NiFi ExecuteScript 프로세서(Groovy)에서 Apache PDFBox 로 PDF 본문을 뽑아 FlowFile 내용으로 쓰고, 문서 메타데이터를 FlowFile 속성에 넣는 스크립트다. PDFBox jar 를 프로세서의 Module Directory 에 지정해야 한다.
import org.apache.pdfbox.pdmodel.*
import org.apache.pdfbox.util.*
import org.apache.pdfbox.text.*
def flowFile = session.get()
if(!flowFile) return
def s = new PDFTextStripper()
def doc, info
flowFile = session.write(flowFile, {inputStream, outputStream ->
doc = PDDocument.load(inputStream)
info = doc.getDocumentInformation()
s.writeText(doc, new OutputStreamWriter(outputStream))
} as StreamCallback
)
flowFile = session.putAttribute(flowFile, 'pdf.page.count', "${doc.getNumberOfPages()}")
flowFile = session.putAttribute(flowFile, 'pdf.title', "${info.getTitle()}" )
flowFile = session.putAttribute(flowFile, 'pdf.author',"${info.getAuthor()}" );
flowFile = session.putAttribute(flowFile, 'pdf.subject', "${info.getSubject()}" );
flowFile = session.putAttribute(flowFile, 'pdf.keywords', "${info.getKeywords()}" );
flowFile = session.putAttribute(flowFile, 'pdf.creator', "${info.getCreator()}" );
flowFile = session.putAttribute(flowFile, 'pdf.producer', "${info.getProducer()}" );
flowFile = session.putAttribute(flowFile, 'pdf.date.creation', "${info.getCreationDate()}" );
flowFile = session.putAttribute(flowFile, 'pdf.date.modified', "${info.getModificationDate()}");
flowFile = session.putAttribute(flowFile, 'pdf.trapped', "${info.getTrapped()}" );
session.transfer(flowFile, REL_SUCCESS)