Merge remote-tracking branch 'origin/develop' into feat-bluetooth

lib/Epub/Epub.cpp

@@ -153,18 +153,11 @@ bool Epub::parseTocNcxFile() const {
 
   LOG_DBG("EBP", "Parsing toc ncx file: %s", tocNcxItem.c_str());
 
-  const auto tmpNcxPath = getCachePath() + "/toc.ncx";
-  HalFile tempNcxFile;
-  if (!Storage.openFileForWrite("EBP", tmpNcxPath, tempNcxFile)) {
+  size_t ncxSize;
+  if (!getItemSize(tocNcxItem, &ncxSize)) {
+    LOG_ERR("EBP", "Could not get size of toc ncx file");
     return false;
   }
-  readItemContentsToStream(tocNcxItem, tempNcxFile, 1024);
-  // Explicitly close() file before reopening for reading
-  tempNcxFile.close();
-  if (!Storage.openFileForRead("EBP", tmpNcxPath, tempNcxFile)) {
-    return false;
-  }
-  const auto ncxSize = tempNcxFile.size();
 
   TocNcxParser ncxParser(contentBasePath, ncxSize, bookMetadataCache.get());
 
@@ -173,29 +166,13 @@ bool Epub::parseTocNcxFile() const {
     return false;
   }
 
-  const auto ncxBuffer = static_cast<uint8_t*>(malloc(1024));
-  if (!ncxBuffer) {
-    LOG_ERR("EBP", "Could not allocate memory for toc ncx parser");
+  // Stream the decompressed NCX straight into the parser instead of round-tripping
+  // through a temp file on the SD card (decompress -> write -> reopen -> reread -> delete).
+  if (!readItemContentsToStream(tocNcxItem, ncxParser, 1024)) {
+    LOG_ERR("EBP", "Could not read toc ncx file");
     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) {
-      LOG_ERR("EBP", "Could not process all toc ncx data");
-      free(ncxBuffer);
-      return false;
-    }
-  }
-
-  free(ncxBuffer);
-  // Explicitly close() file before calling Storage.remove()
-  tempNcxFile.close();
-  Storage.remove(tmpNcxPath.c_str());
-
   LOG_DBG("EBP", "Parsed TOC items");
   return true;
 }
@@ -209,18 +186,11 @@ bool Epub::parseTocNavFile() const {
 
   LOG_DBG("EBP", "Parsing toc nav file: %s", tocNavItem.c_str());
 
-  const auto tmpNavPath = getCachePath() + "/toc.nav";
-  HalFile tempNavFile;
-  if (!Storage.openFileForWrite("EBP", tmpNavPath, tempNavFile)) {
+  size_t navSize;
+  if (!getItemSize(tocNavItem, &navSize)) {
+    LOG_ERR("EBP", "Could not get size of toc nav file");
     return false;
   }
-  readItemContentsToStream(tocNavItem, tempNavFile, 1024);
-  // Explicitly close() file before reopening for reading
-  tempNavFile.close();
-  if (!Storage.openFileForRead("EBP", tmpNavPath, tempNavFile)) {
-    return false;
-  }
-  const auto navSize = tempNavFile.size();
 
   // Note: We can't use `contentBasePath` here as the nav file may be in a different folder to the content.opf
   // and the HTMLX nav file will have hrefs relative to itself
@@ -232,28 +202,13 @@ bool Epub::parseTocNavFile() const {
     return false;
   }
 
-  const auto navBuffer = static_cast<uint8_t*>(malloc(1024));
-  if (!navBuffer) {
-    LOG_ERR("EBP", "Could not allocate memory for toc nav parser");
+  // Stream the decompressed nav document straight into the parser instead of round-tripping
+  // through a temp file on the SD card (decompress -> write -> reopen -> reread -> delete).
+  if (!readItemContentsToStream(tocNavItem, navParser, 1024)) {
+    LOG_ERR("EBP", "Could not read toc nav file");
     return false;
   }
 
-  while (tempNavFile.available()) {
-    const auto readSize = tempNavFile.read(navBuffer, 1024);
-    const auto processedSize = navParser.write(navBuffer, readSize);
-
-    if (processedSize != readSize) {
-      LOG_ERR("EBP", "Could not process all toc nav data");
-      free(navBuffer);
-      return false;
-    }
-  }
-
-  free(navBuffer);
-  // Explicitly close() file before calling Storage.remove()
-  tempNavFile.close();
-  Storage.remove(tmpNavPath.c_str());
-
   LOG_DBG("EBP", "Parsed TOC nav items");
   return true;
 }
@@ -396,6 +351,11 @@ bool Epub::load(const bool buildIfMissing, const bool skipLoadingCss) {
         Storage.removeDir((cachePath + "/sections").c_str());
       }
     }
+    // Release the resolved CSS rule map: it is only needed transiently while building
+    // section caches, and createSectionFile reloads it from cache on demand. Holding it
+    // resident pins tens of KB for the whole reading session (more on warm resume into
+    // an already-cached chapter, where createSectionFile never runs to clear it).
+    cssParser->clear();
     LOG_DBG("EBP", "Loaded ePub: %s", filepath.c_str());
     return true;
   }

lib/Epub/Epub/BookMetadataCache.cpp

@@ -1,5 +1,6 @@
 #include "BookMetadataCache.h"
 
+#include <BufferedFile.h>
 #include <Logging.h>
 #include <Serialization.h>
 #include <Utf8.h>
@@ -14,6 +15,52 @@ constexpr uint8_t BOOK_CACHE_VERSION = 8;  // v8: TOC/book titles stored NFC-com
 constexpr char bookBinFile[] = "/book.bin";
 constexpr char tmpSpineBinFile[] = "/spine.bin.tmp";
 constexpr char tmpTocBinFile[] = "/toc.bin.tmp";
+// Buffer size for the buildBookBin streams. 3 buffers x 4KB, transient (freed on
+// return); 4KB = 8 SD sectors per transfer, enough to stop the sector-cache thrash.
+constexpr size_t BUILD_IO_BUFFER_SIZE = 4096;
+
+// Entry (de)serializers, templated so they run over HalFile and the Buffered*
+// wrappers alike (two instantiations each -- a few hundred bytes of flash, in
+// exchange for the build path streaming at SD speed instead of per-pod).
+template <typename F>
+uint32_t writeSpineEntryTo(F& file, const BookMetadataCache::SpineEntry& entry) {
+  const uint32_t pos = file.position();
+  serialization::writeString(file, entry.href);
+  serialization::writePod(file, entry.cumulativeSize);
+  serialization::writePod(file, entry.tocIndex);
+  return pos;
+}
+
+template <typename F>
+uint32_t writeTocEntryTo(F& file, const BookMetadataCache::TocEntry& entry) {
+  const uint32_t pos = file.position();
+  serialization::writeString(file, entry.title);
+  serialization::writeString(file, entry.href);
+  serialization::writeString(file, entry.anchor);
+  serialization::writePod(file, entry.level);
+  serialization::writePod(file, entry.spineIndex);
+  return pos;
+}
+
+template <typename F>
+BookMetadataCache::SpineEntry readSpineEntryFrom(F& file) {
+  BookMetadataCache::SpineEntry entry;
+  serialization::readString(file, entry.href);
+  serialization::readPod(file, entry.cumulativeSize);
+  serialization::readPod(file, entry.tocIndex);
+  return entry;
+}
+
+template <typename F>
+BookMetadataCache::TocEntry readTocEntryFrom(F& file) {
+  BookMetadataCache::TocEntry entry;
+  serialization::readString(file, entry.title);
+  serialization::readString(file, entry.href);
+  serialization::readString(file, entry.anchor);
+  serialization::readPod(file, entry.level);
+  serialization::readPod(file, entry.spineIndex);
+  return entry;
+}
 }  // namespace
 
 /* ============= WRITING / BUILDING FUNCTIONS ================ */
@@ -30,13 +77,23 @@ bool BookMetadataCache::beginContentOpfPass() {
   LOG_DBG("BMC", "Beginning content opf pass");
 
   // Open spine file for writing
-  return Storage.openFileForWrite("BMC", cachePath + tmpSpineBinFile, spineFile);
+  if (!Storage.openFileForWrite("BMC", cachePath + tmpSpineBinFile, spineFile)) {
+    return false;
+  }
+  // Wrapper OOM is fine: createSpineEntry falls back to unbuffered writes.
+  passOut = makeUniqueNoThrow<serialization::BufferedFileWriter>(spineFile, BUILD_IO_BUFFER_SIZE);
+  return true;
 }
 
 bool BookMetadataCache::endContentOpfPass() {
+  const bool flushed = !passOut || passOut->flush();
+  passOut.reset();
   // Explicit close() required: member variable persists beyond function scope
   spineFile.close();
-  return true;
+  if (!flushed) {
+    LOG_ERR("BMC", "Failed writing spine tmp file");
+  }
+  return flushed;
 }
 
 bool BookMetadataCache::beginTocPass() {
@@ -74,10 +131,17 @@ bool BookMetadataCache::beginTocPass() {
     useSpineHrefIndex = false;
   }
 
+  // Wrapper OOM is fine: createTocEntry falls back to unbuffered writes.
+  passOut = makeUniqueNoThrow<serialization::BufferedFileWriter>(tocFile, BUILD_IO_BUFFER_SIZE);
   return true;
 }
 
 bool BookMetadataCache::endTocPass() {
+  const bool flushed = !passOut || passOut->flush();
+  passOut.reset();
+  if (!flushed) {
+    LOG_ERR("BMC", "Failed writing toc tmp file");
+  }
   // Explicit close() required: member variables persist beyond function scope
   tocFile.close();
   spineFile.close();
@@ -86,7 +150,7 @@ bool BookMetadataCache::endTocPass() {
   spineHrefIndex.shrink_to_fit();
   useSpineHrefIndex = false;
 
-  return true;
+  return flushed;
 }
 
 bool BookMetadataCache::endWrite() {
@@ -119,6 +183,14 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
     return false;
   }
 
+  // Buffered streams for the whole build: every access below is sequential per
+  // file, but interleaved ACROSS files, which thrashes SdFat's single shared
+  // sector cache when unbuffered (one 512B SD transaction per 4-byte pod --
+  // measured 31s for a 1,732-spine omnibus). Three 4KB buffers, freed on return.
+  serialization::BufferedFileWriter bookOut(bookFile, BUILD_IO_BUFFER_SIZE);
+  serialization::BufferedFileReader spineIn(spineFile, BUILD_IO_BUFFER_SIZE);
+  serialization::BufferedFileReader tocIn(tocFile, BUILD_IO_BUFFER_SIZE);
+
   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.language.size() +
@@ -128,31 +200,34 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
   const uint32_t lutOffset = headerASize + metadataSize;
 
   // Header A
-  serialization::writePod(bookFile, BOOK_CACHE_VERSION);
-  serialization::writePod(bookFile, lutOffset);
-  serialization::writePod(bookFile, spineCount);
-  serialization::writePod(bookFile, tocCount);
+  serialization::writePod(bookOut, BOOK_CACHE_VERSION);
+  serialization::writePod(bookOut, lutOffset);
+  serialization::writePod(bookOut, spineCount);
+  serialization::writePod(bookOut, tocCount);
   // Metadata
-  serialization::writeString(bookFile, metadata.title);
-  serialization::writeString(bookFile, metadata.author);
-  serialization::writeString(bookFile, metadata.language);
-  serialization::writeString(bookFile, metadata.coverItemHref);
-  serialization::writeString(bookFile, metadata.textReferenceHref);
+  serialization::writeString(bookOut, metadata.title);
+  serialization::writeString(bookOut, metadata.author);
+  serialization::writeString(bookOut, metadata.language);
+  serialization::writeString(bookOut, metadata.coverItemHref);
+  serialization::writeString(bookOut, metadata.textReferenceHref);
 
   // Loop through spine entries, writing LUT positions
-  spineFile.seek(0);
+  spineIn.seek(0);
   for (int i = 0; i < spineCount; i++) {
-    uint32_t pos = spineFile.position();
-    auto spineEntry = readSpineEntry(spineFile);
-    serialization::writePod(bookFile, pos + lutOffset + lutSize);
+    const uint32_t pos = spineIn.position();
+    readSpineEntryFrom(spineIn);
+    serialization::writePod(bookOut, pos + lutOffset + lutSize);
   }
+  // Total size of the spine tmp file: entries land in book.bin after the toc LUT
+  // and the full spine block, so toc LUT positions are offset by it.
+  const auto spineBytes = static_cast<uint32_t>(spineIn.position());
 
   // Loop through toc entries, writing LUT positions
-  tocFile.seek(0);
+  tocIn.seek(0);
   for (int i = 0; i < tocCount; i++) {
-    uint32_t pos = tocFile.position();
-    auto tocEntry = readTocEntry(tocFile);
-    serialization::writePod(bookFile, pos + lutOffset + lutSize + static_cast<uint32_t>(spineFile.position()));
+    const uint32_t pos = tocIn.position();
+    readTocEntryFrom(tocIn);
+    serialization::writePod(bookOut, pos + lutOffset + lutSize + spineBytes);
   }
 
   // LUTs complete
@@ -160,9 +235,9 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
 
   // Build spineIndex->tocIndex mapping in one pass (O(n) instead of O(n*m))
   std::deque<int16_t> spineToTocIndex(spineCount, -1);
-  tocFile.seek(0);
+  tocIn.seek(0);
   for (int j = 0; j < tocCount; j++) {
-    auto tocEntry = readTocEntry(tocFile);
+    auto tocEntry = readTocEntryFrom(tocIn);
     if (tocEntry.spineIndex >= 0 && tocEntry.spineIndex < spineCount) {
       if (spineToTocIndex[tocEntry.spineIndex] == -1) {
         spineToTocIndex[tocEntry.spineIndex] = static_cast<int16_t>(j);
@@ -197,9 +272,9 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
     std::deque<ZipFile::SizeTarget> targets;
     targets.resize(spineCount);
 
-    spineFile.seek(0);
+    spineIn.seek(0);
     for (int i = 0; i < spineCount; i++) {
-      auto entry = readSpineEntry(spineFile);
+      auto entry = readSpineEntryFrom(spineIn);
       std::string path = FsHelpers::normalisePath(entry.href);
 
       ZipFile::SizeTarget t;
@@ -224,10 +299,10 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
   }
 
   uint32_t cumSize = 0;
-  spineFile.seek(0);
+  spineIn.seek(0);
   int lastSpineTocIndex = -1;
   for (int i = 0; i < spineCount; i++) {
-    auto spineEntry = readSpineEntry(spineFile);
+    auto spineEntry = readSpineEntryFrom(spineIn);
 
     spineEntry.tocIndex = spineToTocIndex[i];
 
@@ -260,23 +335,33 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
     spineEntry.cumulativeSize = cumSize;
 
     // Write out spine data to book.bin
-    writeSpineEntry(bookFile, spineEntry);
+    writeSpineEntryTo(bookOut, spineEntry);
   }
   // Close opened zip file
   zip.close();
 
   // Loop through toc entries from toc file writing to book.bin
-  tocFile.seek(0);
+  tocIn.seek(0);
   for (int i = 0; i < tocCount; i++) {
-    auto tocEntry = readTocEntry(tocFile);
-    writeTocEntry(bookFile, tocEntry);
+    auto tocEntry = readTocEntryFrom(tocIn);
+    writeTocEntryTo(bookOut, tocEntry);
   }
 
+  const bool written = bookOut.flush();
+
   // Explicit close() required: member variables persist beyond function scope
   bookFile.close();
   spineFile.close();
   tocFile.close();
 
+  if (!written) {
+    // A short write (card full/removed) would leave a truncated book.bin that
+    // still passes the version check on load; remove it so the next open rebuilds.
+    LOG_ERR("BMC", "Failed writing book.bin, removing truncated file");
+    Storage.remove((cachePath + bookBinFile).c_str());
+    return false;
+  }
+
   LOG_DBG("BMC", "Successfully built book.bin");
   return true;
 }
@@ -294,21 +379,11 @@ bool BookMetadataCache::cleanupTmpFiles() const {
 }
 
 uint32_t BookMetadataCache::writeSpineEntry(HalFile& file, const SpineEntry& entry) const {
-  const uint32_t pos = file.position();
-  serialization::writeString(file, entry.href);
-  serialization::writePod(file, entry.cumulativeSize);
-  serialization::writePod(file, entry.tocIndex);
-  return pos;
+  return writeSpineEntryTo(file, entry);
 }
 
 uint32_t BookMetadataCache::writeTocEntry(HalFile& file, const TocEntry& entry) const {
-  const uint32_t pos = file.position();
-  serialization::writeString(file, entry.title);
-  serialization::writeString(file, entry.href);
-  serialization::writeString(file, entry.anchor);
-  serialization::writePod(file, entry.level);
-  serialization::writePod(file, entry.spineIndex);
-  return pos;
+  return writeTocEntryTo(file, entry);
 }
 
 // Note: for the LUT to be accurate, this **MUST** be called for all spine items before `addTocEntry` is ever called
@@ -320,7 +395,11 @@ void BookMetadataCache::createSpineEntry(const std::string& href) {
   }
 
   const SpineEntry entry(href, 0, -1);
-  writeSpineEntry(spineFile, entry);
+  if (passOut) {
+    writeSpineEntryTo(*passOut, entry);
+  } else {
+    writeSpineEntry(spineFile, entry);
+  }
   spineCount++;
 }
 
@@ -368,7 +447,11 @@ void BookMetadataCache::createTocEntry(const std::string& title, const std::stri
   // Compose the title to NFC at index time so the cache stores precomposed glyphs;
   // device fonts have no combining-mark positioning, so NFD titles render broken.
   const TocEntry entry(utf8ComposeNfc(title), href, anchor, level, spineIndex);
-  writeTocEntry(tocFile, entry);
+  if (passOut) {
+    writeTocEntryTo(*passOut, entry);
+  } else {
+    writeTocEntry(tocFile, entry);
+  }
   tocCount++;
 }
 
@@ -442,19 +525,7 @@ BookMetadataCache::TocEntry BookMetadataCache::getTocEntry(const int index) {
 }
 
 BookMetadataCache::SpineEntry BookMetadataCache::readSpineEntry(HalFile& file) const {
-  SpineEntry entry;
-  serialization::readString(file, entry.href);
-  serialization::readPod(file, entry.cumulativeSize);
-  serialization::readPod(file, entry.tocIndex);
-  return entry;
+  return readSpineEntryFrom(file);
 }
 
-BookMetadataCache::TocEntry BookMetadataCache::readTocEntry(HalFile& file) const {
-  TocEntry entry;
-  serialization::readString(file, entry.title);
-  serialization::readString(file, entry.href);
-  serialization::readString(file, entry.anchor);
-  serialization::readPod(file, entry.level);
-  serialization::readPod(file, entry.spineIndex);
-  return entry;
-}
+BookMetadataCache::TocEntry BookMetadataCache::readTocEntry(HalFile& file) const { return readTocEntryFrom(file); }

lib/Epub/Epub/BookMetadataCache.h

@@ -1,9 +1,11 @@
 #pragma once
 
+#include <BufferedFile.h>
 #include <HalStorage.h>
 
 #include <algorithm>
 #include <deque>
+#include <memory>
 #include <string>
 
 class BookMetadataCache {
@@ -54,6 +56,11 @@ class BookMetadataCache {
   // Temp file handles during build
   HalFile spineFile;
   HalFile tocFile;
+  // Buffers the per-entry tmp-file writes during the OPF/TOC passes: those
+  // writes interleave with zip-inflate SD reads, and unbuffered they thrash
+  // SdFat's shared sector cache (one 512B transaction per 4-byte pod). One
+  // wrapper serves whichever pass is active (spine, then toc).
+  std::unique_ptr<serialization::BufferedFileWriter> passOut;
 
   // Index for fast href→spineIndex lookup (used only for large EPUBs)
   struct SpineHrefIndexEntry {

lib/Epub/Epub/Page.cpp

@@ -57,6 +57,10 @@ void PageImage::render(GfxRenderer& renderer, const int fontId, const int xOffse
   imageBlock->render(renderer, xPos + xOffset, yPos + yOffset);
 }
 
+void PageImage::renderPlaceholder(GfxRenderer& renderer, const int xOffset, const int yOffset) const {
+  imageBlock->renderPlaceholder(renderer, xPos + xOffset, yPos + yOffset);
+}
+
 bool PageImage::serialize(HalFile& file) {
   serialization::writePod(file, xPos);
   serialization::writePod(file, yPos);
@@ -125,6 +129,17 @@ void Page::renderImages(GfxRenderer& renderer, const int fontId, const int xOffs
                              [](const PageElement& element) { return element.getTag() == TAG_PageImage; });
 }
 
+void Page::renderWithImagePlaceholders(GfxRenderer& renderer, const int fontId, const int xOffset,
+                                       const int yOffset) const {
+  for (const auto& element : elements) {
+    if (element->getTag() == TAG_PageImage) {
+      static_cast<const PageImage&>(*element).renderPlaceholder(renderer, xOffset, yOffset);
+    } else {
+      element->render(renderer, fontId, xOffset, yOffset);
+    }
+  }
+}
+
 bool Page::serialize(HalFile& file) const {
   const uint16_t count = elements.size();
   serialization::writePod(file, count);

lib/Epub/Epub/Page.h

@@ -50,6 +50,7 @@ class PageImage final : public PageElement {
   PageImage(std::shared_ptr<ImageBlock> block, const int16_t xPos, const int16_t yPos)
       : PageElement(xPos, yPos), imageBlock(std::move(block)) {}
   void render(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) override;
+  void renderPlaceholder(GfxRenderer& renderer, int xOffset, int yOffset) const;
   bool serialize(HalFile& file) override;
   PageElementTag getTag() const override { return TAG_PageImage; }
   static std::unique_ptr<PageImage> deserialize(HalFile& file);
@@ -89,6 +90,7 @@ class Page {
 
   void render(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) const;
   void renderImages(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) const;
+  void renderWithImagePlaceholders(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) const;
   bool serialize(HalFile& file) const;
   static std::unique_ptr<Page> deserialize(HalFile& file);
 
@@ -98,6 +100,13 @@ class Page {
                        [](const std::shared_ptr<PageElement>& el) { return el->getTag() == TAG_PageImage; });
   }
 
+  bool hasImagesNeedingDecode() const {
+    return std::any_of(elements.begin(), elements.end(), [](const std::shared_ptr<PageElement>& element) {
+      return element->getTag() == TAG_PageImage &&
+             static_cast<const PageImage&>(*element).getImageBlock().needsDecode();
+    });
+  }
+
   // Get bounding box of all images on the page (union of image rects)
   // Returns false if no images. Coordinates are relative to page origin.
   bool getImageBoundingBox(int16_t& outX, int16_t& outY, int16_t& outW, int16_t& outH) const {

lib/Epub/Epub/Section.cpp

@@ -11,9 +11,13 @@
 #include "parsers/ChapterHtmlSlimParser.h"
 
 namespace {
+// v28: text decoration bits now include line-through in serialized wordStyles.
 // v29: TextBlock word data stored as one flat arena (offset table + NUL-terminated
 // text blob) instead of length-prefixed strings and per-field arrays.
-constexpr uint8_t SECTION_FILE_VERSION = 29;
+// v30: Arabic shaping changed both drawing and measurement (getTextAdvanceX now
+//      measures the shaped visual text); cached word positions from v29 no longer
+//      match what drawText renders.
+constexpr uint8_t SECTION_FILE_VERSION = 30;
 // Written into the version field while a build is in progress; patched to
 // SECTION_FILE_VERSION only when the build is finalized. An abandoned /
 // crash-interrupted .bin therefore carries version 0, which loadSectionFile rejects

lib/Epub/Epub/blocks/ImageBlock.cpp

@@ -5,6 +5,8 @@
 #include <Logging.h>
 #include <Serialization.h>
 
+#include <cstdlib>
+
 #include "Epub/converters/DirectPixelWriter.h"
 #include "Epub/converters/ImageDecoderFactory.h"
 
@@ -29,6 +31,54 @@ std::string getCachePath(const std::string& imagePath) {
   return imagePath + ".pxc";
 }
 
+bool readValidCacheHeader(HalFile& cacheFile, const int expectedWidth, const int expectedHeight, uint16_t& cachedWidth,
+                          uint16_t& cachedHeight) {
+  if (cacheFile.read(&cachedWidth, 2) != 2 || cacheFile.read(&cachedHeight, 2) != 2) {
+    return false;
+  }
+
+  const int widthDiff = abs(cachedWidth - expectedWidth);
+  const int heightDiff = abs(cachedHeight - expectedHeight);
+  if (widthDiff > 1 || heightDiff > 1) {
+    return false;
+  }
+
+  const size_t bytesPerRow = (cachedWidth + 3) / 4;
+  const size_t expectedSize = 4 + bytesPerRow * cachedHeight;
+  return cacheFile.size() >= expectedSize;
+}
+
+// Pages are deserialized afresh on each visit. Keep a bounded, allocation-free
+// record so an image that failed renders its placeholder directly for the rest
+// of the reader session instead of paying another placeholder refresh and
+// decode. The reader clears this on entry so transient memory/storage failures
+// are retried.
+constexpr size_t MAX_SESSION_IMAGE_FAILURES = 16;
+uint64_t failedImageHashes[MAX_SESSION_IMAGE_FAILURES];
+size_t failedImageCount = 0;
+
+uint64_t imagePathHash(const std::string& path) {
+  uint64_t hash = 14695981039346656037ull;
+  for (const char c : path) {
+    hash ^= static_cast<uint8_t>(c);
+    hash *= 1099511628211ull;
+  }
+  return hash;
+}
+
+bool imageFailedThisSession(const std::string& path) {
+  const uint64_t hash = imagePathHash(path);
+  for (size_t i = 0; i < failedImageCount; i++) {
+    if (failedImageHashes[i] == hash) return true;
+  }
+  return false;
+}
+
+void rememberImageFailure(const std::string& path) {
+  if (failedImageCount == MAX_SESSION_IMAGE_FAILURES || imageFailedThisSession(path)) return;
+  failedImageHashes[failedImageCount++] = imagePathHash(path);
+}
+
 bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x, int y, int expectedWidth,
                      int expectedHeight) {
   HalFile cacheFile;
@@ -37,16 +87,8 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
   }
 
   uint16_t cachedWidth, cachedHeight;
-  if (cacheFile.read(&cachedWidth, 2) != 2 || cacheFile.read(&cachedHeight, 2) != 2) {
-    return false;
-  }
-
-  // Verify dimensions are close (allow 1 pixel tolerance for rounding differences)
-  int widthDiff = abs(cachedWidth - expectedWidth);
-  int heightDiff = abs(cachedHeight - expectedHeight);
-  if (widthDiff > 1 || heightDiff > 1) {
-    LOG_ERR("IMG", "Cache dimension mismatch: %dx%d vs %dx%d", cachedWidth, cachedHeight, expectedWidth,
-            expectedHeight);
+  if (!readValidCacheHeader(cacheFile, expectedWidth, expectedHeight, cachedWidth, cachedHeight)) {
+    LOG_ERR("IMG", "Invalid image cache: %s", cachePath.c_str());
     return false;
   }
 
@@ -119,6 +161,28 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
 
 }  // namespace
 
+bool ImageBlock::hasValidCache() const {
+  const auto cachePath = getCachePath(imagePath);
+  HalFile cacheFile;
+  if (!Storage.openFileForRead("IMG", cachePath, cacheFile)) {
+    return false;
+  }
+
+  uint16_t cachedWidth, cachedHeight;
+  return readValidCacheHeader(cacheFile, width, height, cachedWidth, cachedHeight);
+}
+
+bool ImageBlock::needsDecode() const { return !imageFailedThisSession(imagePath) && !hasValidCache(); }
+
+void ImageBlock::clearSessionRenderFailures() { failedImageCount = 0; }
+
+void ImageBlock::renderPlaceholder(GfxRenderer& renderer, const int x, const int y) const {
+  renderer.fillRect(x, y, width, height, true);
+  if (width > 2 && height > 2) {
+    renderer.fillRect(x + 1, y + 1, width - 2, height - 2, false);
+  }
+}
+
 void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
   // The font-prewarm scan pass only accumulates glyphs; an image contributes
   // none, and its DirectPixelWriter output bypasses the renderer's scan-mode
@@ -150,6 +214,11 @@ void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
     return;
   }
 
+  if (imageFailedThisSession(imagePath)) {
+    renderPlaceholder(renderer, x, y);
+    return;
+  }
+
   // Try to render from cache first
   std::string cachePath = getCachePath(imagePath);
   if (renderFromCache(renderer, cachePath, x, y, width, height)) {
@@ -161,6 +230,8 @@ void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
   HalFile file;
   if (!Storage.openFileForRead("IMG", imagePath, file)) {
     LOG_ERR("IMG", "Image file not found: %s", imagePath.c_str());
+    rememberImageFailure(imagePath);
+    renderPlaceholder(renderer, x, y);
     return;
   }
   size_t fileSize = file.size();
@@ -168,6 +239,8 @@ void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
 
   if (fileSize == 0) {
     LOG_ERR("IMG", "Image file is empty: %s", imagePath.c_str());
+    rememberImageFailure(imagePath);
+    renderPlaceholder(renderer, x, y);
     return;
   }
 
@@ -187,6 +260,8 @@ void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
   ImageToFramebufferDecoder* decoder = ImageDecoderFactory::getDecoder(imagePath);
   if (!decoder) {
     LOG_ERR("IMG", "No decoder found for image: %s", imagePath.c_str());
+    rememberImageFailure(imagePath);
+    renderPlaceholder(renderer, x, y);
     return;
   }
 
@@ -195,6 +270,8 @@ void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
   bool success = decoder->decodeToFramebuffer(imagePath, renderer, config);
   if (!success) {
     LOG_ERR("IMG", "Failed to decode image: %s", imagePath.c_str());
+    rememberImageFailure(imagePath);
+    renderPlaceholder(renderer, x, y);
     return;
   }
 

lib/Epub/Epub/blocks/ImageBlock.h

@@ -16,6 +16,10 @@ class ImageBlock final : public Block {
   int16_t getHeight() const { return height; }
 
   bool imageExists() const;
+  bool hasValidCache() const;
+  bool needsDecode() const;
+  void renderPlaceholder(GfxRenderer& renderer, int x, int y) const;
+  static void clearSessionRenderFailures();
 
   BlockType getType() override { return IMAGE_BLOCK; }
   bool isEmpty() override { return false; }

lib/Epub/Epub/converters/PngToFramebufferConverter.cpp

@@ -99,24 +99,58 @@ int bytesPerPixelFromType(int pixelType) {
   }
 }
 
-int requiredPngInternalBufferBytes(int srcWidth, int pixelType) {
+int packedRowBytes(int srcWidth, int bitsPerSample) { return (srcWidth * bitsPerSample + 7) / 8; }
+
+int requiredPngInternalBufferBytes(int srcWidth, int pixelType, int bitsPerSample) {
   // +1 filter byte per scanline, *2 for current+previous lines, +32 for alignment margin.
   int pitch = srcWidth * bytesPerPixelFromType(pixelType);
+  if ((pixelType == PNG_PIXEL_GRAYSCALE || pixelType == PNG_PIXEL_INDEXED) && bitsPerSample < 8) {
+    pitch = packedRowBytes(srcWidth, bitsPerSample);
+  }
   return ((pitch + 1) * 2) + 32;
 }
 
+bool isSupportedBitDepth(int pixelType, int bitsPerSample) {
+  if (bitsPerSample == 8) return true;
+  if (bitsPerSample != 1 && bitsPerSample != 2 && bitsPerSample != 4) return false;
+  return pixelType == PNG_PIXEL_GRAYSCALE || pixelType == PNG_PIXEL_INDEXED;
+}
+
+uint8_t readPackedSample(const uint8_t* pixels, int x, int bitsPerSample) {
+  if (bitsPerSample == 8) return pixels[x];
+
+  const int bitOffset = x * bitsPerSample;
+  const int shift = 8 - bitsPerSample - (bitOffset & 7);
+  const uint8_t mask = (1U << bitsPerSample) - 1;
+  return (pixels[bitOffset >> 3] >> shift) & mask;
+}
+
+uint8_t expandSampleToByte(uint8_t sample, int bitsPerSample) {
+  if (bitsPerSample == 8) return sample;
+  const uint8_t maxSample = (1U << bitsPerSample) - 1;
+  return static_cast<uint8_t>((sample * 255U) / maxSample);
+}
+
 // Convert entire source line to grayscale with alpha blending to white background.
+// Low-bit-depth grayscale/indexed scanlines are packed most-significant sample first.
 // For indexed PNGs with tRNS chunk, alpha values are stored at palette[768] onwards.
 // Processing the whole line at once improves cache locality and reduces per-pixel overhead.
-void convertLineToGray(uint8_t* pPixels, uint8_t* grayLine, int width, int pixelType, uint8_t* palette, int hasAlpha) {
+void convertLineToGray(const uint8_t* pPixels, uint8_t* grayLine, int width, int pixelType, int bitsPerSample,
+                       uint8_t* palette, int hasAlpha) {
   switch (pixelType) {
     case PNG_PIXEL_GRAYSCALE:
-      memcpy(grayLine, pPixels, width);
+      if (bitsPerSample == 8) {
+        memcpy(grayLine, pPixels, width);
+      } else {
+        for (int x = 0; x < width; x++) {
+          grayLine[x] = expandSampleToByte(readPackedSample(pPixels, x, bitsPerSample), bitsPerSample);
+        }
+      }
       break;
 
     case PNG_PIXEL_TRUECOLOR:
       for (int x = 0; x < width; x++) {
-        uint8_t* p = &pPixels[x * 3];
+        const uint8_t* p = &pPixels[x * 3];
         grayLine[x] = (uint8_t)((p[0] * 77 + p[1] * 150 + p[2] * 29) >> 8);
       }
       break;
@@ -125,7 +159,7 @@ void convertLineToGray(uint8_t* pPixels, uint8_t* grayLine, int width, int pixel
       if (palette) {
         if (hasAlpha) {
           for (int x = 0; x < width; x++) {
-            uint8_t idx = pPixels[x];
+            uint8_t idx = readPackedSample(pPixels, x, bitsPerSample);
             uint8_t* p = &palette[idx * 3];
             uint8_t gray = (uint8_t)((p[0] * 77 + p[1] * 150 + p[2] * 29) >> 8);
             uint8_t alpha = palette[768 + idx];
@@ -133,12 +167,15 @@ void convertLineToGray(uint8_t* pPixels, uint8_t* grayLine, int width, int pixel
           }
         } else {
           for (int x = 0; x < width; x++) {
-            uint8_t* p = &palette[pPixels[x] * 3];
+            uint8_t idx = readPackedSample(pPixels, x, bitsPerSample);
+            uint8_t* p = &palette[idx * 3];
             grayLine[x] = (uint8_t)((p[0] * 77 + p[1] * 150 + p[2] * 29) >> 8);
           }
         }
       } else {
-        memcpy(grayLine, pPixels, width);
+        for (int x = 0; x < width; x++) {
+          grayLine[x] = expandSampleToByte(readPackedSample(pPixels, x, bitsPerSample), bitsPerSample);
+        }
       }
       break;
 
@@ -152,7 +189,7 @@ void convertLineToGray(uint8_t* pPixels, uint8_t* grayLine, int width, int pixel
 
     case PNG_PIXEL_TRUECOLOR_ALPHA:
       for (int x = 0; x < width; x++) {
-        uint8_t* p = &pPixels[x * 4];
+        const uint8_t* p = &pPixels[x * 4];
         uint8_t gray = (uint8_t)((p[0] * 77 + p[1] * 150 + p[2] * 29) >> 8);
         uint8_t alpha = p[3];
         grayLine[x] = (uint8_t)((gray * alpha + 255 * (255 - alpha)) / 255);
@@ -172,74 +209,83 @@ int pngDrawCallback(PNGDRAW* pDraw) {
   int srcY = pDraw->y;
   int srcWidth = ctx->srcWidth;
 
-  // Calculate destination Y with scaling
-  int dstY = (int)(srcY * ctx->scale);
+  // Map source rows with the exact output-height ratio. During downscaling,
+  // multiple source rows can select the same output row; during upscaling, one
+  // source row must be repeated across every output row in its range. Emitting
+  // only the first row of an upscale leaves zero-filled (black) gaps in the
+  // streamed pixel cache.
+  int firstDstY = (srcY * ctx->dstHeight) / ctx->srcHeight;
+  int endDstY = firstDstY + 1;
+  if (ctx->dstHeight > ctx->srcHeight) {
+    endDstY = ((srcY + 1) * ctx->dstHeight) / ctx->srcHeight;
+  }
 
-  // Skip if we already rendered this destination row (multiple source rows map to same dest)
-  if (dstY == ctx->lastDstY) return 1;
-  ctx->lastDstY = dstY;
-
-  // Check bounds
-  if (dstY >= ctx->dstHeight) return 1;
-
-  int outY = ctx->config->y + dstY;
-  if (outY >= ctx->screenHeight) return 1;
+  if (firstDstY <= ctx->lastDstY) firstDstY = ctx->lastDstY + 1;
+  if (firstDstY >= endDstY || firstDstY >= ctx->dstHeight) return 1;
+  if (endDstY > ctx->dstHeight) endDstY = ctx->dstHeight;
 
   // Convert entire source line to grayscale (improves cache locality)
-  convertLineToGray(pDraw->pPixels, ctx->grayLineBuffer, srcWidth, pDraw->iPixelType, pDraw->pPalette,
+  convertLineToGray(pDraw->pPixels, ctx->grayLineBuffer, srcWidth, pDraw->iPixelType, pDraw->iBpp, pDraw->pPalette,
                     pDraw->iHasAlpha);
 
-  // Render scaled row using Bresenham-style integer stepping (no floating-point division)
+  // Render scaled rows using Bresenham-style integer stepping (no floating-point division)
   int dstWidth = ctx->dstWidth;
   int outXBase = ctx->config->x;
   int screenWidth = ctx->screenWidth;
   bool useDithering = ctx->config->useDithering;
-  bool caching = ctx->caching;
 
-  // Pre-compute orientation and render-mode state once per row
+  // Pre-compute orientation and render-mode state once per callback.
   DirectPixelWriter pw;
   pw.init(*ctx->renderer);
-  pw.beginRow(outY);
 
-  // The cache streams to disk one row at a time. Flushing rows below this one
-  // (PNGdec delivers scanlines top to bottom) repositions the single-row band.
-  // A flush failure stops caching for the rest of the decode so we never write
-  // past the band buffer; finalize() then drops the partial file.
-  DirectCacheWriter cw;
-  if (caching) {
-    if (!ctx->cache.advanceTo(dstY)) {
-      caching = false;
-      ctx->caching = false;
-    } else {
-      cw.init(ctx->cache.buffer, ctx->cache.bytesPerRow, ctx->cache.bandRows, ctx->cache.originX);
-      cw.beginRow(outY, ctx->config->y + ctx->cache.bandStart);
-    }
-  }
+  for (int dstY = firstDstY; dstY < endDstY; dstY++) {
+    ctx->lastDstY = dstY;
+    int outY = ctx->config->y + dstY;
+    if (outY >= ctx->screenHeight) continue;
 
-  int srcX = 0;
-  int error = 0;
+    pw.beginRow(outY);
 
-  for (int dstX = 0; dstX < dstWidth; dstX++) {
-    int outX = outXBase + dstX;
-    if (outX < screenWidth) {
-      uint8_t gray = ctx->grayLineBuffer[srcX];
-
-      uint8_t ditheredGray;
-      if (useDithering) {
-        ditheredGray = applyBayerDither4Level(gray, outX, outY);
+    // The cache streams to disk one row at a time. Flushing rows below this one
+    // (PNGdec delivers scanlines top to bottom) repositions the single-row band.
+    // A flush failure stops caching for the rest of the decode so we never write
+    // past the band buffer; finalize() then drops the partial file.
+    bool caching = ctx->caching;
+    DirectCacheWriter cw;
+    if (caching) {
+      if (!ctx->cache.advanceTo(dstY)) {
+        caching = false;
+        ctx->caching = false;
       } else {
-        ditheredGray = gray / 85;
-        if (ditheredGray > 3) ditheredGray = 3;
+        cw.init(ctx->cache.buffer, ctx->cache.bytesPerRow, ctx->cache.bandRows, ctx->cache.originX);
+        cw.beginRow(outY, ctx->config->y + ctx->cache.bandStart);
       }
-      pw.writePixel(outX, ditheredGray);
-      if (caching) cw.writePixel(outX, ditheredGray);
     }
 
-    // Bresenham-style stepping: advance srcX based on ratio srcWidth/dstWidth
-    error += srcWidth;
-    while (error >= dstWidth) {
-      error -= dstWidth;
-      srcX++;
+    int srcX = 0;
+    int error = 0;
+
+    for (int dstX = 0; dstX < dstWidth; dstX++) {
+      int outX = outXBase + dstX;
+      if (outX < screenWidth) {
+        uint8_t gray = ctx->grayLineBuffer[srcX];
+
+        uint8_t ditheredGray;
+        if (useDithering) {
+          ditheredGray = applyBayerDither4Level(gray, outX, outY);
+        } else {
+          ditheredGray = gray / 85;
+          if (ditheredGray > 3) ditheredGray = 3;
+        }
+        pw.writePixel(outX, ditheredGray);
+        if (caching) cw.writePixel(outX, ditheredGray);
+      }
+
+      // Bresenham-style stepping: advance srcX based on ratio srcWidth/dstWidth
+      error += srcWidth;
+      while (error >= dstWidth) {
+        error -= dstWidth;
+        srcX++;
+      }
     }
   }
 
@@ -332,30 +378,44 @@ bool PngToFramebufferConverter::decodeToFramebuffer(const std::string& imagePath
   }
   ctx.lastDstY = -1;  // Reset row tracking
 
-  LOG_DBG("PNG", "PNG %dx%d -> %dx%d (scale %.2f), bpp: %d", ctx.srcWidth, ctx.srcHeight, ctx.dstWidth, ctx.dstHeight,
-          ctx.scale, png->getBpp());
-
   const int pixelType = png->getPixelType();
-  const int requiredInternal = requiredPngInternalBufferBytes(ctx.srcWidth, pixelType);
+  const int bitsPerSample = png->getBpp();
+  LOG_DBG("PNG", "PNG %dx%d -> %dx%d (scale %.2f), type: %d, bpp: %d", ctx.srcWidth, ctx.srcHeight, ctx.dstWidth,
+          ctx.dstHeight, ctx.scale, pixelType, bitsPerSample);
+
+  const int requiredInternal = requiredPngInternalBufferBytes(ctx.srcWidth, pixelType, bitsPerSample);
   if (requiredInternal > PNG_MAX_BUFFERED_PIXELS) {
-    LOG_ERR("PNG",
-            "PNG row buffer too small: need %d bytes for width=%d type=%d, configured PNG_MAX_BUFFERED_PIXELS=%d",
-            requiredInternal, ctx.srcWidth, pixelType, PNG_MAX_BUFFERED_PIXELS);
+    LOG_ERR(
+        "PNG",
+        "PNG row buffer too small: need %d bytes for width=%d type=%d bpp=%d, configured PNG_MAX_BUFFERED_PIXELS=%d",
+        requiredInternal, ctx.srcWidth, pixelType, bitsPerSample, PNG_MAX_BUFFERED_PIXELS);
     LOG_ERR("PNG", "Aborting decode to avoid PNGdec internal buffer overflow");
     return false;
   }
 
-  if (png->getBpp() != 8) {
-    warnUnsupportedFeature("bit depth (" + std::to_string(png->getBpp()) + "bpp)", imagePath);
+  if (!isSupportedBitDepth(pixelType, bitsPerSample)) {
+    warnUnsupportedFeature(
+        "bit depth (" + std::to_string(bitsPerSample) + "bpp) for pixel type " + std::to_string(pixelType), imagePath);
+    return false;
   }
 
-  // Allocate grayscale line buffer on demand (~3.2 KB) - freed after decode
-  const size_t grayBufSize = PNG_MAX_BUFFERED_PIXELS / 2;
-  ctx.grayLineBuffer = static_cast<uint8_t*>(malloc(grayBufSize));
-  if (!ctx.grayLineBuffer) {
+  // The converter expands each source row to 8-bit grayscale before dithering,
+  // so this scratch buffer is sized by source pixels even when PNGdec reads a
+  // packed 1/2/4-bit row internally.
+  constexpr size_t MAX_GRAY_LINE_BUFFER_BYTES = PNG_MAX_BUFFERED_PIXELS / 2;
+  const size_t grayBufSize = static_cast<size_t>(ctx.srcWidth);
+  if (grayBufSize > MAX_GRAY_LINE_BUFFER_BYTES) {
+    LOG_ERR("PNG", "Expanded gray row too wide: need %u bytes for width=%d, max=%u", static_cast<unsigned>(grayBufSize),
+            ctx.srcWidth, static_cast<unsigned>(MAX_GRAY_LINE_BUFFER_BYTES));
+    return false;
+  }
+
+  auto grayLineBuffer = makeUniqueNoThrow<uint8_t[]>(grayBufSize);
+  if (!grayLineBuffer) {
     LOG_ERR("PNG", "Failed to allocate gray line buffer");
     return false;
   }
+  ctx.grayLineBuffer = grayLineBuffer.get();
 
   // Stream the pixel cache to disk. PNGdec delivers source scanlines top to
   // bottom and we emit at most one (downscaled) output row per callback, so the
@@ -375,7 +435,6 @@ bool PngToFramebufferConverter::decodeToFramebuffer(const std::string& imagePath
   rc = png->decode(&ctx, 0);
   unsigned long decodeTime = millis() - decodeStart;
 
-  free(ctx.grayLineBuffer);
   ctx.grayLineBuffer = nullptr;
 
   if (rc != PNG_SUCCESS) {

lib/Epub/Epub/css/CssParser.cpp

@@ -803,6 +803,9 @@ bool CssParser::loadFromCache() {
     return false;
   }
 
+  // Size the bucket array up front to avoid incremental rehashes while loading rules.
+  rulesBySelector_.reserve(ruleCount);
+
   auto hasRemainingBytes = [&file](const size_t neededBytes) -> bool {
     return static_cast<size_t>(file.available()) >= neededBytes;
   };

lib/Epub/Epub/hyphenation/Hyphenator.cpp

@@ -24,7 +24,7 @@ struct Iso639Mapping {
 };
 static constexpr Iso639Mapping kIso639Mappings[] = {{"eng", "en"}, {"fra", "fr"}, {"fre", "fr"}, {"deu", "de"},
                                                     {"ger", "de"}, {"rus", "ru"}, {"spa", "es"}, {"ita", "it"},
-                                                    {"ukr", "uk"}, {"swe", "sv"}};
+                                                    {"ukr", "uk"}, {"swe", "sv"}, {"fin", "fi"}};
 
 // Maps a BCP-47 or ISO 639-2 language tag to a language-specific hyphenator.
 const LanguageHyphenator* hyphenatorForLanguage(const std::string& langTag) {

lib/Epub/Epub/hyphenation/LanguageRegistry.cpp

@@ -7,6 +7,7 @@
 #include "generated/hyph-de.trie.h"
 #include "generated/hyph-en.trie.h"
 #include "generated/hyph-es.trie.h"
+#include "generated/hyph-fi.trie.h"
 #include "generated/hyph-fr.trie.h"
 #include "generated/hyph-it.trie.h"
 #include "generated/hyph-pl.trie.h"
@@ -26,8 +27,9 @@ LanguageHyphenator italianHyphenator(it_patterns, isLatinLetter, toLowerLatin);
 LanguageHyphenator swedishHyphenator(sv_patterns, isLatinLetter, toLowerLatin);
 LanguageHyphenator ukrainianHyphenator(uk_patterns, isCyrillicLetter, toLowerCyrillic);
 LanguageHyphenator polishHyphenator(pl_patterns, isLatinLetter, toLowerLatin);
+LanguageHyphenator finnishHyphenator(fi_patterns, isLatinLetter, toLowerLatin);
 
-using EntryArray = std::array<LanguageEntry, 9>;
+using EntryArray = std::array<LanguageEntry, 10>;
 
 const EntryArray& entries() {
   static const EntryArray kEntries = {{{"english", "en", &englishHyphenator},
@@ -38,7 +40,8 @@ const EntryArray& entries() {
                                        {"italian", "it", &italianHyphenator},
                                        {"polish", "pl", &polishHyphenator},
                                        {"swedish", "sv", &swedishHyphenator},
-                                       {"ukrainian", "uk", &ukrainianHyphenator}}};
+                                       {"ukrainian", "uk", &ukrainianHyphenator},
+                                       {"finnish", "fi", &finnishHyphenator}}};
   return kEntries;
 }
 

lib/Epub/Epub/hyphenation/generated/hyph-fi.trie.h

@@ -0,0 +1,95 @@
+#pragma once
+
+#include <cstddef>
+#include <cstdint>
+
+#include "Epub/hyphenation/SerializedHyphenationTrie.h"
+
+// Auto-generated by generate_hyphenation_trie.py. Do not edit manually.
+alignas(4) constexpr uint8_t fi_trie_data[] = {
+    0x01, 0x01, 0x16, 0x0B, 0x0C, 0x17, 0x0C, 0x15, 0x0C, 0x0B, 0x16, 0x29, 0x2B, 0x20, 0x1F, 0x0C,
+    0x33, 0x02, 0x0B, 0x02, 0x0B, 0x0C, 0x01, 0x0C, 0x34, 0x0B, 0x2A, 0x0B, 0x2A, 0x0B, 0x0C, 0x20,
+    0x0B, 0x21, 0xA0, 0x00, 0x41, 0xA0, 0x02, 0x51, 0x21, 0x69, 0xFD, 0x21, 0x6C, 0xFD, 0xA1, 0x00,
+    0x41, 0x62, 0xFD, 0xA0, 0x01, 0xA2, 0xA1, 0x00, 0x81, 0x6F, 0xFD, 0xA3, 0x00, 0x81, 0x69, 0x6F,
+    0x75, 0xF8, 0xF8, 0xF8, 0x28, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0x6C, 0x72, 0xDE, 0xDE, 0xEA,
+    0xDE, 0xDE, 0xDE, 0xF2, 0xF7, 0x22, 0xA4, 0xB6, 0xCD, 0xCD, 0xA1, 0x00, 0x81, 0x61, 0xD9, 0x28,
+    0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x72, 0xC3, 0xC3, 0xC3, 0xC3, 0xC3, 0xC3, 0xF6, 0xFB,
+    0xA2, 0x00, 0x81, 0x61, 0x65, 0xC3, 0xC3, 0x48, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0x6C, 0x72,
+    0xFF, 0xAB, 0xFF, 0xAB, 0xFF, 0xAB, 0xFF, 0xAB, 0xFF, 0xAB, 0xFF, 0xAB, 0xFF, 0xE3, 0xFF, 0xF9,
+    0x49, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x6C, 0x72, 0xFF, 0x92, 0xFF, 0x92, 0xFF, 0x92,
+    0xFF, 0x92, 0xFF, 0x92, 0xFF, 0x92, 0xFF, 0xC5, 0xFF, 0xA6, 0xFF, 0xCA, 0x47, 0x61, 0x65, 0x69,
+    0x6F, 0x75, 0x79, 0xC3, 0xFF, 0x76, 0xFF, 0x76, 0xFF, 0x76, 0xFF, 0x76, 0xFF, 0x76, 0xFF, 0x76,
+    0xFF, 0xA9, 0xA0, 0x00, 0xF1, 0x21, 0x73, 0xFD, 0xA1, 0x00, 0x41, 0x75, 0xFD, 0xA0, 0x00, 0x81,
+    0x43, 0x61, 0x65, 0x69, 0xFF, 0x63, 0xFF, 0x63, 0xFF, 0x63, 0xC1, 0x01, 0xA2, 0x61, 0xFF, 0x59,
+    0x4A, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x6C, 0x72, 0x76, 0xFF, 0x42, 0xFF, 0xE8, 0xFF,
+    0x42, 0xFF, 0x42, 0xFF, 0x42, 0xFF, 0x42, 0xFF, 0x75, 0xFF, 0xED, 0xFF, 0xF0, 0xFF, 0xFA, 0xA1,
+    0x00, 0x41, 0x73, 0xCE, 0x47, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0xFF, 0xFB, 0xFF, 0x1E,
+    0xFF, 0x1E, 0xFF, 0x1E, 0xFF, 0x1E, 0xFF, 0x1E, 0xFF, 0x51, 0xA0, 0x01, 0x52, 0x21, 0x6F, 0xFD,
+    0x22, 0x74, 0x6E, 0xFD, 0xFD, 0xA0, 0x01, 0x73, 0x21, 0x6E, 0xFD, 0x22, 0x61, 0x6F, 0xFD, 0xFA,
+    0x21, 0x61, 0xEA, 0x21, 0x6B, 0xFD, 0x21, 0x65, 0xF2, 0xA4, 0x00, 0x41, 0x6E, 0x6A, 0x69, 0x6C,
+    0xE7, 0xF2, 0xFA, 0xFD, 0x21, 0x73, 0xE1, 0x21, 0x75, 0xFD, 0xA1, 0x00, 0x41, 0x64, 0xFD, 0x21,
+    0x74, 0xD6, 0x21, 0x73, 0xFD, 0x22, 0x65, 0x69, 0xFA, 0xFD, 0x21, 0x61, 0xCB, 0x21, 0x6E, 0xBD,
+    0x22, 0x74, 0x6F, 0xBD, 0xFD, 0x21, 0x69, 0xC0, 0x21, 0x61, 0xFD, 0xA4, 0x00, 0x41, 0x70, 0x73,
+    0x74, 0x6D, 0xEA, 0xEF, 0xF5, 0xFD, 0x21, 0x69, 0xD9, 0xA1, 0x00, 0x41, 0x6C, 0xFD, 0x47, 0x61,
+    0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0xFF, 0xBB, 0xFF, 0xCC, 0xFE, 0xA4, 0xFF, 0xED, 0xFE, 0xA4,
+    0xFF, 0xFB, 0xFE, 0xD7, 0xA0, 0x01, 0x41, 0x21, 0x73, 0xFD, 0x21, 0x75, 0xFD, 0xA1, 0x00, 0x41,
+    0x72, 0xFD, 0x49, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x6C, 0x72, 0xFE, 0x80, 0xFF, 0xFB,
+    0xFE, 0x80, 0xFE, 0x80, 0xFE, 0x80, 0xFE, 0x80, 0xFE, 0xB3, 0xFF, 0x2B, 0xFE, 0x94, 0x21, 0x61,
+    0xDC, 0x48, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x74, 0xFF, 0x3E, 0xFE, 0x61, 0xFE, 0x61,
+    0xFE, 0x61, 0xFE, 0x61, 0xFE, 0x61, 0xFE, 0x94, 0xFF, 0xFD, 0x42, 0x69, 0x65, 0xFF, 0x80, 0xFF,
+    0x40, 0x42, 0x6F, 0x65, 0xFF, 0x84, 0xFF, 0x47, 0x41, 0x75, 0xFF, 0x32, 0x21, 0x74, 0xFC, 0x42,
+    0x61, 0x6F, 0xFF, 0xFD, 0xFF, 0x36, 0xA4, 0x00, 0x41, 0x73, 0x6C, 0x6A, 0x70, 0xE4, 0xEB, 0xF9,
+    0xF2, 0x41, 0x79, 0xFF, 0x24, 0x21, 0x74, 0xFC, 0x21, 0x69, 0xFD, 0xA1, 0x00, 0x41, 0x73, 0xFD,
+    0x42, 0x2E, 0x6E, 0xFF, 0x15, 0xFF, 0x15, 0x21, 0x61, 0xF9, 0x21, 0x65, 0xFD, 0xA1, 0x00, 0x41,
+    0x64, 0xFD, 0x41, 0x65, 0xFE, 0xF8, 0x21, 0x6A, 0xFC, 0x42, 0x6B, 0x74, 0xFE, 0xFC, 0xFE, 0xFC,
+    0x21, 0x73, 0xF9, 0x21, 0x69, 0xFD, 0xC3, 0x00, 0x41, 0x68, 0x70, 0x73, 0xFF, 0xF0, 0xFF, 0xFD,
+    0xFF, 0x24, 0x41, 0x74, 0xFF, 0x23, 0xC2, 0x00, 0x41, 0x72, 0x68, 0xFF, 0x30, 0xFF, 0xFC, 0xA0,
+    0x00, 0x52, 0x21, 0x72, 0xFD, 0x21, 0x69, 0xFA, 0x21, 0x6C, 0xFD, 0xA0, 0x00, 0x61, 0x21, 0x68,
+    0xFD, 0x4A, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x74, 0x70, 0x63, 0xFF, 0x95, 0xFF, 0xAA,
+    0xFF, 0xBC, 0xFF, 0xD5, 0xFD, 0xC1, 0xFF, 0xE5, 0xFD, 0xF4, 0xFF, 0xF1, 0xFF, 0xF7, 0xFF, 0xFD,
+    0x48, 0x61, 0x65, 0x69, 0x6F, 0x75, 0x79, 0xC3, 0x73, 0xFD, 0xA2, 0xFD, 0xA2, 0xFD, 0xA2, 0xFD,
+    0xA2, 0xFD, 0xA2, 0xFD, 0xA2, 0xFD, 0xD5, 0xFF, 0xDE, 0xA0, 0x00, 0x92, 0xA0, 0x00, 0xB2, 0xA0,
+    0x01, 0x01, 0xC3, 0x00, 0x61, 0x69, 0x65, 0x79, 0xFE, 0x20, 0xFE, 0x20, 0xFF, 0xFD, 0x22, 0xA4,
+    0xB6, 0xF4, 0xAD, 0x25, 0x79, 0x61, 0x6F, 0x75, 0xC3, 0xA8, 0xE6, 0xE6, 0xE9, 0xFB, 0x42, 0xB6,
+    0xA4, 0xFF, 0x9D, 0xFF, 0x9D, 0x46, 0x79, 0x61, 0x6F, 0x75, 0xC3, 0x65, 0xFF, 0x96, 0xFF, 0xD4,
+    0xFF, 0xD4, 0xFF, 0xD7, 0xFF, 0xF9, 0xFF, 0xD7, 0x22, 0xA4, 0xB6, 0xDB, 0xED, 0xA0, 0x00, 0x72,
+    0xA0, 0x00, 0x71, 0x21, 0xA4, 0xFD, 0x21, 0xC3, 0xFD, 0x21, 0xA4, 0xFD, 0x21, 0x69, 0xF4, 0xA0,
+    0x01, 0x22, 0x21, 0x70, 0xFD, 0x21, 0x6F, 0xFD, 0x21, 0x69, 0xFD, 0x26, 0x61, 0x6F, 0x75, 0xC3,
+    0x65, 0x6C, 0xE2, 0xE2, 0xE2, 0xEE, 0xF1, 0xFD, 0x22, 0xA4, 0xB6, 0xD8, 0xD8, 0x21, 0x61, 0xD3,
+    0xA0, 0x00, 0xB1, 0x24, 0x75, 0x69, 0x65, 0x6F, 0xCD, 0xCD, 0xFD, 0xFD, 0x24, 0x61, 0x65, 0x6F,
+    0x75, 0xF4, 0xF4, 0xF4, 0xF4, 0x25, 0x79, 0xC3, 0x61, 0x75, 0x69, 0xBB, 0xE3, 0xE8, 0xEE, 0xF7,
+    0xA0, 0x00, 0xD2, 0x22, 0xA4, 0xB6, 0xFD, 0xFD, 0x44, 0x61, 0x65, 0x6F, 0x69, 0xFF, 0x64, 0xFF,
+    0x64, 0xFF, 0x64, 0xFF, 0x64, 0x42, 0x65, 0x61, 0xFF, 0x9B, 0xFF, 0xCB, 0x21, 0x65, 0xC4, 0x22,
+    0x61, 0x75, 0xC1, 0xC1, 0xA0, 0x02, 0x32, 0x21, 0x73, 0xFD, 0x21, 0x6F, 0xFD, 0x49, 0x79, 0xC3,
+    0x75, 0x61, 0x65, 0x69, 0x6F, 0x73, 0x6C, 0xFF, 0x80, 0xFF, 0xD6, 0xFF, 0xDB, 0xFF, 0xB0, 0xFF,
+    0xE8, 0xFF, 0xEF, 0xFF, 0xF2, 0xFD, 0x70, 0xFF, 0xFD, 0x44, 0x69, 0x65, 0x6F, 0x75, 0xFF, 0x23,
+    0xFF, 0x23, 0xFF, 0x23, 0xFF, 0x23, 0x43, 0x75, 0x61, 0x65, 0xFF, 0x5A, 0xFF, 0x8A, 0xFF, 0x8A,
+    0x41, 0x76, 0xFF, 0x5F, 0x21, 0x61, 0xFC, 0xA0, 0x01, 0xC2, 0x21, 0x73, 0xFD, 0x21, 0x69, 0xFD,
+    0x21, 0x65, 0xFD, 0x43, 0x69, 0x6F, 0x6B, 0xFF, 0xF1, 0xFD, 0xF7, 0xFF, 0xFD, 0xA0, 0x01, 0xA4,
+    0x21, 0x73, 0xFD, 0x21, 0x61, 0xFD, 0x43, 0x6E, 0x74, 0x6B, 0xFC, 0x7D, 0xFC, 0x7D, 0xFF, 0xFD,
+    0x41, 0x69, 0xFC, 0x73, 0x22, 0x61, 0x6F, 0xF2, 0xFC, 0x21, 0x69, 0xFB, 0x48, 0xC3, 0x61, 0x75,
+    0x65, 0x6F, 0x69, 0x6C, 0x73, 0xFF, 0x3C, 0xFF, 0xAD, 0xFF, 0xBA, 0xFF, 0x20, 0xFF, 0x20, 0xFF,
+    0x50, 0xFF, 0xD7, 0xFF, 0xFD, 0x44, 0x61, 0x69, 0x75, 0x79, 0xFE, 0xB7, 0xFE, 0xB7, 0xFE, 0xB7,
+    0xFE, 0xB7, 0x42, 0x61, 0x69, 0xFE, 0xEE, 0xFE, 0xEE, 0x42, 0x75, 0x61, 0xFE, 0xE7, 0xFF, 0x17,
+    0x42, 0xA4, 0xB6, 0xFE, 0xE6, 0xFF, 0x30, 0x24, 0x65, 0x61, 0x75, 0xC3, 0xDE, 0xEB, 0xF2, 0xF9,
+    0x43, 0x61, 0x65, 0x6F, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0x42, 0x61, 0x75, 0xFE, 0xC6, 0xFE,
+    0xC6, 0x44, 0x75, 0x61, 0x65, 0x6F, 0xFE, 0xBF, 0xFE, 0xEF, 0xFE, 0xEF, 0xFE, 0xEF, 0x41, 0xB6,
+    0xFE, 0xB2, 0x21, 0xC3, 0xFC, 0x42, 0xA4, 0xB6, 0xFE, 0xB1, 0xFF, 0xFD, 0x43, 0x61, 0x6F, 0x79,
+    0xFE, 0xD4, 0xFE, 0xD4, 0xFE, 0xD4, 0x42, 0x61, 0x65, 0xFE, 0x56, 0xFE, 0x56, 0x26, 0x69, 0x61,
+    0x75, 0xC3, 0x65, 0x6F, 0xC3, 0xCD, 0xD4, 0xE8, 0xEF, 0xF9, 0xA0, 0x01, 0x11, 0x21, 0xA4, 0xFD,
+    0xA0, 0x01, 0xE2, 0x21, 0x6E, 0xFD, 0x21, 0x69, 0xFD, 0x21, 0x64, 0xFD, 0xA0, 0x02, 0x03, 0x21,
+    0x61, 0xFD, 0x21, 0x72, 0xFD, 0x21, 0x75, 0xFD, 0x21, 0x75, 0xFD, 0x23, 0xC3, 0x79, 0x73, 0xE2,
+    0xEE, 0xFD, 0x41, 0x72, 0xFD, 0xD9, 0x42, 0x6C, 0x68, 0xFC, 0x47, 0xFF, 0xFC, 0xC1, 0x00, 0x81,
+    0x69, 0xFB, 0xA6, 0x21, 0x76, 0xFA, 0x59, 0x62, 0x64, 0x66, 0x67, 0x68, 0x6A, 0x6B, 0x6C, 0x6D,
+    0x6E, 0x70, 0x72, 0x73, 0x74, 0x76, 0xC3, 0x79, 0x6F, 0x75, 0x61, 0x65, 0x69, 0x2E, 0x63, 0x71,
+    0xFB, 0xAE, 0xFB, 0xC9, 0xFB, 0xE1, 0xFB, 0xFA, 0xFC, 0x16, 0xFC, 0x16, 0xFC, 0x4A, 0xFC, 0x6E,
+    0xFC, 0x16, 0xFC, 0xE8, 0xFD, 0x0C, 0xFD, 0x2B, 0xFD, 0xCB, 0xFD, 0xEA, 0xFC, 0x16, 0xFE, 0x42,
+    0xFE, 0x65, 0xFE, 0x8F, 0xFE, 0xC7, 0xFF, 0x36, 0xFF, 0x71, 0xFF, 0xB7, 0xFF, 0xE5, 0xFF, 0xF0,
+    0xFF, 0xFD,
+};
+
+constexpr SerializedHyphenationPatterns fi_patterns = {
+    0x496u,
+    fi_trie_data,
+    sizeof(fi_trie_data),
+};

lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp

@@ -35,7 +35,7 @@ constexpr const char* BOLD_TAGS[] = {"b", "strong"};
 constexpr const char* ITALIC_TAGS[] = {"i", "em"};
 constexpr const char* UNDERLINE_TAGS[] = {"u", "ins"};
 constexpr const char* LINETHROUGH_TAGS[] = {"del", "s", "strike"};
-constexpr const char* IMAGE_TAGS[] = {"img"};
+constexpr const char* IMAGE_TAGS[] = {"img", "image"};
 constexpr const char* SKIP_TAGS[] = {"head"};
 
 bool isWhitespace(const char c) { return c == ' ' || c == '\r' || c == '\n' || c == '\t'; }
@@ -225,6 +225,7 @@ void ChapterHtmlSlimParser::flushPartWordBuffer() {
   currentTextBlock->addWord(partWordBuffer, fontStyle, false, nextWordContinues);
   partWordBufferIndex = 0;
   nextWordContinues = false;
+  listItemBulletOnly = false;
 }
 
 // start a new text block if needed
@@ -254,6 +255,17 @@ void ChapterHtmlSlimParser::startNewTextBlock(const BlockStyle& blockStyle) {
       return;
     }
 
+    // <li> added a bullet as the first word, making the block non-empty. When a nested
+    // block-level child (<p>, <div>, etc.) opens, reuse the block instead of flushing
+    // the bullet to its own line. The bullet stays inline with the child's text.
+    if (listItemBulletOnly) {
+      const auto style = currentTextBlock->getBlockStyle();
+      currentTextBlock->setBlockStyle(style.getCombinedBlockStyle(blockStyle, BlockStyle::CombineAxis::Vertical));
+      listItemBulletOnly = false;
+      flushPendingAnchor();
+      return;
+    }
+
     makePages();
   }
   // If the pending anchor is a TOC chapter boundary, force a page break after the previous
@@ -261,6 +273,7 @@ void ChapterHtmlSlimParser::startNewTextBlock(const BlockStyle& blockStyle) {
   flushPendingAnchor();
   currentTextBlock.reset(new ParsedText(extraParagraphSpacing, hyphenationEnabled, focusReadingEnabled, blockStyle));
   wordsExtractedInBlock = 0;
+  listItemBulletOnly = false;
 }
 
 void ChapterHtmlSlimParser::emitHorizontalRule(const BlockStyle& blockStyle) {
@@ -495,11 +508,18 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
       for (int i = 0; atts[i]; i += 2) {
         if (strcmp(atts[i], "src") == 0) {
           src = atts[i + 1];
+        } else if (src.empty() && (strcmp(atts[i], "href") == 0 || strcmp(atts[i], "xlink:href") == 0)) {
+          src = atts[i + 1];
         } else if (strcmp(atts[i], "alt") == 0) {
           alt = atts[i + 1];
         }
       }
 
+      const size_t fragmentPos = src.find('#');
+      if (fragmentPos != std::string::npos) {
+        src.resize(fragmentPos);
+      }
+
       // imageRendering: 0=display, 1=placeholder (alt text only), 2=suppress entirely
       if (self->imageRendering == 2) {
         self->skipUntilDepth = self->depth;
@@ -507,19 +527,6 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
         return;
       }
 
-      // Skip image if CSS display:none
-      if (self->cssParser) {
-        CssStyle imgDisplayStyle = self->cssParser->resolveStyle("img", classAttr);
-        if (!styleAttr.empty()) {
-          imgDisplayStyle.applyOver(CssParser::parseInlineStyle(styleAttr));
-        }
-        if (imgDisplayStyle.hasDisplay() && imgDisplayStyle.display == CssDisplay::None) {
-          self->skipUntilDepth = self->depth;
-          self->depth += 1;
-          return;
-        }
-      }
-
       if (!src.empty() && self->imageRendering != 1) {
         LOG_DBG("EHP", "Found image: src=%s", src.c_str());
 
@@ -543,24 +550,28 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
               extractSuccess = self->epub->readItemContentsToStream(resolvedPath, cachedImageFile, 4096);
               cachedImageFile.flush();
               cachedImageFile.close();
-              delay(50);  // Give SD card time to sync
             }
 
             if (extractSuccess) {
-              // Get image dimensions
+              // Get image dimensions, retrying to absorb SD-card sync latency on slow
+              // cards. Replaces a blanket delay(50) that cost ~50ms on every image, and
+              // closes the silent-drop bug where a single getDimensions failure was fatal.
               ImageDimensions dims = {0, 0};
               ImageToFramebufferDecoder* decoder = ImageDecoderFactory::getDecoder(cachedImagePath);
-              if (decoder && decoder->getDimensions(cachedImagePath, dims)) {
+              bool gotDimensions = false;
+              for (int attempt = 0; attempt < 3 && !gotDimensions; attempt++) {
+                if (attempt > 0) {
+                  delay(50);  // Give a slow SD card time to finish syncing before retrying
+                }
+                gotDimensions = decoder && decoder->getDimensions(cachedImagePath, dims);
+              }
+              if (gotDimensions) {
                 LOG_DBG("EHP", "Image dimensions: %dx%d", dims.width, dims.height);
 
                 int displayWidth = 0;
                 int displayHeight = 0;
                 const float emSize = static_cast<float>(self->renderer.getFontAscenderSize(self->fontId));
-                CssStyle imgStyle = self->cssParser ? self->cssParser->resolveStyle("img", classAttr) : CssStyle{};
-                // Merge inline style (e.g. style="height: 2em") so it overrides stylesheet rules
-                if (!styleAttr.empty()) {
-                  imgStyle.applyOver(CssParser::parseInlineStyle(styleAttr));
-                }
+                const CssStyle& imgStyle = cssStyle;
                 const bool hasCssHeight = imgStyle.hasImageHeight();
                 const bool hasCssWidth = imgStyle.hasImageWidth();
 
@@ -882,6 +893,7 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
 
       if (strcmp(name, "li") == 0) {
         self->currentTextBlock->addWord("\xe2\x80\xa2", EpdFontFamily::REGULAR);
+        self->listItemBulletOnly = true;
       }
     }
   } else if (matches(name, UNDERLINE_TAGS, std::size(UNDERLINE_TAGS))) {
@@ -1288,6 +1300,13 @@ void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* n
       }
       self->blockStyleStack.pop_back();
     }
+
+    // </li> closes: if the bullet never got inline text (empty <li> or <li> with only
+    // block children that were flushed), clear the flag so the next sibling doesn't
+    // merge into this block.
+    if (strcmp(name, "li") == 0) {
+      self->listItemBulletOnly = false;
+    }
   }
 }
 

lib/Epub/Epub/parsers/ChapterHtmlSlimParser.h

@@ -80,6 +80,7 @@ class ChapterHtmlSlimParser {
   int tableDepth = 0;
   int tableRowIndex = 0;
   int tableColIndex = 0;
+  bool listItemBulletOnly = false;  // true when currentTextBlock has only the <li> bullet
 
   // Anchor-to-page mapping: tracks which page each HTML id attribute lands on
   int completedPageCount = 0;

lib/Epub/Epub/parsers/ContentOpfParser.cpp

@@ -137,8 +137,10 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
       LOG_ERR("COF", "Couldn't open temp items file for reading. This is probably going to be a fatal error.");
     }
 
-    // Sort item index for binary search if we have enough items
-    if (self->itemIndex.size() >= LARGE_SPINE_THRESHOLD) {
+    // Sort the (unconditionally-built) item index so every idref lookup uses binary
+    // search. Without this, small/medium manifests fell back to an O(spine × manifest)
+    // linear rescan of .items.bin per itemref (up to ~200ms/item at large scale).
+    if (!self->itemIndex.empty()) {
       std::sort(self->itemIndex.begin(), self->itemIndex.end(), [](const ItemIndexEntry& a, const ItemIndexEntry& b) {
         return a.idHash < b.idHash || (a.idHash == b.idHash && a.idLen < b.idLen);
       });
@@ -284,9 +286,8 @@ void XMLCALL ContentOpfParser::startElement(void* userData, const XML_Char* name
               ++it;
             }
           } else {
-            // Slow path: linear scan (for small manifests, keeps original behavior)
-            // TODO: This lookup is slow as need to scan through all items each time.
-            //       It can take up to 200ms per item when getting to 1500 items.
+            // Fallback linear scan, only reached when the index is empty (no manifest
+            // items). The fast binary-search path above is used for all real manifests.
             self->tempItemStore.seek(0);
             std::string itemId;
             while (self->tempItemStore.available()) {

lib/Epub/Epub/parsers/ContentOpfParser.h

@@ -32,7 +32,7 @@ class ContentOpfParser final : public Print {
   HalFile tempItemStore;
   std::string coverItemId;
 
-  // Index for fast idref→href lookup (used only for large EPUBs)
+  // Index for fast idref→href lookup (binary search over .items.bin)
   struct ItemIndexEntry {
     uint32_t idHash;      // FNV-1a hash of itemId
     uint16_t idLen;       // length for collision reduction
@@ -41,8 +41,6 @@ class ContentOpfParser final : public Print {
   std::deque<ItemIndexEntry> itemIndex;
   bool useItemIndex = false;
 
-  static constexpr uint16_t LARGE_SPINE_THRESHOLD = 400;
-
   // FNV-1a hash function
   static uint32_t fnvHash(const std::string& s) {
     uint32_t hash = 2166136261u;