read.markets/tests/test_llm_csv_parser.py
Giorgio Gilestro b99f46d2fc csv-parser: add _apply_mapping helper
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 12:18:31 +02:00

222 lines
7.2 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)
def test_detect_dialect_no_preamble_comma():
from app.services.llm_csv_parser import _detect_dialect
raw = b"Symbol,Quantity,Avg Price\nAAPL,100,150.25\nMSFT,50,310.00\n"
delimiter, preamble = _detect_dialect(raw)
assert delimiter == ","
assert preamble == 0
def test_detect_dialect_with_preamble():
from app.services.llm_csv_parser import _detect_dialect
raw = (
b"Statement,Header,Field Name,Field Value\n"
b"Statement,Data,BrokerName,Interactive Brokers LLC\n"
b"Statement,Data,Title,Activity Statement\n"
b"Statement,Data,Period,\"January 1, 2026 - January 31, 2026\"\n"
b"Symbol,Quantity,Avg Price,Currency,Description\n"
b"AAPL,100,150.25,USD,Apple Inc\n"
)
delimiter, preamble = _detect_dialect(raw)
assert delimiter == ","
# The data-row header line is the FIFTH line (index 4); preamble = 4.
assert preamble == 4
def test_detect_dialect_tab_delimited():
from app.services.llm_csv_parser import _detect_dialect
raw = b"Symbol\tQuantity\tAvg Price\nAAPL\t100\t150.25\n"
delimiter, preamble = _detect_dialect(raw)
assert delimiter == "\t"
assert preamble == 0
def test_detect_dialect_empty_raises():
from app.services.llm_csv_parser import LLMParseError, _detect_dialect
with pytest.raises(LLMParseError):
_detect_dialect(b"")
def test_validate_mapping_accepts_well_formed():
from app.services.llm_csv_parser import _validate_mapping
headers = ["Symbol", "Quantity", "Avg Price", "Currency"]
first_row = ["AAPL", "100", "150.25", "USD"]
mapping = {
"ticker_col": "Symbol",
"qty_col": "Quantity",
"cost_col": "Avg Price",
"currency_col": "Currency",
"name_col": None,
}
_validate_mapping(mapping, headers, first_row) # no raise
def test_validate_mapping_missing_ticker_raises():
from app.services.llm_csv_parser import LLMParseError, _validate_mapping
headers = ["Symbol", "Quantity"]
first_row = ["AAPL", "100"]
mapping = {"ticker_col": None, "qty_col": "Quantity"}
with pytest.raises(LLMParseError, match="ticker"):
_validate_mapping(mapping, headers, first_row)
def test_validate_mapping_missing_qty_raises():
from app.services.llm_csv_parser import LLMParseError, _validate_mapping
headers = ["Symbol", "Quantity"]
first_row = ["AAPL", "100"]
mapping = {"ticker_col": "Symbol", "qty_col": None}
with pytest.raises(LLMParseError, match="qty"):
_validate_mapping(mapping, headers, first_row)
def test_validate_mapping_unknown_column_raises():
from app.services.llm_csv_parser import LLMParseError, _validate_mapping
headers = ["Symbol", "Quantity"]
first_row = ["AAPL", "100"]
mapping = {"ticker_col": "Symbol", "qty_col": "NotARealColumn"}
with pytest.raises(LLMParseError, match="NotARealColumn"):
_validate_mapping(mapping, headers, first_row)
def test_validate_mapping_non_numeric_qty_raises():
from app.services.llm_csv_parser import LLMParseError, _validate_mapping
headers = ["Symbol", "Description"]
first_row = ["AAPL", "Apple Inc"]
# Mapping says qty is "Description", but "Apple Inc" can't parse as a number.
mapping = {"ticker_col": "Symbol", "qty_col": "Description"}
with pytest.raises(LLMParseError, match="numeric"):
_validate_mapping(mapping, headers, first_row)
def test_apply_mapping_builds_parsed_pie():
from app.services.csv_import import ParsedPie, ParsedPosition
from app.services.llm_csv_parser import _apply_mapping
headers = ["Symbol", "Quantity", "Avg Price", "Currency", "Description"]
data_rows = [
["AAPL", "100", "150.25", "USD", "Apple Inc"],
["MSFT", "50", "310.00", "USD", "Microsoft Corp"],
]
mapping = {
"ticker_col": "Symbol",
"qty_col": "Quantity",
"cost_col": "Avg Price",
"currency_col": "Currency",
"name_col": "Description",
}
pie = _apply_mapping(headers, data_rows, mapping)
assert isinstance(pie, ParsedPie)
assert len(pie.positions) == 2
p0 = pie.positions[0]
assert isinstance(p0, ParsedPosition)
assert p0.slice == "AAPL"
assert p0.name == "Apple Inc"
assert p0.quantity == 100.0
assert p0.invested_value == pytest.approx(15025.0)
# invested = qty * avg_cost = 100 * 150.25 = 15025
assert pie.invested == pytest.approx(15025.0 + 50 * 310.00)
def test_apply_mapping_handles_missing_optional_columns():
from app.services.llm_csv_parser import _apply_mapping
headers = ["Symbol", "Quantity"]
data_rows = [["AAPL", "100"]]
mapping = {
"ticker_col": "Symbol",
"qty_col": "Quantity",
"cost_col": None,
"currency_col": None,
"name_col": None,
}
pie = _apply_mapping(headers, data_rows, mapping)
p = pie.positions[0]
assert p.slice == "AAPL"
assert p.quantity == 100.0
assert p.invested_value is None
assert p.name == "AAPL" # falls back to ticker when name_col absent
def test_apply_mapping_skips_blank_and_unparseable_rows():
from app.services.llm_csv_parser import _apply_mapping
headers = ["Symbol", "Quantity"]
data_rows = [
["AAPL", "100"],
["", ""], # blank
["MSFT", "not-a-number"], # bad qty
["NVDA", "40"],
]
mapping = {"ticker_col": "Symbol", "qty_col": "Quantity"}
pie = _apply_mapping(headers, data_rows, mapping)
assert [p.slice for p in pie.positions] == ["AAPL", "NVDA"]