crosspoint-reader/lib/Epub/Epub/parsers/ContentOpfParser.h
Dave Allie b6bc1f7ed3
New book.bin spine and table of contents cache (#104)
## Summary

* Use single unified cache file for book spine, table of contents, and
core metadata (title, author, cover image)
* Use new temp item store file in OPF parsing to store items to be
rescaned when parsing spine
  * This avoids us holding these items in memory
* Use new toc.bin.tmp and spine.bin.tmp to build out partial toc / spine
data as part of parsing content.opf and the NCX file
  * These files are re-read multiple times to ultimately build book.bin

## Additional Context

* Spec for file format included below as an image
* This should help with:
  * #10 
  * #60 
  * #99
2025-12-24 22:36:13 +11:00

47 lines
1.2 KiB
C++

#pragma once
#include <Print.h>
#include "Epub.h"
#include "expat.h"
class BookMetadataCache;
class ContentOpfParser final : public Print {
enum ParserState {
START,
IN_PACKAGE,
IN_METADATA,
IN_BOOK_TITLE,
IN_MANIFEST,
IN_SPINE,
};
const std::string& cachePath;
const std::string& baseContentPath;
size_t remainingSize;
XML_Parser parser = nullptr;
ParserState state = START;
BookMetadataCache* cache;
File tempItemStore;
std::string coverItemId;
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:
std::string title;
std::string tocNcxPath;
std::string coverItemHref;
explicit ContentOpfParser(const std::string& cachePath, const std::string& baseContentPath, const size_t xmlSize,
BookMetadataCache* cache)
: cachePath(cachePath), baseContentPath(baseContentPath), remainingSize(xmlSize), cache(cache) {}
~ContentOpfParser() override;
bool setup();
size_t write(uint8_t) override;
size_t write(const uint8_t* buffer, size_t size) override;
};