File size: 13,317 Bytes
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
 
4780d8d
6ba0947
 
 
 
 
 
4780d8d
 
6ba0947
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
 
 
 
 
 
 
 
 
4780d8d
 
6ba0947
 
 
 
 
 
 
 
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ba0947
4780d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
"""Tests for UI event handlers and state management.

This module tests complex event interactions in the Mosaic Gradio UI, including:
- Settings state management across events
- Generator behavior and incremental updates
- Error and warning display
"""

import pytest
import pandas as pd
from unittest.mock import Mock, patch, MagicMock
from pathlib import Path
import inspect

from mosaic.ui.app import (
    analyze_slides,
    set_cancer_subtype_maps,
)
from mosaic.ui.utils import SETTINGS_COLUMNS, validate_settings, load_settings


class TestSettingsStateManagement:
    """Test settings state management across multiple events."""

    def test_csv_upload_replaces_settings(
        self, sample_csv_valid, mock_cancer_subtype_maps
    ):
        """Test CSV upload replaces existing settings."""
        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )

        # Load CSV
        loaded_df = load_settings(sample_csv_valid)
        validated_df = validate_settings(
            loaded_df, cancer_subtype_name_map, cancer_subtypes, reversed_map
        )

        # Verify new settings loaded
        assert len(validated_df) == 3
        assert validated_df.iloc[0]["Slide"] == "slide1.svs"
        assert validated_df.iloc[1]["Slide"] == "slide2.svs"


class TestGeneratorBehavior:
    """Test generator behavior for incremental updates."""

    @patch("mosaic.ui.app.analyze_slide")
    @patch("mosaic.ui.app.create_user_directory")
    def test_analyze_slides_is_generator(
        self,
        mock_create_dir,
        mock_analyze,
        sample_files_single,
        mock_analyze_slide_results,
        mock_cancer_subtype_maps,
        temp_output_dir,
    ):
        """Test analyze_slides returns a generator."""
        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )
        set_cancer_subtype_maps(cancer_subtype_name_map, reversed_map, cancer_subtypes)

        mock_create_dir.return_value = temp_output_dir
        mock_analyze.return_value = mock_analyze_slide_results

        settings_df = pd.DataFrame(
            {
                "Slide": ["test_slide_1.svs"],
                "Site Type": ["Primary"],
                "Sex": ["Male"],
                "Tissue Site": ["Unknown"],
                "Cancer Subtype": ["Unknown"],
                "IHC Subtype": [""],
                "Segmentation Config": ["Biopsy"],
            }
        )

        result = analyze_slides(
            sample_files_single,
            settings_df,
            "Primary",
            "Unknown",
            "Unknown",
            "Unknown",
            "",
            "Biopsy",
            temp_output_dir,
        )

        # Verify it's a generator
        assert inspect.isgenerator(result)

    @patch("mosaic.ui.app.load_all_models")
    @patch("mosaic.ui.app.analyze_slide")
    @patch("mosaic.ui.app.create_user_directory")
    def test_intermediate_yields_update_masks_only(
        self,
        mock_create_dir,
        mock_analyze,
        mock_load_models,
        sample_files_multiple,
        mock_analyze_slide_results,
        mock_model_cache,
        mock_cancer_subtype_maps,
        temp_output_dir,
    ):
        """Test intermediate yields show only slide masks."""
        from PIL import Image

        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )
        set_cancer_subtype_maps(cancer_subtype_name_map, reversed_map, cancer_subtypes)

        mock_create_dir.return_value = temp_output_dir
        mock_load_models.return_value = mock_model_cache

        # Return fresh DataFrames on each call
        def mock_analyze_side_effect(*args, **kwargs):
            mask = Image.new("RGB", (100, 100), color="red")
            aeon_results = pd.DataFrame(
                {"Cancer Subtype": ["LUAD"], "Confidence": [0.95]}
            )
            paladin_results = pd.DataFrame(
                {
                    "Cancer Subtype": ["LUAD", "LUAD", "LUAD"],
                    "Biomarker": ["TP53", "KRAS", "EGFR"],
                    "Score": [0.85, 0.72, 0.63],
                }
            )
            return (mask, aeon_results, paladin_results)

        mock_analyze.side_effect = mock_analyze_side_effect

        settings_df = pd.DataFrame(
            {
                "Slide": ["test_slide_1.svs", "test_slide_2.svs", "test_slide_3.svs"],
                "Site Type": ["Primary", "Primary", "Primary"],
                "Sex": ["Male", "Female", "Male"],
                "Tissue Site": ["Unknown", "Unknown", "Unknown"],
                "Cancer Subtype": ["Unknown", "Unknown", "Unknown"],
                "IHC Subtype": ["", "", ""],
                "Segmentation Config": ["Biopsy", "Biopsy", "Biopsy"],
            }
        )

        gen = analyze_slides(
            sample_files_multiple,
            settings_df,
            "Primary",
            "Unknown",
            "Unknown",
            "Unknown",
            "",
            "Biopsy",
            temp_output_dir,
        )

        # Get first intermediate yield (after first slide)
        first_yield = next(gen)

        # Should be tuple with 7 elements (added settings_input back)
        assert len(first_yield) == 7

        # First element is settings_input (visible during processing for progress)
        settings = first_yield[0]
        assert hasattr(settings, "visible") and settings.visible

        # Second element is slide_masks (should have 1 entry)
        slide_masks = first_yield[1]
        assert len(slide_masks) == 1

        # Third element should be AEON results DataFrame (now visible with partial results)
        aeon_output = first_yield[2]
        # Should have a DataFrame (not hidden anymore)
        assert aeon_output is not None

        # Fourth element should be AEON download button (hidden until complete)
        aeon_download = first_yield[3]
        # Download button should be hidden during intermediate yields
        assert hasattr(aeon_download, "visible") and not aeon_download.visible

        # Fifth element should be PALADIN results DataFrame (partial results)
        paladin_output = first_yield[4]
        # Should have data (DataFrame with partial results)
        assert paladin_output is not None

        # Sixth element should be PALADIN download button (hidden until complete)
        paladin_download = first_yield[5]
        # Download button should be hidden during intermediate yields
        assert hasattr(paladin_download, "visible") and not paladin_download.visible

    @patch("mosaic.ui.app.load_all_models")
    @patch("mosaic.ui.app.analyze_slide")
    @patch("mosaic.ui.app.create_user_directory")
    def test_final_yield_has_complete_results(
        self,
        mock_create_dir,
        mock_analyze,
        mock_load_models,
        sample_files_multiple,
        mock_analyze_slide_results,
        mock_model_cache,
        mock_cancer_subtype_maps,
        temp_output_dir,
    ):
        """Test final yield contains complete results."""
        from PIL import Image

        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )
        set_cancer_subtype_maps(cancer_subtype_name_map, reversed_map, cancer_subtypes)

        mock_create_dir.return_value = temp_output_dir
        mock_load_models.return_value = mock_model_cache

        # Return fresh DataFrames on each call
        def mock_analyze_side_effect(*args, **kwargs):
            mask = Image.new("RGB", (100, 100), color="red")
            aeon_results = pd.DataFrame(
                {"Cancer Subtype": ["LUAD"], "Confidence": [0.95]}
            )
            paladin_results = pd.DataFrame(
                {
                    "Cancer Subtype": ["LUAD", "LUAD", "LUAD"],
                    "Biomarker": ["TP53", "KRAS", "EGFR"],
                    "Score": [0.85, 0.72, 0.63],
                }
            )
            return (mask, aeon_results, paladin_results)

        mock_analyze.side_effect = mock_analyze_side_effect

        settings_df = pd.DataFrame(
            {
                "Slide": ["test_slide_1.svs", "test_slide_2.svs", "test_slide_3.svs"],
                "Site Type": ["Primary", "Primary", "Primary"],
                "Sex": ["Male", "Female", "Male"],
                "Tissue Site": ["Unknown", "Unknown", "Unknown"],
                "Cancer Subtype": ["Unknown", "Unknown", "Unknown"],
                "IHC Subtype": ["", "", ""],
                "Segmentation Config": ["Biopsy", "Biopsy", "Biopsy"],
            }
        )

        gen = analyze_slides(
            sample_files_multiple,
            settings_df,
            "Primary",
            "Unknown",
            "Unknown",
            "Unknown",
            "",
            "Biopsy",
            temp_output_dir,
        )

        # Consume generator to get final yield
        results = list(gen)
        final_yield = results[-1]

        # Final yield should have all results (7 elements with settings_input)
        assert len(final_yield) == 7

        # First element is settings_input (should be visible for 3 slides)
        settings = final_yield[0]
        assert hasattr(settings, "visible") and settings.visible  # Visible for multiple slides

        # Second element is slide_masks
        slide_masks = final_yield[1]
        assert len(slide_masks) == 3  # All 3 slides

        # AEON download button should be visible on final yield (4th element, index 3)
        aeon_download = final_yield[3]
        assert hasattr(aeon_download, "visible") and aeon_download.visible

        # PALADIN download button should be visible on final yield (6th element, index 5)
        paladin_download = final_yield[5]
        assert hasattr(paladin_download, "visible") and paladin_download.visible


class TestErrorDisplay:
    """Test error and warning display behavior."""

    @patch("mosaic.ui.app.create_user_directory")
    def test_no_slides_raises_gr_error(
        self, mock_create_dir, mock_cancer_subtype_maps, temp_output_dir
    ):
        """Test that no slides raises gr.Error."""
        import gradio as gr

        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )
        set_cancer_subtype_maps(cancer_subtype_name_map, reversed_map, cancer_subtypes)

        mock_create_dir.return_value = temp_output_dir

        gen = analyze_slides(
            None,
            None,
            "Primary",
            "Unknown",
            "Unknown",
            "Unknown",
            "",
            "Biopsy",
            temp_output_dir,
        )

        # Should raise gr.Error
        with pytest.raises(gr.Error):
            next(gen)

    @patch("mosaic.ui.utils.gr.Warning")
    def test_validation_warnings_shown(self, mock_warning, mock_cancer_subtype_maps):
        """Test validation warnings are displayed."""
        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )

        # Create DataFrame with multiple invalid values
        df = pd.DataFrame(
            {
                "Slide": ["test1.svs", "test2.svs"],
                "Site Type": ["InvalidSite", "Primary"],
                "Sex": ["Unknown", "InvalidSex"],
                "Tissue Site": ["Unknown", "Unknown"],
                "Cancer Subtype": ["InvalidSubtype", "Unknown"],
                "IHC Subtype": ["", ""],
                "Segmentation Config": ["Biopsy", "InvalidConfig"],
            }
        )

        result = validate_settings(
            df, cancer_subtype_name_map, cancer_subtypes, reversed_map
        )

        # Should have warning calls (at least 1 for the multiple invalid values)
        assert mock_warning.call_count >= 1

        # Verify defaults applied
        assert result.iloc[0]["Site Type"] == "Primary"  # Invalid → Primary
        assert result.iloc[0]["Cancer Subtype"] == "Unknown"  # Invalid → Unknown
        assert result.iloc[1]["Sex"] == ""  # Invalid → empty string
        assert result.iloc[1]["Segmentation Config"] == "Biopsy"  # Invalid → Biopsy

    @patch("mosaic.ui.app.create_user_directory")
    def test_settings_mismatch_raises_gr_error(
        self,
        mock_create_dir,
        sample_files_multiple,
        sample_settings_df,
        mock_cancer_subtype_maps,
        temp_output_dir,
    ):
        """Test settings/files count mismatch raises gr.Error."""
        import gradio as gr

        cancer_subtype_name_map, reversed_map, cancer_subtypes = (
            mock_cancer_subtype_maps
        )
        set_cancer_subtype_maps(cancer_subtype_name_map, reversed_map, cancer_subtypes)

        mock_create_dir.return_value = temp_output_dir

        # Create mismatch: 2 files but 3 settings rows
        two_files = sample_files_multiple[:2]

        gen = analyze_slides(
            two_files,
            sample_settings_df,
            "Primary",
            "Unknown",
            "Unknown",
            "Unknown",
            "",
            "Biopsy",
            temp_output_dir,
        )

        # Should raise gr.Error about mismatch
        with pytest.raises(gr.Error):
            next(gen)