public override bool Read()
{
PDFTextOp op = null;
string style;
while (this.MoveToNext())
{
if (this.InnerReader.NodeType == XmlNodeType.Element)
{
if (this.InnerReader.Name.Equals("br", StringComparison.CurrentCultureIgnoreCase))
{
op = new PDFTextNewLineOp();
break;
}
else if (this.IsFontStyleOp(this.InnerReader.Name, out style))
{
op = new PDFTextFontOp(style, true);
break;
}
else if (this.InnerReader.Name.Equals("span", StringComparison.CurrentCultureIgnoreCase))
{
throw new NotSupportedException("Span is not a currently supported Component");
}
}
else if (this.InnerReader.NodeType == XmlNodeType.Text)
{
string text = this.StripWhiteSpace(this.InnerReader.Value.Trim(), op != null);
op = new PDFTextDrawOp(text);
break;
}
else if (this.InnerReader.NodeType == XmlNodeType.EndElement)
{
if (this.IsFontStyleOp(this.InnerReader.Name, out style))
{
op = new PDFTextFontOp(style, false);
break;
}
}
}
this._op = op;
return(op != null);
}
//
// public methods
//
/// <summary>
/// Takes the provided text and splits it into a list of
/// tokens that can be read in sequence to generate the text
/// </summary>
/// <param name="text">The full text to be read</param>
/// <returns></returns>
public virtual List <PDFTextOp> Parse(string text, bool preserveWhitespace)
{
List <PDFTextOp> all = new List <PDFTextOp>();
int lastindex = 0;
string normalized;
string value;
int index = text.IndexOf('<');
bool first = true;
while (index >= 0)
{
if (lastindex < index)
{
//We have some text between the last point and the position of the <, so we need to normalise and add
value = text.Substring(lastindex, index - lastindex);
if (preserveWhitespace)
{
string[] lines = WhitespaceText(first, value);
for (int i = 0; i < lines.Length; i++)
{
string txt = lines[i];
if (i > 0)
{
all.Add(new PDFTextNewLineOp());
}
if (string.IsNullOrEmpty(txt))
{
all.Add(new PDFTextDrawOp(" "));
}
else
{
all.Add(new PDFTextDrawOp(txt));
}
}
}
else
{
normalized = NormalizeText(first, value);
if (!string.IsNullOrEmpty(normalized))
{
all.Add(new PDFTextDrawOp(normalized));
}
}
}
//check the validity of the element
int endindex = text.IndexOf('>', index);
if (endindex < 0) //Make sure it is closed
{
throw new PDFXmlFormatException("No closing brace found after oening brace - character #" + index.ToString());
}
int nextindex = text.IndexOf('<', index + 1); //and make sure a new element is not opened before
if (nextindex > 0 && endindex > nextindex)
{
throw new PDFXmlFormatException("No closing brace found after oening brace - character #" + index.ToString());
}
value = text.Substring(index + 1, (endindex - index) - 1);
//We have element content - parse and if valid add
PDFTextOp ele = ParseElement(value);
if (ele is PDFTextNewLineOp)
{
first = true;
}
else
{
first = false;
}
if (null != ele)
{
all.Add(ele);
}
lastindex = endindex + 1;
//check to see if there are some more elements
if (lastindex < text.Length)
{
index = text.IndexOf('<', lastindex);
}
else
{
index = -1;
}
}
//No more elements, so just make sure we cature any trailing text
if (lastindex < text.Length)
{
value = text.Substring(lastindex);
if (preserveWhitespace)
{
string[] lines = WhitespaceText(first, value);
for (int i = 0; i < lines.Length; i++)
{
if (i > 0)
{
all.Add(new PDFTextNewLineOp());
}
string txt = lines[i];
if (string.IsNullOrEmpty(txt))
{
all.Add(new PDFTextDrawOp(" "));
}
else
{
all.Add(new PDFTextDrawOp(txt));
}
}
}
else
{
normalized = NormalizeText(first, value);
if (!string.IsNullOrEmpty(normalized))
{
PDFTextDrawOp op = new PDFTextDrawOp(normalized);
all.Add(op);
}
}
}
return(all);
}
