From bf600c6eb08314a29e4b5570e292107ff3844cca Mon Sep 17 00:00:00 2001
From: Oleg Korshul <Oleg.Korshul@onlyoffice.com>
Date: Fri, 21 Jun 2019 12:54:00 +0300
Subject: [PATCH 1/3] Core/mac build (#161)

---
 Common/3dParty/boost/build.sh            |  4 +---
 Common/3dParty/boost/fetch.sh            | 20 +++-----------------
 Common/3dParty/cef/fetch.sh              | 21 ++++++++++++++++-----
 Common/3dParty/icu/fetch.sh              | 22 ++++++++++++++--------
 Common/3dParty/icu/fetch_mobile.sh       |  4 +---
 Common/3dParty/make.sh                   |  3 +--
 Common/3dParty/openssl/build.sh          |  4 +---
 Common/3dParty/openssl/fetch.sh          |  4 +---
 Common/3dParty/v8/build.sh               |  3 +--
 Common/3dParty/v8/fetch.sh               |  4 +---
 Common/3dParty/v8/fetch_linux_correct.sh |  4 +---
 11 files changed, 41 insertions(+), 52 deletions(-)

diff --git a/Common/3dParty/boost/build.sh b/Common/3dParty/boost/build.sh
index bb3b8f2248..946939c5dc 100755
--- a/Common/3dParty/boost/build.sh
+++ b/Common/3dParty/boost/build.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 os=$(uname -s)
 platform=""
diff --git a/Common/3dParty/boost/fetch.sh b/Common/3dParty/boost/fetch.sh
index 4970c3199a..7e3415af54 100755
--- a/Common/3dParty/boost/fetch.sh
+++ b/Common/3dParty/boost/fetch.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 os=$(uname -s)
 platform=""
@@ -12,21 +10,11 @@ case "$os" in
   *)        exit ;;
 esac
 
-if [[ "$platform" == *"mac"* ]]
-then
-if [[ -f "$SCRIPTPATH/7zX_1.7.1.dmg" ]]
-then
-echo "7z already downloaded"
-else
-wget http://static.updatestar.net/dl/7zX/7zX_1.7.1.dmg
-fi
-fi
-
 if [[ -f "$SCRIPTPATH/boost_1_58_0.7z" ]]
 then
 echo "boost already downloaded"
 else
-wget http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
+wget http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z || curl -O http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
 fi
 
 if [ -d "$SCRIPTPATH/boost_1_58_0" ]; then
@@ -36,8 +24,6 @@ if [[ "$platform" == *"linux"* ]]
 then
 7z x -y "$SCRIPTPATH/boost_1_58_0.7z" -o"$SCRIPTPATH/"
 else
-hdiutil mount "$SCRIPTPATH/7zX_1.7.1.dmg"
-/Volumes/7zX/7zX.app/Contents/Resources/7za x "$SCRIPTPATH/boost_1_58_0.7z" -o"$SCRIPTPATH/"
-hdiutil unmount /Volumes/7zX
+7za x "$SCRIPTPATH/boost_1_58_0.7z" -o"$SCRIPTPATH/"
 fi
 fi
diff --git a/Common/3dParty/cef/fetch.sh b/Common/3dParty/cef/fetch.sh
index 6a46be3d56..aa9f31b21b 100755
--- a/Common/3dParty/cef/fetch.sh
+++ b/Common/3dParty/cef/fetch.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 os=$(uname -s)
 platform=""
@@ -42,9 +40,10 @@ cef_version="3163"
 if [[ "$platform" == *"linux"* ]]
 then
 cef_version="3202"
-fi
-
 cef_url=http://d2ettrnqo7v976.cloudfront.net/cef/$cef_version/$platform$arch/$cef_arch
+else
+cef_url=http://d2ettrnqo7v976.cloudfront.net/cef/$cef_version/$platform/$cef_arch
+fi
 
 if [[ "$platform" == *"linux"* ]]
 then
@@ -75,3 +74,15 @@ then
   cp -r -t build/ ./$cef_binary/Release/*  ./$cef_binary/Resources/*
   chmod a+xr build/locales
 fi
+
+if [[ "$platform" == *"mac"* ]]
+then
+  if [ -d "build/Chromium Embedded Framework.framework" ]
+  then
+    echo "cef_binary already extracted"
+  else
+    wget $cef_url || curl -O $cef_url
+    7za x $cef_arch
+    mv "$cef_binary" "build/Chromium Embedded Framework.framework"
+  fi
+fi
diff --git a/Common/3dParty/icu/fetch.sh b/Common/3dParty/icu/fetch.sh
index 99ebd16ffc..613da85543 100755
--- a/Common/3dParty/icu/fetch.sh
+++ b/Common/3dParty/icu/fetch.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 ICU_MAJOR_VER=58
 ICU_MINOR_VER=2
@@ -59,11 +57,19 @@ else
   svn export http://source.icu-project.org/repos/icu/tags/release-$ICU_MAJOR_VER-$ICU_MINOR_VER/icu4c ./icu
 fi
 
-# Workaround for building icu older than 60.0
-# on systems without xlocale.h (removed from glibc since 2.26)
-# See https://sourceware.org/glibc/wiki/Release/2.26#Removal_of_.27xlocale.h.27
-# See https://bugs.archlinux.org/task/55246
-sed -i 's/xlocale/locale/' ./icu/source/i18n/digitlst.cpp
+if [[ "$platform" == *"linux"* ]]
+then
+  # Workaround for building icu older than 60.0
+  # on systems without xlocale.h (removed from glibc since 2.26)
+  # See https://sourceware.org/glibc/wiki/Release/2.26#Removal_of_.27xlocale.h.27
+  # See https://bugs.archlinux.org/task/55246
+  sed -i 's/xlocale/locale/' ./icu/source/i18n/digitlst.cpp
+fi
+
+if [[ "$platform" == *"mac"* ]]
+then
+  sed -i -e 's/cmd\, \"%s %s -o %s%s %s %s%s %s %s\"\,/cmd\, \"%s %s -o %s%s %s %s %s %s %s\"\,/' ./icu/source/tools/pkgdata/pkgdata.cpp
+fi
 
 cd ./icu/source/
 
diff --git a/Common/3dParty/icu/fetch_mobile.sh b/Common/3dParty/icu/fetch_mobile.sh
index 588d7fd118..76e12253f8 100755
--- a/Common/3dParty/icu/fetch_mobile.sh
+++ b/Common/3dParty/icu/fetch_mobile.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 ICU_MAJOR_VER=62
 ICU_MINOR_VER=1
diff --git a/Common/3dParty/make.sh b/Common/3dParty/make.sh
index 38fb02302f..f0f416d066 100755
--- a/Common/3dParty/make.sh
+++ b/Common/3dParty/make.sh
@@ -1,8 +1,7 @@
 #!/bin/bash
 set -e
 
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 cd "$SCRIPTPATH"
 
diff --git a/Common/3dParty/openssl/build.sh b/Common/3dParty/openssl/build.sh
index 8497650d69..f557707980 100755
--- a/Common/3dParty/openssl/build.sh
+++ b/Common/3dParty/openssl/build.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 cd "$SCRIPTPATH"/openssl
 
diff --git a/Common/3dParty/openssl/fetch.sh b/Common/3dParty/openssl/fetch.sh
index f31e20b980..5433582a20 100755
--- a/Common/3dParty/openssl/fetch.sh
+++ b/Common/3dParty/openssl/fetch.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 cd "$SCRIPTPATH"
 
diff --git a/Common/3dParty/v8/build.sh b/Common/3dParty/v8/build.sh
index 2885cff449..9dbd402fdc 100755
--- a/Common/3dParty/v8/build.sh
+++ b/Common/3dParty/v8/build.sh
@@ -2,8 +2,7 @@
 
 export PATH=`pwd`/depot_tools:"$PATH"
 
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 os=$(uname -s)
 platform=""
diff --git a/Common/3dParty/v8/fetch.sh b/Common/3dParty/v8/fetch.sh
index d112514eb5..36a5ac6e00 100755
--- a/Common/3dParty/v8/fetch.sh
+++ b/Common/3dParty/v8/fetch.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0" || grealpath "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 cd "$SCRIPTPATH"
 
diff --git a/Common/3dParty/v8/fetch_linux_correct.sh b/Common/3dParty/v8/fetch_linux_correct.sh
index a52e79228c..39365f9864 100755
--- a/Common/3dParty/v8/fetch_linux_correct.sh
+++ b/Common/3dParty/v8/fetch_linux_correct.sh
@@ -1,7 +1,5 @@
 #!/bin/bash
-
-SCRIPT=$(readlink -f "$0")
-SCRIPTPATH=$(dirname "$SCRIPT")
+SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 
 export PATH=`pwd`/depot_tools:"$PATH"
 

From 221436242607f5b656a77437acabe6b50f3ac5a2 Mon Sep 17 00:00:00 2001
From: Alexey Golubev <Alexey.Golubev@onlyoffice.com>
Date: Mon, 24 Jun 2019 14:51:39 +0300
Subject: [PATCH 2/3] Fix boost download error

---
 Common/3dParty/boost/fetch.bat | 2 +-
 Common/3dParty/boost/fetch.sh  | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/Common/3dParty/boost/fetch.bat b/Common/3dParty/boost/fetch.bat
index 1bab4c0925..607fc23a73 100644
--- a/Common/3dParty/boost/fetch.bat
+++ b/Common/3dParty/boost/fetch.bat
@@ -4,7 +4,7 @@ CD /D %~dp0
 if exist "%SCRIPTPATH%boost_1_58_0.7z" (
     echo "boost already downloaded"
 ) else (
-    Powershell.exe Invoke-WebRequest -OutFile boost_1_58_0.7z http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
+    Powershell.exe Invoke-WebRequest -OutFile boost_1_58_0.7z https://downloads.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
 )
 
 SET UNSIP_PROGRAMM="C:\Program Files\7-Zip\7z.exe"
diff --git a/Common/3dParty/boost/fetch.sh b/Common/3dParty/boost/fetch.sh
index 7e3415af54..0cf8ea457e 100755
--- a/Common/3dParty/boost/fetch.sh
+++ b/Common/3dParty/boost/fetch.sh
@@ -1,5 +1,6 @@
 #!/bin/bash
 SCRIPTPATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+BOOST_URL=https://downloads.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
 
 os=$(uname -s)
 platform=""
@@ -14,7 +15,7 @@ if [[ -f "$SCRIPTPATH/boost_1_58_0.7z" ]]
 then
 echo "boost already downloaded"
 else
-wget http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z || curl -O http://freefr.dl.sourceforge.net/project/boost/boost/1.58.0/boost_1_58_0.7z
+wget $BOOST_URL || curl -O $BOOST_URL
 fi
 
 if [ -d "$SCRIPTPATH/boost_1_58_0" ]; then

From c9330ee0f12b1745357d8cffb53d184a15aba1ca Mon Sep 17 00:00:00 2001
From: Sergey Konovalov <Sergey.Konovalov@onlyoffice.com>
Date: Mon, 24 Jun 2019 14:56:02 +0300
Subject: [PATCH 3/3] Feature/bug 41890 (#164)

* [x2t] Decode xlsx escaped chars

* [x2t] Fix bug #41890, #36575. Add CStringBuilder::WriteEncodeXmlStringHHHH
---
 .../Source/XlsxFormat/SharedStrings/Text.h    |  20 +-
 DesktopEditor/common/File.cpp                 | 247 ++++++++++++++++++
 DesktopEditor/common/File.h                   |  11 +-
 DesktopEditor/common/StringBuilder.cpp        | 116 ++++++++
 DesktopEditor/common/StringBuilder.h          |   7 +-
 5 files changed, 396 insertions(+), 5 deletions(-)

diff --git a/Common/DocxFormat/Source/XlsxFormat/SharedStrings/Text.h b/Common/DocxFormat/Source/XlsxFormat/SharedStrings/Text.h
index af318bea6b..f6e1761451 100644
--- a/Common/DocxFormat/Source/XlsxFormat/SharedStrings/Text.h
+++ b/Common/DocxFormat/Source/XlsxFormat/SharedStrings/Text.h
@@ -61,7 +61,7 @@ namespace OOX
 				if(std::wstring::npos != m_sText.find(' ') || std::wstring::npos != m_sText.find('\n'))
 					writer.WriteString(_T(" xml:space=\"preserve\""));
 				writer.WriteString(_T(">"));
-				writer.WriteEncodeXmlString(m_sText);
+				writer.WriteEncodeXmlStringHHHH(m_sText);
 				writer.WriteString(_T("</t>"));
 			}
 			virtual void toXML2(NSStringUtils::CStringBuilder& writer, const wchar_t* name) const
@@ -71,7 +71,7 @@ namespace OOX
 				if(std::wstring::npos != m_sText.find(' ') || std::wstring::npos != m_sText.find('\n'))
 					writer.WriteString(_T(" xml:space=\"preserve\""));
 				writer.WriteString(_T(">"));
-				writer.WriteEncodeXmlString(m_sText);
+				writer.WriteEncodeXmlStringHHHH(m_sText);
 				writer.WriteString(_T("</"));
 				writer.WriteString(name);
 				writer.WriteString(_T(">"));
@@ -83,7 +83,21 @@ namespace OOX
 				if ( oReader.IsEmptyNode() )
 					return;
 
-				m_sText = oReader.GetText3();
+				int nDepth = oReader.GetDepth();
+				XmlUtils::XmlNodeType eNodeType = XmlUtils::XmlNodeType_EndElement;
+				while (oReader.Read(eNodeType) && oReader.GetDepth() >= nDepth && XmlUtils::XmlNodeType_EndElement != eNodeType)
+				{
+					if (eNodeType == XmlUtils::XmlNodeType_Text || eNodeType == XmlUtils::XmlNodeType_Whitespace || eNodeType == XmlUtils::XmlNodeType_SIGNIFICANT_WHITESPACE)
+					{
+						std::string sTemp = oReader.GetTextA();
+						wchar_t* pUnicodes = NULL;
+						LONG lOutputCount = 0;
+						NSFile::CUtf8Converter::GetUnicodeStringFromUTF8WithHHHH((BYTE*)sTemp.c_str(), sTemp.length(), pUnicodes, lOutputCount);
+						m_sText.append(pUnicodes);
+						RELEASEARRAYOBJECTS(pUnicodes);
+					}
+				}
+
 				NSStringExt::Replace(m_sText, L"\t", L"");
 				if(!(m_oSpace.IsInit() && SimpleTypes::xmlspacePreserve == m_oSpace->GetValue()))
 				{
diff --git a/DesktopEditor/common/File.cpp b/DesktopEditor/common/File.cpp
index 7aa6745498..657cd46c48 100644
--- a/DesktopEditor/common/File.cpp
+++ b/DesktopEditor/common/File.cpp
@@ -121,6 +121,10 @@ namespace NSFile
     std::wstring CUtf8Converter::GetUnicodeFromCharPtr(const std::string& sParam, INT bIsUtf8)
     {
         return GetUnicodeFromCharPtr(sParam.c_str(), (LONG)sParam.length(), bIsUtf8);
+    }
+	LONG CUtf8Converter::GetUnicodeStringFromUTF8BufferSize(LONG lCount)
+    {
+        return lCount + 1;
     }
     std::wstring CUtf8Converter::GetUnicodeStringFromUTF8_4bytes( BYTE* pBuffer, LONG lCount )
     {
@@ -305,6 +309,249 @@ namespace NSFile
         return GetUnicodeStringFromUTF8_4bytes(pBuffer, lCount);
     }
 
+#define CHECK_HHHH(pBuffer) \
+    wchar_t code = 0; \
+    if('_' == pBuffer[0] && 'x' == pBuffer[1] && 0 != pBuffer[2] && 0 != pBuffer[3] && 0 != pBuffer[4] && 0 != pBuffer[5]  && '_' == pBuffer[6]) \
+    { \
+        int i = 2; \
+        for(; i < 6; ++i) \
+        { \
+            code *= 16; \
+            if('0' <= pBuffer[i] && pBuffer[i] <= '9') \
+            { \
+                code += pBuffer[i] - '0'; \
+            } \
+            else if('A' <= pBuffer[i] && pBuffer[i] <= 'F') \
+            { \
+                code += pBuffer[i] - 'A' + 10; \
+            } \
+            else if('a' <= pBuffer[i] && pBuffer[i] <= 'f') \
+            { \
+                code += pBuffer[i] - 'a' + 10; \
+            } \
+            else \
+            { \
+                break; \
+            } \
+        } \
+        if(i == 6) \
+        { \
+            if(0x005F == code) \
+            { \
+                code = '_'; \
+            } \
+            return code; \
+        } \
+    } \
+    return -1;
+
+    long CUtf8Converter::CheckHHHHChar(const BYTE* pBuffer)
+	{
+        CHECK_HHHH(pBuffer);
+	}
+    long CUtf8Converter::CheckHHHHChar(const wchar_t* pBuffer)
+	{
+        CHECK_HHHH(pBuffer);
+	}
+
+    void CUtf8Converter::GetUnicodeStringFromUTF8WithHHHH_4bytes( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount )
+    {
+        if (NULL == pUnicodes)
+        {
+            pUnicodes = new wchar_t[GetUnicodeStringFromUTF8BufferSize(lCount)];
+        }
+        WCHAR* pUnicodeString = pUnicodes;
+        LONG lIndexUnicode = 0;
+
+        LONG lIndex = 0;
+        while (lIndex < lCount)
+        {
+            BYTE byteMain = pBuffer[lIndex];
+            if (0x00 == (byteMain & 0x80))
+            {
+				// 1 byte
+                long code = CheckHHHHChar(pBuffer + lIndex);
+                if(code < 0)
+                {
+					pUnicodeString[lIndexUnicode++] = (WCHAR)byteMain;
+					++lIndex;
+				}
+                else
+                {
+                    pUnicodeString[lIndexUnicode++] = (WCHAR)code;
+                    lIndex += 7;
+                }
+            }
+            else if (0x00 == (byteMain & 0x20))
+            {
+                // 2 byte
+                int val = (int)(((byteMain & 0x1F) << 6) |
+                    (pBuffer[lIndex + 1] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 2;
+            }
+            else if (0x00 == (byteMain & 0x10))
+            {
+                // 3 byte
+                int val = (int)(((byteMain & 0x0F) << 12) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 2] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 3;
+            }
+            else if (0x00 == (byteMain & 0x0F))
+            {
+                // 4 byte
+                int val = (int)(((byteMain & 0x07) << 18) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 3] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 4;
+            }
+            else if (0x00 == (byteMain & 0x08))
+            {
+                // 4 byte
+                int val = (int)(((byteMain & 0x07) << 18) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 3] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 4;
+            }
+            else if (0x00 == (byteMain & 0x04))
+            {
+                // 5 byte
+                int val = (int)(((byteMain & 0x03) << 24) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 18) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 3] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 4] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 5;
+            }
+            else
+            {
+                // 6 byte
+                int val = (int)(((byteMain & 0x01) << 30) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 24) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 18) |
+                    ((pBuffer[lIndex + 3] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 4] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 5] & 0x3F));
+                pUnicodeString[lIndexUnicode++] = (WCHAR)(val);
+                lIndex += 5;
+            }
+        }
+
+        pUnicodeString[lIndexUnicode] = 0;
+        lOutputCount = lIndexUnicode;
+    }
+    void CUtf8Converter::GetUnicodeStringFromUTF8WithHHHH_2bytes( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount )
+    {
+        if (NULL == pUnicodes)
+        {
+            pUnicodes = new wchar_t[GetUnicodeStringFromUTF8BufferSize(lCount)];
+        }
+        WCHAR* pUnicodeString = pUnicodes;
+        WCHAR* pStart = pUnicodeString;
+        LONG lIndex = 0;
+        while (lIndex < lCount)
+        {
+            BYTE byteMain = pBuffer[lIndex];
+            if (0x00 == (byteMain & 0x80))
+            {
+                // 1 byte
+                long code = CheckHHHHChar(pBuffer + lIndex);
+                if(code < 0)
+                {
+                    *pUnicodeString++ = (WCHAR)byteMain;
+                    ++lIndex;
+                }
+                else
+                {
+                    *pUnicodeString++ = (WCHAR)code;
+                    lIndex += 7;
+                }
+
+            }
+            else if (0x00 == (byteMain & 0x20))
+            {
+                // 2 byte
+                int val = (int)(((byteMain & 0x1F) << 6) |
+                    (pBuffer[lIndex + 1] & 0x3F));
+                *pUnicodeString++ = (WCHAR)(val);
+                lIndex += 2;
+            }
+            else if (0x00 == (byteMain & 0x10))
+            {
+                // 3 byte
+                int val = (int)(((byteMain & 0x0F) << 12) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 2] & 0x3F));
+
+                WriteUtf16_WCHAR(val, pUnicodeString);
+                lIndex += 3;
+            }
+            else if (0x00 == (byteMain & 0x0F))
+            {
+                // 4 byte
+                int val = (int)(((byteMain & 0x07) << 18) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 3] & 0x3F));
+
+                WriteUtf16_WCHAR(val, pUnicodeString);
+                lIndex += 4;
+            }
+            else if (0x00 == (byteMain & 0x08))
+            {
+                // 4 byte
+                int val = (int)(((byteMain & 0x07) << 18) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 3] & 0x3F));
+
+                WriteUtf16_WCHAR(val, pUnicodeString);
+                lIndex += 4;
+            }
+            else if (0x00 == (byteMain & 0x04))
+            {
+                // 5 byte
+                int val = (int)(((byteMain & 0x03) << 24) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 18) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 3] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 4] & 0x3F));
+
+                WriteUtf16_WCHAR(val, pUnicodeString);
+                lIndex += 5;
+            }
+            else
+            {
+                // 6 byte
+                int val = (int)(((byteMain & 0x01) << 30) |
+                    ((pBuffer[lIndex + 1] & 0x3F) << 24) |
+                    ((pBuffer[lIndex + 2] & 0x3F) << 18) |
+                    ((pBuffer[lIndex + 3] & 0x3F) << 12) |
+                    ((pBuffer[lIndex + 4] & 0x3F) << 6) |
+                    (pBuffer[lIndex + 5] & 0x3F));
+
+                WriteUtf16_WCHAR(val, pUnicodeString);
+                lIndex += 5;
+            }
+        }
+
+        *pUnicodeString++ = 0;
+        lOutputCount = pUnicodeString - pStart;
+    }
+    void CUtf8Converter::GetUnicodeStringFromUTF8WithHHHH( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount )
+    {
+        if (sizeof(WCHAR) == 2)
+            return GetUnicodeStringFromUTF8WithHHHH_2bytes(pBuffer, lCount, pUnicodes, lOutputCount);
+        return GetUnicodeStringFromUTF8WithHHHH_4bytes(pBuffer, lCount, pUnicodes, lOutputCount);
+    }
+
     void CUtf8Converter::GetUtf8StringFromUnicode_4bytes(const wchar_t* pUnicodes, LONG lCount, BYTE*& pData, LONG& lOutputCount, bool bIsBOM)
     {
         if (NULL == pData)
diff --git a/DesktopEditor/common/File.h b/DesktopEditor/common/File.h
index f8b8aa7f5b..c5993b7189 100644
--- a/DesktopEditor/common/File.h
+++ b/DesktopEditor/common/File.h
@@ -100,11 +100,17 @@ namespace NSFile
 
         static std::wstring GetUnicodeFromCharPtr(const char* pData, LONG lCount, INT bIsUtf8 = FALSE);
         static std::wstring GetUnicodeFromCharPtr(const std::string& sParam, INT bIsUtf8 = FALSE);
+
         static std::wstring GetUnicodeStringFromUTF8_4bytes( BYTE* pBuffer, LONG lCount );
         static std::wstring GetUnicodeStringFromUTF8_2bytes( BYTE* pBuffer, LONG lCount );
-
         static std::wstring GetUnicodeStringFromUTF8( BYTE* pBuffer, LONG lCount );
 
+        static void GetUnicodeStringFromUTF8WithHHHH_4bytes( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount );
+        static void GetUnicodeStringFromUTF8WithHHHH_2bytes( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount );
+        static void GetUnicodeStringFromUTF8WithHHHH( const BYTE* pBuffer, LONG lCount, wchar_t*& pUnicodes, LONG& lOutputCount );
+
+        static inline LONG GetUnicodeStringFromUTF8BufferSize( LONG lCount );
+
         static void GetUtf8StringFromUnicode_4bytes(const wchar_t* pUnicodes, LONG lCount, BYTE*& pData, LONG& lOutputCount, bool bIsBOM = false);
         static void GetUtf8StringFromUnicode_2bytes(const wchar_t* pUnicodes, LONG lCount, BYTE*& pData, LONG& lOutputCount, bool bIsBOM = false);
         static void GetUtf8StringFromUnicode(const wchar_t* pUnicodes, LONG lCount, BYTE*& pData, LONG& lOutputCount, bool bIsBOM = false);
@@ -118,6 +124,9 @@ namespace NSFile
 	
         static std::wstring GetWStringFromUTF16(const CStringUtf16& data);
         static std::wstring GetWStringFromUTF16(const unsigned short* pUtf16, LONG lCount);
+
+        static inline long CheckHHHHChar(const BYTE* pBuffer);
+        static inline long CheckHHHHChar(const wchar_t* pBuffer);
 	};
 
     class KERNEL_DECL CFileBinary
diff --git a/DesktopEditor/common/StringBuilder.cpp b/DesktopEditor/common/StringBuilder.cpp
index 4a6aeef1a2..e098f933eb 100644
--- a/DesktopEditor/common/StringBuilder.cpp
+++ b/DesktopEditor/common/StringBuilder.cpp
@@ -30,6 +30,7 @@
  *
  */
 #include "StringBuilder.h"
+#include "File.h"
 
 namespace NSStringUtils
 {
@@ -301,6 +302,18 @@ namespace NSStringUtils
 		else
 			WriteEncodeXmlString_4bytes(pString, nCount);
 	}
+	void CStringBuilder::WriteEncodeXmlStringHHHH(const std::wstring& sString)
+	{
+		WriteEncodeXmlStringHHHH(sString.c_str(), (int)sString.length());
+	}
+
+	void CStringBuilder::WriteEncodeXmlStringHHHH(const wchar_t* pString, int nCount)
+	{
+		if (sizeof(wchar_t) == 2)
+			WriteEncodeXmlStringHHHH_2bytes(pString, nCount);
+		else
+			WriteEncodeXmlStringHHHH_4bytes(pString, nCount);
+	}
 	inline void CStringBuilder::WriteEncodeXmlString_4bytes(const wchar_t* pString, int nCount)
 	{
 		const wchar_t* pData = pString;
@@ -354,6 +367,59 @@ namespace NSStringUtils
 			}
 		}
 	}
+	inline void CStringBuilder::WriteEncodeXmlStringHHHH_4bytes(const wchar_t* pString, int nCount)
+	{
+		const wchar_t* pData = pString;
+		int nCounter = 0;
+		unsigned int code;
+		while (*pData != 0)
+		{
+			code = (unsigned int)*pData;
+			WriteEncodeXmlChar(*pData, CheckXmlCodeHHHH(code, pData));
+
+			++pData;
+			if (-1 != nCount)
+			{
+				++nCounter;
+				if (nCounter >= nCount)
+					break;
+			}
+		}
+	}
+	inline void CStringBuilder::WriteEncodeXmlStringHHHH_2bytes(const wchar_t* pString, int nCount)
+	{
+		const wchar_t* pData = pString;
+		int nCounter = 0;
+		unsigned int code;
+		BYTE type;
+		while (*pData != 0)
+		{
+			code = (unsigned int)*pData;
+			if (code >= 0xD800 && code <= 0xDFFF && *(pData + 1) != 0)
+			{
+				code = 0x10000 + (((code & 0x3FF) << 10) | (0x03FF & *(pData + 1)));
+				type = CheckXmlCodeHHHH(code, pData);
+				if(0 != type)
+				{
+					WriteEncodeXmlChar(*pData, type);
+					++pData;
+				}
+			}
+			else
+			{
+				type = CheckXmlCodeHHHH(code, pData);
+			}
+			WriteEncodeXmlChar(*pData, type);
+
+			++pData;
+			if (-1 != nCount)
+			{
+				++nCounter;
+				if (nCounter >= nCount)
+					break;
+			}
+		}
+	}
 	inline void CStringBuilder::WriteEncodeXmlChar(wchar_t code, BYTE type)
 	{
 		switch (type)
@@ -436,6 +502,27 @@ namespace NSStringUtils
 			*m_pDataCur++ = (wchar_t)(';');
 			m_lSizeCur += 5;
 			break;
+		case 10:
+			AddSize(7);
+			*m_pDataCur++ = (wchar_t)('_');
+			*m_pDataCur++ = (wchar_t)('x');
+			*m_pDataCur++ = (wchar_t)('0');
+			*m_pDataCur++ = (wchar_t)('0');
+			*m_pDataCur++ = (wchar_t)('5');
+			*m_pDataCur++ = (wchar_t)('F');
+			*m_pDataCur++ = (wchar_t)('_');
+			m_lSizeCur += 7;
+			break;
+		case 11:
+			AddSize(7);
+			*m_pDataCur++ = (wchar_t)('_');
+			*m_pDataCur++ = (wchar_t)('x');
+			m_lSizeCur += 2;
+			WriteHexByteNoSafe((code >> 8) & 0xFF);
+			WriteHexByteNoSafe(code & 0xFF);
+			*m_pDataCur++ = (wchar_t)('_');
+			++m_lSizeCur;
+			break;
 		default:
 			break;
 		}
@@ -751,6 +838,35 @@ namespace NSStringUtils
 
 		return 0;
 	}
+	unsigned char CStringBuilder::CheckXmlCodeHHHH(unsigned int c, const wchar_t* pData)
+	{
+		if ('&' == c)
+			return 2;
+		if ('\'' == c)
+			return 3;
+		if ('<' == c)
+			return 4;
+		if ('>' == c)
+			return 5;
+		if ('\"' == c)
+			return 6;
+		if ('\n' == c)//when reading from the attributes is replaced by a space.
+			return 7;
+		if ('\r' == c)//when reading from the attributes is replaced by a space.
+			return 8;
+		if ('\t' == c)//when reading from the attributes is replaced by a space.
+			return 9;
+		if (NSFile::CUtf8Converter::CheckHHHHChar(pData) >= 0)
+			return 10;
+
+		//xml 1.0 Character Range https://www.w3.org/TR/xml/#charsets
+		if ((0x20 <= c && c <= 0xD7FF) || (0xE000 <= c && c <= 0xFFFD) || (0x10000 <= c && c <= 0x10FFFF))
+			return 1;
+		else if(c <= 0xFFFF)
+			return 11;
+
+		return 0;
+	}
 
     void string_replace(std::wstring& text, const std::wstring& replaceFrom, const std::wstring& replaceTo)
     {
diff --git a/DesktopEditor/common/StringBuilder.h b/DesktopEditor/common/StringBuilder.h
index 43bddc38fa..c45275ce4c 100644
--- a/DesktopEditor/common/StringBuilder.h
+++ b/DesktopEditor/common/StringBuilder.h
@@ -109,9 +109,11 @@ namespace NSStringUtils
         void AddChar2Safe(const wchar_t _c1, const wchar_t& _c2);
 
         void WriteEncodeXmlString(const std::wstring& sString);
-
         void WriteEncodeXmlString(const wchar_t* pString, int nCount = -1);
 
+        void WriteEncodeXmlStringHHHH(const std::wstring& sString);
+        void WriteEncodeXmlStringHHHH(const wchar_t* pString, int nCount = -1);
+
         size_t GetCurSize();
         void SetCurSize(size_t lCurSize);
         size_t GetSize();
@@ -147,8 +149,11 @@ namespace NSStringUtils
 	protected:
         inline void WriteEncodeXmlString_4bytes(const wchar_t* pString, int nCount);
         inline void WriteEncodeXmlString_2bytes(const wchar_t* pString, int nCount);
+        inline void WriteEncodeXmlStringHHHH_4bytes(const wchar_t* pString, int nCount);
+        inline void WriteEncodeXmlStringHHHH_2bytes(const wchar_t* pString, int nCount);
         inline void WriteEncodeXmlChar(wchar_t code, unsigned char type);
         inline unsigned char CheckXmlCode(unsigned int c);
+        inline unsigned char CheckXmlCodeHHHH(unsigned int c, const wchar_t* pData);
 	};
 
     KERNEL_DECL void string_replace(std::wstring& text, const std::wstring& replaceFrom, const std::wstring& replaceTo);