a temporary hack to make testing wxTLW/Univ easier

[wxWidgets.git] / src / html / htmlpars.cpp

diff --git a/src/html/htmlpars.cpp b/src/html/htmlpars.cpp
index 64054fc2d2f246bdf211e123bd3d607688c28cc0..09f7c0ecd96041630d469b283e8613f609ab4cfa 100644 (file)
--- a/src/html/htmlpars.cpp
+++ b/src/html/htmlpars.cpp
@@ -80,8 +80,9 @@ wxHtmlParser::wxHtmlParser()
 
 wxHtmlParser::~wxHtmlParser()
 {
 
 wxHtmlParser::~wxHtmlParser()
 {

-    while (RestoreState())
-        DestroyDOMTree();
+    while (RestoreState()) {}
+    DestroyDOMTree();
+    

     delete m_HandlersStack;
     m_HandlersHash.Clear();
     m_HandlersList.DeleteContents(TRUE);
     delete m_HandlersStack;
     m_HandlersHash.Clear();
     m_HandlersList.DeleteContents(TRUE);


@@ -271,8 +272,9 @@ void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
              pieces[m_CurTextPiece].m_pos < m_CurTag->GetBeginPos()))
         {
             // Add text:
              pieces[m_CurTextPiece].m_pos < m_CurTag->GetBeginPos()))
         {
             // Add text:

-            AddText(m_Source.Mid(pieces[m_CurTextPiece].m_pos,
-                                 pieces[m_CurTextPiece].m_lng));
+            AddText(GetEntitiesParser()->Parse(
+                       m_Source.Mid(pieces[m_CurTextPiece].m_pos,
+                                    pieces[m_CurTextPiece].m_lng)));

             begin_pos = pieces[m_CurTextPiece].m_pos +
                         pieces[m_CurTextPiece].m_lng;
             m_CurTextPiece++;
             begin_pos = pieces[m_CurTextPiece].m_pos +
                         pieces[m_CurTextPiece].m_lng;
             m_CurTextPiece++;


@@ -316,7 +318,7 @@ void wxHtmlParser::AddTagHandler(wxHtmlTagHandler *handler)
     wxStringTokenizer tokenizer(s, wxT(", "));
 
     while (tokenizer.HasMoreTokens())
     wxStringTokenizer tokenizer(s, wxT(", "));
 
     while (tokenizer.HasMoreTokens())

-        m_HandlersHash.Put(tokenizer.NextToken(), handler);
+        m_HandlersHash.Put(tokenizer.GetNextToken(), handler);

 
     if (m_HandlersList.IndexOf(handler) == wxNOT_FOUND)
         m_HandlersList.Append(handler);
 
     if (m_HandlersList.IndexOf(handler) == wxNOT_FOUND)
         m_HandlersList.Append(handler);


@@ -339,7 +341,7 @@ void wxHtmlParser::PushTagHandler(wxHtmlTagHandler *handler, wxString tags)
 
     while (tokenizer.HasMoreTokens())
     {
 
     while (tokenizer.HasMoreTokens())
     {

-        key = tokenizer.NextToken();
+        key = tokenizer.GetNextToken();

         m_HandlersHash.Delete(key);
         m_HandlersHash.Put(key, handler);
     }
         m_HandlersHash.Delete(key);
         m_HandlersHash.Put(key, handler);
     }


@@ -385,6 +387,8 @@ bool wxHtmlParser::RestoreState()
 {
     if (!m_SavedStates) return FALSE;
 
 {
     if (!m_SavedStates) return FALSE;
 

+    DestroyDOMTree();
+

     wxHtmlParserState *s = m_SavedStates;
     m_SavedStates = s->m_nextState;
 
     wxHtmlParserState *s = m_SavedStates;
     m_SavedStates = s->m_nextState;
 


@@ -444,6 +448,8 @@ wxString wxHtmlEntitiesParser::Parse(const wxString& input)
     const wxChar *c, *last;
     const wxChar *in_str = input.c_str();
     wxString output;
     const wxChar *c, *last;
     const wxChar *in_str = input.c_str();
     wxString output;

+    
+    output.reserve(input.length());

 
     for (c = in_str, last = in_str; *c != wxT('\0'); c++)
     {
 
     for (c = in_str, last = in_str; *c != wxT('\0'); c++)
     {


@@ -452,8 +458,11 @@ wxString wxHtmlEntitiesParser::Parse(const wxString& input)
             if (c - last > 0)
                 output.append(last, c - last);
             if (++c == wxT('\0')) break;
             if (c - last > 0)
                 output.append(last, c - last);
             if (++c == wxT('\0')) break;

+        

             wxString entity;
             const wxChar *ent_s = c;
             wxString entity;
             const wxChar *ent_s = c;

+            wxChar entity_char;
+        

             for (; (*c >= wxT('a') && *c <= wxT('z')) ||
                    (*c >= wxT('A') && *c <= wxT('Z')) ||
                    (*c >= wxT('0') && *c <= wxT('9')) ||
             for (; (*c >= wxT('a') && *c <= wxT('z')) ||
                    (*c >= wxT('A') && *c <= wxT('Z')) ||
                    (*c >= wxT('0') && *c <= wxT('9')) ||


@@ -461,7 +470,14 @@ wxString wxHtmlEntitiesParser::Parse(const wxString& input)
             entity.append(ent_s, c - ent_s);
             if (*c != wxT(';')) c--;
             last = c+1;
             entity.append(ent_s, c - ent_s);
             if (*c != wxT(';')) c--;
             last = c+1;

-            output << GetEntityChar(entity);
+            entity_char = GetEntityChar(entity);
+            if (entity_char)
+                output << entity_char;
+            else
+            {
+                output.append(ent_s-1, c-ent_s+2);
+                wxLogDebug(wxT("Unrecognized HTML entity: '%s'"), entity.c_str());
+            }

         }
     }
     if (*last != wxT('\0'))
         }
     }
     if (*last != wxT('\0'))


@@ -791,7 +807,7 @@ wxChar wxHtmlEntitiesParser::GetEntityChar(const wxString& entity)
     }
 
     if (code == 0)
     }
 
     if (code == 0)

-        return wxT('?');
+        return 0;

     else
         return GetCharForCode(code);
 }
     else
         return GetCharForCode(code);
 }