Author: kwright
Date: Tue Oct 28 12:40:05 2014
New Revision: 1634859
URL: http://svn.apache.org/r1634859
Log:
Pull up fix for CONNECTORS-1088 from trunk.
Added:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Boilerplate.html
- copied unchanged from r1634857,
manifoldcf/trunk/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Boilerplate.html
Modified:
manifoldcf/branches/dev_1x/ (props changed)
manifoldcf/branches/dev_1x/CHANGES.txt
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tika/TikaExtractor.java
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_en_US.properties
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_ja_JP.properties
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_zh_CN.properties
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Exceptions.html
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/viewSpecification.html
Propchange: manifoldcf/branches/dev_1x/
------------------------------------------------------------------------------
Merged /manifoldcf/trunk:r1634857
Modified: manifoldcf/branches/dev_1x/CHANGES.txt
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/CHANGES.txt?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
--- manifoldcf/branches/dev_1x/CHANGES.txt (original)
+++ manifoldcf/branches/dev_1x/CHANGES.txt Tue Oct 28 12:40:05 2014
@@ -3,6 +3,9 @@ $Id$
======================= 1.8-dev =====================
+CONNECTORS-1088: Add boilerplate extraction to Tika extractor.
+(Arcadius Ahouansou, Karl Wright)
+
CONNECTORS-1087: Fix failing alfresco-webscript unit test.
(Karl Wright)
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tika/TikaExtractor.java
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tika/TikaExtractor.java?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tika/TikaExtractor.java
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tika/TikaExtractor.java
Tue Oct 28 12:40:05 2014
@@ -47,6 +47,7 @@ public class TikaExtractor extends org.a
private static final String EDIT_SPECIFICATION_JS = "editSpecification.js";
private static final String EDIT_SPECIFICATION_FIELDMAPPING_HTML =
"editSpecification_FieldMapping.html";
private static final String EDIT_SPECIFICATION_EXCEPTIONS_HTML =
"editSpecification_Exceptions.html";
+ private static final String EDIT_SPECIFICATION_BOILERPLATE_HTML =
"editSpecification_Boilerplate.html";
private static final String VIEW_SPECIFICATION_HTML =
"viewSpecification.html";
protected static final String ACTIVITY_EXTRACT = "extract";
@@ -373,10 +374,12 @@ public class TikaExtractor extends org.a
tabsArray.add(Messages.getString(locale,
"TikaExtractor.FieldMappingTabName"));
tabsArray.add(Messages.getString(locale,
"TikaExtractor.ExceptionsTabName"));
+ tabsArray.add(Messages.getString(locale,
"TikaExtractor.BoilerplateTabName"));
// Fill in the specification header map, using data from all tabs.
fillInFieldMappingSpecificationMap(paramMap, os);
fillInExceptionsSpecificationMap(paramMap, os);
+ fillInBoilerplateSpecificationMap(paramMap, os);
Messages.outputResourceWithVelocity(out,locale,EDIT_SPECIFICATION_JS,paramMap);
}
@@ -407,9 +410,11 @@ public class TikaExtractor extends org.a
// Fill in the field mapping tab data
fillInFieldMappingSpecificationMap(paramMap, os);
fillInExceptionsSpecificationMap(paramMap, os);
-
+ fillInBoilerplateSpecificationMap(paramMap, os);
+
Messages.outputResourceWithVelocity(out,locale,EDIT_SPECIFICATION_FIELDMAPPING_HTML,paramMap);
Messages.outputResourceWithVelocity(out,locale,EDIT_SPECIFICATION_EXCEPTIONS_HTML,paramMap);
+
Messages.outputResourceWithVelocity(out,locale,EDIT_SPECIFICATION_BOILERPLATE_HTML,paramMap);
}
/** Process a specification post.
@@ -514,6 +519,27 @@ public class TikaExtractor extends org.a
os.addChild(os.getChildCount(), node);
}
+ x = variableContext.getParameter(seqPrefix+"boilerplateclassname");
+ if (x != null)
+ {
+ int i = 0;
+ while (i < os.getChildCount())
+ {
+ SpecificationNode node = os.getChild(i);
+ if (node.getType().equals(TikaConfig.NODE_BOILERPLATEPROCESSOR))
+ os.removeChild(i);
+ else
+ i++;
+ }
+
+ if (x.length() > 0)
+ {
+ SpecificationNode node = new
SpecificationNode(TikaConfig.NODE_BOILERPLATEPROCESSOR);
+ node.setAttribute(TikaConfig.ATTRIBUTE_VALUE, x);
+ os.addChild(os.getChildCount(), node);
+ }
+ }
+
return null;
}
@@ -537,6 +563,7 @@ public class TikaExtractor extends org.a
// Fill in the map with data from all tabs
fillInFieldMappingSpecificationMap(paramMap, os);
fillInExceptionsSpecificationMap(paramMap, os);
+ fillInBoilerplateSpecificationMap(paramMap, os);
Messages.outputResourceWithVelocity(out,locale,VIEW_SPECIFICATION_HTML,paramMap);
@@ -590,6 +617,20 @@ public class TikaExtractor extends org.a
paramMap.put("IGNORETIKAEXCEPTIONS",ignoreTikaExceptions);
}
+ protected static void fillInBoilerplateSpecificationMap(Map<String,Object>
paramMap, Specification os)
+ {
+ String boilerplateClassName = "";
+ for (int i = 0; i < os.getChildCount(); i++)
+ {
+ SpecificationNode sn = os.getChild(i);
+ if (sn.getType().equals(TikaConfig.NODE_BOILERPLATEPROCESSOR))
+ {
+ boilerplateClassName =
sn.getAttributeValue(TikaConfig.ATTRIBUTE_VALUE);
+ }
+ }
+ paramMap.put("BOILERPLATECLASSNAME",boilerplateClassName);
+ }
+
protected static int handleTikaException(TikaException e)
throws IOException, ManifoldCFException, ServiceInterruption
{
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_en_US.properties
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_en_US.properties?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_en_US.properties
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_en_US.properties
Tue Oct 28 12:40:05 2014
@@ -15,6 +15,15 @@
TikaExtractor.FieldMappingTabName=Field mapping
TikaExtractor.ExceptionsTabName=Exceptions
+TikaExtractor.BoilerplateTabName=Boilerplate
+TikaExtractor.BoilerplateExtractorColon=Boilerplate extractor:
+TikaExtractor.NoExtractionSelected=-- No extraction selected --
+TikaExtractor.ExtractArticles=Extract articles
+TikaExtractor.ExtractArticleSentences=Extract article sentences
+TikaExtractor.BasicExtraction=Basic general-purpose extraction
+TikaExtractor.ExtractEverything=Extract everything
+TikaExtractor.ExtractLargestTextComponent=Extract the largest text component
of the document
+TikaExtractor.ExtractNumWords=Extract based on number of words per block
TikaExtractor.FieldMappings=Field mappings:
TikaExtractor.MetadataFieldName=Metadata field name
TikaExtractor.FinalFieldName=Final field name
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_ja_JP.properties
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_ja_JP.properties?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_ja_JP.properties
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_ja_JP.properties
Tue Oct 28 12:40:05 2014
@@ -13,16 +13,25 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-TikaExtractor.FieldMappingTabName=Field mapping
-TikaExtractor.ExceptionsTabName=Exceptions
-TikaExtractor.FieldMappings=Field mappings:
-TikaExtractor.MetadataFieldName=Metadata field name
-TikaExtractor.FinalFieldName=Final field name
-TikaExtractor.NoFieldMappingSpecified=No field mapping specified
-TikaExtractor.KeepAllMetadata=Keep all metadata:
-TikaExtractor.Add=Add
-TikaExtractor.AddFieldMapping=Add field mapping
-TikaExtractor.Delete=Delete
-TikaExtractor.DeleteFieldMapping=Delete field mapping
-TikaExtractor.NoFieldNameSpecified=Please specify a field name
-TikaExtractor.IgnoreTikaExceptions=Ignore Tika exceptions:
\ No newline at end of file
+TikaExtractor.FieldMappingTabName=ãã£ã¼ã«ããããã³ã°
+TikaExtractor.ExceptionsTabName=ä¾å¤
+TikaExtractor.BoilerplateTabName=Boilerplate
+TikaExtractor.BoilerplateExtractorColon=Boilerplate extractor:
+TikaExtractor.NoExtractionSelected=-- No extraction selected --
+TikaExtractor.ExtractArticles=Extract articles
+TikaExtractor.ExtractArticleSentences=Extract article sentences
+TikaExtractor.BasicExtraction=Basic general-purpose extraction
+TikaExtractor.ExtractEverything=Extract everything
+TikaExtractor.ExtractLargestTextComponent=Extract the largest text component
of the document
+TikaExtractor.ExtractNumWords=Extract based on number of words per block
+TikaExtractor.FieldMappings=ãã£ã¼ã«ããããã³ã°:
+TikaExtractor.MetadataFieldName=ã¡ã¿ãã¼ã¿ãã£ã¼ã«ãå
+TikaExtractor.FinalFieldName=æå¾ã®ãã£ã¼ã«ãå
+TikaExtractor.NoFieldMappingSpecified=ãã£ã¼ã«ããããã³ã°ãæå®ãã¦ãã
ãã
+TikaExtractor.KeepAllMetadata=å
¨ã¡ã¿ãã¼ã¿ãä¿å:
+TikaExtractor.Add=追å
+TikaExtractor.AddFieldMapping=ãã£ã¼ã«ããããã³ã°ã追å
+TikaExtractor.Delete=åé¤
+TikaExtractor.DeleteFieldMapping=ãã£ã¼ã«ããããã³ã°ãåé¤
+TikaExtractor.NoFieldNameSpecified=ãã£ã¼ã«ãåãæå®ãã¦ãã
ãã
+TikaExtractor.IgnoreTikaExceptions=Tikaä¾å¤ãç¡è¦ãã¦ãã ãã:
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_zh_CN.properties
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_zh_CN.properties?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_zh_CN.properties
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/native2ascii/org/apache/manifoldcf/agents/transformation/tika/common_zh_CN.properties
Tue Oct 28 12:40:05 2014
@@ -13,16 +13,25 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-TikaExtractor.FieldMappingTabName=Field mapping
-TikaExtractor.ExceptionsTabName=Exceptions
-TikaExtractor.FieldMappings=Field mappings:
-TikaExtractor.MetadataFieldName=Metadata field name
-TikaExtractor.FinalFieldName=Final field name
-TikaExtractor.NoFieldMappingSpecified=No field mapping specified
-TikaExtractor.KeepAllMetadata=Keep all metadata:
-TikaExtractor.Add=Add
-TikaExtractor.AddFieldMapping=Add field mapping
-TikaExtractor.Delete=Delete
-TikaExtractor.DeleteFieldMapping=Delete field mapping
-TikaExtractor.NoFieldNameSpecified=Please specify a field name
-TikaExtractor.IgnoreTikaExceptions=Ignore Tika exceptions:
\ No newline at end of file
+TikaExtractor.FieldMappingTabName=åæ®µæ å°
+TikaExtractor.ExceptionsTabName=å¼å¸¸
+TikaExtractor.BoilerplateTabName=Boilerplate
+TikaExtractor.BoilerplateExtractorColon=Boilerplate extractor:
+TikaExtractor.NoExtractionSelected=-- No extraction selected --
+TikaExtractor.ExtractArticles=Extract articles
+TikaExtractor.ExtractArticleSentences=Extract article sentences
+TikaExtractor.BasicExtraction=Basic general-purpose extraction
+TikaExtractor.ExtractEverything=Extract everything
+TikaExtractor.ExtractLargestTextComponent=Extract the largest text component
of the document
+TikaExtractor.ExtractNumWords=Extract based on number of words per block
+TikaExtractor.FieldMappings=åæ®µæ å°:
+TikaExtractor.MetadataFieldName=å
æ°æ®å段å
+TikaExtractor.FinalFieldName=æç»å段å
+TikaExtractor.NoFieldMappingSpecified=æªæå®å段æ å°
+TikaExtractor.KeepAllMetadata=ä¿åææå
æ°æ®:
+TikaExtractor.Add=æ·»å
+TikaExtractor.AddFieldMapping=æ·»å åæ®µæ å°
+TikaExtractor.Delete=å é¤
+TikaExtractor.DeleteFieldMapping=å é¤å段æ å°
+TikaExtractor.NoFieldNameSpecified=æªæå®å段å
+TikaExtractor.IgnoreTikaExceptions=忽ç¥Tikaå¼å¸¸:
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Exceptions.html
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Exceptions.html?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Exceptions.html
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/editSpecification_Exceptions.html
Tue Oct 28 12:40:05 2014
@@ -35,6 +35,6 @@
#else
<input type="hidden" name="s${SEQNUM}_ignoretikaexceptions_present"
value="true"/>
-<input type="hidden" name="s${SEQNUM}_ignoretikaexceptions"
value="$Encoder.bodyEscape($IGNORETIKAEXCEPTIONS)"/>
+<input type="hidden" name="s${SEQNUM}_ignoretikaexceptions"
value="$Encoder.attributeEscape($IGNORETIKAEXCEPTIONS)"/>
#end
\ No newline at end of file
Modified:
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/viewSpecification.html
URL:
http://svn.apache.org/viewvc/manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/viewSpecification.html?rev=1634859&r1=1634858&r2=1634859&view=diff
==============================================================================
---
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/viewSpecification.html
(original)
+++
manifoldcf/branches/dev_1x/connectors/tika/connector/src/main/resources/org/apache/manifoldcf/agents/transformation/tika/viewSpecification.html
Tue Oct 28 12:40:05 2014
@@ -56,5 +56,16 @@
<td
class="description"><nobr>$Encoder.bodyEscape($ResourceBundle.getString('TikaExtractor.IgnoreTikaExceptions'))</nobr></td>
<td
class="value"><nobr>$Encoder.bodyEscape($IGNORETIKAEXCEPTIONS)</nobr></td>
</tr>
+ <tr><td class="separator" colspan="2"><hr/></td></tr>
+ <tr>
+ <td
class="description"><nobr>$Encoder.bodyEscape($ResourceBundle.getString('TikaExtractor.BoilerplateExtractorColon'))</nobr></td>
+ <td class="value">
+#if ($BOILERPLATECLASSNAME == '')
+
<nobr>$Encoder.bodyEscape($ResourceBundle.getString('TikaExtractor.NoExtractionSelected'))</nobr>
+#else
+ <nobr>$Encoder.bodyEscape($BOILERPLATECLASSNAME)</nobr>
+#end
+ </td>
+ </tr>
</table>