Apache
/
poi
mirror of https://github.com/apache/poi.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

continue SXSSF docs updates and polishing 

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1133782 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Yegor Kozlov 2011-06-09 10:38:31 +00:00
parent 21405bf0e3
commit 84de0558db
4 changed files with 95 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
src/documentation/content/xdocs/spreadsheet/how-to.xml
View File

@ -626,7 +626,7 @@ public class ExampleEventUserModel {
<anchor id="sxssf"/>
<section><title>SXSSF (Streaming Usermodel API)</title>
<p>
XSSF is an API-compatible streaming extension of XSSF to be used when
SXSSF (package: org.apache.poi.xssf.streaming) is an API-compatible streaming extension of XSSF to be used when
very large spreadsheets have to be produced, and heap space is limited.
SXSSF achieves its low memory footprint by limiting access to the rows that
are within a sliding window, while XSSF gives access to all rows in the
@ -634,21 +634,30 @@ public class ExampleEventUserModel {
as they are written to the disk.
</p>
<p>
You can specify the window size at workbook construction time via <em>new SXSSFWorkbook(int windowSize)</em>
or you can set it per-sheet via <em>SXSSFSheet#setRandomAccessWindowSize(int windowSize)</em>
</p>
<p>
When a new row is created via createRow() and the total number
of unflushed records would exeed the specified window size, then the
of unflushed records would exceed the specified window size, then the
row with the lowest index value is flushed and cannot be accessed
via getRow() anymore.
</p>
<p>
A value of -1 indicates unlimited access. In this case all
records that have not been flushed by a call to flush() are available
The default window size is <em>100</em> and defined by SXSSFWorkbook.DEFAULT_WINDOW_SIZE.
</p>
<p>
A windowSize of -1 indicates unlimited access. In this case all
records that have not been flushed by a call to flushRows() are available
for random access.
</p>
<p> The example below writes a sheet with a window of 100 rows. When the row count reaches 101,
the row with rownum=0 is flushed to disk and removed from memory, when rownum reaches 102 then the row with rownum=1 is flushed, etc.
</p>
<source><![CDATA[
package com.dinom.excel;
import org.apache.poi.ss.SpreadsheetVersion;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
@ -656,38 +665,68 @@ import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.util.CellReference;
import org.apache.poi.xssf.streaming.SXSSFWorkbook;
public class Main {
public static void main(String[] args) throws Throwable {
Workbook wb = new SXSSFWorkbook(100); // keep 100 rows in memory
Workbook wb = new SXSSFWorkbook(100); // keep 100 rows in memory, exceeding rows will be flushed to disk
Sheet sh = wb.createSheet();
for(int rownum = 0; rownum < 100000; rownum++){
for(int rownum = 0; rownum < 1000; rownum++){
Row row = sh.createRow(rownum);
for(int cellnum = 0; cellnum < 1000; cellnum++){
for(int cellnum = 0; cellnum < 10; cellnum++){
Cell cell = row.createCell(cellnum);
String address = new CellReference(cell).formatAsString();
cell.setCellValue(address);
}
// previous row is withing the window and accessible
Row prev = sheet.getRow(rownum - 1);
for(Row rowInMemory : sh) {
// the row iterator iterates over rows in memory, i.e. over the last 100 rows
System.out.println("Row in memory: " + rowInMemory.getRowNum());
}
// attempt to access flushed rows results in a exception:
try {
Row firstRow = sheet.getRow(0);
} catch (Exception e){
System.out.println("cannot access flushed rows");
}
FileOutputStream out = new FileOutputStream("/temp/sxssf.xlsx");
wb.write(out);
out.close();
}
]]></source>
<p>The next example turns off auto-flashing (windowSize=-1) and the code manually controls how portions of data are written to disk</p>
<source><![CDATA[
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.util.CellReference;
import org.apache.poi.xssf.streaming.SXSSFWorkbook;
public static void main(String[] args) throws Throwable {
Workbook wb = new SXSSFWorkbook(-1); // turn off auto-flashing and accumulate all rows in memory
Sheet sh = wb.createSheet();
for(int rownum = 0; rownum < 1000; rownum++){
Row row = sh.createRow(rownum);
for(int cellnum = 0; cellnum < 10; cellnum++){
Cell cell = row.createCell(cellnum);
String address = new CellReference(cell).formatAsString();
cell.setCellValue(address);
}
// manually control how rows are flushed to disk
if(rownum % 100 == 0) {
((SXSSFSheet)sh).flushRows(100); // retain 100 last rows and flush all others
// ((SXSSFSheet)sh).flushRows() is a shortcut for ((SXSSFSheet)sh).flushRows(0),
// this method flushes all rows
}
}
FileOutputStream out = new FileOutputStream("/temp/sxssf.xlsx");
wb.write(out);
out.close();
}
}
]]></source>
</section>

11
src/documentation/content/xdocs/spreadsheet/index.xml
View File

@ -79,10 +79,10 @@
</section>
<section>
<title>SXSSF (SInce POI 3.8 beta3)</title>
<title>SXSSF (Since POI 3.8 beta3)</title>
<p>Since 3.8-beta3, POI provides a low-memory footprint SXSSF API built on top of XSSF.</p>
<p>
XSSF is an API-compatible streaming extension of XSSF to be used when
SXSSF is an API-compatible streaming extension of XSSF to be used when
very large spreadsheets have to be produced, and heap space is limited.
SXSSF achieves its low memory footprint by limiting access to the rows that
are within a sliding window, while XSSF gives access to all rows in the
@ -90,7 +90,10 @@ document. Older rows that are no longer in the window become inaccessible,
as they are written to the disk.
</p>
<p>
In auto-flush mode the size of the access window can be specified, to hold a certain number of rows in memory. When that value is reached, the creationof an additional row causes the row with the lowest index to to be removed from the access window and written to disk.. Or, the window size can be set to grow dynamically; it can be trimmed periodically by an explicit call to flush(int keepRows) as needed.
In auto-flush mode the size of the access window can be specified, to hold a certain number of rows in memory.
When that value is reached, the creation of an additional row causes the row with the lowest index to to be
removed from the access window and written to disk. Or, the window size can be set to grow dynamically;
it can be trimmed periodically by an explicit call to flushRows(int keepRows) as needed.
</p>
<p>
Due to the streaming nature of the implementation, there are the following
@ -102,6 +105,8 @@ limitations when compared to XSSF:
<li>Formula evaluation is not supported</li>
</ul>
<p> See more details at <link href="how-to.html#sxssf">SXSSF How-To</link></p>
<p>The table below synopsizes the comparative features of POI's Spreadsheet API:</p>
<p><em>Spreadsheet API Feature Summary</em></p>

4
src/examples/src/org/apache/poi/xssf/usermodel/examples/BigGridDemo.java
View File

@ -45,9 +45,11 @@ import org.apache.poi.xssf.usermodel.*;
* document. Older rows that are no longer in the window become inaccessible,
* as they are written to the disk.
* </p>
* See <a "http://poi.apache.org/spreadsheet/how-to.html#sxssf">
* http://poi.apache.org/spreadsheet/how-to.html#sxssf</a>.
*
* @author Yegor Kozlov
* @see <a "http://poi.apache.org/spreadsheet/how-to.html#sxssf">http://poi.apache.org/spreadsheet/how-to.html#sxssf</a>
*/
public class BigGridDemo {
private static final String XML_ENCODING = "UTF-8";

23
src/ooxml/java/org/apache/poi/xssf/streaming/SXSSFSheet.java
View File

@ -22,6 +22,7 @@ import java.util.Iterator;
import java.util.TreeMap;
import java.util.Map;
import org.apache.poi.hpsf.IllegalPropertySetDataException;
import org.apache.poi.ss.usermodel.*;
import org.apache.poi.ss.util.CellReference;
@ -1179,20 +1180,34 @@ public class SXSSFSheet implements Sheet, Cloneable
* A value of 0 is not allowed because it would flush any newly created row
* without having a chance to specify any cells.
*/
void setRandomAccessWindowSize(int value)
public void setRandomAccessWindowSize(int value)
{
assert value!=0;
if(value == 0 || value < -1) {
throw new IllegalArgumentException("RandomAccessWindowSize must be either -1 or a positive integer");
}
_randomAccessWindowSize=value;
}
/**
* Specifies how many rows can be accessed at most via getRow().
* The exeeding rows (if any) are flushed to the disk while rows
* with lower index values are flushed first.
*/
void flushRows(int remaining) throws IOException
public void flushRows(int remaining) throws IOException
{
while(_rows.size()>remaining) flushOneRow();
while(_rows.size() > remaining) flushOneRow();
}
/**
* Flush all rows to disk. After this call no rows can be accessed via getRow()
*
* @throws IOException
*/
public void flushRows() throws IOException
{
this.flushRows(0);
}
private void flushOneRow() throws IOException
{
Map.Entry<Integer,SXSSFRow> firstEntry=_rows.firstEntry();