/// <summary>
/// Attempt to parse the given data stream, returning an indicator of parse progress
/// </summary>
/// <param name="StartingToken">The token immediately preceeding the starting index in Data stream</param>
/// <param name="Data">Raw byte stream to parse</param>
/// <param name="StartingIndex">0-based starting index into Data where StartingToken appears</param>
/// <param name="EndingIndex">Index into data stream where parsing ended (either successfully or unsuccessfully)</param>
/// <returns>Object parsed from data stream, or NULL if unable to parse. If NULL and EndingIndex is equal to Data.Length, parsing may be successful with more data</returns>
public static IPDFObject TryParse(string StartingToken, byte[] Data, int StartingIndex, out int EndingIndex)
{
if (!String.IsNullOrEmpty(StartingToken) && (StartingToken[0] == '<') && (!StartingToken.Equals("<<")))
{
List <byte> StringBytes = new List <byte>(StartingToken.Length);
bool HaveString = false;
EndingIndex = StartingIndex + 1;
while (!HaveString && (EndingIndex < Data.Length))
{
byte NextByte = Data[EndingIndex++];
if (NextByte == (byte)'>')
{
HaveString = true;
}
else if (!PDF.IsWhitespace(NextByte))
{
StringBytes.Add(NextByte);
}
}
return(new PDFHexString(Encoding.UTF8.GetString(StringBytes.ToArray())));
}
else
{
EndingIndex = StartingIndex;
return(null);
}
}
/// <summary>
/// Attempt to parse the given data stream, returning an indicator of parse progress
/// </summary>
/// <param name="StartingToken">The token immediately preceeding the starting index in Data stream</param>
/// <param name="Data">Raw byte stream to parse</param>
/// <param name="StartingIndex">0-based starting index into Data where StartingToken appears</param>
/// <param name="EndingIndex">Index into data stream where parsing ended (either successfully or unsuccessfully)</param>
/// <returns>Object parsed from data stream, or NULL if unable to parse. If NULL and EndingIndex is equal to Data.Length, parsing may be successful with more data</returns>
public static IPDFObject TryParse(string StartingToken, byte[] Data, int StartingIndex, out int EndingIndex)
{
EndingIndex = StartingIndex;
if (!String.IsNullOrEmpty(StartingToken) && (StartingToken[0] == '['))
{
PDFArray ObjectArray = new PDFArray();
EndingIndex = StartingIndex + 1;
while (EndingIndex < Data.Length)
{
IPDFObject nextObject = PDFObjectParser.Parse(Data, out EndingIndex, EndingIndex);
if (nextObject != null)
{
ObjectArray.Add(nextObject);
}
byte nextChar = PDF.Whitespace[0];
while (PDF.IsWhitespace(nextChar))
{
nextChar = Data[EndingIndex++];
}
if (nextChar == ']')
{
return(ObjectArray);
}
else
{
EndingIndex--;
}
}
}
return(null);
}
/// <summary>
/// Read a number of tokens (seperated by whitespace) from a PDF data stream as UTF8 characters
/// </summary>
/// <param name="Data">Data stream to read</param>
/// <param name="StartingIndex">Starting offset</param>
/// <param name="TokenStartIndex">Offset in the data array where the token appears</param>
/// <param name="EndingIndex">Offset in the data array where reading stopped</param>
/// <param name="WordCount">Number of tokens sepreated by whitespace to read. If multiple words are read, all whitespace will be replaced by a single space character (0x20)</param>
/// <returns>Read tokens as a UTF8 string, or NULL if unable to read the specified number of words before running out of data</returns>
internal static string GetTokenString(byte[] Data, int StartingIndex, out int TokenStartIndex, out int EndingIndex, int WordCount = 1)
{
List <Byte> TokenString = new List <Byte>(20);
bool InComment = false;
bool InWhitespace = false;
TokenStartIndex = 0;
EndingIndex = StartingIndex;
while ((WordCount > 0) && (EndingIndex < Data.Length))
{
byte DataByte = Data[EndingIndex];
InComment = InComment || (DataByte == PDF.CommentDelimiter);
if (InComment)
{
InComment = !PDF.IsEOL(DataByte);
}
else
{
if (InWhitespace && !PDF.IsWhitespace(DataByte))
{
InWhitespace = false;
}
if (!InWhitespace)
{
if (PDF.IsWhitespace(DataByte))
{
InWhitespace = true;
if (TokenString.Count > 0)
{
// Don't add leading/trailing whitespace
WordCount--;
if (WordCount > 0)
{
TokenString.Add(0x20);
}
}
}
else
{
if (TokenString.Count == 0)
{
TokenStartIndex = EndingIndex;
}
TokenString.Add(DataByte);
}
}
}
EndingIndex++;
}
if (WordCount > 0)
{
return(null);
}
return(Encoding.UTF8.GetString(TokenString.ToArray()));
}