"""Tests for Balabit Mouse Dynamics Challenge data adapter.""" from __future__ import annotations import json from pathlib import Path import pytest def test_module_exports(): """The adapter module must export the public functions used by CLI.""" from tools.data_adapters import balabit assert hasattr(balabit, "parse_session_csv") assert hasattr(balabit, "segment_by_clicks") assert hasattr(balabit, "filter_segments") assert hasattr(balabit, "process_session") assert hasattr(balabit, "MouseEvent") assert hasattr(balabit, "Segment") def test_mouse_event_dataclass(): """MouseEvent has expected fields.""" from tools.data_adapters.balabit import MouseEvent e = MouseEvent(t_ms=100, button="NoButton", state="Move", x=300, y=400) assert e.t_ms == 100 assert e.state == "Move" assert e.x == 300 def test_segment_dataclass(): """Segment has expected fields.""" from tools.data_adapters.balabit import MouseEvent, Segment events = [MouseEvent(t_ms=0, button="NoButton", state="Move", x=10, y=20)] s = Segment(events=events, click_x=100, click_y=200, click_t_ms=500, session_id="user1_s1") assert s.events == events assert s.click_x == 100 assert s.session_id == "user1_s1" def _write_csv(path: Path, rows: list[str]) -> None: """Helper to write a Balabit-format CSV with header.""" header = "record timestamp,client timestamp,button,state,x,y" path.write_text(header + "\n" + "\n".join(rows) + "\n", encoding="utf-8") class TestParseSessionCsv: def test_parses_basic_rows(self, tmp_path): from tools.data_adapters.balabit import parse_session_csv csv = tmp_path / "session_1" _write_csv(csv, [ "1500000000.000,0.000,NoButton,Move,100,200", "1500000000.050,0.050,NoButton,Move,110,210", "1500000000.100,0.100,Left,Pressed,120,220", ]) events = parse_session_csv(csv) assert len(events) == 3 assert events[0].t_ms == 0 assert events[0].state == "Move" assert events[0].x == 100 assert events[2].t_ms == 100 assert events[2].state == "Pressed" assert events[2].button == "Left" def test_handles_float_timestamps(self, tmp_path): """Client timestamps are floats in seconds; we convert to int ms.""" from tools.data_adapters.balabit import parse_session_csv csv = tmp_path / "session_2" _write_csv(csv, [ "0,1.234,NoButton,Move,50,60", "0,1.250,NoButton,Move,55,65", ]) events = parse_session_csv(csv) assert events[0].t_ms == 1234 assert events[1].t_ms == 1250 def test_skips_malformed_rows(self, tmp_path): """Rows with bad data are logged and skipped, not raised.""" from tools.data_adapters.balabit import parse_session_csv csv = tmp_path / "session_3" _write_csv(csv, [ "0,0.000,NoButton,Move,100,200", "BROKEN_ROW", "0,abc,NoButton,Move,100,200", # bad timestamp "0,0.100,NoButton,Move,150,250", ]) events = parse_session_csv(csv) assert len(events) == 2 assert events[0].x == 100 assert events[1].x == 150 def test_returns_empty_list_for_empty_file(self, tmp_path): from tools.data_adapters.balabit import parse_session_csv csv = tmp_path / "session_4" csv.write_text("record timestamp,client timestamp,button,state,x,y\n", encoding="utf-8") events = parse_session_csv(csv) assert events == [] class TestSegmentByClicks: def _make_event(self, t_ms: int, state: str, x: int, y: int, button: str = "NoButton"): from tools.data_adapters.balabit import MouseEvent return MouseEvent(t_ms=t_ms, button=button, state=state, x=x, y=y) def test_one_click_one_segment(self): from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), self._make_event(100, "Move", 50, 60), self._make_event(500, "Move", 100, 100), self._make_event(600, "Pressed", 110, 110, button="Left"), ] segments = segment_by_clicks(events, window_ms=1200, session_id="test_s1") assert len(segments) == 1 seg = segments[0] assert seg.click_x == 110 assert seg.click_y == 110 assert seg.click_t_ms == 600 assert len(seg.events) == 3 assert seg.session_id == "test_s1" def test_window_excludes_old_events(self): """Move events earlier than (click_t - window_ms) are dropped.""" from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), # too old self._make_event(100, "Move", 20, 30), # too old self._make_event(900, "Move", 30, 40), # in window self._make_event(1000, "Pressed", 40, 50, button="Left"), ] segments = segment_by_clicks(events, window_ms=200, session_id="s") assert len(segments) == 1 assert len(segments[0].events) == 1 assert segments[0].events[0].t_ms == 900 def test_multiple_clicks_multiple_segments(self): from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), self._make_event(100, "Pressed", 50, 50, button="Left"), self._make_event(200, "Released", 50, 50, button="Left"), self._make_event(300, "Move", 60, 60), self._make_event(400, "Move", 70, 70), self._make_event(500, "Pressed", 80, 80, button="Left"), ] segments = segment_by_clicks(events, window_ms=1200, session_id="s") assert len(segments) == 2 assert segments[0].click_x == 50 assert segments[1].click_x == 80 # Second segment's events must not include the first Pressed for e in segments[1].events: assert e.state == "Move" def test_skips_pressed_with_non_left_button(self): """Right-clicks and wheel-clicks don't anchor segments (only Left).""" from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), self._make_event(100, "Pressed", 50, 50, button="Right"), # ignored self._make_event(200, "Move", 60, 60), self._make_event(300, "Pressed", 70, 70, button="Left"), # anchor ] segments = segment_by_clicks(events, window_ms=1200, session_id="s") assert len(segments) == 1 assert segments[0].click_x == 70 def test_no_clicks_returns_empty(self): from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), self._make_event(100, "Move", 20, 30), ] segments = segment_by_clicks(events, window_ms=1200, session_id="s") assert segments == [] def test_excludes_drag_events(self): """Drag events are not Move; segment should only include Move.""" from tools.data_adapters.balabit import segment_by_clicks events = [ self._make_event(0, "Move", 10, 20), self._make_event(100, "Drag", 30, 40), # not Move self._make_event(200, "Move", 50, 60), self._make_event(300, "Pressed", 70, 80, button="Left"), ] segments = segment_by_clicks(events, window_ms=1200, session_id="s") assert len(segments) == 1 # Drag event should not appear in seg.events assert all(e.state == "Move" for e in segments[0].events) assert len(segments[0].events) == 2 class TestFilterSegments: def _seg(self, events_data: list[tuple[int, int, int]], click=(500, 500), session="s"): """events_data: list of (t_ms, x, y) tuples.""" from tools.data_adapters.balabit import MouseEvent, Segment events = [MouseEvent(t_ms=t, button="NoButton", state="Move", x=x, y=y) for (t, x, y) in events_data] click_t = events[-1].t_ms + 50 if events else 100 return Segment(events=events, click_x=click[0], click_y=click[1], click_t_ms=click_t, session_id=session) def test_drops_segment_with_too_few_events(self): from tools.data_adapters.balabit import filter_segments seg = self._seg([(0, 100, 100), (50, 105, 105)]) # 2 events, min=5 result = filter_segments([seg], min_events=5, min_dist=10, max_span_ms=5000, max_gap_ms=200) assert result == [] def test_drops_segment_with_short_distance(self): from tools.data_adapters.balabit import filter_segments # Start (100,100), end click=(105,100) → dist=5, min_dist=50 events = [(i*10, 100+i, 100) for i in range(10)] seg = self._seg(events, click=(105, 100)) result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=200) assert result == [] def test_drops_segment_with_too_long_span(self): from tools.data_adapters.balabit import filter_segments # Span 6000ms, max_span=5000 events = [(0, 100, 100), (2000, 200, 200), (4000, 300, 300), (6000, 400, 400), (6010, 410, 400), (6020, 420, 400)] seg = self._seg(events, click=(500, 500)) result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=10000) assert result == [] def test_drops_segment_with_gap(self): from tools.data_adapters.balabit import filter_segments # Gap of 500ms between events 2 and 3, max_gap=200 events = [(0, 100, 100), (50, 110, 110), (100, 120, 120), (600, 200, 200), (650, 210, 210), (700, 220, 220)] seg = self._seg(events, click=(300, 300)) result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=200) assert result == [] def test_drops_segment_with_out_of_range_coords(self): from tools.data_adapters.balabit import filter_segments # x=10000 out of range events = [(i*10, 10000, 100) for i in range(6)] seg = self._seg(events, click=(10100, 100)) result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=200) assert result == [] def test_drops_segment_with_short_arc_length(self): """Total arc < 50 even though endpoints are far → high-frequency jitter only.""" from tools.data_adapters.balabit import filter_segments # Tiny back-and-forth with click 100px away — unrealistic, drop it events = [(i*10, 100 + (i % 2), 100) for i in range(10)] seg = self._seg(events, click=(200, 100)) # arc length = sum of |Δp| ≈ 9 (alternating ±1) which is < 50 result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=200) assert result == [] def test_keeps_valid_segment(self): from tools.data_adapters.balabit import filter_segments # Smooth 100→500 px straight line, 10 events, span 500ms events = [(i*50, 100 + i*40, 100) for i in range(10)] seg = self._seg(events, click=(500, 100)) result = filter_segments([seg], min_events=5, min_dist=50, max_span_ms=5000, max_gap_ms=200) assert len(result) == 1 class TestProcessSession: def test_writes_jsonl_in_expected_format(self, tmp_path): from tools.config import BalabitAdapterConfig from tools.data_adapters.balabit import process_session # Construct a Balabit-format CSV with one valid segment csv_path = tmp_path / "user_session_42" rows = [] # 10 Move events going from (100,100) to (500,200) over 500ms for i in range(10): t = i * 0.05 x = 100 + i * 40 y = 100 + i * 10 rows.append(f"0,{t:.3f},NoButton,Move,{x},{y}") rows.append(f"0,0.550,Left,Pressed,510,210") _write_csv(csv_path, rows) out = tmp_path / "out.jsonl" config = BalabitAdapterConfig( window_ms=1200, min_dist=50, min_events=5, max_span_ms=5000, max_gap_ms=200, ) n = process_session(csv_path, out, config) assert n == 1 assert out.exists() line = out.read_text(encoding="utf-8").strip() record = json.loads(line) assert record["meta"]["start"] == [100, 100] assert record["meta"]["end"] == [510, 210] assert record["meta"]["dist"] > 0 assert record["meta"]["source"] == "balabit" assert record["meta"]["session_id"] == "user_session_42" # Events: only move events, no down/up assert all(e["type"] == "move" for e in record["events"]) # Timestamps relative (start at 0) assert record["events"][0]["t"] == 0 def test_returns_zero_for_session_with_no_valid_segments(self, tmp_path): from tools.config import BalabitAdapterConfig from tools.data_adapters.balabit import process_session csv_path = tmp_path / "empty_session" _write_csv(csv_path, ["0,0.000,NoButton,Move,100,100"]) # no clicks out = tmp_path / "out.jsonl" config = BalabitAdapterConfig() n = process_session(csv_path, out, config) assert n == 0 # File may not exist or may be empty — both acceptable if out.exists(): assert out.read_text() == "" def test_appends_to_existing_jsonl(self, tmp_path): from tools.config import BalabitAdapterConfig from tools.data_adapters.balabit import process_session out = tmp_path / "out.jsonl" out.write_text('{"meta":{"start":[0,0],"end":[1,1]},"events":[]}\n', encoding="utf-8") csv_path = tmp_path / "session_x" rows = [f"0,{i*0.05:.3f},NoButton,Move,{100+i*40},100" for i in range(10)] rows.append("0,0.550,Left,Pressed,510,100") _write_csv(csv_path, rows) config = BalabitAdapterConfig() process_session(csv_path, out, config) lines = out.read_text(encoding="utf-8").strip().split("\n") assert len(lines) == 2 # original + appended