我正在使用POI的XSSF和SAX（事件API）阅读Excel文件。 Excel工作表有数千行，所以这是我发现具有良好性能的唯一方法。现在我想从一个特别的行读取Excel文件，例如第6行，因为这些Excel文件每天都会更新，我存储了我已经存储的最后一行，所以我只能读取新行。
如何从一行开始？
private void getExcelField(AcquisitionForm acquisitionForm) throws ExcelReadException, IOException{
InputStream stream=null;
OPCPackage p=null;
try{
p = OPCPackage.open(acquisitionForm.getDatatablePath(), PackageAccess.READ);
ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(p);
XSSFReader xssfReader = new XSSFReader(p);
StylesTable styles = xssfReader.getStylesTable();
XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData();
int index = 0;
//Test with one sheet
iter.hasNext();
//(iter.hasNext()) {
stream = iter.next();
String sheetName = iter.getSheetName();
processSheet(styles, strings, stream, acquisitionForm);
stream.close();
//++index;
//}
p.close();
}catch(Exception e){
throw new ExcelReadException("An error occured during excel file reading ", e);
}finally{
if (stream!=null)
stream.close();
if (p!=null)
p.close();
//++index;
// }
}
}
/**
* Parses and shows the content of one sheet
* using the specified styles and shared-strings tables.
* @param styles
* @param strings
* @param sheetInputStream
* @throws ExcelReadException
*/
private void processSheet(StylesTable styles, ReadOnlySharedStringsTable strings, InputStream sheetInputStream, AcquisitionForm acquisitionForm) throws Exception {
InputSource sheetSource = new InputSource(sheetInputStream);
SAXParserFactory saxFactory = SAXParserFactory.newInstance();
SAXParser saxParser = saxFactory.newSAXParser();
XMLReader sheetParser = saxParser.getXMLReader();
//ContentHandler handler = new MyXSSFSheetHandler(styles, strings);
MyXSSFSheetHandler handler = new MyXSSFSheetHandler(styles, strings,databaseAcquisitionServices, acquisitionForm);
sheetParser.setContentHandler(handler);
sheetParser.parse(sheetSource);
}
MyXSSFSheetHandler
public MyXSSFSheetHandler(StylesTable styles, ReadOnlySharedStringsTable strings,DatabaseAcquisitionServices databaseAcquisitionServices, AcquisitionForm acquisitionForm, int sheetIndex) {
this.stylesTable = styles;
this.sharedStringsTable = strings;
this.formatter = new DataFormatter();
this.value = new StringBuffer();
this.nextDataType = XssfDataType.NUMBER;
this.databaseAcquisitionServices=databaseAcquisitionServices;
this.acquisitionForm=acquisitionForm;
this.sheetIndex = sheetIndex;
}
/**
*
*/
public void startElement(String uri, String localName, String name,
Attributes attributes) throws SAXException {
if ("inlineStr".equals(name) || "v".equals(name)) {
vIsOpen = true;
// Clear contents cache
value.setLength(0);
}
// c => cell
else if ("c".equals(name)) {
// Get the cell reference
cellCoordinate = attributes.getValue("r");
int firstDigit = -1;
for (int c = 0; c < cellCoordinate.length(); ++c) {
if (Character.isDigit(cellCoordinate.charAt(c))) {
firstDigit = c;
break;
}
}
thisColumn = nameToColumn(cellCoordinate.substring(0, firstDigit));
// Set up defaults.
this.nextDataType = XssfDataType.NUMBER;
this.formatIndex = -1;
this.formatString = null;
String cellType = attributes.getValue("t");
String cellStyleStr = attributes.getValue("s");
if ("b".equals(cellType)) {
nextDataType = XssfDataType.BOOL;
} else if ("e".equals(cellType)) {
nextDataType = XssfDataType.ERROR;
} else if ("inlineStr".equals(cellType)) {
nextDataType = XssfDataType.INLINESTR;
} else if ("s".equals(cellType)) {
nextDataType = XssfDataType.SSTINDEX;
} else if ("str".equals(cellType)) {
nextDataType = XssfDataType.FORMULA;
} else if (cellStyleStr != null) {
// It's a number, but almost certainly one
// with a special style or format
int styleIndex = Integer.parseInt(cellStyleStr);
XSSFCellStyle style = stylesTable.getStyleAt(styleIndex);
this.formatIndex = style.getDataFormat();
this.formatString = style.getDataFormatString();
if (this.formatString == null) {
this.formatString = BuiltinFormats.getBuiltinFormat(this.formatIndex);
}
}
}
}
/*
* (non-Javadoc)
* @see org.xml.sax.helpers.DefaultHandler#endElement(java.lang.String, java.lang.String, java.lang.String)
*/
public void endElement(String uri, String localName, String name)
throws SAXException {
String cellValue = null;
//String thisStr = null;
// v => contents of a cell
if ("v".equals(name)) {
// Process the value contents as required.
// Do now, as characters() may be called more than once
switch (nextDataType) {
case BOOL:
char first = value.charAt(0);
//thisStr = first == '0' ? "FALSE" : "TRUE";
//cellValue= new Boolean(first =='0' ? false: true);
cellValue=first == '0' ? "false" : "true";
break;
case ERROR:
//thisStr = "\"ERROR:" + value.toString() + '"';
cellValue=new String(value.toString());
break;
case FORMULA:
// A formula could result in a string value,
// so always add double-quote characters.
//thisStr = '"' + value.toString() + '"';
cellValue=new String(value.toString());
break;
case INLINESTR:
XSSFRichTextString rtsi = new XSSFRichTextString(value.toString());
//thisStr = '"' + rtsi.toString() + '"';
cellValue=new String(rtsi.toString());
break;
case SSTINDEX:
String sstIndex = value.toString();
try {
int idx = Integer.parseInt(sstIndex);
XSSFRichTextString rtss = new XSSFRichTextString(sharedStringsTable.getEntryAt(idx));
// thisStr = '"' + rtss.toString() + '"';
cellValue=new String(rtss.toString());
}
catch (NumberFormatException ex) {
System.out.println("Failed to parse SST index '" + sstIndex + "': " + ex.toString());
}
break;
case NUMBER:
String n = value.toString();
if (this.formatString != null && n.length() > 0){
cellValue = formatter.formatRawCellContents(Double.parseDouble(n), this.formatIndex, this.formatString);
//cellValue=new Double(Double.parseDouble(n));
}
else{
//thisStr = n;
cellValue=new String(n);
}
break;
default:
cellValue="";
//thisStr = "(TODO: Unexpected type: " + nextDataType + ")";
break;
}
// Output after we've seen the string contents
// Emit commas for any fields that were missing on this row
if (lastColumnNumber == -1) {
lastColumnNumber = 0;
}
// for (int i = lastColumnNumber; i < thisColumn; ++i){
// System.out.print(',');
// }
// Might be the empty string.
rowValues.put(cellCoordinate,cellValue);
//System.out.print(cellValue);
// Update column
if (thisColumn > -1)
lastColumnNumber = thisColumn;
} else if ("row".equals(name)) {
// We're onto a new row
//I have to pass new HashMap because otherwise all the map into archiveAcquisition have the same values
databaseAcquisitionServices.archiveAcquisition(new TreeMap<>(rowValues), rowCounter, acquisitionForm, sheetIndex);
//Clear the structure used to store row data
rowValues.clear();
rowCounter++;
//System.out.println();
lastColumnNumber = -1;
}
}
/**
* Captures characters only if a suitable element is open.
* Originally was just "v"; extended for inlineStr also.
*/
public void characters(char[] ch, int start, int length)
throws SAXException {
if (vIsOpen)
value.append(ch, start, length);
}
/**
* Converts an Excel column name like "C" to a zero-based index.
*
* @param name
* @return Index corresponding to the specified name
*/
private int nameToColumn(String name) {
int column = -1;
for (int i = 0; i < name.length(); ++i) {
int c = name.charAt(i);
column = (column + 1) * 26 + c - 'A';
}
return column;
}
答案 0 :(得分：1)
您可能需要计算从SheetContentsHandler派生的类中看到的行数，我认为您不需要单独的XSSFSheetHAndler，我宁愿使用默认值一个且只有一个被赋予SheetContentsHandler，它具有你感兴趣的所有东西的回调方法，例如startRow，endRow，cell。
您可以查看XLSX2CSV sample，了解如何完成XLSX文件的流式读取，尤其是如何使用类SheetToCSV来获取每个行/单元格的调用，可以，例如在方法if (currentRow < startRow) { return }中使用类似cell()的内容来跳过行。
使用参数String cellReference调用单元格方法，该参数可用于通过new CellReference(cellReference).getCol()和new CellReference(cellReference).getRow()检索行/单元格坐标。