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 2021/01/27 14:20:55 UTC
[tika] branch main updated (91ef469 -> e31267f)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git.
from 91ef469 TIKA-3226 -- clean up pom.xml
new 3fbe435 fix typo in steamfactory
new e31267f TIKA-3281 -- fix up recursive parserwrapper -- remove deprecated bits and centralize metadata properties in TikaCoreProperties
The 2 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.
Summary of changes:
pom.xml | 4 +-
.../tika/cli/TikaCLIBatchIntegrationTest.java | 8 +-
.../tika/extractor/TestEmbeddedDocumentUtil.java | 3 +-
.../tika/batch/fs/StreamOutRPWFSConsumer.java | 8 +-
.../RecursiveParserWrapperFSConsumerTest.java | 10 +-
.../main/java/org/apache/tika/fork/ForkParser.java | 3 +-
.../fork/RecursiveMetadataContentHandlerProxy.java | 4 +-
.../java/org/apache/tika/io/TikaInputStream.java | 8 +-
.../apache/tika/metadata/TikaCoreProperties.java | 36 ++++-
.../apache/tika/parser/RecursiveParserWrapper.java | 177 +++------------------
.../parser/multiple/AbstractMultipleParser.java | 2 +-
.../sax/AbstractRecursiveParserWrapperHandler.java | 24 +--
.../tika/sax/RecursiveParserWrapperHandler.java | 7 +-
.../java/org/apache/tika/utils/ParserUtils.java | 5 +-
.../org/apache/tika/MultiThreadedTikaTest.java | 6 +-
.../java/org/apache/tika/fork/ForkParserTest.java | 39 +++--
.../tika/parser/multiple/MultipleParserTest.java | 2 +-
.../org/apache/tika/eval/app/AbstractProfiler.java | 19 ++-
.../org/apache/tika/eval/app/ExtractComparer.java | 9 +-
.../org/apache/tika/eval/app/ExtractProfiler.java | 4 +-
.../org/apache/tika/eval/app/io/ExtractReader.java | 12 +-
.../apache/tika/eval/app/SimpleComparerTest.java | 14 +-
.../apache/tika/eval/app/io/ExtractReaderTest.java | 26 +--
.../test-dirs/extractsA/file6_accessEx.pdf.json | 2 +-
.../test-dirs/extractsB/file6_accessEx.pdf.json | 2 +-
.../eval/core/metadata/TikaEvalMetadataFilter.java | 3 +-
.../core/metadata/TikaEvalMetadataFilterTest.java | 4 +-
.../apache/tika/parser/apple/PListParserTest.java | 4 +-
.../apache/tika/parser/html/HtmlParserTest.java | 14 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 24 ++-
.../apache/tika/parser/mbox/MboxParserTest.java | 5 +-
.../tika/parser/microsoft/EMFParserTest.java | 5 +-
.../tika/parser/microsoft/ExcelParserTest.java | 6 +-
.../tika/parser/microsoft/JackcessParserTest.java | 4 +-
.../tika/parser/microsoft/OutlookParserTest.java | 8 +-
.../microsoft/POIContainerExtractionTest.java | 2 +-
.../parser/microsoft/PowerPointParserTest.java | 14 +-
.../tika/parser/microsoft/WMFParserTest.java | 4 +-
.../tika/parser/microsoft/WordParserTest.java | 4 +-
.../ooxml/OOXMLContainerExtractionTest.java | 3 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 28 ++--
.../parser/microsoft/ooxml/SXSLFExtractorTest.java | 12 +-
.../parser/microsoft/ooxml/SXWPFExtractorTest.java | 18 +--
.../parser/microsoft/ooxml/TruncatedOOXMLTest.java | 8 +-
.../parser/microsoft/ooxml/xps/XPSParserTest.java | 4 +-
.../ooxml/xwpf/ml2006/Word2006MLParserTest.java | 2 +-
.../apache/tika/parser/epub/EpubParserTest.java | 7 +-
.../parser/pdf/PDFMarkedContent2XHTMLTest.java | 4 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 3 +-
.../tika/parser/RecursiveParserWrapperTest.java | 75 ++-------
.../parser/apple/AppleSingleFileParserTest.java | 2 +-
.../apache/tika/parser/apple/PListParserTest.java | 4 +-
.../apache/tika/parser/crypto/TSDParserTest.java | 6 +-
.../apache/tika/parser/html/HtmlParserTest.java | 5 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 7 +-
.../tika/parser/microsoft/EMFParserTest.java | 8 +-
.../tika/parser/microsoft/ExcelParserTest.java | 4 +-
.../microsoft/POIContainerExtractionTest.java | 1 -
.../parser/microsoft/PowerPointParserTest.java | 5 +-
.../tika/parser/microsoft/XML2003ParserTest.java | 3 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 12 +-
.../tika/parser/microsoft/rtf/RTFParserTest.java | 3 +-
.../apache/tika/parser/mock/MockParserTest.java | 1 -
.../tika/parser/ocr/TesseractOCRParserTest.java | 9 +-
.../org/apache/tika/parser/odf/ODFParserTest.java | 27 ++--
.../org/apache/tika/parser/pdf/PDFParserTest.java | 14 +-
.../apache/tika/parser/pkg/CompressParserTest.java | 3 -
.../tika/parser/pkg/CompressorParserTest.java | 4 +-
.../org/apache/tika/parser/pkg/TarParserTest.java | 3 -
.../org/apache/tika/parser/pkg/ZipParserTest.java | 3 +-
.../tika/parser/sqlite3/SQLite3ParserTest.java | 11 +-
.../org/apache/tika/emitter/solr/TestBasic.java | 7 +-
.../metadata/serialization/JsonMetadataList.java | 6 +-
.../serialization/JsonMetadataListTest.java | 4 +-
.../apache/tika/server/classic/FetcherTest.java | 4 +-
.../classic/RecursiveMetadataResourceTest.java | 34 ++--
.../tika/server/core/resource/EmitterResource.java | 8 +-
.../apache/tika/server/core/TikaEmitterTest.java | 12 +-
78 files changed, 332 insertions(+), 577 deletions(-)
[tika] 01/02: fix typo in steamfactory
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 3fbe435b865c92c428c905a00c8cf564364759cd
Author: tballison <ta...@apache.org>
AuthorDate: Wed Jan 27 09:16:36 2021 -0500
fix typo in steamfactory
---
tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
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 deb11e1..3f1c1e0 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
@@ -307,7 +307,7 @@ public class TikaInputStream extends TaggedInputStream {
*/
public static TikaInputStream get(InputStreamFactory factory, TemporaryResources tmp) throws IOException {
TikaInputStream stream = get(factory.getInputStream(), tmp);
- stream.steamFactory = factory;
+ stream.streamFactory = factory;
return stream;
}
@@ -481,7 +481,7 @@ public class TikaInputStream extends TaggedInputStream {
* The Factory that can create fresh {@link InputStream}s for
* the resource this reads for, eg when needing to re-read.
*/
- private InputStreamFactory steamFactory;
+ private InputStreamFactory streamFactory;
/**
* The path to the file that contains the contents of this stream.
@@ -633,7 +633,7 @@ public class TikaInputStream extends TaggedInputStream {
}
public boolean hasInputStreamFactory() {
- return steamFactory != null;
+ return streamFactory != null;
}
/**
@@ -641,7 +641,7 @@ public class TikaInputStream extends TaggedInputStream {
* return that, otherwise <code>null</code>.
*/
public InputStreamFactory getInputStreamFactory() {
- return steamFactory;
+ return streamFactory;
}
public boolean hasFile() {
[tika] 02/02: TIKA-3281 -- fix up recursive parserwrapper -- remove
deprecated bits and centralize metadata properties in TikaCoreProperties
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
commit e31267fcafccf4dee085f48f44babbb8a476ab81
Author: tballison <ta...@apache.org>
AuthorDate: Wed Jan 27 09:18:22 2021 -0500
TIKA-3281 -- fix up recursive parserwrapper -- remove deprecated bits and centralize metadata properties in TikaCoreProperties
---
pom.xml | 4 +-
.../tika/cli/TikaCLIBatchIntegrationTest.java | 8 +-
.../tika/extractor/TestEmbeddedDocumentUtil.java | 3 +-
.../tika/batch/fs/StreamOutRPWFSConsumer.java | 8 +-
.../RecursiveParserWrapperFSConsumerTest.java | 10 +-
.../main/java/org/apache/tika/fork/ForkParser.java | 3 +-
.../fork/RecursiveMetadataContentHandlerProxy.java | 4 +-
.../apache/tika/metadata/TikaCoreProperties.java | 36 ++++-
.../apache/tika/parser/RecursiveParserWrapper.java | 177 +++------------------
.../parser/multiple/AbstractMultipleParser.java | 2 +-
.../sax/AbstractRecursiveParserWrapperHandler.java | 24 +--
.../tika/sax/RecursiveParserWrapperHandler.java | 7 +-
.../java/org/apache/tika/utils/ParserUtils.java | 5 +-
.../org/apache/tika/MultiThreadedTikaTest.java | 6 +-
.../java/org/apache/tika/fork/ForkParserTest.java | 39 +++--
.../tika/parser/multiple/MultipleParserTest.java | 2 +-
.../org/apache/tika/eval/app/AbstractProfiler.java | 19 ++-
.../org/apache/tika/eval/app/ExtractComparer.java | 9 +-
.../org/apache/tika/eval/app/ExtractProfiler.java | 4 +-
.../org/apache/tika/eval/app/io/ExtractReader.java | 12 +-
.../apache/tika/eval/app/SimpleComparerTest.java | 14 +-
.../apache/tika/eval/app/io/ExtractReaderTest.java | 26 +--
.../test-dirs/extractsA/file6_accessEx.pdf.json | 2 +-
.../test-dirs/extractsB/file6_accessEx.pdf.json | 2 +-
.../eval/core/metadata/TikaEvalMetadataFilter.java | 3 +-
.../core/metadata/TikaEvalMetadataFilterTest.java | 4 +-
.../apache/tika/parser/apple/PListParserTest.java | 4 +-
.../apache/tika/parser/html/HtmlParserTest.java | 14 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 24 ++-
.../apache/tika/parser/mbox/MboxParserTest.java | 5 +-
.../tika/parser/microsoft/EMFParserTest.java | 5 +-
.../tika/parser/microsoft/ExcelParserTest.java | 6 +-
.../tika/parser/microsoft/JackcessParserTest.java | 4 +-
.../tika/parser/microsoft/OutlookParserTest.java | 8 +-
.../microsoft/POIContainerExtractionTest.java | 2 +-
.../parser/microsoft/PowerPointParserTest.java | 14 +-
.../tika/parser/microsoft/WMFParserTest.java | 4 +-
.../tika/parser/microsoft/WordParserTest.java | 4 +-
.../ooxml/OOXMLContainerExtractionTest.java | 3 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 28 ++--
.../parser/microsoft/ooxml/SXSLFExtractorTest.java | 12 +-
.../parser/microsoft/ooxml/SXWPFExtractorTest.java | 18 +--
.../parser/microsoft/ooxml/TruncatedOOXMLTest.java | 8 +-
.../parser/microsoft/ooxml/xps/XPSParserTest.java | 4 +-
.../ooxml/xwpf/ml2006/Word2006MLParserTest.java | 2 +-
.../apache/tika/parser/epub/EpubParserTest.java | 7 +-
.../parser/pdf/PDFMarkedContent2XHTMLTest.java | 4 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 3 +-
.../tika/parser/RecursiveParserWrapperTest.java | 75 ++-------
.../parser/apple/AppleSingleFileParserTest.java | 2 +-
.../apache/tika/parser/apple/PListParserTest.java | 4 +-
.../apache/tika/parser/crypto/TSDParserTest.java | 6 +-
.../apache/tika/parser/html/HtmlParserTest.java | 5 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 7 +-
.../tika/parser/microsoft/EMFParserTest.java | 8 +-
.../tika/parser/microsoft/ExcelParserTest.java | 4 +-
.../microsoft/POIContainerExtractionTest.java | 1 -
.../parser/microsoft/PowerPointParserTest.java | 5 +-
.../tika/parser/microsoft/XML2003ParserTest.java | 3 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 12 +-
.../tika/parser/microsoft/rtf/RTFParserTest.java | 3 +-
.../apache/tika/parser/mock/MockParserTest.java | 1 -
.../tika/parser/ocr/TesseractOCRParserTest.java | 9 +-
.../org/apache/tika/parser/odf/ODFParserTest.java | 27 ++--
.../org/apache/tika/parser/pdf/PDFParserTest.java | 14 +-
.../apache/tika/parser/pkg/CompressParserTest.java | 3 -
.../tika/parser/pkg/CompressorParserTest.java | 4 +-
.../org/apache/tika/parser/pkg/TarParserTest.java | 3 -
.../org/apache/tika/parser/pkg/ZipParserTest.java | 3 +-
.../tika/parser/sqlite3/SQLite3ParserTest.java | 11 +-
.../org/apache/tika/emitter/solr/TestBasic.java | 7 +-
.../metadata/serialization/JsonMetadataList.java | 6 +-
.../serialization/JsonMetadataListTest.java | 4 +-
.../apache/tika/server/classic/FetcherTest.java | 4 +-
.../classic/RecursiveMetadataResourceTest.java | 34 ++--
.../tika/server/core/resource/EmitterResource.java | 8 +-
.../apache/tika/server/core/TikaEmitterTest.java | 12 +-
77 files changed, 328 insertions(+), 573 deletions(-)
diff --git a/pom.xml b/pom.xml
index e69028a..17bc12d 100644
--- a/pom.xml
+++ b/pom.xml
@@ -1,4 +1,4 @@
- <?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8"?>
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -46,11 +46,11 @@
<module>tika-langdetect</module>
<module>tika-app</module>
<module>tika-server</module>
+ <module>tika-eval</module>
<module>tika-fuzzing</module>
<module>tika-translate</module>
<module>tika-example</module>
<module>tika-java7</module>
- <module>tika-eval</module>
</modules>
<profiles>
diff --git a/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchIntegrationTest.java b/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchIntegrationTest.java
index a57fa56..c208138 100644
--- a/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchIntegrationTest.java
+++ b/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchIntegrationTest.java
@@ -34,8 +34,8 @@ import java.util.List;
import org.apache.commons.io.FileUtils;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.serialization.JsonMetadataList;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
@@ -109,7 +109,7 @@ public class TikaCLIBatchIntegrationTest {
try (Reader reader = Files.newBufferedReader(jsonFile, UTF_8)) {
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- assertTrue(metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).contains("human events"));
+ assertTrue(metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).contains("human events"));
}
}
@@ -128,9 +128,9 @@ public class TikaCLIBatchIntegrationTest {
try (Reader reader = Files.newBufferedReader(jsonFile, UTF_8)) {
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- assertTrue(metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).contains("human events"));
+ assertTrue(metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).contains("human events"));
//test that the last written object has been bumped to the first by JsonMetadataList.fromJson()
- assertNull( metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertNull( metadataList.get(0).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
}
diff --git a/tika-app/src/test/java/org/apache/tika/extractor/TestEmbeddedDocumentUtil.java b/tika-app/src/test/java/org/apache/tika/extractor/TestEmbeddedDocumentUtil.java
index c78204c..98905ac 100644
--- a/tika-app/src/test/java/org/apache/tika/extractor/TestEmbeddedDocumentUtil.java
+++ b/tika-app/src/test/java/org/apache/tika/extractor/TestEmbeddedDocumentUtil.java
@@ -46,8 +46,7 @@ public class TestEmbeddedDocumentUtil {
@Test
public void testDoublyDecorated() {
Parser d = new DigestingAutoDetectParserFactory().getParser(TikaConfig.getDefaultConfig());
- RecursiveParserWrapper wrapper = new RecursiveParserWrapper(d,
- new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1));
+ RecursiveParserWrapper wrapper = new RecursiveParserWrapper(d,true);
ParseContext parseContext = new ParseContext();
parseContext.set(Parser.class, wrapper);
Parser txtParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(org.apache.tika.parser.csv.TextAndCSVParser.class, parseContext);
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/fs/StreamOutRPWFSConsumer.java b/tika-batch/src/main/java/org/apache/tika/batch/fs/StreamOutRPWFSConsumer.java
index dd39a6c..87513d2 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/fs/StreamOutRPWFSConsumer.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/fs/StreamOutRPWFSConsumer.java
@@ -20,11 +20,8 @@ package org.apache.tika.batch.fs;
import org.apache.commons.io.IOUtils;
-import org.apache.tika.Tika;
import org.apache.tika.batch.FileResource;
import org.apache.tika.batch.OutputStreamFactory;
-import org.apache.tika.batch.ParserFactory;
-import org.apache.tika.config.TikaConfig;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
@@ -32,11 +29,8 @@ import org.apache.tika.metadata.filter.MetadataFilter;
import org.apache.tika.metadata.serialization.JsonStreamingSerializer;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.ContentHandlerFactory;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
-import org.apache.tika.utils.ExceptionUtils;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -154,7 +148,7 @@ public class StreamOutRPWFSConsumer extends AbstractFSConsumer {
@Override
public void endEmbeddedDocument(ContentHandler contentHandler, Metadata metadata) throws SAXException {
- metadata.add(RecursiveParserWrapperHandler.TIKA_CONTENT, contentHandler.toString());
+ metadata.add(TikaCoreProperties.TIKA_CONTENT, contentHandler.toString());
try {
metadataFilter.filter(metadata);
} catch (TikaException e) {
diff --git a/tika-batch/src/test/java/org/apache/tika/batch/RecursiveParserWrapperFSConsumerTest.java b/tika-batch/src/test/java/org/apache/tika/batch/RecursiveParserWrapperFSConsumerTest.java
index aa92a78..73cf353 100644
--- a/tika-batch/src/test/java/org/apache/tika/batch/RecursiveParserWrapperFSConsumerTest.java
+++ b/tika-batch/src/test/java/org/apache/tika/batch/RecursiveParserWrapperFSConsumerTest.java
@@ -38,9 +38,7 @@ import org.apache.tika.metadata.filter.NoOpFilter;
import org.apache.tika.metadata.serialization.JsonMetadataList;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.RecursiveParserWrapper;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.Test;
public class RecursiveParserWrapperFSConsumerTest extends TikaTest {
@@ -85,12 +83,12 @@ public class RecursiveParserWrapperFSConsumerTest extends TikaTest {
assertEquals(4, results.size());
assertContains("another null pointer",
- results.get(2).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_EXCEPTION));
+ results.get(2).get(TikaCoreProperties.EMBEDDED_EXCEPTION));
assertEquals("Nikolai Lobachevsky", results.get(0).get("author"));
for (int i = 1; i < 4; i++) {
assertEquals("embeddedAuthor"+i, results.get(i).get("author"));
- assertContains("some_embedded_content"+i, results.get(i).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("some_embedded_content"+i, results.get(i).get(TikaCoreProperties.TIKA_CONTENT));
}
}
@@ -132,10 +130,10 @@ public class RecursiveParserWrapperFSConsumerTest extends TikaTest {
List<Metadata> results = JsonMetadataList.fromJson(new InputStreamReader(new ByteArrayInputStream(bytes), UTF_8));
assertEquals(2, results.size());
assertContains("another null pointer",
- results.get(0).get(RecursiveParserWrapperHandler.CONTAINER_EXCEPTION));
+ results.get(0).get(TikaCoreProperties.CONTAINER_EXCEPTION));
assertEquals("Nikolai Lobachevsky", results.get(0).get("author"));
assertEquals("embeddedAuthor", results.get(1).get("author"));
- assertContains("some_embedded_content", results.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("some_embedded_content", results.get(1).get(TikaCoreProperties.TIKA_CONTENT));
}
diff --git a/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java b/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
index 6092951..e61e7fa 100644
--- a/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
+++ b/tika-core/src/main/java/org/apache/tika/fork/ForkParser.java
@@ -31,6 +31,7 @@ import java.util.Set;
import org.apache.tika.config.Field;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AbstractParser;
import org.apache.tika.parser.AutoDetectParser;
@@ -236,7 +237,7 @@ public class ForkParser extends AbstractParser implements Closeable
* If the handler does not implement {@link java.io.Serializable} or if there is a
* {@link java.io.NotSerializableException} thrown during serialization, the server will
* call {@link ContentHandler#toString()} on the ContentHandler and set that value with the
- * {@link org.apache.tika.sax.RecursiveParserWrapperHandler#TIKA_CONTENT} key and then
+ * {@link TikaCoreProperties#TIKA_CONTENT} key and then
* serialize and proxy that data back.
* </p>
*
diff --git a/tika-core/src/main/java/org/apache/tika/fork/RecursiveMetadataContentHandlerProxy.java b/tika-core/src/main/java/org/apache/tika/fork/RecursiveMetadataContentHandlerProxy.java
index 7e89bc1..21fdecb 100644
--- a/tika-core/src/main/java/org/apache/tika/fork/RecursiveMetadataContentHandlerProxy.java
+++ b/tika-core/src/main/java/org/apache/tika/fork/RecursiveMetadataContentHandlerProxy.java
@@ -17,7 +17,7 @@
package org.apache.tika.fork;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.sax.ContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.xml.sax.ContentHandler;
@@ -102,7 +102,7 @@ class RecursiveMetadataContentHandlerProxy extends RecursiveParserWrapperHandler
//if contenthandler is not allegedly or actually Serializable
//fall back to adding contentHandler.toString() to the metadata object
//and send that.
- metadata.set(RecursiveParserWrapperHandler.TIKA_CONTENT, contentHandler.toString());
+ metadata.set(TikaCoreProperties.TIKA_CONTENT, contentHandler.toString());
output.writeByte(METADATA_ONLY);
send(metadata);
output.writeByte(COMPLETE);
diff --git a/tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java b/tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java
index a8e804a..37a36da 100644
--- a/tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java
+++ b/tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java
@@ -16,6 +16,11 @@
*/
package org.apache.tika.metadata;
+import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.sax.ContentHandlerFactory;
+import org.apache.tika.sax.RecursiveParserWrapperHandler;
+import org.apache.tika.utils.ParserUtils;
+
/**
* Contains a core set of basic Tika metadata properties, which all parsers
* will attempt to supply (where the file format permits). These are all
@@ -73,14 +78,40 @@ public interface TikaCoreProperties {
* between metadata that was contained within the document and
* metadata about the parsing process.
*/
- public static String TIKA_META_PREFIX = "X-TIKA"+NAMESPACE_PREFIX_DELIMITER;
+ String TIKA_META_PREFIX = "X-TIKA"+NAMESPACE_PREFIX_DELIMITER;
+
+ Property EMBEDDED_DEPTH =
+ Property.internalInteger(TIKA_META_PREFIX +"embedded_depth");
+ Property EMBEDDED_RESOURCE_PATH =
+ Property.internalText(TIKA_META_PREFIX +"embedded_resource_path");
+ Property PARSE_TIME_MILLIS = Property.internalText(TIKA_META_PREFIX + "parse_time_millis");
+ /**
+ * Simple class name of the content handler
+ */
+ Property TIKA_CONTENT_HANDLER = Property.internalText(TIKA_META_PREFIX +"content_handler");
+ Property TIKA_CONTENT = Property.internalText(TIKA_META_PREFIX +"content");
/**
* Use this to store parse exception information in the Metadata object.
*/
- public static String TIKA_META_EXCEPTION_PREFIX = TIKA_META_PREFIX+"EXCEPTION"+
+ String TIKA_META_EXCEPTION_PREFIX = TIKA_META_PREFIX+"EXCEPTION"+
NAMESPACE_PREFIX_DELIMITER;
+ //exception in main file
+ Property CONTAINER_EXCEPTION = Property.internalText(
+ TIKA_META_EXCEPTION_PREFIX +"container_exception");
+
+ //exception in an embedded file
+ Property EMBEDDED_EXCEPTION =
+ Property.internalText(
+ TIKA_META_EXCEPTION_PREFIX + "embedded_exception");
+
+ Property WRITE_LIMIT_REACHED =
+ Property.internalBoolean(TIKA_META_EXCEPTION_PREFIX + "write_limit_reached");
+
+ Property EMBEDDED_RESOURCE_LIMIT_REACHED =
+ Property.internalBoolean(TIKA_META_EXCEPTION_PREFIX + "embedded_resource_limit_reached");
+
/**
* Use this to store exceptions caught during a parse that are
* non-fatal, e.g. if a parser is in lenient mode and more
@@ -111,6 +142,7 @@ public interface TikaCoreProperties {
String EMBEDDED_RESOURCE_TYPE_KEY = "embeddedResourceType";
+
/**
* Some file formats can store information about their original
* file name/location or about their attachment's original file name/location
diff --git a/tika-core/src/main/java/org/apache/tika/parser/RecursiveParserWrapper.java b/tika-core/src/main/java/org/apache/tika/parser/RecursiveParserWrapper.java
index 7edd0d7..9034ed0 100644
--- a/tika-core/src/main/java/org/apache/tika/parser/RecursiveParserWrapper.java
+++ b/tika-core/src/main/java/org/apache/tika/parser/RecursiveParserWrapper.java
@@ -24,7 +24,6 @@ import org.apache.tika.io.FilenameUtils;
import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.metadata.Property;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
@@ -51,7 +50,7 @@ import java.util.Set;
* Metadata objects, one for each embedded resource. The first item
* in the list will contain the Metadata for the outer container file.
* <p>
- * Content can also be extracted and stored in the {@link #TIKA_CONTENT} field
+ * Content can also be extracted and stored in the {@link TikaCoreProperties#TIKA_CONTENT} field
* of a Metadata object. Select the type of content to be stored
* at initialization.
* <p>
@@ -68,10 +67,6 @@ import java.util.Set;
* Note that this wrapper holds all data in memory and is not appropriate
* for files with content too large to be held in memory.
* <p>
- * Note, too, that this wrapper is not thread safe because it stores state.
- * The client must initialize a new wrapper for each thread, and the client
- * is responsible for calling {@link #reset()} after each parse.
- * <p>
* The unit tests for this class are in the tika-parsers module.
* </p>
*/
@@ -82,63 +77,10 @@ public class RecursiveParserWrapper extends ParserDecorator {
*/
private static final long serialVersionUID = 9086536568120690938L;
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#TIKA_CONTENT}
- */
- @Deprecated
- public final static Property TIKA_CONTENT = AbstractRecursiveParserWrapperHandler.TIKA_CONTENT;
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#PARSE_TIME_MILLIS}
- */
- @Deprecated
- public final static Property PARSE_TIME_MILLIS = AbstractRecursiveParserWrapperHandler.PARSE_TIME_MILLIS;
-
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#EMBEDDED_EXCEPTION}
- */
- @Deprecated
- public final static Property WRITE_LIMIT_REACHED =
- AbstractRecursiveParserWrapperHandler.WRITE_LIMIT_REACHED;
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#EMBEDDED_RESOURCE_LIMIT_REACHED}
- */
- @Deprecated
- public final static Property EMBEDDED_RESOURCE_LIMIT_REACHED =
- AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_LIMIT_REACHED;
-
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#EMBEDDED_EXCEPTION}
- */
- @Deprecated
- public final static Property EMBEDDED_EXCEPTION = AbstractRecursiveParserWrapperHandler.EMBEDDED_EXCEPTION;
-
- /**
- * @deprecated use {@link org.apache.tika.sax.RecursiveParserWrapperHandler#EMBEDDED_RESOURCE_PATH}
- */
- @Deprecated
- public final static Property EMBEDDED_RESOURCE_PATH = AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH;
-
- /**
- * @deprecated this should be passed in via the {@link RecursiveParserWrapperHandler}
- */
- @Deprecated
- private ContentHandlerFactory contentHandlerFactory = null;
private final boolean catchEmbeddedExceptions;
/**
- * set this on the RecursiveParserWrapperHandler instead
- * @deprecated this is here only for legacy behavior; it will be removed in 2.0 and/or 1.20
- */
- @Deprecated
- private int maxEmbeddedResources = -1;
- /**
- * @deprecated this is here only for legacy behavior; it will be removed in 2.0 and/or 1.20
- */
- @Deprecated
- private ParserState lastParseState = null;
-
- /**
* Initialize the wrapper with {@link #catchEmbeddedExceptions} set
* to <code>true</code> as default.
*
@@ -160,65 +102,35 @@ public class RecursiveParserWrapper extends ParserDecorator {
super(wrappedParser);
this.catchEmbeddedExceptions = catchEmbeddedExceptions;
}
- /**
- * Initialize the wrapper with {@link #catchEmbeddedExceptions} set
- * to <code>true</code> as default.
- *
- * @param wrappedParser parser to use for the container documents and the embedded documents
- * @param contentHandlerFactory factory to use to generate a new content handler for
- * the container document and each embedded document
- * @deprecated use {@link RecursiveParserWrapper#RecursiveParserWrapper(Parser)}
- */
- @Deprecated
- public RecursiveParserWrapper(Parser wrappedParser, ContentHandlerFactory contentHandlerFactory) {
- this(wrappedParser, contentHandlerFactory, true);
- }
- /**
- * Initialize the wrapper.
- *
- * @param wrappedParser parser to use for the container documents and the embedded documents
- * @param contentHandlerFactory factory to use to generate a new content handler for
- * the container document and each embedded document
- * @param catchEmbeddedExceptions whether or not to catch the embedded exceptions.
- * If set to <code>true</code>, the stack traces will be stored in
- * the metadata object with key: {@link #EMBEDDED_EXCEPTION}.
- * @deprecated use {@link RecursiveParserWrapper#RecursiveParserWrapper(Parser, boolean)}
- */
- @Deprecated
- public RecursiveParserWrapper(Parser wrappedParser,
- ContentHandlerFactory contentHandlerFactory, boolean catchEmbeddedExceptions) {
- super(wrappedParser);
- this.contentHandlerFactory = contentHandlerFactory;
- this.catchEmbeddedExceptions = catchEmbeddedExceptions;
- }
@Override
public Set<MediaType> getSupportedTypes(ParseContext context) {
return getWrappedParser().getSupportedTypes(context);
}
+
/**
- * Acts like a regular parser except it ignores the ContentHandler
- * and it automatically sets/overwrites the embedded Parser in the
- * ParseContext object.
- * <p>
- * To retrieve the results of the parse, use {@link #getMetadata()}.
- * <p>
- * Make sure to call {@link #reset()} after each parse.
+ *
+ * @param stream
+ * @param recursiveParserWrapperHandler -- handler must implement {@link RecursiveParserWrapperHandler}
+ * @param metadata
+ * @param context
+ * @throws IOException
+ * @throws SAXException
+ * @throws TikaException
+ * @throws IllegalStateException if the handler is not a {@link RecursiveParserWrapperHandler}
*/
@Override
public void parse(InputStream stream, ContentHandler recursiveParserWrapperHandler,
Metadata metadata, ParseContext context) throws IOException,
SAXException, TikaException {
//this tracks the state of the parent parser, per call to #parse
- //in future versions, we can remove lastParseState, and this will be thread-safe
ParserState parserState;
if (recursiveParserWrapperHandler instanceof AbstractRecursiveParserWrapperHandler) {
parserState = new ParserState((AbstractRecursiveParserWrapperHandler)recursiveParserWrapperHandler);
} else {
- parserState = new ParserState(new RecursiveParserWrapperHandler(contentHandlerFactory, maxEmbeddedResources));
- lastParseState = parserState;
+ throw new IllegalStateException("ContentHandler must implement RecursiveParserWrapperHandler");
}
EmbeddedParserDecorator decorator = new EmbeddedParserDecorator(getWrappedParser(), "/", parserState);
context.set(Parser.class, decorator);
@@ -237,76 +149,23 @@ public class RecursiveParserWrapper extends ParserDecorator {
if (wlr == false) {
throw e;
}
- metadata.set(RecursiveParserWrapperHandler.WRITE_LIMIT_REACHED, "true");
+ metadata.set(TikaCoreProperties.WRITE_LIMIT_REACHED, "true");
} catch (Throwable e) {
//try our best to record the problem in the metadata object
//then rethrow
String stackTrace = ExceptionUtils.getFilteredStackTrace(e);
- metadata.add(RecursiveParserWrapperHandler.CONTAINER_EXCEPTION, stackTrace);
+ metadata.add(TikaCoreProperties.CONTAINER_EXCEPTION, stackTrace);
throw e;
} finally {
tmp.dispose();
long elapsedMillis = System.currentTimeMillis() - started;
- metadata.set(RecursiveParserWrapperHandler.PARSE_TIME_MILLIS, Long.toString(elapsedMillis));
+ metadata.set(TikaCoreProperties.PARSE_TIME_MILLIS, Long.toString(elapsedMillis));
parserState.recursiveParserWrapperHandler.endDocument(localHandler, metadata);
parserState.recursiveParserWrapperHandler.endDocument();
}
}
/**
- *
- * The first element in the returned list represents the
- * data from the outer container file. There is no guarantee
- * about the ordering of the list after that.
- *
- * @deprecated use a {@link RecursiveParserWrapperHandler} instead
- *
- * @return list of Metadata objects that were gathered during the parse
- * @throws IllegalStateException if you've used a {@link RecursiveParserWrapperHandler} in your last
- * call to {@link #parse(InputStream, ContentHandler, Metadata, ParseContext)}
- */
- @Deprecated
- public List<Metadata> getMetadata() {
- if (lastParseState != null) {
- return ((RecursiveParserWrapperHandler) lastParseState.recursiveParserWrapperHandler).getMetadataList();
- } else {
- throw new IllegalStateException("This is deprecated; please use a RecursiveParserWrapperHandler instead");
- }
- }
-
- /**
- * Set the maximum number of embedded resources to store.
- * If the max is hit during parsing, the {@link #EMBEDDED_RESOURCE_LIMIT_REACHED}
- * property will be added to the container document's Metadata.
- *
- * <p>
- * If this value is < 0 (the default), the wrapper will store all Metadata.
- * @deprecated set this on a {@link RecursiveParserWrapperHandler}
- * @param max maximum number of embedded resources to store
- */
- @Deprecated
- public void setMaxEmbeddedResources(int max) {
- maxEmbeddedResources = max;
- }
-
-
- /**
- * This clears the last parser state (metadata list, unknown count, hit embeddedresource count)
- *
- * @deprecated use a {@link org.apache.tika.sax.RecursiveParserWrapperHandler} instead
- * @throws IllegalStateException if you used a {@link RecursiveParserWrapper} in your call
- * to {@link #parse(InputStream, ContentHandler, Metadata, ParseContext)}
- */
- @Deprecated
- public void reset() {
- if (lastParseState != null) {
- lastParseState = new ParserState(new RecursiveParserWrapperHandler(contentHandlerFactory, maxEmbeddedResources));
- } else {
- throw new IllegalStateException("This is deprecated; please use a RecursiveParserWrapperHandler instead");
- }
- }
-
- /**
* Copied/modified from WriteOutContentHandler. Couldn't make that
* static, and we need to have something that will work
* with exceptions thrown from both BodyContentHandler and WriteOutContentHandler
@@ -367,7 +226,7 @@ public class RecursiveParserWrapper extends ParserDecorator {
String objectName = getResourceName(metadata, parserState);
String objectLocation = this.location + objectName;
- metadata.add(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, objectLocation);
+ metadata.add(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, objectLocation);
//get a fresh handler
@@ -388,7 +247,7 @@ public class RecursiveParserWrapper extends ParserDecorator {
} catch (SAXException e) {
boolean wlr = isWriteLimitReached(e);
if (wlr == true) {
- metadata.add(WRITE_LIMIT_REACHED, "true");
+ metadata.add(TikaCoreProperties.WRITE_LIMIT_REACHED, "true");
} else {
if (catchEmbeddedExceptions) {
ParserUtils.recordParserFailure(this, e, metadata);
@@ -411,7 +270,7 @@ public class RecursiveParserWrapper extends ParserDecorator {
context.set(Parser.class, preContextParser);
secureContentHandler.updateContentHandler(preContextHandler);
long elapsedMillis = System.currentTimeMillis() - started;
- metadata.set(RecursiveParserWrapperHandler.PARSE_TIME_MILLIS, Long.toString(elapsedMillis));
+ metadata.set(TikaCoreProperties.PARSE_TIME_MILLIS, Long.toString(elapsedMillis));
parserState.recursiveParserWrapperHandler.endEmbeddedDocument(localHandler, metadata);
}
}
diff --git a/tika-core/src/main/java/org/apache/tika/parser/multiple/AbstractMultipleParser.java b/tika-core/src/main/java/org/apache/tika/parser/multiple/AbstractMultipleParser.java
index c05dc0f..7682f01 100644
--- a/tika-core/src/main/java/org/apache/tika/parser/multiple/AbstractMultipleParser.java
+++ b/tika-core/src/main/java/org/apache/tika/parser/multiple/AbstractMultipleParser.java
@@ -314,7 +314,7 @@ public abstract class AbstractMultipleParser extends AbstractParser {
// for tracking/errors, then always keep the latest one!
if (n.equals(TikaCoreProperties.TIKA_PARSED_BY.getName())) continue;
if (n.equals(ParserUtils.EMBEDDED_PARSER.getName())) continue;
- if (n.equals(ParserUtils.EMBEDDED_EXCEPTION.getName())) continue;
+ if (n.equals(TikaCoreProperties.EMBEDDED_EXCEPTION.getName())) continue;
// Merge as per policy
String[] newVals = newMetadata.getValues(n);
diff --git a/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java b/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
index 8515f09..248e96d 100644
--- a/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
+++ b/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
@@ -19,7 +19,6 @@ package org.apache.tika.sax;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Property;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.utils.ParserUtils;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
@@ -35,28 +34,9 @@ import java.nio.charset.Charset;
*/
public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandler implements Serializable {
- public final static Property TIKA_CONTENT = Property.internalText(TikaCoreProperties.TIKA_META_PREFIX+"content");
- /**
- * Simple class name of the content handler
- */
- public final static Property TIKA_CONTENT_HANDLER = Property.internalText(TikaCoreProperties.TIKA_META_PREFIX+"content_handler");
- public final static Property PARSE_TIME_MILLIS = Property.internalText(TikaCoreProperties.TIKA_META_PREFIX + "parse_time_millis");
- public final static Property WRITE_LIMIT_REACHED =
- Property.internalBoolean(TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX + "write_limit_reached");
public final static Property EMBEDDED_RESOURCE_LIMIT_REACHED =
Property.internalBoolean(TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX + "embedded_resource_limit_reached");
- //exception in embedded file
- public final static Property EMBEDDED_EXCEPTION = ParserUtils.EMBEDDED_EXCEPTION;
- //exception in main file
- public final static Property CONTAINER_EXCEPTION = Property.internalText(
- TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX+"runtime");
- public final static Property EMBEDDED_RESOURCE_PATH =
- Property.internalText(TikaCoreProperties.TIKA_META_PREFIX+"embedded_resource_path");
-
- public final static Property EMBEDDED_DEPTH =
- Property.internalInteger(TikaCoreProperties.TIKA_META_PREFIX+"embedded_depth");
-
private final ContentHandlerFactory contentHandlerFactory;
@@ -97,7 +77,7 @@ public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandl
if (embeddedDepth >= MAX_DEPTH) {
throw new SAXException("Max embedded depth reached: "+embeddedDepth);
}
- metadata.set(EMBEDDED_DEPTH, embeddedDepth);
+ metadata.set(TikaCoreProperties.EMBEDDED_DEPTH, embeddedDepth);
}
/**
* This is called after parsing each embedded document. Override this
@@ -125,7 +105,7 @@ public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandl
if (hasHitMaximumEmbeddedResources()) {
metadata.set(EMBEDDED_RESOURCE_LIMIT_REACHED, "true");
}
- metadata.set(EMBEDDED_DEPTH, 0);
+ metadata.set(TikaCoreProperties.EMBEDDED_DEPTH, 0);
}
/**
diff --git a/tika-core/src/main/java/org/apache/tika/sax/RecursiveParserWrapperHandler.java b/tika-core/src/main/java/org/apache/tika/sax/RecursiveParserWrapperHandler.java
index 50f0fb8..f856350 100644
--- a/tika-core/src/main/java/org/apache/tika/sax/RecursiveParserWrapperHandler.java
+++ b/tika-core/src/main/java/org/apache/tika/sax/RecursiveParserWrapperHandler.java
@@ -18,6 +18,7 @@ package org.apache.tika.sax;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.filter.MetadataFilter;
import org.apache.tika.metadata.filter.NoOpFilter;
import org.apache.tika.utils.ParserUtils;
@@ -33,7 +34,7 @@ import java.util.List;
* See its documentation for more details.
*
* This caches the a metadata object for each embedded file and for the container file.
- * It places the extracted content in the metadata object, with this key: {@link AbstractRecursiveParserWrapperHandler#TIKA_CONTENT}
+ * It places the extracted content in the metadata object, with this key: {@link TikaCoreProperties#TIKA_CONTENT}
* If memory is a concern, subclass AbstractRecursiveParserWrapperHandler to handle each
* embedded document.
* <p>
@@ -138,8 +139,8 @@ public class RecursiveParserWrapperHandler extends AbstractRecursiveParserWrappe
} else {
String content = handler.toString();
if (content != null && content.trim().length() > 0 ) {
- metadata.add(TIKA_CONTENT, content);
- metadata.add(TIKA_CONTENT_HANDLER, handler.getClass().getSimpleName());
+ metadata.add(TikaCoreProperties.TIKA_CONTENT, content);
+ metadata.add(TikaCoreProperties.TIKA_CONTENT_HANDLER, handler.getClass().getSimpleName());
}
}
}
diff --git a/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java b/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
index 555f0e7..9b1d2f4 100644
--- a/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
+++ b/tika-core/src/main/java/org/apache/tika/utils/ParserUtils.java
@@ -27,6 +27,8 @@ import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ParserDecorator;
+import static org.apache.tika.metadata.TikaCoreProperties.EMBEDDED_EXCEPTION;
+
/**
* Helper util methods for Parsers themselves.
*/
@@ -34,8 +36,7 @@ public class ParserUtils {
public final static Property EMBEDDED_PARSER =
Property.internalText(TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX + "embedded_parser");
- public final static Property EMBEDDED_EXCEPTION =
- Property.internalText(TikaCoreProperties.TIKA_META_EXCEPTION_PREFIX + "embedded_exception");
+
/**
* Does a deep clone of a Metadata object.
diff --git a/tika-core/src/test/java/org/apache/tika/MultiThreadedTikaTest.java b/tika-core/src/test/java/org/apache/tika/MultiThreadedTikaTest.java
index 6e4ad3b..1064b88 100644
--- a/tika-core/src/test/java/org/apache/tika/MultiThreadedTikaTest.java
+++ b/tika-core/src/test/java/org/apache/tika/MultiThreadedTikaTest.java
@@ -22,10 +22,10 @@ import org.apache.tika.detect.XmlRootExtractor;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.apache.tika.utils.XMLReaderUtils;
@@ -401,8 +401,8 @@ public class MultiThreadedTikaTest extends TikaTest {
extractA.metadataList.get(i).size(), extractB.metadataList.get(i).size());
assertEquals("content in attachment: " + i,
- extractA.metadataList.get(i).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT),
- extractB.metadataList.get(i).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ extractA.metadataList.get(i).get(TikaCoreProperties.TIKA_CONTENT),
+ extractB.metadataList.get(i).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java b/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
index d2342c5..e4a3b7a 100644
--- a/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
+++ b/tika-core/src/test/java/org/apache/tika/fork/ForkParserTest.java
@@ -35,11 +35,9 @@ import java.io.StringWriter;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
-import java.nio.file.Paths;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
-import java.util.LinkedList;
import java.util.List;
import java.util.concurrent.Semaphore;
@@ -58,7 +56,6 @@ import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
-import org.apache.tika.sax.ToTextContentHandler;
import org.junit.Test;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -259,13 +256,13 @@ public class ForkParserTest extends TikaTest {
List<Metadata> metadataList = handler.getMetadataList();
Metadata m0 = metadataList.get(0);
assertEquals("Nikolai Lobachevsky", m0.get(TikaCoreProperties.CREATOR));
- assertContains("main_content", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("embed1.xml", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("main_content", m0.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("embed1.xml", m0.get(TikaCoreProperties.TIKA_CONTENT));
Metadata m1 = metadataList.get(1);
assertEquals("embeddedAuthor", m1.get(TikaCoreProperties.CREATOR));
- assertContains("some_embedded_content", m1.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertEquals("/embed1.xml", m1.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertContains("some_embedded_content", m1.get(TikaCoreProperties.TIKA_CONTENT));
+ assertEquals("/embed1.xml", m1.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
@@ -284,14 +281,14 @@ public class ForkParserTest extends TikaTest {
List<Metadata> metadataList = handler.getMetadataList();
Metadata m0 = metadataList.get(0);
assertEquals("Nikolai Lobachevsky", m0.get(TikaCoreProperties.CREATOR));
- assertContains("main_content", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("embed1.xml", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("main_content", m0.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("embed1.xml", m0.get(TikaCoreProperties.TIKA_CONTENT));
Metadata m1 = metadataList.get(1);
assertEquals("embeddedAuthor", m1.get(TikaCoreProperties.CREATOR));
- assertContains("some_embedded_content", m1.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertEquals("/embed1.xml", m1.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
- assertContains("another null pointer exception", m1.get(RecursiveParserWrapperHandler.EMBEDDED_EXCEPTION));
+ assertContains("some_embedded_content", m1.get(TikaCoreProperties.TIKA_CONTENT));
+ assertEquals("/embed1.xml", m1.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
+ assertContains("another null pointer exception", m1.get(TikaCoreProperties.EMBEDDED_EXCEPTION));
}
@Test
@@ -314,13 +311,13 @@ public class ForkParserTest extends TikaTest {
List<Metadata> metadataList = handler.getMetadataList();
Metadata m0 = metadataList.get(0);
assertEquals("Nikolai Lobachevsky", m0.get(TikaCoreProperties.CREATOR));
- assertContains("main_content", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("embed1.xml", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("main_content", m0.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("embed1.xml", m0.get(TikaCoreProperties.TIKA_CONTENT));
Metadata m1 = metadataList.get(1);
assertEquals("embeddedAuthor", m1.get(TikaCoreProperties.CREATOR));
- assertContains("some_embedded_content", m1.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertEquals("/embed1.xml", m1.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertContains("some_embedded_content", m1.get(TikaCoreProperties.TIKA_CONTENT));
+ assertEquals("/embed1.xml", m1.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
@@ -385,7 +382,7 @@ public class ForkParserTest extends TikaTest {
String content1 = contentHandlers.get(1).toString();
assertEquals("embeddedAuthor", m1.get(TikaCoreProperties.CREATOR));
assertContains("some_embedded_content", content1);
- assertEquals("/embed1.xml", m1.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/embed1.xml", m1.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@@ -408,13 +405,13 @@ public class ForkParserTest extends TikaTest {
List<Metadata> metadataList = handler.getMetadataList();
Metadata m0 = metadataList.get(0);
assertEquals("Nikolai Lobachevsky", m0.get(TikaCoreProperties.CREATOR));
- assertContains("main_content", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("embed1.xml", m0.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("main_content", m0.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("embed1.xml", m0.get(TikaCoreProperties.TIKA_CONTENT));
Metadata m1 = metadataList.get(1);
assertEquals("embeddedAuthor", m1.get(TikaCoreProperties.CREATOR));
- assertContains("some_embedded_content", m1.get(RecursiveParserWrapperHandler.TIKA_CONTENT));
- assertEquals("/embed1.xml", m1.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertContains("some_embedded_content", m1.get(TikaCoreProperties.TIKA_CONTENT));
+ assertEquals("/embed1.xml", m1.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
diff --git a/tika-core/src/test/java/org/apache/tika/parser/multiple/MultipleParserTest.java b/tika-core/src/test/java/org/apache/tika/parser/multiple/MultipleParserTest.java
index 8107d82..c339e0e 100644
--- a/tika-core/src/test/java/org/apache/tika/parser/multiple/MultipleParserTest.java
+++ b/tika-core/src/test/java/org/apache/tika/parser/multiple/MultipleParserTest.java
@@ -104,7 +104,7 @@ public class MultipleParserTest {
assertEquals(DummyParser.class.getName(), usedParsers[1]);
// Check we got an exception
- assertNotNull(metadata.get(ParserUtils.EMBEDDED_EXCEPTION));
+ assertNotNull(metadata.get(TikaCoreProperties.EMBEDDED_EXCEPTION));
assertNotNull(metadata.get(ParserUtils.EMBEDDED_PARSER));
assertEquals(ErrorParser.class.getName(), metadata.get(ParserUtils.EMBEDDED_PARSER));
diff --git a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
index 910fe09..aee72b3 100644
--- a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
+++ b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/AbstractProfiler.java
@@ -68,8 +68,7 @@ import org.apache.tika.exception.TikaException;
import org.apache.tika.language.detect.LanguageResult;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.PagedText;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.sax.ToXMLContentHandler;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -293,7 +292,7 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
data.put(Cols.FILE_NAME, fps.getRelativeSourceFilePath().getFileName().toString());
} else {
data.put(Cols.IS_EMBEDDED, TRUE);
- data.put(Cols.FILE_NAME, getFileName(m.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH)));
+ data.put(Cols.FILE_NAME, getFileName(m.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH)));
}
String ext = FilenameUtils.getExtension(data.get(Cols.FILE_NAME));
ext = (ext == null) ? "" : ext.toLowerCase(Locale.US);
@@ -470,7 +469,7 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
String getTime(Metadata m) {
String elapsed = "-1";
- String v = m.get(AbstractRecursiveParserWrapperHandler.PARSE_TIME_MILLIS);
+ String v = m.get(TikaCoreProperties.PARSE_TIME_MILLIS);
if (v != null) {
return v;
}
@@ -490,10 +489,10 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
void getExceptionStrings(Metadata metadata, Map<Cols, String> data) {
- String fullTrace = metadata.get(RecursiveParserWrapperHandler.CONTAINER_EXCEPTION);
+ String fullTrace = metadata.get(TikaCoreProperties.CONTAINER_EXCEPTION);
if (fullTrace == null) {
- fullTrace = metadata.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_EXCEPTION);
+ fullTrace = metadata.get(TikaCoreProperties.EMBEDDED_EXCEPTION);
}
if (fullTrace != null) {
@@ -738,7 +737,7 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
Map<String, Integer> counts = new HashMap<>();
for (int i = 1; i < list.size(); i++) {
- String path = list.get(i).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ String path = list.get(i).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
if (path == null) {
//shouldn't ever happen
continue;
@@ -760,7 +759,7 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
}
for (int i = 1; i < list.size(); i++) {
- Integer count = counts.get(list.get(i).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ Integer count = counts.get(list.get(i).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
if (count == null) {
count = 0;
}
@@ -779,12 +778,12 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
}
private static ContentTags parseContentAndTags(EvalFilePaths evalFilePaths, Metadata metadata) {
- String s = metadata.get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String s = metadata.get(TikaCoreProperties.TIKA_CONTENT);
if (s == null || s.length() == 0) {
return ContentTags.EMPTY_CONTENT_TAGS;
}
- String handlerClass = metadata.get(RecursiveParserWrapperHandler.TIKA_CONTENT_HANDLER);
+ String handlerClass = metadata.get(TikaCoreProperties.TIKA_CONTENT_HANDLER);
if (evalFilePaths.getExtractFile().getFileName().toString().toLowerCase(Locale.ENGLISH).endsWith(".html")) {
try {
return ContentTagParser.parseHTML(s, UC_TAGS_OF_INTEREST.keySet());
diff --git a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
index 4b827f7..0f9286f 100644
--- a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
+++ b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java
@@ -47,7 +47,6 @@ import org.apache.tika.eval.core.tokens.TokenIntPair;
import org.apache.tika.eval.core.util.ContentTags;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
public class ExtractComparer extends AbstractProfiler {
@@ -406,10 +405,10 @@ public class ExtractComparer extends AbstractProfiler {
String pathA = null;
String pathB = null;
if (mA != null) {
- pathA = mA.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ pathA = mA.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
}
if (mB != null) {
- pathB = mB.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ pathB = mB.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
}
if (pathA != null) {
Map<Cols, String> d = new HashMap<>();
@@ -473,11 +472,11 @@ public class ExtractComparer extends AbstractProfiler {
//assume same embedded resource path. Not always true!
Metadata thisMetadata = metadataListA.get(aIndex);
- String embeddedPath = thisMetadata.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ String embeddedPath = thisMetadata.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
if (embeddedPath != null) {
for (int j = 0; j < metadataListB.size(); j++) {
String thatEmbeddedPath = metadataListB.get(j).get(
- AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
if (embeddedPath.equals(thatEmbeddedPath)) {
return j;
}
diff --git a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
index 029162e..4fc4a69 100644
--- a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
+++ b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractProfiler.java
@@ -36,7 +36,7 @@ import org.apache.tika.eval.app.io.ExtractReaderException;
import org.apache.tika.eval.app.io.IDBWriter;
import org.apache.tika.eval.core.util.ContentTags;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
public class ExtractProfiler extends AbstractProfiler {
@@ -271,7 +271,7 @@ public class ExtractProfiler extends AbstractProfiler {
Map<Cols, String> data = new HashMap<>();
data.put(Cols.ID, fileId);
data.put(Cols.EMBEDDED_FILE_PATH,
- m.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ m.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
try {
writer.writeRow(embeddedFilePathTable, data);
} catch (IOException e) {
diff --git a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/io/ExtractReader.java b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/io/ExtractReader.java
index eb6be14..40ef751 100644
--- a/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/io/ExtractReader.java
+++ b/tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/io/ExtractReader.java
@@ -40,8 +40,6 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.serialization.JsonMetadataList;
import org.apache.tika.mime.MediaType;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.apache.tika.sax.ToTextContentHandler;
import org.apache.tika.sax.ToXMLContentHandler;
import org.slf4j.Logger;
@@ -152,13 +150,13 @@ public class ExtractReader {
StringBuilder sb = new StringBuilder();
Metadata containerMetadata = metadataList.get(0);
for (Metadata m : metadataList) {
- String c = m.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String c = m.get(TikaCoreProperties.TIKA_CONTENT);
if (c != null) {
sb.append(c);
sb.append(" ");
}
}
- containerMetadata.set(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT, sb.toString());
+ containerMetadata.set(TikaCoreProperties.TIKA_CONTENT, sb.toString());
while (metadataList.size() > 1) {
metadataList.remove(metadataList.size()-1);
}
@@ -182,11 +180,11 @@ public class ExtractReader {
List<Metadata> metadataList = new ArrayList<>();
String content = IOUtils.toString(reader);
Metadata m = new Metadata();
- m.set(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT, content);
+ m.set(TikaCoreProperties.TIKA_CONTENT, content);
if (fileSuffixes.format == FileSuffixes.FORMAT.HTML) {
- m.set(RecursiveParserWrapperHandler.TIKA_CONTENT_HANDLER, ToXMLContentHandler.class.getSimpleName());
+ m.set(TikaCoreProperties.TIKA_CONTENT_HANDLER, ToXMLContentHandler.class.getSimpleName());
} else if (fileSuffixes.format == FileSuffixes.FORMAT.TXT) {
- m.set(RecursiveParserWrapperHandler.TIKA_CONTENT_HANDLER, ToTextContentHandler.class.getSimpleName());
+ m.set(TikaCoreProperties.TIKA_CONTENT_HANDLER, ToTextContentHandler.class.getSimpleName());
}
//Let's hope the file name has a suffix that can
//be used to determine the mime. Could be wrong or missing,
diff --git a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/SimpleComparerTest.java b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/SimpleComparerTest.java
index 4d32f4e..097a884 100644
--- a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/SimpleComparerTest.java
+++ b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/SimpleComparerTest.java
@@ -37,7 +37,7 @@ import org.apache.tika.eval.app.io.ExtractReader;
import org.apache.tika.eval.app.io.ExtractReaderException;
import org.apache.tika.eval.core.util.ContentTags;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Before;
import org.junit.BeforeClass;
import org.junit.Ignore;
@@ -232,23 +232,23 @@ public class SimpleComparerTest extends TikaTest {
public void testAttachmentCounts() {
List<Metadata> list = new ArrayList<>();
Metadata m0 = new Metadata();
- m0.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "dir1/dir2/file.zip");//bad data should be ignored
+ m0.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "dir1/dir2/file.zip");//bad data should be ignored
//in the first metadata object
list.add(m0);
Metadata m1 = new Metadata();
- m1.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip/text1.txt");
+ m1.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip/text1.txt");
list.add(m1);
Metadata m2 = new Metadata();
- m2.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip/text2.txt");
+ m2.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip/text2.txt");
list.add(m2);
Metadata m3 = new Metadata();
- m3.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip");
+ m3.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/f1.docx/f2.zip");
list.add(m3);
Metadata m4 = new Metadata();
- m4.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/f1.docx");
+ m4.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/f1.docx");
list.add(m4);
Metadata m5 = new Metadata();
- m5.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/f1.docx/text3.txt");
+ m5.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/f1.docx/text3.txt");
list.add(m5);
List<Integer> counts = AbstractProfiler.countAttachments(list);
diff --git a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/io/ExtractReaderTest.java b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/io/ExtractReaderTest.java
index 18a65ee..f8509ff 100644
--- a/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/io/ExtractReaderTest.java
+++ b/tika-eval/tika-eval-app/src/test/java/org/apache/tika/eval/app/io/ExtractReaderTest.java
@@ -25,7 +25,7 @@ import java.util.List;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Before;
import org.junit.Test;
@@ -47,24 +47,24 @@ public class ExtractReaderTest extends TikaTest {
List<Metadata> metadataList = extractReader.loadExtract(testJsonFile);
assertEquals(2, metadataList.size());
- assertEquals(1, metadataList.get(0).getValues(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).length);
- assertEquals(1, metadataList.get(1).getValues(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).length);
- assertContains("fox", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("attachment", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertEquals(1, metadataList.get(0).getValues(TikaCoreProperties.TIKA_CONTENT).length);
+ assertEquals(1, metadataList.get(1).getValues(TikaCoreProperties.TIKA_CONTENT).length);
+ assertContains("fox", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("attachment", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
extractReader = new ExtractReader(ExtractReader.ALTER_METADATA_LIST.FIRST_ONLY);
metadataList = extractReader.loadExtract(testJsonFile);
assertEquals(1, metadataList.size());
- assertEquals(1, metadataList.get(0).getValues(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).length);
- assertContains("fox", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertNotContained("attachment", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertEquals(1, metadataList.get(0).getValues(TikaCoreProperties.TIKA_CONTENT).length);
+ assertContains("fox", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
+ assertNotContained("attachment", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
extractReader = new ExtractReader(ExtractReader.ALTER_METADATA_LIST.CONCATENATE_CONTENT_INTO_FIRST);
metadataList = extractReader.loadExtract(testJsonFile);
assertEquals(1, metadataList.size());
- assertEquals(1, metadataList.get(0).getValues(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).length);
- assertContains("fox", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("attachment", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertEquals(1, metadataList.get(0).getValues(TikaCoreProperties.TIKA_CONTENT).length);
+ assertContains("fox", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("attachment", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -73,9 +73,9 @@ public class ExtractReaderTest extends TikaTest {
List<Metadata> metadataList = extractReader.loadExtract(testTxtFile);
assertEquals(1, metadataList.size());
Metadata m = metadataList.get(0);
- assertEquals(1, m.getValues(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).length);
+ assertEquals(1, m.getValues(TikaCoreProperties.TIKA_CONTENT).length);
assertContains("the quick brown fox fox fox jumped over the lazy lazy dog",
- m.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ m.get(TikaCoreProperties.TIKA_CONTENT));
//test that the mime is inferred from the file extension
assertEquals("application/msword", m.get(Metadata.CONTENT_TYPE));
diff --git a/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsA/file6_accessEx.pdf.json b/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsA/file6_accessEx.pdf.json
index ded29af..04b321e 100644
--- a/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsA/file6_accessEx.pdf.json
+++ b/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsA/file6_accessEx.pdf.json
@@ -1 +1 @@
-[{"Content-Type":"application/pdf","X-Parsed-By":["org.apache.tika.parser.DefaultParser","org.apache.tika.parser.pdf.PDFParser"],"X-TIKA:EXCEPTION:runtime":"org.apache.tika.exception.AccessPermissionException: Content extraction is not allowed.\n\tat org.apache.tika.parser.pdf.AccessChecker.check(AccessChecker.java:77)\n\tat org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:147)\n\tat org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:270)\n\tat org.apache.tika.par [...]
\ No newline at end of file
+[{"Content-Type":"application/pdf","X-Parsed-By":["org.apache.tika.parser.DefaultParser","org.apache.tika.parser.pdf.PDFParser"],"X-TIKA:EXCEPTION:container_exception":"org.apache.tika.exception.AccessPermissionException: Content extraction is not allowed.\n\tat org.apache.tika.parser.pdf.AccessChecker.check(AccessChecker.java:77)\n\tat org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:147)\n\tat org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:270)\n\tat org.apa [...]
\ No newline at end of file
diff --git a/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsB/file6_accessEx.pdf.json b/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsB/file6_accessEx.pdf.json
index ded29af..04b321e 100644
--- a/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsB/file6_accessEx.pdf.json
+++ b/tika-eval/tika-eval-app/src/test/resources/test-dirs/extractsB/file6_accessEx.pdf.json
@@ -1 +1 @@
-[{"Content-Type":"application/pdf","X-Parsed-By":["org.apache.tika.parser.DefaultParser","org.apache.tika.parser.pdf.PDFParser"],"X-TIKA:EXCEPTION:runtime":"org.apache.tika.exception.AccessPermissionException: Content extraction is not allowed.\n\tat org.apache.tika.parser.pdf.AccessChecker.check(AccessChecker.java:77)\n\tat org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:147)\n\tat org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:270)\n\tat org.apache.tika.par [...]
\ No newline at end of file
+[{"Content-Type":"application/pdf","X-Parsed-By":["org.apache.tika.parser.DefaultParser","org.apache.tika.parser.pdf.PDFParser"],"X-TIKA:EXCEPTION:container_exception":"org.apache.tika.exception.AccessPermissionException: Content extraction is not allowed.\n\tat org.apache.tika.parser.pdf.AccessChecker.check(AccessChecker.java:77)\n\tat org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:147)\n\tat org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:270)\n\tat org.apa [...]
\ No newline at end of file
diff --git a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilter.java b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilter.java
index f5fa9da..fa3f2ed 100644
--- a/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilter.java
+++ b/tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilter.java
@@ -30,7 +30,6 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Property;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.filter.MetadataFilter;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import java.util.ArrayList;
import java.util.List;
@@ -68,7 +67,7 @@ public class TikaEvalMetadataFilter implements MetadataFilter {
@Override
public void filter(Metadata metadata) throws TikaException {
- String content = metadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = metadata.get(TikaCoreProperties.TIKA_CONTENT);
if (StringUtils.isAllBlank(content)) {
return;
}
diff --git a/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilterTest.java b/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilterTest.java
index 51a5291..9f374cd 100644
--- a/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilterTest.java
+++ b/tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilterTest.java
@@ -17,9 +17,9 @@
package org.apache.tika.eval.core.metadata;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.filter.DefaultMetadataFilter;
import org.apache.tika.metadata.filter.MetadataFilter;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.junit.Test;
import static org.junit.Assert.assertEquals;
@@ -35,7 +35,7 @@ public class TikaEvalMetadataFilterTest {
}) {
Metadata metadata = new Metadata();
String content = "the quick brown fox, Zothro 1234 1235, jumped over the lazy dog";
- metadata.set(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT, content);
+ metadata.set(TikaCoreProperties.TIKA_CONTENT, content);
filter.filter(metadata);
assertEquals("eng", metadata.get(TikaEvalMetadataFilter.LANGUAGE));
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/apple/PListParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
index 94ddbe4..15f7a7c 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
@@ -18,7 +18,7 @@ package org.apache.tika.parser.apple;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
import java.util.List;
@@ -36,7 +36,7 @@ public class PListParserTest extends TikaTest {
assertEquals(21, metadataList.size());
Metadata m = metadataList.get(0);
assertEquals("application/x-bplist-itunes", m.get(Metadata.CONTENT_TYPE));
- String content = m.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = m.get(TikaCoreProperties.TIKA_CONTENT);
assertContains("<key>Application Version</key><string>9.0", content);
//TODO -- bad encoding right after this...smart quote?
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
index 05aea75..b5a99f1 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
@@ -67,11 +67,9 @@ import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.LinkContentHandler;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.apache.tika.sax.TeeContentHandler;
import org.apache.tika.sax.boilerpipe.BoilerpipeContentHandler;
import org.ccil.cowan.tagsoup.HTMLSchema;
@@ -1291,8 +1289,8 @@ public class HtmlParserTest extends TikaTest {
assertEquals(2, metadataList.size());
assertEquals("MACRO", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
assertContains("cool",
- metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertNotContained("cool", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
+ assertNotContained("cool", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -1304,8 +1302,8 @@ public class HtmlParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testHTMLGoodScript.html", p);
assertEquals(2, metadataList.size());
assertEquals("MACRO", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
- assertContains("cool", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertNotContained("cool", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("cool", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
+ assertNotContained("cool", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
}
@@ -1414,7 +1412,7 @@ public class HtmlParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testHTML_embedded_data_uri_js.html");
assertEquals(1, metadataList.size());
assertNotContained("alert( 'Hello, world!' );",
- metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
//make sure to include it if a user wants scripts to be extracted
try (InputStream is = getResourceAsStream("/org/apache/tika/parser/html/tika-config.xml")) {
@@ -1424,7 +1422,7 @@ public class HtmlParserTest extends TikaTest {
metadataList = getRecursiveMetadata("testHTML_embedded_data_uri_js.html", p);
assertEquals(2, metadataList.size());
assertContains("alert( 'Hello, world!' );",
- metadataList.get(1).get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
}
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
index 4e1ee70..9965452 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
@@ -54,9 +54,7 @@ import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.parser.ocr.TesseractOCRParserTest;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.XHTMLContentHandler;
import org.junit.BeforeClass;
@@ -466,7 +464,7 @@ public class RFC822ParserTest extends TikaTest {
assertEquals("text/plain; charset=UTF-8", metadataList.get(1).get(Metadata.CONTENT_TYPE));
assertEquals("image/png", metadataList.get(2).get(Metadata.CONTENT_TYPE));
assertEquals("testPNG.png", metadataList.get(2).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("This email has a PNG attachment included in it", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("This email has a PNG attachment included in it", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals(null, metadataList.get(1).get(Metadata.CONTENT_DISPOSITION));
assertEquals("attachment; filename=\"testPNG.png\"", metadataList.get(2).get(Metadata.CONTENT_DISPOSITION));
}
@@ -522,12 +520,12 @@ public class RFC822ParserTest extends TikaTest {
*/
List<Metadata> metadataList = getRecursiveMetadata("testRFC822-multipart");
assertEquals(2, metadataList.size());
- String body = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String body = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("body 2", body);
assertNotContained("body 1", body);
assertEquals("message/rfc822", metadataList.get(0).get(Metadata.CONTENT_TYPE));
assertEquals("image/gif", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- assertEquals("/logo.gif", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/logo.gif", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
@@ -546,17 +544,17 @@ public class RFC822ParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testRFC822-mixed-simple");
assertEquals(3, metadataList.size());
- assertContains("body 2", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertNotContained("body 1", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("body 2", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
+ assertNotContained("body 1", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("message/rfc822", metadataList.get(0).get(Metadata.CONTENT_TYPE));
assertEquals("image/jpeg", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- assertEquals("/Mary with cooler.jpeg", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/Mary with cooler.jpeg", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals(TikaCoreProperties.EmbeddedResourceType.INLINE.toString(),
metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
assertEquals("image/jpeg", metadataList.get(2).get(Metadata.CONTENT_TYPE));
- assertEquals("/mary-coffee.jpg", metadataList.get(2).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/mary-coffee.jpg", metadataList.get(2).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals(TikaCoreProperties.EmbeddedResourceType.ATTACHMENT.toString(),
metadataList.get(2).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
}
@@ -577,20 +575,20 @@ public class RFC822ParserTest extends TikaTest {
*/
List<Metadata> metadataList = getRecursiveMetadata("testRFC822-mixed-with-pdf-inline");
assertEquals(2, metadataList.size());
- String body = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String body = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("body 2", body);
assertContains("body 3", body);
assertNotContained("body 1", body);
assertEquals("message/rfc822", metadataList.get(0).get(Metadata.CONTENT_TYPE));
assertEquals("application/pdf", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- assertEquals("/tzora-titan-4-hummer-xl-manual.pdf", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/tzora-titan-4-hummer-xl-manual.pdf", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
public void testSimpleBodyInlined() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testRFC822_simple_inline_body.txt");
assertEquals(1, metadataList.size());
- assertContains("asked", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("asked", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -598,6 +596,6 @@ public class RFC822ParserTest extends TikaTest {
//TODO -- this should treat attachments as attachments, no?
List<Metadata> metadataList = getRecursiveMetadata("testGroupWiseEml.eml");
assertEquals(1, metadataList.size());
- assertContains("ssssss", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("ssssss", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java
index 541794c..042ba28 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mbox/MboxParserTest.java
@@ -29,7 +29,6 @@ import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.junit.Before;
import org.junit.Test;
@@ -155,7 +154,7 @@ public class MboxParserTest extends TikaTest {
assertEquals(2, metadataList.size());
assertEquals("application/mbox", metadataList.get(0).get(Metadata.CONTENT_TYPE));
assertEquals("message/rfc822", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- assertContains("body 2", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertNotContained("body 1", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("body 2", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
+ assertNotContained("body 1", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
index 50df51f..f3d938b 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
@@ -22,6 +22,7 @@ import java.util.List;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.RecursiveParserWrapper;
import org.junit.Test;
@@ -34,9 +35,9 @@ public class EMFParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testEXCEL_embeddedPDF_mac.xls");
Metadata emfMetadata = metadataList.get(2);
assertEquals("image/emf", emfMetadata.get(Metadata.CONTENT_TYPE));
- assertContains("is a toolkit for detecting", emfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("is a toolkit for detecting", emfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
//test that a space was inserted before url
- assertContains("Tika http://incubator.apache.org/tika/", emfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Tika http://incubator.apache.org/tika/", emfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
index d9b87ff..c8ad23f 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
@@ -22,7 +22,6 @@ import static org.junit.Assert.fail;
import java.io.InputStream;
import java.text.DecimalFormatSymbols;
-import java.util.List;
import java.util.Locale;
import org.apache.poi.util.LocaleUtil;
@@ -40,7 +39,6 @@ import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.sax.BodyContentHandler;
import org.junit.Test;
@@ -494,8 +492,8 @@ public class ExcelParserTest extends TikaTest {
context.set(OfficeParserConfig.class, officeParserConfig);
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Dirty()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "dirty dirt dirt");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Dirty()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "dirty dirt dirt");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/JackcessParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/JackcessParserTest.java
index 37cab17..6787d4f 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/JackcessParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/JackcessParserTest.java
@@ -61,7 +61,7 @@ public class JackcessParserTest extends TikaTest {
}
List<Metadata> list = handler.getMetadataList();
assertEquals(4, list.size());
- String mainContent = list.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String mainContent = list.get(0).get(TikaCoreProperties.TIKA_CONTENT);
//make sure there's a thead and tbody
assertContains("</thead><tbody>", mainContent);
@@ -81,7 +81,7 @@ public class JackcessParserTest extends TikaTest {
//test embedded document handling
assertContains("Test Document with embedded pdf",
- list.get(3).get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ list.get(3).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
index eb54234..ad5f940 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
@@ -296,7 +296,7 @@ public class OutlookParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testMSG.msg");
assertEquals(1, metadataList.size());
assertContains("breaking your application",
- metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT));
+ metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.ms-outlook",
metadataList.get(0).get(Metadata.CONTENT_TYPE));
@@ -311,17 +311,17 @@ public class OutlookParserTest extends TikaTest {
assertEquals(3, metadataList.size());
assertNotContained("breaking your application",
- metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT));
+ metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.ms-outlook",
metadataList.get(0).get(Metadata.CONTENT_TYPE));
assertContains("breaking your application",
- metadataList.get(1).get(RecursiveParserWrapper.TIKA_CONTENT));
+ metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/rtf",
metadataList.get(1).get(Metadata.CONTENT_TYPE));
assertContains("breaking your application",
- metadataList.get(2).get(RecursiveParserWrapper.TIKA_CONTENT));
+ metadataList.get(2).get(TikaCoreProperties.TIKA_CONTENT));
assertTrue(metadataList.get(2).get(Metadata.CONTENT_TYPE).startsWith("text/plain"));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
index ac2e06c..ab1008e 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
@@ -156,7 +156,7 @@ public class POIContainerExtractionTest extends AbstractPOIContainerExtractionTe
if (m.get(Metadata.CONTENT_TYPE).equals(POIFSContainerDetector.MS_GRAPH_CHART.toString())) {
found = true;
}
- assertNull(m.get(ParserUtils.EMBEDDED_EXCEPTION));
+ assertNull(m.get(TikaCoreProperties.EMBEDDED_EXCEPTION));
}
assertTrue("didn't find chart in "+suffix, found);
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
index d95978d..585cd72 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
@@ -289,8 +289,8 @@ public class PowerPointParserTest extends TikaTest {
@Test
public void testMacros() throws Exception {
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -333,7 +333,7 @@ public class PowerPointParserTest extends TikaTest {
public void testGroups() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_groups.ppt");
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
//this tests that we're ignoring text shapes at depth=0
//i.e. POI has already included them in the slide's getTextParagraphs()
assertContainsCount("Text box1", content, 1);
@@ -356,10 +356,10 @@ public class PowerPointParserTest extends TikaTest {
assertContains("MyTitle", content);
assertEquals("/embedded-1",
- metadataList.get(1).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals("/embedded-2",
- metadataList.get(2).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(2).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@@ -382,8 +382,8 @@ public class PowerPointParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_oleWorkbook.ppt");
assertEquals(3, metadataList.size());
Metadata xlsx = metadataList.get(1);
- assertContains("<h1>Sheet1</h1>", xlsx.get(RecursiveParserWrapper.TIKA_CONTENT));
- assertContains("<td>1</td>", xlsx.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("<h1>Sheet1</h1>", xlsx.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("<td>1</td>", xlsx.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
xlsx.get(Metadata.CONTENT_TYPE));
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WMFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WMFParserTest.java
index d61b816..c5c61be 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WMFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WMFParserTest.java
@@ -22,7 +22,7 @@ import java.util.List;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.RecursiveParserWrapper;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
public class WMFParserTest extends TikaTest {
@@ -42,7 +42,7 @@ public class WMFParserTest extends TikaTest {
Metadata wmfMetadata = metadataList.get(metaDataItemIndex);
assertEquals("image/wmf", wmfMetadata.get(Metadata.CONTENT_TYPE));
- assertContains(expectedText, wmfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains(expectedText, wmfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
index 40d4ab8..5f5006e 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
@@ -581,8 +581,8 @@ public class WordParserTest extends TikaTest {
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
index a1123fe..0a19651 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLContainerExtractionTest.java
@@ -26,6 +26,7 @@ import org.apache.tika.Tika;
import org.apache.tika.extractor.ContainerExtractor;
import org.apache.tika.extractor.ParserContainerExtractor;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.microsoft.AbstractPOIContainerExtractionTest;
import org.apache.tika.detect.microsoft.POIFSContainerDetector;
import org.apache.tika.utils.ParserUtils;
@@ -317,7 +318,7 @@ public class OOXMLContainerExtractionTest extends AbstractPOIContainerExtraction
if (m.get(Metadata.CONTENT_TYPE).equals(POIFSContainerDetector.MS_GRAPH_CHART.toString())) {
found = true;
}
- assertNull(m.get(ParserUtils.EMBEDDED_EXCEPTION));
+ assertNull(m.get(TikaCoreProperties.EMBEDDED_EXCEPTION));
}
assertTrue("didn't find chart in "+suffix, found);
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index 364ea4b..f5a49f1 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -451,7 +451,7 @@ public class OOXMLParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("headerPic.docx");
assertEquals(2, metadataList.size());
Metadata m = metadataList.get(0);
- String mainContent = m.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String mainContent = m.get(TikaCoreProperties.TIKA_CONTENT);
assertEquals(
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
m.get(Metadata.CONTENT_TYPE));
@@ -468,7 +468,7 @@ public class OOXMLParserTest extends TikaTest {
//only process embedded resources once
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
for (int i = 1; i < 4; i++) {
assertContains("header"+i+"_pic", content);
assertContains("footer"+i+"_pic", content);
@@ -1335,8 +1335,8 @@ public class OOXMLParserTest extends TikaTest {
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -1368,8 +1368,8 @@ public class OOXMLParserTest extends TikaTest {
context.set(OfficeParserConfig.class, officeParserConfig);
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -1401,8 +1401,8 @@ public class OOXMLParserTest extends TikaTest {
context.set(OfficeParserConfig.class, officeParserConfig);
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Dirty()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "dirty dirt dirt");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Dirty()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "dirty dirt dirt");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -1497,7 +1497,7 @@ public class OOXMLParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testEXCEL_various.xlsb", parseContext);
assertEquals(4, metadataList.size());
- String xml = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String xml = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("<td>13</td>", xml);
assertContains("<td>13.1211231321</td>", xml);
assertContains("<td>$ 3.03</td>", xml);
@@ -1639,7 +1639,7 @@ public class OOXMLParserTest extends TikaTest {
public void testPPTXGroups() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_groups.pptx");
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("WordArt1", content);
assertContains("WordArt2", content);
assertContainsCount("Ungrouped text box", content, 1);//should only be 1
@@ -1655,10 +1655,10 @@ public class OOXMLParserTest extends TikaTest {
assertContains("MyTitle", content);
assertEquals("/image1.jpg",
- metadataList.get(1).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals("/thumbnail.jpeg",
- metadataList.get(2).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(2).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
@@ -1717,8 +1717,8 @@ public class OOXMLParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_oleWorkbook.pptx");
assertEquals(4, metadataList.size());
Metadata xlsx = metadataList.get(2);
- assertContains("<h1>Sheet1</h1>", xlsx.get(RecursiveParserWrapper.TIKA_CONTENT));
- assertContains("<td>1</td>", xlsx.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("<h1>Sheet1</h1>", xlsx.get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("<td>1</td>", xlsx.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
xlsx.get(Metadata.CONTENT_TYPE));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
index 30a6b1a..54c9efe 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXSLFExtractorTest.java
@@ -65,7 +65,7 @@ public class SXSLFExtractorTest extends TikaTest {
assertEquals("right number of attachments", 14, metadataList.size());
- String mainContent = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String mainContent = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("This slide is hidden", mainContent);//TODO: parameterize this
@@ -557,8 +557,8 @@ public class SXSLFExtractorTest extends TikaTest {
context.set(OfficeParserConfig.class, officeParserConfig);
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -607,7 +607,7 @@ public class SXSLFExtractorTest extends TikaTest {
public void testPPTXGroups() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_groups.pptx", parseContext);
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("WordArt1", content);
assertContains("WordArt2", content);
assertContainsCount("Ungrouped text box", content, 1);//should only be 1
@@ -623,10 +623,10 @@ public class SXSLFExtractorTest extends TikaTest {
assertContains("MyTitle", content);
assertEquals("/image1.jpg",
- metadataList.get(1).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals("/thumbnail.jpeg",
- metadataList.get(2).get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH));
+ metadataList.get(2).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
index 42cbe7e..6a51587 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/SXWPFExtractorTest.java
@@ -85,7 +85,7 @@ public class SXWPFExtractorTest extends TikaTest {
assertEquals("16.0000", m.get(OfficeOpenXMLExtended.APP_VERSION));
- String content = m.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = m.get(TikaCoreProperties.TIKA_CONTENT);
assertContainsCount("engaging title page", content, 1);
//need \n to differentiate from metadata values
@@ -290,7 +290,7 @@ public class SXWPFExtractorTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("headerPic.docx", parseContext);
assertEquals(2, metadataList.size());
Metadata m = metadataList.get(0);
- String mainContent = m.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String mainContent = m.get(TikaCoreProperties.TIKA_CONTENT);
assertEquals(
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
m.get(Metadata.CONTENT_TYPE));
@@ -306,7 +306,7 @@ public class SXWPFExtractorTest extends TikaTest {
//only process embedded resources once
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
for (int i = 1; i < 4; i++) {
assertContains("header" + i + "_pic", content);
assertContains("footer" + i + "_pic", content);
@@ -722,13 +722,13 @@ public class SXWPFExtractorTest extends TikaTest {
metadataList = getRecursiveMetadata("testWORD_macros.docm", context);
//check that content came out of the .docm file
- assertContains("quick", metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("quick", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertContainsAtLeast(parsedBy, metadataList);
Metadata minExpected = new Metadata();
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
- minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Embolden()");
+ minExpected.add(TikaCoreProperties.TIKA_CONTENT.getName(), "Sub Italicize()");
minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
@@ -750,7 +750,7 @@ public class SXWPFExtractorTest extends TikaTest {
public void testEmbedded() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testWORD_embeded.docx", parseContext);
Metadata main = metadataList.get(0);
- String content = main.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = main.get(TikaCoreProperties.TIKA_CONTENT);
//make sure mark up is there
assertContains("<img src=\"embedded:image2.jpeg\" alt=\"A description...\" />",
content);
@@ -764,7 +764,7 @@ public class SXWPFExtractorTest extends TikaTest {
@Test
public void testDotx() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testWORD_template.docx", parseContext);
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("Metallica", content);
assertContains("Hetfield", content);
assertContains("one eye open", content);
@@ -773,7 +773,7 @@ public class SXWPFExtractorTest extends TikaTest {
assertContains("table rows", content);
metadataList = getRecursiveMetadata("testWORD_template.dotx", parseContext);
- content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
//from glossary document
assertContainsCount("ready to write", content, 2);
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/TruncatedOOXMLTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/TruncatedOOXMLTest.java
index c19cf50..e71d034 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/TruncatedOOXMLTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/TruncatedOOXMLTest.java
@@ -21,20 +21,16 @@ import org.apache.commons.compress.archivers.zip.ZipArchiveInputStream;
import org.apache.commons.io.IOUtils;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Ignore;
import org.junit.Test;
-import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.EOFException;
import java.io.File;
import java.io.FileInputStream;
-import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
-import java.nio.file.Files;
-import java.nio.file.Paths;
import java.util.List;
import java.util.Random;
@@ -51,7 +47,7 @@ public class TruncatedOOXMLTest extends TikaTest {
"testWORD_various.docx", 14435), true);
assertEquals(1, metadataList.size());
Metadata metadata = metadataList.get(0);
- String content = metadata.get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = metadata.get(TikaCoreProperties.TIKA_CONTENT);
assertEquals("application/vnd.openxmlformats-officedocument.wordprocessingml.document",
metadata.get(Metadata.CONTENT_TYPE));
assertContains("This is the header", content);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSParserTest.java
index f9ed085..6015f6a 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSParserTest.java
@@ -39,7 +39,7 @@ public class XPSParserTest extends TikaTest {
assertEquals("2010-06-29T12:06:31Z", metadataList.get(0).get(TikaCoreProperties.MODIFIED));
assertEquals("Attachment Test", metadataList.get(0).get(TikaCoreProperties.TITLE));
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("<p>Attachment Test</p>", content);
assertContains("<div class=\"canvas\"><p>Different", content);
@@ -61,7 +61,7 @@ public class XPSParserTest extends TikaTest {
"\u0627\u0644\u0628\u0646\u064A\u0020" +
"\u0627\u0644\u0633\u0631\u064A\u0639";
- String content = metadataList.get(0).get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains(quickBrownFox, content);
assertContains("The \u0627\u0644\u0628\u0646\u064A fox", content);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xwpf/ml2006/Word2006MLParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xwpf/ml2006/Word2006MLParserTest.java
index 7a9f443..e5ec2e4 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xwpf/ml2006/Word2006MLParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/xwpf/ml2006/Word2006MLParserTest.java
@@ -68,7 +68,7 @@ public class Word2006MLParserTest extends MultiThreadedTikaTest {
assertEquals("16.0000", m.get(OfficeOpenXMLExtended.APP_VERSION));
- String content = m.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String content = m.get(TikaCoreProperties.TIKA_CONTENT);
assertContainsCount("This is the Author", content, 1);
assertContainsCount("This is an engaging title page", content, 1);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java
index 79d7f52..02659b6 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/epub/EpubParserTest.java
@@ -28,7 +28,6 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.Test;
public class EpubParserTest extends TikaTest {
@@ -72,7 +71,7 @@ public class EpubParserTest extends TikaTest {
//test attachments
assertEquals(2, metadataList.size());
assertEquals("image/jpeg", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- String xml = metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String xml = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
int tocIndex = xml.indexOf("h3 class=\"toc_heading\">Table of Contents<");
int ch1 = xml.indexOf("<h1>Chapter 1");
int ch2 = xml.indexOf("<h1>Chapter 2");
@@ -103,7 +102,7 @@ public class EpubParserTest extends TikaTest {
try (InputStream is = truncate("testEPUB.epub", 10000)) {
metadataList = getRecursiveMetadata(is, p, true);
}
- String xml = metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String xml = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
int ch1 = xml.indexOf("<h1>Chapter 1");
int ch2 = xml.indexOf("<h1>Chapter 2");
assert(ch1 < ch2);
@@ -115,6 +114,6 @@ public class EpubParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testEPUB_xml_ext.epub");
assertEquals(1, metadataList.size());
assertContains("It was a bright cold day in April",
- metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTMLTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTMLTest.java
index 740899b..ed87361 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTMLTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTMLTest.java
@@ -18,8 +18,8 @@ package org.apache.tika.parser.pdf;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.BeforeClass;
import org.junit.Test;
@@ -69,7 +69,7 @@ public class PDFMarkedContent2XHTMLTest extends TikaTest {
//make sure that embedded docs are still getting extracted
assertEquals(3, metadataList.size());
- String xml = metadataList.get(0).get(RecursiveParserWrapperHandler.TIKA_CONTENT);
+ String xml = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
//the point here is that in the annotations (that we were grabbing by the classic PDF2XHTML),
//the <a> content is identical to the href. Here, they are not, which we only get from
//marked up content...victory!!!
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index f34129d..202f4e2 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -63,7 +63,6 @@ import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ContentHandlerDecorator;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Ignore;
@@ -1271,7 +1270,7 @@ public class PDFParserTest extends TikaTest {
assertNull(context.get(ZeroByteFileException.IgnoreZeroByteFileException.class));
assertEquals(2, metadataList.size());
assertEquals("image/png", metadataList.get(1).get(Metadata.CONTENT_TYPE));
- assertEquals("/image0.png", metadataList.get(1).get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/image0.png", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
assertEquals(261, (int)metadataList.get(1).getInt(Metadata.IMAGE_LENGTH));
assertEquals(934, (int)metadataList.get(1).getInt(Metadata.IMAGE_WIDTH));
assertEquals("image0.png", metadataList.get(1).get(TikaCoreProperties.RESOURCE_NAME_KEY));
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java
index 957e25b..ae7ee9d 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/RecursiveParserWrapperTest.java
@@ -54,7 +54,7 @@ public class RecursiveParserWrapperTest extends TikaTest {
List<Metadata> list = getMetadata(new Metadata(),
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
Metadata container = list.get(0);
- String content = container.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = container.get(TikaCoreProperties.TIKA_CONTENT);
//not much differentiates html from xml in this test file
assertTrue(content.indexOf("<p class=\"header\" />") > -1);
}
@@ -64,7 +64,7 @@ public class RecursiveParserWrapperTest extends TikaTest {
List<Metadata> list = getMetadata(new Metadata(),
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.HTML, -1));
Metadata container = list.get(0);
- String content = container.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = container.get(TikaCoreProperties.TIKA_CONTENT);
//not much differentiates html from xml in this test file
assertTrue(content.indexOf("<p class=\"header\"></p>") > -1);
}
@@ -74,7 +74,7 @@ public class RecursiveParserWrapperTest extends TikaTest {
List<Metadata> list = getMetadata(new Metadata(),
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1));
Metadata container = list.get(0);
- String content = container.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = container.get(TikaCoreProperties.TIKA_CONTENT);
assertTrue(content.indexOf("<p ") < 0);
assertTrue(content.indexOf("embed_0") > -1);
}
@@ -84,7 +84,7 @@ public class RecursiveParserWrapperTest extends TikaTest {
List<Metadata> list = getMetadata(new Metadata(),
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.IGNORE, -1));
Metadata container = list.get(0);
- String content = container.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = container.get(TikaCoreProperties.TIKA_CONTENT);
assertNull(content);
}
@@ -105,7 +105,7 @@ public class RecursiveParserWrapperTest extends TikaTest {
int wlr = 0;
for (Metadata m : list) {
- String limitReached = m.get(AbstractRecursiveParserWrapperHandler.WRITE_LIMIT_REACHED);
+ String limitReached = m.get(TikaCoreProperties.WRITE_LIMIT_REACHED);
if (limitReached != null && limitReached.equals("true")) {
wlr++;
}
@@ -114,60 +114,6 @@ public class RecursiveParserWrapperTest extends TikaTest {
}
- /**
- * @deprecated this will be removed in 1.20 or 2.0
- * @throws Exception
- */
- @Test
- public void testMaxEmbeddedLegacy() throws Exception {
- int maxEmbedded = 4;
- int totalNoLimit = 12;//including outer container file
- ParseContext context = new ParseContext();
- Metadata metadata = new Metadata();
- String limitReached = null;
-
- RecursiveParserWrapper wrapper = new RecursiveParserWrapper(AUTO_DETECT_PARSER,
- new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1));
-
- InputStream stream = getResourceAsStream("/test-documents/test_recursive_embedded.docx");
- wrapper.parse(stream, new DefaultHandler(), metadata, context);
- List<Metadata> list = wrapper.getMetadata();
- //test default
- assertEquals(totalNoLimit, list.size());
-
- limitReached = list.get(0).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_LIMIT_REACHED);
- assertNull(limitReached);
-
-
- wrapper.reset();
- stream.close();
-
- //test setting value
- metadata = new Metadata();
- stream = getResourceAsStream("/test-documents/test_recursive_embedded.docx");
- wrapper.setMaxEmbeddedResources(maxEmbedded);
- wrapper.parse(stream, new DefaultHandler(), metadata, context);
- list = wrapper.getMetadata();
-
- //add 1 for outer container file
- assertEquals(maxEmbedded+1, list.size());
-
- limitReached = list.get(0).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_LIMIT_REACHED);
- assertEquals("true", limitReached);
-
- wrapper.reset();
- stream.close();
-
- //test setting value < 0
- metadata = new Metadata();
- stream = getResourceAsStream("/test-documents/test_recursive_embedded.docx");
-
- wrapper.setMaxEmbeddedResources(-2);
- wrapper.parse(stream, new DefaultHandler(), metadata, context);
- assertEquals(totalNoLimit, wrapper.getMetadata().size());
- limitReached = wrapper.getMetadata().get(0).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_LIMIT_REACHED);
- assertNull(limitReached);
- }
@Test
public void testMaxEmbedded() throws Exception {
@@ -242,12 +188,12 @@ public class RecursiveParserWrapperTest extends TikaTest {
List<Metadata> list = getMetadata(metadata,
new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
Metadata container = list.get(0);
- String content = container.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = container.get(TikaCoreProperties.TIKA_CONTENT);
assertTrue(content.indexOf("<p class=\"header\" />") > -1);
Set<String> seen = new HashSet<String>();
for (Metadata m : list) {
- String path = m.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ String path = m.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
if (path != null) {
seen.add(path);
}
@@ -265,7 +211,8 @@ public class RecursiveParserWrapperTest extends TikaTest {
//is to catch the exception
assertEquals(13, list.size());
Metadata mockNPEMetadata = list.get(10);
- assertContains("java.lang.NullPointerException", mockNPEMetadata.get(ParserUtils.EMBEDDED_EXCEPTION));
+ assertContains("java.lang.NullPointerException",
+ mockNPEMetadata.get(TikaCoreProperties.EMBEDDED_EXCEPTION));
metadata = new Metadata();
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, "test_recursive_embedded_npe.docx");
@@ -312,11 +259,11 @@ public class RecursiveParserWrapperTest extends TikaTest {
assertEquals(2, metadataList.size());
Metadata outerMetadata = metadataList.get(0);
Metadata embeddedMetadata = metadataList.get(1);
- assertContains("main_content", outerMetadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("main_content", outerMetadata.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("embedded_then_npe.xml", outerMetadata.get(TikaCoreProperties.RESOURCE_NAME_KEY));
assertEquals("Nikolai Lobachevsky", outerMetadata.get("author"));
- assertContains("some_embedded_content", embeddedMetadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("some_embedded_content", embeddedMetadata.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("embed1.xml", embeddedMetadata.get(TikaCoreProperties.RESOURCE_NAME_KEY));
assertEquals("embeddedAuthor", embeddedMetadata.get("author"));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
index 5f37f73..8fa3fdd 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/AppleSingleFileParserTest.java
@@ -41,7 +41,7 @@ public class AppleSingleFileParserTest extends TikaTest {
Arrays.asList(list.get(0).getValues(TikaCoreProperties.TIKA_PARSED_BY)));
assertContains(PDFParser.class.getName(),
Arrays.asList(list.get(1).getValues(TikaCoreProperties.TIKA_PARSED_BY)));
- assertContains("Hello World", list.get(1).get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World", list.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("fltsyllabussortie2rev1_2.pdf", list.get(1).get(TikaCoreProperties.ORIGINAL_RESOURCE_NAME));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/PListParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
index 59b7657..794dd7d 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/apple/PListParserTest.java
@@ -18,7 +18,7 @@ package org.apache.tika.parser.apple;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
import java.util.List;
@@ -33,7 +33,7 @@ public class PListParserTest extends TikaTest {
Metadata m0 = metadataList.get(0);
assertEquals("application/x-bplist-webarchive", m0.get(Metadata.CONTENT_TYPE));
Metadata m1 = metadataList.get(1);
- String content = m1.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = m1.get(TikaCoreProperties.TIKA_CONTENT);
assertContains("December 2008: Apache Tika Release", content);
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
index 9ecf2f5..a9ab9b2 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
@@ -18,7 +18,7 @@ package org.apache.tika.parser.crypto;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.utils.ParserUtils;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
import java.util.List;
@@ -34,8 +34,8 @@ public class TSDParserTest extends TikaTest {
List<Metadata> list = getRecursiveMetadata("testTSD_broken_pdf.tsd");
assertEquals(2, list.size());
assertEquals("application/pdf", list.get(1).get(Metadata.CONTENT_TYPE));
- assertNotNull(list.get(1).get(ParserUtils.EMBEDDED_EXCEPTION));
- assertContains("org.apache.pdfbox.pdmodel.PDDocument.load", list.get(1).get(ParserUtils.EMBEDDED_EXCEPTION));
+ assertNotNull(list.get(1).get(TikaCoreProperties.EMBEDDED_EXCEPTION));
+ assertContains("org.apache.pdfbox.pdmodel.PDDocument.load", list.get(1).get(TikaCoreProperties.EMBEDDED_EXCEPTION));
}
@Test
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
index 41861f7..794c99e 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
@@ -22,7 +22,6 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.junit.Test;
import java.io.InputStream;
@@ -37,7 +36,7 @@ public class HtmlParserTest extends TikaTest {
public void testDataURI() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testHTML_embedded_img.html");
assertEquals(2, metadataList.size());
- String content = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("some content", content);
//make sure that you've truncated the data: value
assertContains("src=\"data:\"", content);
@@ -55,7 +54,7 @@ public class HtmlParserTest extends TikaTest {
Parser p = new AutoDetectParser(tikaConfig);
List<Metadata> metadataList = getRecursiveMetadata("testHTML_embedded_img_in_js.html", p);
assertEquals(3, metadataList.size());
- String content = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String content = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("some content", content);
Metadata imgMetadata = metadataList.get(1);
assertEquals("image/jpeg", imgMetadata.get(Metadata.CONTENT_TYPE));
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
index ebdb850..744239b 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mail/RFC822ParserTest.java
@@ -24,7 +24,6 @@ import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.junit.BeforeClass;
import org.junit.Test;
@@ -152,16 +151,16 @@ public class RFC822ParserTest extends TikaTest {
//not treated as an attachment. TIKA-2547
List<Metadata> metadataList = getRecursiveMetadata("testRFC822_oddfrom");
assertEquals(7, metadataList.size());
- assertContains("Air Quality Planning", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("Air Quality Planning", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
//Make sure text alternative doesn't get treated as an attachment
metadataList = getRecursiveMetadata("testRFC822_normal_zip");
assertEquals(3, metadataList.size());
- assertContains("This is the HTML part", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("This is the HTML part", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/zip", metadataList.get(2).get(Metadata.CONTENT_TYPE));
metadataList = getRecursiveMetadata("testRFC822-txt-body");
assertEquals(2, metadataList.size());
- assertContains("body 1", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("body 1", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
index 8795021..f98fdb1 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/EMFParserTest.java
@@ -18,7 +18,7 @@ package org.apache.tika.parser.microsoft;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.RecursiveParserWrapper;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
import java.util.List;
@@ -32,12 +32,12 @@ public class EMFParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testEXCEL_embeddedPDF_windows.xls");
Metadata emfMetadata = metadataList.get(1);
assertEquals("image/emf", emfMetadata.get(Metadata.CONTENT_TYPE));
- assertContains("<p>testPDF.pdf</p>", emfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("<p>testPDF.pdf</p>", emfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
//this is just the usual embedded pdf
Metadata pdfMetadata = metadataList.get(2);
assertEquals("application/pdf", pdfMetadata.get(Metadata.CONTENT_TYPE));
- assertContains("is a toolkit for detecting", pdfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("is a toolkit for detecting", pdfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -47,6 +47,6 @@ public class EMFParserTest extends TikaTest {
//it does not exist as a standalone pdf file inside the _mac.xls file.
Metadata pdfMetadata = metadataList.get(1);
assertEquals("application/pdf", pdfMetadata.get(Metadata.CONTENT_TYPE));
- assertContains("is a toolkit for detecting", pdfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("is a toolkit for detecting", pdfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
index f97e68e..a0e948c 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
@@ -18,7 +18,7 @@ package org.apache.tika.parser.microsoft;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.RecursiveParserWrapper;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
import java.util.List;
@@ -27,6 +27,6 @@ public class ExcelParserTest extends TikaTest {
@Test
public void testEmbeddedPDF() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testExcel_embeddedPDF.xls");
- assertContains("Hello World!", metadataList.get(2).get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World!", metadataList.get(2).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
index c9e9daf..7d4a428 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
@@ -19,7 +19,6 @@ package org.apache.tika.parser.microsoft;
import org.apache.tika.TikaTest;
import org.apache.tika.extractor.ContainerExtractor;
import org.apache.tika.extractor.ParserContainerExtractor;
-import org.apache.tika.parser.microsoft.AbstractPOIContainerExtractionTest;
import org.junit.Test;
import static org.junit.Assert.assertEquals;
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
index 4345304..a9d57f2 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
@@ -19,7 +19,6 @@ package org.apache.tika.parser.microsoft;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.junit.Test;
import java.util.List;
@@ -30,9 +29,9 @@ public class PowerPointParserTest extends TikaTest {
@Test
public void testEmbeddedPDF() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_EmbeddedPDF.ppt");
- assertContains("Apache Tika project", metadataList.get(1).get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Apache Tika project", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("3.pdf", metadataList.get(1).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("Hello World", metadataList.get(2).get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World", metadataList.get(2).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("4.pdf", metadataList.get(2).get(TikaCoreProperties.RESOURCE_NAME_KEY));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/XML2003ParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/XML2003ParserTest.java
index 044f832..de45fb6 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/XML2003ParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/XML2003ParserTest.java
@@ -21,7 +21,6 @@ import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.Office;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.junit.Test;
import java.util.Arrays;
@@ -35,7 +34,7 @@ public class XML2003ParserTest extends TikaTest {
List<Metadata> list = getRecursiveMetadata("testWORD2003.xml");
assertEquals(8, list.size());
Metadata m = list.get(0);//container doc
- String xml = m.get(RecursiveParserWrapper.TIKA_CONTENT);
+ String xml = m.get(TikaCoreProperties.TIKA_CONTENT);
xml = xml.replaceAll("\\s+", " ");
//make sure that metadata gets dumped to xml
assertContains("<meta name=\"meta:character-count-with-spaces\" content=\"256\"", xml);
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
index b4e17d3..5a9933e 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
@@ -18,8 +18,8 @@ package org.apache.tika.parser.microsoft.ooxml;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
-import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.parser.microsoft.OfficeParserConfig;
import org.junit.Ignore;
import org.junit.Test;
@@ -32,16 +32,16 @@ public class OOXMLParserTest extends TikaTest {
public void testEmbeddedPDFInPPTX() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_EmbeddedPDF.pptx");
Metadata pdfMetadata1 = metadataList.get(4);
- assertContains("Apache Tika", pdfMetadata1.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Apache Tika", pdfMetadata1.get(TikaCoreProperties.TIKA_CONTENT));
Metadata pdfMetadata2 = metadataList.get(5);
- assertContains("Hello World", pdfMetadata2.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World", pdfMetadata2.get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
public void testEmbeddedPDFInXLSX() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testExcel_embeddedPDF.xlsx");
Metadata pdfMetadata = metadataList.get(1);
- assertContains("Hello World", pdfMetadata.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World", pdfMetadata.get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -53,9 +53,9 @@ public class OOXMLParserTest extends TikaTest {
List<Metadata> metadataList = getRecursiveMetadata("testPPT_EmbeddedPDF.pptx", parseContext);
Metadata pdfMetadata1 = metadataList.get(4);
- assertContains("Apache Tika", pdfMetadata1.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Apache Tika", pdfMetadata1.get(TikaCoreProperties.TIKA_CONTENT));
Metadata pdfMetadata2 = metadataList.get(5);
- assertContains("Hello World", pdfMetadata2.get(RecursiveParserWrapper.TIKA_CONTENT));
+ assertContains("Hello World", pdfMetadata2.get(TikaCoreProperties.TIKA_CONTENT));
}
@Ignore("TODO figure out why this doesn't work")
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java
index bbd5a64..c474240 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java
@@ -24,7 +24,6 @@ import org.apache.tika.metadata.RTFMetadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.RecursiveParserWrapper;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.Assert;
@@ -77,7 +76,7 @@ public class RTFParserTest extends TikaTest {
//directory: _1457338524/HW.txt
Assert.assertEquals("filename equals ",
p.fileName, FilenameUtils.getName(
- metadata.get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH)));
+ metadata.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH)));
assertEquals(p.mimeType, metadata.get(Metadata.CONTENT_TYPE));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mock/MockParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mock/MockParserTest.java
index 6026118..c5c8d3c 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mock/MockParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/mock/MockParserTest.java
@@ -26,7 +26,6 @@ import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintStream;
-import java.util.Date;
import org.apache.commons.io.IOUtils;
import org.apache.tika.TikaTest;
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
index 40778f1..c53cb86 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
@@ -17,27 +17,20 @@
package org.apache.tika.parser.ocr;
import static org.junit.Assert.assertEquals;
-import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
import static org.junit.Assume.assumeTrue;
-import java.io.InputStream;
import java.util.List;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
import org.apache.tika.TikaTest;
-import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.DefaultParser;
import org.apache.tika.parser.ParseContext;
-import org.apache.tika.parser.Parser;
import org.apache.tika.parser.external.ExternalParser;
import org.apache.tika.parser.image.ImageParser;
import org.apache.tika.parser.pdf.PDFParserConfig;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.junit.Assert;
import org.junit.Assume;
@@ -156,7 +149,7 @@ public class TesseractOCRParserTest extends TikaTest {
StringBuilder contents = new StringBuilder();
for (Metadata m : metadataList) {
- contents.append(m.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ contents.append(m.get(TikaCoreProperties.TIKA_CONTENT));
}
for (String needle : nonOCRContains) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
index fbf5df0..7bd8244 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
@@ -24,7 +24,6 @@ import org.apache.tika.metadata.PagedText;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.Parser;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.junit.BeforeClass;
import org.junit.Test;
import org.xml.sax.SAXException;
@@ -50,7 +49,7 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<p>Hello dear user,</p>",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.text",
parent.get(Metadata.CONTENT_TYPE));
@@ -61,12 +60,12 @@ public class ODFParserTest extends TikaTest {
Metadata macro1 = metadataList.get(1);
assertEquals("MACRO", macro1.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro1.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro1.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test", macro1.get(TikaCoreProperties.RESOURCE_NAME_KEY));
Metadata macro2 = metadataList.get(2);
assertEquals("MACRO", macro2.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 1 Then", macro2.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 1 Then", macro2.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test2", macro2.get(TikaCoreProperties.RESOURCE_NAME_KEY));
Metadata image = metadataList.get(3);
@@ -97,13 +96,13 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<tr>",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.spreadsheet",
parent.get(Metadata.CONTENT_TYPE));
Metadata macro = metadataList.get(1);
assertEquals("MACRO", macro.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test1", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
Metadata image = metadataList.get(2);
@@ -117,7 +116,7 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<p",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.presentation",
parent.get(Metadata.CONTENT_TYPE));
//make sure metadata came through
@@ -128,7 +127,7 @@ public class ODFParserTest extends TikaTest {
Metadata macro = metadataList.get(1);
assertEquals("MACRO", macro.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("testmodule", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
assertEquals("testmodule", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
@@ -141,7 +140,7 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<p>Hello dear user,</p>",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.flat.text",
parent.get(Metadata.CONTENT_TYPE));
@@ -152,7 +151,7 @@ public class ODFParserTest extends TikaTest {
Metadata macro = metadataList.get(1);
assertEquals("MACRO", macro.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
Metadata image = metadataList.get(2);
@@ -174,13 +173,13 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<tr>",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.flat.spreadsheet",
parent.get(Metadata.CONTENT_TYPE));
Metadata macro = metadataList.get(1);
assertEquals("MACRO", macro.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test1", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
Metadata image = metadataList.get(2);
@@ -194,7 +193,7 @@ public class ODFParserTest extends TikaTest {
Metadata parent = metadataList.get(0);
assertContains("<p",
- parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ parent.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("application/vnd.oasis.opendocument.flat.presentation",
parent.get(Metadata.CONTENT_TYPE));
//make sure metadata came through
@@ -205,7 +204,7 @@ public class ODFParserTest extends TikaTest {
Metadata macro = metadataList.get(1);
assertEquals("MACRO", macro.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE_KEY));
- assertContains("If WsGQFM Or 2 Then", macro.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("If WsGQFM Or 2 Then", macro.get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("test", macro.get(TikaCoreProperties.RESOURCE_NAME_KEY));
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 439a6ea..56721eb 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -32,9 +32,7 @@ import org.apache.tika.parser.Parser;
import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.ocr.TesseractOCRParser;
-import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.parser.xml.XMLProfiler;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.junit.AfterClass;
@@ -146,13 +144,13 @@ public class PDFParserTest extends TikaTest {
assertEquals("metadata size", 5, metadatas.size());
assertEquals("file name", "Test.txt", metadatas.get(1).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("os specific", metadatas.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("os specific", metadatas.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("file name", "TestMac.txt", metadatas.get(2).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("mac embedded", metadatas.get(2).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("mac embedded", metadatas.get(2).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("file name", "TestDos.txt", metadatas.get(3).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("dos embedded", metadatas.get(3).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("dos embedded", metadatas.get(3).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("file name", "TestUnix.txt", metadatas.get(4).get(TikaCoreProperties.RESOURCE_NAME_KEY));
- assertContains("unix embedded", metadatas.get(4).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("unix embedded", metadatas.get(4).get(TikaCoreProperties.TIKA_CONTENT));
}
@@ -280,7 +278,7 @@ public class PDFParserTest extends TikaTest {
List<Metadata> contents = getRecursiveMetadata("testPDFFileEmbInAnnotation_noContents.pdf",
NO_OCR());
assertEquals(2, contents.size());
- assertContains("This is a Excel", contents.get(1).get(RecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("This is a Excel", contents.get(1).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -322,7 +320,7 @@ public class PDFParserTest extends TikaTest {
List<Metadata> metadatas = getRecursiveMetadata("testPDF_JBIG2.pdf", context);
assertEquals(2, metadatas.size());
- assertContains("test images compressed using JBIG2", metadatas.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("test images compressed using JBIG2", metadatas.get(0).get(TikaCoreProperties.TIKA_CONTENT));
for (String key : metadatas.get(1).names()) {
if (key.startsWith("X-TIKA:EXCEPTION")) {
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressParserTest.java
index 21c2d4f..4bb12d2 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressParserTest.java
@@ -18,9 +18,6 @@ package org.apache.tika.parser.pkg;
import org.apache.tika.exception.TikaMemoryLimitException;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.pkg.AbstractPkgTest;
-import org.apache.tika.parser.pkg.TarParserTest;
-import org.apache.tika.parser.pkg.ZipParserTest;
import org.apache.tika.sax.BodyContentHandler;
import org.junit.Test;
import org.xml.sax.ContentHandler;
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressorParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressorParserTest.java
index 16dffa5..7b245a3 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressorParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/CompressorParserTest.java
@@ -21,8 +21,6 @@ package org.apache.tika.parser.pkg;
import org.apache.tika.TikaTest;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
-import org.junit.Ignore;
import org.junit.Test;
import java.util.List;
@@ -58,7 +56,7 @@ public class CompressorParserTest extends TikaTest {
metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, "testBROTLI_compressed.br");
List<Metadata> metadataList = getRecursiveMetadata("testBROTLI_compressed.br", metadata);
- assertContains("XXXXXXXXXXYYYYYYYYYY", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("XXXXXXXXXXYYYYYYYYYY", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
assertEquals("testBROTLI_compressed", metadataList.get(1).get(TikaCoreProperties.RESOURCE_NAME_KEY));
}
}
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/TarParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/TarParserTest.java
index 702a34c..561aac5 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/TarParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/TarParserTest.java
@@ -24,9 +24,6 @@ import org.xml.sax.ContentHandler;
import java.io.InputStream;
import static org.junit.Assert.assertEquals;
-import static org.junit.Assert.assertNotNull;
-import static org.junit.Assert.assertNull;
-import static org.junit.Assert.assertTrue;
/**
* Test case for parsing tar files.
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
index e375627..0da1e77 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-package/src/test/java/org/apache/tika/parser/pkg/ZipParserTest.java
@@ -20,7 +20,6 @@ import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.ParseContext;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BodyContentHandler;
import org.junit.Test;
import org.xml.sax.ContentHandler;
@@ -119,7 +118,7 @@ public class ZipParserTest extends AbstractPkgTest {
assertContains("EncryptedDocumentException: stream (encrypted.txt) is encrypted", values[0]);
- assertContains("hello world", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("hello world", metadataList.get(1).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
diff --git a/tika-parsers/tika-parsers-extended/tika-parsers-extended-integration-tests/src/test/java/org/apache/tika/parser/sqlite3/SQLite3ParserTest.java b/tika-parsers/tika-parsers-extended/tika-parsers-extended-integration-tests/src/test/java/org/apache/tika/parser/sqlite3/SQLite3ParserTest.java
index 7721210..3b56489 100644
--- a/tika-parsers/tika-parsers-extended/tika-parsers-extended-integration-tests/src/test/java/org/apache/tika/parser/sqlite3/SQLite3ParserTest.java
+++ b/tika-parsers/tika-parsers-extended/tika-parsers-extended-integration-tests/src/test/java/org/apache/tika/parser/sqlite3/SQLite3ParserTest.java
@@ -29,7 +29,6 @@ import org.apache.tika.parser.EmptyParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.RecursiveParserWrapper;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.sax.BasicContentHandlerFactory;
import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.apache.tika.sax.ToXMLContentHandler;
@@ -147,19 +146,19 @@ public class SQLite3ParserTest extends TikaTest {
assertEquals(5, metadataList.size());
//make sure the \t are inserted in a body handler
- String table = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String table = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("0\t2.3\t2.4\tlorem", table);
assertContains("普林斯顿大学", table);
//make sure the \n is inserted
- String table2 = metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String table2 = metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT);
assertContains("do eiusmod tempor\n", table2);
- assertContains("The quick brown fox", metadataList.get(2).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
- assertContains("The quick brown fox", metadataList.get(4).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertContains("The quick brown fox", metadataList.get(2).get(TikaCoreProperties.TIKA_CONTENT));
+ assertContains("The quick brown fox", metadataList.get(4).get(TikaCoreProperties.TIKA_CONTENT));
//confirm .doc was added to blob
- assertEquals("/BYTES_COL_0.doc/image1.png", metadataList.get(1).get(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH));
+ assertEquals("/BYTES_COL_0.doc/image1.png", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH));
}
@Test
diff --git a/tika-pipes/tika-emitters/tika-emitter-solr/src/test/java/org/apache/tika/emitter/solr/TestBasic.java b/tika-pipes/tika-emitters/tika-emitter-solr/src/test/java/org/apache/tika/emitter/solr/TestBasic.java
index 3df4c4a..62b8c87 100644
--- a/tika-pipes/tika-emitters/tika-emitter-solr/src/test/java/org/apache/tika/emitter/solr/TestBasic.java
+++ b/tika-pipes/tika-emitters/tika-emitter-solr/src/test/java/org/apache/tika/emitter/solr/TestBasic.java
@@ -22,7 +22,6 @@ import org.apache.tika.pipes.emitter.Emitter;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.filter.MetadataFilter;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.junit.Ignore;
import org.junit.Test;
@@ -41,14 +40,14 @@ public class TestBasic {
Metadata m1 = new Metadata();
m1.set("id", "1");
m1.set(Metadata.CONTENT_LENGTH, "314159");
- m1.set(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT, "the quick brown");
+ m1.set(TikaCoreProperties.TIKA_CONTENT, "the quick brown");
m1.set(TikaCoreProperties.TITLE, "this is the first title");
m1.add(TikaCoreProperties.CREATOR, "firstAuthor");
m1.add(TikaCoreProperties.CREATOR, "secondAuthor");
Metadata m2 = new Metadata();
- m2.set(AbstractRecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/path_to_this.txt");
- m2.set(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT, "fox jumped over the lazy");
+ m2.set(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/path_to_this.txt");
+ m2.set(TikaCoreProperties.TIKA_CONTENT, "fox jumped over the lazy");
MetadataFilter filter = tikaConfig.getMetadataFilter();
filter.filter(m1);
filter.filter(m2);
diff --git a/tika-serialization/src/main/java/org/apache/tika/metadata/serialization/JsonMetadataList.java b/tika-serialization/src/main/java/org/apache/tika/metadata/serialization/JsonMetadataList.java
index 0fd8098..dea6faf 100644
--- a/tika-serialization/src/main/java/org/apache/tika/metadata/serialization/JsonMetadataList.java
+++ b/tika-serialization/src/main/java/org/apache/tika/metadata/serialization/JsonMetadataList.java
@@ -28,7 +28,7 @@ import com.google.gson.JsonIOException;
import com.google.gson.reflect.TypeToken;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
public class JsonMetadataList extends JsonMetadataBase {
@@ -79,9 +79,9 @@ public class JsonMetadataList extends JsonMetadataBase {
//flip it to be the first element.
if (ms.size() > 1) {
Metadata last = ms.get(ms.size()-1);
- String embResourcePath = last.get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH);
+ String embResourcePath = last.get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH);
if (embResourcePath == null &&
- ms.get(0).get(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH) != null) {
+ ms.get(0).get(TikaCoreProperties.EMBEDDED_RESOURCE_PATH) != null) {
ms.add(0, ms.remove(ms.size()-1));
}
}
diff --git a/tika-serialization/src/test/java/org/apache/tika/metadata/serialization/JsonMetadataListTest.java b/tika-serialization/src/test/java/org/apache/tika/metadata/serialization/JsonMetadataListTest.java
index 427e598..522807e 100644
--- a/tika-serialization/src/test/java/org/apache/tika/metadata/serialization/JsonMetadataListTest.java
+++ b/tika-serialization/src/test/java/org/apache/tika/metadata/serialization/JsonMetadataListTest.java
@@ -29,7 +29,7 @@ import java.util.LinkedList;
import java.util.List;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
+import org.apache.tika.metadata.TikaCoreProperties;
import org.junit.Test;
public class JsonMetadataListTest {
@@ -143,7 +143,7 @@ public class JsonMetadataListTest {
m1.add("k1", "v4");
m1.add("k1", "v4");
m1.add("k2", "v1");
- m1.add(RecursiveParserWrapperHandler.EMBEDDED_RESOURCE_PATH, "/embedded-1");
+ m1.add(TikaCoreProperties.EMBEDDED_RESOURCE_PATH, "/embedded-1");
Metadata m2 = new Metadata();
m2.add("k3", "v1");
diff --git a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/FetcherTest.java b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/FetcherTest.java
index 2343d4a..1760225 100644
--- a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/FetcherTest.java
+++ b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/FetcherTest.java
@@ -21,12 +21,10 @@ import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.cxf.jaxrs.JAXRSServerFactoryBean;
import org.apache.cxf.jaxrs.client.WebClient;
import org.apache.cxf.jaxrs.lifecycle.SingletonResourceProvider;
-import org.apache.tika.TikaTest;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.serialization.JsonMetadataList;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.server.core.CXFTestBase;
import org.apache.tika.server.core.FetcherStreamFactory;
import org.apache.tika.server.core.InputStreamFactory;
@@ -90,7 +88,7 @@ public class FetcherTest extends CXFTestBase {
Reader reader = new InputStreamReader(new GzipCompressorInputStream((InputStream) response.getEntity()), UTF_8);
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
Metadata parent = metadataList.get(0);
- String txt = parent.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT);
+ String txt = parent.get(TikaCoreProperties.TIKA_CONTENT);
assertContains("toolkit detects and extracts metadata", txt);
assertEquals("Apache Tika – Apache Tika", parent.get(TikaCoreProperties.TITLE));
}
diff --git a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/RecursiveMetadataResourceTest.java b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/RecursiveMetadataResourceTest.java
index b9db2e5..6b911c5 100644
--- a/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/RecursiveMetadataResourceTest.java
+++ b/tika-server/tika-server-classic/src/test/java/org/apache/tika/server/classic/RecursiveMetadataResourceTest.java
@@ -45,8 +45,6 @@ import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.OfficeOpenXMLExtended;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.serialization.JsonMetadataList;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
-import org.apache.tika.sax.RecursiveParserWrapperHandler;
import org.apache.tika.server.core.CXFTestBase;
import org.apache.tika.server.core.resource.RecursiveMetadataResource;
import org.apache.tika.server.core.writer.MetadataListMessageBodyWriter;
@@ -178,7 +176,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertNotNull(metadataList.get(0).get(TikaCoreProperties.CREATOR));
- assertContains("org.apache.tika.exception.EncryptedDocumentException", metadataList.get(0).get(RecursiveParserWrapperHandler.CONTAINER_EXCEPTION));
+ assertContains("org.apache.tika.exception.EncryptedDocumentException", metadataList.get(0).get(TikaCoreProperties.CONTAINER_EXCEPTION));
// Try again, this time with the password
response = WebClient
.create(endPoint + META_PATH)
@@ -209,7 +207,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
Reader reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- String content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ String content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//extra slash
@@ -221,7 +219,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//unparseable
@@ -233,7 +231,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//xml
@@ -245,7 +243,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//text
@@ -257,7 +255,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("embed_3"));
//ignore
@@ -269,7 +267,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- assertNull(metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertNull(metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT));
}
@@ -288,7 +286,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
Reader reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- String content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ String content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//unparseable
@@ -304,7 +302,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//xml
@@ -320,7 +318,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("<html xmlns=\"http://www.w3.org/1999/xhtml\">"));
//text
@@ -336,7 +334,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- content = metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim();
+ content = metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT).trim();
assertTrue(content.startsWith("embed_3"));
//ignore -- no content
@@ -352,7 +350,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- assertNull(metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ assertNull(metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT));
}
@Test
@@ -388,7 +386,7 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
Reader reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
assertEquals(1, metadataList.size());
- assertEquals("true", metadataList.get(0).get(AbstractRecursiveParserWrapperHandler.WRITE_LIMIT_REACHED));
+ assertEquals("true", metadataList.get(0).get(TikaCoreProperties.WRITE_LIMIT_REACHED));
//now try with a write limit of 100
writeLimit = 100;
@@ -404,11 +402,11 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
metadataList = JsonMetadataList.fromJson(reader);
assertEquals(12, metadataList.size());
- assertEquals("true", metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.WRITE_LIMIT_REACHED));
+ assertEquals("true", metadataList.get(6).get(TikaCoreProperties.WRITE_LIMIT_REACHED));
assertContains("When in the Course of human events it becomes necessary for one people",
- metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT));
TikaTest.assertNotContained("to dissolve",
- metadataList.get(6).get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT));
+ metadataList.get(6).get(TikaCoreProperties.TIKA_CONTENT));
}
}
diff --git a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/EmitterResource.java b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/EmitterResource.java
index 7f116fa..9752608 100644
--- a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/EmitterResource.java
+++ b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/EmitterResource.java
@@ -23,11 +23,9 @@ import com.google.gson.JsonParser;
import org.apache.tika.pipes.emitter.Emitter;
import org.apache.tika.pipes.emitter.TikaEmitterException;
import org.apache.tika.exception.TikaException;
-import org.apache.tika.pipes.fetcher.FetchId;
import org.apache.tika.pipes.fetcher.Fetcher;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.utils.ExceptionUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -105,7 +103,7 @@ public class EmitterResource {
* fetcher, use the get or post options.
* <p>
* The extracted text content is stored with the key
- * {@link org.apache.tika.sax.AbstractRecursiveParserWrapperHandler#TIKA_CONTENT}
+ * {@link TikaCoreProperties#TIKA_CONTENT}
* <p>
* Must specify an emitter in the path, e.g. /emit/solr
* @param info uri info
@@ -141,7 +139,7 @@ public class EmitterResource {
* through of metadata from the client.
* <p>
* The extracted text content is stored with the key
- * {@link AbstractRecursiveParserWrapperHandler#TIKA_CONTENT}
+ * {@link TikaCoreProperties#TIKA_CONTENT}
* <p>
* Must specify a fetcherString and an emitter in the posted json.
* @param info uri info
@@ -229,7 +227,7 @@ public class EmitterResource {
statusMap.put("emitter_exception", exceptionMsg);
}
String parseStackTrace = metadataList.get(0).get(
- AbstractRecursiveParserWrapperHandler.CONTAINER_EXCEPTION);
+ TikaCoreProperties.CONTAINER_EXCEPTION);
if (parseStackTrace != null) {
statusMap.put("parse_exception", parseStackTrace);
}
diff --git a/tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/TikaEmitterTest.java b/tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/TikaEmitterTest.java
index 0631eef..4e41d2f 100644
--- a/tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/TikaEmitterTest.java
+++ b/tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/TikaEmitterTest.java
@@ -22,17 +22,14 @@ import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import com.google.gson.JsonPrimitive;
import org.apache.commons.io.FileUtils;
-import org.apache.commons.io.IOUtils;
import org.apache.cxf.jaxrs.JAXRSServerFactoryBean;
import org.apache.cxf.jaxrs.client.WebClient;
import org.apache.cxf.jaxrs.lifecycle.ResourceProvider;
import org.apache.cxf.jaxrs.lifecycle.SingletonResourceProvider;
-import org.apache.tika.TikaTest;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.serialization.JsonMetadataList;
-import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
import org.apache.tika.server.core.resource.EmitterResource;
import org.apache.tika.server.core.writer.JSONObjWriter;
import org.junit.AfterClass;
@@ -45,7 +42,6 @@ import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
-import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Path;
@@ -162,7 +158,7 @@ public class TikaEmitterTest extends CXFTestBase {
assertEquals(1, metadataList.size());
Metadata metadata = metadataList.get(0);
assertEquals("hello world",
- metadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim());
+ metadata.get(TikaCoreProperties.TIKA_CONTENT).trim());
assertEquals("Nikolai Lobachevsky", metadata.get("author"));
assertEquals("你好，世界", metadata.get("title"));
assertEquals("application/mock+xml", metadata.get(Metadata.CONTENT_TYPE));
@@ -201,7 +197,7 @@ public class TikaEmitterTest extends CXFTestBase {
assertEquals(1, metadataList.size());
Metadata metadata = metadataList.get(0);
assertEquals("hello world",
- metadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim());
+ metadata.get(TikaCoreProperties.TIKA_CONTENT).trim());
assertEquals("Nikolai Lobachevsky", metadata.get("author"));
assertEquals("你好，世界", metadata.get("title"));
assertEquals("application/mock+xml", metadata.get(Metadata.CONTENT_TYPE));
@@ -231,7 +227,7 @@ public class TikaEmitterTest extends CXFTestBase {
assertEquals(1, metadataList.size());
Metadata metadata = metadataList.get(0);
assertEquals("hello world",
- metadata.get(AbstractRecursiveParserWrapperHandler.TIKA_CONTENT).trim());
+ metadata.get(TikaCoreProperties.TIKA_CONTENT).trim());
assertEquals("Nikolai Lobachevsky", metadata.get("author"));
assertEquals("你好，世界", metadata.get("title"));
assertEquals("application/mock+xml", metadata.get(Metadata.CONTENT_TYPE));
@@ -281,7 +277,7 @@ public class TikaEmitterTest extends CXFTestBase {
assertEquals("application/mock+xml", metadata.get(Metadata.CONTENT_TYPE));
assertEquals("my-value", metadata.get("my-key"));
assertArrayEquals(valueArray, metadata.getValues("my-key-multi"));
- assertContains("NullPointerException", metadata.get(AbstractRecursiveParserWrapperHandler.CONTAINER_EXCEPTION));
+ assertContains("NullPointerException", metadata.get(TikaCoreProperties.CONTAINER_EXCEPTION));
}
//can't test system_exit here because server is in same process