274 lines
8.5 KiB
Python
274 lines
8.5 KiB
Python
# html_template = """
|
|
# <!DOCTYPE html>
|
|
# <html>
|
|
# <head>
|
|
# <meta charset="utf-8">
|
|
# <style>
|
|
# /* Existing styles... */
|
|
|
|
# /* Styles for Links */
|
|
# a {{
|
|
# color: #0000ff; /* Sets the link color to blue */
|
|
# text-decoration: underline; /* Ensures the underline is visible */
|
|
# }}
|
|
# a:visited {{
|
|
# color: #0000ff; /* Keeps the link blue even after it is clicked */
|
|
# }}
|
|
|
|
# /* Styles for clean Table Lines */
|
|
# table {{
|
|
# width: 100%;
|
|
# border-collapse: collapse; /* Merges adjacent cell borders into a single line */
|
|
# margin: 20px 0;
|
|
# font-size: 11pt;
|
|
# }}
|
|
# th, td {{
|
|
# border: 1px solid #bdc3c7; /* Draws the actual grid lines */
|
|
# padding: 10px;
|
|
# text-align: left;
|
|
# }}
|
|
# th {{
|
|
# background-color: #f2f4f4; /* Optional: adds a neat background header color */
|
|
# font-weight: bold;
|
|
# color: #2c3e50;
|
|
# }}
|
|
# tr:nth-child(even) {{
|
|
# background-color: #f9f9f9; /* Optional: adds zebra striping to rows */
|
|
# }}
|
|
|
|
# /* Table of Contents Styles */
|
|
# .toc-list {{
|
|
# list-style-type: decimal;
|
|
# padding-left: 20px;
|
|
# margin: 10px 0;
|
|
# }}
|
|
# .toc-list li {{
|
|
# margin-bottom: 6px;
|
|
# font-size: 11pt;
|
|
# }}
|
|
# /* Styles the nested sub-sections */
|
|
# .toc-list ul {{
|
|
# list-style-type: none; /* Removes numbers/bullets from sub-items */
|
|
# padding-left: 20px; /* Creates the indent */
|
|
# margin: 4px 0;
|
|
# }}
|
|
# .toc-list ul li {{
|
|
# position: relative;
|
|
# font-size: 10.5pt;
|
|
# color: #555;
|
|
# }}
|
|
# /* Adds a clean dash prefix (-) to the sub-items */
|
|
# .toc-list ul li::before {{
|
|
# content: "- ";
|
|
# position: absolute;
|
|
# left: -12px;
|
|
# }}
|
|
# </style>
|
|
# </head>
|
|
# <body>
|
|
# {content}
|
|
# </body>
|
|
# </html>
|
|
# """
|
|
|
|
html_template = """
|
|
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<style>
|
|
/* --- WeasyPrint Page Parameters --- */
|
|
@page {{
|
|
size: A4;
|
|
margin: 20mm;
|
|
@bottom-right {{
|
|
content: counter(page) " / " counter(pages);
|
|
font-family: Arial, sans-serif;
|
|
font-size: 9pt;
|
|
color: #7f8c8d;
|
|
}}
|
|
}}
|
|
|
|
body {{
|
|
font-family: Arial, sans-serif;
|
|
color: #2c3e50;
|
|
line-height: 1.6;
|
|
font-size: 11pt;
|
|
}}
|
|
|
|
/* --- Table of Contents Component --- */
|
|
.toc-box {{
|
|
margin: 25px 0;
|
|
padding: 20px;
|
|
background-color: #fcfcfc;
|
|
border: 1px solid #eaeaea;
|
|
border-radius: 4px;
|
|
}}
|
|
|
|
/* Direct Parents (1., 2., 3.) */
|
|
.toc-box > ol {{
|
|
list-style-type: decimal;
|
|
padding-left: 20px;
|
|
margin: 0;
|
|
}}
|
|
|
|
.toc-box > ol > li {{
|
|
font-size: 12pt;
|
|
font-weight: bold;
|
|
margin-top: 12px;
|
|
color: #2c3e50;
|
|
}}
|
|
|
|
/* Targets sub-items that Python and Markdown nested inside the <li> tag */
|
|
.toc-box ol li ul {{
|
|
list-style-type: none; /* Destroys standard browser bullet points */
|
|
padding-left: 20px; /* Indents sub-items perfectly to the right */
|
|
margin: 6px 0 0 0;
|
|
}}
|
|
|
|
.toc-box ol li ul li {{
|
|
font-size: 11pt;
|
|
font-weight: normal; /* Removes parent bold styles from sub-items */
|
|
color: #555555;
|
|
margin-bottom: 5px;
|
|
position: relative;
|
|
}}
|
|
|
|
/* Injects a clean layout hyphen prefix natively via CSS */
|
|
.toc-box ol li ul li::before {{
|
|
content: "- ";
|
|
font-weight: bold;
|
|
color: #7f8c8d;
|
|
}}
|
|
|
|
/* --- Global Structural Typography --- */
|
|
h1, h2, h3, h4, h5, h6 {{
|
|
color: #2c3e50;
|
|
font-weight: bold;
|
|
page-break-after: avoid;
|
|
break-after: avoid;
|
|
}}
|
|
|
|
table {{
|
|
width: 100%;
|
|
border-collapse: collapse;
|
|
margin: 24px 0;
|
|
font-size: 10.5pt;
|
|
page-break-inside: auto;
|
|
break-inside: auto;
|
|
}}
|
|
tr {{ page-break-inside: avoid; break-inside: avoid; }}
|
|
th, td {{ border: 1px solid #bdc3c7; padding: 10px; text-align: left; }}
|
|
th {{ background-color: #f2f4f4; font-weight: bold; }}
|
|
|
|
a {{ color: #2980b9; text-decoration: none; }}
|
|
.page-break {{ page-break-before: always; }}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
{content}
|
|
</body>
|
|
</html>
|
|
"""
|
|
|
|
import re
|
|
import markdown
|
|
from html.parser import HTMLParser
|
|
from weasyprint import HTML
|
|
|
|
class TOCHtmlRestructurer(HTMLParser):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.output = []
|
|
self.level_stack = [] # Tracks nesting hierarchy
|
|
self.parent_count = 0
|
|
self.child_count = 0
|
|
self.capture_text = False
|
|
self.current_item_text = ""
|
|
self.current_href = None # Tracks anchor references dynamically
|
|
|
|
def handle_starttag(self, tag, attrs):
|
|
if tag in ['ol', 'ul']:
|
|
if not self.level_stack:
|
|
self.level_stack.append('parent')
|
|
else:
|
|
self.level_stack.append('child')
|
|
elif tag == 'li':
|
|
self.capture_text = True
|
|
self.current_item_text = ""
|
|
self.current_href = None
|
|
elif tag == 'a' and self.capture_text:
|
|
# Capture the link anchor destination safely
|
|
attrs_dict = dict(attrs)
|
|
self.current_href = attrs_dict.get('href')
|
|
|
|
def handle_endtag(self, tag):
|
|
if tag in ['ol', 'ul']:
|
|
if self.level_stack:
|
|
self.level_stack.pop()
|
|
elif tag == 'li':
|
|
self.capture_text = False
|
|
self.process_accumulated_item()
|
|
|
|
def handle_data(self, data):
|
|
if self.capture_text:
|
|
self.current_item_text += data
|
|
|
|
def process_accumulated_item(self):
|
|
# 1. Clean out stray prefix digits and list flags safely
|
|
clean = self.current_item_text.strip()
|
|
clean = re.sub(r'^([\d\.\s\-•]*\d+\.\d+|[\d\.\s\-•]*\d+\.)\s*', '', clean)
|
|
clean = re.sub(r'^\d+\s+(?=[A-Za-z])', '', clean)
|
|
clean = re.sub(r'^[\s\-•]*', '', clean).strip()
|
|
|
|
if not clean:
|
|
return
|
|
|
|
# 2. Check current depth level stack state
|
|
current_state = self.level_stack[-1] if self.level_stack else 'parent'
|
|
|
|
# 3. Rebuild the text as a clickable link if an anchor was present
|
|
if self.current_href:
|
|
display_text = f'<a href="{self.current_href}">{clean}</a>'
|
|
else:
|
|
display_text = clean
|
|
|
|
# 4. Generate structured HTML outputs with calculated taxonomy counters
|
|
if current_state == 'parent':
|
|
self.parent_count += 1
|
|
self.child_count = 0
|
|
self.output.append(f'<div class="toc-parent">{self.parent_count}. {display_text}</div>')
|
|
else:
|
|
self.child_count += 1
|
|
self.output.append(f'<div class="toc-child">{self.parent_count}.{self.child_count} {display_text}</div>')
|
|
|
|
def extract_and_fix_toc_blocks(html_content):
|
|
"""
|
|
Finds the compiled HTML lists block, intercepts it, clears
|
|
numbering artifacts structurally via HTML parsing tree mechanics.
|
|
"""
|
|
match = re.search(r'(<(?:ol|ul)>[\s\S]*?</(?:ol|ul)>)', html_content)
|
|
if not match:
|
|
return html_content
|
|
|
|
raw_toc_html = match.group(1)
|
|
|
|
parser = TOCHtmlRestructurer()
|
|
parser.feed(raw_toc_html)
|
|
|
|
new_toc_html = '<div class="toc-box">\n<h2>Table of Contents</h2>\n'
|
|
new_toc_html += '\n'.join(parser.output)
|
|
new_toc_html += '\n</div>'
|
|
|
|
return html_content.replace(raw_toc_html, new_toc_html, 1)
|
|
|
|
def export_to_pdf(inputText, filename):
|
|
"""
|
|
Processes plain dynamic markdown, captures structural compilation output,
|
|
restructures TOC nodes downstream safely, and outputs a high-fidelity PDF.
|
|
"""
|
|
html_content = markdown.markdown(inputText, extensions=['tables', 'fenced_code'])
|
|
final_body_content = extract_and_fix_toc_blocks(html_content)
|
|
|
|
final_html = html_template.format(content=final_body_content)
|
|
HTML(string=final_html).write_pdf(filename) |