JAVA: DA HTML A PDF CON ITEXT

Prima di procedere con il progetto SqlDocGen è necessario conoscere come si può produrre file PDF con un programma scritto in linguaggio Java, in particolare tramite l'utilizzo della libreria iTextFree. La cosa interessante è che l'input sarà un testo in HTML!

La cosa inizialmente può portare a confusione: cosa c'entra l'HTML con un file PDF? è presto fatto con la libreria iText che mette a disposizione metodi veloci per la conversione di un file HTML, formattato indentato con tabelle e colori, in un pratico file PDF in "sola lettura".

Salto volontariamente la discussione riguardo alla licenza AGPL sotto cui è distribuita attualmente la libreria iText. Vi consiglio di trovare in rete la versione 2.1.5 distribuita sotto LGPL.

Adesso vi mostro la classe-utility che ho pensato per incapsulare le funzionalità di questa interessante libreria:

package org.dgl.manager;

import com.lowagie.text.Document;
import com.lowagie.text.Element;
import com.lowagie.text.Font;
import com.lowagie.text.HeaderFooter;
import com.lowagie.text.PageSize;
import com.lowagie.text.Phrase;
import com.lowagie.text.Rectangle;
import com.lowagie.text.html.simpleparser.HTMLWorker;
import com.lowagie.text.pdf.PdfWriter;
import com.lowagie.text.pdf.codec.Base64;
import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.Reader;
import java.util.ArrayList;

public class PDFManager {

    private final String CHARSET = "UTF-8";
    private final String EXCEPTION_HTMLNOTPARSED = "HTML has not been parsed";
    private final String EXCEPTION_UNKNOWNHEADERALIGNMENT = "Unknown header alignment";
    private final String EXCEPTION_ILLEGALHEADEREXCEPTION="illegal header size";
    private final String PDF_CONTENTTYPE = "application/pdf";
    private final boolean DEFAULT_PAGECOUNTING = false;
    private final float DEFAULT_HEADERSIZE=12.0f;
    private final int DEFAULT_HEADER_ALIGN = HeaderFooter.ALIGN_LEFT;
    private final Document document;
    private final OutputStream pdfByteArrayOutputStream;
    private ArrayList htmlTags;
    private boolean htmlParsed;
    private final boolean pageCounting;
    private float headerSize;
    public static final int LEFT_HEADER_ALIGNMENT = HeaderFooter.ALIGN_LEFT;
    public static final int RIGHT_HEADER_ALIGNMENT = HeaderFooter.ALIGN_RIGHT;
    public static final int CENTER_HEADER_ALIGNMENT = HeaderFooter.ALIGN_CENTER;
    public static final float SMALL_HEADER_SIZE = 8;
    public static final float NORMAL_HEADER_SIZE =12.0f;
    public static final Rectangle LAYOUT_A3V=PageSize.A3;
    public static final Rectangle LAYOUT_A3H=PageSize.A3.rotate();
    public static final Rectangle LAYOUT_A4V=PageSize.A4;
    public static final Rectangle LAYOUT_A4H=PageSize.A4.rotate();
    public static final Rectangle LAYOUT_DEFAULT=LAYOUT_A4V;

    public PDFManager() {
        document = new Document(LAYOUT_DEFAULT);
        pdfByteArrayOutputStream = new ByteArrayOutputStream();
        htmlParsed = false;
        pageCounting = DEFAULT_PAGECOUNTING;
        headerSize=DEFAULT_HEADERSIZE;
    }

    public PDFManager(Rectangle layout) {
        document = new Document(layout);
        pdfByteArrayOutputStream = new ByteArrayOutputStream();
        htmlParsed = false;
        pageCounting = DEFAULT_PAGECOUNTING;
        headerSize=DEFAULT_HEADERSIZE;
    }

    public PDFManager(boolean pageCounting) {
        document = new Document(LAYOUT_DEFAULT);
        pdfByteArrayOutputStream = new ByteArrayOutputStream();
        htmlParsed = false;
        this.pageCounting = pageCounting;
        headerSize=DEFAULT_HEADERSIZE;
    }

    public PDFManager(boolean pageCounting,Rectangle layout) {
        document = new Document(layout);
        pdfByteArrayOutputStream = new ByteArrayOutputStream();
        htmlParsed = false;
        this.pageCounting = pageCounting;
        headerSize=DEFAULT_HEADERSIZE;
    }

    public void parseHTML(String html) throws Exception {
        html = purge(html);
        Reader tagReader = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(html.getBytes(CHARSET))));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    public void parseHTML(File file) throws Exception {
        Reader tagReader = new BufferedReader(new FileReader(file));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    public void parseHTML(String html, String header) throws Exception {
        html = purge(html);
        Reader tagReader = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(html.getBytes(CHARSET))));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        setHeader(header);
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    public void parseHTML(File file, String header) throws Exception {
        Reader tagReader = new BufferedReader(new FileReader(file));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        setHeader(header);
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    public void parseHTML(String html, String header, int alignment) throws Exception {
        Reader tagReader = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(html.getBytes(CHARSET))));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        setHeader(header, alignment);
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    public void parseHTML(File file, String header, int alignment) throws Exception {
        Reader tagReader = new BufferedReader(new FileReader(file));
        if (pageCounting) {
            (PdfWriter.getInstance(document, pdfByteArrayOutputStream)).setPageEvent(new PDFPageCounterManager());
        } else {
            PdfWriter.getInstance(document, pdfByteArrayOutputStream);
        }
        setHeader(header, alignment);
        document.open();
        htmlTags = HTMLWorker.parseToList(tagReader, null);
        for (int i = 0; i < htmlTags.size(); i++) {
            document.add(htmlTags.get(i));
        }
        document.close();
        tagReader.close();
        htmlParsed = true;
    }

    private void setHeader(String headerText) {
        Font f=new Font();
        f.setSize(headerSize);
        HeaderFooter header = new HeaderFooter(new Phrase(headerText,f), false);
        header.setAlignment(DEFAULT_HEADER_ALIGN);
        document.setHeader(header);
    }

    private void setHeader(String headerText, int alignment) throws Exception {
        if ((alignment != LEFT_HEADER_ALIGNMENT) && (alignment != RIGHT_HEADER_ALIGNMENT) && (alignment != CENTER_HEADER_ALIGNMENT)) {
            throw new Exception(EXCEPTION_UNKNOWNHEADERALIGNMENT);
        }
        Font f=new Font();
        f.setSize(headerSize);
        HeaderFooter header = new HeaderFooter(new Phrase(headerText,f), false);
        header.setAlignment(alignment);
        document.setHeader(header);
    }

    public void writePDF(String file) throws Exception {
        if (!htmlParsed) {
            throw new Exception(EXCEPTION_HTMLNOTPARSED);
        }
        byte[] pdfData = ((ByteArrayOutputStream) this.pdfByteArrayOutputStream).toByteArray();
        Base64.encodeBytes(pdfData);
        FileOutputStream pdfOutputStream = new FileOutputStream(new File(file));
        pdfOutputStream.write(pdfData);
        pdfOutputStream.close();
    }

    public void writePDF(File file) throws Exception {
        if (!htmlParsed) {
            throw new Exception(EXCEPTION_HTMLNOTPARSED);
        }
        byte[] pdfData = ((ByteArrayOutputStream) this.pdfByteArrayOutputStream).toByteArray();
        Base64.encodeBytes(pdfData);
        FileOutputStream pdfOutputStream = new FileOutputStream(file);
        pdfOutputStream.write(pdfData);
        pdfOutputStream.close();
    }

    public void setHeaderSize(float newHeaderSize) throws Exception{
        if(newHeaderSize<=0){
            throw new Exception(EXCEPTION_ILLEGALHEADEREXCEPTION);
        }
        this.headerSize=newHeaderSize;
    }

    public void close() throws Exception {
        pdfByteArrayOutputStream.flush();
        pdfByteArrayOutputStream.close();
        htmlTags.clear();
    }

    public static String purge(String text) {
        text = text.replaceAll("à", "à");
        text = text.replaceAll("é", "é");
        text = text.replaceAll("è", "è");
        text = text.replaceAll("ì", "ì");
        text = text.replaceAll("ò", "ò");
        text = text.replaceAll("ù", "ù");
        text = text.replaceAll("°", "°");
        return text;
    }
}

public class PDFPageCounterManager implements PdfPageEvent {

    private PdfTemplate total;

    @Override
    public void onOpenDocument(PdfWriter writer, Document document) {
        total = writer.getDirectContent().createTemplate(100, 100);
        total.setBoundingBox(new Rectangle(-20, -20, 100, 100));
    }

    @Override
    public void onStartPage(PdfWriter writer, Document dcmnt) {
        
    }

    @Override
    public void onEndPage(PdfWriter writer, Document document){
        String text = writer.getPageNumber()+"    ";

        float footerBase = document.bottom() - 30;

        float textSize = 8;
        float adjust = 2;

        PdfContentByte cb = writer.getDirectContent();
        cb.beginText();
        try {
            cb.setFontAndSize(BaseFont.createFont(BaseFont.TIMES_ROMAN, "Cp1252",false), 12);
        } catch(Exception ex){}
        cb.setTextMatrix(document.right() - textSize - adjust, footerBase);
        cb.showText(text);
        cb.endText();
        cb.addTemplate(total, document.right() - adjust, footerBase);
    }

    @Override
    public void onCloseDocument(PdfWriter writer, Document document) {
        total.beginText();
        try {
            total.setFontAndSize(BaseFont.createFont(BaseFont.TIMES_ROMAN, "Cp1252",false), 12);
        } catch(Exception ex){}
        total.setTextMatrix(0, 0);
        total.showText("  di "+String.valueOf(writer.getPageNumber() - 1));
        total.endText();
    }

    @Override
    public void onParagraph(PdfWriter writer, Document dcmnt, float f) {
       
    }

    @Override
    public void onParagraphEnd(PdfWriter writer, Document dcmnt, float f) {
        
    }

    @Override
    public void onChapter(PdfWriter writer, Document dcmnt, float f, Paragraph prgrph) {
       
    }

    @Override
    public void onChapterEnd(PdfWriter writer, Document dcmnt, float f) {
       
    }

    @Override
    public void onSection(PdfWriter writer, Document dcmnt, float f, int i, Paragraph prgrph) {
        
    }

    @Override
    public void onSectionEnd(PdfWriter writer, Document dcmnt, float f) {
       
    }

    @Override
    public void onGenericTag(PdfWriter writer, Document dcmnt, Rectangle rctngl, String string) {
       
    }
}

L'utilizzo di questa classe è immediato tramite il codice:

PDFManager pdfm = new PDFManager(true); \\initialize new instance and i want the page counting
pdfm.parseHTML("content","header"); \\it can be used tables, div, font, color, span ...
pdfm.writePDF("C:\\output.pdf"); \\set the output file name and path
pdfm.close(); \\free resources