File size: 15,393 Bytes
c732cdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fea994e
 
 
 
 
 
c732cdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fea994e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c732cdb
 
fea994e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c732cdb
 
fea994e
c732cdb
fea994e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c732cdb
 
 
fea994e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c732cdb
fea994e
 
 
 
 
c732cdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fea994e
 
c732cdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fea994e
c732cdb
 
 
 
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
"""
The Lecturer's Stone - Standalone CLI.
Analyzes raw strings and documents (.docx, .xlsx, .pptx, .pdf, .txt, .md).
Inspects container metadata, detects generator signatures (openpyxl, python-docx, etc.),
and provides one-click sanitization or super-sanitization (nuke).
"""

import os
import sys
import argparse
import json
from pathlib import Path

# Add current directory to path
current_dir = Path(__file__).resolve().parent
if str(current_dir) not in sys.path:
    sys.path.insert(0, str(current_dir))

from document_parser import extract_text_from_file
from metadata_forensics import inspect_metadata, cleanse_metadata, DEFAULT_AUTHOR
sanitize_metadata = cleanse_metadata


def format_color_bar(probability: float, length: int = 24) -> str:
    filled = int(round(probability * length))
    empty = length - filled
    pct = round(probability * 100, 1)
    bar = "[" + "#" * filled + "-" * empty + f"] {pct}%"
    return bar


def print_metadata_section(meta: dict, action_note: str = None):
    print("\n" + "=" * 64)
    print(" THE LECTURER'S STONE - METADATA FORENSICS & CONTAINER")
    print("=" * 64)
    print(f"File:               {meta.get('file_name')} ({meta.get('file_type')})")

    all_auths = meta.get('all_authors', [])
    authors_str = ", ".join(all_auths) if all_auths else "[None / Stripped]"
    print(f"All Authors/Owners: {authors_str}")
    print(f"Primary Creator:    {meta.get('creator') or '[None / Stripped]'}")
    print(f"Last Modifier:      {meta.get('last_modified_by') or '[None / Stripped]'}")
    if meta.get('comment_authors'):
        print(f"Comment Authors:    {', '.join(meta['comment_authors'])}")
    if meta.get('contributors'):
        print(f"Contributors:       {', '.join(meta['contributors'])}")

    app_info = meta.get('application') or 'Unknown'
    if meta.get('app_version'):
        app_info += f" (v{meta.get('app_version')})"
    print(f"Application:        {app_info}")

    if meta.get('company'):
        print(f"Company:            {meta.get('company')}")
    if meta.get('manager'):
        print(f"Manager:            {meta.get('manager')}")

    created_str = meta.get('created_formatted') or meta.get('created') or '[None]'
    modified_str = meta.get('modified_formatted') or meta.get('modified') or '[None]'
    print(f"Created:            {created_str}")
    print(f"Modified:           {modified_str}")

    rev = meta.get('revision')
    edit_time = meta.get('total_edit_time_min')
    if rev or edit_time:
        rev_part = f"Rev {rev}" if rev else "Rev N/A"
        time_part = f"{edit_time} min edit time" if edit_time else "edit time N/A"
        print(f"Revision / Time:    {rev_part} | {time_part}")

    env_details = meta.get('environment_details', {})
    env_items = [f"{k}: {v}" for k, v in env_details.items() if k not in ["Application", "AppVersion", "Company", "Manager", "TotalTime"]]
    if env_items:
        print(f"Environment:        {', '.join(env_items[:3])}")

    risk = meta.get('risk_level', 'CLEAN')
    print(f"Forensic Risk:      [{risk}] {meta.get('verdict')}")
    clues = meta.get('clues', [])
    if clues:
        print("\nDetected Programmatic Clues:")
        for clue in clues:
            print(f" [!] {clue}")
    else:
        print("\nDetected Programmatic Clues: None (No automated generator fingerprints found)")

    if action_note:
        print("-" * 64)
        print(f"ACTION: {action_note}")

    print("=" * 64)


def main():
    parser = argparse.ArgumentParser(
        description="The Lecturer's Stone - Multi-Service AI Content Detection, Container Metadata Forensics, and Cleanser."
    )
    group = parser.add_mutually_exclusive_group(required=True)
    group.add_argument("-t", "--text", type=str, help="Plain text string to analyze.")
    group.add_argument(
        "-f", "--file", "--files",
        dest="files",
        nargs="+",
        help="Path(s) to document file(s), directory, or glob pattern (.txt, .md, .pdf, .docx, .xlsx, .pptx)."
    )

    # Metadata & Cleansing Options
    parser.add_argument("--cleanse", "--sanitize", dest="cleanse", nargs="?", const="", default=None, metavar="OUT_PATH",
                        help="Cleanse metadata (Creator/Modifier -> Author, preserves old creation date, cleans environment).")
    parser.add_argument("--author", type=str, default=DEFAULT_AUTHOR,
                        help=f"Author / Creator name to apply when cleansing (default: from LECTURERS_STONE_AUTHOR or '{DEFAULT_AUTHOR}').")
    parser.add_argument("--skip-ai", action="store_true",
                        help="Skip AI NLP model analysis (perform metadata inspection / cleansing only).")

    # AI Detection Options
    parser.add_argument("--json", action="store_true", help="Output results in JSON format.")
    parser.add_argument("--services", nargs="+", choices=["local_deberta", "szegedai", "radar", "fakespot", "yugamj", "piratexx", "heuristic"], help="Specific services to check (default: all active).")
    parser.add_argument("--export", type=str, default=None, help="Export detailed report to file (e.g. report.json).")

    args = parser.parse_args()

    # Collect files if provided
    SUPPORTED_EXTENSIONS = {
        ".txt", ".md", ".markdown", ".rtf", ".rst", ".py", ".json", ".csv",
        ".pdf", ".docx", ".doc", ".pptx", ".ppt", ".xlsx", ".xlsm", ".xltx"
    }

    if args.files:
        collected_paths = []
        for item in args.files:
            p = Path(item)
            if p.is_file():
                collected_paths.append(p)
            elif p.is_dir():
                for f in sorted(p.iterdir()):
                    if f.is_file() and f.suffix.lower() in SUPPORTED_EXTENSIONS and not f.name.startswith("~$") and not f.name.startswith("."):
                        collected_paths.append(f)
            else:
                # Try glob expansion
                import glob
                matched = glob.glob(item)
                if matched:
                    for m in sorted(matched):
                        mp = Path(m)
                        if mp.is_file() and mp.suffix.lower() in SUPPORTED_EXTENSIONS:
                            collected_paths.append(mp)
                else:
                    print(f"Error: File or path not found: '{item}'", file=sys.stderr)
                    sys.exit(1)

        if not collected_paths:
            print("Error: No supported document files found to process.", file=sys.stderr)
            sys.exit(1)

        is_batch = len(collected_paths) > 1
        reports = []

        from checker_hub import AICheckerHub
        hub = None if args.skip_ai else AICheckerHub()

        for idx, file_path in enumerate(collected_paths, 1):
            source_name = file_path.name
            ext = file_path.suffix.lower()
            meta_info = None
            action_note = None

            if ext in [".docx", ".xlsx", ".xlsm", ".pptx", ".pdf"]:
                try:
                    meta_info = inspect_metadata(file_path)
                except Exception as e:
                    meta_info = {"error": f"Failed to inspect metadata: {e}"}

            # Document Cleansing
            if args.cleanse is not None:
                if is_batch:
                    # In batch mode, if out_target is a directory, place cleansed files inside;
                    # otherwise default to <stem>_cleansed<ext> alongside original.
                    if args.cleanse and Path(args.cleanse).is_dir():
                        out_target = Path(args.cleanse) / f"{file_path.stem}_cleansed{file_path.suffix}"
                    else:
                        out_target = file_path.parent / f"{file_path.stem}_cleansed{file_path.suffix}"
                else:
                    out_target = Path(args.cleanse) if args.cleanse else None

                try:
                    saved_to = cleanse_metadata(file_path, output_path=out_target, author=args.author, keep_created_date=True)
                    action_note = f"Cleansed file written to: {saved_to} (Author: {args.author}, Old creation date preserved)"
                except Exception as e:
                    action_note = f"Error during metadata cleansing: {e}"

            if args.skip_ai:
                file_report = {
                    "source": source_name,
                    "file_path": str(file_path.resolve()),
                    "metadata_forensics": meta_info,
                    "action": action_note
                }
                reports.append(file_report)
                if not args.json:
                    if meta_info:
                        print_metadata_section(meta_info, action_note=action_note)
                    elif action_note:
                        print(f"[{source_name}] {action_note}")
                continue

            try:
                text = extract_text_from_file(file_path)
            except Exception as e:
                err_msg = f"Error extracting text from file '{file_path}': {e}"
                if is_batch:
                    print(err_msg, file=sys.stderr)
                    reports.append({
                        "source": source_name,
                        "file_path": str(file_path.resolve()),
                        "error": err_msg,
                        "metadata_forensics": meta_info,
                        "action": action_note
                    })
                    continue
                else:
                    print(err_msg, file=sys.stderr)
                    sys.exit(1)

            if not text.strip():
                empty_msg = f"Warning: Input text in '{file_path.name}' is empty."
                if is_batch:
                    print(empty_msg, file=sys.stderr)
                    reports.append({
                        "source": source_name,
                        "file_path": str(file_path.resolve()),
                        "warning": "Empty document text",
                        "metadata_forensics": meta_info,
                        "action": action_note
                    })
                    continue
                else:
                    print(f"Error: Input text is empty.", file=sys.stderr)
                    sys.exit(1)

            results = hub.analyze_text(text, services=args.services)
            results["source"] = source_name
            results["file_path"] = str(file_path.resolve())
            if meta_info:
                results["metadata_forensics"] = meta_info
            if action_note:
                results["action"] = action_note

            reports.append(results)

            if not args.json:
                if is_batch:
                    print(f"\n>>> Processing ({idx}/{len(collected_paths)}): {source_name}")
                if meta_info:
                    print_metadata_section(meta_info, action_note=action_note)

                print("\n" + "=" * 64)
                print(" THE LECTURER'S STONE - AI CONTENT CONSENSUS REPORT")
                print("=" * 64)
                print(f"Source:        {source_name}")
                print(f"Document Size: {results['document_stats']['words']} words | {results['document_stats']['characters']} characters")
                print("-" * 64)
                print(f"VERDICT:       {results['verdict'].upper()}")
                score_str = format_color_bar(results['consensus_ai_probability']) if results['consensus_ai_probability'] is not None else "N/A"
                print(f"AI SCORE:      {score_str}")
                print(f"SERVICE VOTES: {results['votes']['ai']} AI vs {results['votes']['human']} Human (out of {results['votes']['total_valid_services']} active services)")
                print(f"SCORE RANGE:   {results['score_spread']['min'] * 100:.1f}% to {results['score_spread']['max'] * 100:.1f}% (Spread: {results['score_spread']['range'] * 100:.1f}%)")
                print("-" * 64)
                print("INDIVIDUAL SERVICE BREAKDOWN:")
                for s in results["services"]:
                    s_name = s.get("service_name")
                    status = s.get("status")
                    prob = s.get("ai_probability")
                    label = s.get("label")
                    lat = s.get("latency_sec", 0.0)
                    if status == "success" and prob is not None:
                        bar = format_color_bar(prob, length=15)
                        print(f" * {s_name:<36} {bar} | {label} ({lat}s)")
                    else:
                        print(f" * {s_name:<36} [STATUS: {status}] ({lat}s)")
                print("=" * 64 + "\n")

        # Output handling for files (single vs batch)
        final_output = reports if is_batch else reports[0]
        if args.json:
            output_data = json.dumps(final_output, indent=2)
            print(output_data)

        if args.export:
            export_path = Path(args.export)
            export_path.write_text(json.dumps(final_output, indent=2), encoding="utf-8")
            print(f"Report saved to {export_path.resolve()}", file=sys.stderr)

        return

    # Plain text branch
    source_name = "Raw Text Input"
    text = args.text
    if not text.strip():
        print("Error: Input text is empty.", file=sys.stderr)
        sys.exit(1)

    from checker_hub import AICheckerHub
    hub = AICheckerHub()
    results = hub.analyze_text(text, services=args.services)
    results["source"] = source_name

    if args.json:
        output_data = json.dumps(results, indent=2)
        print(output_data)
        if args.export:
            Path(args.export).write_text(output_data, encoding="utf-8")
            print(f"\nReport exported to {args.export}", file=sys.stderr)
        return

    # Formatted terminal report for AI detection
    print("\n" + "=" * 64)
    print(" THE LECTURER'S STONE - AI CONTENT CONSENSUS REPORT")
    print("=" * 64)
    print(f"Source:        {source_name}")
    print(f"Document Size: {results['document_stats']['words']} words | {results['document_stats']['characters']} characters")
    print("-" * 64)
    print(f"VERDICT:       {results['verdict'].upper()}")
    score_str = format_color_bar(results['consensus_ai_probability']) if results['consensus_ai_probability'] is not None else "N/A"
    print(f"AI SCORE:      {score_str}")
    print(f"SERVICE VOTES: {results['votes']['ai']} AI vs {results['votes']['human']} Human (out of {results['votes']['total_valid_services']} active services)")
    print(f"SCORE RANGE:   {results['score_spread']['min'] * 100:.1f}% to {results['score_spread']['max'] * 100:.1f}% (Spread: {results['score_spread']['range'] * 100:.1f}%)")
    print("-" * 64)
    print("INDIVIDUAL SERVICE BREAKDOWN:")
    for s in results["services"]:
        s_name = s.get("service_name")
        status = s.get("status")
        prob = s.get("ai_probability")
        label = s.get("label")
        lat = s.get("latency_sec", 0.0)
        if status == "success" and prob is not None:
            bar = format_color_bar(prob, length=15)
            print(f" * {s_name:<36} {bar} | {label} ({lat}s)")
        else:
            print(f" * {s_name:<36} [STATUS: {status}] ({lat}s)")

    print("=" * 64 + "\n")

    if args.export:
        export_path = Path(args.export)
        export_path.write_text(json.dumps(results, indent=2), encoding="utf-8")
        print(f"Report saved to {export_path.resolve()}", file=sys.stderr)


if __name__ == "__main__":
    main()