package com.h3c.oos.util; import java.io.File; import java.io.IOException; import java.io.InputStream; import java.io.PrintStream; import java.sql.PreparedStatement; import java.util.ArrayList; import java.util.List; import javax.xml.parsers.ParserConfigurationException; import javax.xml.parsers.SAXParser; import javax.xml.parsers.SAXParserFactory; import org.apache.poi.openxml4j.opc.OPCPackage; import org.apache.poi.openxml4j.opc.PackageAccess; import org.apache.poi.ss.usermodel.BuiltinFormats; import org.apache.poi.ss.usermodel.DataFormatter; import org.apache.poi.xssf.eventusermodel.ReadOnlySharedStringsTable; import org.apache.poi.xssf.eventusermodel.XSSFReader; import org.apache.poi.xssf.model.StylesTable; import org.apache.poi.xssf.usermodel.XSSFCellStyle; import org.apache.poi.xssf.usermodel.XSSFRichTextString; import org.xml.sax.Attributes; import org.xml.sax.ContentHandler; import org.xml.sax.InputSource; import org.xml.sax.SAXException; import org.xml.sax.XMLReader; import org.xml.sax.helpers.DefaultHandler; /** * */ public class ReaderEcxel { // The type of the data value is indicated by an attribute on the cell. // The value is usually in a "v" element within the cell. enum xssfDataType { BOOL, ERROR, FORMULA, INLINESTR, SSTINDEX, NUMBER, } int countrows = 0; private List<String> list = new ArrayList<String>(); private List<String> listException = new ArrayList<String>(); class MyXSSFSheetHandler extends DefaultHandler { // Table with styles private StylesTable stylesTable; // Table with unique strings private ReadOnlySharedStringsTable sharedStringsTable; // Destination for data private final PrintStream output; // Number of columns to read starting with leftmost private final int minColumnCount; // Set when V start element is seen private boolean vIsOpen; // Set when cell start element is seen; // used when cell close element is seen. private xssfDataType nextDataType; // Used to format numeric cell values. private short formatIndex; private String formatString; private final DataFormatter formatter; private int thisColumn = -1; // The last column printed to the output stream private int lastColumnNumber = -1; // Gathers characters as they are seen. private StringBuffer value; // Accepts objects needed while parsing. // @param styles Table of styles // @param strings Table of shared strings // @param cols Minimum number of columns to show // @param target Sink for output public MyXSSFSheetHandler(StylesTable styles, ReadOnlySharedStringsTable strings, int cols, PrintStream target) { this.stylesTable = styles; this.sharedStringsTable = strings; this.minColumnCount = cols; this.output = target; this.value = new StringBuffer(); this.nextDataType = xssfDataType.NUMBER; this.formatter = new DataFormatter(); } // @see // org.xml.sax.helpers.DefaultHandler#startElement(java.lang.String, // java.lang.String, java.lang.String, org.xml.sax.Attributes) 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 String r = attributes.getValue("r"); int firstDigit = -1; for (int c = 0; c < r.length(); ++c) { if (Character.isDigit(r.charAt(c))) { firstDigit = c; break; } } thisColumn = nameToColumn(r.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); } } } // @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 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"; break; case ERROR: thisStr = "\"ERROR:" + value.toString() + '"'; break; case FORMULA: // A formula could result in a string value, // so always add double-quote characters. thisStr = value.toString(); break; case INLINESTR: // TODO: have seen an example of this, so it's untested. XSSFRichTextString rtsi = new XSSFRichTextString(value .toString()); thisStr = 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(); } catch (NumberFormatException ex) { output.println("Failed to parse SST index '" + sstIndex + "': " + ex.toString()); } break; case NUMBER: String n = value.toString(); if (this.formatString != null) thisStr = formatter.formatRawCellContents(Double .parseDouble(n), this.formatIndex, this.formatString); else thisStr = n; break; default: 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) { output.print(','); } // Might be the empty string. output.print(thisStr); if ("".equals(thisStr)) { thisStr = "N/A"; } list.add(thisStr); // Update column if (thisColumn > -1) { lastColumnNumber = thisColumn; } } else if ("row".equals(name)) { // Print out any missing commas if needed if (minColumns > 0) { // Columns are 0 based if (lastColumnNumber == -1) { lastColumnNumber = 0; } for (int i = lastColumnNumber; i < (this.minColumnCount); i++) { output.print(','); } } // We're onto a new row output.println(); output.println(countrows++); 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; } } // ///////////////////////////////////// private OPCPackage xlsxPackage; private int minColumns; private PrintStream output; // Creates a new XLSX -> CSV converter // @param pkg The XLSX package to process // @param output The PrintStream to output the CSV to // @param minColumns The minimum number of columns to output, or -1 for no // minimum public ReaderEcxel(OPCPackage pkg, PrintStream output, int minColumns) { this.xlsxPackage = pkg; this.output = output; this.minColumns = minColumns; } // Parses and shows the content of one sheet // using the specified styles and shared-strings tables. // @param styles // @param strings // @param sheetInputStream public void processSheet(StylesTable styles, ReadOnlySharedStringsTable strings, InputStream sheetInputStream) throws IOException, ParserConfigurationException, SAXException { InputSource sheetSource = new InputSource(sheetInputStream); SAXParserFactory saxFactory = SAXParserFactory.newInstance(); SAXParser saxParser = saxFactory.newSAXParser(); XMLReader sheetParser = saxParser.getXMLReader(); ContentHandler handler = new MyXSSFSheetHandler(styles, strings, this.minColumns, this.output); sheetParser.setContentHandler(handler); sheetParser.parse(sheetSource); } // Initiates the processing of the XLS workbook file to CSV. // @throws IOException // @throws OpenXML4JException // @throws ParserConfigurationException // @throws SAXException public void process() throws Exception { ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable( this.xlsxPackage); XSSFReader xssfReader = new XSSFReader(this.xlsxPackage); StylesTable styles = xssfReader.getStylesTable(); XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader .getSheetsData(); int index = 0; while (iter.hasNext()) { InputStream stream = iter.next(); String sheetName = iter.getSheetName(); this.output.println(); this.output.println(sheetName + " [index=" + index + "]:"); processSheet(styles, strings, stream); stream.close(); ++index; break; } } public static void main(String[] args) throws Exception { // File xlsxFile = new File(args[0]); File xlsxFile = new File("C:/Users/zkf4583/develp/1.xlsx"); if (!xlsxFile.exists()) { System.err .println("Not found or not a file: " + xlsxFile.getPath()); return; } int minColumns = -1; // if (args.length >= 2) // minColumns = Integer.parseInt(args[1]); // minColumns = 0; // The package open is instantaneous, as it should be. OPCPackage p = OPCPackage.open(xlsxFile.getPath(), PackageAccess.READ); ReaderEcxel xlsx2csv = new ReaderEcxel(p, System.out, minColumns); xlsx2csv.process(); } public List processReaderSheet(OPCPackage pkg) throws Exception { ReaderEcxel xlsx2csv = new ReaderEcxel(pkg, System.out, -1); xlsx2csv.process(); return list; } }
相关推荐
在本例中,我们将聚焦于“poi3.9读写EXCEL”这一主题,特别是针对支持2007版Excel(XLSX格式)的特性。 Apache POI是Apache软件基金会的一个开源项目,其主要目标是提供一个API,使得Java程序员能够处理Microsoft ...
在标题中提到的“poi 3.9读取excel xls xlsx 有jar包”,指的是使用Apache POI 3.9版本来读取Excel的工作簿(XLS和XLSX格式)。这个版本的POI包含了处理Excel文件所需的核心组件。 Apache POI 提供了HSSF(Horrible...
"poi3.9读写excel兼容03和07版本"这个标题指的是使用Apache POI 3.9版本的API,能够兼容两种不同格式的Excel文件:.xls(Excel 2003及更早版本)和.xlsx(Excel 2007及更高版本)。 在描述中提到的"完美修订版本...
Poi 3.9是这个库的一个版本,包含了对Excel文件读写功能的完善支持。 批量导入和导出功能在企业级应用中非常常见,尤其是在数据分析和数据处理方面。使用Spring MVC和Apache POI,我们可以构建一个高效、可扩展的...
Poi读取Excel2003+Excel2007 Poi生成Excel2003 源码,调用 方法即可
在本文中,我们将深入探讨如何使用Apache POI 3.9版本来读取Excel 2007及更高版本(即XLSX格式)的文件,特别是通过`XSSFWorkbook`类进行操作。首先,你需要确保已经下载了必要的库,这通常包括poi-bin-3.9压缩包,...
7. **兼容性**:Apache POI 3.9能够处理Excel 97-2007的XLS格式以及2007年之后的XLSX格式,提供了广泛的文件兼容性。 通过这个压缩包,开发者不仅可以获取到一个高性能的POI版本,还能获得实际应用案例,这对于学习...
利用poi3.9做的excel导出工具。 这是一个工程直接压缩而成的。 测试10万行*8列,从查询到生成文件所花时间13620毫秒 测试100万行*8列,从查询到生成文件所花时间121443毫秒 主要目录: src com.util ----DBUtil.java...
2. **poi-ooxml-3.9.jar**:这个库支持处理OOXML格式,即基于XML的Microsoft Office 2007及更高版本的文件格式(XLSX、DOCX、PPTX)。它包含了对Open Packaging Convention (OPC) 的实现,是处理OOXML文件的基础。 ...
通过POI3.9驱动模式读取excel2007时,对含有空的单位格处理实现,使用起来很简单了
在Java环境中,Apache POI库是处理Excel数据的首选工具,它提供了丰富的API来读取、写入和操作Excel文件。在这个“poi-3.9”包中,你将获得Apache POI 3.9版本的所有组件,这个版本发布于2012年,虽然相对较旧,但...
总的来说,Apache POI 3.9版本为Java开发者提供了强大的处理Excel文件的能力,无论是读取旧版的.xls文件,还是编写现代的.xlsx文件,都能游刃有余。在实际项目中,我们可以利用它进行数据的读取、分析、转换和报告...
首先,Apache POI 3.9是Apache软件基金会的一个项目,它提供了API来处理Microsoft Office的文件格式,如XLS(Excel 97-2003)和XLSX(Excel 2007及以上)。在这个例子中,我们看到两个主要的任务:生成双色球历史...
"org.apache.poi3.9.jar"是这个项目的一个版本,适用于Java环境,它提供了对Office文档的读取、写入和修改功能。在Java编程中,如果你需要处理Excel数据,这个库是一个非常重要的工具。 该jar包中的主要类和接口...
"poi3.9jar包下载"指的是获取Apache POI 3.9版本的库文件,这个版本的POI支持对Excel的各种操作。 1. **Apache POI基本介绍** Apache POI 是Apache软件基金会的一个项目,它允许Java程序员创建、修改和显示MS ...
2. **XSSF/SXSSFWorkbook**: 用于处理Microsoft Excel 2007及以后版本的XLSX文件。XSSF是基于OOXML规范的实现,而SXSSFWorkbook是一个内存优化的版本,适用于处理大量数据,它将部分数据写入磁盘,以降低内存消耗。 ...
- `poi-ooxml-3.9.jar`: 提供了对Open XML格式(.xlsx, .docx, .pptx)的支持,这是从Excel 2007开始引入的新文件格式。XSSF接口和相关的类就位于这个库中。 - `poi-ooxml-schemas-3.9.jar`: 包含了Open XML格式的...
总之,"POI3.9必要jar包"是Java开发人员处理Excel文件时必不可少的工具集,包含了所有与Apache POI3.9版本相关的库,能够确保项目运行的稳定性和兼容性。使用这些jar文件,开发者可以高效、灵活地进行Excel文件的...
POI 3.9 API文档(英文版),poi 3.9的最新版本,最新合成的chm帮助文档