Java ContentReader.setMimetype方法代码示例

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test transforming a valid eml with a html part containing html special characters to text
 */
public void testHtmlSpecialCharsToText() throws Exception
{
    File emlSourceFile = loadQuickTestFile("htmlChars.eml");
    File txtTargetFile = TempFileProvider.createTempFile("test6", ".txt");
    ContentReader reader = new FileContentReader(emlSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_RFC822);
    ContentWriter writer = new FileContentWriter(txtTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);

    transformer.transform(reader, writer);

    ContentReader reader2 = new FileContentReader(txtTargetFile);
    reader2.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    String contentStr = reader2.getContentString();
    assertTrue(!contentStr.contains(HTML_SPACE_SPECIAL_CHAR));
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test transforming a non-ascii eml file to text
 */
public void testNonAsciiRFC822ToText() throws Exception
{
    File emlSourceFile = loadQuickTestFile("spanish.eml");
    File txtTargetFile = TempFileProvider.createTempFile("test2", ".txt");
    ContentReader reader = new FileContentReader(emlSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_RFC822);
    ContentWriter writer = new FileContentWriter(txtTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);

    transformer.transform(reader, writer);

    ContentReader reader2 = new FileContentReader(txtTargetFile);
    reader2.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    String contentStr = reader2.getContentString();
    assertTrue(contentStr.contains(QUICK_EML_CONTENT_SPANISH_UNICODE));
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
private Map<String, Serializable> openAndCheck(String fileBase, String expMimeType) throws Throwable {
   // Get the mimetype via the MimeTypeMap 
   // (Uses Tika internally for the detection)
   File file = open(fileBase);
   ContentReader detectReader = new FileContentReader(file);
   String mimetype = mimetypeMap.guessMimetype(fileBase, detectReader);

   assertEquals("Wrong mimetype for " + fileBase, mimetype, expMimeType);
   
   // Ensure the Tika Auto parser actually handles this
   assertTrue("Mimetype should be supported but isn't: " + mimetype, extracter.isSupported(mimetype));
   
   // Now create our proper reader
   ContentReader sourceReader = new FileContentReader(file);
   sourceReader.setMimetype(mimetype);
   
   // And finally do the properties extraction
   return extracter.extractRaw(sourceReader);
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test for MNT-577: Alfresco is running 100% CPU for over 10 minutes while extracting metadata for Word office document
 * 
 * @throws Exception
 */
public void testFootnotesLimitParameterUsingDefault() throws Exception
{
    PoiMetadataExtracter extractor = (PoiMetadataExtracter) getExtracter();

    File sourceFile = AbstractContentTransformerTest.loadNamedQuickTestFile(PROBLEM_FOOTNOTES_DOCUMENT_NAME);
    ContentReader sourceReader = new FileContentReader(sourceFile);
    sourceReader.setMimetype(MimetypeMap.MIMETYPE_OPENXML_WORDPROCESSING);

    Map<QName, Serializable> properties = new HashMap<QName, Serializable>();
    long startTime = System.currentTimeMillis();
    extractor.extract(sourceReader, properties);
    extractionTimeWithDefaultFootnotesLimit = System.currentTimeMillis() - startTime;

    assertExtractedProperties(properties);
    if (extractionTimeWithLargeFootnotesLimit != null)
    {
        assertTrue("The second metadata extraction operation must be longer!", extractionTimeWithLargeFootnotesLimit > extractionTimeWithDefaultFootnotesLimit);
    }
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Writes the supplied text out to a temporary file, and opens
 *  a content reader onto it. 
 */
protected static ContentReader buildContentReader(String text, Charset encoding)
    throws IOException
{
    File tmpFile = TempFileProvider.createTempFile("AlfrescoTest_", ".txt");
    FileOutputStream out = new FileOutputStream(tmpFile);
    OutputStreamWriter wout = new OutputStreamWriter(out, encoding);
    wout.write(text);
    wout.close();
    out.close();
    
    ContentReader reader = new FileContentReader(tmpFile);
    reader.setEncoding(encoding.displayName());
    reader.setMimetype("text/plain");
    return reader;
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
public void testCsvOutput() throws Exception
{
   File sourceFile = AbstractContentTransformerTest.loadQuickTestFile("xls");
   ContentReader sourceReader = new FileContentReader(sourceFile);

   File targetFile = TempFileProvider.createTempFile(
         getClass().getSimpleName() + "_" + getName() + "_xls_",
         ".csv");
   ContentWriter targetWriter = new FileContentWriter(targetFile);
   
   sourceReader.setMimetype(MimetypeMap.MIMETYPE_EXCEL);
   targetWriter.setMimetype(MimetypeMap.MIMETYPE_TEXT_CSV);
   transformer.transform(sourceReader, targetWriter);
   
   ContentReader targetReader = targetWriter.getReader();
   String checkContent = targetReader.getContentString();
   
   additionalContentCheck(
         MimetypeMap.MIMETYPE_EXCEL, 
         MimetypeMap.MIMETYPE_TEXT_CSV, 
         checkContent
   );
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test what is up with HTML to PDF
 */
public void testHtmlToPdf() throws Exception
{
    if (!isOpenOfficeWorkerAvailable())
    {
        // no connection
        System.err.println("ooWorker not available - skipping testHtmlToPdf !!");
        return;
    }
    File htmlSourceFile = loadQuickTestFile("html");
    File pdfTargetFile = TempFileProvider.createTempFile(getName() + "-target-", ".pdf");
    ContentReader reader = new FileContentReader(htmlSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_HTML);
    ContentWriter writer = new FileContentWriter(pdfTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_PDF);
    
    transformer.transform(reader, writer);
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * ALF-219. Transforamtion from .html to .pdf for empty file.
 * @throws Exception
 */
public void testEmptyHtmlToEmptyPdf() throws Exception
{
    if (!isOpenOfficeWorkerAvailable())
    {
        // no connection
        System.err.println("ooWorker not available - skipping testEmptyHtmlToEmptyPdf !!");
        return;
    }
    URL url = this.getClass().getClassLoader().getResource("misc/empty.html");
    assertNotNull("URL was unexpectedly null", url);

    File htmlSourceFile = new File(url.getFile());
    assertTrue("Test file does not exist.", htmlSourceFile.exists());
    
    File pdfTargetFile = TempFileProvider.createTempFile(getName() + "-target-", ".pdf");
    
    ContentReader reader = new FileContentReader(htmlSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_HTML);
    ContentWriter writer = new FileContentWriter(pdfTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_PDF);
    
    transformer.transform(reader, writer);
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test for MNT-577: Alfresco is running 100% CPU for over 10 minutes while extracting metadata for Word office document
 * 
 * @throws Exception
 */
public void testFootnotesLimitParameterUsingLarge() throws Exception
{
    PoiMetadataExtracter extractor = (PoiMetadataExtracter) getExtracter();

    File sourceFile = AbstractContentTransformerTest.loadNamedQuickTestFile(PROBLEM_FOOTNOTES_DOCUMENT_NAME);
    ContentReader sourceReader = new FileContentReader(sourceFile);
    sourceReader.setMimetype(MimetypeMap.MIMETYPE_OPENXML_WORDPROCESSING);

    // Just let the extractor do the job...
    extractor.setPoiFootnotesLimit(LARGE_FOOTNOTES_LIMIT);
    extractor.afterPropertiesSet();
    Map<QName, Serializable> properties = new HashMap<QName, Serializable>();
    long startTime = System.currentTimeMillis();
    extractor.extract(sourceReader, properties);
    extractionTimeWithLargeFootnotesLimit = System.currentTimeMillis() - startTime;

    assertExtractedProperties(properties);
    if (extractionTimeWithDefaultFootnotesLimit != null)
    {
        assertTrue("The second metadata extraction operation must be longer!", extractionTimeWithLargeFootnotesLimit > extractionTimeWithDefaultFootnotesLimit);
    }
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test transforming a valid unicode msg file to text
 */
public void testUnicodeMsgToText() throws Exception
{
    File msgSourceFile = loadQuickTestFile("unicode.msg");
    File txtTargetFile = TempFileProvider.createTempFile(getName() + "-target-2", ".txt");
    ContentReader reader = new FileContentReader(msgSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_OUTLOOK_MSG);
    ContentWriter writer = new FileContentWriter(txtTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    
    transformer.transform(reader, writer);
    
    ContentReader reader2 = new FileContentReader(txtTargetFile);
    reader2.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    assertTrue(reader2.getContentString().contains(QUICK_CONTENT));
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test transforming a chinese non-unicode msg file to
 *  text
 */
public void testNonUnicodeChineseMsgToText() throws Exception
{
    File msgSourceFile = loadQuickTestFile("chinese.msg");
    File txtTargetFile = TempFileProvider.createTempFile(getName() + "-target-2", ".txt");
    ContentReader reader = new FileContentReader(msgSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_OUTLOOK_MSG);
    ContentWriter writer = new FileContentWriter(txtTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    
    transformer.transform(reader, writer);
    
    ContentReader reader2 = new FileContentReader(txtTargetFile);
    reader2.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    
    // Check the quick text
    String text = reader2.getContentString();
    assertTrue(text.contains(QUICK_CONTENT));
    
    // Now check the non quick parts came out ok
    assertTrue(text.contains("(\u5f35\u6bd3\u502b)"));
    assertTrue(text.contains("\u683c\u5f0f\u6e2c\u8a66 )"));
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Test transforming a valid eml file to text
 */
public void testRFC822ToText() throws Exception
{
    File emlSourceFile = loadQuickTestFile("eml");
    File txtTargetFile = TempFileProvider.createTempFile("test", ".txt");
    ContentReader reader = new FileContentReader(emlSourceFile);
    reader.setMimetype(MimetypeMap.MIMETYPE_RFC822);
    ContentWriter writer = new FileContentWriter(txtTargetFile);
    writer.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);

    transformer.transform(reader, writer);

    ContentReader reader2 = new FileContentReader(txtTargetFile);
    reader2.setMimetype(MimetypeMap.MIMETYPE_TEXT_PLAIN);
    assertTrue(reader2.getContentString().contains(QUICK_EML_CONTENT));
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
/**
 * Performs checks and copies required reader attributes
 */
public final ContentReader getReader() throws ContentIOException
{
    String contentUrl = getContentUrl();
    if (!isClosed())
    {
        return new EmptyContentReader(contentUrl);
    }
    ContentReader reader = createReader();
    if (reader == null)
    {
        throw new AlfrescoRuntimeException("ContentReader failed to create new reader: \n" +
                "   writer: " + this);
    }
    else if (reader.getContentUrl() == null || !reader.getContentUrl().equals(contentUrl))
    {
        throw new AlfrescoRuntimeException("ContentReader has different URL: \n" +
                "   writer: " + this + "\n" +
                "   new reader: " + reader);
    }
    // copy across common attributes
    reader.setMimetype(this.getMimetype());
    reader.setEncoding(this.getEncoding());
    reader.setLocale(this.getLocale());
    // done
    if (logger.isDebugEnabled())
    {
        logger.debug("Writer spawned new reader: \n" +
                "   writer: " + this + "\n" +
                "   new reader: " + reader);
    }
    return reader;
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
protected Map<QName, Serializable> extractFromFile(File sourceFile, String mimetype) throws Exception
{
    Map<QName, Serializable> properties = new HashMap<QName, Serializable>();
    // construct a reader onto the source file
    ContentReader sourceReader = new FileContentReader(sourceFile);
    sourceReader.setMimetype(mimetype);
    getExtracter().extract(sourceReader, properties);
    return properties;
}
 

import org.alfresco.service.cmr.repository.ContentReader; //导入方法依赖的package包/类
public void testExcelToPdfConversion() throws Exception
{
    String[] quickFiles = getQuickFilenames(sourceMimeType);
    for (String quickFile : quickFiles)
    {
        String sourceExtension = quickFile.substring(quickFile.lastIndexOf('.') + 1);

        // is there a test file for this conversion?
        File sourceFile = AbstractContentTransformerTest.loadNamedQuickTestFile(quickFile);
        if (sourceFile == null)
        {
            continue; // no test file available for that extension
        }
        ContentReader sourceReader = new FileContentReader(sourceFile);

        // make a writer for the target file
        File targetFile = TempFileProvider.createTempFile(getClass().getSimpleName() + "_" + getName() + "_" + sourceExtension + "_", ".pdf");
        ContentWriter targetWriter = new FileContentWriter(targetFile);

        // do the transformation
        sourceReader.setMimetype(sourceMimeType);
        targetWriter.setMimetype(targetMimeType);
        try
        {
            transformer.transform(sourceReader.getReader(), targetWriter);
        }
        catch (ContentIOException e)
        {
            // all transformers expected to fail for password protected MS office document
        }
        
        if (transformer.getTriggered().getValue())
        {
            org.junit.Assert.fail("final AbstractContentTransformer2.transform was called for html2pdf");
        }
    }
}