#!/usr/bin/env python3
"""
Markdown to PDF converter with proper UTF-8 support using fpdf2
"""
import markdown
from fpdf import FPDF
import re
import os

class PDF(FPDF):
    def __init__(self):
        super().__init__()
        self.set_auto_page_break(auto=True, margin=15)

    def header(self):
        # Header with title
        pass

    def footer(self):
        # Page number
        self.set_y(-15)
        self.set_font('Arial', 'I', 8)
        self.set_text_color(128, 128, 128)
        self.cell(0, 10, f'Page {self.page_no()}', 0, 0, 'C')

class MarkdownToPDF:
    def __init__(self, input_file, output_file):
        self.input_file = input_file
        self.output_file = output_file
        self.pdf = PDF()
        self.pdf.add_page()

    def convert(self):
        # Read markdown
        with open(self.input_file, 'r', encoding='utf-8') as f:
            md_content = f.read()

        # Parse line by line
        lines = md_content.split('\n')

        for line in lines:
            line = line.strip()

            if not line:
                self.pdf.ln(3)
                continue

            # Main title (H1)
            if line.startswith('# ') and not line.startswith('## '):
                title = line[2:].strip()
                self.pdf.set_font('Arial', 'B', 20)
                self.pdf.set_text_color(44, 62, 80)  # #2C3E50
                self.pdf.multi_cell(0, 10, title, align='C')
                self.pdf.ln(5)

            # H2
            elif line.startswith('## ') and not line.startswith('### '):
                title = line[3:].strip()
                self.pdf.ln(3)
                self.pdf.set_font('Arial', 'B', 16)
                self.pdf.set_text_color(44, 62, 80)
                self.pdf.multi_cell(0, 8, title)
                self.pdf.ln(2)

            # H3
            elif line.startswith('### ') and not line.startswith('#### '):
                title = line[4:].strip()
                self.pdf.ln(2)
                self.pdf.set_font('Arial', 'B', 14)
                self.pdf.set_text_color(39, 174, 96)  # #27AE60
                self.pdf.multi_cell(0, 7, title)
                self.pdf.ln(1)

            # H4
            elif line.startswith('#### '):
                title = line[5:].strip()
                self.pdf.ln(1)
                self.pdf.set_font('Arial', 'B', 12)
                self.pdf.set_text_color(44, 62, 80)
                self.pdf.multi_cell(0, 6, title)

            # Horizontal rule
            elif line.startswith('---'):
                self.pdf.ln(2)

            # Code block start/end (```)
            elif line.startswith('```'):
                continue

            # List item
            elif line.startswith('- ') or line.startswith('* '):
                text = line[2:].strip()
                # Remove markdown formatting
                text = self._clean_markdown(text)
                self.pdf.set_font('Arial', '', 10)
                self.pdf.set_text_color(51, 51, 51)
                self.pdf.set_x(self.pdf.l_margin + 5)
                self.pdf.multi_cell(0, 5, f'• {text}')

            # Blockquote
            elif line.startswith('>'):
                text = line[1:].strip()
                text = self._clean_markdown(text)
                self.pdf.set_font('Arial', 'I', 10)
                self.pdf.set_text_color(85, 85, 85)
                self.pdf.set_fill_color(245, 245, 245)
                self.pdf.multi_cell(0, 5, text, fill=True)

            # Table separator
            elif line.startswith('|') and '---' in line:
                continue

            # Table row
            elif line.startswith('|'):
                continue  # Skip tables for now (complex to render)

            # Normal paragraph
            else:
                # Skip if it's likely a table header or separator
                if '|' in line:
                    continue

                text = self._clean_markdown(line)
                if text:
                    self.pdf.set_font('Arial', '', 10)
                    self.pdf.set_text_color(51, 51, 51)
                    self.pdf.multi_cell(0, 5, text)

        # Save PDF
        self.pdf.output(self.output_file)
        print(f"PDF created successfully: {self.output_file}")

    def _clean_markdown(self, text):
        """Remove markdown formatting"""
        # Remove bold **text**
        text = re.sub(r'\*\*(.*?)\*\*', r'\1', text)
        # Remove italic *text*
        text = re.sub(r'\*(.*?)\*', r'\1', text)
        # Remove inline code `text`
        text = re.sub(r'`(.*?)`', r'\1', text)
        # Remove links [text](url)
        text = re.sub(r'\[(.*?)\]\(.*?\)', r'\1', text)
        return text

if __name__ == '__main__':
    input_file = r'C:\Users\alexi\Documents\projects\freelance-dashboard\TECHNICAL_REFERENCE_EN.md'
    output_file = r'C:\Users\alexi\Documents\projects\freelance-dashboard\TECHNICAL_REFERENCE_EN.pdf'

    converter = MarkdownToPDF(input_file, output_file)
    converter.convert()