Add EPUB 3 nav.xhtml TOC support (#197)

## Summary * **What is the goal of this PR?** Add EPUB 3 support by implementing native navigation document (nav.xhtml) parsing with NCX fallback, addressing issue Fixes: #143. * **What changes are included?** - New `TocNavParser` for parsing EPUB 3 HTML5 navigation documents (`<nav epub:type="toc">`) - Detection of nav documents via `properties="nav"` attribute in OPF manifest - Fallback logic: try EPUB 3 nav first, fall back to NCX (EPUB 2) if unavailable - Graceful degradation: books without any TOC now load with a warning instead of failing ## Additional Context * The implementation follows the existing streaming XML parser pattern using Expat to minimize RAM usage on the ESP32-C3 * EPUB 3 books that include both nav.xhtml and toc.ncx will prefer the nav document (per EPUB 3 spec recommendation) * No breaking changes - existing EPUB 2 books continue to work as before * Tested on examples from https://idpf.github.io/epub3-samples/30/samples.html
2026-01-03 19:10:35 +11:00
parent 5790d6f5dc
commit 0332e1103a
7 changed files with 328 additions and 6 deletions
@@ -0,0 +1,47 @@
+#pragma once
+#include <Print.h>
+#include <expat.h>
+
+#include <string>
+
+class BookMetadataCache;
+
+// Parser for EPUB 3 nav.xhtml navigation documents
+// Parses HTML5 nav elements with epub:type="toc" to extract table of contents
+class TocNavParser final : public Print {
+  enum ParserState {
+    START,
+    IN_HTML,
+    IN_BODY,
+    IN_NAV_TOC,  // Inside <nav epub:type="toc">
+    IN_OL,       // Inside <ol>
+    IN_LI,       // Inside <li>
+    IN_ANCHOR,   // Inside <a>
+  };
+
+  const std::string& baseContentPath;
+  size_t remainingSize;
+  XML_Parser parser = nullptr;
+  ParserState state = START;
+  BookMetadataCache* cache;
+
+  // Track nesting depth for <ol> elements to determine TOC depth
+  uint8_t olDepth = 0;
+  // Current entry data being collected
+  std::string currentLabel;
+  std::string currentHref;
+
+  static void startElement(void* userData, const XML_Char* name, const XML_Char** atts);
+  static void characterData(void* userData, const XML_Char* s, int len);
+  static void endElement(void* userData, const XML_Char* name);
+
+ public:
+  explicit TocNavParser(const std::string& baseContentPath, const size_t xmlSize, BookMetadataCache* cache)
+      : baseContentPath(baseContentPath), remainingSize(xmlSize), cache(cache) {}
+  ~TocNavParser() override;
+
+  bool setup();
+
+  size_t write(uint8_t) override;
+  size_t write(const uint8_t* buffer, size_t size) override;
+};