Skip to content

Completing reports migration #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 18 commits into
base: main
Choose a base branch
from
Draft
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
lenses
  • Loading branch information
max-ostapenko committed Jan 7, 2025
commit bf90fd876520761cde5f0d51d99b6a1f5a7cb26c
87 changes: 57 additions & 30 deletions definitions/output/reports/reports_dynamic.js
Original file line number Diff line number Diff line change
@@ -1,47 +1,74 @@
const configs = new reports.HTTPArchiveReports()
const metrics = configs.listMetrics()

// Adjust start and end dates to update reports retrospectively
const startDate = '2024-12-01' // constants.currentMonth;
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TODO: remove hardcoded dates.

const endDate = '2024-12-01' // constants.currentMonth;

const lenses = {
all: '',
top1k: 'AND rank <= 1000',
top10k: 'AND rank <= 10000',
top100k: 'AND rank <= 100000',
top1m: 'AND rank <= 1000000',
drupal: 'AND \'Drupal\' IN UNNEST(technologies.technology)',
magento: 'AND \'Magento\' IN UNNEST(technologies.technology)',
wordpress: 'AND \'WordPress\' IN UNNEST(technologies.technology)'
}

const iterations = []
// dates
for (
let month = constants.currentMonth; month >= constants.currentMonth; month = constants.fnPastMonth(month)) {
iterations.push({
date: month,
devRankFilter: constants.devRankFilter
let date = endDate;
date >= startDate;
date = constants.fnPastMonth(date)
) {
// metrics
metrics.forEach(metric => {
// timeseries and histograms
metric.SQL.forEach(sql => {
// lenses
for (const [key, value] of Object.entries(lenses)) {
iterations.push({
date,
metric,
sql,
lense: { key, value },
devRankFilter: constants.devRankFilter
})
}
})
})
}

if (iterations.length === 1) {
const params = iterations[0]
metrics.forEach(metric => {
metric.SQL.forEach(sql => {
publish(metric.id + '_' + sql.type, {
type: 'incremental',
protected: true,
bigquery: sql.type === 'histogram' ? { partitionBy: 'date', clusterBy: ['client'] } : {},
schema: 'reports',
tags: ['crawl_complete']
}).preOps(ctx => `
if (startDate === endDate) {
iterations.forEach((params, i) => {
publish(params.metric.id + '_' + params.sql.type + '_' + params.lense.key, {
type: 'incremental',
protected: true,
bigquery: params.sql.type === 'histogram' ? { partitionBy: 'date', clusterBy: ['client'] } : {},
schema: 'reports',
tags: ['crawl_complete', 'reports']
}).preOps(ctx => `
--DELETE FROM ${ctx.self()}
--WHERE date = '${params.date}';
`).query(ctx => `
/* {"dataform_trigger": "report_complete", "date": "${params.date}", "name": "${metric.id}", "type": "${sql.type}"} */` +
sql.query(ctx, params))
})
`).query(ctx => `
/* {"dataform_trigger": "report_complete", "date": "${params.date}", "name": "${params.metric.id}", "type": "${params.sql.type}", "lense": "${params.lense.key}"} */` +
params.sql.query(ctx, params)
)
})
} else {
iterations.forEach((params, i) => {
metrics.forEach(metric => {
metric.SQL.forEach(sql => {
operate(metric.id + '_' + sql.type + '_' + params.date, {
tags: ['crawl_complete']
}).queries(ctx => `
DELETE FROM reports.${metric.id}_${sql.type}
operate(
params.metric.id + '_' + params.sql.type + '_' + params.lense.key + '_' + params.date)
.tags(['crawl_complete', 'reports'])
.queries(ctx => `
DELETE FROM reports.${params.metric.id}_${params.sql.type}
WHERE date = '${params.date}';

/* {"dataform_trigger": "report_complete", "date": "${params.date}", "name": "${metric.id}", "type": "${sql.type}"} */
INSERT INTO reports.${metric.id}_${sql.type}` +
sql.query(ctx, params))
})
})
/* {"dataform_trigger": "report_complete", "date": "${params.date}", "name": "${params.metric.id}", "type": "${params.sql.type}", "lense": "${params.lense.key}"} */
INSERT INTO reports.${params.metric.id}_${params.sql.type}` +
params.sql.query(ctx, params)
)
})
}
Loading