iText 7 获取所有文本块及其位置

如何解决iText 7 获取所有文本块及其位置

我正在尝试使用 iText7 获取所有单独的文本夹头及其位置。我需要解析夹头并让用户选择要从未来相同的 PDF 中解析的特定文本。我需要让用户选择员工姓名、ID 和其他文本。然后我将存储该数据的位置以用于处理未来的 PDF。选择/映射是一次性设置。以下是我在 iText 5 中返回的数据示例：

X	Y	块文本
1.763889	282.9278	11225 north Sourth St,bedrock,ND,99780,Ph: 999 321-6543
15.166975	277.17752	员工 ID
67.3675	277.17752	员工姓名
18.458744	272.22098	001159
68.33058	272.22098	Fred Flintstone

以下代码适用于 iText 5，我正在尝试将其迁移到 iText 7 以用于项目。 iText 7 中不再公开某些对象。

void Main()
{
    string filename = @"C:\Employee Info.pdf";
    
    using (var reader = new PdfReader(filename))
    {

        var parser = new PdfReaderContentParser(reader);

        var strategy = parser.ProcessContent(1,new LocationTextExtractionStrategyWithPosition());

        // work with the locatins on the chucks to provide list to user.

        reader.Close();
    }
}


public class LocationTextExtractionStrategyWithPosition : LocationTextExtractionStrategy
{
    public readonly List<TextChunk> locationalResult = new List<TextChunk>();

    private readonly ITextChunkLocationStrategy tclStrat;

    public LocationTextExtractionStrategyWithPosition() : this(new TextChunkLocationStrategyDefaultImp())
    {
    }

    public LocationTextExtractionStrategyWithPosition(ITextChunkLocationStrategy strat)
    {
        tclStrat = strat;
    }

    public override void RenderText(TextRenderInfo renderInfo)
    {
        Linesegment segment = renderInfo.GetBaseline();
        if (renderInfo.GetRise() != 0)
        { // remove the rise from the baseline - we do this because the text from a super/subscript render operations should probably be considered as part of the baseline of the text the super/sub is relative to 
            Matrix riSEOffsetTransform = new Matrix(0,-renderInfo.GetRise());
            segment = segment.TransformBy(riSEOffsetTransform);
        }
        TextChunk tc = new TextChunk(renderInfo.GetText(),tclStrat.CreateLocation(renderInfo,segment));
        //tc.Dump();
        locationalResult.Add(tc);
    }
}

public class TextLocation
{
    public float X { get; set; }
    public float Y { get; set; }

    public string Text { get; set; }
}