You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@jackrabbit.apache.org by mr...@apache.org on 2008/04/11 13:47:47 UTC
svn commit: r647128 - in
/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor:
MsExcelTextExtractor.java MsWordTextExtractor.java
Author: mreutegg
Date: Fri Apr 11 04:47:42 2008
New Revision: 647128
URL: http://svn.apache.org/viewvc?rev=647128&view=rev
Log:
JCR-1534: Use POIExtractor wherever possible
Modified:
jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java
jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java
Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java?rev=647128&r1=647127&r2=647128&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java Fri Apr 11 04:47:42 2008
@@ -17,20 +17,14 @@
package org.apache.jackrabbit.extractor;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
-import org.apache.poi.hssf.usermodel.HSSFWorkbook;
-import org.apache.poi.hssf.usermodel.HSSFSheet;
-import org.apache.poi.hssf.usermodel.HSSFRow;
-import org.apache.poi.hssf.usermodel.HSSFCell;
+import org.apache.poi.hssf.extractor.ExcelExtractor;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.Reader;
import java.io.InputStream;
import java.io.IOException;
-import java.io.CharArrayWriter;
-import java.io.CharArrayReader;
import java.io.StringReader;
-import java.util.Iterator;
/**
* Text extractor for Microsoft Excel sheets.
@@ -65,40 +59,9 @@
public Reader extractText(InputStream stream,
String type,
String encoding) throws IOException {
- CharArrayWriter writer = new CharArrayWriter();
try {
POIFSFileSystem fs = new POIFSFileSystem(stream);
- HSSFWorkbook workbook = new HSSFWorkbook(fs);
-
- for (int i = 0; i < workbook.getNumberOfSheets(); i++) {
- HSSFSheet sheet = workbook.getSheetAt(i);
-
- Iterator rows = sheet.rowIterator();
- while (rows.hasNext()) {
- HSSFRow row = (HSSFRow) rows.next();
-
- Iterator cells = row.cellIterator();
- while (cells.hasNext()) {
- HSSFCell cell = (HSSFCell) cells.next();
- switch (cell.getCellType()) {
- case HSSFCell.CELL_TYPE_NUMERIC:
- String num = Double.toString(cell.getNumericCellValue()).trim();
- if (num.length() > 0) {
- writer.write(num + " ");
- }
- break;
- case HSSFCell.CELL_TYPE_STRING:
- String text = cell.getStringCellValue().trim();
- if (text.length() > 0) {
- writer.write(text + " ");
- }
- break;
- }
- }
- }
- }
-
- return new CharArrayReader(writer.toCharArray());
+ return new StringReader(new ExcelExtractor(fs).getText());
} catch (RuntimeException e) {
logger.warn("Failed to extract Excel text content", e);
return new StringReader("");
Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java?rev=647128&r1=647127&r2=647128&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java Fri Apr 11 04:47:42 2008
@@ -18,7 +18,7 @@
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
-import org.apache.poi.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.extractor.WordExtractor;
import java.io.Reader;
import java.io.InputStream;
@@ -40,7 +40,7 @@
* Force loading of dependent class.
*/
static {
- HWPFDocument.class.getName();
+ WordExtractor.class.getName();
}
/**
@@ -61,9 +61,7 @@
String type,
String encoding) throws IOException {
try {
- HWPFDocument doc = new HWPFDocument(stream);
- String text = doc.getRange().text();
- return new StringReader(text);
+ return new StringReader(new WordExtractor(stream).getText());
} catch (Exception e) {
logger.warn("Failed to extract Word text content", e);
return new StringReader("");