md2pdf-tex 0.1.0__py3-none-any.whl

md2pdf.py

@@ -0,0 +1,416 @@
+"""
+Convert a Markdown file with LaTeX math to a polished PDF file using KaTeX
+for math rendering and Selenium (headless Chrome) for printing.
+
+Usage: python3 md2pdf.py <input.md> [output.pdf]
+"""
+import re
+import sys
+import os
+import tempfile
+import base64
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.support.ui import WebDriverWait
+
+# Execution logic is wrapped in main() at the bottom
+
+
+# --- Step 1: Protect math blocks from markdown processing ---
+# Extract display math $$ ... $$ and inline math $ ... $
+# We'll convert markdown manually since we need fine control.
+
+def md_to_html(md):
+	"""Simple markdown to HTML converter that preserves LaTeX math."""
+	lines = md.split('\n')
+	html_lines = []
+	in_list = False
+	in_sublist = False
+	i = 0
+
+	while i < len(lines):
+		line = lines[i]
+
+		# Display math block
+		if line.strip().startswith('$$'):
+			if in_list:
+				if in_sublist:
+					html_lines.append('</ul></li>')
+					in_sublist = False
+				html_lines.append('</ul>')
+				in_list = False
+			# Collect all lines until closing $$
+			math_content = []
+			if line.strip() == '$$':
+				i += 1
+				while i < len(lines) and lines[i].strip() != '$$':
+					math_content.append(lines[i])
+					i += 1
+				i += 1  # skip closing $$
+			elif line.strip().endswith('$$') and line.strip() != '$$':
+				# Single-line: $$...$$
+				inner = line.strip()[2:-2]
+				math_content.append(inner)
+				i += 1
+			else:
+				# Opens with $$ but doesn't close on same line
+				rest = line.strip()[2:]
+				if rest:
+					math_content.append(rest)
+				i += 1
+				while i < len(lines) and not lines[i].strip().endswith('$$'):
+					math_content.append(lines[i])
+					i += 1
+				if i < len(lines):
+					last = lines[i].strip()
+					if last != '$$':
+						math_content.append(last[:-2])
+					i += 1
+
+			latex = '\n'.join(math_content).strip()
+			html_lines.append(f'<div class="math-display">$${latex}$$</div>')
+			continue
+
+		# Headers
+		if line.startswith('###'):
+			if in_list:
+				if in_sublist:
+					html_lines.append('</ul></li>')
+					in_sublist = False
+				html_lines.append('</ul>')
+				in_list = False
+			html_lines.append(f'<h3>{process_inline(line.lstrip("#").strip())}</h3>')
+			i += 1
+			continue
+		if line.startswith('##'):
+			if in_list:
+				if in_sublist:
+					html_lines.append('</ul></li>')
+					in_sublist = False
+				html_lines.append('</ul>')
+				in_list = False
+			html_lines.append(f'<h2>{process_inline(line.lstrip("#").strip())}</h2>')
+			i += 1
+			continue
+		if line.startswith('#'):
+			if in_list:
+				if in_sublist:
+					html_lines.append('</ul></li>')
+					in_sublist = False
+				html_lines.append('</ul>')
+				in_list = False
+			html_lines.append(f'<h1>{process_inline(line.lstrip("#").strip())}</h1>')
+			i += 1
+			continue
+
+		# List items (detect indent level)
+		if line.strip().startswith('- '):
+			# Determine indent level
+			stripped = line.rstrip()
+			leading_ws = len(stripped) - len(stripped.lstrip())
+			is_sub = leading_ws >= 2 or stripped.startswith('\t-') or stripped.startswith('\t\t-')
+			text = line.strip().lstrip('- ').strip()
+
+			if is_sub:
+				if not in_list:
+					html_lines.append('<ul>')
+					in_list = True
+				if not in_sublist:
+					html_lines.append('<li><ul>')
+					in_sublist = True
+				html_lines.append(f'<li>{process_inline(text)}</li>')
+			else:
+				if in_sublist:
+					html_lines.append('</ul></li>')
+					in_sublist = False
+				if not in_list:
+					html_lines.append('<ul>')
+					in_list = True
+				html_lines.append(f'<li>{process_inline(text)}</li>')
+			i += 1
+			continue
+
+		# Close any open list
+		if in_list and line.strip() == '':
+			if in_sublist:
+				html_lines.append('</ul></li>')
+				in_sublist = False
+			html_lines.append('</ul>')
+			in_list = False
+			i += 1
+			continue
+
+		# Empty line
+		if line.strip() == '':
+			i += 1
+			continue
+
+		# Regular paragraph — collect contiguous lines
+		para_lines = [line]
+		i += 1
+		while i < len(lines):
+			next_line = lines[i]
+			if (next_line.strip() == '' or
+				next_line.startswith('#') or
+				next_line.strip().startswith('- ') or
+				next_line.strip().startswith('$$')):
+				break
+			para_lines.append(next_line)
+			i += 1
+
+		if in_list:
+			if in_sublist:
+				html_lines.append('</ul></li>')
+				in_sublist = False
+			html_lines.append('</ul>')
+			in_list = False
+
+		paragraph = ' '.join(l.strip() for l in para_lines)
+		html_lines.append(f'<p>{process_inline(paragraph)}</p>')
+
+	# Close any remaining open list
+	if in_sublist:
+		html_lines.append('</ul></li>')
+	if in_list:
+		html_lines.append('</ul>')
+
+	return '\n'.join(html_lines)
+
+
+def process_inline(text):
+	"""Process inline markdown: bold, italic, code, inline math."""
+	# Protect inline math first — replace with placeholders
+	math_parts = []
+	def save_math(m):
+		math_parts.append(m.group(0))
+		return f'%%MATH{len(math_parts)-1}%%'
+
+	text = re.sub(r'(?<!\$)\$(?!\$)(.+?)\$(?!\$)', save_math, text)
+
+	# Code
+	text = re.sub(r'`(.+?)`', r'<code>\1</code>', text)
+	# Bold
+	text = re.sub(r'\*\*(.+?)\*\*', r'<strong>\1</strong>', text)
+	# Italic
+	text = re.sub(r'\*(.+?)\*', r'<em>\1</em>', text)
+
+	# Restore math
+	for i, m in enumerate(math_parts):
+		text = text.replace(f'%%MATH{i}%%', f'<span class="math-inline">{m}</span>')
+
+	return text
+
+
+def main():
+	if len(sys.argv) < 2:
+		print("Usage: md2pdf <input.md> [output.pdf]")
+		sys.exit(1)
+
+	INPUT = sys.argv[1]
+	if len(sys.argv) >= 3:
+		OUTPUT_PDF = sys.argv[2]
+	else:
+		OUTPUT_PDF = os.path.splitext(os.path.basename(INPUT))[0] + ".pdf"
+
+	with open(INPUT, "r") as f:
+		md_text = f.read()
+
+	TITLE = os.path.splitext(os.path.basename(INPUT))[0].replace('_', ' ').title()
+
+	body_html = md_to_html(md_text)
+
+	full_html = f"""<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<title>{TITLE}</title>
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.22/dist/katex.min.css">
+<script defer src="https://cdn.jsdelivr.net/npm/katex@0.16.22/dist/katex.min.js"></script>
+<script defer src="https://cdn.jsdelivr.net/npm/katex@0.16.22/dist/contrib/auto-render.min.js"
+  onload="renderMathInElement(document.body, {{
+    delimiters: [
+      {{left: '$$', right: '$$', display: true}},
+      {{left: '$', right: '$', display: false}}
+    ],
+    throwOnError: false
+  }});"></script>
+<style>
+  @import url('https://fonts.googleapis.com/css2?family=Source+Serif+4:ital,wght@0,400;0,600;0,700;1,400&family=Source+Sans+3:wght@400;600;700&family=Source+Code+Pro:wght@400&display=swap');
+
+  :root {{
+    --text: #1a1a2e;
+    --muted: #555;
+    --accent: #2d5aa0;
+    --border: #d0d7de;
+    --bg-code: #f6f8fa;
+  }}
+
+  * {{ margin: 0; padding: 0; box-sizing: border-box; }}
+
+  body {{
+    font-family: 'Source Serif 4', Georgia, 'Times New Roman', serif;
+    font-size: 11pt;
+    line-height: 1.7;
+    color: var(--text);
+    max-width: 680px;
+    margin: 0 auto;
+    padding: 48px 32px;
+  }}
+
+  h1 {{
+    font-family: 'Source Sans 3', 'Helvetica Neue', Arial, sans-serif;
+    font-size: 24pt;
+    font-weight: 700;
+    margin: 36px 0 12px 0;
+    color: var(--text);
+    letter-spacing: -0.02em;
+  }}
+
+  h2 {{
+    font-family: 'Source Sans 3', 'Helvetica Neue', Arial, sans-serif;
+    font-size: 17pt;
+    font-weight: 700;
+    margin: 32px 0 8px 0;
+    padding-bottom: 6px;
+    border-bottom: 2px solid var(--border);
+    color: var(--text);
+    letter-spacing: -0.01em;
+  }}
+
+  h3 {{
+    font-family: 'Source Sans 3', 'Helvetica Neue', Arial, sans-serif;
+    font-size: 13pt;
+    font-weight: 600;
+    margin: 24px 0 6px 0;
+    color: var(--accent);
+  }}
+
+  p {{
+    margin: 10px 0;
+    text-align: justify;
+    hyphens: auto;
+  }}
+
+  ul {{
+    margin: 8px 0;
+    padding-left: 24px;
+  }}
+
+  li {{
+    margin-bottom: 5px;
+  }}
+
+  li > ul {{
+    margin-top: 4px;
+  }}
+
+  strong {{
+    font-weight: 600;
+  }}
+
+  code {{
+    font-family: 'Source Code Pro', 'Menlo', 'Consolas', monospace;
+    font-size: 0.9em;
+    background: var(--bg-code);
+    padding: 1px 5px;
+    border-radius: 3px;
+    border: 1px solid #e1e4e8;
+  }}
+
+  .math-display {{
+    margin: 20px 0;
+    text-align: center;
+    overflow-x: auto;
+  }}
+
+  .math-inline .katex {{
+    font-size: 1.0em;
+  }}
+
+  .math-display .katex {{
+    font-size: 1.15em;
+  }}
+
+  /* Print-specific styles */
+  @media print {{
+    body {{
+      padding: 0;
+      max-width: none;
+    }}
+    h2 {{
+      page-break-after: avoid;
+    }}
+    .math-display {{
+      page-break-inside: avoid;
+    }}
+  }}
+</style>
+</head>
+<body>
+{body_html}
+</body>
+</html>
+"""
+
+	# Write HTML to a temporary file
+	with tempfile.NamedTemporaryFile(mode='w', suffix='.html', delete=False, encoding='utf-8') as f:
+		f.write(full_html)
+		temp_html_path = f.name
+
+	try:
+		options = Options()
+		options.add_argument('--headless')
+		options.add_argument('--no-sandbox')
+		options.add_argument('--disable-dev-shm-usage')
+
+		# Point to playwright-installed chromium in test sandbox
+		sandbox_chrome = "/home/agent/.cache/ms-playwright/chromium-1223/chrome-linux64/chrome"
+		if os.path.exists(sandbox_chrome):
+			options.binary_location = sandbox_chrome
+
+		# Create driver (Selenium Manager handles chromedriver automatically)
+		driver = webdriver.Chrome(options=options)
+
+		try:
+			# Load the HTML file
+			driver.get(f"file://{os.path.abspath(temp_html_path)}")
+
+			# Wait for KaTeX to finish rendering
+			WebDriverWait(driver, 10).until(
+				lambda d: d.execute_script("""
+					const mathElements = document.querySelectorAll('.math-display, .math-inline');
+					if (mathElements.length === 0) return true;
+					return document.querySelectorAll('.katex').length > 0;
+				""")
+			)
+
+			# Print to PDF using CDP
+			print_settings = {
+				"printBackground": True,
+				"paperWidth": 8.27,    # A4 width in inches
+				"paperHeight": 11.69,  # A4 height in inches
+				"marginTop": 0.5,      # 48px margin in inches (48 / 96 = 0.5)
+				"marginBottom": 0.5,
+				"marginLeft": 0.5,
+				"marginRight": 0.5
+			}
+
+			result = driver.execute_cdp_cmd("Page.printToPDF", print_settings)
+			pdf_data = base64.b64decode(result['data'])
+
+			with open(OUTPUT_PDF, "wb") as pdf_file:
+				pdf_file.write(pdf_data)
+
+			print(f"PDF written to {os.path.abspath(OUTPUT_PDF)}")
+		finally:
+			driver.quit()
+	except Exception as e:
+		print(f"Error printing PDF via Selenium: {e}", file=sys.stderr)
+		sys.exit(1)
+	finally:
+		if os.path.exists(temp_html_path):
+			os.remove(temp_html_path)
+
+
+if __name__ == '__main__':
+	main()

md2pdf_tex-0.1.0.dist-info/METADATA

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: md2pdf-tex
+Version: 0.1.0
+Summary: Convert Markdown with LaTeX math to PDF using KaTeX and headless Chrome
+Author: Roberto Moura
+Project-URL: Homepage, https://github.com/robertoffmoura/md2pdf
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+Requires-Dist: selenium
+
+# md2pdf
+
+A minimalist, high-fidelity Markdown-to-PDF converter written in Python. It parses Markdown files containing LaTeX mathematical formulas, renders them using KaTeX, and outputs a print-perfect PDF using a headless Chrome instance via Selenium.
+
+## Features
+
+- **High-Fidelity PDF Output**: Employs headless Google Chrome to print the rendered HTML layout to PDF, preserving pagination, fonts, margins, and alignments.
+- **LaTeX Math Support**: Seamlessly renders inline math (`$...$`) and block math (`$$...$$`) via **KaTeX**.
+- **Minimal Dependencies**: Requires only Python, Chrome/Chromium, and the Python `selenium` library.
+- **Polished Typography**: Features premium, print-optimized font pairings (Source Serif 4, Source Sans 3, and Source Code Pro) loaded dynamically from Google Fonts.
+- **Clean Markdown Parser**: A custom regex-based parser that translates standard Markdown elements into clean HTML while protecting LaTeX delimiters from markdown interference.
+
+---
+
+## Installation
+
+### 1. Prerequisites
+- **Python 3.x**
+- **Google Chrome** or **Chromium** browser installed on your system.
+
+### 2. Install Python Package
+Install the Python dependencies via `pip`. It is recommended to use a virtual environment:
+
+```bash
+# Create and activate a virtual environment (optional)
+python3 -m venv venv
+source venv/bin/activate
+
+# Install Selenium
+pip install selenium
+```
+
+*Note: Selenium Manager will automatically locate and download the appropriate driver (`chromedriver`) for your Chrome version. No manual driver setup is needed.*
+
+---
+
+## Usage
+
+Run the converter from your terminal:
+
+```bash
+python3 md2pdf.py <input.md> [output.pdf]
+```
+
+- **`<input.md>`**: The path to your input Markdown file.
+- **`[output.pdf]`** *(Optional)*: The path for the output PDF file. If omitted, it defaults to the input file's name with a `.pdf` extension in the same directory.
+
+### Example
+
+Given a file `document.md` containing:
+
+```markdown
+# Physics Report
+
+Let's discuss the Maxwell's equations. In differential form, Faraday's law of induction is:
+
+$$\nabla \times \mathbf{E} = -\frac{\partial \mathbf{B}}{\partial t}$$
+
+Where:
+- $\mathbf{E}$ is the electric field.
+- $\mathbf{B}$ is the magnetic field.
+```
+
+Convert it using:
+
+```bash
+python3 md2pdf.py document.md
+```
+
+This generates `document.pdf` with properly formatted headers, bulleted lists, and beautiful, high-resolution mathematical equations.
+
+---
+
+## Supported Markdown Elements
+
+- **Headings**: `#` (H1), `##` (H2), and `###` (H3).
+- **Inline Math**: `$ ... $` for inline formulas (e.g. $E = mc^2$).
+- **Block Math**: `$$ ... $$` for centered display equations.
+- **Unordered Lists**: `- item` and indented `- subitem`.
+- **Text Styling**: `**bold**`, `*italic*`, and inline `` `code` `` fragments.
+- **Paragraphs**: Contiguous lines are automatically joined into standard justified paragraphs.
+
+---
+
+## How It Works
+
+1. **Preprocessing**: The script reads the input Markdown, identifies math blocks, and translates markdown elements (headers, lists, styling) to semantic HTML tags.
+2. **HTML Generation**: It constructs a self-contained HTML document loading **KaTeX** stylesheets/scripts and applying typography rules.
+3. **Rendering & Math Processing**: Selenium starts a headless Chrome browser, loads the HTML, and waits for KaTeX's auto-render extension to process the mathematical formatting.
+4. **PDF Printing**: Headless Chrome's print-to-PDF functionality (`Page.printToPDF` via Chrome DevTools Protocol) is triggered with A4 measurements and standard margins to produce a high-fidelity document.

md2pdf_tex-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+md2pdf.py,sha256=bP61rxR8Y9ishF3uCg35c26Yeo7S3HamN1pcns3IZSE,10389
+md2pdf_tex-0.1.0.dist-info/METADATA,sha256=b3cSQNYeElIEryQfOktrBzBcG6oHNhqkl0VfUSLKx0w,4041
+md2pdf_tex-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+md2pdf_tex-0.1.0.dist-info/entry_points.txt,sha256=XIFGjuiUXJ4L6dHsDEx0qC0mzoD2FOk4GQSljXl9J0A,39
+md2pdf_tex-0.1.0.dist-info/top_level.txt,sha256=M6w-SJJb4vYpGkCZOC_PLJ47_mldkUsf0HvtDmdhJJ0,7
+md2pdf_tex-0.1.0.dist-info/RECORD,,

md2pdf_tex-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

md2pdf_tex-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+md2pdf = md2pdf:main

md2pdf_tex-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+md2pdf