从 PDF 中提取文本时,我也需要提取字体大小。首先我是这样提取的:
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(
curBaseline[Vector.I1],
curBaseline[Vector.I2],
topRight[Vector.I1],
topRight[Vector.I2]);
在这我无法获得确切的字体大小。之后我尝试使用renderinfo.gs.fontsize;
. 在这个renderinfo.gs.fontsize
我会得到一些文本字体大小确切的一个,但很少我不会得到确切的字体大小。我将在哪里获得字体大小为“1.0”。谁能告诉我我使用的方法是正确的。如果否,是否有任何其他方法可以使用 iTextSharp 提取字体大小。我正在使用 iTextSharp 5.4 版本。先感谢您。
using System;
using System.Collections;
// code java to C# conversion
public void renderText(TextRenderInfo renderInfo)
{
LineSegment curBaseline = renderInfo.Baseline;
LineSegment curAscentline = renderInfo.AscentLine;
Rectangle rect = new Rectangle(curBaseline.StartPoint.get(ArrayList.I1), curBaseline.StartPoint.get(ArrayList.I2), curAscentline.EndPoint.get(ArrayList.I1), curAscentline.EndPoint.get(ArrayList.I2));
try
{
Console.Write(" [{0,6:F2}, {1,6:F2}, {2,6:F2}] \"{3}\" ({4} at {5,6:F2})\n", rect.Width, rect.Height, getEffectiveFontSize(renderInfo), renderInfo.Text, renderInfo.Font.FullFontName[0], getFontSize(renderInfo));
}
catch (Exception e)
{
Console.WriteLine(e.ToString());
Console.Write(e.StackTrace);
}
}
float getEffectiveFontSize(TextRenderInfo renderInfo) throws System.ArgumentException, SecurityException, IllegalAccessException, InvocationTargetException, NoSuchFieldException, NoSuchMethodException
{
Method convertHeight = typeof(TextRenderInfo).getDeclaredMethod("convertHeightFromTextSpaceToUserSpace", float.TYPE);
convertHeight.Accessible = true;
return (float?)convertHeight.invoke(renderInfo, getFontSize(renderInfo));
}
float getFontSize(TextRenderInfo renderInfo) throws SecurityException, NoSuchFieldException, System.ArgumentException, IllegalAccessException
{
Field gsField = typeof(TextRenderInfo).getDeclaredField("gs");
gsField.Accessible = true;
GraphicsState gs = (GraphicsState) gsField.get(renderInfo);
return gs.FontSize;
}