Task ID: task_e_682fd1846810832395c995534735ae96
Configuring language runtimes...
+ rm -- /tmp/DBE0O9-setup_script.sh
+ source ./codex_setup.sh
++ uv sync --frozen
Using CPython 3.12.3 interpreter at: /usr/bin/python3.12
Creating virtual environment at: .venv
Building scubaduck @ file:///workspace/scubaduck
Downloading duckdb (19.3MiB)
Downloading pyright (5.3MiB)
Downloading ruff (11.0MiB)
Downloading playwright (43.1MiB)
Downloading ruff
Built scubaduck @ file:///workspace/scubaduck
Downloading duckdb
Downloading playwright
Downloading pyright
Prepared 33 packages in 1.40s
Installed 33 packages in 76ms
+ 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/DBE0O9-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/v22.16.0/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/v22.16.0/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
++ python -c 'import os; import duckdb; con = duckdb.connect(); con.execute(f"SET http_proxy = '\''{os.getenv("HTTP_PROXY")}'\''"); con.execute("INSTALL '\''sqlite'\'';")'
++ 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% 11.1s167.7 MiB [] 0% 56.6s167.7 MiB [] 0% 62.2s167.7 MiB [] 0% 46.2s167.7 MiB [] 0% 36.8s167.7 MiB [] 0% 28.8s167.7 MiB [] 0% 22.0s167.7 MiB [] 0% 16.8s167.7 MiB [] 1% 12.0s167.7 MiB [] 1% 8.6s167.7 MiB [] 2% 6.1s167.7 MiB [] 3% 4.7s167.7 MiB [] 5% 3.9s167.7 MiB [] 5% 3.6s167.7 MiB [] 7% 3.1s167.7 MiB [] 8% 2.9s167.7 MiB [] 9% 2.6s167.7 MiB [] 10% 2.6s167.7 MiB [] 11% 2.4s167.7 MiB [] 13% 2.2s167.7 MiB [] 14% 2.1s167.7 MiB [] 15% 2.0s167.7 MiB [] 16% 2.0s167.7 MiB [] 17% 1.9s167.7 MiB [] 18% 1.9s167.7 MiB [] 19% 1.8s167.7 MiB [] 20% 1.8s167.7 MiB [] 21% 1.7s167.7 MiB [] 23% 1.7s167.7 MiB [] 23% 1.6s167.7 MiB [] 25% 1.6s167.7 MiB [] 26% 1.5s167.7 MiB [] 27% 1.5s167.7 MiB [] 29% 1.4s167.7 MiB [] 30% 1.4s167.7 MiB [] 31% 1.3s167.7 MiB [] 33% 1.3s167.7 MiB [] 34% 1.3s167.7 MiB [] 35% 1.3s167.7 MiB [] 36% 1.2s167.7 MiB [] 37% 1.2s167.7 MiB [] 38% 1.2s167.7 MiB [] 40% 1.1s167.7 MiB [] 41% 1.1s167.7 MiB [] 43% 1.1s167.7 MiB [] 45% 1.0s167.7 MiB [] 46% 1.0s167.7 MiB [] 48% 0.9s167.7 MiB [] 50% 0.9s167.7 MiB [] 51% 0.9s167.7 MiB [] 52% 0.8s167.7 MiB [] 53% 0.8s167.7 MiB [] 54% 0.8s167.7 MiB [] 56% 0.8s167.7 MiB [] 57% 0.8s167.7 MiB [] 59% 0.7s167.7 MiB [] 60% 0.7s167.7 MiB [] 61% 0.7s167.7 MiB [] 62% 0.7s167.7 MiB [] 64% 0.6s167.7 MiB [] 65% 0.6s167.7 MiB [] 67% 0.6s167.7 MiB [] 68% 0.5s167.7 MiB [] 69% 0.5s167.7 MiB [] 71% 0.5s167.7 MiB [] 72% 0.5s167.7 MiB [] 74% 0.4s167.7 MiB [] 75% 0.4s167.7 MiB [] 76% 0.4s167.7 MiB [] 77% 0.4s167.7 MiB [] 78% 0.4s167.7 MiB [] 79% 0.4s167.7 MiB [] 80% 0.3s167.7 MiB [] 81% 0.3s167.7 MiB [] 82% 0.3s167.7 MiB [] 84% 0.3s167.7 MiB [] 85% 0.2s167.7 MiB [] 87% 0.2s167.7 MiB [] 89% 0.2s167.7 MiB [] 91% 0.1s167.7 MiB [] 93% 0.1s167.7 MiB [] 94% 0.1s167.7 MiB [] 95% 0.1s167.7 MiB [] 96% 0.1s167.7 MiB [] 97% 0.0s167.7 MiB [] 98% 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% 0.7s2.3 MiB [] 5% 0.7s2.3 MiB [] 11% 0.5s2.3 MiB [] 16% 0.4s2.3 MiB [] 27% 0.2s2.3 MiB [] 44% 0.1s2.3 MiB [] 68% 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% 31.2s101.4 MiB [] 0% 35.2s101.4 MiB [] 0% 24.4s101.4 MiB [] 0% 19.8s101.4 MiB [] 0% 17.6s101.4 MiB [] 1% 10.1s101.4 MiB [] 1% 7.6s101.4 MiB [] 2% 5.0s101.4 MiB [] 4% 3.5s101.4 MiB [] 6% 2.6s101.4 MiB [] 8% 2.1s101.4 MiB [] 9% 2.0s101.4 MiB [] 12% 1.6s101.4 MiB [] 14% 1.4s101.4 MiB [] 16% 1.3s101.4 MiB [] 18% 1.2s101.4 MiB [] 20% 1.2s101.4 MiB [] 23% 1.0s101.4 MiB [] 24% 1.0s101.4 MiB [] 26% 0.9s101.4 MiB [] 28% 0.9s101.4 MiB [] 30% 0.9s101.4 MiB [] 32% 0.8s101.4 MiB [] 34% 0.8s101.4 MiB [] 36% 0.7s101.4 MiB [] 39% 0.7s101.4 MiB [] 40% 0.7s101.4 MiB [] 42% 0.6s101.4 MiB [] 45% 0.6s101.4 MiB [] 46% 0.6s101.4 MiB [] 48% 0.5s101.4 MiB [] 50% 0.5s101.4 MiB [] 53% 0.5s101.4 MiB [] 54% 0.5s101.4 MiB [] 56% 0.4s101.4 MiB [] 59% 0.4s101.4 MiB [] 60% 0.4s101.4 MiB [] 63% 0.4s101.4 MiB [] 65% 0.3s101.4 MiB [] 67% 0.3s101.4 MiB [] 68% 0.3s101.4 MiB [] 71% 0.3s101.4 MiB [] 73% 0.3s101.4 MiB [] 75% 0.2s101.4 MiB [] 77% 0.2s101.4 MiB [] 78% 0.2s101.4 MiB [] 81% 0.2s101.4 MiB [] 84% 0.2s101.4 MiB [] 85% 0.1s101.4 MiB [] 87% 0.1s101.4 MiB [] 89% 0.1s101.4 MiB [] 90% 0.1s101.4 MiB [] 91% 0.1s101.4 MiB [] 92% 0.1s101.4 MiB [] 93% 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'bash: .venv/bin/activate: No such file or directory
root@8c33e558aa85:/workspace# ls
scubaduckroot@8c33e558aa85:/workspace# cd scubaduck
root@8c33e558aa85:/workspace/scubaduck# ls
AGENTS.md codex_setup.sh scubaduck tests
README.md pyproject.toml stubs uv.lockroot@8c33e558aa85:/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.pyI'll open the README to better understand the project. Let's dive in!
root@8c33e558aa85:/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.
## Running the server
Activate the virtual environment and run the Flask development server:
```bash
flask --app scubaduck.server run --debug
```
By default the server loads `sample.csv`. Set the `SCUBADUCK_DB` environment
variable to point at a different database file (CSV, SQLite or DuckDB) if you
want to use another dataset. The special value `TEST` starts the server with a
small in-memory SQLite dataset used by the automated tests. If the file does
not exist, the server will raise a `FileNotFoundError` during startup.I'm going to check out the tests now.
root@8c33e558aa85:/workspace/scubaduck# ls tests
conftest.py test_server_errors.py test_web_columns.py
test_multi_table_web.py test_server_time.py test_web_graph.py
test_server.py test_server_timeseries.py test_web_table.py
test_server_basic.py test_web_basics.py test_web_timeseries.py
test_server_db_types.py test_web_chips.py web_utils.pyI’ll look into the Scubaduck repo to find any server-related tests.
root@8c33e558aa85:/workspace/scubaduck# ls scubaduck
__init__.py sample.csv server.py staticI’m diving into server.py now to take a closer look. Let’s explore!
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,200p' scubaduck/server.py
from __future__ import annotations
from dataclasses import dataclass, field, replace
from typing import Any, Dict, List, Tuple, cast
import re
from datetime import datetime, timedelta, timezone
import time
from pathlib import Path
import os
import traceback
import math
import duckdb
from dateutil import parser as dtparser
from flask import Flask, jsonify, request, send_from_directory
def _quote(ident: str) -> str:
"""Return identifier quoted for SQL."""
return f'"{ident.replace('"', '""')}"'
@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"
table: str = "events"
time_column: str | None = "timestamp"
time_unit: str = "s"
def _load_database(path: Path) -> duckdb.DuckDBPyConnection:
if not path.exists():
raise FileNotFoundError(path)
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()
con.execute("LOAD sqlite")
con.execute(f"ATTACH '{path.as_posix()}' AS db (TYPE SQLITE)")
tables = [
r[0]
for r in con.execute(
"SELECT name FROM sqlite_master WHERE type='table'"
).fetchall()
]
for t in tables:
con.execute(f'CREATE VIEW "{t}" AS SELECT * FROM db."{t}"')
else:
con = duckdb.connect(path)
return con
def _create_test_database() -> duckdb.DuckDBPyConnection:
"""Return a DuckDB connection with a small multi-table dataset."""
con = duckdb.connect()
con.execute(
"CREATE TABLE events (id INTEGER PRIMARY KEY, ts INTEGER, val REAL, name
TEXT, flag BOOLEAN)"
)
con.execute("INSERT INTO events VALUES (1, 1704067200, 1.5, 'alice', 1)")
con.execute("INSERT INTO events VALUES (2, 1704070800, 2.0, 'bob', 0)")
con.execute('CREATE TABLE extra (ts INTEGER, "desc" TEXT, num INTEGER)')
con.execute("INSERT INTO extra VALUES (1704067200, 'x', 1)")
con.execute("INSERT INTO extra VALUES (1704070800, 'y', 2)")
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 _time_expr(col: str, column_types: Dict[str, str] | None, unit: str) -> str:
"""Return SQL expression for column interpreted as timestamp."""
qcol = _quote(col)
if column_types is None:
return qcol
ctype = column_types.get(col, "").upper()
if not any(t in ctype for t in ["TIMESTAMP", "DATE", "TIME"]):
if any(
t in ctype
for t in [
"INT",
"DECIMAL",
"REAL",
"DOUBLE",
"FLOAT",
"NUMERIC",
"HUGEINT",
]
):
if unit == "ns":
expr = f"CAST({qcol} AS BIGINT)"
return f"make_timestamp_ns({expr})"
multiplier = {
"s": 1_000_000,
"ms": 1_000,
"us": 1,
}.get(unit, 1_000_000)
expr = (
f"CAST({qcol} * {multiplier} AS BIGINT)"
if multiplier != 1
else f"CAST({qcol} AS BIGINT)"
)
return f"make_timestamp({expr})"
return qcolI'm scrolling further to gather the remaining details I need.
root@8c33e558aa85:/workspace/scubaduck# sed -n '200,400p' scubaduck/server.py
return qcol
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 params.time_column
if x_axis is None:
raise ValueError("x_axis required for timeseries")
xexpr = _time_expr(x_axis, column_types, params.time_unit)
if params.start:
bucket_expr = (
f"TIMESTAMP '{params.start}' + INTERVAL '{sec} second' * "
f"CAST(floor((epoch({xexpr}) - epoch(TIMESTAMP '{params.start}')
)/{sec}) AS BIGINT)"
)
else:
bucket_expr = (
f"TIMESTAMP 'epoch' + INTERVAL '{sec} second' * "
f"CAST(floor(epoch({xexpr})/{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(_quote(c) for c in select_cols)
agg = (params.aggregate or "count").lower()
def agg_expr(col: str) -> str:
expr = _quote(col)
ctype = column_types.get(col, "").upper() if column_types else ""
if "BOOL" in ctype:
expr = f"CAST({_quote(col)} AS BIGINT)"
if agg.startswith("p"):
quant = float(agg[1:]) / 100
return f"quantile({expr}, {quant})"
if agg == "count distinct":
return f"count(DISTINCT {expr})"
if agg == "avg" and column_types is not None:
if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in ctype:
return (
"TIMESTAMP 'epoch' + INTERVAL '1 second' * "
f"CAST(avg(epoch({_quote(col)})) AS BIGINT)"
)
return f"{agg}({expr})"
if agg == "count":
select_parts.append("count(*) AS Count")
else:
for col in params.columns:
if col in group_cols:
continue
select_parts.append(f"{agg_expr(col)} AS {_quote(col)}")
if params.show_hits:
select_parts.insert(len(group_cols), "count(*) AS Hits")
else:
select_parts.extend(_quote(c) for c in 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.derived_columns.items()
]
indented_inner = "\n".join(" " + line for line in inner_sql.splitline
s())
lines = [
f"SELECT {', '.join(outer_select)}",
"FROM (",
indented_inner,
") t",
]
if params.order_by:
lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_dir}
")
elif params.graph_type == "timeseries":
lines.append("ORDER BY bucket")
if params.limit is not None:
lines.append(f"LIMIT {params.limit}")
return "\n".join(lines)
for name, expr in params.derived_columns.items():
select_parts.append(f"{expr} AS {name}")
select_clause = ", ".join(select_parts) if select_parts else "*"
lines = [f"SELECT {select_clause}", f'FROM "{params.table}"']
where_parts: list[str] = []
if params.time_column:
time_expr = _time_expr(params.time_column, column_types, params.time_uni
t)
else:
time_expr = None
if time_expr and params.start:
where_parts.append(f"{time_expr} >= '{params.start}'")
if time_expr and params.end:
where_parts.append(f"{time_expr} <= '{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 == "=":
qcol = _quote(f.column)
vals = " OR ".join(f"{qcol} = '{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)
qcol = _quote(f.column)
if op == "contains":
where_parts.append(f"{qcol} ILIKE '%' || {val} || '%'")
elif op == "!contains":
where_parts.append(f"{qcol} NOT ILIKE '%' || {val} || '%'")
elif op == "empty":
where_parts.append(f"{qcol} = {val}")
elif op == "!empty":
where_parts.append(f"{qcol} != {val}")
else:
where_parts.append(f"{qcol} {op} {val}")
if where_parts:
lines.append("WHERE " + " AND ".join(where_parts))
if group_cols:
lines.append("GROUP BY " + ", ".join(_quote(c) for c in group_cols))
if params.order_by:
lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_dir}")
elif params.graph_type == "timeseries":
lines.append("ORDER BY bucket")
if params.limit is not None:
lines.append(f"LIMIT {params.limit}")
return "\n".join(lines)
def create_app(db_file: str | Path | None = None) -> Flask:
app = Flask(__name__, static_folder="static")
if db_file is None:
env_db = os.environ.get("SCUBADUCK_DB")
if env_db:
db_file = env_db
if isinstance(db_file, str) and db_file.upper() == "TEST":
con = _create_test_database()
else:
db_path = Path(db_file or Path(__file__).with_name("sample.csv")).resolv
e()
con = _load_database(db_path)
tables = [r[0] for r in con.execute("SHOW TABLES").fetchall()]
if not tables:
raise ValueError("No tables found in database")
default_table = tables[0]
columns_cache: Dict[str, Dict[str, str]] = {}
def get_columns(table: str) -> Dict[str, str]:
if table not in columns_cache:
rows = con.execute(f'PRAGMA table_info("{table}")').fetchall()
if not rows:
raise ValueError(f"Unknown table: {table}")
columns_cache[table] = {r[1]: r[2] for r in rows}
return columns_cache[table]
sample_cache: Dict[Tuple[str, 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/tables")
def tables_endpoint() -> Any: # pyright: ignore[reportUnusedFunction]
return jsonify(tables)
@app.route("/api/columns")
def columns() -> Any: # pyright: ignore[reportUnusedFunction]
table = request.args.get("table", default_table)
rows = con.execute(f'PRAGMA table_info("{table}")').fetchall()
return jsonify([{"name": r[1], "type": r[2]} for r in rows])
def _cache_get(key: Tuple[str, 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())root@8c33e558aa85:/workspace/scubaduck# sed -n '400,800p' scubaduck/server.py
sample_cache[key] = (vals, time.time())
return vals
def _cache_set(key: Tuple[str, 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]
table = request.args.get("table", default_table)
column = request.args.get("column")
substr = request.args.get("q", "")
column_types = get_columns(table)
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 = (table, column, substr)
cached = _cache_get(key)
if cached is not None:
return jsonify(cached)
qcol = _quote(column)
rows = con.execute(
f"SELECT DISTINCT {qcol} FROM \"{table}\" WHERE CAST({qcol} AS VARCH
AR) 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"),
table=payload.get("table", default_table),
time_column=payload.get("time_column", "timestamp"),
time_unit=payload.get("time_unit", "s"),
)
for f in payload.get("filters", []):
params.filters.append(Filter(f["column"], f["op"], f.get("value")))
if params.table not in tables:
return jsonify({"error": "Invalid table"}), 400
column_types = get_columns(params.table)
if params.time_column and params.time_column not in column_types:
return jsonify({"error": "Invalid time_column"}), 400
if params.time_unit not in {"s", "ms", "us", "ns"}:
return jsonify({"error": "Invalid time_unit"}), 400
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:
params.x_axis = params.time_column
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()
is_time = any(t in ctype for t in ["TIMESTAMP", "DATE", "TIME"])
is_numeric = any(
t in ctype
for t in [
"INT",
"DECIMAL",
"REAL",
"DOUBLE",
"FLOAT",
"NUMERIC",
"HUGEINT",
]
)
if not (is_time or is_numeric):
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":
...
)
if allow_time and not (is_numeric or is_time):
return (
jsonify(
{
"error": f"Aggregate {agg} cannot be applied
to column {c}",
}
),
400,
)
if (params.start is None or params.end is None) and (
params.x_axis or params.time_column
):
axis = params.x_axis or params.time_column
assert axis is not None
row = cast(
tuple[datetime | None, datetime | None],
con.execute(
f'SELECT min({_quote(axis)}), max({_quote(axis)}) FROM "{par
ams.table}"'
).fetchall()[0],
)
mn, mx = row
divisor = {
"s": 1,
"ms": 1000,
"us": 1_000_000,
"ns": 1_000_000_000,
}.get(params.time_unit, 1)
if isinstance(mn, (int, float)):
try:
mn = datetime.fromtimestamp(int(mn) / divisor, tz=timezone.u
tc)
except Exception:
return (
jsonify(
{
"error": (
f"Invalid time value {mn} for column {axis}"
f" with time_unit {params.time_unit}"
)
}
),
400,
)
if isinstance(mx, (int, float)):
try:
mx = datetime.fromtimestamp(int(mx) / divisor, tz=timezone.u
tc)
except Exception:
return (
jsonify(
{
"error": (
f"Invalid time value {mx} for column {axis}"
f" with time_unit {params.time_unit}"
)
}
),
400,
)
if params.start is None and mn is not None:
params.start = (
mn.strftime("%Y-%m-%d %H:%M:%S") if not isinstance(mn, str)
else mn
)
if params.end is None and mx is not None:
params.end = (
mx.strftime("%Y-%m-%d %H:%M:%S") if not isinstance(mx, str)
else mx
)
bucket_size: int | None = None
if params.graph_type == "timeseries":
bucket_size = _granularity_seconds(
params.granularity,
params.start if isinstance(params.start, str) else None,
params.end if isinstance(params.end, str) else None,
)
if (
params.limit is not None
and params.start is not None
and params.end is not None
):
try:
start_dt = dtparser.parse(params.start)
end_dt = dtparser.parse(params.end)
buckets = math.ceil(
(end_dt - start_dt).total_seconds() / bucket_size
)
if buckets > 1:
params.limit *= buckets
except Exception:
pass
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,
)
result: Dict[str, Any] = {"sql": sql, "rows": rows}
if params.start is not None:
result["start"] = str(params.start)
if params.end is not None:
result["end"] = str(params.end)
if bucket_size is not None:
result["bucket_size"] = bucket_size
return jsonify(result)
return app
app = create_app()
if __name__ == "__main__":
app.run(debug=True)Next, I'll take a look at static JS to check if the logic is implemented there.
root@8c33e558aa85:/workspace/scubaduck# ls scubaduck/static
index.html jsroot@8c33e558aa85:/workspace/scubaduck# ls scubaduck/static/js
chip_input.js table_view.js timeseries_chart.js
sidebar.js time_column.js view_settings.jsI’ll start by taking a look at the sidebar.js file to see what's inside.
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,200p' scubaduck/static/js/side
bar.js
// Sidebar resizing logic extracted from index.html
const sidebar = document.getElementById('sidebar');
const sidebarResizer = document.getElementById('sidebar-resizer');
let sidebarWidth = parseInt(localStorage.getItem('sidebarWidth') || 450, 10);
sidebar.style.width = sidebarWidth + 'px';
let sidebarResize = false;
function startSidebarDrag(e) {
e.preventDefault();
sidebarResize = true;
document.addEventListener('mousemove', onSidebarDrag);
document.addEventListener('mouseup', stopSidebarDrag);
}
function onSidebarDrag(e) {
if (!sidebarResize) return;
sidebarWidth = Math.max(200, e.clientX - sidebar.getBoundingClientRect().left)
;
sidebar.style.width = sidebarWidth + 'px';
}
function stopSidebarDrag() {
document.removeEventListener('mousemove', onSidebarDrag);
document.removeEventListener('mouseup', stopSidebarDrag);
sidebarResize = false;
localStorage.setItem('sidebarWidth', sidebarWidth);
}
sidebarResizer.addEventListener('mousedown', startSidebarDrag);Let's take a look at the view_settings.js file.
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,200p' scubaduck/static/js/view
_settings.js
// Logic for View Settings, Columns, and URL handling extracted from index.html
const allColumns = [];
const baseColumns = [];
const columnTypes = {};
const stringColumns = [];
const baseStringColumns = [];
const integerColumns = [];
const baseIntegerColumns = [];
const timeColumns = [];
const baseTimeColumns = [];
const timeColumnOptions = [];
const baseTimeColumnOptions = [];
const derivedColumns = [];
let selectedColumns = [];
let displayType = 'samples';
let groupBy = {chips: [], addChip: () => {}, renderChips: () => {}};
let defaultTimeColumn = '';
const limitInput = document.getElementById('limit');
const limitValues = {
samples: parseInt(limitInput.value, 10),
table: parseInt(limitInput.value, 10),
timeseries: 7
};
const columnValues = {
samples: [],
table: [],
timeseries: []
};
limitInput.addEventListener('input', () => {
limitValues[displayType] = parseInt(limitInput.value, 10);
limitInput.dataset.setByUser = '1';
});
function initDropdown(select) {
// Avoid creating duplicate wrappers if this dropdown was already initialised.
if (select.dataset.dropdownInit) {
const disp = select.parentElement?.querySelector('.dropdown-display');
if (disp) {
const opt = select.options[select.selectedIndex];
disp.textContent = opt ? opt.textContent : '';
}
return;
}
select.dataset.dropdownInit = '1';
const wrapper = document.createElement('div');
wrapper.className = 'dropdown';
if (select.classList.contains('f-col')) {
wrapper.classList.add('f-col');
}
select.parentNode.insertBefore(wrapper, select);
wrapper.appendChild(select);
select.style.display = 'none';
const disp = document.createElement('div');
disp.className = 'dropdown-display';
function updateDisplay() {
const opt = select.options[select.selectedIndex];
disp.textContent = opt ? opt.textContent : '';
}
updateDisplay();
wrapper.appendChild(disp);
const menu = document.createElement('div');
menu.className = 'dropdown-menu';
const search = document.createElement('input');
search.placeholder = 'Search';
menu.appendChild(search);
const list = document.createElement('div');
menu.appendChild(list);
wrapper.appendChild(menu);
function close() {
menu.style.display = 'none';
}
function open() {
renderOptions();
menu.style.display = 'block';
search.focus();
}
disp.addEventListener('click', () => {
if (menu.style.display === 'block') {
close();
} else {
open();
}
});
document.addEventListener('click', e => {
if (!wrapper.contains(e.target)) {
close();
}
});
function renderOptions() {
const q = search.value.toLowerCase();
list.innerHTML = '';
Array.from(select.options).forEach(o => {
if (!o.textContent.toLowerCase().includes(q)) return;
const div = document.createElement('div');
div.className = 'option';
if (q) {
const text = o.textContent;
const idx = text.toLowerCase().indexOf(q);
if (idx !== -1) {
div.innerHTML =
text.slice(0, idx) +
'<u>' +
text.slice(idx, idx + q.length) +
'</u>' +
text.slice(idx + q.length);
} else {
div.textContent = text;
}
} else {
div.textContent = o.textContent;
}
if (o.value === select.value) div.classList.add('selected');
div.addEventListener('mousedown', evt => {
evt.preventDefault();
select.value = o.value;
select.dispatchEvent(new Event('change'));
updateDisplay();
close();
});
list.appendChild(div);
});
}
search.addEventListener('input', renderOptions);
select.addEventListener('change', updateDisplay);
}
let orderDir = 'ASC';
const orderDirBtn = document.getElementById('order_dir');
const graphTypeSel = document.getElementById('graph_type');
function updateOrderDirButton() {
orderDirBtn.textContent = orderDir + (orderDir === 'ASC' ? ' \u25B2' : ' \u25B
C');
}
function updateDisplayTypeUI() {
const prevType = displayType;
updateSelectedColumns(prevType);
const newType = graphTypeSel.value;
const showTable = newType === 'table';
const showTS = newType === 'timeseries';
document.getElementById('group_by_field').style.display = showTable || showTS
? 'flex' : 'none';
document.getElementById('aggregate_field').style.display = showTable || showTS
? 'flex' : 'none';
document.getElementById('show_hits_field').style.display = showTable ? 'flex'
: 'none';
document.getElementById('x_axis_field').style.display = showTS ? 'flex' : 'non
e';
document.getElementById('granularity_field').style.display = showTS ? 'flex' :
'none';
document.getElementById('fill_field').style.display = showTS ? 'flex' : 'none'
;
document.querySelectorAll('#column_groups .col-group').forEach(g => {
if (g.querySelector('.col-group-header').textContent.startsWith('Strings'))
{
g.style.display = showTable || showTS ? 'none' : '';
}
});
limitValues[prevType] = parseInt(limitInput.value, 10);
if (showTS && limitValues.timeseries === undefined) {
limitValues.timeseries = 7;
}
limitInput.value = limitValues[newType];
document.querySelectorAll('#column_groups input').forEach(cb => {
cb.checked = columnValues[newType].includes(cb.value);
});
if (showTS) {
document.querySelectorAll('#column_groups input').forEach(cb => {
if (isTimeColumn(cb.value) || isStringColumn(cb.value)) {
cb.checked = false;
}
});
document.getElementById('order_by').value = '';
}
updateSelectedColumns(newType);
displayType = newType;
}
function updateTimeFieldVisibility() {
const show = document.getElementById('time_column').value !== '';
document.getElementById('start').closest('.field').style.display = show
? 'flex'
: 'none';
document.getElementById('end').closest('.field').style.display = show
? 'flex'
: 'none';
}
orderDirBtn.addEventListener('click', () => {
orderDir = orderDir === 'ASC' ? 'DESC' : 'ASC';
updateOrderDirButton();
});
updateOrderDirButton();
graphTypeSel.addEventListener('change', updateDisplayTypeUI);
document.getElementById('time_column').addEventListener('change', updateTimeFiel
dVisibility);
updateTimeFieldVisibility();
function loadColumns(table) {
return fetch('/api/columns?table=' + encodeURIComponent(table)).then(r => r.js
on()).then(cols => {
const orderSelect = document.getElementById('order_by');
const xAxisSelect = document.getElementById('x_axis');
const groupsEl = document.getElementById('column_groups');
const timeColumnSelect = document.getElementById('time_column');root@8c33e558aa85:/workspace/scubaduck# sed -n '200,400p' scubaduck/static/js/vi
ew_settings.js
const timeColumnSelect = document.getElementById('time_column');
orderSelect.innerHTML = '';
xAxisSelect.innerHTML = '';
const defOpt = document.createElement('option');
defOpt.value = '';
defOpt.textContent = '(default)';
xAxisSelect.appendChild(defOpt);
timeColumnSelect.innerHTML = '';
const noneOpt = document.createElement('option');
noneOpt.value = '';
noneOpt.textContent = '(none)';
timeColumnSelect.appendChild(noneOpt);
groupsEl.innerHTML = '';
allColumns.length = 0;
stringColumns.length = 0;
integerColumns.length = 0;
timeColumns.length = 0;
timeColumnOptions.length = 0;
baseColumns.length = 0;
baseStringColumns.length = 0;
baseIntegerColumns.length = 0;
baseTimeColumns.length = 0;
baseTimeColumnOptions.length = 0;
for (const k in columnTypes) delete columnTypes[k];
const groups = {
time: {name: 'Time', cols: [], ul: null},
integer: {name: 'Integers', cols: [], ul: null},
string: {name: 'Strings', cols: [], ul: null},
};
cols.forEach(c => {
const t = c.type.toUpperCase();
columnTypes[c.name] = c.type;
allColumns.push(c.name);
baseColumns.push(c.name);
let g = 'string';
const isNumeric = t.includes('INT') || t.includes('DECIMAL') || t.includes
('NUMERIC') || t.includes('REAL') || t.includes('DOUBLE') || t.includes('FLOAT')
|| t.includes('HUGEINT');
const isTimeType = t.includes('TIMESTAMP') || t.includes('DATE') || t.incl
udes('TIME');
if (isNumeric || isTimeType) {
timeColumnOptions.push(c.name);
baseTimeColumnOptions.push(c.name);
}
if (isTimeType) {
g = 'time';
timeColumns.push(c.name);
baseTimeColumns.push(c.name);
} else if (isNumeric) {
g = 'integer';
}
if (g === 'string') {
stringColumns.push(c.name);
baseStringColumns.push(c.name);
} else if (g === 'integer') {
integerColumns.push(c.name);
baseIntegerColumns.push(c.name);
}
groups[g].cols.push(c.name);
if (g !== 'string') {
const o = document.createElement('option');
o.value = c.name;
o.textContent = c.name;
orderSelect.appendChild(o);
}
});
timeColumns.forEach(name => {
const o = document.createElement('option');
o.value = name;
o.textContent = name;
xAxisSelect.appendChild(o);
});
timeColumnOptions.forEach(name => {
const o = document.createElement('option');
o.value = name;
o.textContent = name;
timeColumnSelect.appendChild(o);
});
xAxisSelect.value = '';
defaultTimeColumn = guessTimeColumn(cols) || '';
updateTimeFieldVisibility();
Object.keys(groups).forEach(key => {
const g = groups[key];
const div = document.createElement('div');
div.className = 'col-group';
const header = document.createElement('div');
header.className = 'col-group-header';
header.appendChild(document.createTextNode(g.name + ': '));
const links = document.createElement('span');
links.className = 'links';
const allBtn = document.createElement('a');
allBtn.href = '#';
allBtn.textContent = 'All';
const noneBtn = document.createElement('a');
noneBtn.href = '#';
noneBtn.textContent = 'None';
links.appendChild(allBtn);
links.appendChild(noneBtn);
header.appendChild(links);
div.appendChild(header);
const ul = document.createElement('ul');
g.ul = ul;
g.cols.forEach(name => {
const li = document.createElement('li');
const label = document.createElement('label');
const cb = document.createElement('input');
cb.type = 'checkbox';
cb.value = name;
cb.checked = true;
cb.addEventListener('change', updateSelectedColumns);
label.appendChild(cb);
label.appendChild(document.createTextNode(' ' + name));
li.appendChild(label);
ul.appendChild(li);
});
allBtn.addEventListener('click', e => {
e.preventDefault();
ul.querySelectorAll('input').forEach(cb => (cb.checked = true));
updateSelectedColumns();
});
noneBtn.addEventListener('click', e => {
e.preventDefault();
ul.querySelectorAll('input').forEach(cb => (cb.checked = false));
updateSelectedColumns();
});
div.appendChild(ul);
groupsEl.appendChild(div);
});
document.getElementById('columns_all').addEventListener('click', e => {
e.preventDefault();
groupsEl.querySelectorAll('input').forEach(cb => (cb.checked = true));
updateSelectedColumns();
});
document.getElementById('columns_none').addEventListener('click', e => {
e.preventDefault();
groupsEl.querySelectorAll('input').forEach(cb => (cb.checked = false));
updateSelectedColumns();
});
updateSelectedColumns();
columnValues.samples = allColumns.slice();
columnValues.table = [];
columnValues.timeseries = [];
groupBy = document.getElementById('group_by').closest('.field');
initChipInput(groupBy, typed =>
allColumns.filter(c => c.toLowerCase().includes(typed.toLowerCase()))
);
initDropdown(orderSelect);
initDropdown(document.getElementById('aggregate'));
});
}
let columnsInitialized = false;
fetch('/api/tables').then(r => r.json()).then(tables => {
const tableSel = document.getElementById('table');
tables.forEach(t => {
const o = document.createElement('option');
o.value = t;
o.textContent = t;
tableSel.appendChild(o);
});
initDropdown(tableSel);
const measure = document.createElement('span');
measure.style.visibility = 'hidden';
measure.style.position = 'absolute';
document.body.appendChild(measure);
let maxWidth = 0;
tables.forEach(t => {
measure.textContent = t;
const w = measure.getBoundingClientRect().width;
if (w > maxWidth) maxWidth = w;
});
measure.remove();
const disp = tableSel.parentElement.querySelector('.dropdown-display');
if (disp) disp.style.minWidth = maxWidth + 30 + 'px';
const table = parseSearch().table || tables[0];
tableSel.value = table;
tableSel.dispatchEvent(new Event('change'));
loadColumns(table).then(() => {
updateDisplayTypeUI();
addFilter();
initFromUrl();
columnsInitialized = true;
});
tableSel.addEventListener('change', () => {
loadColumns(tableSel.value).then(() => {
if (columnsInitialized) {
// keep the newly selected table when updating from the URL
const params = parseSearch();
params.table = tableSel.value;
applyParams(params);
}
});
});
});
document.querySelectorAll('#tabs .tab').forEach(btn => {
btn.addEventListener('click', () => {
document.querySelectorAll('#tabs .tab').forEach(t => t.classList.remove('act
ive'));
document.querySelectorAll('.tab-content').forEach(c => c.classList.remove('a
ctive'));
btn.classList.add('active');
document.getElementById(btn.dataset.tab).classList.add('active');
});
});I'll check out view_settings.js next to understand query building and related logic.
ew_settings.js
document.querySelectorAll('.rel-btn').forEach(btn => {
btn.addEventListener('click', () => {
const dd = document.getElementById(btn.dataset.target);
const show = dd.style.display === 'none' || dd.style.display === '';
document.querySelectorAll('.rel-dropdown').forEach(d => (d.style.display = '
none'));
dd.style.display = show ? 'block' : 'none';
});
});
document.querySelectorAll('.rel-dropdown div').forEach(opt => {
opt.addEventListener('click', () => {
const box = opt.closest('.rel-box');
const input = box.querySelector('input');
input.value = opt.dataset.value || opt.textContent;
opt.parentElement.style.display = 'none';
});
});
document.addEventListener('click', e => {
document.querySelectorAll('.rel-dropdown').forEach(dd => {
if (!dd.parentElement.contains(e.target)) dd.style.display = 'none';
});
});
function updateColumnsTabCount() {
const baseCount = document.querySelectorAll('#column_groups input:checked').le
ngth;
const derivedCount = document.querySelectorAll('#derived_list .derived .d-use:
checked').length;
const btn = document.getElementById('columns_tab');
if (btn) btn.textContent = `Columns (${baseCount + derivedCount})`;
}
function updateSelectedColumns(type = graphTypeSel.value) {
const base = allColumns.filter(name => {
const cb = document.querySelector(`#column_groups input[value="${name}"]`);
if (!cb || !cb.checked) return false;
if (type === 'table' && isStringColumn(name)) return false;
return true;
});
if (type === 'table' || type === 'timeseries') {
selectedColumns = groupBy.chips.slice();
if (document.getElementById('show_hits').checked) selectedColumns.push('Hits
');
base.forEach(c => {
if (!selectedColumns.includes(c)) selectedColumns.push(c);
});
derivedColumns.forEach(dc => {
if (dc.include && !selectedColumns.includes(dc.name)) selectedColumns.push
(dc.name);
});
} else {
selectedColumns = base.slice();
derivedColumns.forEach(dc => {
if (dc.include) selectedColumns.push(dc.name);
});
}
columnValues[type] = selectedColumns.slice();
updateColumnsTabCount();
}
function isStringColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
return t.includes('CHAR') || t.includes('STRING') || t.includes('VARCHAR');
}
function isIntegerColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
return t.includes('INT');
}
function isTimeColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
if (t.includes('TIMESTAMP') || t.includes('DATE') || t.includes('TIME')) retur
n true;
const sel = document.getElementById('time_column').value;
const xsel = document.getElementById('x_axis').value;
if (name === sel || name === xsel) return true;
return false;
}
function formatNumber(val) {
if (typeof val !== 'number') val = Number(val);
if (Number.isNaN(val)) return '';
if (val === 0) return '0';
const abs = Math.abs(val);
if (abs > 999.999) {
const units = [
{n: 1e12, s: 'T'},
{n: 1e9, s: 'B'},
{n: 1e6, s: 'M'},
{n: 1e3, s: 'K'},
];
for (const u of units) {
if (abs >= u.n) {
return (val / u.n).toFixed(2) + ' ' + u.s;
}
}
}
if (abs < 0.0005) return '0.000';
if (Number.isInteger(val)) return val.toString();
return val.toFixed(3);
}
function addFilter() {
const container = document.createElement('div');
container.className = 'filter';
container.innerHTML = `
<div class="filter-row">
<select class="f-col"></select>
<select class="f-op"></select>
<button type="button" class="remove" onclick="this.closest('.filter').remo
ve()">✖</button>
</div>
<div class="chip-box">
<div class="chip-input">
<input class="f-val" type="text">
<button type="button" class="chip-copy">⎘</button>
</div>
<div class="chip-dropdown"></div>
</div>
...
graph_type: graphTypeSel.value,
filters: Array.from(document.querySelectorAll('#filters .filter')).map(f =>
{
const chips = f.chips || [];
const op = f.querySelector('.f-op').value;
let value = null;
if (op !== 'empty' && op !== '!empty') {
value = chips.length === 0 ? null : (chips.length === 1 ? chips[0] : chi
ps);
}
const colSel = f.querySelector('.f-col select') || f.querySelector('.f-col
');
return {column: colSel.value, op, value};
}),
derived_columns: Array.from(document.querySelectorAll('#derived_list .derive
d')).map(d => ({
type: d.querySelector('.d-type').value,
name: d.querySelector('.d-name').value,
expr: d.querySelector('.d-expr').value,
include: d.querySelector('.d-use').checked,
}))
};
if (graphTypeSel.value === 'table' || graphTypeSel.value === 'timeseries') {
payload.group_by = groupBy.chips || [];
payload.aggregate = document.getElementById('aggregate').value;
payload.show_hits = document.getElementById('show_hits').checked;
}
if (graphTypeSel.value === 'timeseries') {
const xval = document.getElementById('x_axis').value;
if (xval) payload.x_axis = xval;
payload.granularity = document.getElementById('granularity').value;
payload.fill = document.getElementById('fill').value;
}
return payload;
}
function paramsToSearch(params) {
const sp = new URLSearchParams();
if (params.table) sp.set('table', params.table);
if (params.time_column) sp.set('time_column', params.time_column);
if (params.time_unit) sp.set('time_unit', params.time_unit);
if (params.start) sp.set('start', params.start);
if (params.end) sp.set('end', params.end);
if (params.order_by) sp.set('order_by', params.order_by);
if (params.order_dir) sp.set('order_dir', params.order_dir);
if (params.limit !== null && params.limit !== undefined) sp.set('limit', param
s.limit);
if (params.samples_columns && params.samples_columns.length) sp.set('samples_c
olumns', params.samples_columns.join(','));
if (params.table_columns && params.table_columns.length) sp.set('table_columns
', params.table_columns.join(','));
if (params.timeseries_columns && params.timeseries_columns.length) sp.set('tim
eseries_columns', params.timeseries_columns.join(','));
if (params.filters && params.filters.length) sp.set('filters', JSON.stringify(
params.filters));
if (params.derived_columns && params.derived_columns.length) sp.set('derived_c
olumns', JSON.stringify(params.derived_columns));
if (params.graph_type) sp.set('graph_type', params.graph_type);
if (params.graph_type === 'table' || params.graph_type === 'timeseries') {
if (params.group_by && params.group_by.length) sp.set('group_by', params.gro
up_by.join(','));
if (params.aggregate) sp.set('aggregate', params.aggregate);
if (params.show_hits) sp.set('show_hits', '1');
}
if (params.graph_type === 'timeseries') {
if (params.x_axis) sp.set('x_axis', params.x_axis);
if (params.granularity) sp.set('granularity', params.granularity);
if (params.fill) sp.set('fill', params.fill);
}
const qs = sp.toString();
return qs ? '?' + qs : '';
}
function applyParams(params) {
if (params.table) document.getElementById('table').value = params.table;
document.getElementById('time_column').value = params.time_column || defaultTi
meColumn;
updateTimeFieldVisibility();
if (params.time_unit) document.getElementById('time_unit').value = params.time
_unit;
document.getElementById('start').value = params.start || '';
document.getElementById('end').value = params.end || '';
if (params.order_by) {
document.getElementById('order_by').value = params.order_by;
}
orderDir = params.order_dir || 'ASC';
updateOrderDirButton();
if (params.limit !== undefined && params.limit !== null) {
document.getElementById('limit').value = params.limit;
limitValues[params.graph_type || 'samples'] = params.limit;
limitInput.dataset.setByUser = '1';
}
graphTypeSel.value = params.graph_type || 'samples';
updateDisplayTypeUI();
limitInput.value = limitValues[graphTypeSel.value];
if (params.x_axis) {
document.getElementById('x_axis').value = params.x_axis;
} else {
document.getElementById('x_axis').value = '';
}
if (params.granularity) document.getElementById('granularity').value = params.
granularity;
if (params.fill) document.getElementById('fill').value = params.fill;
if (params.group_by) {
groupBy.chips.splice(0, groupBy.chips.length, ...params.group_by);
groupBy.renderChips();
}
if (params.aggregate) document.getElementById('aggregate').value = params.aggr
egate;
document.getElementById('show_hits').checked = params.show_hits ?? true;
if (params.samples_columns) columnValues.samples = params.samples_columns;
if (params.table_columns) columnValues.table = params.table_columns;
if (params.timeseries_columns) columnValues.timeseries = params.timeseries_col
umns;
document.querySelectorAll('#column_groups input').forEach(cb => {
cb.checked = columnValues[graphTypeSel.value].includes(cb.value);
});
updateSelectedColumns(graphTypeSel.value);
const dlist = document.getElementById('derived_list');
dlist.innerHTML = '';
derivedColumns.splice(0, derivedColumns.length);
if (params.derived_columns && params.derived_columns.length) {
params.derived_columns.forEach(dc => addDerived(dc));
}root@8c33e558aa85:/workspace/scubaduck# sed -n '800,1200p' scubaduck/static/js/v
iew_settings.js
}
refreshDerivedColumns();
const list = document.getElementById('filter_list');
list.innerHTML = '';
if (params.filters && params.filters.length) {
params.filters.forEach(f => {
addFilter();
const el = list.lastElementChild;
const colSel = el.querySelector('.f-col select') || el.querySelector('.f-c
ol');
colSel.value = f.column;
colSel.dispatchEvent(new Event('change'));
el.querySelector('.f-op').value = f.op;
el.querySelector('.f-op').dispatchEvent(new Event('change'));
if (f.value !== null && f.op !== 'empty' && f.op !== '!empty') {
const values = Array.isArray(f.value) ? f.value : [f.value];
values.forEach(v => el.addChip(v));
el.renderChips();
}
});
} else {
addFilter();
}
}
function parseSearch() {
const sp = new URLSearchParams(window.location.search);
const params = {};
if (sp.has('table')) params.table = sp.get('table');
if (sp.has('time_column')) params.time_column = sp.get('time_column');
if (sp.has('time_unit')) params.time_unit = sp.get('time_unit');
if (sp.has('start')) params.start = sp.get('start');
if (sp.has('end')) params.end = sp.get('end');
if (sp.has('order_by')) params.order_by = sp.get('order_by');
if (sp.has('order_dir')) params.order_dir = sp.get('order_dir');
if (sp.has('limit')) params.limit = parseInt(sp.get('limit'), 10);
if (sp.has('samples_columns')) params.samples_columns = sp.get('samples_column
s').split(',').filter(c => c);
if (sp.has('table_columns')) params.table_columns = sp.get('table_columns').sp
lit(',').filter(c => c);
if (sp.has('timeseries_columns')) params.timeseries_columns = sp.get('timeseri
es_columns').split(',').filter(c => c);
if (sp.has('filters')) {
try { params.filters = JSON.parse(sp.get('filters')); } catch(e) { params.fi
lters = []; }
}
if (sp.has('graph_type')) params.graph_type = sp.get('graph_type');
if (sp.has('group_by')) params.group_by = sp.get('group_by').split(',').filter
(c => c);
if (sp.has('aggregate')) params.aggregate = sp.get('aggregate');
if (sp.has('show_hits')) params.show_hits = sp.get('show_hits') === '1';
if (sp.has('x_axis')) params.x_axis = sp.get('x_axis');
if (sp.has('granularity')) params.granularity = sp.get('granularity');
if (sp.has('fill')) params.fill = sp.get('fill');
if (sp.has('derived_columns')) {
try { params.derived_columns = JSON.parse(sp.get('derived_columns')); } catc
h(e) { params.derived_columns = []; }
}
return params;
}
function initFromUrl() {
const params = parseSearch();
history.replaceState(params, '', paramsToSearch(params));
applyParams(params);
dive(false);
}
window.addEventListener('popstate', e => {
const params = e.state || parseSearch();
applyParams(params);
dive(false);
});
function setSelectValue(selector, value) {
const el = typeof selector === 'string' ? document.querySelector(selector) : s
elector;
if (el) {
const select = el.tagName === 'SELECT' ? el : el.querySelector('select');
if (select) {
select.value = value;
select.dispatchEvent(new Event('change'));
}
}
}The order_by column needs to be handled in the query, even when not selected.
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,200p' tests/test_server.py
"""Legacy test module.
Tests have been split into multiple files:
- test_server_basic.py
- test_server_db_types.py
- test_server_time.py
- test_server_errors.py
- test_server_timeseries.py
"""The root instruction says to add tests to test_server.py, but the files are split.
from scubaduck import server
def test_basic_query() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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 = {
"table": "events",
"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 = {
"table": "events",
"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 = {
"table": "events",
"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,
"columns": ["timestamp", "event", "value", "user"],
}
contains = {
**base,
"filters": [{"column": "user", "op": "contains", "value": "ali"}],
}
rv = client.post(
"/api/query", data=json.dumps(contains), content_type="application/json"
)
rows = rv.get_json()["rows"]
assert all("ali" in r[3] for r in rows)
regex = {
**base,
"filters": [{"column": "user", "op": "~", "value": "^a.*"}],
}
rv = client.post(
"/api/query", data=json.dumps(regex), content_type="application/json"
)
rows = rv.get_json()["rows"]
assert all(r[3].startswith("a") for r in rows)
assert len(rows) == 2
not_empty = {**base, "filters": [{"column": "user", "op": "!empty"}]}
rv = client.post(
"/api/query", data=json.dumps(not_empty), content_type="application/json
"
)
assert len(rv.get_json()["rows"]) == 4root@8c33e558aa85:/workspace/scubaduck# sed -n '200,400p' tests/test_server_basi
c.pyNext, I'll inspect test_server_timeseries.py to understand its style.
from scubaduck import server
def test_group_by_table() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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_table_avg_with_timestamp() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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"],
"aggregate": "Avg",
}
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 = {
"table": "events",
"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 = {
"table": "events",
"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_count_no_columns() -> None:
app = server.app
client = app.test_client()
payload: dict[str, Any] = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"granularity": "1 day",
"columns": [],
}
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"]
assert len(rows) == 2
assert rows[0][1] == 2
assert rows[1][1] == 2
def test_timeseries_limit_applies_to_series() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "timeseries",
"limit": 1,
"order_by": "user",
"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"]) == 2
assert all(r[1] == "alice" for r in data["rows"])
def test_timeseries_auto_and_fine_buckets() -> None:
app = server.app
client = app.test_client()
def run(gran: str) -> None:
payload = {
"start": "2024-01-01 00:00:00",
"end": "2024-01-02 03:00:00",
"graph_type": "timeseries",
"columns": ["value"],
"x_axis": "timestamp",
"granularity": gran,
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/js
on"
)
data = rv.get_json()
assert rv.status_code == 200
from dateutil import parser
start = parser.parse(cast(str, payload["start"])).replace(tzinfo=None)
buckets = [
parser.parse(cast(str, r[0])).replace(tzinfo=None) for r in data["ro
ws"]
]
assert buckets[0] == start
if len(buckets) > 1:
step = (buckets[1] - buckets[0]).total_seconds()
assert step % data["bucket_size"] == 0
assert any(r[1] != 0 for r in data["rows"])
run("Auto")
run("Fine")
def test_timeseries_string_column_error() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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",I’ll scroll closer to the end to review the test style.
"granularity": "1 hour",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
assert rv.status_code == 200
def test_derived_column_basic() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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] == 20
def test_timeseries_derived_column() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"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"},
"aggregate": "Avg",
}
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"]
assert all(r[2] == r[1] * 2 for r in rows)
def test_reserved_word_column() -> None:
app = server.create_app("TEST")
client = app.test_client()
payload = {
"table": "extra",
"columns": ["ts", "desc"],
"order_by": "ts",
"time_column": "",
}
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"]) == 2
assert data["rows"][0][1] == "x"It seems the tests are focused on server functions. I’ll inspect test_web_* files.
er.py
204: select_parts: list[str] = []
222: select_parts.append(f"{bucket_expr} AS bucket")
229: select_parts.extend(_quote(c) for c in select_cols)
251: select_parts.append("count(*) AS Count")
256: select_parts.append(f"{agg_expr(col)} AS {_quote(col)}")
258: select_parts.insert(len(group_cols), "count(*) AS Hits")
260: select_parts.extend(_quote(c) for c in params.columns)
289: select_parts.append(f"{expr} AS {name}")
290: select_clause = ", ".join(select_parts) if select_parts else "*"I think organizing by groups could be useful. Let's check the relevant lines.
return qcol
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 params.time_column
if x_axis is None:
raise ValueError("x_axis required for timeseries")
xexpr = _time_expr(x_axis, column_types, params.time_unit)
if params.start:
bucket_expr = (
f"TIMESTAMP '{params.start}' + INTERVAL '{sec} second' * "
f"CAST(floor((epoch({xexpr}) - epoch(TIMESTAMP '{params.start}')
)/{sec}) AS BIGINT)"
)
else:
bucket_expr = (
f"TIMESTAMP 'epoch' + INTERVAL '{sec} second' * "
f"CAST(floor(epoch({xexpr})/{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(_quote(c) for c in select_cols)
agg = (params.aggregate or "count").lower()
def agg_expr(col: str) -> str:
expr = _quote(col)
ctype = column_types.get(col, "").upper() if column_types else ""
if "BOOL" in ctype:
expr = f"CAST({_quote(col)} AS BIGINT)"
if agg.startswith("p"):
quant = float(agg[1:]) / 100
return f"quantile({expr}, {quant})"
if agg == "count distinct":
return f"count(DISTINCT {expr})"
if agg == "avg" and column_types is not None:
if "TIMESTAMP" in ctype or "DATE" in ctype or "TIME" in ctype:
return (
"TIMESTAMP 'epoch' + INTERVAL '1 second' * "
f"CAST(avg(epoch({_quote(col)})) AS BIGINT)"
)
return f"{agg}({expr})"
if agg == "count":
select_parts.append("count(*) AS Count")
else:
for col in params.columns:
if col in group_cols:
continue
select_parts.append(f"{agg_expr(col)} AS {_quote(col)}")
if params.show_hits:
select_parts.insert(len(group_cols), "count(*) AS Hits")
else:
select_parts.extend(_quote(c) for c in 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.derived_columns.items()
]
indented_inner = "\n".join(" " + line for line in inner_sql.splitline
s())
lines = [
f"SELECT {', '.join(outer_select)}",
"FROM (",
indented_inner,
") t",
]
if params.order_by:
lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_dir}
")
elif params.graph_type == "timeseries":
lines.append("ORDER BY bucket")
if params.limit is not None:
lines.append(f"LIMIT {params.limit}")
return "\n".join(lines)
for name, expr in params.derived_columns.items():
select_parts.append(f"{expr} AS {name}")
select_clause = ", ".join(select_parts) if select_parts else "*"
lines = [f"SELECT {select_clause}", f'FROM "{params.table}"']
where_parts: list[str] = []
if params.time_column:
time_expr = _time_expr(params.time_column, column_types, params.time_uni
t)
else:
time_expr = None
if time_expr and params.start:
where_parts.append(f"{time_expr} >= '{params.start}'")
if time_expr and params.end:
where_parts.append(f"{time_expr} <= '{params.end}'")where_parts.append(f"{time_expr} <= '{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 == "=":
qcol = _quote(f.column)
vals = " OR ".join(f"{qcol} = '{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)
qcol = _quote(f.column)
if op == "contains":
where_parts.append(f"{qcol} ILIKE '%' || {val} || '%'")
elif op == "!contains":
where_parts.append(f"{qcol} NOT ILIKE '%' || {val} || '%'")
elif op == "empty":
where_parts.append(f"{qcol} = {val}")
elif op == "!empty":
where_parts.append(f"{qcol} != {val}")
else:
where_parts.append(f"{qcol} {op} {val}")
if where_parts:
lines.append("WHERE " + " AND ".join(where_parts))
if group_cols:
lines.append("GROUP BY " + ", ".join(_quote(c) for c in group_cols))
if params.order_by:
lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_dir}")
elif params.graph_type == "timeseries":
lines.append("ORDER BY bucket")
if params.limit is not None:
lines.append(f"LIMIT {params.limit}")
return "\n".join(lines)
def create_app(db_file: str | Path | None = None) -> Flask:
app = Flask(__name__, static_folder="static")
if db_file is None:
env_db = os.environ.get("SCUBADUCK_DB")
if env_db:
db_file = env_db
if isinstance(db_file, str) and db_file.upper() == "TEST":
con = _create_test_database()
else:
db_path = Path(db_file or Path(__file__).with_name("sample.csv")).resolv
e()
con = _load_database(db_path)
tables = [r[0] for r in con.execute("SHOW TABLES").fetchall()]
if not tables:
raise ValueError("No tables found in database")
default_table = tables[0]
columns_cache: Dict[str, Dict[str, str]] = {}
def get_columns(table: str) -> Dict[str, str]:
if table not in columns_cache:
rows = con.execute(f'PRAGMA table_info("{table}")').fetchall()
if not rows:
raise ValueError(f"Unknown table: {table}")
columns_cache[table] = {r[1]: r[2] for r in rows}
return columns_cache[table]
sample_cache: Dict[Tuple[str, 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/tables")
def tables_endpoint() -> Any: # pyright: ignore[reportUnusedFunction]
return jsonify(tables)
@app.route("/api/columns")
def columns() -> Any: # pyright: ignore[reportUnusedFunction]
table = request.args.get("table", default_table)
rows = con.execute(f'PRAGMA table_info("{table}")').fetchall()
return jsonify([{"name": r[1], "type": r[2]} for r in rows])
def _cache_get(key: Tuple[str, 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, 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]
table = request.args.get("table", default_table)
column = request.args.get("column")
substr = request.args.get("q", "")
column_types = get_columns(table)
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 = (table, column, substr)
cached = _cache_get(key)
...
}
),
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:
params.x_axis = params.time_column
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()
is_time = any(t in ctype for t in ["TIMESTAMP", "DATE", "TIME"])
is_numeric = any(
t in ctype
for t in [
"INT",
"DECIMAL",
"REAL",
"DOUBLE",
"FLOAT",
"NUMERIC",
"HUGEINT",
]
)
if not (is_time or is_numeric):
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 "count").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(
{
"error": f"Aggregate {agg} cannot be applied
to column {c}",
}
),
400,
)
if (params.start is None or params.end is None) and (
params.x_axis or params.time_column
):
axis = params.x_axis or params.time_column
assert axis is not None
row = cast(
tuple[datetime | None, datetime | None],
con.execute(
f'SELECT min({_quote(axis)}), max({_quote(axis)}) FROM "{par
ams.table}"'
).fetchall()[0],
)
mn, mx = row
divisor = {
"s": 1,
"ms": 1000,
"us": 1_000_000,
"ns": 1_000_000_000,
}.get(params.time_unit, 1)
if isinstance(mn, (int, float)):
try:
mn = datetime.fromtimestamp(int(mn) / divisor, tz=timezone.u
tc)
except Exception:
return (
jsonify(
{
"error": (
f"Invalid time value {mn} for column {axis}"
f" with time_unit {params.time_unit}"
)
}
),
400,
)I'll search for "order_by" in server.py to confirm how it's validated after columns.
root@8c33e558aa85:/workspace/scubaduck# grep -n "order_by" -n scubaduck/server.p
y
36: order_by: str | None = None
266: order_by=None,
280: if params.order_by:
281: lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_
dir}")
333: if params.order_by:
334: lines.append(f"ORDER BY {_quote(params.order_by)} {params.order_dir}
")
445: order_by=payload.get("order_by"),
516: if params.order_by and params.order_by not in valid_cols:
517: return jsonify({"error": f"Unknown column: {params.order_by}"}),
400The server validates order_by, but excludes checking if it's selected. I'll check for exceptions.
root@8c33e558aa85:/workspace/scubaduck# grep -n "selectedColumns" -r scubaduck/s
tatic/js | head
scubaduck/static/js/timeseries_chart.js:38: const valueCols = selectedColumns.s
lice(groups.length + hasHits);
scubaduck/static/js/table_view.js:11: let hitsIndex = selectedColumns.indexOf("
Hits");
scubaduck/static/js/table_view.js:17: selectedColumns.forEach((col, i) => {
scubaduck/static/js/table_view.js:51: const col = selectedColumns[i];
scubaduck/static/js/view_settings.js:15:let selectedColumns = [];
scubaduck/static/js/view_settings.js:439: selectedColumns = groupBy.chips.sli
ce();
scubaduck/static/js/view_settings.js:440: if (document.getElementById('show_h
its').checked) selectedColumns.push('Hits');
scubaduck/static/js/view_settings.js:442: if (!selectedColumns.includes(c))
selectedColumns.push(c);
scubaduck/static/js/view_settings.js:445: if (dc.include && !selectedColumn
s.includes(dc.name)) selectedColumns.push(dc.name);
scubaduck/static/js/view_settings.js:448: selectedColumns = base.slice();I'll take a look at timeseries_chart.js now.
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,100p' scubaduck/static/js/tabl
e_view.js
// Logic for rendering the table based views. Extracted from index.html so that
// the inline script only handles wiring up the UI.
let originalRows = [];
let sortState = { index: null, dir: null };
function renderTable(rows) {
const table = document.getElementById("results");
table.innerHTML = "";
if (rows.length === 0) return;
let hitsIndex = selectedColumns.indexOf("Hits");
let totalHits = 0;
if (hitsIndex !== -1) {
totalHits = rows.reduce((s, r) => s + Number(r[hitsIndex]), 0);
}
const header = document.createElement("tr");
selectedColumns.forEach((col, i) => {
const th = document.createElement("th");
let label = col;
if (
displayType === "table" &&
col !== "Hits" &&
!(groupBy.chips || []).includes(col)
) {
const agg = document.getElementById("aggregate").value.toLowerCase();
label += ` (${agg})`;
}
th.textContent = label;
th.dataset.index = i;
th.addEventListener("click", handleSort);
if (sortState.index === i) {
th.classList.add("sorted");
th.textContent = label + (sortState.dir === "desc" ? " \u25BC" : " \u25B2"
);
}
if (!isStringColumn(col)) th.style.textAlign = "right";
header.appendChild(th);
});
table.appendChild(header);
rows.forEach((row) => {
const tr = document.createElement("tr");
tr.addEventListener("click", () => {
const wasSelected = tr.classList.contains("selected");
document
.querySelectorAll("#results tr.selected")
.forEach((el) => el.classList.remove("selected"));
if (!wasSelected) {
tr.classList.add("selected");
}
});
row.forEach((v, i) => {
const col = selectedColumns[i];
const td = document.createElement("td");
if (isTimeColumn(col)) {
let d;
const t = (columnTypes[col] || "").toUpperCase();
if (t.includes("TIMESTAMP") || t.includes("DATE") || t.includes("TIME"))
{
d = new Date(v);
} else {
const unit = document.getElementById("time_unit").value;
const factors = { s: 1000, ms: 1, us: 0.001, ns: 0.000001 };
d = new Date(Number(v) * (factors[unit] || 1000));
}
td.textContent = d.toLocaleString("en-US", {
weekday: "short",
month: "short",
day: "numeric",
year: "numeric",
hour: "numeric",
minute: "numeric",
second: "numeric",
hour12: true,
timeZoneName: "short",
});
td.classList.add("date");
} else {
if (col === "Hits") {
const pct = totalHits ? ((v / totalHits) * 100).toFixed(1) : "0";
td.textContent = `${formatNumber(v)} (${pct}%)`;
} else {
td.textContent = isStringColumn(col) ? v : formatNumber(v);
}
}
if (!isStringColumn(col) && !isTimeColumn(col)) {
td.classList.add("numeric");
}
td.style.textAlign = isStringColumn(col) ? "left" : "right";
tr.appendChild(td);
});
table.appendChild(tr);
});
// ensure table does not overflow unless necessary
const view = document.getElementById("view");
if (table.scrollWidth <= view.clientWidth) {
table.style.width = "100%";
}
}
function handleSort(e) {
const idx = parseInt(e.target.dataset.index, 10);
if (sortState.index !== idx) {I'll scroll a bit more to reach the end.
root@8c33e558aa85:/workspace/scubaduck# sed -n '100,200p' scubaduck/static/js/ta
ble_view.js
if (sortState.index !== idx) {
sortState.index = idx;
sortState.dir = "asc";
} else if (sortState.dir === "asc") {
sortState.dir = "desc";
} else if (sortState.dir === "desc") {
sortState.index = null;
sortState.dir = null;
} else {
sortState.dir = "asc";
}
let rows = originalRows.slice();
if (sortState.index !== null) {
rows.sort((a, b) => {
const va = a[sortState.index];
const vb = b[sortState.index];
if (va === vb) return 0;
if (sortState.dir === "desc") return va < vb ? 1 : -1;
return va > vb ? 1 : -1;
});
}
renderTable(rows);
}
function showResults(data) {
window.lastResults = data;
const view = document.getElementById("view");
if (graphTypeSel.value === "timeseries") {
showTimeSeries(data);
} else {
if (data.rows.length === 0) {
view.innerHTML =
'<p id="empty-message">Empty data provided to table</p><table id="result
s"></table>';
} else {
view.innerHTML = '<table id="results"></table>';
}
originalRows = data.rows.slice();
sortState = { index: null, dir: null };
renderTable(originalRows);
}
const sqlEl = document.createElement("pre");
sqlEl.id = "sql_query";
sqlEl.style.whiteSpace = "pre-wrap";
sqlEl.style.marginTop = "10px";
sqlEl.textContent = data.sql;
view.appendChild(sqlEl);
document.getElementById("query_info").textContent = `Your query took about ${l
astQueryTime} ms`;
}
function showError(err) {
window.lastResults = err;
const view = document.getElementById("view");
let msg = "";
if (typeof err === "string") {
msg = err;
} else if (err) {
msg = err.error || "Error";
if (err.sql) {
msg += "\nSQL: " + err.sql;
}
if (err.traceback) {
msg += "\n" + err.traceback;
}
}
view.innerHTML = `<pre id="error-message">${msg}</pre>`;
document.getElementById("query_info").textContent = "";
}I think the issue arises when the server returns an unexpected column. I'll search for where the query payload is built.
root@8c33e558aa85:/workspace/scubaduck# grep -n "dive(" -n scubaduck/static/js -
r
scubaduck/static/js/timeseries_chart.js:439: dive();
scubaduck/static/js/timeseries_chart.js:452: dive();
scubaduck/static/js/view_settings.js:646:function dive(push=true) {
scubaduck/static/js/view_settings.js:858: dive(false);
scubaduck/static/js/view_settings.js:864: dive(false);Time to check out the area around dive! Let's go explore.
root@8c33e558aa85:/workspace/scubaduck# sed -n '640,740p' scubaduck/static/js/vi
ew_settings.jsupdateSelectedColumns();
}
let lastQueryTime = 0;
let queryStart = 0;
function dive(push=true) {
const params = collectParams();
if (push) {
history.pushState(params, '', paramsToSearch(params));
}
const payload = Object.assign({}, params);
const dcMap = {};
(params.derived_columns || []).forEach(d => {
if (d.include) dcMap[d.name] = d.expr;
});
payload.derived_columns = dcMap;
const view = document.getElementById('view');
view.innerHTML = '<p>Loading...</p>';
window.lastResults = undefined;
queryStart = performance.now();
fetch('/api/query', {method:'POST', headers:{'Content-Type':'application/json'
}, body:JSON.stringify(payload)})
.then(async r => {
const data = await r.json();
if (!r.ok) throw data;
return data;
})
.then(data => {
lastQueryTime = Math.round(performance.now() - queryStart);
showResults(data);
})
.catch(err => {
showError(err);
});
}
function collectParams() {
updateSelectedColumns();
const payload = {
table: document.getElementById('table').value,
time_column: document.getElementById('time_column').value,
time_unit: document.getElementById('time_unit').value,
start: document.getElementById('start').value,
end: document.getElementById('end').value,
order_by: document.getElementById('order_by').value,
order_dir: orderDir,
limit: parseInt(document.getElementById('limit').value, 10),
columns: selectedColumns.filter(c =>
c !== 'Hits' && !derivedColumns.some(dc => dc.name === c)
),
samples_columns: columnValues.samples.slice(),
table_columns: columnValues.table.slice(),
timeseries_columns: columnValues.timeseries.slice(),
graph_type: graphTypeSel.value,
filters: Array.from(document.querySelectorAll('#filters .filter')).map(f =>
{
const chips = f.chips || [];
const op = f.querySelector('.f-op').value;
let value = null;
if (op !== 'empty' && op !== '!empty') {
value = chips.length === 0 ? null : (chips.length === 1 ? chips[0] : chi
ps);
}
const colSel = f.querySelector('.f-col select') || f.querySelector('.f-col
');
return {column: colSel.value, op, value};
}),
derived_columns: Array.from(document.querySelectorAll('#derived_list .derive
d')).map(d => ({
type: d.querySelector('.d-type').value,
name: d.querySelector('.d-name').value,
expr: d.querySelector('.d-expr').value,
include: d.querySelector('.d-use').checked,
}))
};
if (graphTypeSel.value === 'table' || graphTypeSel.value === 'timeseries') {
payload.group_by = groupBy.chips || [];
payload.aggregate = document.getElementById('aggregate').value;
payload.show_hits = document.getElementById('show_hits').checked;
}
if (graphTypeSel.value === 'timeseries') {
const xval = document.getElementById('x_axis').value;
if (xval) payload.x_axis = xval;
payload.granularity = document.getElementById('granularity').value;
payload.fill = document.getElementById('fill').value;
}
return payload;
}
function paramsToSearch(params) {
const sp = new URLSearchParams();
if (params.table) sp.set('table', params.table);
if (params.time_column) sp.set('time_column', params.time_column);
if (params.time_unit) sp.set('time_unit', params.time_unit);
if (params.start) sp.set('start', params.start);
if (params.end) sp.set('end', params.end);
if (params.order_by) sp.set('order_by', params.order_by);
if (params.order_dir) sp.set('order_dir', params.order_dir);
if (params.limit !== null && params.limit !== undefined) sp.set('limit', param
s.limit);
if (params.samples_columns && params.samples_columns.length) sp.set('samples_c
olumns', params.samples_columns.join(','));
if (params.table_columns && params.table_columns.length) sp.set('table_columns
', params.table_columns.join(','));
if (params.timeseries_columns && params.timeseries_columns.length) sp.set('tim
eseries_columns', params.timeseries_columns.join(','));
if (params.filters && params.filters.length) sp.set('filters', JSON.stringify(
params.filters));
if (params.derived_columns && params.derived_columns.length) sp.set('derived_c
olumns', JSON.stringify(params.derived_columns));
if (params.graph_type) sp.set('graph_type', params.graph_type);I need to check how order_by is being used on the frontend.
root@8c33e558aa85:/workspace/scubaduck# grep -n "order_by" -r scubaduck/static/j
s
scubaduck/static/js/view_settings.js:172: document.getElementById('order_by')
.value = '';
scubaduck/static/js/view_settings.js:197: const orderSelect = document.getEle
mentById('order_by');
scubaduck/static/js/view_settings.js:684: order_by: document.getElementById('
order_by').value,
scubaduck/static/js/view_settings.js:732: if (params.order_by) sp.set('order_by
', params.order_by);
scubaduck/static/js/view_settings.js:762: if (params.order_by) {
scubaduck/static/js/view_settings.js:763: document.getElementById('order_by')
.value = params.order_by;
scubaduck/static/js/view_settings.js:832: if (sp.has('order_by')) params.order_
by = sp.get('order_by');I’ll add order_by to selectedColumns when not selected in the checkbox and send it to the server. It won’t affect the checkbox state, but the column will appear in the results table. I'll check updateSelectedColumns to ensure order_by is added to selectedColumns when necessary.
I’ll show the order-by column in results, determining its position after group_by. Let’s refine updateSelectedColumns.
root@8c33e558aa85:/workspace/scubaduck# grep -n "updateSelectedColumns" -n scuba
duck/static/js/view_settings.js
143: updateSelectedColumns(prevType);
174: updateSelectedColumns(newType);
306: cb.addEventListener('change', updateSelectedColumns);
315: updateSelectedColumns();
320: updateSelectedColumns();
328: updateSelectedColumns();
333: updateSelectedColumns();
335: updateSelectedColumns();
431:function updateSelectedColumns(type = graphTypeSel.value) {
640: updateSelectedColumns();
677: updateSelectedColumns();
794: updateSelectedColumns(graphTypeSel.value);I’ll check around lines 431 to review how updateSelectedColumns was implemented.
root@8c33e558aa85:/workspace/scubaduck# sed -n '420,470p' scubaduck/static/js/vi
ew_settings.js
if (!dd.parentElement.contains(e.target)) dd.style.display = 'none';
});
});
function updateColumnsTabCount() {
const baseCount = document.querySelectorAll('#column_groups input:checked').le
ngth;
const derivedCount = document.querySelectorAll('#derived_list .derived .d-use:
checked').length;
const btn = document.getElementById('columns_tab');
if (btn) btn.textContent = `Columns (${baseCount + derivedCount})`;
}
function updateSelectedColumns(type = graphTypeSel.value) {
const base = allColumns.filter(name => {
const cb = document.querySelector(`#column_groups input[value="${name}"]`);
if (!cb || !cb.checked) return false;
if (type === 'table' && isStringColumn(name)) return false;
return true;
});
if (type === 'table' || type === 'timeseries') {
selectedColumns = groupBy.chips.slice();
if (document.getElementById('show_hits').checked) selectedColumns.push('Hits
');
base.forEach(c => {
if (!selectedColumns.includes(c)) selectedColumns.push(c);
});
derivedColumns.forEach(dc => {
if (dc.include && !selectedColumns.includes(dc.name)) selectedColumns.push
(dc.name);
});
} else {
selectedColumns = base.slice();
derivedColumns.forEach(dc => {
if (dc.include) selectedColumns.push(dc.name);
});
}
columnValues[type] = selectedColumns.slice();
updateColumnsTabCount();
}
function isStringColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
return t.includes('CHAR') || t.includes('STRING') || t.includes('VARCHAR');
}
function isIntegerColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
return t.includes('INT');
}
function isTimeColumn(name) {
const t = (columnTypes[name] || '').toUpperCase();
if (t.includes('TIMESTAMP') || t.includes('DATE') || t.includes('TIME')) retur
n true;
const sel = document.getElementById('time_column').value;from typing import Any
from tests.web_utils import select_value
def test_column_toggle_and_selection(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
count = page.evaluate(
"document.querySelectorAll('#column_groups input:checked').length"
)
assert count == 4
page.click("#columns_none")
count = page.evaluate(
"document.querySelectorAll('#column_groups input:checked').length"
)
assert count == 0
page.click("#columns_all")
count = page.evaluate(
"document.querySelectorAll('#column_groups input:checked').length"
)
assert count == 4
page.uncheck("#column_groups input[value='value']")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
select_value(page, "#order_by", "timestamp")
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 len(data["rows"][0]) == 3
headers = page.locator("#results th").all_inner_texts()
assert "value" not in headers
def test_columns_links_alignment(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
tag = page.evaluate("document.getElementById('columns_all').tagName")
assert tag == "A"
align = page.evaluate(
"getComputedStyle(document.querySelector('#column_actions')).textAlign"
)
assert align == "right"
def test_column_group_links(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups a", state="attached")
tag = page.evaluate("document.querySelector('#column_groups .col-group a').t
agName")
assert tag == "A"
def test_column_group_links_float_right(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups .col-group .links", state="attached")
float_val = page.evaluate(
"getComputedStyle(document.querySelector('#column_groups .col-group .lin
ks')).float"
)
assert float_val == "right"
def test_columns_tab_selected_count(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
count_text = page.text_content("#columns_tab")
assert count_text is not None and "(4)" in count_text
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
page.uncheck("#column_groups input[value='value']")
count_text = page.text_content("#columns_tab")
assert count_text is not None and "(3)" in count_textAGENTS instructions say to add to tests/test_web.py, but files are split. I'll create it.
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")
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)
if page.input_value("#graph_type") != "samples":
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
if not page.is_checked("#column_groups input[value='value']"):
page.check("#column_groups input[value='value']")
order_col = order_by or page.input_value("#order_by")
if order_col and not page.is_checked(
f"#column_groups input[value='{order_col}']"
):
if page.query_selector(f"#column_groups input[value='{order_col}']")
:
page.check(f"#column_groups input[value='{order_col}']")
page.click("text=View Settings")
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
return page.evaluate("window.lastResults")I see that run_query auto-selects 'order_by,' so I'll create a custom test instead.
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="user",
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="user",
limit=2,
)
assert len(data["rows"]) == 2
def test_time_column_dropdown(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#time_column option", state="attached")
options = page.locator("#time_column option").all_inner_texts()
assert "(none)" in options
assert "timestamp" in options
assert "value" in options
assert page.input_value("#time_column") == "timestamp"
def test_time_column_none_hides_range(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#time_column option", state="attached")
select_value(page, "#time_column", "")
assert page.is_hidden("#start")
assert page.is_hidden("#end")
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
data = page.evaluate("window.lastResults")
assert len(data["rows"]) == 4
assert "start" not in data and "end" not in data
def test_time_unit_dropdown(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#time_unit", state="attached")
opts = page.locator("#time_unit option").all_inner_texts()
assert "ms" in opts
assert page.input_value("#time_unit") == "s"
def test_table_selector_dropdown(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#table option", state="attached")
disp = page.query_selector("#table + .dropdown-display")
assert disp
assert (
page.evaluate("getComputedStyle(document.querySelector('#table')).displa
y")
== "none"
)
assert page.query_selector("#table + .dropdown-display + .dropdown-menu inpu
t")
def test_x_axis_default_entry(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#graph_type", state="attached")
select_value(page, "#graph_type", "timeseries")
page.wait_for_selector("#x_axis option", state="attached")
options = page.locator("#x_axis option").all_inner_texts()
assert "(default)" in options
assert page.input_value("#x_axis") == ""
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")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
assert page.is_visible("#settings")
assert page.is_hidden("#columns")
page.click("text=Columns")
assert page.is_visible("#columns")
cols = [c.strip() for c in page.locator("#column_groups li").all_inner_texts
()]
assert "timestamp" in cols
assert "event" in cols
page.click("text=View Settings")
assert page.is_visible("#settings")
btn_color = page.evaluate(
"getComputedStyle(document.querySelector('#dive')).backgroundColor"
)
assert "rgb(0, 128, 0)" == btn_color
sidebar_overflow = page.evaluate(
"getComputedStyle(document.querySelector('#sidebar')).overflowY"
)
view_overflow = page.evaluate(
"getComputedStyle(document.querySelector('#view')).overflowY"
)
assert sidebar_overflow == "auto"
assert view_overflow == "auto"
def test_help_and_alignment(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
titles = page.evaluate(
"Array.from(document.querySelectorAll('#settings .help')).map(e => e.tit
le)"
)
assert any("start/end of the time range" in t for t in titles)
text_align = page.evaluate(
"getComputedStyle(document.querySelector('#settings label')).textAlign"
)
assert text_align == "right"
def test_relative_dropdown(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
btn = page.query_selector('[data-target="start-select"]')
assert btn
btn.click()
page.click("#start-select div:text('-3 hours')")
assert page.input_value("#start") == "-3 hours"
def test_end_dropdown_now(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click('[data-target="end-select"]')
page.click("#end-select div:text('now')")
assert page.input_value("#end") == "now"
def test_invalid_time_error_shown(page: Any, server_url: str) -> None:
data = run_query(
page,
server_url,
start="nonsense",
end="now",
order_by="user",
)
assert "error" in data
msg = page.text_content("#view")
assert "nonsense" in msg
def test_url_query_persistence(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.wait_for_function("window.lastResults !== undefined")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
page.fill("#limit", "1")
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
first_url = page.urlAlright, I’ll follow the instructions and modify tests/test_web.py. Time to review test styles.
def test_table_sorting(page: Any, server_url: str) -> None:
run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="user",
order_dir="ASC",
limit=100,
)
# header alignment
align = page.evaluate(
"getComputedStyle(document.querySelector('#results th')).textAlign"
)
assert align == "right"
header = page.locator("#results th").nth(3)
def values() -> list[str]:
return page.locator("#results td:nth-child(4)").all_inner_texts()
orig_rows = values()
assert orig_rows == ["alice", "bob", "alice", "charlie"]
first_sql = page.evaluate("window.lastResults.sql")
header.click()
assert values() == sorted(orig_rows)
assert header.inner_text().endswith("▲")
color = page.evaluate(
"getComputedStyle(document.querySelector('#results th:nth-child(4)')).co
lor"
)
assert "0, 0, 255" in color
assert page.evaluate("window.lastResults.sql") == first_sql
header.click()
assert values() == sorted(orig_rows, reverse=True)
assert header.inner_text().endswith("▼")
header.click()
assert values() == orig_rows
assert header.inner_text() == "user"
color = page.evaluate(
"getComputedStyle(document.querySelector('#results th:nth-child(4)')).co
lor"
)
assert "0, 0, 255" not in color
def test_table_avg_group_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="timestamp",
group_by=["user"],
aggregate="Avg",
)
assert "error" not in data
assert len(data["rows"]) == 3
def test_table_enhancements(page: Any, server_url: str) -> None:
run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="timestamp",
limit=10,
)
border = page.evaluate(
"getComputedStyle(document.querySelector('#results td')).borderStyle"
)
assert border == "solid"
color1 = page.evaluate(
"getComputedStyle(document.querySelector('#results tr:nth-child(2) td'))
.backgroundColor"
)
color2 = page.evaluate(
"getComputedStyle(document.querySelector('#results tr:nth-child(3) td'))
.backgroundColor"
)
assert color1 != color2
page.hover("#results tr:nth-child(2)")
hover_color = page.evaluate(
"getComputedStyle(document.querySelector('#results tr:nth-child(2) td'))
.backgroundColor"
)
assert hover_color != color1
page.click("#results tr:nth-child(2)")
selected_color = page.evaluate(
"getComputedStyle(document.querySelector('#results tr:nth-child(2) td'))
.backgroundColor"
)
assert "189, 228, 255" in selected_color
overflow = page.evaluate(
"var v=document.getElementById('view'); v.scrollWidth > v.clientWidth"
)
assert not overflow
def test_table_single_selection(page: Any, server_url: str) -> None:
run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-03 00:00:00",
order_by="timestamp",
limit=10,
)
page.click("#results tr:nth-child(2)")
page.click("#results tr:nth-child(3)")
count = page.evaluate("document.querySelectorAll('#results tr.selected').len
gth")
assert count == 1
is_third = page.evaluate(
"document.querySelector('#results tr:nth-child(3)').classList.contains('
selected')"
)
assert is_third
def test_timestamp_rendering(page: Any, server_url: str) -> None:
run_query(
page,
server_url,
start="2024-01-01 00:00:00",
end="2024-01-02 00:00:00",
order_by="timestamp",
limit=1,
)
cell = page.text_content("#results td")
assert cell != "Invalid Date"
valid = page.evaluate("v => !isNaN(Date.parse(v))", cell)
assert valid
def test_empty_data_message(page: Any, server_url: str) -> None:
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)Instead of using run_query, I'll modify the test manually to control column selection.
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")
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)
if page.input_value("#graph_type") != "samples":
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
if not page.is_checked("#column_groups input[value='value']"):
page.check("#column_groups input[value='value']")
order_col = order_by or page.input_value("#order_by")
if order_col and not page.is_checked(
f"#column_groups input[value='{order_col}']"
):
if page.query_selector(f"#column_groups input[value='{order_col}']")
:
page.check(f"#column_groups input[value='{order_col}']")
page.click("text=View Settings")
page.evaluate("window.lastResults = undefined")
page.click("text=Dive")
page.wait_for_function("window.lastResults !== undefined")
return page.evaluate("window.lastResults")I'll simulate a user unchecking the 'timestamp' column but still selecting it for ordering.
root@8c33e558aa85:/workspace/scubaduck# head -n 5 scubaduck/sample.csv
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,charlieThe default columns are set, but I'll confirm the sorting and retrieve values from index.html.
root@8c33e558aa85:/workspace/scubaduck# sed -n '1,200p' scubaduck/static/index.h
tml
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>ScubaDuck</title>
<style>
body { margin: 0; font-family: sans-serif; height: 100vh; display: flex; fle
x-direction: column; }
#header { padding: 10px; font-weight: bold; border-bottom: 1px solid #ccc; }
#content { flex: 1; display: flex; height: calc(100vh - 42px); overflow: hid
den; }
#sidebar { width: 450px; padding: 10px; border-right: 3px solid #ccc; overfl
ow-y: auto; display: flex; flex-direction: column; box-sizing: border-box; }
#sidebar-resizer { width: 5px; cursor: col-resize; background: #ccc; }
#view { flex: 1; padding: 10px; overflow-y: auto; overflow-x: auto; }
.field { display: flex; align-items: center; margin-bottom: 10px; }
.field label { width: 80px; text-align: right; margin-right: 5px; }
.help { margin-left: 4px; cursor: help; }
.rel-btn { margin-left: 4px; }
#tabs { display: flex; align-items: center; margin-bottom: 10px; }
#tabs .tab { margin-right: 5px; background: none; border: 1px solid #ccc; pa
dding: 4px 8px; cursor: pointer; width: 120px; text-align: center; box-sizing: b
order-box; }
#tabs .tab.active { background: #eee; font-weight: bold; }
#dive { margin-left: auto; background: green; color: white; border: none; pa
dding: 5px 10px; cursor: pointer; }
.tab-content { display: none; }
.tab-content.active { display: block; }
#filter_list { display: flex; flex-direction: column; }
#filters .filter {
border: 1px solid #ccc;
padding: 5px;
margin-bottom: 5px;
position: relative;
display: flex;
flex-direction: column;
}
#derived_columns .derived {
border: 1px solid #ccc;
padding: 5px;
margin-bottom: 5px;
display: flex;
flex-direction: column;
}
#derived_columns .derived-row {
display: flex;
margin-bottom: 5px;
}
#derived_columns .derived-row input[type="text"] {
margin-left: 5px;
flex: 1;
}
#derived_columns .derived-row button.remove {
margin-left: 5px;
width: 20px;
flex: 0 0 auto;
padding: 0;
text-align: center;
line-height: 1;
}
#derived_columns textarea {
width: 100%;
box-sizing: border-box;
}
#filters .filter-row { display: flex; margin-bottom: 5px; }
#filters .filter-row .f-col { flex: 1; }
#filters .filter-row .f-op {
margin-left: 5px;
width: fit-content;
flex: 0 0 auto;
}
.chip-input input {
border: none;
flex: 1;
min-width: 60px;
margin: 2px;
outline: none;
}
.chip-box { position: relative; }
.chip-input { display: flex; flex-wrap: wrap; border: 1px solid #ccc; paddin
g: 2px; min-height: 24px; }
.chip { background: #eee; border: 1px solid #999; padding: 2px 4px; margin:
2px; border-radius: 3px; display: flex; align-items: center; }
.chip .x { margin-left: 4px; cursor: pointer; }
.chip-copy { margin-left: 4px; cursor: pointer; background: none; border: no
ne; }
.chip-dropdown { position: absolute; left: 0; right: 0; top: 100%; backgroun
d: white; border: 1px solid #ccc; max-height: 120px; overflow-y: auto; z-index:
10; display: none; }
.chip-dropdown div { padding: 2px 4px; cursor: pointer; }
.chip-dropdown div.highlight { background: #bde4ff; }
.rel-box { position: relative; display: flex; }
.rel-dropdown { position: absolute; left: 0; right: 0; top: 100%; background
: white; border: 1px solid #ccc; z-index: 10; display: none; }
.rel-dropdown div { padding: 2px 4px; cursor: pointer; }
.rel-dropdown div:hover { background: #bde4ff; }
.dropdown { position: relative; display: inline-block; }
.dropdown-display {
border: 1px solid #ccc;
padding: 2px 18px 2px 4px;
cursor: pointer;
min-width: 80px;
position: relative;
}
.dropdown-display::after {
content: '\25BC';
position: absolute;
right: 4px;
pointer-events: none;
}
.dropdown-menu { position: absolute; left: 0; right: 0; top: 100%; backgroun
d: white; border: 1px solid #ccc; z-index: 10; max-height: 160px; overflow-y: au
to; display: none; }
.dropdown-menu input { width: 100%; box-sizing: border-box; padding: 2px 4px
; border: none; border-bottom: 1px solid #ccc; }
.dropdown-menu div { padding: 2px 4px; cursor: pointer; }
.dropdown-menu div.selected { background: #bde4ff; }
.dropdown-menu .option:hover { background: #eee; }
.dropdown-menu input::placeholder { color: #999; }
#filters .filter button.remove {
margin-left: 5px;
width: 20px;
flex: 0 0 auto;
padding: 0;
text-align: center;
line-height: 1;
}
#filters h4 { margin: 0 0 5px 0; }
table { border-collapse: collapse; min-width: 100%; }
th, td { border: 1px solid #ccc; padding: 4px; box-sizing: border-box; }
td.numeric { white-space: nowrap; }
td.date { white-space: nowrap; }
th { text-align: left; cursor: pointer; position: relative; }
th.sorted { color: blue; }
tr:nth-child(even) td { background: #f9f9f9; }
tr.selected td { background: #bde4ff !important; }
tr:hover:not(.selected) td { background: #eee; }
#column_actions {
text-align: right;
margin-bottom: 5px;
}
#column_actions a {
margin-left: 5px;
}
.col-group-header {
overflow: hidden;
}
.col-group-header .links {
float: right;
}
.col-group-header .links a {
margin-left: 5px;
}
#ts-container {
display: flex;
}
#legend {
width: 150px;
flex: 0 0 150px;
margin-right: 10px;
overflow-y: auto;
}
.legend-group {
margin-bottom: 4px;
}
.legend-header {
font-weight: normal;
}
.legend-item {
display: flex;
justify-content: space-between;
padding-left: 8px;
}
.legend-value {
margin-left: 4px;
}
#chart-wrapper {
flex: 1;
}
.legend-item.highlight {
background: #ddd;
}
#legend .drill-links h4 {
margin: 10px 0 4px 0;
}
#legend .drill-links a {
display: block;
margin-left: 8px;
}
#chart text.tick-label {
font-size: 10px;
user-select: none;
}
#chart text.tick-label.rotated {
text-anchor: end;
}
#chart text.y-tick-label {
font-size: 10px;
user-select: none;
}
#chart line.grid {
stroke: #ccc;
}
/* Column resizer removed */
</style>
</head>
<body>
<div id="header">sample.csv - <select id="table"></select> <select id="graph_t
ype"><option value="samples">Samples</option><option value="table">Table</option
><option value="timeseries">Time Series</option></select></div>
<div id="content">
<div id="sidebar">
<div id="tabs">
<button class="tab active" data-tab="settings">View Settings</button>
<button id="columns_tab" class="tab" data-tab="columns">Columns</button>
<button id="dive" onclick="dive()">Dive</button>
</div>I'm looking at the bottom to confirm the default options, like order_by.
root@8c33e558aa85:/workspace/scubaduck# grep -n "order_by" -n scubaduck/static/i
ndex.html
251: <select id="order_by"></select>I’m checking 250 lines to locate the <div> related to order_by.
root@8c33e558aa85:/workspace/scubaduck# sed -n '240,260p' scubaduck/static/index
.html
<div data-value="-1 day">-1 day</div>
<div data-value="-3 days">-3 days</div>
<div data-value="-1 week">-1 week</div>
<div data-value="-1 fortnight">-1 fortnight</div>
<div data-value="-30 days">-30 days</div>
<div data-value="-90 days">-90 days</div>
</div>
</div>
</div>
<div class="field">
<label>Order By<span class="help" title="Choose a column to sort resul
ts by.">[?]</span></label>
<select id="order_by"></select>
<button id="order_dir" type="button">ASC \u25B2</button>
</div>
<div class="field">
<label>Limit<span class="help" title="Choose the maximum number of res
ults 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.">[?]</span></lab
el>
<input id="limit" type="number" value="100" />
</div>
<div id="x_axis_field" class="field" style="display:none;">
<label>X-axis</label>
<select id="x_axis"></select>I'm checking if the default order_by is set to "timestamp" in the JS code.
root@8c33e558aa85:/workspace/scubaduck# grep -n "order_by'" -n scubaduck/static/
js -n | head
grep: scubaduck/static/js: Is a directoryI’ll use grep to search for the '#id' labeled 'order_by'.
root@8c33e558aa85:/workspace/scubaduck# grep -n "order_by" scubaduck/static/js -
r
scubaduck/static/js/view_settings.js:172: document.getElementById('order_by')
.value = '';
scubaduck/static/js/view_settings.js:197: const orderSelect = document.getEle
mentById('order_by');
scubaduck/static/js/view_settings.js:684: order_by: document.getElementById('
order_by').value,
scubaduck/static/js/view_settings.js:732: if (params.order_by) sp.set('order_by
', params.order_by);
scubaduck/static/js/view_settings.js:762: if (params.order_by) {
scubaduck/static/js/view_settings.js:763: document.getElementById('order_by')
.value = params.order_by;
scubaduck/static/js/view_settings.js:832: if (sp.has('order_by')) params.order_
by = sp.get('order_by');I'm reviewing the pyproject file to check the ruff configuration before running tests.
root@8c33e558aa85:/workspace/scubaduck# cat pyproject.toml
[project]
name = "scubaduck"
version = "0.1.0"
description = "Scuba on DuckDB"
readme = "README.md"
requires-python = ">=3.12"
license = {text = "MIT"}
dependencies = [
"duckdb",
"flask",
"python-dateutil>=2.9.0.post0",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.pytest.ini_options]
addopts = "-n auto --tb=native"
[tool.pyright]
# Pyright configuration with strict settings
include = ["scubaduck", "tests"]
exclude = ["**/__pycache__", "dist"]
stubPath = "stubs"
venvPath = "."
venv = ".venv"
reportMissingImports = true
reportMissingTypeStubs = true
pythonVersion = "3.12"
pythonPlatform = "All"
typeCheckingMode = "strict"
reportUnknownMemberType = true
reportUnknownParameterType = true
reportUnknownVariableType = true
reportUnknownArgumentType = true
reportPrivateImportUsage = true
reportUntypedFunctionDecorator = true
reportFunctionMemberAccess = true
reportIncompatibleMethodOverride = true
[tool.ruff]
target-version = "py312"
[tool.uv]
dev-dependencies = [
"pytest>=8.3.5",
"ruff>=0.11.2",
"pytest-xdist>=3.6.1",
"playwright>=1.52.0",
"pyright>=1.1.350",
"pytest-playwright>=0.7.0",
]I'll start by sourcing the virtual environment before running tests and checks.
root@8c33e558aa85:/workspace/scubaduck# source .venv/bin/activate
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll modify updateSelectedColumns to add "order_by" column, adjust collectParams, and add the Playwright test.
I'll check if select_value exists, then import it for the new test and patch.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# git status --short(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '430,455p' scubaduck/
static/js/view_settings.js
function updateSelectedColumns(type = graphTypeSel.value) {
const base = allColumns.filter(name => {
const cb = document.querySelector(`#column_groups input[value="${name}"]`);
if (!cb || !cb.checked) return false;
if (type === 'table' && isStringColumn(name)) return false;
return true;
});
if (type === 'table' || type === 'timeseries') {
selectedColumns = groupBy.chips.slice();
if (document.getElementById('show_hits').checked) selectedColumns.push('Hits
');
base.forEach(c => {
if (!selectedColumns.includes(c)) selectedColumns.push(c);
});
derivedColumns.forEach(dc => {
if (dc.include && !selectedColumns.includes(dc.name)) selectedColumns.push
(dc.name);
});
} else {
selectedColumns = base.slice();
derivedColumns.forEach(dc => {
if (dc.include) selectedColumns.push(dc.name);
});
}
columnValues[type] = selectedColumns.slice();
updateColumnsTabCount();
}
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll set columnValues first, then add order_by to selectedColumns, ensuring the checkbox behavior.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# apply_patch<<'PATCH'
> *** Begin Patch
> *** Update File: scubaduck/static/js/view_settings.js
> @@
> columnValues[type] = selectedColumns.slice();
> + const orderCol = document.getElementById('order_by').value;
> + if (orderCol && !selectedColumns.includes(orderCol)) {
> + selectedColumns.push(orderCol);
> + }
> updateColumnsTabCount();
> }
> *** End Patch
> PATCH
Success. Updated the following files:
M scubaduck/static/js/view_settings.js
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll run ruff format on the modified file to make sure everything's clear.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# ruff format scubaduck/static
/js/view_settings.js > /tmp/format.log && tail -n 20 /tmp/format.log
error: Failed to parse scubaduck/static/js/view_settings.js:1:1: Expected a stat
ement
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#Ruff only supports Python, so I'll run ruff check for the repo but only for Python files.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# ruff check > /tmp/ruff.log &
& tail -n 20 /tmp/ruff.log
All checks passed!
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll run pyright next since there are no Python files to format with ruff.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# pyright > /tmp/pyright.log &
& tail -n 20 /tmp/pyright.log0 errors, 0 warnings, 0 informations
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I’ll create a fresh test file, tests/test_web.py, to add the new test.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# cat <<'EOF' > tests/test_web
.py
> from typing import Any
> from tests.web_utils import select_value
>
> def test_order_by_implict_column(page: Any, server_url: str) -> None:
> page.goto(server_url)
> page.wait_for_selector("#order_by option", state="attached")
> page.click("text=Columns")
> page.wait_for_selector("#column_groups input", state="attached")
> page.uncheck("#column_groups input[value='timestamp']")
> page.click("text=View Settings")
> page.fill("#start", "2024-01-01 00:00:00")
> page.fill("#end", "2024-01-02 00:00:00")
> select_value(page, "#order_by", "timestamp")
> 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")
> headers = page.locator("#results th").all_inner_texts()
> assert "timestamp" in headers
> assert len(data["rows"][0]) == 4
> EOF
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I misspelled "implicit" as "implict." I'll fix that now.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '1,20p' tests/test_we
b.py
from typing import Any
from tests.web_utils import select_value
def test_order_by_implict_column(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
page.uncheck("#column_groups input[value='timestamp']")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
select_value(page, "#order_by", "timestamp")
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")
headers = page.locator("#results th").all_inner_texts()
assert "timestamp" in headers(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '20,40p' tests/test_w
eb.py
assert "timestamp" in headers
assert len(data["rows"][0]) == 4
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll correct the spelling of the function name from 'implicit' to the correct one.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '3,5p' tests/test_web
.py
def test_order_by_implict_column(page: Any, server_url: str) -> None:
page.goto(server_url)(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '1,20p' tests/test_we
b.py
from typing import Any
from tests.web_utils import select_value
def test_order_by_implict_column(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
page.uncheck("#column_groups input[value='timestamp']")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
select_value(page, "#order_by", "timestamp")
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")
headers = page.locator("#results th").all_inner_texts()
assert "timestamp" in headers
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll update the function's name to be more suitable for its purpose.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '5,6p' tests/test_web
.py
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '1,5p' tests/test_web
.py
from typing import Any
from tests.web_utils import select_value
def test_order_by_implict_column(page: Any, server_url: str) -> None:
page.goto(server_url)
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'm renaming the test to "test_order_by_implicit_column".
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# apply_patch<<'PATCH'
> *** Begin Patch
> *** Update File: tests/test_web.py
> @@
> -from typing import Any
> -from tests.web_utils import select_value
> -
> -def test_order_by_implict_column(page: Any, server_url: str) -> None:
> +from typing import Any
> +from tests.web_utils import select_value
> +
> +
> +def test_order_by_implicit_column(page: Any, server_url: str) -> None:
> *** End Patch
> PATCH
Success. Updated the following files:
M tests/test_web.py
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll take another look at the file.
b.py
from typing import Any
from tests.web_utils import select_value
def test_order_by_implicit_column(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
page.uncheck("#column_groups input[value='timestamp']")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
select_value(page, "#order_by", "timestamp")
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")
headers = page.locator("#results th").all_inner_texts()(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '20,40p' tests/test_w
eb.py
headers = page.locator("#results th").all_inner_texts()
assert "timestamp" in headers
assert len(data["rows"][0]) == 4
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll ensure the "timestamp" checkbox remains unchecked after the query results are loaded.
> *** Begin Patch
> *** Update File: tests/test_web.py
> @@
> data = page.evaluate("window.lastResults")
> headers = page.locator("#results th").all_inner_texts()
> assert "timestamp" in headers
> assert len(data["rows"][0]) == 4
> + page.click("text=Columns")
> + page.wait_for_selector("#column_groups input", state="attached")
> + assert not page.is_checked("#column_groups input[value='timestamp']")
> *** End Patch
> PATCH
Success. Updated the following files:
M tests/test_web.py(scubaduck) root@8c33e558aa85:/workspace/scubaduck# sed -n '1,40p' tests/test_we
b.py
from typing import Any
from tests.web_utils import select_value
def test_order_by_implicit_column(page: Any, server_url: str) -> None:
page.goto(server_url)
page.wait_for_selector("#order_by option", state="attached")
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
page.uncheck("#column_groups input[value='timestamp']")
page.click("text=View Settings")
page.fill("#start", "2024-01-01 00:00:00")
page.fill("#end", "2024-01-02 00:00:00")
select_value(page, "#order_by", "timestamp")
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")
headers = page.locator("#results th").all_inner_texts()
assert "timestamp" in headers
assert len(data["rows"][0]) == 4
page.click("text=Columns")
page.wait_for_selector("#column_groups input", state="attached")
assert not page.is_checked("#column_groups input[value='timestamp']")y > /tmp/format.log && tail -n 20 /tmp/format.log
1 file left unchanged(scubaduck) root@8c33e558aa85:/workspace/scubaduck# ruff check > /tmp/ruff.log &
& tail -n 20 /tmp/ruff.log
All checks passed!(scubaduck) root@8c33e558aa85:/workspace/scubaduck# pyright > /tmp/pyright.log &
& tail -n 20 /tmp/pyright.log0 errors, 0 warnings, 0 informations(scubaduck) root@8c33e558aa85:/workspace/scubaduck# pytest -q > /tmp/pytest.log
&& tail -n 20 /tmp/pytest.logbringing up nodes...
bringing up nodes...
........................................................................ [ 66%]
..................................... [100%]
109 passed in 14.62s
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#Tests passed—time to check the overall status.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# git status --short
M scubaduck/static/js/view_settings.js
?? tests/test_web.py
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I’ll stage the test changes and commit them now.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# git add scubaduck/static/js/
view_settings.js tests/test_web.py(scubaduck) root@8c33e558aa85:/workspace/scubaduck# git commit -m "feat(web): sh
ow order column when used" && git status --short
[work e76be7e] feat(web): show order column when used
2 files changed, 29 insertions(+)
create mode 100644 tests/test_web.py(scubaduck) root@8c33e558aa85:/workspace/scubaduck# git status --short
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I’ll pull citations related to the patch for the order column in view_settings.js.
iew_settings.js | sed -n '430,460p'
430
431 function updateSelectedColumns(type = graphTypeSel.value) {
432 const base = allColumns.filter(name => {
433 const cb = document.querySelector(`#column_groups input[value="${nam
e}"]`);
434 if (!cb || !cb.checked) return false;
435 if (type === 'table' && isStringColumn(name)) return false;
436 return true;
437 });
438 if (type === 'table' || type === 'timeseries') {
439 selectedColumns = groupBy.chips.slice();
440 if (document.getElementById('show_hits').checked) selectedColumns.pu
sh('Hits');
441 base.forEach(c => {
442 if (!selectedColumns.includes(c)) selectedColumns.push(c);
443 });
444 derivedColumns.forEach(dc => {
445 if (dc.include && !selectedColumns.includes(dc.name)) selectedColu
mns.push(dc.name);
446 });
447 } else {
448 selectedColumns = base.slice();
449 derivedColumns.forEach(dc => {
450 if (dc.include) selectedColumns.push(dc.name);
451 });
452 }
453 columnValues[type] = selectedColumns.slice();
454 const orderCol = document.getElementById('order_by').value;
455 if (orderCol && !selectedColumns.includes(orderCol)) {
456 selectedColumns.push(orderCol);
457 }
458 updateColumnsTabCount();
459 }
460
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#It's time to dive into the test_web.py file. Let's see what's inside.
(scubaduck) root@8c33e558aa85:/workspace/scubaduck# nl -ba tests/test_web.py
1 from typing import Any
2 from tests.web_utils import select_value
3
4
5 def test_order_by_implicit_column(page: Any, server_url: str) -> None:
6 page.goto(server_url)
7 page.wait_for_selector("#order_by option", state="attached")
8 page.click("text=Columns")
9 page.wait_for_selector("#column_groups input", state="attached")
10 page.uncheck("#column_groups input[value='timestamp']")
11 page.click("text=View Settings")
12 page.fill("#start", "2024-01-01 00:00:00")
13 page.fill("#end", "2024-01-02 00:00:00")
14 select_value(page, "#order_by", "timestamp")
15 page.fill("#limit", "10")
16 page.evaluate("window.lastResults = undefined")
17 page.click("text=Dive")
18 page.wait_for_function("window.lastResults !== undefined")
19 data = page.evaluate("window.lastResults")
20 headers = page.locator("#results th").all_inner_texts()
21 assert "timestamp" in headers
22 assert len(data["rows"][0]) == 4
23 page.click("text=Columns")
24 page.wait_for_selector("#column_groups input", state="attached")
25 assert not page.is_checked("#column_groups input[value='timestamp']"
)
(scubaduck) root@8c33e558aa85:/workspace/scubaduck#I'll write the PR message, mentioning the original user prompt and test results.