phares3757/pdf-text-stripper
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use of Splitter

Browse Source 
dotnet 8.0.100
This commit is contained in:
Mike Phares
2025-02-26 12:36:41 -07:00
parent 18ee50624e
commit cb333ec871
7 changed files with 71 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
PDF-Text-Stripper/PDF-Text-Stripper.csproj
View File

@ -8,7 +8,7 @@
<PackageId>Infineon.Mesa.PDF.Text.Stripper</PackageId>
<RuntimeIdentifier>win-x86</RuntimeIdentifier>
<TargetFrameworks>net48</TargetFrameworks>
<Version>4.8.0.1</Version>
<Version>4.8.0.2</Version>
</PropertyGroup>
<ItemGroup Condition=" '$(TargetFramework)' == 'net48' ">
<Reference Include="Microsoft.CSharp" />

45
PDF-Text-Stripper/Program.cs
View File

@ -5,19 +5,42 @@ using System.Linq;
namespace PDF_Text_Stripper;
internal class Program
public class Program
{
private static void PDFTextStripper(string file)
private static void PortableDocumentFormatWriteText(string sourceFileName)
{
string altFileName = Path.ChangeExtension(file, ".txt");
if(File.Exists(altFileName))
File.Delete(altFileName);
org.apache.pdfbox.pdmodel.PDDocument pdfDocument = org.apache.pdfbox.pdmodel.PDDocument.load(file);
org.apache.pdfbox.util.PDFTextStripper stripper = new();
string text = stripper.getText(pdfDocument);
pdfDocument.close();
File.WriteAllText(altFileName, text);
object item;
string pageText;
string pagePDFFile;
string pageTextFile;
java.io.File file = new(sourceFileName);
org.apache.pdfbox.util.Splitter splitter = new();
string sourcePath = Path.GetDirectoryName(sourceFileName) ?? throw new Exception();
string sourceFileNameWithoutExtension = Path.GetFileNameWithoutExtension(sourceFileName);
org.apache.pdfbox.pdmodel.PDDocument pdDocument = org.apache.pdfbox.pdmodel.PDDocument.load(file);
java.util.List list = splitter.split(pdDocument);
java.util.ListIterator iterator = list.listIterator();
org.apache.pdfbox.util.PDFTextStripper dataStripper = new();
for (short i = 1; i < short.MaxValue; i++)
{
if (!iterator.hasNext())
break;
item = iterator.next();
pagePDFFile = string.Concat(sourcePath, @"\", sourceFileNameWithoutExtension, "_", i, ".pdf");
if (File.Exists(pagePDFFile))
File.Delete(pagePDFFile);
pageTextFile = Path.ChangeExtension(pagePDFFile, ".txt");
if (File.Exists(pageTextFile))
File.Delete(pageTextFile);
if (item is not org.apache.pdfbox.pdmodel.PDDocument pd)
continue;
pageText = dataStripper.getText(pd);
pd.save(pagePDFFile);
pd.close();
File.WriteAllText(pageTextFile, pageText);
}
pdDocument.close();
}
public static void Secondary(List<string> args)
@ -28,7 +51,7 @@ internal class Program
try
{
if (args.Any() && File.Exists(args[0]))
PDFTextStripper(args[0]);
PortableDocumentFormatWriteText(args[0]);
else
throw new Exception(args[0]);
}