File size: 32,753 Bytes
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
edf1149
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
69256da
 
edf1149
 
69256da
edf1149
 
69256da
 
 
 
 
edf1149
 
 
69256da
 
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
69256da
 
edf1149
 
 
69256da
 
 
 
edf1149
 
 
 
 
 
 
 
 
3b1e6c7
 
 
 
 
 
edf1149
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
 
 
edf1149
 
 
 
 
 
69256da
 
 
 
 
 
 
 
 
 
 
edf1149
 
69256da
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
edf1149
 
 
 
 
 
 
 
69256da
 
 
 
 
 
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
 
 
 
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
69256da
edf1149
 
 
69256da
 
edf1149
 
69256da
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69256da
 
edf1149
 
 
 
 
 
 
 
 
 
 
 
 
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
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
# DEPENDENCIES
import json
from typing import Any
from typing import Dict
from typing import List
from pathlib import Path
from loguru import logger
from typing import Optional
from datetime import datetime
from dataclasses import dataclass
from detector.orchestrator import DetectionResult
from detector.attribution import AttributionResult
from reporter.reasoning_generator import DetailedReasoning
from reporter.reasoning_generator import ReasoningGenerator


@dataclass
class DetailedMetric:
    """
    Metric data structure with sub-metrics
    """
    name              : str
    ai_probability    : float
    human_probability : float
    confidence        : float
    verdict           : str
    description       : str
    detailed_metrics  : Dict[str, float]
    weight            : float


class ReportGenerator:
    """
    Generates comprehensive detection reports with detailed metrics
    
    Supports:
    - JSON (structured data with all details)
    - PDF (printable reports with tables and formatting)
    """
    def __init__(self, output_dir: Optional[Path] = None):
        """
        Initialize report generator
        
        Arguments:
        ----------
            output_dir { str } : Directory for saving reports (default: data/reports)
        """
        if (output_dir is None):
            output_dir = Path(__file__).parent.parent / "data" / "reports"
        
        self.output_dir = Path(output_dir)
        self.output_dir.mkdir(parents  = True, 
                              exist_ok = True,
                             )
        
        self.reasoning_generator = ReasoningGenerator()
        
        logger.info(f"ReportGenerator initialized (output_dir={self.output_dir})")
    

    def generate_complete_report(self, detection_result: DetectionResult, attribution_result: Optional[AttributionResult] = None, highlighted_sentences: Optional[List] = None, 
                                 formats: List[str] = ["json", "pdf"], filename_prefix: str = "ai_detection_report") -> Dict[str, str]:
        """
        Generate comprehensive report in JSON and PDF formats with detailed metrics
        
        Arguments:
        ----------
            detection_result      : Detection analysis result

            attribution_result    : Model attribution result (optional)

            highlighted_sentences : List of highlighted sentences (optional)
        
            formats               : List of formats to generate (json, pdf)
            
            filename_prefix       : Prefix for output filenames
            
        Returns:
        --------
                { dict }          : Dictionary mapping format to filepath
        """
        # Convert DetectionResult to dict for consistent access
        detection_dict = detection_result.to_dict() if hasattr(detection_result, 'to_dict') else detection_result
        
        # Generate detailed reasoning
        reasoning        = self.reasoning_generator.generate(ensemble_result    = detection_result.ensemble_result,
                                                             metric_results     = detection_result.metric_results,
                                                             domain             = detection_result.domain_prediction.primary_domain,
                                                             attribution_result = attribution_result,
                                                             text_length        = detection_result.processed_text.word_count,
                                                            )
        
        # Extract detailed metrics from ACTUAL detection results
        detailed_metrics = self._extract_detailed_metrics(detection_dict)
        
        # Timestamp for filenames
        timestamp        = datetime.now().strftime("%Y%m%d_%H%M%S")
        
        generated_files  = dict()
        
        # Generate requested formats
        if ("json" in formats):  
            json_path               = self._generate_json_report(detection_dict        = detection_dict, 
                                                                 reasoning             = reasoning, 
                                                                 detailed_metrics      = detailed_metrics, 
                                                                 attribution_result    = attribution_result,
                                                                 highlighted_sentences = highlighted_sentences,
                                                                 filename              = f"{filename_prefix}_{timestamp}.json",
                                                                )
            generated_files["json"] = str(json_path)
        
        if ("pdf" in formats):
            try:
                pdf_path               = self._generate_pdf_report(detection_dict        = detection_dict, 
                                                                   reasoning             = reasoning, 
                                                                   detailed_metrics      = detailed_metrics, 
                                                                   attribution_result    = attribution_result,
                                                                   highlighted_sentences = highlighted_sentences,
                                                                   filename              = f"{filename_prefix}_{timestamp}.pdf",
                                                                  )  
                generated_files["pdf"] = str(pdf_path)

            except Exception as e:
                logger.warning(f"PDF generation failed: {repr(e)}")
                logger.info("Install reportlab for PDF support: pip install reportlab")
        
        logger.info(f"Generated {len(generated_files)} report(s): {list(generated_files.keys())}")
        
        return generated_files


    def _extract_detailed_metrics(self, detection_dict: Dict) -> List[DetailedMetric]:
        """
        Extract detailed metrics with sub-metrics from ACTUAL detection result
        """
        detailed_metrics = list()
        metrics_data     = detection_dict.get("metrics", {})
        ensemble_data    = detection_dict.get("ensemble", {})
        
        # Get actual metric weights from ensemble
        metric_weights   = ensemble_data.get("metric_contributions", {})
        
        # Extract actual metric data
        for metric_name, metric_result in metrics_data.items():
            if not isinstance(metric_result, dict):
                continue
                
            if metric_result.get("error") is not None:
                continue
                
            # Get actual probabilities and confidence
            ai_prob    = metric_result.get("ai_probability", 0) * 100
            human_prob = metric_result.get("human_probability", 0) * 100
            confidence = metric_result.get("confidence", 0) * 100
            
            # Determine verdict based on actual probability
            if (ai_prob >= 60):
                verdict = "AI"

            elif (ai_prob <= 40):
                verdict = "HUMAN"

            else:
                verdict = "MIXED (AI + HUMAN)"
            
            # Get actual weight or use default
            weight = 0.0
            if metric_name in metric_weights:
                weight = metric_weights[metric_name].get("weight", 0.0) * 100
            
            # Extract actual detailed metrics from metric result
            detailed_metrics_data = self._extract_metric_details(metric_name   = metric_name, 
                                                                 metric_result = metric_result,
                                                                )
            
            # Get description based on metric type
            description           = self._get_metric_description(metric_name = metric_name)
            
            detailed_metrics.append(DetailedMetric(name              = metric_name,
                                                   ai_probability    = ai_prob,
                                                   human_probability = human_prob,
                                                   confidence        = confidence,
                                                   verdict           = verdict,
                                                   description       = description,
                                                   detailed_metrics  = detailed_metrics_data,
                                                   weight            = weight,
                                                  )
                                   )
        
        return detailed_metrics


    def _extract_metric_details(self, metric_name: str, metric_result: Dict) -> Dict[str, float]:
        """
        Extract detailed sub-metrics from metric result
        """
        details = dict()
        
        # Try to get details from metric result
        if metric_result.get("details"):
            details = metric_result["details"].copy()
        
        # If no details available, provide basic calculated values
        if not details:
            details = {"ai_probability"    : metric_result.get("ai_probability", 0) * 100,
                       "human_probability" : metric_result.get("human_probability", 0) * 100,
                       "confidence"        : metric_result.get("confidence", 0) * 100,
                       "score"             : metric_result.get("score", 0) * 100,
                      }
        
        return details


    def _get_metric_description(self, metric_name: str) -> str:
        """
        Get description for each metric type
        """
        descriptions = {"structural"                   : "Analyzes sentence structure, length patterns, and statistical features",
                        "perplexity"                   : "Measures text predictability using language model cross-entropy",
                        "entropy"                      : "Evaluates token diversity and sequence unpredictability",
                        "semantic_analysis"            : "Examines semantic coherence, topic consistency, and logical flow",
                        "linguistic"                   : "Assesses grammatical patterns, syntactic complexity, and style markers",
                        "multi_perturbation_stability" : "Tests text stability under perturbation using curvature analysis",
                       }

        return descriptions.get(metric_name, "Advanced text analysis metric.")


    def _generate_json_report(self, detection_dict: Dict, reasoning: DetailedReasoning, detailed_metrics: List[DetailedMetric], 
                              attribution_result: Optional[AttributionResult], highlighted_sentences: Optional[List] = None, filename: str = None) -> Path:
        """
        Generate JSON format report with detailed metrics
        """
        # Convert metrics to serializable format
        metrics_data = list()

        for metric in detailed_metrics:
            metrics_data.append({"name"              : metric.name,
                                 "ai_probability"    : metric.ai_probability,
                                 "human_probability" : metric.human_probability,
                                 "confidence"        : metric.confidence,
                                 "verdict"           : metric.verdict,
                                 "description"       : metric.description,
                                 "weight"            : metric.weight,
                                 "detailed_metrics"  : metric.detailed_metrics,
                               })
        
        # Convert highlighted sentences to serializable format
        highlighted_data = None
        
        if highlighted_sentences:
            highlighted_data = list()

            for sent in highlighted_sentences:
                highlighted_data.append({"text"           : sent.text,
                                         "ai_probability" : sent.ai_probability,
                                         "confidence"     : sent.confidence,
                                         "color_class"    : sent.color_class,
                                         "index"          : sent.index,
                                       })

        # Attribution data
        attribution_data = None
        
        if attribution_result:
            attribution_data = {"predicted_model"     : attribution_result.predicted_model.value,
                                "confidence"          : attribution_result.confidence,
                                "model_probabilities" : attribution_result.model_probabilities,
                                "reasoning"           : attribution_result.reasoning,
                                "fingerprint_matches" : attribution_result.fingerprint_matches,
                                "domain_used"         : attribution_result.domain_used.value,
                                "metric_contributions": attribution_result.metric_contributions,
                               }
        
        # Use ACTUAL detection results from dictionary
        ensemble_data = detection_dict.get("ensemble", {})
        analysis_data = detection_dict.get("analysis", {})
        metrics_data_dict = detection_dict.get("metrics", {})
        performance_data = detection_dict.get("performance", {})
        
        report_data     = {"report_metadata"     : {"generated_at" : datetime.now().isoformat(),
                                                    "version"      : "1.0.0",
                                                    "format"       : "json",
                                                    "report_id"    : filename.replace('.json', ''),
                                                   },
                           "overall_results"     : {"final_verdict"      : ensemble_data.get("final_verdict", "Unknown"),
                                                    "ai_probability"     : ensemble_data.get("ai_probability", 0),
                                                    "human_probability"  : ensemble_data.get("human_probability", 0),
                                                    "mixed_probability"  : ensemble_data.get("mixed_probability", 0),
                                                    "overall_confidence" : ensemble_data.get("overall_confidence", 0),
                                                    "uncertainty_score"  : ensemble_data.get("uncertainty_score", 0),
                                                    "consensus_level"    : ensemble_data.get("consensus_level", 0),
                                                    "domain"             : analysis_data.get("domain", "general"),
                                                    "domain_confidence"  : analysis_data.get("domain_confidence", 0),
                                                    "text_length"        : analysis_data.get("text_length", 0),
                                                    "sentence_count"     : analysis_data.get("sentence_count", 0),
                                                   },
                           "ensemble_analysis"   : {"method_used"     : "confidence_calibrated",
                                                    "metric_weights"  : ensemble_data.get("metric_contributions", {}),
                                                    "reasoning"       : ensemble_data.get("reasoning", []),
                                                   },
                           "detailed_metrics"    : metrics_data,
                           "detection_reasoning" : {"summary"                : reasoning.summary,
                                                    "key_indicators"         : reasoning.key_indicators,
                                                    "metric_explanations"    : reasoning.metric_explanations,
                                                    "supporting_evidence"    : reasoning.supporting_evidence,
                                                    "contradicting_evidence" : reasoning.contradicting_evidence,
                                                    "confidence_explanation" : reasoning.confidence_explanation,
                                                    "domain_analysis"        : reasoning.domain_analysis,
                                                    "ensemble_analysis"      : reasoning.ensemble_analysis,
                                                    "uncertainty_analysis"   : reasoning.uncertainty_analysis,
                                                    "recommendations"        : reasoning.recommendations,
                                                   },
                           "highlighted_text"    : highlighted_data,
                           "model_attribution"   : attribution_data,
                           "performance_metrics" : {"total_processing_time"  : performance_data.get("total_time", 0),
                                                    "metrics_execution_time" : performance_data.get("metrics_time", {}),
                                                    "warnings"               : detection_dict.get("warnings", []),
                                                    "errors"                 : detection_dict.get("errors", []),
                                                   }
                          }
        
        output_path     = self.output_dir / filename
        
        with open(output_path, 'w', encoding='utf-8') as f:
            json.dump(obj          = report_data, 
                      fp           = f, 
                      indent       = 4, 
                      ensure_ascii = False,
                     )
        
        logger.info(f"JSON report saved: {output_path}")
        return output_path


    def _generate_pdf_report(self, detection_dict: Dict, reasoning: DetailedReasoning, detailed_metrics: List[DetailedMetric], 
                             attribution_result: Optional[AttributionResult], highlighted_sentences: Optional[List] = None, filename: str = None) -> Path:
        """
        Generate PDF format report with detailed metrics
        """
        try:
            from reportlab.lib import colors
            from reportlab.lib.pagesizes import letter, A4
            from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
            from reportlab.lib.units import inch
            from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, PageBreak
            from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_JUSTIFY
        
        except ImportError:
            raise ImportError("reportlab is required for PDF generation. Install: pip install reportlab")
        
        output_path   = self.output_dir / filename
        
        # Create PDF
        doc           = SimpleDocTemplate(str(output_path),
                                          pagesize     = letter,
                                          rightMargin  = 50,
                                          leftMargin   = 50,
                                          topMargin    = 50,
                                          bottomMargin = 20,
                                         )
        
        # Container for PDF elements
        elements      = list()
        styles        = getSampleStyleSheet()
        
        # Custom styles
        title_style   = ParagraphStyle('CustomTitle',
                                       parent     = styles['Heading1'],
                                       fontSize   = 20,
                                       textColor  = colors.HexColor('#667eea'),
                                       spaceAfter = 20,
                                       alignment  = TA_CENTER,
                                      )
                                
        heading_style = ParagraphStyle('CustomHeading',
                                       parent      = styles['Heading2'],
                                       fontSize    = 14,
                                       textColor   = colors.HexColor('#111827'),
                                       spaceAfter  = 12,
                                       spaceBefore = 12,
                                      )
        
        body_style    = ParagraphStyle('CustomBody',
                                       parent     = styles['BodyText'],
                                       fontSize   = 10,
                                       alignment  = TA_JUSTIFY,
                                       spaceAfter = 8,
                                      )
        
        # Use detection results from dictionary
        ensemble_data = detection_dict.get("ensemble", {})
        analysis_data = detection_dict.get("analysis", {})
        
        # Title and main sections
        elements.append(Paragraph("AI Text Detection Analysis Report", title_style))
        elements.append(Paragraph(f"Generated on {datetime.now().strftime('%B %d, %Y at %I:%M %p')}", styles['Normal']))
        elements.append(Spacer(1, 0.3*inch))
        
        # Verdict section with ensemble metrics
        elements.append(Paragraph("Detection Summary", heading_style))
        verdict_data = [['Final Verdict:', ensemble_data.get("final_verdict", "Unknown")],
                        ['AI Probability:', f"{ensemble_data.get('ai_probability', 0):.1%}"],
                        ['Human Probability:', f"{ensemble_data.get('human_probability', 0):.1%}"],
                        ['Mixed Probability:', f"{ensemble_data.get('mixed_probability', 0):.1%}"],
                        ['Overall Confidence:', f"{ensemble_data.get('overall_confidence', 0):.1%}"],
                        ['Uncertainty Score:', f"{ensemble_data.get('uncertainty_score', 0):.1%}"],
                        ['Consensus Level:', f"{ensemble_data.get('consensus_level', 0):.1%}"],
                       ]
        
        verdict_table = Table(verdict_data, colWidths=[2*inch, 3*inch])
        verdict_table.setStyle(TableStyle([('BACKGROUND', (0, 0), (0, -1), colors.HexColor('#f8fafc')),
                                           ('FONTNAME', (0, 0), (0, -1), 'Helvetica-Bold'),
                                           ('FONTSIZE', (0, 0), (-1, -1), 10),
                                           ('BOTTOMPADDING', (0, 0), (-1, -1), 6),
                                         ])
                              )
        
        elements.append(verdict_table)
        elements.append(Spacer(1, 0.2*inch))
        
        # Content analysis
        elements.append(Paragraph("Content Analysis", heading_style))
        content_data = [['Content Domain:', analysis_data.get("domain", "general").title()],
                        ['Domain Confidence:', f"{analysis_data.get('domain_confidence', 0):.1%}"],
                        ['Word Count:', str(analysis_data.get("text_length", 0))],
                        ['Sentence Count:', str(analysis_data.get("sentence_count", 0))],
                        ['Processing Time:', f"{detection_dict.get('performance', {}).get('total_time', 0):.2f}s"],
                       ]
        
        content_table = Table(content_data, colWidths=[2*inch, 3*inch])
        content_table.setStyle(TableStyle([('FONTSIZE', (0, 0), (-1, -1), 10),
                                           ('BOTTOMPADDING', (0, 0), (-1, -1), 4),
                                         ])
                              )
        
        elements.append(content_table)
        elements.append(Spacer(1, 0.2*inch))
        
        # Ensemble Analysis
        elements.append(Paragraph("Ensemble Analysis", heading_style))
        elements.append(Paragraph("Method: Confidence Calibrated Aggregation", styles['Normal']))
        elements.append(Spacer(1, 0.1*inch))
        
        # Metric weights table
        metric_contributions = ensemble_data.get("metric_contributions", {})
        if metric_contributions:
            elements.append(Paragraph("Metric Weights", styles['Heading3']))
            weight_data = [['Metric', 'Weight']]
            for metric, contribution in metric_contributions.items():
                weight = contribution.get("weight", 0)
                weight_data.append([metric.title(), f"{weight:.1%}"])
            
            weight_table = Table(weight_data, colWidths=[3*inch, 1*inch])
            weight_table.setStyle(TableStyle([('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#667eea')),
                                              ('TEXTCOLOR', (0, 0), (-1, 0), colors.white),
                                              ('ALIGN', (0, 0), (-1, -1), 'LEFT'),
                                              ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
                                              ('FONTSIZE', (0, 0), (-1, -1), 9),
                                              ('BOTTOMPADDING', (0, 0), (-1, -1), 4),
                                              ('GRID', (0, 0), (-1, -1), 1, colors.black),
                                            ])
                                 )
            elements.append(weight_table)
            elements.append(Spacer(1, 0.2*inch))
        
        # Detailed metrics
        elements.append(Paragraph("Detailed Metric Analysis", heading_style))
        for metric in detailed_metrics:
            elements.append(Paragraph(f"{metric.name.title().replace('_', ' ')}", styles['Heading3']))
            metric_data = [['Verdict:', metric.verdict],
                           ['AI Probability:', f"{metric.ai_probability:.1f}%"],
                           ['Human Probability:', f"{metric.human_probability:.1f}%"],
                           ['Confidence:', f"{metric.confidence:.1f}%"],
                           ['Ensemble Weight:', f"{metric.weight:.1f}%"],
                          ]
            
            metric_table = Table(metric_data, colWidths=[1.5*inch, 1.5*inch])
            metric_table.setStyle(TableStyle([('FONTSIZE', (0, 0), (-1, -1), 9),
                                              ('BOTTOMPADDING', (0, 0), (-1, -1), 2),
                                            ])
                                 )
            
            elements.append(metric_table)
            elements.append(Paragraph(metric.description, body_style))
            
            # Add detailed sub-metrics if available
            if metric.detailed_metrics:
                elements.append(Paragraph("Detailed Metrics:", styles['Heading4']))
                sub_metric_data = [['Metric', 'Value']]
                for sub_name, sub_value in list(metric.detailed_metrics.items())[:6]:  # Show top 6
                    sub_metric_data.append([sub_name.replace('_', ' ').title(), f"{sub_value:.2f}"])
                
                sub_metric_table = Table(sub_metric_data, colWidths=[2*inch, 1*inch])
                sub_metric_table.setStyle(TableStyle([('FONTSIZE', (0, 0), (-1, -1), 8),
                                                      ('BOTTOMPADDING', (0, 0), (-1, -1), 2),
                                                      ('GRID', (0, 0), (-1, -1), 1, colors.grey),
                                                    ])
                                         )

                elements.append(sub_metric_table)
            
            elements.append(Spacer(1, 0.1*inch))
        
        # Detection Reasoning
        elements.append(Paragraph("Detection Reasoning", heading_style))
        elements.append(Paragraph(reasoning.summary, body_style))
        elements.append(Spacer(1, 0.1*inch))
        
        # Key Indicators
        elements.append(Paragraph("Key Indicators", styles['Heading3']))
        for indicator in reasoning.key_indicators[:5]:  # Show top 5
            elements.append(Paragraph(f"• {indicator}", body_style))
        
        elements.append(Spacer(1, 0.1*inch))
        
        # Confidence Explanation
        elements.append(Paragraph("Confidence Analysis", styles['Heading3']))
        elements.append(Paragraph(reasoning.confidence_explanation, body_style))
        elements.append(Spacer(1, 0.1*inch))
        
        # Uncertainty Analysis
        elements.append(Paragraph("Uncertainty Analysis", styles['Heading3']))
        elements.append(Paragraph(reasoning.uncertainty_analysis, body_style))
        
        # Model Attribution Section
        if attribution_result:
            elements.append(PageBreak())
            elements.append(Paragraph("AI Model Attribution", heading_style))
            
            # Attribution summary
            predicted_model = attribution_result.predicted_model.value.replace("_", " ").title()
            confidence = attribution_result.confidence * 100
            
            attribution_summary = [['Predicted Model:', predicted_model],
                                   ['Attribution Confidence:', f"{confidence:.1f}%"],
                                   ['Domain Used:', attribution_result.domain_used.value.title()],
                                  ]
            
            attribution_table = Table(attribution_summary, colWidths=[2*inch, 3*inch])
            attribution_table.setStyle(TableStyle([('BACKGROUND', (0, 0), (0, -1), colors.HexColor('#f8fafc')),
                                                   ('FONTNAME', (0, 0), (0, -1), 'Helvetica-Bold'),
                                                   ('FONTSIZE', (0, 0), (-1, -1), 10),
                                                   ('BOTTOMPADDING', (0, 0), (-1, -1), 6),
                                                 ])
                                      )
            
            elements.append(attribution_table)
            elements.append(Spacer(1, 0.1*inch))
            
            # Model probabilities table
            if attribution_result.model_probabilities:
                elements.append(Paragraph("Model Probability Breakdown", styles['Heading3']))
                
                prob_data     = [['Model', 'Probability']]
                
                # Show top 5
                sorted_models = sorted(attribution_result.model_probabilities.items(),
                                       key     = lambda x: x[1],
                                       reverse = True)[:5]
                
                for model_name, probability in sorted_models:
                    display_name = model_name.replace("_", " ").replace("-", " ").title()
                    prob_data.append([display_name, f"{probability:.1%}"])
                
                prob_table = Table(prob_data, colWidths=[3*inch, 1*inch])
                prob_table.setStyle(TableStyle([('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#667eea')),
                                                ('TEXTCOLOR', (0, 0), (-1, 0), colors.white),
                                                ('ALIGN', (0, 0), (-1, -1), 'LEFT'),
                                                ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
                                                ('FONTSIZE', (0, 0), (-1, -1), 9),
                                                ('BOTTOMPADDING', (0, 0), (-1, -1), 4),
                                                ('GRID', (0, 0), (-1, -1), 1, colors.black),
                                              ])
                                   )
                
                elements.append(prob_table)
                elements.append(Spacer(1, 0.2*inch))
            
            # Attribution reasoning
            if attribution_result.reasoning:
                elements.append(Paragraph("Attribution Reasoning", styles['Heading3']))
                for reason in attribution_result.reasoning[:3]:  # Show top 3 reasons
                    elements.append(Paragraph(f"• {reason}", body_style))
        
        # Recommendations
        elements.append(PageBreak())
        elements.append(Paragraph("Recommendations", heading_style))
        for recommendation in reasoning.recommendations:
            elements.append(Paragraph(f"• {recommendation}", body_style))
        
        # Footer
        elements.append(Spacer(1, 0.3*inch))
        elements.append(Paragraph(f"Generated by AI Text Detector v2.0 | Processing Time: {detection_dict.get('performance', {}).get('total_time', 0):.2f}s", 
                        ParagraphStyle('Footer', parent=styles['Normal'], fontSize=8, textColor=colors.gray)))
        
        # Build PDF
        doc.build(elements)
        
        logger.info(f"PDF report saved: {output_path}")
        return output_path



# Export
__all__ = ["ReportGenerator", 
           "DetailedMetric",
          ]