feat: Support for Korean line breaks and glyph spacing (#2288)

Co-authored-by: Uri Tauber <uritaube@gmail.com>

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 +15,40 @@ 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;
+
+  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/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;
@@ -132,12 +261,54 @@ 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 +337,19 @@ 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 +371,7 @@ 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 +384,14 @@ 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 +419,8 @@ 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 +432,8 @@ 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 +502,16 @@ 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 +520,7 @@ 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 +537,8 @@ 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 +577,9 @@ 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 +654,8 @@ 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 +673,9 @@ 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 +805,7 @@ 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 +815,8 @@ 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 +849,11 @@ 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 +882,8 @@ 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 +902,13 @@ 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 +935,7 @@ 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 +943,11 @@ 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 +963,9 @@ 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)
@@ -805,9 +1004,11 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
         }
         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;
         }
@@ -846,11 +1047,15 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
           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;
@@ -880,11 +1085,15 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
           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/GfxRenderer/GfxRenderer.cpp

@@ -1437,8 +1437,18 @@ int GfxRenderer::getTextAdvanceX(const int fontId, const char* text, EpdFontFami
     int32_t widthFP = 0;
     const bool isSupSub = (style & (EpdFontFamily::SUP | EpdFontFamily::SUB)) != 0;
     const uint8_t styleIdx = resolveSdCardStyle(*sdIt->second, style);
+    const auto fontIt = fontMap.find(fontId);
+    if (fontIt == fontMap.end()) {
+      LOG_ERR("GFX", "Font %d not found", fontId);
+      return 0;
+    }
+    const auto& font = fontIt->second;
     while (uint32_t cp = utf8NextCodepoint(reinterpret_cast<const uint8_t**>(&text))) {
       int32_t advFP = sdIt->second->getAdvance(cp, styleIdx);
+      if (advFP == 0 && !utf8IsCombiningMark(cp)) {
+        const EpdGlyph* glyph = font.getGlyph(cp, style);
+        advFP = glyph ? glyph->advanceX : 0;
+      }
       widthFP += isSupSub ? (advFP + 1) / 2 : advFP;
     }
     return fp4::toPixel(widthFP);

lib/Utf8/Utf8.h

@@ -21,12 +21,15 @@ int utf8SafeTruncateBuffer(const char* buf, int len);
 // Covers CJK Unified Ideographs, Hiragana, Katakana, Hangul Syllables, CJK punctuation,
 // and fullwidth forms — the ranges where word boundaries are implicit per character.
 inline bool utf8IsCjkBreakable(const uint32_t cp) {
-  return (cp >= 0x3000 && cp <= 0x303F)        // CJK Symbols and Punctuation
+  return (cp >= 0x1100 && cp <= 0x11FF)        // Hangul Jamo
+         || (cp >= 0x3000 && cp <= 0x303F)     // CJK Symbols and Punctuation
          || (cp >= 0x3040 && cp <= 0x309F)     // Hiragana
          || (cp >= 0x30A0 && cp <= 0x30FF)     // Katakana
+         || (cp >= 0x3130 && cp <= 0x318F)     // Hangul Compatibility Jamo
          || (cp >= 0x3400 && cp <= 0x4DBF)     // CJK Extension A
          || (cp >= 0x4E00 && cp <= 0x9FFF)     // CJK Unified Ideographs
          || (cp >= 0xAC00 && cp <= 0xD7AF)     // Hangul Syllables
+         || (cp >= 0xD7B0 && cp <= 0xD7FF)     // Hangul Jamo Extended-B
          || (cp >= 0xF900 && cp <= 0xFAFF)     // CJK Compatibility Ideographs
          || (cp >= 0xFE30 && cp <= 0xFE4F)     // CJK Compatibility Forms
          || (cp >= 0xFF01 && cp <= 0xFF60)     // Fullwidth Latin / Punctuation

lib/ZipFile/ZipFile.cpp

@@ -397,37 +397,34 @@ uint8_t* ZipFile::readFileToMemory(const char* filename, size_t* size, const boo
 
     // Continue out of block with data set
   } else if (fileStat.method == ZIP_METHOD_DEFLATED) {
-    // Read out deflated content from file
-    const auto deflatedData = static_cast<uint8_t*>(malloc(deflatedDataSize));
-    if (deflatedData == nullptr) {
-      LOG_ERR("ZIP", "Failed to allocate memory for decompression buffer");
+    auto* fileReadBuffer = static_cast<uint8_t*>(malloc(1024));
+    if (!fileReadBuffer) {
+      LOG_ERR("ZIP", "Failed to allocate memory for zip file read buffer");
       free(data);
       return nullptr;
     }
 
-    const size_t dataRead = file.read(deflatedData, deflatedDataSize);
+    ZipInflateCtx ctx;
+    ctx.file = &file;
+    ctx.fileRemaining = deflatedDataSize;
+    ctx.readBuf = fileReadBuffer;
+    ctx.readBufSize = 1024;
 
-    if (dataRead != deflatedDataSize) {
-      LOG_ERR("ZIP", "Failed to read data, expected %d got %d", deflatedDataSize, dataRead);
-      free(deflatedData);
+    if (!ctx.reader.init(true)) {
+      LOG_ERR("ZIP", "Failed to init inflate reader");
+      free(fileReadBuffer);
       free(data);
       return nullptr;
     }
+    ctx.reader.setReadCallback(zipReadCallback);
 
-    bool success = false;
-    {
-      InflateReader r;
-      r.init(false);
-      r.setSource(deflatedData, deflatedDataSize);
-      success = r.read(data, inflatedDataSize);
-    }
-    free(deflatedData);
-
-    if (!success) {
+    if (!ctx.reader.read(data, inflatedDataSize)) {
       LOG_ERR("ZIP", "Failed to inflate file");
+      free(fileReadBuffer);
       free(data);
       return nullptr;
     }
+    free(fileReadBuffer);
 
     // Continue out of block with data set
   } else {

src/SdCardFontSystem.cpp

@@ -5,12 +5,16 @@
 
 #include "CrossPointSettings.h"
 
+namespace {
+
 static uint8_t fontSizeEnumFromSettings() {
   uint8_t e = SETTINGS.fontSize;
   if (e >= CrossPointSettings::FONT_SIZE_COUNT) e = 1;  // default to MEDIUM
   return e;
 }
 
+}  // namespace
+
 void SdCardFontSystem::begin(GfxRenderer& renderer) {
   registry_.discover();
 
@@ -74,10 +78,8 @@ void SdCardFontSystem::ensureLoaded(GfxRenderer& renderer) {
       SETTINGS.sdFontFamilyName[0] = '\0';
       return;
     }
-    auto sizes = family->availableSizes();
-    uint8_t idx = sizeEnum;
-    if (idx >= sizes.size()) idx = sizes.size() - 1;
-    uint8_t wantedPt = sizes.empty() ? 0 : sizes[idx];
+    const auto* selected = family->findClosestReaderSize(sizeEnum);
+    const uint8_t wantedPt = selected ? selected->pointSize : 0;
     if (!registryWasDirty && wantedPt == manager_.currentPointSize()) return;
     LOG_DBG("SDFS", "Reloading %s: size %u -> %u (enum %u)%s", wantedFamily, manager_.currentPointSize(), wantedPt,
             sizeEnum, registryWasDirty ? " [registry dirty]" : "");

src/activities/ActivityManager.cpp

@@ -1,5 +1,6 @@
 #include "ActivityManager.h"
 
+#include <FontCacheManager.h>
 #include <HalPowerManager.h>
 
 #include <algorithm>

src/activities/reader/ReaderActivity.cpp

@@ -2,6 +2,7 @@
 
 #include <FsHelpers.h>
 #include <HalStorage.h>
+#include <Memory.h>
 
 #include "CrossPointSettings.h"
 #include "Epub.h"
@@ -29,7 +30,11 @@ std::unique_ptr<Epub> ReaderActivity::loadEpub(const std::string& path) {
     return nullptr;
   }
 
-  auto epub = std::unique_ptr<Epub>(new Epub(path, "/.crosspoint"));
+  auto epub = makeUniqueNoThrow<Epub>(path, "/.crosspoint");
+  if (!epub) {
+    LOG_ERR("READER", "Failed to allocate EPUB object");
+    return nullptr;
+  }
   if (epub->load(true, SETTINGS.embeddedStyle == 0)) {
     return epub;
   }
@@ -44,7 +49,11 @@ std::unique_ptr<Xtc> ReaderActivity::loadXtc(const std::string& path) {
     return nullptr;
   }
 
-  auto xtc = std::unique_ptr<Xtc>(new Xtc(path, "/.crosspoint"));
+  auto xtc = makeUniqueNoThrow<Xtc>(path, "/.crosspoint");
+  if (!xtc) {
+    LOG_ERR("READER", "Failed to allocate XTC object");
+    return nullptr;
+  }
   if (xtc->load()) {
     return xtc;
   }
@@ -59,7 +68,11 @@ std::unique_ptr<Txt> ReaderActivity::loadTxt(const std::string& path) {
     return nullptr;
   }
 
-  auto txt = std::unique_ptr<Txt>(new Txt(path, "/.crosspoint"));
+  auto txt = makeUniqueNoThrow<Txt>(path, "/.crosspoint");
+  if (!txt) {
+    LOG_ERR("READER", "Failed to allocate TXT object");
+    return nullptr;
+  }
   if (txt->load()) {
     return txt;
   }