PDF重构时文本定位异常问题求助（附相关代码）

我在重构PDF时遇到文本定位问题：已通过text stripper提取所有文本，能在新PDF中使用正确的字体和字号绘制文本，但无法将文本放置在正确位置。

相关示例图：

• 输入PDF示例图
• 输出PDF示例图

提取TextPosition数据的代码 #

protected void processTextPosition(TextPosition text) {
    textPositionPDGraphicsStatesMap.put(text, getGraphicsState());
    PDGraphicsState state = getGraphicsState();
    PDTextState textState = state.getTextState();
    float fontSize = textState.getFontSize();
    float horizontalScaling = textState.getHorizontalScaling() / 100f;
    float charSpacing = textState.getCharacterSpacing();

    // 将文本状态参数转换为矩阵形式
    Matrix parameters = new Matrix(
               fontSize * horizontalScaling, 0, // 0
               0, fontSize,                     // 0
               0, textState.getRise());         // 1
    
    // 文本渲染矩阵（文本空间 -> 设备空间）
    Matrix ctm = state.getCurrentTransformationMatrix();
    Matrix textRenderingMatrix = parameters.multiply(text.getTextMatrix()).multiply(ctm);
    
    TextPositionsInfo txtInfo = new TextPositionsInfo();
    txtInfo.xDir = text.getXDirAdj();
    txtInfo.yDir = text.getYDirAdj();
    txtInfo.x =  textRenderingMatrix.getTranslateX();
    txtInfo.y = textRenderingMatrix.getTranslateY();
    txtInfo.textMatrix = textRenderingMatrix;
    txtInfo.height= text.getHeightDir();
    txtInfo.width = text.getWidthDirAdj(); 
    txtInfo.unicode = text.getUnicode();
    txtInfo.fontName = text.getFont().getFontDescriptor().getFontName();
    txtInfo.fontSize = getActualFontSize(text, getGraphicsState());
    pdfGraphicContent.textPositions.add(txtInfo);
    
}

逐字符绘制文本到内容流的代码 #

private void addTextCharByChar(String string, List<TextPositionsInfo> textinfoList, TextBBoxinfo textBBoxinfo,PDPage page) throws IOException {

    PDResources res = page.getResources();
    currentContentStream.beginText(); 
    if (textBBoxinfo._ElementType.toLowerCase().equals("h2")) {
        beginMarkedConent(COSName.P);
        for(TextPositionsInfo textInfo : textinfoList) {
            PDFont font = getFont(res, textInfo.fontName);
            currentContentStream.setFont(font, textInfo.fontSize);
            Matrix _tm = textInfo.textMatrix;
            currentContentStream.newLineAtOffset(_tm.getTranslateX(), _tm.getTranslateY());
            currentContentStream.setTextMatrix(_tm);
            currentContentStream.showText(textInfo.unicode);
        }
        currentContentStream.endMarkedContent();
        addContentToCurrentSection(COSName.P, StandardStructureTypes.H2);
        
    }else if (textBBoxinfo._ElementType.toLowerCase().equals("h1")) {
        beginMarkedConent(COSName.P);
        for(TextPositionsInfo textInfo : textinfoList) {
            PDFont font = getFont(res, textInfo.fontName);
            currentContentStream.setFont(font, textInfo.fontSize);
            currentContentStream.newLineAtOffset(textInfo.textMatrix.getTranslateX(), 
          textInfo.textMatrix.getTranslateY());
           currentContentStream.setTextMatrix(textInfo.textMatrix);
            currentContentStream.showText(textInfo.unicode);
        }
        currentContentStream.endMarkedContent();
        addContentToCurrentSection(COSName.P, StandardStructureTypes.H1);
        
    }
    currentContentStream.endText();
    }

内容的提问来源于stack exchange，提问作者Nitish Kumar