Merge branch 'master' into fork/itsthisjustin/feature/koreader-sync

This commit is contained in:
Dave Allie
2026-01-19 22:50:59 +11:00
48 changed files with 2792 additions and 202 deletions

View File

@@ -409,6 +409,70 @@ bool Epub::generateCoverBmp(bool cropped) const {
return false;
}
std::string Epub::getThumbBmpPath() const { return cachePath + "/thumb.bmp"; }
bool Epub::generateThumbBmp() const {
// Already generated, return true
if (SdMan.exists(getThumbBmpPath().c_str())) {
return true;
}
if (!bookMetadataCache || !bookMetadataCache->isLoaded()) {
Serial.printf("[%lu] [EBP] Cannot generate thumb BMP, cache not loaded\n", millis());
return false;
}
const auto coverImageHref = bookMetadataCache->coreMetadata.coverItemHref;
if (coverImageHref.empty()) {
Serial.printf("[%lu] [EBP] No known cover image for thumbnail\n", millis());
return false;
}
if (coverImageHref.substr(coverImageHref.length() - 4) == ".jpg" ||
coverImageHref.substr(coverImageHref.length() - 5) == ".jpeg") {
Serial.printf("[%lu] [EBP] Generating thumb BMP from JPG cover image\n", millis());
const auto coverJpgTempPath = getCachePath() + "/.cover.jpg";
FsFile coverJpg;
if (!SdMan.openFileForWrite("EBP", coverJpgTempPath, coverJpg)) {
return false;
}
readItemContentsToStream(coverImageHref, coverJpg, 1024);
coverJpg.close();
if (!SdMan.openFileForRead("EBP", coverJpgTempPath, coverJpg)) {
return false;
}
FsFile thumbBmp;
if (!SdMan.openFileForWrite("EBP", getThumbBmpPath(), thumbBmp)) {
coverJpg.close();
return false;
}
// Use smaller target size for Continue Reading card (half of screen: 240x400)
// Generate 1-bit BMP for fast home screen rendering (no gray passes needed)
constexpr int THUMB_TARGET_WIDTH = 240;
constexpr int THUMB_TARGET_HEIGHT = 400;
const bool success = JpegToBmpConverter::jpegFileTo1BitBmpStreamWithSize(coverJpg, thumbBmp, THUMB_TARGET_WIDTH,
THUMB_TARGET_HEIGHT);
coverJpg.close();
thumbBmp.close();
SdMan.remove(coverJpgTempPath.c_str());
if (!success) {
Serial.printf("[%lu] [EBP] Failed to generate thumb BMP from JPG cover image\n", millis());
SdMan.remove(getThumbBmpPath().c_str());
}
Serial.printf("[%lu] [EBP] Generated thumb BMP from JPG cover image, success: %s\n", millis(),
success ? "yes" : "no");
return success;
} else {
Serial.printf("[%lu] [EBP] Cover image is not a JPG, skipping thumbnail\n", millis());
}
return false;
}
uint8_t* Epub::readItemContentsToBytes(const std::string& itemHref, size_t* size, const bool trailingNullByte) const {
if (itemHref.empty()) {
Serial.printf("[%lu] [EBP] Failed to read item, empty href\n", millis());

View File

@@ -46,6 +46,8 @@ class Epub {
const std::string& getAuthor() const;
std::string getCoverBmpPath(bool cropped = false) const;
bool generateCoverBmp(bool cropped = false) const;
std::string getThumbBmpPath() const;
bool generateThumbBmp() 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;

View File

@@ -43,7 +43,7 @@ std::vector<uint16_t> ParsedText::calculateWordWidths(const GfxRenderer& rendere
wordWidths.reserve(totalWordCount);
// add em-space at the beginning of first word in paragraph to indent
if (!extraParagraphSpacing) {
if ((style == TextBlock::JUSTIFIED || style == TextBlock::LEFT_ALIGN) && !extraParagraphSpacing) {
std::string& first_word = words.front();
first_word.insert(0, "\xe2\x80\x83");
}

View File

@@ -25,7 +25,7 @@ constexpr int NUM_ITALIC_TAGS = sizeof(ITALIC_TAGS) / sizeof(ITALIC_TAGS[0]);
const char* IMAGE_TAGS[] = {"img"};
constexpr int NUM_IMAGE_TAGS = sizeof(IMAGE_TAGS) / sizeof(IMAGE_TAGS[0]);
const char* SKIP_TAGS[] = {"head", "table"};
const char* SKIP_TAGS[] = {"head"};
constexpr int NUM_SKIP_TAGS = sizeof(SKIP_TAGS) / sizeof(SKIP_TAGS[0]);
bool isWhitespace(const char c) { return c == ' ' || c == '\r' || c == '\n' || c == '\t'; }
@@ -63,13 +63,44 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
return;
}
if (matches(name, IMAGE_TAGS, NUM_IMAGE_TAGS)) {
// TODO: Start processing image tags
// Special handling for tables - show placeholder text instead of dropping silently
if (strcmp(name, "table") == 0) {
// Add placeholder text
self->startNewTextBlock(TextBlock::CENTER_ALIGN);
if (self->currentTextBlock) {
self->currentTextBlock->addWord("[Table omitted]", EpdFontFamily::ITALIC);
}
// Skip table contents
self->skipUntilDepth = self->depth;
self->depth += 1;
return;
}
if (matches(name, IMAGE_TAGS, NUM_IMAGE_TAGS)) {
// TODO: Start processing image tags
std::string alt;
if (atts != nullptr) {
for (int i = 0; atts[i]; i += 2) {
if (strcmp(atts[i], "alt") == 0) {
alt = "[Image: " + std::string(atts[i + 1]) + "]";
}
}
Serial.printf("[%lu] [EHP] Image alt: %s\n", millis(), alt.c_str());
self->startNewTextBlock(TextBlock::CENTER_ALIGN);
self->italicUntilDepth = min(self->italicUntilDepth, self->depth);
self->depth += 1;
self->characterData(userData, alt.c_str(), alt.length());
} else {
// Skip for now
self->skipUntilDepth = self->depth;
self->depth += 1;
return;
}
}
if (matches(name, SKIP_TAGS, NUM_SKIP_TAGS)) {
// start skip
self->skipUntilDepth = self->depth;
@@ -97,6 +128,9 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
self->startNewTextBlock(self->currentTextBlock->getStyle());
} else {
self->startNewTextBlock((TextBlock::Style)self->paragraphAlignment);
if (strcmp(name, "li") == 0) {
self->currentTextBlock->addWord("\xe2\x80\xa2", EpdFontFamily::REGULAR);
}
}
} else if (matches(name, BOLD_TAGS, NUM_BOLD_TAGS)) {
self->boldUntilDepth = std::min(self->boldUntilDepth, self->depth);
@@ -151,6 +185,20 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
}
}
// Skip Zero Width No-Break Space / BOM (U+FEFF) = 0xEF 0xBB 0xBF
const XML_Char FEFF_BYTE_1 = static_cast<XML_Char>(0xEF);
const XML_Char FEFF_BYTE_2 = static_cast<XML_Char>(0xBB);
const XML_Char FEFF_BYTE_3 = static_cast<XML_Char>(0xBF);
if (s[i] == FEFF_BYTE_1) {
// Check if the next two bytes complete the 3-byte sequence
if ((i + 2 < len) && (s[i + 1] == FEFF_BYTE_2) && (s[i + 2] == FEFF_BYTE_3)) {
// Sequence 0xEF 0xBB 0xBF found!
i += 2; // Skip the next two bytes
continue; // Move to the next iteration
}
}
// If we're about to run out of space, then cut the word off and start a new one
if (self->partWordBufferIndex >= MAX_WORD_SIZE) {
self->partWordBuffer[self->partWordBufferIndex] = '\0';