query-npm-modules.sql

-- warning:  this query looks at ~2 TB of data and will cost ~$10 to run.
SELECT 
  COUNT(*) as cnt, package
FROM 
  JS(
    (SELECT content FROM [bigquery-public-data:github_repos.contents] WHERE id IN (
      SELECT id FROM [bigquery-public-data:github_repos.files] WHERE RIGHT(path, 12) = "package.json" 
    )),
    content,
    "[{ name: 'package', type: 'string'}]",
    "function(row, emit) { 
      try {
        x = JSON.parse(row.content);
        if (x.dependencies) {
          Object.keys(x.dependencies).forEach(function(dep) {
            emit({ package: dep });
          });
        }
      } catch (e) {}
    }" 
  )
GROUP BY package
ORDER BY cnt DESC
LIMIT 1000