Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -280,6 +280,105 @@ def get_document_checks(doc_type, template_type):
|
|
| 280 |
# Add other document types as needed
|
| 281 |
return {"required_headings": []}
|
| 282 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 283 |
def format_results_for_gradio(**kwargs):
|
| 284 |
"""Format the results for display in Gradio."""
|
| 285 |
results = []
|
|
@@ -422,132 +521,6 @@ def format_results_for_gradio(**kwargs):
|
|
| 422 |
|
| 423 |
return "\n".join(results)
|
| 424 |
|
| 425 |
-
def process_file(file_obj, doc_type, template_type):
|
| 426 |
-
"""
|
| 427 |
-
Process the uploaded file and return results with error handling
|
| 428 |
-
"""
|
| 429 |
-
if file_obj is None:
|
| 430 |
-
return "Please upload a document first."
|
| 431 |
-
|
| 432 |
-
try:
|
| 433 |
-
# Convert bytes to BytesIO object that Document can read
|
| 434 |
-
if isinstance(file_obj, bytes):
|
| 435 |
-
doc_bytes = io.BytesIO(file_obj)
|
| 436 |
-
else:
|
| 437 |
-
doc_bytes = io.BytesIO(file_obj.read())
|
| 438 |
-
|
| 439 |
-
# Process the document and get results
|
| 440 |
-
results = process_document(doc_bytes, doc_type, template_type)
|
| 441 |
-
return results
|
| 442 |
-
|
| 443 |
-
except Exception as e:
|
| 444 |
-
error_trace = traceback.format_exc()
|
| 445 |
-
print(f"Error processing file: {str(e)}")
|
| 446 |
-
print(f"Full traceback: {error_trace}")
|
| 447 |
-
|
| 448 |
-
error_message = f"""An error occurred while processing the document:
|
| 449 |
-
|
| 450 |
-
Error: {str(e)}
|
| 451 |
-
|
| 452 |
-
Please ensure:
|
| 453 |
-
1. The file is a valid Word document (.docx)
|
| 454 |
-
2. The file is not corrupted
|
| 455 |
-
3. The file is not password protected
|
| 456 |
-
|
| 457 |
-
Technical details: {str(e)}"""
|
| 458 |
-
|
| 459 |
-
return error_message
|
| 460 |
-
|
| 461 |
-
def process_document(file_obj, doc_type, template_type):
|
| 462 |
-
"""Process the document and perform checks."""
|
| 463 |
-
try:
|
| 464 |
-
# Read the Word document
|
| 465 |
-
doc = Document(file_obj)
|
| 466 |
-
print("Document read successfully.")
|
| 467 |
-
|
| 468 |
-
# Get required headings based on document type
|
| 469 |
-
required_headings = get_document_checks(doc_type, template_type).get("required_headings", [])
|
| 470 |
-
|
| 471 |
-
# Perform checks
|
| 472 |
-
heading_valid, headings_found = heading_title_check(doc, required_headings)
|
| 473 |
-
acronyms_valid, undefined_acronyms = acronym_check(doc)
|
| 474 |
-
|
| 475 |
-
# Format results
|
| 476 |
-
results = format_results_for_gradio(
|
| 477 |
-
heading_valid=heading_valid,
|
| 478 |
-
headings_found=headings_found,
|
| 479 |
-
acronyms_valid=acronyms_valid,
|
| 480 |
-
undefined_acronyms=undefined_acronyms,
|
| 481 |
-
legal_valid=True, # Placeholder
|
| 482 |
-
incorrect_legal_references=[],
|
| 483 |
-
table_valid=True, # Placeholder
|
| 484 |
-
incorrect_captions=[],
|
| 485 |
-
figure_valid=True, # Placeholder
|
| 486 |
-
incorrect_fig_captions=[],
|
| 487 |
-
references_valid=True, # Placeholder
|
| 488 |
-
incorrect_table_figure_references=[],
|
| 489 |
-
title_style_valid=True, # Placeholder
|
| 490 |
-
incorrect_titles=[],
|
| 491 |
-
required_headings=required_headings,
|
| 492 |
-
doc_type=doc_type,
|
| 493 |
-
double_period_valid=True, # Placeholder
|
| 494 |
-
incorrect_sentences=[],
|
| 495 |
-
spacing_valid=True, # Placeholder
|
| 496 |
-
incorrect_spacing=[],
|
| 497 |
-
abbreviation_issues=[],
|
| 498 |
-
date_issues=[],
|
| 499 |
-
placeholder_issues=[]
|
| 500 |
-
)
|
| 501 |
-
|
| 502 |
-
return results
|
| 503 |
-
|
| 504 |
-
except Exception as e:
|
| 505 |
-
print(f"Error in process_document: {str(e)}")
|
| 506 |
-
raise
|
| 507 |
-
|
| 508 |
-
def get_document_checks(doc_type, template_type):
|
| 509 |
-
"""Return the required headings and other checks based on document type."""
|
| 510 |
-
if doc_type == "Advisory Circular":
|
| 511 |
-
if template_type == "Short AC template AC":
|
| 512 |
-
return {
|
| 513 |
-
"required_headings": ["Purpose", "Applicability", "Related Reading Material",
|
| 514 |
-
"Background", "Discussion"]
|
| 515 |
-
}
|
| 516 |
-
else: # Long AC template
|
| 517 |
-
return {
|
| 518 |
-
"required_headings": ["Purpose", "Applicability", "Audience", "Related Reading Material",
|
| 519 |
-
"Background", "Discussion", "Conclusion"]
|
| 520 |
-
}
|
| 521 |
-
# Add other document types as needed
|
| 522 |
-
return {"required_headings": []}
|
| 523 |
-
|
| 524 |
-
def format_results_for_gradio(**kwargs):
|
| 525 |
-
"""Format the results for display."""
|
| 526 |
-
results = []
|
| 527 |
-
results.append("# Document Check Results\n")
|
| 528 |
-
|
| 529 |
-
# Required Headings Check
|
| 530 |
-
results.append("## Required Headings Check")
|
| 531 |
-
if kwargs['heading_valid']:
|
| 532 |
-
results.append("✅ All required headings are present.\n")
|
| 533 |
-
else:
|
| 534 |
-
missing_headings = set(kwargs['required_headings']) - set(kwargs['headings_found'])
|
| 535 |
-
results.append("❌ Missing Required Headings:")
|
| 536 |
-
for heading in missing_headings:
|
| 537 |
-
results.append(f"- {heading}")
|
| 538 |
-
results.append("")
|
| 539 |
-
|
| 540 |
-
# Acronym Check
|
| 541 |
-
results.append("## Acronym Check")
|
| 542 |
-
if kwargs['acronyms_valid']:
|
| 543 |
-
results.append("✅ All acronyms are properly defined.\n")
|
| 544 |
-
else:
|
| 545 |
-
results.append("❌ The following acronyms need to be defined at first use:")
|
| 546 |
-
for acronym in kwargs['undefined_acronyms']:
|
| 547 |
-
results.append(f"- {acronym}")
|
| 548 |
-
|
| 549 |
-
return "\n".join(results)
|
| 550 |
-
|
| 551 |
def process_file(file_obj, doc_type, template_type):
|
| 552 |
"""Process the uploaded file and return results with error handling."""
|
| 553 |
if file_obj is None:
|
|
|
|
| 280 |
# Add other document types as needed
|
| 281 |
return {"required_headings": []}
|
| 282 |
|
| 283 |
+
def process_file(file_obj, doc_type, template_type):
|
| 284 |
+
"""
|
| 285 |
+
Process the uploaded file and return results with error handling
|
| 286 |
+
"""
|
| 287 |
+
if file_obj is None:
|
| 288 |
+
return "Please upload a document first."
|
| 289 |
+
|
| 290 |
+
try:
|
| 291 |
+
# Convert bytes to BytesIO object that Document can read
|
| 292 |
+
if isinstance(file_obj, bytes):
|
| 293 |
+
doc_bytes = io.BytesIO(file_obj)
|
| 294 |
+
else:
|
| 295 |
+
doc_bytes = io.BytesIO(file_obj.read())
|
| 296 |
+
|
| 297 |
+
# Process the document and get results
|
| 298 |
+
results = process_document(doc_bytes, doc_type, template_type)
|
| 299 |
+
return results
|
| 300 |
+
|
| 301 |
+
except Exception as e:
|
| 302 |
+
error_trace = traceback.format_exc()
|
| 303 |
+
print(f"Error processing file: {str(e)}")
|
| 304 |
+
print(f"Full traceback: {error_trace}")
|
| 305 |
+
|
| 306 |
+
error_message = f"""An error occurred while processing the document:
|
| 307 |
+
|
| 308 |
+
Error: {str(e)}
|
| 309 |
+
|
| 310 |
+
Please ensure:
|
| 311 |
+
1. The file is a valid Word document (.docx)
|
| 312 |
+
2. The file is not corrupted
|
| 313 |
+
3. The file is not password protected
|
| 314 |
+
|
| 315 |
+
Technical details: {str(e)}"""
|
| 316 |
+
|
| 317 |
+
return error_message
|
| 318 |
+
|
| 319 |
+
def process_document(file_obj, doc_type, template_type):
|
| 320 |
+
"""Process the document and perform checks."""
|
| 321 |
+
try:
|
| 322 |
+
# Read the Word document
|
| 323 |
+
doc = Document(file_obj)
|
| 324 |
+
print("Document read successfully.")
|
| 325 |
+
|
| 326 |
+
# Get required headings based on document type
|
| 327 |
+
required_headings = get_document_checks(doc_type, template_type).get("required_headings", [])
|
| 328 |
+
|
| 329 |
+
# Perform checks
|
| 330 |
+
heading_valid, headings_found = heading_title_check(doc, required_headings)
|
| 331 |
+
acronyms_valid, undefined_acronyms = acronym_check(doc)
|
| 332 |
+
|
| 333 |
+
# Format results
|
| 334 |
+
results = format_results_for_gradio(
|
| 335 |
+
heading_valid=heading_valid,
|
| 336 |
+
headings_found=headings_found,
|
| 337 |
+
acronyms_valid=acronyms_valid,
|
| 338 |
+
undefined_acronyms=undefined_acronyms,
|
| 339 |
+
legal_valid=True, # Placeholder
|
| 340 |
+
incorrect_legal_references=[],
|
| 341 |
+
table_valid=True, # Placeholder
|
| 342 |
+
incorrect_captions=[],
|
| 343 |
+
figure_valid=True, # Placeholder
|
| 344 |
+
incorrect_fig_captions=[],
|
| 345 |
+
references_valid=True, # Placeholder
|
| 346 |
+
incorrect_table_figure_references=[],
|
| 347 |
+
title_style_valid=True, # Placeholder
|
| 348 |
+
incorrect_titles=[],
|
| 349 |
+
required_headings=required_headings,
|
| 350 |
+
doc_type=doc_type,
|
| 351 |
+
double_period_valid=True, # Placeholder
|
| 352 |
+
incorrect_sentences=[],
|
| 353 |
+
spacing_valid=True, # Placeholder
|
| 354 |
+
incorrect_spacing=[],
|
| 355 |
+
abbreviation_issues=[],
|
| 356 |
+
date_issues=[],
|
| 357 |
+
placeholder_issues=[]
|
| 358 |
+
)
|
| 359 |
+
|
| 360 |
+
return results
|
| 361 |
+
|
| 362 |
+
except Exception as e:
|
| 363 |
+
print(f"Error in process_document: {str(e)}")
|
| 364 |
+
raise
|
| 365 |
+
|
| 366 |
+
def get_document_checks(doc_type, template_type):
|
| 367 |
+
"""Return the required headings and other checks based on document type."""
|
| 368 |
+
if doc_type == "Advisory Circular":
|
| 369 |
+
if template_type == "Short AC template AC":
|
| 370 |
+
return {
|
| 371 |
+
"required_headings": ["Purpose", "Applicability", "Related Reading Material",
|
| 372 |
+
"Background", "Discussion"]
|
| 373 |
+
}
|
| 374 |
+
else: # Long AC template
|
| 375 |
+
return {
|
| 376 |
+
"required_headings": ["Purpose", "Applicability", "Audience", "Related Reading Material",
|
| 377 |
+
"Background", "Discussion", "Conclusion"]
|
| 378 |
+
}
|
| 379 |
+
# Add other document types as needed
|
| 380 |
+
return {"required_headings": []}
|
| 381 |
+
|
| 382 |
def format_results_for_gradio(**kwargs):
|
| 383 |
"""Format the results for display in Gradio."""
|
| 384 |
results = []
|
|
|
|
| 521 |
|
| 522 |
return "\n".join(results)
|
| 523 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 524 |
def process_file(file_obj, doc_type, template_type):
|
| 525 |
"""Process the uploaded file and return results with error handling."""
|
| 526 |
if file_obj is None:
|