使用 itextsharp 在 C# 中提取阿拉伯文本

Question

我有这段代码，我用它来获取 PDF 的文本。这对于英文 PDF 来说非常棒，但是当我尝试提取阿拉伯语文本时，它向我显示了类似这样的内容。

") + n 9 n <+, + )+ $ # $ +$ F% 9& .< $ : ;"

using (PdfReader reader = new PdfReader(path))
{
     ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
     String text = "";
     for (int i = 1; i <= reader.NumberOfPages; i++)
     {
          text = PdfTextExtractor.GetTextFromPage(reader, i,strategy);
     }

}

Answer 1

我不得不像这样改变策略

var t = PdfTextExtractor.GetTextFromPage(reader, i, new LocationTextExtractionStrategy());
var te = Convert(t);

这个函数可以反转阿拉伯语单词并保留英语

  private string Convert(string source)
  {
       string arabicWord = string.Empty;
       StringBuilder sbDestination = new StringBuilder();

       foreach (var ch in source)
       {
           if (IsArabic(ch))
               arabicWord += ch;
           else
           {
               if (arabicWord != string.Empty)
                    sbDestination.Append(Reverse(arabicWord));

               sbDestination.Append(ch);
               arabicWord = string.Empty;
            }
        }

        // if the last word was arabic    
        if (arabicWord != string.Empty)
            sbDestination.Append(Reverse(arabicWord));

        return sbDestination.ToString();
     }


     private bool IsArabic(char character)
     {
         if (character >= 0x600 && character <= 0x6ff)
             return true;

         if (character >= 0x750 && character <= 0x77f)
             return true;

         if (character >= 0xfb50 && character <= 0xfc3f)
             return true;

         if (character >= 0xfe70 && character <= 0xfefc)
             return true;

         return false;
     }

     // Reverse the characters of string
     string Reverse(string source)
     {
          return new string(source.ToCharArray().Reverse().ToArray());
     }