Add cppunit test for SwScanner that would have caught fdo#40449

Move SwScanner so it can be tested easily and add a unit test that would have
detected fdo#40449 in advance

sw/inc/swscanner.hxx

+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*************************************************************************
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * Copyright 2000, 2010 Oracle and/or its affiliates.
+ *
+ * OpenOffice.org - a multi-platform office productivity suite
+ *
+ * This file is part of OpenOffice.org.
+ *
+ * OpenOffice.org is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License version 3
+ * only, as published by the Free Software Foundation.
+ *
+ * OpenOffice.org is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License version 3 for more details
+ * (a copy is included in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * version 3 along with OpenOffice.org.  If not, see
+ * <http://www.openoffice.org/license.html>
+ * for a copy of the LGPLv3 License.
+ *
+ ************************************************************************/
+#ifndef _SWSCANNER_HXX
+#define _SWSCANNER_HXX
+
+#include <i18npool/lang.h>
+#include <modeltoviewhelper.hxx>
+
+class SwTxtNode;
+
+/*************************************************************************
+ *                class SwScanner
+ * Hilfsklasse, die beim Spellen die Worte im gewuenschten Bereich
+ * nacheinander zur Verfuegung stellt.
+ *************************************************************************/
+
+class SwScanner
+{
+    rtl::OUString aWord;
+    const SwTxtNode& rNode;
+    const rtl::OUString aText;
+    const LanguageType* pLanguage;
+    const ModelToViewHelper::ConversionMap* pConversionMap;
+    sal_Int32 nStartPos;
+    sal_Int32 nEndPos;
+    sal_Int32 nBegin;
+    sal_Int32 nLen;
+    LanguageType aCurrLang;
+    sal_uInt16 nWordType;
+    sal_Bool bClip;
+
+public:
+    SwScanner( const SwTxtNode& rNd, const rtl::OUString& rTxt,
+               const LanguageType* pLang,
+               const ModelToViewHelper::ConversionMap* pConvMap,
+               sal_uInt16 nWordType,
+               sal_Int32 nStart, sal_Int32 nEnde, sal_Bool bClip = sal_False );
+
+
+    // This next word function tries to find the language for the next word
+    // It should currently _not_ be used for spell checking, and works only for
+    // ! bReverse
+    sal_Bool NextWord();
+
+    const rtl::OUString& GetWord() const    { return aWord; }
+
+    sal_Int32 GetBegin() const         { return nBegin; }
+    sal_Int32 GetEnd() const           { return nBegin + nLen; }
+    sal_Int32 GetLen() const           { return nLen; }
+
+    LanguageType GetCurrentLanguage() const {return aCurrLang;}
+};
+
+#endif
+
+/* vim:set shiftwidth=4 softtabstop=4 expandtab: */

sw/qa/core/swdoc-test.cxx

@@ -57,9 +57,11 @@
 #include "swtypes.hxx"
 #include "docstat.hxx"
 #include "doc.hxx"
+#include "ndtxt.hxx"
 #include "docsh.hxx"
 #include "shellres.hxx"
 #include "docufld.hxx"
+#include "swscanner.hxx"
 #include "swcrsr.hxx"
 #include "swmodule.hxx"
 
@@ -83,12 +85,14 @@ public:
     void testPageDescName();
     void testFileNameFields();
     void testDocStat();
+    void testSwScanner();
 
     CPPUNIT_TEST_SUITE(SwDocTest);
     CPPUNIT_TEST(randomTest);
     CPPUNIT_TEST(testPageDescName);
     CPPUNIT_TEST(testFileNameFields);
     CPPUNIT_TEST(testDocStat);
+    CPPUNIT_TEST(testSwScanner);
     CPPUNIT_TEST_SUITE_END();
 
 private:
@@ -175,6 +179,9 @@ void SwDocTest::testFileNameFields()
     m_xDocShRef->DoInitNew(0);
 }
 
+//See http://lists.freedesktop.org/archives/libreoffice/2011-August/016666.html
+//Remove unnecessary parameter to IDocumentStatistics::UpdateDocStat for
+//motivation
 void SwDocTest::testDocStat()
 {
     CPPUNIT_ASSERT_MESSAGE("Expected initial 0 count", m_pDoc->GetDocStat().nChar == 0);
@@ -195,6 +202,36 @@ void SwDocTest::testDocStat()
     CPPUNIT_ASSERT_MESSAGE("And cache is updated too", m_pDoc->GetDocStat().nChar == nLen);
 }
 
+//See https://bugs.freedesktop.org/show_bug.cgi?id=40449 for motivation
+void SwDocTest::testSwScanner()
+{
+    SwNodeIndex aIdx(m_pDoc->GetNodes().GetEndOfContent(), -1);
+    SwPaM aPaM(aIdx);
+
+    const SwTxtNode* pTxtNode = aPaM.GetNode()->GetTxtNode();
+
+    CPPUNIT_ASSERT_MESSAGE("Has Text Node", pTxtNode);
+
+    //Use a temporary rtl::OUString as the arg, as that's the trouble behind
+    //fdo#40449 and fdo#39365
+    SwScanner aScanner(*pTxtNode,
+        rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("Hello World")),
+        0, 0, i18n::WordType::DICTIONARY_WORD, 0,
+        RTL_CONSTASCII_LENGTH("Hello World"));
+
+    bool bFirstOk = aScanner.NextWord();
+    CPPUNIT_ASSERT_MESSAGE("First Token", bFirstOk);
+    const rtl::OUString &rHello = aScanner.GetWord();
+    CPPUNIT_ASSERT_MESSAGE("Should be Hello",
+        rHello.equalsAsciiL(RTL_CONSTASCII_STRINGPARAM("Hello")));
+
+    bool bSecondOk = aScanner.NextWord();
+    CPPUNIT_ASSERT_MESSAGE("Second Token", bSecondOk);
+    const rtl::OUString &rWorld = aScanner.GetWord();
+    CPPUNIT_ASSERT_MESSAGE("Should be World",
+        rWorld.equalsAsciiL(RTL_CONSTASCII_STRINGPARAM("World")));
+}
+
 static int
 getRand(int modulus)
 {
@@ -206,7 +243,8 @@ getRand(int modulus)
 static rtl::OUString
 getRandString()
 {
-    static rtl::OUString aText( rtl::OUString::createFromAscii("AAAAA BBBB CCC DD E \n"));
+    static rtl::OUString aText(RTL_CONSTASCII_USTRINGPARAM(
+        "AAAAA BBBB CCC DD E \n"));
     int s = getRand(aText.getLength());
     int j = getRand(aText.getLength() - s);
     rtl::OUString aRet(aText + s, j);

sw/source/core/inc/scriptinfo.hxx

@@ -32,10 +32,8 @@
 #define _SVSTDARR_XUB_STRLEN
 #include <svl/svstdarr.hxx>
 #endif
-#include <i18npool/lang.h>
 #include <list>
-#include <modeltoviewhelper.hxx>
-
+#include "swscanner.hxx"
 
 class SwTxtNode;
 class Point;
@@ -45,49 +43,6 @@ typedef std::list< xub_StrLen > PositionList;
 
 #define SPACING_PRECISION_FACTOR 100
 
-/*************************************************************************
- *                class SwScanner
- * Hilfsklasse, die beim Spellen die Worte im gewuenschten Bereich
- * nacheinander zur Verfuegung stellt.
- *************************************************************************/
-
-class SwScanner
-{
-    rtl::OUString aWord;
-    const SwTxtNode& rNode;
-    const rtl::OUString aText;
-    const LanguageType* pLanguage;
-    const ModelToViewHelper::ConversionMap* pConversionMap;
-    sal_Int32 nStartPos;
-    sal_Int32 nEndPos;
-    sal_Int32 nBegin;
-    sal_Int32 nLen;
-    LanguageType aCurrLang;
-    sal_uInt16 nWordType;
-    sal_Bool bClip;
-
-public:
-    SwScanner( const SwTxtNode& rNd, const rtl::OUString& rTxt,
-               const LanguageType* pLang,
-               const ModelToViewHelper::ConversionMap* pConvMap,
-               sal_uInt16 nWordType,
-               sal_Int32 nStart, sal_Int32 nEnde, sal_Bool bClip = sal_False );
-
-
-    // This next word function tries to find the language for the next word
-    // It should currently _not_ be used for spell checking, and works only for
-    // ! bReverse
-    sal_Bool NextWord();
-
-    const rtl::OUString& GetWord() const    { return aWord; }
-
-    sal_Int32 GetBegin() const         { return nBegin; }
-    sal_Int32 GetEnd() const           { return nBegin + nLen; }
-    sal_Int32 GetLen() const           { return nLen; }
-
-    LanguageType GetCurrentLanguage() const {return aCurrLang;}
-};
-
 /*************************************************************************
  *                      class SwScriptInfo
  *