You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ju...@apache.org on 2008/03/26 19:32:05 UTC
svn commit: r641463 -
/incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
Author: jukka
Date: Wed Mar 26 11:32:00 2008
New Revision: 641463
URL: http://svn.apache.org/viewvc?rev=641463&view=rev
Log:
TIKA-132: Refactor Excel extractor to parse per sheet and add hyperlink support
- Refactored processCellValue to a getCellValue factory method
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
Modified: incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java
URL: http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java?rev=641463&r1=641462&r2=641463&view=diff
==============================================================================
--- incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java (original)
+++ incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java Wed Mar 26 11:32:00 2008
@@ -268,9 +268,14 @@
default:
if (insideWorksheet
&& record instanceof CellValueRecordInterface) {
- processCellValue(
- record.getSid(),
- (CellValueRecordInterface)record);
+ CellValueRecordInterface value =
+ (CellValueRecordInterface) record;
+ Cell cell = getCellValue(record.getSid(), value);
+ if (cell != null) {
+ Point point =
+ new Point(value.getColumn(), value.getRow());
+ currentSheet.put(point, cell);
+ }
}
break;
}
@@ -282,7 +287,7 @@
* @param sid record type identifier
* @param record The cell value record
*/
- private void processCellValue(
+ private Cell getCellValue(
short sid, CellValueRecordInterface record)
throws SAXException {
@@ -323,10 +328,9 @@
text = text.trim();
}
if (text != null && text.length() > 0) {
- currentSheet.put(
- new Point(record.getColumn(), record.getRow()),
- new TextCell(text));
+ return new TextCell(text);
}
+ return null;
}
/**