Implement client-side ebook parsers for EPUB, FB2, TXT, and HTML formats

- epub-parser.ts: EPUB2/EPUB3 parsing with container, encryption, and navigation support - fb2-parser.ts: FictionBook 2.0/XML parser with metadata and TOC extraction - txt-parser.ts: Plain text parser with encoding detection and chapter detection - html-parser.ts: HTML document parser with metadata and structure extraction All parsers convert their respective formats to the Common Intermediate Format (CIF) for universal handling. Client-side parsing provides instant access without server processing for common ebook formats. Phase 1 focuses on these client-side parsers. Server-side parsers for MOBI, AZW3, DOCX, and RTF will be implemented in Phase 2.5.
2026-04-03 22:29:33 -04:00
parent 1e47b0e459
commit d8bb5ff68a
4 changed files with 830 additions and 0 deletions
@@ -0,0 +1,121 @@
+// 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 extractTXTMetadata(
+  txtBlob: Blob,
+): Promise<Partial<EbookCIF["metadata"]>> {
+  return extractTXTMetadata(txtBlob);
+}