Author: tallison
Date: Fri Jul 24 14:06:30 2015
New Revision: 1692521
URL: http://svn.apache.org/r1692521
Log:
TIKA-1678: clean up and add test file and unit test
Added:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
(with props)
tika/trunk/tika-parsers/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf
Removed:
tika/trunk/tika-parsers/src/main/java/org/apache/pdfbox/
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
Added:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java?rev=1692521&view=auto
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
(added)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
Fri Jul 24 14:06:30 2015
@@ -0,0 +1,115 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.tika.parser.pdf;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.pdfbox.cos.COSString;
+import org.apache.pdfbox.pdfparser.BaseParser;
+
+/**
+ * In fairly rare cases, a PDF's XMP will contain a string that
+ * has incorrectly been encoded with PDFEncoding: an octal for non-ascii and
+ * ascii for ascii, e.g.
"\376\377\000M\000i\000c\000r\000o\000s\000o\000f\000t\000"
+ * <p>
+ * This class can be used to decode those strings.
+ * <p>
+ * See TIKA-1678. Many thanks to Andrew Jackson for raising this issue
+ * and Tilman Hausherr for the solution.
+ * <p>
+ * As of this writing, we are only handling strings that start with
+ * an encoded BOM. Andrew Jackson found a handful of other examples (e.g.
+ * this ISO-8859-7 string:
+ * "Microsoft Word - \\323\\365\\354\\354\\345\\364\\357\\367\\336
+ * \\364\\347\\362 PRAKSIS \\363\\364\\357")
+ * that we aren't currently handling.
+ */
+class PDFEncodedStringDecoder {
+
+ private static final String[] PDF_ENCODING_BOMS = {
+ "\\376\\377", //UTF-16BE
+ "\\377\\376", //UTF-16LE
+ "\\357\\273\\277"//UTF-8
+ };
+
+ /**
+ * Does this string contain an octal-encoded UTF BOM?
+ * Call this statically to determine if you should bother creating a new
parser to parse it.
+ * @param s
+ * @return
+ */
+ static boolean shouldDecode(String s) {
+ if (s == null || s.length() < 8) {
+ return false;
+ }
+ for (String BOM : PDF_ENCODING_BOMS) {
+ if (s.startsWith(BOM)) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ /**
+ * This assumes that {@link #shouldDecode(String)} has been called
+ * and has returned true. If you run this on a non-octal encoded string,
+ * disaster will happen!
+ *
+ * @param value
+ * @return
+ */
+ String decode(String value) {
+ try {
+ byte[] bytes = new String("(" + value +
")").getBytes("ISO-8859-1");
+ InputStream is = new ByteArrayInputStream(bytes);
+ COSStringParser p = new COSStringParser(is);
+ String parsed = p.myParseCOSString();
+ if (parsed != null) {
+ return parsed;
+ }
+ } catch (IOException e) {
+ //oh well, we tried.
+ }
+ //just return value if something went wrong
+ return value;
+ }
+
+ class COSStringParser extends BaseParser {
+
+ COSStringParser(InputStream buffer) throws IOException {
+ super(buffer);
+ }
+
+ /**
+ *
+ * @return parsed string or null if something went wrong.
+ */
+ String myParseCOSString() {
+ try {
+ COSString cosString = parseCOSString();
+ if (cosString != null) {
+ return cosString.getString();
+ }
+ } catch (IOException e) {
+ }
+ return null;
+ }
+ }
+}
Propchange:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFEncodedStringDecoder.java
------------------------------------------------------------------------------
svn:eol-style = LF
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=1692521&r1=1692520&r2=1692521&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
Fri Jul 24 14:06:30 2015
@@ -37,7 +37,6 @@ import org.apache.pdfbox.exceptions.Cryp
import org.apache.pdfbox.io.RandomAccess;
import org.apache.pdfbox.io.RandomAccessBuffer;
import org.apache.pdfbox.io.RandomAccessFile;
-import org.apache.pdfbox.pdfparser.PDFOctalUnicodeDecoder;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
@@ -458,8 +457,8 @@ public class PDFParser extends AbstractP
}
private String decode(String value) {
- if (PDFOctalUnicodeDecoder.shouldDecode(value)) {
- PDFOctalUnicodeDecoder d = new PDFOctalUnicodeDecoder();
+ if (PDFEncodedStringDecoder.shouldDecode(value)) {
+ PDFEncodedStringDecoder d = new PDFEncodedStringDecoder();
return d.decode(value);
}
return value;
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java?rev=1692521&r1=1692520&r2=1692521&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
Fri Jul 24 14:06:30 2015
@@ -1346,6 +1346,13 @@ public class PDFParserTest extends TikaT
}
}
+ @Test
+ public void testPDFEncodedStringsInXMP() throws Exception {
+ //TIKA-1678
+ XMLResult r = getXML("testPDF_PDFEncodedStringInXMP.pdf");
+ assertEquals("Microsoft", r.metadata.get(TikaCoreProperties.TITLE));
+ }
+
private void assertException(String path, Parser parser, ParseContext
context, Class expected) {
boolean noEx = false;
InputStream is = getResourceAsStream(path);
Added:
tika/trunk/tika-parsers/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf?rev=1692521&view=auto
==============================================================================
Binary files
tika/trunk/tika-parsers/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf
(added) and
tika/trunk/tika-parsers/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf
Fri Jul 24 14:06:30 2015 differ
