From 3319aa1720224cd197905294c63f0c7f3d8eae3b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ph=E1=BA=A1m=20B=C3=ACnh=20An?=
 <111893501+brianhuster@users.noreply.github.com>
Date: Mon, 20 Jul 2026 19:02:08 +0700
Subject: [PATCH] fix(epub): preserve word continuation when splitting CJK text
 on MAX_WORD_SIZE (#2652)

---
 lib/Epub/Epub/Section.cpp                       | 2 +-
 lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/Epub/Epub/Section.cpp b/lib/Epub/Epub/Section.cpp
index 56daeed0..10d2b4f3 100644
--- a/lib/Epub/Epub/Section.cpp
+++ b/lib/Epub/Epub/Section.cpp
@@ -17,7 +17,7 @@ namespace {
 // v30: Arabic shaping changed both drawing and measurement (getTextAdvanceX now
 //      measures the shaped visual text); cached word positions from v29 no longer
 //      match what drawText renders.
-constexpr uint8_t SECTION_FILE_VERSION = 30;
+constexpr uint8_t SECTION_FILE_VERSION = 31;
 // Written into the version field while a build is in progress; patched to
 // SECTION_FILE_VERSION only when the build is finalized. An abandoned /
 // crash-interrupted .bin therefore carries version 0, which loadSectionFile rejects
diff --git a/lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp b/lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
index 2ec1d2c2..a686b366 100644
--- a/lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
+++ b/lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
@@ -1154,12 +1154,14 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
         }
         self->partWordBufferIndex = safeLen;
         self->flushPartWordBuffer();
+        self->nextWordContinues = true;
         for (int j = 0; j < overflow; j++) {
           self->partWordBuffer[j] = saved[j];
         }
         self->partWordBufferIndex = overflow;
       } else {
         self->flushPartWordBuffer();
+        self->nextWordContinues = true;
       }
     }