java - SAS Proc Groovy - Apache PDFBox 库无法从 pdfbox.jar 文件中读取资源

Question

目标：阅读PDF文件并将其转换为文本格式。

我为此使用 SAS“Proc Groovy”和“Java Apache PDFBox Library”。但是代码给出了错误，因为 Apache PDFBox 版本已从 2.0.21 更改为 2.0.22。请建议必须对此代码进行哪些更改才能再次使用它。

SAS Proc Groovy 可以运行 Java 代码。因此，我们在 SAS Proc Groovy 中使用 Java PDF 库 (Apache PDFBox) 将 PDF 转换为文本格式。

代码：

filename overview "&temp/overview.pdf";
filename ov_text  "&temp/overview.txt";

* download a pdf document;
proc http           
url="https://cdn.nar.realtor/sites/default/files/documents/ehs-11-2020-overview-2020-12-22.pdf"       
method="get"        
proxyhost="&proxy_host."        
proxyport=&port         
out=overview;     
run;

* download the Apache PDFBox library (a .jar file); 
filename jar '&temp/pdfbox.jar';

%if %sysfunc(FEXIST(jar)) ne 1 %then %do;
proc http
url='https://www.apache.org/dyn/closer.lua?filename=pdfbox/2.0.22/pdfbox-app-2.0.22.jar&action=download'
proxyhost="&proxy_host."        
proxyport=&port
out=jar;
run;
%end;

* Use GROOVY to read the PDF, strip out the text and position, and write that
* parse to a text file which SAS can read;

proc groovy classpath="&temp.jar"; 
  submit 
    "%sysfunc(pathname(overview))"  /* the input, a pdf file */
    "%sysfunc(pathname(ov_text))"   /* the output, a text file */
  ;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.ArrayList;
import java.util.List;
import java.io.FileWriter;
import java.io.PrintWriter;

public class GetLinesFromPDF extends PDFTextStripper {
    
    static List<String> lines = new ArrayList<String>();
    public GetLinesFromPDF() throws IOException {
    }
    /**
     * @throws IOException If there is an error parsing the document.
     */
    public static void main( String[] args ) throws IOException {
        PDDocument document = null;
        PrintWriter out = null;
        String inPdf = args[0];
        String outTxt = args[1];

        try {
            document = PDDocument.load( new File(inPdf) );

            PDFTextStripper stripper = new GetLinesFromPDF();

            stripper.setSortByPosition( true );
            stripper.setStartPage( 0 );
            stripper.setEndPage( document.getNumberOfPages() );

            Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
            stripper.writeText(document, dummy);
            
            out = new PrintWriter(new FileWriter(outTxt));

            // print lines to text file
            for(String line:lines){
              out.println(line); 
            }
        }
        finally {
            if( document != null ) {
                document.close();
            }
            if( out != null ) {
                out.close();
            }
        }
    }
    /**
     * Override the default functionality of PDFTextStripper.writeString()
     */
    @Override
    protected void writeString(String str, List<TextPosition> textPositions) throws IOException {
        String places = "";

        for(TextPosition tp:textPositions){
          places += "(" + tp.getX() + "," + tp.getY() + ") ";
        }

        lines.add(str + " found @ " + places);
    }
}

  endsubmit;
quit;

* preview the stripped text that was saved;

data _null_;
  infile ov_text;
  input;
  putlog _infile_;
run;

运行上述代码后的部分错误消息：

    ERROR: The SUBMIT command failed.
    groovy.lang.GroovyRuntimeException: Failed to create Script instance for class: class GetLinesFromPDF. Reason: 
    java.util.zip.ZipException: error reading zip file
         at org.codehaus.groovy.runtime.InvokerHelper.createScript(InvokerHelper.java:475)
         at groovy.lang.GroovyShell.parse(GroovyShell.java:689)
         at groovy.lang.GroovyShell.parse(GroovyShell.java:725)
         at groovy.lang.GroovyShell.parse(GroovyShell.java:716)
    Caused by: java.util.zip.ZipException: error reading zip file
         at java.util.zip.ZipFile.read(Native Method)
         at java.util.zip.ZipFile.access$1400(ZipFile.java:60)
         at java.util.zip.ZipFile$ZipFileInputStream.read(ZipFile.java:734)
         at java.util.zip.ZipFile$ZipFileInflaterInputStream.fill(ZipFile.java:434)
         at java.util.zip.InflaterInputStream.read(InflaterInputStream.java:158)
         at java.io.FilterInputStream.read(FilterInputStream.java:133)
         at sun.nio.cs.StreamDecoder.readBytes(StreamDecoder.java:284)
         at sun.nio.cs.StreamDecoder.implRead(StreamDecoder.java:326)
         at sun.nio.cs.StreamDecoder.read(StreamDecoder.java:178)
         at java.io.InputStreamReader.read(InputStreamReader.java:184)
         at java.io.BufferedReader.fill(BufferedReader.java:161)
         at java.io.BufferedReader.readLine(BufferedReader.java:324)
         at java.io.BufferedReader.readLine(BufferedReader.java:389)
         at org.apache.pdfbox.pdmodel.font.encoding.GlyphList.loadList(GlyphList.java:147)
         at org.apache.pdfbox.pdmodel.font.encoding.GlyphList.<init>(GlyphList.java:137)
         at org.apache.pdfbox.text.LegacyPDFStreamEngine.<init>(LegacyPDFStreamEngine.java:120)
         at org.apache.pdfbox.text.PDFTextStripper.<init>(PDFTextStripper.java:214)

标签： javasaspdfboxpdftotext