sepehr
f403b2851d
All checks were successful
Deploy to Production / Build and Deploy (push) Successful in 3m5s
L0 quality detection layer to catch translation failures BEFORE they
reach users. Pure Python/TypeScript, zero new dependencies, no API calls.
Backend (Python — services/quality/):
- Script detection: 145 langs mapped to 23 scripts (Latin, Cyrillic,
Greek, Arabic, Hebrew, CJK, Hangul, Kana, Devanagari, Bengali, etc.)
- Language confusion detection (e.g. Arabic text for French target)
- Arabic-script variant discrimination (Persian/Urdu/Pashto/Kurdish
confusion — e.g. Persian text returned when Arabic was requested)
- Length sanity check (with numeric/short-source exemptions)
- Prompt leak detection (Translation: / Voici la traduction: / 翻译:)
- Repetition hallucination detection (token + character level)
- File text extraction for .docx/.xlsx/.pptx/.pdf (no translator
changes needed)
- Defensive pipeline that never raises (L0 must NEVER break a job)
Frontend (TypeScript — wordly.art---traduction-de-documents/src/utils/):
- Exact 1:1 mirror of the Python module
- Zero dependencies, works in browser AND Node.js
- Native Unicode regex (\\p{L}/u) and codePoint iteration
- 63 tests using Node's built-in test runner
Integration:
- Feature-flagged: QUALITY_L0_ENABLED=false (default)
- Observation only: logs structured events, never modifies files
- try/except wrapped: impossible to break a translation job
- Lazy imports: only loaded when flag is on
- Zero impact on existing tests / behavior
Tests:
- 111 Python tests covering all paths (config, script, length, leak,
pipeline, file_extractor) — 100% pass
- 63 TypeScript tests (Node --test) — 100% pass
- 174/174 total tests for the L0 layer
Bug fixes in script mapping:
- yi (Yiddish) -> hebrew (was incorrectly mapped to arabic)
- dv (Maldivian) -> thaana (was incorrectly mapped to arabic)
- ja (Japanese) -> hiragana_katakana (distinguishes from Chinese CJK)
Phase 1 (backend) + Phase 2 (frontend) of Track A complete.
Next: Track B1 (Word/Excel format preservation quick wins).
Closes Track A phase 1+2 of the dev plan.
50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
"""
|
|
Tests for services/quality/length_checker.py
|
|
"""
|
|
import pytest
|
|
|
|
from services.quality.length_checker import check
|
|
|
|
|
|
class TestLengthCheck:
|
|
def test_normal_length(self):
|
|
r = check("Hello world, this is a test of translation length",
|
|
"Bonjour le monde, ceci est un test de longueur de traduction")
|
|
assert r["issue"] is None
|
|
assert r["ratio"] is not None
|
|
assert 0.5 < r["ratio"] < 2.0
|
|
|
|
def test_huge_translation(self):
|
|
src = "A" * 200
|
|
r = check(src, "x" * 1000)
|
|
assert r["issue"] == "length_outlier"
|
|
assert r["ratio"] > 3.5
|
|
|
|
def test_tiny_translation(self):
|
|
r = check("A" * 100, "ok")
|
|
assert r["issue"] == "truncation_suspect"
|
|
assert r["ratio"] < 0.15
|
|
|
|
def test_empty_translation_flagged(self):
|
|
r = check("Hello world, this is a test", "")
|
|
assert r["issue"] == "truncation_suspect"
|
|
|
|
def test_short_source_skips_ratio(self):
|
|
r = check("Hi", "ok")
|
|
assert r["issue"] is None
|
|
assert r["ratio"] is None
|
|
|
|
def test_empty_inputs(self):
|
|
r = check("", "")
|
|
assert r["issue"] is None
|
|
assert r["source_length"] == 0
|
|
assert r["translated_length"] == 0
|
|
|
|
def test_none_source(self):
|
|
r = check(None, "translation")
|
|
assert r["issue"] is None
|
|
|
|
def test_numeric_source(self):
|
|
r = check("Price: 100", "100")
|
|
assert r["issue"] is None # numeric sources skip the check
|