JodConverter 在 java 中不支持 docx 文件

Question

我正在使用 JodConverter 将我的 .docx (Microsoft Office) 文件转换为 pdf，但不知何故它不会转换并给我 error.When 如果我尝试将 .doc 文档转换为 pdf 那么它可以工作 fine.I 我正在使用 maven JodConverter 插件版本 2.2.0 .

我的问题是是否可以使用 JODCoverter 将 .docx 文件转换为 pdf？

Answer 1

import java.io.File;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;

import org.apache.commons.io.FilenameUtils;

import com.artofsolving.jodconverter.DefaultDocumentFormatRegistry;
import com.artofsolving.jodconverter.DocumentConverter;
import com.artofsolving.jodconverter.DocumentFormat;
import com.artofsolving.jodconverter.DocumentFormatRegistry;
import com.artofsolving.jodconverter.openoffice.connection.OpenOfficeConnection;
import com.sun.star.beans.PropertyValue;
import com.sun.star.lang.XComponent;
import com.sun.star.uno.UnoRuntime;
import com.sun.star.util.XRefreshable;

public abstract class AbstractOpenOfficeDocumentConverter implements DocumentConverter {

    private final Map/*<String,Object>*/ defaultLoadProperties;

    protected OpenOfficeConnection openOfficeConnection;
    private DocumentFormatRegistry documentFormatRegistry;

    public AbstractOpenOfficeDocumentConverter(OpenOfficeConnection connection) {
        this(connection, new DefaultDocumentFormatRegistry());
    }

    public AbstractOpenOfficeDocumentConverter(OpenOfficeConnection openOfficeConnection, DocumentFormatRegistry documentFormatRegistry) {
        this.openOfficeConnection = openOfficeConnection;
        this.documentFormatRegistry = documentFormatRegistry;

        defaultLoadProperties = new HashMap();
        defaultLoadProperties.put("Hidden", Boolean.TRUE);
        defaultLoadProperties.put("ReadOnly", Boolean.TRUE);
    }

    public void setDefaultLoadProperty(String name, Object value) {
        defaultLoadProperties.put(name, value);
    }

    protected Map getDefaultLoadProperties() {
        return defaultLoadProperties;
    }

    protected DocumentFormatRegistry getDocumentFormatRegistry() {
        return documentFormatRegistry;
    }

    public void convert(File inputFile, File outputFile) {
        convert(inputFile, outputFile, null);
    }

    public void convert(File inputFile, File outputFile, DocumentFormat outputFormat) {
        convert(inputFile, null, outputFile, outputFormat);
    }

    public void convert(InputStream inputStream, DocumentFormat inputFormat, OutputStream outputStream, DocumentFormat outputFormat) {
        ensureNotNull("inputStream", inputStream);
        ensureNotNull("inputFormat", inputFormat);
        ensureNotNull("outputStream", outputStream);
        ensureNotNull("outputFormat", outputFormat);
        convertInternal(inputStream, inputFormat, outputStream, outputFormat);
    }

    public void convert(File inputFile, DocumentFormat inputFormat, File outputFile, DocumentFormat outputFormat) {
        ensureNotNull("inputFile", inputFile);
        ensureNotNull("outputFile", outputFile);

        if (!inputFile.exists()) {
            throw new IllegalArgumentException("inputFile doesn't exist: " + inputFile);
        }
        if (inputFormat == null) {
            inputFormat = guessDocumentFormat(inputFile);
        }
        if (outputFormat == null) {
            outputFormat = guessDocumentFormat(outputFile);
        }
        if (!inputFormat.isImportable()) {
            throw new IllegalArgumentException("unsupported input format: " + inputFormat.getName());
        }
        if (!inputFormat.isExportableTo(outputFormat)) {
            throw new IllegalArgumentException("unsupported conversion: from " + inputFormat.getName() + " to " + outputFormat.getName());
        }
        convertInternal(inputFile, inputFormat, outputFile, outputFormat);
    }

    protected abstract void convertInternal(InputStream inputStream, DocumentFormat inputFormat, OutputStream outputStream, DocumentFormat outputFormat);

    protected abstract void convertInternal(File inputFile, DocumentFormat inputFormat, File outputFile, DocumentFormat outputFormat);

    private void ensureNotNull(String argumentName, Object argumentValue) {
        if (argumentValue == null) {
            throw new IllegalArgumentException(argumentName + " is null");
        }
    }

    private DocumentFormat guessDocumentFormat(File file) {
        String extension = FilenameUtils.getExtension(file.getName());
        DocumentFormat format = getDocumentFormatRegistry().getFormatByFileExtension(extension);
        if (format == null) {
            throw new IllegalArgumentException("unknown document format for file: " + file);
        }
        return format;
    }

    protected void refreshDocument(XComponent document) {
        XRefreshable refreshable = (XRefreshable) UnoRuntime.queryInterface(XRefreshable.class, document);
        if (refreshable != null) {
            refreshable.refresh();
        }
    }

    protected static PropertyValue property(String name, Object value) {
        PropertyValue property = new PropertyValue();
        property.Name = name;
        property.Value = value;
        return property;
    }

    protected static PropertyValue[] toPropertyValues(Map/*<String,Object>*/ properties) {
        PropertyValue[] propertyValues = new PropertyValue[properties.size()];
        int i = 0;
        for (Iterator iter = properties.entrySet().iterator(); iter.hasNext();) {
            Map.Entry entry = (Map.Entry) iter.next();
            Object value = entry.getValue();
            if (value instanceof Map) {
                // recursively convert nested Map to PropertyValue[]
                Map subProperties = (Map) value;
                value = toPropertyValues(subProperties);
            }
            propertyValues[i++] = property((String) entry.getKey(), value);
        }
        return propertyValues;
    }
}

Answer 2

JodConverter 2.2.1 版无法猜测 docx 的文档格式。虽然您可以将输入文件的文档格式作为参数传递。

final DocumentFormat docx = new DocumentFormat("Microsoft Word 2007 XML", DocumentFamily.TEXT, "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "docx");
converter.convert(inputFile, docx, outputFile, null);

Answer 3

免责声明：我拥有 jodconverter.org 域并在 GitHub 上分叉了原始项目。

晚会有点晚了，但您可以使用 Maven 上提供的原始项目的分支：

JODConverter

它支持 docx 和 xlsx 格式。

Answer 4

如果您还在使用旧的JodConverter 2.2.1 并且不想升级它，您可以将docx 文档格式添加到注册表中。代码将如下所示：

DefaultDocumentFormatRegistry documentFormatRegistry= new DefaultDocumentFormatRegistry();
DocumentFormat docx = new DocumentFormat("Microsoft Word 2007 XML", "application/vnd.openxmlformats-officedocument.wordprocessingml.document","docx");
docx.setExportFilter(DocumentFamily.TEXT,"MS Word 2007 XML");
documentFormatRegistry.addDocumentFormat(docx);
OpenOfficeDocumentConverter converter = new OpenOfficeDocumentConverter(connection,documentFormatRegistry);

JodConverter 在 java 中不支持 docx 文件

JodConverter does not support docx file in java

docx

jodconverter