Compare commits
4 Commits
4c67c116b2
..
dev
| Author | SHA1 | Date | |
|---|---|---|---|
| ffdbdbaf07 | |||
| a017771621 | |||
| 25e555cab6 | |||
| 3c7ab44e74 |
@@ -364,9 +364,49 @@ async def translation_test():
|
||||
return jsonify({"healthy": healthy})
|
||||
|
||||
|
||||
@settings_bp.route("/settings/translation/probe", methods=["POST"])
|
||||
async def translation_probe():
|
||||
"""Diagnostic for the Settings 'Test translation' box: translate a pasted
|
||||
snippet WITHOUT saving anything, returning what Interpreter *detected*
|
||||
(language + confidence) alongside the result. Lets the operator see why a
|
||||
given string was (mis-)detected — e.g. a short English title flagged as
|
||||
another language — so a detection guard can be tuned from real numbers.
|
||||
Read-only: no post is touched. Uses the currently-saved base URL + target."""
|
||||
body = await request.get_json(silent=True)
|
||||
body = body if isinstance(body, dict) else {}
|
||||
text = (body.get("text") or "").strip()
|
||||
if not text:
|
||||
return jsonify({"error": "provide text to translate"}), 400
|
||||
async with get_session() as session:
|
||||
cfg = await ImportSettings.load(session)
|
||||
base_url = (cfg.interpreter_base_url or "").strip()
|
||||
if not base_url:
|
||||
return jsonify({"error": "no Interpreter base URL is set"}), 400
|
||||
target = (cfg.translation_target_lang or "en").strip() or "en"
|
||||
try:
|
||||
res = await asyncio.to_thread(
|
||||
ic.translate, [text], base_url=base_url, target=target,
|
||||
)
|
||||
except ic.InterpreterUnavailable as e:
|
||||
return jsonify({"error": f"Interpreter unavailable: {e}"}), 503
|
||||
except ic.InterpreterBadRequest as e:
|
||||
return jsonify({"error": f"Interpreter rejected the request: {e}"}), 400
|
||||
translations = res.get("translations") or []
|
||||
return jsonify({
|
||||
"target": target,
|
||||
"detected_lang": res.get("detected_lang"),
|
||||
"detected_confidence": res.get("detected_confidence"),
|
||||
"engine": res.get("engine"),
|
||||
"engine_version": res.get("engine_version"),
|
||||
"translated": translations[0] if translations else None,
|
||||
})
|
||||
|
||||
|
||||
@settings_bp.route("/settings/translation/run", methods=["POST"])
|
||||
async def translation_run():
|
||||
"""Enqueue the translate sweep now (the Settings 'Translate now' button)."""
|
||||
"""Enqueue the translate sweep now (the Settings 'Translate now' button).
|
||||
Runs in drain mode — run-until-done — so one press chases the whole
|
||||
untranslated backlog to zero rather than a single 300-post chunk."""
|
||||
async with get_session() as session:
|
||||
cfg = await ImportSettings.load(session)
|
||||
if not cfg.translation_enabled or not (cfg.interpreter_base_url or "").strip():
|
||||
@@ -375,7 +415,7 @@ async def translation_run():
|
||||
), 400
|
||||
from ..tasks.translation import translate_posts
|
||||
|
||||
r = translate_posts.delay()
|
||||
r = translate_posts.delay(drain=True)
|
||||
return jsonify({"celery_task_id": r.id}), 202
|
||||
|
||||
|
||||
|
||||
@@ -178,9 +178,13 @@ def make_celery() -> Celery:
|
||||
"task": "backend.app.tasks.ml.prune_presentation_reviews",
|
||||
"schedule": 86400.0, # retention: drop resolved review flags >30d
|
||||
},
|
||||
"translate-posts-daily": {
|
||||
"translate-posts-8h": {
|
||||
"task": "backend.app.tasks.translation.translate_posts",
|
||||
"schedule": 86400.0, # no-op unless translation configured + healthy
|
||||
"schedule": 28800.0, # every 8h: steady-state cadence for the
|
||||
# trickle of newly-imported posts (no-op unless translation
|
||||
# configured + healthy). One bounded 300-chunk per fire — the
|
||||
# one-time backlog drains via the "Translate now" button
|
||||
# (drain=True, run-until-done), not this sweep.
|
||||
},
|
||||
"snapshot-head-metrics-daily": {
|
||||
"task": "backend.app.tasks.maintenance.snapshot_head_metrics",
|
||||
|
||||
@@ -96,8 +96,9 @@ def translate(
|
||||
) -> dict:
|
||||
"""Translate a batch. Returns::
|
||||
|
||||
{"translations": [str, ...], # SAME order & length as `texts`
|
||||
"detected_lang": str | None, # aggregate: describes the FIRST item
|
||||
{"translations": [str, ...], # SAME order & length as `texts`
|
||||
"detected_lang": str | None, # aggregate: describes the FIRST item
|
||||
"detected_confidence": float | None, # detector's confidence, if given
|
||||
"engine": str | None,
|
||||
"engine_version": str | None}
|
||||
|
||||
@@ -110,6 +111,7 @@ def translate(
|
||||
"""
|
||||
if not texts:
|
||||
return {"translations": [], "detected_lang": None,
|
||||
"detected_confidence": None,
|
||||
"engine": None, "engine_version": None}
|
||||
try:
|
||||
r = session.post(
|
||||
@@ -140,9 +142,11 @@ def translate(
|
||||
if not isinstance(out, list):
|
||||
out = [out]
|
||||
interp = body.get("interpreter") or {}
|
||||
detected = body.get("detectedLanguage") or {}
|
||||
return {
|
||||
"translations": out,
|
||||
"detected_lang": (body.get("detectedLanguage") or {}).get("language"),
|
||||
"detected_lang": detected.get("language"),
|
||||
"detected_confidence": detected.get("confidence"),
|
||||
"engine": interp.get("engine"),
|
||||
"engine_version": interp.get("engine_version"),
|
||||
}
|
||||
|
||||
@@ -7,8 +7,10 @@ same pattern as the other backfill sweeps. No-op unless translation is enabled,
|
||||
a base URL is set, and the service is healthy.
|
||||
|
||||
Two entry points:
|
||||
- ``translate_posts`` — the daily untranslated sweep (translated_source_lang IS
|
||||
NULL only); also the Settings "Translate now" button.
|
||||
- ``translate_posts`` — the periodic untranslated sweep (every 8h;
|
||||
translated_source_lang IS NULL only), one bounded chunk per fire. The Settings
|
||||
"Translate now" button calls it with ``drain=True`` to chase the tail
|
||||
run-until-done and clear the whole backlog in a single press.
|
||||
- ``retranslate_posts`` — after a model change, resets the stored translation
|
||||
columns for a scoped set of posts (all, or a given set of artists) so the
|
||||
untranslated selection re-runs them, then chases the tail until drained
|
||||
@@ -56,13 +58,19 @@ def _interrupt_backoff(retry_after) -> int:
|
||||
name="backend.app.tasks.translation.translate_posts",
|
||||
soft_time_limit=1800, time_limit=2100,
|
||||
)
|
||||
def translate_posts() -> str:
|
||||
def translate_posts(drain: bool = False) -> str:
|
||||
"""Translate untranslated non-English post title/description (default target
|
||||
en) via Interpreter. Per-post [title, description] batch → per-post detected
|
||||
language. Passthrough / already-target posts are marked handled (source ==
|
||||
target) with no stored translation. 503 or a connection error interrupts the
|
||||
run (retry next cycle); 400 stops it (fix config); posts done so far stay
|
||||
committed. No-op unless configured + healthy. Returns a summary string."""
|
||||
committed. No-op unless configured + healthy. Returns a summary string.
|
||||
|
||||
``drain`` (the Settings "Translate now" button) chases the tail
|
||||
run-until-done: on a clean chunk with work still remaining it re-enqueues
|
||||
itself until the untranslated backlog is zero, like ``retranslate_posts``. The
|
||||
periodic beat leaves it False → one bounded chunk per fire (the 8h cadence
|
||||
drives the rest, enough for the trickle of newly-imported posts)."""
|
||||
SessionLocal = _sync_session_factory()
|
||||
with SessionLocal() as session:
|
||||
ready = _translation_config(session)
|
||||
@@ -73,14 +81,28 @@ def translate_posts() -> str:
|
||||
status, translated, retry_after = _translate_batch(
|
||||
session, posts, base_url, target,
|
||||
)
|
||||
# Steady-state daily sweep: one chunk per run on success (the beat drives
|
||||
# the rest — no tail-chase). But if Interpreter drained mid-chunk, don't
|
||||
# make a manual "Translate now" wait a whole day — re-enqueue after its
|
||||
# Retry-After hint (or the default backoff). Self-terminating: once the
|
||||
# service is down the health gate returns "interpreter unavailable" early.
|
||||
if status == "interrupted" and _count_untranslated(session, None):
|
||||
# Drain mode (manual "Translate now"): chase the tail until the backlog is
|
||||
# zero, so one press clears the whole pile instead of one 300-chunk.
|
||||
# Termination is guaranteed — every handled post leaves the untranslated
|
||||
# set, so the remaining count strictly decreases each chunk.
|
||||
if status == "ok" and drain:
|
||||
remaining = _count_untranslated(session, None)
|
||||
if remaining:
|
||||
translate_posts.apply_async(
|
||||
(), {"drain": True}, countdown=_RETRANSLATE_COUNTDOWN,
|
||||
)
|
||||
log.info(
|
||||
"translate_posts: draining — %d remaining → re-enqueued",
|
||||
remaining,
|
||||
)
|
||||
# Interpreter drained mid-chunk (graceful restart): don't make a manual
|
||||
# "Translate now" wait a whole beat cycle — re-enqueue after its
|
||||
# Retry-After hint (or the default backoff), preserving `drain` so a bulk
|
||||
# drain resumes cleanly. Self-terminating: once the service is down the
|
||||
# health gate returns "interpreter unavailable" early.
|
||||
elif status == "interrupted" and _count_untranslated(session, None):
|
||||
delay = _interrupt_backoff(retry_after)
|
||||
translate_posts.apply_async((), {}, countdown=delay)
|
||||
translate_posts.apply_async((), {"drain": drain}, countdown=delay)
|
||||
log.info(
|
||||
"translate_posts: interrupted (service draining) → retry in %ss",
|
||||
delay,
|
||||
@@ -250,29 +272,39 @@ def _summary(status: str, translated: int, scanned: int) -> str:
|
||||
return f"translated={translated} scanned={scanned}"
|
||||
|
||||
|
||||
def _translate_field(text: str, base_url: str, target: str):
|
||||
"""Translate ONE field independently. Returns (translated, source_lang,
|
||||
engine_version), or (None, None, None) when there's nothing to store — empty
|
||||
text, already the target language, or a passthrough (engine "none"). Per-field
|
||||
(not aggregate first-item) detection so a non-English description still gets
|
||||
translated when the title is already English (mixed-language posts)."""
|
||||
if not text:
|
||||
return None, None, None
|
||||
res = ic.translate([text], base_url=base_url, target=target)
|
||||
detected = res["detected_lang"] or target
|
||||
if detected == target or res["engine"] == "none":
|
||||
return None, None, None
|
||||
return res["translations"][0], detected, res["engine_version"]
|
||||
|
||||
|
||||
def _translate_one(session, post, base_url: str, target: str) -> int:
|
||||
"""Translate one post's title/description in place. Returns 1 if it stored a
|
||||
translation, 0 for passthrough/empty (which still marks the post handled)."""
|
||||
"""Translate a post's title/description in place, each field independently.
|
||||
Returns 1 if it stored at least one translation, 0 when the post is all
|
||||
passthrough/empty (still marks it handled so the sweep won't revisit it)."""
|
||||
title = (post.post_title or "").strip()
|
||||
desc = (html_to_plain(post.description) if post.description else "") or ""
|
||||
desc = desc.strip()
|
||||
fields: list[tuple[str, str]] = []
|
||||
if title:
|
||||
fields.append(("title", title))
|
||||
if desc:
|
||||
fields.append(("desc", desc))
|
||||
if not fields:
|
||||
post.translated_source_lang = target # nothing to translate → handled
|
||||
title_tr, title_lang, title_ev = _translate_field(title, base_url, target)
|
||||
desc_tr, desc_lang, desc_ev = _translate_field(desc, base_url, target)
|
||||
if title_tr is None and desc_tr is None:
|
||||
# Nothing non-target (or nothing to translate) → handled, store nothing.
|
||||
post.translated_source_lang = target
|
||||
return 0
|
||||
res = ic.translate([t for _, t in fields], base_url=base_url, target=target)
|
||||
detected = res["detected_lang"] or target
|
||||
if detected == target or res["engine"] == "none":
|
||||
post.translated_source_lang = target # already target language → handled
|
||||
return 0
|
||||
by_field = {f: res["translations"][i] for i, (f, _) in enumerate(fields)}
|
||||
post.post_title_translated = by_field.get("title")
|
||||
post.description_translated = by_field.get("desc")
|
||||
post.translated_source_lang = detected
|
||||
post.translation_engine_version = res["engine_version"]
|
||||
post.post_title_translated = title_tr
|
||||
post.description_translated = desc_tr
|
||||
# Source lang = whichever field was actually non-target (for a mixed post,
|
||||
# the translated field's language, not the already-English one).
|
||||
post.translated_source_lang = title_lang or desc_lang
|
||||
post.translation_engine_version = title_ev or desc_ev
|
||||
post.translated_at = datetime.now(UTC)
|
||||
return 1
|
||||
|
||||
@@ -143,7 +143,19 @@ function iconFor (k) { return KIND_ICONS[k] || 'mdi-tag' }
|
||||
chip's hover title. */
|
||||
.fc-tag-chip { display: inline-flex; align-items: center; gap: 1px; max-width: 100%; min-width: 0; }
|
||||
.fc-tag-chip__nav { max-width: 100%; min-width: 0; }
|
||||
/* Tonal chips (esp. character = info) wash out against the dark rail — the fill
|
||||
is intentionally faint. Give every tag chip a thin border in its OWN kind
|
||||
colour (currentColor = the tonal chip's themed foreground) so the edge reads
|
||||
clearly without touching the fill (operator-asked 2026-07-08). Theme-aware:
|
||||
currentColor tracks the kind colour in either light or dark. */
|
||||
.fc-tag-chip__nav { border: thin solid color-mix(in srgb, currentColor 55%, transparent); }
|
||||
.fc-tag-chip__nav :deep(.v-chip__content) { min-width: 0; overflow: hidden; }
|
||||
/* The bigger size=default chip widens Vuetify's negative start-margin on the
|
||||
leading kind-icon, pulling it LEFT of the content box above — where that
|
||||
overflow:hidden then clips the icon's left edge as a vertical slice
|
||||
(operator-flagged 2026-07-08). Zero the pull so the icon sits inside the clip
|
||||
box; the chip's own 12px padding keeps a comfortable left inset. */
|
||||
.fc-tag-chip__nav :deep(.v-icon--start) { margin-inline-start: 0; }
|
||||
.fc-tag-chip__name {
|
||||
overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
|
||||
min-width: 0; flex: 0 1 auto;
|
||||
|
||||
@@ -78,6 +78,61 @@
|
||||
artist, use the Re-translate button on that artist's page.
|
||||
</p>
|
||||
|
||||
<v-divider class="my-3" />
|
||||
|
||||
<!-- Diagnostic probe (task #1376): paste text → what Interpreter DETECTS
|
||||
(language + confidence) and returns, without saving. Used to see why a
|
||||
short/abbreviation-heavy English title gets mis-detected, and to pick a
|
||||
detection-confidence / min-length guard from real numbers. -->
|
||||
<div class="mb-1">
|
||||
<span class="fc-section-h">Test translation</span>
|
||||
<p class="fc-muted text-caption mt-1 mb-2">
|
||||
Paste a title or snippet to see what Interpreter detects and returns —
|
||||
handy for checking why a short string is mis-detected. Nothing is saved.
|
||||
</p>
|
||||
</div>
|
||||
<v-textarea
|
||||
v-model="probeText" label="Text to test" rows="2" auto-grow
|
||||
density="compact" hide-details class="mb-2" :disabled="!baseUrl"
|
||||
/>
|
||||
<div class="d-flex align-center flex-wrap mb-2" style="gap: 8px;">
|
||||
<v-btn
|
||||
size="small" variant="tonal" rounded="pill" prepend-icon="mdi-magnify"
|
||||
:loading="probing" :disabled="!baseUrl || !probeText.trim()"
|
||||
@click="onProbe"
|
||||
>Test translation</v-btn>
|
||||
</div>
|
||||
<v-sheet
|
||||
v-if="probeResult" rounded class="pa-3 mb-1 text-body-2"
|
||||
color="rgba(var(--v-theme-accent), 0.06)"
|
||||
>
|
||||
<div class="d-flex flex-wrap" style="gap: 4px 16px;">
|
||||
<span>
|
||||
<span class="fc-muted">Detected:</span>
|
||||
<strong>{{ probeResult.detected_lang || '—' }}</strong>
|
||||
</span>
|
||||
<span v-if="probeResult.detected_confidence != null">
|
||||
<span class="fc-muted">Confidence:</span>
|
||||
<strong>{{ fmtConf(probeResult.detected_confidence) }}</strong>
|
||||
</span>
|
||||
<span>
|
||||
<span class="fc-muted">Engine:</span>
|
||||
{{ probeResult.engine || '—' }}<template
|
||||
v-if="probeResult.engine_version"
|
||||
> ({{ probeResult.engine_version }})</template>
|
||||
</span>
|
||||
<span><span class="fc-muted">Target:</span> {{ probeResult.target }}</span>
|
||||
</div>
|
||||
<v-divider class="my-2" />
|
||||
<div class="fc-muted mb-1">
|
||||
Result<template v-if="probeResult.detected_lang === probeResult.target">
|
||||
— already {{ probeResult.target }}, so the sweep leaves it as-is</template>:
|
||||
</div>
|
||||
<p class="mb-0" style="white-space: pre-wrap;">{{
|
||||
probeResult.translated || '(no change)'
|
||||
}}</p>
|
||||
</v-sheet>
|
||||
|
||||
<v-alert
|
||||
v-if="err" type="error" variant="tonal" density="compact"
|
||||
class="mt-3" closable @click:close="err = null"
|
||||
@@ -129,6 +184,17 @@ const testResult = ref(null) // null = not tested this session; true/false = l
|
||||
const status = ref(null)
|
||||
const err = ref(null)
|
||||
|
||||
// #1376 "Test translation" probe: paste text → detected lang/confidence + result.
|
||||
const probeText = ref('')
|
||||
const probing = ref(false)
|
||||
const probeResult = ref(null)
|
||||
|
||||
// Confidence scale is Interpreter-defined (0–100 or 0–1) — show it as-is, just
|
||||
// trimmed to 2 decimals, so the operator reads the true number.
|
||||
function fmtConf (c) {
|
||||
return c == null ? '' : Math.round(c * 100) / 100
|
||||
}
|
||||
|
||||
const statusColor = computed(() => {
|
||||
if (!enabled.value || !baseUrl.value) return 'grey'
|
||||
return status.value?.healthy ? 'success' : 'error'
|
||||
@@ -170,6 +236,21 @@ async function onTest() {
|
||||
}
|
||||
}
|
||||
|
||||
async function onProbe () {
|
||||
probing.value = true
|
||||
err.value = null
|
||||
probeResult.value = null
|
||||
try {
|
||||
probeResult.value = await api.post('/api/settings/translation/probe', {
|
||||
body: { text: probeText.value.trim() },
|
||||
})
|
||||
} catch (e) {
|
||||
err.value = e.message
|
||||
} finally {
|
||||
probing.value = false
|
||||
}
|
||||
}
|
||||
|
||||
onMounted(async () => {
|
||||
try {
|
||||
await store.loadSettings()
|
||||
|
||||
@@ -113,9 +113,10 @@ async def test_translation_test_connection(client, monkeypatch):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_translation_run_enqueues_when_configured(client, monkeypatch):
|
||||
sink = {}
|
||||
monkeypatch.setattr(
|
||||
"backend.app.tasks.translation.translate_posts.delay",
|
||||
lambda *a, **k: type("R", (), {"id": "t1"})(),
|
||||
lambda *a, **k: sink.update(k) or type("R", (), {"id": "t1"})(),
|
||||
)
|
||||
await client.patch("/api/settings/import", json={
|
||||
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
|
||||
@@ -123,6 +124,46 @@ async def test_translation_run_enqueues_when_configured(client, monkeypatch):
|
||||
resp = await client.post("/api/settings/translation/run")
|
||||
assert resp.status_code == 202
|
||||
assert (await resp.get_json())["celery_task_id"] == "t1"
|
||||
assert sink["drain"] is True # "Translate now" chases the whole backlog
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_translation_probe_requires_text(client):
|
||||
resp = await client.post(
|
||||
"/api/settings/translation/probe", json={"text": " "})
|
||||
assert resp.status_code == 400
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_translation_probe_requires_base_url(client):
|
||||
# Text given but no Interpreter URL saved → nothing to probe against.
|
||||
resp = await client.post(
|
||||
"/api/settings/translation/probe", json={"text": "hello"})
|
||||
assert resp.status_code == 400
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_translation_probe_returns_detection(client, monkeypatch):
|
||||
# The diagnostic surfaces detected language + confidence + result, unsaved.
|
||||
monkeypatch.setattr(
|
||||
"backend.app.api.settings.ic.translate",
|
||||
lambda texts, **k: {
|
||||
"translations": ["Work in Progress"],
|
||||
"detected_lang": "de", "detected_confidence": 71.5,
|
||||
"engine": "llm", "engine_version": "v1",
|
||||
},
|
||||
)
|
||||
await client.patch("/api/settings/import", json={
|
||||
"translation_enabled": True, "interpreter_base_url": "http://i.lan",
|
||||
})
|
||||
resp = await client.post(
|
||||
"/api/settings/translation/probe", json={"text": "WIP"})
|
||||
assert resp.status_code == 200
|
||||
body = await resp.get_json()
|
||||
assert body["detected_lang"] == "de"
|
||||
assert body["detected_confidence"] == 71.5
|
||||
assert body["translated"] == "Work in Progress"
|
||||
assert body["target"] == "en"
|
||||
|
||||
|
||||
def _fake_retranslate(monkeypatch, sink):
|
||||
|
||||
@@ -34,6 +34,7 @@ def test_translate_maps_batch_in_order(monkeypatch):
|
||||
out = ic.translate(["ねこが可愛い", "金髪ギャル!"], base_url="http://i.lan")
|
||||
assert out["translations"] == ["The cat is cute", "Blonde gal!"]
|
||||
assert out["detected_lang"] == "ja"
|
||||
assert out["detected_confidence"] == 0.98 # surfaced for the detection guard
|
||||
assert out["engine_version"] == "ollama:x:12b"
|
||||
assert captured["json"]["q"] == ["ねこが可愛い", "金髪ギャル!"]
|
||||
assert captured["json"]["target"] == "en"
|
||||
|
||||
@@ -5,7 +5,11 @@ from sqlalchemy import select
|
||||
|
||||
from backend.app.models import Artist, ImportSettings, Post
|
||||
from backend.app.services import interpreter_client as ic
|
||||
from backend.app.tasks.translation import retranslate_posts, translate_posts
|
||||
from backend.app.tasks.translation import (
|
||||
_RETRANSLATE_COUNTDOWN,
|
||||
retranslate_posts,
|
||||
translate_posts,
|
||||
)
|
||||
|
||||
pytestmark = pytest.mark.integration
|
||||
|
||||
@@ -115,6 +119,35 @@ def test_translate_posts_passthrough_english_marks_handled(db_sync, monkeypatch)
|
||||
assert p.post_title_translated is None # ...but nothing to show
|
||||
|
||||
|
||||
def test_translate_posts_mixed_language_translates_nonenglish_field(db_sync, monkeypatch):
|
||||
# English title + Japanese description: the description is still translated
|
||||
# even though the title is already English (per-field detection, not the old
|
||||
# aggregate first-item bail). Source lang comes from the translated field.
|
||||
_patch(monkeypatch, db_sync)
|
||||
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
|
||||
|
||||
def fake_translate(texts, **k):
|
||||
t = texts[0]
|
||||
if t.isascii(): # already English → passthrough
|
||||
return {"translations": [t], "detected_lang": "en",
|
||||
"engine": "none", "engine_version": None}
|
||||
return {"translations": [f"EN:{t}"], "detected_lang": "ja",
|
||||
"engine": "llm", "engine_version": "v9"}
|
||||
|
||||
monkeypatch.setattr("backend.app.tasks.translation.ic.translate", fake_translate)
|
||||
a = _artist(db_sync)
|
||||
p = _post(db_sync, a.id, title="hello", desc="ねこ")
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
assert "translated=1" in translate_posts()
|
||||
db_sync.refresh(p)
|
||||
assert p.post_title_translated is None # English title untouched
|
||||
assert p.description_translated == "EN:ねこ" # Japanese desc translated
|
||||
assert p.translated_source_lang == "ja" # from the translated field
|
||||
assert p.translation_engine_version == "v9"
|
||||
|
||||
|
||||
def test_translate_posts_disabled_is_noop(db_sync, monkeypatch):
|
||||
_patch(monkeypatch, db_sync)
|
||||
a = _artist(db_sync)
|
||||
@@ -162,6 +195,63 @@ def test_translate_posts_interrupt_reenqueues_after_backoff(db_sync, monkeypatch
|
||||
assert calls[0][1]["countdown"] == 30
|
||||
|
||||
|
||||
def _mock_ok(monkeypatch):
|
||||
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
|
||||
monkeypatch.setattr(
|
||||
"backend.app.tasks.translation.ic.translate",
|
||||
lambda texts, **k: {
|
||||
"translations": [f"EN:{t}" for t in texts],
|
||||
"detected_lang": "ja", "engine": "llm", "engine_version": "v1",
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
def test_translate_posts_drain_chases_tail(db_sync, monkeypatch):
|
||||
# "Translate now" (drain=True): with the chunk capped at 1 and 2 untranslated
|
||||
# posts, the first chunk re-enqueues itself — drain preserved — to finish the
|
||||
# backlog rather than waiting for the next beat.
|
||||
_patch(monkeypatch, db_sync)
|
||||
_mock_ok(monkeypatch)
|
||||
monkeypatch.setattr("backend.app.tasks.translation._MAX_POSTS_PER_RUN", 1)
|
||||
calls = []
|
||||
monkeypatch.setattr(
|
||||
"backend.app.tasks.translation.translate_posts.apply_async",
|
||||
lambda *a, **k: calls.append((a, k)),
|
||||
)
|
||||
a = _artist(db_sync)
|
||||
_post(db_sync, a.id, title="ねこ", ext="p1")
|
||||
_post(db_sync, a.id, title="いぬ", ext="p2")
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
translate_posts(drain=True)
|
||||
assert len(calls) == 1 # one re-enqueue for the tail
|
||||
args, kw = calls[0]
|
||||
assert args[1] == {"drain": True} # drain flag carried forward
|
||||
assert kw["countdown"] == _RETRANSLATE_COUNTDOWN
|
||||
|
||||
|
||||
def test_translate_posts_beat_single_chunk_no_tail_chase(db_sync, monkeypatch):
|
||||
# The periodic beat (drain defaults False) does exactly ONE chunk and never
|
||||
# re-enqueues — the 8h cadence drives the rest.
|
||||
_patch(monkeypatch, db_sync)
|
||||
_mock_ok(monkeypatch)
|
||||
monkeypatch.setattr("backend.app.tasks.translation._MAX_POSTS_PER_RUN", 1)
|
||||
calls = []
|
||||
monkeypatch.setattr(
|
||||
"backend.app.tasks.translation.translate_posts.apply_async",
|
||||
lambda *a, **k: calls.append((a, k)),
|
||||
)
|
||||
a = _artist(db_sync)
|
||||
_post(db_sync, a.id, title="ねこ", ext="p1")
|
||||
_post(db_sync, a.id, title="いぬ", ext="p2")
|
||||
_enable(db_sync)
|
||||
db_sync.commit()
|
||||
|
||||
translate_posts() # drain=False
|
||||
assert calls == [] # no self-re-enqueue
|
||||
|
||||
|
||||
def _mock_new_model(monkeypatch, *, ver="v2"):
|
||||
"""Interpreter is up and translates with a NEW engine version."""
|
||||
monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
|
||||
|
||||
Reference in New Issue
Block a user