06ced8f2d1
Three optimizations for EPUBs with many chapters (e.g. 2768 chapters): 1. OPF idref→href lookup: Build sorted hash index during manifest parsing, use binary search during spine resolution. Reduces ~4min to ~30-60s. 2. TOC href→spineIndex lookup: Build sorted hash index in beginTocPass(), use binary search in createTocEntry(). Reduces ~4min to ~30-60s. 3. ZIP central-dir cursor: Resume scanning from last position instead of restarting from beginning. Reduces ~8min to ~1-3min. All optimizations only activate for large EPUBs (≥400 spine items). Small books use unchanged code paths. Memory impact: ~33KB + ~39KB temporary during indexing, freed after. Expected total: ~17min → ~3-5min for Shadow Slave (2768 chapters). Also adds phase timing logs for performance measurement.
113 lines
3.2 KiB
C++
113 lines
3.2 KiB
C++
#pragma once
|
|
|
|
#include <SDCardManager.h>
|
|
|
|
#include <algorithm>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
class BookMetadataCache {
|
|
public:
|
|
struct BookMetadata {
|
|
std::string title;
|
|
std::string author;
|
|
std::string language;
|
|
std::string coverItemHref;
|
|
std::string textReferenceHref;
|
|
};
|
|
|
|
struct SpineEntry {
|
|
std::string href;
|
|
size_t cumulativeSize;
|
|
int16_t tocIndex;
|
|
|
|
SpineEntry() : cumulativeSize(0), tocIndex(-1) {}
|
|
SpineEntry(std::string href, const size_t cumulativeSize, const int16_t tocIndex)
|
|
: href(std::move(href)), cumulativeSize(cumulativeSize), tocIndex(tocIndex) {}
|
|
};
|
|
|
|
struct TocEntry {
|
|
std::string title;
|
|
std::string href;
|
|
std::string anchor;
|
|
uint8_t level;
|
|
int16_t spineIndex;
|
|
|
|
TocEntry() : level(0), spineIndex(-1) {}
|
|
TocEntry(std::string title, std::string href, std::string anchor, const uint8_t level, const int16_t spineIndex)
|
|
: title(std::move(title)),
|
|
href(std::move(href)),
|
|
anchor(std::move(anchor)),
|
|
level(level),
|
|
spineIndex(spineIndex) {}
|
|
};
|
|
|
|
private:
|
|
std::string cachePath;
|
|
size_t lutOffset;
|
|
uint16_t spineCount;
|
|
uint16_t tocCount;
|
|
bool loaded;
|
|
bool buildMode;
|
|
|
|
FsFile bookFile;
|
|
// Temp file handles during build
|
|
FsFile spineFile;
|
|
FsFile tocFile;
|
|
|
|
// Index for fast href→spineIndex lookup (used only for large EPUBs)
|
|
struct SpineHrefIndexEntry {
|
|
uint64_t hrefHash; // FNV-1a 64-bit hash
|
|
uint16_t hrefLen; // length for collision reduction
|
|
int16_t spineIndex;
|
|
};
|
|
std::vector<SpineHrefIndexEntry> spineHrefIndex;
|
|
bool useSpineHrefIndex = false;
|
|
|
|
static constexpr uint16_t LARGE_SPINE_THRESHOLD = 400;
|
|
|
|
// FNV-1a 64-bit hash function
|
|
static uint64_t fnvHash64(const std::string& s) {
|
|
uint64_t hash = 14695981039346656037ull;
|
|
for (char c : s) {
|
|
hash ^= static_cast<uint8_t>(c);
|
|
hash *= 1099511628211ull;
|
|
}
|
|
return hash;
|
|
}
|
|
|
|
uint32_t writeSpineEntry(FsFile& file, const SpineEntry& entry) const;
|
|
uint32_t writeTocEntry(FsFile& file, const TocEntry& entry) const;
|
|
SpineEntry readSpineEntry(FsFile& file) const;
|
|
TocEntry readTocEntry(FsFile& file) const;
|
|
|
|
public:
|
|
BookMetadata coreMetadata;
|
|
|
|
explicit BookMetadataCache(std::string cachePath)
|
|
: cachePath(std::move(cachePath)), lutOffset(0), spineCount(0), tocCount(0), loaded(false), buildMode(false) {}
|
|
~BookMetadataCache() = default;
|
|
|
|
// Building phase (stream to disk immediately)
|
|
bool beginWrite();
|
|
bool beginContentOpfPass();
|
|
void createSpineEntry(const std::string& href);
|
|
bool endContentOpfPass();
|
|
bool beginTocPass();
|
|
void createTocEntry(const std::string& title, const std::string& href, const std::string& anchor, uint8_t level);
|
|
bool endTocPass();
|
|
bool endWrite();
|
|
bool cleanupTmpFiles() const;
|
|
|
|
// Post-processing to update mappings and sizes
|
|
bool buildBookBin(const std::string& epubPath, const BookMetadata& metadata);
|
|
|
|
// Reading phase (read mode)
|
|
bool load();
|
|
SpineEntry getSpineEntry(int index);
|
|
TocEntry getTocEntry(int index);
|
|
int getSpineCount() const { return spineCount; }
|
|
int getTocCount() const { return tocCount; }
|
|
bool isLoaded() const { return loaded; }
|
|
};
|