go

pdf_report_generation_service.py

@@ -1,12 +1,13 @@
 """
-Professional Q4 Report Generator - Complete Markdown Parsing
-Ensures ALL markdown syntax is properly rendered in PDF reports
+Professional Q4 Report Generator - Soft Professional Theme
+Comfortable, professional colors with random filename generation
 """
 import markdown
 from weasyprint import HTML, CSS
 import requests
 import os
 import re
+import secrets
 from datetime import datetime
 from typing import List, Dict, Optional
 import logging
@@ -23,7 +24,7 @@ logging.basicConfig(
 logger = logging.getLogger(__name__)
 
 # ---------------------------------------------------------
-# EXECUTIVE Q4 REPORT THEME - COMPLETE STYLING
+# SOFT PROFESSIONAL THEME - COMFORTABLE COLORS
 # ---------------------------------------------------------
 CSS_STYLE = """
 @page {
@@ -41,7 +42,7 @@ CSS_STYLE = """
 
 body {
     font-family: 'Helvetica', Arial, sans-serif;
-    color: #1a1a1a;
+    color: #2d3748;
     line-height: 1.65;
     font-size: 11pt;
 }
@@ -49,8 +50,8 @@ body {
 .header {
     position: running(header);
     font-size: 9pt;
-    color: #666;
-    border-bottom: 1px solid #ddd;
+    color: #718096;
+    border-bottom: 1px solid #e2e8f0;
     padding-bottom: 6px;
     margin-bottom: 20px;
 }
@@ -58,8 +59,8 @@ body {
 .footer {
     position: running(footer);
     font-size: 9pt;
-    color: #666;
-    border-top: 1px solid #ddd;
+    color: #718096;
+    border-top: 1px solid #e2e8f0;
     padding-top: 6px;
     text-align: center;
 }
@@ -69,7 +70,7 @@ body {
 }
 
 .confidential-mark {
-    color: #d32f2f;
+    color: #e53e3e;
     font-weight: bold;
     float: left;
 }
@@ -83,7 +84,7 @@ body {
 .cover-title {
     font-size: 36pt;
     font-weight: bold;
-    color: #003366;
+    color: #4a5568;
     margin-bottom: 0.5in;
     letter-spacing: 1px;
     line-height: 1.2;
@@ -91,35 +92,35 @@ body {
 
 .cover-subtitle {
     font-size: 20pt;
-    color: #0055a5;
+    color: #5a67d8;
     margin-bottom: 1.2in;
     font-weight: 500;
 }
 
 .cover-meta {
     font-size: 15pt;
-    color: #555;
+    color: #718096;
     margin-bottom: 0.25in;
     line-height: 1.5;
 }
 
 .cover-date {
     font-size: 12pt;
-    color: #888;
+    color: #a0aec0;
     margin-top: 0.5in;
 }
 
 .cover-divider {
     width: 3in;
     height: 3px;
-    background: linear-gradient(to right, #003366, #0055a5);
+    background: linear-gradient(to right, #667eea, #764ba2);
     margin: 0.5in auto;
 }
 
 h1 {
-    color: #003366;
+    color: #4a5568;
     font-size: 20pt;
-    border-bottom: 3px solid #0055a5;
+    border-bottom: 3px solid #7c3aed;
     padding-bottom: 10px;
     margin-top: 28px;
     margin-bottom: 18px;
@@ -128,7 +129,7 @@ h1 {
 }
 
 h2 {
-    color: #0055a5;
+    color: #5a67d8;
     font-size: 15pt;
     margin-top: 22px;
     margin-bottom: 14px;
@@ -137,7 +138,7 @@ h2 {
 }
 
 h3 {
-    color: #333;
+    color: #4c51bf;
     font-size: 13pt;
     margin-top: 18px;
     margin-bottom: 12px;
@@ -146,7 +147,7 @@ h3 {
 }
 
 h4 {
-    color: #555;
+    color: #667eea;
     font-size: 12pt;
     margin-top: 16px;
     margin-bottom: 10px;
@@ -155,7 +156,7 @@ h4 {
 }
 
 h5 {
-    color: #666;
+    color: #718096;
     font-size: 11.5pt;
     margin-top: 14px;
     margin-bottom: 8px;
@@ -164,7 +165,7 @@ h5 {
 }
 
 h6 {
-    color: #777;
+    color: #a0aec0;
     font-size: 11pt;
     margin-top: 12px;
     margin-bottom: 8px;
@@ -183,31 +184,31 @@ table {
     margin: 18px 0;
     font-size: 10pt;
     page-break-inside: avoid;
-    box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+    box-shadow: 0 1px 3px rgba(0,0,0,0.08);
 }
 
 thead {
-    background: linear-gradient(to bottom, #003366, #00264d);
+    background: linear-gradient(to bottom, #667eea, #5a67d8);
 }
 
 th {
-    background-color: #003366;
+    background-color: #667eea;
     color: white;
     padding: 12px;
     text-align: left;
     font-weight: bold;
-    border: 1px solid #002244;
+    border: 1px solid #5a67d8;
     font-size: 10.5pt;
 }
 
 td {
     padding: 10px 12px;
-    border: 1px solid #ddd;
+    border: 1px solid #e2e8f0;
     line-height: 1.5;
 }
 
 tr:nth-child(even) {
-    background-color: #f8f9fa;
+    background-color: #f7fafc;
 }
 
 tr:nth-child(odd) {
@@ -215,12 +216,12 @@ tr:nth-child(odd) {
 }
 
 .highlight-box {
-    background-color: #e8f4f8;
-    border-left: 5px solid #0055a5;
+    background-color: #edf2f7;
+    border-left: 5px solid #5a67d8;
     padding: 16px 20px;
     margin: 20px 0;
     page-break-inside: avoid;
-    box-shadow: 0 2px 4px rgba(0,0,0,0.05);
+    box-shadow: 0 2px 4px rgba(0,0,0,0.04);
 }
 
 .highlight-box p:first-child {
@@ -232,13 +233,13 @@ tr:nth-child(odd) {
 }
 
 .key-metric-box {
-    background: linear-gradient(135deg, #003366 0%, #0055a5 100%);
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
     color: white;
     border-radius: 8px;
     padding: 18px 22px;
     margin: 20px 0;
     page-break-inside: avoid;
-    box-shadow: 0 3px 6px rgba(0,0,0,0.15);
+    box-shadow: 0 3px 6px rgba(0,0,0,0.12);
 }
 
 .key-metric-box h3,
@@ -261,15 +262,15 @@ tr:nth-child(odd) {
 }
 
 blockquote {
-    border-left: 5px solid #003366;
+    border-left: 5px solid #5a67d8;
     margin-left: 0;
     padding-left: 20px;
-    color: #333;
+    color: #4a5568;
     font-style: italic;
-    background-color: #f8f9fa;
+    background-color: #f7fafc;
     padding: 14px 14px 14px 20px;
     margin: 18px 0;
-    box-shadow: 0 1px 2px rgba(0,0,0,0.05);
+    box-shadow: 0 1px 2px rgba(0,0,0,0.04);
 }
 
 blockquote p:first-child {
@@ -282,7 +283,7 @@ blockquote p:last-child {
 
 blockquote strong {
     font-weight: 700;
-    color: #000;
+    color: #2d3748;
 }
 
 .figure-container {
@@ -294,23 +295,23 @@ blockquote strong {
 .figure-container img {
     max-width: 100%;
     height: auto;
-    border: 1px solid #ddd;
+    border: 1px solid #e2e8f0;
     padding: 8px;
     background: white;
-    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+    box-shadow: 0 2px 4px rgba(0,0,0,0.08);
 }
 
 .figure-caption {
     font-size: 9.5pt;
-    color: #666;
+    color: #718096;
     margin-top: 10px;
     font-style: italic;
     font-weight: 500;
 }
 
 .executive-summary {
-    background-color: #f0f7ff;
-    border: 2px solid #0055a5;
+    background-color: #ebf4ff;
+    border: 2px solid #5a67d8;
     padding: 20px;
     margin: 24px 0;
     page-break-inside: avoid;
@@ -394,7 +395,7 @@ blockquote ol {
 /* TEXT FORMATTING */
 strong, b {
     font-weight: 700;
-    color: #000;
+    color: #2d3748;
 }
 
 em, i {
@@ -403,16 +404,16 @@ em, i {
 
 code {
     font-family: 'Courier New', monospace;
-    background-color: #f4f4f4;
+    background-color: #edf2f7;
     padding: 2px 6px;
     border-radius: 3px;
     font-size: 10pt;
-    color: #c7254e;
+    color: #805ad5;
 }
 
 pre {
-    background-color: #f4f4f4;
-    border: 1px solid #ddd;
+    background-color: #edf2f7;
+    border: 1px solid #e2e8f0;
     border-radius: 4px;
     padding: 12px;
     overflow-x: auto;
@@ -425,11 +426,11 @@ pre {
 pre code {
     background-color: transparent;
     padding: 0;
-    color: #333;
+    color: #4a5568;
 }
 
 a {
-    color: #0055a5;
+    color: #5a67d8;
     text-decoration: none;
 }
 
@@ -439,18 +440,25 @@ a:hover {
 
 hr {
     border: none;
-    border-top: 2px solid #ddd;
+    border-top: 2px solid #e2e8f0;
     margin: 24px 0;
 }
 """
 
+# ---------------------------------------------------------
+# FILENAME GENERATION
+# ---------------------------------------------------------
+def generate_random_filename(base_name: str = "Q4_Report") -> str:
+    """Generate a random filename to avoid duplicates."""
+    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+    random_suffix = secrets.token_hex(4)  # 8 character hex string
+    return f"{base_name}_{timestamp}_{random_suffix}.pdf"
+
 # ---------------------------------------------------------
 # IMAGE HANDLING
 # ---------------------------------------------------------
 def fetch_image(url: str, output_dir: str) -> Optional[str]:
-    """
-    Download image from URL to persistent file for PDF rendering.
-    """
+    """Download image from URL to persistent file for PDF rendering."""
     if not url.startswith(('http://', 'https://')):
         if os.path.exists(url):
             abs_path = os.path.abspath(url)
@@ -499,21 +507,14 @@ def fetch_image(url: str, output_dir: str) -> Optional[str]:
 # MARKDOWN PREPROCESSING
 # ---------------------------------------------------------
 def preprocess_markdown(content: str) -> str:
-    """
-    Preprocess markdown content to ensure proper parsing inside HTML blocks.
-    Adds markdown="1" attribute to known HTML container tags.
-    """
-    # List of container tags that might contain markdown
+    """Preprocess markdown content to ensure proper parsing inside HTML blocks."""
     container_tags = ['div', 'blockquote', 'section', 'article', 'aside']
     
     for tag in container_tags:
-        # Pattern to find opening tags without markdown attribute
-        # Matches: <div class="something"> or <div> but not <div markdown="1">
         pattern = rf'<{tag}(\s+[^>]*?)?(?!\s+markdown\s*=)>'
         
         def add_markdown_attr(match):
             attrs = match.group(1) or ''
-            # If there are existing attributes, add markdown after them
             if attrs:
                 return f'<{tag}{attrs} markdown="1">'
             else:
@@ -527,7 +528,7 @@ def preprocess_markdown(content: str) -> str:
 # Q4 REPORT GENERATOR CLASS
 # ---------------------------------------------------------
 class Q4ReportGenerator:
-    """Generates executive-quality Q4 reports using WeasyPrint with complete markdown support."""
+    """Generates executive-quality Q4 reports with soft professional colors."""
     
     def __init__(self, 
                  title: str = "Q4 Performance Report",
@@ -574,34 +575,19 @@ class Q4ReportGenerator:
         """
     
     def _process_section(self, section: Dict, output_dir: str) -> str:
-        """
-        Process section with COMPLETE markdown parsing support.
-        Handles markdown both outside and inside HTML tags.
-        """
+        """Process section with complete markdown parsing support."""
         html = ""
         
         content = section.get("content", "")
         if content:
-            # Step 1: Preprocess to add markdown="1" to HTML containers
             preprocessed_content = preprocess_markdown(content)
             
-            # Step 2: Apply comprehensive markdown parsing
             html_content = markdown.markdown(
                 preprocessed_content,
                 extensions=[
-                    'extra',           # Tables, footnotes, attributes, etc.
-                    'sane_lists',      # Better list handling
-                    'tables',          # Table support
-                    'fenced_code',     # Code blocks with ```
-                    'nl2br',           # Convert newlines to <br>
-                    'codehilite',      # Syntax highlighting
-                    'toc',             # Table of contents
-                    'md_in_html',      # CRITICAL: Parse markdown inside HTML tags
-                    'attr_list',       # Add attributes to elements
-                    'def_list',        # Definition lists
-                    'abbr',            # Abbreviations
-                    'footnotes',       # Footnotes
-                    'smarty'           # Smart quotes and dashes
+                    'extra', 'sane_lists', 'tables', 'fenced_code',
+                    'nl2br', 'codehilite', 'toc', 'md_in_html',
+                    'attr_list', 'def_list', 'abbr', 'footnotes', 'smarty'
                 ],
                 extension_configs={
                     'codehilite': {
@@ -635,7 +621,6 @@ class Q4ReportGenerator:
                     </div>
                     """
         
-        # Page break if requested
         if section.get("page_break", False):
             html += '<div class="page-break"></div>'
         
@@ -643,23 +628,36 @@ class Q4ReportGenerator:
     
     def generate(self, 
                  sections: List[Dict], 
-                 filename: str = "Q4_Report.pdf",
+                 filename: str = None,
                  output_dir: str = "./output",
-                 cover_page: bool = True) -> bool:
-        """Generate PDF report with complete markdown parsing everywhere."""
+                 cover_page: bool = True) -> tuple[bool, str]:
+        """
+        Generate PDF report with random filename.
+        Returns: (success: bool, output_path: str)
+        """
         try:
             os.makedirs(output_dir, exist_ok=True)
+            
+            # Generate random filename if not provided
+            if filename is None:
+                filename = generate_random_filename("Q4_Report")
+            elif not filename.endswith('.pdf'):
+                # Add random suffix even if filename provided
+                base = filename.replace('.pdf', '')
+                timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+                random_suffix = secrets.token_hex(4)
+                filename = f"{base}_{timestamp}_{random_suffix}.pdf"
+            
             output_path = os.path.join(output_dir, filename)
             
             logger.info(f"Starting Q4 report generation: {output_path}")
-            logger.info("Markdown parsing: FULL (inside and outside HTML tags)")
+            logger.info("Theme: Soft Professional Colors")
             
             # Build HTML body
             body_html = ""
             if cover_page:
                 body_html += self._build_cover_page()
             
-            # Process all sections
             for idx, section in enumerate(sections):
                 logger.info(f"Processing section {idx + 1}/{len(sections)}")
                 body_html += self._process_section(section, output_dir)
@@ -688,12 +686,11 @@ class Q4ReportGenerator:
             html_doc.write_pdf(output_path, stylesheets=[css_doc])
             
             logger.info(f"✓ PDF Generated Successfully: {output_path}")
-            logger.info(f"✓ All markdown syntax properly parsed")
-            return True
+            return True, output_path
             
         except Exception as e:
             logger.error(f"✗ Error generating report: {e}", exc_info=True)
-            return False
+            return False, ""
     
     def cleanup_images(self, output_dir: str):
         """Optional: Clean up downloaded images after PDF generation."""
@@ -711,7 +708,6 @@ class Q4ReportGenerator:
 # EXAMPLE USAGE
 # ---------------------------------------------------------
 if __name__ == "__main__":
-    # Example of how to use the generator
     generator = Q4ReportGenerator(
         title="Q4 2024 Performance Report",
         subtitle="Executive Summary & Analysis",
@@ -748,30 +744,16 @@ This report presents our **Q4 2024** performance metrics.
 </div>
             """,
             "page_break": False
-        },
-        {
-            "content": """
-# Strategic Recommendations
-
-1. **Expand marketing efforts** in Q1 2025
-2. **Invest in customer support** infrastructure
-3. **Explore new markets** in Southeast Asia
-
----
-
-*Report generated on January 24, 2026*
-            """,
-            "page_break": False
         }
     ]
     
-    success = generator.generate(
+    success, output_path = generator.generate(
         sections=sections,
-        filename="Q4_2024_Report.pdf",
+        filename="Q4_2024_Report",  # Will add random suffix automatically
         output_dir="./reports"
     )
     
     if success:
-        print("✓ Report generated successfully!")
+        print(f"✓ Report generated: {output_path}")
     else:
         print("✗ Report generation failed!")