URL https://opencores.org/ocsvn/openrisc_me/openrisc_me/trunk

Subversion Repositories openrisc_me

[/] [openrisc/] [trunk/] [rtos/] [ecos-2.0/] [tools/] [src/] [tools/] [configtool/] [standalone/] [wxwin/] [htmlparser.cpp] - Blame information for rev 438

Go to most recent revision | Details | Compare with Previous | View Log


//####COPYRIGHTBEGIN####
//
// ----------------------------------------------------------------------------
// Copyright (C) 1998, 1999, 2000 Red Hat, Inc.
//
// This program is part of the eCos host tools.
//
// This program is free software; you can redistribute it and/or modify it
// under the terms of the GNU General Public License as published by the Free
// Software Foundation; either version 2 of the License, or (at your option)
// any later version.
//
// This program 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 General Public License for
// more details.
//
// You should have received a copy of the GNU General Public License along with
// this program; if not, write to the Free Software Foundation, Inc.,
// 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
//
// ----------------------------------------------------------------------------
//
//####COPYRIGHTEND####
// htmlparser.cpp :
//
//===========================================================================
//#####DESCRIPTIONBEGIN####
//
// Author(s):   julians
// Contact(s):  julians
// Date:        2001/04/04
// Version:     $Id: htmlparser.cpp,v 1.1.1.1 2004-02-14 13:28:46 phoenix Exp $
// Purpose:
// Description: HTML parser/HTML Help file generator
// Requires:
// Provides:
// See also:
// Known bugs:
// Usage:
//
//####DESCRIPTIONEND####
//
//===========================================================================
 
// ============================================================================
// declarations
// ============================================================================
 
// ----------------------------------------------------------------------------
// headers
// ----------------------------------------------------------------------------
#ifdef __GNUG__
#pragma implementation "htmlparser.h"
#endif
 
// Includes other headers for precompiled compilation
#include "ecpch.h"
 
#ifdef __BORLANDC__
#pragma hdrstop
#endif
 
#include "wx/textfile.h"
#include "wx/wfstream.h"
 
#include "ecutils.h"
#include "htmlparser.h"
 
/*
 * wxSimpleHtmlAttribute
 * Representation of an attribute
 */
 
wxSimpleHtmlParser::wxSimpleHtmlParser()
{
    m_topLevel = NULL;
    m_pos = 0;
}
 
 
wxSimpleHtmlParser::~wxSimpleHtmlParser()
{
    Clear();
}
 
bool wxSimpleHtmlParser::ParseFile(const wxString& filename)
{
    wxTextFile textFile;
 
    if (textFile.Open(filename))
    {
        wxString text;
        wxString line;
        int i;
        int count = textFile.GetLineCount();
        for (i = 0; i < count; i++)
        {
            if (i == 0)
                line = textFile.GetFirstLine();
            else
                line = textFile.GetNextLine();
 
            text += line;
            if (i != (count - 1))
                text += wxT("\n");
        }
 
#if 0
        for ( line = textFile.GetFirstLine(); !textFile.Eof(); line = textFile.GetNextLine() )
        {
            text += line;
            if (!textFile.Eof())
                text += wxT("\n");
        }
#endif
 
        return ParseString(text);
    }
    else
        return FALSE;
}
 
bool wxSimpleHtmlParser::ParseString(const wxString& str)
{
    Clear();
 
    m_pos = 0;
    m_text = str;
    m_length = str.Length();
 
    m_topLevel = new wxSimpleHtmlTag(wxT("TOPLEVEL"), wxSimpleHtmlTag_TopLevel);
 
    return ParseHtml(m_topLevel);
}
 
// Main recursive parsing function
bool wxSimpleHtmlParser::ParseHtml(wxSimpleHtmlTag* parent)
{
    while (!Eof())
    {
        EatWhitespace();
        if (IsComment())
        {
            ParseComment();
        }
        else if (IsDirective())
        {
            wxSimpleHtmlTag* tag = ParseDirective();
            if (tag)
                parent->AppendTag(tag);
        }
        else if (IsTagClose())
        {
            wxSimpleHtmlTag* tag = ParseTagClose();
            if (tag)
                parent->AppendTag(tag);
        }
        else if (IsTagStartBracket(GetChar(m_pos)))
        {
            wxSimpleHtmlTag* tag = ParseTagHeader();
            if (tag)
                parent->AppendTag(tag);
        }
        else
        {
            // Just a text string
            wxString text;
            ParseText(text);
 
            wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(wxT("TEXT"), wxSimpleHtmlTag_Text);
            tag->SetText(text);
            parent->AppendTag(tag);
        }
    }
    return TRUE;
}
 
// Plain text, up until an angled bracket
bool wxSimpleHtmlParser::ParseText(wxString& text)
{
    while (!Eof() && GetChar(m_pos) != wxT('<'))
    {
        text += GetChar(m_pos);
        m_pos ++;
    }
    return TRUE;
}
 
wxSimpleHtmlTag* wxSimpleHtmlParser::ParseTagHeader()
{
    if (IsTagStartBracket(GetChar(m_pos)))
    {
        m_pos ++;
        EatWhitespace();
 
        wxString word;
        ReadWord(word, TRUE);
 
        EatWhitespace();
 
        wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Open);
 
        ParseAttributes(tag);
 
        EatWhitespace();
 
        if (IsTagEndBracket(GetChar(m_pos)))
            m_pos ++;
 
        return tag;
    }
    else
        return NULL;
}
 
wxSimpleHtmlTag* wxSimpleHtmlParser::ParseTagClose()
{
    Matches(wxT("</"), TRUE);
 
    EatWhitespace();
 
    wxString word;
    ReadWord(word, TRUE);
 
    EatWhitespace();
    m_pos ++;
 
    wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Close);
    return tag;
}
 
bool wxSimpleHtmlParser::ParseAttributes(wxSimpleHtmlTag* tag)
{
    // Parse attributes of a tag header until we reach >
    while (!IsTagEndBracket(GetChar(m_pos)) && !Eof())
    {
        EatWhitespace();
 
        wxString attrName, attrValue;
 
        if (IsString())
        {
            ReadString(attrName, TRUE);
            tag->AppendAttribute(attrName, wxEmptyString);
        }
        else if (IsNumeric(GetChar(m_pos)))
        {
            ReadNumber(attrName, TRUE);
            tag->AppendAttribute(attrName, wxEmptyString);
        }
        else
        {
            // Try to read an attribute name/value pair, or at least a name
            // without the value
            ReadLiteral(attrName, TRUE);
            EatWhitespace();
 
            if (GetChar(m_pos) == wxT('='))
            {
                m_pos ++;
                EatWhitespace();
 
                if (IsString())
                    ReadString(attrValue, TRUE);
                else if (!Eof() && !IsTagEndBracket(GetChar(m_pos)))
                    ReadLiteral(attrValue, TRUE);
            }
            if (!attrName.IsEmpty())
                tag->AppendAttribute(attrName, attrValue);
        }
    }
    return TRUE;
}
 
// e.g. <!DOCTYPE ....>
wxSimpleHtmlTag* wxSimpleHtmlParser::ParseDirective()
{
    Matches(wxT("<!"), TRUE);
 
    EatWhitespace();
 
    wxString word;
    ReadWord(word, TRUE);
 
    EatWhitespace();
 
    wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Directive);
 
    ParseAttributes(tag);
 
    EatWhitespace();
 
    if (IsTagEndBracket(GetChar(m_pos)))
        m_pos ++;
 
    return tag;
}
 
bool wxSimpleHtmlParser::ParseComment()
{
    // Eat the comment tag start
    Matches(wxT("<!--"), TRUE);
 
    while (!Eof() && !Matches(wxT("-->"), TRUE))
    {
        m_pos ++;
    }
 
    return TRUE;
}
 
bool wxSimpleHtmlParser::EatWhitespace()
{
    while (!Eof() && IsWhitespace(GetChar(m_pos)))
        m_pos ++;
    return TRUE;
}
 
bool wxSimpleHtmlParser::EatWhitespace(int& pos)
{
    while (!Eof(pos) && IsWhitespace(GetChar(pos)))
        pos ++;
    return TRUE;
}
 
bool wxSimpleHtmlParser::ReadString(wxString& str, bool eatIt)
{
    int pos = m_pos;
    if (GetChar(pos) == (int) '"')
    {
        pos ++;
        while (!Eof(pos) && GetChar(pos) != (int) '"')
        {
            // TODO: how are quotes escaped in HTML?
            str += (wxChar) GetChar(pos);
            pos ++;
        }
        if (GetChar(pos) == (int) '"')
            pos ++;
        if (eatIt)
            m_pos = pos;
        return TRUE;
    }
    else
        return FALSE;
}
 
bool wxSimpleHtmlParser::ReadWord(wxString& str, bool eatIt)
{
    int pos = m_pos;
 
    if (!IsAlpha(GetChar(pos)))
        return FALSE;
 
    str += (wxChar) GetChar(pos) ;
    pos ++;
 
    while (!Eof(pos) && IsWordChar(GetChar(pos)))
    {
        str += (wxChar) GetChar(pos);
        pos ++;
    }
    if (eatIt)
        m_pos = pos;
    return TRUE;
}
 
bool wxSimpleHtmlParser::ReadNumber(wxString& str, bool eatIt)
{
    int pos = m_pos;
 
    if (!IsNumeric(GetChar(pos)))
        return FALSE;
 
    str += (wxChar) GetChar(pos) ;
    pos ++;
 
    while (!Eof(pos) && IsNumeric(GetChar(pos)))
    {
        str += (wxChar) GetChar(pos);
        pos ++;
    }
    if (eatIt)
        m_pos = pos;
    return TRUE;
}
 
// Could be number, string, whatever, but read up until whitespace or end of tag (but not a quoted string)
bool wxSimpleHtmlParser::ReadLiteral(wxString& str, bool eatIt)
{
    int pos = m_pos;
 
    while (!Eof(pos) && !IsWhitespace(GetChar(pos)) && !IsTagEndBracket(GetChar(pos)) && GetChar(pos) != wxT('='))
    {
        str += GetChar(pos);
        pos ++;
    }
    if (eatIt)
        m_pos = pos;
    return TRUE;
}
 
bool wxSimpleHtmlParser::IsTagClose()
{
    return Matches(wxT("</"));
}
 
bool wxSimpleHtmlParser::IsComment()
{
    return Matches(wxT("<!--"));
}
 
bool wxSimpleHtmlParser::IsDirective()
{
    return Matches(wxT("<!"));
}
 
bool wxSimpleHtmlParser::IsString()
{
    return (GetChar(m_pos) == (int) '"') ;
}
 
bool wxSimpleHtmlParser::IsWord()
{
    return (IsAlpha(GetChar(m_pos)));
}
 
bool wxSimpleHtmlParser::IsTagStartBracket(int ch)
{
    return (ch == wxT('<'));
}
 
bool wxSimpleHtmlParser::IsTagEndBracket(int ch)
{
    return (ch == wxT('>'));
}
 
bool wxSimpleHtmlParser::IsWhitespace(int ch)
{
    return ((ch == 13) || (ch == 10) || (ch == 32) || (ch == (int) '\t')) ;
}
 
bool wxSimpleHtmlParser::IsAlpha(int ch)
{
    return (wxIsalpha((wxChar) ch) != 0);
}
 
bool wxSimpleHtmlParser::IsWordChar(int ch)
{
    return (wxIsalpha((wxChar) ch) != 0 || ch == wxT('-') || ch == wxT('_') || IsNumeric(ch));
}
 
bool wxSimpleHtmlParser::IsNumeric(int ch)
{
    return (wxIsdigit((wxChar) ch) != 0 || ch == wxT('-') || ch == wxT('.')) ;
}
 
// Matches this string (case insensitive)
bool wxSimpleHtmlParser::Matches(const wxString& tok, bool eatIt)
{
    wxString text(m_text.Mid(m_pos, tok.Length()));
    bool success = (text.CmpNoCase(tok) == 0) ;
    if (success && eatIt)
    {
        m_pos += tok.Length();
    }
    return success;
}
 
// Safe way of getting a character
int wxSimpleHtmlParser::GetChar(size_t i) const
{
    if (i >= m_length)
        return -1;
    return m_text[i];
}
 
void wxSimpleHtmlParser::Clear()
{
    if (m_topLevel)
        delete m_topLevel;
    m_topLevel = NULL;
    m_text = wxEmptyString;
    m_pos = 0;
    m_length = 0;
}
 
// Write this file
void wxSimpleHtmlParser::Write(wxOutputStream& stream)
{
    if (m_topLevel)
        m_topLevel->Write(stream);
}
 
bool wxSimpleHtmlParser::WriteFile(wxString& filename)
{
    wxFileOutputStream fstream(filename);
    if (fstream.Ok())
    {
        Write(fstream);
        return TRUE;
    }
    else
        return FALSE;
}
 
/*
 * wxSimpleHtmlTag
 * Representation of a tag or chunk of text
 */
 
wxSimpleHtmlTag::wxSimpleHtmlTag(const wxString& tagName, int tagType)
{
    m_name = tagName;
    m_type = tagType;
    m_attributes = NULL;
    m_children = NULL;
    m_parent = NULL;
    m_next = NULL;
}
 
wxSimpleHtmlTag::~wxSimpleHtmlTag()
{
    ClearAttributes();
    ClearChildren();
}
 
//// Operations
void wxSimpleHtmlTag::ClearAttributes()
{
    if (m_attributes)
    {
        wxSimpleHtmlAttribute* attr = m_attributes;
        while (attr)
        {
            wxSimpleHtmlAttribute* next = attr->m_next;
 
            attr->m_next = NULL;
            delete attr;
            attr = next;
        }
        m_attributes = NULL;
    }
}
 
wxSimpleHtmlAttribute* wxSimpleHtmlTag::FindAttribute(const wxString& name) const
{
    wxSimpleHtmlAttribute* attr = m_attributes;
    while (attr)
    {
        if (attr->GetName().CmpNoCase(name) == 0)
        {
            return attr;
        }
        attr = attr->m_next;
    }
    return NULL;
}
 
void wxSimpleHtmlTag::AppendAttribute(const wxString& name, const wxString& value)
{
    wxSimpleHtmlAttribute* attr = new wxSimpleHtmlAttribute(name, value);
    if (m_attributes)
    {
        // Find tail
        wxSimpleHtmlAttribute* last = m_attributes;
        while (last->m_next)
            last = last->m_next;
 
        last->m_next = attr;
    }
    else
        m_attributes = attr;
}
 
void wxSimpleHtmlTag::ClearChildren()
{
    if (m_children)
    {
        wxSimpleHtmlTag* child = m_children;
        while (child)
        {
            wxSimpleHtmlTag* next = child->m_next;
 
            child->m_next = NULL;
            delete child;
            child = next;
        }
        m_children = NULL;
    }
}
 
void wxSimpleHtmlTag::AppendTag(wxSimpleHtmlTag* tag)
{
    if (m_children)
    {
        // Find tail
        wxSimpleHtmlTag* last = m_children;
        while (last->m_next)
            last = last->m_next;
 
        last->m_next = tag;
        tag->m_parent = this;
    }
    else
        m_children = tag;
}
 
// Gets the text from this tag and its descendants
wxString wxSimpleHtmlTag::GetTagText()
{
    wxString text;
    if (m_children)
    {
        wxSimpleHtmlTag* tag = m_children;
        while (tag)
        {
            text += tag->GetTagText();
            tag = tag->m_next;
        }
        return text;
    }
    else if (GetType() == wxSimpleHtmlTag_Text)
        return GetText();
    else
        return wxEmptyString;
}
 
int wxSimpleHtmlTag::GetAttributeCount() const
{
    int count = 0;
    wxSimpleHtmlAttribute* attr = m_attributes;
    while (attr)
    {
        count ++;
        attr = attr->m_next;
    }
    return count;
}
 
wxSimpleHtmlAttribute* wxSimpleHtmlTag::GetAttribute(int i) const
{
    int count = 0;
    wxSimpleHtmlAttribute* attr = m_attributes;
    while (attr)
    {
        if (count == i)
            return attr;
        count ++;
        attr = attr->m_next;
    }
    return NULL;
}
 
int wxSimpleHtmlTag::GetChildCount() const
{
    int count = 0;
    wxSimpleHtmlTag* tag = m_children;
    while (tag)
    {
        count ++;
        tag = tag->m_next;
    }
    return count;
}
 
bool wxSimpleHtmlTag::HasAttribute(const wxString& name, const wxString& value) const
{
    wxSimpleHtmlAttribute* attr = FindAttribute(name);
 
    return (attr && (attr->GetValue().CmpNoCase(value) == 0)) ;
}
 
bool wxSimpleHtmlTag::HasAttribute(const wxString& name) const
{
    return FindAttribute(name) != NULL ;
}
 
bool wxSimpleHtmlTag::GetAttributeValue(wxString& value, const wxString& attrName)
{
    wxSimpleHtmlAttribute* attr = FindAttribute(attrName);
    if (attr)
    {
        value = attr->GetValue();
        return TRUE;
    }
    else
        return FALSE;
}
 
// Search forward from this tag until we find a tag with this name & attribute 
wxSimpleHtmlTag* wxSimpleHtmlTag::FindTag(const wxString& tagName, const wxString& attrName)
{
    wxSimpleHtmlTag* tag = m_next;
    while (tag)
    {
        if (tag->NameIs(tagName) && tag->FindAttribute(attrName))
            return tag;
 
        tag = tag->m_next;
    }
    return NULL;
}
 
bool wxSimpleHtmlTag::FindTextUntilTagClose(wxString& text, const wxString& tagName)
{
    wxSimpleHtmlTag* tag = this;
    while (tag)
    {
        if (tag->GetType() == wxSimpleHtmlTag_Close && tag->NameIs(tagName))
            return TRUE;
 
        if (tag->GetType() == wxSimpleHtmlTag_Text)
            text += tag->GetText();
 
        tag = tag->m_next;
    }
    return TRUE;
}
 
 
wxSimpleHtmlTag* wxSimpleHtmlTag::GetChild(int i) const
{
    int count = 0;
    wxSimpleHtmlTag* tag = m_children;
    while (tag)
    {
        if (count == i)
            return tag;
 
        count ++;
        tag = tag->m_next;
    }
    return NULL;
}
 
void wxSimpleHtmlTag::Write(wxOutputStream& stream)
{
    switch (GetType())
    {
    case wxSimpleHtmlTag_Text:
        {
            stream << m_text;
            break;
        }
    case wxSimpleHtmlTag_Open:
        {
            stream << "<" << m_name;
            if (GetAttributeCount() > 0)
                stream << " ";
            int i;
            for (i = 0; i < GetAttributeCount(); i++)
            {
                wxSimpleHtmlAttribute* attr = GetAttribute(i);
                attr->Write(stream);
                if (i < GetAttributeCount() - 1)
                    stream << " ";
            }
            stream << ">\n";
            break;
        }
    case wxSimpleHtmlTag_Directive:
        {
            stream << "<!" << m_name << " ";
            int i;
            for (i = 0; i < GetAttributeCount(); i++)
            {
                wxSimpleHtmlAttribute* attr = GetAttribute(i);
                attr->Write(stream);
                if (i < GetAttributeCount() - 1)
                    stream << " ";
            }
            stream << ">\n";
            break;
        }
    case wxSimpleHtmlTag_Close:
        {
            stream << "</" << m_name << ">\n";
            break;
        }
    default:
        {
            break;
        }
    }
    wxSimpleHtmlTag* tag = m_children;
    while (tag)
    {
        tag->Write(stream);
        tag = tag->m_next;
    }
 
}
 
void wxSimpleHtmlAttribute::Write(wxOutputStream& stream)
{
    if (m_value.IsEmpty())
        stream << m_name;
    else
    {
        stream << m_name;
        stream << "=\"";
        stream << m_value;
        stream << "\"";
    }
}

Browse

Tools

Subversion Repositories openrisc_me

[/] [openrisc/] [trunk/] [rtos/] [ecos-2.0/] [tools/] [src/] [tools/] [configtool/] [standalone/] [wxwin/] [htmlparser.cpp] - Blame information for rev 438

Line No.	Rev	Author	Line
1	26	unneback	`//####COPYRIGHTBEGIN####`
2			`//`
3			`// ----------------------------------------------------------------------------`
4			`// Copyright (C) 1998, 1999, 2000 Red Hat, Inc.`
5			`//`
6			`// This program is part of the eCos host tools.`
7			`//`
8			`// This program is free software; you can redistribute it and/or modify it`
9			`// under the terms of the GNU General Public License as published by the Free`
10			`// Software Foundation; either version 2 of the License, or (at your option)`
11			`// any later version.`
12			`//`
13			`// This program is distributed in the hope that it will be useful, but WITHOUT`
14			`// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or`
15			`// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for`
16			`// more details.`
17			`//`
18			`// You should have received a copy of the GNU General Public License along with`
19			`// this program; if not, write to the Free Software Foundation, Inc.,`
20			`// 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.`
21			`//`
22			`// ----------------------------------------------------------------------------`
23			`//`
24			`//####COPYRIGHTEND####`
25			`// htmlparser.cpp :`
26			`//`
27			`//===========================================================================`
28			`//#####DESCRIPTIONBEGIN####`
29			`//`
30			`// Author(s): julians`
31			`// Contact(s): julians`
32			`// Date: 2001/04/04`
33			`// Version: $Id: htmlparser.cpp,v 1.1.1.1 2004-02-14 13:28:46 phoenix Exp $`
34			`// Purpose:`
35			`// Description: HTML parser/HTML Help file generator`
36			`// Requires:`
37			`// Provides:`
38			`// See also:`
39			`// Known bugs:`
40			`// Usage:`
41			`//`
42			`//####DESCRIPTIONEND####`
43			`//`
44			`//===========================================================================`
45
46			`// ============================================================================`
47			`// declarations`
48			`// ============================================================================`
49
50			`// ----------------------------------------------------------------------------`
51			`// headers`
52			`// ----------------------------------------------------------------------------`
53			`#ifdef __GNUG__`
54			`#pragma implementation "htmlparser.h"`
55			`#endif`
56
57			`// Includes other headers for precompiled compilation`
58			`#include "ecpch.h"`
59
60			`#ifdef __BORLANDC__`
61			`#pragma hdrstop`
62			`#endif`
63
64			`#include "wx/textfile.h"`
65			`#include "wx/wfstream.h"`
66
67			`#include "ecutils.h"`
68			`#include "htmlparser.h"`
69
70			`/*`
71			`* wxSimpleHtmlAttribute`
72			`* Representation of an attribute`
73			`*/`
74
75			`wxSimpleHtmlParser::wxSimpleHtmlParser()`
76			`{`
77			`m_topLevel = NULL;`
78			`m_pos = 0;`
79			`}`
80
81
82			`wxSimpleHtmlParser::~wxSimpleHtmlParser()`
83			`{`
84			`Clear();`
85			`}`
86
87			`bool wxSimpleHtmlParser::ParseFile(const wxString& filename)`
88			`{`
89			`wxTextFile textFile;`
90
91			`if (textFile.Open(filename))`
92			`{`
93			`wxString text;`
94			`wxString line;`
95			`int i;`
96			`int count = textFile.GetLineCount();`
97			`for (i = 0; i < count; i++)`
98			`{`
99			`if (i == 0)`
100			`line = textFile.GetFirstLine();`
101			`else`
102			`line = textFile.GetNextLine();`
103
104			`text += line;`
105			`if (i != (count - 1))`
106			`text += wxT("\n");`
107			`}`
108
109			`#if 0`
110			`for ( line = textFile.GetFirstLine(); !textFile.Eof(); line = textFile.GetNextLine() )`
111			`{`
112			`text += line;`
113			`if (!textFile.Eof())`
114			`text += wxT("\n");`
115			`}`
116			`#endif`
117
118			`return ParseString(text);`
119			`}`
120			`else`
121			`return FALSE;`
122			`}`
123
124			`bool wxSimpleHtmlParser::ParseString(const wxString& str)`
125			`{`
126			`Clear();`
127
128			`m_pos = 0;`
129			`m_text = str;`
130			`m_length = str.Length();`
131
132			`m_topLevel = new wxSimpleHtmlTag(wxT("TOPLEVEL"), wxSimpleHtmlTag_TopLevel);`
133
134			`return ParseHtml(m_topLevel);`
135			`}`
136
137			`// Main recursive parsing function`
138			`bool wxSimpleHtmlParser::ParseHtml(wxSimpleHtmlTag* parent)`
139			`{`
140			`while (!Eof())`
141			`{`
142			`EatWhitespace();`
143			`if (IsComment())`
144			`{`
145			`ParseComment();`
146			`}`
147			`else if (IsDirective())`
148			`{`
149			`wxSimpleHtmlTag* tag = ParseDirective();`
150			`if (tag)`
151			`parent->AppendTag(tag);`
152			`}`
153			`else if (IsTagClose())`
154			`{`
155			`wxSimpleHtmlTag* tag = ParseTagClose();`
156			`if (tag)`
157			`parent->AppendTag(tag);`
158			`}`
159			`else if (IsTagStartBracket(GetChar(m_pos)))`
160			`{`
161			`wxSimpleHtmlTag* tag = ParseTagHeader();`
162			`if (tag)`
163			`parent->AppendTag(tag);`
164			`}`
165			`else`
166			`{`
167			`// Just a text string`
168			`wxString text;`
169			`ParseText(text);`
170
171			`wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(wxT("TEXT"), wxSimpleHtmlTag_Text);`
172			`tag->SetText(text);`
173			`parent->AppendTag(tag);`
174			`}`
175			`}`
176			`return TRUE;`
177			`}`
178
179			`// Plain text, up until an angled bracket`
180			`bool wxSimpleHtmlParser::ParseText(wxString& text)`
181			`{`
182			`while (!Eof() && GetChar(m_pos) != wxT('<'))`
183			`{`
184			`text += GetChar(m_pos);`
185			`m_pos ++;`
186			`}`
187			`return TRUE;`
188			`}`
189
190			`wxSimpleHtmlTag* wxSimpleHtmlParser::ParseTagHeader()`
191			`{`
192			`if (IsTagStartBracket(GetChar(m_pos)))`
193			`{`
194			`m_pos ++;`
195			`EatWhitespace();`
196
197			`wxString word;`
198			`ReadWord(word, TRUE);`
199
200			`EatWhitespace();`
201
202			`wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Open);`
203
204			`ParseAttributes(tag);`
205
206			`EatWhitespace();`
207
208			`if (IsTagEndBracket(GetChar(m_pos)))`
209			`m_pos ++;`
210
211			`return tag;`
212			`}`
213			`else`
214			`return NULL;`
215			`}`
216
217			`wxSimpleHtmlTag* wxSimpleHtmlParser::ParseTagClose()`
218			`{`
219			`Matches(wxT("</"), TRUE);`
220
221			`EatWhitespace();`
222
223			`wxString word;`
224			`ReadWord(word, TRUE);`
225
226			`EatWhitespace();`
227			`m_pos ++;`
228
229			`wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Close);`
230			`return tag;`
231			`}`
232
233			`bool wxSimpleHtmlParser::ParseAttributes(wxSimpleHtmlTag* tag)`
234			`{`
235			`// Parse attributes of a tag header until we reach >`
236			`while (!IsTagEndBracket(GetChar(m_pos)) && !Eof())`
237			`{`
238			`EatWhitespace();`
239
240			`wxString attrName, attrValue;`
241
242			`if (IsString())`
243			`{`
244			`ReadString(attrName, TRUE);`
245			`tag->AppendAttribute(attrName, wxEmptyString);`
246			`}`
247			`else if (IsNumeric(GetChar(m_pos)))`
248			`{`
249			`ReadNumber(attrName, TRUE);`
250			`tag->AppendAttribute(attrName, wxEmptyString);`
251			`}`
252			`else`
253			`{`
254			`// Try to read an attribute name/value pair, or at least a name`
255			`// without the value`
256			`ReadLiteral(attrName, TRUE);`
257			`EatWhitespace();`
258
259			`if (GetChar(m_pos) == wxT('='))`
260			`{`
261			`m_pos ++;`
262			`EatWhitespace();`
263
264			`if (IsString())`
265			`ReadString(attrValue, TRUE);`
266			`else if (!Eof() && !IsTagEndBracket(GetChar(m_pos)))`
267			`ReadLiteral(attrValue, TRUE);`
268			`}`
269			`if (!attrName.IsEmpty())`
270			`tag->AppendAttribute(attrName, attrValue);`
271			`}`
272			`}`
273			`return TRUE;`
274			`}`
275
276			`// e.g. <!DOCTYPE ....>`
277			`wxSimpleHtmlTag* wxSimpleHtmlParser::ParseDirective()`
278			`{`
279			`Matches(wxT("<!"), TRUE);`
280
281			`EatWhitespace();`
282
283			`wxString word;`
284			`ReadWord(word, TRUE);`
285
286			`EatWhitespace();`
287
288			`wxSimpleHtmlTag* tag = new wxSimpleHtmlTag(word, wxSimpleHtmlTag_Directive);`
289
290			`ParseAttributes(tag);`
291
292			`EatWhitespace();`
293
294			`if (IsTagEndBracket(GetChar(m_pos)))`
295			`m_pos ++;`
296
297			`return tag;`
298			`}`
299
300			`bool wxSimpleHtmlParser::ParseComment()`
301			`{`
302			`// Eat the comment tag start`
303			`Matches(wxT("<!--"), TRUE);`
304
305			`while (!Eof() && !Matches(wxT("-->"), TRUE))`
306			`{`
307			`m_pos ++;`
308			`}`
309
310			`return TRUE;`
311			`}`
312
313			`bool wxSimpleHtmlParser::EatWhitespace()`
314			`{`
315			`while (!Eof() && IsWhitespace(GetChar(m_pos)))`
316			`m_pos ++;`
317			`return TRUE;`
318			`}`
319
320			`bool wxSimpleHtmlParser::EatWhitespace(int& pos)`
321			`{`
322			`while (!Eof(pos) && IsWhitespace(GetChar(pos)))`
323			`pos ++;`
324			`return TRUE;`
325			`}`
326
327			`bool wxSimpleHtmlParser::ReadString(wxString& str, bool eatIt)`
328			`{`
329			`int pos = m_pos;`
330			`if (GetChar(pos) == (int) '"')`
331			`{`
332			`pos ++;`
333			`while (!Eof(pos) && GetChar(pos) != (int) '"')`
334			`{`
335			`// TODO: how are quotes escaped in HTML?`
336			`str += (wxChar) GetChar(pos);`
337			`pos ++;`
338			`}`
339			`if (GetChar(pos) == (int) '"')`
340			`pos ++;`
341			`if (eatIt)`
342			`m_pos = pos;`
343			`return TRUE;`
344			`}`
345			`else`
346			`return FALSE;`
347			`}`
348
349			`bool wxSimpleHtmlParser::ReadWord(wxString& str, bool eatIt)`
350			`{`
351			`int pos = m_pos;`
352
353			`if (!IsAlpha(GetChar(pos)))`
354			`return FALSE;`
355
356			`str += (wxChar) GetChar(pos) ;`
357			`pos ++;`
358
359			`while (!Eof(pos) && IsWordChar(GetChar(pos)))`
360			`{`
361			`str += (wxChar) GetChar(pos);`
362			`pos ++;`
363			`}`
364			`if (eatIt)`
365			`m_pos = pos;`
366			`return TRUE;`
367			`}`
368
369			`bool wxSimpleHtmlParser::ReadNumber(wxString& str, bool eatIt)`
370			`{`
371			`int pos = m_pos;`
372
373			`if (!IsNumeric(GetChar(pos)))`
374			`return FALSE;`
375
376			`str += (wxChar) GetChar(pos) ;`
377			`pos ++;`
378
379			`while (!Eof(pos) && IsNumeric(GetChar(pos)))`
380			`{`
381			`str += (wxChar) GetChar(pos);`
382			`pos ++;`
383			`}`
384			`if (eatIt)`
385			`m_pos = pos;`
386			`return TRUE;`
387			`}`
388
389			`// Could be number, string, whatever, but read up until whitespace or end of tag (but not a quoted string)`
390			`bool wxSimpleHtmlParser::ReadLiteral(wxString& str, bool eatIt)`
391			`{`
392			`int pos = m_pos;`
393
394			`while (!Eof(pos) && !IsWhitespace(GetChar(pos)) && !IsTagEndBracket(GetChar(pos)) && GetChar(pos) != wxT('='))`
395			`{`
396			`str += GetChar(pos);`
397			`pos ++;`
398			`}`
399			`if (eatIt)`
400			`m_pos = pos;`
401			`return TRUE;`
402			`}`
403
404			`bool wxSimpleHtmlParser::IsTagClose()`
405			`{`
406			`return Matches(wxT("</"));`
407			`}`
408
409			`bool wxSimpleHtmlParser::IsComment()`
410			`{`
411			`return Matches(wxT("<!--"));`
412			`}`
413
414			`bool wxSimpleHtmlParser::IsDirective()`
415			`{`
416			`return Matches(wxT("<!"));`
417			`}`
418
419			`bool wxSimpleHtmlParser::IsString()`
420			`{`
421			`return (GetChar(m_pos) == (int) '"') ;`
422			`}`
423
424			`bool wxSimpleHtmlParser::IsWord()`
425			`{`
426			`return (IsAlpha(GetChar(m_pos)));`
427			`}`
428
429			`bool wxSimpleHtmlParser::IsTagStartBracket(int ch)`
430			`{`
431			`return (ch == wxT('<'));`
432			`}`
433
434			`bool wxSimpleHtmlParser::IsTagEndBracket(int ch)`
435			`{`
436			`return (ch == wxT('>'));`
437			`}`
438
439			`bool wxSimpleHtmlParser::IsWhitespace(int ch)`
440			`{`
441			`return ((ch == 13) \|\| (ch == 10) \|\| (ch == 32) \|\| (ch == (int) '\t')) ;`
442			`}`
443
444			`bool wxSimpleHtmlParser::IsAlpha(int ch)`
445			`{`
446			`return (wxIsalpha((wxChar) ch) != 0);`
447			`}`
448
449			`bool wxSimpleHtmlParser::IsWordChar(int ch)`
450			`{`
451			`return (wxIsalpha((wxChar) ch) != 0 \|\| ch == wxT('-') \|\| ch == wxT('_') \|\| IsNumeric(ch));`
452			`}`
453
454			`bool wxSimpleHtmlParser::IsNumeric(int ch)`
455			`{`
456			`return (wxIsdigit((wxChar) ch) != 0 \|\| ch == wxT('-') \|\| ch == wxT('.')) ;`
457			`}`
458
459			`// Matches this string (case insensitive)`
460			`bool wxSimpleHtmlParser::Matches(const wxString& tok, bool eatIt)`
461			`{`
462			`wxString text(m_text.Mid(m_pos, tok.Length()));`
463			`bool success = (text.CmpNoCase(tok) == 0) ;`
464			`if (success && eatIt)`
465			`{`
466			`m_pos += tok.Length();`
467			`}`
468			`return success;`
469			`}`
470
471			`// Safe way of getting a character`
472			`int wxSimpleHtmlParser::GetChar(size_t i) const`
473			`{`
474			`if (i >= m_length)`
475			`return -1;`
476			`return m_text[i];`
477			`}`
478
479			`void wxSimpleHtmlParser::Clear()`
480			`{`
481			`if (m_topLevel)`
482			`delete m_topLevel;`
483			`m_topLevel = NULL;`
484			`m_text = wxEmptyString;`
485			`m_pos = 0;`
486			`m_length = 0;`
487			`}`
488
489			`// Write this file`
490			`void wxSimpleHtmlParser::Write(wxOutputStream& stream)`
491			`{`
492			`if (m_topLevel)`
493			`m_topLevel->Write(stream);`
494			`}`
495
496			`bool wxSimpleHtmlParser::WriteFile(wxString& filename)`
497			`{`
498			`wxFileOutputStream fstream(filename);`
499			`if (fstream.Ok())`
500			`{`
501			`Write(fstream);`
502			`return TRUE;`
503			`}`
504			`else`
505			`return FALSE;`
506			`}`
507
508			`/*`
509			`* wxSimpleHtmlTag`
510			`* Representation of a tag or chunk of text`
511			`*/`
512
513			`wxSimpleHtmlTag::wxSimpleHtmlTag(const wxString& tagName, int tagType)`
514			`{`
515			`m_name = tagName;`
516			`m_type = tagType;`
517			`m_attributes = NULL;`
518			`m_children = NULL;`
519			`m_parent = NULL;`
520			`m_next = NULL;`
521			`}`
522
523			`wxSimpleHtmlTag::~wxSimpleHtmlTag()`
524			`{`
525			`ClearAttributes();`
526			`ClearChildren();`
527			`}`
528
529			`//// Operations`
530			`void wxSimpleHtmlTag::ClearAttributes()`
531			`{`
532			`if (m_attributes)`
533			`{`
534			`wxSimpleHtmlAttribute* attr = m_attributes;`
535			`while (attr)`
536			`{`
537			`wxSimpleHtmlAttribute* next = attr->m_next;`
538
539			`attr->m_next = NULL;`
540			`delete attr;`
541			`attr = next;`
542			`}`
543			`m_attributes = NULL;`
544			`}`
545			`}`
546
547			`wxSimpleHtmlAttribute* wxSimpleHtmlTag::FindAttribute(const wxString& name) const`
548			`{`
549			`wxSimpleHtmlAttribute* attr = m_attributes;`
550			`while (attr)`
551			`{`
552			`if (attr->GetName().CmpNoCase(name) == 0)`
553			`{`
554			`return attr;`
555			`}`
556			`attr = attr->m_next;`
557			`}`
558			`return NULL;`
559			`}`
560
561			`void wxSimpleHtmlTag::AppendAttribute(const wxString& name, const wxString& value)`
562			`{`
563			`wxSimpleHtmlAttribute* attr = new wxSimpleHtmlAttribute(name, value);`
564			`if (m_attributes)`
565			`{`
566			`// Find tail`
567			`wxSimpleHtmlAttribute* last = m_attributes;`
568			`while (last->m_next)`
569			`last = last->m_next;`
570
571			`last->m_next = attr;`
572			`}`
573			`else`
574			`m_attributes = attr;`
575			`}`
576
577			`void wxSimpleHtmlTag::ClearChildren()`
578			`{`
579			`if (m_children)`
580			`{`
581			`wxSimpleHtmlTag* child = m_children;`
582			`while (child)`
583			`{`
584			`wxSimpleHtmlTag* next = child->m_next;`
585
586			`child->m_next = NULL;`
587			`delete child;`
588			`child = next;`
589			`}`
590			`m_children = NULL;`
591			`}`
592			`}`
593
594			`void wxSimpleHtmlTag::AppendTag(wxSimpleHtmlTag* tag)`
595			`{`
596			`if (m_children)`
597			`{`
598			`// Find tail`
599			`wxSimpleHtmlTag* last = m_children;`
600			`while (last->m_next)`
601			`last = last->m_next;`
602
603			`last->m_next = tag;`
604			`tag->m_parent = this;`
605			`}`
606			`else`
607			`m_children = tag;`
608			`}`
609
610			`// Gets the text from this tag and its descendants`
611			`wxString wxSimpleHtmlTag::GetTagText()`
612			`{`
613			`wxString text;`
614			`if (m_children)`
615			`{`
616			`wxSimpleHtmlTag* tag = m_children;`
617			`while (tag)`
618			`{`
619			`text += tag->GetTagText();`
620			`tag = tag->m_next;`
621			`}`
622			`return text;`
623			`}`
624			`else if (GetType() == wxSimpleHtmlTag_Text)`
625			`return GetText();`
626			`else`
627			`return wxEmptyString;`
628			`}`
629
630			`int wxSimpleHtmlTag::GetAttributeCount() const`
631			`{`
632			`int count = 0;`
633			`wxSimpleHtmlAttribute* attr = m_attributes;`
634			`while (attr)`
635			`{`
636			`count ++;`
637			`attr = attr->m_next;`
638			`}`
639			`return count;`
640			`}`
641
642			`wxSimpleHtmlAttribute* wxSimpleHtmlTag::GetAttribute(int i) const`
643			`{`
644			`int count = 0;`
645			`wxSimpleHtmlAttribute* attr = m_attributes;`
646			`while (attr)`
647			`{`
648			`if (count == i)`
649			`return attr;`
650			`count ++;`
651			`attr = attr->m_next;`
652			`}`
653			`return NULL;`
654			`}`
655
656			`int wxSimpleHtmlTag::GetChildCount() const`
657			`{`
658			`int count = 0;`
659			`wxSimpleHtmlTag* tag = m_children;`
660			`while (tag)`
661			`{`
662			`count ++;`
663			`tag = tag->m_next;`
664			`}`
665			`return count;`
666			`}`
667
668			`bool wxSimpleHtmlTag::HasAttribute(const wxString& name, const wxString& value) const`
669			`{`
670			`wxSimpleHtmlAttribute* attr = FindAttribute(name);`
671
672			`return (attr && (attr->GetValue().CmpNoCase(value) == 0)) ;`
673			`}`
674
675			`bool wxSimpleHtmlTag::HasAttribute(const wxString& name) const`
676			`{`
677			`return FindAttribute(name) != NULL ;`
678			`}`
679
680			`bool wxSimpleHtmlTag::GetAttributeValue(wxString& value, const wxString& attrName)`
681			`{`
682			`wxSimpleHtmlAttribute* attr = FindAttribute(attrName);`
683			`if (attr)`
684			`{`
685			`value = attr->GetValue();`
686			`return TRUE;`
687			`}`
688			`else`
689			`return FALSE;`
690			`}`
691
692			`// Search forward from this tag until we find a tag with this name & attribute`
693			`wxSimpleHtmlTag* wxSimpleHtmlTag::FindTag(const wxString& tagName, const wxString& attrName)`
694			`{`
695			`wxSimpleHtmlTag* tag = m_next;`
696			`while (tag)`
697			`{`
698			`if (tag->NameIs(tagName) && tag->FindAttribute(attrName))`
699			`return tag;`
700
701			`tag = tag->m_next;`
702			`}`
703			`return NULL;`
704			`}`
705
706			`bool wxSimpleHtmlTag::FindTextUntilTagClose(wxString& text, const wxString& tagName)`
707			`{`
708			`wxSimpleHtmlTag* tag = this;`
709			`while (tag)`
710			`{`
711			`if (tag->GetType() == wxSimpleHtmlTag_Close && tag->NameIs(tagName))`
712			`return TRUE;`
713
714			`if (tag->GetType() == wxSimpleHtmlTag_Text)`
715			`text += tag->GetText();`
716
717			`tag = tag->m_next;`
718			`}`
719			`return TRUE;`
720			`}`
721
722
723			`wxSimpleHtmlTag* wxSimpleHtmlTag::GetChild(int i) const`
724			`{`
725			`int count = 0;`
726			`wxSimpleHtmlTag* tag = m_children;`
727			`while (tag)`
728			`{`
729			`if (count == i)`
730			`return tag;`
731
732			`count ++;`
733			`tag = tag->m_next;`
734			`}`
735			`return NULL;`
736			`}`
737
738			`void wxSimpleHtmlTag::Write(wxOutputStream& stream)`
739			`{`
740			`switch (GetType())`
741			`{`
742			`case wxSimpleHtmlTag_Text:`
743			`{`
744			`stream << m_text;`
745			`break;`
746			`}`
747			`case wxSimpleHtmlTag_Open:`
748			`{`
749			`stream << "<" << m_name;`
750			`if (GetAttributeCount() > 0)`
751			`stream << " ";`
752			`int i;`
753			`for (i = 0; i < GetAttributeCount(); i++)`
754			`{`
755			`wxSimpleHtmlAttribute* attr = GetAttribute(i);`
756			`attr->Write(stream);`
757			`if (i < GetAttributeCount() - 1)`
758			`stream << " ";`
759			`}`
760			`stream << ">\n";`
761			`break;`
762			`}`
763			`case wxSimpleHtmlTag_Directive:`
764			`{`
765			`stream << "<!" << m_name << " ";`
766			`int i;`
767			`for (i = 0; i < GetAttributeCount(); i++)`
768			`{`
769			`wxSimpleHtmlAttribute* attr = GetAttribute(i);`
770			`attr->Write(stream);`
771			`if (i < GetAttributeCount() - 1)`
772			`stream << " ";`
773			`}`
774			`stream << ">\n";`
775			`break;`
776			`}`
777			`case wxSimpleHtmlTag_Close:`
778			`{`
779			`stream << "</" << m_name << ">\n";`
780			`break;`
781			`}`
782			`default:`
783			`{`
784			`break;`
785			`}`
786			`}`
787			`wxSimpleHtmlTag* tag = m_children;`
788			`while (tag)`
789			`{`
790			`tag->Write(stream);`
791			`tag = tag->m_next;`
792			`}`
793
794			`}`
795
796			`void wxSimpleHtmlAttribute::Write(wxOutputStream& stream)`
797			`{`
798			`if (m_value.IsEmpty())`
799			`stream << m_name;`
800			`else`
801			`{`
802			`stream << m_name;`
803			`stream << "=\"";`
804			`stream << m_value;`
805			`stream << "\"";`
806			`}`
807			`}`