Applied part of [ 1575767 ] Init/size/check fixes for sockets

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

diff --git a/src/html/htmlpars.cpp b/src/html/htmlpars.cpp
index b205c3305b222f2b14f4e0390953b8a735acd9c1..7efb69af345f19d0b43b0fec336b5933a00a9a1a 100644 (file)
--- a/src/html/htmlpars.cpp
+++ b/src/html/htmlpars.cpp
@@ -1,29 +1,25 @@
 /////////////////////////////////////////////////////////////////////////////
 /////////////////////////////////////////////////////////////////////////////

-// Name:        htmlpars.cpp
+// Name:        src/html/htmlpars.cpp

 // Purpose:     wxHtmlParser class (generic parser)
 // Author:      Vaclav Slavik
 // RCS-ID:      $Id$
 // Copyright:   (c) 1999 Vaclav Slavik
 // Purpose:     wxHtmlParser class (generic parser)
 // Author:      Vaclav Slavik
 // RCS-ID:      $Id$
 // Copyright:   (c) 1999 Vaclav Slavik

-// Licence:     wxWindows Licence
+// Licence:     wxWindows licence

 /////////////////////////////////////////////////////////////////////////////
 
 /////////////////////////////////////////////////////////////////////////////
 

-
-#ifdef __GNUG__
-#pragma implementation "htmlpars.h"
-#endif
-

 #include "wx/wxprec.h"
 
 #include "wx/wxprec.h"
 

-#include "wx/defs.h"
-#if wxUSE_HTML && wxUSE_STREAMS
-

 #ifdef __BORLANDC__
 #ifdef __BORLANDC__

-#pragma hdrstop
+    #pragma hdrstop

 #endif
 
 #endif
 

+#if wxUSE_HTML && wxUSE_STREAMS
+

 #ifndef WXPRECOMP
 #ifndef WXPRECOMP

+    #include "wx/dynarray.h"

     #include "wx/log.h"
     #include "wx/intl.h"
     #include "wx/log.h"
     #include "wx/intl.h"

+    #include "wx/app.h"

 #endif
 
 #include "wx/tokenzr.h"
 #endif
 
 #include "wx/tokenzr.h"


@@ -32,14 +28,17 @@
 #include "wx/fontmap.h"
 #include "wx/html/htmldefs.h"
 #include "wx/html/htmlpars.h"
 #include "wx/fontmap.h"
 #include "wx/html/htmldefs.h"
 #include "wx/html/htmlpars.h"

-#include "wx/dynarray.h"

 #include "wx/arrimpl.cpp"
 
 #include "wx/arrimpl.cpp"
 

+#ifdef __WXWINCE__
+    #include "wx/msw/wince/missing.h"       // for bsearch()
+#endif

 
 // DLL options compatibility check:
 
 // DLL options compatibility check:

-#include "wx/app.h"

 WX_CHECK_BUILD_OPTIONS("wxHTML")
 
 WX_CHECK_BUILD_OPTIONS("wxHTML")
 

+const wxChar *wxTRACE_HTML_DEBUG = _T("htmldebug");
+

 //-----------------------------------------------------------------------------
 // wxHtmlParser helpers
 //-----------------------------------------------------------------------------
 //-----------------------------------------------------------------------------
 // wxHtmlParser helpers
 //-----------------------------------------------------------------------------


@@ -52,7 +51,7 @@ public:
 };
 
 WX_DECLARE_OBJARRAY(wxHtmlTextPiece, wxHtmlTextPieces);
 };
 
 WX_DECLARE_OBJARRAY(wxHtmlTextPiece, wxHtmlTextPieces);

-WX_DEFINE_OBJARRAY(wxHtmlTextPieces);
+WX_DEFINE_OBJARRAY(wxHtmlTextPieces)

 
 class wxHtmlParserState
 {
 
 class wxHtmlParserState
 {


@@ -114,7 +113,7 @@ wxObject* wxHtmlParser::Parse(const wxString& source)
 void wxHtmlParser::InitParser(const wxString& source)
 {
     SetSource(source);
 void wxHtmlParser::InitParser(const wxString& source)
 {
     SetSource(source);

-    m_stopParsing = FALSE;
+    m_stopParsing = false;

 }
 
 void wxHtmlParser::DoneParser()
 }
 
 void wxHtmlParser::DoneParser()


@@ -135,7 +134,7 @@ void wxHtmlParser::CreateDOMTree()
 {
     wxHtmlTagsCache cache(m_Source);
     m_TextPieces = new wxHtmlTextPieces;
 {
     wxHtmlTagsCache cache(m_Source);
     m_TextPieces = new wxHtmlTextPieces;

-    CreateDOMSubTree(NULL, 0, m_Source.Length(), &cache);
+    CreateDOMSubTree(NULL, 0, m_Source.length(), &cache);

     m_CurTextPiece = 0;
 }
 
     m_CurTextPiece = 0;
 }
 


@@ -199,7 +198,7 @@ void wxHtmlParser::CreateDOMSubTree(wxHtmlTag *cur,
 
             // add another tag to the tree:
             else if (i < end_pos-1 && m_Source.GetChar(i+1) != wxT('/'))
 
             // add another tag to the tree:
             else if (i < end_pos-1 && m_Source.GetChar(i+1) != wxT('/'))

-               {
+            {

                 wxHtmlTag *chd;
                 if (cur)
                     chd = new wxHtmlTag(cur, m_Source,
                 wxHtmlTag *chd;
                 if (cur)
                     chd = new wxHtmlTag(cur, m_Source,


@@ -232,7 +231,7 @@ void wxHtmlParser::CreateDOMSubTree(wxHtmlTag *cur,
                 }
                 else
                     i = chd->GetBeginPos();
                 }
                 else
                     i = chd->GetBeginPos();

-                
+

                 textBeginning = i;
             }
 
                 textBeginning = i;
             }
 


@@ -272,7 +271,7 @@ void wxHtmlParser::DoParsing()
 {
     m_CurTag = m_Tags;
     m_CurTextPiece = 0;
 {
     m_CurTag = m_Tags;
     m_CurTextPiece = 0;

-    DoParsing(0, m_Source.Length());
+    DoParsing(0, m_Source.length());

 }
 
 void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
 }
 
 void wxHtmlParser::DoParsing(int begin_pos, int end_pos)


@@ -304,14 +303,10 @@ void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
         }
         else if (m_CurTag)
         {
         }
         else if (m_CurTag)
         {

-            // Add tag:
-            if (m_CurTag)
-            {
-                if (m_CurTag->HasEnding())
-                    begin_pos = m_CurTag->GetEndPos2();
-                else
-                    begin_pos = m_CurTag->GetBeginPos();
-            }
+            if (m_CurTag->HasEnding())
+                begin_pos = m_CurTag->GetEndPos2();
+            else
+                begin_pos = m_CurTag->GetBeginPos();

             wxHtmlTag *t = m_CurTag;
             m_CurTag = m_CurTag->GetNextTag();
             AddTag(*t);
             wxHtmlTag *t = m_CurTag;
             m_CurTag = m_CurTag->GetNextTag();
             AddTag(*t);


@@ -325,7 +320,7 @@ void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
 void wxHtmlParser::AddTag(const wxHtmlTag& tag)
 {
     wxHtmlTagHandler *h;
 void wxHtmlParser::AddTag(const wxHtmlTag& tag)
 {
     wxHtmlTagHandler *h;

-    bool inner = FALSE;
+    bool inner = false;

 
     h = (wxHtmlTagHandler*) m_HandlersHash.Get(tag.GetName());
     if (h)
 
     h = (wxHtmlTagHandler*) m_HandlersHash.Get(tag.GetName());
     if (h)


@@ -355,7 +350,7 @@ void wxHtmlParser::AddTagHandler(wxHtmlTagHandler *handler)
     handler->SetParser(this);
 }
 
     handler->SetParser(this);
 }
 

-void wxHtmlParser::PushTagHandler(wxHtmlTagHandler *handler, wxString tags)
+void wxHtmlParser::PushTagHandler(wxHtmlTagHandler *handler, const wxString& tags)

 {
     wxStringTokenizer tokenizer(tags, wxT(", "));
     wxString key;
 {
     wxStringTokenizer tokenizer(tags, wxT(", "));
     wxString key;


@@ -419,7 +414,7 @@ void wxHtmlParser::SetSourceAndSaveState(const wxString& src)
 
 bool wxHtmlParser::RestoreState()
 {
 
 bool wxHtmlParser::RestoreState()
 {

-    if (!m_SavedStates) return FALSE;
+    if (!m_SavedStates) return false;

 
     DestroyDOMTree();
 
 
     DestroyDOMTree();
 


@@ -433,7 +428,13 @@ bool wxHtmlParser::RestoreState()
     m_Source = s->m_source;
 
     delete s;
     m_Source = s->m_source;
 
     delete s;

-    return TRUE;
+    return true;
+}
+
+wxString wxHtmlParser::GetInnerSource(const wxHtmlTag& tag)
+{
+    return GetSource()->Mid(tag.GetBeginPos(),
+                            tag.GetEndPos1() - tag.GetBeginPos());

 }
 
 //-----------------------------------------------------------------------------
 }
 
 //-----------------------------------------------------------------------------


@@ -442,6 +443,15 @@ bool wxHtmlParser::RestoreState()
 
 IMPLEMENT_ABSTRACT_CLASS(wxHtmlTagHandler,wxObject)
 
 
 IMPLEMENT_ABSTRACT_CLASS(wxHtmlTagHandler,wxObject)
 

+void wxHtmlTagHandler::ParseInnerSource(const wxString& source)
+{
+    // It is safe to temporarily change the source being parsed,
+    // provided we restore the state back after parsing
+    m_Parser->SetSourceAndSaveState(source);
+    m_Parser->DoParsing();
+    m_Parser->RestoreState();
+}
+

 
 //-----------------------------------------------------------------------------
 // wxHtmlEntitiesParser
 
 //-----------------------------------------------------------------------------
 // wxHtmlEntitiesParser


@@ -486,7 +496,7 @@ 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++)
     output.reserve(input.length());
 
     for (c = in_str, last = in_str; *c != wxT('\0'); c++)


@@ -495,12 +505,13 @@ wxString wxHtmlEntitiesParser::Parse(const wxString& input)
         {
             if (c - last > 0)
                 output.append(last, c - last);
         {
             if (c - last > 0)
                 output.append(last, c - last);

-            if (++c == wxT('\0')) break;
-        
+            if ( *++c == wxT('\0') )
+                break;
+

             wxString entity;
             const wxChar *ent_s = c;
             wxChar entity_char;
             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')) ||


@@ -514,7 +525,9 @@ wxString wxHtmlEntitiesParser::Parse(const wxString& input)
             else
             {
                 output.append(ent_s-1, c-ent_s+2);
             else
             {
                 output.append(ent_s-1, c-ent_s+2);

-                wxLogDebug(wxT("Unrecognized HTML entity: '%s'"), entity.c_str());
+                wxLogTrace(wxTRACE_HTML_DEBUG,
+                           wxT("Unrecognized HTML entity: '%s'"),
+                           entity.c_str());

             }
         }
     }
             }
         }
     }


@@ -835,11 +848,24 @@ wxChar wxHtmlEntitiesParser::GetEntityChar(const wxString& entity)
             while (substitutions[substitutions_cnt].code != 0)
                 substitutions_cnt++;
 
             while (substitutions[substitutions_cnt].code != 0)
                 substitutions_cnt++;
 

-        wxHtmlEntityInfo *info;
+        wxHtmlEntityInfo *info = NULL;
+#ifdef __WXWINCE__
+        // bsearch crashes under WinCE for some reason
+        size_t i;
+        for (i = 0; i < substitutions_cnt; i++)
+        {
+            if (entity == substitutions[i].name)
+            {
+                info = & substitutions[i];
+                break;
+            }
+        }
+#else

         info = (wxHtmlEntityInfo*) bsearch(entity.c_str(), substitutions,
                                            substitutions_cnt,
                                            sizeof(wxHtmlEntityInfo),
                                            wxHtmlEntityCompare);
         info = (wxHtmlEntityInfo*) bsearch(entity.c_str(), substitutions,
                                            substitutions_cnt,
                                            sizeof(wxHtmlEntityInfo),
                                            wxHtmlEntityCompare);

+#endif

         if (info)
             code = info->code;
     }
         if (info)
             code = info->code;
     }


@@ -850,10 +876,11 @@ wxChar wxHtmlEntitiesParser::GetEntityChar(const wxString& entity)
         return GetCharForCode(code);
 }
 
         return GetCharForCode(code);
 }
 

-wxFSFile *wxHtmlParser::OpenURL(wxHtmlURLType WXUNUSED(type), 
+wxFSFile *wxHtmlParser::OpenURL(wxHtmlURLType WXUNUSED(type),

                                 const wxString& url) const
 {
                                 const wxString& url) const
 {

-    return GetFS()->OpenFile(url);
+    return m_FS ? m_FS->OpenFile(url) : NULL;
+

 }
 
 
 }
 
 


@@ -892,21 +919,21 @@ bool wxMetaTagHandler::HandleTag(const wxHtmlTag& tag)
     if (tag.GetName() == _T("BODY"))
     {
         m_Parser->StopParsing();
     if (tag.GetName() == _T("BODY"))
     {
         m_Parser->StopParsing();

-        return FALSE;
+        return false;

     }
 
     if (tag.HasParam(_T("HTTP-EQUIV")) &&
         tag.GetParam(_T("HTTP-EQUIV")).IsSameAs(_T("Content-Type"), false) &&
         tag.HasParam(_T("CONTENT")))
     {
     }
 
     if (tag.HasParam(_T("HTTP-EQUIV")) &&
         tag.GetParam(_T("HTTP-EQUIV")).IsSameAs(_T("Content-Type"), false) &&
         tag.HasParam(_T("CONTENT")))
     {

-        wxString content = tag.GetParam(_T("CONTENT"));
+        wxString content = tag.GetParam(_T("CONTENT")).Lower();

         if (content.Left(19) == _T("text/html; charset="))
         {
             *m_retval = content.Mid(19);
             m_Parser->StopParsing();
         }
     }
         if (content.Left(19) == _T("text/html; charset="))
         {
             *m_retval = content.Mid(19);
             m_Parser->StopParsing();
         }
     }

-    return FALSE;
+    return false;

 }
 
 
 }
 
 


@@ -914,9 +941,13 @@ bool wxMetaTagHandler::HandleTag(const wxHtmlTag& tag)
 wxString wxHtmlParser::ExtractCharsetInformation(const wxString& markup)
 {
     wxString charset;
 wxString wxHtmlParser::ExtractCharsetInformation(const wxString& markup)
 {
     wxString charset;

-    wxMetaTagParser parser;
-    parser.AddTagHandler(new wxMetaTagHandler(&charset));
-    parser.Parse(markup);
+    wxMetaTagParser *parser = new wxMetaTagParser();
+    if(parser)
+    {
+        parser->AddTagHandler(new wxMetaTagHandler(&charset));
+        parser->Parse(markup);
+        delete parser;
+    }

     return charset;
 }
 
     return charset;
 }