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
This commit is contained in:
Dave Allie
2025-12-24 22:36:13 +11:00
committed by GitHub
parent b1657d39d5
commit 7ae3584857
15 changed files with 748 additions and 169 deletions
+52 -8
View File
@@ -1,11 +1,16 @@
#include "ContentOpfParser.h"
#include <FsHelpers.h>
#include <HardwareSerial.h>
#include <Serialization.h>
#include <ZipFile.h>
#include "../BookMetadataCache.h"
namespace {
constexpr char MEDIA_TYPE_NCX[] = "application/x-dtbncx+xml";
}
constexpr char itemCacheFile[] = "/.items.bin";
} // namespace
bool ContentOpfParser::setup() {
parser = XML_ParserCreate(nullptr);
@@ -28,6 +33,12 @@ ContentOpfParser::~ContentOpfParser() {
XML_ParserFree(parser);
parser = nullptr;
}
if (tempItemStore) {
tempItemStore.close();
}
if (SD.exists((cachePath + itemCacheFile).c_str())) {
SD.remove((cachePath + itemCacheFile).c_str());
}
}
size_t ContentOpfParser::write(const uint8_t data) { return write(&data, 1); }
@@ -94,11 +105,21 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
if (self->state == IN_PACKAGE && (strcmp(name, "manifest") == 0 || strcmp(name, "opf:manifest") == 0)) {
self->state = IN_MANIFEST;
if (!FsHelpers::openFileForWrite("COF", self->cachePath + itemCacheFile, self->tempItemStore)) {
Serial.printf(
"[%lu] [COF] Couldn't open temp items file for writing. This is probably going to be a fatal error.\n",
millis());
}
return;
}
if (self->state == IN_PACKAGE && (strcmp(name, "spine") == 0 || strcmp(name, "opf:spine") == 0)) {
self->state = IN_SPINE;
if (!FsHelpers::openFileForRead("COF", self->cachePath + itemCacheFile, self->tempItemStore)) {
Serial.printf(
"[%lu] [COF] Couldn't open temp items file for reading. This is probably going to be a fatal error.\n",
millis());
}
return;
}
@@ -135,7 +156,13 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
}
}
self->items[itemId] = href;
// Write items down to SD card
serialization::writeString(self->tempItemStore, itemId);
serialization::writeString(self->tempItemStore, href);
if (itemId == self->coverItemId) {
self->coverItemHref = href;
}
if (mediaType == MEDIA_TYPE_NCX) {
if (self->tocNcxPath.empty()) {
@@ -148,14 +175,29 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
return;
}
if (self->state == IN_SPINE && (strcmp(name, "itemref") == 0 || strcmp(name, "opf:itemref") == 0)) {
for (int i = 0; atts[i]; i += 2) {
if (strcmp(atts[i], "idref") == 0) {
self->spineRefs.emplace_back(atts[i + 1]);
break;
// NOTE: This relies on spine appearing after item manifest (which is pretty safe as it's part of the EPUB spec)
// Only run the spine parsing if there's a cache to add it to
if (self->cache) {
if (self->state == IN_SPINE && (strcmp(name, "itemref") == 0 || strcmp(name, "opf:itemref") == 0)) {
for (int i = 0; atts[i]; i += 2) {
if (strcmp(atts[i], "idref") == 0) {
const std::string idref = atts[i + 1];
// Resolve the idref to href using items map
self->tempItemStore.seek(0);
std::string itemId;
std::string href;
while (self->tempItemStore.available()) {
serialization::readString(self->tempItemStore, itemId);
serialization::readString(self->tempItemStore, href);
if (itemId == idref) {
self->cache->createSpineEntry(href);
break;
}
}
}
}
return;
}
return;
}
}
@@ -174,11 +216,13 @@ void XMLCALL ContentOpfParser::endElement(void* userData, const XML_Char* name)
if (self->state == IN_SPINE && (strcmp(name, "spine") == 0 || strcmp(name, "opf:spine") == 0)) {
self->state = IN_PACKAGE;
self->tempItemStore.close();
return;
}
if (self->state == IN_MANIFEST && (strcmp(name, "manifest") == 0 || strcmp(name, "opf:manifest") == 0)) {
self->state = IN_PACKAGE;
self->tempItemStore.close();
return;
}