From 2421317990d00e14325298f34db3c60735527697 Mon Sep 17 00:00:00 2001
From: Rohit Deshmukh <rohit.deshmukh@synerzip.com>
Date: Fri, 6 Dec 2013 15:42:53 +0530
Subject: [PATCH 8/9] fdo#72219: Fix for corruption of symbols in docx

Issue:
OUString uses UTF-16, so for a Unicode surrogate character there are 2
values stored, not just 1.
So we are getting assert failure in "rtl_uString_iterateCodePoints" method.

erAck: Underlying cause was that the dictionary breakiterator misused
UTF-16 positions as Unicode code point positions.

Change-Id: I923485f56c2d879b63687adaea2b489a3479991c
Reviewed-on: https://gerrit.libreoffice.org/6955
Reviewed-by: Eike Rathke <erack@redhat.com>
Tested-by: Eike Rathke <erack@redhat.com>
(cherry picked from commit d8fd15875901d584a4bbcc07c927fa20332e4841)
Reviewed-on: https://gerrit.libreoffice.org/7322
(cherry picked from commit 994d0c9e7aa8d1a7602e61b770991da980c1cde5)
Reviewed-on: https://gerrit.libreoffice.org/7324
---
 i18npool/qa/cppunit/test_breakiterator.cxx    | 19 ++++++++++++++++++-
 i18npool/source/breakiterator/xdictionary.cxx |  6 ++++--
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/i18npool/qa/cppunit/test_breakiterator.cxx b/i18npool/qa/cppunit/test_breakiterator.cxx
index 41e4077..b4174ba 100644
--- a/i18npool/qa/cppunit/test_breakiterator.cxx
+++ b/i18npool/qa/cppunit/test_breakiterator.cxx
@@ -44,7 +44,7 @@ public:
 #endif
     void testKhmer();
     void testJapanese();
-
+    void testChinese();
     CPPUNIT_TEST_SUITE(TestBreakIterator);
     CPPUNIT_TEST(testLineBreaking);
     CPPUNIT_TEST(testGraphemeIteration);
@@ -60,6 +60,7 @@ public:
     CPPUNIT_TEST(testKhmer);
 #endif
     CPPUNIT_TEST(testJapanese);
+    CPPUNIT_TEST(testChinese);
     CPPUNIT_TEST_SUITE_END();
 private:
     uno::Reference<i18n::XBreakIterator> m_xBreak;
@@ -909,6 +910,22 @@ void TestBreakIterator::testJapanese()
     }
 }
 
+void TestBreakIterator::testChinese()
+{
+    lang::Locale aLocale;
+    aLocale.Language = "zh";
+    aLocale.Country = "CN";
+    i18n::Boundary aBounds;
+
+    {
+        const sal_Unicode CHINESE[] = { 0x6A35, 0x6A30, 0x69FE, 0x8919, 0xD867, 0xDEDB  };
+
+        OUString aTest(CHINESE, SAL_N_ELEMENTS(CHINESE));
+        aBounds = m_xBreak->getWordBoundary(aTest, 4, aLocale,
+            i18n::WordType::DICTIONARY_WORD, true);
+        CPPUNIT_ASSERT(aBounds.startPos == 4 && aBounds.endPos == 6);
+    }
+}
 void TestBreakIterator::setUp()
 {
     BootstrapFixtureBase::setUp();
diff --git a/i18npool/source/breakiterator/xdictionary.cxx b/i18npool/source/breakiterator/xdictionary.cxx
index 72da09f..3b43fa3 100644
--- a/i18npool/source/breakiterator/xdictionary.cxx
+++ b/i18npool/source/breakiterator/xdictionary.cxx
@@ -383,9 +383,11 @@ Boundary xdictionary::getWordBoundary(const OUString& rText, sal_Int32 anyPos, s
                 if (u_isWhitespace(ch))
                     i--;
             }
+
             boundary.endPos = boundary.startPos;
-            rText.iterateCodePoints(&boundary.endPos, aCache.wordboundary[i]);
-            rText.iterateCodePoints(&boundary.startPos, aCache.wordboundary[i-1]);
+            boundary.endPos += aCache.wordboundary[i];
+            boundary.startPos += aCache.wordboundary[i-1];
+
         } else {
             boundary.startPos = anyPos;
             if (anyPos < len) rText.iterateCodePoints(&anyPos, 1);
-- 
1.8.4.2