diff --git a/alfresco-docker-tika/src/main/java/org/alfresco/transformer/Tika.java b/alfresco-docker-tika/src/main/java/org/alfresco/transformer/Tika.java
index a7091002..c97993cb 100644
--- a/alfresco-docker-tika/src/main/java/org/alfresco/transformer/Tika.java
+++ b/alfresco-docker-tika/src/main/java/org/alfresco/transformer/Tika.java
@@ -22,6 +22,7 @@ import org.apache.tika.parser.Parser;
import org.apache.tika.parser.microsoft.OfficeParser;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.parser.pdf.PDFParser;
+import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.parser.pkg.PackageParser;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ExpandedTitleContentHandler;
@@ -429,6 +430,7 @@ public class Tika
public static final String TARGET_MIMETYPE = "--targetMimetype=";
public static final String TARGET_ENCODING = "--targetEncoding=";
public static final String INCLUDE_CONTENTS = "--includeContents";
+ public static final String NOT_EXTRACT_BOOKMARKS_TEXT = "--notExtractBookmarksText";
public static final String CSV = "csv";
public static final String DOC = "doc";
@@ -449,6 +451,7 @@ public class Tika
private Parser autoDetectParser;
private Parser ooXmlParser = new OOXMLParser();
private Parser tikaOfficeDetectParser = new TikaOfficeDetectParser();
+ private PDFParserConfig pdfParserConfig = new PDFParserConfig();
private DocumentSelector pdfBoxEmbededDocumentSelector = new DocumentSelector()
{
@@ -505,6 +508,7 @@ public class Tika
String sourceFilename = null;
String targetFilename = null;
Boolean includeContents = null;
+ Boolean notExtractBookmarksText = null;
for (String arg: args)
{
@@ -523,6 +527,11 @@ public class Tika
{
targetMimetype = getValue(arg, true, targetMimetype, TARGET_MIMETYPE);
}
+ else if (arg.startsWith(NOT_EXTRACT_BOOKMARKS_TEXT))
+ {
+ getValue(arg, false, notExtractBookmarksText, NOT_EXTRACT_BOOKMARKS_TEXT);
+ notExtractBookmarksText = true;
+ }
else
{
throw new IllegalArgumentException("Unexpected argument "+arg);
@@ -553,8 +562,9 @@ public class Tika
throw new IllegalArgumentException("Missing arguments");
}
includeContents = includeContents == null ? false : includeContents;
+ notExtractBookmarksText = notExtractBookmarksText == null ? false : notExtractBookmarksText;
- transform(transform, includeContents, sourceFilename, targetFilename, targetMimetype, targetEncoding);
+ transform(transform, includeContents, notExtractBookmarksText, sourceFilename, targetFilename, targetMimetype, targetEncoding);
}
private String getValue(String arg, boolean valueExpected, Object value, String optionName)
@@ -577,6 +587,7 @@ public class Tika
// Adds transform specific values such as parser and documentSelector.
private void transform(String transform, Boolean includeContents,
+ Boolean notExtractBookmarksText,
String sourceFilename,
String targetFilename, String targetMimetype, String targetEncoding)
{
@@ -608,11 +619,12 @@ public class Tika
break;
}
- transform(parser, documentSelector, includeContents, sourceFilename, targetFilename, targetMimetype, targetEncoding);
+ transform(parser, documentSelector, includeContents, notExtractBookmarksText, sourceFilename, targetFilename, targetMimetype, targetEncoding);
}
private void transform(Parser parser, DocumentSelector documentSelector, Boolean includeContents,
+ Boolean notExtractBookmarksText,
String sourceFilename,
String targetFilename, String targetMimetype, String targetEncoding)
{
@@ -626,7 +638,7 @@ public class Tika
os = new FileOutputStream(targetFilename);
ow = new BufferedWriter(new OutputStreamWriter(os, targetEncoding));
Metadata metadata = new Metadata();
- ParseContext context = buildParseContext(documentSelector, includeContents);
+ ParseContext context = buildParseContext(documentSelector, includeContents, notExtractBookmarksText);
ContentHandler handler = getContentHandler(targetMimetype, ow);
parser.parse(is, handler, metadata, context);
@@ -780,15 +792,21 @@ public class Tika
}
}
- protected ParseContext buildParseContext(DocumentSelector documentSelector, Boolean includeContents)
+ protected ParseContext buildParseContext(DocumentSelector documentSelector, Boolean includeContents, Boolean notExtractBookmarksText)
{
ParseContext context = new ParseContext();
+
if (documentSelector != null)
{
context.set(DocumentSelector.class, documentSelector);
}
- // pdfParserConfig is never set in the original repo code, so code removed here.
+ if (notExtractBookmarksText.equals(true))
+ {
+ pdfParserConfig.setExtractBookmarksText(false);
+ // pdfParserConfig is set to override default settings
+ context.set(PDFParserConfig.class, pdfParserConfig);
+ }
// If Archive transform
if (includeContents != null)
@@ -798,4 +816,5 @@ public class Tika
return context;
}
+
}
diff --git a/alfresco-docker-tika/src/main/java/org/alfresco/transformer/TikaController.java b/alfresco-docker-tika/src/main/java/org/alfresco/transformer/TikaController.java
index 8c365f0c..6c23e9d6 100644
--- a/alfresco-docker-tika/src/main/java/org/alfresco/transformer/TikaController.java
+++ b/alfresco-docker-tika/src/main/java/org/alfresco/transformer/TikaController.java
@@ -113,7 +113,9 @@ public class TikaController extends AbstractTransformerController
@RequestParam(value = "testDelay", required = false) Long testDelay,
@RequestParam(value = "transform") String transform,
- @RequestParam(value="includeContents", required = false) Boolean includeContents)
+ @RequestParam(value="includeContents", required = false) Boolean includeContents,
+ @RequestParam(value="notExtractBookmarksText", required = false) Boolean notExtractBookmarksText)
+
{
if (!TRANSFORM_NAMES.contains(transform))
{
@@ -130,6 +132,7 @@ public class TikaController extends AbstractTransformerController
callTransform(sourceFile, targetFile, transform,
includeContents != null && includeContents ? INCLUDE_CONTENTS : null,
+ notExtractBookmarksText != null && notExtractBookmarksText ? NOT_EXTRACT_BOOKMARKS_TEXT: null,
TARGET_MIMETYPE+targetMimetype, TARGET_ENCODING+targetEncoding);
return createAttachment(targetFilename, targetFile, testDelay);
diff --git a/alfresco-docker-tika/src/main/resources/templates/transformForm.html b/alfresco-docker-tika/src/main/resources/templates/transformForm.html
index 5e230dbf..9171491e 100644
--- a/alfresco-docker-tika/src/main/resources/templates/transformForm.html
+++ b/alfresco-docker-tika/src/main/resources/templates/transformForm.html
@@ -25,8 +25,8 @@
includeContents (archive) * | |
timeout | |
testDelay | |
-
- | |
+ notExtractBookmarksText | |
+ | |
diff --git a/alfresco-docker-tika/src/test/java/org/alfresco/transformer/TikaControllerTest.java b/alfresco-docker-tika/src/test/java/org/alfresco/transformer/TikaControllerTest.java
index bbf14145..dd711d73 100644
--- a/alfresco-docker-tika/src/test/java/org/alfresco/transformer/TikaControllerTest.java
+++ b/alfresco-docker-tika/src/test/java/org/alfresco/transformer/TikaControllerTest.java
@@ -341,4 +341,13 @@ public class TikaControllerTest extends AbstractTransformerControllerTest
{
transform(TEXT_MINING, DOC, TXT, MIMETYPE_WORD, MIMETYPE_TEXT_PLAIN, null, EXPECTED_TEXT_CONTENT_CONTAINS);
}
+
+ @Test
+ public void pdfToTxtExtractBookmarksTest() throws Exception
+ {
+ super.mockTransformCommand(controller, PDF, TXT, MIMETYPE_PDF, true);
+ mockMvc.perform(mockMvcRequest("/transform", sourceFile, "targetExtension", targetExtension).param("notExtractBookmarksText", "true"))
+ .andExpect(status().is(200))
+ .andExpect(header().string("Content-Disposition", "attachment; filename*= UTF-8''quick." + targetExtension));
+ }
}