Task ID: task_e_682e18d0844083238d2067f83465ef88
Building scubaduck @ file:///workspace/scubaduck
⠙ Preparing packages... (0/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
itsdangerous ------------------------------ 14.88 KiB/15.85 KiB
pytest-playwright ------------------------------ 16.23 KiB/16.23 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
markupsafe ------------------------------ 22.58 KiB/22.58 KiB
execnet ------------------------------ 32.00 KiB/39.66 KiB
pytest-xdist ------------------------------ 16.00 KiB/45.03 KiB
requests ------------------------------ 16.00 KiB/63.41 KiB
packaging ------------------------------ 14.88 KiB/64.91 KiB
text-unidecode ------------------------------ 76.32 KiB/76.32 KiB
click ------------------------------ 62.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 77.40 KiB/125.66 KiB
jinja2 ------------------------------ 6.87 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 93.69 KiB/219.24 KiB
python-dateutil ------------------------------ 32.00 KiB/224.50 KiB
pytest ------------------------------ 30.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 14.91 KiB/5.31 MiB
ruff ------------------------------ 92.68 KiB/11.02 MiB
duckdb ------------------------------ 221.61 KiB/19.27 MiB
Building scubaduck @ file:///workspace/scubaduck
⠙ Preparing packages... (0/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
itsdangerous ------------------------------ 14.88 KiB/15.85 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
markupsafe ------------------------------ 22.58 KiB/22.58 KiB
execnet ------------------------------ 32.00 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 16.00 KiB/63.41 KiB
packaging ------------------------------ 14.88 KiB/64.91 KiB
text-unidecode ------------------------------ 76.32 KiB/76.32 KiB
click ------------------------------ 62.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 77.40 KiB/125.66 KiB
jinja2 ------------------------------ 6.87 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 93.69 KiB/219.24 KiB
python-dateutil ------------------------------ 32.00 KiB/224.50 KiB
pytest ------------------------------ 30.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 14.91 KiB/5.31 MiB
ruff ------------------------------ 108.68 KiB/11.02 MiB
duckdb ------------------------------ 237.61 KiB/19.27 MiB
playwright ------------------------------ 8.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠙ Preparing packages... (0/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
itsdangerous ------------------------------ 14.88 KiB/15.85 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
markupsafe ------------------------------ 22.58 KiB/22.58 KiB
execnet ------------------------------ 32.00 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 32.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 62.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 77.40 KiB/125.66 KiB
jinja2 ------------------------------ 30.88 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 93.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 62.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 30.91 KiB/5.31 MiB
ruff ------------------------------ 188.68 KiB/11.02 MiB
duckdb ------------------------------ 333.61 KiB/19.27 MiB
playwright ------------------------------ 16.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
itsdangerous ------------------------------ 14.88 KiB/15.85 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
markupsafe ------------------------------ 22.58 KiB/22.58 KiB
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 32.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 78.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 30.88 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 93.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 62.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 46.91 KiB/5.31 MiB
ruff ------------------------------ 204.68 KiB/11.02 MiB
duckdb ------------------------------ 349.61 KiB/19.27 MiB
playwright ------------------------------ 16.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
itsdangerous ------------------------------ 14.88 KiB/15.85 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 32.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 78.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 30.88 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 93.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 62.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 46.91 KiB/5.31 MiB
ruff ------------------------------ 220.68 KiB/11.02 MiB
duckdb ------------------------------ 365.61 KiB/19.27 MiB
playwright ------------------------------ 16.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyee ------------------------------ 14.91 KiB/15.36 KiB
pluggy ------------------------------ 20.06 KiB/20.06 KiB
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 48.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 78.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 30.88 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 109.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 62.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 78.91 KiB/5.31 MiB
ruff ------------------------------ 252.68 KiB/11.02 MiB
duckdb ------------------------------ 397.61 KiB/19.27 MiB
playwright ------------------------------ 16.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pluggy ------------------------------ 20.06 KiB/20.06 KiB
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 48.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 94.88 KiB/99.76 KiB
flask ------------------------------ 62.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 46.88 KiB/131.74 KiB
certifi ------------------------------ 155.88 KiB/155.88 KiB
werkzeug ------------------------------ 109.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 62.88 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 78.91 KiB/5.31 MiB
ruff ------------------------------ 252.68 KiB/11.02 MiB
duckdb ------------------------------ 397.61 KiB/19.27 MiB
playwright ------------------------------ 32.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pluggy ------------------------------ 20.06 KiB/20.06 KiB
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 48.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 94.88 KiB/99.76 KiB
flask ------------------------------ 78.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 46.88 KiB/131.74 KiB
werkzeug ------------------------------ 109.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 75.19 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 94.91 KiB/5.31 MiB
ruff ------------------------------ 268.68 KiB/11.02 MiB
duckdb ------------------------------ 413.61 KiB/19.27 MiB
playwright ------------------------------ 32.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
execnet ------------------------------ 39.66 KiB/39.66 KiB
pytest-xdist ------------------------------ 32.00 KiB/45.03 KiB
requests ------------------------------ 48.00 KiB/63.41 KiB
packaging ------------------------------ 46.88 KiB/64.91 KiB
click ------------------------------ 94.88 KiB/99.76 KiB
flask ------------------------------ 78.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 46.88 KiB/131.74 KiB
werkzeug ------------------------------ 109.69 KiB/219.24 KiB
python-dateutil ------------------------------ 48.00 KiB/224.50 KiB
pytest ------------------------------ 75.19 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 94.91 KiB/5.31 MiB
ruff ------------------------------ 268.68 KiB/11.02 MiB
duckdb ------------------------------ 413.61 KiB/19.27 MiB
playwright ------------------------------ 32.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest-xdist ------------------------------ 45.03 KiB/45.03 KiB
requests ------------------------------ 63.41 KiB/63.41 KiB
packaging ------------------------------ 62.88 KiB/64.91 KiB
click ------------------------------ 99.76 KiB/99.76 KiB
flask ------------------------------ 78.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 94.76 KiB/131.74 KiB
werkzeug ------------------------------ 125.69 KiB/219.24 KiB
python-dateutil ------------------------------ 95.48 KiB/224.50 KiB
pytest ------------------------------ 107.19 KiB/335.58 KiB
greenlet ------------------------------ 495.59 KiB/589.71 KiB
pyright ------------------------------ 238.91 KiB/5.31 MiB
ruff ------------------------------ 412.68 KiB/11.02 MiB
duckdb ------------------------------ 557.61 KiB/19.27 MiB
playwright ------------------------------ 32.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest-xdist ------------------------------ 45.03 KiB/45.03 KiB
requests ------------------------------ 63.41 KiB/63.41 KiB
packaging ------------------------------ 62.88 KiB/64.91 KiB
flask ------------------------------ 94.88 KiB/100.88 KiB
urllib3 ------------------------------ 93.40 KiB/125.66 KiB
jinja2 ------------------------------ 94.76 KiB/131.74 KiB
werkzeug ------------------------------ 141.69 KiB/219.24 KiB
python-dateutil ------------------------------ 143.48 KiB/224.50 KiB
pytest ------------------------------ 123.19 KiB/335.58 KiB
greenlet ------------------------------ 511.59 KiB/589.71 KiB
pyright ------------------------------ 270.91 KiB/5.31 MiB
ruff ------------------------------ 444.68 KiB/11.02 MiB
duckdb ------------------------------ 589.61 KiB/19.27 MiB
playwright ------------------------------ 48.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest-xdist ------------------------------ 45.03 KiB/45.03 KiB
packaging ------------------------------ 62.88 KiB/64.91 KiB
flask ------------------------------ 100.88 KiB/100.88 KiB
urllib3 ------------------------------ 109.40 KiB/125.66 KiB
jinja2 ------------------------------ 110.76 KiB/131.74 KiB
werkzeug ------------------------------ 141.69 KiB/219.24 KiB
python-dateutil ------------------------------ 191.48 KiB/224.50 KiB
pytest ------------------------------ 123.19 KiB/335.58 KiB
greenlet ------------------------------ 511.59 KiB/589.71 KiB
pyright ------------------------------ 334.91 KiB/5.31 MiB
ruff ------------------------------ 508.68 KiB/11.02 MiB
duckdb ------------------------------ 669.61 KiB/19.27 MiB
playwright ------------------------------ 48.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest-xdist ------------------------------ 45.03 KiB/45.03 KiB
flask ------------------------------ 100.88 KiB/100.88 KiB
urllib3 ------------------------------ 109.40 KiB/125.66 KiB
jinja2 ------------------------------ 110.76 KiB/131.74 KiB
werkzeug ------------------------------ 141.69 KiB/219.24 KiB
python-dateutil ------------------------------ 224.50 KiB/224.50 KiB
pytest ------------------------------ 139.19 KiB/335.58 KiB
greenlet ------------------------------ 511.59 KiB/589.71 KiB
pyright ------------------------------ 382.91 KiB/5.31 MiB
ruff ------------------------------ 556.68 KiB/11.02 MiB
duckdb ------------------------------ 701.61 KiB/19.27 MiB
playwright ------------------------------ 48.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
flask ------------------------------ 100.88 KiB/100.88 KiB
urllib3 ------------------------------ 109.40 KiB/125.66 KiB
jinja2 ------------------------------ 110.76 KiB/131.74 KiB
werkzeug ------------------------------ 141.69 KiB/219.24 KiB
python-dateutil ------------------------------ 224.50 KiB/224.50 KiB
pytest ------------------------------ 139.19 KiB/335.58 KiB
greenlet ------------------------------ 511.59 KiB/589.71 KiB
pyright ------------------------------ 382.91 KiB/5.31 MiB
ruff ------------------------------ 572.68 KiB/11.02 MiB
duckdb ------------------------------ 701.61 KiB/19.27 MiB
playwright ------------------------------ 48.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
urllib3 ------------------------------ 125.66 KiB/125.66 KiB
jinja2 ------------------------------ 126.76 KiB/131.74 KiB
werkzeug ------------------------------ 141.69 KiB/219.24 KiB
python-dateutil ------------------------------ 224.50 KiB/224.50 KiB
pytest ------------------------------ 171.19 KiB/335.58 KiB
greenlet ------------------------------ 543.59 KiB/589.71 KiB
pyright ------------------------------ 456.56 KiB/5.31 MiB
ruff ------------------------------ 652.68 KiB/11.02 MiB
duckdb ------------------------------ 797.61 KiB/19.27 MiB
playwright ------------------------------ 48.00 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
urllib3 ------------------------------ 125.66 KiB/125.66 KiB
jinja2 ------------------------------ 126.76 KiB/131.74 KiB
werkzeug ------------------------------ 157.69 KiB/219.24 KiB
pytest ------------------------------ 187.19 KiB/335.58 KiB
greenlet ------------------------------ 543.59 KiB/589.71 KiB
pyright ------------------------------ 536.56 KiB/5.31 MiB
ruff ------------------------------ 716.68 KiB/11.02 MiB
duckdb ------------------------------ 877.61 KiB/19.27 MiB
playwright ------------------------------ 61.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
urllib3 ------------------------------ 125.66 KiB/125.66 KiB
jinja2 ------------------------------ 126.76 KiB/131.74 KiB
werkzeug ------------------------------ 157.69 KiB/219.24 KiB
pytest ------------------------------ 187.19 KiB/335.58 KiB
greenlet ------------------------------ 543.59 KiB/589.71 KiB
pyright ------------------------------ 584.56 KiB/5.31 MiB
ruff ------------------------------ 748.68 KiB/11.02 MiB
duckdb ------------------------------ 909.61 KiB/19.27 MiB
playwright ------------------------------ 61.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
jinja2 ------------------------------ 131.74 KiB/131.74 KiB
werkzeug ------------------------------ 157.69 KiB/219.24 KiB
pytest ------------------------------ 187.19 KiB/335.58 KiB
greenlet ------------------------------ 543.59 KiB/589.71 KiB
pyright ------------------------------ 600.56 KiB/5.31 MiB
ruff ------------------------------ 780.68 KiB/11.02 MiB
duckdb ------------------------------ 925.61 KiB/19.27 MiB
playwright ------------------------------ 61.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
werkzeug ------------------------------ 157.69 KiB/219.24 KiB
pytest ------------------------------ 203.19 KiB/335.58 KiB
greenlet ------------------------------ 559.59 KiB/589.71 KiB
pyright ------------------------------ 664.56 KiB/5.31 MiB
ruff ------------------------------ 844.68 KiB/11.02 MiB
duckdb ------------------------------ 989.61 KiB/19.27 MiB
playwright ------------------------------ 77.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest ------------------------------ 251.19 KiB/335.58 KiB
greenlet ------------------------------ 575.59 KiB/589.71 KiB
pyright ------------------------------ 1.16 MiB/5.31 MiB
ruff ------------------------------ 1.32 MiB/11.02 MiB
duckdb ------------------------------ 1.47 MiB/19.27 MiB
playwright ------------------------------ 109.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest ------------------------------ 251.19 KiB/335.58 KiB
greenlet ------------------------------ 589.71 KiB/589.71 KiB
pyright ------------------------------ 1.23 MiB/5.31 MiB
ruff ------------------------------ 1.40 MiB/11.02 MiB
duckdb ------------------------------ 1.53 MiB/19.27 MiB
playwright ------------------------------ 109.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pytest ------------------------------ 271.19 KiB/335.58 KiB
pyright ------------------------------ 1.32 MiB/5.31 MiB
ruff ------------------------------ 1.49 MiB/11.02 MiB
duckdb ------------------------------ 1.64 MiB/19.27 MiB
playwright ------------------------------ 157.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyright ------------------------------ 1.78 MiB/5.31 MiB
ruff ------------------------------ 2.07 MiB/11.02 MiB
duckdb ------------------------------ 2.25 MiB/19.27 MiB
playwright ------------------------------ 717.26 KiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyright ------------------------------ 1.79 MiB/5.31 MiB
ruff ------------------------------ 2.44 MiB/11.02 MiB
duckdb ------------------------------ 2.63 MiB/19.27 MiB
playwright ------------------------------ 1.09 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠹ Preparing packages... (10/33)
pyright ------------------------------ 1.84 MiB/5.31 MiB
ruff ------------------------------ 3.77 MiB/11.02 MiB
duckdb ------------------------------ 3.92 MiB/19.27 MiB
playwright ------------------------------ 2.43 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠸ Preparing packages... (28/33)
pyright ------------------------------ 1.90 MiB/5.31 MiB
ruff ------------------------------ 5.12 MiB/11.02 MiB
duckdb ------------------------------ 5.31 MiB/19.27 MiB
playwright ------------------------------ 3.78 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠸ Preparing packages... (28/33)
pyright ------------------------------ 1.97 MiB/5.31 MiB
ruff ------------------------------ 6.53 MiB/11.02 MiB
duckdb ------------------------------ 6.71 MiB/19.27 MiB
playwright ------------------------------ 5.19 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠸ Preparing packages... (28/33)
pyright ------------------------------ 2.05 MiB/5.31 MiB
ruff ------------------------------ 8.05 MiB/11.02 MiB
duckdb ------------------------------ 8.23 MiB/19.27 MiB
playwright ------------------------------ 6.73 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠸ Preparing packages... (28/33)
pyright ------------------------------ 2.11 MiB/5.31 MiB
ruff ------------------------------ 9.52 MiB/11.02 MiB
duckdb ------------------------------ 9.64 MiB/19.27 MiB
playwright ------------------------------ 8.22 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.14 MiB/5.31 MiB
ruff ------------------------------ 10.89 MiB/11.02 MiB
duckdb ------------------------------ 11.03 MiB/19.27 MiB
playwright ------------------------------ 9.57 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.14 MiB/5.31 MiB
duckdb ------------------------------ 11.20 MiB/19.27 MiB
playwright ------------------------------ 9.75 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.19 MiB/5.31 MiB
duckdb ------------------------------ 12.94 MiB/19.27 MiB
playwright ------------------------------ 11.54 MiB/43.05 MiB
Building scubaduck @ file:///workspace/scubaduck
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.22 MiB/5.31 MiB
duckdb ------------------------------ 15.11 MiB/19.27 MiB
playwright ------------------------------ 13.70 MiB/43.05 MiB
Built scubaduck @ file:///workspace/scubaduck
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.25 MiB/5.31 MiB
duckdb ------------------------------ 16.70 MiB/19.27 MiB
playwright ------------------------------ 15.25 MiB/43.05 MiB
⠼ Preparing packages... (28/33)
pyright ------------------------------ 2.25 MiB/5.31 MiB
duckdb ------------------------------ 17.09 MiB/19.27 MiB
playwright ------------------------------ 15.67 MiB/43.05 MiB
⠴ Preparing packages... (30/33)
pyright ------------------------------ 2.30 MiB/5.31 MiB
duckdb ------------------------------ 19.00 MiB/19.27 MiB
playwright ------------------------------ 17.58 MiB/43.05 MiB
⠴ Preparing packages... (30/33)
pyright ------------------------------ 2.38 MiB/5.31 MiB
playwright ------------------------------ 19.50 MiB/43.05 MiB
⠴ Preparing packages... (30/33)
pyright ------------------------------ 2.39 MiB/5.31 MiB
playwright ------------------------------ 20.80 MiB/43.05 MiB
⠴ Preparing packages... (30/33)
pyright ------------------------------ 2.44 MiB/5.31 MiB
playwright ------------------------------ 25.64 MiB/43.05 MiB
⠦ Preparing packages... (31/33)
pyright ------------------------------ 2.58 MiB/5.31 MiB
playwright ------------------------------ 27.34 MiB/43.05 MiB
⠦ Preparing packages... (31/33)
pyright ------------------------------ 2.68 MiB/5.31 MiB
playwright ------------------------------ 29.00 MiB/43.05 MiB
⠦ Preparing packages... (31/33)
pyright ------------------------------ 2.78 MiB/5.31 MiB
playwright ------------------------------ 30.97 MiB/43.05 MiB
⠦ Preparing packages... (31/33)
pyright ------------------------------ 2.91 MiB/5.31 MiB
playwright ------------------------------ 32.51 MiB/43.05 MiB
⠦ Preparing packages... (31/33)
pyright ------------------------------ 3.09 MiB/5.31 MiB
playwright ------------------------------ 34.47 MiB/43.05 MiB
⠧ Preparing packages... (31/33)
pyright ------------------------------ 3.22 MiB/5.31 MiB
playwright ------------------------------ 36.06 MiB/43.05 MiB
⠧ Preparing packages... (31/33)
pyright ------------------------------ 3.35 MiB/5.31 MiB
playwright ------------------------------ 37.96 MiB/43.05 MiB
⠧ Preparing packages... (31/33)
pyright ------------------------------ 3.53 MiB/5.31 MiB
playwright ------------------------------ 39.58 MiB/43.05 MiB
⠧ Preparing packages... (31/33)
pyright ------------------------------ 3.69 MiB/5.31 MiB
playwright ------------------------------ 40.98 MiB/43.05 MiB
⠇ Preparing packages... (31/33)
pyright ------------------------------ 3.89 MiB/5.31 MiB
playwright ------------------------------ 42.15 MiB/43.05 MiB
⠇ Preparing packages... (31/33)
pyright ------------------------------ 4.02 MiB/5.31 MiB
⠇ Preparing packages... (31/33)
pyright ------------------------------ 4.25 MiB/5.31 MiB
⠇ Preparing packages... (31/33)
pyright ------------------------------ 4.49 MiB/5.31 MiB
⠇ Preparing packages... (31/33)
Prepared 33 packages in 1.58s
░░░░░░░░░░░░░░░░░░░░ [0/0] Installing wheels...
░░░░░░░░░░░░░░░░░░░░ [0/33] Installing wheels...
░░░░░░░░░░░░░░░░░░░░ [0/33] python-slugify==8.0.4
░░░░░░░░░░░░░░░░░░░░ [1/33] python-slugify==8.0.4
░░░░░░░░░░░░░░░░░░░░ [1/33] execnet==2.1.1
█░░░░░░░░░░░░░░░░░░░ [2/33] execnet==2.1.1
█░░░░░░░░░░░░░░░░░░░ [2/33] six==1.17.0
█░░░░░░░░░░░░░░░░░░░ [3/33] six==1.17.0
█░░░░░░░░░░░░░░░░░░░ [3/33] click==8.2.0
██░░░░░░░░░░░░░░░░░░ [4/33] click==8.2.0
██░░░░░░░░░░░░░░░░░░ [4/33] typing-extensions==4.13.2
███░░░░░░░░░░░░░░░░░ [5/33] typing-extensions==4.13.2
███░░░░░░░░░░░░░░░░░ [5/33] blinker==1.9.0
███░░░░░░░░░░░░░░░░░ [6/33] blinker==1.9.0
███░░░░░░░░░░░░░░░░░ [6/33] idna==3.10
████░░░░░░░░░░░░░░░░ [7/33] idna==3.10
████░░░░░░░░░░░░░░░░ [7/33] requests==2.32.3
████░░░░░░░░░░░░░░░░ [8/33] requests==2.32.3
████░░░░░░░░░░░░░░░░ [8/33] pytest-base-url==2.1.0
█████░░░░░░░░░░░░░░░ [9/33] pytest-base-url==2.1.0
███████████████████░ [32/33] pyright==1.1.400
Installed 33 packages in 81ms
+ blinker==1.9.0
+ certifi==2025.4.26
+ charset-normalizer==3.4.2
+ click==8.2.0
+ duckdb==1.2.2
+ execnet==2.1.1
+ flask==3.1.1
+ greenlet==3.2.2
+ idna==3.10
+ iniconfig==2.1.0
+ itsdangerous==2.2.0
+ jinja2==3.1.6
+ markupsafe==3.0.2
+ nodeenv==1.9.1
+ packaging==25.0
+ playwright==1.52.0
+ pluggy==1.6.0
+ pyee==13.0.0
+ pyright==1.1.400
+ pytest==8.3.5
+ pytest-base-url==2.1.0
+ pytest-playwright==0.7.0
+ pytest-xdist==3.6.1
+ python-dateutil==2.9.0.post0
+ python-slugify==8.0.4
+ requests==2.32.3
+ ruff==0.11.10
+ scubaduck==0.1.0 (from file:///workspace/scubaduck)
+ six==1.17.0
+ text-unidecode==1.3
+ typing-extensions==4.13.2
+ urllib3==2.4.0
+ werkzeug==3.1.3
++ source .venv/bin/activate
+++ '[' -z '' ']'
+++ '[' -n x ']'
+++ SCRIPT_PATH=.venv/bin/activate
+++ '[' .venv/bin/activate = /tmp/o8Ni9g-setup_script.sh ']'
+++ deactivate nondestructive
+++ unset -f pydoc
+++ '[' -z '' ']'
+++ '[' -z '' ']'
+++ hash -r
+++ '[' -z '' ']'
+++ unset VIRTUAL_ENV
+++ unset VIRTUAL_ENV_PROMPT
+++ '[' '!' nondestructive = nondestructive ']'
+++ VIRTUAL_ENV=/workspace/scubaduck/.venv
+++ '[' linux-gnu = cygwin ']'
+++ '[' linux-gnu = msys ']'
+++ export VIRTUAL_ENV
+++ '[' -z '' ']'
+++ unset SCRIPT_PATH
+++ _OLD_VIRTUAL_PATH=/root/.cargo/bin:/root/.rbenv/shims:/root/.rbenv/bin:/root/.rbenv/shims:/root/.local/share/swiftly/bin:/root/.bun/bin:/root/.nvm/versions/node/v22.15.1/bin:/root/.pyenv/shims:3441PYENV_ROOT/shims:/root/.pyenv/bin:/usr/local/go/bin:/root/go/bin:/root/.rbenv/bin:/root/.rbenv/shims:/root/.bun/bin:/root/.local/bin:/root/.pyenv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ PATH=/workspace/scubaduck/.venv/bin:/root/.cargo/bin:/root/.rbenv/shims:/root/.rbenv/bin:/root/.rbenv/shims:/root/.local/share/swiftly/bin:/root/.bun/bin:/root/.nvm/versions/node/v22.15.1/bin:/root/.pyenv/shims:3441PYENV_ROOT/shims:/root/.pyenv/bin:/usr/local/go/bin:/root/go/bin:/root/.rbenv/bin:/root/.rbenv/shims:/root/.bun/bin:/root/.local/bin:/root/.pyenv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ export PATH
+++ '[' xscubaduck '!=' x ']'
+++ VIRTUAL_ENV_PROMPT='(scubaduck) '
+++ export VIRTUAL_ENV_PROMPT
+++ '[' -z '' ']'
+++ '[' -z '' ']'
+++ _OLD_VIRTUAL_PS1=
+++ PS1='(scubaduck) '
+++ export PS1
+++ alias pydoc
+++ true
+++ hash -r
++ playwright install chromium
Downloading Chromium 136.0.7103.25 (playwright build v1169) from https://cdn.playwright.dev/dbazure/download/playwright/builds/chromium/1169/chromium-linux.zip
167.7 MiB [] 0% 0.0s167.7 MiB [] 0% 25.5s167.7 MiB [] 0% 21.7s167.7 MiB [] 0% 11.1s167.7 MiB [] 1% 7.0s167.7 MiB [] 1% 4.5s167.7 MiB [] 2% 4.4s167.7 MiB [] 3% 3.5s167.7 MiB [] 4% 3.1s167.7 MiB [] 5% 2.8s167.7 MiB [] 5% 2.7s167.7 MiB [] 6% 2.7s167.7 MiB [] 7% 2.6s167.7 MiB [] 8% 2.4s167.7 MiB [] 9% 2.3s167.7 MiB [] 9% 2.4s167.7 MiB [] 11% 2.3s167.7 MiB [] 13% 1.9s167.7 MiB [] 15% 1.8s167.7 MiB [] 16% 1.7s167.7 MiB [] 18% 1.6s167.7 MiB [] 19% 1.5s167.7 MiB [] 21% 1.5s167.7 MiB [] 22% 1.4s167.7 MiB [] 24% 1.3s167.7 MiB [] 26% 1.2s167.7 MiB [] 27% 1.2s167.7 MiB [] 29% 1.2s167.7 MiB [] 30% 1.1s167.7 MiB [] 32% 1.0s167.7 MiB [] 34% 1.0s167.7 MiB [] 36% 1.0s167.7 MiB [] 38% 0.9s167.7 MiB [] 39% 0.9s167.7 MiB [] 41% 0.8s167.7 MiB [] 43% 0.8s167.7 MiB [] 44% 0.8s167.7 MiB [] 45% 0.7s167.7 MiB [] 46% 0.7s167.7 MiB [] 47% 0.7s167.7 MiB [] 48% 0.7s167.7 MiB [] 49% 0.7s167.7 MiB [] 50% 0.7s167.7 MiB [] 51% 0.7s167.7 MiB [] 52% 0.7s167.7 MiB [] 53% 0.7s167.7 MiB [] 55% 0.6s167.7 MiB [] 57% 0.6s167.7 MiB [] 58% 0.6s167.7 MiB [] 59% 0.6s167.7 MiB [] 61% 0.5s167.7 MiB [] 62% 0.5s167.7 MiB [] 63% 0.5s167.7 MiB [] 65% 0.5s167.7 MiB [] 66% 0.5s167.7 MiB [] 68% 0.4s167.7 MiB [] 70% 0.4s167.7 MiB [] 71% 0.4s167.7 MiB [] 72% 0.4s167.7 MiB [] 73% 0.4s167.7 MiB [] 74% 0.3s167.7 MiB [] 76% 0.3s167.7 MiB [] 77% 0.3s167.7 MiB [] 80% 0.3s167.7 MiB [] 82% 0.2s167.7 MiB [] 84% 0.2s167.7 MiB [] 86% 0.2s167.7 MiB [] 88% 0.1s167.7 MiB [] 90% 0.1s167.7 MiB [] 93% 0.1s167.7 MiB [] 95% 0.1s167.7 MiB [] 97% 0.0s167.7 MiB [] 99% 0.0s167.7 MiB [] 100% 0.0s
Chromium 136.0.7103.25 (playwright build v1169) downloaded to /root/.cache/ms-playwright/chromium-1169
Downloading FFMPEG playwright build v1011 from https://cdn.playwright.dev/dbazure/download/playwright/builds/ffmpeg/1011/ffmpeg-linux.zip
2.3 MiB [] 0% 0.0s2.3 MiB [] 2% 0.9s2.3 MiB [] 21% 0.1s2.3 MiB [] 49% 0.1s2.3 MiB [] 100% 0.0s
FFMPEG playwright build v1011 downloaded to /root/.cache/ms-playwright/ffmpeg-1011
Downloading Chromium Headless Shell 136.0.7103.25 (playwright build v1169) from https://cdn.playwright.dev/dbazure/download/playwright/builds/chromium/1169/chromium-headless-shell-linux.zip
101.4 MiB [] 0% 0.0s101.4 MiB [] 0% 16.2s101.4 MiB [] 0% 10.2s101.4 MiB [] 0% 6.4s101.4 MiB [] 1% 4.7s101.4 MiB [] 3% 2.6s101.4 MiB [] 3% 2.7s101.4 MiB [] 5% 2.0s101.4 MiB [] 7% 1.7s101.4 MiB [] 8% 1.7s101.4 MiB [] 8% 1.8s101.4 MiB [] 10% 1.7s101.4 MiB [] 11% 1.5s101.4 MiB [] 13% 1.4s101.4 MiB [] 15% 1.3s101.4 MiB [] 18% 1.1s101.4 MiB [] 21% 1.0s101.4 MiB [] 23% 0.9s101.4 MiB [] 27% 0.8s101.4 MiB [] 29% 0.7s101.4 MiB [] 34% 0.6s101.4 MiB [] 36% 0.6s101.4 MiB [] 40% 0.5s101.4 MiB [] 44% 0.5s101.4 MiB [] 46% 0.5s101.4 MiB [] 50% 0.4s101.4 MiB [] 52% 0.4s101.4 MiB [] 54% 0.4s101.4 MiB [] 57% 0.3s101.4 MiB [] 61% 0.3s101.4 MiB [] 63% 0.3s101.4 MiB [] 66% 0.3s101.4 MiB [] 69% 0.2s101.4 MiB [] 70% 0.2s101.4 MiB [] 70% 0.3s101.4 MiB [] 74% 0.2s101.4 MiB [] 78% 0.2s101.4 MiB [] 84% 0.1s101.4 MiB [] 88% 0.1s101.4 MiB [] 91% 0.1s101.4 MiB [] 95% 0.0s101.4 MiB [] 98% 0.0s101.4 MiB [] 100% 0.0s
Chromium Headless Shell 136.0.7103.25 (playwright build v1169) downloaded to /root/.cache/ms-playwright/chromium_headless_shell-1169
++ echo 'source .venv/bin/activate'I'll look for AGENTS.md in the root of the repository.
bash: .venv/bin/activate: No such file or directory
root@75b162e381df:/workspace# ls
scubaduckroot@75b162e381df:/workspace# cd scubaduck
root@75b162e381df:/workspace/scubaduck# ls
AGENTS.md codex_setup.sh scubaduck tests
README.md pyproject.toml stubs uv.lockroot@75b162e381df:/workspace/scubaduck# cat AGENTS.md
- Use "source .venv/bin/activate" to activate the virtual environment before
running any commands
- ONLY use non-interactive commands like cat, sed, apply_patch to do edits.
Do NOT use interactive editors.
- Do NOT attempt to install packages. Only the packages specified in
pyproject.toml are available. You cannot add new packages. If you
desperately want another package, make a note of it in the final PR
description.
- Use conventional commits to format PR title
- There are no nested AGENTS.md files, this is the only agents file
- When using Playwright, ONLY use chromium browser. This browser is already
installed.
- Use "ruff check" to check lint, "ruff format" to autoformat files and
"pyright" to typecheck.
- When writing the PR description, include the original prompt supplied by the
user.
- When you add functionality to the server, add server tests to
tests/test_server.py. When you add features to the frontend, add frontend
tests to tests/test_web.pyAGENTS says to activate a venv before running commands like ruff check and pyright.
root@75b162e381df:/workspace/scubaduck# cat README.md
I really like Scuba (Meta's internal real-time database system). The distributed
, real-time database part of Scuba is quite difficult (and expensive) to replica
te, but I also really like Scuba's UI for doing queries, and I have found myself
wishing that I have access to it even for "small" databases, e.g., I have a sql
ite dataset I want to explore.
Pivotal ideas:
* Time series by default. In the dedicated "time series" view, there are many fe
atures specifically oriented towards working towards tables that represent event
s that occurred over time: the start, end, compare, aggregate and granularity fi
elds all specially privilege the timestamp field. In fact, you can't log events
to Scuba's backing data store without a timestamp, they always come with one. (S
cuba also supports other views that don't presuppose a time series, but the time
series is the most beloved and well used view.) This is in contrast to typical
software which tries to generalize to arbitrary data first, with time series bei
ng added on later.
* It's all about exploration. Scuba is predicated on the idea that you don't kno
w what you're looking for, that you are going to spend time tweaking queries and
changing filters/grouping as part of an investigation to figure out why a syste
m behaves the way it is. So the filters/comparisons/groupings you want to edit a
re always visible on the left sidebar, with the expectation that you're going to
tweak the query to look at something else. Similarly, all the parameters of you
r query get saved into your URL, so your browser history can double up as a quer
y history / you can easily share a query with someone else. This is contrast to
typical software which is often oriented to making pretty dashboards and reports
. (This function is important too, but it's not what I want in exploration mode!
)
* You can fix data problems in the query editor. It's pretty common to have mess
ed up and ended up with a database that doesn't have exactly the columns you nee
d, or some columns that are corrupted in some way. Scuba has pretty robust suppo
rt for defining custom columns with arbitrary SQL functions, grouping over them
as if they were native functions, and doing so with minimal runtime cost (Scuba
aims to turn around your query in milliseconds!) Having to go and run a huge dat
a pipeline to fix your data is a big impediment to exploration; quick and easy c
ustom columns means you can patch over problems when you're investigating and fi
x them for real later.
We're going to build a exploratory data analysis tool like Scuba for time series
database (i.e., a database with a mandatory timestamp representing the time an
event occurred). We'll use DuckDB as the underlying SQL engine served from a Py
thon server, and render the GUI/results as a webpage with vanilla HTML and JS. W
e'll use choices.js to support token inputs. We define a token input to mean a
text input element where as you type a dropdown displays with valid values, and
if you select one or press enter, the selection turns into a token/chip that can
only be deleted as one unit.
To start, we are going to support one views: samples. The samples view only all
ows you to view individual samples from the database, subject to a filter. Our m
ain UI concept is that there is a left sidebar that is the query editor, and the
right side that shows the view. The sidebar is always visible and defaults to
the query parameters of the current view. After you make changes to the query,
clicking the "Dive" button updates the view. The URL of the page encodes all of
the values of the query (and gets updated when you Dive), so the browser's back
button lets you view previous queries.
The query editor's job is to generate a SQL query, which then is applied on the
database, and then the result visualized according to the view.
Here are the settings you can apply to the query. The help text should show up w
hen you mouse over the field name:
* Start/End - Help text: "Sets the start/end of the time range to query. Can be
any kind of datetime string. For example: 'April 23, 2014' or 'yesterday'." The
UI for this selector supports both relative selections (now, -1 hour, -3 hours,
-12 hours, -1 day, -3 days, -1 week, -1 fortnight, -30 days, -90 days) as well a
s specifying an absolute date. The way this field is rendered is there is a fre
e form text box, a drop down arrow (for the relative selectors), and then a cale
ndar button (for date selection).
* Order By - Help text: "Choose a column to sort results by." There is an ASC/D
ESC toggle next to it.
* Limit - Help text: "Choose the maximum number of results to show in the chart
after any aggregations have been applied. For example, a limit of 10 will show
no more than 10 rows for a table, etc."
* Filters - You can create as many filters as you want. You can either write a f
ilter using a UI or manual SQL. In the UI, filter consists of a column name, a r
elation (e.g., =, !=, <, >) and then a text field. The text field is a token inp
ut. It accepts multiple tokens for = relation, in which case we match using an O
R for all options.
There is also a "Columns" tab which lets you view all fields in the table, organ
ized by their type. You can also define derived columns, by specifying a column
name and SQL expression. Derived columns can be used for all parts of the UI, in
cluding filters/group by/etc. Columns have checkboxes indicating if we should SE
LECT them or not. Each selected column shows up in the graph. There is an All/N
one link which can be used to select/deselect all checkboxes.
The query UI constructs a SQL query that intuitively has this form:
```
SELECT column, column, ...,
FROM table
WHERE time >= min-timestamp
AND time <= max-timestamp
[AND condition ...]
ORDER BY aggregate(column)
LIMIT number
```
You should write tests for the server backend, demonstrating that at specific qu
ery values we get back the correct rows of data.I'll check the rest of the README to make sure I have all the details.
root@75b162e381df:/workspace/scubaduck# ^Croot@75b162e381df:/workspace/scubaduck# grep -n "View" -n README.mdI’ll check out the tests/test_server.py and test_web files in the tests directory.
root@75b162e381df:/workspace/scubaduck# ls tests
conftest.py test_server.py test_web.pyroot@75b162e381df:/workspace/scubaduck# cat tests/test_server.py
from __future__ import annotations
import json
from pathlib import Path
import duckdb
from scubaduck import server
import pytest
def test_basic_query() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-02 00:00:00",
"order_by": "timestamp",
"order_dir": "ASC",
"limit": 10,
"columns": ["timestamp", "event", "value", "user"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert data
rows = data["rows"]
# We expect first three rows (until 2024-01-02 00:00:00)
assert len(rows) == 3
assert rows[0][1] == "login"
assert rows[1][1] == "logout"
def test_js_served() -> None:
app = server.app
client = app.test_client()
rv = client.get("/js/chip_input.js")
assert rv.status_code == 200
assert b"initChipInput" in rv.data
def test_filter_multi_token() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-02 03:00:00",
"order_by": "timestamp",
"limit": 10,
"columns": ["timestamp", "event", "value", "user"],
"filters": [{"column": "user", "op": "=", "value": ["alice", "charlie"]}
],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert data
rows = data["rows"]
# Should only return rows for alice and charlie
assert len(rows) == 3
assert rows[0][3] == "alice"
assert rows[-1][3] == "charlie"
def test_empty_filter_is_noop() -> None:
app = server.app
client = app.test_client()
base_payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"limit": 100,
"columns": ["timestamp", "event", "value", "user"],
}
no_filter = {**base_payload, "filters": []}
empty_filter = {
**base_payload,
"filters": [{"column": "user", "op": "=", "value": None}],
}
rv1 = client.post(
"/api/query", data=json.dumps(no_filter), content_type="application/json
"
)
rv2 = client.post(
"/api/query", data=json.dumps(empty_filter), content_type="application/j
son"
)
rows1 = rv1.get_json()["rows"]
rows2 = rv2.get_json()["rows"]
assert rows1 == rows2
def test_select_columns() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"order_by": "timestamp",
"limit": 10,
"columns": ["timestamp", "user"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert data
rows = data["rows"]
assert len(rows[0]) == 2
assert rows[0][1] == "alice"
def test_string_filter_ops() -> None:
app = server.app
client = app.test_client()
base = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"order_by": "timestamp",
"limit": 100,
...
app = server.app
client = app.test_client()
payload = {
"graph_type": "samples",
"group_by": ["user"],
"columns": ["timestamp"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "only valid" in data["error"]
def test_table_avg_with_timestamp() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "user",
"limit": 100,
"columns": ["user", "timestamp", "value"],
"group_by": ["user"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert "error" not in data
rows = data["rows"]
assert rows[0][0] == "alice"
from dateutil import parser
ts = parser.parse(rows[0][1]).replace(tzinfo=None)
assert ts == parser.parse("2024-01-01 12:00:00")
def test_timeseries_basic() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 100,
"group_by": ["user"],
"aggregate": "Count",
"columns": ["value"],
"x_axis": "timestamp",
"granularity": "1 day",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 4
def test_timeseries_orders_by_xaxis() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 100,
"columns": ["value"],
"x_axis": "timestamp",
"granularity": "1 day",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
rows = data["rows"]
from dateutil import parser
timestamps = [parser.parse(r[0]).replace(tzinfo=None) for r in rows]
assert timestamps == sorted(timestamps)
def test_timeseries_string_column_error() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 7,
"columns": ["timestamp", "event", "value", "user"],
"x_axis": "timestamp",
"granularity": "1 hour",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "Aggregate" in data["error"]
def test_derived_column_basic() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"limit": 10,
"columns": ["timestamp"],
"derived_columns": {"val2": "value * 2"},
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert data["rows"][0][1] == 20I'll keep scrolling to check if there's more past 203 lines.
root@75b162e381df:/workspace/scubaduck# sed -n '200,400p' tests/test_server.py
assert len(rows) == 3
def test_group_by_table() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "user",
"limit": 10,
"columns": ["value"],
"group_by": ["user"],
"aggregate": "Sum",
"show_hits": True,
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
rows = rv.get_json()["rows"]
assert rows[0][0] == "alice"
assert rows[0][1] == 2
assert rows[0][2] == 40
def test_relative_time_query(monkeypatch: pytest.MonkeyPatch) -> None:
app = server.app
client = app.test_client()
from datetime import datetime
fixed_now = datetime(2024, 1, 2, 4, 0, 0)
class FixedDateTime(datetime):
@classmethod
def now(cls, tz=None): # type: ignore[override]
return fixed_now if tz is None else fixed_now.astimezone(tz)
monkeypatch.setattr(server, "datetime", FixedDateTime)
payload = {
"start": "-1 hour",
"end": "now",
"order_by": "timestamp",
"limit": 100,
"columns": ["timestamp", "event", "value", "user"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 1
assert data["rows"][0][3] == "charlie"
def test_invalid_time_error() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "nonsense",
"end": "now",
"order_by": "timestamp",
"limit": 10,
"columns": ["timestamp"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "error" in data
def test_query_error_returns_sql_and_traceback() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"columns": ["event"],
"group_by": ["user"],
"aggregate": "avg",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "error" in data
def test_table_unknown_column_error() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "timestamp",
"limit": 100,
"columns": ["user", "Hits", "value"],
"group_by": ["user"],
"aggregate": "Count",
"show_hits": True,
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "Unknown column" in data["error"]
def test_samples_view_rejects_group_by() -> None:
app = server.app
client = app.test_client()
payload = {
"graph_type": "samples",
"group_by": ["user"],
"columns": ["timestamp"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "only valid" in data["error"]
def test_table_avg_with_timestamp() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "user",
"limit": 100,
"columns": ["user", "timestamp", "value"],
"group_by": ["user"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert "error" not in data
rows = data["rows"]
assert rows[0][0] == "alice"
from dateutil import parser
ts = parser.parse(rows[0][1]).replace(tzinfo=None)
assert ts == parser.parse("2024-01-01 12:00:00")
def test_timeseries_basic() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 100,
"group_by": ["user"],
"aggregate": "Count",
"columns": ["value"],
"x_axis": "timestamp",
"granularity": "1 day",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 4
def test_timeseries_orders_by_xaxis() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 100,
"columns": ["value"],
"x_axis": "timestamp",
"granularity": "1 day",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
rows = data["rows"]
from dateutil import parserI need to keep going to reach the bottom lines.
root@75b162e381df:/workspace/scubaduck# wc -l tests/test_server.py
441 tests/test_server.pyI’ll open test_web now after checking the 441 lines and duplicates I found.
select_value(page, "#order_by", order_by)
if order_dir is not None and order_dir == "DESC":
page.click("#order_dir")
if limit is not None:
page.fill("#limit", str(limit))
if group_by is not None:
select_value(page, "#graph_type", "table")
page.evaluate(
"g => { groupBy.chips = g; groupBy.renderChips(); }",
group_by,
)
if aggregate is not None:
select_value(page, "#graph_type", "table")
select_value(page, "#aggregate", aggregate)
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
return page.evaluate("window.lastResults")
def test_range_filters(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-02 00:00:00",
end="2024-01-02 04:00:00",
order_by="timestamp",
limit=100,
)
assert len(data["rows"]) == 2
from dateutil import parser
timestamps = [parser.parse(row[0]).replace(tzinfo=None) for row in data["row
s"]]
assert timestamps == [
parser.parse("2024-01-02 00:00:00"),
parser.parse("2024-01-02 03:00:00"),
]
def test_order_by(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="value",
order_dir="DESC",
limit=100,
)
values = [row[2] for row in data["rows"]]
assert values == sorted(values, reverse=True)
def test_limit(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="timestamp",
limit=2,
)
assert len(data["rows"]) == 2
def test_simple_filter(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Add Filter")
filter_el = page.query_selector("#filters .filter:last-child")
assert filter_el
page.evaluate(
"arg => setSelectValue(arg.el.querySelector('.f-col'), arg.val)",
{"el": filter_el, "val": "user"},
)
val_input = filter_el.query_selector(".f-val")
val_input.click()
page.keyboard.type("alice")
page.keyboard.press("Enter")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
data = page.evaluate("window.lastResults")
assert len(data["rows"]) == 2
assert all(row[3] == "alice" for row in data["rows"])
def test_default_filter_and_layout(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
count = page.evaluate("document.querySelectorAll('#filters .filter').length"
)
assert count == 1
last_is_button = page.evaluate(
"document.querySelector('#filters').lastElementChild.id === 'add_filter'
"
)
assert last_is_button
position = page.evaluate(
"getComputedStyle(document.querySelector('#filters .filter button.remove
')).position"
)
assert position == "static"
def test_filter_remove_alignment(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
diff = page.evaluate(
"() => { const r=document.querySelector('#filters .filter-row').getBound
ingClientRect(); const x=document.querySelector('#filters .filter-row button.rem
ove').getBoundingClientRect(); return Math.abs(r.right - x.right); }"
)
assert diff <= 1
def test_header_and_tabs(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
header = page.text_content("#header")
assert "sample.csv" in header
assert "events" in header
...
data = run_query(
page,
server_url,
start="2025-01-01 00:00:00",
end="2025-01-02 00:00:00",
order_by="timestamp",
limit=100,
)
assert data["rows"] == []
msg = page.text_content("#view")
assert "Empty data provided to table" in msg
def test_group_by_chip_from_url(page: Any, server_url: str) -> None:
url = f"{server_url}?graph_type=table&group_by=user&order_by=user&limit=10"
page.goto(url)
page.wait_for_selector("#group_by_field .chip", state="attached")
chips = page.evaluate(
"Array.from(document.querySelectorAll('#group_by_field .chip')).map(c =>
c.firstChild.textContent)"
)
assert chips == ["user"]
def test_group_by_autocomplete(page: Any, server_url: str) -> None:
page.goto(f"{server_url}?graph_type=table")
page.wait_for_selector("#group_by_field", state="visible")
inp = page.query_selector("#group_by_field .f-val")
assert inp
inp.click()
page.keyboard.type("us")
page.wait_for_selector("#group_by_field .chip-dropdown div")
options = page.locator("#group_by_field .chip-dropdown div").all_inner_texts
()
assert "user" in options
def test_group_by_copy_icon(page: Any, server_url: str) -> None:
page.goto(f"{server_url}?graph_type=table")
page.wait_for_selector("#group_by_field", state="visible")
icon = page.text_content("#group_by_field .chip-copy")
assert icon == "⎘"
def test_group_by_input_no_border(page: Any, server_url: str) -> None:
page.goto(f"{server_url}?graph_type=table")
page.wait_for_selector("#group_by_field", state="visible")
border = page.evaluate(
"getComputedStyle(document.querySelector('#group_by_field .f-val')).bord
erStyle"
)
assert border == "none"
def test_table_group_by_query(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="timestamp",
limit=100,
group_by=["user"],
aggregate="Count",
)
assert "error" not in data
assert len(data["rows"]) == 3
def test_table_avg_no_group_by(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
aggregate="Avg",
)
assert len(data["rows"]) == 1
row = data["rows"][0]
assert row[0] == 4
from dateutil import parser
ts = parser.parse(row[1]).replace(tzinfo=None)
assert ts == parser.parse("2024-01-01 13:00:00")
assert row[2] == 25
def test_table_headers_show_aggregate(page: Any, server_url: str) -> None:
run_query(
page,
server_url,
aggregate="Avg",
)
headers = page.locator("#results th").all_inner_texts()
assert "Hits" in headers
assert "timestamp (avg)" in headers
assert "value (avg)" in headers
def test_format_number_function(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
vals = page.evaluate(
"() => [formatNumber(815210), formatNumber(999.999), formatNumber(0.0004
), formatNumber(0)]"
)
assert vals == ["815.21 K", "999.999", "0.000", "0"]
def test_derived_column_query(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.click("text=Add Derived")
expr = page.query_selector("#derived_list .derived textarea")
assert expr
expr.fill("value * 2")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-03 00:00:00")
page.fill("#limit", "10")
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
data = page.evaluate("window.lastResults")
assert data["rows"][0][-1] == 20I’m continuing to page towards the bottom for the information I need.
root@75b162e381df:/workspace/scubaduck# wc -l tests/test_web.py
879 tests/test_web.pyI need to add a test for timeseries views with derived columns, replicating the failure.
root@75b162e381df:/workspace/scubaduck# ls scubaduck
__init__.py sample.csv server.py staticimport time
from pathlib import Path
import sqlite3
import traceback
import duckdb
from dateutil import parser as dtparser
from flask import Flask, jsonify, request, send_from_directory
@dataclass
class Filter:
column: str
op: str
value: str | int | float | list[str] | None
@dataclass
class QueryParams:
start: str | None = None
end: str | None = None
order_by: str | None = None
order_dir: str = "ASC"
limit: int | None = None
columns: list[str] = field(default_factory=lambda: [])
filters: list[Filter] = field(default_factory=lambda: [])
derived_columns: dict[str, str] = field(default_factory=lambda: {})
graph_type: str = "samples"
group_by: list[str] = field(default_factory=lambda: [])
aggregate: str | None = None
show_hits: bool = False
x_axis: str | None = None
granularity: str = "Auto"
fill: str = "0"
def _load_database(path: Path) -> duckdb.DuckDBPyConnection:
ext = path.suffix.lower()
if ext == ".csv":
con = duckdb.connect()
con.execute(
f"CREATE TABLE events AS SELECT * FROM read_csv_auto('{path.as_posix
()}')"
)
elif ext in {".db", ".sqlite"}:
con = duckdb.connect()
sconn = sqlite3.connect(path)
info = sconn.execute("PRAGMA table_info(events)").fetchall()
col_defs = ", ".join(f"{r[1]} {r[2]}" for r in info)
con.execute(f"CREATE TABLE events ({col_defs})")
placeholders = ",".join("?" for _ in info)
for row in sconn.execute("SELECT * FROM events"):
con.execute(f"INSERT INTO events VALUES ({placeholders})", row)
sconn.close()
else:
con = duckdb.connect(path)
return con
_REL_RE = re.compile(
r"([+-]?\d+(?:\.\d*)?)\s*(hour|hours|day|days|week|weeks|fortnight|fortnight
s)",
re.IGNORECASE,
)
def parse_time(val: str | None) -> str | None:
"""Parse an absolute or relative time string into ``YYYY-MM-DD HH:MM:SS``.""
"
if val is None or val == "":
return None
s = val.strip()
if s.lower() == "now":
dt = datetime.now(timezone.utc)
return dt.replace(microsecond=0).strftime("%Y-%m-%d %H:%M:%S")
m = _REL_RE.fullmatch(s)
if m:
qty = float(m.group(1))
unit = m.group(2).lower()
delta: timedelta
if unit.startswith("hour"):
delta = timedelta(hours=qty)
elif unit.startswith("day"):
delta = timedelta(days=qty)
elif unit.startswith("week"):
delta = timedelta(weeks=qty)
elif unit.startswith("fortnight"):
delta = timedelta(weeks=2 * qty)
else: # pragma: no cover - defensive
raise ValueError(f"Unsupported unit: {unit}")
dt = datetime.now(timezone.utc) + delta
return dt.replace(microsecond=0).strftime("%Y-%m-%d %H:%M:%S")
dt = dtparser.parse(s)
return dt.replace(microsecond=0, tzinfo=None).strftime("%Y-%m-%d %H:%M:%S")
def _granularity_seconds(granularity: str, start: str | None, end: str | None) -
> int:
gran = granularity.lower()
mapping = {
"1 second": 1,
"5 seconds": 5,
"10 seconds": 10,
"30 seconds": 30,
"1 minute": 60,
"4 minutes": 240,
"5 minutes": 300,
"10 minutes": 600,
"15 minutes": 900,
"30 minutes": 1800,
"1 hour": 3600,
"3 hours": 10800,
"6 hours": 21600,
"1 day": 86400,
"1 week": 604800,
"30 days": 2592000,
}
if gran in mapping:
return mapping[gran]
if gran in {"auto", "fine"} and start and end:
try:
s = dtparser.parse(start)
e = dtparser.parse(end)
except Exception:
return 3600
total = max((e - s).total_seconds(), 1)
buckets = 100 if gran == "auto" else 500
return max(int(total // buckets), 1)
return 3600
def build_query(params: QueryParams, column_types: Dict[str, str] | None = None)
-> str:
select_parts: list[str] = []
group_cols = params.group_by[:]
if params.graph_type == "timeseries":
sec = _granularity_seconds(params.granularity, params.start, params.end)
x_axis = params.x_axis or "timestamp"
bucket_expr = (
f"TIMESTAMP 'epoch' + INTERVAL '{sec} second' * "
f"CAST(floor(epoch({x_axis})/{sec}) AS BIGINT)"
)
select_parts.append(f"{bucket_expr} AS bucket")
group_cols = ["bucket"] + group_cols
has_agg = bool(group_cols) or params.aggregate is not None
if has_agg:
select_cols = (
group_cols[1:] if params.graph_type == "timeseries" else group_cols
)
select_parts.extend(select_cols)
agg = (params.aggregate or "avg").lower()
def agg_expr(col: str) -> str:
if agg.startswith("p"):
quant = float(agg[1:]) / 100
return f"quantile({col}, {quant})"
if agg == "count distinct":
return f"count(DISTINCT {col})"
if agg == "avg" and column_types is not None:
ctype = column_types.get(col, "").upper()
if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in ctype:
return (
"TIMESTAMP 'epoch' + INTERVAL '1 second' * "
f"CAST(avg(epoch({col})) AS BIGINT)"
)
return f"{agg}({col})"
for col in params.columns:
if col in group_cols:
continue
select_parts.append(f"{agg_expr(col)} AS {col}")
if params.show_hits:
select_parts.insert(len(group_cols), "count(*) AS Hits")
else:
select_parts.extend(params.columns)
for name, expr in params.derived_columns.items():
select_parts.append(f"{expr} AS {name}")
select_clause = ", ".join(select_parts) if select_parts else "*"
query = f"SELECT {select_clause} FROM events"
where_parts: list[str] = []
if params.start:
where_parts.append(f"timestamp >= '{params.start}'")
if params.end:
where_parts.append(f"timestamp <= '{params.end}'")
for f in params.filters:
op = f.op
if op in {"empty", "!empty"}:
val = "''"
else:
if f.value is None:
continue
if isinstance(f.value, list):
if not f.value:
continue
if op == "=":if op == "=":
vals = " OR ".join(f"{f.column} = '{v}'" for v in f.value)
where_parts.append(f"({vals})")
continue
val = f"'{f.value}'" if isinstance(f.value, str) else str(f.value)
if op == "contains":
where_parts.append(f"{f.column} ILIKE '%' || {val} || '%'")
elif op == "!contains":
where_parts.append(f"{f.column} NOT ILIKE '%' || {val} || '%'")
elif op == "empty":
where_parts.append(f"{f.column} = {val}")
elif op == "!empty":
where_parts.append(f"{f.column} != {val}")
else:
where_parts.append(f"{f.column} {op} {val}")
if where_parts:
query += " WHERE " + " AND ".join(where_parts)
if group_cols:
query += " GROUP BY " + ", ".join(group_cols)
if params.order_by:
query += f" ORDER BY {params.order_by} {params.order_dir}"
elif params.graph_type == "timeseries":
query += " ORDER BY bucket"
if params.limit is not None:
query += f" LIMIT {params.limit}"
return query
def create_app(db_file: str | Path | None = None) -> Flask:
app = Flask(__name__, static_folder="static")
db_path = Path(db_file or Path(__file__).with_name("sample.csv")).resolve()
con = _load_database(db_path)
column_types: Dict[str, str] = {
r[1]: r[2] for r in con.execute("PRAGMA table_info(events)").fetchall()
}
sample_cache: Dict[Tuple[str, str], Tuple[List[str], float]] = {}
CACHE_TTL = 60.0
CACHE_LIMIT = 200
@app.route("/")
def index() -> Any: # pyright: ignore[reportUnusedFunction]
assert app.static_folder is not None
return send_from_directory(app.static_folder, "index.html")
@app.route("/js/<path:filename>")
def js(filename: str) -> Any: # pyright: ignore[reportUnusedFunction]
assert app.static_folder is not None
folder = Path(app.static_folder) / "js"
return send_from_directory(folder, filename)
@app.route("/api/columns")
def columns() -> Any: # pyright: ignore[reportUnusedFunction]
rows = con.execute("PRAGMA table_info(events)").fetchall()
return jsonify([{"name": r[1], "type": r[2]} for r in rows])
def _cache_get(key: Tuple[str, str]) -> List[str] | None:
item = sample_cache.get(key)
if item is None:
return None
vals, ts = item
if time.time() - ts > CACHE_TTL:
del sample_cache[key]
return None
sample_cache[key] = (vals, time.time())
return vals
def _cache_set(key: Tuple[str, str], vals: List[str]) -> None:
sample_cache[key] = (vals, time.time())
if len(sample_cache) > CACHE_LIMIT:
oldest = min(sample_cache.items(), key=lambda kv: kv[1][1])[0]
del sample_cache[oldest]
@app.route("/api/samples")
def sample_values() -> Any: # pyright: ignore[reportUnusedFunction]
column = request.args.get("column")
substr = request.args.get("q", "")
if not column or column not in column_types:
return jsonify([])
ctype = column_types[column].upper()
if "CHAR" not in ctype and "STRING" not in ctype and "VARCHAR" not in ct
ype:
return jsonify([])
key = (column, substr)
cached = _cache_get(key)
if cached is not None:
return jsonify(cached)
rows = con.execute(
f"SELECT DISTINCT {column} FROM events WHERE CAST({column} AS VARCHA
R) ILIKE '%' || ? || '%' LIMIT 20",
[substr],
).fetchall()
values = [r[0] for r in rows]
_cache_set(key, values)
return jsonify(values)
@app.route("/api/query", methods=["POST"])
def query() -> Any: # pyright: ignore[reportUnusedFunction]
payload = request.get_json(force=True)
try:
start = parse_time(payload.get("start"))
end = parse_time(payload.get("end"))
except Exception as exc:
return jsonify({"error": str(exc)}), 400
params = QueryParams(
start=start,
end=end,
order_by=payload.get("order_by"),
order_dir=payload.get("order_dir", "ASC"),
limit=payload.get("limit"),
columns=payload.get("columns", []),
derived_columns=payload.get("derived_columns", {}),
graph_type=payload.get("graph_type", "samples"),
group_by=payload.get("group_by", []),
aggregate=payload.get("aggregate"),
show_hits=payload.get("show_hits", False),
x_axis=payload.get("x_axis"),
granularity=payload.get("granularity", "Auto"),
fill=payload.get("fill", "0"),
)
for f in payload.get("filters", []):
params.filters.append(Filter(f["column"], f["op"], f.get("value")))
if params.graph_type not in {"table", "timeseries"} and (
params.group_by or params.aggregate or params.show_hits
):
return (
jsonify(
{
"error": "group_by, aggregate and show_hits are only val
id for table or timeseries view"
}
),
400,
)
valid_cols = set(column_types.keys())
valid_cols.update(params.derived_columns.keys())
if params.graph_type == "timeseries":
if params.x_axis is None:
for cand in ["time", "timestamp"]:
if cand in valid_cols:
params.x_axis = cand
break
if params.x_axis is None or params.x_axis not in valid_cols:
return jsonify({"error": "Invalid x_axis"}), 400
ctype = column_types.get(params.x_axis, "").upper()
if not any(t in ctype for t in ["TIMESTAMP", "DATE", "TIME"]):
return jsonify({"error": "x_axis must be a time column"}), 400
for col in params.columns:
if col not in valid_cols:
return jsonify({"error": f"Unknown column: {col}"}), 400
for col in params.group_by:
if col not in valid_cols:
return jsonify({"error": f"Unknown column: {col}"}), 400
if params.order_by and params.order_by not in valid_cols:
return jsonify({"error": f"Unknown column: {params.order_by}"}), 400
if params.group_by or params.graph_type == "timeseries":
agg = (params.aggregate or "avg").lower()
if agg.startswith("p") or agg == "sum":
need_numeric = True
allow_time = False
elif agg == "avg" or agg in {"min", "max"}:
need_numeric = False
allow_time = True
else:
need_numeric = False
allow_time = False
if need_numeric or allow_time:
for c in params.columns:
if c in params.group_by or c == params.x_axis:
continue
if c not in column_types:
continue
ctype = column_types.get(c, "").upper()
is_numeric = any(
t in ctype
for t in [
"INT",
"DECIMAL",
"REAL",
"DOUBLE",
"FLOAT",
"NUMERIC",
"HUGEINT",
]
)
is_time = "TIMESTAMP" in ctype or "DATE" in ctype or "TIME"
in ctype
if need_numeric and not is_numeric:
return (
jsonify(
{
"error": f"Aggregate {agg} cannot be applied
to column {c}",
}
),
400,
)
if allow_time and not (is_numeric or is_time):
return (
jsonify(
{root@75b162e381df:/workspace/scubaduck# sed -n '400,800p' scubaduck/server.py
{
"error": f"Aggregate {agg} cannot be applied
to column {c}",
}
),
400,
)
sql = build_query(params, column_types)
try:
rows = con.execute(sql).fetchall()
except Exception as exc:
tb = traceback.format_exc()
print(f"Query failed:\n{sql}\n{tb}")
return (
jsonify({"sql": sql, "error": str(exc), "traceback": tb}),
400,
)
return jsonify({"sql": sql, "rows": rows})
return app
app = create_app()
if __name__ == "__main__":
app.run(debug=True)I'm looking at the timeseries and group_by parts. The design around aliasing is complex, especially for derived columns.
I need to modify how derived columns refer to aggregated aliases using unique names to prevent conflicts.
To prevent conflicts, I'll alias aggregated columns uniquely, then rename them in the outer query.
I'll separate the query into two layers, with derived columns computed in the outer query.
I'll keep aliases consistent and build queries with an inner and outer structure for derived columns.
root@75b162e381df:/workspace/scubaduck# cat scubaduck/sample.csv | head
timestamp,event,value,user
2024-01-01 00:00:00,login,10,alice
2024-01-01 01:00:00,logout,20,bob
2024-01-02 00:00:00,login,30,alice
2024-01-02 03:00:00,login,40,charlieI want to be sure about the test setup, especially the run_query in test_web.
def select_value(page: Any, selector: str, value: str) -> None:
page.evaluate(
"arg => setSelectValue(arg.sel, arg.val)",
{"sel": selector, "val": value},
)
def run_query(
page: Any,
url: str,
*,
start: str | None = None,
end: str | None = None,
order_by: str | None = None,
order_dir: str | None = "ASC",
limit: int | None = None,
group_by: list[str] | None = None,
aggregate: str | None = None,
) -> dict[str, Any]:
page.goto(url)
page.wait_for_selector("#order_by option", state="attached")
page.wait_for_selector("#order_dir", state="attached")
page.wait_for_function("window.lastResults !== undefined")
if start is not None:
page.fill("#start", start)
if end is not None:
page.fill("#end", end)
if order_by is not None:
select_value(page, "#order_by", order_by)
if order_dir is not None and order_dir == "DESC":
page.click("#order_dir")
if limit is not None:
page.fill("#limit", str(limit))
if group_by is not None:
select_value(page, "#graph_type", "table")"g => { groupBy.chips = g; groupBy.renderChips(); }",
group_by,
)
if aggregate is not None:
select_value(page, "#graph_type", "table")
select_value(page, "#aggregate", aggregate)
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
return page.evaluate("window.lastResults")
def test_range_filters(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-02 00:00:00",
end="2024-01-02 04:00:00",
order_by="timestamp",
limit=100,
)
assert len(data["rows"]) == 2
from dateutil import parser
timestamps = [parser.parse(row[0]).replace(tzinfo=None) for row in data["row
s"]]
assert timestamps == [
parser.parse("2024-01-02 00:00:00"),
parser.parse("2024-01-02 03:00:00"),
]
def test_order_by(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="value",
order_dir="DESC",
limit=100,
)
values = [row[2] for row in data["rows"]]
assert values == sorted(values, reverse=True)
def test_limit(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="timestamp",
limit=2,
)
assert len(data["rows"]) == 2
def test_simple_filter(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Add Filter")
filter_el = page.query_selector("#filters .filter:last-child")
assert filter_el
page.evaluate(
"arg => setSelectValue(arg.el.querySelector('.f-col'), arg.val)",
{"el": filter_el, "val": "user"},
)
val_input = filter_el.query_selector(".f-val")
val_input.click()
page.keyboard.type("alice")
page.keyboard.press("Enter")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
data = page.evaluate("window.lastResults")
assert len(data["rows"]) == 2
assert all(row[3] == "alice" for row in data["rows"])
def test_default_filter_and_layout(page: Any, server_url: str) -> None:I'll check out the server code and search for build_query to fix the bug.
r.py
138:def build_query(params: QueryParams, column_types: Dict[str, str] | None = N
one) -> str:
406: sql = build_query(params, column_types)I'll review the code around 138 and confirm if I can replicate the bug.
root@75b162e381df:/workspace/scubaduck# grep -n "derived" -n tests/test_server.p
y
425:def test_derived_column_basic() -> None:
433: "derived_columns": {"val2": "value * 2"},It looks like the only existing test is test_derived_column_basic. I'll add my test nearby, checking for duplicates around line 420.
data = rv.get_json()
assert rv.status_code == 400
assert "Aggregate" in data["error"]
def test_derived_column_basic() -> None:
app = server.app
client = app.test_client()
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"limit": 10,
"columns": ["timestamp"],
"derived_columns": {"val2": "value * 2"},
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert data["rows"][0][1] == 20I’ll check for any additional tests at the file’s bottom.
root@75b162e381df:/workspace/scubaduck# sed -n '460,520p' tests/test_server.pyI'm adding the new test for derived columns and checking the expected value logic.
I'll assert that derived column equals aggregated value times 2 and verify numeric types.
root@75b162e381df:/workspace/scubaduck# git status --short(scubaduck) root@75b162e381df:/workspace/scubaduck# python - <<'EOF'
> import json
> from scubaduck.server import create_app
> app = create_app()
> client = app.test_client()
>
> payload = {
> "start": "2024-01-01 00:00:00",
> "end": "2024-01-03 00:00:00",
> "graph_type": "timeseries",
> "limit": 7,
> "columns": ["value"],
> "derived_columns": {"derived_1": "value * 2"},
> "granularity": "1 hour",
> "x_axis": "timestamp"
> }
> rv = client.post('/api/query', data=json.dumps(payload), content_type='applica
tion/json')
> print(rv.status_code)
> print(rv.get_json())
> EOFQuery failed:
SELECT TIMESTAMP 'epoch' + INTERVAL '3600 second' * CAST(floor(epoch(timestamp)/
3600) AS BIGINT) AS bucket, avg(value) AS value, value * 2 AS derived_1 FROM eve
nts WHERE timestamp >= '2024-01-01 00:00:00' AND timestamp <= '2024-01-03 00:00:
00' GROUP BY bucket ORDER BY bucket LIMIT 7
Traceback (most recent call last):
File "/workspace/scubaduck/scubaduck/server.py", line 408, in query
rows = con.execute(sql).fetchall()
^^^^^^^^^^^^^^^^
duckdb.duckdb.BinderException: Binder Error: column "value" must appear in the G
ROUP BY clause or must be part of an aggregate function.
Either add it to the GROUP BY list, or use "ANY_VALUE(value)" if the exact value
of "value" is not important.
LINE 1: ...(timestamp)/3600) AS BIGINT) AS bucket, avg(value) AS value, value *
2 AS derived_1 FROM events WHERE timestamp >= '2024...
^
400
{'error': 'Binder Error: column "value" must appear in the GROUP BY clause or mu
st be part of an aggregate function.\nEither add it to the GROUP BY list, or use
"ANY_VALUE(value)" if the exact value of "value" is not important.\n\nLINE 1: .
..(timestamp)/3600) AS BIGINT) AS bucket, avg(value) AS value, value * 2 AS deri
ved_1 FROM events WHERE timestamp >= \'2024...\n
^', 'sql': "SELECT TIMESTAMP 'epoch' + I
NTERVAL '3600 second' * CAST(floor(epoch(timestamp)/3600) AS BIGINT) AS bucket,
avg(value) AS value, value * 2 AS derived_1 FROM events WHERE timestamp >= '2024
-01-01 00:00:00' AND timestamp <= '2024-01-03 00:00:00' GROUP BY bucket ORDER BY
bucket LIMIT 7", 'traceback': 'Traceback (most recent call last):\n File "/wor
kspace/scubaduck/scubaduck/server.py", line 408, in query\n rows = con.execut
e(sql).fetchall()\n ^^^^^^^^^^^^^^^^\nduckdb.duckdb.BinderException: B
inder Error: column "value" must appear in the GROUP BY clause or must be part o
f an aggregate function.\nEither add it to the GROUP BY list, or use "ANY_VALUE(
value)" if the exact value of "value" is not important.\n\nLINE 1: ...(timestamp
)/3600) AS BIGINT) AS bucket, avg(value) AS value, value * 2 AS derived_1 FROM e
vents WHERE timestamp >= \'2024...\n
^\n'}
(scubaduck) root@75b162e381df:/workspace/scubaduck#To address the bug, I'll adjust build_query to properly handle outer and inner queries.
To avoid recursion, I'll manually build the inner query with adjusted parameters.
I'll map columns from params to generate the correct select statement for the query.
I need to ensure proper prefixing for derived columns and avoid ambiguity in the outer query.
(scubaduck) root@75b162e381df:/workspace/scubaduck# head -n 10 scubaduck/server.
py
from __future__ import annotations
from dataclasses import dataclass, field
from typing import Any, Dict, List, Tuple
import re
from datetime import datetime, timedelta, timezone
import time
from pathlib import Path
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll add dataclasses.replace to the import statement and review server.py for updates.
(scubaduck) root@75b162e381df:/workspace/scubaduck# grep -n "replace" -n scubadu
ck/server.py
80: return dt.replace(microsecond=0).strftime("%Y-%m-%d %H:%M:%S")
98: return dt.replace(microsecond=0).strftime("%Y-%m-%d %H:%M:%S")
101: return dt.replace(microsecond=0, tzinfo=None).strftime("%Y-%m-%d %H:%M:%
S")
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll import dataclasses and implement the patch now.
(scubaduck) root@75b162e381df:/workspace/scubaduck# apply_patch<<'PATCH'
> *** Begin Patch
> *** Update File: scubaduck/server.py
> @@
> -from dataclasses import dataclass, field
> +from dataclasses import dataclass, field, replace
> *** End Patch
> PATCH
Success. Updated the following files:
M scubaduck/server.py
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll start by making the necessary modifications in build_query and opening the patch.
(scubaduck) root@75b162e381df:/workspace/scubaduck# sed -n '140,230p' scubaduck/
server.py
group_cols = params.group_by[:]
if params.graph_type == "timeseries":
sec = _granularity_seconds(params.granularity, params.start, params.end)
x_axis = params.x_axis or "timestamp"
bucket_expr = (
f"TIMESTAMP 'epoch' + INTERVAL '{sec} second' * "
f"CAST(floor(epoch({x_axis})/{sec}) AS BIGINT)"
)
select_parts.append(f"{bucket_expr} AS bucket")
group_cols = ["bucket"] + group_cols
has_agg = bool(group_cols) or params.aggregate is not None
if has_agg:
select_cols = (
group_cols[1:] if params.graph_type == "timeseries" else group_cols
)
select_parts.extend(select_cols)
agg = (params.aggregate or "avg").lower()
def agg_expr(col: str) -> str:
if agg.startswith("p"):
quant = float(agg[1:]) / 100
return f"quantile({col}, {quant})"
if agg == "count distinct":
return f"count(DISTINCT {col})"
if agg == "avg" and column_types is not None:
ctype = column_types.get(col, "").upper()
if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in ctype:
return (
"TIMESTAMP 'epoch' + INTERVAL '1 second' * "
f"CAST(avg(epoch({col})) AS BIGINT)"
)
return f"{agg}({col})"
for col in params.columns:
if col in group_cols:
continue
select_parts.append(f"{agg_expr(col)} AS {col}")
if params.show_hits:
select_parts.insert(len(group_cols), "count(*) AS Hits")
else:
select_parts.extend(params.columns)
for name, expr in params.derived_columns.items():
select_parts.append(f"{expr} AS {name}")
select_clause = ", ".join(select_parts) if select_parts else "*"
query = f"SELECT {select_clause} FROM events"
where_parts: list[str] = []
if params.start:
where_parts.append(f"timestamp >= '{params.start}'")
if params.end:
where_parts.append(f"timestamp <= '{params.end}'")
for f in params.filters:
op = f.op
if op in {"empty", "!empty"}:
val = "''"
else:
if f.value is None:
continue
if isinstance(f.value, list):
if not f.value:
continue
if op == "=":
vals = " OR ".join(f"{f.column} = '{v}'" for v in f.value)
where_parts.append(f"({vals})")
continue
val = f"'{f.value}'" if isinstance(f.value, str) else str(f.value)
if op == "contains":
where_parts.append(f"{f.column} ILIKE '%' || {val} || '%'")
elif op == "!contains":
where_parts.append(f"{f.column} NOT ILIKE '%' || {val} || '%'")
elif op == "empty":
where_parts.append(f"{f.column} = {val}")
elif op == "!empty":
where_parts.append(f"{f.column} != {val}")
else:
where_parts.append(f"{f.column} {op} {val}")
if where_parts:
query += " WHERE " + " AND ".join(where_parts)
if group_cols:
query += " GROUP BY " + ", ".join(group_cols)
if params.order_by:
query += f" ORDER BY {params.order_by} {params.order_dir}"
elif params.graph_type == "timeseries":
query += " ORDER BY bucket"
if params.limit is not None:
query += f" LIMIT {params.limit}"
return query
def create_app(db_file: str | Path | None = None) -> Flask:
app = Flask(__name__, static_folder="static")
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll adjust logic to handle derived_columns with has_agg. I'll modify the query building process.
I’ll avoid code duplication by calling build_query recursively for the inner query construction.
I need to ensure that inner_sql includes bucket alias, then apply the patch.
> *** Begin Patch
> *** Update File: scubaduck/server.py
> @@
> has_agg = bool(group_cols) or params.aggregate is not None
> if has_agg:
> @@
> - if params.show_hits:
> - select_parts.insert(len(group_cols), "count(*) AS Hits")
> - else:
> - select_parts.extend(params.columns)
> - for name, expr in params.derived_columns.items():
> - select_parts.append(f"{expr} AS {name}")
> - select_clause = ", ".join(select_parts) if select_parts else "*"
> - query = f"SELECT {select_clause} FROM events"
> + if params.show_hits:
> + select_parts.insert(len(group_cols), "count(*) AS Hits")
> + else:
> + select_parts.extend(params.columns)
> +
> + if has_agg and params.derived_columns:
> + inner_params = replace(
> + params,
> + derived_columns={},
> + order_by=None,
> + limit=None,
> + )
> + inner_sql = build_query(inner_params, column_types)
> + outer_select = ["t.*"] + [f"{expr} AS {name}" for name, expr in param
s.derived_columns.items()]
> + query = f"SELECT {', '.join(outer_select)} FROM ({inner_sql}) t"
> + if params.order_by:
> + query += f" ORDER BY {params.order_by} {params.order_dir}"
> + elif params.graph_type == "timeseries":
> + query += " ORDER BY bucket"
> + if params.limit is not None:
> + query += f" LIMIT {params.limit}"
> + return query
> +
> + for name, expr in params.derived_columns.items():
> + select_parts.append(f"{expr} AS {name}")
> + select_clause = ", ".join(select_parts) if select_parts else "*"
> + query = f"SELECT {select_clause} FROM events"
> *** End Patch
> PATCH
Success. Updated the following files:
M scubaduck/server.py
(scubaduck) root@75b162e381df:/workspace/scubaduck#Looks like the function might be missing a proper return or closing—I'll open the file.
server.py
def build_query(params: QueryParams, column_types: Dict[str, str] | None = None)
-> str:
select_parts: list[str] = []
group_cols = params.group_by[:]
if params.graph_type == "timeseries":
sec = _granularity_seconds(params.granularity, params.start, params.end)
x_axis = params.x_axis or "timestamp"
bucket_expr = (
f"TIMESTAMP 'epoch' + INTERVAL '{sec} second' * "
f"CAST(floor(epoch({x_axis})/{sec}) AS BIGINT)"
)
select_parts.append(f"{bucket_expr} AS bucket")
group_cols = ["bucket"] + group_cols
has_agg = bool(group_cols) or params.aggregate is not None
if has_agg:
select_cols = (
group_cols[1:] if params.graph_type == "timeseries" else group_cols
)
select_parts.extend(select_cols)
agg = (params.aggregate or "avg").lower()
def agg_expr(col: str) -> str:
if agg.startswith("p"):
quant = float(agg[1:]) / 100
return f"quantile({col}, {quant})"
if agg == "count distinct":
return f"count(DISTINCT {col})"
if agg == "avg" and column_types is not None:
ctype = column_types.get(col, "").upper()
if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in ctype:
return (
"TIMESTAMP 'epoch' + INTERVAL '1 second' * "
f"CAST(avg(epoch({col})) AS BIGINT)"
)
return f"{agg}({col})"
for col in params.columns:
if col in group_cols:
continue
select_parts.append(f"{agg_expr(col)} AS {col}")
if params.show_hits:
select_parts.insert(len(group_cols), "count(*) AS Hits")
else:
select_parts.extend(params.columns)
if has_agg and params.derived_columns:
inner_params = replace(
params,
derived_columns={},
order_by=None,
limit=None,
)
inner_sql = build_query(inner_params, column_types)
outer_select = ["t.*"] + [f"{expr} AS {name}" for name, expr in params.d
erived_columns.items()]
query = f"SELECT {', '.join(outer_select)} FROM ({inner_sql}) t"
if params.order_by:
query += f" ORDER BY {params.order_by} {params.order_dir}"
elif params.graph_type == "timeseries":
query += " ORDER BY bucket"
if params.limit is not None:
query += f" LIMIT {params.limit}"
return query
for name, expr in params.derived_columns.items():
select_parts.append(f"{expr} AS {name}")
select_clause = ", ".join(select_parts) if select_parts else "*"
query = f"SELECT {select_clause} FROM events"
where_parts: list[str] = []
if params.start:
where_parts.append(f"timestamp >= '{params.start}'")
if params.end:
where_parts.append(f"timestamp <= '{params.end}'")
for f in params.filters:
op = f.op
if op in {"empty", "!empty"}:
val = "''"
else:
if f.value is None:
continue
if isinstance(f.value, list):
if not f.value:
continue
if op == "=":
vals = " OR ".join(f"{f.column} = '{v}'" for v in f.value)
where_parts.append(f"({vals})")
continue
val = f"'{f.value}'" if isinstance(f.value, str) else str(f.value)
if op == "contains":
where_parts.append(f"{f.column} ILIKE '%' || {val} || '%'")
elif op == "!contains":
where_parts.append(f"{f.column} NOT ILIKE '%' || {val} || '%'")
elif op == "empty":
where_parts.append(f"{f.column} = {val}")server.py
where_parts.append(f"{f.column} = {val}")
elif op == "!empty":
where_parts.append(f"{f.column} != {val}")
else:
where_parts.append(f"{f.column} {op} {val}")
if where_parts:
query += " WHERE " + " AND ".join(where_parts)
if group_cols:
query += " GROUP BY " + ", ".join(group_cols)
if params.order_by:
query += f" ORDER BY {params.order_by} {params.order_dir}"
elif params.graph_type == "timeseries":
query += " ORDER BY bucket"
if params.limit is not None:
query += f" LIMIT {params.limit}"
return query
def create_app(db_file: str | Path | None = None) -> Flask:
app = Flask(__name__, static_folder="static")
db_path = Path(db_file or Path(__file__).with_name("sample.csv")).resolve()
con = _load_database(db_path)
column_types: Dict[str, str] = {
r[1]: r[2] for r in con.execute("PRAGMA table_info(events)").fetchall()
}
sample_cache: Dict[Tuple[str, str], Tuple[List[str], float]] = {}
CACHE_TTL = 60.0
CACHE_LIMIT = 200
@app.route("/")
def index() -> Any: # pyright: ignore[reportUnusedFunction]
assert app.static_folder is not None
return send_from_directory(app.static_folder, "index.html")
@app.route("/js/<path:filename>")
def js(filename: str) -> Any: # pyright: ignore[reportUnusedFunction]
assert app.static_folder is not None
folder = Path(app.static_folder) / "js"
return send_from_directory(folder, filename)
@app.route("/api/columns")
def columns() -> Any: # pyright: ignore[reportUnusedFunction]
rows = con.execute("PRAGMA table_info(events)").fetchall()
return jsonify([{"name": r[1], "type": r[2]} for r in rows])
def _cache_get(key: Tuple[str, str]) -> List[str] | None:
item = sample_cache.get(key)
if item is None:
return None
vals, ts = item
if time.time() - ts > CACHE_TTL:
del sample_cache[key]
return None
sample_cache[key] = (vals, time.time())
return vals
def _cache_set(key: Tuple[str, str], vals: List[str]) -> None:
sample_cache[key] = (vals, time.time())
if len(sample_cache) > CACHE_LIMIT:
oldest = min(sample_cache.items(), key=lambda kv: kv[1][1])[0]
del sample_cache[oldest]
@app.route("/api/samples")
def sample_values() -> Any: # pyright: ignore[reportUnusedFunction]
column = request.args.get("column")
substr = request.args.get("q", "")
if not column or column not in column_types:
return jsonify([])
ctype = column_types[column].upper()
if "CHAR" not in ctype and "STRING" not in ctype and "VARCHAR" not in ct
ype:
return jsonify([])
key = (column, substr)
cached = _cache_get(key)
if cached is not None:
return jsonify(cached)
rows = con.execute(
f"SELECT DISTINCT {column} FROM events WHERE CAST({column} AS VARCHA
R) ILIKE '%' || ? || '%' LIMIT 20",
[substr],
).fetchall()
values = [r[0] for r in rows]
_cache_set(key, values)
return jsonify(values)
@app.route("/api/query", methods=["POST"])
def query() -> Any: # pyright: ignore[reportUnusedFunction]
payload = request.get_json(force=True)
try:
start = parse_time(payload.get("start"))
end = parse_time(payload.get("end"))
except Exception as exc:
return jsonify({"error": str(exc)}), 400
params = QueryParams(
start=start,
end=end,
order_by=payload.get("order_by"),
order_dir=payload.get("order_dir", "ASC"),
limit=payload.get("limit"),
columns=payload.get("columns", []),
derived_columns=payload.get("derived_columns", {}),
graph_type=payload.get("graph_type", "samples"),
group_by=payload.get("group_by", []),
aggregate=payload.get("aggregate"),
show_hits=payload.get("show_hits", False),
x_axis=payload.get("x_axis"),
granularity=payload.get("granularity", "Auto"),
fill=payload.get("fill", "0"),
)
for f in payload.get("filters", []):
params.filters.append(Filter(f["column"], f["op"], f.get("value")))
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll check for duplicates in variables or loops, and run ruff format to clean up.
(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff format scubaduck/server
.py > /tmp/format.log && tail -n 20 /tmp/format.log
1 file reformatted
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll try running ruff and pyright to verify everything.
(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff check scubaduck > /tmp/
ruff.log && tail -n 20 /tmp/ruff.log
All checks passed!(scubaduck) root@75b162e381df:/workspace/scubaduck# pyright scubaduck > /tmp/pyr
ight.log && tail -n 20 /tmp/pyright.log
0 errors, 0 warnings, 0 informations
(scubaduck) root@75b162e381df:/workspace/scubaduck#Time to add a test for the derived column timeseries in test_server.py.
(scubaduck) root@75b162e381df:/workspace/scubaduck# sed -n '440,460p' tests/test
_server.py
assert rv.status_code == 200
assert data["rows"][0][1] == 20
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll inspect lines 430-460 to wrap this up.
(scubaduck) root@75b162e381df:/workspace/scubaduck# sed -n '430,452p' tests/test
_server.py
"end": "2024-01-03 00:00:00",
"limit": 10,
"columns": ["timestamp"],
"derived_columns": {"val2": "value * 2"},
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert data["rows"][0][1] == 20
(scubaduck) root@75b162e381df:/workspace/scubaduck#I’m thinking of adding a new test after this step.
> *** Begin Patch
> *** Update File: tests/test_server.py
> @@
> def test_derived_column_basic() -> None:
> @@
> assert rv.status_code == 200
> assert data["rows"][0][1] == 20
> +
> +
> +def test_timeseries_derived_column() -> None:
> + app = server.app
> + client = app.test_client()
> + payload = {
> + "start": "2024-01-01 00:00:00",
> + "end": "2024-01-03 00:00:00",
> + "graph_type": "timeseries",
> + "granularity": "1 hour",
> + "limit": 7,
> + "columns": ["value"],
> + "derived_columns": {"derived_1": "value * 2"},
> + }
> + rv = client.post(
> + "/api/query", data=json.dumps(payload), content_type="application/jso
n"
> + )
> + data = rv.get_json()
> + assert rv.status_code == 200
> + rows = data["rows"]
> + assert all(r[2] == r[1] * 2 for r in rows)
> *** End Patch
> PATCH
Success. Updated the following files:
M tests/test_server.py(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff format tests/test_serve
r.py > /tmp/format.log && tail -n 20 /tmp/format.log
1 file left unchanged(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff check tests/test_server
.py > /tmp/ruff.log && tail -n 20 /tmp/ruff.log
All checks passed!
(scubaduck) root@75b162e381df:/workspace/scubaduck#I’ll run pyright now to check for any typing issues in the code.
(scubaduck) root@75b162e381df:/workspace/scubaduck# pyright tests/test_server.py
> /tmp/pyright.log && tail -n 20 /tmp/pyright.log
0 errors, 0 warnings, 0 informations
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll run ruff check, format, and pyright to make sure there are no new issues.
(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff format > /tmp/format.lo
g && tail -n 20 /tmp/format.log
6 files left unchanged(scubaduck) root@75b162e381df:/workspace/scubaduck# ruff check > /tmp/ruff.log &
& tail -n 20 /tmp/ruff.log
All checks passed!(scubaduck) root@75b162e381df:/workspace/scubaduck# pyright > /tmp/pyright.log &
& tail -n 20 /tmp/pyright.log0 errors, 0 warnings, 0 informations
(scubaduck) root@75b162e381df:/workspace/scubaduck#Now, it's time to run the tests and check everything works correctly!
(scubaduck) root@75b162e381df:/workspace/scubaduck# pytest -q > /tmp/pytest.log
&& tail -n 20 /tmp/pytest.logbringing up nodes...
bringing up nodes...
................................................................ [100%]
64 passed in 9.01s
(scubaduck) root@75b162e381df:/workspace/scubaduck#All tests passed, now checking the git status.
(scubaduck) root@75b162e381df:/workspace/scubaduck# git status --short
M scubaduck/server.py
M tests/test_server.py
(scubaduck) root@75b162e381df:/workspace/scubaduck#I’m ready to commit the changes now.
(scubaduck) root@75b162e381df:/workspace/scubaduck# git add scubaduck/server.py
tests/test_server.py(scubaduck) root@75b162e381df:/workspace/scubaduck# git commit -m "fix(server):
support derived columns with aggregation" && git status --short
[work 84b031b] fix(server): support derived columns with aggregation
2 files changed, 43 insertions(+), 1 deletion(-)
(scubaduck) root@75b162e381df:/workspace/scubaduck#I’m reviewing the commit status now.
(scubaduck) root@75b162e381df:/workspace/scubaduck# git status --short
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll gather line references from server and test changes for the PR.
sed -n '150,215p'
150 has_agg = bool(group_cols) or params.aggregate is not None
151 if has_agg:
152 select_cols = (
153 group_cols[1:] if params.graph_type == "timeseries" else gro
up_cols
154 )
155 select_parts.extend(select_cols)
156 agg = (params.aggregate or "avg").lower()
157
158 def agg_expr(col: str) -> str:
159 if agg.startswith("p"):
160 quant = float(agg[1:]) / 100
161 return f"quantile({col}, {quant})"
162 if agg == "count distinct":
163 return f"count(DISTINCT {col})"
164 if agg == "avg" and column_types is not None:
165 ctype = column_types.get(col, "").upper()
166 if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in
ctype:
167 return (
168 "TIMESTAMP 'epoch' + INTERVAL '1 second' * "
169 f"CAST(avg(epoch({col})) AS BIGINT)"
170 )
171 return f"{agg}({col})"
172
173 for col in params.columns:
174 if col in group_cols:
175 continue
176 select_parts.append(f"{agg_expr(col)} AS {col}")
177 if params.show_hits:
178 select_parts.insert(len(group_cols), "count(*) AS Hits")
179 else:
180 select_parts.extend(params.columns)
181
182 if has_agg and params.derived_columns:
183 inner_params = replace(
184 params,
185 derived_columns={},
186 order_by=None,
187 limit=None,
188 )
189 inner_sql = build_query(inner_params, column_types)
190 outer_select = ["t.*"] + [
191 f"{expr} AS {name}" for name, expr in params.derived_columns
.items()
192 ]
193 query = f"SELECT {', '.join(outer_select)} FROM ({inner_sql}) t"
194 if params.order_by:
195 query += f" ORDER BY {params.order_by} {params.order_dir}"
196 elif params.graph_type == "timeseries":
197 query += " ORDER BY bucket"
198 if params.limit is not None:
199 query += f" LIMIT {params.limit}"
200 return query
201
202 for name, expr in params.derived_columns.items():
203 select_parts.append(f"{expr} AS {name}")
204 select_clause = ", ".join(select_parts) if select_parts else "*"
205 query = f"SELECT {select_clause} FROM events"
206 where_parts: list[str] = []
207 if params.start:
208 where_parts.append(f"timestamp >= '{params.start}'")
209 if params.end:
210 where_parts.append(f"timestamp <= '{params.end}'")
211 for f in params.filters:
212 op = f.op
213 if op in {"empty", "!empty"}:
214 val = "''"
215 else:
(scubaduck) root@75b162e381df:/workspace/scubaduck#I’ll focus on lines 150-205 and capture the test lines.
(scubaduck) root@75b162e381df:/workspace/scubaduck# nl -ba tests/test_server.py
| sed -n '435,472p'
435 }
436 rv = client.post(
437 "/api/query", data=json.dumps(payload), content_type="applicatio
n/json"
438 )
439 data = rv.get_json()
440 assert rv.status_code == 200
441 assert data["rows"][0][1] == 20
442
443
444 def test_timeseries_derived_column() -> None:
445 app = server.app
446 client = app.test_client()
447 payload = {
448 "start": "2024-01-01 00:00:00",
449 "end": "2024-01-03 00:00:00",
450 "graph_type": "timeseries",
451 "granularity": "1 hour",
452 "limit": 7,
453 "columns": ["value"],
454 "derived_columns": {"derived_1": "value * 2"},
455 }
456 rv = client.post(
457 "/api/query", data=json.dumps(payload), content_type="applicatio
n/json"
458 )
459 data = rv.get_json()
460 assert rv.status_code == 200
461 rows = data["rows"]
462 assert all(r[2] == r[1] * 2 for r in rows)
(scubaduck) root@75b162e381df:/workspace/scubaduck#I'll summarize the changes and add the relevant user prompt to the PR message.