go

pdf_report_generation_service.py

@@ -1,11 +1,12 @@
 """
-Professional Q4 Report Generator - Enhanced Markdown Parsing
-Generates executive-quality PDF reports with proper list rendering
+Professional Q4 Report Generator - Complete Markdown Parsing
+Ensures ALL markdown syntax is properly rendered in PDF reports
 """
 import markdown
 from weasyprint import HTML, CSS
 import requests
 import os
+import re
 from datetime import datetime
 from typing import List, Dict, Optional
 import logging
@@ -22,7 +23,7 @@ logging.basicConfig(
 logger = logging.getLogger(__name__)
 
 # ---------------------------------------------------------
-# EXECUTIVE Q4 REPORT THEME - ENHANCED LIST STYLING
+# EXECUTIVE Q4 REPORT THEME - COMPLETE STYLING
 # ---------------------------------------------------------
 CSS_STYLE = """
 @page {
@@ -144,6 +145,38 @@ h3 {
     font-weight: 600;
 }
 
+h4 {
+    color: #555;
+    font-size: 12pt;
+    margin-top: 16px;
+    margin-bottom: 10px;
+    page-break-after: avoid;
+    font-weight: 600;
+}
+
+h5 {
+    color: #666;
+    font-size: 11.5pt;
+    margin-top: 14px;
+    margin-bottom: 8px;
+    page-break-after: avoid;
+    font-weight: 600;
+}
+
+h6 {
+    color: #777;
+    font-size: 11pt;
+    margin-top: 12px;
+    margin-bottom: 8px;
+    page-break-after: avoid;
+    font-weight: 600;
+}
+
+p {
+    margin: 10px 0;
+    line-height: 1.65;
+}
+
 table {
     width: 100%;
     border-collapse: collapse;
@@ -190,6 +223,14 @@ tr:nth-child(odd) {
     box-shadow: 0 2px 4px rgba(0,0,0,0.05);
 }
 
+.highlight-box p:first-child {
+    margin-top: 0;
+}
+
+.highlight-box p:last-child {
+    margin-bottom: 0;
+}
+
 .key-metric-box {
     background: linear-gradient(135deg, #003366 0%, #0055a5 100%);
     color: white;
@@ -200,11 +241,25 @@ tr:nth-child(odd) {
     box-shadow: 0 3px 6px rgba(0,0,0,0.15);
 }
 
-.key-metric-box h3 {
+.key-metric-box h3,
+.key-metric-box h4,
+.key-metric-box h5 {
     color: white;
     margin-top: 0;
 }
 
+.key-metric-box p:first-child {
+    margin-top: 0;
+}
+
+.key-metric-box p:last-child {
+    margin-bottom: 0;
+}
+
+.key-metric-box strong {
+    color: #ffffff;
+}
+
 blockquote {
     border-left: 5px solid #003366;
     margin-left: 0;
@@ -217,6 +272,19 @@ blockquote {
     box-shadow: 0 1px 2px rgba(0,0,0,0.05);
 }
 
+blockquote p:first-child {
+    margin-top: 0;
+}
+
+blockquote p:last-child {
+    margin-bottom: 0;
+}
+
+blockquote strong {
+    font-weight: 700;
+    color: #000;
+}
+
 .figure-container {
     text-align: center;
     margin: 24px 0;
@@ -249,11 +317,19 @@ blockquote {
     border-radius: 5px;
 }
 
+.executive-summary p:first-child {
+    margin-top: 0;
+}
+
+.executive-summary p:last-child {
+    margin-bottom: 0;
+}
+
 .page-break {
     page-break-after: always;
 }
 
-/* ENHANCED LIST STYLING - ENSURES PROPER BULLET RENDERING */
+/* COMPREHENSIVE LIST STYLING */
 ul {
     margin: 16px 0;
     padding-left: 35px;
@@ -275,6 +351,10 @@ li {
     display: list-item;
 }
 
+li p {
+    margin: 4px 0;
+}
+
 ul ul {
     margin: 8px 0;
     padding-left: 25px;
@@ -291,12 +371,33 @@ ol ol {
     list-style-type: lower-alpha;
 }
 
-strong {
-    font-weight: 600;
+ol ol ol {
+    list-style-type: lower-roman;
+}
+
+/* Lists inside special boxes */
+.highlight-box ul,
+.highlight-box ol,
+.key-metric-box ul,
+.key-metric-box ol,
+.executive-summary ul,
+.executive-summary ol,
+blockquote ul,
+blockquote ol {
+    margin: 12px 0;
+}
+
+.key-metric-box li {
+    color: white;
+}
+
+/* TEXT FORMATTING */
+strong, b {
+    font-weight: 700;
     color: #000;
 }
 
-em {
+em, i {
     font-style: italic;
 }
 
@@ -306,6 +407,7 @@ code {
     padding: 2px 6px;
     border-radius: 3px;
     font-size: 10pt;
+    color: #c7254e;
 }
 
 pre {
@@ -319,6 +421,27 @@ pre {
     line-height: 1.4;
     margin: 16px 0;
 }
+
+pre code {
+    background-color: transparent;
+    padding: 0;
+    color: #333;
+}
+
+a {
+    color: #0055a5;
+    text-decoration: none;
+}
+
+a:hover {
+    text-decoration: underline;
+}
+
+hr {
+    border: none;
+    border-top: 2px solid #ddd;
+    margin: 24px 0;
+}
 """
 
 # ---------------------------------------------------------
@@ -372,11 +495,39 @@ def fetch_image(url: str, output_dir: str) -> Optional[str]:
         logger.warning(f"Failed to download image: {url[:50]}... - {e}")
         return None
 
+# ---------------------------------------------------------
+# 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
+    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:
+                return f'<{tag} markdown="1">'
+        
+        content = re.sub(pattern, add_markdown_attr, content, flags=re.IGNORECASE)
+    
+    return content
+
 # ---------------------------------------------------------
 # Q4 REPORT GENERATOR CLASS
 # ---------------------------------------------------------
 class Q4ReportGenerator:
-    """Generates executive-quality Q4 reports using WeasyPrint."""
+    """Generates executive-quality Q4 reports using WeasyPrint with complete markdown support."""
     
     def __init__(self, 
                  title: str = "Q4 Performance Report",
@@ -423,30 +574,47 @@ class Q4ReportGenerator:
         """
     
     def _process_section(self, section: Dict, output_dir: str) -> str:
-        """Process section with enhanced markdown parsing for proper list rendering."""
+        """
+        Process section with COMPLETE markdown parsing support.
+        Handles markdown both outside and inside HTML tags.
+        """
         html = ""
         
         content = section.get("content", "")
         if content:
-            # Use comprehensive markdown extensions for full parsing
+            # 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(
-                content,
+                preprocessed_content,
                 extensions=[
-                    'extra',           # Tables, footnotes, attributes
+                    'extra',           # Tables, footnotes, attributes, etc.
                     'sane_lists',      # Better list handling
                     'tables',          # Table support
-                    'fenced_code',     # Code blocks
-                    'nl2br',           # Newline to <br>
+                    'fenced_code',     # Code blocks with ```
+                    'nl2br',           # Convert newlines to <br>
                     'codehilite',      # Syntax highlighting
-                    'toc'              # Table of contents
+                    '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
                 ],
                 extension_configs={
                     'codehilite': {
                         'guess_lang': False,
-                        'noclasses': True
+                        'noclasses': True,
+                        'css_class': 'highlight'
+                    },
+                    'md_in_html': {
+                        'allowed_elements': ['div', 'blockquote', 'section', 'article', 'aside', 'span']
                     }
                 }
             )
+            
             html += f"<div class='section'>{html_content}</div>"
         
         # Handle images
@@ -481,12 +649,13 @@ class Q4ReportGenerator:
                  filename: str = "Q4_Report.pdf",
                  output_dir: str = "./output",
                  cover_page: bool = True) -> bool:
-        """Generate PDF report with proper markdown parsing."""
+        """Generate PDF report with complete markdown parsing everywhere."""
         try:
             os.makedirs(output_dir, exist_ok=True)
             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)")
             
             # Build HTML body
             body_html = ""
@@ -522,6 +691,7 @@ 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
             
         except Exception as e:
@@ -538,54 +708,3 @@ class Q4ReportGenerator:
                 logger.info("Cleaned up temporary images")
         except Exception as e:
             logger.warning(f"Failed to cleanup images: {e}")
-
-
-# ---------------------------------------------------------
-# USAGE EXAMPLE
-# ---------------------------------------------------------
-# if __name__ == "__main__":
-#     # Example usage
-#     generator = Q4ReportGenerator(
-#         title="Q4 2024 Performance Report",
-#         subtitle="Product Analytics Summary",
-#         author="Analytics Team",
-#         department="Product Department"
-#     )
-    
-#     sections = [
-#         {
-#             "content": """
-# # Executive Summary
-
-# This report provides a comprehensive analysis of Q4 2024 product performance.
-
-# ## Key Highlights
-
-# * Revenue increased by 23% compared to Q3
-# * Customer satisfaction improved to 4.7/5.0
-# * Successfully launched 3 new product features
-
-# ## Daily Product Additions
-
-# Example Daily Additions:
-
-# * 2023-09-30: 3 products
-# * 2023-10-01: 1 product
-# * 2023-10-02: 4 products
-# * 2024-09-27: 3 products
-# * 2024-09-28: 3 products
-# * 2024-09-29: 2 products
-
-# ## Growth Metrics
-
-# 1. User acquisition up 45%
-# 2. Retention rate improved to 87%
-# 3. Average session time increased by 12 minutes
-#             """,
-#             "page_break": False
-#         }
-#     ]
-    
-#     success = generator.generate(sections, filename="Q4_Report.pdf")
-#     if success:
-#         print("Report generated successfully!")