Author: mikemccand
Date: Tue Sep 11 14:55:33 2012
New Revision: 1383440
URL: http://svn.apache.org/viewvc?rev=1383440&view=rev
Log:
TIKA-918: extract chart name for charts embedded in Numbers documents
Added:
tika/trunk/tika-parsers/src/test/resources/test-documents/testNumbersCharts.numbers
(with props)
Modified:
tika/trunk/CHANGES.txt
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java
Modified: tika/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1383440&r1=1383439&r2=1383440&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Tue Sep 11 14:55:33 2012
@@ -11,6 +11,9 @@ Release 1.3 - Current Development
* PKCS7: Detached signatures no longer through NullPointerException
(TIKA-986).
+ * iWork: The chart name for charts embedded in numbers documents is
+ now extracted (TIKA-918).
+
Release 1.2 - 07/10/2012
---------------------------------
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java?rev=1383440&r1=1383439&r2=1383440&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/iwork/NumbersContentHandler.java
Tue Sep 11 14:55:33 2012
@@ -155,6 +155,15 @@ class NumbersContentHandler extends Defa
xhtml.element("td",
menuItems.get(attributes.getValue("sfa:IDREF")));
currentColumn++;
}
+
+ if ("sf:chart-name".equals(qName)) {
+ // Extract chart name:
+ xhtml.startElement("div", "class", "chart");
+ xhtml.startElement("h1");
+ xhtml.characters(attributes.getValue("sfa:string"));
+ xhtml.endElement("h1");
+ xhtml.endElement("div");
+ }
}
@Override
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java?rev=1383440&r1=1383439&r2=1383440&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/iwork/IWorkParserTest.java
Tue Sep 11 14:55:33 2012
@@ -416,6 +416,18 @@ public class IWorkParserTest extends Tes
assertContains(contents, commentB);
}
+ // TIKA-918
+ public void testNumbersExtractChartNames() throws Exception {
+ InputStream input =
IWorkParserTest.class.getResourceAsStream("/test-documents/testNumbersCharts.numbers");
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ iWorkParser.parse(input, handler, metadata, parseContext);
+ String contents = handler.toString();
+ assertContains(contents, "Expenditure by Category");
+ assertContains(contents, "Currency Chart name");
+ assertContains(contents, "Chart 2");
+ }
+
public void assertContains(String haystack, String needle) {
assertTrue(needle + " not found in:\n" + haystack,
haystack.contains(needle));
}
Added:
tika/trunk/tika-parsers/src/test/resources/test-documents/testNumbersCharts.numbers
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testNumbersCharts.numbers?rev=1383440&view=auto
==============================================================================
Binary file - no diff available.
Propchange:
tika/trunk/tika-parsers/src/test/resources/test-documents/testNumbersCharts.numbers
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream