cottongin/crosspoint-reader
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 4 Wiki Activity

Merge branch 'daveallie:master' into feature/show-img-alt-text

Browse Source
This commit is contained in:
Jonas Diemer
2025-12-30 14:18:31 +01:00
committed by GitHub
parent c960e32d05 6a8971fc20
commit 61b2622206
16 changed files with 391 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
lib/Epub/Epub.cpp
View File

@@ -74,6 +74,7 @@ bool Epub::parseContentOpf(BookMetadataCache::BookMetadata& bookMetadata) {
bookMetadata.title = opfParser.title;
bookMetadata.author = opfParser.author;
bookMetadata.coverItemHref = opfParser.coverItemHref;
bookMetadata.textReferenceHref = opfParser.textReferenceHref;
if (!opfParser.tocNcxPath.empty()) {
tocNcxItem = opfParser.tocNcxPath;
@@ -108,17 +109,20 @@ bool Epub::parseTocNcxFile() const {
if (!ncxParser.setup()) {
Serial.printf("[%lu] [EBP] Could not setup toc ncx parser\n", millis());
tempNcxFile.close();
return false;
}
const auto ncxBuffer = static_cast<uint8_t*>(malloc(1024));
if (!ncxBuffer) {
Serial.printf("[%lu] [EBP] Could not allocate memory for toc ncx parser\n", millis());
tempNcxFile.close();
return false;
}
while (tempNcxFile.available()) {
const auto readSize = tempNcxFile.read(ncxBuffer, 1024);
if (readSize == 0) break;
const auto processedSize = ncxParser.write(ncxBuffer, readSize);
if (processedSize != readSize) {
@@ -138,7 +142,7 @@ bool Epub::parseTocNcxFile() const {
}
// load in the meta data for the epub file
bool Epub::load() {
bool Epub::load(const bool buildIfMissing) {
Serial.printf("[%lu] [EBP] Loading ePub: %s\n", millis(), filepath.c_str());
// Initialize spine/TOC cache
@@ -150,6 +154,11 @@ bool Epub::load() {
return true;
}
// If we didn't load from cache above and we aren't allowed to build, fail now
if (!buildIfMissing) {
return false;
}
// Cache doesn't exist or is invalid, build it
Serial.printf("[%lu] [EBP] Cache not found, building spine/TOC cache\n", millis());
setupCacheDir();
@@ -426,6 +435,35 @@ size_t Epub::getBookSize() const {
return getCumulativeSpineItemSize(getSpineItemsCount() - 1);
}
int Epub::getSpineIndexForTextReference() const {
if (!bookMetadataCache || !bookMetadataCache->isLoaded()) {
Serial.printf("[%lu] [EBP] getSpineIndexForTextReference called but cache not loaded\n", millis());
return 0;
}
Serial.printf("[%lu] [ERS] Core Metadata: cover(%d)=%s, textReference(%d)=%s\n", millis(),
bookMetadataCache->coreMetadata.coverItemHref.size(),
bookMetadataCache->coreMetadata.coverItemHref.c_str(),
bookMetadataCache->coreMetadata.textReferenceHref.size(),
bookMetadataCache->coreMetadata.textReferenceHref.c_str());
if (bookMetadataCache->coreMetadata.textReferenceHref.empty()) {
// there was no textReference in epub, so we return 0 (the first chapter)
return 0;
}
// loop through spine items to get the correct index matching the text href
for (size_t i = 0; i < getSpineItemsCount(); i++) {
if (getSpineItem(i).href == bookMetadataCache->coreMetadata.textReferenceHref) {
Serial.printf("[%lu] [ERS] Text reference %s found at index %d\n", millis(),
bookMetadataCache->coreMetadata.textReferenceHref.c_str(), i);
return i;
}
}
// This should not happen, as we checked for empty textReferenceHref earlier
Serial.printf("[%lu] [EBP] Section not found for text reference\n", millis());
return 0;
}
// Calculate progress in book
uint8_t Epub::calculateProgress(const int currentSpineIndex, const float currentSpineRead) const {
const size_t bookSize = getBookSize();

3
lib/Epub/Epub.h
View File

@@ -34,7 +34,7 @@ class Epub {
}
~Epub() = default;
std::string& getBasePath() { return contentBasePath; }
bool load();
bool load(bool buildIfMissing = true);
bool clearCache() const;
void setupCacheDir() const;
const std::string& getCachePath() const;
@@ -54,6 +54,7 @@ class Epub {
int getSpineIndexForTocIndex(int tocIndex) const;
int getTocIndexForSpineIndex(int spineIndex) const;
size_t getCumulativeSpineItemSize(int spineIndex) const;
int getSpineIndexForTextReference() const;
size_t getBookSize() const;
uint8_t calculateProgress(int currentSpineIndex, float currentSpineRead) const;

8
lib/Epub/Epub/BookMetadataCache.cpp
View File

@@ -9,7 +9,7 @@
#include "FsHelpers.h"
namespace {
constexpr uint8_t BOOK_CACHE_VERSION = 2;
constexpr uint8_t BOOK_CACHE_VERSION = 3;
constexpr char bookBinFile[] = "/book.bin";
constexpr char tmpSpineBinFile[] = "/spine.bin.tmp";
constexpr char tmpTocBinFile[] = "/toc.bin.tmp";
@@ -87,8 +87,8 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
constexpr uint32_t headerASize =
sizeof(BOOK_CACHE_VERSION) + /* LUT Offset */ sizeof(uint32_t) + sizeof(spineCount) + sizeof(tocCount);
const uint32_t metadataSize =
metadata.title.size() + metadata.author.size() + metadata.coverItemHref.size() + sizeof(uint32_t) * 3;
const uint32_t metadataSize = metadata.title.size() + metadata.author.size() + metadata.coverItemHref.size() +
metadata.textReferenceHref.size() + sizeof(uint32_t) * 4;
const uint32_t lutSize = sizeof(uint32_t) * spineCount + sizeof(uint32_t) * tocCount;
const uint32_t lutOffset = headerASize + metadataSize;
@@ -101,6 +101,7 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
serialization::writeString(bookFile, metadata.title);
serialization::writeString(bookFile, metadata.author);
serialization::writeString(bookFile, metadata.coverItemHref);
serialization::writeString(bookFile, metadata.textReferenceHref);
// Loop through spine entries, writing LUT positions
spineFile.seek(0);
@@ -289,6 +290,7 @@ bool BookMetadataCache::load() {
serialization::readString(bookFile, coreMetadata.title);
serialization::readString(bookFile, coreMetadata.author);
serialization::readString(bookFile, coreMetadata.coverItemHref);
serialization::readString(bookFile, coreMetadata.textReferenceHref);
loaded = true;
Serial.printf("[%lu] [BMC] Loaded cache data: %d spine, %d TOC entries\n", millis(), spineCount, tocCount);

1
lib/Epub/Epub/BookMetadataCache.h
View File

@@ -10,6 +10,7 @@ class BookMetadataCache {
std::string title;
std::string author;
std::string coverItemHref;
std::string textReferenceHref;
};
struct SpineEntry {

12
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
View File

@@ -57,7 +57,6 @@ void ChapterHtmlSlimParser::startNewTextBlock(const TextBlock::BLOCK_STYLE style
void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char* name, const XML_Char** atts) {
auto* self = static_cast<ChapterHtmlSlimParser*>(userData);
(void)atts;
// Middle of skip
if (self->skipUntilDepth < self->depth) {
@@ -111,7 +110,7 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
if (matches(name, HEADER_TAGS, NUM_HEADER_TAGS)) {
self->startNewTextBlock(TextBlock::CENTER_ALIGN);
self->boldUntilDepth = min(self->boldUntilDepth, self->depth);
self->boldUntilDepth = std::min(self->boldUntilDepth, self->depth);
} else if (matches(name, BLOCK_TAGS, NUM_BLOCK_TAGS)) {
if (strcmp(name, "br") == 0) {
self->startNewTextBlock(self->currentTextBlock->getStyle());
@@ -119,9 +118,9 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
self->startNewTextBlock(TextBlock::JUSTIFIED);
}
} else if (matches(name, BOLD_TAGS, NUM_BOLD_TAGS)) {
self->boldUntilDepth = min(self->boldUntilDepth, self->depth);
self->boldUntilDepth = std::min(self->boldUntilDepth, self->depth);
} else if (matches(name, ITALIC_TAGS, NUM_ITALIC_TAGS)) {
self->italicUntilDepth = min(self->italicUntilDepth, self->depth);
self->italicUntilDepth = std::min(self->italicUntilDepth, self->depth);
}
self->depth += 1;
@@ -180,7 +179,6 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* name) {
auto* self = static_cast<ChapterHtmlSlimParser*>(userData);
(void)name;
if (self->partWordBufferIndex > 0) {
// Only flush out part word buffer if we're closing a block tag or are at the top of the HTML file.
@@ -263,9 +261,9 @@ bool ChapterHtmlSlimParser::parseAndBuildPages() {
return false;
}
const size_t len = file.read(static_cast<uint8_t*>(buf), 1024);
const size_t len = file.read(buf, 1024);
if (len == 0) {
if (len == 0 && file.available() > 0) {
Serial.printf("[%lu] [EHP] File read error\n", millis());
XML_StopParser(parser, XML_FALSE); // Stop any pending processing
XML_SetElementHandler(parser, nullptr, nullptr); // Clear callbacks

41
lib/Epub/Epub/parsers/ContentOpfParser.cpp
View File

@@ -127,6 +127,18 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
return;
}
if (self->state == IN_PACKAGE && (strcmp(name, "guide") == 0 || strcmp(name, "opf:guide") == 0)) {
self->state = IN_GUIDE;
// TODO Remove print
Serial.printf("[%lu] [COF] Entering guide state.\n", millis());
if (!SdMan.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;
}
if (self->state == IN_METADATA && (strcmp(name, "meta") == 0 || strcmp(name, "opf:meta") == 0)) {
bool isCover = false;
std::string coverItemId;
@@ -205,6 +217,29 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
return;
}
}
// parse the guide
if (self->state == IN_GUIDE && (strcmp(name, "reference") == 0 || strcmp(name, "opf:reference") == 0)) {
std::string type;
std::string textHref;
for (int i = 0; atts[i]; i += 2) {
if (strcmp(atts[i], "type") == 0) {
type = atts[i + 1];
if (type == "text" || type == "start") {
continue;
} else {
Serial.printf("[%lu] [COF] Skipping non-text reference in guide: %s\n", millis(), type.c_str());
break;
}
} else if (strcmp(atts[i], "href") == 0) {
textHref = self->baseContentPath + atts[i + 1];
}
}
if ((type == "text" || (type == "start" && !self->textReferenceHref.empty())) && (textHref.length() > 0)) {
Serial.printf("[%lu] [COF] Found %s reference in guide: %s.\n", millis(), type.c_str(), textHref.c_str());
self->textReferenceHref = textHref;
}
return;
}
}
void XMLCALL ContentOpfParser::characterData(void* userData, const XML_Char* s, const int len) {
@@ -231,6 +266,12 @@ void XMLCALL ContentOpfParser::endElement(void* userData, const XML_Char* name)
return;
}
if (self->state == IN_GUIDE && (strcmp(name, "guide") == 0 || strcmp(name, "opf:guide") == 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();

2
lib/Epub/Epub/parsers/ContentOpfParser.h
View File

@@ -15,6 +15,7 @@ class ContentOpfParser final : public Print {
IN_BOOK_AUTHOR,
IN_MANIFEST,
IN_SPINE,
IN_GUIDE,
};
const std::string& cachePath;
@@ -35,6 +36,7 @@ class ContentOpfParser final : public Print {
std::string author;
std::string tocNcxPath;
std::string coverItemHref;
std::string textReferenceHref;
explicit ContentOpfParser(const std::string& cachePath, const std::string& baseContentPath, const size_t xmlSize,
BookMetadataCache* cache)