Example usage for org.apache.poi.poifs.filesystem Entry getName

List of usage examples for org.apache.poi.poifs.filesystem Entry getName

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.poifs.filesystem.*
  5. Entry
  6. getName

Introduction

In this page you can find the example usage for org.apache.poi.poifs.filesystem Entry getName.

Prototype


public String getName();

Source Link

Document

get the name of the Entry

Usage

From source file:NewEmptyJUnitTest.java

/**
 * [RESOLVED FIXED] Bug 51686 - Update to POI 3.8 beta 4 causes
 * ConcurrentModificationException in Tika's OfficeParser
 */// w ww.  j ava  2  s  . c  o m
public void testBug51686() throws IOException {
    InputStream is = POIDataSamples.getDocumentInstance().openResourceAsStream("Bug51686.doc");

    POIFSFileSystem fs = new POIFSFileSystem(is);

    String text = null;

    for (Entry entry : fs.getRoot()) {
        if ("WordDocument".equals(entry.getName())) {
            WordExtractor ex = new WordExtractor(fs);
            try {
                text = ex.getText();
            } finally {
                ex.close();
            }
        }
    }

    assertNotNull(text);
}

From source file:com.argo.hwp.v5.HwpTextExtractorV5.java

License:Open Source License

/**
 * ? /*from   ww w.j  a  va 2  s  . c om*/
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("BodyText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid BodyText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);
            if (header.compressed)
                input = new InflaterInputStream(input, new Inflater(true));

            HwpStreamReader sectionStream = new HwpStreamReader(input);

            try {
                extractText(sectionStream, writer);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:com.hp.application.automation.tools.octane.actions.UFTParameterFactory.java

License:Apache License

public static String convertResourceMtrAsJSON(InputStream resourceMtrInputStream) throws IOException {

    //TODO: Check is exists
    poiFS = new POIFSFileSystem(resourceMtrInputStream);
    DirectoryNode root = poiFS.getRoot();

    for (Entry entry : root) {
        String name = entry.getName();
        if (name.equals("ComponentInfo")) {
            if (entry instanceof DirectoryEntry) {
                System.out.println(entry);
            } else if (entry instanceof DocumentEntry) {
                byte[] content = new byte[((DocumentEntry) entry).getSize()];
                poiFS.createDocumentInputStream("ComponentInfo").read(content);
                String fromUnicodeLE = StringUtil.getFromUnicodeLE(content);
                xmlData = fromUnicodeLE.substring(fromUnicodeLE.indexOf('<')).replaceAll("\u0000", "");
                //                    System.out.println(xmlData);
            }/*from   ww  w .j  a  v  a2  s.co  m*/
        }
    }
    try {
        SAXBuilder saxBuilder = new SAXBuilder(XMLReaders.NONVALIDATING, (SAXHandlerFactory) null,
                (JDOMFactory) null);
        Document document = null;
        document = saxBuilder.build(new StringReader(xmlData));
        Element classElement = document.getRootElement();
        List<Element> studentList = classElement.getChildren();
        ObjectMapper mapper = new ObjectMapper();
        ArrayList<UFTParameter> uftParameters = new ArrayList<UFTParameter>();
        UFTParameter uftParameter = new UFTParameter();
        for (int temp = 0; temp < studentList.size(); temp++) {
            Element tag = studentList.get(temp);
            if ("ArgumentsCollection".equalsIgnoreCase(tag.getName())) {
                List<Element> children = tag.getChildren();
                for (int i = 0; i < children.size(); i++) {
                    Element element = children.get(i);
                    List<Element> elements = element.getChildren();

                    for (int j = 0; j < elements.size(); j++) {

                        Element element1 = elements.get(j);
                        switch (element1.getName()) {
                        case "ArgName":
                            uftParameter.setArgName(element1.getValue());
                            break;
                        case "ArgDirection":
                            uftParameter.setArgDirection(Integer.parseInt(element1.getValue()));
                            break;
                        case "ArgDefaultValue":
                            uftParameter.setArgDefaultValue(element1.getValue());
                            break;
                        case "ArgType":
                            uftParameter.setArgType(element1.getValue());
                            break;
                        case "ArgIsExternal":
                            uftParameter.setArgIsExternal(Integer.parseInt(element1.getValue()));
                            break;
                        default:
                            logger.warning(
                                    String.format("Element name %s didn't match any case", element1.getName()));
                            break;
                        }
                    }
                    uftParameters.add(uftParameter);
                }
                return mapper.writerWithDefaultPrettyPrinter().writeValueAsString(uftParameters);
            }
        }
    } catch (Exception e) {
        logger.severe(e.getMessage());
    }
    return null;
}

From source file:com.hp.octane.integrations.uft.UftTestDiscoveryUtils.java

License:Apache License

private static String extractXmlContentFromTspFile(InputStream stream) throws IOException {
    POIFSFileSystem poiFS = new POIFSFileSystem(stream);
    DirectoryNode root = poiFS.getRoot();
    String xmlData = "";

    for (Entry entry : root) {
        String name = entry.getName();
        if ("ComponentInfo".equals(name)) {
            if (entry instanceof DirectoryEntry) {
                System.out.println(entry);
            } else if (entry instanceof DocumentEntry) {
                byte[] content = new byte[((DocumentEntry) entry).getSize()];
                int readBytes = poiFS.createDocumentInputStream("ComponentInfo").read(content);
                if (readBytes < content.length) {
                    //  [YG] probably should handle this case and continue to read
                    logger.warn("expected to read " + content.length + " bytes, but read and stopped after "
                            + readBytes);
                }/*from  w  w  w. j av  a  2  s  .c  o  m*/
                String fromUnicodeLE = StringUtil.getFromUnicodeLE(content);
                xmlData = fromUnicodeLE.substring(fromUnicodeLE.indexOf('<')).replaceAll("\u0000", "");
            }
        }
    }
    return xmlData;
}

From source file:com.hpe.application.automation.tools.octane.actions.UFTTestUtil.java

License:Open Source License

public static String decodeXmlContent(InputStream stream) throws IOException {
    POIFSFileSystem poiFS = new POIFSFileSystem(stream);
    DirectoryNode root = poiFS.getRoot();
    String xmlData = "";

    for (Entry entry : root) {
        String name = entry.getName();
        if ("ComponentInfo".equals(name)) {
            if (entry instanceof DirectoryEntry) {
                System.out.println(entry);
            } else if (entry instanceof DocumentEntry) {
                byte[] content = new byte[((DocumentEntry) entry).getSize()];
                poiFS.createDocumentInputStream("ComponentInfo").read(content);
                String fromUnicodeLE = StringUtil.getFromUnicodeLE(content);
                xmlData = fromUnicodeLE.substring(fromUnicodeLE.indexOf('<')).replaceAll("\u0000", "");
            }//w w w.j  a v  a  2s  .  c o  m
        }
    }
    return xmlData;
}

From source file:com.pnf.plugin.ole.parser.streams.OleProcessor.java

License:Apache License

private void addAll(ContainerStream parent, DirectoryEntry root) throws IOException {
    // Iterate through all entries in the current fs directory
    for (Entry e : root) {
        // If it's another directory entry, recurse deeper
        if (e instanceof DirectoryEntry) {
            // Recurse and parse files, if any, within the current directory
            DirectoryEntry d = (DirectoryEntry) e;
            ClassID id = d.getStorageClsid();

            if (Stream.isVbaStorage(d.getName())) {
                VbaContainerStream vba = new VbaContainerStream(parent, id, d.getName());
                addAll(vba, d);//from   ww  w . ja  va2s .  com
            } else {
                ContainerStream currDir = new ContainerStream(parent, id, d.getName());
                addAll(currDir, d);
            }
        } else if (e instanceof DocumentEntry) {
            // Retrieve chained representation of files in image
            DocumentEntry doc = (DocumentEntry) e;

            // Create byte array around contents of file.
            byte[] data = new byte[doc.getSize()];

            // Read data from image file into buffer
            boolean error = false;
            try (DocumentInputStream stream = new DocumentInputStream(doc)) {
                try {
                    stream.readFully(data);
                } catch (IndexOutOfBoundsException i) {
                    error = true;
                }
            } catch (IOException e1) {
                error = true;
            }

            ByteBuffer buff = ByteBuffer.wrap(data);
            new DocumentStream(parent, e.getName(), buff, error); // constructor takes care of notifying parent of a new child
        }
    }
}

From source file:Coop.argo.hwp.v5.HwpTextExtractorV5.java

License:Apache License

/**
 * ? //  ww w  .  j av a2 s  .  co m
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractBodyText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("BodyText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid BodyText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);
            try {
                if (header.compressed)
                    input = new InflaterInputStream(input, new Inflater(true));

                HwpStreamReader sectionStream = new HwpStreamReader(input);

                extractText(sectionStream, writer);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:Coop.argo.hwp.v5.HwpTextExtractorV5.java

License:Apache License

/**
 * ? /*  w  w w .j  a  va  2  s.c  om*/
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractViewText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("ViewText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid ViewText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);

            // FIXME   ?
            Key key = readKey(input);
            try {
                input = createDecryptStream(input, key);
                if (header.compressed)
                    input = new InflaterInputStream(input, new Inflater(true));

                HwpStreamReader sectionStream = new HwpStreamReader(input);
                extractText(sectionStream, writer);
            } catch (InvalidKeyException e) {
                throw new IOException(e);
            } catch (NoSuchAlgorithmException e) {
                throw new IOException(e);
            } catch (NoSuchPaddingException e) {
                throw new IOException(e);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:edu.tsinghua.lumaqq.customface.EIPImporter.java

License:Open Source License

@SuppressWarnings("unchecked")
public EIPImporter(String file, String destDir) {
    this.destDir = destDir;
    buffer = new byte[8192];

    POIFSFileSystem eipSystem;/*from ww w  .  j  ava  2s  .com*/
    try {
        // eip
        eipStream = new FileInputStream(file);
        eipSystem = new POIFSFileSystem(eipStream);

        // 
        DirectoryEntry configDir = null, fileDir = null;
        DirectoryEntry root = eipSystem.getRoot();
        Iterator<Entry> i = root.getEntries();
        while (i.hasNext()) {
            Entry e = i.next();
            if (e.isDirectoryEntry()) {
                if (CONFIG_DIRECTORY.equals(e.getName().toLowerCase()))
                    configDir = (DirectoryEntry) e;
                else if (FILES_DIRECTORY.equals(e.getName().toLowerCase()))
                    fileDir = (DirectoryEntry) e;
            }
        }

        // ??
        if (configDir == null || fileDir == null)
            throw new IOException("Can't find correct directories");

        // ?face.xml
        i = configDir.getEntries();
        while (i.hasNext()) {
            Entry e = i.next();
            if (e.isDocumentEntry() && CONFIG_FILE.equals(e.getName().toLowerCase())) {
                DocumentInputStream dis = new DocumentInputStream((DocumentEntry) e);
                parser = new FaceXMLParser(dis);
                dis.close();
                break;
            }
        }

        // ??face.xml
        if (parser == null)
            throw new IOException("Can't find " + CONFIG_FILE);

        // iterator
        groupIterator = fileDir.getEntries();
        currentDir = fileDir;
        faceIterator = currentDir.getEntries();
    } catch (IOException e) {
        eipSystem = null;
        try {
            if (eipStream != null) {
                eipStream.close();
                eipStream = null;
            }
        } catch (IOException e1) {
        }
    }
}

From source file:FeatureExtraction.FeatureExtractorDocStreamPaths.java

private static void GetStreamsPaths(DirectoryNode dir, String parentPath, Map<String, Integer> streamPaths) {
    // run over all directory chidlrens
    for (Iterator<Entry> entryIter = dir.getEntries(); entryIter.hasNext();) {
        Entry entry = entryIter.next();
        String entryName = entry.getName();

        // Some entry names starts with binary value that are not printable - remove it
        if (entryName.charAt(0) < 10) {
            entryName = entryName.substring(1);
        }/*w ww.ja  v  a 2  s .  com*/

        // Recursively search for directory (storage) children
        if (entry instanceof DirectoryNode) {
            GetStreamsPaths((DirectoryNode) entry, parentPath + "\\" + entryName, streamPaths);
        } else {
            // Add stream path to set of paths
            String filePath = parentPath + "\\" + entryName;
            AddStreamPath(filePath, streamPaths);
        }
    }
}