Skip to content

Commit

Permalink
Merge pull request #1995 from mabel-dev/#1993-1
Browse files Browse the repository at this point in the history 
#1993
  • Loading branch information
@joocer
joocer authored Sep 8, 2024
2 parents c0e97a2 + 77337dd commit 764beed
Show file tree
Hide file tree
Showing 4 changed files with 46 additions and 2 deletions.
3 changes: 2 additions & 1 deletion opteryx/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,8 @@ def opteryx(self, line, cell):
)

ip = get_ipython()
ip.register_magics(OpteryxMagics)
if ip:
ip.register_magics(OpteryxMagics)
except Exception as err: # no sec
pass

Expand Down
2 changes: 1 addition & 1 deletion opteryx/__version__.py
View file
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
__build__ = 776
__build__ = 777

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
Expand Down
Binary file added testdata/clickbench_tiny/hits_48.parquet
View file
Binary file not shown.
43 changes: 43 additions & 0 deletions tests/sql_battery/tests/clickbench.run_tests
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
SELECT COUNT(*) FROM testdata.clickbench_tiny;
SELECT COUNT(*) FROM testdata.clickbench_tiny WHERE AdvEngineID <> 0;
SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM testdata.clickbench_tiny;
SELECT AVG(UserID) FROM testdata.clickbench_tiny;
SELECT COUNT(DISTINCT UserID) FROM testdata.clickbench_tiny;
SELECT COUNT(DISTINCT SearchPhrase) FROM testdata.clickbench_tiny;
SELECT MIN(EventDate), MAX(EventDate) FROM testdata.clickbench_tiny;
SELECT AdvEngineID, COUNT(*) FROM testdata.clickbench_tiny WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC;
SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM testdata.clickbench_tiny GROUP BY RegionID ORDER BY u DESC LIMIT 10;
SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM testdata.clickbench_tiny GROUP BY RegionID ORDER BY c DESC LIMIT 10;
SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM testdata.clickbench_tiny WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM testdata.clickbench_tiny WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
SELECT SearchPhrase, COUNT(*) AS c FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT UserID, COUNT(*) FROM testdata.clickbench_tiny GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID, SearchPhrase, COUNT(*) FROM testdata.clickbench_tiny GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID, SearchPhrase, COUNT(*) FROM testdata.clickbench_tiny GROUP BY UserID, SearchPhrase LIMIT 10;
# SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM testdata.clickbench_tiny GROUP BY UserID, extract(minute FROM EventTime), SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
SELECT UserID FROM testdata.clickbench_tiny WHERE UserID = 435090932899640449;
SELECT COUNT(*) FROM testdata.clickbench_tiny WHERE URL LIKE '%google%';
SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM testdata.clickbench_tiny WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT SearchPhrase, MIN(URL), MIN(Title), COUNT(*) AS c, COUNT(DISTINCT UserID) FROM testdata.clickbench_tiny WHERE Title LIKE '%Google%' AND URL NOT LIKE '%.google.%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
SELECT * FROM testdata.clickbench_tiny WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10;
SELECT SearchPhrase FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10;
SELECT SearchPhrase FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10;
SELECT SearchPhrase FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10;
SELECT CounterID, AVG(length(URL)) AS l, COUNT(*) AS c FROM testdata.clickbench_tiny WHERE URL <> '' GROUP BY CounterID HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
# SELECT REGEXP_REPLACE(Referer, '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length(Referer)) AS l, COUNT(*) AS c, MIN(Referer) FROM testdata.clickbench_tiny WHERE Referer <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
SELECT SUM(ResolutionWidth), SUM(ResolutionWidth + 1), SUM(ResolutionWidth + 2), SUM(ResolutionWidth + 3), SUM(ResolutionWidth + 4), SUM(ResolutionWidth + 5), SUM(ResolutionWidth + 6), SUM(ResolutionWidth + 7), SUM(ResolutionWidth + 8), SUM(ResolutionWidth + 9), SUM(ResolutionWidth + 10), SUM(ResolutionWidth + 11), SUM(ResolutionWidth + 12), SUM(ResolutionWidth + 13), SUM(ResolutionWidth + 14), SUM(ResolutionWidth + 15), SUM(ResolutionWidth + 16), SUM(ResolutionWidth + 17), SUM(ResolutionWidth + 18), SUM(ResolutionWidth + 19), SUM(ResolutionWidth + 20), SUM(ResolutionWidth + 21), SUM(ResolutionWidth + 22), SUM(ResolutionWidth + 23), SUM(ResolutionWidth + 24), SUM(ResolutionWidth + 25), SUM(ResolutionWidth + 26), SUM(ResolutionWidth + 27), SUM(ResolutionWidth + 28), SUM(ResolutionWidth + 29), SUM(ResolutionWidth + 30), SUM(ResolutionWidth + 31), SUM(ResolutionWidth + 32), SUM(ResolutionWidth + 33), SUM(ResolutionWidth + 34), SUM(ResolutionWidth + 35), SUM(ResolutionWidth + 36), SUM(ResolutionWidth + 37), SUM(ResolutionWidth + 38), SUM(ResolutionWidth + 39), SUM(ResolutionWidth + 40), SUM(ResolutionWidth + 41), SUM(ResolutionWidth + 42), SUM(ResolutionWidth + 43), SUM(ResolutionWidth + 44), SUM(ResolutionWidth + 45), SUM(ResolutionWidth + 46), SUM(ResolutionWidth + 47), SUM(ResolutionWidth + 48), SUM(ResolutionWidth + 49), SUM(ResolutionWidth + 50), SUM(ResolutionWidth + 51), SUM(ResolutionWidth + 52), SUM(ResolutionWidth + 53), SUM(ResolutionWidth + 54), SUM(ResolutionWidth + 55), SUM(ResolutionWidth + 56), SUM(ResolutionWidth + 57), SUM(ResolutionWidth + 58), SUM(ResolutionWidth + 59), SUM(ResolutionWidth + 60), SUM(ResolutionWidth + 61), SUM(ResolutionWidth + 62), SUM(ResolutionWidth + 63), SUM(ResolutionWidth + 64), SUM(ResolutionWidth + 65), SUM(ResolutionWidth + 66), SUM(ResolutionWidth + 67), SUM(ResolutionWidth + 68), SUM(ResolutionWidth + 69), SUM(ResolutionWidth + 70), SUM(ResolutionWidth + 71), SUM(ResolutionWidth + 72), SUM(ResolutionWidth + 73), SUM(ResolutionWidth + 74), SUM(ResolutionWidth + 75), SUM(ResolutionWidth + 76), SUM(ResolutionWidth + 77), SUM(ResolutionWidth + 78), SUM(ResolutionWidth + 79), SUM(ResolutionWidth + 80), SUM(ResolutionWidth + 81), SUM(ResolutionWidth + 82), SUM(ResolutionWidth + 83), SUM(ResolutionWidth + 84), SUM(ResolutionWidth + 85), SUM(ResolutionWidth + 86), SUM(ResolutionWidth + 87), SUM(ResolutionWidth + 88), SUM(ResolutionWidth + 89) FROM testdata.clickbench_tiny;
SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM testdata.clickbench_tiny WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM testdata.clickbench_tiny GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
SELECT URL, COUNT(*) AS c FROM testdata.clickbench_tiny GROUP BY URL ORDER BY c DESC LIMIT 10;
SELECT 1, URL, COUNT(*) AS c FROM testdata.clickbench_tiny GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
SELECT ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3, COUNT(*) AS c FROM testdata.clickbench_tiny GROUP BY ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3 ORDER BY c DESC LIMIT 10;
# SELECT URL, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCounttestdata.clickbench_tiny = 0 AND IsRefresh = 0 AND URL <> '' GROUP BY URL ORDER BY PageViews DESC LIMIT 10;
# SELECT Title, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCounttestdata.clickbench_tiny = 0 AND IsRefresh = 0 AND Title <> '' GROUP BY Title ORDER BY PageViews DESC LIMIT 10;
# SELECT URL, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND IsLink <> 0 AND IsDownload = 0 GROUP BY URL ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
# SELECT TraficSourceID, SearchEngineID, AdvEngineID, CASE WHEN (SearchEngineID = 0 AND AdvEngineID = 0) THEN Referer ELSE '' END AS Src, URL AS Dst, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 GROUP BY TraficSourceID, SearchEngineID, AdvEngineID, Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
# SELECT URLHash, EventDate, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND TraficSourceID IN (-1, 6) AND RefererHash = 3594120000172545465 GROUP BY URLHash, EventDate ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
# SELECT WindowClientWidth, WindowClientHeight, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND DontCounttestdata.clickbench_tiny = 0 AND URLHash = 2868770270353813622 GROUP BY WindowClientWidth, WindowClientHeight ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
# SELECT DATE_TRUNC('minute', EventTime) AS M, COUNT(*) AS PageViews FROM testdata.clickbench_tiny WHERE CounterID = 62 AND EventDate >= '2013-07-14' AND EventDate <= '2013-07-15' AND IsRefresh = 0 AND DontCounttestdata.clickbench_tiny = 0 GROUP BY DATE_TRUNC('minute', EventTime) ORDER BY DATE_TRUNC('minute', EventTime) LIMIT 10 OFFSET 1000;

0 comments on commit 764beed

Please sign in to comment.