stringTaggingSeparators)
@@ -188,14 +189,21 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
* the taggable property should still contain raw string values.
*
* Mixing of NodeRefs and string values is permitted so each raw value is
- * checked for a valid NodeRef representation and if so, converts to a NodeRef,
+ * checked for a valid NodeRef representation and if so, converts to a NodeRef,
* if not, adds as a tag via the {@link TaggingService}.
- *
+ *
* @param actionedUponNodeRef The NodeRef being actioned upon
* @param propertyDef the PropertyDefinition of the taggable property
* @param rawValue the raw value from the metadata extracter
*/
protected void addTags(NodeRef actionedUponNodeRef, PropertyDefinition propertyDef, Serializable rawValue)
+ {
+ addTags(actionedUponNodeRef, propertyDef, rawValue, nodeService, stringTaggingSeparators, taggingService);
+ }
+
+ private static void addTags(NodeRef actionedUponNodeRef, PropertyDefinition propertyDef, Serializable rawValue,
+ NodeService nodeService, List stringTaggingSeparators,
+ TaggingService taggingService)
{
if (rawValue == null)
{
@@ -231,7 +239,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
logger.trace("adding string tag name'" + tagName + "' (from tag nodeRef "+nodeRef+") to " + actionedUponNodeRef);
}
- tags.addAll(splitTag(tagName));
+ tags.addAll(splitTag(tagName, stringTaggingSeparators));
}
catch (InvalidNodeRefException e)
{
@@ -250,7 +258,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
logger.trace("adding string tag name'" + singleValue + "' to " + actionedUponNodeRef);
}
- tags.addAll(splitTag((String)singleValue));
+ tags.addAll(splitTag((String)singleValue, stringTaggingSeparators));
}
}
else if (singleValue instanceof NodeRef)
@@ -263,7 +271,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
logger.trace("adding string tag name'" + tagName + "' (for nodeRef "+nodeRef+") to " + actionedUponNodeRef);
}
- tags.addAll(splitTag(tagName));
+ tags.addAll(splitTag(tagName, stringTaggingSeparators));
}
}
}
@@ -273,8 +281,8 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
{
logger.trace("adding string tag name'" + (String)rawValue + "' to " + actionedUponNodeRef);
}
-
- tags.addAll(splitTag((String)rawValue));
+
+ tags.addAll(splitTag((String)rawValue, stringTaggingSeparators));
}
if (logger.isDebugEnabled())
@@ -297,6 +305,11 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
}
protected List splitTag(String str)
+ {
+ return splitTag(str, stringTaggingSeparators);
+ }
+
+ private static List splitTag(String str, List stringTaggingSeparators)
{
List result = new ArrayList<>();
if ((str != null) && (!str.equals("")))
@@ -323,7 +336,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
return result;
}
-
+
/**
* @see org.alfresco.repo.action.executer.ActionExecuter#execute(Action,
* NodeRef)
@@ -347,7 +360,8 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
return;
}
String mimetype = reader.getMimetype();
- MetadataExtracter extracter = metadataExtracterRegistry.getExtracter(mimetype);
+ long sourceSizeInBytes = reader.getSize();
+ MetadataExtracter extracter = metadataExtracterRegistry.getExtractor(mimetype, sourceSizeInBytes);
if (extracter == null)
{
if(logger.isDebugEnabled())
@@ -372,6 +386,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
try
{
modifiedProperties = extracter.extract(
+ actionedUponNodeRef,
reader,
/*OverwritePolicy.PRAGMATIC,*/
nodeProperties);
@@ -408,11 +423,22 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
{
return;
}
-
+
+ addExtractedMetadataToNode(actionedUponNodeRef, nodeProperties, modifiedProperties,
+ nodeService, dictionaryService, taggingService, enableStringTagging, carryAspectProperties,
+ stringTaggingSeparators);
+ }
+
+ public static void addExtractedMetadataToNode(NodeRef actionedUponNodeRef, Map nodeProperties,
+ Map modifiedProperties,
+ NodeService nodeService, DictionaryService dictionaryService,
+ TaggingService taggingService, boolean enableStringTagging,
+ boolean carryAspectProperties, List stringTaggingSeparators)
+ {
// Check that all properties have the appropriate aspect applied
Set requiredAspectQNames = new HashSet(3);
Set aspectPropertyQNames = new HashSet(17);
-
+
/**
* The modified properties contain null values as well. As we are only interested
* in the keys, this will force aspect aspect properties to be removed even if there
@@ -432,9 +458,10 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
if (enableStringTagging && propertyContainerDef.getName().equals(ContentModel.ASPECT_TAGGABLE))
{
Serializable oldValue = nodeProperties.get(propertyQName);
- addTags(actionedUponNodeRef, propertyDef, oldValue);
+ addTags(actionedUponNodeRef, propertyDef, oldValue,
+ nodeService, stringTaggingSeparators, taggingService);
// Replace the raw value with the created tag NodeRefs
- nodeProperties.put(ContentModel.PROP_TAGS,
+ nodeProperties.put(ContentModel.PROP_TAGS,
nodeService.getProperty(actionedUponNodeRef, ContentModel.PROP_TAGS));
}
else
@@ -447,7 +474,7 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
}
}
}
-
+
if (!carryAspectProperties)
{
// Remove any node properties that are defined on the aspects but were not extracted
@@ -465,10 +492,14 @@ public class ContentMetadataExtracter extends ActionExecuterAbstractBase
}
}
}
-
+
+ // The following code can result in a postCommit to extract the metadata again via JavaBehaviour
+ // (such as ImapContentPolicy.onAddAspect). Not very efficient, but I cannot think of a way to
+ // avoid it that does not risk memory leaks or disabling behaviour we want.
+
// Add all the properties to the node BEFORE we add the aspects
nodeService.setProperties(actionedUponNodeRef, nodeProperties);
-
+
// Add each of the aspects, as required
for (QName requiredAspectQName : requiredAspectQNames)
{
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/AbstractMappingMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/AbstractMappingMetadataExtracter.java
index 78865f8768..ece13df5b5 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/AbstractMappingMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/AbstractMappingMetadataExtracter.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -25,6 +25,33 @@
*/
package org.alfresco.repo.content.metadata;
+import org.alfresco.api.AlfrescoPublicApi;
+import org.alfresco.error.AlfrescoRuntimeException;
+import org.alfresco.model.ContentModel;
+import org.alfresco.repo.content.StreamAwareContentReaderProxy;
+import org.alfresco.service.cmr.dictionary.DataTypeDefinition;
+import org.alfresco.service.cmr.dictionary.DictionaryService;
+import org.alfresco.service.cmr.dictionary.PropertyDefinition;
+import org.alfresco.service.cmr.repository.ContentIOException;
+import org.alfresco.service.cmr.repository.ContentReader;
+import org.alfresco.service.cmr.repository.ContentWriter;
+import org.alfresco.service.cmr.repository.MalformedNodeRefException;
+import org.alfresco.service.cmr.repository.MimetypeService;
+import org.alfresco.service.cmr.repository.NodeRef;
+import org.alfresco.service.cmr.repository.datatype.DefaultTypeConverter;
+import org.alfresco.service.cmr.repository.datatype.TypeConversionException;
+import org.alfresco.service.namespace.InvalidQNameException;
+import org.alfresco.service.namespace.QName;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.joda.time.DateTime;
+import org.joda.time.format.DateTimeFormat;
+import org.joda.time.format.DateTimeFormatter;
+import org.springframework.beans.factory.BeanNameAware;
+import org.springframework.context.ApplicationContext;
+import org.springframework.context.ApplicationContextAware;
+import org.springframework.extensions.surf.util.ISO8601DateFormat;
+
import java.io.InputStream;
import java.io.Serializable;
import java.lang.reflect.Array;
@@ -50,32 +77,6 @@ import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.concurrent.atomic.AtomicInteger;
-import org.alfresco.api.AlfrescoPublicApi;
-import org.alfresco.error.AlfrescoRuntimeException;
-import org.alfresco.model.ContentModel;
-import org.alfresco.repo.content.StreamAwareContentReaderProxy;
-import org.alfresco.service.cmr.dictionary.DataTypeDefinition;
-import org.alfresco.service.cmr.dictionary.DictionaryService;
-import org.alfresco.service.cmr.dictionary.PropertyDefinition;
-import org.alfresco.service.cmr.repository.ContentIOException;
-import org.alfresco.service.cmr.repository.ContentReader;
-import org.alfresco.service.cmr.repository.ContentWriter;
-import org.alfresco.service.cmr.repository.MalformedNodeRefException;
-import org.alfresco.service.cmr.repository.MimetypeService;
-import org.alfresco.service.cmr.repository.datatype.DefaultTypeConverter;
-import org.alfresco.service.cmr.repository.datatype.TypeConversionException;
-import org.alfresco.service.namespace.InvalidQNameException;
-import org.alfresco.service.namespace.QName;
-import org.apache.commons.logging.Log;
-import org.apache.commons.logging.LogFactory;
-import org.joda.time.DateTime;
-import org.joda.time.format.DateTimeFormat;
-import org.joda.time.format.DateTimeFormatter;
-import org.springframework.beans.factory.BeanNameAware;
-import org.springframework.context.ApplicationContext;
-import org.springframework.context.ApplicationContextAware;
-import org.springframework.extensions.surf.util.ISO8601DateFormat;
-
/**
* Support class for metadata extracters that support dynamic and config-driven
* mapping between extracted values and model properties. Extraction is broken
@@ -131,7 +132,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
private MetadataExtracterRegistry registry;
private MimetypeService mimetypeService;
- private DictionaryService dictionaryService;
+ protected DictionaryService dictionaryService;
private boolean initialized;
private Set supportedMimetypes;
@@ -232,6 +233,11 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
this.dictionaryService = dictionaryService;
}
+ public Set getSupportedMimetypes()
+ {
+ return supportedMimetypes;
+ }
+
/**
* Set the mimetypes that are supported by the extracter.
*
@@ -278,7 +284,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
return supportedEmbedMimetypes.contains(sourceMimetype);
}
- private boolean isEnabled(String mimetype)
+ protected boolean isEnabled(String mimetype)
{
return properties == null || mimetypeService == null ||
(getBooleanProperty(beanName+".enabled", true) &&
@@ -714,10 +720,10 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
return readMappingProperties(mappingProperties.entrySet());
}
-
+
/**
* A utility method to convert mapping properties entries to the Map form.
- *
+ *
* @see #setMappingProperties(Properties)
*/
private Map> readMappingProperties(Set> mappingPropertiesEntries)
@@ -765,8 +771,8 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
throw new AlfrescoRuntimeException(
"No prefix mapping for extracter property mapping: \n" +
- " Extracter: " + this + "\n" +
- " Mapping: " + entry);
+ " Extracter: " + this + "\n" +
+ " Mapping: " + entry);
}
qnameStr = QName.NAMESPACE_BEGIN + uri + QName.NAMESPACE_END + suffix;
}
@@ -780,8 +786,8 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
throw new AlfrescoRuntimeException(
"Can't create metadata extracter property mapping: \n" +
- " Extracter: " + this + "\n" +
- " Mapping: " + entry);
+ " Extracter: " + this + "\n" +
+ " Mapping: " + entry);
}
}
if (logger.isTraceEnabled())
@@ -1132,7 +1138,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
@Override
public final Map extract(ContentReader reader, Map destination)
{
- return extract(reader, this.overwritePolicy, destination, this.mapping);
+ return extract(null, reader, this.overwritePolicy, destination, this.mapping);
}
/**
@@ -1144,7 +1150,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
OverwritePolicy overwritePolicy,
Map destination)
{
- return extract(reader, overwritePolicy, destination, this.mapping);
+ return extract(null, reader, overwritePolicy, destination, this.mapping);
}
/**
@@ -1156,6 +1162,29 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
OverwritePolicy overwritePolicy,
Map destination,
Map> mapping)
+ {
+ return extract(null, reader, overwritePolicy, destination, mapping);
+ }
+
+ /**
+ * {@inheritDoc}
+ */
+ @Override
+ public Map extract(NodeRef nodeRef, ContentReader reader, Map destination)
+ {
+ return extract(nodeRef, reader, overwritePolicy, destination, mapping);
+ }
+
+ /**
+ * {@inheritDoc}
+ */
+ @Override
+ public Map extract(
+ NodeRef nodeRef,
+ ContentReader reader,
+ OverwritePolicy overwritePolicy,
+ Map destination,
+ Map> mapping)
{
// Done
if (logger.isDebugEnabled())
@@ -1182,12 +1211,13 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
// Check that the content has some meat
if (reader.getSize() > 0 && reader.exists())
{
- rawMetadata = extractRaw(reader, getLimits(reader.getMimetype()));
+ rawMetadata = extractRaw(nodeRef, reader, getLimits(reader.getMimetype()));
}
else
{
rawMetadata = new HashMap(1);
}
+
// Convert to system properties (standalone)
Map systemProperties = mapRawToSystem(rawMetadata);
// Convert the properties according to the dictionary types
@@ -1215,7 +1245,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
// the current mime type is plausible
String typeErrorMessage = null;
String differentType = null;
- if(mimetypeService != null)
+ if (mimetypeService != null)
{
differentType = mimetypeService.getMimetypeIfNotMatches(reader.getReader());
}
@@ -1224,7 +1254,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
logger.info("Unable to verify mimetype of " + reader.getReader() +
" as no MimetypeService available to " + getClass().getName());
}
- if(differentType != null)
+ if (differentType != null)
{
typeErrorMessage = "\n" +
" claimed mime type: " + reader.getMimetype() + "\n" +
@@ -1285,6 +1315,19 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
Map properties,
ContentReader reader,
ContentWriter writer)
+ {
+ embed(null, properties, reader, writer);
+ }
+
+ /**
+ * {@inheritDoc}
+ */
+ @Override
+ public void embed(
+ NodeRef nodeRef,
+ Map properties,
+ ContentReader reader,
+ ContentWriter writer)
{
// Done
if (logger.isDebugEnabled())
@@ -1307,7 +1350,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
try
{
- embedInternal(mapSystemToRaw(properties), reader, writer);
+ embedInternal(nodeRef, mapSystemToRaw(properties), reader, writer);
if(logger.isDebugEnabled())
{
logger.debug("Embedded Metadata into " + writer);
@@ -1472,7 +1515,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
* @return Returns a modified map of properties that have been converted.
*/
@SuppressWarnings("unchecked")
- private Map convertSystemPropertyValues(Map systemProperties)
+ protected Map convertSystemPropertyValues(Map systemProperties)
{
Map convertedProperties = new HashMap(systemProperties.size() + 7);
for (Map.Entry entry : systemProperties.entrySet())
@@ -1500,6 +1543,10 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
convertedPropertyValue = propertyValue;
}
+ else if (propertyValue instanceof Long)
+ {
+ convertedPropertyValue = new Date((Long)propertyValue);
+ }
else if (propertyValue instanceof Collection)
{
convertedPropertyValue = (Serializable) makeDates((Collection) propertyValue);
@@ -1518,7 +1565,9 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
StringBuilder mesg = new StringBuilder();
mesg.append("Unable to convert Date property: ").append(propertyQName)
- .append(", value: ").append(propertyValue).append(", type: ").append(propertyTypeDef.getName());
+ .append(", value: ").append(propertyValue).append(" (")
+ .append(propertyValue.getClass().getSimpleName())
+ .append("), type: ").append(propertyTypeDef.getName());
logger.warn(mesg.toString());
}
}
@@ -1688,6 +1737,21 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
}
}
+ // Try milliseconds. This was introduced with T-Engine extractors. Previously Dates would have been
+ // created and then converted to a Alfresco Date property in a single operation. T-Engines do not know
+ // about Alfresco Date property formats.
+ try
+ {
+ long ms = Long.parseLong(dateStr);
+ if (Long.toString(ms).equals(dateStr))
+ {
+ date = new Date(ms);
+ }
+ }
+ catch (NumberFormatException ignore)
+ {
+ }
+
if (date == null)
{
// Still no luck
@@ -1982,7 +2046,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
return limits;
}
-
+
/**
* Callable wrapper for the
* {@link AbstractMappingMetadataExtracter#extractRaw(ContentReader)} method
@@ -2026,7 +2090,7 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
/**
* Exception wrapper to handle exceeded limits imposed by {@link MetadataExtracterLimits}
- * {@link AbstractMappingMetadataExtracter#extractRaw(ContentReader, MetadataExtracterLimits)}
+ * {@link AbstractMappingMetadataExtracter#extractRaw(NodeRef, ContentReader, MetadataExtracterLimits)}
*/
private class LimitExceededException extends Exception
{
@@ -2047,19 +2111,17 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
*
* If no timeout limit is defined or is unlimited (-1),
* the extractRaw method is called directly.
- *
+ *
+ * @param nodeRef the node being acted on.
* @param reader the document to extract the values from. This stream provided by
* the reader must be closed if accessed directly.
* @param limits the limits to impose on the extraction
* @return Returns a map of document property values keyed by property name.
* @throws Throwable All exception conditions can be handled.
*/
- private Map extractRaw(
+ private Map extractRaw(NodeRef nodeRef,
ContentReader reader, MetadataExtracterLimits limits) throws Throwable
{
- FutureTask> task = null;
- StreamAwareContentReaderProxy proxiedReader = null;
-
if (reader.getSize() > limits.getMaxDocumentSizeMB() * MEGABYTE_SIZE)
{
throw new LimitExceededException("Max doc size exceeded " + limits.getMaxDocumentSizeMB() + " MB");
@@ -2084,7 +2146,16 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
throw new LimitExceededException("Reached concurrent extractions limit - " + limits.getMaxConcurrentExtractionsCount());
}
}
-
+
+ return extractRawInThread(nodeRef, reader, limits);
+ }
+
+ protected Map extractRawInThread(NodeRef nodeRef, ContentReader reader,
+ MetadataExtracterLimits limits)
+ throws Throwable
+ {
+ FutureTask> task = null;
+ StreamAwareContentReaderProxy proxiedReader = null;
try
{
proxiedReader = new StreamAwareContentReaderProxy(reader);
@@ -2119,14 +2190,19 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
}
finally
{
- int totalDocCount = CONCURRENT_EXTRACTIONS_COUNT.decrementAndGet();
- if (logger.isDebugEnabled())
- {
- logger.debug("Extraction finalized. Remaining concurrent extraction : " + totalDocCount);
- }
+ extractRawThreadFinished();
}
}
-
+
+ protected void extractRawThreadFinished()
+ {
+ int totalDocCount = CONCURRENT_EXTRACTIONS_COUNT.decrementAndGet();
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Extraction finalized. Remaining concurrent extraction : " + totalDocCount);
+ }
+ }
+
/**
* Override to provide the raw extracted metadata values. An extracter should extract
* as many of the available properties as is realistically possible. Even if the
@@ -2162,6 +2238,11 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
*/
protected abstract Map extractRaw(ContentReader reader) throws Throwable;
+ protected void embedInternal(NodeRef nodeRef, Map metadata, ContentReader reader, ContentWriter writer) throws Throwable
+ {
+ embedInternal(metadata, reader, writer);
+ }
+
/**
* Override to embed metadata values. An extracter should embed
* as many of the available properties as is realistically possible. Even if the
@@ -2182,4 +2263,46 @@ abstract public class AbstractMappingMetadataExtracter implements MetadataExtrac
{
// TODO make this an abstract method once more extracters support embedding
}
+
+ // Originally in TikaPoweredMetadataExtracter
+ public static Map convertMetadataToStrings(Map properties)
+ {
+ Map propertiesAsStrings = new HashMap<>();
+ for (String metadataKey : properties.keySet())
+ {
+ Serializable value = properties.get(metadataKey);
+ if (value == null)
+ {
+ continue;
+ }
+ if (value instanceof Collection)
+ {
+ for (Object singleValue : (Collection) value)
+ {
+ try
+ {
+ // Convert to a string value
+ propertiesAsStrings.put(metadataKey, DefaultTypeConverter.INSTANCE.convert(String.class, singleValue));
+ }
+ catch (TypeConversionException e)
+ {
+ TikaPoweredMetadataExtracter.logger.info("Could not convert " + metadataKey + ": " + e.getMessage());
+ }
+ }
+ }
+ else
+ {
+ try
+ {
+ // Convert to a string value
+ propertiesAsStrings.put(metadataKey, DefaultTypeConverter.INSTANCE.convert(String.class, value));
+ }
+ catch (TypeConversionException e)
+ {
+ TikaPoweredMetadataExtracter.logger.info("Could not convert " + metadataKey + ": " + e.getMessage());
+ }
+ }
+ }
+ return propertiesAsStrings;
+ }
}
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/AsynchronousExtractor.java b/repository/src/main/java/org/alfresco/repo/content/metadata/AsynchronousExtractor.java
new file mode 100644
index 0000000000..f2d9469bf6
--- /dev/null
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/AsynchronousExtractor.java
@@ -0,0 +1,537 @@
+/*
+ * #%L
+ * Alfresco Repository
+ * %%
+ * Copyright (C) 2020 Alfresco Software Limited
+ * %%
+ * This file is part of the Alfresco software.
+ * If the software was purchased under a paid Alfresco license, the terms of
+ * the paid license agreement will prevail. Otherwise, the software is
+ * provided under the following open source license terms:
+ *
+ * Alfresco is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Alfresco is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with Alfresco. If not, see .
+ * #L%
+ */
+package org.alfresco.repo.content.metadata;
+
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.core.type.TypeReference;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import org.alfresco.model.ContentModel;
+import org.alfresco.repo.action.executer.ContentMetadataExtracter;
+import org.alfresco.repo.content.transform.TransformerDebug;
+import org.alfresco.repo.rendition2.RenditionService2;
+import org.alfresco.repo.rendition2.TransformDefinition;
+import org.alfresco.repo.security.authentication.AuthenticationUtil;
+import org.alfresco.service.cmr.repository.ContentReader;
+import org.alfresco.service.cmr.repository.ContentService;
+import org.alfresco.service.cmr.repository.ContentWriter;
+import org.alfresco.service.cmr.repository.NodeRef;
+import org.alfresco.service.cmr.repository.NodeService;
+import org.alfresco.service.cmr.tagging.TaggingService;
+import org.alfresco.service.namespace.NamespaceException;
+import org.alfresco.service.namespace.NamespacePrefixResolver;
+import org.alfresco.service.namespace.QName;
+import org.alfresco.service.transaction.TransactionService;
+import org.alfresco.transform.client.registry.TransformServiceRegistry;
+import org.apache.commons.csv.CSVFormat;
+import org.apache.commons.csv.CSVParser;
+import org.apache.commons.csv.CSVRecord;
+import org.springframework.dao.ConcurrencyFailureException;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.NoSuchElementException;
+import java.util.Set;
+import java.util.StringJoiner;
+import java.util.concurrent.ExecutorService;
+
+import static org.alfresco.repo.rendition2.RenditionDefinition2.TIMEOUT;
+import static org.alfresco.repo.rendition2.TransformDefinition.getTransformName;
+
+/**
+ * Requests an extract of metadata via a remote async transform using
+ * {@link RenditionService2#transform(NodeRef, TransformDefinition)}. The properties that will extracted are defined
+ * by the transform. This allows out of process metadata extracts to be defined without the need to apply an AMP.
+ * The actual transform is a request to go from the source mimetype to {@code "alfresco-metadata-extract"}. The
+ * resulting transform is a Map in json of properties and values to be set on the source node.
+ *
+ * As with other sub-classes of {@link AbstractMappingMetadataExtracter} it also supports embedding of metadata in
+ * a source node. In this case the remote async transform states that it supports a transform from a source mimetype
+ * to {@code "alfresco-metadata-embed"}. The resulting transform is a replacement for the content of the node.
+ *
+ * @author adavis
+ */
+public class AsynchronousExtractor extends AbstractMappingMetadataExtracter
+{
+ private static final String EXTRACT = "extract";
+ private static final String EMBED = "embed";
+ private static final String MIMETYPE_METADATA_EXTRACT = "alfresco-metadata-extract";
+ private static final String MIMETYPE_METADATA_EMBED = "alfresco-metadata-embed";
+ private static final String METADATA = "metadata";
+ private static final Map EMPTY_METADATA = Collections.emptyMap();
+
+ private final ObjectMapper jsonObjectMapper = new ObjectMapper();
+
+ private NodeService nodeService;
+ private NamespacePrefixResolver namespacePrefixResolver;
+ private TransformerDebug transformerDebug;
+ private RenditionService2 renditionService2;
+ private ContentService contentService;
+ private TransactionService transactionService;
+ private TransformServiceRegistry transformServiceRegistry;
+ private TaggingService taggingService;
+
+ public void setNodeService(NodeService nodeService)
+ {
+ this.nodeService = nodeService;
+ }
+
+ public void setNamespacePrefixResolver(NamespacePrefixResolver namespacePrefixResolver)
+ {
+ this.namespacePrefixResolver = namespacePrefixResolver;
+ }
+
+ public void setTransformerDebug(TransformerDebug transformerDebug)
+ {
+ this.transformerDebug = transformerDebug;
+ }
+
+ public void setRenditionService2(RenditionService2 renditionService2)
+ {
+ this.renditionService2 = renditionService2;
+ }
+
+ public void setContentService(ContentService contentService)
+ {
+ this.contentService = contentService;
+ }
+
+ public void setTransactionService(TransactionService transactionService)
+ {
+ this.transactionService = transactionService;
+ }
+
+ public void setTransformServiceRegistry(TransformServiceRegistry transformServiceRegistry)
+ {
+ this.transformServiceRegistry = transformServiceRegistry;
+ }
+
+ public void setTaggingService(TaggingService taggingService)
+ {
+ this.taggingService = taggingService;
+ }
+
+ @Override
+ protected Map> getDefaultMapping()
+ {
+ return Collections.emptyMap(); // Mappings are done by the transform, but a non null value must be returned.
+ }
+
+ public boolean isSupported(String sourceMimetype, long sourceSizeInBytes)
+ {
+ return isEnabled(sourceMimetype) && isSupported(sourceMimetype, sourceSizeInBytes, MIMETYPE_METADATA_EXTRACT);
+ }
+
+ public boolean isEmbedderSupported(String sourceMimetype, long sourceSizeInBytes)
+ {
+ return isSupported(sourceMimetype, sourceSizeInBytes, MIMETYPE_METADATA_EMBED);
+ }
+
+ private boolean isSupported(String sourceMimetype, long sourceSizeInBytes, String targetMimetype)
+ {
+ return transformServiceRegistry.isSupported(sourceMimetype, sourceSizeInBytes, targetMimetype, Collections.emptyMap(), targetMimetype);
+ }
+
+ public static boolean isMetadataExtractMimetype(String targetMimetype)
+ {
+ return MIMETYPE_METADATA_EXTRACT.equals(targetMimetype);
+ }
+
+ public static boolean isMetadataEmbedMimetype(String targetMimetype)
+ {
+ return MIMETYPE_METADATA_EMBED.equals(targetMimetype);
+ }
+
+ /**
+ * Returns a file extension used as the target in a transform. The normal extension is changed if the
+ * {@code targetMimetype} is an extraction or embedding type.
+ *
+ * @param targetMimetype the target mimetype
+ * @param sourceExtension normal source extension
+ * @param targetExtension current target extension (normally {@code "bin" for embedding and extraction})
+ * @return the extension to be used.
+ */
+ public static String getExtension(String targetMimetype, String sourceExtension, String targetExtension)
+ {
+ return isMetadataExtractMimetype(targetMimetype)
+ ? "json"
+ : isMetadataEmbedMimetype(targetMimetype)
+ ? sourceExtension
+ : targetExtension;
+ }
+
+ /**
+ * Returns a rendition name used in {@link TransformerDebug}. The normal name is changed if it is a metadata
+ * extract or embed. The name in this case is actually the {@code "alfresco-metadata-extract/"}
+ * {@code "alfresco-metadata-embed/"} followed by the source mimetype.
+ *
+ * @param renditionName the normal name, or a special one based on the source mimetype and a prefixed.
+ * @return the renditionName to be used.
+ */
+ public static String getRenditionName(String renditionName)
+ {
+ String transformName = getTransformName(renditionName);
+ return transformName != null && transformName.startsWith(MIMETYPE_METADATA_EXTRACT)
+ ? "metadataExtract"
+ : transformName != null && transformName.startsWith(MIMETYPE_METADATA_EMBED)
+ ? "metadataEmbed"
+ : renditionName;
+ }
+
+ @Override
+ protected void checkIsSupported(ContentReader reader)
+ {
+ // Just return, as we have already checked when this extractor was selected.
+ }
+
+ @Override
+ protected void checkIsEmbedSupported(ContentWriter writer)
+ {
+ // Just return, as we have already checked when this embedder was selected.
+ }
+
+ @Override
+ // Not called. Overloaded method with the NodeRef is called.
+ protected Map extractRaw(ContentReader reader)
+ {
+ return null;
+ }
+
+ @Override
+ protected Map extractRawInThread(NodeRef nodeRef, ContentReader reader, MetadataExtracterLimits limits)
+ throws Throwable
+ {
+ long timeoutMs = limits.getTimeoutMs();
+ Map options = Collections.singletonMap(TIMEOUT, Long.toString(timeoutMs));
+ transformInBackground(nodeRef, reader, MIMETYPE_METADATA_EXTRACT, EXTRACT, options);
+ return EMPTY_METADATA;
+ }
+
+ @Override
+ protected void embedInternal(NodeRef nodeRef, Map metadata, ContentReader reader, ContentWriter writer)
+ {
+ String metadataAsJson = metadataToString(metadata);
+ Map options = Collections.singletonMap(METADATA, metadataAsJson);
+ transformInBackground(nodeRef, reader, MIMETYPE_METADATA_EMBED, EMBED, options);
+ }
+
+ private void transformInBackground(NodeRef nodeRef, ContentReader reader, String targetMimetype,
+ String embedOrExtract, Map options)
+ {
+ ExecutorService executorService = getExecutorService();
+ executorService.execute(() ->
+ {
+ try
+ {
+ transform(nodeRef, reader, targetMimetype, embedOrExtract, options);
+ }
+ finally
+ {
+ extractRawThreadFinished();
+ }
+ });
+ }
+
+ private void transform(NodeRef nodeRef, ContentReader reader, String targetMimetype,
+ String embedOrExtract, Map options)
+ {
+ String sourceMimetype = reader.getMimetype();
+
+ // This needs to be specific to each source mimetype and the extract or embed as the name
+ // is used to cache the transform name that will be used.
+ String transformName = targetMimetype + '/' + sourceMimetype;
+
+ TransformDefinition transformDefinition = new TransformDefinition(transformName, targetMimetype,
+ options, null, null, null);
+
+ if (logger.isTraceEnabled())
+ {
+ StringJoiner sj = new StringJoiner("\n");
+ sj.add("Request " + embedOrExtract + " transform on " + nodeRef);
+ options.forEach((k,v)->sj.add(" "+k+"="+v));
+ logger.trace(sj);
+ }
+
+ AuthenticationUtil.runAs(
+ (AuthenticationUtil.RunAsWork) () ->
+ transactionService.getRetryingTransactionHelper().doInTransaction(() ->
+ {
+ try
+ {
+ renditionService2.transform(nodeRef, transformDefinition);
+ }
+ catch (IllegalArgumentException e)
+ {
+ if (e.getMessage().endsWith("The supplied sourceNodeRef "+nodeRef+" does not exist."))
+ {
+ throw new ConcurrencyFailureException(
+ "The original transaction may not have finished. " + e.getMessage());
+ }
+ }
+ return null;
+ }), AuthenticationUtil.getSystemUserName());
+ }
+
+ public void setMetadata(NodeRef nodeRef, InputStream transformInputStream)
+ {
+ if (logger.isTraceEnabled())
+ {
+ logger.trace("Update metadata on " + nodeRef);
+ }
+
+ Map metadata = readMetadata(transformInputStream);
+ if (metadata == null)
+ {
+ return; // Error state.
+ }
+
+ // Remove well know entries from the map that drive how the real metadata is applied.
+ OverwritePolicy overwritePolicy = removeOverwritePolicy(metadata, "sys:overwritePolicy", OverwritePolicy.PRAGMATIC);
+ Boolean enableStringTagging = removeBoolean(metadata, "sys:enableStringTagging", false);
+ Boolean carryAspectProperties = removeBoolean(metadata, "sys:carryAspectProperties", true);
+ List stringTaggingSeparators = removeTaggingSeparators(metadata, "sys:stringTaggingSeparators",
+ ContentMetadataExtracter.DEFAULT_STRING_TAGGING_SEPARATORS);
+ if (overwritePolicy == null ||
+ enableStringTagging == null ||
+ carryAspectProperties == null ||
+ stringTaggingSeparators == null)
+ {
+ return; // Error state.
+ }
+
+ AuthenticationUtil.runAsSystem((AuthenticationUtil.RunAsWork) () ->
+ transactionService.getRetryingTransactionHelper().doInTransaction(() ->
+ {
+ // Based on: AbstractMappingMetadataExtracter.extract
+ Map nodeProperties = nodeService.getProperties(nodeRef);
+ // Convert to system properties (standalone)
+ Map systemProperties = convertKeysToQNames(metadata);
+ // Convert the properties according to the dictionary types
+ systemProperties = convertSystemPropertyValues(systemProperties);
+ // There is no last filter in the AsynchronousExtractor.
+ // Now use the proper overwrite policy
+ Map changedProperties = overwritePolicy.applyProperties(systemProperties, nodeProperties);
+
+ // Based on: ContentMetadataExtracter.executeImpl
+ // If none of the properties where changed, then there is nothing more to do
+ if (changedProperties.size() == 0)
+ {
+ return null;
+ }
+ boolean transformerDebugEnabled = transformerDebug.isEnabled();
+ boolean debugEnabled = logger.isDebugEnabled();
+ if (transformerDebugEnabled || debugEnabled)
+ {
+ for (Map.Entry entry : changedProperties.entrySet())
+ {
+ QName qname = entry.getKey();
+ Serializable value = entry.getValue();
+ String prefixString = qname.toPrefixString(namespacePrefixResolver);
+ String debugMessage = prefixString + "=" + (value == null ? "" : value);
+ if (transformerDebugEnabled)
+ {
+ transformerDebug.debugUsingPreviousReference(" "+debugMessage);
+ }
+ if (debugEnabled)
+ {
+ logger.debug(debugMessage);
+ }
+ }
+ }
+ ContentMetadataExtracter.addExtractedMetadataToNode(nodeRef, nodeProperties, changedProperties,
+ nodeService, dictionaryService, taggingService,
+ enableStringTagging, carryAspectProperties, stringTaggingSeparators);
+
+ if (logger.isTraceEnabled())
+ {
+ logger.trace("Extraction of Metadata from " + nodeRef + " complete " + changedProperties);
+ }
+
+ return null;
+ }, false, true));
+ }
+
+ private Map readMetadata(InputStream transformInputStream)
+ {
+ try
+ {
+ TypeReference> typeRef = new TypeReference>() {};
+ return jsonObjectMapper.readValue(transformInputStream, typeRef);
+ }
+ catch (IOException e)
+ {
+ logger.error("Failed to read metadata from transform result", e);
+ return null;
+ }
+ }
+
+ private String metadataToString(Map metadata)
+ {
+ Map metadataAsStrings = AbstractMappingMetadataExtracter.convertMetadataToStrings(metadata);
+ try
+ {
+ return jsonObjectMapper.writeValueAsString(metadataAsStrings);
+ }
+ catch (JsonProcessingException e)
+ {
+ logger.error("Failed to save metadata as Json", e);
+ return null;
+ }
+ }
+
+ private OverwritePolicy removeOverwritePolicy(Map map, String key, OverwritePolicy defaultValue)
+ {
+ Serializable value = map.remove(key);
+ if (value == null)
+ {
+ return defaultValue;
+ }
+ try
+ {
+ return OverwritePolicy.valueOf((String)value);
+ }
+ catch (IllegalArgumentException|ClassCastException e)
+ {
+ logger.error(key + "=" + value + " is invalid");
+ return null;
+ }
+ }
+
+ private Boolean removeBoolean(Map map, Serializable key, boolean defaultValue)
+ {
+ @SuppressWarnings("SuspiciousMethodCalls") Serializable value = map.remove(key);
+ if (value != null &&
+ (!(value instanceof String) ||
+ (!(Boolean.FALSE.toString().equals(value) || Boolean.TRUE.toString().equals(value)))))
+ {
+ logger.error(key + "=" + value + " is invalid. Must be " + Boolean.TRUE + " or " + Boolean.FALSE);
+ return null; // no flexibility of parseBoolean(...). It is just invalid
+ }
+ return value == null ? defaultValue : Boolean.parseBoolean((String)value);
+ }
+
+ private List removeTaggingSeparators(Map map, String key, List defaultValue)
+ {
+ Serializable value = map.remove(key);
+ if (value == null)
+ {
+ return defaultValue;
+ }
+ if (!(value instanceof String))
+ {
+ logger.error(key + "=" + value + " is invalid.");
+ return null;
+ }
+
+ List list = new ArrayList<>();
+ try (CSVParser parser = CSVParser.parse((String)value, CSVFormat.RFC4180))
+ {
+ Iterator iterator = parser.iterator();
+ CSVRecord record = iterator.next();
+ if (iterator.hasNext())
+ {
+ logger.error(key + "=" + value + " is invalid. Should only have one record");
+ return null;
+ }
+ record.forEach(list::add);
+ }
+ catch (IOException|NoSuchElementException e)
+ {
+ logger.error(key + "=" + value + " is invalid. Must be a CSV using CSVFormat.RFC4180");
+ return null;
+ }
+ return list;
+ }
+
+ private Map convertKeysToQNames(Map documentMetadata)
+ {
+ Map properties = new HashMap<>();
+ for (Map.Entry entry : documentMetadata.entrySet())
+ {
+ String key = entry.getKey();
+ Serializable value = entry.getValue();
+ try
+ {
+ QName qName = QName.createQName(key);
+ try
+ {
+ qName.toPrefixString(namespacePrefixResolver);
+ properties.put(qName, value);
+ }
+ catch (NamespaceException e)
+ {
+ logger.error("Error unregistered namespace in " + qName);
+ }
+ }
+ catch (NamespaceException e)
+ {
+ logger.error("Error creating qName from "+key);
+ }
+ }
+ return properties;
+ }
+
+ public void setEmbeddedMetadata(NodeRef nodeRef, InputStream transformInputStream)
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Update of content to include metadata on " + nodeRef);
+ }
+ AuthenticationUtil.runAsSystem(() ->
+ transactionService.getRetryingTransactionHelper().doInTransaction(() ->
+ {
+ try
+ {
+ // Set or replace content
+ ContentReader reader = contentService.getReader(nodeRef, ContentModel.PROP_CONTENT);
+ String mimetype = reader.getMimetype();
+ String encoding = reader.getEncoding();
+ ContentWriter writer = contentService.getWriter(nodeRef, ContentModel.PROP_CONTENT, true);
+ writer.setMimetype(mimetype);
+ writer.setEncoding(encoding);
+ writer.putContent(transformInputStream);
+
+ if (logger.isTraceEnabled())
+ {
+ logger.trace("Embedded Metadata on " + nodeRef + " complete");
+ }
+ }
+ catch (Exception e)
+ {
+ logger.error("Failed to copy embedded metadata transform InputStream into " + nodeRef);
+ throw e;
+ }
+
+ return null;
+ }, false, true));
+ }
+}
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/HtmlMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/HtmlMetadataExtracter.java
index ff164ca105..691a5ac707 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/HtmlMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/HtmlMetadataExtracter.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracter.java
index 5cb216de90..61783333ad 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracter.java
@@ -25,19 +25,14 @@
*/
package org.alfresco.repo.content.metadata;
-import java.io.Serializable;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.HashSet;
-import java.util.Map;
-import java.util.Set;
-
-import org.alfresco.repo.content.MimetypeMap;
-import org.alfresco.repo.content.metadata.AbstractMappingMetadataExtracter;
-import org.alfresco.repo.content.metadata.OpenOfficeMetadataWorker;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.util.PropertyCheck;
+import java.io.Serializable;
+import java.util.Collections;
+import java.util.Map;
+import java.util.Set;
+
/**
* @deprecated OOTB extractors are being moved to T-Engines.
*
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracterWorker.java b/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracterWorker.java
index 3646e4864b..0a8a1e1ab0 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracterWorker.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/JodConverterMetadataExtracterWorker.java
@@ -35,7 +35,6 @@ import java.util.HashMap;
import java.util.Map;
import org.alfresco.repo.content.JodConverter;
-import org.alfresco.repo.content.metadata.OpenOfficeMetadataWorker;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.MimetypeService;
import org.alfresco.util.TempFileProvider;
@@ -60,7 +59,17 @@ import com.sun.star.util.XCloseable;
import com.sun.star.util.XRefreshable;
/**
+ * Extracts values from Open Office documents into the following:
+ *
+ * author: -- cm:author
+ * title: -- cm:title
+ * description: -- cm:description
+ *
+ *
+ * @deprecated The JodConverterMetadataExtracter has not been in use since 6.0.1
* @deprecated OOTB extractors are being moved to T-Engines.
+ *
+ * @author Neil McErlean
*/
@Deprecated
public class JodConverterMetadataExtracterWorker implements
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataEmbedder.java b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataEmbedder.java
index 3fbba6cf74..79eed186a1 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataEmbedder.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataEmbedder.java
@@ -1,28 +1,28 @@
-/*
- * #%L
- * Alfresco Repository
- * %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
- * %%
- * This file is part of the Alfresco software.
- * If the software was purchased under a paid Alfresco license, the terms of
- * the paid license agreement will prevail. Otherwise, the software is
- * provided under the following open source license terms:
- *
- * Alfresco is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Alfresco is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Alfresco. If not, see .
- * #L%
- */
+/*
+ * #%L
+ * Alfresco Repository
+ * %%
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
+ * %%
+ * This file is part of the Alfresco software.
+ * If the software was purchased under a paid Alfresco license, the terms of
+ * the paid license agreement will prevail. Otherwise, the software is
+ * provided under the following open source license terms:
+ *
+ * Alfresco is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Alfresco is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with Alfresco. If not, see .
+ * #L%
+ */
package org.alfresco.repo.content.metadata;
import java.io.Serializable;
@@ -33,6 +33,7 @@ import org.alfresco.repo.content.ContentWorker;
import org.alfresco.service.cmr.repository.ContentIOException;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.ContentWriter;
+import org.alfresco.service.cmr.repository.NodeRef;
import org.alfresco.service.namespace.QName;
/**
@@ -69,5 +70,18 @@ public interface MetadataEmbedder extends ContentWorker {
*/
public void embed(Map properties, ContentReader reader, ContentWriter writer) throws ContentIOException;
-
+ /**
+ * Identical to {@link #embed(Map, ContentReader, ContentWriter)} but with the addition of the
+ * {@code NodeRef} being acted on. By default, the method without the {@code NodeRef} is called.
+ *
+ * @param nodeRef the node being acted on.
+ * @param properties the model properties to embed
+ * @param reader the reader for the original source content file
+ * @param writer the writer for the content after metadata has been embedded
+ * @throws ContentIOException
+ */
+ public default void embed(NodeRef nodeRef, Map properties, ContentReader reader, ContentWriter writer) throws ContentIOException
+ {
+ embed(properties, reader, writer);
+ }
}
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracter.java
index 051184fd10..054c0077df 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracter.java
@@ -1,28 +1,28 @@
-/*
- * #%L
- * Alfresco Repository
- * %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
- * %%
- * This file is part of the Alfresco software.
- * If the software was purchased under a paid Alfresco license, the terms of
- * the paid license agreement will prevail. Otherwise, the software is
- * provided under the following open source license terms:
- *
- * Alfresco is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Alfresco is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Alfresco. If not, see .
- * #L%
- */
+/*
+ * #%L
+ * Alfresco Repository
+ * %%
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
+ * %%
+ * This file is part of the Alfresco software.
+ * If the software was purchased under a paid Alfresco license, the terms of
+ * the paid license agreement will prevail. Otherwise, the software is
+ * provided under the following open source license terms:
+ *
+ * Alfresco is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Alfresco is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with Alfresco. If not, see .
+ * #L%
+ */
/*
* Copyright (C) 2005 Jesper Steen Møller
*
@@ -52,6 +52,7 @@ import org.alfresco.api.AlfrescoPublicApi;
import org.alfresco.repo.content.ContentWorker;
import org.alfresco.service.cmr.repository.ContentIOException;
import org.alfresco.service.cmr.repository.ContentReader;
+import org.alfresco.service.cmr.repository.NodeRef;
import org.alfresco.service.namespace.NamespaceService;
import org.alfresco.service.namespace.QName;
@@ -402,4 +403,46 @@ public interface MetadataExtracter extends ContentWorker
OverwritePolicy overwritePolicy,
Map destination,
Map> mapping);
+
+ /**
+ * Identical to {@link #extract(ContentReader, Map)} but with the addition of the {@code NodeRef} being acted on.
+ * By default, the method without the {@code NodeRef} is called.
+ *
+ * @param nodeRef the node being acted on.
+ * @param reader the source of the content
+ * @param destination the map of properties to populate (essentially a return value)
+ * @return Returns a map of all properties on the destination map that were
+ * added or modified. If the return map is empty, then no properties
+ * were modified.
+ * @throws ContentIOException if a detectable error occurs
+ */
+ public default Map extract(NodeRef nodeRef, ContentReader reader, Map destination)
+ {
+ return extract(reader, destination);
+ }
+
+ /**
+ * Identical to {@link #extract(ContentReader, OverwritePolicy, Map, Map)} but with the addition of the
+ * {@code NodeRef} being acted on. By default, the method without the {@code NodeRef} is called.
+ *
+ * @param nodeRef the node being acted on.
+ * @param reader the source of the content
+ * @param overwritePolicy the policy stipulating how the system properties must be
+ * overwritten if present
+ * @param destination the map of properties to populate (essentially a return value)
+ * @param mapping a mapping of document-specific properties to system properties.
+ * @return Returns a map of all properties on the destination map that were
+ * added or modified. If the return map is empty, then no properties
+ * were modified.
+ * @throws ContentIOException if a detectable error occurs
+ */
+ public default Map extract(
+ NodeRef nodeRef,
+ ContentReader reader,
+ OverwritePolicy overwritePolicy,
+ Map destination,
+ Map> mapping)
+ {
+ return extract(reader, overwritePolicy, destination, mapping);
+ }
}
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracterRegistry.java b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracterRegistry.java
index 945cd49781..0db88f7400 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracterRegistry.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/MetadataExtracterRegistry.java
@@ -1,28 +1,28 @@
-/*
- * #%L
- * Alfresco Repository
- * %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
- * %%
- * This file is part of the Alfresco software.
- * If the software was purchased under a paid Alfresco license, the terms of
- * the paid license agreement will prevail. Otherwise, the software is
- * provided under the following open source license terms:
- *
- * Alfresco is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Alfresco is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Alfresco. If not, see .
- * #L%
- */
+/*
+ * #%L
+ * Alfresco Repository
+ * %%
+ * Copyright (C) 2005 - 2016 Alfresco Software Limited
+ * %%
+ * This file is part of the Alfresco software.
+ * If the software was purchased under a paid Alfresco license, the terms of
+ * the paid license agreement will prevail. Otherwise, the software is
+ * provided under the following open source license terms:
+ *
+ * Alfresco is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Alfresco is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with Alfresco. If not, see .
+ * #L%
+ */
/*
* Copyright (C) 2005-2012 Jesper Steen Møller
*
@@ -73,18 +73,22 @@ public class MetadataExtracterRegistry
private List extracters;
private Map> extracterCache;
private Map> embedderCache;
+ private AsynchronousExtractor asynchronousExtractor;
/** Controls read access to the cache */
private Lock extracterCacheReadLock;
/** controls write access to the cache */
private Lock extracterCacheWriteLock;
+ private boolean asyncExtractEnabled = true;
+ private boolean asyncEmbedEnabled = true;
+
public MetadataExtracterRegistry()
{
// initialise lists
- extracters = new ArrayList(10);
- extracterCache = new HashMap>(17);
- embedderCache = new HashMap>(17);
+ extracters = new ArrayList<>(11);
+ extracterCache = new HashMap<>(18);
+ embedderCache = new HashMap<>(18);
// create lock objects for access to the cache
ReadWriteLock extractionCacheLock = new ReentrantReadWriteLock();
@@ -125,7 +129,14 @@ public class MetadataExtracterRegistry
extracterCacheWriteLock.lock();
try
{
- extracters.add(extracter);
+ if (extracter instanceof AsynchronousExtractor)
+ {
+ asynchronousExtractor = (AsynchronousExtractor)extracter;
+ }
+ else
+ {
+ extracters.add(extracter);
+ }
extracterCache.clear();
embedderCache.clear();
}
@@ -135,16 +146,42 @@ public class MetadataExtracterRegistry
}
}
+ public void setAsyncExtractEnabled(boolean asyncExtractEnabled)
+ {
+ this.asyncExtractEnabled = asyncExtractEnabled;
+ }
+
+ public void setAsyncEmbedEnabled(boolean asyncEmbedEnabled)
+ {
+ this.asyncEmbedEnabled = asyncEmbedEnabled;
+ }
+
+ /**
+ * Returns the {@link AsynchronousExtractor} if it is able to perform the extraction and is enabled. Failing that it
+ * calls {@link #getExtracter(String)}.
+ *
+ * @param sourceSizeInBytes size of the source content.
+ * @param sourceMimetype the source MIMETYPE of the extraction
+ * @return Returns a metadata extractor that can extract metadata from the chosen MIME type.
+ */
+ public MetadataExtracter getExtractor(String sourceMimetype, long sourceSizeInBytes)
+ {
+ return asyncExtractEnabled && asynchronousExtractor != null &&
+ asynchronousExtractor.isSupported(sourceMimetype, sourceSizeInBytes)
+ ? asynchronousExtractor
+ : getExtracter(sourceMimetype);
+ }
+
/**
* Gets the best metadata extracter. This is a combination of the most
* reliable and the most performant extracter.
- *
- * The result is cached for quicker access next time.
- *
- * @param sourceMimetype the source MIME of the extraction
- * @return Returns a metadata extracter that can extract metadata from the
- * chosen MIME type.
- */
+ *
+ * The result is cached for quicker access next time.
+ *
+ * @param sourceMimetype the source MIME of the extraction
+ * @return Returns a metadata extracter that can extract metadata from the
+ * chosen MIME type.
+ */
public MetadataExtracter getExtracter(String sourceMimetype)
{
logger.debug("Get extractors for " + sourceMimetype);
@@ -202,18 +239,18 @@ public class MetadataExtracterRegistry
}
private String getName(MetadataExtracter extractor)
- {
- if (extractor == null)
- {
- return null;
- }
- else if (extractor instanceof AbstractMappingMetadataExtracter)
- {
- return ((AbstractMappingMetadataExtracter)extractor).getBeanName();
- }
- else
- {
- return extractor.getClass().getSimpleName();
+ {
+ if (extractor == null)
+ {
+ return null;
+ }
+ else if (extractor instanceof AbstractMappingMetadataExtracter)
+ {
+ return ((AbstractMappingMetadataExtracter)extractor).getBeanName();
+ }
+ else
+ {
+ return extractor.getClass().getSimpleName();
}
}
@@ -222,48 +259,64 @@ public class MetadataExtracterRegistry
* @return Returns a set of extractors that will work for the given mimetype
*/
private List findBestExtracters(String sourceMimetype)
- {
- if (logger.isDebugEnabled())
+ {
+ if (logger.isDebugEnabled())
{
- logger.debug("Finding extractors for " + sourceMimetype);
+ logger.debug("Finding extractors for " + sourceMimetype);
}
- List extractors = new ArrayList(1);
+ List extractors = new ArrayList<>(1);
for (MetadataExtracter extractor : extracters)
{
if (!extractor.isSupported(sourceMimetype))
{
- // extraction not achievable
- if (logger.isDebugEnabled())
+ // extraction not achievable
+ if (logger.isDebugEnabled())
{
- logger.debug("Find unsupported: "+getName(extractor));
+ logger.debug("Find unsupported: "+getName(extractor));
}
continue;
- }
- if (logger.isDebugEnabled())
+ }
+ if (logger.isDebugEnabled())
{
- logger.debug("Find supported: "+getName(extractor));
+ logger.debug("Find supported: "+getName(extractor));
}
extractors.add(extractor);
- }
- if (logger.isDebugEnabled())
+ }
+ if (logger.isDebugEnabled())
{
- logger.debug("Find returning: "+extractors);
+ logger.debug("Find returning: "+extractors);
}
return extractors;
}
-
+
+ /**
+ * Returns the {@link AsynchronousExtractor} if it is able to perform the embedding and is enabled. Failing that it
+ * calls {@link #getEmbedder(String)}.
+ *
+ * @param sourceSizeInBytes size of the source content.
+ * @param sourceMimetype the source MIMETYPE of the extraction
+ * @return Returns a metadata extractor that can extract metadata from the chosen MIME type.
+ */
+ public MetadataEmbedder getEmbedder(String sourceMimetype, long sourceSizeInBytes)
+ {
+ return asyncEmbedEnabled && asynchronousExtractor != null &&
+ asynchronousExtractor.isEmbedderSupported(sourceMimetype, sourceSizeInBytes)
+ ? asynchronousExtractor
+ : getEmbedder(sourceMimetype);
+ }
+
/**
* Gets the best metadata embedder. This is a combination of the most
* reliable and the most performant embedder.
- *
- * The result is cached for quicker access next time.
- *
- * @param sourceMimetype the source MIME of the extraction
- * @return Returns a metadata embedder that can embed metadata in the
- * chosen MIME type.
- */
+ *
+ * The result is cached for quicker access next time.
+ *
+ * @param sourceMimetype the source MIME of the extraction
+ * @return Returns a metadata embedder that can embed metadata in the
+ * chosen MIME type.
+ */
public MetadataEmbedder getEmbedder(String sourceMimetype)
{
List embedders = null;
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/OpenDocumentMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/OpenDocumentMetadataExtracter.java
index 8d2da83e7c..25034754c6 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/OpenDocumentMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/OpenDocumentMetadataExtracter.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/TikaPoweredMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/TikaPoweredMetadataExtracter.java
index 5f8e89cf7c..0c89f63cfe 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/TikaPoweredMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/TikaPoweredMetadataExtracter.java
@@ -31,7 +31,6 @@ import java.io.OutputStream;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
-import java.util.Collection;
import java.util.Date;
import java.util.HashMap;
import java.util.HashSet;
@@ -45,8 +44,6 @@ import org.alfresco.repo.content.MimetypeMap;
import org.alfresco.repo.content.filestore.FileContentReader;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.ContentWriter;
-import org.alfresco.service.cmr.repository.datatype.DefaultTypeConverter;
-import org.alfresco.service.cmr.repository.datatype.TypeConversionException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.tika.embedder.Embedder;
@@ -476,43 +473,11 @@ public abstract class TikaPoweredMetadataExtracter
{
return;
}
-
+
+ Map metadataAsStrings = convertMetadataToStrings(properties);
Metadata metadataToEmbed = new Metadata();
- for (String metadataKey : properties.keySet())
- {
- Serializable value = properties.get(metadataKey);
- if (value == null)
- {
- continue;
- }
- if (value instanceof Collection)
- {
- for (Object singleValue : (Collection) value)
- {
- try
- {
- // Convert to a string value for Tika
- metadataToEmbed.add(metadataKey, DefaultTypeConverter.INSTANCE.convert(String.class, singleValue));
- }
- catch (TypeConversionException e)
- {
- logger.info("Could not convert " + metadataKey + ": " + e.getMessage());
- }
- }
- }
- else
- {
- try
- {
- // Convert to a string value for Tika
- metadataToEmbed.add(metadataKey, DefaultTypeConverter.INSTANCE.convert(String.class, value));
- }
- catch (TypeConversionException e)
- {
- logger.info("Could not convert " + metadataKey + ": " + e.getMessage());
- }
- }
- }
+ metadataAsStrings.forEach((k,v)->metadataToEmbed.add(k, v));
+
InputStream inputStream = getInputStream(reader);
OutputStream outputStream = writer.getContentOutputStream();
embedder.embed(metadataToEmbed, inputStream, outputStream, null);
diff --git a/repository/src/main/java/org/alfresco/repo/content/metadata/xml/XmlMetadataExtracter.java b/repository/src/main/java/org/alfresco/repo/content/metadata/xml/XmlMetadataExtracter.java
index 775e6ee9f6..bd8cc89d7f 100644
--- a/repository/src/main/java/org/alfresco/repo/content/metadata/xml/XmlMetadataExtracter.java
+++ b/repository/src/main/java/org/alfresco/repo/content/metadata/xml/XmlMetadataExtracter.java
@@ -60,6 +60,7 @@ import org.alfresco.util.PropertyCheck;
* @since 2.1
* @author Derek Hulley
*/
+@Deprecated
public class XmlMetadataExtracter extends AbstractMappingMetadataExtracter
{
public static String[] SUPPORTED_MIMETYPES = new String[] { MimetypeMap.MIMETYPE_XML };
diff --git a/repository/src/main/java/org/alfresco/repo/content/transform/AdminUiTransformerDebug.java b/repository/src/main/java/org/alfresco/repo/content/transform/AdminUiTransformerDebug.java
index c4ed028550..8e0ffe5e5f 100644
--- a/repository/src/main/java/org/alfresco/repo/content/transform/AdminUiTransformerDebug.java
+++ b/repository/src/main/java/org/alfresco/repo/content/transform/AdminUiTransformerDebug.java
@@ -249,7 +249,7 @@ public class AdminUiTransformerDebug extends TransformerDebug implements Applica
boolean firstTransformer)
{
String mimetypes = firstTransformer
- ? getMimetypeExt(sourceMimetype)+getMimetypeExt(targetMimetype)
+ ? getSourceAndTargetExt(sourceMimetype, targetMimetype)
: spaces(10);
char c = (char)('a'+transformerCount);
log(mimetypes+
diff --git a/repository/src/main/java/org/alfresco/repo/content/transform/LegacyTransformerDebug.java b/repository/src/main/java/org/alfresco/repo/content/transform/LegacyTransformerDebug.java
index db85c40e9b..7831333627 100644
--- a/repository/src/main/java/org/alfresco/repo/content/transform/LegacyTransformerDebug.java
+++ b/repository/src/main/java/org/alfresco/repo/content/transform/LegacyTransformerDebug.java
@@ -25,6 +25,7 @@
*/
package org.alfresco.repo.content.transform;
+import org.alfresco.repo.content.metadata.AsynchronousExtractor;
import org.alfresco.service.cmr.repository.NodeRef;
import org.alfresco.service.cmr.repository.TransformationOptions;
import org.alfresco.transform.client.registry.SupportedTransform;
@@ -99,10 +100,9 @@ public class LegacyTransformerDebug extends AdminUiTransformerDebug
public void blacklistTransform(ContentTransformer transformer, String sourceMimetype,
String targetMimetype, TransformationOptions options)
{
- log("Blacklist "+getName(transformer)+" "+getMimetypeExt(sourceMimetype)+getMimetypeExt(targetMimetype));
+ log("Blacklist "+getName(transformer)+" "+ getSourceAndTargetExt(sourceMimetype, targetMimetype));
}
-
@Deprecated
public void pushTransform(ContentTransformer transformer, String fromUrl, String sourceMimetype,
String targetMimetype, long sourceSize, TransformationOptions options)
@@ -265,7 +265,10 @@ public class LegacyTransformerDebug extends AdminUiTransformerDebug
}
String i = Integer.toString(mimetypePairCount);
String priority = gePriority(transformer, sourceMimetype, targetMimetype);
- log(spaces(5-i.length())+mimetypePairCount+") "+getMimetypeExt(sourceMimetype)+getMimetypeExt(targetMimetype)+
+ String sourceExt = getMimetypeExt(sourceMimetype);
+ String targetExt = getMimetypeExt(targetMimetype);
+ targetExt = AsynchronousExtractor.getExtension(targetMimetype, sourceExt, targetExt);
+ log(spaces(5-i.length())+mimetypePairCount+") "+ sourceExt + targetExt +
priority +
' '+fileSize((maxSourceSizeKBytes > 0) ? maxSourceSizeKBytes*1024 : maxSourceSizeKBytes)+
(maxSourceSizeKBytes == 0 ? " disabled" : ""));
diff --git a/repository/src/main/java/org/alfresco/repo/content/transform/LocalTransformImpl.java b/repository/src/main/java/org/alfresco/repo/content/transform/LocalTransformImpl.java
index ffefc4ba15..ef0ab8b3d5 100644
--- a/repository/src/main/java/org/alfresco/repo/content/transform/LocalTransformImpl.java
+++ b/repository/src/main/java/org/alfresco/repo/content/transform/LocalTransformImpl.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2019 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -25,6 +25,7 @@
*/
package org.alfresco.repo.content.transform;
+import org.alfresco.repo.content.metadata.AsynchronousExtractor;
import org.alfresco.repo.rendition2.RenditionDefinition2;
import org.alfresco.service.cmr.repository.ContentReader;
import org.alfresco.service.cmr.repository.ContentWriter;
@@ -188,6 +189,7 @@ public class LocalTransformImpl extends AbstractLocalTransform
args[i++] = "targetMimetype";
args[i++] = targetMimetype;
+ targetExtension = AsynchronousExtractor.getExtension(targetMimetype, sourceExtension, targetExtension);
remoteTransformerClient.request(reader, writer, sourceMimetype, sourceExtension, targetExtension,
timeoutMs, log, args);
}
diff --git a/repository/src/main/java/org/alfresco/repo/content/transform/TransformerDebug.java b/repository/src/main/java/org/alfresco/repo/content/transform/TransformerDebug.java
index c13e76f949..bd6d656f89 100644
--- a/repository/src/main/java/org/alfresco/repo/content/transform/TransformerDebug.java
+++ b/repository/src/main/java/org/alfresco/repo/content/transform/TransformerDebug.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2019 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -26,6 +26,7 @@
package org.alfresco.repo.content.transform;
import org.alfresco.model.ContentModel;
+import org.alfresco.repo.content.metadata.AsynchronousExtractor;
import org.alfresco.service.cmr.repository.MimetypeService;
import org.alfresco.service.cmr.repository.NodeRef;
import org.alfresco.service.cmr.repository.NodeService;
@@ -68,6 +69,7 @@ public class TransformerDebug
protected Log logger;
protected NodeService nodeService;
protected MimetypeService mimetypeService;
+ private final ThreadLocal previousTransformId = ThreadLocal.withInitial(()->-1);
protected enum Call
{
@@ -280,6 +282,16 @@ public class TransformerDebug
this.mimetypeService = mimetypeService;
}
+ public void setPreviousTransformId(int id)
+ {
+ previousTransformId.set(id);
+ }
+
+ private int getPreviousTransformId()
+ {
+ return previousTransformId.get();
+ }
+
public void afterPropertiesSet() throws Exception
{
PropertyCheck.mandatory(this, "nodeService", nodeService);
@@ -351,7 +363,7 @@ public class TransformerDebug
log(frame.sourceMimetype+' '+frame.targetMimetype, false);
String fileName = getFileName(frame.sourceNodeRef, firstLevel, sourceSize);
- log(getMimetypeExt(frame.sourceMimetype)+getMimetypeExt(frame.targetMimetype) +
+ log(getSourceAndTargetExt(frame.sourceMimetype, frame.targetMimetype) +
((fileName != null) ? fileName+' ' : "")+
((sourceSize >= 0) ? fileSize(sourceSize)+' ' : "") +
(firstLevel ? getRenditionName(renditionName) : "") + message);
@@ -370,7 +382,7 @@ public class TransformerDebug
Map options, String renditionName, String message)
{
String fileName = getFileName(sourceNodeRef, true, -1);
- log(" "+getMimetypeExt(sourceMimetype)+getMimetypeExt(targetMimetype) +
+ log(" "+ getSourceAndTargetExt(sourceMimetype, targetMimetype) +
((fileName != null) ? fileName+' ' : "")+
((sourceSize >= 0) ? fileSize(sourceSize)+' ' : "") +
(getRenditionName(renditionName)) + message);
@@ -453,6 +465,7 @@ public class TransformerDebug
ourStack.pop();
}
}
+ setPreviousTransformId(id);
return id;
}
@@ -462,8 +475,7 @@ public class TransformerDebug
{
String failureReason = frame.getFailureReason();
boolean firstLevel = size == 1;
- String sourceExt = getMimetypeExt(frame.sourceMimetype);
- String targetExt = getMimetypeExt(frame.targetMimetype);
+ String sourceAndTargetExt = getSourceAndTargetExt(frame.sourceMimetype, frame.targetMimetype);
String fileName = getFileName(frame.sourceNodeRef, firstLevel, frame.sourceSize);
long sourceSize = frame.getSourceSize();
String transformerName = frame.getTransformerName();
@@ -506,19 +518,18 @@ public class TransformerDebug
if (level != null)
{
- infoLog(getReference(debug, false), sourceExt, targetExt, level, fileName, sourceSize,
+ infoLog(getReference(debug, false, false), sourceAndTargetExt, level, fileName, sourceSize,
transformerName, renditionName, failureReason, ms, debug);
}
}
}
- private void infoLog(String reference, String sourceExt, String targetExt, String level, String fileName,
+ private void infoLog(String reference, String sourceAndTargetExt, String level, String fileName,
long sourceSize, String transformerName, String renditionName, String failureReason, String ms, boolean debug)
{
String message =
reference +
- sourceExt +
- targetExt +
+ sourceAndTargetExt +
(level == null ? "" : level+' ') +
(fileName == null ? "" : fileName) +
(sourceSize >= 0 ? ' '+fileSize(sourceSize) : "") +
@@ -569,6 +580,18 @@ public class TransformerDebug
}
}
+ /**
+ * Log a message prefixed with the previous transformation reference, used by this Thread.
+ * @param message
+ */
+ public void debugUsingPreviousReference(String message)
+ {
+ if (isEnabled() && message != null)
+ {
+ log(message, null,true, true);
+ }
+ }
+
/**
* Log a message prefixed with the current transformation reference
* and include a exception, suppressing the stack trace if repeated
@@ -631,16 +654,21 @@ public class TransformerDebug
{
log(message, null, debug);
}
-
+
private void log(String message, Throwable t, boolean debug)
+ {
+ log(message, t, debug, false);
+ }
+
+ private void log(String message, Throwable t, boolean debug, boolean usePreviousRef)
{
if (debug && ThreadInfo.getDebugOutput() && logger.isDebugEnabled())
{
- logger.debug(getReference(false, false)+message, t);
+ logger.debug(getReference(false, false, usePreviousRef)+message, t);
}
else if (logger.isTraceEnabled())
{
- logger.trace(getReference(false, false)+message, t);
+ logger.trace(getReference(false, false, usePreviousRef)+message, t);
}
if (debug)
@@ -648,7 +676,7 @@ public class TransformerDebug
StringBuilder sb = ThreadInfo.getStringBuilder();
if (sb != null)
{
- sb.append(getReference(false, true));
+ sb.append(getReference(false, true, usePreviousRef));
sb.append(message);
if (t != null)
{
@@ -691,10 +719,21 @@ public class TransformerDebug
* Returns a N.N.N style reference to the transformation.
* @param firstLevelOnly indicates if only the top level should be included and no extra padding.
* @param overrideFirstLevel if the first level id should just be set to 1 (used in test methods)
+ * @param usePreviousRef if the reference of the last transform performed by this Thread should be used.
* @return a padded (fixed length) reference.
*/
- private String getReference(boolean firstLevelOnly, boolean overrideFirstLevel)
+ private String getReference(boolean firstLevelOnly, boolean overrideFirstLevel, boolean usePreviousRef)
{
+ if (usePreviousRef)
+ {
+ int id = getPreviousTransformId();
+ String ref = "";
+ if (id >= 0)
+ {
+ ref = Integer.toString(id)+spaces(13);
+ }
+ return ref;
+ }
StringBuilder sb = new StringBuilder("");
Frame frame = null;
Iterator iterator = ThreadInfo.getStack().descendingIterator();
@@ -737,7 +776,7 @@ public class TransformerDebug
}
else
{
- sb.append(spaces(13-sb.length()+lengthOfFirstId)); // Try to pad to level 7
+ sb.append(spaces(13-sb.length()+lengthOfFirstId)); // Try to pad to level 7
}
}
return sb.toString();
@@ -783,6 +822,14 @@ public class TransformerDebug
return result;
}
+ protected String getSourceAndTargetExt(String sourceMimetype, String targetMimetype)
+ {
+ String sourceExt = getMimetypeExt(sourceMimetype);
+ String targetExt = getMimetypeExt(targetMimetype);
+ targetExt = AsynchronousExtractor.getExtension(targetMimetype, sourceExt, targetExt);
+ return sourceExt + targetExt + spaces(1+4-targetExt.length());
+ }
+
protected String getMimetypeExt(String mimetype)
{
StringBuilder sb = new StringBuilder("");
@@ -867,16 +914,15 @@ public class TransformerDebug
if (isEnabled())
{
pushMisc();
- String sourceExt = getMimetypeExt(sourceMimetype);
- String targetExt = getMimetypeExt(targetMimetype);
- debug(sourceExt + targetExt +
+ String sourceAndTargetExt = getSourceAndTargetExt(sourceMimetype, targetMimetype);
+ debug(sourceAndTargetExt +
((fileName != null) ? fileName + ' ' : "") +
((sourceSize >= 0) ? fileSize(sourceSize) + ' ' : "") +
getRenditionName(renditionName) + " "+ TRANSFORM_SERVICE_NAME);
log(options);
log(sourceNodeRef.toString() + ' ' + contentHashcode);
- String reference = getReference(true, false);
- infoLog(reference, sourceExt, targetExt, null, fileName, sourceSize, TRANSFORM_SERVICE_NAME,
+ String reference = getReference(true, false, false);
+ infoLog(reference, sourceAndTargetExt, null, fileName, sourceSize, TRANSFORM_SERVICE_NAME,
renditionName, null, "", true);
}
return pop(Call.AVAILABLE, true, false);
@@ -884,19 +930,21 @@ public class TransformerDebug
private String getRenditionName(String renditionName)
{
- return renditionName != null ? "-- "+renditionName+" -- " : "";
+ return renditionName != null
+ ? "-- "+ AsynchronousExtractor.getRenditionName(renditionName)+" -- "
+ : "";
}
/**
* Debugs a response to the Transform Service
*/
public void debugTransformServiceResponse(NodeRef sourceNodeRef, int contentHashcode,
- long requested, int seq, String sourceExt, String targetExt, String msg)
+ long requested, int id, String sourceExt, String targetExt, String msg)
{
pushMisc();
Frame frame = ThreadInfo.getStack().getLast();
- frame.id = seq;
- boolean suppressFinish = seq == -1 || requested == -1;
+ frame.id = id;
+ boolean suppressFinish = id == -1 || requested == -1;
if (!suppressFinish)
{
frame.start = requested;
diff --git a/repository/src/main/java/org/alfresco/repo/rendition2/RenditionService2Impl.java b/repository/src/main/java/org/alfresco/repo/rendition2/RenditionService2Impl.java
index 298723c76d..350411d903 100644
--- a/repository/src/main/java/org/alfresco/repo/rendition2/RenditionService2Impl.java
+++ b/repository/src/main/java/org/alfresco/repo/rendition2/RenditionService2Impl.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2019 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -29,6 +29,7 @@ import org.alfresco.model.ContentModel;
import org.alfresco.model.RenditionModel;
import org.alfresco.repo.content.ContentServicePolicies;
import org.alfresco.repo.content.MimetypeMap;
+import org.alfresco.repo.content.metadata.AsynchronousExtractor;
import org.alfresco.repo.policy.BehaviourFilter;
import org.alfresco.repo.policy.PolicyComponent;
import org.alfresco.repo.rendition.RenditionPreventionRegistry;
@@ -112,6 +113,7 @@ public class RenditionService2Impl implements RenditionService2, InitializingBea
private RuleService ruleService;
private PostTxnCallbackScheduler renditionRequestSheduler;
private TransformReplyProvider transformReplyProvider;
+ private AsynchronousExtractor asynchronousExtractor;
private boolean enabled;
private boolean thumbnailsEnabled;
@@ -176,6 +178,11 @@ public class RenditionService2Impl implements RenditionService2, InitializingBea
this.transformReplyProvider = transformReplyProvider;
}
+ public void setAsynchronousExtractor(AsynchronousExtractor asynchronousExtractor)
+ {
+ this.asynchronousExtractor = asynchronousExtractor;
+ }
+
public void setEnabled(boolean enabled)
{
this.enabled = enabled;
@@ -203,6 +210,7 @@ public class RenditionService2Impl implements RenditionService2, InitializingBea
PropertyCheck.mandatory(this, "policyComponent", policyComponent);
PropertyCheck.mandatory(this, "behaviourFilter", behaviourFilter);
PropertyCheck.mandatory(this, "ruleService", ruleService);
+ PropertyCheck.mandatory(this, "asynchronousExtractor", asynchronousExtractor);
}
@Override
@@ -374,41 +382,115 @@ public class RenditionService2Impl implements RenditionService2, InitializingBea
public void consume(NodeRef sourceNodeRef, InputStream transformInputStream, RenditionDefinition2 renditionDefinition,
int transformContentHashCode)
{
+ int sourceContentHashCode = getSourceContentHashCode(sourceNodeRef);
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Consume: Source " + sourceContentHashCode + " and transform's source " + transformContentHashCode+" hashcodes");
+ }
+
if (renditionDefinition instanceof TransformDefinition)
{
- if (logger.isDebugEnabled())
+ TransformDefinition transformDefinition = (TransformDefinition)renditionDefinition;
+ String targetMimetype = transformDefinition.getTargetMimetype();
+ if (AsynchronousExtractor.isMetadataExtractMimetype(targetMimetype))
{
- TransformDefinition transformDefinition = (TransformDefinition)renditionDefinition;
- String transformName = transformDefinition.getTransformName();
- String replyQueue = transformDefinition.getReplyQueue();
- String clientData = transformDefinition.getClientData();
- boolean success = transformInputStream != null;
- logger.info("Reply to " + replyQueue + " that the transform " + transformName +
- " with the client data " + clientData + " " + (success ? "was successful" : "failed."));
+ consumeExtractedMetadata(sourceNodeRef, sourceContentHashCode, transformInputStream, transformDefinition, transformContentHashCode);
+ }
+ else if (AsynchronousExtractor.isMetadataEmbedMimetype(targetMimetype))
+ {
+ consumeEmbeddedMetadata(sourceNodeRef, sourceContentHashCode, transformInputStream, transformDefinition, transformContentHashCode);
+ }
+ else
+ {
+ consumeTransformReply(sourceNodeRef, transformInputStream, transformDefinition, transformContentHashCode);
}
- transformReplyProvider.produceTransformEvent(sourceNodeRef, transformInputStream,
- (TransformDefinition)renditionDefinition, transformContentHashCode);
}
else
{
- consumeRendition(sourceNodeRef, transformInputStream, renditionDefinition, transformContentHashCode);
+ consumeRendition(sourceNodeRef, sourceContentHashCode, transformInputStream, renditionDefinition, transformContentHashCode);
}
}
+ private void consumeExtractedMetadata(NodeRef nodeRef, int sourceContentHashCode, InputStream transformInputStream,
+ TransformDefinition transformDefinition, int transformContentHashCode)
+ {
+ if (transformInputStream == null)
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Ignore transform for metadata extraction on " + nodeRef + " as it failed");
+ }
+ }
+ else if (transformContentHashCode != sourceContentHashCode)
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Ignore transform for metadata extraction on " + nodeRef + " as it is no longer needed");
+ }
+ }
+ else
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Set the metadata extraction on " + nodeRef);
+ }
+ asynchronousExtractor.setMetadata(nodeRef, transformInputStream);
+ }
+ }
+
+ private void consumeEmbeddedMetadata(NodeRef nodeRef, int sourceContentHashCode, InputStream transformInputStream,
+ TransformDefinition transformDefinition, int transformContentHashCode)
+ {
+ if (transformInputStream == null)
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Ignore transform for metadata embed on " + nodeRef + " as it failed");
+ }
+ }
+ else if (transformContentHashCode != sourceContentHashCode)
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Ignore transform for metadata embed on " + nodeRef + " as it is no longer needed");
+ }
+ }
+ else
+ {
+ if (logger.isDebugEnabled())
+ {
+ logger.debug("Set the content with embedded metadata on " + nodeRef);
+ }
+
+ asynchronousExtractor.setEmbeddedMetadata(nodeRef, transformInputStream);
+ }
+ }
+
+ private void consumeTransformReply(NodeRef sourceNodeRef, InputStream transformInputStream,
+ TransformDefinition transformDefinition, int transformContentHashCode)
+ {
+ if (logger.isDebugEnabled())
+ {
+ String transformName = transformDefinition.getTransformName();
+ String replyQueue = transformDefinition.getReplyQueue();
+ String clientData = transformDefinition.getClientData();
+ boolean success = transformInputStream != null;
+ logger.info("Reply to " + replyQueue + " that the transform " + transformName +
+ " with the client data " + clientData + " " + (success ? "was successful" : "failed."));
+ }
+ transformReplyProvider.produceTransformEvent(sourceNodeRef, transformInputStream,
+ transformDefinition, transformContentHashCode);
+ }
+
/**
* Takes a transformation (InputStream) and attaches it as a rendition to the source node.
* Does nothing if there is already a newer rendition.
* If the transformInputStream is null, this is taken to be a transform failure.
*/
- private void consumeRendition(NodeRef sourceNodeRef, InputStream transformInputStream,
+ private void consumeRendition(NodeRef sourceNodeRef, int sourceContentHashCode, InputStream transformInputStream,
RenditionDefinition2 renditionDefinition, int transformContentHashCode)
{
String renditionName = renditionDefinition.getRenditionName();
- int sourceContentHashCode = getSourceContentHashCode(sourceNodeRef);
- if (logger.isDebugEnabled())
- {
- logger.debug("Consume: Source " + sourceContentHashCode + " and transform's source " + transformContentHashCode+" hashcodes");
- }
if (transformContentHashCode != sourceContentHashCode)
{
if (logger.isDebugEnabled())
@@ -475,7 +557,7 @@ public class RenditionService2Impl implements RenditionService2, InitializingBea
}
catch (Exception e)
{
- logger.error("Failed to read transform InputStream into rendition " + renditionName + " on " + sourceNodeRef);
+ logger.error("Failed to copy transform InputStream into rendition " + renditionName + " on " + sourceNodeRef);
throw e;
}
}
diff --git a/repository/src/main/java/org/alfresco/repo/rendition2/TransformDefinition.java b/repository/src/main/java/org/alfresco/repo/rendition2/TransformDefinition.java
index 26df001b31..3c0b1522f6 100644
--- a/repository/src/main/java/org/alfresco/repo/rendition2/TransformDefinition.java
+++ b/repository/src/main/java/org/alfresco/repo/rendition2/TransformDefinition.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2019 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -80,7 +80,14 @@ public class TransformDefinition extends RenditionDefinition2Impl
public String getTransformName()
{
String renditionName = getRenditionName();
- return renditionName == null ? null : renditionName.substring(TRANSFORM_NAMESPACE.length());
+ return getTransformName(renditionName);
+ }
+
+ public static String getTransformName(String renditionName)
+ {
+ return renditionName == null || !renditionName.startsWith(TRANSFORM_NAMESPACE)
+ ? null
+ : renditionName.substring(TRANSFORM_NAMESPACE.length());
}
public String getClientData()
diff --git a/repository/src/main/java/org/alfresco/repo/tagging/TaggingServiceImpl.java b/repository/src/main/java/org/alfresco/repo/tagging/TaggingServiceImpl.java
index 478da899bc..e9f2fc17ae 100644
--- a/repository/src/main/java/org/alfresco/repo/tagging/TaggingServiceImpl.java
+++ b/repository/src/main/java/org/alfresco/repo/tagging/TaggingServiceImpl.java
@@ -1,28 +1,28 @@
-/*
- * #%L
- * Alfresco Repository
- * %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
- * %%
- * This file is part of the Alfresco software.
- * If the software was purchased under a paid Alfresco license, the terms of
- * the paid license agreement will prevail. Otherwise, the software is
- * provided under the following open source license terms:
- *
- * Alfresco is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Alfresco is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Alfresco. If not, see .
- * #L%
- */
+/*
+ * #%L
+ * Alfresco Repository
+ * %%
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
+ * %%
+ * This file is part of the Alfresco software.
+ * If the software was purchased under a paid Alfresco license, the terms of
+ * the paid license agreement will prevail. Otherwise, the software is
+ * provided under the following open source license terms:
+ *
+ * Alfresco is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Alfresco is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with Alfresco. If not, see .
+ * #L%
+ */
package org.alfresco.repo.tagging;
import java.io.BufferedReader;
@@ -74,9 +74,9 @@ import org.alfresco.service.cmr.repository.NodeService;
import org.alfresco.service.cmr.repository.Path;
import org.alfresco.service.cmr.repository.StoreRef;
import org.alfresco.service.cmr.search.CategoryService;
-import org.alfresco.service.cmr.search.ResultSet;
-import org.alfresco.service.cmr.search.SearchParameters;
-import org.alfresco.service.cmr.search.SearchParameters.FieldFacet;
+import org.alfresco.service.cmr.search.ResultSet;
+import org.alfresco.service.cmr.search.SearchParameters;
+import org.alfresco.service.cmr.search.SearchParameters.FieldFacet;
import org.alfresco.service.cmr.search.SearchService;
import org.alfresco.service.cmr.tagging.TagDetails;
import org.alfresco.service.cmr.tagging.TagScope;
@@ -1544,35 +1544,35 @@ public class TaggingServiceImpl implements TaggingService,
{
updateAllScopeTags(workingCopy, Boolean.FALSE);
}
- }
-
- /**
- * @see org.alfresco.service.cmr.tagging.TaggingService#findTaggedNodesAndCountByTagName(StoreRef)
- */
- @Override
- public List> findTaggedNodesAndCountByTagName(StoreRef storeRef)
- {
- String queryTaggeble = "ASPECT:\"" + ContentModel.ASPECT_TAGGABLE + "\"" + "-ASPECT:\"" + ContentModel.ASPECT_WORKING_COPY + "\"";
- SearchParameters sp = new SearchParameters();
- sp.setQuery(queryTaggeble);
- sp.setLanguage(SearchService.LANGUAGE_LUCENE);
- sp.addStore(storeRef);
- sp.addFieldFacet(new FieldFacet("TAG"));
-
- ResultSet resultSet = null;
- try
- {
- // Do the search for nodes
- resultSet = this.searchService.query(sp);
- return resultSet.getFieldFacet("TAG");
- }
- finally
- {
- if (resultSet != null)
- {
- resultSet.close();
- }
- }
+ }
+
+ /**
+ * @see org.alfresco.service.cmr.tagging.TaggingService#findTaggedNodesAndCountByTagName(StoreRef)
+ */
+ @Override
+ public List> findTaggedNodesAndCountByTagName(StoreRef storeRef)
+ {
+ String queryTaggeble = "ASPECT:\"" + ContentModel.ASPECT_TAGGABLE + "\"" + "-ASPECT:\"" + ContentModel.ASPECT_WORKING_COPY + "\"";
+ SearchParameters sp = new SearchParameters();
+ sp.setQuery(queryTaggeble);
+ sp.setLanguage(SearchService.LANGUAGE_LUCENE);
+ sp.addStore(storeRef);
+ sp.addFieldFacet(new FieldFacet("TAG"));
+
+ ResultSet resultSet = null;
+ try
+ {
+ // Do the search for nodes
+ resultSet = this.searchService.query(sp);
+ return resultSet.getFieldFacet("TAG");
+ }
+ finally
+ {
+ if (resultSet != null)
+ {
+ resultSet.close();
+ }
+ }
}
}
diff --git a/repository/src/main/java/org/alfresco/repo/thumbnail/CreateThumbnailActionExecuter.java b/repository/src/main/java/org/alfresco/repo/thumbnail/CreateThumbnailActionExecuter.java
index 9bd8a65864..058b614d95 100644
--- a/repository/src/main/java/org/alfresco/repo/thumbnail/CreateThumbnailActionExecuter.java
+++ b/repository/src/main/java/org/alfresco/repo/thumbnail/CreateThumbnailActionExecuter.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2005 - 2016 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -33,6 +33,9 @@ import org.alfresco.error.AlfrescoRuntimeException;
import org.alfresco.model.ContentModel;
import org.alfresco.repo.action.ParameterDefinitionImpl;
import org.alfresco.repo.action.executer.ActionExecuterAbstractBase;
+import org.alfresco.repo.rendition2.RenditionDefinition2;
+import org.alfresco.repo.rendition2.RenditionDefinitionRegistry2;
+import org.alfresco.repo.rendition2.RenditionService2;
import org.alfresco.service.cmr.action.Action;
import org.alfresco.service.cmr.action.ActionServiceTransientException;
import org.alfresco.service.cmr.action.ParameterDefinition;
@@ -71,6 +74,8 @@ public class CreateThumbnailActionExecuter extends ActionExecuterAbstractBase
// Size limitations (in KBytes) indexed by mimetype for thumbnail creation
private HashMap mimetypeMaxSourceSizeKBytes;
+ private RenditionService2 renditionService2;
+
/** Action name and parameters */
public static final String NAME = "create-thumbnail";
public static final String PARAM_CONTENT_PROPERTY = "content-property";
@@ -104,7 +109,12 @@ public class CreateThumbnailActionExecuter extends ActionExecuterAbstractBase
{
this.mimetypeMaxSourceSizeKBytes = mimetypeMaxSourceSizeKBytes;
}
-
+
+ public void setRenditionService2(RenditionService2 renditionService2)
+ {
+ this.renditionService2 = renditionService2;
+ }
+
/**
* Enable thumbnail creation at all regardless of mimetype.
* @param generateThumbnails a {@code false} value turns off all thumbnail creation.
@@ -187,30 +197,44 @@ public class CreateThumbnailActionExecuter extends ActionExecuterAbstractBase
}
}
}
-
+
// Create the thumbnail
try
{
- TransformationOptions options = details.getTransformationOptions();
- this.thumbnailService.createThumbnail(actionedUponNodeRef, contentProperty, details.getMimetype(), options, thumbnailName, null);
+ boolean async = action.getExecuteAsychronously();
+ RenditionDefinition2 renditionDefinition = null;
+ if (async)
+ {
+ RenditionDefinitionRegistry2 renditionDefinitionRegistry2 = renditionService2.getRenditionDefinitionRegistry2();
+ renditionDefinition = renditionDefinitionRegistry2.getRenditionDefinition(thumbnailName);
+ }
+ if (async && renditionDefinition != null)
+ {
+ renditionService2.render(actionedUponNodeRef, thumbnailName);
+ }
+ else
+ {
+ TransformationOptions options = details.getTransformationOptions();
+ this.thumbnailService.createThumbnail(actionedUponNodeRef, contentProperty, details.getMimetype(), options, thumbnailName, null);
+ }
}
catch (ContentServiceTransientException cste)
{
// any transient failures in the thumbnail creation must be handled as transient failures of the action to execute.
StringBuilder msg = new StringBuilder();
- msg.append("Creation of thumbnail '") .append(details.getName()) .append("' declined");
+ msg.append("Creation of thumbnail '").append(details.getName()).append("' declined");
if (logger.isDebugEnabled())
{
logger.debug(msg.toString());
}
-
+
throw new ActionServiceTransientException(msg.toString(), cste);
}
catch (Exception exception)
{
final String msg = "Creation of thumbnail '" + details.getName() + "' failed";
logger.info(msg);
-
+
// We need to rethrow in order to trigger the compensating action.
// See AddFailedThumbnailActionExecuter
throw new AlfrescoRuntimeException(msg, exception);
diff --git a/repository/src/main/java/org/alfresco/transform/client/registry/CombinedConfig.java b/repository/src/main/java/org/alfresco/transform/client/registry/CombinedConfig.java
index 6a5b192901..dcd0b8f9d0 100644
--- a/repository/src/main/java/org/alfresco/transform/client/registry/CombinedConfig.java
+++ b/repository/src/main/java/org/alfresco/transform/client/registry/CombinedConfig.java
@@ -2,7 +2,7 @@
* #%L
* Alfresco Repository
* %%
- * Copyright (C) 2019 Alfresco Software Limited
+ * Copyright (C) 2005 - 2020 Alfresco Software Limited
* %%
* This file is part of the Alfresco software.
* If the software was purchased under a paid Alfresco license, the terms of
@@ -48,7 +48,6 @@ import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
-import java.util.Collections;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
@@ -56,6 +55,9 @@ import java.util.Map;
import java.util.Set;
import java.util.stream.Collectors;
+import static org.alfresco.repo.content.metadata.AsynchronousExtractor.isMetadataEmbedMimetype;
+import static org.alfresco.repo.content.metadata.AsynchronousExtractor.isMetadataExtractMimetype;
+
/**
* This class reads multiple T-Engine config and local files and registers them all with a registry as if they were all
* in one file. Transform options are shared between all sources.
@@ -398,7 +400,13 @@ public class CombinedConfig
// the source matches the last intermediate.
Set supportedSourceAndTargets = sourceMediaTypesAndMaxSizes.stream().
flatMap(s -> stepTransformer.getSupportedSourceAndTargetList().stream().
- filter(st -> st.getSourceMediaType().equals(src)).
+ filter(st ->
+ {
+ String targetMimetype = st.getTargetMediaType();
+ return st.getSourceMediaType().equals(src) &&
+ !(isMetadataExtractMimetype(targetMimetype) ||
+ isMetadataEmbedMimetype(targetMimetype));
+ }).
map(t -> t.getTargetMediaType()).
map(trg -> SupportedSourceAndTarget.builder().
withSourceMediaType(s.getSourceMediaType()).
diff --git a/repository/src/main/resources/alfresco/content-services-context.xml b/repository/src/main/resources/alfresco/content-services-context.xml
index 8f39d8aeea..95648c0748 100644
--- a/repository/src/main/resources/alfresco/content-services-context.xml
+++ b/repository/src/main/resources/alfresco/content-services-context.xml
@@ -253,7 +253,10 @@
-
+
+
diff --git a/repository/src/main/resources/alfresco/rendition-services2-context.xml b/repository/src/main/resources/alfresco/rendition-services2-context.xml
index 7a88f3b2f1..4280e29e6f 100644
--- a/repository/src/main/resources/alfresco/rendition-services2-context.xml
+++ b/repository/src/main/resources/alfresco/rendition-services2-context.xml
@@ -59,6 +59,7 @@
+
diff --git a/repository/src/main/resources/alfresco/repository.properties b/repository/src/main/resources/alfresco/repository.properties
index 9cc7900f66..5aaa00f2bb 100644
--- a/repository/src/main/resources/alfresco/repository.properties
+++ b/repository/src/main/resources/alfresco/repository.properties
@@ -516,6 +516,9 @@ system.thumbnail.quietPeriod=604800
system.thumbnail.quietPeriodRetriesEnabled=true
system.thumbnail.redeployStaticDefsOnStartup=true
+content.metadata.async.extract.enabled=true
+content.metadata.async.embed.enabled=true
+
# The default timeout for metadata mapping extracters
content.metadataExtracter.default.timeoutMs=20000
diff --git a/repository/src/main/resources/alfresco/thumbnail-service-context.xml b/repository/src/main/resources/alfresco/thumbnail-service-context.xml
index 4f1020f6b2..a1dcdf173d 100644
--- a/repository/src/main/resources/alfresco/thumbnail-service-context.xml
+++ b/repository/src/main/resources/alfresco/thumbnail-service-context.xml
@@ -276,7 +276,8 @@