word,excel 檔案轉換成HTML檔案
阿新 • • 發佈:2020-12-23
word,excel 檔案轉換成HTML檔案
-
匯入的JAR包
<dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-scratchpad</artifactId> <version>3.14-beta1</version> </dependency> <dependency> <groupId>org.apache.commons</groupId> <artifactId>commons-lang3</artifactId> <version>3.4</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml</artifactId> <version>3.14-beta1</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>ooxml-schemas</artifactId> <version>1.3</version> </dependency> <dependency> <groupId>org.apache.xmlbeans</groupId> <artifactId>xmlbeans</artifactId> <version>2.6.0</version> </dependency> <dependency> <groupId>fr.opensagres.xdocreport</groupId> <artifactId>xdocreport</artifactId> <version>1.0.6</version> </dependency>
-
啟動類:
import com.example.demo.util.ExcelToHTML; import com.example.demo.util.POIWordUtils; import java.io.FileNotFoundException; /** * 檔案預覽 * */ public class FilePreviewController { public static void main(String[] args) throws FileNotFoundException { String fileName = "1102.docx"; String filePath = "E:\\"; String newfileName = "1103.html"; String fileType = fileName.substring(fileName.lastIndexOf(".")); String name = fileName.substring(0, fileName.lastIndexOf(".")); //轉換 word 檔案 if (fileType != null && (".doc".equals(fileType.toLowerCase()) || ".docx".equals(fileType.toLowerCase() ))){ POIWordUtils.docConversionToHtml( newfileName, fileName, filePath); } //轉換 excel 檔案 if (fileType!= null && (".xlsx".equals(fileType.toLowerCase()) || ".xls".equals(fileType.toLowerCase() ))){ ExcelToHTML.readExcelToHtml( filePath+fileName,filePath+newfileName, true); } } }
-
word 轉換HTML類
package com.example.demo.util; import org.apache.commons.lang3.StringUtils; import org.apache.poi.hwpf.HWPFDocument; import org.apache.poi.hwpf.converter.WordToHtmlConverter; import org.apache.poi.xwpf.converter.core.BasicURIResolver; import org.apache.poi.xwpf.converter.core.FileImageExtractor; import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter; import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions; import org.apache.poi.xwpf.usermodel.XWPFDocument; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.w3c.dom.Document; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.transform.OutputKeys; import javax.xml.transform.Transformer; import javax.xml.transform.TransformerFactory; import javax.xml.transform.dom.DOMSource; import javax.xml.transform.stream.StreamResult; import java.io.*; import java.util.HashMap; import java.util.Map; public class POIWordUtils { private static final Logger log = LoggerFactory.getLogger(POIWordUtils.class.getName()); /** * docx to html * * @param in 輸入流 * @return * @throws IOException */ public static InputStream docxToHtml(InputStream in, String filePath) { XWPFDocument document = null; try { document = new XWPFDocument(in); XHTMLOptions options = XHTMLOptions.create(); options.setIgnoreStylesIfUnused(false); options.setFragment(true); filePath = filePath+"image"+File.separator; options.setExtractor(new FileImageExtractor(new File(filePath))); options.URIResolver(new BasicURIResolver("image")); ByteArrayOutputStream out = new ByteArrayOutputStream(); XHTMLConverter.getInstance().convert(document, out, options); return new ByteArrayInputStream(out.toByteArray()); } catch (IOException e) { log.error(e.getMessage(), e); } return in; } /** * doc to html * * @param in * @return * @throws Exception */ public static InputStream docToHtml(InputStream in) { try { HWPFDocument wordDocument = new HWPFDocument(in); WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter( DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument()); wordToHtmlConverter.processDocument(wordDocument); Document htmlDocument = wordToHtmlConverter.getDocument(); ByteArrayOutputStream outStream = new ByteArrayOutputStream(); DOMSource domSource = new DOMSource(htmlDocument); StreamResult streamResult = new StreamResult(outStream); TransformerFactory factory = TransformerFactory.newInstance(); Transformer serializer = factory.newTransformer(); serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8"); serializer.setOutputProperty(OutputKeys.INDENT, "yes"); serializer.setOutputProperty(OutputKeys.METHOD, "html"); serializer.transform(domSource, streamResult); outStream.close(); return new ByteArrayInputStream(outStream.toByteArray()); } catch (Exception e) { log.error(e.getMessage(), e); } return in; } public static InputStream docToHtml(Map<String, Object> request, InputStream in) { String fileName = (String) request.get("name"); if (StringUtils.isEmpty(fileName)) { return in; } String extensionName = fileName.substring(fileName.lastIndexOf(".") + 1, fileName.length()); String prevName = fileName.substring(0, fileName.lastIndexOf(".")); if ("html".equalsIgnoreCase(extensionName)) { return in; } if ("doc".equalsIgnoreCase(extensionName)) { request.put("name", prevName + ".html"); return docToHtml(in); } if ("docx".equalsIgnoreCase(extensionName)) { request.put("name", prevName + ".html"); return docxToHtml(in, (String)request.get("filePath")); } return in; } public static void inputStreamToFile(InputStream inputStream, String newPath) { OutputStream outputStream = null; try { File file = new File(newPath); outputStream = new FileOutputStream(file); int bytesWritten = 0; int byteCount = 0; byte[] bytes = new byte[1024]; while ((byteCount = inputStream.read(bytes)) != -1) { outputStream.write(bytes, bytesWritten, byteCount); } System.out.println("Done!"); } catch (IOException e) { e.printStackTrace(); } finally { if (inputStream != null) { try { inputStream.close(); } catch (IOException e) { e.printStackTrace(); } } if (outputStream != null) { try { outputStream.close(); } catch (IOException e) { e.printStackTrace(); } } } } public static void docConversionToHtml( String newfileName, String fileName, String filePath) throws FileNotFoundException { Map<String, Object> paramsMap = new HashMap<String, Object>(); paramsMap.put("name", fileName); paramsMap.put("filePath", filePath); InputStream in = new FileInputStream(filePath + fileName);// 讀取檔案的資料。 InputStream result = POIWordUtils.docToHtml(paramsMap, in); POIWordUtils.inputStreamToFile(result, filePath+newfileName); } }
-
Excel 轉換成HTML
package com.example.demo.util; import org.apache.poi.hssf.usermodel.*; import org.apache.poi.hssf.util.HSSFColor; import org.apache.poi.ss.usermodel.*; import org.apache.poi.ss.util.CellRangeAddress; import org.apache.poi.xssf.usermodel.XSSFCellStyle; import org.apache.poi.xssf.usermodel.XSSFColor; import org.apache.poi.xssf.usermodel.XSSFFont; import org.apache.poi.xssf.usermodel.XSSFWorkbook; import java.io.*; import java.text.DecimalFormat; import java.text.SimpleDateFormat; import java.util.Date; import java.util.HashMap; import java.util.Map; public class ExcelToHTML { /** * @param filePath excel原始檔檔案的路徑 * @param htmlPositon 生成的html檔案的路徑 * @param isWithStyle 是否需要表格樣式 包含 字型 顏色 邊框 對齊方式 */ public static String readExcelToHtml(String filePath, String htmlPositon, boolean isWithStyle) { InputStream is = null; String htmlExcel = null; try { File sourcefile = new File(filePath); is = new FileInputStream(sourcefile); Workbook wb = WorkbookFactory.create(is); if (wb instanceof XSSFWorkbook) { //03版excel處理方法 XSSFWorkbook xWb = (XSSFWorkbook) wb; htmlExcel = ExcelToHTML.getExcelInfo(xWb, isWithStyle); } else if (wb instanceof HSSFWorkbook) { //07及10版以後的excel處理方法 HSSFWorkbook hWb = (HSSFWorkbook) wb; htmlExcel = ExcelToHTML.getExcelInfo(hWb, isWithStyle); } writeFile(htmlExcel, htmlPositon); } catch (Exception e) { e.printStackTrace(); } finally { try { is.close(); } catch (IOException e) { e.printStackTrace(); } } return htmlPositon; } private static String getExcelInfo(Workbook wb, boolean isWithStyle) { StringBuffer sb = new StringBuffer(); Sheet sheet = wb.getSheetAt(0);//獲取第一個Sheet的內容 int lastRowNum = sheet.getLastRowNum(); Map<String, String> map[] = getRowSpanColSpanMap(sheet); sb.append("<table style='border-collapse:collapse;' width='100%'>"); Row row = null; //相容 Cell cell = null; //相容 for (int rowNum = sheet.getFirstRowNum(); rowNum <= lastRowNum; rowNum++) { row = sheet.getRow(rowNum); if (row == null) { sb.append("<tr><td ><nobr> </nobr></td></tr>"); continue; } sb.append("<tr>"); int lastColNum = row.getLastCellNum(); for (int colNum = 0; colNum < lastColNum; colNum++) { cell = row.getCell(colNum); if (cell == null) { //特殊情況 空白的單元格會返回null sb.append("<td> </td>"); continue; } String stringValue = getCellValue(cell); if (map[0].containsKey(rowNum + "," + colNum)) { String pointString = map[0].get(rowNum + "," + colNum); map[0].remove(rowNum + "," + colNum); int bottomeRow = Integer.valueOf(pointString.split(",")[0]); int bottomeCol = Integer.valueOf(pointString.split(",")[1]); int rowSpan = bottomeRow - rowNum + 1; int colSpan = bottomeCol - colNum + 1; sb.append("<td rowspan= '" + rowSpan + "' colspan= '" + colSpan + "' "); } else if (map[1].containsKey(rowNum + "," + colNum)) { map[1].remove(rowNum + "," + colNum); continue; } else { sb.append("<td "); } //判斷是否需要樣式 if (isWithStyle) { dealExcelStyle(wb, sheet, cell, sb);//處理單元格樣式 } sb.append("><nobr>"); if (stringValue == null || "".equals(stringValue.trim())) { sb.append(" "); } else { // 將ascii碼為160的空格轉換為html下的空格( ) String aaa = stringValue.replace(String.valueOf((char) 160), " "); sb.append(stringValue.replace(String.valueOf((char) 160), " ")); } sb.append("</nobr></td>"); } sb.append("</tr>"); } sb.append("</table>"); return sb.toString(); } private static Map<String, String>[] getRowSpanColSpanMap(Sheet sheet) { Map<String, String> map0 = new HashMap<String, String>(); Map<String, String> map1 = new HashMap<String, String>(); int mergedNum = sheet.getNumMergedRegions(); CellRangeAddress range = null; for (int i = 0; i < mergedNum; i++) { range = sheet.getMergedRegion(i); int topRow = range.getFirstRow(); int topCol = range.getFirstColumn(); int bottomRow = range.getLastRow(); int bottomCol = range.getLastColumn(); map0.put(topRow + "," + topCol, bottomRow + "," + bottomCol); // System.out.println(topRow + "," + topCol + "," + bottomRow + "," + bottomCol); int tempRow = topRow; while (tempRow <= bottomRow) { int tempCol = topCol; while (tempCol <= bottomCol) { map1.put(tempRow + "," + tempCol, ""); tempCol++; } tempRow++; } map1.remove(topRow + "," + topCol); } Map[] map = {map0, map1}; return map; } /** * 獲取表格單元格Cell內容 * * @param cell * @return */ private static String getCellValue(Cell cell) { String result = new String(); switch (cell.getCellType()) { case Cell.CELL_TYPE_NUMERIC:// 數字型別 if (HSSFDateUtil.isCellDateFormatted(cell)) {// 處理日期格式、時間格式 SimpleDateFormat sdf = null; if (cell.getCellStyle().getDataFormat() == HSSFDataFormat.getBuiltinFormat("h:mm")) { sdf = new SimpleDateFormat("HH:mm"); } else {// 日期 sdf = new SimpleDateFormat("yyyy-MM-dd"); } Date date = cell.getDateCellValue(); result = sdf.format(date); } else if (cell.getCellStyle().getDataFormat() == 58) { // 處理自定義日期格式:m月d日(通過判斷單元格的格式id解決,id的值是58) SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd"); double value = cell.getNumericCellValue(); Date date = DateUtil .getJavaDate(value); result = sdf.format(date); } else { double value = cell.getNumericCellValue(); CellStyle style = cell.getCellStyle(); DecimalFormat format = new DecimalFormat(); String temp = style.getDataFormatString(); // 單元格設定成常規 if (temp.equals("General")) { format.applyPattern("#"); } result = format.format(value); } break; case Cell.CELL_TYPE_STRING:// String型別 result = cell.getRichStringCellValue().toString(); break; case Cell.CELL_TYPE_BLANK: result = ""; break; default: result = ""; break; } return result; } /** * 處理表格樣式 * * @param wb * @param sheet * @param sb */ private static void dealExcelStyle(Workbook wb, Sheet sheet, Cell cell, StringBuffer sb) { CellStyle cellStyle = cell.getCellStyle(); if (cellStyle != null) { short alignment = cellStyle.getAlignment(); // sb.append("align='" + convertAlignToHtml(alignment) + "' ");//單元格內容的水平對齊方式 short verticalAlignment = cellStyle.getVerticalAlignment(); sb.append("valign='" + convertVerticalAlignToHtml(verticalAlignment) + "' ");//單元格中內容的垂直排列方式 if (wb instanceof XSSFWorkbook) { XSSFFont xf = ((XSSFCellStyle) cellStyle).getFont(); short boldWeight = xf.getBoldweight(); String align = convertAlignToHtml(alignment); sb.append("style='"); sb.append("font-weight:" + boldWeight + ";"); // 字型加粗 sb.append("font-size: " + xf.getFontHeight() / 2 + "%;"); // 字型大小 int columnWidth = sheet.getColumnWidth(cell.getColumnIndex()); sb.append("width:" + columnWidth + "px;"); sb.append("text-align:" + align + ";");//表頭排版樣式 XSSFColor xc = xf.getXSSFColor(); if (xc != null && !"".equals(xc)) { sb.append("color:#" + xc.getARGBHex().substring(2) + ";"); // 字型顏色 } XSSFColor bgColor = (XSSFColor) cellStyle.getFillForegroundColorColor(); if (bgColor != null && !"".equals(bgColor)) { sb.append("background-color:#" + bgColor.getARGBHex().substring(2) + ";"); // 背景顏色 } sb.append(getBorderStyle(0, cellStyle.getBorderTop(), ((XSSFCellStyle) cellStyle).getTopBorderXSSFColor())); sb.append(getBorderStyle(1, cellStyle.getBorderRight(), ((XSSFCellStyle) cellStyle).getRightBorderXSSFColor())); sb.append(getBorderStyle(2, cellStyle.getBorderBottom(), ((XSSFCellStyle) cellStyle).getBottomBorderXSSFColor())); sb.append(getBorderStyle(3, cellStyle.getBorderLeft(), ((XSSFCellStyle) cellStyle).getLeftBorderXSSFColor())); } else if (wb instanceof HSSFWorkbook) { HSSFFont hf = ((HSSFCellStyle) cellStyle).getFont(wb); short boldWeight = hf.getBoldweight(); short fontColor = hf.getColor(); sb.append("style='"); HSSFPalette palette = ((HSSFWorkbook) wb).getCustomPalette(); // 類HSSFPalette用於求的顏色的國際標準形式 HSSFColor hc = palette.getColor(fontColor); sb.append("font-weight:" + boldWeight + ";"); // 字型加粗 sb.append("font-size: " + hf.getFontHeight() / 2 + "%;"); // 字型大小 String align = convertAlignToHtml(alignment); sb.append("text-align:" + align + ";");//表頭排版樣式 String fontColorStr = convertToStardColor(hc); if (fontColorStr != null && !"".equals(fontColorStr.trim())) { sb.append("color:" + fontColorStr + ";"); // 字型顏色 } int columnWidth = sheet.getColumnWidth(cell.getColumnIndex()); sb.append("width:" + columnWidth + "px;"); short bgColor = cellStyle.getFillForegroundColor(); hc = palette.getColor(bgColor); String bgColorStr = convertToStardColor(hc); if (bgColorStr != null && !"".equals(bgColorStr.trim())) { sb.append("background-color:" + bgColorStr + ";"); // 背景顏色 } sb.append(getBorderStyle(palette, 0, cellStyle.getBorderTop(), cellStyle.getTopBorderColor())); sb.append(getBorderStyle(palette, 1, cellStyle.getBorderRight(), cellStyle.getRightBorderColor())); sb.append(getBorderStyle(palette, 3, cellStyle.getBorderLeft(), cellStyle.getLeftBorderColor())); sb.append(getBorderStyle(palette, 2, cellStyle.getBorderBottom(), cellStyle.getBottomBorderColor())); } sb.append("' "); } } /** * 單元格內容的水平對齊方式 * * @param alignment * @return */ private static String convertAlignToHtml(short alignment) { String align = "center"; switch (alignment) { case CellStyle.ALIGN_LEFT: align = "left"; break; case CellStyle.ALIGN_CENTER: align = "center"; break; case CellStyle.ALIGN_RIGHT: align = "right"; break; default: break; } return align; } /** * 單元格中內容的垂直排列方式 * * @param verticalAlignment * @return */ private static String convertVerticalAlignToHtml(short verticalAlignment) { String valign = "middle"; switch (verticalAlignment) { case CellStyle.VERTICAL_BOTTOM: valign = "bottom"; break; case CellStyle.VERTICAL_CENTER: valign = "center"; break; case CellStyle.VERTICAL_TOP: valign = "top"; break; default: break; } return valign; } private static String convertToStardColor(HSSFColor hc) { StringBuffer sb = new StringBuffer(""); if (hc != null) { if (HSSFColor.AUTOMATIC.index == hc.getIndex()) { return null; } sb.append("#"); for (int i = 0; i < hc.getTriplet().length; i++) { sb.append(fillWithZero(Integer.toHexString(hc.getTriplet()[i]))); } } return sb.toString(); } private static String fillWithZero(String str) { if (str != null && str.length() < 2) { return "0" + str; } return str; } static String[] bordesr = {"border-top:", "border-right:", "border-bottom:", "border-left:"}; static String[] borderStyles = {"solid ", "solid ", "solid ", "solid ", "solid ", "solid ", "solid ", "solid ", "solid ", "solid", "solid", "solid", "solid", "solid"}; private static String getBorderStyle(HSSFPalette palette, int b, short s, short t) { if (s == 0) { return bordesr[b] + borderStyles[s] + "#d0d7e5 1px;"; } String borderColorStr = convertToStardColor(palette.getColor(t)); borderColorStr = borderColorStr == null || borderColorStr.length() < 1 ? "#000000" : borderColorStr; return bordesr[b] + borderStyles[s] + borderColorStr + " 1px;"; } private static String getBorderStyle(int b, short s, XSSFColor xc) { if (s == 0) { return bordesr[b] + borderStyles[s] + "#d0d7e5 1px;"; } if (xc != null && !"".equals(xc)) { String borderColorStr = xc.getARGBHex();//t.getARGBHex(); borderColorStr = borderColorStr == null || borderColorStr.length() < 1 ? "#000000" : borderColorStr.substring(2); return bordesr[b] + borderStyles[s] + borderColorStr + " 1px;"; } return ""; } /* * @param content 生成的excel表格標籤 * @param htmlPath 生成的html檔案地址 */ private static void writeFile(String content, String htmlPath) throws UnsupportedEncodingException { File file2 = new File(htmlPath); StringBuilder sb = new StringBuilder(); sb.append("<html><head><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><title>Html Test</title></head><body>"); sb.append("<div>"); sb.append(content); sb.append("</div>"); sb.append("</body></html>"); String fileText = sb.toString(); try { file2.createNewFile();//建立檔案 BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file2), "utf-8")); // FileWriter fw=new FileWriter(file2);//在workspace工作空間裡建立檔案,檔名為hello out.write(fileText); } catch (IOException e) { e.printStackTrace(); } } }