comment on text extraction

Update:

I have made a small change on source so that the result becomes at least as good as with option 3. It cannot assured that the text is always splitt to single words but I can avoid the partially doubled entries.

The remaining problem:
How can I determine if (T)83(es)-1(t)-333("Thi)1(s)-1(,)-333(th)1(at") are one, two or more words?

Is it allowed to post the changes here on this forum?

best regards,
Ulrich

Ok, here it is:

Description: With the following change option 4 results in correct text when having text like [(te) 83 (s) -1 (t) -333 (thi) 82(s)]TJ
The original version results in "tetestest thithis" while the new version result in "test this".
Restriction: having text like the above it is not possible to divide it to single words. So it works more like option 3.

search for UKO in the following code (2 lines) and add the lines to your source.

Unit: uPDFRenderer
Method: SubRender
local SubMethod: ShowText

procedure ShowText;
var
    X: Integer;
    C: Char;
    M: TPDFXForm;
    OldM: TPDFXForm;
    DX: Double;
    OI: Integer;
    Text: string;
    W: Double;
    CW: Word;
    WI: Integer;
    DXS: Double;
    MapText: string;
    TestP1: TPDFXFormPoint;
    TestP2: TPDFXFormPoint;
    RealTextSize: Double;
    GC: TPDFGenericCanvas;
    CIDToGIDMap: string;
    CN: string;
    MappedText: string;
    ThisMappedText: string;
    MatrixScale: Double;
    UC: Word;
    UX: Integer;
    UFound: Boolean;
begin
    MatrixScale := 1000;
    MappedText := '';
    CIDToGIDMap := FFontCol.FoundFontData.CIDToGIDMap;
    if FDestination = rdEPS then
      GC := FEPS
    else
      GC := Picasso;
    GC.BeginPath;
    if GS.TextSize <> 0 then
    begin
      if Assigned(FFontCol.FoundFontData.Rasterizer) then
        FFontCol.FoundFontData.Rasterizer.RenderingMode := GS.TextRenderingMode;
      SetFill(pfUnknown);
      SetPen;
      OI := Operands.Count - ArrayCount;
      SelectFont;
      OldM := CanvasMat;
      try
        CombinePDFXForm(CanvasMat, GS.TM, CanvasMat);
        if FFontCol.FoundFontData.Rasterizer is TPDFType3Rasterizer then
        begin
          MatrixScale := 1;
          CombinePDFXForm(CanvasMat, TPDFType3Rasterizer(
            FFontCol.FoundFontData.Rasterizer).FontMatrix, CanvasMat);
          TPDFType3Rasterizer(FFontCol.FoundFontData.Rasterizer).FillColor :=
            GS.FillColor;
        end;
        Mat(M, GS.TextSize / MatrixScale * GS.TextScaling / 100, 0, 0, GS.TextSize / MatrixScale, 0, 0);
        CombinePDFXForm(CanvasMat, M, CanvasMat);

        TestP1.X := 0;
        TestP1.Y := 0;
        TestP2.X := 0;
        TestP2.Y := MatrixScale;
        TestP1 := DoPDFXForm(CanvasMat, TestP1);
        TestP2 := DoPDFXForm(CanvasMat, TestP2);
        RealTextSize := Sqrt(Sqr(TestP2.X - TestP1.X) + Sqr(TestP2.Y - TestP1.Y));

        DX := 0;
        repeat
          Text := Operands[OI];
          if (Copy(Text, 1, 1) <> '(') and (Copy(Text, 1, 1) <> '<') then
          begin
            DX := DX - TazzToFloat(Text) * MatrixScale / 1000;
          end else
          begin
            if (Copy(Text, 1, 1) = '(') then
            begin
              Text := FStructure.DecodeString(Text);
            end else
            if (Copy(Text, 1, 1) = '<') then
            begin
              Text := FStructure.DecodeHex(Text);
            end;
            if FFontCol.FoundFontData.IsComposite then
            begin
              DXS := DX;
              for X := 1 to Length(Text) div 2 do
              begin
               CW := Ord(Text[X * 2 - 1]) * 256 + Ord(Text[X * 2]);

               if CIDToGIDMap <> '' then
               begin
                  if (CW * 2) < Length(CIDToGIDMap) then
                  begin
                    CN := 'GID:' + IntToStr(Ord(CIDToGIDMap[CW * 2 + 1]) * 256 +
                      Ord(CIDToGIDMap[CW * 2 + 2]));
                  end;
               end else
                  CN := 'GID:' + IntToStr(CW);
               if Assigned(FFontCol.FoundFontData.CIDWidths) then
               begin
                  WI := FFontCol.FoundFontData.CIDWidths.IndexOf('CID:' + IntToStr(CW));
                  if WI >= 0 then
                  begin
                    WI := Integer(FFontCol.FoundFontData.CIDWidths.Objects[WI]);
                    {***Th W := WI * GS.TextScaling / 100; ***}
                    W := WI{***Th W ***} + GS.CharSpacing * MatrixScale / Abs(GS.TextSize);
                  end else
                    W := MatrixScale;
               end else
                  W := MatrixScale;
               if FDestination <> rdTextFunnel then
               begin
                  if Assigned(FFontCol.FoundFontData.Rasterizer) then
                    with FFontCol.FoundFontData do
                      Rasterizer.RenderToCanvas(DX, GS.TextRise * MatrixScale /
                        Abs(GS.TextSize), GC, CanvasMat, CN);
               end;
               if (FDestination = rdTextFunnel) and FFunnel.SplitWords then
               begin
                  ThisMappedText := FFontCol.FoundFontData.DisplayCS[Ord(CW)];
                  if (ThisMappedText = ' ') and (MappedText <> '') then
                  begin
                    FFunnel.AddText(CanvasMat, MappedText, HTMLColor(GS.FillColor),
                      FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                        GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                        FFontCol.FoundFontData.Descent, DX - DXS,
                        FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
                    MappedText := '';
                    FFunnel.SetNextMatch(False);
                    DXS := DX + W;
                  end else
                    MappedText := MappedText + ThisMappedText;
               end;
               DX := DX + W;
              end;
              FFunnel.SetNextMatch(True);
              if (FDestination = rdTextFunnel) and FFunnel.SplitWords then
              begin
               FFunnel.AddText(CanvasMat, MappedText, HTMLColor(GS.FillColor),
                  FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                    GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                    FFontCol.FoundFontData.Descent, DX - DXS,
                    FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
               MappedText := ''; // UKO Reset (necessary for positioned text glyphs)
              end;
              if (FDestination = rdTextFunnel) and (not FFunnel.SplitWords) then
              begin
               MapText := '';
               //MapText := MapText + FFontCol.FoundFontData.DisplayCS[Ord(Text[X * 2 - 1]) * 256 + Ord(Text[X * 2])];
               for X := 1 to Length(Text) div 2 do
               begin
                  UC := Ord(Text[X * 2 - 1]) * 256 + Ord(Text[X * 2]);
                  UX := 0;
                  UFound := False;
                  while (not UFound) and (UX < Length(FFontCol.FoundFontData.DisplayCS2)) do
                  begin
                    if (UC >= FFontCol.FoundFontData.DisplayCS2[X].StartCode) and
                      (UC <= FFontCol.FoundFontData.DisplayCS2[X].EndCode) then
                    begin
                      UC := FFontCol.FoundFontData.DisplayCS2[X].ResultCode +
                        UC - FFontCol.FoundFontData.DisplayCS2[X].StartCode;
                      UFound := True;
                    end else
                      Inc(UX);
                  end;
                  if UFound then MapText := MapText + WideChar(UC);
               end;
               FFunnel.AddText(CanvasMat, MapText, HTMLColor(GS.FillColor),
                  FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                    GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                    FFontCol.FoundFontData.Descent, DX - DXS,
                    FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
              end;
            end else
            begin
              DXS := DX;
              for X := 1 to Length(Text) do
              begin
               C := Text[X];
               W := (Widths[Ord(C)] * Abs(GS.TextSize) {***Th GS.TextScaling / 100 ***} / Abs(GS.TextSize));
               if Assigned(FFontCol.FoundFontData.Rasterizer) then
                  W := W / FFontCol.FoundFontData.Rasterizer.FontMatrixScaling;
               W := W + GS.CharSpacing * MatrixScale / Abs(GS.TextSize);
               if C = #32 then
                  W := W + GS.WordSpacing * MatrixScale / Abs(GS.TextSize);
               if FDestination <> rdTextFunnel then
               begin
                  if Assigned(FFontCol.FoundFontData.Rasterizer) then
                    with FFontCol.FoundFontData do
                      Rasterizer.RenderToCanvas(DX, GS.TextRise * MatrixScale /
                        Abs(GS.TextSize), GC, CanvasMat, Encoding[Ord(C)]);
               end;
               if (FDestination = rdTextFunnel) and FFunnel.SplitWords then
               begin
                  ThisMappedText := FFontCol.FoundFontData.DisplayCS[Ord(Text[X])];
                  if (ThisMappedText = ' ') and (MappedText <> '') then
                  begin
                    FFunnel.AddText(CanvasMat, MappedText, HTMLColor(GS.FillColor),
                      FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                        GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                        FFontCol.FoundFontData.Descent, DX - DXS,
                        FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
                    MappedText := '';
                    FFunnel.SetNextMatch(False);
                    DXS := DX + W;
                  end else
                    MappedText := MappedText + ThisMappedText;
               end;
               DX := DX + W;
              end;
              FFunnel.SetNextMatch(True);
              if (FDestination = rdTextFunnel) and FFunnel.SplitWords then
              begin
               FFunnel.AddText(CanvasMat, MappedText, HTMLColor(GS.FillColor),
                  FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                    GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                    FFontCol.FoundFontData.Descent, DX - DXS,
                    FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
               MappedText := '';   // UKO Reset (necessary for positioned text glyphs)
              end;
              if (FDestination = rdTextFunnel) and (not FFunnel.SplitWords) then
              begin
               MapText := '';
               for X := 1 to Length(Text) do
                  MapText := MapText + FFontCol.FoundFontData.DisplayCS[Ord(Text[X])];
               FFunnel.AddText(CanvasMat, MapText, HTMLColor(GS.FillColor),
                  FFontCol.FoundFontData.FontName, RealTextSize, DXS,
                    GS.TextRise * MatrixScale / Abs(GS.TextSize) +
                    FFontCol.FoundFontData.Descent, DX - DXS,
                    FFontCol.FoundFontData.Ascent - FFontCol.FoundFontData.Descent);
              end;
            end;
          end;
          Inc(OI);
        until OI = Operands.Count;
        Mat(M, 1, 0, 0, 1, DX * Abs(GS.TextSize) / MatrixScale, 0);
        CombinePDFXForm(GS.TM, M, GS.TM);
      finally
        CanvasMat := OldM;
      end;
    end;
    ArrayCount := 0;
    if FDestination = rdEPS then
    begin
      if (GS.TextRenderingMode = 0) or (GS.TextRenderingMode = 2) or
        (GS.TextRenderingMode = 4) or (GS.TextRenderingMode = 6) then
      begin
        FEPS.PSSetColor(GS.FillColorEPS);
        FEPS.PSFill(epsFillModeNonZeroWinding);
      end;
      if (GS.TextRenderingMode = 1) or (GS.TextRenderingMode = 2) or
        (GS.TextRenderingMode = 5) or (GS.TextRenderingMode = 6) then
      begin
        FEPS.PSSetColor(GS.StrokeColorEPS);
        FEPS.PSStroke;
      end;
    end else
    begin
      if (GS.TextRenderingMode = 1) or (GS.TextRenderingMode = 2) or
        (GS.TextRenderingMode = 5) or (GS.TextRenderingMode = 6) then
          SetPen;
      if (GS.TextRenderingMode = 0) or (GS.TextRenderingMode = 2) or
        (GS.TextRenderingMode = 4) or (GS.TextRenderingMode = 6) then
          SetFill(pfWinding);
      if GS.TextRenderingMode >= 4 then
        Picasso.SetClippingPath(pfWinding);
      case GS.TextRenderingMode of
        0: Picasso.FillPath;
        1: Picasso.StrokePath;
        2: Picasso.StrokeAndFillPath;
        4: Picasso.FillPath;
        5: Picasso.StrokePath;
        6: Picasso.StrokeAndFillPath;
        7: Picasso.NullPath;
      end;
    end;
end;



So please test it and if it works ok, can it be included in Version 5.15 ?

best regards,
Ulrich

Good job

Working fine for me.

The function can be improved, surely, but working better than the old version wich was too bugged before.

thanks very much Ukobsa :)