barrett/cp.nvim
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(submit): use file path over stdin; fix CF CodeMirror textarea (#305)

Browse source 
## Problem

After the initial submit hardening, two issues remained: source code was
read in Lua and piped as stdin to the scraper (unnecessary roundtrip
since
the file exists on disk), and CF's `page.fill()` timed out on the hidden
`textarea[name="source"]` because CodeMirror owns the editor state.

## Solution

Pass the source file path as a CLI arg instead — AtCoder calls
`page.set_input_files(file_path)` directly, CF reads it with
`Path(file_path).read_text()`. Fix CF source injection via
`page.evaluate()`
into the CodeMirror instance. Extract `BROWSER_SUBMIT_NAV_TIMEOUT` as a
per-platform `defaultdict` (CF defaults to 2× nav timeout). Save the
buffer
with `vim.cmd.update()` before submitting.
This commit is contained in:
Barrett Ruth 2026-03-05 14:34:14 -05:00 • committed by GitHub
parent 127089c57f
commit a202725cc5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 269 additions and 168 deletions
Download patch file Download diff file Expand all files Collapse all files

29
scrapers/atcoder.py
View file

@ -33,6 +33,7 @@ from .timeouts import (
BROWSER_NAV_TIMEOUT,
BROWSER_SESSION_TIMEOUT,
BROWSER_SETTLE_DELAY,
BROWSER_SUBMIT_NAV_TIMEOUT,
BROWSER_TURNSTILE_POLL,
HTTP_TIMEOUT,
)
@ -297,7 +298,7 @@ def _ensure_browser() -> None:
def _submit_headless(
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
_retried: bool = False,
@ -362,19 +363,12 @@ def _submit_headless(
f'select[name="data.LanguageId"] option[value="{language_id}"]'
).wait_for(state="attached", timeout=BROWSER_ELEMENT_WAIT)
page.select_option('select[name="data.LanguageId"]', language_id)
ext = _LANGUAGE_ID_EXTENSION.get(language_id, "txt")
page.set_input_files(
"#input-open-file",
{
"name": f"solution.{ext}",
"mimeType": "text/plain",
"buffer": source_code.encode(),
},
)
page.set_input_files("#input-open-file", file_path)
page.wait_for_timeout(BROWSER_SETTLE_DELAY)
page.locator('button[type="submit"]').click()
page.wait_for_url(
lambda url: "/submissions/me" in url, timeout=BROWSER_NAV_TIMEOUT
lambda url: "/submissions/me" in url,
timeout=BROWSER_SUBMIT_NAV_TIMEOUT["atcoder"],
)
except Exception as e:
submit_error = str(e)
@ -423,7 +417,7 @@ def _submit_headless(
return _submit_headless(
contest_id,
problem_id,
source_code,
file_path,
language_id,
credentials,
_retried=True,
@ -581,7 +575,7 @@ class AtcoderScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult:
@ -589,7 +583,7 @@ class AtcoderScraper(BaseScraper):
_submit_headless,
contest_id,
problem_id,
source_code,
file_path,
language_id,
credentials,
)
@ -651,15 +645,14 @@ async def main_async() -> int:
return 0 if contest_result.success else 1
if mode == "submit":
if len(sys.argv) != 5:
if len(sys.argv) != 6:
print(
SubmitResult(
success=False,
error="Usage: atcoder.py submit <contest_id> <problem_id> <language>",
error="Usage: atcoder.py submit <contest_id> <problem_id> <language> <file_path>",
).model_dump_json()
)
return 1
source_code = sys.stdin.read()
creds_raw = os.environ.get("CP_CREDENTIALS", "{}")
try:
credentials = json.loads(creds_raw)
@ -667,7 +660,7 @@ async def main_async() -> int:
credentials = {}
language_id = get_language_id("atcoder", sys.argv[4]) or sys.argv[4]
submit_result = await scraper.submit(
sys.argv[2], sys.argv[3], source_code, language_id, credentials
sys.argv[2], sys.argv[3], sys.argv[5], language_id, credentials
)
print(submit_result.model_dump_json())
return 0 if submit_result.success else 1

9
scrapers/base.py
View file

@ -53,7 +53,7 @@ class BaseScraper(ABC):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult: ...
@ -114,14 +114,13 @@ class BaseScraper(ABC):
return 0 if result.success else 1
case "submit":
if len(args) != 5:
if len(args) != 6:
print(
self._submit_error(
"Usage: <platform> submit <contest_id> <problem_id> <language_id>"
"Usage: <platform> submit <contest_id> <problem_id> <language_id> <file_path>"
).model_dump_json()
)
return 1
source_code = sys.stdin.read()
creds_raw = os.environ.get("CP_CREDENTIALS", "{}")
try:
credentials = json.loads(creds_raw)
@ -129,7 +128,7 @@ class BaseScraper(ABC):
credentials = {}
language_id = get_language_id(self.platform_name, args[4]) or args[4]
result = await self.submit(
args[2], args[3], source_code, language_id, credentials
args[2], args[3], args[5], language_id, credentials
)
print(result.model_dump_json())
return 0 if result.success else 1

4
scrapers/codechef.py
View file

@ -33,7 +33,7 @@ MEMORY_LIMIT_RE = re.compile(
)
async def fetch_json(client: httpx.AsyncClient, path: str) -> dict:
async def fetch_json(client: httpx.AsyncClient, path: str) -> dict[str, Any]:
r = await client.get(BASE_URL + path, headers=HEADERS, timeout=HTTP_TIMEOUT)
r.raise_for_status()
return r.json()
@ -256,7 +256,7 @@ class CodeChefScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult:

25
scrapers/codeforces.py
View file

@ -21,6 +21,7 @@ from .models import (
from .timeouts import (
BROWSER_NAV_TIMEOUT,
BROWSER_SESSION_TIMEOUT,
BROWSER_SUBMIT_NAV_TIMEOUT,
HTTP_TIMEOUT,
)
@ -289,7 +290,7 @@ class CodeforcesScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult:
@ -297,7 +298,7 @@ class CodeforcesScraper(BaseScraper):
_submit_headless,
contest_id,
problem_id,
source_code,
file_path,
language_id,
credentials,
)
@ -306,13 +307,15 @@ class CodeforcesScraper(BaseScraper):
def _submit_headless(
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
_retried: bool = False,
) -> SubmitResult:
from pathlib import Path
source_code = Path(file_path).read_text()
try:
from scrapling.fetchers import StealthySession # type: ignore[import-untyped,unresolved-import]
except ImportError:
@ -379,12 +382,22 @@ def _submit_headless(
problem_id.upper(),
)
page.select_option('select[name="programTypeId"]', language_id)
page.fill('textarea[name="source"]', source_code)
page.evaluate(
"""(code) => {
const cm = document.querySelector('.CodeMirror');
if (cm && cm.CodeMirror) {
cm.CodeMirror.setValue(code);
}
const ta = document.querySelector('textarea[name="source"]');
if (ta) ta.value = code;
}""",
source_code,
)
page.locator("form.submit-form input.submit").click(no_wait_after=True)
try:
page.wait_for_url(
lambda url: "/my" in url or "/status" in url,
timeout=BROWSER_NAV_TIMEOUT * 2,
timeout=BROWSER_SUBMIT_NAV_TIMEOUT["codeforces"],
)
except Exception:
err_el = page.query_selector("span.error")
@ -441,7 +454,7 @@ def _submit_headless(
return _submit_headless(
contest_id,
problem_id,
source_code,
file_path,
language_id,
credentials,
_retried=True,

5
scrapers/cses.py
View file

@ -357,10 +357,13 @@ class CSESScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult:
from pathlib import Path
source_code = Path(file_path).read_text()
username = credentials.get("username", "")
password = credentials.get("password", "")
if not username or not password:

2
scrapers/kattis.py
View file

@ -273,7 +273,7 @@ class KattisScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult:

6
scrapers/timeouts.py
View file

@ -1,7 +1,13 @@
from collections import defaultdict
HTTP_TIMEOUT = 15.0
BROWSER_SESSION_TIMEOUT = 15000
BROWSER_NAV_TIMEOUT = 10000
BROWSER_SUBMIT_NAV_TIMEOUT: defaultdict[str, int] = defaultdict(
lambda: BROWSER_NAV_TIMEOUT
)
BROWSER_SUBMIT_NAV_TIMEOUT["codeforces"] = BROWSER_NAV_TIMEOUT * 2
BROWSER_TURNSTILE_POLL = 5000
BROWSER_ELEMENT_WAIT = 10000
BROWSER_SETTLE_DELAY = 500

9
scrapers/usaco.py
View file

@ -73,8 +73,11 @@ def _parse_results_page(html: str) -> dict[str, list[tuple[str, str]]]:
for part in parts:
heading_m = DIVISION_HEADING_RE.search(part)
if heading_m:
current_div = heading_m.group(3).lower()
sections.setdefault(current_div, [])
div = heading_m.group(3)
if div:
key = div.lower()
current_div = key
sections.setdefault(key, [])
continue
if current_div is not None:
for m in PROBLEM_BLOCK_RE.finditer(part):
@ -285,7 +288,7 @@ class USACOScraper(BaseScraper):
self,
contest_id: str,
problem_id: str,
source_code: str,
file_path: str,
language_id: str,
credentials: dict[str, str],
) -> SubmitResult: