File size: 40,487 Bytes
ec4aa90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
"""Gradio UI for Legacy Code Modernizer Agent - Phase 5 Complete."""

import gradio as gr
import os
import asyncio
import logging
import zipfile
import tempfile
from dotenv import load_dotenv
from pathlib import Path

# Import orchestrator
import sys
import os
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
from src.workflow.orchestrator import ModernizationOrchestrator

# Load environment variables
load_dotenv()

# Configure logging with sensitive data redaction
class SensitiveDataFilter(logging.Filter):
    """Filter to redact sensitive information from logs."""
    def __init__(self):
        super().__init__()
        self.sensitive_patterns = []
        
        # Collect sensitive values from environment
        sensitive_keys = [
            "GEMINI_API_KEY", 
            "NEBIUS_API_KEY", 
            "OPENAI_API_KEY", 
            "MODAL_TOKEN_ID", 
            "MODAL_TOKEN_SECRET",
            "GITHUB_TOKEN"
        ]
        
        for key in sensitive_keys:
            value = os.getenv(key)
            if value and len(value) > 5:  # Only redact if value is substantial
                self.sensitive_patterns.append(value)

    def filter(self, record):
        msg = str(record.msg)
        for sensitive_value in self.sensitive_patterns:
            if sensitive_value in msg:
                msg = msg.replace(sensitive_value, "[REDACTED]")
        record.msg = msg
        return True

# Initialize logging with redaction
logging.basicConfig(level=logging.INFO)
root_logger = logging.getLogger()
root_logger.addFilter(SensitiveDataFilter())
logger = logging.getLogger(__name__)

# Initialize orchestrator with intelligent pattern matching
orchestrator = ModernizationOrchestrator(use_intelligent_matcher=True)


# Supported file extensions for single file upload
SUPPORTED_EXTENSIONS = {
    # Python
    '.py', '.pyw', '.pyx',
    # Java
    '.java',
    # JavaScript/TypeScript
    '.js', '.jsx', '.ts', '.tsx', '.mjs', '.cjs'
}

# Language to file extension mapping
LANGUAGE_EXTENSIONS = {
    'python': ['.py', '.pyw', '.pyx'],
    'java': ['.java'],
    'javascript': ['.js', '.jsx', '.mjs', '.cjs'],
    'typescript': ['.ts', '.tsx']
}

# Target version options for each language (Updated November 2025)
TARGET_VERSIONS = {
    'python': ['Python 3.14', 'Python 3.13', 'Python 3.12', 'Python 3.11', 'Python 3.10'],
    'java': ['Java 25 LTS', 'Java 23', 'Java 21 LTS', 'Java 17 LTS'],
    'javascript': ['ES2025', 'ES2024', 'Node.js 25', 'Node.js 24 LTS', 'Node.js 22 LTS'],
    'typescript': ['TypeScript 5.9', 'TypeScript 5.8', 'TypeScript 5.7', 'TypeScript 5.6']
}

# Framework-specific versions (Updated November 2025)
FRAMEWORK_VERSIONS = [
    'React 19', 'React 18', 'React 18 (Hooks)', 'React 17',
    'Angular 21', 'Angular 20', 'Angular 19',
    'Vue 3.5', 'Vue 3.4', 'Vue 2.7',
    'Django 5.2 LTS', 'Django 5.1', 'Django 5.0',
    'Flask 3.1', 'Flask 3.0', 'Flask 2.3',
    'Spring Boot 4.0', 'Spring Boot 3.4', 'Spring Boot 3.3',
    'Laravel 12', 'Laravel 11',
    'Rails 8.1', 'Rails 8.0', 'Rails 7.2',
    'Express 5.1', 'Express 5.0', 'Express 4.21',
    'FastAPI 0.122', 'FastAPI 0.115',
    'Next.js 16', 'Next.js 15', 'Next.js 14'
]

def detect_language_from_extension(file_ext):
    """Detect language from file extension."""
    for lang, exts in LANGUAGE_EXTENSIONS.items():
        if file_ext in exts:
            return lang
    return None


def get_target_versions_for_language(language):
    """Get appropriate target versions for a detected language."""
    if not language:
        # Return all options if language unknown
        all_versions = []
        for versions in TARGET_VERSIONS.values():
            all_versions.extend(versions)
        all_versions.extend(FRAMEWORK_VERSIONS)
        return sorted(set(all_versions))
    
    # Get language-specific versions
    versions = TARGET_VERSIONS.get(language, [])
    
    # Add framework versions for web languages
    if language in ['javascript', 'typescript']:
        versions.extend([v for v in FRAMEWORK_VERSIONS if 'React' in v or 'Angular' in v or 'Vue' in v or 'Express' in v])
    elif language == 'python':
        versions.extend([v for v in FRAMEWORK_VERSIONS if 'Django' in v or 'Flask' in v or 'FastAPI' in v])
    elif language == 'java':
        versions.extend([v for v in FRAMEWORK_VERSIONS if 'Spring' in v])
    elif language == 'php':
        versions.extend([v for v in FRAMEWORK_VERSIONS if 'Laravel' in v])
    elif language == 'ruby':
        versions.extend([v for v in FRAMEWORK_VERSIONS if 'Rails' in v])
    
    return versions if versions else get_target_versions_for_language(None)


def detect_languages_from_files(file_paths):
    """
    Detect languages from multiple files.
    
    Args:
        file_paths: List of file paths
        
    Returns:
        Dictionary with language counts and suggested target versions
    """
    language_counts = {}
    
    for file_path in file_paths:
        ext = Path(file_path).suffix.lower()
        lang = detect_language_from_extension(ext)
        if lang:
            language_counts[lang] = language_counts.get(lang, 0) + 1
    
    if not language_counts:
        return None, []
    
    # Get primary language (most files)
    primary_language = max(language_counts.items(), key=lambda x: x[1])[0]
    
    # Get suggested versions
    suggested_versions = get_target_versions_for_language(primary_language)
    
    return primary_language, suggested_versions


def validate_single_file(file_path):
    """
    Validate if a single file is supported for modernization.
    
    Args:
        file_path: Path to the uploaded file
        
    Returns:
        Tuple of (is_valid, message, file_info, suggested_versions)
    """
    if not file_path:
        return False, "❌ No file uploaded", None, []
    
    try:
        file_name = Path(file_path).name
        file_ext = Path(file_path).suffix.lower()
        file_size = os.path.getsize(file_path)
        
        # Check file extension
        if file_ext not in SUPPORTED_EXTENSIONS:
            supported_list = ', '.join(sorted(SUPPORTED_EXTENSIONS))
            return False, f"❌ Unsupported file type: {file_ext}\n\nβœ… Supported types:\n{supported_list}", None, []
        
        # Check file size (max 10MB for single file)
        max_size = 10 * 1024 * 1024  # 10MB
        if file_size > max_size:
            return False, f"❌ File too large: {file_size / 1024 / 1024:.2f} MB (max 10 MB)", None, []
        
        # Read file to check if it's valid text
        try:
            with open(file_path, 'r', encoding='utf-8') as f:
                content = f.read(1000)  # Read first 1000 chars
                line_count = len(content.split('\n'))
        except UnicodeDecodeError:
            return False, f"❌ File is not a valid text file (encoding error)", None, []
        
        # Detect language and get suggested versions
        language = detect_language_from_extension(file_ext)
        suggested_versions = get_target_versions_for_language(language)
        
        # Language name mapping
        language_names = {
            'python': 'Python',
            'java': 'Java',
            'javascript': 'JavaScript',
            'typescript': 'TypeScript'
        }
        
        file_info = {
            'name': file_name,
            'extension': file_ext,
            'size': file_size,
            'path': file_path,
            'language': language
        }
        
        lang_display = language_names.get(language, 'Unknown')
        
        message = f"""βœ… File validated successfully!

πŸ“„ File: {file_name}
πŸ“Š Type: {file_ext} ({lang_display})
πŸ’Ύ Size: {file_size / 1024:.2f} KB

🎯 Suggested target versions updated in dropdown

✨ Ready to modernize! Click 'Start Modernization' button."""
        
        return True, message, file_info, suggested_versions
        
    except Exception as e:
        return False, f"❌ Error validating file: {str(e)}", None, []


def process_single_file(file_path):
    """
    Process single file upload by creating a temporary ZIP.
    
    Args:
        file_path: Path to the uploaded file
        
    Returns:
        Tuple of (status message, zip path, suggested_versions)
    """
    is_valid, message, file_info, suggested_versions = validate_single_file(file_path)
    
    if not is_valid:
        return message, None, []
    
    try:
        # Create a temporary ZIP containing the single file
        import tempfile
        import zipfile
        
        zip_path = tempfile.NamedTemporaryFile(delete=False, suffix='.zip')
        with zipfile.ZipFile(zip_path.name, 'w', zipfile.ZIP_DEFLATED) as zipf:
            zipf.write(file_path, file_info['name'])
        
        return message, zip_path.name, suggested_versions
        
    except Exception as e:
        return f"❌ Error processing file: {str(e)}", None, []


def detect_languages_from_zip(zip_path):
    """
    Detect languages from files in a ZIP archive.
    
    Args:
        zip_path: Path to ZIP file
        
    Returns:
        Tuple of (language_summary, suggested_versions)
    """
    try:
        import zipfile
        
        file_paths = []
        with zipfile.ZipFile(zip_path, 'r') as zipf:
            file_paths = [name for name in zipf.namelist() if not name.endswith('/')]
        
        primary_language, suggested_versions = detect_languages_from_files(file_paths)
        
        if not primary_language:
            return "Multiple file types detected", []
        
        language_names = {
            'python': 'Python',
            'java': 'Java',
            'javascript': 'JavaScript',
            'typescript': 'TypeScript'
        }
        
        return f"Primary language: {language_names.get(primary_language, 'Unknown')}", suggested_versions
        
    except Exception as e:
        logger.error(f"Error detecting languages from ZIP: {e}")
        return "Could not detect language", []


def clone_github_repo(github_url):
    """
    Clone GitHub repository and show preview.
    
    Args:
        github_url: GitHub repository URL
        
    Returns:
        Tuple of (status message, cloned repo path)
    """
    if not github_url or not github_url.strip():
        return "❌ Please enter a GitHub repository URL", None, gr.update(visible=True)
    
    try:
        import tempfile
        import subprocess
        
        # Clean URL (remove .git if present)
        github_url = github_url.strip().rstrip('/')
        if github_url.endswith('.git'):
            github_url = github_url[:-4]
        
        # Create temp directory for clone
        temp_dir = tempfile.mkdtemp(prefix="github_clone_")
        
        # Clone repository
        result = subprocess.run(
            ["git", "clone", "--depth", "1", github_url, temp_dir],
            capture_output=True,
            text=True,
            timeout=300
        )
        
        if result.returncode != 0:
            error_msg = result.stderr if result.stderr else "Unknown error"
            return f"❌ Failed to clone repository:\n{error_msg}", None, gr.update(visible=True)
        
        # Count files (only supported extensions)
        code_extensions = {'.py', '.pyw', '.pyx', '.java', '.js', '.jsx', '.ts', '.tsx', '.mjs', '.cjs'}
        file_count = 0
        code_files = []
        
        for root, dirs, files in os.walk(temp_dir):
            # Skip .git directory
            if '.git' in root:
                continue
            for file in files:
                file_path = os.path.join(root, file)
                rel_path = os.path.relpath(file_path, temp_dir)
                ext = os.path.splitext(file)[1].lower()
                if ext in code_extensions:
                    file_count += 1
                    code_files.append(rel_path)
        
        # Create ZIP from cloned repo
        import zipfile
        zip_path = tempfile.NamedTemporaryFile(delete=False, suffix='.zip')
        with zipfile.ZipFile(zip_path.name, 'w', zipfile.ZIP_DEFLATED) as zipf:
            for root, dirs, files in os.walk(temp_dir):
                # Skip .git directory
                if '.git' in root:
                    continue
                for file in files:
                    file_path = os.path.join(root, file)
                    arcname = os.path.relpath(file_path, temp_dir)
                    zipf.write(file_path, arcname)
        
        # Detect languages
        all_code_files = []
        for root, dirs, files in os.walk(temp_dir):
            if '.git' in root:
                continue
            for file in files:
                ext = os.path.splitext(file)[1].lower()
                if ext in SUPPORTED_EXTENSIONS:
                    all_code_files.append(os.path.join(root, file))
        
        primary_language, suggested_versions = detect_languages_from_files(all_code_files)
        
        language_names = {
            'python': 'Python',
            'java': 'Java',
            'javascript': 'JavaScript',
            'typescript': 'TypeScript'
        }
        
        # Generate preview message with all files
        status = f"""βœ… Repository cloned successfully!

πŸ“ Repository: {github_url.split('/')[-1]}
πŸ“Š Code files found: {file_count}
πŸ”€ Primary language: {language_names.get(primary_language, 'Mixed')}

πŸ“ Loaded files ({file_count} total):
"""
        # Show all files, not just first 15
        for f in code_files:
            status += f"   β€’ {f}\n"
        
        status += "\n🎯 Suggested target versions updated in dropdown"
        status += "\n✨ Ready to modernize! Click 'Start Modernization' button above."
        
        return status, zip_path.name, gr.update(visible=True), suggested_versions
        
    except subprocess.TimeoutExpired:
        return "❌ Clone timeout (>5 minutes). Repository might be too large.", None, gr.update(visible=True)
    except Exception as e:
        return f"❌ Error cloning from GitHub: {str(e)}", None, gr.update(visible=True)


def modernize_code(repo_file, target_version, create_pr, repo_url, github_token, cloned_repo_path, single_file_path, progress=gr.Progress()):
    """
    Main function to process uploaded repository.
    
    Args:
        repo_file: Uploaded ZIP file containing the repository
        target_version: Target language/framework version
        create_pr: Whether to create GitHub PR
        repo_url: GitHub repository URL for PR
        github_token: GitHub personal access token for PR creation
        cloned_repo_path: Path to cloned repo ZIP (if using GitHub clone)
        single_file_path: Path to single file ZIP (if using single file upload)
        progress: Gradio progress tracker
        
    Returns:
        Tuple of (status message, download files)
    """
    logger.info(f"modernize_code called with: repo_file={repo_file}, single_file_path={single_file_path}, cloned_repo_path={cloned_repo_path}")
    
    # Priority: single file > cloned repo > uploaded file
    if single_file_path:
        logger.info(f"Single file path detected: {single_file_path}")
        repo_file = type('obj', (object,), {'name': single_file_path})()
        logger.info(f"Using single file path: {single_file_path}")
    elif cloned_repo_path:
        logger.info(f"Cloned repo path detected: {cloned_repo_path}")
        repo_file = type('obj', (object,), {'name': cloned_repo_path})()
        logger.info(f"Using cloned repo path: {cloned_repo_path}")
    else:
        logger.info("Using uploaded ZIP file")
    
    # Check if any valid input source is provided
    if repo_file is None:
        logger.error("No input source provided")
        return "❌ Please upload a repository ZIP file, single file, or clone from GitHub.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
    
    logger.info(f"Processing with file: {repo_file.name}")
    
    try:
        file_path = repo_file.name
        file_size = os.path.getsize(file_path)
        
        # Initial status
        status = f"""βœ… Processing started!
        
πŸ“ File: {Path(file_path).name}
πŸ“Š Size: {file_size / 1024:.2f} KB
🎯 Target: {target_version}

"""
        progress(0.05, desc="Starting...")
        yield status, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)  # Hide download buttons initially
        
        # Create a callback to update progress from orchestrator
        current_status = [status]  # Use list to allow modification in nested function
        
        def progress_callback(phase, message):
            """Callback to update progress from orchestrator."""
            phase_progress = {
                "Phase 1": 0.15,
                "Phase 2": 0.30,
                "Phase 3": 0.45,
                "Phase 4": 0.65,
                "Phase 5": 0.85
            }
            prog_value = phase_progress.get(phase, 0.5)
            progress(prog_value, desc=f"{phase}: {message}")
            current_status[0] += f"⏳ {phase}: {message}\n"
        
        # Run orchestrator with callback
        progress(0.1, desc="Initializing workflow...")
        
        loop = asyncio.new_event_loop()
        asyncio.set_event_loop(loop)
        
        results = loop.run_until_complete(
            orchestrator.modernize_repository(
                repo_path=file_path,
                target_version=target_version,
                create_pr=create_pr,
                repo_url=repo_url if create_pr else None,
                github_token=github_token if github_token and github_token.strip() else None,
                progress_callback=progress_callback
            )
        )
        
        loop.close()
        
        progress(0.95, desc="Preparing downloads...")
        status = current_status[0]
        
        # Prepare download files
        modernized_zip = None
        tests_zip = None
        report_file = None
        
        if results.get('output'):
            import zipfile
            import tempfile
            import time
            
            # Create timestamp for file naming
            timestamp = time.strftime("%Y%m%d_%H%M%S")
            
            output_dir = Path(results['output']['modernized_files'])
            
            # Get list of files that were actually transformed in this run
            transformed_files = []
            if results.get('phases', {}).get('transformation'):
                # Extract file paths from transformation results
                for t in results.get('transformations', []):
                    if 'file_path' in t:
                        transformed_files.append(Path(t['file_path']).name)
            
            # Create ZIP of modernized files with better naming - ONLY current run files
            if output_dir.exists() and transformed_files:
                modernized_zip = tempfile.NamedTemporaryFile(
                    delete=False, 
                    suffix='.zip',
                    prefix=f'modernized_code_{timestamp}_'
                )
                with zipfile.ZipFile(modernized_zip.name, 'w', zipfile.ZIP_DEFLATED) as zipf:
                    # Only include files from current transformation
                    for file in output_dir.iterdir():
                        if file.is_file() and file.name in transformed_files:
                            zipf.write(file, file.name)
                modernized_zip.close()
            else:
                modernized_zip = None
            
            # Create ZIP of test files with better naming - ONLY current run files
            tests_dir = Path(results['output']['test_files'])
            if tests_dir.exists() and transformed_files:
                tests_zip = tempfile.NamedTemporaryFile(
                    delete=False, 
                    suffix='.zip',
                    prefix=f'test_files_{timestamp}_'
                )
                with zipfile.ZipFile(tests_zip.name, 'w', zipfile.ZIP_DEFLATED) as zipf:
                    # Only include test files from current transformation
                    for file in tests_dir.iterdir():
                        if file.is_file():
                            # Check if this test file corresponds to a transformed file
                            test_base = file.name.replace('test_', '')
                            if test_base in transformed_files:
                                zipf.write(file, file.name)
                tests_zip.close()
            else:
                tests_zip = None
            
            # Create report file with UTF-8 encoding and better naming
            report_file = tempfile.NamedTemporaryFile(
                delete=False, 
                suffix='.txt',
                prefix=f'modernization_report_{timestamp}_',
                mode='w', 
                encoding='utf-8'
            )
            report_content = orchestrator.generate_report(results)
            report_file.write(report_content)
            report_file.close()
        
        # Generate final report
        if results['success']:
            status += "\n" + "=" * 60 + "\n"
            status += "βœ… MODERNIZATION COMPLETE!\n"
            status += "=" * 60 + "\n\n"
            
            stats = results.get('statistics', {})
            status += f"πŸ“Š **Statistics:**\n"
            status += f"   β€’ Total files: {stats.get('total_files', 0)}\n"
            status += f"   β€’ Files modernized: {stats.get('files_modernized', 0)}\n"
            status += f"   β€’ Tests generated: {stats.get('tests_generated', 0)}\n"
            status += f"   β€’ Test pass rate: {stats.get('test_pass_rate', 0):.1f}%\n"
            # Only show coverage if it's greater than 0
            if stats.get('average_coverage', 0) > 0:
                status += f"   β€’ Code coverage: {stats.get('average_coverage', 0):.1f}%\n"
            status += "\n"
            
            # Phase details
            phases = results.get('phases', {})
            
            if 'classification' in phases:
                c = phases['classification']
                status += f"πŸ“‹ **Classification:**\n"
                status += f"   β€’ High priority: {c.get('modernize_high', 0)} files\n"
                status += f"   β€’ Low priority: {c.get('modernize_low', 0)} files\n"
                status += f"   β€’ Skip: {c.get('skip', 0)} files\n\n"
            
            if 'search' in phases:
                s = phases['search']
                status += f"πŸ” **Semantic Search:**\n"
                status += f"   β€’ Indexed files: {s.get('indexed_files', 0)}\n"
                status += f"   β€’ Pattern groups: {s.get('pattern_groups', 0)}\n\n"
            
            if 'validation' in phases:
                v = phases['validation']
                status += f"βœ… **Validation:**\n"
                status += f"   β€’ Tests run: {v.get('total_tests', 0)}\n"
                status += f"   β€’ Tests passed: {v.get('tests_passed', 0)}\n"
                status += f"   β€’ Tests failed: {v.get('tests_failed', 0)}\n"
                status += f"   β€’ Pass rate: {v.get('pass_rate', 0):.1f}%\n"
                
                # Show execution mode
                exec_mode = v.get('execution_mode', 'unknown')
                if exec_mode == 'modal':
                    status += f"   β€’ Execution: πŸš€ Modal (cloud)\n\n"
                elif exec_mode == 'local':
                    status += f"   β€’ Execution: πŸ’» Local\n\n"
                else:
                    status += f"\n"
            
            if 'github_pr' in phases:
                pr = phases['github_pr']
                if pr.get('success'):
                    status += f"πŸ”— **GitHub PR:**\n"
                    status += f"   β€’ PR URL: {pr.get('pr_url', 'N/A')}\n"
                    status += f"   β€’ PR Number: #{pr.get('pr_number', 0)}\n"
                    status += f"   β€’ Branch: {pr.get('branch', 'N/A')}\n\n"
                else:
                    status += f"⚠️ **GitHub PR:** {pr.get('error', 'Failed')}\n\n"
            
            if results.get('errors'):
                status += f"⚠️ **Warnings:**\n"
                for error in results['errors'][:5]:
                    status += f"   β€’ {error}\n"
            
            # Add output locations
            if results.get('output'):
                status += f"\nπŸ“ **Output Locations:**\n"
                status += f"   β€’ Modernized files: {results['output']['modernized_files']}\n"
                status += f"   β€’ Test files: {results['output']['test_files']}\n"
                status += f"   β€’ Original files: {results['output']['original_files']}\n"
            
            status += "\n" + "=" * 60 + "\n"
            status += "πŸŽ‰ Ready for review and deployment!\n"
            status += "πŸ“₯ Download files using the buttons below.\n"
            
        else:
            status += "\n❌ MODERNIZATION FAILED\n\n"
            status += "Errors:\n"
            for error in results.get('errors', []):
                status += f"  β€’ {error}\n"
        
        progress(1.0, desc="Complete!")
        
        # Final yield with status and download files (make visible)
        yield (
            status, 
            gr.update(value=modernized_zip.name, visible=True) if modernized_zip else gr.update(visible=False),
            gr.update(value=tests_zip.name, visible=True) if tests_zip else gr.update(visible=False),
            gr.update(value=report_file.name, visible=True) if report_file else gr.update(visible=False)
        )
        
    except Exception as e:
        logger.error(f"Error in modernize_code: {e}", exc_info=True)
        progress(1.0, desc="Error occurred")
        yield f"❌ Error: {str(e)}\n\nPlease check logs for details.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)

# Custom CSS for better styling
custom_css = """
.gradio-container {
    font-family: 'Inter', sans-serif;
}
.header {
    text-align: center;
    padding: 20px;
    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
    color: white;
    border-radius: 10px;
    margin-bottom: 20px;
}
/* Style token input to match other inputs */
.token-input input {
    background-color: var(--input-background-fill) !important;
    border: 1px solid var(--input-border-color) !important;
}
"""

# Get execution mode info for display
from src.sandbox.config import EXECUTION_MODE, IS_HUGGINGFACE, MODAL_CONFIGURED

exec_mode_display = ""
if IS_HUGGINGFACE:
    if MODAL_CONFIGURED:
        exec_mode_display = "πŸš€ Running on Hugging Face Spaces with Modal (cloud execution)"
    else:
        exec_mode_display = "⚠️ Running on Hugging Face but Modal not configured - tests will fail!"
elif EXECUTION_MODE == "modal":
    exec_mode_display = "πŸš€ Modal execution enabled (cloud)"
elif EXECUTION_MODE == "local":
    exec_mode_display = "πŸ’» Local execution mode"
else:
    exec_mode_display = ""  # Don't show anything for auto mode

# Build Gradio interface
with gr.Blocks(title="Legacy Code Modernizer") as app:
    # Add custom CSS via HTML
    gr.HTML(f"""
        <style>
        {custom_css}
        </style>
        <div class="header">
            <h1>πŸ€– Legacy Code Modernizer</h1>
            <p>AI-powered code modernization for Python, Java, and JavaScript/TypeScript</p>
            <p style="font-size: 12px; opacity: 0.8; margin-top: 8px;">{exec_mode_display}</p>
        </div>
    """)
    
    gr.Markdown("""
    ### Modernization Workflow:
    1. **Discovery & Classification**: Analyze codebase structure and prioritize files
    2. **Semantic Search**: Group similar patterns using vector-based search
    3. **Code Transformation**: Apply AI-powered modernization patterns
    4. **Testing & Validation**: Generate tests and validate in secure sandbox
    5. **GitHub Integration**: Create pull requests with comprehensive documentation
    
    **Powered by**: Google Gemini, Nebius AI, LlamaIndex, Chroma, Modal, MCP Protocol
    """)
    
    with gr.Row():
        with gr.Column(scale=2):
            # Input method selection
            with gr.Tabs() as input_tabs:
                with gr.Tab("πŸ“„ Single File"):
                    single_file_input = gr.File(
                        label="Upload Single Code File",
                        file_types=[
                            ".py", ".pyw", ".pyx",
                            ".java",
                            ".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs"
                        ],
                        type="filepath"
                    )
                    
                    file_status = gr.Textbox(
                        label="File Status",
                        lines=8,
                        interactive=False,
                        visible=True
                    )
                    
                    single_file_path = gr.State(value=None)
                    
                    gr.Markdown("""
                    **Supported Languages**:
                    - Python (.py, .pyw, .pyx) - pytest with coverage
                    - Java (.java) - Maven + JUnit 5 + JaCoCo
                    - JavaScript (.js, .jsx, .mjs, .cjs) - Jest with coverage
                    - TypeScript (.ts, .tsx) - Jest with coverage
                    
                    **Max file size**: 10 MB per file
                    
                    **Note**: All supported languages include code transformation, test generation, and secure Modal sandbox execution with automatic dependency management.
                    """)
                
                with gr.Tab("πŸ“ Upload ZIP"):
                    file_input = gr.File(
                        label="Upload Repository (.zip)",
                        file_types=[".zip"],
                        type="filepath"
                    )
                
                with gr.Tab("πŸ”— Clone from GitHub"):
                    github_repo_url = gr.Textbox(
                        label="GitHub Repository URL",
                        placeholder="https://github.com/owner/repo",
                        info="Enter full GitHub URL to clone (without .git extension)"
                    )
                    
                    clone_btn = gr.Button(
                        "πŸ“₯ Load Repository",
                        variant="secondary",
                        size="sm"
                    )
                    
                    clone_status = gr.Textbox(
                        label="Repository Files",
                        lines=15,
                        interactive=False,
                        visible=False
                    )
                    
                    cloned_repo_path = gr.State(value=None)
                    
                    gr.Markdown("**Note**: Requires git to be installed on your system")
            
            # Build comprehensive target version list
            all_target_versions = []
            for versions in TARGET_VERSIONS.values():
                all_target_versions.extend(versions)
            all_target_versions.extend(FRAMEWORK_VERSIONS)
            all_target_versions = sorted(set(all_target_versions))
            
            target_version = gr.Dropdown(
                choices=all_target_versions,
                label="🎯 Target Version (auto-detected from files)",
                value="Python 3.14",
                info="Automatically updated based on uploaded files",
                allow_custom_value=False
            )
            
            # Add option to select from full list
            with gr.Accordion("πŸ“‹ Browse All Versions", open=False):
                gr.Markdown("""
                **Auto-detection incorrect?** Select from the full list below:
                
                **Python**: 3.14, 3.13, 3.12, 3.11, 3.10
                **Java**: 25 LTS, 23, 21 LTS, 17 LTS
                **JavaScript**: ES2025, ES2024, Node.js 25, 24 LTS, 22 LTS
                **TypeScript**: 5.9, 5.8, 5.7, 5.6
                
                **Frameworks**: React 19, Angular 21, Vue 3.5, Django 5.2 LTS, Spring Boot 4.0, Laravel 12, Rails 8.1, Next.js 16, FastAPI 0.122, and more
                
                Simply select your desired version from the dropdown above.
                """)
            
            with gr.Accordion("βš™οΈ Advanced Options", open=False):
                create_pr = gr.Checkbox(
                    label="Create GitHub PR",
                    value=False,
                    info="Automatically create pull request with modernized code"
                )
                
                repo_url = gr.Textbox(
                    label="GitHub Repository URL for PR",
                    placeholder="owner/repo (e.g., myorg/myproject)",
                    info="Required if creating PR"
                )
                
                github_token_input = gr.Textbox(
                    label="GitHub Personal Access Token",
                    placeholder="ghp_xxxxxxxxxxxxxxxxxxxx",
                    type="password",
                    info="Required for PR creation. Leave empty to use token from .env file",
                    container=True,
                    elem_classes=["token-input"]
                )
            
            process_btn = gr.Button(
                "πŸš€ Start Modernization",
                variant="primary",
                size="lg"
            )
        
        with gr.Column(scale=3):
            output = gr.Textbox(
                label="πŸ“Š Status & Progress",
                lines=25,
                max_lines=35
            )
    
    # Download section (separate row, below main interface)
    with gr.Row():
        download_modernized = gr.File(
            label="πŸ“¦ Download Modernized Code",
            visible=False
        )
        download_tests = gr.File(
            label="πŸ§ͺ Download Test Files",
            visible=False
        )
        download_report = gr.File(
            label="πŸ“„ Download Report",
            visible=False
        )
    
    with gr.Accordion("πŸ“– Features & Capabilities", open=False):
        gr.Markdown("""
        ### Core Features:
        
        **πŸ” Semantic Code Search**
        - Vector-based similarity search using LlamaIndex and Chroma
        - Automatic pattern grouping for efficient refactoring
        - Bulk code transformation capabilities
        
        **πŸ€– AI-Powered Analysis**
        - Powered by Google Gemini and Nebius AI models
        - Large context window for comprehensive code understanding
        - Multi-language support (Python, Java, JavaScript, TypeScript)
        
        **πŸ§ͺ Automated Testing**
        - Isolated test execution in Modal sandbox
        - Secure environment with no network access
        - Performance benchmarking and coverage reporting
        
        **πŸ”— GitHub Integration**
        - Automated pull request creation via MCP Protocol
        - Comprehensive documentation generation
        - Deployment checklists and rollback plans
        
        **πŸ“Š Quality Assurance**
        - High test pass rates with comprehensive coverage
        - Behavioral equivalence testing
        - Automated validation before deployment
        """)
    
    with gr.Accordion("🎯 Supported Languages & Versions", open=False):
        gr.Markdown("""
        ### Supported Languages (Updated November 2025):
        
        **Python**
        - Versions: 3.9, 3.10, 3.11, 3.12, 3.13
        - Frameworks: Django 5.1, Flask 3.1, FastAPI 0.115
        - Testing: pytest with coverage
        
        **Java**
        - Versions: Java 11 LTS, 17 LTS, 21 LTS, 23
        - Frameworks: Spring Boot 3.4
        - Testing: Maven + JUnit 5 + JaCoCo
        
        **JavaScript**
        - Standards: ES2023, ES2024, ES2025
        - Runtimes: Node.js 20 LTS, 22 LTS, 23
        - Frameworks: React 19, Angular 19, Vue 3.5, Express 5.0, Next.js 15
        - Testing: Jest with coverage
        
        **TypeScript**
        - Versions: 5.4, 5.5, 5.6, 5.7
        - Frameworks: React 19, Angular 19, Vue 3.5, Next.js 15
        - Testing: Jest with ts-jest
        """)
    
    # State for suggested versions
    suggested_versions_state = gr.State(value=[])
    
    # Event handlers
    # Handle single file validation (automatic on upload)
    def validate_and_show(file_path):
        """Wrapper to validate file and show status."""
        logger.info(f"validate_and_show called with file_path: {file_path}")
        if not file_path:
            logger.warning("No file path provided to validate_and_show")
            return "πŸ“„ Upload a code file to get started", None, gr.update(), []
        
        try:
            message, zip_path, suggested_versions = process_single_file(file_path)
            logger.info(f"Validation result: message='{message}', zip_path='{zip_path}', versions={len(suggested_versions)}")
            
            # Update dropdown with suggested versions
            if suggested_versions:
                return message, zip_path, gr.update(choices=suggested_versions, value=suggested_versions[0]), suggested_versions
            else:
                return message, zip_path, gr.update(), []
        except Exception as e:
            logger.error(f"Error in validate_and_show: {e}", exc_info=True)
            return f"❌ Error: {str(e)}", None, gr.update(), []
    
    # Handle ZIP file upload
    def handle_zip_upload(file_path):
        """Handle ZIP file upload and detect languages."""
        if not file_path:
            return gr.update(), []
        
        try:
            lang_summary, suggested_versions = detect_languages_from_zip(file_path)
            logger.info(f"ZIP upload: {lang_summary}, {len(suggested_versions)} versions")
            
            if suggested_versions:
                return gr.update(choices=suggested_versions, value=suggested_versions[0]), suggested_versions
            else:
                return gr.update(), []
        except Exception as e:
            logger.error(f"Error handling ZIP upload: {e}")
            return gr.update(), []
    
    # Auto-validate on file upload
    single_file_input.change(
        fn=validate_and_show,
        inputs=[single_file_input],
        outputs=[file_status, single_file_path, target_version, suggested_versions_state],
        show_progress=True
    )
    
    # Auto-detect on ZIP upload
    file_input.change(
        fn=handle_zip_upload,
        inputs=[file_input],
        outputs=[target_version, suggested_versions_state],
        show_progress=False
    )
    
    # Handle GitHub clone button
    def handle_github_clone(github_url):
        """Wrapper for GitHub clone with version detection."""
        status, zip_path, visibility, suggested_versions = clone_github_repo(github_url)
        
        if suggested_versions:
            return status, zip_path, visibility, gr.update(choices=suggested_versions, value=suggested_versions[0]), suggested_versions
        else:
            return status, zip_path, visibility, gr.update(), []
    
    clone_btn.click(
        fn=handle_github_clone,
        inputs=[github_repo_url],
        outputs=[clone_status, cloned_repo_path, clone_status, target_version, suggested_versions_state],
        show_progress=True
    )
    
    # Handle modernization
    process_btn.click(
        fn=modernize_code,
        inputs=[file_input, target_version, create_pr, repo_url, github_token_input, cloned_repo_path, single_file_path],
        outputs=[output, download_modernized, download_tests, download_report],
        show_progress="full"
    )
    
    # Examples
    gr.Examples(
        examples=[
            [None, "Python 3.12", False, "", "", None, None],
            [None, "Java 21 LTS", False, "", "", None, None],
            [None, "React 18 (Hooks)", True, "myorg/myproject", "", None, None]
        ],
        inputs=[file_input, target_version, create_pr, repo_url, github_token_input, cloned_repo_path, single_file_path],
        label="πŸ“ Example Configurations"
    )
    


if __name__ == "__main__":
    app.launch(
        server_name="0.0.0.0",
        server_port=7860,
        share=False,
        show_error=True,
        css=custom_css
    )