Compare commits

..
Author SHA1 Message Date
Typosaurus 63366bb240 ticket #93 attempt 1
DevPlace CI / test (pull_request) Failing after 11s
2026-07-23 02:03:12 +00:00
Typosaurus a55d12696a ticket #93 attempt 1 2026-07-23 01:33:37 +00:00
6 changed files with 115 additions and 126 deletions
File diff suppressed because one or more lines are too long
-5
View File
@@ -12,7 +12,6 @@ from fastapi import FastAPI, Request
from fastapi.responses import HTMLResponse, RedirectResponse
from fastapi.staticfiles import StaticFiles
from fastapi.exceptions import RequestValidationError
from starlette.middleware.gzip import GZipMiddleware
from devplacepy.config import (
STATIC_DIR,
STATIC_VERSION,
@@ -610,10 +609,6 @@ async def response_timing(request: Request, call_next):
response.headers["X-Response-Time"] = f"{(time.perf_counter() - start) * 1000:.1f}ms"
return response
app.add_middleware(GZipMiddleware, minimum_size=512, compresslevel=5)
_home_cache = TTLCache(ttl=int(os.environ.get("DEVPLACE_HOME_CACHE_TTL", "60")), max_size=4)
+15 -18
View File
@@ -22,8 +22,6 @@ from .pdf import MAX_PDF_BYTES, extract_pdf_text, is_pdf
logger = logging.getLogger(__name__)
_pw_lock = asyncio.Lock()
RSEARCH_URL = "https://rsearch.app.molodetz.nl"
RSEARCH_TIMEOUT_SECONDS = 45.0
FETCH_TIMEOUT_SECONDS = 20.0
@@ -174,7 +172,13 @@ async def _render_with_playwright(
) -> tuple[str, str, int, list[tuple[str, str]]]:
from playwright.async_api import async_playwright
async def _render(browser) -> tuple[str, str, int, list[tuple[str, str]]]:
own_browser = browser is None
if own_browser:
pw = await async_playwright().__aenter__()
browser = await pw.chromium.launch(
headless=True, args=["--no-sandbox", "--disable-dev-shm-usage"]
)
try:
context = await browser.new_context(user_agent=USER_AGENT)
page = await context.new_page()
response = await page.goto(url, wait_until="load", timeout=30000)
@@ -185,18 +189,10 @@ async def _render_with_playwright(
await context.close()
extracted = extract_html(content, base_url=url)
return extracted.title, extracted.text, status, extracted.links
if browser is None:
async with async_playwright() as pw:
browser = await pw.chromium.launch(
headless=True, args=["--no-sandbox", "--disable-dev-shm-usage"]
)
try:
return await _render(browser)
finally:
if own_browser:
await browser.close()
else:
return await _render(browser)
await pw.__aexit__(None, None, None)
async def fetch_page(url: str, depth: int, browser=None) -> CrawledPage | None:
@@ -246,12 +242,8 @@ async def fetch_page(url: str, depth: int, browser=None) -> CrawledPage | None:
except (LookupError, ValueError) as exc:
logger.info("deepsearch decode failed for %s: %s", url, exc)
if len(text) < MIN_PAGE_CHARS:
async with _pw_lock:
try:
r_title, r_text, r_status, r_links = await _render_with_playwright(url, browser)
except Exception as exc:
logger.info("deepsearch render failed for %s: %s", url, exc)
r_title, r_text, r_status, r_links = "", "", 0, []
if len(r_text) > len(text):
title, text, status, source, links = (
r_title or title,
@@ -260,6 +252,8 @@ async def fetch_page(url: str, depth: int, browser=None) -> CrawledPage | None:
"playwright",
r_links,
)
except Exception as exc:
logger.info("deepsearch render failed for %s: %s", url, exc)
if len(text) < MIN_PAGE_CHARS:
return None
return CrawledPage(
@@ -302,9 +296,10 @@ async def crawl(
total = min(len(level_candidates), max_pages)
cancelled = False
pw = None
browser = None
async with async_playwright() as pw:
try:
pw = await async_playwright().__aenter__()
browser = await pw.chromium.launch(
headless=True, args=["--no-sandbox", "--disable-dev-shm-usage"]
)
@@ -397,4 +392,6 @@ async def crawl(
finally:
if browser is not None:
await browser.close()
if pw is not None:
await pw.__aexit__(None, None, None)
return outcome
-4
View File
@@ -620,10 +620,6 @@ img {
.topnav-logo span { color: var(--accent); }
.topnav-links { display: flex; gap: 0.25rem; }
.topnav-link {
display: inline-flex;
align-items: center;
gap: 0.375rem;
white-space: nowrap;
padding: 0.5rem 0.75rem;
border-radius: var(--radius);
font-size: 0.875rem;
@@ -11,7 +11,7 @@ How a request flows through middleware to a router, how the database layer is bu
## Middleware
Seven HTTP middlewares run as a stack around every request, listed outermost first. `response_timing` is the outermost, `refresh_db_snapshot` the innermost, and a `GZipMiddleware` (responses over 512 bytes) wraps the whole stack on top:
Six HTTP middlewares run as a stack around every request, listed outermost first. `response_timing` is the outermost and `refresh_db_snapshot` the innermost. Compression is handled by nginx in production; the Python application does not compress responses itself.
| Middleware (outermost first) | Responsibility |
|------------|----------------|
+2 -1
View File
@@ -4,7 +4,8 @@ version = "1.0.0"
description = "DevPlace - The Developer Social Network"
requires-python = ">=3.12"
dependencies = [
"fastapi",
"fastapi>=0.110.0",
"starlette>=0.37.0",
"uvicorn[standard]",
"jinja2",
"python-multipart",