chore: Update version to 1.4.0 (#2283)

(#2334)

Introduces a new display method that prepares the framebuffer as a base
frame for grayscale overlays. On X3 panels, this uses the OEM
differential base waveform (AA-pre-BW) without forcing a resync. Other
panels fall back to normal display with configurable refresh mode.


Dependent upon matching SDK commit to work

USER_GUIDE.md

@@ -241,6 +241,10 @@ The Settings screen allows you to configure the device's behavior. There are a f
   
   - "Chapter Skip" (default) - Long-pressing skips to next/previous chapter
   - "Page Scroll" - Long-pressing scrolls a page up/down
+- **Long-press Menu**: Selects the function bound to holding the menu button (Confirm) while reading an EPUB. **Cycles through the available functions** each time the setting is selected — additional functions may be added in future releases, so this is not a binary on/off toggle. A short press of Confirm always opens the reader menu as normal:
+  - "Bookmark" (default) - Hold Confirm (~0.4 second) to drop a bookmark at the current page.
+  - "KOSync" - Hold Confirm (~1 second) to launch KOReader sync directly.
+  - "Disabled" - Long-press is ignored; only short-press opens the reader menu.
 
 - **Short Power Button Click**: Controls the effect of a short click of the power button:
   
@@ -523,11 +527,14 @@ On the **Xteink X3**, the gyroscope can be used to turn pages by tilting the dev
 
 When reading an EPUB that contains footnotes, you can navigate to the footnote text by selecting the footnote reference in the book. From the footnote, you can return to your original reading position.
 
+If the device goes to sleep or you close the book while viewing a footnote, the book reopens to your original reading position, not the footnote.
+
 ### System Navigation
 
 * **Return to Home:** Press the **Back** button to close the book and return to the **[Home](#31-home-screen)** screen.
 * **Return to Browse Files:** Press and hold the **Back** button to close the book and return to the **[Browse Files](#33-browse-files-screen)** screen.
 * **Reader Menu:** Press **Confirm** to open the **[Reader Menu](#5-reader-menu)**, which includes chapter navigation, reading options, and more.
+* **Long-press Confirm (configurable):** Holding **Confirm** runs the function chosen by the **Long-press Menu** setting in **[Controls Settings](#363-controls)** — "Bookmark" (default) drops a bookmark, "KOSync" launches KOReader Sync, "Disabled" does nothing. A short press always opens the Reader Menu.
 
 ### Supported Languages
 
@@ -574,9 +581,9 @@ Accessible by selecting **Chapters** from the Reader Menu.
 
 Bookmarks can be created to quickly save and restore your place in a book.
 
-To create a bookmark, hold **Confirm** for 1 second while inside a book. A popup will appear letting you know a bookmark was created. The popup message will automatically disappear in a couple of seconds.
+To create a bookmark, hold **Confirm** for about half a second while inside a book. A popup will appear letting you know a bookmark was created. The popup message will automatically disappear in a couple of seconds.
 
-To open bookmarks, press **Confirm** while inside a book. Then navigate to the **Bookmarks** menu. Bookmarks can be opened by navigating to them and pressing **Confirm**, which will redirect you to that place in the book. You can delete bookmarks by holding **Confirm** for 1 second, and then pressing **Confirm** again to confirm deletion, or **Back** to cancel.
+To open bookmarks, press **Confirm** while inside a book. Then navigate to the **Bookmarks** menu. Bookmarks can be opened by navigating to them and pressing **Confirm**, which will redirect you to that place in the book. You can delete bookmarks by holding **Confirm** for about 0.7 seconds, and then pressing **Confirm** again to confirm deletion, or **Back** to cancel.
 
 Bookmarks are stored in the `.crosspoint/bookmarks` folder in the JSON format.
 

lib/EpdFont/EpdFont.cpp

@@ -101,6 +101,9 @@ static uint8_t lookupKernClass(const EpdKernClassEntry* entries, const uint16_t
 }
 
 int8_t EpdFont::getKerning(const uint32_t leftCp, const uint32_t rightCp) const {
+  if (utf8IsCjkBreakable(leftCp) || utf8IsCjkBreakable(rightCp)) {
+    return 0;
+  }
   if (!data->kernMatrix) {
     return 0;
   }

lib/EpdFont/SdCardFont.cpp

@@ -115,6 +115,9 @@ void SdCardFont::freeStyleAll(PerStyle& s) {
   freeStyleMiniData(s);
   delete[] s.fullIntervals;
   s.fullIntervals = nullptr;
+  delete[] s.bmpIntervals;
+  s.bmpIntervals = nullptr;
+  s.intervalsAreBmp16 = false;
   freeStyleKernLigatureData(s);
   s.present = false;
 }
@@ -516,59 +519,94 @@ bool SdCardFont::load(const char* path) {
   styleCount_ = styleCount;
   contentHash_ = hash;
 
-  // Load full intervals into RAM for each present style
+  // Load full intervals into RAM for each present style. BMP-only fonts with
+  // fewer than 65536 glyphs use a compact 6-byte interval table instead of the
+  // on-disk 12-byte table; large sparse CJK subsets otherwise keep tens of KB
+  // of always-resident heap just for lookup metadata.
   for (uint8_t i = 0; i < MAX_STYLES; i++) {
     auto& s = styles_[i];
     if (!s.present) continue;
 
-    s.fullIntervals = new (std::nothrow) EpdUnicodeInterval[s.header.intervalCount];
-    if (!s.fullIntervals) {
-      LOG_ERR("SDCF", "Failed to allocate %u intervals for style %u", s.header.intervalCount, i);
-      freeAll();
-      return false;
-    }
-
     if (!file.seekSet(s.intervalsFileOffset)) {
       LOG_ERR("SDCF", "Failed to seek to intervals for style %u", i);
       freeAll();
       return false;
     }
-    size_t intervalsBytes = s.header.intervalCount * sizeof(EpdUnicodeInterval);
-    if (file.read(reinterpret_cast<uint8_t*>(s.fullIntervals), intervalsBytes) != static_cast<int>(intervalsBytes)) {
-      LOG_ERR("SDCF", "Failed to read intervals for style %u", i);
-      freeAll();
-      return false;
-    }
 
     // Validate interval contents before any later code (findGlobalGlyphIndex,
     // glyph reads) trusts them. A malformed file could otherwise drive
     // out-of-range glyph indices into bogus on-disk reads.
-    {
-      uint32_t expectedOffset = 0;
-      uint32_t prevLast = 0;
+    bool canUseBmp16 = s.header.glyphCount <= UINT16_MAX;
+    uint32_t expectedOffset = 0;
+    uint32_t prevLast = 0;
+    EpdUnicodeInterval iv{};
+    for (uint32_t j = 0; j < s.header.intervalCount; ++j) {
+      if (file.read(reinterpret_cast<uint8_t*>(&iv), sizeof(iv)) != sizeof(iv)) {
+        LOG_ERR("SDCF", "Failed to read interval %u for style %u", j, i);
+        freeAll();
+        return false;
+      }
+      if (iv.first > iv.last) {
+        LOG_ERR("SDCF", "Style %u: invalid interval %u (first 0x%lX > last 0x%lX)", i, j,
+                static_cast<unsigned long>(iv.first), static_cast<unsigned long>(iv.last));
+        file.close();
+        freeAll();
+        return false;
+      }
+      const uint32_t span = iv.last - iv.first + 1;
+      const bool overlapsPrev = (j > 0 && iv.first <= prevLast);
+      const bool spanTooBig = (span > s.header.glyphCount);
+      const bool offsetMismatch = (iv.offset != expectedOffset);
+      const bool offsetOverruns = (iv.offset > s.header.glyphCount - span);
+      if (overlapsPrev || spanTooBig || offsetMismatch || offsetOverruns) {
+        LOG_ERR("SDCF", "Style %u: invalid interval layout at %u (overlap=%d span=%u offMis=%d offOver=%d)", i, j,
+                overlapsPrev, span, offsetMismatch, offsetOverruns);
+        file.close();
+        freeAll();
+        return false;
+      }
+      if (iv.first > UINT16_MAX || iv.last > UINT16_MAX || iv.offset > UINT16_MAX) {
+        canUseBmp16 = false;
+      }
+      expectedOffset += span;
+      prevLast = iv.last;
+    }
+
+    if (!file.seekSet(s.intervalsFileOffset)) {
+      LOG_ERR("SDCF", "Failed to seek back to intervals for style %u", i);
+      freeAll();
+      return false;
+    }
+
+    if (canUseBmp16) {
+      s.bmpIntervals = new (std::nothrow) PerStyle::BmpInterval16[s.header.intervalCount];
+      if (!s.bmpIntervals) {
+        LOG_ERR("SDCF", "Failed to allocate compact intervals for style %u", i);
+        freeAll();
+        return false;
+      }
       for (uint32_t j = 0; j < s.header.intervalCount; ++j) {
-        const auto& iv = s.fullIntervals[j];
-        if (iv.first > iv.last) {
-          LOG_ERR("SDCF", "Style %u: invalid interval %u (first 0x%lX > last 0x%lX)", i, j,
-                  static_cast<unsigned long>(iv.first), static_cast<unsigned long>(iv.last));
-          file.close();
+        if (file.read(reinterpret_cast<uint8_t*>(&iv), sizeof(iv)) != sizeof(iv)) {
+          LOG_ERR("SDCF", "Failed to read compact interval %u for style %u", j, i);
           freeAll();
           return false;
         }
-        const uint32_t span = iv.last - iv.first + 1;
-        const bool overlapsPrev = (j > 0 && iv.first <= prevLast);
-        const bool spanTooBig = (span > s.header.glyphCount);
-        const bool offsetMismatch = (iv.offset != expectedOffset);
-        const bool offsetOverruns = (iv.offset > s.header.glyphCount - span);
-        if (overlapsPrev || spanTooBig || offsetMismatch || offsetOverruns) {
-          LOG_ERR("SDCF", "Style %u: invalid interval layout at %u (overlap=%d span=%u offMis=%d offOver=%d)", i, j,
-                  overlapsPrev, span, offsetMismatch, offsetOverruns);
-          file.close();
-          freeAll();
-          return false;
-        }
-        expectedOffset += span;
-        prevLast = iv.last;
+        s.bmpIntervals[j] = {static_cast<uint16_t>(iv.first), static_cast<uint16_t>(iv.last),
+                             static_cast<uint16_t>(iv.offset)};
+      }
+      s.intervalsAreBmp16 = true;
+    } else {
+      s.fullIntervals = new (std::nothrow) EpdUnicodeInterval[s.header.intervalCount];
+      if (!s.fullIntervals) {
+        LOG_ERR("SDCF", "Failed to allocate %u intervals for style %u", s.header.intervalCount, i);
+        freeAll();
+        return false;
+      }
+      size_t intervalsBytes = s.header.intervalCount * sizeof(EpdUnicodeInterval);
+      if (file.read(reinterpret_cast<uint8_t*>(s.fullIntervals), intervalsBytes) != static_cast<int>(intervalsBytes)) {
+        LOG_ERR("SDCF", "Failed to read intervals for style %u", i);
+        freeAll();
+        return false;
       }
     }
 
@@ -603,13 +641,15 @@ int32_t SdCardFont::findGlobalGlyphIndex(const PerStyle& s, uint32_t codepoint)
   int right = static_cast<int>(s.header.intervalCount) - 1;
   while (left <= right) {
     int mid = left + (right - left) / 2;
-    const auto& interval = s.fullIntervals[mid];
-    if (codepoint < interval.first) {
+    const uint32_t first = s.intervalsAreBmp16 ? s.bmpIntervals[mid].first : s.fullIntervals[mid].first;
+    const uint32_t last = s.intervalsAreBmp16 ? s.bmpIntervals[mid].last : s.fullIntervals[mid].last;
+    if (codepoint < first) {
       right = mid - 1;
-    } else if (codepoint > interval.last) {
+    } else if (codepoint > last) {
       left = mid + 1;
     } else {
-      return static_cast<int32_t>(interval.offset + (codepoint - interval.first));
+      const uint32_t offset = s.intervalsAreBmp16 ? s.bmpIntervals[mid].offset : s.fullIntervals[mid].offset;
+      return static_cast<int32_t>(offset + (codepoint - first));
     }
   }
   return -1;
@@ -1257,7 +1297,7 @@ const EpdGlyph* SdCardFont::onGlyphMiss(void* ctx, uint32_t codepoint) {
 
   if (!self->loaded_ || styleIdx >= MAX_STYLES || !self->styles_[styleIdx].present) return nullptr;
   const auto& s = self->styles_[styleIdx];
-  if (!s.fullIntervals) return nullptr;
+  if (!s.fullIntervals && !s.bmpIntervals) return nullptr;
 
   // Check overflow cache first (matching both codepoint and style)
   for (uint32_t i = 0; i < self->overflowCount_; i++) {

lib/EpdFont/SdCardFont.h

@@ -58,9 +58,9 @@ class SdCardFont {
   // Returns true if advance table is populated for at least one style.
   bool hasAdvanceTable() const;
 
-  // Free mini data for all styles, restore stub EpdFontData.
-  // Also clears the temporary advance table (built per layout pass) but
-  // preserves the persistent advance cache (reused across passes).
+  // Free mini data for all styles and restore stub EpdFontData.
+  // Preserves the persistent advance cache so repeated layout passes can reuse
+  // previously fetched metrics.
   void clearCache();
 
   // Drop the persistent advance cache. Call when unloading the SD font or
@@ -140,6 +140,14 @@ class SdCardFont {
 
     // Full intervals loaded from file (kept in RAM for codepoint lookup)
     EpdUnicodeInterval* fullIntervals = nullptr;
+    struct BmpInterval16 {
+      uint16_t first;
+      uint16_t last;
+      uint16_t offset;
+    } __attribute__((packed));
+    static_assert(sizeof(BmpInterval16) == 6, "BmpInterval16 must remain compact");
+    BmpInterval16* bmpIntervals = nullptr;
+    bool intervalsAreBmp16 = false;
 
     // Persistent kern-class + ligature tables (lazy-loaded on first prewarm).
     // The full kern MATRIX is NOT resident — on Literata-class fonts a single

lib/EpdFont/SdCardFontManager.cpp

@@ -34,19 +34,15 @@ bool SdCardFontManager::loadFamily(const SdCardFontFamilyInfo& family, GfxRender
     unloadAll(renderer);
   }
 
-  // Select by ordinal position: sort available sizes, then map the font size
-  // enum (SMALL=0 .. EXTRA_LARGE=3) to the corresponding slot. When the
-  // family has fewer sizes than 4, clamp to the last available size.
-  auto sizes = family.availableSizes();
-  if (sizes.empty()) {
+  // Select the physical point size closest to the built-in reader sizes. Some
+  // CJK font packs only ship larger sizes, so ordinal selection can make
+  // MEDIUM load 18pt+ and produce oversized pages on small devices.
+  const SdCardFontFileInfo* selected = family.findClosestReaderSize(fontSizeEnum);
+  if (!selected) {
     LOG_ERR("SDMGR", "Family %s has no files to load", family.name.c_str());
     return false;
   }
 
-  uint8_t idx = fontSizeEnum;
-  if (idx >= sizes.size()) idx = sizes.size() - 1;
-  const SdCardFontFileInfo* selected = family.findFile(sizes[idx]);
-
   auto* font = new (std::nothrow) SdCardFont();
   if (!font) {
     LOG_ERR("SDMGR", "Failed to allocate SdCardFont for %s", selected->path.c_str());

lib/EpdFont/SdCardFontManager.h

@@ -15,10 +15,10 @@ class SdCardFontManager {
   SdCardFontManager(const SdCardFontManager&) = delete;
   SdCardFontManager& operator=(const SdCardFontManager&) = delete;
 
-  // Load the font file matching fontSizeEnum (SMALL=0 .. EXTRA_LARGE=3) by
-  // ordinal position in the family's sorted size list. Only one .cpfont file
-  // is loaded; other sizes remain on disk. This keeps resident interval +
-  // kern/ligature tables to one size's worth of memory.
+  // Load the font file whose physical point size is closest to the reader
+  // fontSizeEnum (SMALL=12, MEDIUM=14, LARGE=16, EXTRA_LARGE=18). Only one
+  // .cpfont file is loaded; other sizes remain on disk. This keeps resident
+  // interval + kern/ligature tables to one size's worth of memory.
   // Returns true on success.
   bool loadFamily(const SdCardFontFamilyInfo& family, GfxRenderer& renderer, uint8_t fontSizeEnum);
 
@@ -32,7 +32,7 @@ class SdCardFontManager {
   // Get name of currently loaded family (empty if none).
   const std::string& currentFamilyName() const { return loadedFamilyName_; };
 
-  // Point size that was actually loaded (closest match to targetPtSize).
+  // Point size that was actually loaded.
   // 0 if nothing loaded.
   uint8_t currentPointSize() const { return loadedPointSize_; };
 

lib/EpdFont/SdCardFontRegistry.cpp

@@ -15,6 +15,60 @@ const SdCardFontFileInfo* SdCardFontFamilyInfo::findFile(uint8_t size, uint8_t s
   return nullptr;
 }
 
+const SdCardFontFileInfo* SdCardFontFamilyInfo::findClosestReaderSize(const uint8_t fontSizeEnum,
+                                                                      const uint8_t style) const {
+  if (files.empty()) return nullptr;
+
+  // Collect sizes matching the requested style, sorted ascending.
+  std::vector<uint8_t> sizes;
+  for (const auto& f : files) {
+    if (f.style != style) continue;
+    sizes.push_back(f.pointSize);
+  }
+  if (sizes.empty()) return nullptr;
+  std::sort(sizes.begin(), sizes.end());
+
+  // When the family provides at least 4 sizes, use ordinal (index-based)
+  // selection so custom-built font sets (e.g. 10/12/14/16) map SMALL to
+  // the smallest file, not to a hardcoded 12pt target.
+  if (sizes.size() >= 4) {
+    uint8_t idx = fontSizeEnum;
+    if (idx >= sizes.size()) idx = sizes.size() - 1;
+    return findFile(sizes[idx], style);
+  }
+
+  // Fewer sizes than enum slots (e.g. CJK packs with only 2-3 sizes):
+  // fall back to closest-match against the built-in reader targets.
+  uint8_t target = 14;
+  switch (fontSizeEnum) {
+    case 0:
+      target = 12;
+      break;
+    case 2:
+      target = 16;
+      break;
+    case 3:
+      target = 18;
+      break;
+    case 1:
+    default:
+      target = 14;
+      break;
+  }
+
+  const SdCardFontFileInfo* best = nullptr;
+  uint8_t bestDelta = 255;
+  for (const auto& f : files) {
+    if (f.style != style) continue;
+    const uint8_t delta = f.pointSize > target ? f.pointSize - target : target - f.pointSize;
+    if (!best || delta < bestDelta || (delta == bestDelta && f.pointSize < best->pointSize)) {
+      best = &f;
+      bestDelta = delta;
+    }
+  }
+  return best;
+}
+
 bool SdCardFontFamilyInfo::hasSize(uint8_t size) const {
   for (const auto& f : files) {
     if (f.pointSize == size) return true;

lib/EpdFont/SdCardFontRegistry.h

@@ -18,6 +18,7 @@ struct SdCardFontFamilyInfo {
   std::vector<SdCardFontFileInfo> files;
 
   const SdCardFontFileInfo* findFile(uint8_t size, uint8_t style = 0) const;
+  const SdCardFontFileInfo* findClosestReaderSize(uint8_t fontSizeEnum, uint8_t style = 0) const;
   bool hasSize(uint8_t size) const;
   std::vector<uint8_t> availableSizes() const;
 };

lib/EpdFont/scripts/fontconvert.py

@@ -248,7 +248,7 @@ unmerged_intervals = sorted(intervals + add_ints)
 intervals = []
 unvalidated_intervals = []
 for i_start, i_end in unmerged_intervals:
-    if len(unvalidated_intervals) > 0 and i_start + 1 <= unvalidated_intervals[-1][1]:
+    if len(unvalidated_intervals) > 0 and i_start <= unvalidated_intervals[-1][1] + 1:
         unvalidated_intervals[-1] = (unvalidated_intervals[-1][0], max(unvalidated_intervals[-1][1], i_end))
         continue
     unvalidated_intervals.append((i_start, i_end))

lib/EpdFont/scripts/fontconvert_sdcard.py

@@ -40,7 +40,8 @@ INTERVAL_PRESETS = {
     "ascii":       [(0x0020, 0x007E)],
     "latin1":      [(0x0080, 0x00FF)],
     "latin-ext":   [(0x0020, 0x007E), (0x0080, 0x00FF), (0x0100, 0x024F),
-                    (0x1E00, 0x1EFF), (0x2000, 0x206F), (0xFB00, 0xFB06)],
+                    (0x02B0, 0x02FF), (0x1E00, 0x1EFF), (0x2000, 0x206F),
+                    (0xFB00, 0xFB06)],
     "greek":       [(0x0370, 0x03FF), (0x1F00, 0x1FFF)],
     "cyrillic":    [(0x0400, 0x04FF), (0x0500, 0x052F)],
     "hebrew":      [(0x0590, 0x05FF), (0xFB1D, 0xFB4F)],
@@ -62,7 +63,7 @@ INTERVAL_PRESETS = {
     # Composite preset for English-language literary fiction including scifi/popsci.
     # Greek for physics terms, math operators, geometric shapes, uncommon
     # dialogue punctuation, CJK quote marks, miscellaneous symbols (♪♫♬), dingbats.
-    "reading":     [(0x0020, 0x024F), (0x0300, 0x036F), (0x0370, 0x03FF),
+    "reading":     [(0x0020, 0x024F), (0x02B0, 0x02FF), (0x0300, 0x036F), (0x0370, 0x03FF),
                     (0x0400, 0x04FF), (0x1E00, 0x1EFF), (0x2000, 0x206F),
                     (0x2070, 0x209F), (0x20A0, 0x20CF), (0x2150, 0x218F),
                     (0x2190, 0x21FF), (0x2200, 0x22FF), (0x2500, 0x257F),

lib/Epub/Epub.cpp

@@ -5,6 +5,7 @@
 #include <JpegToBmpConverter.h>
 #include <Logging.h>
 #include <PngToBmpConverter.h>
+#include <Utf8.h>
 #include <ZipFile.h>
 
 #include "Epub/parsers/ContainerParser.h"
@@ -73,8 +74,9 @@ bool Epub::parseContentOpf(BookMetadataCache::BookMetadata& bookMetadata, const
     return false;
   }
 
-  // Grab data from opfParser into epub
-  bookMetadata.title = opfParser.title;
+  // Grab data from opfParser into epub. Normalize titles to NFC so NFD (combining
+  // mark) text renders correctly — the device fonts have no mark positioning.
+  bookMetadata.title = utf8ComposeNfc(opfParser.title);
   bookMetadata.author = opfParser.author;
   bookMetadata.language = opfParser.language;
   bookMetadata.coverItemHref = opfParser.coverItemHref;

lib/Epub/Epub/BookMetadataCache.cpp

@@ -2,6 +2,7 @@
 
 #include <Logging.h>
 #include <Serialization.h>
+#include <Utf8.h>
 #include <ZipFile.h>
 
 #include <deque>
@@ -9,7 +10,7 @@
 #include "FsHelpers.h"
 
 namespace {
-constexpr uint8_t BOOK_CACHE_VERSION = 7;
+constexpr uint8_t BOOK_CACHE_VERSION = 8;  // v8: TOC/book titles stored NFC-composed
 constexpr char bookBinFile[] = "/book.bin";
 constexpr char tmpSpineBinFile[] = "/spine.bin.tmp";
 constexpr char tmpTocBinFile[] = "/toc.bin.tmp";
@@ -364,7 +365,9 @@ void BookMetadataCache::createTocEntry(const std::string& title, const std::stri
     }
   }
 
-  const TocEntry entry(title, href, anchor, level, spineIndex);
+  // 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);
   tocCount++;
 }

lib/Epub/Epub/Page.cpp

@@ -6,6 +6,20 @@
 
 #include <new>
 
+namespace {
+
+template <typename Predicate>
+void renderFilteredPageElements(const std::vector<std::shared_ptr<PageElement>>& elements, GfxRenderer& renderer,
+                                const int fontId, const int xOffset, const int yOffset, Predicate&& predicate) {
+  for (const auto& element : elements) {
+    if (predicate(*element)) {
+      element->render(renderer, fontId, xOffset, yOffset);
+    }
+  }
+}
+
+}  // namespace
+
 void PageLine::render(GfxRenderer& renderer, const int fontId, const int xOffset, const int yOffset) {
   block->render(renderer, fontId, xPos + xOffset, yPos + yOffset);
 }
@@ -93,9 +107,12 @@ std::unique_ptr<PageHorizontalRule> PageHorizontalRule::deserialize(HalFile& fil
 }
 
 void Page::render(GfxRenderer& renderer, const int fontId, const int xOffset, const int yOffset) const {
-  for (auto& element : elements) {
-    element->render(renderer, fontId, xOffset, yOffset);
-  }
+  renderFilteredPageElements(elements, renderer, fontId, xOffset, yOffset, [](const PageElement&) { return true; });
+}
+
+void Page::renderImages(GfxRenderer& renderer, const int fontId, const int xOffset, const int yOffset) const {
+  renderFilteredPageElements(elements, renderer, fontId, xOffset, yOffset,
+                             [](const PageElement& element) { return element.getTag() == TAG_PageImage; });
 }
 
 bool Page::serialize(HalFile& file) const {

lib/Epub/Epub/Page.h

@@ -88,6 +88,7 @@ class Page {
   }
 
   void render(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) const;
+  void renderImages(GfxRenderer& renderer, int fontId, int xOffset, int yOffset) const;
   bool serialize(HalFile& file) const;
   static std::unique_ptr<Page> deserialize(HalFile& file);
 

lib/Epub/Epub/ParsedText.cpp

@@ -24,6 +24,7 @@ constexpr size_t RTL_PARAGRAPH_PROBE_WORDS = 3;
 // Per-word: scan enough chars to see through leading neutrals (quotes, numbers)
 // before giving up. 64 is a hedge for pathological cases like long numeric tokens.
 constexpr int RTL_PER_WORD_PROBE_DEPTH = 64;
+constexpr size_t MIN_JUSTIFY_GAPS = 1;
 
 // Byte-level pre-check: Hebrew UTF-8 lead bytes 0xD6-0xD7, Arabic/Syriac 0xD8-0xDB.
 bool mayContainRtlBytes(const char* str) {
@@ -57,6 +58,134 @@ uint32_t lastCodepoint(const std::string& word) {
 
 bool containsSoftHyphen(const std::string& word) { return word.find(SOFT_HYPHEN_UTF8) != std::string::npos; }
 
+bool isNoBreakBeforeCjkPunctuation(const uint32_t cp) {
+  switch (cp) {
+    case '.':
+    case ',':
+    case ':':
+    case ';':
+    case '!':
+    case '?':
+    case ')':
+    case ']':
+    case '}':
+    case 0x00BB:  // »
+    case 0x2019:  // ’
+    case 0x201D:  // ”
+    case 0x3001:  // 、
+    case 0x3002:  // 。
+    case 0x3009:  // 〉
+    case 0x300B:  // 》
+    case 0x300D:  // 」
+    case 0x300F:  // 』
+    case 0x3011:  // 】
+    case 0x3015:  // 〕
+    case 0x3017:  // 〗
+    case 0x3019:  // 〙
+    case 0x301B:  // 〛
+    case 0xFF01:  // ！
+    case 0xFF09:  // ）
+    case 0xFF0C:  // ，
+    case 0xFF0E:  // ．
+    case 0xFF1A:  // ：
+    case 0xFF1B:  // ；
+    case 0xFF1F:  // ？
+    case 0xFF3D:  // ］
+    case 0xFF5D:  // ｝
+      return true;
+    default:
+      return false;
+  }
+}
+
+bool isNoBreakAfterCjkPunctuation(const uint32_t cp) {
+  switch (cp) {
+    case '(':
+    case '[':
+    case '{':
+    case 0x00AB:  // «
+    case 0x2018:  // ‘
+    case 0x201C:  // “
+    case 0x3008:  // 〈
+    case 0x300A:  // 《
+    case 0x300C:  // 「
+    case 0x300E:  // 『
+    case 0x3010:  // 【
+    case 0x3014:  // 〔
+    case 0x3016:  // 〖
+    case 0x3018:  // 〘
+    case 0x301A:  // 〚
+    case 0xFF08:  // （
+    case 0xFF3B:  // ［
+    case 0xFF5B:  // ｛
+      return true;
+    default:
+      return false;
+  }
+}
+
+bool containsCjkBreakableCodepoint(const std::string& text) {
+  const auto* ptr = reinterpret_cast<const unsigned char*>(text.c_str());
+  while (*ptr) {
+    const uint32_t cp = utf8NextCodepoint(&ptr);
+    if (utf8IsCjkBreakable(cp)) {
+      return true;
+    }
+  }
+  return false;
+}
+
+bool hasCjkBreakOpportunityBetween(const uint32_t leftCp, const uint32_t rightCp) {
+  if (!utf8IsCjkBreakable(leftCp) && !utf8IsCjkBreakable(rightCp)) return false;
+  if (isNoBreakAfterCjkPunctuation(leftCp) || isNoBreakBeforeCjkPunctuation(rightCp)) return false;
+  if (utf8IsCombiningMark(rightCp)) return false;
+  return true;
+}
+
+std::vector<size_t> cjkCharacterBreakByteOffsets(const std::string& text) {
+  struct CodepointBoundary {
+    uint32_t cp;
+    size_t endOffset;
+  };
+
+  std::vector<CodepointBoundary> codepoints;
+  codepoints.reserve(text.size());
+  bool hasCjkBreakable = false;
+
+  const auto* ptr = reinterpret_cast<const unsigned char*>(text.c_str());
+  const auto* const start = ptr;
+  while (*ptr) {
+    const uint32_t cp = utf8NextCodepoint(&ptr);
+    if (cp == 0) break;
+    if (utf8IsCjkBreakable(cp)) {
+      hasCjkBreakable = true;
+    }
+    codepoints.push_back({cp, static_cast<size_t>(ptr - start)});
+  }
+
+  if (!hasCjkBreakable || codepoints.size() < 2) return {};
+
+  std::vector<size_t> allowedOffsets;
+  allowedOffsets.reserve(codepoints.size() - 1);
+  for (size_t i = 0; i + 1 < codepoints.size(); ++i) {
+    const uint32_t current = codepoints[i].cp;
+    const uint32_t next = codepoints[i + 1].cp;
+    if (!hasCjkBreakOpportunityBetween(current, next)) continue;
+    allowedOffsets.push_back(codepoints[i].endOffset);
+  }
+  return allowedOffsets;
+}
+
+int computeJustifyExtra(const int spareSpace, const size_t gapCount) {
+  if (gapCount < MIN_JUSTIFY_GAPS || spareSpace <= 0) return 0;
+  // Distribute the spare space evenly across gaps. Do NOT bail out to 0 when the
+  // per-gap stretch is large: a sparse line (few words on a wide page) legitimately
+  // needs big gaps to reach the margin. Returning 0 there disables justification for
+  // that line, leaving it right-aligned (RTL) / left-aligned (LTR) — the mismatched
+  // alignment bug. Match the un-capped behavior of the old code.
+  return spareSpace / static_cast<int>(gapCount);
+}
+
 // Removes every soft hyphen in-place so rendered glyphs match measured widths.
 void stripSoftHyphensInPlace(std::string& word) {
   size_t pos = 0;
@@ -125,6 +254,14 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
                          const bool attachToPrevious) {
   if (word.empty()) return;
 
+  // The device fonts carry no combining-mark positioning, so EPUB text stored in NFD
+  // (a base letter followed by separate combining accents -- common for Vietnamese,
+  // and used for many EPUB <h1> chapter headings) renders with the marks detached or
+  // misplaced. Compose to NFC here, the single funnel every word passes through, so a
+  // precomposed glyph is used instead. This runs once per word at layout time (the
+  // result is cached in the section file) and is a cheap no-op for mark-free text.
+  word = utf8ComposeNfc(word);
+
   EpdFontFamily::Style baseStyle = fontStyle;
   if (underline) {
     baseStyle = static_cast<EpdFontFamily::Style>(baseStyle | EpdFontFamily::UNDERLINE);
@@ -132,12 +269,54 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
   const bool wordStartsRtl = !hasRtlWord && mayContainRtlBytes(word.c_str()) &&
                              BidiUtils::startsWithRtl(word.c_str(), RTL_PER_WORD_PROBE_DEPTH);
 
+  const auto pushToken = [&](std::string token, const bool continues, const bool noSpaceBefore,
+                             const bool isFocusSuffix) {
+    words.push_back(std::move(token));
+    wordStyles.push_back(baseStyle);
+    wordContinues.push_back(continues);
+    wordNoSpaceBefore.push_back(noSpaceBefore);
+    wordIsFocusSuffix.push_back(isFocusSuffix);
+  };
+
+  bool effectiveAttachToPrevious = attachToPrevious;
+  bool effectiveNoSpaceBefore = false;
+  if (attachToPrevious && !words.empty() &&
+      hasCjkBreakOpportunityBetween(lastCodepoint(words.back()), firstCodepoint(word))) {
+    effectiveAttachToPrevious = false;
+    effectiveNoSpaceBefore = true;
+  }
+
+  if (auto breakOffsets = cjkCharacterBreakByteOffsets(word); !breakOffsets.empty()) {
+    bool firstToken = true;
+    size_t tokenStart = 0;
+    for (const size_t breakOffset : breakOffsets) {
+      if (breakOffset <= tokenStart || breakOffset > word.size()) continue;
+      pushToken(word.substr(tokenStart, breakOffset - tokenStart), firstToken ? effectiveAttachToPrevious : false,
+                firstToken ? effectiveNoSpaceBefore : true, false);
+      firstToken = false;
+      tokenStart = breakOffset;
+    }
+    if (tokenStart < word.size()) {
+      pushToken(word.substr(tokenStart), firstToken ? effectiveAttachToPrevious : false,
+                firstToken ? effectiveNoSpaceBefore : true, false);
+    }
+    if (wordStartsRtl) {
+      hasRtlWord = true;
+    }
+    return;
+  }
+
+  if (containsCjkBreakableCodepoint(word)) {
+    pushToken(std::move(word), effectiveAttachToPrevious, effectiveNoSpaceBefore, false);
+    if (wordStartsRtl) {
+      hasRtlWord = true;
+    }
+    return;
+  }
+
   // Already-bold text should stay fully bold; focus splitting would make its suffix regular later.
   if (!this->focusReadingEnabled || (baseStyle & EpdFontFamily::BOLD) != 0) {
-    words.push_back(std::move(word));
-    wordStyles.push_back(baseStyle);
-    wordContinues.push_back(attachToPrevious);
-    wordIsFocusSuffix.push_back(false);
+    pushToken(std::move(word), effectiveAttachToPrevious, effectiveNoSpaceBefore, false);
     if (wordStartsRtl) {
       hasRtlWord = true;
     }
@@ -166,17 +345,19 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
     words.reserve(newCapacity);
     wordStyles.reserve(newCapacity);
     wordContinues.reserve(newCapacity);
+    wordNoSpaceBefore.reserve(newCapacity);
     wordIsFocusSuffix.reserve(newCapacity);
   }
 
   // Lambda helper to process and push individual sub-segments of the string
   // Use std::string_view to avoid heap allocations when slicing
-  auto processSegment = [&](std::string_view segment, bool isWord, bool attach) {
+  auto processSegment = [&](std::string_view segment, bool isWord, bool attach, bool noSpaceBefore) {
     if (!isWord) {
       // Punctuation and Numbers stay regular
       words.emplace_back(segment);
       wordStyles.push_back(baseStyle);
       wordContinues.push_back(attach);
+      wordNoSpaceBefore.push_back(noSpaceBefore);
       wordIsFocusSuffix.push_back(false);
     } else {
       size_t charCount = 0;
@@ -198,6 +379,7 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
         words.emplace_back(segment);
         wordStyles.push_back(static_cast<EpdFontFamily::Style>(baseStyle | EpdFontFamily::BOLD));
         wordContinues.push_back(attach);
+        wordNoSpaceBefore.push_back(noSpaceBefore);
         wordIsFocusSuffix.push_back(false);
       } else {
         countPtr = reinterpret_cast<const unsigned char*>(segment.data());
@@ -210,12 +392,14 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
         words.emplace_back(segment.substr(0, splitByteOffset));
         wordStyles.push_back(static_cast<EpdFontFamily::Style>(baseStyle | EpdFontFamily::BOLD));
         wordContinues.push_back(attach);
+        wordNoSpaceBefore.push_back(noSpaceBefore);
         wordIsFocusSuffix.push_back(false);
 
         // Regular suffix - marked so extractLine can merge it back into single TextBlock entry
         words.emplace_back(segment.substr(splitByteOffset));
         wordStyles.push_back(baseStyle);
         wordContinues.push_back(true);
+        wordNoSpaceBefore.push_back(false);
         wordIsFocusSuffix.push_back(true);
       }
     }
@@ -243,7 +427,8 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
 
       // Only the very first segment inherits the original attachToPrevious flag.
       // Every subsequent segment MUST attach=true so it glues seamlessly to the prefix.
-      processSegment(segment, inWordSegment, isFirstSegment ? attachToPrevious : true);
+      processSegment(segment, inWordSegment, isFirstSegment ? effectiveAttachToPrevious : true,
+                     isFirstSegment ? effectiveNoSpaceBefore : false);
 
       // Setup for the next segment
       segmentStart = currentCpStart;
@@ -255,7 +440,8 @@ void ParsedText::addWord(std::string word, const EpdFontFamily::Style fontStyle,
   // Process the final remaining segment
   size_t segmentLen = end - segmentStart;
   std::string_view segment(reinterpret_cast<const char*>(segmentStart), segmentLen);
-  processSegment(segment, inWordSegment, isFirstSegment ? attachToPrevious : true);
+  processSegment(segment, inWordSegment, isFirstSegment ? effectiveAttachToPrevious : true,
+                 isFirstSegment ? effectiveNoSpaceBefore : false);
   if (wordStartsRtl) {
     hasRtlWord = true;
   }
@@ -324,14 +510,16 @@ void ParsedText::layoutAndExtractLines(const GfxRenderer& renderer, const int fo
   std::vector<size_t> lineBreakIndices;
   if (hyphenationEnabled) {
     // Use greedy layout that can split words mid-loop when a hyphenated prefix fits.
-    lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues);
+    lineBreakIndices =
+        computeHyphenatedLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues, wordNoSpaceBefore);
   } else {
-    lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues);
+    lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, wordWidths, wordContinues, wordNoSpaceBefore);
   }
   const size_t lineCount = includeLastLine ? lineBreakIndices.size() : lineBreakIndices.size() - 1;
 
   for (size_t i = 0; i < lineCount; ++i) {
-    extractLine(i, pageWidth, wordWidths, wordContinues, lineBreakIndices, processLine, renderer, fontId);
+    extractLine(i, pageWidth, wordWidths, wordContinues, wordNoSpaceBefore, lineBreakIndices, processLine, renderer,
+                fontId);
   }
 
   // Remove consumed words so size() reflects only remaining words
@@ -340,6 +528,7 @@ void ParsedText::layoutAndExtractLines(const GfxRenderer& renderer, const int fo
     words.erase(words.begin(), words.begin() + consumed);
     wordStyles.erase(wordStyles.begin(), wordStyles.begin() + consumed);
     wordContinues.erase(wordContinues.begin(), wordContinues.begin() + consumed);
+    wordNoSpaceBefore.erase(wordNoSpaceBefore.begin(), wordNoSpaceBefore.begin() + consumed);
     wordIsFocusSuffix.erase(wordIsFocusSuffix.begin(), wordIsFocusSuffix.begin() + consumed);
   }
 }
@@ -356,7 +545,8 @@ std::vector<uint16_t> ParsedText::calculateWordWidths(const GfxRenderer& rendere
 }
 
 std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, const int fontId, const int pageWidth,
-                                                  std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec) {
+                                                  std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec,
+                                                  std::vector<bool>& noSpaceBeforeVec) {
   if (words.empty()) {
     return {};
   }
@@ -395,7 +585,9 @@ std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, c
     for (size_t j = i; j < totalWordCount; ++j) {
       // Add space before word j, unless it's the first word on the line or a continuation
       int gap = 0;
-      if (j > static_cast<size_t>(i) && !continuesVec[j]) {
+      if (j > static_cast<size_t>(i) && noSpaceBeforeVec[j]) {
+        gap = 0;
+      } else if (j > static_cast<size_t>(i) && !continuesVec[j]) {
         gap =
             renderer.getSpaceAdvance(fontId, lastCodepoint(words[j - 1]), firstCodepoint(words[j]), wordStyles[j - 1]);
       } else if (j > static_cast<size_t>(i) && continuesVec[j]) {
@@ -470,7 +662,8 @@ std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, c
 // Builds break indices while opportunistically splitting the word that would overflow the current line.
 std::vector<size_t> ParsedText::computeHyphenatedLineBreaks(const GfxRenderer& renderer, const int fontId,
                                                             const int pageWidth, std::vector<uint16_t>& wordWidths,
-                                                            std::vector<bool>& continuesVec) {
+                                                            std::vector<bool>& continuesVec,
+                                                            std::vector<bool>& noSpaceBeforeVec) {
   const int firstLineIndent = resolveFirstLineIndent(true, renderer, fontId);
 
   std::vector<size_t> lineBreakIndices;
@@ -488,7 +681,9 @@ std::vector<size_t> ParsedText::computeHyphenatedLineBreaks(const GfxRenderer& r
     while (currentIndex < wordWidths.size()) {
       const bool isFirstWord = currentIndex == lineStart;
       int spacing = 0;
-      if (!isFirstWord && !continuesVec[currentIndex]) {
+      if (!isFirstWord && noSpaceBeforeVec[currentIndex]) {
+        spacing = 0;
+      } else if (!isFirstWord && !continuesVec[currentIndex]) {
         spacing = renderer.getSpaceAdvance(fontId, lastCodepoint(words[currentIndex - 1]),
                                            firstCodepoint(words[currentIndex]), wordStyles[currentIndex - 1]);
       } else if (!isFirstWord && continuesVec[currentIndex]) {
@@ -618,6 +813,7 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
   // line, while "kilometer" moves to the next line.
   // wordContinues[wordIndex] is intentionally left unchanged — the prefix keeps its original attachment.
   wordContinues.insert(wordContinues.begin() + wordIndex + 1, false);
+  wordNoSpaceBefore.insert(wordNoSpaceBefore.begin() + wordIndex + 1, false);
 
   // Update cached widths to reflect the new prefix/remainder pairing.
   wordWidths[wordIndex] = static_cast<uint16_t>(chosenWidth);
@@ -627,7 +823,8 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
 }
 
 void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const std::vector<uint16_t>& wordWidths,
-                             const std::vector<bool>& continuesVec, const std::vector<size_t>& lineBreakIndices,
+                             const std::vector<bool>& continuesVec, const std::vector<bool>& noSpaceBeforeVec,
+                             const std::vector<size_t>& lineBreakIndices,
                              const std::function<void(std::shared_ptr<TextBlock>)>& processLine,
                              const GfxRenderer& renderer, const int fontId) {
   const size_t lineBreak = lineBreakIndices[breakIndex];
@@ -660,7 +857,11 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
   for (size_t wordIdx = 0; wordIdx < lineWordCount; wordIdx++) {
     lineWordWidthSum += wordWidths[lastBreakAt + wordIdx];
     // Count gaps: each word after the first creates a gap, unless it's a continuation
-    if (wordIdx > 0 && !continuesVec[lastBreakAt + wordIdx]) {
+    if (wordIdx > 0 && noSpaceBeforeVec[lastBreakAt + wordIdx]) {
+      // Unicode break opportunity with no inserted Latin-style space. It is still
+      // a stretchable gap for justified CJK/Korean text.
+      actualGapCount++;
+    } else if (wordIdx > 0 && !continuesVec[lastBreakAt + wordIdx]) {
       actualGapCount++;
       totalNaturalGaps += renderer.getSpaceAdvance(fontId, lastCodepoint(lineWords[wordIdx - 1]),
                                                    firstCodepoint(lineWords[wordIdx]), lineWordStyles[wordIdx - 1]);
@@ -689,8 +890,8 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
 
   // For justified text, compute per-gap extra to distribute remaining space evenly
   const int spareSpace = effectivePageWidth - lineWordWidthSum - totalNaturalGaps;
-  const int justifyExtra = (effectiveAlignment == CssTextAlign::Justify && !isLastLine && actualGapCount >= 1)
-                               ? spareSpace / static_cast<int>(actualGapCount)
+  const int justifyExtra = (effectiveAlignment == CssTextAlign::Justify && !isLastLine)
+                               ? computeJustifyExtra(spareSpace, actualGapCount)
                                : 0;
 
   // BiDi processing: reorder words with UAX#9 in full-line context.
@@ -709,11 +910,13 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
     reorderedStylesScratch.clear();
     reorderedWidthsScratch.clear();
     reorderedContinuesScratch.clear();
+    reorderedNoSpaceBeforeScratch.clear();
     reorderedFocusSuffixScratch.clear();
     reorderedWordsScratch.reserve(visualOrderScratch.size());
     reorderedStylesScratch.reserve(visualOrderScratch.size());
     reorderedWidthsScratch.reserve(visualOrderScratch.size());
     reorderedContinuesScratch.reserve(visualOrderScratch.size());
+    reorderedNoSpaceBeforeScratch.reserve(visualOrderScratch.size());
     reorderedFocusSuffixScratch.reserve(visualOrderScratch.size());
 
     for (size_t i = 0; i < visualOrderScratch.size(); ++i) {
@@ -740,6 +943,7 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
         }
       }
       reorderedContinuesScratch.push_back(continues);
+      reorderedNoSpaceBeforeScratch.push_back(!continues && noSpaceBeforeVec[lastBreakAt + src]);
     }
 
     int reorderedWordWidthSum = 0;
@@ -747,7 +951,11 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
     int reorderedNaturalGaps = 0;
     for (size_t wordIdx = 0; wordIdx < reorderedWidthsScratch.size(); wordIdx++) {
       reorderedWordWidthSum += reorderedWidthsScratch[wordIdx];
-      if (wordIdx > 0 && !reorderedContinuesScratch[wordIdx]) {
+      if (wordIdx > 0 && reorderedNoSpaceBeforeScratch[wordIdx]) {
+        // Unicode break opportunity with no inserted Latin-style space. It is still
+        // a stretchable gap for justified CJK/Korean text.
+        reorderedGapCount++;
+      } else if (wordIdx > 0 && !reorderedContinuesScratch[wordIdx]) {
         reorderedGapCount++;
         reorderedNaturalGaps += renderer.getSpaceAdvance(fontId, lastCodepoint(reorderedWordsScratch[wordIdx - 1]),
                                                          firstCodepoint(reorderedWordsScratch[wordIdx]),
@@ -763,10 +971,9 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
     }
 
     const int reorderedSpare = effectivePageWidth - reorderedWordWidthSum - reorderedNaturalGaps;
-    const int reorderedJustifyExtra =
-        (effectiveAlignment == CssTextAlign::Justify && !isLastLine && reorderedGapCount >= 1)
-            ? reorderedSpare / static_cast<int>(reorderedGapCount)
-            : 0;
+    const int reorderedJustifyExtra = (effectiveAlignment == CssTextAlign::Justify && !isLastLine)
+                                          ? computeJustifyExtra(reorderedSpare, reorderedGapCount)
+                                          : 0;
 
     const int justifyContribution = (effectiveAlignment == CssTextAlign::Justify && !isLastLine)
                                         ? reorderedJustifyExtra * static_cast<int>(reorderedGapCount)
@@ -799,15 +1006,20 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
         int advance =
             renderer.getKerning(fontId, lastCodepoint(reorderedWordsScratch[wordIdx]),
                                 firstCodepoint(reorderedWordsScratch[wordIdx + 1]), reorderedStylesScratch[wordIdx]);
-        if (reorderedWordsScratch[wordIdx] == " " && reorderedContinuesScratch[wordIdx] &&
+        // wordIdx > 0 mirrors the gap accounting above (which skips index 0): a leading
+        // no-break space must not receive justifyExtra, or the line over-stretches by one
+        // gap and the last word is pushed past the right margin (issue #2185).
+        if (wordIdx > 0 && reorderedWordsScratch[wordIdx] == " " && reorderedContinuesScratch[wordIdx] &&
             effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
           advance += reorderedJustifyExtra;
         }
         xpos += advance;
       } else if (wordIdx + 1 < reorderedWidthsScratch.size()) {
-        int gap = renderer.getSpaceAdvance(fontId, lastCodepoint(reorderedWordsScratch[wordIdx]),
-                                           firstCodepoint(reorderedWordsScratch[wordIdx + 1]),
-                                           reorderedStylesScratch[wordIdx]);
+        const bool nextNoSpace = reorderedNoSpaceBeforeScratch[wordIdx + 1];
+        int gap = nextNoSpace ? 0
+                              : renderer.getSpaceAdvance(fontId, lastCodepoint(reorderedWordsScratch[wordIdx]),
+                                                         firstCodepoint(reorderedWordsScratch[wordIdx + 1]),
+                                                         reorderedStylesScratch[wordIdx]);
         if (effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
           gap += reorderedJustifyExtra;
         }
@@ -839,18 +1051,23 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
           // Cross-boundary kerning for continuation words
           int advance = renderer.getKerning(fontId, lastCodepoint(lineWords[wordIdx]),
                                             firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
-          if (lineWords[wordIdx] == " " && continuesVec[lastBreakAt + wordIdx] &&
+          // wordIdx > 0: see the LTR branch — a leading no-break space is not a justifiable gap.
+          if (wordIdx > 0 && lineWords[wordIdx] == " " && continuesVec[lastBreakAt + wordIdx] &&
               effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
             advance += justifyExtra;
           }
           xpos -= advance;
         } else {
           int gap = 0;
+          bool nextNoSpace = false;
           if (wordIdx + 1 < lineWordCount) {
-            gap = renderer.getSpaceAdvance(fontId, lastCodepoint(lineWords[wordIdx]),
-                                           firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
+            nextNoSpace = noSpaceBeforeVec[lastBreakAt + wordIdx + 1];
+            gap = nextNoSpace
+                      ? 0
+                      : renderer.getSpaceAdvance(fontId, lastCodepoint(lineWords[wordIdx]),
+                                                 firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
           }
-          if (effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
+          if (wordIdx + 1 < lineWordCount && effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
             gap += justifyExtra;
           }
           xpos -= gap;
@@ -873,18 +1090,25 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
           int advance = wordWidths[lastBreakAt + wordIdx];
           advance += renderer.getKerning(fontId, lastCodepoint(lineWords[wordIdx]),
                                          firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
-          if (lineWords[wordIdx] == " " && continuesVec[lastBreakAt + wordIdx] &&
+          // wordIdx > 0 mirrors the gap accounting above (which skips index 0): a leading
+          // no-break space must not receive justifyExtra, or the line over-stretches by one
+          // gap and the last word is pushed past the right margin (issue #2185).
+          if (wordIdx > 0 && lineWords[wordIdx] == " " && continuesVec[lastBreakAt + wordIdx] &&
               effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
             advance += justifyExtra;
           }
           xpos += advance;
         } else {
           int gap = 0;
+          bool nextNoSpace = false;
           if (wordIdx + 1 < lineWordCount) {
-            gap = renderer.getSpaceAdvance(fontId, lastCodepoint(lineWords[wordIdx]),
-                                           firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
+            nextNoSpace = noSpaceBeforeVec[lastBreakAt + wordIdx + 1];
+            gap = nextNoSpace
+                      ? 0
+                      : renderer.getSpaceAdvance(fontId, lastCodepoint(lineWords[wordIdx]),
+                                                 firstCodepoint(lineWords[wordIdx + 1]), lineWordStyles[wordIdx]);
           }
-          if (effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
+          if (wordIdx + 1 < lineWordCount && effectiveAlignment == CssTextAlign::Justify && !isLastLine) {
             gap += justifyExtra;
           }
           xpos += wordWidths[lastBreakAt + wordIdx] + gap;

lib/Epub/Epub/ParsedText.h

@@ -15,7 +15,8 @@ class GfxRenderer;
 class ParsedText {
   std::vector<std::string> words;
   std::vector<EpdFontFamily::Style> wordStyles;
-  std::vector<bool> wordContinues;      // true = word attaches to previous (no space before it)
+  std::vector<bool> wordContinues;      // true = word attaches to previous with no break
+  std::vector<bool> wordNoSpaceBefore;  // true = may break before token, but no synthetic space when joined
   std::vector<bool> wordIsFocusSuffix;  // true = token is the regular tail of a focus bold-prefix split
   BlockStyle blockStyle;
   bool extraParagraphSpacing;
@@ -27,18 +28,22 @@ class ParsedText {
   std::vector<EpdFontFamily::Style> reorderedStylesScratch;
   std::vector<uint16_t> reorderedWidthsScratch;
   std::vector<bool> reorderedContinuesScratch;
+  std::vector<bool> reorderedNoSpaceBeforeScratch;
   std::vector<bool> reorderedFocusSuffixScratch;
   std::vector<uint16_t> visualOrderScratch;
 
   int resolveFirstLineIndent(bool isFirstLine, const GfxRenderer& renderer, int fontId) const;
   std::vector<size_t> computeLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth,
-                                        std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec);
+                                        std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec,
+                                        std::vector<bool>& noSpaceBeforeVec);
   std::vector<size_t> computeHyphenatedLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth,
-                                                  std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec);
+                                                  std::vector<uint16_t>& wordWidths, std::vector<bool>& continuesVec,
+                                                  std::vector<bool>& noSpaceBeforeVec);
   bool hyphenateWordAtIndex(size_t wordIndex, int availableWidth, const GfxRenderer& renderer, int fontId,
                             std::vector<uint16_t>& wordWidths, bool allowFallbackBreaks);
   void extractLine(size_t breakIndex, int pageWidth, const std::vector<uint16_t>& wordWidths,
-                   const std::vector<bool>& continuesVec, const std::vector<size_t>& lineBreakIndices,
+                   const std::vector<bool>& continuesVec, const std::vector<bool>& noSpaceBeforeVec,
+                   const std::vector<size_t>& lineBreakIndices,
                    const std::function<void(std::shared_ptr<TextBlock>)>& processLine, const GfxRenderer& renderer,
                    int fontId);
   std::vector<uint16_t> calculateWordWidths(const GfxRenderer& renderer, int fontId);

lib/Epub/Epub/Section.cpp

@@ -10,7 +10,8 @@
 #include "parsers/ChapterHtmlSlimParser.h"
 
 namespace {
-constexpr uint8_t SECTION_FILE_VERSION = 26;
+// v27: words NFC-composed at layout time; bump invalidates NFD section caches.
+constexpr uint8_t SECTION_FILE_VERSION = 27;
 constexpr uint32_t HEADER_SIZE = sizeof(uint8_t) + sizeof(int) + sizeof(float) + sizeof(bool) + sizeof(uint8_t) +
                                  sizeof(uint16_t) + sizeof(uint16_t) + sizeof(uint16_t) + sizeof(bool) + sizeof(bool) +
                                  sizeof(uint8_t) + sizeof(bool) + sizeof(uint32_t) + sizeof(uint32_t) +

lib/Epub/Epub/htmlEntities.cpp

@@ -13,54 +13,57 @@ struct EntityPair {
 
 // Sorted lexicographically by key to allow binary search.
 static constexpr EntityPair ENTITY_LOOKUP[] = {
-    {"Æ", "Æ"},    {"Á", "Á"},     {"Â", "Â"},      {"À", "À"},   {"Α", "Α"},
-    {"Å", "Å"},    {"Ã", "Ã"},     {"Ä", "Ä"},       {"Β", "Β"},     {"Ç", "Ç"},
-    {"Χ", "Χ"},      {"‡", "‡"},     {"Δ", "Δ"},      {"Ð", "Ð"},      {"É", "É"},
-    {"Ê", "Ê"},    {"È", "È"},     {"Ε", "Ε"},    {"Η", "Η"},      {"Ë", "Ë"},
-    {"Γ", "Γ"},    {"Í", "Í"},     {"Î", "Î"},      {"Ì", "Ì"},   {"Ι", "Ι"},
-    {"Ï", "Ï"},     {"Κ", "Κ"},      {"Λ", "Λ"},     {"Μ", "Μ"},       {"Ñ", "Ñ"},
-    {"Ν", "Ν"},       {"Œ", "Œ"},      {"Ó", "Ó"},     {"Ô", "Ô"},    {"Ò", "Ò"},
-    {"Ω", "Ω"},    {"Ο", "Ο"},    {"Ø", "Ø"},     {"Õ", "Õ"},   {"Ö", "Ö"},
-    {"Φ", "Φ"},      {"Π", "Π"},         {"″", "″"},      {"Ψ", "Ψ"},      {"Ρ", "Ρ"},
-    {"Š", "Š"},   {"Σ", "Σ"},      {"Þ", "Þ"},      {"Τ", "Τ"},      {"Θ", "Θ"},
-    {"Ú", "Ú"},   {"Û", "Û"},      {"Ù", "Ù"},     {"Υ", "Υ"},  {"Ü", "Ü"},
-    {"Ξ", "Ξ"},       {"Ý", "Ý"},     {"Ÿ", "Ÿ"},       {"Ζ", "Ζ"},     {"á", "á"},
-    {"â", "â"},    {"´", "´"},      {"æ", "æ"},      {"à", "à"},   {"α", "α"},
-    {"&", "&"},      {"∧", "∧"},        {"∠", "∠"},        {"å", "å"},    {"≈", "≈"},
-    {"ã", "ã"},   {"ä", "ä"},       {"„", "„"},      {"β", "β"},     {"¦", "¦"},
-    {"•", "•"},     {"∩", "∩"},        {"ç", "ç"},     {"¸", "¸"},    {"¢", "¢"},
-    {"χ", "χ"},      {"ˆ", "ˆ"},       {"♣", "♣"},      {"≅", "≅"},     {"©", "©"},
-    {"↵", "↵"},    {"∪", "∪"},        {"¤", "¤"},     {"†", "†"},   {"↓", "↓"},
-    {"°", "°"},      {"δ", "δ"},      {"♦", "♦"},      {"÷", "÷"},   {"é", "é"},
-    {"ê", "ê"},    {"è", "è"},     {"∅", "∅"},      {" ", " "},     {" ", " "},
-    {"ε", "ε"},  {"≡", "≡"},      {"η", "η"},        {"ð", "ð"},      {"ë", "ë"},
-    {"€", "€"},     {"∃", "∃"},      {"ƒ", "ƒ"},       {"∀", "∀"},   {"½", "½"},
-    {"¼", "¼"},   {"¾", "¾"},     {"⁄", "⁄"},      {"γ", "γ"},    {"≥", "≥"},
-    {">", ">"},       {"↔", "↔"},       {"♥", "♥"},     {"…", "…"},   {"í", "í"},
-    {"î", "î"},    {"¡", "¡"},      {"ì", "ì"},     {"∞", "∞"},    {"∫", "∫"},
-    {"ι", "ι"},     {"¿", "¿"},     {"∈", "∈"},       {"ï", "ï"},     {"κ", "κ"},
-    {"λ", "λ"},   {"«", "«"},      {"←", "←"},       {"⌈", "⌈"},    {"“", "\u201C"},
-    {"≤", "≤"},       {"⌊", "⌊"},     {"∗", "∗"},     {"◊", "◊"},      {"‎", "\u200E"},
-    {"&lsaquo;", "‹"},   {"&lsquo;", "\u2018"}, {"&lt;", "<"},         {"&macr;", "¯"},     {"&mdash;", "—"},
-    {"&micro;", "µ"},    {"&minus;", "−"},      {"&mu;", "μ"},         {"&nabla;", "∇"},    {"&nbsp;", "\xC2\xA0"},
-    {"&ndash;", "–"},    {"&ne;", "≠"},         {"&ni;", "∋"},         {"&not;", "¬"},      {"&notin;", "∉"},
-    {"&nsub;", "⊄"},     {"&ntilde;", "ñ"},     {"&nu;", "ν"},         {"&oacute;", "ó"},   {"&ocirc;", "ô"},
-    {"&oelig;", "œ"},    {"&ograve;", "ò"},     {"&oline;", "‾"},      {"&omega;", "ω"},    {"&omicron;", "ο"},
-    {"&oplus;", "⊕"},    {"&or;", "∨"},         {"&ordf;", "ª"},       {"&ordm;", "º"},     {"&oslash;", "ø"},
-    {"&otilde;", "õ"},   {"&otimes;", "⊗"},     {"&ouml;", "ö"},       {"&para;", "¶"},     {"&part;", "∂"},
-    {"&permil;", "‰"},   {"&perp;", "⊥"},       {"&phi;", "φ"},        {"&pi;", "π"},       {"&piv;", "ϖ"},
-    {"&plusmn;", "±"},   {"&pound;", "£"},      {"&prime;", "′"},      {"&prod;", "∏"},     {"&prop;", "∝"},
-    {"&psi;", "ψ"},      {"&quot;", "\""},      {"&radic;", "√"},      {"&raquo;", "»"},    {"&rarr;", "→"},
-    {"&rceil;", "⌉"},    {"&rdquo;", "\u201D"}, {"&reg;", "®"},        {"&rfloor;", "⌋"},   {"&rho;", "ρ"},
-    {"&rlm;", "\u200F"}, {"&rsaquo;", "›"},     {"&rsquo;", "\u2019"}, {"&sbquo;", "‚"},    {"&scaron;", "š"},
-    {"&sdot;", "⋅"},     {"&sect;", "§"},       {"&shy;", "\xC2\xAD"}, {"&sigma;", "σ"},    {"&sigmaf;", "ς"},
-    {"&sim;", "∼"},      {"&spades;", "♠"},     {"&sub;", "⊂"},        {"&sube;", "⊆"},     {"&sum;", "∑"},
-    {"&sup1;", "¹"},     {"&sup2;", "²"},       {"&sup3;", "³"},       {"&sup;", "⊃"},      {"&supe;", "⊇"},
-    {"&szlig;", "ß"},    {"&tau;", "τ"},        {"&there4;", "∴"},     {"&theta;", "θ"},    {"&thetasym;", "ϑ"},
-    {"&thinsp;", " "},   {"&thorn;", "þ"},      {"&tilde;", "˜"},      {"&times;", "×"},    {"&trade;", "™"},
-    {"&uacute;", "ú"},   {"&uarr;", "↑"},       {"&ucirc;", "û"},      {"&ugrave;", "ù"},   {"&uml;", "¨"},
-    {"&upsih;", "ϒ"},    {"&upsilon;", "υ"},    {"&uuml;", "ü"},       {"&xi;", "ξ"},       {"&yacute;", "ý"},
-    {"&yen;", "¥"},      {"&yuml;", "ÿ"},       {"&zeta;", "ζ"},       {"&zwj;", "\u200D"}, {"&zwnj;", "\u200C"},
+    {"&AElig;", "Æ"},      {"&Aacute;", "Á"},      {"&Acirc;", "Â"},      {"&Agrave;", "À"},  {"&Alpha;", "Α"},
+    {"&Aring;", "Å"},      {"&Atilde;", "Ã"},      {"&Auml;", "Ä"},       {"&Beta;", "Β"},    {"&Ccedil;", "Ç"},
+    {"&Chi;", "Χ"},        {"&Dagger;", "‡"},      {"&Delta;", "Δ"},      {"&ETH;", "Ð"},     {"&Eacute;", "É"},
+    {"&Ecirc;", "Ê"},      {"&Egrave;", "È"},      {"&Epsilon;", "Ε"},    {"&Eta;", "Η"},     {"&Euml;", "Ë"},
+    {"&Gamma;", "Γ"},      {"&Iacute;", "Í"},      {"&Icirc;", "Î"},      {"&Igrave;", "Ì"},  {"&Iota;", "Ι"},
+    {"&Iuml;", "Ï"},       {"&Kappa;", "Κ"},       {"&Lambda;", "Λ"},     {"&Mu;", "Μ"},      {"&Ntilde;", "Ñ"},
+    {"&Nu;", "Ν"},         {"&OElig;", "Œ"},       {"&Oacute;", "Ó"},     {"&Ocirc;", "Ô"},   {"&Ograve;", "Ò"},
+    {"&Omega;", "Ω"},      {"&Omicron;", "Ο"},     {"&Oslash;", "Ø"},     {"&Otilde;", "Õ"},  {"&Ouml;", "Ö"},
+    {"&Phi;", "Φ"},        {"&Pi;", "Π"},          {"&Prime;", "″"},      {"&Psi;", "Ψ"},     {"&Rho;", "Ρ"},
+    {"&Scaron;", "Š"},     {"&Sigma;", "Σ"},       {"&THORN;", "Þ"},      {"&Tau;", "Τ"},     {"&Theta;", "Θ"},
+    {"&Uacute;", "Ú"},     {"&Ucirc;", "Û"},       {"&Ugrave;", "Ù"},     {"&Upsilon;", "Υ"}, {"&Uuml;", "Ü"},
+    {"&Xi;", "Ξ"},         {"&Yacute;", "Ý"},      {"&Yuml;", "Ÿ"},       {"&Zeta;", "Ζ"},    {"&aacute;", "á"},
+    {"&acirc;", "â"},      {"&acute;", "´"},       {"&aelig;", "æ"},      {"&agrave;", "à"},  {"&alefsym;", "ℵ"},
+    {"&alpha;", "α"},      {"&amp;", "&"},         {"&and;", "∧"},        {"&ang;", "∠"},     {"&aring;", "å"},
+    {"&asymp;", "≈"},      {"&atilde;", "ã"},      {"&auml;", "ä"},       {"&bdquo;", "„"},   {"&beta;", "β"},
+    {"&brvbar;", "¦"},     {"&bull;", "•"},        {"&cap;", "∩"},        {"&ccedil;", "ç"},  {"&cedil;", "¸"},
+    {"&cent;", "¢"},       {"&chi;", "χ"},         {"&circ;", "ˆ"},       {"&clubs;", "♣"},   {"&cong;", "≅"},
+    {"&copy;", "©"},       {"&crarr;", "↵"},       {"&cup;", "∪"},        {"&curren;", "¤"},  {"&dArr;", "⇓"},
+    {"&dagger;", "†"},     {"&darr;", "↓"},        {"&deg;", "°"},        {"&delta;", "δ"},   {"&diams;", "♦"},
+    {"&divide;", "÷"},     {"&eacute;", "é"},      {"&ecirc;", "ê"},      {"&egrave;", "è"},  {"&empty;", "∅"},
+    {"&emsp;", " "},       {"&ensp;", " "},        {"&epsilon;", "ε"},    {"&equiv;", "≡"},   {"&eta;", "η"},
+    {"&eth;", "ð"},        {"&euml;", "ë"},        {"&euro;", "€"},       {"&exist;", "∃"},   {"&fnof;", "ƒ"},
+    {"&forall;", "∀"},     {"&frac12;", "½"},      {"&frac14;", "¼"},     {"&frac34;", "¾"},  {"&frasl;", "⁄"},
+    {"&gamma;", "γ"},      {"&ge;", "≥"},          {"&gt;", ">"},         {"&hArr;", "⇔"},    {"&harr;", "↔"},
+    {"&hearts;", "♥"},     {"&hellip;", "…"},      {"&iacute;", "í"},     {"&icirc;", "î"},   {"&iexcl;", "¡"},
+    {"&igrave;", "ì"},     {"&image;", "ℑ"},       {"&infin;", "∞"},      {"&int;", "∫"},     {"&iota;", "ι"},
+    {"&iquest;", "¿"},     {"&isin;", "∈"},        {"&iuml;", "ï"},       {"&kappa;", "κ"},   {"&lArr;", "⇐"},
+    {"&lambda;", "λ"},     {"&lang;", "〈"},       {"&laquo;", "«"},      {"&larr;", "←"},    {"&lceil;", "⌈"},
+    {"&ldquo;", "\u201C"}, {"&le;", "≤"},          {"&lfloor;", "⌊"},     {"&lowast;", "∗"},  {"&loz;", "◊"},
+    {"&lrm;", "\u200E"},   {"&lsaquo;", "‹"},      {"&lsquo;", "\u2018"}, {"&lt;", "<"},      {"&macr;", "¯"},
+    {"&mdash;", "—"},      {"&micro;", "µ"},       {"&middot;", "·"},     {"&minus;", "−"},   {"&mu;", "μ"},
+    {"&nabla;", "∇"},      {"&nbsp;", "\xC2\xA0"}, {"&ndash;", "–"},      {"&ne;", "≠"},      {"&ni;", "∋"},
+    {"&not;", "¬"},        {"&notin;", "∉"},       {"&nsub;", "⊄"},       {"&ntilde;", "ñ"},  {"&nu;", "ν"},
+    {"&oacute;", "ó"},     {"&ocirc;", "ô"},       {"&oelig;", "œ"},      {"&ograve;", "ò"},  {"&oline;", "‾"},
+    {"&omega;", "ω"},      {"&omicron;", "ο"},     {"&oplus;", "⊕"},      {"&or;", "∨"},      {"&ordf;", "ª"},
+    {"&ordm;", "º"},       {"&oslash;", "ø"},      {"&otilde;", "õ"},     {"&otimes;", "⊗"},  {"&ouml;", "ö"},
+    {"&para;", "¶"},       {"&part;", "∂"},        {"&permil;", "‰"},     {"&perp;", "⊥"},    {"&phi;", "φ"},
+    {"&pi;", "π"},         {"&piv;", "ϖ"},         {"&plusmn;", "±"},     {"&pound;", "£"},   {"&prime;", "′"},
+    {"&prod;", "∏"},       {"&prop;", "∝"},        {"&psi;", "ψ"},        {"&quot;", "\""},   {"&rArr;", "⇒"},
+    {"&radic;", "√"},      {"&rang;", "〉"},       {"&raquo;", "»"},      {"&rarr;", "→"},    {"&rceil;", "⌉"},
+    {"&rdquo;", "\u201D"}, {"&real;", "\u211C"},   {"&reg;", "®"},        {"&rfloor;", "⌋"},  {"&rho;", "ρ"},
+    {"&rlm;", "\u200F"},   {"&rsaquo;", "›"},      {"&rsquo;", "\u2019"}, {"&sbquo;", "‚"},   {"&scaron;", "š"},
+    {"&sdot;", "⋅"},       {"&sect;", "§"},        {"&shy;", "\xC2\xAD"}, {"&sigma;", "σ"},   {"&sigmaf;", "ς"},
+    {"&sim;", "∼"},        {"&spades;", "♠"},      {"&sub;", "⊂"},        {"&sube;", "⊆"},    {"&sum;", "∑"},
+    {"&sup1;", "¹"},       {"&sup2;", "²"},        {"&sup3;", "³"},       {"&sup;", "⊃"},     {"&supe;", "⊇"},
+    {"&szlig;", "ß"},      {"&tau;", "τ"},         {"&there4;", "∴"},     {"&theta;", "θ"},   {"&thetasym;", "ϑ"},
+    {"&thinsp;", " "},     {"&thorn;", "þ"},       {"&tilde;", "˜"},      {"&times;", "×"},   {"&trade;", "™"},
+    {"&uArr;", "⇑"},       {"&uacute;", "ú"},      {"&uarr;", "↑"},       {"&ucirc;", "û"},   {"&ugrave;", "ù"},
+    {"&uml;", "¨"},        {"&upsih;", "ϒ"},       {"&upsilon;", "υ"},    {"&uuml;", "ü"},    {"&weierp;", "℘"},
+    {"&xi;", "ξ"},         {"&yacute;", "ý"},      {"&yen;", "¥"},        {"&yuml;", "ÿ"},    {"&zeta;", "ζ"},
+    {"&zwj;", "\u200D"},   {"&zwnj;", "\u200C"},
 };
 
 // Verify the table is sorted at compile time.

lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp

@@ -317,6 +317,14 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
         const bool isTocAnchor =
             std::find(self->tocAnchors.begin(), self->tocAnchors.end(), idValue) != self->tocAnchors.end();
         if (isTocAnchor || (!isNonNavigableInlineElement(name) && self->anchorData.size() < MAX_ANCHORS_PER_CHAPTER)) {
+          // Flush a displaced anchor before overwriting. Consecutive non-block elements
+          // (e.g. <aside id="fn1">text</aside><aside id="fn2">) with no intervening block
+          // never trigger startNewTextBlock, so fn1 gets silently overwritten. That leaves
+          // fn1 missing from the anchor map -> getPageForAnchor returns nullopt -> reader
+          // lands at page 0 (section start) instead of the footnote.
+          if (!self->pendingAnchorId.empty()) {
+            self->flushPendingAnchor();
+          }
           self->pendingAnchorId = idValue;
         }
       } else if (strcmp(atts[i], "dir") == 0) {