fix(epub): NFC-normalize EPUB text so NFD diacritics render correctly (#2277)

Co-authored-by: Uri Tauber <uritaube@gmail.com>
Co-authored-by: Julia <julia@uxj.io>

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/ParsedText.cpp

@@ -254,6 +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);

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) +