[Libreoffice-commits] core.git: Branch 'libreoffice-5-4' - sw/source

[Michael Stahl]

 sw/source/filter/html/htmltab.cxx |    3 +++
 sw/source/filter/html/swhtml.cxx  |   31 +++++++++++++++++++------------
 sw/source/filter/html/swhtml.hxx  |    2 ++
 3 files changed, 24 insertions(+), 12 deletions(-)

New commits:
commit 7283bdaf9cdc81dbec55c915ecd8c2571478bc4d
Author: Michael Stahl <mstahl at redhat.com>
Date:   Mon Jan 22 19:48:06 2018 +0100

    ofz#5566 sw: HTML import: ignore <DIV> in table structure elements
    
    Looking at the HTML4 DTD https://www.w3.org/TR/html4/sgml/dtd.html,
    inside TABLE only various elements defining the structure of the table
    allowed, except inside cells (TD and TH elements).
    
    DIV in a table but outside cells may cause cursor positions to go
    off the rails, so better ignore such invalid DIV tags.
    
    Reviewed-on: https://gerrit.libreoffice.org/48359
    Tested-by: Jenkins <ci at libreoffice.org>
    Reviewed-by: Caolán McNamara <caolanm at redhat.com>
    Tested-by: Caolán McNamara <caolanm at redhat.com>
    (cherry picked from commit 8b1a83bffe35ae0e71735569512c1586bcb37b25)
    
    Change-Id: Ia6195d80670631669c252d572242874b13642b74
    Reviewed-on: https://gerrit.libreoffice.org/48526
    Tested-by: Jenkins <ci at libreoffice.org>
    Reviewed-by: Eike Rathke <erack at redhat.com>

diff --git a/sw/source/filter/html/htmltab.cxx b/sw/source/filter/html/htmltab.cxx
index 0a499420f247..e033e4f36c61 100644
--- a/sw/source/filter/html/htmltab.cxx
+++ b/sw/source/filter/html/htmltab.cxx
@@ -19,6 +19,7 @@
 
 #include <memory>
 #include "hintids.hxx"
+#include <comphelper/flagguard.hxx>
 #include <vcl/svapp.hxx>
 #include <vcl/wrkwin.hxx>
 #include <editeng/boxitem.hxx>
@@ -3313,6 +3314,7 @@ void SwHTMLParser::BuildTableCell( HTMLTable *pCurTable, bool bReadOptions,
     if( !IsParserWorking() && !m_pPendStack )
         return;
 
+    ::comphelper::FlagRestorationGuard g(m_isInTableStructure, false);
     CellSaveStruct* pSaveStruct;
 
     HtmlTokenId nToken = HtmlTokenId::NONE;
@@ -4978,6 +4980,7 @@ HTMLTable *SwHTMLParser::BuildTable( SvxAdjust eParentAdjust,
     if( !IsParserWorking() && !m_pPendStack )
         return nullptr;
 
+    ::comphelper::FlagRestorationGuard g(m_isInTableStructure, true);
     HtmlTokenId nToken = HtmlTokenId::NONE;
     bool bPending = false;
     TableSaveStruct* pSaveStruct;
diff --git a/sw/source/filter/html/swhtml.cxx b/sw/source/filter/html/swhtml.cxx
index 3ec9997c8c33..f3560b11fbb6 100644
--- a/sw/source/filter/html/swhtml.cxx
+++ b/sw/source/filter/html/swhtml.cxx
@@ -298,6 +298,7 @@ SwHTMLParser::SwHTMLParser( SwDoc* pD, SwPaM& rCursor, SvStream& rIn,
     m_bInFootEndNoteSymbol( false ),
     m_bIgnoreHTMLComments( bNoHTMLComments ),
     m_bRemoveHidden( false ),
+    m_isInTableStructure(false),
     m_pTempViewFrame(nullptr)
 {
     m_nEventId = nullptr;
@@ -1538,26 +1539,32 @@ void SwHTMLParser::NextToken( HtmlTokenId nToken )
     // divisions
     case HtmlTokenId::DIVISION_ON:
     case HtmlTokenId::CENTER_ON:
-        if( m_nOpenParaToken != HtmlTokenId::NONE )
+        if (!m_isInTableStructure)
         {
-            if( IsReadPRE() )
-                m_nOpenParaToken = HtmlTokenId::NONE;
-            else
-                EndPara();
+            if (m_nOpenParaToken != HtmlTokenId::NONE)
+            {
+                if (IsReadPRE())
+                    m_nOpenParaToken = HtmlTokenId::NONE;
+                else
+                    EndPara();
+            }
+            NewDivision( nToken );
         }
-        NewDivision( nToken );
         break;
 
     case HtmlTokenId::DIVISION_OFF:
     case HtmlTokenId::CENTER_OFF:
-        if( m_nOpenParaToken != HtmlTokenId::NONE )
+        if (!m_isInTableStructure)
         {
-            if( IsReadPRE() )
-                m_nOpenParaToken = HtmlTokenId::NONE;
-            else
-                EndPara();
+            if (m_nOpenParaToken != HtmlTokenId::NONE)
+            {
+                if (IsReadPRE())
+                    m_nOpenParaToken = HtmlTokenId::NONE;
+                else
+                    EndPara();
+            }
+            EndDivision();
         }
-        EndDivision();
         break;
 
     case HtmlTokenId::MULTICOL_ON:
diff --git a/sw/source/filter/html/swhtml.hxx b/sw/source/filter/html/swhtml.hxx
index a1ef95e54d8c..5284590f9f0f 100644
--- a/sw/source/filter/html/swhtml.hxx
+++ b/sw/source/filter/html/swhtml.hxx
@@ -476,6 +476,8 @@ class SwHTMLParser : public SfxHTMLParser, public SwClient
     bool m_bIgnoreHTMLComments : 1;
     bool m_bRemoveHidden : 1; // the filter implementation might set the hidden flag
 
+    bool m_isInTableStructure;
+
     /// the names corresponding to the DOCINFO field subtypes INFO[1-4]
     OUString m_InfoNames[4];