利用Java实现Word文档自动编号提取的方法详解

 
public class NumberingContext {
    private final Map<String, List<Integer>> numberingStates = new HashMap<>();
    // 编号格式映射（可以扩展更多格式）
    public static final Map<String, NumberFormatter> FORMATTERS = new HashMap<>();
 
    static {
        FORMATTERS.put("decimal", new DecimalFormatter());
        FORMATTERS.put("lowerLetter", new LowerLetterFormatter());
        FORMATTERS.put("upperLetter", new UpperLetterFormatter()); // 新增
        FORMATTERS.put("upperRoman", new UpperRomanFormatter());
        FORMATTERS.put("chineseCounting", new ChineseCountingFormatter());
    }
 
    public String resolveNumberText(String numIdKey, int ilvl, String format, String textTemplate) {
        List<Integer> counters = numberingStates.computeIfAbsent(numIdKey, k -> new ArrayList<>());
 
        // 确保层级计数器足够长
        while (counters.size() <= ilvl) {
            counters.add(0);
        }
 
        // 更新当前层级计数器，并清空下级
        counters.set(ilvl, counters.get(ilvl) + 1);
        for (int i = ilvl + 1; i < counters.size(); i++) {
            counters.set(i, 0);
        }
 
        // 获取格式化器
        NumberFormatter formatter = FORMATTERS.get(format);
        if (formatter == null) {
            formatter = new DecimalFormatter();
        }
 
        // 替换模板中的占位符
        String result = textTemplate;
        for (int i = 0; i <= ilvl; i++) {
            String placeholder = "%" + (i + 1);
            if (i < counters.size()) {
                String replacement = formatter.format(counters.get(i));
                result = result.replace(placeholder, replacement);
            }
        }
 
        return result;
    }
}

public class DecimalFormatter implements NumberFormatter {
    @Override
    public String format(int number) {
        return String.valueOf(number);
    }
}

public class LowerLetterFormatter implements NumberFormatter {
    @Override
    public String format(int number) {
        return String.valueOf((char) ('a' + number - 1));
    }
}

public class UpperLetterFormatter  implements NumberFormatter {
    @Override
    public String format(int number) {
        if (number < 1 || number > 26) {
            throw new IllegalArgumentException("upperLetter 格式仅支持 1-26");
        }
        return String.valueOf((char) ('A' + number - 1));
    }
}

public static String getParagraphNumbering(NumberingContext numberingContext, XWPFParagraph paragraph) {
        try {
            if (paragraph.getNumID() == null) {
                //"无编号";
                return "";
            }
 
            BigInteger numId = paragraph.getNumID();
            BigInteger ilvl = paragraph.getNumIlvl() != null ? paragraph.getNumIlvl() : new BigInteger("0");
 
            // 使用numId和文档信息创建唯一键
            String numIdKey = numId.toString();
 
            XWPFNumbering numbering = paragraph.getDocument().getNumbering();
            if (numbering == null) {
                //"无编号定义";
                return "";
            }
 
            XWPFNum num = numbering.getNum(numId);
            if (num == null) {
                //"编号定义不存在";
                return "";
            }
 
            BigInteger abstractNumId = num.getCTNum().getAbstractNumId().getVal();
            for (XWPFAbstractNum abstractNum : numbering.getAbstractNums()) {
                if (abstractNum.getCTAbstractNum().getAbstractNumId().equals(abstractNumId)) {
                    CTAbstractNum ctAbstractNum = abstractNum.getCTAbstractNum();
                    CTLvl ctLvl = ctAbstractNum.getLvlArray(ilvl.intValue());
                    if (ctLvl != null && ctLvl.getNumFmt() != null && ctLvl.getLvlText() != null) {
                        String format = ctLvl.getNumFmt().getVal().toString();
                        String text = ctLvl.getLvlText().getVal();
 
                        return numberingContext.resolveNumberText(
                                numIdKey, ilvl.intValue(), format, text);
                    }
                }
            }
 
            //"编号层级不存在或定义不完整";
            return "";
        } catch (Exception e) {
            //"解析编号时出错";
            return "";
        }
    }