Task ID: task_e_682fcb235f84832384f2d27224c578b9
Configuring language runtimes...
+ rm -- /tmp/TPi7ym-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 ruff (11.0MiB)
Downloading duckdb (19.3MiB)
Downloading pyright (5.3MiB)
Downloading playwright (43.1MiB)
Downloading ruff
Built scubaduck @ file:///workspace/scubaduck
Downloading duckdb
Downloading playwright
Downloading pyright
Prepared 33 packages in 1.50s
Installed 33 packages in 89ms
+ 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/TPi7ym-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% 0.0s167.7 MiB [] 0% 43.8s167.7 MiB [] 0% 52.9s167.7 MiB [] 0% 40.7s167.7 MiB [] 0% 32.8s167.7 MiB [] 0% 25.2s167.7 MiB [] 0% 19.6s167.7 MiB [] 0% 14.4s167.7 MiB [] 1% 10.1s167.7 MiB [] 2% 7.2s167.7 MiB [] 3% 5.2s167.7 MiB [] 4% 4.2s167.7 MiB [] 4% 4.1s167.7 MiB [] 5% 3.5s167.7 MiB [] 6% 3.2s167.7 MiB [] 8% 2.7s167.7 MiB [] 9% 2.6s167.7 MiB [] 10% 2.4s167.7 MiB [] 12% 2.2s167.7 MiB [] 13% 2.1s167.7 MiB [] 14% 2.0s167.7 MiB [] 15% 1.9s167.7 MiB [] 16% 1.8s167.7 MiB [] 18% 1.7s167.7 MiB [] 19% 1.6s167.7 MiB [] 20% 1.6s167.7 MiB [] 21% 1.5s167.7 MiB [] 23% 1.5s167.7 MiB [] 24% 1.5s167.7 MiB [] 25% 1.4s167.7 MiB [] 27% 1.4s167.7 MiB [] 28% 1.3s167.7 MiB [] 29% 1.3s167.7 MiB [] 30% 1.3s167.7 MiB [] 32% 1.2s167.7 MiB [] 33% 1.2s167.7 MiB [] 34% 1.2s167.7 MiB [] 35% 1.1s167.7 MiB [] 36% 1.1s167.7 MiB [] 37% 1.1s167.7 MiB [] 39% 1.1s167.7 MiB [] 41% 1.0s167.7 MiB [] 43% 1.0s167.7 MiB [] 44% 0.9s167.7 MiB [] 45% 0.9s167.7 MiB [] 47% 0.9s167.7 MiB [] 48% 0.9s167.7 MiB [] 50% 0.8s167.7 MiB [] 51% 0.8s167.7 MiB [] 53% 0.8s167.7 MiB [] 54% 0.8s167.7 MiB [] 55% 0.7s167.7 MiB [] 56% 0.7s167.7 MiB [] 58% 0.7s167.7 MiB [] 59% 0.7s167.7 MiB [] 60% 0.6s167.7 MiB [] 61% 0.6s167.7 MiB [] 63% 0.6s167.7 MiB [] 64% 0.6s167.7 MiB [] 66% 0.5s167.7 MiB [] 67% 0.5s167.7 MiB [] 68% 0.5s167.7 MiB [] 69% 0.5s167.7 MiB [] 70% 0.5s167.7 MiB [] 71% 0.5s167.7 MiB [] 72% 0.5s167.7 MiB [] 73% 0.4s167.7 MiB [] 76% 0.4s167.7 MiB [] 78% 0.3s167.7 MiB [] 79% 0.3s167.7 MiB [] 80% 0.3s167.7 MiB [] 81% 0.3s167.7 MiB [] 82% 0.3s167.7 MiB [] 83% 0.3s167.7 MiB [] 85% 0.2s167.7 MiB [] 86% 0.2s167.7 MiB [] 87% 0.2s167.7 MiB [] 88% 0.2s167.7 MiB [] 89% 0.2s167.7 MiB [] 91% 0.1s167.7 MiB [] 92% 0.1s167.7 MiB [] 93% 0.1s167.7 MiB [] 94% 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% 0.6s2.3 MiB [] 5% 0.7s2.3 MiB [] 10% 0.5s2.3 MiB [] 14% 0.4s2.3 MiB [] 24% 0.3s2.3 MiB [] 38% 0.2s2.3 MiB [] 59% 0.1s2.3 MiB [] 85% 0.0s2.3 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 [] 1% 1.0s101.4 MiB [] 4% 0.8s101.4 MiB [] 6% 0.7s101.4 MiB [] 8% 0.7s101.4 MiB [] 10% 0.8s101.4 MiB [] 12% 0.7s101.4 MiB [] 14% 0.7s101.4 MiB [] 16% 0.7s101.4 MiB [] 18% 0.7s101.4 MiB [] 19% 0.7s101.4 MiB [] 22% 0.6s101.4 MiB [] 23% 0.6s101.4 MiB [] 26% 0.6s101.4 MiB [] 27% 0.6s101.4 MiB [] 29% 0.6s101.4 MiB [] 31% 0.6s101.4 MiB [] 33% 0.6s101.4 MiB [] 36% 0.5s101.4 MiB [] 37% 0.5s101.4 MiB [] 39% 0.5s101.4 MiB [] 40% 0.5s101.4 MiB [] 42% 0.5s101.4 MiB [] 45% 0.4s101.4 MiB [] 48% 0.4s101.4 MiB [] 50% 0.4s101.4 MiB [] 51% 0.4s101.4 MiB [] 53% 0.4s101.4 MiB [] 56% 0.4s101.4 MiB [] 58% 0.3s101.4 MiB [] 60% 0.3s101.4 MiB [] 62% 0.3s101.4 MiB [] 64% 0.3s101.4 MiB [] 66% 0.3s101.4 MiB [] 68% 0.3s101.4 MiB [] 69% 0.2s101.4 MiB [] 72% 0.2s101.4 MiB [] 74% 0.2s101.4 MiB [] 75% 0.2s101.4 MiB [] 76% 0.2s101.4 MiB [] 78% 0.2s101.4 MiB [] 80% 0.2s101.4 MiB [] 82% 0.1s101.4 MiB [] 85% 0.1s101.4 MiB [] 86% 0.1s101.4 MiB [] 88% 0.1s101.4 MiB [] 92% 0.1s101.4 MiB [] 94% 0.0s101.4 MiB [] 95% 0.0s101.4 MiB [] 98% 0.0s101.4 MiB [] 100% 0.0s
Chromium Headless Shell 136.0.7103.25 (playwright build v1169) downloaded to /root/.cache/ms-playwright/chromium_headless_shell-1169
++ echo 'source .venv/bin/activate'
I need to check the AGENTS.md file at the repo's root directory.
bash: .venv/bin/activate: No such file or directory
root@68312fca34e0:/workspace# ls
scubaduck
root@68312fca34e0:/workspace# cd scubaduck
root@68312fca34e0:/workspace/scubaduck# ls
AGENTS.md codex_setup.sh scubaduck tests
README.md pyproject.toml stubs uv.lock
root@68312fca34e0:/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.py
root@68312fca34e0:/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'll check for the '_create_test_database' in the code using grep
.
root@68312fca34e0:/workspace/scubaduck# grep -R "_create_test_database" -n
scubaduck/server.py:81:def _create_test_database() -> duckdb.DuckDBPyConnection:
scubaduck/server.py:349: con = _create_test_database()
root@68312fca34e0:/workspace/scubaduck# sed -n '1,150p' 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 TEXT, val REAL, name TE
XT, flag BOOLEAN)"
)
con.execute("INSERT INTO events VALUES (1, '2024-01-01 00:00:00', 1.5, 'alic
e', 1)")
con.execute("INSERT INTO events VALUES (2, '2024-01-01 01:00:00', 2.0, 'bob'
, 0)")
con.execute('CREATE TABLE extra (ts TEXT, "desc" TEXT, num INTEGER)')
con.execute("INSERT INTO extra VALUES ('2024-01-01 00:00:00', 'x', 1)")
con.execute("INSERT INTO extra VALUES ('2024-01-01 01:00:00', '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,
I’ll keep exploring to see how _create_test_database is being used in the code.
root@68312fca34e0:/workspace/scubaduck# grep -n "_create_test_database" -n scuba
duck/server.py
81:def _create_test_database() -> duckdb.DuckDBPyConnection:
349: con = _create_test_database()
root@68312fca34e0:/workspace/scubaduck# sed -n '340,360p' scubaduck/server.py
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:
I need to modify _create_test_database to store timestamps as Unix epoch time instead of TEXT.
root@68312fca34e0:/workspace/scubaduck# grep -n "create_test_database" -R .
./scubaduck/server.py:81:def _create_test_database() -> duckdb.DuckDBPyConnectio
n:
./scubaduck/server.py:349: con = _create_test_database()
I'll search for timestamp usage and remember to review any associated tests.
root@68312fca34e0:/workspace/scubaduck# grep -n "ts TEXT" -R tests
root@68312fca34e0:/workspace/scubaduck# grep -n "ts" -R tests | head
tests/test_server.py:16: "table": "events",
tests/test_server.py:49: "table": "events",
tests/test_server.py:73: "table": "events",
tests/test_server.py:100: "table": "events",
tests/test_server.py:147: assert all(r[3].startswith("a") for r in rows)
tests/test_server.py:159: "table": "events",
tests/test_server.py:171: csv_file = tmp_path / "events.csv"
tests/test_server.py:174: sqlite_file = tmp_path / "events.sqlite"
tests/test_server.py:179: "CREATE TABLE events (timestamp TEXT, event TEX
T, value INTEGER, user TEXT)"
tests/test_server.py:184: ts, ev, val, user = line.strip().split(",")
I’ll check the top of tests/test_server.py to understand how _create_test_database is used.
root@68312fca34e0:/workspace/scubaduck# sed -n '1,220p' tests/test_server.py
from __future__ import annotations
import json
from pathlib import Path
from typing import Any, cast
import duckdb
from scubaduck import server
import pytest
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"]) == 4
def _make_payload() -> dict[str, object]:
return {
"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": [],
}
def test_database_types(tmp_path: Path) -> None:
csv_file = tmp_path / "events.csv"
csv_file.write_text(Path("scubaduck/sample.csv").read_text())
sqlite_file = tmp_path / "events.sqlite"
import sqlite3
conn = sqlite3.connect(sqlite_file)
conn.execute(
"CREATE TABLE events (timestamp TEXT, event TEXT, value INTEGER, user TE
XT)"
)
with open(csv_file) as f:
next(f)
for line in f:
ts, ev, val, user = line.strip().split(",")
conn.execute(
"INSERT INTO events VALUES (?, ?, ?, ?)", (ts, ev, int(val), use
r)
)
conn.commit()
conn.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcce
ssIssue]
duckdb_file = tmp_path / "events.duckdb"
con = duckdb.connect(duckdb_file)
con.execute(
f"CREATE TABLE events AS SELECT * FROM read_csv_auto('{csv_file.as_posix
()}')"
)
con.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcces
sIssue]
for db in (csv_file, sqlite_file, duckdb_file):
app = server.create_app(db)
client = app.test_client()
payload = _make_payload()
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/js
on"
)
rows = rv.get_json()["rows"]
assert len(rows) == 3
def test_sqlite_longvarchar(tmp_path: Path) -> None:
sqlite_file = tmp_path / "events.sqlite"
import sqlite3
conn = sqlite3.connect(sqlite_file)
conn.execute(
"CREATE TABLE events (timestamp TEXT, url LONGVARCHAR, title VARCHAR(10)
)"
)
conn.execute(
"INSERT INTO events VALUES ('2024-01-01 00:00:00', 'https://a.com', 'Hom
e')"
)
conn.commit()
I'm checking the rest of the tests to see if they depend on a TS string.
root@68312fca34e0:/workspace/scubaduck# sed -n '220,440p' tests/test_server.py
conn.commit()
conn.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcce
ssIssue]
app = server.create_app(sqlite_file)
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-01 01:00:00",
"order_by": "timestamp",
"columns": ["timestamp", "url", "title"],
}
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] == "https://a.com"
def test_sqlite_bigint(tmp_path: Path) -> None:
sqlite_file = tmp_path / "big.sqlite"
import sqlite3
conn = sqlite3.connect(sqlite_file)
conn.execute("CREATE TABLE events (timestamp TEXT, value INTEGER)")
big_value = 13385262862605259
conn.execute(
"INSERT INTO events VALUES ('2024-01-01 00:00:00', ?)",
(big_value,),
)
conn.commit()
conn.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcce
ssIssue]
app = server.create_app(sqlite_file)
client = app.test_client()
payload = {
"table": "events",
"order_by": "timestamp",
"columns": ["timestamp", "value"],
}
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] == big_value
def test_sqlite_boolean_aggregation(tmp_path: Path) -> None:
sqlite_file = tmp_path / "bool.sqlite"
import sqlite3
conn = sqlite3.connect(sqlite_file)
conn.execute("CREATE TABLE events (timestamp TEXT, flag BOOLEAN)")
conn.execute("INSERT INTO events VALUES ('2024-01-01 00:00:00', 1)")
conn.execute("INSERT INTO events VALUES ('2024-01-01 00:30:00', 0)")
conn.commit()
conn.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcce
ssIssue]
app = server.create_app(sqlite_file)
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-02 00:00:00",
"graph_type": "table",
"aggregate": "Avg",
"columns": ["flag"],
"show_hits": True,
}
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][0] == 2
assert data["rows"][0][1] == 0.5
def test_integer_time_column(tmp_path: Path) -> None:
csv_file = tmp_path / "events.csv"
csv_file.write_text("created,event\n1704067200,login\n1704070800,logout\n")
app = server.create_app(csv_file)
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-01 01:00:00",
"order_by": "created",
"columns": ["created", "event"],
"time_column": "created",
}
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
def test_integer_time_unit_ms(tmp_path: Path) -> None:
csv_file = tmp_path / "events.csv"
csv_file.write_text("created,event\n1704067200000,login\n1704070800000,logou
t\n")
app = server.create_app(csv_file)
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-01 01:00:00",
"order_by": "created",
"columns": ["created", "event"],
"time_column": "created",
"time_unit": "ms",
}
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
def test_timeseries_default_xaxis_uses_time_column(tmp_path: Path) -> None:
csv_file = tmp_path / "events.csv"
csv_file.write_text("created,event\n1704067200000,login\n1704070800000,logou
t\n")
app = server.create_app(csv_file)
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-01 01:00:00",
"graph_type": "timeseries",
"granularity": "1 hour",
"columns": ["event"],
"aggregate": "Count",
"time_column": "created",
"time_unit": "ms",
}
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
def test_integer_time_unit_us_default_start_end(tmp_path: Path) -> None:
csv_file = tmp_path / "events.csv"
csv_file.write_text(
"created,event\n1704067200000000,login\n1704070800000000,logout\n"
)
app = server.create_app(csv_file)
client = app.test_client()
payload = {
"table": "events",
"order_by": "created",
"columns": ["created", "event"],
"time_column": "created",
"time_unit": "us",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert data["start"] == "2024-01-01 00:00:00"
assert data["end"] == "2024-01-01 01:00:00"
assert len(data["rows"]) == 2
def test_sqlite_integer_time_unit_us(tmp_path: Path) -> None:
sqlite_file = tmp_path / "events.sqlite"
import sqlite3
conn = sqlite3.connect(sqlite_file)
conn.execute("CREATE TABLE visits (visit_time INTEGER, event TEXT)")
big_ts = 13384551652000000
conn.execute("INSERT INTO visits VALUES (?, ?)", (big_ts, "foo"))
conn.commit()
conn.close() # pyright: ignore[reportUnknownMemberType, reportAttributeAcce
ssIssue]
app = server.create_app(sqlite_file)
client = app.test_client()
payload = {
"table": "visits",
"start": "2394-02-20 00:00:00",
"end": "2394-02-21 00:00:00",
"order_by": "visit_time",
"columns": ["visit_time", "event"],
"time_column": "visit_time",
"time_unit": "us",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 1
def test_envvar_db(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
csv_file = tmp_path / "custom.csv"
csv_file.write_text("timestamp,event,value,user\n2024-01-01 00:00:00,login,5
,bob\n")
monkeypatch.setenv("SCUBADUCK_DB", str(csv_file))
app = server.create_app()
client = app.test_client()
payload = _make_payload()
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
rows = rv.get_json()["rows"]
assert len(rows) == 1
def test_envvar_db_missing(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> N
one:
missing = tmp_path / "missing.sqlite"
monkeypatch.setenv("SCUBADUCK_DB", str(missing))
with pytest.raises(FileNotFoundError):
server.create_app()
I'll need to scroll further to check the rest of the file beyond 440 lines.
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "user",
"limit": 10,
"columns": ["value"],
"group_by": ["user"],
"aggregate": "Sum",
"show_hits": True,
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
rows = rv.get_json()["rows"]
assert rows[0][0] == "alice"
assert rows[0][1] == 2
assert rows[0][2] == 40
def test_relative_time_query(monkeypatch: pytest.MonkeyPatch) -> None:
app = server.app
client = app.test_client()
from datetime import datetime
fixed_now = datetime(2024, 1, 2, 4, 0, 0)
class FixedDateTime(datetime):
@classmethod
def now(cls, tz=None): # type: ignore[override]
return fixed_now if tz is None else fixed_now.astimezone(tz)
monkeypatch.setattr(server, "datetime", FixedDateTime)
payload = {
"table": "events",
"start": "-1 hour",
"end": "now",
"order_by": "timestamp",
"limit": 100,
"columns": ["timestamp", "event", "value", "user"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 1
assert data["rows"][0][3] == "charlie"
def test_invalid_time_error() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"start": "nonsense",
"end": "now",
"order_by": "timestamp",
"limit": 10,
"columns": ["timestamp"],
"filters": [],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "error" in data
def test_query_error_returns_sql_and_traceback() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"columns": ["event"],
"group_by": ["user"],
"aggregate": "avg",
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "error" in data
def test_table_unknown_column_error() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"start": "2024-01-01 00:00:00",
"end": "2024-01-03 00:00:00",
"graph_type": "table",
"order_by": "timestamp",
"limit": 100,
"columns": ["user", "Hits", "value"],
"group_by": ["user"],
"aggregate": "Count",
"show_hits": True,
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 400
assert "Unknown column" in data["error"]
def test_samples_view_rejects_group_by() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"graph_type": "samples",
"group_by": ["user"],
"columns": ["timestamp"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
...
]
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",
"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_default_start_end_returned() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"order_by": "timestamp",
"limit": 5,
"columns": ["timestamp"],
}
rv = client.post(
"/api/query", data=json.dumps(payload), content_type="application/json"
)
data = rv.get_json()
assert rv.status_code == 200
assert data["start"] == "2024-01-01 00:00:00"
assert data["end"] == "2024-01-02 03:00:00"
def test_time_column_none_no_time_filter() -> None:
app = server.app
client = app.test_client()
payload = {
"table": "events",
"columns": ["timestamp", "event"],
"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 "start" not in data and "end" not in data
assert len(data["rows"]) == 4
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"
root@68312fca34e0:/workspace/scubaduck# sed -n '880,1760p' tests/test_server.py
The tests file ends around line 865. Now, I'll check the 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,charlie
I’ll check the server.py file, especially near the bottom, for the app variable setup.
root@68312fca34e0:/workspace/scubaduck# grep -n "app =" -n scubaduck/server.py
343: app = Flask(__name__, static_folder="static")
671:app = create_app()
I'll double-check create_app
again to confirm how the TEST
environment variable is handled.
root@68312fca34e0:/workspace/scubaduck# sed -n '660,720p' scubaduck/server.py
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)
I'll review the server file regarding _create_test_database and the SCUBADUCK_DB=TEST condition.
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 TEXT, val REAL, name TE
XT, flag BOOLEAN)"
)
con.execute("INSERT INTO events VALUES (1, '2024-01-01 00:00:00', 1.5, 'alic
e', 1)")
con.execute("INSERT INTO events VALUES (2, '2024-01-01 01:00:00', 2.0, 'bob'
, 0)")
con.execute('CREATE TABLE extra (ts TEXT, "desc" TEXT, num INTEGER)')
con.execute("INSERT INTO extra VALUES ('2024-01-01 00:00:00', 'x', 1)")
con.execute("INSERT INTO extra VALUES ('2024-01-01 01:00:00', '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
I need to modify _create_test_database to store timestamps as unix epoch integers in the events table. Only the 'events' table is affected, though. I'll adjust the test for 'extra' where necessary.
root@68312fca34e0:/workspace/scubaduck# grep -n "extra" -n tests/test_server.py
836: "table": "extra",
I was navigating around line 836 earlier to check details.
assert len(data["rows"]) == 4
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()
root@68312fca34e0:/workspace/scubaduck# sed -n '844,860p' tests/test_server.py
data = rv.get_json()
assert rv.status_code == 200
assert len(data["rows"]) == 2
assert data["rows"][0][1] == "x"
The timestamp should be stored as an integer in _create_test_database, considering user input.
16: "table": "events",
49: "table": "events",
73: "table": "events",
100: "table": "events",
147: assert all(r[3].startswith("a") for r in rows)
159: "table": "events",
171: csv_file = tmp_path / "events.csv"
174: sqlite_file = tmp_path / "events.sqlite"
179: "CREATE TABLE events (timestamp TEXT, event TEXT, value INTEGER, use
r TEXT)"
184: ts, ev, val, user = line.strip().split(",")
I'll search for "create_app("TEST")" or "SCUBADUCK_DB=TEST" to check test data usage.
root@68312fca34e0:/workspace/scubaduck# grep -n "create_app(" tests/test_server.
py
199: app = server.create_app(db)
223: app = server.create_app(sqlite_file)
254: app = server.create_app(sqlite_file)
280: app = server.create_app(sqlite_file)
303: app = server.create_app(csv_file)
324: app = server.create_app(csv_file)
346: app = server.create_app(csv_file)
372: app = server.create_app(csv_file)
402: app = server.create_app(sqlite_file)
425: app = server.create_app()
439: server.create_app()
833: app = server.create_app("TEST")
I'm checking calls to create_app, particularly where file names or environments are passed in.
root@68312fca34e0:/workspace/scubaduck# grep -n "170" -R scubaduck
I'll adjust _create_test_database, considering integer time units and any default table settings.
root@68312fca34e0:/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 check the contents of scubaduck/init.py next.
root@68312fca34e0:/workspace/scubaduck# ls scubaduck
__init__.py sample.csv server.py static
root@68312fca34e0:/workspace/scubaduck# cat scubaduck/__init__.py
def hello() -> str:
return "Hello from scubaduck!"
I’ll modify _create_test_database and check all tests relying on create_app("TEST"), like reserved_word_column.
root@68312fca34e0:/workspace/scubaduck# grep -n "TEST" -n tests/test_server.py
833: app = server.create_app("TEST")
It seems safest to change both events.ts
and extra.ts
to integer for consistency.
I'll change both events.ts
and extra.ts
to integer for consistency, despite the test.
Tests should be fine even if extra.ts
changes to integer. I'll double-check.
root@68312fca34e0:/workspace/scubaduck# sed -n '832,856p' tests/test_server.py
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"
I'll search again to check if _create_test_database is used outside the current context.
root@68312fca34e0:/workspace/scubaduck# grep -R "CREATE TABLE extra" -n
scubaduck/server.py:89: con.execute('CREATE TABLE extra (ts TEXT, "desc" TEXT
, num INTEGER)')
I'll modify _create_test_database to use "ts" as INTEGER and compute epoch times using Python.
root@68312fca34e0:/workspace/scubaduck# python3 - <<'EOF'
> import datetime
> print(int(datetime.datetime(2024,1,1,0,0).timestamp()))
> print(int(datetime.datetime(2024,1,1,1,0).timestamp()))
> EOF
1704067200
1704070800
I need to verify how create_app
handles integer timestamps and possibly update tests or handle time detection.
root@68312fca34e0:/workspace/scubaduck# grep -n "time_unit" -n scubaduck/server.
py
51: time_unit: str = "s"
211: xexpr = _time_expr(x_axis, column_types, params.time_unit)
294: time_expr = _time_expr(params.time_column, column_types, params.time
_unit)
459: time_unit=payload.get("time_unit", "s"),
472: if params.time_unit not in {"s", "ms", "us", "ns"}:
473: return jsonify({"error": "Invalid time_unit"}), 400
585: }.get(params.time_unit, 1)
595: f" with time_unit {params.time_unit}"
610: f" with time_unit {params.time_unit}"
I'm checking out functions around _time_expr to understand how different time units are handled.
root@68312fca34e0:/workspace/scubaduck# sed -n '204,232p' scubaduck/server.py
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:
I'm checking out the _time_expr function to understand its purpose.
root@68312fca34e0:/workspace/scubaduck# grep -n "def _time_expr" -n scubaduck/se
rver.py
166:def _time_expr(col: str, column_types: Dict[str, str] | None, unit: str) ->
str:
root@68312fca34e0:/workspace/scubaduck# sed -n '166,203p' scubaduck/server.py
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 qcol
def build_query(params: QueryParams, column_types: Dict[str, str] | None = None)
-> str:
I'm reassessing how create_app sets the default "time_column"; it should match the events table.
root@68312fca34e0:/workspace/scubaduck# grep -n "time_column" -n scubaduck/serve
r.py
50: time_column: str | None = "timestamp"
208: x_axis = params.x_axis or params.time_column
293: if params.time_column:
294: time_expr = _time_expr(params.time_column, column_types, params.time
_unit)
458: time_column=payload.get("time_column", "timestamp"),
469: if params.time_column and params.time_column not in column_types:
470: return jsonify({"error": "Invalid time_column"}), 400
491: params.x_axis = params.time_column
569: params.x_axis or params.time_column
571: axis = params.x_axis or params.time_column
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",
I’m verifying that time_column defaults to "timestamp" but can be set to "" or others.
I’ll confirm if the test covers integer ts and adjust if necessary before running checks.
root@68312fca34e0:/workspace/scubaduck# ls -a
. .git .gitignore AGENTS.md codex_setup.sh scubaduck tests
.. .github .venv README.md pyproject.toml stubs uv.lock
root@68312fca34e0:/workspace/scubaduck# source .venv/bin/activate
(scubaduck) root@68312fca34e0:/workspace/scubaduck#
I'll go ahead and apply the patch to implement the necessary modifications.
(scubaduck) root@68312fca34e0:/workspace/scubaduck# sed -n '78,96p' scubaduck/se
rver.py
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 TEXT, val REAL, name TE
XT, flag BOOLEAN)"
)
con.execute("INSERT INTO events VALUES (1, '2024-01-01 00:00:00', 1.5, 'alic
e', 1)")
con.execute("INSERT INTO events VALUES (2, '2024-01-01 01:00:00', 2.0, 'bob'
, 0)")
con.execute('CREATE TABLE extra (ts TEXT, "desc" TEXT, num INTEGER)')
con.execute("INSERT INTO extra VALUES ('2024-01-01 00:00:00', 'x', 1)")
con.execute("INSERT INTO extra VALUES ('2024-01-01 01:00:00', 'y', 2)")
return con
_REL_RE = re.compile(
r"([+-]?\d+(?:\.\d*)?)\s*(hour|hours|day|days|week|weeks|fortnight|fortnight
s)",
> *** Update File: scubaduck/server.py
> @@
> -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 TEXT, val REAL, name
TEXT, flag BOOLEAN)"
> - )
> - con.execute("INSERT INTO events VALUES (1, '2024-01-01 00:00:00', 1.5, 'a
lice', 1)")
> - con.execute("INSERT INTO events VALUES (2, '2024-01-01 01:00:00', 2.0, 'b
ob', 0)")
> - con.execute('CREATE TABLE extra (ts TEXT, "desc" TEXT, num INTEGER)')
> - con.execute("INSERT INTO extra VALUES ('2024-01-01 00:00:00', 'x', 1)")
> - con.execute("INSERT INTO extra VALUES ('2024-01-01 01:00:00', 'y', 2)")
> - 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, n
ame 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
> *** End Patch
> PATCH
Success. Updated the following files:
M scubaduck/server.py
(scubaduck) root@68312fca34e0:/workspace/scubaduck# ruff format scubaduck/server
.py
1 file left unchanged
(scubaduck) root@68312fca34e0:/workspace/scubaduck# ruff check scubaduck/server.
py
All checks passed!
(scubaduck) root@68312fca34e0:/workspace/scubaduck# pyright
0 errors, 0 warnings, 0 informations
(scubaduck) root@68312fca34e0:/workspace/scubaduck# pytest -q
bringing up nodes...
........................................................................ [ 67%]
................................... [100%]
107 passed in 14.51s
(scubaduck) root@68312fca34e0:/workspace/scubaduck#
Tests have passed, so I'll go ahead and commit the updates. Let’s check status.
(scubaduck) root@68312fca34e0:/workspace/scubaduck# git status --short
M scubaduck/server.py
(scubaduck) root@68312fca34e0:/workspace/scubaduck#
I'll go ahead and add the modified file to my staging area.
(scubaduck) root@68312fca34e0:/workspace/scubaduck# git add scubaduck/server.py
(scubaduck) root@68312fca34e0:/workspace/scubaduck# git commit -m "fix(server):
store test timestamps as epoch" && git status --short
[work 643ecd9] fix(server): store test timestamps as epoch
1 file changed, 6 insertions(+), 6 deletions(-)
(scubaduck) root@68312fca34e0:/workspace/scubaduck# git status --short
(scubaduck) root@68312fca34e0:/workspace/scubaduck#
I’ll look at the modified lines in server.py to gather the citations.
(scubaduck) root@68312fca34e0:/workspace/scubaduck# nl -ba scubaduck/server.py |
sed -n '80,96p'
80
81 def _create_test_database() -> duckdb.DuckDBPyConnection:
82 """Return a DuckDB connection with a small multi-table dataset."""
83 con = duckdb.connect()
84 con.execute(
85 "CREATE TABLE events (id INTEGER PRIMARY KEY, ts INTEGER, val RE
AL, name TEXT, flag BOOLEAN)"
86 )
87 con.execute("INSERT INTO events VALUES (1, 1704067200, 1.5, 'alice',
1)")
88 con.execute("INSERT INTO events VALUES (2, 1704070800, 2.0, 'bob', 0
)")
89 con.execute('CREATE TABLE extra (ts INTEGER, "desc" TEXT, num INTEGE
R)')
90 con.execute("INSERT INTO extra VALUES (1704067200, 'x', 1)")
91 con.execute("INSERT INTO extra VALUES (1704070800, 'y', 2)")
92 return con
93
94
95 _REL_RE = re.compile(
96 r"([+-]?\d+(?:\.\d*)?)\s*(hour|hours|day|days|week|weeks|fortnight|f
ortnights)",
(scubaduck) root@68312fca34e0:/workspace/scubaduck#
I'll summarize the changes in _create_test_database for the PR message.