You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2025/04/08 17:27:21 UTC
(tika) branch TIKA-4399 created (now 5053c7dff)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-4399
in repository https://gitbox.apache.org/repos/asf/tika.git
at 5053c7dff TIKA-4399 -- require TikaInputStream for embedded documents
This branch includes the following new commits:
new 5053c7dff TIKA-4399 -- require TikaInputStream for embedded documents
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(tika) 01/01: TIKA-4399 -- require TikaInputStream for embedded documents
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch TIKA-4399
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 5053c7dff439d0e74100e9f81a1e588a38fb1134
Author: tallison <ta...@apache.org>
AuthorDate: Tue Apr 8 13:20:43 2025 -0400
TIKA-4399 -- require TikaInputStream for embedded documents
---
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 14 +++----
.../tika/extractor/EmbeddedDocumentExtractor.java | 4 +-
.../tika/extractor/EmbeddedDocumentUtil.java | 5 +--
.../ParsingEmbeddedDocumentExtractor.java | 20 +++-------
.../apache/tika/extractor/RUnpackExtractor.java | 20 ++++------
.../java/org/apache/tika/io/TikaInputStream.java | 45 ++++++++++++++++++++++
.../org/apache/tika/renderer/RenderResult.java | 3 +-
.../org/apache/tika/parser/mock/MockParser.java | 4 +-
.../apache/tika/example/ExtractEmbeddedFiles.java | 3 +-
.../tika/parser/apple/AppleSingleFileParser.java | 18 +++++++--
.../parser/iwork/iwana/IWork13PackageParser.java | 30 ++++++++-------
.../org/apache/tika/parser/crypto/TSDParser.java | 4 +-
.../org/apache/tika/parser/html/HtmlHandler.java | 20 +++++-----
.../apache/tika/parser/jdbc/JDBCTableReader.java | 6 +--
.../tika/parser/mail/MailContentHandler.java | 8 ++--
.../org/apache/tika/parser/mbox/MboxParser.java | 5 ++-
.../apache/tika/parser/microsoft/EMFParser.java | 8 ++--
.../tika/parser/microsoft/JackcessExtractor.java | 6 +--
.../apache/tika/parser/microsoft/OfficeParser.java | 9 ++---
.../tika/parser/microsoft/OutlookExtractor.java | 11 +++---
.../tika/parser/microsoft/chm/ChmParser.java | 9 ++---
.../tika/parser/microsoft/libpst/EmailVisitor.java | 5 +--
.../microsoft/ooxml/xps/XPSExtractorDecorator.java | 13 ++++---
.../parser/microsoft/pst/PSTMailItemParser.java | 6 +--
.../parser/odf/FlatOpenDocumentMacroHandler.java | 5 +--
.../tika/parser/odf/OpenDocumentBodyHandler.java | 5 +--
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 38 ++++++++----------
.../java/org/apache/tika/parser/pdf/PDF2XHTML.java | 5 +--
.../java/org/apache/tika/parser/pdf/PDFParser.java | 4 +-
.../apache/tika/parser/pdf/PDFRenderingTest.java | 11 +++---
.../apache/tika/parser/pkg/CompressorParser.java | 5 ++-
.../java/org/apache/tika/parser/pkg/RarParser.java | 4 +-
.../org/apache/tika/parser/pkg/UnrarParser.java | 4 +-
.../org/apache/tika/parser/http/HttpParser.java | 11 +++---
.../org/apache/tika/parser/wacz/WACZParser.java | 4 +-
.../org/apache/tika/parser/warc/WARCParser.java | 2 +-
.../apache/tika/parser/xml/FictionBookParser.java | 8 ++--
.../org/apache/tika/parser/pkg/ZipParserTest.java | 3 +-
.../server/core/resource/UnpackerResource.java | 8 ++--
39 files changed, 214 insertions(+), 179 deletions(-)
diff --git a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
index 74c3cbf44..448feeff3 100644
--- a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
+++ b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
@@ -1086,12 +1086,10 @@ public class TikaCLI {
return true;
}
- public void parseEmbedded(InputStream inputStream, ContentHandler contentHandler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
+ @Override
+ public void parseEmbedded(TikaInputStream tis, ContentHandler contentHandler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
- if (!inputStream.markSupported()) {
- inputStream = TikaInputStream.get(inputStream);
- }
- MediaType contentType = detector.detect(inputStream, metadata);
+ MediaType contentType = detector.detect(tis, metadata);
String name = metadata.get(TikaCoreProperties.RESOURCE_NAME_KEY);
File outputFile = null;
@@ -1110,12 +1108,12 @@ public class TikaCLI {
System.out.println("Extracting '" + name + "' (" + contentType + ") to " + outputFile);
try (FileOutputStream os = new FileOutputStream(outputFile)) {
- if (embeddedStreamTranslator.shouldTranslate(inputStream, metadata)) {
- try (InputStream translated = embeddedStreamTranslator.translate(inputStream, metadata)) {
+ if (embeddedStreamTranslator.shouldTranslate(tis, metadata)) {
+ try (InputStream translated = embeddedStreamTranslator.translate(tis, metadata)) {
IOUtils.copy(translated, os);
}
} else {
- IOUtils.copy(inputStream, os);
+ IOUtils.copy(tis, os);
}
} catch (Exception e) {
//
diff --git a/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentExtractor.java b/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentExtractor.java
index f80420868..3f977e3db 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentExtractor.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentExtractor.java
@@ -18,11 +18,11 @@
package org.apache.tika.extractor;
import java.io.IOException;
-import java.io.InputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
public interface EmbeddedDocumentExtractor {
@@ -39,6 +39,6 @@ public interface EmbeddedDocumentExtractor {
* @throws java.io.IOException
*/
void parseEmbedded(
- InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
+ TikaInputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
throws SAXException, IOException;
}
diff --git a/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java b/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java
index d6e2c28a8..4d73545c1 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java
@@ -18,7 +18,6 @@ package org.apache.tika.extractor;
import java.io.IOException;
-import java.io.InputStream;
import java.io.Serializable;
import org.xml.sax.ContentHandler;
@@ -219,9 +218,9 @@ public class EmbeddedDocumentUtil implements Serializable {
return embeddedDocumentExtractor;
}
- public void parseEmbedded(InputStream inputStream, ContentHandler handler, Metadata metadata,
+ public void parseEmbedded(TikaInputStream tis, ContentHandler handler, Metadata metadata,
boolean outputHtml) throws IOException, SAXException {
- embeddedDocumentExtractor.parseEmbedded(inputStream, handler, metadata, outputHtml);
+ embeddedDocumentExtractor.parseEmbedded(tis, handler, metadata, outputHtml);
}
/**
diff --git a/tika-core/src/main/java/org/apache/tika/extractor/ParsingEmbeddedDocumentExtractor.java b/tika-core/src/main/java/org/apache/tika/extractor/ParsingEmbeddedDocumentExtractor.java
index 4f2331359..21117b33b 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/ParsingEmbeddedDocumentExtractor.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/ParsingEmbeddedDocumentExtractor.java
@@ -21,9 +21,7 @@ import static org.apache.tika.sax.XHTMLContentHandler.XHTML;
import java.io.File;
import java.io.FilenameFilter;
import java.io.IOException;
-import java.io.InputStream;
-import org.apache.commons.io.input.CloseShieldInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
@@ -31,7 +29,6 @@ import org.xml.sax.helpers.AttributesImpl;
import org.apache.tika.exception.CorruptedFileException;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
-import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -82,7 +79,7 @@ public class ParsingEmbeddedDocumentExtractor implements EmbeddedDocumentExtract
@Override
public void parseEmbedded(
- InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
+ TikaInputStream tis, ContentHandler handler, Metadata metadata, boolean outputHtml)
throws SAXException, IOException {
if (outputHtml) {
AttributesImpl attributes = new AttributesImpl();
@@ -99,16 +96,9 @@ public class ParsingEmbeddedDocumentExtractor implements EmbeddedDocumentExtract
}
// Use the delegate parser to parse this entry
- try (TemporaryResources tmp = new TemporaryResources()) {
- final TikaInputStream newStream =
- TikaInputStream.get(CloseShieldInputStream.wrap(stream), tmp, metadata);
- if (stream instanceof TikaInputStream) {
- final Object container = ((TikaInputStream) stream).getOpenContainer();
- if (container != null) {
- newStream.setOpenContainer(container);
- }
- }
- DELEGATING_PARSER.parse(newStream, new EmbeddedContentHandler(new BodyContentHandler(handler)),
+ try {
+ tis.setCloseShield();
+ DELEGATING_PARSER.parse(tis, new EmbeddedContentHandler(new BodyContentHandler(handler)),
metadata, context);
} catch (EncryptedDocumentException ede) {
recordException(ede, context);
@@ -118,6 +108,8 @@ public class ParsingEmbeddedDocumentExtractor implements EmbeddedDocumentExtract
throw new IOException(e);
} catch (TikaException e) {
recordException(e, context);
+ } finally {
+ tis.removeCloseShield();
}
if (outputHtml) {
diff --git a/tika-core/src/main/java/org/apache/tika/extractor/RUnpackExtractor.java b/tika-core/src/main/java/org/apache/tika/extractor/RUnpackExtractor.java
index 0e5928845..cbd560c50 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/RUnpackExtractor.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/RUnpackExtractor.java
@@ -35,7 +35,6 @@ import org.apache.tika.exception.CorruptedFileException;
import org.apache.tika.exception.EncryptedDocumentException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.BoundedInputStream;
-import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -68,7 +67,7 @@ public class RUnpackExtractor extends ParsingEmbeddedDocumentExtractor {
@Override
public void parseEmbedded(
- InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
+ TikaInputStream tis, ContentHandler handler, Metadata metadata, boolean outputHtml)
throws SAXException, IOException {
if (outputHtml) {
AttributesImpl attributes = new AttributesImpl();
@@ -85,20 +84,13 @@ public class RUnpackExtractor extends ParsingEmbeddedDocumentExtractor {
}
// Use the delegate parser to parse this entry
- try (TemporaryResources tmp = new TemporaryResources()) {
- final TikaInputStream newStream =
- TikaInputStream.get(CloseShieldInputStream.wrap(stream), tmp, metadata);
- if (stream instanceof TikaInputStream) {
- final Object container = ((TikaInputStream) stream).getOpenContainer();
- if (container != null) {
- newStream.setOpenContainer(container);
- }
- }
+ try {
EmbeddedDocumentBytesHandler bytesHandler = context.get(EmbeddedDocumentBytesHandler.class);
+ tis.setCloseShield();
if (bytesHandler != null) {
- parseWithBytes(newStream, handler, metadata);
+ parseWithBytes(tis, handler, metadata);
} else {
- parse(newStream, handler, metadata);
+ parse(tis, handler, metadata);
}
} catch (EncryptedDocumentException ede) {
recordException(ede, context);
@@ -108,6 +100,8 @@ public class RUnpackExtractor extends ParsingEmbeddedDocumentExtractor {
throw new IOException(e);
} catch (TikaException e) {
recordException(e, context);
+ } finally {
+ tis.removeCloseShield();
}
if (outputHtml) {
diff --git a/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java b/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
index 77e09226a..ea48487a0 100644
--- a/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
+++ b/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
@@ -119,6 +119,11 @@ public class TikaInputStream extends TaggedInputStream {
private int consecutiveEOFs = 0;
private byte[] skipBuffer;
+ /**
+ * If the stream should be shielded from closing
+ */
+ private int closeShieldDepth = 0;
+
//suffix of the file if known. This is used to create temp files
//with the right suffixes. This should include the initial . as in ".doc"
private String suffix = null;
@@ -266,6 +271,32 @@ public class TikaInputStream extends TaggedInputStream {
return get(stream, new TemporaryResources(), null);
}
+ /**
+ * Casts or wraps the given stream to a TikaInputStream instance.
+ * This method can be used to access the functionality of this class
+ * even when given just a normal input stream instance.
+ * <p>
+ * Use this method instead of the
+ * {@link #get(InputStream, TemporaryResources, Metadata)} alternative when you
+ * <em>do</em> explicitly close the returned stream. The recommended
+ * access pattern is:
+ * <pre>
+ * try (TikaInputStream stream = TikaInputStream.get(...)) {
+ * // process stream
+ * }
+ * </pre>
+ * <p>
+ * The given stream instance will be closed along with any other resources
+ * associated with the returned TikaInputStream instance when the
+ * {@link #close()} method is called by the try-with-resources statement.
+ *
+ * @param stream normal input stream
+ * @return a TikaInputStream instance
+ */
+ public static TikaInputStream get(InputStream stream, Metadata metadata) {
+ return get(stream, new TemporaryResources(), metadata);
+ }
+
/**
* Returns the given stream casts to a TikaInputStream, or
* <code>null</code> if the stream is not a TikaInputStream.
@@ -827,6 +858,9 @@ public class TikaInputStream extends TaggedInputStream {
@Override
public void close() throws IOException {
+ if (closeShieldDepth > 0) {
+ return;
+ }
path = null;
mark = -1;
@@ -853,6 +887,17 @@ public class TikaInputStream extends TaggedInputStream {
}
}
+ public void setCloseShield() {
+ this.closeShieldDepth++;
+ }
+
+ public void removeCloseShield() {
+ this.closeShieldDepth--;
+ }
+
+ public boolean isCloseShield() {
+ return closeShieldDepth > 0;
+ }
@Override
public String toString() {
String str = "TikaInputStream of ";
diff --git a/tika-core/src/main/java/org/apache/tika/renderer/RenderResult.java b/tika-core/src/main/java/org/apache/tika/renderer/RenderResult.java
index 3fd8d7d2c..25588c45b 100644
--- a/tika-core/src/main/java/org/apache/tika/renderer/RenderResult.java
+++ b/tika-core/src/main/java/org/apache/tika/renderer/RenderResult.java
@@ -18,7 +18,6 @@ package org.apache.tika.renderer;
import java.io.Closeable;
import java.io.IOException;
-import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
@@ -62,7 +61,7 @@ public class RenderResult implements Closeable {
}
}
- public InputStream getInputStream() throws IOException {
+ public TikaInputStream getInputStream() throws IOException {
if (result instanceof Path) {
return TikaInputStream.get((Path)result, metadata);
} else {
diff --git a/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java b/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
index 16458c9e9..84c9b7ab1 100644
--- a/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
+++ b/tika-core/src/test/java/org/apache/tika/parser/mock/MockParser.java
@@ -19,7 +19,6 @@ package org.apache.tika.parser.mock;
import static java.nio.charset.StandardCharsets.UTF_8;
-import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintStream;
@@ -56,6 +55,7 @@ import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
@@ -267,7 +267,7 @@ public class MockParser implements Parser {
if (!"".equals(contentType)) {
m.set(Metadata.CONTENT_TYPE, contentType);
}
- try (InputStream is = new ByteArrayInputStream(embeddedText.getBytes(UTF_8))) {
+ try (TikaInputStream is = TikaInputStream.get(embeddedText.getBytes(UTF_8))) {
extractor.parseEmbedded(is, new EmbeddedContentHandler(handler), m, true);
}
}
diff --git a/tika-example/src/main/java/org/apache/tika/example/ExtractEmbeddedFiles.java b/tika-example/src/main/java/org/apache/tika/example/ExtractEmbeddedFiles.java
index 9f1425da8..68d136202 100644
--- a/tika-example/src/main/java/org/apache/tika/example/ExtractEmbeddedFiles.java
+++ b/tika-example/src/main/java/org/apache/tika/example/ExtractEmbeddedFiles.java
@@ -32,6 +32,7 @@ import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
@@ -73,7 +74,7 @@ public class ExtractEmbeddedFiles {
}
@Override
- public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
+ public void parseEmbedded(TikaInputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
//try to get the name of the embedded file from the metadata
String name = metadata.get(TikaCoreProperties.RESOURCE_NAME_KEY);
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
index ac43b2985..d97ed1ba7 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
@@ -26,7 +26,6 @@ import java.util.List;
import java.util.Set;
import org.apache.commons.io.IOUtils;
-import org.apache.commons.io.input.CloseShieldInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -35,6 +34,8 @@ import org.apache.tika.exception.TikaMemoryLimitException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
import org.apache.tika.io.EndianUtils;
+import org.apache.tika.io.TemporaryResources;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
@@ -99,8 +100,19 @@ public class AppleSingleFileParser implements Parser {
// TODO: we should probably add a readlimiting wrapper around this
// stream to ensure that not more than contentFieldInfo.length bytes
// are read
- ex.parseEmbedded(CloseShieldInputStream.wrap(stream), xhtml, embeddedMetadata,
- true);
+ TikaInputStream tis = TikaInputStream.cast(stream);
+ TemporaryResources tmp = null;
+ if (tis == null) {
+ tmp = new TemporaryResources();
+ tis = TikaInputStream.get(stream, tmp, embeddedMetadata);
+ }
+ try {
+ ex.parseEmbedded(tis, xhtml, embeddedMetadata, true);
+ } finally {
+ if (tmp != null) {
+ tmp.close();
+ }
+ }
}
}
xhtml.endDocument();
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork13PackageParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork13PackageParser.java
index 2816efac1..ac65ff587 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork13PackageParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork13PackageParser.java
@@ -36,13 +36,13 @@ import com.dd.plist.PropertyListParser;
import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
import org.apache.commons.compress.archivers.zip.ZipFile;
import org.apache.commons.io.IOUtils;
-import org.apache.commons.io.input.CloseShieldInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Property;
@@ -128,9 +128,11 @@ public class IWork13PackageParser implements Parser {
if (type == null) {
type = IWork13DocumentType.detectIfPossible(entry);
}
- processZipEntry(entry, CloseShieldInputStream.wrap(zipStream), metadata, xhtml,
- parseContext,
- embeddedDocumentExtractor);
+
+ try (TemporaryResources tmp = new TemporaryResources()) {
+ TikaInputStream tis = TikaInputStream.get(zipStream, tmp, new Metadata());
+ processZipEntry(entry, tis, metadata, xhtml, parseContext, embeddedDocumentExtractor);
+ }
entry = zipStream.getNextEntry();
}
if (type == null) {
@@ -153,8 +155,8 @@ public class IWork13PackageParser implements Parser {
if (type == null) {
type = IWork13DocumentType.detectIfPossible(entry);
}
- try (InputStream is = zipFile.getInputStream(entry)) {
- processZipEntry(entry, is, metadata, xhtml, parseContext, embeddedDocumentExtractor);
+ try (TikaInputStream tis = TikaInputStream.get(zipFile.getInputStream(entry))) {
+ processZipEntry(entry, tis, metadata, xhtml, parseContext, embeddedDocumentExtractor);
} catch (SecurityException e) {
throw e;
} catch (Exception e) {
@@ -171,7 +173,7 @@ public class IWork13PackageParser implements Parser {
}
private void processZipEntry(ZipEntry entry,
- InputStream inputStream,
+ TikaInputStream tis,
Metadata metadata, XHTMLContentHandler xhtml,
ParseContext parseContext,
EmbeddedDocumentExtractor embeddedDocumentExtractor)
@@ -181,18 +183,18 @@ public class IWork13PackageParser implements Parser {
return;
}
if ("Metadata/Properties.plist".equals(streamName)) {
- extractProperties(inputStream, metadata);
+ extractProperties(tis, metadata);
} else if ("Metadata/BuildVersionHistory.plist".equals(streamName)) {
- extractVersionHistory(inputStream, metadata);
+ extractVersionHistory(tis, metadata);
} else if ("Metadata/DocumentIdentifier".equals(streamName)) {
- extractDocumentIdentifier(inputStream, metadata);
+ extractDocumentIdentifier(tis, metadata);
} else if ("preview.jpg".equals(streamName)) {
//process thumbnail
Metadata embeddedMetadata = new Metadata();
embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString());
embeddedMetadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, streamName);
- handleEmbedded(inputStream, embeddedMetadata, xhtml, embeddedDocumentExtractor);
+ handleEmbedded(tis, embeddedMetadata, xhtml, embeddedDocumentExtractor);
} else if (streamName.equals("preview-micro.jpg") ||
streamName.equals("preview-web.jpg")
|| streamName.endsWith(".iwa")) {
@@ -200,18 +202,18 @@ public class IWork13PackageParser implements Parser {
} else {
Metadata embeddedMetadata = new Metadata();
embeddedMetadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, streamName);
- handleEmbedded(inputStream, embeddedMetadata, xhtml, embeddedDocumentExtractor);
+ handleEmbedded(tis, embeddedMetadata, xhtml, embeddedDocumentExtractor);
}
}
- private void handleEmbedded(InputStream inputStream, Metadata embeddedMetadata,
+ private void handleEmbedded(TikaInputStream tis, Metadata embeddedMetadata,
XHTMLContentHandler xhtml,
EmbeddedDocumentExtractor embeddedDocumentExtractor)
throws IOException, SAXException {
if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
- embeddedDocumentExtractor.parseEmbedded(inputStream, xhtml, embeddedMetadata, true);
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, embeddedMetadata, true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
index c5a362464..2a0e4a0f9 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/main/java/org/apache/tika/parser/crypto/TSDParser.java
@@ -171,8 +171,8 @@ public class TSDParser implements Parser {
try {
cmsTimeStampedDataParser = new CMSTimeStampedDataParser(stream);
- try (InputStream is = TikaInputStream.get(cmsTimeStampedDataParser.getContent())) {
- edx.parseEmbedded(is, handler, metadata, true);
+ try (TikaInputStream tis = TikaInputStream.get(cmsTimeStampedDataParser.getContent())) {
+ edx.parseEmbedded(tis, handler, metadata, true);
}
} catch (SecurityException e) {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
index ea4d0195f..b613f3939 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
@@ -17,7 +17,6 @@
package org.apache.tika.parser.html;
import java.io.IOException;
-import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.nio.charset.StandardCharsets;
@@ -31,7 +30,6 @@ import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -39,6 +37,7 @@ import org.xml.sax.helpers.AttributesImpl;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.HTML;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Office;
@@ -341,8 +340,8 @@ class HtmlHandler extends TextContentHandler {
EmbeddedDocumentExtractor embeddedDocumentExtractor =
EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
- try (InputStream stream = UnsynchronizedByteArrayInputStream.builder().setByteArray(string.getBytes(StandardCharsets.UTF_8)).get()) {
- embeddedDocumentExtractor.parseEmbedded(stream, xhtml, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(string.getBytes(StandardCharsets.UTF_8))) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, m, true);
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
}
@@ -368,8 +367,8 @@ class HtmlHandler extends TextContentHandler {
EmbeddedDocumentExtractor embeddedDocumentExtractor =
EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
- try (InputStream stream = dataURIScheme.getInputStream()) {
- embeddedDocumentExtractor.parseEmbedded(stream, xhtml, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(dataURIScheme.getInputStream())) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, m, true);
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
}
@@ -401,18 +400,17 @@ class HtmlHandler extends TextContentHandler {
TikaCoreProperties.EmbeddedResourceType.INLINE.toString());
dataUriMetadata.set(Metadata.CONTENT_TYPE, dataURIScheme.getMediaType().toString());
if (embeddedDocumentExtractor.shouldParseEmbedded(dataUriMetadata)) {
- try (InputStream dataURISchemeInputStream = dataURIScheme.getInputStream()) {
+ try (TikaInputStream tis = TikaInputStream.get(dataURIScheme.getInputStream())) {
embeddedDocumentExtractor
- .parseEmbedded(dataURISchemeInputStream, xhtml, dataUriMetadata, true);
+ .parseEmbedded(tis, xhtml, dataUriMetadata, true);
} catch (IOException e) {
//swallow
}
}
}
- try (InputStream stream = UnsynchronizedByteArrayInputStream.builder().setByteArray(
- script.toString().getBytes(StandardCharsets.UTF_8)).get()) {
- embeddedDocumentExtractor.parseEmbedded(stream, xhtml, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(script.toString().getBytes(StandardCharsets.UTF_8))) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, m, true);
} catch (IOException e) {
//shouldn't ever happen
} finally {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
index 9df4d197d..3ed87ae0b 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-jdbc-commons/src/main/java/org/apache/tika/parser/jdbc/JDBCTableReader.java
@@ -32,7 +32,6 @@ import java.util.List;
import org.apache.commons.io.FilenameUtils;
import org.apache.commons.io.IOUtils;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -200,8 +199,9 @@ public class JDBCTableReader {
//is there a more efficient way to go from a Reader to an InputStream?
String s = clob.getSubString(0, readSize);
if (embeddedDocumentUtil.shouldParseEmbedded(m)) {
- embeddedDocumentUtil
- .parseEmbedded(UnsynchronizedByteArrayInputStream.builder().setByteArray(s.getBytes(UTF_8)).get(), handler, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(s.getBytes(UTF_8))) {
+ embeddedDocumentUtil.parseEmbedded(tis, handler, m, true);
+ }
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
index 7c5d266ca..9af23d004 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java
@@ -26,7 +26,6 @@ import java.util.Map.Entry;
import java.util.Stack;
import org.apache.commons.io.IOUtils;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.apache.commons.io.output.UnsynchronizedByteArrayOutputStream;
import org.apache.james.mime4j.MimeException;
import org.apache.james.mime4j.codec.DecodeMonitor;
@@ -546,9 +545,10 @@ class MailContentHandler implements ContentHandler {
inlineMetadata.set(TikaCoreProperties.CONTENT_TYPE_PARSER_OVERRIDE,
MediaType.TEXT_PLAIN.toString());
}
- parser.parse(UnsynchronizedByteArrayInputStream.builder().setByteArray(part.bytes).get(),
- new EmbeddedContentHandler(new BodyContentHandler(handler)), inlineMetadata,
- parseContext);
+ try (TikaInputStream tis = TikaInputStream.get(part.bytes)) {
+ parser.parse(tis,
+ new EmbeddedContentHandler(new BodyContentHandler(handler)), inlineMetadata, parseContext);
+ }
} catch (SAXException | TikaException e) {
throw new MimeException(e);
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mbox/MboxParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mbox/MboxParser.java
index 4c7bea74c..dddd9bd92 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mbox/MboxParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mbox/MboxParser.java
@@ -40,6 +40,7 @@ import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Message;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -130,11 +131,11 @@ public class MboxParser implements Parser {
saveHeaderInMetadata(mailMetadata, item);
}
- InputStream messageStream = message.toInputStream();
+ TikaInputStream msgStream = TikaInputStream.get(message.toInputStream());
message = null;
if (extractor.shouldParseEmbedded(mailMetadata)) {
- extractor.parseEmbedded(messageStream, xhtml, mailMetadata, true);
+ extractor.parseEmbedded(msgStream, xhtml, mailMetadata, true);
}
if (tracking) {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/EMFParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/EMFParser.java
index ae80cb62b..1ef4f1ee6 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/EMFParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/EMFParser.java
@@ -69,11 +69,11 @@ public class EMFParser implements Parser {
private static void handleEmbedded(byte[] data,
EmbeddedDocumentExtractor embeddedDocumentExtractor,
ContentHandler handler) throws TikaException, SAXException {
- try (InputStream is = TikaInputStream.get(data)) {
+ try (TikaInputStream tis = TikaInputStream.get(data)) {
Metadata embeddedMetadata = new Metadata();
if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
embeddedDocumentExtractor
- .parseEmbedded(is, new EmbeddedContentHandler(handler), embeddedMetadata,
+ .parseEmbedded(tis, new EmbeddedContentHandler(handler), embeddedMetadata,
true);
}
} catch (IOException e) {
@@ -204,9 +204,9 @@ public class EMFParser implements Parser {
Metadata embeddedMetadata = new Metadata();
embeddedMetadata.set(Metadata.CONTENT_TYPE, WMF_MEDIA_TYPE.toString());
if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
- try (InputStream is = TikaInputStream.get(bytes)) {
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
embeddedDocumentExtractor
- .parseEmbedded(is, new EmbeddedContentHandler(contentHandler),
+ .parseEmbedded(tis, new EmbeddedContentHandler(contentHandler),
embeddedMetadata, true);
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
index 409c34ca0..619ba601c 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
@@ -41,7 +41,6 @@ import com.healthmarketscience.jackcess.Table;
import com.healthmarketscience.jackcess.query.Query;
import com.healthmarketscience.jackcess.util.OleBlob;
import org.apache.commons.io.IOUtils;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.xml.sax.SAXException;
@@ -220,9 +219,8 @@ class JackcessExtractor extends AbstractPOIFSExtractor {
BodyContentHandler h = new BodyContentHandler();
Metadata m = new Metadata();
m.set(Metadata.CONTENT_TYPE, "text/html; charset=UTF-8");
- try {
- htmlParser
- .parse(UnsynchronizedByteArrayInputStream.builder().setByteArray(v.getBytes(UTF_8)).get(), h, m, parseContext);
+ try (TikaInputStream tis = TikaInputStream.get(v.getBytes(UTF_8))) {
+ htmlParser.parse(tis, h, m, parseContext);
handler.characters(h.toString());
} catch (SAXException e) {
WriteLimitReachedException.throwIfWriteLimitReached(e);
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
index 8fe685686..dade2ca5f 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
@@ -32,7 +32,6 @@ import java.util.Set;
import org.apache.commons.io.IOUtils;
import org.apache.commons.io.input.CloseShieldInputStream;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.apache.poi.hdgf.extractor.VisioTextExtractor;
import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.apache.poi.poifs.crypt.Decryptor;
@@ -118,7 +117,7 @@ public class OfficeParser extends AbstractOfficeParser {
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
embeddedDocumentExtractor.parseEmbedded(
//pass in space character so that we don't trigger a zero-byte exception
- UnsynchronizedByteArrayInputStream.builder().setByteArray(new byte[]{'\u0020'}).get(), xhtml, m, true);
+ TikaInputStream.get(new byte[]{'\u0020'}), xhtml, m, true);
}
return;
}
@@ -131,9 +130,9 @@ public class OfficeParser extends AbstractOfficeParser {
m.set(TikaCoreProperties.RESOURCE_NAME_KEY, e.getKey());
}
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
- embeddedDocumentExtractor.parseEmbedded(
- UnsynchronizedByteArrayInputStream.builder().setByteArray(e.getValue().getBytes(StandardCharsets.UTF_8)).get(),
- xhtml, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(e.getValue().getBytes(StandardCharsets.UTF_8))) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, m, true);
+ }
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
index 687724566..30e1ca14a 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
@@ -468,9 +468,9 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
if (htmlParser == null) {
htmlParser = new JSoupParser();
}
- htmlParser.parse(UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get(),
- new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(),
- parseContext);
+ try (TikaInputStream tis = TikaInputStream.get(data)) {
+ htmlParser.parse(tis, new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(), parseContext);
+ }
doneBody = true;
}
}
@@ -488,8 +488,9 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
if (rtfParser == null) {
rtfParser = new RTFParser();
}
- rtfParser.parseInline(UnsynchronizedByteArrayInputStream.builder().setByteArray(rtf.getData()).get(),
- xhtml, new Metadata(), parseContext);
+ try (TikaInputStream tis = TikaInputStream.get(rtf.getData())) {
+ rtfParser.parseInline(tis, xhtml, new Metadata(), parseContext);
+ }
doneBody = true;
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmParser.java
index 0255a9161..06b2dd518 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmParser.java
@@ -23,12 +23,12 @@ import java.util.Collections;
import java.util.HashSet;
import java.util.Set;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
@@ -94,12 +94,11 @@ public class ChmParser implements Parser {
private void parsePage(byte[] byteObject, Parser htmlParser, ContentHandler xhtml,
ParseContext context) throws TikaException, IOException, SAXException { // throws IOException
- InputStream stream = null;
Metadata metadata = new Metadata();
ContentHandler handler = new EmbeddedContentHandler(new BodyContentHandler(xhtml));// -1
- stream = UnsynchronizedByteArrayInputStream.builder().setByteArray(byteObject).get();
- htmlParser.parse(stream, handler, metadata, context);
-
+ try (TikaInputStream tis = TikaInputStream.get(byteObject)) {
+ htmlParser.parse(tis, handler, metadata, context);
+ }
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/libpst/EmailVisitor.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/libpst/EmailVisitor.java
index a12806472..d9cb6b9d2 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/libpst/EmailVisitor.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/libpst/EmailVisitor.java
@@ -17,7 +17,6 @@
package org.apache.tika.parser.microsoft.libpst;
import java.io.IOException;
-import java.io.InputStream;
import java.nio.file.FileVisitResult;
import java.nio.file.FileVisitor;
import java.nio.file.Path;
@@ -78,9 +77,9 @@ public class EmailVisitor implements FileVisitor<Path> {
.relativize(file.getParent())
.toString();
emailMetadata.set(PST.PST_FOLDER_PATH, pstPath);
- try (InputStream is = TikaInputStream.get(file)) {
+ try (TikaInputStream tis = TikaInputStream.get(file)) {
try {
- embeddedDocumentExtractor.parseEmbedded(is, xhtml, emailMetadata, true);
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, emailMetadata, true);
} catch (SAXException e) {
throw new IOException(e);
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSExtractorDecorator.java
index 933f3e99e..2e3d2d914 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSExtractorDecorator.java
@@ -41,6 +41,7 @@ import org.xml.sax.helpers.DefaultHandler;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor;
@@ -69,7 +70,7 @@ public class XPSExtractorDecorator extends AbstractOOXMLExtractor {
}
}
- private static InputStream getZipStream(String zipPath, ZipPackage zipPackage)
+ private static TikaInputStream getZipStream(String zipPath, ZipPackage zipPackage)
throws IOException, TikaException {
String targPath =
(zipPath.length() > 1 && zipPath.startsWith("/") ? zipPath.substring(1) : zipPath);
@@ -86,7 +87,7 @@ public class XPSExtractorDecorator extends AbstractOOXMLExtractor {
if (zipEntry == null) {
throw new TikaException("Couldn't find required zip entry: " + zipPath);
}
- return zipEntrySource.getInputStream(zipEntry);
+ return TikaInputStream.get(zipEntrySource.getInputStream(zipEntry));
}
@Override
@@ -130,9 +131,9 @@ public class XPSExtractorDecorator extends AbstractOOXMLExtractor {
private void handleEmbeddedImage(String zipPath, Metadata metadata,
EmbeddedDocumentUtil embeddedDocumentUtil,
XHTMLContentHandler xhtml) throws SAXException, IOException {
- InputStream stream = null;
+ TikaInputStream tis = null;
try {
- stream = getZipStream(zipPath, pkg);
+ tis = getZipStream(zipPath, pkg);
} catch (IOException | TikaException e) {
//store this exception in the parent's metadata
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
@@ -140,9 +141,9 @@ public class XPSExtractorDecorator extends AbstractOOXMLExtractor {
}
try {
- embeddedDocumentUtil.parseEmbedded(stream, xhtml, metadata, true);
+ embeddedDocumentUtil.parseEmbedded(tis, xhtml, metadata, true);
} finally {
- IOUtils.closeQuietly(stream);
+ IOUtils.closeQuietly(tis);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/pst/PSTMailItemParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/pst/PSTMailItemParser.java
index 4b21e5141..13c23a690 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/pst/PSTMailItemParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/pst/PSTMailItemParser.java
@@ -27,7 +27,6 @@ import com.pff.PSTAttachment;
import com.pff.PSTException;
import com.pff.PSTMessage;
import com.pff.PSTRecipient;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
@@ -115,8 +114,9 @@ public class PSTMailItemParser implements Parser {
metadata, context);
} else {
byte[] data = htmlChunk.getBytes(StandardCharsets.UTF_8);
- htmlParser.parse(UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get(),
- new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(), context);
+ try (TikaInputStream tis = TikaInputStream.get(data)) {
+ htmlParser.parse(tis, new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(), context);
+ }
}
return;
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/FlatOpenDocumentMacroHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/FlatOpenDocumentMacroHandler.java
index 3bd4b92de..4688cda1a 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/FlatOpenDocumentMacroHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/FlatOpenDocumentMacroHandler.java
@@ -17,7 +17,6 @@
package org.apache.tika.parser.odf;
import java.io.IOException;
-import java.io.InputStream;
import java.nio.charset.StandardCharsets;
import org.apache.commons.lang3.StringUtils;
@@ -108,9 +107,9 @@ class FlatOpenDocumentMacroHandler extends ContentHandlerDecorator {
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
- try (InputStream is = TikaInputStream.get(bytes)) {
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
embeddedDocumentExtractor
- .parseEmbedded(is, contentHandler, embeddedMetadata, true);
+ .parseEmbedded(tis, contentHandler, embeddedMetadata, true);
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java
index 94b1d86fb..0fbe29a74 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java
@@ -19,7 +19,6 @@ package org.apache.tika.parser.odf;
import static org.apache.tika.sax.XHTMLContentHandler.XHTML;
import java.io.IOException;
-import java.io.InputStream;
import java.util.BitSet;
import java.util.HashMap;
import java.util.Map;
@@ -529,8 +528,8 @@ class OpenDocumentBodyHandler extends ElementMappingContentHandler {
}
Metadata embeddedMetadata = new Metadata();
if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
- try (InputStream is = TikaInputStream.get(bytes)) {
- embeddedDocumentExtractor.parseEmbedded(is, handler, embeddedMetadata, true);
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
+ embeddedDocumentExtractor.parseEmbedded(tis, handler, embeddedMetadata, true);
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
index c3e6bb7e8..de47f2394 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
@@ -263,9 +263,9 @@ class AbstractPDF2XHTML extends PDFTextStripper {
if (supportedTypes.contains(XMP_MEDIA_TYPE)) {
//try the main metadata
if (pdfDocument.getDocumentCatalog().getMetadata() != null) {
- try (InputStream is = pdfDocument.getDocumentCatalog().getMetadata()
- .exportXMPMetadata()) {
- extractXMPAsEmbeddedFile(is, XMP_DOCUMENT_CATALOG_LOCATION);
+ try (TikaInputStream tis = TikaInputStream.get(
+ pdfDocument.getDocumentCatalog().getMetadata().exportXMPMetadata())) {
+ extractXMPAsEmbeddedFile(tis, XMP_DOCUMENT_CATALOG_LOCATION);
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
}
@@ -274,8 +274,8 @@ class AbstractPDF2XHTML extends PDFTextStripper {
int pageNumber = 1;
for (PDPage page : pdfDocument.getPages()) {
if (page.getMetadata() != null) {
- try (InputStream is = page.getMetadata().exportXMPMetadata()) {
- extractXMPAsEmbeddedFile(is, XMP_PAGE_LOCATION_PREFIX + pageNumber);
+ try (TikaInputStream tis = TikaInputStream.get(page.getMetadata().exportXMPMetadata())) {
+ extractXMPAsEmbeddedFile(tis, XMP_PAGE_LOCATION_PREFIX + pageNumber);
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
}
@@ -301,17 +301,17 @@ class AbstractPDF2XHTML extends PDFTextStripper {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
}
if (bytes != null) {
- try (InputStream is = UnsynchronizedByteArrayInputStream.builder().setByteArray(bytes).get()) {
- parseMetadata(is, xfaMetadata);
+ try (TikaInputStream tis = TikaInputStream.get(bytes)) {
+ parseMetadata(tis, xfaMetadata);
}
}
}
}
}
- private void extractXMPAsEmbeddedFile(InputStream is, String location)
+ private void extractXMPAsEmbeddedFile(TikaInputStream tis, String location)
throws IOException, SAXException {
- if (is == null) {
+ if (tis == null) {
return;
}
Metadata xmpMetadata = new Metadata();
@@ -320,19 +320,15 @@ class AbstractPDF2XHTML extends PDFTextStripper {
TikaCoreProperties.EmbeddedResourceType.METADATA.toString());
xmpMetadata.set(PDF.XMP_LOCATION, location);
if (embeddedDocumentExtractor.shouldParseEmbedded(xmpMetadata)) {
- try {
- parseMetadata(is, xmpMetadata);
- } finally {
- IOUtils.closeQuietly(is);
- }
+ parseMetadata(tis, xmpMetadata);
}
}
- private void parseMetadata(InputStream stream, Metadata embeddedMetadata)
+ private void parseMetadata(TikaInputStream tis, Metadata embeddedMetadata)
throws IOException, SAXException {
try {
- embeddedDocumentExtractor.parseEmbedded(stream, new EmbeddedContentHandler(xhtml),
+ embeddedDocumentExtractor.parseEmbedded(tis, new EmbeddedContentHandler(xhtml),
embeddedMetadata, true);
} catch (IOException e) {
handleCatchableIOE(e);
@@ -557,10 +553,10 @@ class AbstractPDF2XHTML extends PDFTextStripper {
try (TemporaryResources tmp = new TemporaryResources()) {
try (RenderResult renderResult = renderCurrentPage(pdPage, context, tmp)) {
Metadata renderMetadata = renderResult.getMetadata();
- try (InputStream is = renderResult.getInputStream()) {
+ try (TikaInputStream tis = renderResult.getInputStream()) {
renderMetadata.set(TikaCoreProperties.CONTENT_TYPE_PARSER_OVERRIDE,
ocrImageMediaType.toString());
- ocrParser.parse(is, new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
+ ocrParser.parse(tis, new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
renderMetadata, context);
}
}
@@ -966,8 +962,8 @@ class AbstractPDF2XHTML extends PDFTextStripper {
String js = jsAction.getAction();
js = (js == null) ? "" : js;
if (embeddedDocumentExtractor.shouldParseEmbedded(m)) {
- try (InputStream is = TikaInputStream.get(js.getBytes(StandardCharsets.UTF_8))) {
- embeddedDocumentExtractor.parseEmbedded(is, xhtml, m, true);
+ try (TikaInputStream tis = TikaInputStream.get(js.getBytes(StandardCharsets.UTF_8))) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, m, true);
}
}
addNonNullAttribute("class", "javascript", attributes);
@@ -1105,7 +1101,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
updateMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.VERSION.toString());
if (embeddedDocumentExtractor.shouldParseEmbedded(updateMetadata)) {
- try (InputStream tis = TikaInputStream.get(update)) {
+ try (TikaInputStream tis = TikaInputStream.get(update)) {
context.set(IsIncrementalUpdate.class, IsIncrementalUpdate.IS_INCREMENTAL_UPDATE);
embeddedDocumentExtractor.parseEmbedded(tis, xhtml, updateMetadata, false);
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
index 70d17a8b3..c483c4090 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
@@ -17,7 +17,6 @@
package org.apache.tika.parser.pdf;
import java.io.IOException;
-import java.io.InputStream;
import java.io.Writer;
import java.util.HashMap;
import java.util.HashSet;
@@ -175,9 +174,9 @@ class PDF2XHTML extends AbstractPDF2XHTML {
if (result.getStatus() == RenderResult.STATUS.SUCCESS) {
if (embeddedDocumentExtractor.shouldParseEmbedded(result.getMetadata())) {
- try (InputStream is = result.getInputStream()) {
+ try (TikaInputStream resultInputStream = result.getInputStream()) {
//TODO: add markup here?
- embeddedDocumentExtractor.parseEmbedded(is, xhtml,
+ embeddedDocumentExtractor.parseEmbedded(resultInputStream, xhtml,
result.getMetadata(), true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
index ce2cb398f..0d92ee520 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
@@ -432,8 +432,8 @@ public class PDFParser implements Parser, RenderingParser, Initializable {
for (RenderResult result : renderResults.getResults()) {
if (result.getStatus() == RenderResult.STATUS.SUCCESS) {
if (embeddedDocumentExtractor.shouldParseEmbedded(result.getMetadata())) {
- try (InputStream is = result.getInputStream()) {
- embeddedDocumentExtractor.parseEmbedded(is, xhtml, result.getMetadata(),
+ try (TikaInputStream tis = result.getInputStream()) {
+ embeddedDocumentExtractor.parseEmbedded(tis, xhtml, result.getMetadata(),
false);
} catch (SecurityException e) {
throw e;
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFRenderingTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFRenderingTest.java
index 08d18b6c1..526f27731 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFRenderingTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFRenderingTest.java
@@ -115,14 +115,13 @@ public class PDFRenderingTest extends TikaTest {
super(context);
}
- public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata,
+ @Override
+ public void parseEmbedded(TikaInputStream tis, ContentHandler handler, Metadata metadata,
boolean outputHtml) throws SAXException, IOException {
- TikaInputStream tstream = TikaInputStream.get(stream);
- byte[] bytes = Files.readAllBytes(tstream.getPath());
+
+ byte[] bytes = Files.readAllBytes(tis.getPath());
embedded.put(count++, bytes);
- try (InputStream is = Files.newInputStream(tstream.getPath())) {
- super.parseEmbedded(is, handler, metadata, outputHtml);
- }
+ super.parseEmbedded(tis, handler, metadata, outputHtml);
}
public Map<Integer, byte[]> getEmbedded() {
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
index 11ecf902e..48651cc7b 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
@@ -65,6 +65,7 @@ import org.apache.tika.exception.TikaException;
import org.apache.tika.exception.TikaMemoryLimitException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
@@ -228,7 +229,9 @@ public class CompressorParser implements Parser {
EmbeddedDocumentExtractor extractor =
EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
if (extractor.shouldParseEmbedded(entrydata)) {
- extractor.parseEmbedded(cis, xhtml, entrydata, true);
+ try (TikaInputStream tis = TikaInputStream.get(cis)) {
+ extractor.parseEmbedded(tis, xhtml, entrydata, true);
+ }
}
} finally {
cis.close();
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/RarParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/RarParser.java
index 871f29388..11a6e52a4 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/RarParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/RarParser.java
@@ -86,9 +86,9 @@ public class RarParser implements Parser {
Metadata entrydata = PackageParser.handleEntryMetadata(header.getFileName(),
header.getCTime(), header.getMTime(), header.getFullUnpackSize(),
xhtml);
- try (InputStream subFile = rar.getInputStream(header)) {
+ try (TikaInputStream rarTis = TikaInputStream.get(rar.getInputStream(header))) {
if (extractor.shouldParseEmbedded(entrydata)) {
- extractor.parseEmbedded(subFile, handler, entrydata, true);
+ extractor.parseEmbedded(rarTis, handler, entrydata, true);
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/UnrarParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/UnrarParser.java
index 20ee89dd7..f4005b526 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/UnrarParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/UnrarParser.java
@@ -132,8 +132,8 @@ public class UnrarParser implements Parser {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, fName);
metadata.set(TikaCoreProperties.ORIGINAL_RESOURCE_NAME, relPath);
if (extractor.shouldParseEmbedded(metadata)) {
- try (InputStream is = TikaInputStream.get(embeddedFile)) {
- extractor.parseEmbedded(is, xhtml, metadata, true);
+ try (TikaInputStream tis = TikaInputStream.get(embeddedFile)) {
+ extractor.parseEmbedded(tis, xhtml, metadata, true);
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/http/HttpParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/http/HttpParser.java
index 440291aee..3bfa09a8f 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/http/HttpParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/http/HttpParser.java
@@ -35,6 +35,7 @@ import org.xml.sax.SAXException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
@@ -79,8 +80,8 @@ public class HttpParser implements Parser {
if (contentLength > 0) {
MessageBody messageBody = LengthedBody.create(channel, buffer, contentLength);
Metadata payloadMetadata = new Metadata();
- try (InputStream messageStream = messageBody.stream()) {
- parsePayload(messageStream, xhtml, payloadMetadata, context);
+ try (TikaInputStream tis = TikaInputStream.get(messageBody.stream())) {
+ parsePayload(tis, xhtml, payloadMetadata, context);
}
}
} finally {
@@ -88,11 +89,11 @@ public class HttpParser implements Parser {
}
}
- private void parsePayload(InputStream stream, ContentHandler handler, Metadata metadata,
- ParseContext context) throws IOException, SAXException {
+ private void parsePayload(TikaInputStream tis, ContentHandler handler, Metadata metadata,
+ ParseContext context) throws IOException, SAXException {
EmbeddedDocumentExtractor ex = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
if (ex.shouldParseEmbedded(metadata)) {
- ex.parseEmbedded(stream, handler, metadata, true);
+ ex.parseEmbedded(tis, handler, metadata, true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/wacz/WACZParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/wacz/WACZParser.java
index e78511f2b..fcf4042df 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/wacz/WACZParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/wacz/WACZParser.java
@@ -116,9 +116,9 @@ public class WACZParser implements Parser {
Metadata metadata = new Metadata();
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, name);
metadata.set(Metadata.CONTENT_LENGTH, Long.toString(zae.getSize()));
- try (InputStream inputStream = getMaybeGzipInputStream(TikaInputStream.get(zais))) {
+ try (TikaInputStream tis = TikaInputStream.get(getMaybeGzipInputStream(TikaInputStream.get(zais)))) {
if (ex.shouldParseEmbedded(metadata)) {
- ex.parseEmbedded(inputStream, xhtml, metadata, true);
+ ex.parseEmbedded(tis, xhtml, metadata, true);
}
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/warc/WARCParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/warc/WARCParser.java
index ad4894b54..9aa1e2f2f 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/warc/WARCParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/warc/WARCParser.java
@@ -146,7 +146,7 @@ public class WARCParser implements Parser {
if (embeddedDocumentExtractor.shouldParseEmbedded(metadata)) {
//TODO check Content-Encoding on the warcResponse.http.headers and wrap the stream.
//May need to sniff first few bytes to confirm accuracy, e.g. gzip compression ?
- try (InputStream tis = TikaInputStream.get(payload.body().stream())) {
+ try (TikaInputStream tis = TikaInputStream.get(payload.body().stream())) {
embeddedDocumentExtractor.parseEmbedded(tis, xhtml, metadata, true);
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
index 4e7f0dad7..094db7cc9 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/main/java/org/apache/tika/parser/xml/FictionBookParser.java
@@ -17,12 +17,10 @@
package org.apache.tika.parser.xml;
import java.io.IOException;
-import java.io.InputStream;
import java.util.Collections;
import java.util.Set;
import org.apache.commons.codec.binary.Base64;
-import org.apache.commons.io.input.UnsynchronizedByteArrayInputStream;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -30,6 +28,7 @@ import org.xml.sax.helpers.DefaultHandler;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedDocumentUtil;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
@@ -86,10 +85,9 @@ public class FictionBookParser extends XMLParser {
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
if (binaryMode) {
- try (InputStream stream =
- UnsynchronizedByteArrayInputStream.builder().setByteArray(Base64.decodeBase64(binaryData.toString())).get()) {
+ try (TikaInputStream tis = TikaInputStream.get(Base64.decodeBase64(binaryData.toString()))) {
partExtractor.parseEmbedded(
- stream, handler, metadata, true);
+ tis, handler, metadata, true);
} catch (IOException e) {
throw new SAXException("IOException in parseEmbedded", e);
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
index 9f9f71357..de112e5ac 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
@@ -29,6 +29,7 @@ import org.junit.jupiter.api.Test;
import org.xml.sax.ContentHandler;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
@@ -134,7 +135,7 @@ public class ZipParserTest extends AbstractPkgTest {
return false;
}
- public void parseEmbedded(InputStream inputStream, ContentHandler contentHandler,
+ public void parseEmbedded(TikaInputStream inputStream, ContentHandler contentHandler,
Metadata metadata, boolean outputHtml) {
throw new UnsupportedOperationException("should never be called");
}
diff --git a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/UnpackerResource.java b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/UnpackerResource.java
index 7fb362300..a2e3064d6 100644
--- a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/UnpackerResource.java
+++ b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/UnpackerResource.java
@@ -58,6 +58,7 @@ import org.apache.tika.extractor.DefaultEmbeddedStreamTranslator;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.EmbeddedStreamTranslator;
import org.apache.tika.io.BoundedInputStream;
+import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MimeTypeException;
@@ -186,12 +187,13 @@ public class UnpackerResource {
return true;
}
- public void parseEmbedded(InputStream inputStream, ContentHandler contentHandler, Metadata metadata, boolean b) throws SAXException, IOException {
+ @Override
+ public void parseEmbedded(TikaInputStream tis, ContentHandler contentHandler, Metadata metadata, boolean b) throws SAXException, IOException {
UnsynchronizedByteArrayOutputStream bos = UnsynchronizedByteArrayOutputStream
.builder()
.get();
- BoundedInputStream bis = new BoundedInputStream(unpackMaxBytes, inputStream);
+ BoundedInputStream bis = new BoundedInputStream(unpackMaxBytes, tis);
IOUtils.copy(bis, bos);
if (bis.hasHitBound()) {
throw new IOException(new TikaMemoryLimitException(
@@ -222,7 +224,7 @@ public class UnpackerResource {
LOG.warn("Unexpected MimeTypeException", e);
}
}
- try (InputStream is = UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get()) {
+ try (TikaInputStream is = TikaInputStream.get(data)) {
if (embeddedStreamTranslator.shouldTranslate(is, metadata)) {
InputStream translated = embeddedStreamTranslator.translate(UnsynchronizedByteArrayInputStream.builder().setByteArray(data).get(), metadata);
UnsynchronizedByteArrayOutputStream bos2 = UnsynchronizedByteArrayOutputStream