Develop Reference

Apache Poi excel remove blank Rows Within range

When I try to upload this file to my application, It shows an error in row 4. When I try
int totalRows = worksheet.getPhysicalNumberOfRows(); This shows incorrect number of rows(like 26,306). But this error only occurs in some excel files. I want to add records to my application which contain in excel file. How to delete this empty records?
This is my code
List<NewLocationFile> newLocationList = new ArrayList<>();
StringBuilder columnBuffer = new StringBuilder();
String comma = "";
List<NewLocationFile> updatedLocationList = new ArrayList<>();
try (Workbook workbook = new XSSFWorkbook(inputStream);) {
Sheet worksheet = workbook.getSheetAt(0);
int totalRows = worksheet.getPhysicalNumberOfRows();
worksheet.removeRow(worksheet.getRow(0));// remove header
LOGGER.info("readNewLocationFileRequest:traceId={}|totalRows={}",traceId,totalRows);
if (totalRows <= 1) {
throw new PSException(ErrorCode.INVALID_INPUT_PROVIDED, "Empty excel sheet ");
}
else {
newLocationList.addAll(locationDetails(worksheet, traceId));
}
private List<NewLocationFile> locationDetails(Sheet worksheet String traceId) {
List<NewLocationFile> newLocationList = new ArrayList<>();
int j = 0;
for (Row row : worksheet) {
j++;
int excelSheetRow = j + 1;
newLocationList.add(returnLocations(row, excelSheetRow, userBrn,traceId));
}
String converToString = CommonUtil.convertToString(newLocationList);
return newLocationList;
}
private NewLocationFile returnLocations(Row row,int excelSheetRow,String traceId)
{
String productCategory = null;
//initiate all values to null here
if (dataFormatter.formatCellValue(row.getCell(13)).trim().length() > 0) {
productCategory = CommonUtil.getWorkSheetCellStringValue(row.getCell(13)).toUpperCase();
} else {
throw new PostSaleModificationException(ErrorCode.INVALID_PRODUCT_TYPE,
"Invalid product category in row :" + excelSheetRow);
}
//All validations listed here
newLocation.setComplexProduct(complexProduct);
//set all values here
}
But Error message pop-up is displayed "Invalid product category in row 4" But this sheet has only 3 rows.

I found this solution ;)
List<NewLocationFile> newLocationList = new ArrayList<>();
StringBuilder columnBuffer = new StringBuilder();
String comma = "";
List<NewLocationFile> updatedLocationList = new ArrayList<>();
try (Workbook workbook = new XSSFWorkbook(inputStream);) {
Sheet worksheet = workbook.getSheetAt(0);
int totalRows = worksheet.getPhysicalNumberOfRows();
worksheet.removeRow(worksheet.getRow(0));// remove header
removeEmptyRows(worksheet);
LOGGER.info("readNewLocationFileRequest:traceId={}|totalRows={}",traceId,totalRows);
if (totalRows <= 1) {
throw new PSException(ErrorCode.INVALID_INPUT_PROVIDED, "Empty excel sheet ");
}
else {
newLocationList.addAll(locationDetails(worksheet, traceId));
}
private Sheet removeEmptyRows(Sheet worksheet) {
boolean stop = false;
boolean nonBlankRowFound;
short c;
XSSFRow lastRow = null;
XSSFCell cell = null;
while (!stop) {
nonBlankRowFound = false;
lastRow = (XSSFRow) worksheet.getRow(worksheet.getLastRowNum());
for (c = lastRow.getFirstCellNum(); c <= lastRow.getLastCellNum(); c++) {
cell = lastRow.getCell(c);
if (cell != null && lastRow.getCell(c).getCellType() != CellType.BLANK) {
nonBlankRowFound = true;
}
}
if (nonBlankRowFound == true) {
stop = true;
} else {
worksheet.removeRow(lastRow);
}
}
return worksheet;
}

Blank row after header

I am writing existing excel by merging many excel files, after generating of final excel file blank row is adding up after headers.
Below is my code which reads data from multiple files and write to particular blank file which have pivot formulas set.
I tried even by
1. Setting createRow(0) , then started filling data from next row.
2. Tried of maintaining int counter, but still didn't work
3. Tried incrementing getLastRowNum() count, but no use
public class DCSReadImpl implements ReadBehavior {
Logger log = Logger.getLogger(DCSReadImpl.class.getName());
#SuppressWarnings("resource")
#Override
public Sheet readReport(Workbook workbook,Map<String,String> masterMap, Properties properties) {
//int firstRow = 0;
int outRowCounter = 0;
String fileToMove= "";
boolean headers = true;
Row outputRow = null;
Sheet outputSheet = null;
Workbook wb = new XSSFWorkbook();
try {
outputSheet = wb.createSheet("Data");
log.info("**** Set headers start"); // this used to be different method
int cellNo = 0;
outputRow = outputSheet.createRow(0);
for(String headerName : ReportConstants.DCS_OUTPUT_HEADER){
outputRow.createCell(cellNo).setCellValue(headerName);
cellNo++;
}
//outRowCounter++;
log.info("**** Set headers completed");
log.info("Read input file(s) for DCS report");
log.info("Input File Path : " + properties.getProperty(ReportConstants.DCS_INPUT_PATH));
File inputDir = new File(properties.getProperty(ReportConstants.DCS_INPUT_PATH));
File[] dirListing = inputDir.listFiles();
if (0 == dirListing.length) {
throw new Exception(properties.getProperty(ReportConstants.DCS_INPUT_PATH) + " is empty");
}
for (File file : dirListing) {
log.info("Processing : " + file.getName());
fileToMove = file.getName();
XSSFWorkbook inputWorkbook = null;
try {
inputWorkbook = new XSSFWorkbook(new FileInputStream(file));
} catch (Exception e) {
throw new Exception("File is already open, please close the file");
}
XSSFSheet inputsheet = inputWorkbook.getSheet("Sheet1");
Iterator<Row> rowItr = inputsheet.iterator();
int headItr = 0;
//log.info("Validating headers : " + file.getName());
while (rowItr.hasNext()) {
Row irow = rowItr.next();
Iterator<Cell> cellItr = irow.cellIterator();
int cellIntItr = 0;
String key = "";
int rowN = outputSheet.getLastRowNum() + 1;
outputRow = outputSheet.createRow(rowN);
Cell outCell = null;
while (cellItr.hasNext()) {
Cell inputCell = cellItr.next();
if (0 == inputCell.getRowIndex()) {
if (!FileUtility.checkHeaders(headItr, inputCell.getStringCellValue().trim(),
ReportConstants.DCS_INPUT_HEADER)) {
throw new Exception("Incorrect header(s) present in Input File, Expected : "
+ ReportConstants.DCS_INPUT_HEADER[headItr]);
}
headItr++;
} else {
//outCell = outputRow.createCell(cellIntItr);
if (0 == inputCell.getColumnIndex()) {
key = inputCell.getStringCellValue().trim();
} else if (2 == inputCell.getColumnIndex()) {
key = key + ReportConstants.DEL + inputCell.getStringCellValue().trim();
}
if (7 == cellIntItr){
outCell = outputRow.createCell(cellIntItr);
outCell.setCellValue(getValue(masterMap, key, 0));
cellIntItr++;
outCell = outputRow.createCell(cellIntItr);
outCell.setCellValue(getValue(masterMap, key, 1));
cellIntItr++;
outCell = outputRow.createCell(cellIntItr);
outCell.setCellValue(getValue(masterMap, key, 2));
cellIntItr++;
}
// Check the cell type and format accordingly
switch (inputCell.getCellType()) {
case Cell.CELL_TYPE_NUMERIC:
outCell = outputRow.createCell(cellIntItr);
outCell.setCellValue(inputCell.getNumericCellValue());
break;
case Cell.CELL_TYPE_STRING:
outCell = outputRow.createCell(cellIntItr);
outCell.setCellValue(inputCell.getStringCellValue().trim());
break;
}
cellIntItr++;
}
}
//outRowCounter ++ ;
}
if(!fileToMove.isEmpty()){
FileUtility.checkDestinationDir(""+properties.get(ReportConstants.DCS_ARCHIVE_PATH));
FileUtility.moveFile(properties.get(ReportConstants.DCS_INPUT_PATH) + fileToMove,
properties.get(ReportConstants.DCS_ARCHIVE_PATH)+fileToMove+FileUtility.getPattern());
}
}
} catch (Exception e) {
log.error("Exception occured : ", e);
}
FileOutputStream outputStream;
try {
outputStream = new FileOutputStream("D:\\DCS\\Output\\Krsna_"+FileUtility.getPattern()+".xlsx");
wb.write(outputStream);
} catch (Exception e) {
e.printStackTrace();
}
return outputSheet;
}
private String getValue(Map<String, String> masterMap, String cellKey, int index) {
String value = masterMap.get(cellKey);
if (null != value) {
String cellValue[] = value.split("\\" + ReportConstants.DEL);
return cellValue[index];
} else {
return "";
}
}
}
There should not be blank row after header row. That is in between of 0th row and 1st row (hope my understanding is correct on row indexing). I know this is very basic question :-(

Unable to write new excel using Apache POI after removing duplicate rows

I am new to Apache POI.
I have written a small code for removing duplicate records from a excel file. I am successfully able to identify the duplicate records across sheets but when writing to a new file after removing records, no output is being generated.
Please help where I am goin wrong?
Am I writing properly ?? Or am missing something?
public static void main(String args[]) {
DataFormatter formatter = new DataFormatter();
HSSFWorkbook input_workbook;
HSSFWorkbook workbook_Output_Final;
HSSFSheet input_workbook_sheet;
HSSFRow row_Output;
HSSFRow row_1_index;
HSSFRow row_2_index;
String value1 = "";
String value2 = "";
int count;
//main try catch block starts
try {
FileInputStream input_file = new FileInputStream("E:\\TEST\\Output.xls"); //reading from input file
input_workbook = new HSSFWorkbook(new POIFSFileSystem(input_file));
for (int sheetnum = 0; sheetnum < input_workbook.getNumberOfSheets(); sheetnum++) { //traversing sheets
input_workbook_sheet = input_workbook.getSheetAt(sheetnum);
int input_workbook_sheet_total_row = input_workbook_sheet.getLastRowNum(); //fetching last row nmber
for (int input_workbook_sheet_row_1 = 0; input_workbook_sheet_row_1 <= input_workbook_sheet_total_row; input_workbook_sheet_row_1++) { //traversing row 1
for (int input_workbook_sheet_row_2 = 0; input_workbook_sheet_row_2 <= input_workbook_sheet_total_row; input_workbook_sheet_row_2++) {
row_1_index = input_workbook_sheet.getRow(input_workbook_sheet_row_1); //fetching one iteration row index
row_2_index = input_workbook_sheet.getRow(input_workbook_sheet_row_2); //fetching sec iteration row index
if (row_1_index != row_2_index) {
count = 0;
value1 = "";
value2 = "";
for (int row_1_index_cell = 0; row_1_index_cell < row_1_index.getLastCellNum(); row_1_index_cell++) { //traversing cell for each row
try {
value1 = value1 + formatter.formatCellValue(row_1_index.getCell(row_1_index_cell)); //fetching row cells value
value2 = value2 + formatter.formatCellValue(row_2_index.getCell(row_1_index_cell)); //fetching row cells value
} catch (NullPointerException e) {
}
count++;
if (count == row_1_index.getLastCellNum()) {
if (value1.hashCode() == value2.hashCode()) { //remove the duplicate logic
System.out.println("deleted : " + row_2_index);
System.out.println("------------------");
input_workbook_sheet.removeRow(row_2_index);
}
}
}
}
}
}
}
FileOutputStream fileOut = new FileOutputStream("E:\\TEST\\workbook.xls");
input_workbook.write(fileOut);
fileOut.close();
input_file.close();
} catch (Exception e) {
//e.printStackTrace();
}
//main try catch block ends
}

A couple of things to note:
you swallow any kind of Exception; Igotsome nullpointers with my test data, and that would prevent the workbook from being written
when removing rows, it is an old trick to move backwards through the row numbers because then you don't have to adjust for the row number you have just removed
the code empties the row, but it doesn't move all rows upwards (=there is a gap after the delete). If you want to remove that gap, you can work with shiftRows
you compare things by hashcode, which is possible (in some use cases), but I feel like .equals() is what you want to do. See also Relationship between hashCode and equals method in Java
Here's some code that worked for my test data, feel free to comment if something doesn't work with your data:
public static void main(String args[]) throws IOException {
DataFormatter formatter = new DataFormatter();
HSSFWorkbook input_workbook;
HSSFWorkbook workbook_Output_Final;
HSSFSheet input_workbook_sheet;
HSSFRow row_Output;
HSSFRow row_1_index;
HSSFRow row_2_index;
String value1 = "";
String value2 = "";
int count;
FileInputStream input_file = new FileInputStream("c:\\temp\\test.xls");
input_workbook = new HSSFWorkbook(new POIFSFileSystem(input_file));
for (int sheetnum = 0; sheetnum < input_workbook.getNumberOfSheets(); sheetnum++) {
input_workbook_sheet = input_workbook.getSheetAt(sheetnum);
int input_workbook_sheet_total_row = input_workbook_sheet.getLastRowNum();
for (int input_workbook_sheet_row_1 = input_workbook_sheet_total_row; input_workbook_sheet_row_1 >=0; input_workbook_sheet_row_1--) { // traversing
for (int input_workbook_sheet_row_2 = input_workbook_sheet_total_row; input_workbook_sheet_row_2 >= 0 ; input_workbook_sheet_row_2--) {
row_1_index = input_workbook_sheet.getRow(input_workbook_sheet_row_1);
row_2_index = input_workbook_sheet.getRow(input_workbook_sheet_row_2);
if (row_1_index != null && row_2_index != null && row_1_index != row_2_index) {
count = 0;
value1 = "";
value2 = "";
int row_1_max = row_1_index.getLastCellNum() - 1;
for (int row_1_index_cell = 0; row_1_index_cell < row_1_max; row_1_index_cell++) {
try {
value1 = value1 + formatter.formatCellValue(row_1_index.getCell(row_1_index_cell));
value2 = value2 + formatter.formatCellValue(row_2_index.getCell(row_1_index_cell));
} catch (NullPointerException e) {
e.printStackTrace();
}
count++;
if (value1.equals(value2)) {
System.out.println("deleted : " + row_2_index.getRowNum());
System.out.println("------------------");
input_workbook_sheet.removeRow(row_2_index);
input_workbook_sheet.shiftRows(
row_2_index.getRowNum() + 1,
input_workbook_sheet_total_row,
-1,
true,
true);
}
}
}
}
}
}
FileOutputStream fileOut = new FileOutputStream("c:\\temp\\workbook.xls");
input_workbook.write(fileOut);
fileOut.close();
input_file.close();
input_workbook.close();
}

Apache POI - Reading excel file in 2D array - returning null values

I am trying to read Excel -2*2 matrix through Apache POI. But the first value returned by 2D array is [null,null]. Please check my code and advise for suitable corrections.
public String[][] getDataArray(String sheetName)
{
String value ="";
String[][] data = null;
int rowCount = wb.getSheet(sheetName).getLastRowNum();
int colCount = wb.getSheet(sheetName).getRow(1).getLastCellNum()-1;
data = new String[rowCount][colCount];
for(int i=1; i<=rowCount;i++)
{
Row row = wb.getSheet(sheetName).getRow(i);
for(int j=0;j<colCount;j++)
{
Cell cell = row.getCell(j);
if(cell.getCellType()==Cell.CELL_TYPE_NUMERIC)
{
value = ""+cell.getStringCellValue();
}
else
{
value = cell.getStringCellValue();
}
data[i][j] = value;
}
}
return data;
}
The debug view where we can see that the first value stored in the variable data is null, null
The excel which i am trying to read. I need only the userName and password data(2*2) alone. Not the header and Run mode datas.

Of course the value in the index 0 will be null because the i starts from 1 and not 0
for (int i = 1; i <= rowCount; i++) //i starts from one
...
data[i][j] = value;
either initialize the i from 0 or do like this
data[i-1][j] = value;

public static String[][] getSheetData(final String fileName, final String workSheetName)
throws Exception {
Integer lastRow = null;
short lastCol = 0;
String[][] sheetData = null;
FileInputStream file=new FileInputStream(MettlTest.class.getClass().getResource("/" + fileName).getPath());
workbook = new XSSFWorkbook(file);
sheet = workbook.getSheet(workSheetName);
try {
XSSFRow row;
XSSFCell cell;
lastRow = sheet.getPhysicalNumberOfRows();
lastCol = sheet.getRow(1).getLastCellNum();
sheetData = new String[lastRow - 1][lastCol];
for (int r = 1; r < lastRow; r++) {
row = sheet.getRow(r);
if (row != null) {
for (int c = 0; c < lastCol; c++) {
cell = row.getCell(c);
if (cell == null) {
sheetData[r][c] = null;
} else {
sheetData[r-1][c] = new DataFormatter().formatCellValue(cell);
}
}
}
}
return sheetData;
}
catch (final Exception e) {
throw e;
}
finally {
try {
file.close();
} catch (IOException io) {
Reporter.log("Unable to close File : " + fileName);
throw io;
}
}

copy excel sheet(With charts) to another excel sheet

I am using APACHE POI 3.0 to add sheets to existing excel sheet. It works fine.
But as APACHE POI has limitations about making charts, I used a template excel file to create charts, which also worked fine, but this always result in new excel file.
If I have an existing excel sheet and I want to add a sheet, having charts, I am not able to do it. As, when I create charts, I use template file and it always makes a new excel file.
so I was wondering if there is any solution of it of adding sheets to excel, where the sheets have charts
public class TagBrowserSelection
{
private static String[] excelBarPlot_Template = { "","barPlot_1Panel_template.xlsx"};
private static String[] excelPieChart_Template = { "","pieChart_1Panel_template.xlsx"};
private static String[] excelPieAndBarPlot_Template = { "","pieAndBarChart_1Panel_template.xlsx"};
private static String REGEX = "";
static public boolean makeTagBrowserSelection(String strOutputFileName, ArrayList<TagBrowserChildPanel> childList, String sheetName, boolean addSheet, ArrayList<Boolean> chartAttributes)
{
// chart attributes
boolean addBarChart = chartAttributes.get(0);
boolean addPieChart = chartAttributes.get(1);
boolean addNoTag = chartAttributes.get(2);
boolean addZeros = chartAttributes.get(3);
REGEX = "^" + sheetName;
Pattern p = Pattern.compile(REGEX);
String[] templateArray = null;
if (addBarChart && addPieChart)
templateArray = excelPieAndBarPlot_Template;
else if (addBarChart)
templateArray = excelBarPlot_Template;
else if (addPieChart)
templateArray = excelPieChart_Template;
try
{
int number = childList.size();
XSSFWorkbook workbook = null;
XSSFWorkbook wb = null;
XSSFSheet sheet = null;
int col_num = 0;
int row_num = 0;
XSSFRow row = null;
XSSFCell cell = null;
// if adding sheet to existing excel file
if (addSheet)
{
FileInputStream fis = new FileInputStream(new File(strOutputFileName));
workbook = new XSSFWorkbook(fis);
fis.close();
// number of existing sheets in excel file
int numberOfSheets = workbook.getNumberOfSheets();
// check is sheetName exists already
if (isSheetExist(sheetName, workbook))
{
int counter = 1;
for (int ii = 0; ii < numberOfSheets; ii++)
{
Matcher m = p.matcher(workbook.getSheetName(ii));
if (m.find())
counter++;
}
sheetName = sheetName + " (" + counter + ")";
}
}
else
{
workbook = new XSSFWorkbook();
}
======================================================================
// if template file needs to be used(if bar chart/pie chart option is selected)
if (templateArray != null)
{
InputStream is = TagBrowserSelection.class.getClassLoader().getResourceAsStream(templateArray[number]);
wb = new XSSFWorkbook(OPCPackage.open(is));
sheet = wb.getSheetAt(0);
// wb.close();
}
else
{
sheet = workbook.createSheet(sheetName);
}
// Freeze top two row
// sheet.createFreezePane(0, 1, 0, 1);
// Filling up the workbook and performing the row/column formatting
for (TagBrowserChildPanel child : childList)
{
// Check if row is already created before(previous tag category)
row = sheet.getRow(0);
if (row == null)
row = sheet.createRow(0);
// Adding tag category name as header
String tagCategory = child.getSelectedCategory().getName();
cell = row.createCell(col_num);
cell.setCellValue(tagCategory);
row = sheet.getRow(1);
if (row == null)
row = sheet.createRow(1);
// Adding column headers
cell = row.createCell(col_num);
cell.setCellValue("tag");
cell = row.createCell(col_num + 1);
cell.setCellValue("counts");
row_num = 2;
// Adding tag category document summary(name and counts)
ArrayList<TagSummaryItem> tagSummary = child.getTagChartCounts();
for (int i = 0; i < tagSummary.size(); i++)
{
// Check if row is already created before(previous tag category)
row = sheet.getRow(row_num);
if (row == null)
row = sheet.createRow(row_num);
cell = row.createCell(col_num);
if (!addNoTag)
{
if (tagSummary.get(i).m_strTag == "[No Tag]")
continue;
}
if (!addZeros)
{
if (tagSummary.get(i).m_nCount == 0)
continue;
}
cell.setCellValue(tagSummary.get(i).m_strTag);
cell = row.createCell(col_num + 1);
cell.setCellValue(tagSummary.get(i).m_nCount);
row_num++;
}
// auto-size of tag column
sheet.autoSizeColumn(col_num);
col_num = col_num + 3;
}
FileOutputStream out = new FileOutputStream(strOutputFileName);
if (templateArray != null)
{
wb.setSheetName(0, sheetName);
wb.write(out);
wb.close();
}
else
{
workbook.write(out);
workbook.close();
}
out.close();
}
catch (Exception e)
{
// TODO Auto-generated catch block
e.printStackTrace();
}
return true;
}
Above is my code, its one code. I split into two sections. Section is the one which uses template to make chart excel sheet.

there's the method cloneSheet() in the HSSFWorkbook class. Try it.