
-- httparchive.all.pages
-- httparchive.all.parsed_css
-- httparchive.all.requests
+- httparchive.crawl.pages
+- httparchive.crawl.parsed_css
+- httparchive.crawl.requests
 
 ### Core Web Vitals Technology Report
 
@@ -39,6 +39,9 @@ Consumers:
 
 Tag: `crawl_results_legacy`
 
+- httparchive.all.pages
+- httparchive.all.parsed_css
+- httparchive.all.requests
 - httparchive.lighthouse.YYYY_MM_DD_client
 - httparchive.pages.YYYY_MM_DD_client
 - httparchive.requests.YYYY_MM_DD_client
@@ -51,7 +54,7 @@ Tag: `crawl_results_legacy`
 
 1. [crawl-complete](https://console.cloud.google.com/cloudpubsub/subscription/detail/dataformTrigger?authuser=7&project=httparchive) PubSub subscription
 
-    Tags: ["crawl_results_all", "blink_features_report", "crawl_results_legacy"]
+    Tags: ["crawl_complete", "blink_features_report", "crawl_results_legacy"]
 
 2. [bq-poller-cwv-tech-report](https://console.cloud.google.com/cloudscheduler/jobs/edit/us-east4/bq-poller-cwv-tech-report?authuser=7&project=httparchive) Scheduler
 

definitions/extra/test_env.js

@@ -1,4 +1,5 @@
 const date = constants.currentMonth
+operate('test')
 
 // List of resources to be copied to the test environment. Comment out the ones you don't need.
 const resourcesList = [
@@ -15,7 +16,7 @@ const resourcesList = [
 resourcesList.forEach(resource => {
   operate(
     `test_table ${resource.datasetId}_dev_dev_${resource.tableId}`
-  ).queries(`
+  ).dependencies(['test']).queries(`
 CREATE SCHEMA IF NOT EXISTS ${resource.datasetId}_dev;
 DROP TABLE IF EXISTS ${resource.datasetId}_dev.dev_${resource.tableId};
 

definitions/output/all/pages.js

@@ -7,7 +7,7 @@ publish('pages', {
     clusterBy: ['client', 'is_root_page', 'rank'],
     requirePartitionFilter: true
   },
-  tags: ['crawl_results_all']
+  tags: ['crawl_results_legacy']
 }).preOps(ctx => `
 DELETE FROM ${ctx.self()}
 WHERE date = '${constants.currentMonth}';

definitions/output/all/parsed_css.js

@@ -7,21 +7,10 @@ publish('parsed_css', {
     clusterBy: ['client', 'is_root_page', 'rank', 'page'],
     requirePartitionFilter: true
   },
-  tags: ['crawl_results_all']
+  tags: ['crawl_results_legacy']
 }).preOps(ctx => `
-DELETE FROM ${ctx.self()}
-WHERE date = '${constants.currentMonth}';
-`).query(ctx => `
-SELECT *
-FROM ${ctx.ref('crawl_staging', 'parsed_css')}
-WHERE date = '${constants.currentMonth}'
-  AND client = 'desktop'
-  ${constants.devRankFilter}
-`).postOps(ctx => `
-INSERT INTO ${ctx.self()}
-SELECT *
-FROM ${ctx.ref('crawl_staging', 'parsed_css')}
-WHERE date = '${constants.currentMonth}'
-  AND client = 'mobile'
-  ${constants.devRankFilter};
+DROP SNAPSHOT TABLE IF EXISTS ${ctx.self()};
+
+CREATE SNAPSHOT TABLE ${ctx.self()}
+CLONE ${ctx.ref('crawl', 'parsed_css')};
 `)