gitea
1a59c9f6c5
CI / compile (pull_request) Successful in 1m26s
CI / unit (pull_request) Successful in 1m8s
CI / integration (pull_request) Failing after 10h21m8s
CI / compile (push) Successful in 12m43s
build / build (push) Failing after 13m30s
CI / unit (push) Successful in 2m32s
CI / integration (push) Failing after 1h54m10s
search_bot conflated MAXTHREADS into two jobs at once - how many chunk files to read (files 0..MAXTHREADS-1) AND how many producer sentinels to wait for - so the two had to match exactly. Set too low it silently skipped trailing chunks; set too high (or with any chunk missing/unreadable) a producer crashed before emitting its sentinel, the consumers' count never reached the threshold, and search_for_doi hung on join() forever. The idle-timeout failsafe that was meant to break a starved consumer was dead code: `if empty_counter > 5: ... elif empty_counter > 10: break` - >10 implies >5, so the elif never ran. Fix, three layers: * auto-discover the chunk files present (discover_chunk_files: <n>_chunk.txt in numeric order) instead of range(0, MAXTHREADS). All files are read regardless of count, and no producer is ever pointed at a missing file; * the sentinel threshold is now the number of producers actually started, so it can't drift from what's emitted; * producers emit their sentinel in a finally, so even a crash (missing/unreadable chunk) can't starve the count; and the idle backstop is reordered so it can actually fire (>EMPTY_LIMIT seconds) as a last resort. MAXTHREADS is deprecated and unused (kept only so old env files don't break); docs/env updated to say chunk files are auto-discovered. For the reported case (MAXTHREADS=40, files 0..43): before, files 40-43 were silently never searched, and any run that referenced a missing chunk hung forever. After, all 44 are searched and it always terminates. Verified in a pytest-only venv (tests/unit/test_search_bot.py): DOI in a trailing chunk is found; an unreadable chunk still terminates; empty dir returns at once; discovery is numeric-sorted. Full unit job 27 passed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
90 lines
3.7 KiB
Python
90 lines
3.7 KiB
Python
"""Unit tests for the librarian DOI search - specifically that it always
|
|
terminates.
|
|
|
|
The producer/consumer search used to hang whenever the number of chunk files it
|
|
was told to read (MAXTHREADS) did not exactly match the files on disk: too few
|
|
and it silently skipped trailing chunks, too many and a producer pointed at a
|
|
missing file crashed before emitting its sentinel, starving the consumers'
|
|
termination count forever. These tests pin down the fix: chunk files are
|
|
auto-discovered, the sentinel threshold equals the number of producers actually
|
|
started, and every producer emits its sentinel even on error.
|
|
"""
|
|
import logging
|
|
import threading
|
|
|
|
import search_bot
|
|
|
|
_LOG = logging.getLogger("test-search-bot")
|
|
_LOG.addHandler(logging.NullHandler())
|
|
|
|
|
|
def _write_chunks(directory, count, target=None, target_index=None):
|
|
"""Create <n>_chunk.txt files; optionally drop `target` into one of them."""
|
|
for n in range(count):
|
|
lines = [f"10.0000/decoy-{n}-a\n", f"10.0000/decoy-{n}-b\n"]
|
|
if target is not None and n == target_index:
|
|
lines.append(target + "\n")
|
|
(directory / f"{n}_chunk.txt").write_text("".join(lines), encoding="utf-8")
|
|
|
|
|
|
def _run_bounded(dois, timeout=20):
|
|
"""Run search_for_doi in a thread; return (finished_in_time, result)."""
|
|
box = {}
|
|
live = []
|
|
worker = threading.Thread(
|
|
target=lambda: box.update(result=search_bot.search_for_doi(dois, live, _LOG)),
|
|
daemon=True,
|
|
)
|
|
worker.start()
|
|
worker.join(timeout)
|
|
return (not worker.is_alive()), box.get("result")
|
|
|
|
|
|
def test_finds_doi_in_trailing_chunk(tmp_path, monkeypatch):
|
|
# Target lives in the LAST chunk - the one the old MAXTHREADS=N-too-low would
|
|
# never have read. Auto-discovery must read every chunk present.
|
|
monkeypatch.setattr(search_bot, "DATABASE_PATH", str(tmp_path) + "/")
|
|
target = "10.1234/target.in.trailing.chunk"
|
|
_write_chunks(tmp_path, count=6, target=target, target_index=5)
|
|
|
|
finished, result = _run_bounded([(target, "DATA"), ("10.9999/absent", "DATA")])
|
|
|
|
assert finished, "search hung instead of terminating"
|
|
hit = [r for r in result if r["DOI"] == target and r["exists"]]
|
|
assert hit, "DOI in the trailing chunk was not found"
|
|
|
|
|
|
def test_terminates_when_a_chunk_is_unreadable(tmp_path, monkeypatch):
|
|
# A chunk that exists at discovery time but cannot be opened (here: it is a
|
|
# directory) makes its producer raise. The finally-sentinel must still fire
|
|
# so the consumers' count completes and the search does not deadlock.
|
|
monkeypatch.setattr(search_bot, "DATABASE_PATH", str(tmp_path) + "/")
|
|
_write_chunks(tmp_path, count=3)
|
|
(tmp_path / "9_chunk.txt").mkdir() # discovered as a chunk, un-openable
|
|
|
|
finished, _ = _run_bounded([("10.0000/decoy-0-a", "DATA")])
|
|
|
|
assert finished, "an unreadable chunk deadlocked the search"
|
|
|
|
|
|
def test_no_chunks_returns_immediately(tmp_path, monkeypatch):
|
|
# Empty database dir: return an (all-not-found) result at once, never hang.
|
|
monkeypatch.setattr(search_bot, "DATABASE_PATH", str(tmp_path) + "/")
|
|
|
|
finished, result = _run_bounded([("10.0/x", "DATA")], timeout=10)
|
|
|
|
assert finished
|
|
assert result == [{"DOI": "10.0/x", "exists": False, "data": "DATA"}]
|
|
|
|
|
|
def test_discover_chunk_files_sorted_numerically(tmp_path, monkeypatch):
|
|
monkeypatch.setattr(search_bot, "DATABASE_PATH", str(tmp_path) + "/")
|
|
for n in (0, 2, 10, 1):
|
|
(tmp_path / f"{n}_chunk.txt").write_text("x\n", encoding="utf-8")
|
|
(tmp_path / "notes.txt").write_text("ignore me\n", encoding="utf-8")
|
|
|
|
found = search_bot.discover_chunk_files(_LOG)
|
|
|
|
# Numeric order (10 after 2, not lexicographic), and non-chunk files ignored.
|
|
assert found == ["0_chunk.txt", "1_chunk.txt", "2_chunk.txt", "10_chunk.txt"]
|