diff --git a/querysrv/querysrv.js b/querysrv/querysrv.js index 6696cef..d8616f9 100644 --- a/querysrv/querysrv.js +++ b/querysrv/querysrv.js @@ -10,7 +10,7 @@ var refRes; const bigQuery = require('gcloud').bigquery({ projectId: 'sodium-primer-120219', - keyFilename: '../cert/Big-Data-34fbefa58bd8.json' + keyFilename: './cert/Big-Data-34fbefa58bd8.json' }); app.use(cors()); diff --git a/server.js b/server.js index 209c0f1..31e0bd3 100644 --- a/server.js +++ b/server.js @@ -24,11 +24,15 @@ wss.on('connection', function connection(ws) { if (argv.live) { var express = require('express'); var app = express(); - + + //start bigquery server + var fork = require('child_process').fork; + var child = fork('./querysrv/querysrv.js'); + app.use(express.static('serve')); - - app.listen(8080, function() { - console.log('Serving content at http://localhost:8080') + var port = process.env.port || 8080; + app.listen(port, function() { + console.log('Serving content at http://localhost:',port) }) -} \ No newline at end of file +} diff --git a/src/data/data.json b/src/data/data.json index bdff6db..493ba1c 100644 --- a/src/data/data.json +++ b/src/data/data.json @@ -1091,8 +1091,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(a+rgh|angry|annoyed|annoying|appalled|bitter|cranky|hate|hating|mad)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(a+rgh|angry|annoyed|annoying|appalled|bitter|cranky|hate|hating|mad)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(a+rgh|angry|annoyed|annoying|appalled|bitter|cranky|hate|hating|mad)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(a+rgh|angry|annoyed|annoying|appalled|bitter|cranky|hate|hating|mad)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -1151,8 +1151,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\(') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\(') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\(') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\(') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -1211,8 +1211,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -1271,8 +1271,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yes|yay|hallelujah|hurray|bingo|amused|cheerful|excited|glad|proud)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yes|yay|hallelujah|hurray|bingo|amused|cheerful|excited|glad|proud)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yes|yay|hallelujah|hurray|bingo|amused|cheerful|excited|glad|proud)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yes|yay|hallelujah|hurray|bingo|amused|cheerful|excited|glad|proud)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -1326,8 +1326,8 @@ "question": "Which programming language has the most issues per commit?", "rowIndex": 48, "approved": true, - "sql": "SELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(#)\\d+') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", - "inputSQL": "SELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(#)\\d+') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\nAND\n repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", + "sql": "SELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(#)\\d+') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", + "inputSQL": "SELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(#)\\d+') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\nAND\n repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", "databases": "GitHub", "units": "Issues per Commit", "hasPassingInputQuery": false, @@ -1386,8 +1386,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yikes|gosh|baffled|stumped|surprised|shocked)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yikes|gosh|baffled|stumped|surprised|shocked)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yikes|gosh|baffled|stumped|surprised|shocked)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(yikes|gosh|baffled|stumped|surprised|shocked)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -1446,8 +1446,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(android)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(android)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(android)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(android)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -1506,8 +1506,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\)') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\)') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\)') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r':\\)') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -1561,8 +1561,8 @@ "question": "Which programming language has the chattiest developers?", "rowIndex": 49, "approved": true, - "sql": "SELECT\n repository_language,\n SUM(LENGTH(payload_commit_msg)) / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", - "inputSQL": "SELECT\n repository_language,\n SUM(LENGTH(payload_commit_msg)) / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\nAND\n repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", + "sql": "SELECT\n repository_language,\n SUM(LENGTH(payload_commit_msg)) / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", + "inputSQL": "SELECT\n repository_language,\n SUM(LENGTH(payload_commit_msg)) / COUNT(*) AS per,\n COUNT(*) AS total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\nAND\n repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE", "databases": "GitHub", "units": "Characters per Commit", "hasPassingInputQuery": false, @@ -1621,8 +1621,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(!)+\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(!)+\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(!)+\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(!)+\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -1681,8 +1681,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(newbie|noob|newb|n00b)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(newbie|noob|newb|n00b)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(newbie|noob|newb|n00b)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(newbie|noob|newb|n00b)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -1854,8 +1854,8 @@ "question": "Which programming language created the most new projects last year?", "rowIndex": 55, "approved": true, - "sql": "SELECT\n repository_language,\n COUNT(UNIQUE(repository_name)) total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'CreateEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nORDER BY\n total DESC", - "inputSQL": "SELECT\n repository_language,\n COUNT(UNIQUE(repository_name)) total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'CreateEvent'\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nORDER BY\n total DESC IGNORE CASE", + "sql": "SELECT\n repository_language,\n COUNT(UNIQUE(repository_name)) total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'CreateEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nORDER BY\n total DESC", + "inputSQL": "SELECT\n repository_language,\n COUNT(UNIQUE(repository_name)) total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'CreateEvent'\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nORDER BY\n total DESC IGNORE CASE", "databases": "GitHub", "units": "Projects", "hasPassingInputQuery": false, @@ -2027,8 +2027,8 @@ "question": "What's the most popular programming language?", "rowIndex": 36, "approved": true, - "sql": "SELECT\n repository_language,\n COUNT(*) total\nFROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name )\nGROUP BY\n repository_language\nORDER BY\n total DESC", - "inputSQL": "SELECT\n repository_language,\n COUNT(*) total\nFROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n LOWER(repository_language) = lower('userInput')\n GROUP BY\n repository_language,\n repository_name )\nGROUP BY\n repository_language\nORDER BY\n total DESC", + "sql": "SELECT\n repository_language,\n COUNT(*) total\nFROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name )\nGROUP BY\n repository_language\nORDER BY\n total DESC", + "inputSQL": "SELECT\n repository_language,\n COUNT(*) total\nFROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n LOWER(repository_language) = lower('userInput')\n GROUP BY\n repository_language,\n repository_name )\nGROUP BY\n repository_language\nORDER BY\n total DESC", "databases": "GitHub", "units": "Repositories", "hasPassingInputQuery": false, @@ -2141,8 +2141,8 @@ "question": "Which programming language has the most forked projects per repo?", "rowIndex": 35, "approved": true, - "sql": "SELECT\n repos.repository_language,\n forks.total / repos.total per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [githubarchive:github.timeline]\n WHERE\n type = 'ForkEvent'\n GROUP BY\n repository_language) forks\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = forks.repository_language\nORDER BY\n per DESC IGNORE CASE", - "inputSQL": "SELECT\n repos.repository_language,\n forks.total / repos.total per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [githubarchive:github.timeline]\n WHERE\n type = 'ForkEvent'\n GROUP BY\n repository_language) forks\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = forks.repository_language\nWHERE\n repos.repository_language = 'userInput'\nORDER BY\n per DESC IGNORE CASE", + "sql": "SELECT\n repos.repository_language,\n forks.total / repos.total per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'ForkEvent'\n GROUP BY\n repository_language) forks\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = forks.repository_language\nORDER BY\n per DESC IGNORE CASE", + "inputSQL": "SELECT\n repos.repository_language,\n forks.total / repos.total per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'ForkEvent'\n GROUP BY\n repository_language) forks\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = forks.repository_language\nWHERE\n repos.repository_language = 'userInput'\nORDER BY\n per DESC IGNORE CASE", "databases": "GitHub", "units": "Forks per Repo", "hasPassingInputQuery": false, @@ -2196,8 +2196,8 @@ "question": "Which programming language has the most open issues per repo?", "rowIndex": 52, "approved": true, - "sql": "SELECT\n repos.repository_language,\n (issues.total / repos.total) per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM \n [githubarchive:github.timeline]\n WHERE\n type = 'IssuesEvent'\n AND\n repository_language IS NOT NULL\n AND\n payload_action = 'opened'\n GROUP BY\n repository_language) issues\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = issues.repository_language\nORDER BY\n per DESC\nLIMIT 10", - "inputSQL": "SELECT\n repos.repository_language,\n (issues.total / repos.total) per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [githubarchive:github.timeline]\n WHERE\n type = 'IssuesEvent'\n AND repository_language IS NOT NULL\n AND payload_action = 'opened'\n GROUP BY\n repository_language) issues\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = issues.repository_language\nWHERE\n repos.repository_language = 'userInput'\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE", + "sql": "SELECT\n repos.repository_language,\n (issues.total / repos.total) per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM \n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'IssuesEvent'\n AND\n repository_language IS NOT NULL\n AND\n payload_action = 'opened'\n GROUP BY\n repository_language) issues\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = issues.repository_language\nORDER BY\n per DESC\nLIMIT 10", + "inputSQL": "SELECT\n repos.repository_language,\n (issues.total / repos.total) per\nFROM (\n SELECT\n repository_language,\n COUNT(*) total\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'IssuesEvent'\n AND repository_language IS NOT NULL\n AND payload_action = 'opened'\n GROUP BY\n repository_language) issues\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = issues.repository_language\nWHERE\n repos.repository_language = 'userInput'\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE", "databases": "GitHub", "units": "Issues per Repo", "hasPassingInputQuery": false, @@ -2251,8 +2251,8 @@ "question": "Which programming language has the most commits per repo?", "rowIndex": 53, "approved": true, - "sql": "SELECT\n repos.repository_language,\n (commits.total / repos.total) per,\nFROM (\n SELECT\n repository_language,\n COUNT(payload_commit_msg) total\n FROM \n [githubarchive:github.timeline]\n WHERE\n type = 'PushEvent'\n AND\n payload_commit_msg IS NOT NULL\n AND\n repository_language IS NOT NULL\n GROUP BY\n repository_language) commits\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = commits.repository_language\nORDER BY\n per DESC\nLIMIT 10", - "inputSQL": "SELECT\n repos.repository_language,\n (commits.total / repos.total) per,\nFROM (\n SELECT\n repository_language,\n COUNT(payload_commit_msg) total\n FROM \n [githubarchive:github.timeline]\n WHERE\n type = 'PushEvent'\n AND\n payload_commit_msg IS NOT NULL\n AND\n repository_language IS NOT NULL\n GROUP BY\n repository_language) commits\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [githubarchive:github.timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = commits.repository_language\nWHERE\n lower(commits.repository_language) = lower('userInput')\nORDER BY\n per DESC\nLIMIT 10", + "sql": "SELECT\n repos.repository_language,\n (commits.total / repos.total) per,\nFROM (\n SELECT\n repository_language,\n COUNT(payload_commit_msg) total\n FROM \n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'PushEvent'\n AND\n payload_commit_msg IS NOT NULL\n AND\n repository_language IS NOT NULL\n GROUP BY\n repository_language) commits\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = commits.repository_language\nORDER BY\n per DESC\nLIMIT 10", + "inputSQL": "SELECT\n repos.repository_language,\n (commits.total / repos.total) per,\nFROM (\n SELECT\n repository_language,\n COUNT(payload_commit_msg) total\n FROM \n [bigquery-public-data:samples.github_timeline]\n WHERE\n type = 'PushEvent'\n AND\n payload_commit_msg IS NOT NULL\n AND\n repository_language IS NOT NULL\n GROUP BY\n repository_language) commits\nJOIN (\n SELECT\n repository_language,\n COUNT(*) total\n FROM (\n SELECT\n repository_language,\n FROM\n [bigquery-public-data:samples.github_timeline]\n WHERE\n repository_language IS NOT NULL\n GROUP BY\n repository_language,\n repository_name)\n GROUP BY\n repository_language\n HAVING\n total > 4000) repos\nON\n repos.repository_language = commits.repository_language\nWHERE\n lower(commits.repository_language) = lower('userInput')\nORDER BY\n per DESC\nLIMIT 10", "databases": "GitHub", "units": "Commits per Repo", "hasPassingInputQuery": false, @@ -2317,66 +2317,6 @@ "hasPassingInputQuery": false, "rowsSearched": 63958245 }, - { - "top10": [ - { - "label": "Go", - "number": 5.388253404266648 - }, - { - "label": "Objective-C", - "number": 1.5749262567619684 - }, - { - "label": "HTML", - "number": 1.3192908210701806 - }, - { - "label": "Java", - "number": 1.2057899096414024 - }, - { - "label": "CSS", - "number": 1.002261160978466 - }, - { - "label": "CoffeeScript", - "number": 0.880547896468914 - }, - { - "label": "JavaScript", - "number": 0.8616159384093158 - }, - { - "label": "C++", - "number": 0.8212381402797673 - }, - { - "label": "TypeScript", - "number": 0.7767971623506069 - }, - { - "label": "Python", - "number": 0.7746727907039265 - } - ], - "answer": "Go", - "answerValue": 5.388253404266648, - "question": "Which programming language mentions Google the most?", - "rowIndex": 42, - "approved": true, - "params": { - "regex": "(?i)\\b(google)\\b", - "per": 100, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(google)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(google)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "% of Comments", - "hasPassingInputQuery": false, - "rowsSearched": 1242016253 - }, { "top10": [ { @@ -6041,8 +5981,8 @@ "per": 100, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fixed)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fixed)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fixed)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fixed)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "% of Commits", "hasPassingInputQuery": false, @@ -6101,8 +6041,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(again)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(again)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(again)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(again)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6161,8 +6101,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hotfix)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hotfix)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hotfix)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hotfix)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6221,8 +6161,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(oops)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(oops)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(oops)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(oops)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6281,8 +6221,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(don\\'?t know|dunno)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(don\\'?t know|dunno)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(don\\'?t know|dunno)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(don\\'?t know|dunno)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -6341,8 +6281,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fix(ed)? conflict)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fix(ed)? conflict)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fix(ed)? conflict)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(fix(ed)? conflict)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -6401,8 +6341,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(\\+1)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(\\+1)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(\\+1)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(\\+1)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6461,8 +6401,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(minor changes?)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(minor changes?)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(minor changes?)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(minor changes?)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6521,8 +6461,8 @@ "per": 100, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(update readme)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(update readme)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(update readme)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(update readme)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "% of Commits", "hasPassingInputQuery": false, @@ -6581,8 +6521,8 @@ "per": 1000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hack|hacks)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hack|hacks)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hack|hacks)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(hack|hacks)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 1,000", "hasPassingInputQuery": false, @@ -6641,133 +6581,13 @@ "per": 100, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(bump.*version)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(bump.*version)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(bump.*version)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(bump.*version)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "% of Commits", "hasPassingInputQuery": false, "rowsSearched": 290264874 }, - { - "top10": [ - { - "label": "CoffeeScript", - "number": 2.545631665299426 - }, - { - "label": "Ruby", - "number": 0.09480590934099663 - }, - { - "label": "JavaScript", - "number": 0.08223396656193335 - }, - { - "label": "DM", - "number": 0.06323837994768461 - }, - { - "label": "CSS", - "number": 0.06032500094257814 - }, - { - "label": "HTML", - "number": 0.05432375014955199 - }, - { - "label": "Emacs Lisp", - "number": 0.053298590548383276 - }, - { - "label": "TypeScript", - "number": 0.042514195017336345 - }, - { - "label": "Haskell", - "number": 0.03875861687107223 - }, - { - "label": "C", - "number": 0.036590967480750816 - } - ], - "answer": "CoffeeScript", - "answerValue": 2.545631665299426, - "question": "Developers of which programming language talk the most about coffee?", - "rowIndex": 192, - "approved": true, - "params": { - "regex": "(?i)\\b(coffee|latte|espresso)\\b", - "per": 100, - "min_comments": 25000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(coffee|latte|espresso)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 25000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(coffee|latte|espresso)\\b') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "% of Comments", - "hasPassingInputQuery": false, - "rowsSearched": 1222377998 - }, - { - "top10": [ - { - "label": "Shell", - "number": 2.1789103269454944 - }, - { - "label": "Objective-C", - "number": 2.103646671505054 - }, - { - "label": "TypeScript", - "number": 1.889519778548282 - }, - { - "label": "Java", - "number": 1.3996745120543785 - }, - { - "label": "Python", - "number": 0.8356295737662451 - }, - { - "label": "Scala", - "number": 0.7196263699887019 - }, - { - "label": "C", - "number": 0.5190208153297988 - }, - { - "label": "JavaScript", - "number": 0.24976147778871177 - }, - { - "label": "PHP", - "number": 0.19257581709919194 - }, - { - "label": "C++", - "number": 0.17227211414061194 - } - ], - "answer": "Shell", - "answerValue": 2.1789103269454944, - "question": "Developers of which programming language mention insomnia the most?", - "rowIndex": 191, - "approved": true, - "params": { - "regex": "(?i)\\b(insomniac?)\\b", - "per": 100000, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(insomniac?)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(insomniac?)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "Comments per 100,000", - "hasPassingInputQuery": false, - "rowsSearched": 1222377991 - }, { "top10": [ { @@ -6887,186 +6707,6 @@ "hasPassingInputQuery": false, "rowsSearched": 6592241573 }, - { - "top10": [ - { - "label": "DM", - "number": 5.763315990686712 - }, - { - "label": "CSS", - "number": 3.361862031695761 - }, - { - "label": "Swift", - "number": 3.3472663991073954 - }, - { - "label": "JavaScript", - "number": 3.085178654385062 - }, - { - "label": "PHP", - "number": 3.036920635654257 - }, - { - "label": "Shell", - "number": 2.832583425029143 - }, - { - "label": "CoffeeScript", - "number": 2.4353978671041836 - }, - { - "label": "HTML", - "number": 2.357262729703774 - }, - { - "label": "C#", - "number": 2.251885355079199 - }, - { - "label": "C", - "number": 2.161721695848612 - } - ], - "answer": "DM", - "answerValue": 5.763315990686712, - "question": "Developers of which programming language LOL the most?", - "rowIndex": 220, - "approved": true, - "params": { - "regex": "(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b", - "per": 1000, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(ha(ha)+|he(he)+|lol|rofl|lmfao|lulz|lolz|rotfl|lawl|hilarious)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "Comments per 1,000", - "hasPassingInputQuery": false, - "rowsSearched": 1222377991 - }, - { - "top10": [ - { - "label": "CSS", - "number": 2.2433359725521247 - }, - { - "label": "HTML", - "number": 2.0662426396168883 - }, - { - "label": "Python", - "number": 1.710951552286387 - }, - { - "label": "C", - "number": 1.666056817208654 - }, - { - "label": "Shell", - "number": 1.6178409177570297 - }, - { - "label": "C++", - "number": 1.571121680962381 - }, - { - "label": "PHP", - "number": 1.3923231576271577 - }, - { - "label": "Ruby", - "number": 1.3823019875138116 - }, - { - "label": "JavaScript", - "number": 1.3480875763645719 - }, - { - "label": "Swift", - "number": 1.2656330663291646 - } - ], - "answer": "CSS", - "answerValue": 2.2433359725521247, - "question": "Developers of which programming language call out the most typos?", - "rowIndex": 237, - "approved": true, - "params": { - "regex": "(?i)\\b(typo|typos)\\b", - "per": 1000, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(typo|typos)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(typo|typos)\\b') THEN 1 ELSE 0 END) * 1000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "Comments per 1,000", - "hasPassingInputQuery": false, - "rowsSearched": 1222377991 - }, - { - "top10": [ - { - "label": "CoffeeScript", - "number": 8.203445447087777 - }, - { - "label": "Ruby", - "number": 5.4109847537547235 - }, - { - "label": "TypeScript", - "number": 3.873515546023978 - }, - { - "label": "C", - "number": 3.2698311365777326 - }, - { - "label": "Rust", - "number": 3.1019042995090897 - }, - { - "label": "Java", - "number": 2.8884192203303996 - }, - { - "label": "JavaScript", - "number": 2.1479487089829212 - }, - { - "label": "C++", - "number": 1.7916299870623642 - }, - { - "label": "Shell", - "number": 1.4707644706882088 - }, - { - "label": "Swift", - "number": 1.332245332978068 - } - ], - "answer": "CoffeeScript", - "answerValue": 8.203445447087777, - "question": "Developers of which programming language give the most 👍?", - "rowIndex": 241, - "approved": true, - "params": { - "regex": "(?i)\\b(👍|:+1:|:thumbsup:)\\b", - "per": 10000, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(👍|:+1:|:thumbsup:)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(👍|:+1:|:thumbsup:)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "Comments per 10,000", - "hasPassingInputQuery": false, - "rowsSearched": 1222377991 - }, { "top10": [ { @@ -7542,66 +7182,6 @@ "hasPassingInputQuery": false, "rowsSearched": 761318228 }, - { - "top10": [ - { - "label": "Scala", - "number": 2.230841746964976 - }, - { - "label": "Java", - "number": 2.0231658856058745 - }, - { - "label": "C++", - "number": 0.3273170168671627 - }, - { - "label": "C#", - "number": 0.2874747261803233 - }, - { - "label": "TypeScript", - "number": 0.2834279667822423 - }, - { - "label": "C", - "number": 0.23355936689840945 - }, - { - "label": "HTML", - "number": 0.22634895895646662 - }, - { - "label": "Shell", - "number": 0.1634182745209121 - }, - { - "label": "DM", - "number": 0.1437235907901923 - }, - { - "label": "JavaScript", - "number": 0.1186367019496381 - } - ], - "answer": "Scala", - "answerValue": 2.230841746964976, - "question": "Developers of which programming language wink the most?", - "rowIndex": 250, - "approved": true, - "params": { - "regex": "(?i)\\b(😉|;\\)|:wink:)\\b", - "per": 10000, - "min_comments": 50000 - }, - "sql": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(😉|;\\)|:wink:)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language IS NOT NULL) repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nHAVING\n total > 50000\nORDER BY\n per DESC\nLIMIT\n 10 IGNORE CASE\n", - "inputSQL": "\nSELECT\n repos.language,\n SUM(CASE WHEN REGEXP_MATCH(JSON_EXTRACT(payload, '$.comment.body'), r'(?i)\\b(😉|;\\)|:wink:)\\b') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) AS total\nFROM (\n SELECT\n *\n FROM\n TABLE_QUERY([githubarchive:month], 'table_id like \"2016%\"')\n WHERE\n type = 'IssueCommentEvent') AS comments\nJOIN (\n SELECT\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.language') language,\n JSON_EXTRACT_SCALAR(payload, '$.pull_request.base.repo.full_name') name\n FROM\n TABLE_QUERY([githubarchive:month], 'REGEXP_MATCH(table_id, \"201604|201603|201602\")')\n WHERE\n type = 'PullRequestEvent'\n GROUP BY\n language,\n name\n HAVING\n language = 'userInput') repos\nON\n repos.name = comments.repo_name\nGROUP BY\n repos.language\nORDER BY\n per DESC IGNORE CASE\n", - "databases": "GitHub", - "units": "Comments per 10,000", - "hasPassingInputQuery": false, - "rowsSearched": 1222377991 - }, { "top10": [ { @@ -8132,8 +7712,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'remove comment') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'remove comment') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'remove comment') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'remove comment') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -8316,8 +7896,8 @@ "per": 100, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'refactor') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'refactor') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'refactor') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'refactor') THEN 1 ELSE 0 END) * 100 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "% of Commits", "hasPassingInputQuery": false, @@ -8558,8 +8138,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -8680,8 +8260,8 @@ "per": 10000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'fix broken') THEN 1 ELSE 0 END) * 10000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 10,000", "hasPassingInputQuery": false, @@ -8799,8 +8379,8 @@ "per": 100000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'what the actual ') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'what the actual ') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'what the actual ') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'what the actual ') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 100,000", "hasPassingInputQuery": false, @@ -8859,8 +8439,8 @@ "per": 100000, "min_commits": 50000 }, - "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(remove credentials)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", - "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(remove credentials)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [githubarchive:github.timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "sql": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(remove credentials)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", + "inputSQL": "\nSELECT\n repository_language,\n SUM(CASE WHEN REGEXP_MATCH(payload_commit_msg, r'(?i)\\b(remove credentials)\\b') THEN 1 ELSE 0 END) * 100000 / COUNT(*) AS per,\n COUNT(*) as total\nFROM\n [bigquery-public-data:samples.github_timeline]\nWHERE\n type = 'PushEvent'\n AND repository_language IS NOT NULL\n AND repository_language = 'userInput'\nGROUP BY\n repository_language\nHAVING\n total > 50000\nORDER BY\n per DESC IGNORE CASE\n", "databases": "GitHub", "units": "Commits per 100,000", "hasPassingInputQuery": false, @@ -10939,4 +10519,4 @@ } ], "total": 185 -} \ No newline at end of file +}