Compare commits

..
Author SHA1 Message Date
Typosaurus 7332e4dd59 ticket #114 attempt 1 2026-07-23 03:15:14 +00:00
5 changed files with 125 additions and 118 deletions
File diff suppressed because one or more lines are too long
+2 -2
View File
@@ -439,8 +439,8 @@ class VoteForm(BaseModel):
@field_validator("value") @field_validator("value")
@classmethod @classmethod
def valid_value(cls, value): def valid_value(cls, value):
if value not in (1, -1): if value not in (1, -1, 0):
raise ValueError("value must be 1 or -1") raise ValueError("value must be 1, -1, or 0")
return value return value
@@ -22,7 +22,7 @@ ENGAGEMENT_ACTIONS: tuple[Action, ...] = (
), ),
body( body(
"value", "value",
"Vote value: 1 to upvote, -1 to downvote (re-send to remove).", "Vote value: 1 to upvote, -1 to downvote, 0 to retract.",
required=True, required=True,
), ),
), ),
+15 -18
View File
@@ -22,8 +22,6 @@ from .pdf import MAX_PDF_BYTES, extract_pdf_text, is_pdf
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
_pw_lock = asyncio.Lock()
RSEARCH_URL = "https://rsearch.app.molodetz.nl" RSEARCH_URL = "https://rsearch.app.molodetz.nl"
RSEARCH_TIMEOUT_SECONDS = 45.0 RSEARCH_TIMEOUT_SECONDS = 45.0
FETCH_TIMEOUT_SECONDS = 20.0 FETCH_TIMEOUT_SECONDS = 20.0
@@ -174,7 +172,13 @@ async def _render_with_playwright(
) -> tuple[str, str, int, list[tuple[str, str]]]: ) -> tuple[str, str, int, list[tuple[str, str]]]:
from playwright.async_api import async_playwright 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) context = await browser.new_context(user_agent=USER_AGENT)
page = await context.new_page() page = await context.new_page()
response = await page.goto(url, wait_until="load", timeout=30000) response = await page.goto(url, wait_until="load", timeout=30000)
@@ -185,18 +189,10 @@ async def _render_with_playwright(
await context.close() await context.close()
extracted = extract_html(content, base_url=url) extracted = extract_html(content, base_url=url)
return extracted.title, extracted.text, status, extracted.links 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: finally:
if own_browser:
await browser.close() await browser.close()
else: await pw.__aexit__(None, None, None)
return await _render(browser)
async def fetch_page(url: str, depth: int, browser=None) -> CrawledPage | 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: except (LookupError, ValueError) as exc:
logger.info("deepsearch decode failed for %s: %s", url, exc) logger.info("deepsearch decode failed for %s: %s", url, exc)
if len(text) < MIN_PAGE_CHARS: if len(text) < MIN_PAGE_CHARS:
async with _pw_lock:
try: try:
r_title, r_text, r_status, r_links = await _render_with_playwright(url, browser) 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): if len(r_text) > len(text):
title, text, status, source, links = ( title, text, status, source, links = (
r_title or title, r_title or title,
@@ -260,6 +252,8 @@ async def fetch_page(url: str, depth: int, browser=None) -> CrawledPage | None:
"playwright", "playwright",
r_links, r_links,
) )
except Exception as exc:
logger.info("deepsearch render failed for %s: %s", url, exc)
if len(text) < MIN_PAGE_CHARS: if len(text) < MIN_PAGE_CHARS:
return None return None
return CrawledPage( return CrawledPage(
@@ -302,9 +296,10 @@ async def crawl(
total = min(len(level_candidates), max_pages) total = min(len(level_candidates), max_pages)
cancelled = False cancelled = False
pw = None
browser = None browser = None
async with async_playwright() as pw:
try: try:
pw = await async_playwright().__aenter__()
browser = await pw.chromium.launch( browser = await pw.chromium.launch(
headless=True, args=["--no-sandbox", "--disable-dev-shm-usage"] headless=True, args=["--no-sandbox", "--disable-dev-shm-usage"]
) )
@@ -397,4 +392,6 @@ async def crawl(
finally: finally:
if browser is not None: if browser is not None:
await browser.close() await browser.close()
if pw is not None:
await pw.__aexit__(None, None, None)
return outcome return outcome
+10
View File
@@ -135,3 +135,13 @@ def test_non_ajax_vote_redirects_to_referer(app_server):
) )
assert r.status_code == 302 assert r.status_code == 302
assert r.headers["location"] == "/gists" assert r.headers["location"] == "/gists"
def test_explicit_zero_retracts_vote(app_server):
s_a, a_name = _session_votes()
s_b, _ = _session_votes()
post_uid = _make_post_votes(_uid_votes(a_name))
s_b.post(f"{BASE_URL}/votes/post/{post_uid}", data={"value": "1"}, headers=AJAX_votes)
r = s_b.post(f"{BASE_URL}/votes/post/{post_uid}", data={"value": "0"}, headers=AJAX_votes)
assert r.json()["value"] == 0
assert r.json()["net"] == 0