public virtual ICollection <IPdfTextLocation> GetResultantLocations()
{
// align characters in "logical" order
JavaCollectionsUtil.Sort(parseResult, new TextChunkLocationBasedComparator(new DefaultTextChunkLocationComparator()));
// process parse results
IList <IPdfTextLocation> retval = new List <IPdfTextLocation>();
CharacterRenderInfo.StringConversionInfo txt = CharacterRenderInfo.MapString(parseResult);
Match mat = iText.IO.Util.StringUtil.Match(pattern, txt.text);
while (mat.Success)
{
int?startIndex = txt.indexMap.Get(mat.Index);
int?endIndex = txt.indexMap.Get(mat.Index + mat.Length);
foreach (Rectangle r in ToRectangles(parseResult.SubList(startIndex.Value, endIndex.Value)))
{
retval.Add(new DefaultPdfTextLocation(0, r, iText.IO.Util.StringUtil.Group(mat, 0)));
}
mat = mat.NextMatch();
}
/* sort
* even though the return type is Collection<Rectangle>, we apply a sorting algorithm here
* This is to ensure that tests that use this functionality (for instance to generate pdf with
* areas of interest highlighted) will not break when compared.
*/
JavaCollectionsUtil.Sort(retval, new _IComparer_54());
return(retval);
}
/// <summary>
/// This method converts a List<CharacterRenderInfo>
/// The data structure that gets returned contains both the plaintext,
/// as well as the mapping of indices (from the list to the string).
/// </summary>
/// <remarks>
/// This method converts a List<CharacterRenderInfo>
/// The data structure that gets returned contains both the plaintext,
/// as well as the mapping of indices (from the list to the string).
/// These indices can differ; if there is sufficient spacing between two CharacterRenderInfo
/// objects, this algorithm will decide to insert space. The inserted space will cause
/// the indices to differ by at least 1.
/// </remarks>
internal static CharacterRenderInfo.StringConversionInfo MapString(IList <iText.Kernel.Pdf.Canvas.Parser.Listener.CharacterRenderInfo
> cris)
{
IDictionary <int, int?> indexMap = new Dictionary <int, int?>();
StringBuilder sb = new StringBuilder();
iText.Kernel.Pdf.Canvas.Parser.Listener.CharacterRenderInfo lastChunk = null;
for (int i = 0; i < cris.Count; i++)
{
iText.Kernel.Pdf.Canvas.Parser.Listener.CharacterRenderInfo chunk = cris[i];
if (lastChunk == null)
{
indexMap.Put(sb.Length, i);
sb.Append(chunk.GetText());
}
else
{
if (chunk.SameLine(lastChunk))
{
// we only insert a blank space if the trailing character of the previous string wasn't a space, and the leading character of the current string isn't a space
if (chunk.GetLocation().IsAtWordBoundary(lastChunk.GetLocation()) && !chunk.GetText().StartsWith(" ") && !
chunk.GetText().EndsWith(" "))
{
sb.Append(' ');
}
indexMap.Put(sb.Length, i);
sb.Append(chunk.GetText());
}
else
{
indexMap.Put(sb.Length, i);
sb.Append(chunk.GetText());
}
}
lastChunk = chunk;
}
CharacterRenderInfo.StringConversionInfo ret = new CharacterRenderInfo.StringConversionInfo();
ret.indexMap = indexMap;
ret.text = sb.ToString();
return(ret);
}
