Como converter Mail Merge PDF em palavra

Este artigo demonstra um exemplo simples de como mostrar Mail Merge em um documento do word convertido de PDF e, em seguida, salvar PDF. Usando Aspose.Words, executar um processo simples Mail Merge no arquivo convertido PDF para palavras não funciona em alguns casos. O problema ocorre porque Aspose.PDF não escreve real MERGEFIELDs durante a conversão de PDF para DOCX (Documentos do Word). Mas isso pode ser alcançado convertendo esses textos estáticos em MERGEFIELDs real e, em seguida, executando a operação Mail Merge. Consulte a seguinte solução alternativa.

// For complete examples and data files, please go to https://github.com/aspose-words/Aspose.Words-for-Java
String dataDir = Utils.getDataDir(BubbleChart.class);

String fileName = "Converted.pdf";
com.aspose.pdf.Document pdfDoc = new com.aspose.pdf.Document(dataDir + fileName);

ByteArrayOutputStream baOs = new ByteArrayOutputStream();
//Converting PDF document to word document
pdfDoc.save(baOs, com.aspose.pdf.SaveFormat.DocX);

String[] referenceFields = {"FIRSTNAME", "MEMFIRST"};
Object[] referenceValues = {"AAA", "BBB"};

Document document = mailMergeTemplate(baOs.toByteArray(), referenceFields, referenceValues);
document.save(dataDir + "Saved.pdf");

// For complete examples and data files, please go to https://github.com/aspose-words/Aspose.Words-for-Java
private static Document mailMergeTemplate(byte[] templateFile, String[] referenceFields, Object[] referenceValues) throws Exception {
    Document doc = null;
    try {
        doc = new Document(new ByteArrayInputStream(templateFile));

        FindReplaceOptions opts = new FindReplaceOptions();
        opts.setFindWholeWordsOnly(false);
        opts.setReplacingCallback(new ReplaceEvaluatorFindAndInsertMergefield());

        doc.getRange().replace(Pattern.compile("�(.*?)�"), "", opts);

        doc.getMailMerge().setFieldMergingCallback(new HandleMergeFields());
        doc.getMailMerge().execute(referenceFields, referenceValues);
    } catch (Exception e) {
        e.printStackTrace();
    }
    return doc;
}

// For complete examples and data files, please go to https://github.com/aspose-words/Aspose.Words-for-Java

    /**
     * This is called when mail merge engine encounters plain text (non image) merge
     */
    static class HandleMergeFields implements IFieldMergingCallback {
        public void fieldMerging(FieldMergingArgs args) throws Exception {
            System.out.println("Mail merge for field : " + args.getFieldName() + " & Value : " + args.getFieldValue());
        }

        /**
         * This is called when mail merge engine encounters Image:XXX merge
         * field in the document. You have a chance to return an Image object,
         * file name or a stream that contains the image.
         */
        public void imageFieldMerging(ImageFieldMergingArgs e) throws Exception {
            System.out.println("Mail merge for field : " + e.getFieldName() + " & Value : " + e.getFieldValue());
        }
    }

// For complete examples and data files, please go to https://github.com/aspose-words/Aspose.Words-for-Java
static class ReplaceEvaluatorFindAndInsertMergefield implements IReplacingCallback {

    public int replacing(ReplacingArgs e) throws Exception {
        // This is a Run node that contains either the beginning or the complete match.
        Node currentNode = e.getMatchNode();

        // The first (and may be the only) run can contain text before the match,
        // in this case it is necessary to split the run.
        if (e.getMatchOffset() > 0)
            currentNode = splitRun((Run) currentNode, e.getMatchOffset());

        ArrayList runs = new ArrayList();

        // Find all runs that contain parts of the match string.
        int remainingLength = e.getMatch().group().length();
        while ((remainingLength > 0) && (currentNode != null) && (currentNode.getText().length() <= remainingLength)) {
            runs.add(currentNode);
            remainingLength = remainingLength - currentNode.getText().length();

            // Select the next Run node.
            // Have to loop because there could be other nodes such as BookmarkStart etc.
            do {
                currentNode = currentNode.getNextSibling();
            } while ((currentNode != null) && (currentNode.getNodeType() != NodeType.RUN));
        }

        // Split the last run that contains the match if there is any text left.
        if ((currentNode != null) && (remainingLength > 0)) {
            splitRun((Run) currentNode, remainingLength);
            runs.add(currentNode);
        }

        //Change static text to real merge fields.
        DocumentBuilder builder = new DocumentBuilder((Document) e.getMatchNode().getDocument());
        builder.moveTo((Run) runs.get(runs.size() - 1));
        builder.insertField("MERGEFIELD \"" + e.getMatch().group(1) + "\"");

        for (Run run : (Iterable<Run>) runs)
            run.remove();

        // Signal to the replace engine to do nothing because we have already done all what we wanted.
        return ReplaceAction.SKIP;
    }

    /**
     * Splits text of the specified run into two runs. Inserts the new run just
     * after the specified run.
     */
    private Run splitRun(Run run, int position) throws Exception {
        Run afterRun = (Run) run.deepClone(true);
        afterRun.setText(run.getText().substring(position));
        run.setText(run.getText().substring((0), (0) + (position)));
        run.getParentNode().insertAfter(afterRun, run);
        return afterRun;
    }
}