XML Worker Word转PDF/html工具类

package com.example.demo.util.office; import com.example.demo.util.BaseUtil; import com.example.demo.util.FilesUtil; import com.example.demo.util.WordUtils; import com.itextpdf.io.font.PdfEncodings; import com.itextpdf.kernel.font.PdfFont; import com.itextpdf.kernel.font.PdfFontFactory; import com.itextpdf.kernel.pdf.PdfDocument; import com.itextpdf.kernel.pdf.PdfWriter; import com.itextpdf.layout.Document; import com.itextpdf.layout.element.Paragraph; import com.itextpdf.layout.element.Text; import com.itextpdf.layout.properties.TextAlignment; import org.apache.commons.lang3.StringUtils; import org.apache.poi.xwpf.usermodel.*; import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTPageMar; import org.springframework.util.ObjectUtils; import java.io.*; import java.net.URL; import java.time.LocalDateTime; import java.time.format.DateTimeFormatter; import java.util.*; /** * @Description: word转pdf */ public class Word2Pdf { //文本 public static String TEXT = "text"; //对齐方式 public static String ALIGNMENT = "alignment"; //行间距 public static String FIXED_LEADING = "fixedLeading"; //字体样式 public static String FONT = "font"; //字体大小 public static String FONT_SIZE = "fontSize"; //是否粗体 public static String IS_BOLD = "isBold"; //首行缩进 public static String INDENT_FIRST_LINE = "indentFirstLine"; /**页边距*/ public static String TOP = "top"; public static String BOTTOM = "bottom"; public static String LEFT = "left"; public static String RIGHT = "right"; public static String IS_FIXED = "isFixed"; /**字体-宋体*/ protected static final String SIM_SUN = "SimSun.ttf"; /**字体-仿宋*/ protected static final String SIM_FANG = "simfang.ttf"; /**字体-宋体-粗体*/ protected static final String SIM_SUN_BD = "simsunbd.ttf"; public static String SONG_TI = "宋体"; public static String FANG_SONG = "仿宋"; private static Map<String,Map<String,Object>> orderMap =new HashMap<String, Map<String,Object>>(); /** * 获取页眉信息 * @param doc XWPFDocument对象 * @return */ private static List<Map<String,Object>> getHeader(XWPFDocument doc){ List<Map<String,Object>> list = new ArrayList<>(); List<XWPFHeader> headerList = doc.getHeaderList(); // 获取页眉对象集合 for (XWPFHeader xwpfHeader : headerList) { Map<String,Object> map = new HashMap<>(); map.put("页眉",xwpfHeader.getText()); // 获取页眉文本 List<XWPFParagraph> listParagraph = xwpfHeader.getListParagraph(); // 获取所有段落的列表 for (XWPFParagraph xwpfParagraph : listParagraph) { List<XWPFRun> runs = xwpfParagraph.getRuns(); // 获取公共属性集的文本区域 for (XWPFRun xwpfRun : runs) { map.put("页眉字体颜色", xwpfRun.getColor()); // 获取页眉字体颜色 map.put("页眉字体大小",xwpfRun.getFontSize()); // 获取页眉字体大小 map.put("页眉字体",xwpfRun.getFontName()); // 获取页眉字体 } } list.add(map); } return list; } /** * 获取页脚信息 * @param doc * @return */ private static List<Map<String,Object>> getFooter(XWPFDocument doc){ List<Map<String,Object>> list = new ArrayList(); List<XWPFFooter> footerList = doc.getFooterList(); // 获取页脚对象集合 for (XWPFFooter xwpfFooter : footerList) { Map<String,Object> map = new HashMap<>(); map.put("页脚",xwpfFooter.getText()); // 获取页脚文本 List<XWPFParagraph> listParagraph = xwpfFooter.getListParagraph(); for (XWPFParagraph xwpfParagraph : listParagraph) { List<XWPFRun> runs = xwpfParagraph.getRuns(); for (XWPFRun xwpfRun : runs) { map.put("页脚字体颜色", xwpfRun.getColor()); // 获取页脚字体颜色 map.put("页脚字体大小",xwpfRun.getFontSize()); // 获取页脚字体大小 map.put("页脚字体",xwpfRun.getFontName()); // 获取页脚字体 } } list.add(map); } return list; } /** * 获取段落信息 * @param doc * @return */ private static List<Map<String,Object>> getXParagraph(XWPFDocument doc){ List<Map<String,Object>> list = new ArrayList(); List<XWPFParagraph> paragraphs2 = doc.getParagraphs(); for (XWPFParagraph xwpfParagraph : paragraphs2) { Map<String,Object> map = new HashMap<>(); map.put(TEXT,xwpfParagraph.getParagraphText());// 段落内容 map.put(ALIGNMENT,xwpfParagraph.getAlignment());// 段落对齐方式 //获取段落行间距格式 LineSpacingRule spacingLineRule = xwpfParagraph.getSpacingLineRule(); map.put(IS_FIXED,spacingLineRule.getValue()); double spacingBetween = xwpfParagraph.getSpacingBetween(); // 返回段落行之间的间距。 if (((double) -1) == spacingBetween){ //此情况下为单倍行间距 spacingBetween = 1; } map.put(FIXED_LEADING,spacingBetween); //567=1cm map.put(INDENT_FIRST_LINE,xwpfParagraph.getFirstLineIndent()); List<XWPFRun> runs = xwpfParagraph.getRuns(); if (runs.size() == 0){ try { if (xwpfParagraph.getCTP().getPPr().getRPr().getSz() == null){ map.put(TEXT,"\n");// 段落内容 }else { map.put(FONT_SIZE,xwpfParagraph.getCTP().getPPr().getRPr().getSz().getVal().floatValue()/2); map.put(FONT,xwpfParagraph.getCTP().getPPr().getRPr().getRFonts().getAscii()); map.put(TEXT,"\n");// 段落内容 } } catch (NullPointerException e) { map.put(TEXT,"\n"); } } for (XWPFRun xwpfRun : runs) { //map.put("段落字体颜色",xwpfRun.getColor()); // 获取段落字体颜色 map.put(FONT_SIZE,xwpfRun.getFontSize()); // 获取段落字体大小 map.put(FONT,xwpfRun.getFontName()); // 获取段落字体 map.put(IS_BOLD,xwpfRun.isBold()); //map.put("段落下划线设置", xwpfRun.getUnderline()); // 获取段落字体下划线设置 //map.put("段落下划线颜色", xwpfRun.getUnderlineColor()); // 获取段落字体下划线颜色 } // String titleLvl = getTitleLvl(doc,xwpfParagraph);// 获取段落级别 // if(!titleLvl.equals("")){ // String orderCode = getOrderCode(titleLvl);// 获取编号 // map.put("段落编号",orderCode); // } list.add(map); } return list; } /** * Word中的大纲级别，可以通过getPPr().getOutlineLvl()直接提取，但需要注意，Word中段落级别，通过如下三种方式定义： * 1、直接对段落进行定义； * 2、对段落的样式进行定义； * 3、对段落样式的基础样式进行定义。 * 因此，在通过“getPPr().getOutlineLvl()”提取时，需要依次在如上三处读取。 * @param doc * @param para * @return */ private static String getTitleLvl(XWPFDocument doc, XWPFParagraph para) { String titleLvl = ""; try { //�