issue #550: PDF invalid characters

ceskaexpedice · Aug 4, 2017 · 53e27ba · 53e27ba
1 parent a095143
commit 53e27ba
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 3 deletions.
diff --git a/common/build.gradle b/common/build.gradle
@@ -46,7 +46,7 @@ dependencies {
     compile name:"djvuframe-0.8.09"
     compile name:"javadjvu-0.8.09"
     compile "commons-configuration:commons-configuration:1.6"
-    compile "org.apache.commons:commons-lang3:3.2.1"
+    compile "org.apache.commons:commons-lang3:3.5"
 
     compile "com.yourmediashelf.fedora.client:fedora-client-core:0.7"
     compile "com.yourmediashelf.fedora.client:fedora-client-messaging:0.7"

diff --git a/indexer/src/cz/incad/kramerius/indexer/ExtendedFields.java b/indexer/src/cz/incad/kramerius/indexer/ExtendedFields.java
@@ -9,6 +9,7 @@
 import cz.incad.kramerius.security.impl.criteria.mw.DatesParser;
 import cz.incad.kramerius.utils.DCUtils;
 import cz.incad.kramerius.utils.conf.KConfiguration;
+import org.apache.commons.io.FileUtils;
 import org.apache.commons.lang3.StringEscapeUtils;
 import org.apache.pdfbox.cos.COSDocument;
 import org.apache.pdfbox.pdfparser.PDFParser;
@@ -25,6 +26,10 @@
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.StringReader;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+import java.nio.charset.CodingErrorAction;
 import java.text.DateFormat;
 import java.text.SimpleDateFormat;
 import java.util.ArrayList;
@@ -115,7 +120,7 @@ public void setPDFDocument(String pid) throws Exception {
 
                 File pdfImg = File.createTempFile(pid,null);
                 pdfImg.deleteOnExit();
-                java.nio.file.Files.copy(is,pdfImg.toPath(),java.nio.file.StandardCopyOption.REPLACE_EXISTING);
+                FileUtils.copyInputStreamToFile(is, pdfImg);
 
 
                 if (KConfiguration.getInstance().getConfiguration().getBoolean("convert.pdf.loadNonSeq", false)){
@@ -159,7 +164,7 @@ private String getPDFPage(int page) throws Exception {
                 stripper.setEndPage(page);
             }
 
-            return StringEscapeUtils.escapeXml(stripper.getText(pdDoc));
+            return StringEscapeUtils.escapeXml10(stripper.getText(pdDoc));
         } catch (Exception ex) {
             return "";
         }