Update app.py

app.py

@@ -11,6 +11,8 @@ import io
 import os
 import traceback
 from datetime import datetime
+import textwrap
+from colorama import init, Fore, Style
 
 # Core data structures
 @dataclass
@@ -868,44 +870,29 @@ class FAADocumentChecker(DocumentChecker):
 def process_document(file_obj, doc_type: str, template_type: Optional[str] = None) -> str:
     """Process document and run all checks."""
     try:
-        # Initialize checker
         checker = FAADocumentChecker()
         
-        # Convert file object to BytesIO if needed
         if isinstance(file_obj, bytes):
             file_obj = io.BytesIO(file_obj)
             
-        # Run all checks
         results = checker.run_all_checks(file_obj, doc_type, template_type)
-        
-        # Format results using DocumentCheckResultsFormatter
-        formatter = DocumentCheckResultsFormatter()
-        formatted_results = formatter.format_results(results, doc_type)
-        
-        # Convert the formatted results to HTML
-        html_content = f"""
-        <div id="document-checker-results"></div>
-        <script type="module">
-            import DocumentCheckerResults from './components/DocumentCheckerResults.jsx';
-            const results = {json.dumps(formatted_results)};
-            const root = document.getElementById('document-checker-results');
-            ReactDOM.render(React.createElement(DocumentCheckerResults, {{ results }}), root);
-        </script>
-        """
-        
-        return html_content
+        return format_markdown_results(results, doc_type)
         
     except Exception as e:
         logging.error(f"Error processing document: {str(e)}")
         traceback.print_exc()
-        error_html = f"""
-        <div class="error-message" style="color: red; padding: 1rem;">
-            ❌ Error processing document: {str(e)}
-            <br><br>
-            Please ensure the file is a valid .docx document and try again.
-        </div>
-        """
-        return error_html
+        return f"""
+# ❌ Error Processing Document
+
+**Error Details:** {str(e)}
+
+Please ensure:
+1. The file is a valid .docx document
+2. The file is not corrupted or password protected
+3. The file is properly formatted
+
+Try again after checking these issues. If the problem persists, contact support.
+"""
     
 def format_markdown_results(results: Dict[str, DocumentCheckResult], doc_type: str) -> str:
     """Format check results into a Markdown string for Gradio display."""
@@ -988,6 +975,190 @@ def format_markdown_results(results: Dict[str, DocumentCheckResult], doc_type: s
 
     return "\n".join(output)
 
+class DocumentCheckResultsFormatter:
+    """Formats document check results in a user-friendly way with detailed examples and fixes."""
+    
+    def __init__(self):
+        """Initialize the formatter with colorama for cross-platform color support."""
+        init()  # Initialize colorama
+        
+        # Enhanced issue categories with examples and specific fixes
+        self.issue_categories = {
+            'acronym_check': {
+                'title': 'Acronym Definition Issues',
+                'description': 'Acronyms must be defined at their first use in the document.',
+                'solution': 'Define each acronym at its first use, e.g., "Federal Aviation Administration (FAA)"',
+                'example_fix': {
+                    'before': 'The FAA published new guidelines.',
+                    'after': 'The Federal Aviation Administration (FAA) published new guidelines.'
+                }
+            },
+            'terminology_check': {
+                'title': 'Incorrect Terminology',
+                'description': 'Non-standard or prohibited terms and phrases detected. Avoid relative position references.',
+                'solution': 'Use explicit references to paragraphs, sections, tables, and figures',
+                'example_fix': {
+                    'before': 'See above section for details | Refer to below table | shall comply with',
+                    'after': 'See paragraph 3.2 for details | Refer to table 2-1 | must comply with'
+                }
+            },
+            'section_symbol_usage_check': {
+                'title': 'Section Symbol (§) Format Issues',
+                'description': 'Incorrect formatting of section symbols in references.',
+                'solution': 'Format section symbols correctly and never start sentences with them',
+                'example_fix': {
+                    'before': '§ 25.25 states | 14 CFR § 21.21',
+                    'after': 'Section 25.25 states | 14 CFR 21.21'
+                }
+            },
+            'caption_check_table': {
+                'title': 'Table Caption Format Issues',
+                'description': 'Table captions do not follow the required format.',
+                'solution': 'Use consistent table numbering format',
+                'example_fix': {
+                    'before': 'Table 5. | Table A | Tables',
+                    'after': 'Table 5-1. | Table 1-1 | Table 2-1'
+                }
+            },
+            'caption_check_figure': {
+                'title': 'Figure Caption Format Issues',
+                'description': 'Figure captions do not follow the required format.',
+                'solution': 'Use consistent figure numbering format',
+                'example_fix': {
+                    'before': 'Figure 5. | Figure A | Figures',
+                    'after': 'Figure 5-1. | Figure 1-1 | Figure 2-1'
+                }
+            },
+            'document_title_check': {
+                'title': 'Document Title Format Issues',
+                'description': 'Document titles are not properly formatted.',
+                'solution': 'Format titles according to document type requirements',
+                'example_fix': {
+                    'before': '"AC 20-114" | "Advisory Circular"',
+                    'after': 'AC 20-114 | Advisory Circular'
+                }
+            },
+            'double_period_check': {
+                'title': 'Multiple Period Issues',
+                'description': 'Sentences ending with multiple periods.',
+                'solution': 'Use single period to end sentences',
+                'example_fix': {
+                    'before': 'The following ACs are related to the guidance in this document..',
+                    'after': 'The following ACs are related to the guidance in this document.'
+                }
+            },
+            'spacing_check': {
+                'title': 'Spacing Issues',
+                'description': 'Incorrect spacing in text.',
+                'solution': 'Maintain consistent spacing throughout the document',
+                'example_fix': {
+                    'before': 'AC25.25 | The  following ACs (double spaces)',
+                    'after': 'AC 25.25 | The following ACs (single space)'
+                }
+            },
+            'date_formats_check': {
+                'title': 'Date Format Issues',
+                'description': 'Dates not in the required format.',
+                'solution': 'Use the format "Month Day, Year"',
+                'example_fix': {
+                    'before': '01/15/2024 | 2024-01-15',
+                    'after': 'January 15, 2024'
+                }
+            },
+            'placeholders_check': {
+                'title': 'Placeholder Content',
+                'description': 'Placeholder text remains in the document.',
+                'solution': 'Replace all placeholder content with actual content',
+                'example_fix': {
+                    'before': 'TBD | To be determined | [Insert text]',
+                    'after': 'Actual content specific to the context'
+                }
+            }
+        }
+
+    def format_results(self, results: Dict[str, Any], doc_type: str) -> str:
+        """Format check results into a Markdown string for display."""
+        output = []
+        
+        # Add header
+        current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        output.extend([
+            "================================================================================",
+            "Document Check Results Summary",
+            "================================================================================\n"
+        ])
+
+        # Count issues
+        total_issues = sum(1 for r in results.values() if not r.success)
+        
+        if total_issues == 0:
+            output.append("✅ All checks passed successfully!\n")
+            return "\n".join(output)
+        
+        output.append(f"Found {total_issues} categories of issues that need attention:\n")
+
+        # Process each check result
+        for check_name, result in results.items():
+            if not result.success and check_name in self.issue_categories:
+                category = self.issue_categories[check_name]
+                
+                # Add section header
+                output.append(f"■ {category['title']}")
+                output.append(f"  {category['description']}")
+                output.append(f"  How to fix: {category['solution']}\n")
+                
+                # Add example
+                output.append("  Example Fix:")
+                output.append(f"    ❌ Incorrect: {category['example_fix']['before']}")
+                output.append(f"    ✓ Correct  : {category['example_fix']['after']}\n")
+                
+                # Add actual issues
+                output.append("  Issues found in your document:")
+                issue_count = len(result.issues)
+                shown_issues = result.issues[:3]  # Show first 3 issues
+                
+                for issue in shown_issues:
+                    if isinstance(issue, dict):
+                        if 'sentence' in issue:
+                            sentence = textwrap.fill(
+                                issue['sentence'],
+                                width=76,
+                                initial_indent='    • ',
+                                subsequent_indent='      '
+                            )
+                            output.append(sentence)
+                        elif 'missing_headings' in issue:
+                            missing = ', '.join(issue['missing_headings'])
+                            output.append(f"    • Missing required headings: {missing}")
+                        else:
+                            issue_str = ', '.join(f"{k}: {v}" for k, v in issue.items())
+                            output.append(f"    • {issue_str}")
+                
+                if issue_count > 3:
+                    output.append(f"\n    ... and {issue_count - 3} more similar issues.")
+                
+                output.append("")  # Add spacing between categories
+        
+        return "\n".join(output)
+
+    def save_report(self, results: Dict[str, Any], filepath: str, doc_type: str):
+        """Save the formatted results to a file with proper formatting."""
+        try:
+            with open(filepath, 'w', encoding='utf-8') as f:
+                # Create a report without color codes
+                report = self.format_results(results, doc_type)
+                
+                # Strip color codes
+                for color in [Fore.CYAN, Fore.GREEN, Fore.YELLOW, Fore.RED, Style.RESET_ALL]:
+                    report = report.replace(str(color), '')
+                
+                # Convert markdown-style italics to alternative formatting for plain text
+                report = report.replace('*', '_')
+                
+                f.write(report)
+        except Exception as e:
+            print(f"Error saving report: {e}")
+
 def create_interface():
     """Create and configure the Gradio interface."""
     
@@ -1006,7 +1177,153 @@ def create_interface():
     ]
     
     template_types = ["Short AC template AC", "Long AC template AC"]
-    
+
+    def format_results_as_html(text_results):
+        """Convert the text results into styled HTML."""
+        if not text_results:
+            return """
+                <div class="p-4 text-gray-600">
+                    Results will appear here after processing...
+                </div>
+            """
+        
+        # Split into sections
+        sections = text_results.split('■')
+        header = sections[0]
+        issues = sections[1:]
+        
+        # Format header
+        header_html = f"""
+            <div class="max-w-4xl mx-auto p-4 bg-white rounded-lg shadow-sm mb-6">
+                <h1 class="text-2xl font-bold text-gray-800 mb-4">Document Check Results Summary</h1>
+                <div class="text-lg {'text-green-600' if 'All checks passed' in header else 'text-amber-600'}">
+                    {header.strip()}
+                </div>
+            </div>
+        """
+        
+        # Format each issue section
+        issues_html = ""
+        for section in issues:
+            if not section.strip():
+                continue
+                
+            lines = section.strip().split('\n')
+            title = lines[0]
+            content = '\n'.join(lines[1:])
+            
+            # Split content into description, how to fix, and examples
+            parts = content.split('Example Fix:')
+            description = parts[0]
+            examples = parts[1] if len(parts) > 1 else ""
+            
+            issues_html += f"""
+                <div class="bg-white rounded-lg shadow-sm mb-6 overflow-hidden">
+                    <div class="bg-gray-50 px-6 py-4 border-b">
+                        <h2 class="text-lg font-semibold text-gray-800">{title.strip()}</h2>
+                    </div>
+                    
+                    <div class="px-6 py-4">
+                        <div class="text-gray-600 mb-4">
+                            {description.strip()}
+                        </div>
+                        
+                        <div class="bg-green-50 rounded p-4 mb-4">
+                            <div class="text-green-800">
+                                <span class="font-medium">How to fix:</span>
+                                {description.split('How to fix:')[1].strip() if 'How to fix:' in description else ''}
+                            </div>
+                        </div>
+                    """
+            
+            if examples:
+                examples_lines = examples.strip().split('\n')
+                issues_html += """
+                    <div class="mb-4">
+                        <h3 class="font-medium text-gray-800 mb-2">Examples:</h3>
+                        <div class="space-y-2 ml-4">
+                """
+                
+                for line in examples_lines:
+                    line = line.strip()
+                    if line.startswith('❌'):
+                        issues_html += f"""
+                            <div class="text-red-600">
+                                <span class="inline-block w-4">❌</span>
+                                {line.replace('❌ Incorrect:', '').strip()}
+                            </div>
+                        """
+                    elif line.startswith('✓'):
+                        issues_html += f"""
+                            <div class="text-green-600">
+                                <span class="inline-block w-4">✓</span>
+                                {line.replace('✓ Correct  :', '').strip()}
+                            </div>
+                        """
+                    elif line.startswith('•'):
+                        issues_html += f"""
+                            <div class="text-gray-600 ml-4">
+                                • {line.replace('•', '').strip()}
+                            </div>
+                        """
+                    elif 'more similar issues' in line:
+                        issues_html += f"""
+                            <div class="text-gray-500 italic mt-2">
+                                {line.strip()}
+                            </div>
+                        """
+                        
+                issues_html += """
+                        </div>
+                    </div>
+                """
+                
+            issues_html += """
+                    </div>
+                </div>
+            """
+        
+        # Combine all HTML
+        full_html = f"""
+        <div class="mx-auto p-4" style="font-family: system-ui, -apple-system, sans-serif;">
+            <style>
+                .text-2xl {{ font-size: 1.5rem; }}
+                .text-lg {{ font-size: 1.125rem; }}
+                .font-bold {{ font-weight: 700; }}
+                .font-semibold {{ font-weight: 600; }}
+                .font-medium {{ font-weight: 500; }}
+                .text-gray-800 {{ color: #1f2937; }}
+                .text-gray-600 {{ color: #4b5563; }}
+                .text-gray-500 {{ color: #6b7280; }}
+                .text-green-600 {{ color: #059669; }}
+                .text-green-800 {{ color: #065f46; }}
+                .text-red-600 {{ color: #dc2626; }}
+                .text-amber-600 {{ color: #d97706; }}
+                .bg-white {{ background-color: #ffffff; }}
+                .bg-gray-50 {{ background-color: #f9fafb; }}
+                .bg-green-50 {{ background-color: #ecfdf5; }}
+                .rounded-lg {{ border-radius: 0.5rem; }}
+                .shadow-sm {{ box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05); }}
+                .mb-6 {{ margin-bottom: 1.5rem; }}
+                .mb-4 {{ margin-bottom: 1rem; }}
+                .mb-2 {{ margin-bottom: 0.5rem; }}
+                .ml-4 {{ margin-left: 1rem; }}
+                .mt-2 {{ margin-top: 0.5rem; }}
+                .p-4 {{ padding: 1rem; }}
+                .px-6 {{ padding-left: 1.5rem; padding-right: 1.5rem; }}
+                .py-4 {{ padding-top: 1rem; padding-bottom: 1rem; }}
+                .space-y-2 > * + * {{ margin-top: 0.5rem; }}
+                .italic {{ font-style: italic; }}
+                .border-b {{ border-bottom: 1px solid #e5e7eb; }}
+                .overflow-hidden {{ overflow: hidden; }}
+            </style>
+            {header_html}
+            {issues_html}
+        </div>
+        """
+        
+        return full_html
+
     with gr.Blocks() as demo:
         gr.Markdown(
             """
@@ -1052,10 +1369,34 @@ def create_interface():
                 )
             
             with gr.Column(scale=2):
-                results = gr.Component("DocumentCheckerResults", 
-                    value=None,
-                    render=False
-                )
+                results = gr.HTML()
+        
+        def process_and_format(file_obj, doc_type, template_type):
+            """Process document and format results as HTML."""
+            try:
+                # Get text results from original process_document function
+                checker = FAADocumentChecker()
+                if isinstance(file_obj, bytes):
+                    file_obj = io.BytesIO(file_obj)
+                results = checker.run_all_checks(file_obj, doc_type, template_type)
+                
+                # Format results using DocumentCheckResultsFormatter
+                formatter = DocumentCheckResultsFormatter()
+                text_results = formatter.format_results(results, doc_type)
+                
+                # Convert to HTML
+                return format_results_as_html(text_results)
+                
+            except Exception as e:
+                logging.error(f"Error processing document: {str(e)}")
+                traceback.print_exc()
+                return f"""
+                    <div style="color: red; padding: 1rem;">
+                        ❌ Error processing document: {str(e)}
+                        <br><br>
+                        Please ensure the file is a valid .docx document and try again.
+                    </div>
+                """
         
         # Update template type visibility based on document type
         def update_template_visibility(doc_type):
@@ -1069,7 +1410,7 @@ def create_interface():
         
         # Handle document processing
         submit_btn.click(
-            fn=process_document,
+            fn=process_and_format,
             inputs=[file_input, doc_type, template_type],
             outputs=[results]
         )