/// <summary>
/// Get the render format for the data extraction, you'll get the left and right side. And for the first page you'll get a shorter format of the rectangles so we can skip unnecessary info
/// Premiere page sans en tête.
/// Rectangle (lower left x, lower left y, upper right x, upper right y)
/// </summary>
/// <param name="page"> Which page are we extracting the date from</param>
/// <param name="right">That's to know which side of the page we should extract the information left or right side </param>
/// <returns></returns>
private static RenderFilter[] get_render(int page, int right)
{
if (page == 1)
{
if (right == 0)
{
System.util.RectangleJ rect = new System.util.RectangleJ(0, 0, 536 / 2, 500);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
return(filter);
}
else
{
System.util.RectangleJ rectL = new System.util.RectangleJ(300, 0, 536 / 2, 500);
RenderFilter[] filterL = { new RegionTextRenderFilter(rectL) };
return(filterL);
}
}
else
{
if (right == 0)
{
System.util.RectangleJ rect = new System.util.RectangleJ(0, 0, 536 / 2, 830);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
return(filter);
}
else
{
System.util.RectangleJ rectL = new System.util.RectangleJ(300, 0, 536 / 2, 830);
RenderFilter[] filterL = { new RegionTextRenderFilter(rectL) };
return(filterL);
}
}
}
public static ITextExtractionStrategy MakeRectangle(float pixelDistanceFromLeft, float pixelDistanceFromBottom, float pixelDistanceWidth, float pixelDistanceHeight)
{
var rectangle = new System.util.RectangleJ(pixelDistanceFromLeft, pixelDistanceFromBottom, pixelDistanceWidth, pixelDistanceHeight);
var filters = new RenderFilter[1];
filters[0] = new RegionTextRenderFilter(rectangle);
ITextExtractionStrategy strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filters);
return(strategy);
}
public virtual void RenderText(TextRenderInfo renderInfo)
{
if (textRectangle == null)
{
textRectangle = renderInfo.GetDescentLine().GetBoundingRectange();
}
else
{
textRectangle.Add(renderInfo.GetDescentLine().GetBoundingRectange());
}
textRectangle.Add(renderInfo.GetAscentLine().GetBoundingRectange());
}
public void Run()
{
var settingsStr = File.ReadAllText("settings.toml");
var settings = Toml.Toml.Parse(settingsStr);
var reader = new PdfReader(settings.input);
writer = new StreamWriter(settings.output);
manualMode = settings.manualMode;
totalNumSponsors = 0;
// first page
{
// Parameters: distanceInPixelsFromLeft, distanceInPixelsFromBottom, width, height
var rect = new System.util.RectangleJ(24, 34, 326, 348);
var strategy = CreateStrategy(rect);
var text = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
Write(text);
}
// middle page
{
var rect = new System.util.RectangleJ(24, 0, 326, 569);
for (var i = 2; i < reader.NumberOfPages; i++)
{
var strategy = CreateStrategy(rect);
var text = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
text = text.Replace("Organisation Name\n", "");
Write(text);
}
}
// last page
{
var rect = new System.util.RectangleJ(24, 229, 326, 339);
var strategy = CreateStrategy(rect);
var text = PdfTextExtractor.GetTextFromPage(reader, reader.NumberOfPages, strategy);
Write(text);
}
writer.Flush();
if (totalNumSponsors != settings.totalNumSponsors)
{
Console.WriteLine(
$@"Warning: mismatched total number of sponsors:
expected `{settings.totalNumSponsors}`,
found `{totalNumSponsors}`");
Console.ReadLine();
}
}
public List <Line> getTextFromRectangle(int x, int y, int w, int h)
{
System.util.RectangleJ rect0 = new System.util.RectangleJ(x, y, w, h);
RenderFilter[] filter = { new RegionTextRenderFilter(rect0) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
sb.AppendLine(PdfTextExtractor.GetTextFromPage(reader, 1, strategy));
List <Line> line = stockLine(sb.ToString());
return(line);
}
public Path RenderPath(PathPaintingRenderInfo renderInfo)
{
if (renderInfo.Operation != PathPaintingRenderInfo.NO_OP)
{
if (textRectangle == null)
{
textRectangle = currentPathRectangle;
}
else
{
textRectangle.Add(currentPathRectangle);
}
}
currentPathRectangle = null;
return(null);
}
public virtual void RenderImage(ImageRenderInfo renderInfo)
{
Matrix imageCtm = renderInfo.GetImageCTM();
Vector a = (new Vector(0, 0, 1)).Cross(imageCtm);
Vector b = (new Vector(1, 0, 1)).Cross(imageCtm);
Vector c = (new Vector(0, 1, 1)).Cross(imageCtm);
Vector d = (new Vector(1, 1, 1)).Cross(imageCtm);
LineSegment bottom = new LineSegment(a, b);
LineSegment top = new LineSegment(c, d);
if (textRectangle == null)
{
textRectangle = bottom.GetBoundingRectange();
}
else
{
textRectangle.Add(bottom.GetBoundingRectange());
}
textRectangle.Add(top.GetBoundingRectange());
}
// ---------------------------------------------------------------------------
public void Write(Stream stream) {
using (ZipFile zip = new ZipFile()) {
zip.AddFile(PREFACE, "");
PdfReader reader = new PdfReader(PREFACE);
System.util.RectangleJ rect = new System.util.RectangleJ(
70, 80, 420, 500
);
RenderFilter[] filter = {new RegionTextRenderFilter(rect)};
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++) {
strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), filter
);
sb.AppendLine(
PdfTextExtractor.GetTextFromPage(reader, i, strategy)
);
}
zip.AddEntry(RESULT, sb.ToString());
zip.Save(stream);
}
}
// ---------------------------------------------------------------------------
public void Write(Stream stream)
{
using (ZipFile zip = new ZipFile()) {
zip.AddFile(PREFACE, "");
PdfReader reader = new PdfReader(PREFACE);
System.util.RectangleJ rect = new System.util.RectangleJ(
70, 80, 420, 500
);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), filter
);
sb.AppendLine(
PdfTextExtractor.GetTextFromPage(reader, i, strategy)
);
}
zip.AddEntry(RESULT, sb.ToString());
zip.Save(stream);
}
}
public void ModifyPath(PathConstructionRenderInfo renderInfo)
{
IList <Vector> points = new List <Vector>();
if (renderInfo.Operation == PathConstructionRenderInfo.RECT)
{
float x = renderInfo.SegmentData[0];
float y = renderInfo.SegmentData[1];
float w = renderInfo.SegmentData[2];
float h = renderInfo.SegmentData[3];
points.Add(new Vector(x, y, 1));
points.Add(new Vector(x + w, y, 1));
points.Add(new Vector(x, y + h, 1));
points.Add(new Vector(x + w, y + h, 1));
}
else if (renderInfo.SegmentData != null)
{
for (int i = 0; i < renderInfo.SegmentData.Count - 1; i += 2)
{
points.Add(new Vector(renderInfo.SegmentData[i], renderInfo.SegmentData[i + 1], 1));
}
}
foreach (Vector point in points)
{
Vector point1 = point.Cross(renderInfo.Ctm);
Rectangle2D pointRectangle = new Rectangle2D(point1[Vector.I1], point1[Vector.I2], 0, 0);
if (currentPathRectangle == null)
{
currentPathRectangle = pointRectangle;
}
else
{
currentPathRectangle.Add(pointRectangle);
}
}
}
/// <summary>
/// Create a TextInfo.
/// </summary>
/// <param name="initialTextChunk"></param>
public TextInfo(TextChunk initialTextChunk)
{
TopLeft = initialTextChunk.AscentLine.GetStartPoint();
BottomRight = initialTextChunk.DecentLine.GetEndPoint();
rectangle = initialTextChunk.AscentLine.GetBoundingRectange();
m_Text = initialTextChunk.Text;
}
public void verify()
{
addresscollection aic = new addresscollection();
addressitem ai = null;
string sourceFileName = _sourcefilename;
FileStream x = new FileStream(sourceFileName, FileMode.Open);
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(x);
//AWESOME!!
x.Close();
x.Dispose();
string s = "";
string s1 = "";
System.Xml.XmlNode ep = null;
System.Xml.XmlNode batch = null;
System.Xml.XmlNode startingpage = null;
System.Xml.XmlNode envelope = null;
int pages = reader.NumberOfPages;
int i;
for (i = 0; i <= reader.NumberOfPages - 1; i++) {
this.Label2.Invoke(new updatetext(updatelabel1text), new object[] { "Processing Page " + Convert.ToString(i + 1) + " of " + pages });
DataRow dr = _dtt.Rows[0];
System.util.RectangleJ rect1 = new System.util.RectangleJ(Convert.ToInt32( dr["x"]), Convert.ToInt32( dr["y"]), Convert.ToInt32( dr["width"]), Convert.ToInt32( dr["height"]));
iTextSharp.text.pdf.parser.RegionTextRenderFilter rf = new iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect1);
iTextSharp.text.pdf.parser.LocationTextExtractionStrategy mystrat = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
iTextSharp.text.pdf.parser.RegionTextRenderFilter[] rtrf = new iTextSharp.text.pdf.parser.RegionTextRenderFilter[2];
rtrf[0] = rf;
//Dim rect2 As New System.util.RectangleJ(0, 700, 800, 140)
//Dim rf2 As New iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect2)
iTextSharp.text.pdf.parser.FilteredTextRenderListener textExtractionStrategy = new iTextSharp.text.pdf.parser.FilteredTextRenderListener(mystrat, rtrf);
DataRow dr1 = _dtt.Rows[1];
System.util.RectangleJ rect2 = new System.util.RectangleJ(Convert.ToInt32( dr1["x"]), Convert.ToInt32( dr1["y"]), Convert.ToInt32( dr1["width"]), Convert.ToInt32( dr1["height"]));
iTextSharp.text.pdf.parser.RegionTextRenderFilter rf1 = new iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect2);
iTextSharp.text.pdf.parser.LocationTextExtractionStrategy mystrat1 = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
iTextSharp.text.pdf.parser.RegionTextRenderFilter[] rtrf1 = new iTextSharp.text.pdf.parser.RegionTextRenderFilter[2];
rtrf1[0] = rf1;
//Dim rect2 As New System.util.RectangleJ(0, 700, 800, 140)
//Dim rf2 As New iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect2)
iTextSharp.text.pdf.parser.FilteredTextRenderListener textExtractionStrategy1 = new iTextSharp.text.pdf.parser.FilteredTextRenderListener(mystrat1, rtrf1);
s = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, i + 1, textExtractionStrategy);
if (!string.IsNullOrEmpty(s)) {
s1 = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, i + 1, textExtractionStrategy1);
if (parseaddress(s, s1, ref batch, i + 1, ref ep, ref envelope, ref startingpage, ref ai)) {
//Des not catch a single first page, anytime this is true it's a new first page
// ep.InnerText = i + 1
// Console.WriteLine(ai.Address1)
aic.Add(ai);
}
}
if (i == reader.NumberOfPages - 1 & (ep != null)) {
ep.InnerText = Convert.ToString(i + 1);
}
if (i == reader.NumberOfPages - 1 & (ai != null)) {
ai.endpage = Convert.ToInt32( i + 1);
}
// CurrentPage = CurrentPage + 1
}
reader.Close();
//Me.RichTextBox1.Invoke(New updatert(AddressOf updaterichtext), New Object() {XMLDOC.OuterXml, badaddress})
this.RichTextBox1.Invoke(new updatert(updaterichtext), new object[] {
XMLDOC,
badaddress
});
//Me.RichTextBox1.Invoke(New updatert(AddressOf updaterichtext), New Object() {badaddress})
Invoke(new updatedatagrid(updatedatagridonMail), new object[] { aic });
Invoke(new updatecomplete(updatecompleted), new object[]{});
//rtrf(0) = rf2
//textExtractionStrategy = New iTextSharp.text.pdf.parser.FilteredTextRenderListener(mystrat, rtrf)
//MsgBox(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy))
// iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy)
}
public string ExtractTextFromRegionOfPdf(string sourceFileName)
{
FileStream x = new FileStream(sourceFileName, FileMode.Open);
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(x);
//AWESOME!!
System.util.RectangleJ rect1 = new System.util.RectangleJ(Rect.X, System.Math.Abs(this.PictureBox1.Height - Rect.Y) - Rect.Height, Rect.Width, Rect.Height);
iTextSharp.text.pdf.parser.RegionTextRenderFilter rf = new iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect1);
iTextSharp.text.pdf.parser.LocationTextExtractionStrategy mystrat = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
iTextSharp.text.pdf.parser.RegionTextRenderFilter[] rtrf = new iTextSharp.text.pdf.parser.RegionTextRenderFilter[2];
rtrf[0] = rf;
//Dim rect2 As New System.util.RectangleJ(0, 700, 800, 140)
//Dim rf2 As New iTextSharp.text.pdf.parser.RegionTextRenderFilter(rect2)
iTextSharp.text.pdf.parser.FilteredTextRenderListener textExtractionStrategy = new iTextSharp.text.pdf.parser.FilteredTextRenderListener(mystrat, rtrf);
//rtrf(0) = rf2
//textExtractionStrategy = New iTextSharp.text.pdf.parser.FilteredTextRenderListener(mystrat, rtrf)
//MsgBox(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy))
// iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy)
x.Close();
x.Dispose();
reader.Close();
if (_mode == 1) {
if (this.loadedbool) {
string s = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, CurrentPage + 1, textExtractionStrategy);
DialogResult y = MessageBox.Show("This field is showing : " + s + "\r\n" + "Is this the correct variable on this page?","Confirm" , MessageBoxButtons.YesNo );
if (y == DialogResult.Yes ) {
_dtt.Rows[_CurrentCount]["x"] = Rect.X;
_dtt.Rows[_CurrentCount]["y"] = System.Math.Abs(this.PictureBox1.Height - Rect.Y) - Rect.Height;
_dtt.Rows[_CurrentCount]["width"] = Rect.Width;
_dtt.Rows[_CurrentCount]["height"] = Rect.Height;
if (_CurrentCount == 0) {
DialogResult xx = MessageBox.Show("There is an optional Parimeter where you can select something that only appears on the first page, do you want to add this. It can be part of a string like Page 1 of XX?", "Confirm", MessageBoxButtons.YesNo);
if (xx == DialogResult.No)
{
_CurrentCount = 2;
}
}
if (_dtt.Rows[_CurrentCount]["FieldName"] == "FirstPageConstant") {
_validatetext = Interaction.InputBox("Enter Charectors to match, if you enter \"1 of \" it will be true for anything after the of");
_dtt.Rows[_CurrentCount + 1]["misc"] = _validatetext;
_CurrentCount += 1;
}
_CurrentCount += 1;
if (_CurrentCount == 3) {
_CurrentCount = 0;
this.Label2.Text = "OK, you have completed the template, if you wish to start over simply do it again and start by selecting the area with:" + _dtt.Rows[0]["fieldname"];
startover = 1;
drawrectangles();
MessageBox.Show("Make sure you save this if you want to use it in the future.");
} else {
this.Label2.Text = "Now Select : " + _dtt.Rows[_CurrentCount]["fieldname"];
}
}
}
} else {
this.Label2.Text = "OK, you have completed the template, if you wish to start over simply do it again and start by selecting the area with:" + _dtt.Rows[0]["fieldname"];
}
return "";
}
