文档有些生词不认识，能划词翻译就很方便。
但是有些文档，看着是一个词，但是划词的时候就是划不全，比如Preface, 划词只能划到Pref,强行划整个的话，结果是
Pref ace,很难受啊。
研究了好几天，废寝忘食，终于给我实验出来了。
下面贴代码，最后附上前后pdf。

import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDFont;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.pdfbox.pdmodel.font.PDType1Font;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

import java.io.*;
import java.net.URLEncoder;
import java.util.List;

public class Fixer extends PDFTextStripper {

    public Fixer() throws IOException {
    }

    public static void main(String[] args) throws IOException {
        String srcFile = "C:\\Users\\tanmingxin\\Desktop\\go\\The.Go.Programming.Language.pdf";
        String dstFile = "C:\\Users\\tanmingxin\\Desktop\\go\\The.Go.Programming.Language-fixed.pdf";

         doIt(srcFile, dstFile);
    }

    TextPosition lastPositon = null;
    StringWriter dummy = new StringWriter();

    public static void doIt( String inputFile, String outputFile)
            throws IOException {

        Fixer fixer = new Fixer();
        try (PDDocument document = Loader.loadPDF(new File(inputFile)); PDDocument dstdocument = new PDDocument();)
        {
            PDFont font = PDType0Font.load(dstdocument, new File("c:/windows/fonts/times.ttf"));
            fixer.setSortByPosition( true );
            for (int i = 1; i <= document.getNumberOfPages(); i++) {
                System.out.println("---------------------------");
                System.out.println("第" + i + "页");
                fixer.setStartPage( i );
                fixer.setEndPage( i);

                StringWriter dummy = new StringWriter();
                fixer.writeText(document, dummy);
                if (fixer.lastPositon != null) {
                    fixer.dummy.append(fixer.lastPositon.getUnicode());
                    fixer.lastPositon = null;
                }
                String text = fixer.dummy.toString();
                fixer.dummy.close();
                fixer.dummy = new StringWriter();

                PDPage my_page = new PDPage();
                dstdocument.addPage(my_page);
                PDPageContentStream contentStream = new PDPageContentStream(dstdocument, my_page);


                contentStream.setFont( font, 12);
                int y = 760;
                String[] ss = text.split("\n");
                for (String s: ss) {
                    contentStream.beginText();
                    contentStream.newLineAtOffset(25, y);
                    contentStream.showText(s);
                    contentStream.newLine();
                    y -= 16;
                    contentStream.newLineAtOffset(25, y);
                    contentStream.endText();
                }
                contentStream.close();
            }
            dstdocument.save(outputFile);
        }
        fixer.dummy.close();

    }
    @Override
    protected void writeString(String string, List<TextPosition> textPositions) throws IOException
    {
        for (TextPosition text : textPositions)
        {
//            System.out.println( "String[" + text.getXDirAdj() + "," +
//                    text.getYDirAdj() + " fs=" + text.getFontSize() + " xscale=" +
//                    text.getXScale() + " height=" + text.getHeightDir() + " space=" +
//                    text.getWidthOfSpace() + " width=" +
//                    text.getWidthDirAdj() + "]" + text.getUnicode() );
            if (lastPositon != null) {
                float xx = text.getX() - lastPositon.getX();
                if (xx > 0) {
                    float abs = Math.abs(xx);
                    if (abs > lastPositon.getWidthOfSpace() / 2) {
                        if (abs > lastPositon.getWidth() + lastPositon.getWidthOfSpace()/ 2) {
                            dummy.append(lastPositon.getUnicode());
                            dummy.append(" ");
                        } else {
                            dummy.append(lastPositon.getUnicode());
                        }
                    }
                } else {
                    dummy.append(lastPositon.getUnicode());
                    dummy.append("\n");
                }
            }
            lastPositon  = text;
        }


    }

}

pdf效果地址

链接：https://pan.baidu.com/s/10v3_XcszZa4tI-BHNI2RKA
提取码：4art