xlsx转csv格式,修改自apache poi提供的转换类
来源:互联网 发布:c语言做贪吃蛇 编辑:程序博客网 时间:2024/05/18 05:43
<pre name="code" class="java">package com.lenovo.lstp.biac.utils; import java.io.BufferedOutputStream;import java.io.File;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStream;import java.io.PrintStream; import javax.xml.parsers.ParserConfigurationException;import javax.xml.parsers.SAXParser;import javax.xml.parsers.SAXParserFactory; import org.apache.poi.openxml4j.exceptions.OpenXML4JException;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 XLSX2CSV { /** * 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, } /** * Derived from http://poi.apache.org/spreadsheet/how-to.html#xssf_sax_api * <p/> * Also see Standard ECMA-376, 1st edition, part 4, pages 1928ff, at * http://www.ecma-international.org/publications/standards/Ecma-376.htm * <p/> * A web-friendly version is http://openiso.org/Ecma/376/Part4 */ class MyXSSFSheetHandler extends DefaultHandler { /** * Table with styles */ private StylesTable stylesTable; /** * Table with unique strings */ private ReadOnlySharedStringsTable sharedStringsTable; /** * Destination for data */ private final PrintStream output; //private final String csvFilePath; /** * 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(); } public void startElement(String uri, String localName, String name, Attributes attributes) throws SAXException { if ("inlineStr".equals(name) || "v".equals(name)||"t".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); } } } public void endElement(String uri, String localName, String name) throws SAXException { String thisStr = null; String vs=""; // v => contents of a cell if ("v".equals(name)||"t".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. vs=value.toString().replaceAll("\"", "“"); thisStr = '"' + vs + '"'; break; case INLINESTR: // TODO: have seen an example of this, so it's untested. XSSFRichTextString rtsi = new XSSFRichTextString(value.toString()); vs=rtsi.toString().replaceAll("\"", "”"); thisStr = '"' + vs + '"'; break; case SSTINDEX: String sstIndex = value.toString(); try { int idx = Integer.parseInt(sstIndex); XSSFRichTextString rtss = new XSSFRichTextString(sharedStringsTable.getEntryAt(idx)); vs=rtss.toString().replaceAll("\"", "”"); thisStr = '"' + vs + '"'; } 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); // 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(); 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; private String fileName; private String csvFilePath; public XLSX2CSV(OPCPackage pkg, String csvFilePath, int minColumns,String fileName) { this.xlsxPackage = pkg; //this.output = output; this.csvFilePath=csvFilePath; this.minColumns = minColumns; this.fileName=fileName; } /** * 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, String sheetFile) throws IOException, ParserConfigurationException, SAXException { PrintStream ps=new PrintStream(new BufferedOutputStream(new FileOutputStream(new File(sheetFile))),false,"UTF-8"); 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,ps); sheetParser.setContentHandler(handler); sheetParser.parse(sheetSource); ps.close(); } /** * Initiates the processing of the XLS workbook file to CSV. * * @throws IOException * @throws OpenXML4JException * @throws ParserConfigurationException * @throws SAXException */ public void process() throws IOException, OpenXML4JException, ParserConfigurationException, SAXException { ReadOnlySharedStringsTable strings = new ReadOnlySharedStringsTable(this.xlsxPackage); XSSFReader xssfReader = new XSSFReader(this.xlsxPackage); StylesTable styles = xssfReader.getStylesTable(); XSSFReader.SheetIterator iter = (XSSFReader.SheetIterator) xssfReader.getSheetsData(); while (iter.hasNext()) { InputStream stream = iter.next(); String sheetNamePath = csvFilePath+File.separator+fileName+"_"+iter.getSheetName()+".csv"; processSheet(styles, strings, stream,sheetNamePath); stream.close(); } } public static void main(String[] args) throws Exception { File xlsxFile = new File("D:\\home\\PH UsageA201502/内部库_销账.xlsx"); if (!xlsxFile.exists()) { System.err.println("Not found or not a file: " + xlsxFile.getPath()); return; } int minColumns = -1; OPCPackage p = OPCPackage.open(xlsxFile.getPath(), PackageAccess.READ); XLSX2CSV xlsx2csv = new XLSX2CSV(p,"G:/sf",minColumns,xlsxFile.getName()); xlsx2csv.process(); } }
0 0
- xlsx转csv格式,修改自apache poi提供的转换类
- Apache 的 POI提供API
- 各种xlsx转换程Csv
- 基于JXL和POI实现的读写Excel工具类(支持.xls和.xlsx格式)
- POI读取加密的EXCEL(兼容XLS,XLSX格式)
- java使用poi读取xlsx格式的Excel总结
- POI读取并解析xlsx格式的excel文件
- Apache POI读写Excel文档入门(支持XLS和XLSX格式)
- 基于Apache POI 向xlsx写入数据
- 基于Apache POI 从xlsx读出数据
- Apache POI TXT转成EXCEL(XLSX)
- Apache POI EXCEL(XLSX)转成JSON
- java使用poi读取xls格式和xlsx格式的excel文件
- 用csv格式的文件代替poi导出xls文件
- POI使用SAX处理大量数据的xlsx格式的Excel文件
- poi创建、解析Excel(还有高版本的xlsx格式的Excel创建)
- POI使用SAX处理大量数据的xlsx格式的Excel文件
- POI使用SAX处理大量数据的xlsx格式的Excel文件
- 列出指定目录的全部内容
- Android-给你一个不一样的EditText
- iOS 开发者经典网站
- 天融信防火墙NGFW4000配置手册
- saltstack入门教程精华案例
- xlsx转csv格式,修改自apache poi提供的转换类
- LeetCode | Happy Number
- curl命令
- Hibernate中HQL函数汇总及其说明
- MFC学习之 在Button控件上画线
- QT——QWidget、QMainWindow、 QDialog用法区别解析
- Openwrt /etc/rc.button/reset 保存配置安全脚本
- AUTOCAD shift+鼠标中键 旋转视图后的还原方法
- 将table边框改为细线