C# code -Compare 2 list and export the difference in excel

anoop gs

I have twp pdfs.I want to compare it.For that i converts 2 pdf into 2 lists.I want to compare the 2 lists and export the difference as 2 columns in excel.Could you please help me to find the c# code for it?Please find the below incomplete code?

public static void CompareTwoPDF(string FirstPDF, string SecondPDF)

{

if (File.Exists(FirstPDF) && File.Exists(SecondPDF))

{

PdfReader reader = new PdfReader(SecondPDF);

for (int page = 1; page <= reader.NumberOfPages; page++)

{

ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();

FirstFile += PdfTextExtractor.GetTextFromPage(reader, page, strategy);

}

PdfReader reader1 = new PdfReader(FirstPDF);

for (int page = 1; page <= reader.NumberOfPages; page++)

{

ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();

SecondFile += PdfTextExtractor.GetTextFromPage(reader1, page, strategy);

}

else

{

Console.WriteLine("Files does not exist.");

}

List File1diff;

List File2diff;

IEnumerable file1 = FirstFile.Trim().Split('\r', '\n');

IEnumerable file2 = SecondFile.Trim().Split('\r', '\n');

File1diff = file1.ToList();

File2diff = file2.ToList();

}

5 Replies

Know the answer? Post it — somebody with the same question will find it here.

Vidhu S6y ago
Hi can you tell how to write code inorder to validate dynamic text in pdf please.
Laxmidhar Sahoo6y ago
Hi anoops

Sorry I am not aware in java

Thanks and regards
Vidhu S6y ago
Hi anoop did u get c# code for this if u get could you plz post it even I'm searching for this same concept but in c#.
anoop gs6y ago
Thanks laxmidhar-sahoo.
In the java there is a library called Zeonpad.If we give two pdf as input files,it will find the difference and will produce 2 pdf files as output with the difference highlighted in different colors(red and green).

Then they will extract the highlighted differences only from the 2 output pdf files.
Now they will write the differences into excel.Please see the below 3 methods thay have used in java.can you please help me to implement the same in c#?

Please see the java code below:
///Method 1 -this will compare 2 pdf and will produce 2 output pdf files with difference highlighted(one in red and other in green)
public static void comparePDFText(String expectfile, String actualfile) throws IOException {
String path = cdir + "\\SkriptmatePDFCompareOutput" + "\\" + currentTimeStamp;
FileUtils.makeDirs(path);
String expectedoutFile_Diff = path + "\\" + "Expectdiff_out.pdf";
String actualFile_Diff = path + "\\Actualdiff_out.pdf";
ZPDFCompare compare = new ZPDFCompare();
compare.pdfcompare(expectfile, actualfile, expectedoutFile_Diff, actualFile_Diff);
writeToExcel(expectedoutFile_Diff, actualFile_Diff);
}
//Method 2 to extract the highlighted difference only
public static HashMap getHighlightedTexts(String file) throws IOException {
HashMap map = new HashMap<>();
try {
PDDocument pddDocument = PDDocument.load(new File(file));
List allPages = new ArrayList<>();
pddDocument.getDocumentCatalog().getPages().forEach(allPages::add);
String completeText = "";
for (int i = 0; i < allPages.size(); i++) {
completeText = "";
int pageNum = i + 1;
PDPage page = (PDPage) allPages.get(i);
List la = page.getAnnotations();
if (la.size() < 1) {
continue;
}
for (PDAnnotation pdfAnnot : la) {
if (pdfAnnot.getSubtype().equals("Popup")) {
continue;
}
PDFTextStripperByArea stripper = new PDFTextStripperByArea();
stripper.setSortByPosition(true);
PDRectangle rect = pdfAnnot.getRectangle();
float x = rect.getLowerLeftX() - 1;
float y = rect.getUpperRightY() - 5;
float width = rect.getWidth() - 1.10f;
float height = (rect.getHeight() + rect.getHeight() / 4) - 5;
int rotation = page.getRotation();
if (rotation == 0) {
PDRectangle pageSize = page.getMediaBox();
y = pageSize.getHeight() - y;
}
Rectangle2D.Float awtRect = new Rectangle2D.Float(x, y, width, height);
stripper.addRegion(Integer.toString(0), awtRect);
stripper.extractRegions(page);
completeText = completeText + stripper.getTextForRegion(Integer.toString(0)).trim() + " ";
}
map.put((i + 1), completeText);
}
// System.out.println(map);
} catch (Exception e) {
e.printStackTrace();
}
return map;
}
////Method 3 ---To export the highlighted difference to excel
public static void writeToExcel(String expectedFile, String actualFile) throws IOException {
HashMap expectedMap = new HashMap();
HashMap actualMap = new HashMap();
String path = cdir + "\\SkriptmatePDFCompareOutput" + "\\" + currentTimeStamp;
FileUtils.makeDirs(path);
String out_destExcel = path + "\\" + "DifferenceOut_excel.xls";
try {
HSSFWorkbook myWorkBook = new HSSFWorkbook();
HSSFSheet mySheet = myWorkBook.createSheet("PDFCompare");
HSSFRow myRow = null;
HSSFCell myCell = null;
expectedMap = getHighlightedTexts(expectedFile);
int expectedPage = 0;
for (Entry dataMap : expectedMap.entrySet()) {
expectedPage = dataMap.getKey();
}
actualMap = getHighlightedTexts(actualFile);
int actualPage = 0;
for (Entry dataMap : actualMap.entrySet()) {
actualPage = dataMap.getKey();
}
int rowSize = 0;
if (expectedPage >= actualPage) {
rowSize = expectedPage;
} else {
rowSize = actualPage;
}
myRow = mySheet.createRow(0);
myRow.createCell(0).setCellValue("Page No");
myRow.createCell(1).setCellValue("Expect Differences");
myRow.createCell(2).setCellValue("Actual Differences");
String tempExpected = "Nil";
String tempActual = "Nil";
for (int i = 1; i <= rowSize; i++) {
myRow = mySheet.createRow(i);
myRow.createCell(0).setCellValue(i);
// To Print Expected result into Excel.
if (expectedMap.get(i) != null) {
myRow.createCell(1).setCellValue(expectedMap.get(i));
} else {
myRow.createCell(1).setCellValue(tempExpected);
}
// To Print Actual result into Excel.
if (actualMap.get(i) != null) {
myRow.createCell(2).setCellValue(actualMap.get(i));
} else {
myRow.createCell(2).setCellValue(tempActual);
}
}
FileOutputStream out = new FileOutputStream(out_destExcel);
myWorkBook.write(out);
out.close();
} catch (Exception e) {
e.printStackTrace();
}
}
Please help me to do the same in c#?
Laxmidhar Sahoo6y ago
hi

Bellow function call for each pdf file to get the list of strinng .But I can not get your point for defference tetween them
public List<string> ExtractTextFromPdf(string path)
    {
    List<string> strlist = new List<string>();
        using (PdfReader reader = new PdfReader(path))
        {
            StringBuilder text = new StringBuilder();
            ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();

            for (int i = 1; i <= reader.NumberOfPages; i++)
            {
                string page = "";

                page = PdfTextExtractor.GetTextFromPage(reader, i,Strategy);
                string[] lines = page.Split('\n');
        foreach (string line in lines)
                {
                    strlist.Add(line);
                }

            }
        }
    return strlist;

    }