Add pre-commit config and run it

yuvipanda · yuvipanda · commit 3ec8bf60ce46 · 2025-06-20T11:24:26.000-07:00
diff --git a/.gitignore b/.gitignore
@@ -174,9 +174,9 @@ cython_debug/
 .abstra/
 
 # Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
 #  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
 #  you could uncomment the following to ignore the enitre vscode folder
 # .vscode/
 
@@ -191,4 +191,4 @@ cython_debug/
 #  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
 #  refer to https://docs.cursor.com/context/ignore-files
 .cursorignore
-.cursorindexingignore
+.cursorindexingignore
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,49 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-case-conflict
+      - id: check-ast
+      - id: check-docstring-first
+      - id: check-executables-have-shebangs
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-json
+      - id: check-toml
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/jsh9/pydoclint
+    rev: 0.5.6
+    hooks:
+      - id: pydoclint
+  - repo: https://github.com/psf/black
+    rev: 24.8.0
+    hooks:
+      - id: black
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+  - repo: https://github.com/PyCQA/flake8
+    rev: "7.1.1"
+    hooks:
+      - id: flake8
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.3.1
+    hooks:
+    - id: autoflake
+      args: [--remove-all-unused-imports, --in-place]
+  - repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: 0.29.1
+    hooks:
+      - id: check-github-workflows
+      - id: check-readthedocs
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.17
+    hooks:
+      - id: mdformat
+        additional_dependencies:
+          [mdformat-gfm, mdformat-frontmatter, mdformat-footnote]
diff --git a/README.md b/README.md
@@ -18,4 +18,4 @@ Successor to [hubtraf](https://github.com/yuvipanda/hubtraf).
 - Support spawning on hubs with profile lists.
 - Support passing on to [playwright-python](https://playwright.dev/python/docs/intro) after the
   server has been started, so we can more accurately test user workflows directly.
-- Output telemetry data in a fashion that can be easily graphed.
+- Output telemetry data in a fashion that can be easily graphed.
diff --git a/simulate.py b/simulate.py
@@ -1,68 +1,83 @@
 import argparse
 import asyncio
-from functools import partial
+import json
+import os
 import secrets
-import time
-import aiometer
+from dataclasses import dataclass
 from datetime import datetime
-from typing import List, override
+from functools import partial
+from typing import List
+
 import aiohttp
-import os
-import json
+import aiometer
+from playwright.async_api import Browser, async_playwright
 from yarl import URL
-from dataclasses import dataclass
-from playwright.async_api import async_playwright, Browser
 
 
 @dataclass
 class HubAccess:
     """
     Information needed to talk to a hub
     """
+
     url: URL
     token: str
 
+
 @dataclass
 class Server:
     """
     Represents a user server
     """
+
     servername: str
     username: str
     hub_access: HubAccess
 
+
 @dataclass
 class RunningServer(Server):
     """
     Represents a running user server
     """
+
     start_request_time: datetime
     start_completion_time: datetime
     server_url: URL
     startup_events: List[dict]
 
+
 @dataclass
 class FailedServer(Server):
     """
     Represents a user server that failed to start
     """
+
     start_request_time: datetime
     start_failure_time: datetime
     startup_events: List[dict]
 
 
-async def load_nbgitpuller_url(browser: Browser, server: RunningServer, token: str, nbgitpuller_url: URL, screenshot_name: str):
+async def load_nbgitpuller_url(
+    browser: Browser,
+    server: RunningServer,
+    token: str,
+    nbgitpuller_url: URL,
+    screenshot_name: str,
+):
     print(f"visiting {server.server_url}")
-    nbgitpuller_url = nbgitpuller_url.extend_query({
-        'targetpath': secrets.token_urlsafe(8)
-    })
-    target_url = (server.server_url / nbgitpuller_url.path).with_query(nbgitpuller_url.query)
+    nbgitpuller_url = nbgitpuller_url.extend_query(
+        {"targetpath": secrets.token_urlsafe(8)}
+    )
+    target_url = (server.server_url / nbgitpuller_url.path).with_query(
+        nbgitpuller_url.query
+    )
     await_url = server.server_url / target_url.query.get("urlpath", "/lab").rstrip("/")
     start_time = datetime.now()
 
-    context = await browser.new_context(extra_http_headers={
-        "Authorization": f"token {token}"
-    })
+    context = await browser.new_context(
+        extra_http_headers={"Authorization": f"token {token}"}
+    )
     page = await context.new_page()
     await page.goto(str(target_url))
     await page.wait_for_url(str(await_url), timeout=120 * 10 * 1000)
@@ -72,28 +87,35 @@ async def load_nbgitpuller_url(browser: Browser, server: RunningServer, token: s
     print(f"{server.server_url} completed test in {duration}")
 
 
-
-async def start_named_server(session: aiohttp.ClientSession, server: Server) -> RunningServer | None:
+async def start_named_server(
+    session: aiohttp.ClientSession, server: Server
+) -> RunningServer | None:
     """
     Try to start a named server as defined
 
     """
-    headers = {
-        "Authorization": f"token {server.hub_access.token}"
-    }
-    server_api_url = server.hub_access.url / "hub/api/users" / server.username / "servers" / server.servername
+    headers = {"Authorization": f"token {server.hub_access.token}"}
+    server_api_url = (
+        server.hub_access.url
+        / "hub/api/users"
+        / server.username
+        / "servers"
+        / server.servername
+    )
     events = []
     async with session.post(server_api_url, headers=headers) as resp:
         start_time = datetime.now()
         if resp.status == 202:
             # we are awaiting start, let's look for events
             print(f"server {server.servername} waiting to start")
-            async with session.get(server_api_url / "progress", headers=headers) as progress_resp:
+            async with session.get(
+                server_api_url / "progress", headers=headers
+            ) as progress_resp:
                 async for line in progress_resp.content:
-                    if line.decode().strip() == '':
+                    if line.decode().strip() == "":
                         # Empty line, just continue
                         continue
-                    progress_event = json.loads(line.decode().strip()[len("data: "):])
+                    progress_event = json.loads(line.decode().strip()[len("data: ") :])
                     events.append(progress_event)
                     if progress_event.get("ready") == True:
                         print(progress_event)
@@ -104,7 +126,9 @@ async def start_named_server(session: aiohttp.ClientSession, server: Server) ->
                             start_request_time=start_time,
                             start_completion_time=datetime.now(),
                             startup_events=events,
-                            server_url=URL(server.hub_access.url / progress_event['url'][1:]) # Trim leading slashG
+                            server_url=URL(
+                                server.hub_access.url / progress_event["url"][1:]
+                            ),  # Trim leading slashG
                         )
         elif resp.status == 201:
             # Means the server is immediately ready, and i don't want to deal with that yet
@@ -114,11 +138,23 @@ async def start_named_server(session: aiohttp.ClientSession, server: Server) ->
             resp.raise_for_status()
 
 
-async def payload(session: aiohttp.ClientSession, browser: Browser,  auth_token: str, nbgitpuller_url: URL, server: Server):
+async def payload(
+    session: aiohttp.ClientSession,
+    browser: Browser,
+    auth_token: str,
+    nbgitpuller_url: URL,
+    server: Server,
+):
     started_server = await start_named_server(session, server)
     match started_server:
         case RunningServer():
-            await load_nbgitpuller_url(browser, started_server, auth_token, nbgitpuller_url, server.servername + ".png")
+            await load_nbgitpuller_url(
+                browser,
+                started_server,
+                auth_token,
+                nbgitpuller_url,
+                server.servername + ".png",
+            )
         case _:
             print("Server startup failed")
 
@@ -128,9 +164,16 @@ async def main():
     argparser.add_argument("hub_url", help="Full URL to the JupyterHub to test against")
     argparser.add_argument("username", help="Name of the user")
     argparser.add_argument("servers_count", type=int, help="Number of servers to start")
-    argparser.add_argument("--max-concurrency", type=int, default=30, help="Max Numbers of Servers to start at the same time")
+    argparser.add_argument(
+        "--max-concurrency",
+        type=int,
+        default=30,
+        help="Max Numbers of Servers to start at the same time",
+    )
     # nbgitpuller_url = URL("git-pull?repo=https%3A%2F%2Fkernel.googlesource.com%2Fpub%2Fscm%2Flinux%2Fkernel%2Fgit%2Ftorvalds%2Flinux.git&urlpath=lab&branch=master")
-    nbgitpuller_url = URL("git-pull?repo=https%3A%2F%2Fgithub.com%2Fspara%2Fcloud-101-geolab&urlpath=lab%2Ftree%2Fcloud-101-geolab%2F&branch=main")
+    nbgitpuller_url = URL(
+        "git-pull?repo=https%3A%2F%2Fgithub.com%2Fspara%2Fcloud-101-geolab&urlpath=lab%2Ftree%2Fcloud-101-geolab%2F&branch=main"
+    )
 
     args = argparser.parse_args()
 
@@ -140,13 +183,20 @@ async def main():
     async with async_playwright() as p:
         browser = await p.firefox.launch(headless=False)
         async with aiohttp.ClientSession() as session:
-            servers_to_start = [Server(f"perf-{i}", args.username, HubAccess(hub_url, token)) for i in range(args.servers_count)]
+            servers_to_start = [
+                Server(f"perf-{i}", args.username, HubAccess(hub_url, token))
+                for i in range(args.servers_count)
+            ]
             await aiometer.run_all(
-                [partial(payload, session, browser, token, nbgitpuller_url, server) for server in servers_to_start],
-                max_at_once=args.max_concurrency
+                [
+                    partial(payload, session, browser, token, nbgitpuller_url, server)
+                    for server in servers_to_start
+                ],
+                max_at_once=args.max_concurrency,
             )
 
         await browser.close()
 
+
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main())
