1

我想通过 PDFBox 将波斯文本写入 pdf，但是，pdfbox 分隔和反向分隔字符。我应该如何解决这个问题？（我使用 pdfbox pdfbox-2.0.19 ）

这是我的代码：

                 PDDocument doc = new PDDocument();
                 PDPage page = new PDPage(PDRectangle.A4);
                 doc.addPage(page);
                 PDPageContentStream cont = new PDPageContentStream(doc, page);
                 cont.beginText();
                 PDType0Font font = PDType0Font.load(doc, new File("C:\\Users\\farhad\\Downloads\\vazir-font-v24.1.0\\Vazir.ttf"));
                 int fontSize = 15;
                 cont.setFont(font, fontSize);
                 String text = "برنامه نویس ایرانی هست اینو بلد باشه؟";
                 float x =  50;
                 float y = page.getMediaBox().getHeight() / 2;
                 cont.newLineAtOffset(x, y);
                 cont.showText(text);
                 cont.endText();
                 cont.close();
                 doc.save("D:\\pdf.pdf");

我附上了一个显示结果的屏幕截图。

在此处输入图像描述

4

1 回答 1

2

对于那些寻求这个问题答案的人：

您应该对 Unicode 字符进行一些操作。您通常知道的每个波斯字符（例如 س ش ت ظ）实际上有 4 种不同的形式，每种形式都有自己的 Unicode 字符。

  • 初始形式
  • 中间形式
  • 最终形式
  • 孤立的形式

让我们说سا这个词

在这种情况下，最初的 س 有一个 Unicode 字符，它与 راس 中的 س 不同，后者位于单词的末尾。

为了更好地理解，请看下图

在此处输入图像描述

如何获得每种形式的 Unicode 字符？

只需访问此网站https://www.compart.com/en/unicode/并搜索您的角色。

请注意，阿拉伯语和波斯语几乎使用相同的脚本，这就是为什么在我上传的图片中，它表示س 字符为“阿拉伯语字母已隔离形式”。

这是一个可用于计算 4 种不同形式的波斯字符的类：

 public class PersianCharachtersUnicode {

    char c;
    private String InitialFom_Unicode;
    private String MedialForm_Unicode;
    private String FinalForm_Unicode;
    private String IsolatedForm_Unicode;


    public void setCharc (char c) {
        this.c = c;
        calculate();
    }





    private void calculate() {

        switch (c) {

        case 'آ':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\0";
            IsolatedForm_Unicode  = "\uFE81";
            break;

        case 'ا':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFE8E";
            IsolatedForm_Unicode  = "\uFE8D";
            break;


        case 'ب':

            InitialFom_Unicode    = "\uFE91";
            MedialForm_Unicode    = "\uFE92";
            FinalForm_Unicode     = "\uFE90";
            IsolatedForm_Unicode  = "\uFE8F";
            break;


        case 'پ':

            InitialFom_Unicode    = "\uFB58";
            MedialForm_Unicode    = "\uFB59";
            FinalForm_Unicode     = "\uFB57";
            IsolatedForm_Unicode  = "\uFB56";
            break;


        case 'ت':

            InitialFom_Unicode    = "\uFE97";
            MedialForm_Unicode    = "\uFE98";
            FinalForm_Unicode     = "\uFE96";
            IsolatedForm_Unicode  = "\uFE95";
            break;


        case 'ث':

            InitialFom_Unicode    = "\uFE9B";
            MedialForm_Unicode    = "\uFE9C";
            FinalForm_Unicode     = "\uFE9A";
            IsolatedForm_Unicode  = "\uFE99";
            break;


        case 'ج':

            InitialFom_Unicode    = "\uFE9F";
            MedialForm_Unicode    = "\uFEA0";
            FinalForm_Unicode     = "\uFE9E";
            IsolatedForm_Unicode  = "\uFE9D";
            break;


        case 'چ':

            InitialFom_Unicode    = "\uFB7C";
            MedialForm_Unicode    = "\uFB7D";
            FinalForm_Unicode     = "\uFE9B";
            IsolatedForm_Unicode  = "\uFB7A";
            break;


        case 'ح':

            InitialFom_Unicode    = "\uFEA3";
            MedialForm_Unicode    = "\uFEA4";
            FinalForm_Unicode     = "\uFEA2";
            IsolatedForm_Unicode  = "\uFEA1";
            break;


        case 'خ':

            InitialFom_Unicode    = "\uFEA7";
            MedialForm_Unicode    = "\uFEA8";
            FinalForm_Unicode     = "\uFEA6";
            IsolatedForm_Unicode  = "\uFEA5";
            break;


        case 'د':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFEAA";
            IsolatedForm_Unicode  = "\uFEA9";
            break;


        case 'ذ':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFEAC";
            IsolatedForm_Unicode  = "\uFEAB";
            break;


        case 'ر':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFEAE";
            IsolatedForm_Unicode  = "\uFEAD";
            break;


        case 'ز':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFEB0";
            IsolatedForm_Unicode  = "\uFEAF";
            break;


        case 'ژ':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFB8B";
            IsolatedForm_Unicode  = "\uFB8A";
            break;


        case 'س':

            InitialFom_Unicode    = "\uFEB3";
            MedialForm_Unicode    = "\uFEB4";
            FinalForm_Unicode     = "\uFEB2";
            IsolatedForm_Unicode  = "\uFEB1";
            break;


        case 'ش':

            InitialFom_Unicode    = "\uFEB7";
            MedialForm_Unicode    = "\uFEB8";
            FinalForm_Unicode     = "\uFEB6";
            IsolatedForm_Unicode  = "\uFEB5";
            break;


        case 'ص':

            InitialFom_Unicode    = "\uFEBB";
            MedialForm_Unicode    = "\uFEBC";
            FinalForm_Unicode     = "\uFEBA";
            IsolatedForm_Unicode  = "\uFEB9";
            break;


        case 'ض':

            InitialFom_Unicode    = "\uFEBF";
            MedialForm_Unicode    = "\uFEC0";
            FinalForm_Unicode     = "\uFEBE";
            IsolatedForm_Unicode  = "\uFEBD";
            break;


        case 'ط':

            InitialFom_Unicode    = "\uFEC3";
            MedialForm_Unicode    = "\uFEC4";
            FinalForm_Unicode     = "\uFEC2";
            IsolatedForm_Unicode  = "\uFEC1";
            break;


        case 'ظ':

            InitialFom_Unicode    = "\uFEC7";
            MedialForm_Unicode    = "\uFEC8";
            FinalForm_Unicode     = "\uFEC6";
            IsolatedForm_Unicode  = "\uFEC5";
            break;


        case 'ع':

            InitialFom_Unicode    = "\uFECB";
            MedialForm_Unicode    = "\uFECC";
            FinalForm_Unicode     = "\uFECA";
            IsolatedForm_Unicode  = "\uFEC9";
            break;


        case 'غ':

            InitialFom_Unicode    = "\uFECF";
            MedialForm_Unicode    = "\uFED0";
            FinalForm_Unicode     = "\uFECE";
            IsolatedForm_Unicode  = "\uFECD";
            break;


        case 'ف':

            InitialFom_Unicode    = "\uFED3";
            MedialForm_Unicode    = "\uFED4";
            FinalForm_Unicode     = "\uFED2";
            IsolatedForm_Unicode  = "\uFED1";
            break;


        case 'ق':

            InitialFom_Unicode    = "\uFED7";
            MedialForm_Unicode    = "\uFED8";
            FinalForm_Unicode     = "\uFED6";
            IsolatedForm_Unicode  = "\uFED5";
            break;


        case 'ک':

            InitialFom_Unicode    = "\uFB90";
            MedialForm_Unicode    = "\uFB91";
            FinalForm_Unicode     = "\uFB8F";
            IsolatedForm_Unicode  = "\uFB8E";
            break;


        case 'گ':

            InitialFom_Unicode    = "\uFB94";
            MedialForm_Unicode    = "\uFB95";
            FinalForm_Unicode     = "\uFB93";
            IsolatedForm_Unicode  = "\uFB92";
            break;


        case 'ل':

            InitialFom_Unicode    = "\uFEDF";
            MedialForm_Unicode    = "\uFEE0";
            FinalForm_Unicode     = "\uFEDE";
            IsolatedForm_Unicode  = "\uFEDD";
            break;


        case 'م':

            InitialFom_Unicode    = "\uFEE3";
            MedialForm_Unicode    = "\uFEE4";
            FinalForm_Unicode     = "\uFEE2";
            IsolatedForm_Unicode  = "\uFEE1";
            break;


        case 'ن':

            InitialFom_Unicode    = "\uFEE7";
            MedialForm_Unicode    = "\uFEE8";
            FinalForm_Unicode     = "\uFEE6";
            IsolatedForm_Unicode  = "\uFEE5";
            break;


        case 'و':

            InitialFom_Unicode    = "\0";
            MedialForm_Unicode    = "\0";
            FinalForm_Unicode     = "\uFEEE";
            IsolatedForm_Unicode  = "\uFEED";
            break;


        case 'ه':

            InitialFom_Unicode    = "\uFEEB";
            MedialForm_Unicode    = "\uFEEC";
            FinalForm_Unicode     = "\uFEEA";
            IsolatedForm_Unicode  = "\uFEE9";
            break;


        case 'ی':

            InitialFom_Unicode    = "\uFBFE";
            MedialForm_Unicode    = "\uFBFF";
            FinalForm_Unicode     = "\uFBFD";
            IsolatedForm_Unicode  = "\uFBFC";
            break;


        default:
            break;
        }

    }




    /**
     * @return the initialFom_Unicode
     */
    public String getInitialFom_Unicode() {
        return InitialFom_Unicode;
    }

    /**
     * @return the finalForm_Unicode
     */
    public String getFinalForm_Unicode() {
        return FinalForm_Unicode;
    }

    /**
     * @return the isolatedForm_Unicode
     */
    public String getIsolatedForm_Unicode() {
        return IsolatedForm_Unicode;
    }

    /**
     * @return the medialForm_Unicode
     */
    public String getMedialForm_Unicode() {
        return MedialForm_Unicode;
    }
 }
于 2020-04-03T11:20:00.667 回答