Function stripHtmlCommentsFromTokens

src/utils/claudemd.ts:303–334

(tokens: ReturnType<Lexer['lex']>)

}

function stripHtmlCommentsFromTokens(tokens: ReturnType<Lexer['lex']>): {
  content: string
  stripped: boolean
} {
  let result = ''
  let stripped = false

  // A well-formed HTML comment span. Non-greedy so multiple comments on the
  // same line are matched independently; [\s\S] to span newlines.
  const commentSpan = /<!--[\s\S]*?-->/g

  for (const token of tokens) {
    if (token.type === 'html') {
      const trimmed = token.raw.trimStart()
      if (trimmed.startsWith('<!--') && trimmed.includes('-->')) {
        // Per CommonMark, a type-2 HTML block ends at the *line* containing
        // `-->`, so text after `-->` on that line is part of this token.
        // Strip only the comment spans and keep any residual content.
        const residue = token.raw.replace(commentSpan, '')
        stripped = true
        if (residue.trim().length > 0) {
          // Residual content exists (e.g. `<!-- note --> Use bun`): keep it.
          result += residue
        }
        continue
      }
    }
    result += token.raw
  }

  return { content: result, stripped }
}

/**
 * Parses raw memory file content into a MemoryFileInfo. Pure function — no I/O.