debug-chapter-simple.js

// Test the fixed regex logic

const testCases = [
  '<h1>Bonus Chapter: The Competition</h1>',  // Should NOT split (subtitle)
  '<h1>Bonus ChapterThree weeks after</h1>',  // SHOULD split (merged body text)
  '<h1>Chapter 1</h1>',                        // Should NOT split (no body)
  '<h1>Chapter 1Dominik stood</h1>',          // SHOULD split (merged body text)
];

testCases.forEach((html, i) => {
  console.log(`\n=== Test Case ${i + 1} ===`);
  console.log('Original HTML:', html);
  
  // Step 1: Normalize multi-line headings
  let result = html.replace(/<h([1-6])([^>]*)>([\s\S]*?)<\/h\1>/gi, (match, level, attrs, inner) => {
    const cleanInner = inner.replace(/<[^>]*>/g, '').replace(/\s+/g, ' ').trim();
    return `<h${level}${attrs}>${cleanInner}</h${level}>`;
  });
  
  console.log('After Step 1:', result);
  
  // Step 2a: Chapter N + merged text
  result = result.replace(/<h([1-6])([^>]*)>(Chapter\s+\d+)([A-Z][a-z][^<]*)<\/h\1>/g, (m, lvl, attrs, cap, rest) => {
    console.log('  → Split Chapter N pattern');
    return `<h${lvl}${attrs}>${cap}</h${lvl}>\n<p>${rest}</p>`;
  });
  
  // Step 2b: Special chapters ONLY when NO subtitle punctuation
  result = result.replace(/<h([1-6])([^>]*)>((?:Bonus|Epilogue|Prologue|Final|Extra)\s+Chapter)(?![\s:.\-])([A-Z][a-z][^<]*)<\/h\1>/g, (m, lvl, attrs, cap, rest) => {
    console.log('  → Split Special Chapter pattern (no subtitle)');
    return `<h${lvl}${attrs}>${cap}</h${lvl}>\n<p>${rest}</p>`;
  });
  
  console.log('After Step 2:', result);
});