read.markets/tests/test_llm_csv_parser.py
Giorgio Gilestro f8a0ed3923 csv-parser: add _fingerprint helper
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 12:08:34 +02:00

56 lines
1.8 KiB
Python

"""Unit + integration tests for the LLM-fallback CSV parser."""
from __future__ import annotations
import pytest
def test_csv_format_template_model_columns():
"""Model exposes every column the spec requires, with correct types."""
from sqlalchemy import inspect
from app.models import CsvFormatTemplate
cols = {c.name: c for c in inspect(CsvFormatTemplate).columns}
assert "fingerprint" in cols
assert "headers" in cols
assert "sample_row" in cols
assert "mapping" in cols
assert "preamble_rows" in cols
assert "delimiter" in cols
assert "broker_label" in cols
assert "first_seen_at" in cols
assert "use_count" in cols
assert "last_used_at" in cols
assert "llm_model" in cols
assert "llm_cost_usd" in cols
# Crucially, no user attribution.
assert "user_id" not in cols
assert "first_seen_user_id" not in cols
# Fingerprint is the cache key.
assert cols["fingerprint"].unique is True
assert cols["fingerprint"].nullable is False
def test_fingerprint_stable_across_case_and_whitespace():
from app.services.llm_csv_parser import _fingerprint
a = _fingerprint(["Symbol", "Quantity", "Avg Price"])
b = _fingerprint(["symbol", "quantity", "avg price"])
c = _fingerprint([" SYMBOL ", "Quantity", " AVG PRICE"])
assert a == b == c
def test_fingerprint_differs_for_different_columns():
from app.services.llm_csv_parser import _fingerprint
a = _fingerprint(["Symbol", "Quantity"])
b = _fingerprint(["Symbol", "Quantity", "Avg Price"])
assert a != b
def test_fingerprint_is_sha256_hex_64_chars():
from app.services.llm_csv_parser import _fingerprint
f = _fingerprint(["Symbol", "Quantity"])
assert len(f) == 64
assert all(c in "0123456789abcdef" for c in f)