bookhoard/web/src/reader/parsers/txt-parser.ts

// TXT Parser - Wraps plain text in HTML structure
// Procedural style: Functions, not classes

// ============================================================
// Main Parse Function
// ============================================================

export async function parseTXT(txtBlob: Blob): Promise<EbookCIF> {
  const textContent = await txtBlob.text();

  const metadata = extractTXTMetadata(txtBlob);
  const toc = createTXTTOC(textContent);
  const spine = createTXTSpine(textContent);
  const resources = new Map(); // No external resources for plain text

  const totalCharacters = textContent.length;

  return {
    metadata,
    toc,
    spine,
    resources,
    locations: {
      totalCharacters,
      estimatedPages: Math.ceil(totalCharacters / 1500),
    },
  };
}

// ============================================================
// Helper Functions
// ============================================================

function extractTXTMetadata(txtBlob: Blob): EbookCIF["metadata"] {
  const filename = txtBlob.name || "Unknown";

  return {
    title: filename.replace(/\.(txt|text)$/i, ""),
    author: "Unknown",
    language: "en",
  };
}

function createTXTTOC(textContent: string): EbookCIF["toc"] {
  // Try to detect chapters (simple heuristic)
  const toc: EbookCIF["toc"] = [];
  const lines = textContent.split("\n");

  let chapterIndex = 0;

  lines.forEach((line, index) => {
    // Common chapter patterns
    const chapterPattern = /^(chapter|part|section)\s+\d+/i;
    if (chapterPattern.test(line.trim())) {
      toc.push({
        id: `chapter-${chapterIndex}`,
        title: line.trim(),
        href: `#chapter-${chapterIndex}`,
        children: [],
      });

      chapterIndex++;
    }
  });

  // If no chapters found, create single entry
  if (toc.length === 0) {
    toc.push({
      id: "full-text",
      title: "Full Text",
      href: "#full-text",
      children: [],
    });
  }

  return toc;
}

function createTXTSpine(textContent: string): EbookCIF["spine"] {
  // Convert plain text to HTML paragraphs
  const lines = textContent.split("\n");
  let htmlContent = '<div class="txt-content">';

  lines.forEach((line) => {
    const trimmed = line.trim();
    if (trimmed) {
      htmlContent += `<p>${escapeHTML(trimmed)}</p>`;
    } else {
      htmlContent += "<br />";
    }
  });

  htmlContent += "</div>";

  return [
    {
      id: "full-text",
      type: "html",
      content: htmlContent,
      index: 0,
    },
  ];
}

function escapeHTML(text: string): string {
  const div = document.createElement("div");
  div.textContent = text;
  return div.innerHTML;
}

// Removed - backend handles detailed position tracking

// ============================================================
// Metadata Quick Extract
// ============================================================

export async function getTXTMetadata(
  txtBlob: Blob,
): Promise<Partial<EbookCIF["metadata"]>> {
  return extractTXTMetadata(txtBlob);
}