Justin Mitchell
02398c8a96
Adds residentBytes() and cssRuleCount() methods to track EPUB memory usage including parsed CSS. Enhances memory audit logging with EPUB heap usage, max allocatable block size, and CSS rule count. Implements one-shot heap block map dump on first settled audit to identify fragmentation and long-lived allocations.
89 lines
3.5 KiB
C++
89 lines
3.5 KiB
C++
#pragma once
|
|
|
|
#include <Print.h>
|
|
|
|
#include <memory>
|
|
#include <string>
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
|
|
#include "Epub/BookMetadataCache.h"
|
|
#include "Epub/css/CssParser.h"
|
|
|
|
class ZipFile;
|
|
|
|
class Epub {
|
|
// the ncx file (EPUB 2)
|
|
std::string tocNcxItem;
|
|
// the nav file (EPUB 3)
|
|
std::string tocNavItem;
|
|
// where is the EPUBfile?
|
|
std::string filepath;
|
|
// the base path for items in the EPUB file
|
|
std::string contentBasePath;
|
|
// Uniq cache key based on filepath
|
|
std::string cachePath;
|
|
// Spine and TOC cache
|
|
std::unique_ptr<BookMetadataCache> bookMetadataCache;
|
|
// CSS parser for styling
|
|
std::unique_ptr<CssParser> cssParser;
|
|
// CSS files
|
|
std::vector<std::string> cssFiles;
|
|
|
|
bool findContentOpfFile(std::string* contentOpfFile) const;
|
|
bool parseContentOpf(BookMetadataCache::BookMetadata& bookMetadata, bool writeSpineEntries = true);
|
|
bool parseTocNcxFile() const;
|
|
bool parseTocNavFile() const;
|
|
void discoverCssFilesFromZip();
|
|
void parseCssFiles() const;
|
|
|
|
public:
|
|
explicit Epub(std::string filepath, const std::string& cacheDir) : filepath(std::move(filepath)) {
|
|
// create a cache key based on the filepath
|
|
cachePath = cacheDir + "/epub_" + std::to_string(std::hash<std::string>{}(this->filepath));
|
|
}
|
|
~Epub() = default;
|
|
std::string& getBasePath() { return contentBasePath; }
|
|
// Approximate resident heap of the open book (audit): path strings, the CSS
|
|
// file list, and the parsed stylesheet. BookMetadataCache is file-backed
|
|
// (counts + HalFile handles) and contributes little.
|
|
size_t residentBytes() const {
|
|
size_t total = sizeof(Epub) + tocNcxItem.capacity() + tocNavItem.capacity() + filepath.capacity() +
|
|
contentBasePath.capacity() + cachePath.capacity();
|
|
for (const auto& f : cssFiles) total += sizeof(f) + (f.capacity() > 15 ? f.capacity() : 0);
|
|
if (cssParser) total += cssParser->residentBytes();
|
|
return total;
|
|
}
|
|
size_t cssRuleCount() const { return cssParser ? cssParser->ruleCount() : 0; }
|
|
bool load(bool buildIfMissing = true, bool skipLoadingCss = false);
|
|
bool clearCache() const;
|
|
void setupCacheDir() const;
|
|
const std::string& getCachePath() const;
|
|
const std::string& getPath() const;
|
|
const std::string& getTitle() const;
|
|
const std::string& getAuthor() const;
|
|
const std::string& getLanguage() const;
|
|
std::string getCoverBmpPath(bool cropped = false) const;
|
|
bool generateCoverBmp(bool cropped = false) const;
|
|
std::string getThumbBmpPath() const;
|
|
std::string getThumbBmpPath(int height) const;
|
|
bool generateThumbBmp(int height) const;
|
|
uint8_t* readItemContentsToBytes(const std::string& itemHref, size_t* size = nullptr,
|
|
bool trailingNullByte = false) const;
|
|
bool readItemContentsToStream(const std::string& itemHref, Print& out, size_t chunkSize) const;
|
|
bool getItemSize(const std::string& itemHref, size_t* size) const;
|
|
BookMetadataCache::SpineEntry getSpineItem(int spineIndex) const;
|
|
BookMetadataCache::TocEntry getTocItem(int tocIndex) const;
|
|
int getSpineItemsCount() const;
|
|
int getTocItemsCount() const;
|
|
int getSpineIndexForTocIndex(int tocIndex) const;
|
|
int getTocIndexForSpineIndex(int spineIndex) const;
|
|
size_t getCumulativeSpineItemSize(int spineIndex) const;
|
|
int getSpineIndexForTextReference() const;
|
|
|
|
size_t getBookSize() const;
|
|
float calculateProgress(int currentSpineIndex, float currentSpineRead) const;
|
|
CssParser* getCssParser() const { return cssParser.get(); }
|
|
int resolveHrefToSpineIndex(const std::string& href) const;
|
|
};
|