/// <summary> Construct a page from a source.</summary>
/// <param name="source">The source of characters.
/// </param>
public Page(Source source)
{
if (null == source)
{
throw new System.ArgumentException("source cannot be null");
}
mSource = source;
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
/// <summary> Construct a page from the given string.</summary>
/// <param name="text">The HTML text.
/// </param>
/// <param name="charset"><em>Optional</em>. The character set encoding that will
/// be reported by {@link #getEncoding}. If charset is <code>null</code>
/// the default character set is used.
/// </param>
public Page(System.String text, System.String charset)
{
if (null == text)
{
throw new System.ArgumentException("text cannot be null");
}
if (null == charset)
{
charset = DEFAULT_CHARSET;
}
mSource = new StringSource(text, charset);
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
/// <summary> Construct a page from a stream encoded with the given charset.</summary>
/// <param name="stream">The source of bytes.
/// </param>
/// <param name="charset">The encoding used.
/// If null, defaults to the <code>DEFAULT_CHARSET</code>.
/// </param>
/// <exception cref="UnsupportedEncodingException">If the given charset
/// is not supported.
/// </exception>
public Page(System.IO.Stream stream, System.String charset)
{
if (null == stream)
{
throw new System.ArgumentException("stream cannot be null");
}
if (null == charset)
{
charset = DEFAULT_CHARSET;
}
mSource = new InputStreamSource(stream, charset);
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
private void GetPageContent(HttpProtocol obProtocol, bool bIsRefresh)
{
if (m_bHasContent && !bIsRefresh)
{
return;
}
if (obProtocol == null)
{
throw new ArgumentNullException("obProtocol", "Null HttpProtocol object specified");
}
lock (this)
{
ParserStream stream = null;
System.String type = String.Empty;
System.String charset = String.Empty;
try
{
m_obProtocolOutput = obProtocol.GetProtocolOutput();
if (m_obProtocolOutput.Status.Code == HttpProtocolStatus.SUCCESS)
{
m_bHasContent = true;
this.m_HttpContentProperties = m_obProtocolOutput.Content.ContentProperties;
type = this.ContentType;
charset = GetCharset(type);
stream = new ParserStream(new System.IO.MemoryStream(m_obProtocolOutput.Content.ContentData));
}
if (null != stream)
{
mSource = new InputStreamSource(stream, charset, m_obProtocolOutput.Content.ContentData.Length);
}
}
catch (System.Exception e)
{
throw new ParserException("Failed to get page content", e);
}
mUrl = obProtocol.URL.ToString();
mIndex = new PageIndex(this);
}
}
/// <summary> Reset the page by resetting the source of characters.</summary>
public virtual void Reset()
{
Source.Reset();
mIndex = new PageIndex(this); // todo: is this really necessary?
}
/// <summary> Reset the page by resetting the source of characters.</summary>
public virtual void Reset()
{
Source.Reset();
mIndex = new PageIndex(this); // todo: is this really necessary?
}
/// <summary> Construct a page from a source.</summary>
/// <param name="source">The source of characters.
/// </param>
public Page(Source source)
{
if (null == source)
throw new System.ArgumentException("source cannot be null");
mSource = source;
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
/// <summary> Construct a page from the given string.</summary>
/// <param name="text">The HTML text.
/// </param>
/// <param name="charset"><em>Optional</em>. The character set encoding that will
/// be reported by {@link #getEncoding}. If charset is <code>null</code>
/// the default character set is used.
/// </param>
public Page(System.String text, System.String charset)
{
if (null == text)
throw new System.ArgumentException("text cannot be null");
if (null == charset)
charset = DEFAULT_CHARSET;
mSource = new StringSource(text, charset);
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
/// <summary> Construct a page from a stream encoded with the given charset.</summary>
/// <param name="stream">The source of bytes.
/// </param>
/// <param name="charset">The encoding used.
/// If null, defaults to the <code>DEFAULT_CHARSET</code>.
/// </param>
/// <exception cref="UnsupportedEncodingException">If the given charset
/// is not supported.
/// </exception>
public Page(System.IO.Stream stream, System.String charset)
{
if (null == stream)
throw new System.ArgumentException("stream cannot be null");
if (null == charset)
charset = DEFAULT_CHARSET;
mSource = new InputStreamSource(stream, charset);
mIndex = new PageIndex(this);
mUrl = null;
mBaseUrl = null;
}
private void GetPageContent(HttpProtocol obProtocol, bool bIsRefresh)
{
if(m_bHasContent && !bIsRefresh)
{
return;
}
if(obProtocol == null)
{
throw new ArgumentNullException("obProtocol", "Null HttpProtocol object specified");
}
lock(this)
{
ParserStream stream = null;
System.String type = String.Empty;
System.String charset = String.Empty;
try
{
m_obProtocolOutput = obProtocol.GetProtocolOutput();
if (m_obProtocolOutput.Status.Code == HttpProtocolStatus.SUCCESS)
{
m_bHasContent = true;
this.m_HttpContentProperties = m_obProtocolOutput.Content.ContentProperties;
type = this.ContentType;
charset = GetCharset(type);
stream = new ParserStream(new System.IO.MemoryStream(m_obProtocolOutput.Content.ContentData));
}
if (null != stream)
{
mSource = new InputStreamSource(stream,charset,m_obProtocolOutput.Content.ContentData.Length);
}
}
catch (System.Exception e)
{
throw new ParserException("Failed to get page content", e);
}
mUrl = obProtocol.URL.ToString();
mIndex = new PageIndex(this);
}
}