Question

我无法显示PDF中HTML内容中的阿拉伯字符。

这是arabic.html的代码：

<html>
<body style="font-family: Noto Naskh Arabic">
<table>
<tr>
<td dir="rtl">رقم التعميم رقم التعميم</td>
<td dir="rtl">رقم التعميم</td>
</tr>
</table>
</body>
</html>

我尝试使用以下Java代码：

import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.charset.Charset;


/**
 *
 * @author iText
 */

public class ParseHtml8 {
    public static final String DEST = "f:\\test.pdf";
    public static final String HTML = "f:\\arabic.html";

    public static void main(String[] args) throws IOException, DocumentException {
        File file = new File(DEST);
        file.getParentFile().mkdirs();
        new ParseHtml8().createPdf(DEST);
    }

    /**
     * Creates a PDF 
     * @param file
     * @throws IOException
     * @throws DocumentException
     */
    public void createPdf(String file) throws IOException, DocumentException {
        // step 1
        Document document = new Document();
        // step 2
        PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(file));
        // step 3
        document.open();
        // step 4
        // Styles
        CSSResolver cssResolver = new StyleAttrCSSResolver();
        XMLWorkerFontProvider fontProvider = new XMLWorkerFontProvider(XMLWorkerFontProvider.DONTLOOKFORFONTS);
        fontProvider.register("f:\\NotoNaskhArabic-Regular.ttf");
        CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
        HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
        htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());

        // Pipelines
        PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
        HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
        CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);

        // XML Worker
        XMLWorker worker = new XMLWorker(css, true);
        XMLParser p = new XMLParser(worker);
        p.parse(new FileInputStream(HTML), Charset.forName("UTF-8"));;
        // step 5
        document.close();
    }
}

生成的PDF不包含任何字符。

pdf文件大小为：6KB，但为空

我使用了它extpdf-5.5.6.jar，xmlworker-5.5.6.jar

在这方面请帮助我。

使用Java将带有阿拉伯字符的html文件转换为pdf

0 个答案: