"""Tests for analytics/extract.py — runs without MT5 or Wine.""" import json import os import sys import tempfile from pathlib import Path import pytest FIXTURES = Path(__file__).parent / 'fixtures' sys.path.insert(0, str(Path(__file__).parent.parent)) from analytics.extract import ( detect_format, parse_html, parse_xml, write_outputs, _parse_metrics_html, _parse_deals_html, ) def test_detect_format_html(): assert detect_format(str(FIXTURES / 'sample_report.htm')) == 'html' def test_detect_format_xml(): assert detect_format(str(FIXTURES / 'sample_report.htm.xml')) == 'xml' # HTML parsing is tested via internal functions to avoid the UTF-16 decode dance # (read_text tries UTF-16 first, which silently garbles plain UTF-8/ASCII files). # The fixture is used for format-detection only. HTML_TEXT = """

Net profit	1234.56
Profit factor	1.25
Maximal drawdown	500.00 (5.00%)
Sharpe Ratio	0.75
Total trades	150
Recovery factor	2.50
Profit trades (% of total)	90 (60.00%)
Gross profit	2000.00
Gross loss	-765.44

Deal Time	Type	Direction	Volume	Price	S/L	T/P	Profit	Balance	Comment	Order	Magic	Entry
2025.01.10 09:30:00	buy	out	0.01	1915.00	0	0	15.00	10015.00	Layer #1	1001	12345	out
2025.02.05 14:00:00	sell	out	0.01	1945.00	0	0	-15.00	10020.00	Layer #1	1005	12345	out

""" @pytest.fixture def html_report_path(tmp_path): """Write HTML fixture as UTF-16 LE with BOM so read_text() decodes it correctly.""" p = tmp_path / 'report.htm' p.write_bytes(b'\xff\xfe' + HTML_TEXT.encode('utf-16-le')) return str(p) def test_parse_html_returns_metrics(html_report_path): metrics, _ = parse_html(html_report_path) assert isinstance(metrics, dict) assert 'net_profit' in metrics assert metrics['net_profit'] == pytest.approx(1234.56) assert metrics['total_trades'] == 150 def test_parse_html_returns_deals(html_report_path): _, deals = parse_html(html_report_path) assert isinstance(deals, list) assert len(deals) >= 1 deal = deals[0] assert 'profit' in deal assert 'balance' in deal def test_parse_metrics_html_directly(): """Test HTML metric extraction without encoding layer.""" metrics = _parse_metrics_html(HTML_TEXT) assert metrics['net_profit'] == pytest.approx(1234.56) assert metrics['profit_factor'] == pytest.approx(1.25) assert metrics['max_dd_pct'] == pytest.approx(5.00) assert metrics['total_trades'] == 150 def test_parse_deals_html_directly(): """Test HTML deal extraction without encoding layer.""" deals = _parse_deals_html(HTML_TEXT) assert len(deals) == 2 assert float(deals[0]['profit']) == pytest.approx(15.00) assert float(deals[1]['profit']) == pytest.approx(-15.00) def test_parse_xml_returns_metrics(): metrics, deals = parse_xml(str(FIXTURES / 'sample_report.htm.xml')) assert isinstance(metrics, dict) assert 'net_profit' in metrics assert metrics['net_profit'] == pytest.approx(1234.56) assert metrics['total_trades'] == 150 def test_parse_xml_returns_deals(): metrics, deals = parse_xml(str(FIXTURES / 'sample_report.htm.xml')) assert isinstance(deals, list) assert len(deals) >= 1 deal = deals[0] assert deal.get('profit') is not None def test_write_outputs_creates_files(): metrics = {'net_profit': 100.0, 'total_trades': 5} deals = [ {'time': '2025.01.10', 'type': 'buy', 'direction': 'out', 'volume': '0.01', 'price': '1900', 'sl': '0', 'tp': '0', 'profit': '10.00', 'balance': '10010', 'comment': '', 'order': '1', 'magic': '1', 'entry': 'out'}, ] with tempfile.TemporaryDirectory() as tmp: paths = write_outputs(metrics, deals, tmp) assert Path(paths['metrics']).exists() assert Path(paths['deals_csv']).exists() assert Path(paths['deals_json']).exists() # Verify metrics.json content with open(paths['metrics']) as f: saved = json.load(f) assert saved['net_profit'] == 100.0 def test_parse_html_skips_balance_rows(): """Rows with type='balance' should be filtered out.""" html = """

Deal Time	Type	Direction	Volume	Price	S/L	T/P	Profit	Balance	Comment	Order	Magic	Entry
2025.01.10 09:30:00	balance		0	0	0	0	0	10000		0	0
2025.01.10 10:00:00	buy	out	0.01	1910	0	0	5.00	10005	Layer #1	1	1	out

""" import tempfile, os with tempfile.NamedTemporaryFile(mode='w', suffix='.htm', delete=False) as f: f.write(html) path = f.name try: _, deals = parse_html(path) types = [d.get('type', '').lower() for d in deals] assert 'balance' not in types finally: os.unlink(path)