Example usage for org.dom4j.io SAXReader read

List of usage examples for org.dom4j.io SAXReader read

  1. HOME
  2. Java
  3. org.dom4j
  4. org.dom4j.io.*
  5. SAXReader
  6. read

Introduction

In this page you can find the example usage for org.dom4j.io SAXReader read.

Prototype

public Document read(InputSource in) throws DocumentException

Source Link

Document

Reads a Document from the given InputSource using SAX

Usage

From source file:com.globalsight.terminology.importer.MtfReader.java

License:Apache License

/**
 * Reads an XML file and checks for correctness. If there's any
 * error in the file, an exception is thrown.
 *///from   ww  w.jav a 2 s.  c o m
private void analyzeXml(String p_url) throws Exception {
    SAXReader reader = new SAXReader();
    reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

    CATEGORY.debug("Analyzing document: " + p_url);

    // enable element complete notifications to conserve memory
    reader.addHandler("/mtf/conceptGrp", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_entryCount;
        }

        public void onEnd(ElementPath path) {
            Element element = path.getCurrent();

            // prune the current element to reduce memory
            element.detach();

            // TODO: validate entry and report errors.
        }
    });

    Document document = reader.read(p_url);

    // all done
}

From source file:com.globalsight.terminology.importer.MtfReaderThread.java

License:Apache License

public void run() {
    try {/* ww  w .  ja  v  a  2  s.c  o m*/
        SAXReader reader = new SAXReader();
        reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

        // enable pruning to call me back as each Element is complete
        reader.addHandler("/mtf/conceptGrp", new ElementHandler() {
            public void onStart(ElementPath path) {
                m_count++;
            }

            public void onEnd(ElementPath path) {
                Element element = path.getCurrent();

                // prune the current element to reduce memory
                element.detach();

                m_result = m_results.hireResult();

                try {
                    // Convert MultiTerm to GlobalSight.
                    element = convertMtf(element);

                    Document doc = m_factory.createDocument(element);
                    Entry entry = new Entry(doc);

                    if (CATEGORY.isDebugEnabled()) {
                        CATEGORY.debug(entry.getXml());
                    }

                    m_result.setResultObject(entry);
                } catch (Throwable ex) {
                    String msg = "Entry " + m_count + ": " + ex.getMessage();

                    m_result.setError(msg);

                    if (CATEGORY.isDebugEnabled()) {
                        CATEGORY.debug(msg, ex);
                    } else {
                        CATEGORY.warn(msg, ex);
                    }
                }

                boolean done = m_results.put(m_result);
                m_result = null;

                // Stop reading the XML file.
                if (done) {
                    throw new ThreadDeath();
                }
            }
        });

        String url = m_options.getFileName();

        Document document = reader.read(url);
    } catch (ThreadDeath ignore) {
        CATEGORY.info("ReaderThread: interrupted.");
    } catch (Throwable ignore) {
        // Should never happen, and I don't know how to handle
        // this case other than passing the exception in
        // m_results, which I won't do for now.
        CATEGORY.error("unexpected error", ignore);
    } finally {
        if (m_result != null) {
            m_results.fireResult(m_result);
            m_result = null;
        }

        m_results.producerDone();
        m_results = null;

        CATEGORY.debug("ReaderThread: done.");
    }
}

From source file:com.globalsight.terminology.importer.TbxReader.java

License:Apache License

private void analyzeTbx(String p_url) throws Exception {
    SAXReader reader = new SAXReader();
    reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

    CATEGORY.debug("Analyzing document: " + p_url);
    // enable element complete notifications to conserve memory

    reader.addHandler("/martif/text/body/termEntry", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_entryCount;//from w w w  . j  a va2s.co  m
        }

        public void onEnd(ElementPath path) {
            Element element = path.getCurrent();

            // prune the current element to reduce memory
            element.detach();
        }
    });

    Document document = reader.read(p_url);
}

From source file:com.globalsight.terminology.importer.TbxReaderThread.java

License:Apache License

public void run() {
    try {/*from w ww . j  a  v a2 s  . c  om*/
        SAXReader reader = new SAXReader();
        reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

        // enable pruning to call me back as each Element is complete
        reader.addHandler("/martif/text/body/termEntry", new ElementHandler() {
            public void onStart(ElementPath path) {
            }

            public void onEnd(ElementPath path) {
                Element element = path.getCurrent();

                // prune the current element to reduce memory
                element.detach();

                Document doc = m_factory.createDocument(element);
                Entry entry = new Entry(doc);

                m_result = m_results.hireResult();
                m_result.setResultObject(entry);

                boolean done = m_results.put(m_result);
                m_result = null;

                // Stop reading the TMX file.
                if (done) {
                    throw new ThreadDeath();
                }
            }
        });

        String url = m_options.getFileName();

        Document document = reader.read(url);
    } catch (ThreadDeath ignore) {
        CATEGORY.info("ReaderThread: interrupted.");
    } catch (Throwable ignore) {
        // Should never happen, and I don't know how to handle
        // this case other than passing the exception in
        // m_results, which I won't do for now.
    } finally {
        if (m_result != null) {
            m_results.fireResult(m_result);
            m_result = null;
        }

        m_results.producerDone();
        m_results = null;

        CATEGORY.debug("ReaderThread: done.");
    }
}

From source file:com.globalsight.terminology.util.MtfAnalyzer.java

License:Apache License

public void analyze(String p_url) throws Exception {
    m_entryCount = 0;// w  ww.  j  a  v  a 2 s .co m

    SAXReader reader = new SAXReader();
    reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

    System.err.println("Analyzing document: " + p_url);

    // enable element complete notifications to conserve memory
    reader.addHandler("/mtf/conceptGrp", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_entryCount;

            if (m_entryCount % 200 == 0) {
                log("Entry " + m_entryCount);
            }
        }

        public void onEnd(ElementPath path) {
            Element element = path.getCurrent();

            // prune the current element to reduce memory
            element.detach();

            element = null;
        }
    });

    Document document = reader.read(p_url);

    log("Total entries: " + m_entryCount);

    // all done
}

From source file:com.globalsight.terminology.util.MtfSplitter.java

License:Apache License

public void split(String p_url, String p_numEntries) throws Exception {
    final int maxEntries = Integer.parseInt(p_numEntries);
    final String baseName = getBaseName(p_url);
    final String extension = getExtension(p_url);

    m_entryCount = 0;//from   w ww . j a va  2  s  . co  m

    SAXReader reader = new SAXReader();
    reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");

    log("Splitting document `" + p_url + "'");

    startFile(baseName, extension);

    // enable element complete notifications to conserve memory
    reader.addHandler("/mtf/conceptGrp", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_entryCount;

            if (m_entryCount % maxEntries == 0) {
                try {
                    closeFile();
                    startFile(baseName, extension);
                } catch (Exception ex) {
                    log(ex.toString());
                    System.exit(1);
                }
            }
        }

        public void onEnd(ElementPath path) {
            Element element = path.getCurrent();

            writeEntry(element.asXML());

            // prune the current element to reduce memory
            element.detach();

            element = null;
        }
    });

    Document document = reader.read(p_url);

    closeFile();

    // all done
}

From source file:com.globalsight.util.ConfigUtil.java

License:Apache License

public static ConfigBO getConfigBO() {
    String hostName;/*from  w  w  w. j a v a2s  .com*/
    int port = 80;
    String userName;
    String password;
    int intervalTimeForArchive;
    int intervalTime;
    boolean isUseHTTPS = false;

    try {
        SAXReader saxReader = new SAXReader();
        Document document = saxReader.read(new File(Constants.CONFIG_FILE_NAME));
        Node serverNode = document.selectSingleNode("/Configuration/server");

        hostName = serverNode.selectSingleNode("host").getText();
        port = Integer.valueOf(serverNode.selectSingleNode("port").getText());
        userName = serverNode.selectSingleNode("username").getText();
        password = serverNode.selectSingleNode("password").getText();
        isUseHTTPS = Boolean.valueOf(serverNode.selectSingleNode("https").getText());

        intervalTimeForArchive = Integer
                .valueOf(document.selectSingleNode("//intervalTimeForArchive").getText());
        intervalTime = Integer.valueOf(document.selectSingleNode("//intervalTime").getText());

        ConfigBO config = new ConfigBO(hostName, port, userName, password, intervalTimeForArchive, intervalTime,
                isUseHTTPS);
        return config;
    } catch (DocumentException e) {
        LogUtil.info("Fail to read configuration info", e);
    }

    return null;
}

From source file:com.globalsight.util.file.XliffFileUtil.java

License:Apache License

/**
 * Check if specified file contains multiple <File> tags
 * //  w w  w .  j a v a  2  s . c o m
 * @param p_filename
 *            File name
 * @return Return true if file contains multiple <File> tags, otherwise
 *         return false
 * 
 * @version 1.0
 * @since 8.2.2
 */
public static boolean isMultipleFileTags(String p_filename) {
    if (StringUtil.isEmpty(p_filename))
        return false;

    int numOfFileTags = 0;
    try {
        SAXReader saxReader = new SAXReader();
        Document document = null;
        Element rootElement = null;

        File file = new File(p_filename);
        if (file.exists() && file.isFile()) {
            document = saxReader.read(file);
            rootElement = document.getRootElement();
            String tag = "";
            for (Iterator<Element> iterator = rootElement.elementIterator(); iterator.hasNext();) {
                tag = iterator.next().getName().trim().toLowerCase();
                if ("file".equals(tag))
                    numOfFileTags++;
            }
        }
        return numOfFileTags > 1;
    } catch (Exception e) {
        logger.error("Can not verify if current file contains multiple file tags.", e);
        return false;
    }
}

From source file:com.globalsight.util.file.XliffFileUtil.java

License:Apache License

public static boolean containsFileTag(String p_filename) {
    if (StringUtil.isEmpty(p_filename))
        return false;

    try {//  ww  w .j  a  v  a2 s . co m
        SAXReader saxReader = new SAXReader();
        Document document = null;
        Element rootElement = null;

        File file = new File(p_filename);
        if (file.exists() && file.isFile()) {
            document = saxReader.read(file);
            rootElement = document.getRootElement();
            String tag = "";
            List fileTags = rootElement.elements("file");
            if (fileTags != null) {
                for (int i = 0; i < fileTags.size(); i++) {
                    Element element = (Element) fileTags.get(i);
                    String attr = element.attributeValue("tool");
                    if (attr == null)
                        return false;
                    else {
                        if (attr.toLowerCase().contains("worldserver"))
                            return true;
                    }
                }
            }
        }
        return false;
    } catch (Exception e) {
        logger.error("Can not verify if current file contains multiple file tags.", e);
        return false;
    }
}

From source file:com.globalsight.util.file.XliffFileUtil.java

License:Apache License

/**
 * Generate separated files in single file level according with content in
 * orignal Xliff file//from w  w w .  j a va2  s. co m
 * 
 * @param multipleFileTagsXliff
 *            Object contains all separated files
 * @param absoluteFilename
 *            File name with absolute path
 * @param header
 *            Header content of original Xliff file
 * @param content
 *            Main content of original Xliff file
 * @param footer
 *            Footer content of original Xliff file
 * 
 * @version 1.0
 * @since 8.2.2
 */
private static void generateSeparatedFiles(MultipleFileTagsXliff multipleFileTagsXliff, String absoluteFilename,
        String header, String content, String footer) {
    try {
        String absolutePath = getBaseAbsoluatePath(absoluteFilename);
        String mainName = getMainFilename(absoluteFilename);
        String separatedDirPath = mainName + SEPARATE_FLAG;
        String absouateSeparatedPath = absolutePath + File.separator + separatedDirPath;
        File file = new File(absouateSeparatedPath);
        file.mkdirs();

        int lengthOfFileEndTag = "</file>".length();
        int beginIndex = -1, endIndex = -1;
        String subContent = "";

        SAXReader saxReader = new SAXReader();
        Document document = null;
        Element rootElement = null, fileTagElement = null, fileHeaderElement = null;
        String originalSubFilename = "";
        String segAssetId = "";
        BufferedWriter fout = null;
        ArrayList<String> separatedFiles = new ArrayList<String>();
        String subFilename = "";
        int count = 1;
        while ((beginIndex = content.indexOf("<file ")) > -1) {
            endIndex = content.indexOf("</file>") + lengthOfFileEndTag;
            subContent = header + content.substring(beginIndex, endIndex) + footer;

            // Use XML parser to get element value
            document = saxReader.read(new StringReader(subContent));
            rootElement = document.getRootElement();
            fileTagElement = rootElement.element("file");
            originalSubFilename = fileTagElement.attributeValue("original").replace("/", File.separator);
            originalSubFilename = originalSubFilename
                    .substring(originalSubFilename.lastIndexOf(File.separator) + 1);
            fileHeaderElement = fileTagElement.element("header");
            if (fileHeaderElement != null && fileHeaderElement.element("asset-data") != null) {
                segAssetId = fileHeaderElement.element("asset-data").elementText("seg_asset_id");
            }

            // Generate file name of separated file
            subFilename = originalSubFilename + "_" + segAssetId + "_" + count + ".xlf";

            // Write separated file into disk
            file = new File(absouateSeparatedPath, subFilename);
            fout = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file), "UTF-8"));
            fout.write(subContent);
            fout.close();

            separatedFiles.add(getRelativePath(file.getAbsolutePath()));

            content = content.substring(endIndex);
            count++;
        }
        multipleFileTagsXliff.setCount(count);
        multipleFileTagsXliff.setSeparatedFiles(separatedFiles);
        multipleFileTagsXliff.setSeparatedFolderName(separatedDirPath);
    } catch (Exception e) {
        logger.error("Error in generateExtractedFile.", e);
    }
}