From 6031ba41fa8c054ebb1e86b1890c75d4df34c6ac Mon Sep 17 00:00:00 2001
From: pdanner <pdanner@7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c>
Date: Mon, 29 Nov 2010 14:23:43 +0000
Subject: added correction on verify

git-svn-id: https://joinup.ec.europa.eu/svn/pdf-as/trunk@629 7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c
---
 .../pdfas/impl/input/IncrementalUpdateParser.java  | 43 +++++++++++++++++-----
 1 file changed, 33 insertions(+), 10 deletions(-)

(limited to 'src')

diff --git a/src/main/java/at/gv/egiz/pdfas/impl/input/IncrementalUpdateParser.java b/src/main/java/at/gv/egiz/pdfas/impl/input/IncrementalUpdateParser.java
index b4c2bef..096bb0b 100644
--- a/src/main/java/at/gv/egiz/pdfas/impl/input/IncrementalUpdateParser.java
+++ b/src/main/java/at/gv/egiz/pdfas/impl/input/IncrementalUpdateParser.java
@@ -5,13 +5,16 @@ package at.gv.egiz.pdfas.impl.input;
 
 import java.util.List;
 
-import at.gv.egiz.pdfas.impl.input.helper.DataSourceHelper;
-import at.gv.egiz.pdfas.exceptions.ErrorCode;
-import at.gv.egiz.pdfas.framework.input.PdfDataSource;
-
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 
+import at.gv.egiz.pdfas.exceptions.ErrorCode;
+import at.gv.egiz.pdfas.framework.input.PdfDataSource;
+import at.gv.egiz.pdfas.framework.input.PdfDataSourceHolder;
+import at.gv.egiz.pdfas.framework.input.correction.Corrector;
+import at.gv.egiz.pdfas.framework.input.correction.CorrectorFactory;
+import at.gv.egiz.pdfas.impl.input.helper.DataSourceHelper;
+import at.knowcenter.wag.egov.egiz.cfg.SettingsReader;
 import at.knowcenter.wag.egov.egiz.exceptions.PDFDocumentException;
 import at.knowcenter.wag.exactparser.ParseDocument;
 
@@ -26,24 +29,44 @@ public class IncrementalUpdateParser
    */
   private static final Log log = LogFactory.getLog(IncrementalUpdateParser.class);
   
-  public static List parsePdfIntoIUBlocks (PdfDataSource pdfDataSource) throws PDFDocumentException
+  public static List parsePdfIntoIUBlocks (PdfDataSourceHolder pdfDataSource) throws PDFDocumentException
   {
     log.trace("parsePdfIntoIUBlocks:");
     
     List blocks = null;
     try
     {
-      byte [] pdf = DataSourceHelper.convertDataSourceToByteArray(pdfDataSource);
+      byte [] pdf = DataSourceHelper.convertDataSourceToByteArray(pdfDataSource.getDataSource());
       blocks = ParseDocument.parseDocument(pdf);
     }
-    catch (Exception e)
-    {
-      log.error("Error while parsing Document into IU blocks.", e);
-      throw new PDFDocumentException(ErrorCode.DOCUMENT_CANNOT_BE_READ, e);
+    catch (Exception e)  {
+       try {
+          log.debug("Error while parsing Document.", e);
+          boolean tryToCorrect = SettingsReader.getInstance().getSetting("correct_document_on_verify_if_necessary", "false").equals("true");
+          if (tryToCorrect) {
+             log.info("Correcting document...");
+             Corrector cor = CorrectorFactory.createCorrector();
+             PdfDataSource correctedDS = cor.correctDocument(pdfDataSource.getDataSource());
+             log.info("Correction finished.");
+             byte [] pdf = DataSourceHelper.convertDataSourceToByteArray(correctedDS);
+             blocks = ParseDocument.parseDocument(pdf);
+             pdfDataSource.setDataSource(correctedDS);
+          } else {
+             makeError(e);
+          }
+
+      } catch (Exception e1) {
+         makeError(e);
+      }
     }
 
     log.trace("parsePdfIntoIUBlocks finished.");
     return blocks;
   }
 
+   private static void makeError(Exception e) throws PDFDocumentException {
+      log.error("Error while parsing Document into IU blocks.", e);
+      throw new PDFDocumentException(ErrorCode.DOCUMENT_CANNOT_BE_READ, e);
+   }
+  
 }
-- 
cgit v1.2.3