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.everest.segmentationhelper.XmlLoader.java

License:Apache License

/**
 * Transfer xml file into Document.//  w  w  w.  ja  v  a  2s.  c  o m
 * 
 * @param file
 */
private static Document parserWithSAX(File file) throws Exception {
    SAXReader xmlReader = new SAXReader();
    Document doc = null;
    try {
        doc = xmlReader.read(file);
    } catch (Exception e) {
        e.printStackTrace();
        throw new Exception(e.getMessage());
    }

    return doc;
}

From source file:com.globalsight.everest.segmentationhelper.XmlLoader.java

License:Apache License

/**
 * Transfer xml text into Document./*from  w ww  .  ja  v  a 2 s .c  om*/
 * 
 * @param xmltext
 */
private static Document parseWithSAX(String xmltext) throws Exception {
    Document doc = null;
    StringReader sr = new StringReader(xmltext);
    SAXReader xmlReader = new SAXReader();
    try {
        doc = xmlReader.read(sr);
    } catch (Exception e) {
        e.printStackTrace();
        throw new Exception(e.getMessage());
    }
    return doc;
}

From source file:com.globalsight.everest.tm.importer.ImportUtil.java

License:Apache License

/**
 * Saves a TM file with sample validation.
 * //from   ww w .  j a v a 2  s.  com
 * For some TM files, it vary easy to happen encoding error or xml role
 * error and can't be import correct. This method try to do some sample
 * validations for each tu. If a tu will be give up if inducing a error.
 * 
 * @param fileName
 * @throws Exception
 */
public void saveTmFileWithValidation(File file, File newFile, TmProcessStatus status) throws Exception {
    String encoding = "UTF-8";
    String outEncoding = "UTF-8";
    String logEncoding = "Unicode";
    String strLine = System.getProperty("line.separator");

    int errorCount = 0;
    int totalCount = 0;
    long lineCounter = 0;

    String s = null;

    try {
        if (file.exists()) {
            CATEGORY.info("Validating TM file: " + newFile.getAbsolutePath());

            Date startTime = new Date();

            File errorFile = getErrorFile(newFile);
            File infoFile = getInfoFile(newFile);
            File logFile = getLogFile(newFile);

            encoding = getEncodingOfXml(file);
            // GBS-2932 : UTF-8 by default
            if (encoding == null) {
                encoding = "UTF-8";
            }

            // Initialize IO.
            FileInputStream fIn = new FileInputStream(file);
            BufferedReader in = new BufferedReader(new InputStreamReader(fIn, encoding));
            FileOutputStream fOut = new FileOutputStream(newFile);
            BufferedWriter out = new BufferedWriter(new OutputStreamWriter(fOut, outEncoding));
            FileOutputStream fError = new FileOutputStream(errorFile);
            OutputStreamWriter error = new OutputStreamWriter(fError, logEncoding);
            FileOutputStream fInfo = new FileOutputStream(infoFile);
            BufferedWriter info = new BufferedWriter(new OutputStreamWriter(fInfo, logEncoding));
            FileOutputStream fLog = new FileOutputStream(logFile);
            OutputStreamWriter log = new OutputStreamWriter(fLog, logEncoding);

            writeHead(error);
            writeHead(log);

            StringBuilder sb = new StringBuilder();

            // It must be <?xml ...
            s = in.readLine();
            s = changeXmlEncodingDec(s, outEncoding);

            status.addSize(s.getBytes(encoding).length);
            if (CATEGORY.isDebugEnabled()) {
                CATEGORY.debug("The content of in.readLine for encoding is " + s);
            }
            sb.append(s);
            sb.append(strLine);

            status.addSize(s.getBytes(encoding).length);

            // If the second line is define dtd
            s = in.readLine();
            if (CATEGORY.isDebugEnabled()) {
                CATEGORY.debug("The content of in.readLine for doctype is " + s);
            }
            if (s != null && s.indexOf("<!DOCTYPE") > -1) {
                status.addSize(s.getBytes(encoding).length);

                sb.append(s);
                sb.append(strLine);
                s = in.readLine();
                if (CATEGORY.isDebugEnabled()) {
                    CATEGORY.debug("The content of in.readLine is " + s);
                }
            } else if (newFile.getName().endsWith("tmx")) {
                // Don't define the dtd, add it.
                sb.append(TMX_DTD_LINE);
                sb.append(strLine);
            }
            boolean isRemoved = false;
            int count = 0;
            SAXReader reader = new SAXReader();
            while (s != null) {
                if (status.isCanceled()) {
                    CATEGORY.info("Cancelled validating");
                    break;
                }
                status.addSize(s.getBytes(encoding).length);

                if (isHeaderStart(s) && isTradosFontTableStart(s) && isHeaderEnd(s)) {
                    int headerEndTag = s.indexOf(">");
                    sb.append(s.subSequence(0, headerEndTag + 1));
                    int endHeaderTag = s.indexOf("</header>");
                    sb.append(s.substring(endHeaderTag));
                    sb.append(endHeaderTag);
                    sb.append(strLine);
                }
                if (isRemoved) {
                    if (isTradosFontTableEnd(s)) {
                        isRemoved = false;
                    }
                    s = in.readLine();
                    continue;
                }
                if (isTuStartTag(s)) {
                    /* The begin of the tu */
                    // Saves information recoded.
                    if (sb.length() > 0) {
                        out.write(sb.toString());
                        out.flush();
                    }

                    sb = resetStringBuilder(sb);
                    sb.append(s);
                    sb.append(strLine);

                    totalCount++;
                }

                // Validate for the tu.
                else if (isTuEndTag(s)) {
                    /* The end of the tu */
                    sb.append(s);
                    sb.append(strLine);
                    String content = sb.toString();

                    try {
                        /* verify the content */
                        reader.read(new StringReader(content));

                        // Saves the tu if no exception happen.
                        out.write(content);
                        out.flush();
                    } catch (Exception e) {
                        // Give up the tu if any exception happened.
                        error.write(content);

                        log.write(strLine);
                        log.write(SPLIT_LINE);
                        log.write(Integer.toString(++errorCount));
                        log.write(SPLIT_LINE);
                        log.write(strLine);

                        log.write(content);
                        log.write(strLine);
                        log.write(e.getMessage());
                        log.write(strLine);

                    }

                    sb = resetStringBuilder(sb);
                } else if (isTradosFontTableStart(s)) {
                    count++;
                    isRemoved = true;
                } else if (count > 0 && isTradosFontTableEnd(s)) {
                    isRemoved = false;
                } else if ((count > 0) && isHeaderEnd(s)) {
                    sb.append("</header>");
                    sb.append(strLine);
                } else {
                    // Records informations which not included in tu, first
                    // line
                    // etc.
                    sb.append(s);
                    sb.append(strLine);
                }

                s = in.readLine();
                if (CATEGORY.isDebugEnabled()) {
                    CATEGORY.debug("The content of in.readLine is " + s);
                }
                lineCounter++;
            }

            // Records informations which not included in tu and not saved
            // to
            // file. Usually it is "</body> </tmx>".
            if (sb.length() > 0) {
                out.write(sb.toString());
                out.flush();
            }

            in.close();

            out.close();

            CATEGORY.info("Done validating");

            log.write(SPLIT_LINE + SPLIT_LINE + strLine + strLine);
            log.write("Error: " + errorCount + strLine);
            log.write("Total: " + totalCount + strLine);

            // Gets the cost time.
            Date endTime = new Date();
            long costTime = endTime.getTime() - startTime.getTime();
            long h = costTime / (1000 * 60 * 60);
            costTime = costTime % (1000 * 60 * 60);
            long m = costTime / (1000 * 60);
            costTime = costTime % (1000 * 60);
            long se = costTime / 1000;
            StringBuffer time = new StringBuffer("Cost time: ");
            time.append(h).append(" h ").append(m).append(" m ").append(se).append(" s ");

            // Recodes some sample informations.
            String msg = "Error: " + errorCount + strLine;
            info.write(msg);
            msg = "Total: " + totalCount + strLine;
            info.write(msg);
            info.write(time.toString());

            writeFoot(error);
            writeFoot(log);

            error.flush();
            error.close();
            info.flush();
            info.close();
            log.flush();
            log.close();

            if (lineCounter > 10000) {
                CATEGORY.debug("forces jvm to perform gc when the line count reaches 10000. line count: "
                        + lineCounter);
                System.gc();
            }
        }
    } catch (IOException ie) {
        CATEGORY.error("IO Exception occured when save the tm file.");
        CATEGORY.error("The content of current line is " + s);
        CATEGORY.error("The stacktrace of the exception is ", ie);
        throw ie;
    } catch (Exception e) {
        CATEGORY.error("error occured when save the tm file.");
        CATEGORY.error("The content of current line is " + s);
        CATEGORY.error("The stacktrace of the exception is ", e);
        throw e;
    }

    status.setErrorTus(Integer.toString(errorCount));
    status.setTotalTus(Integer.toString(totalCount));
}

From source file:com.globalsight.everest.tm.importer.ImportUtil.java

License:Apache License

/**
 * Saves a TM file with sample validation.
 * /*from   w  w w .  j a va  2s .c o  m*/
 * For some TM files, it vary easy to happen encoding error or xml role
 * error and can't be import correct. This method try to do some sample
 * validations for each tu. If a tu will be give up if inducing a error.
 * 
 * This is used for no UI display requirement.
 * 
 * @param fileName
 * @throws Exception
 */
public void saveTmFileWithValidation(File file, File newFile) throws Exception {
    String encoding = "UTF-8";
    String outEncoding = "UTF-8";
    String logEncoding = "Unicode";
    String strLine = System.getProperty("line.separator");

    int errorCount = 0;
    int totalCount = 0;
    long lineCounter = 0;

    String s = null;

    try {
        if (file.exists()) {
            CATEGORY.info("Validating TM file: " + newFile.getAbsolutePath());

            Date startTime = new Date();

            File errorFile = getErrorFile(newFile);
            File infoFile = getInfoFile(newFile);
            File logFile = getLogFile(newFile);

            encoding = getEncodingOfXml(file);
            // GBS-2932 : UTF-8 by default
            if (encoding == null) {
                encoding = "UTF-8";
            }

            // Initialize IO.
            FileInputStream fIn = new FileInputStream(file);
            BufferedReader in = new BufferedReader(new InputStreamReader(fIn, encoding));
            FileOutputStream fOut = new FileOutputStream(newFile);
            BufferedWriter out = new BufferedWriter(new OutputStreamWriter(fOut, outEncoding));
            FileOutputStream fError = new FileOutputStream(errorFile);
            OutputStreamWriter error = new OutputStreamWriter(fError, logEncoding);
            FileOutputStream fInfo = new FileOutputStream(infoFile);
            BufferedWriter info = new BufferedWriter(new OutputStreamWriter(fInfo, logEncoding));
            FileOutputStream fLog = new FileOutputStream(logFile);
            OutputStreamWriter log = new OutputStreamWriter(fLog, logEncoding);

            writeHead(error);
            writeHead(log);

            StringBuilder sb = new StringBuilder();

            // It must be <?xml ...
            s = in.readLine();
            s = changeXmlEncodingDec(s, outEncoding);

            if (CATEGORY.isDebugEnabled()) {
                CATEGORY.debug("The content of in.readLine for encoding is " + s);
            }
            sb.append(s);
            sb.append(strLine);

            // If the second line is define dtd
            s = in.readLine();
            if (CATEGORY.isDebugEnabled()) {
                CATEGORY.debug("The content of in.readLine for doctype is " + s);
            }
            if (s != null && s.indexOf("<!DOCTYPE") > -1) {
                sb.append(s);
                sb.append(strLine);
                s = in.readLine();
                if (CATEGORY.isDebugEnabled()) {
                    CATEGORY.debug("The content of in.readLine is " + s);
                }
            } else if (newFile.getName().endsWith("tmx")) {
                // Don't define the dtd, add it.
                sb.append(TMX_DTD_LINE);
                sb.append(strLine);
            }
            boolean isRemoved = false;
            int count = 0;
            SAXReader reader = new SAXReader();
            while (s != null) {
                if (isHeaderStart(s) && isTradosFontTableStart(s) && isHeaderEnd(s)) {
                    int headerEndTag = s.indexOf(">");
                    sb.append(s.subSequence(0, headerEndTag + 1));
                    int endHeaderTag = s.indexOf("</header>");
                    sb.append(s.substring(endHeaderTag));
                    sb.append(endHeaderTag);
                    sb.append(strLine);
                }
                if (isRemoved) {
                    if (isTradosFontTableEnd(s)) {
                        isRemoved = false;
                    }
                    s = in.readLine();
                    continue;
                }
                if (isTuStartTag(s)) {
                    /* The begin of the tu */
                    // Saves information recoded.
                    if (sb.length() > 0) {
                        out.write(sb.toString());
                        out.flush();
                    }

                    sb = resetStringBuilder(sb);
                    sb.append(s);
                    sb.append(strLine);

                    totalCount++;
                }

                // Validate for the tu.
                else if (isTuEndTag(s)) {
                    /* The end of the tu */
                    sb.append(s);
                    sb.append(strLine);
                    String content = sb.toString();

                    try {
                        /* verify the content */
                        reader.read(new StringReader(content));

                        // Saves the tu if no exception happen.
                        out.write(content);
                        out.flush();
                    } catch (Exception e) {
                        // Give up the tu if any exception happened.
                        error.write(content);

                        log.write(strLine);
                        log.write(SPLIT_LINE);
                        log.write(Integer.toString(++errorCount));
                        log.write(SPLIT_LINE);
                        log.write(strLine);

                        log.write(content);
                        log.write(strLine);
                        log.write(e.getMessage());
                        log.write(strLine);

                    }

                    sb = resetStringBuilder(sb);
                } else if (isTradosFontTableStart(s)) {
                    count++;
                    isRemoved = true;
                } else if (count > 0 && isTradosFontTableEnd(s)) {
                    isRemoved = false;
                } else if ((count > 0) && isHeaderEnd(s)) {
                    sb.append("</header>");
                    sb.append(strLine);
                } else {
                    // Records informations which not included in tu, first
                    // line
                    // etc.
                    sb.append(s);
                    sb.append(strLine);
                }

                s = in.readLine();
                if (CATEGORY.isDebugEnabled()) {
                    CATEGORY.debug("The content of in.readLine is " + s);
                }
                lineCounter++;
            }

            // Records informations which not included in tu and not saved
            // to
            // file. Usually it is "</body> </tmx>".
            if (sb.length() > 0) {
                out.write(sb.toString());
                out.flush();
            }

            in.close();

            out.close();

            CATEGORY.info("Done validating");

            log.write(SPLIT_LINE + SPLIT_LINE + strLine + strLine);
            log.write("Error: " + errorCount + strLine);
            log.write("Total: " + totalCount + strLine);

            // Gets the cost time.
            Date endTime = new Date();
            long costTime = endTime.getTime() - startTime.getTime();
            long h = costTime / (1000 * 60 * 60);
            costTime = costTime % (1000 * 60 * 60);
            long m = costTime / (1000 * 60);
            costTime = costTime % (1000 * 60);
            long se = costTime / 1000;
            StringBuffer time = new StringBuffer("Cost time: ");
            time.append(h).append(" h ").append(m).append(" m ").append(se).append(" s ");

            // Recodes some sample informations.
            String msg = "Error: " + errorCount + strLine;
            info.write(msg);
            msg = "Total: " + totalCount + strLine;
            info.write(msg);
            info.write(time.toString());

            writeFoot(error);
            writeFoot(log);

            error.flush();
            error.close();
            info.flush();
            info.close();
            log.flush();
            log.close();

            if (lineCounter > 10000) {
                CATEGORY.debug("suggests jvm to perform gc when the line count reaches 10000. line count: "
                        + lineCounter);
                System.gc();
            }
        }
    } catch (IOException ie) {
        CATEGORY.error("IO Exception occured when save the tm file.");
        CATEGORY.error("The content of current line is " + s);
        CATEGORY.error("The stacktrace of the exception is ", ie);
        throw ie;
    } catch (Exception e) {
        CATEGORY.error("error occured when save the tm file.");
        CATEGORY.error("The content of current line is " + s);
        CATEGORY.error("The stacktrace of the exception is ", e);
        throw e;
    }
}

From source file:com.globalsight.everest.tm.importer.TmxReader.java

License:Apache License

/**
 * Reads an XML file and checks its correctness by validating
 * against the TMX DTD. If there's any error in the file, an
 * exception is thrown.//from w  w w . j  a v a2s  .c  o  m
 *
 * As a side effect, this method builds a list of source and
 * target locales found in the file, including the declared source
 * locale from the header.
 */
private void analyzeXml(String p_url) throws Exception {
    if (m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_RTF || m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_HTML
            || m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_FM || m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_FM_SGML
            || m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_IL
            || m_tmxLevel == ImportUtil.TMX_LEVEL_TRADOS_XPTAG) {
        // Convert the Trados codes to native System4 codes by
        // converting the file to RTF, saving it as HTML and
        // extracting the resulting TUVs.

        CATEGORY.info("Converting Trados TMX to native TMX: " + p_url);

        p_url = convertTradosTmx(p_url, m_tmxLevel);

        // Now we have a new file that contains native content.
        m_options.setFileName(p_url);
        m_options.setFileType(com.globalsight.everest.tm.importer.ImportOptions.TYPE_XML);

        m_tmxLevel = ImportUtil.TMX_LEVEL_NATIVE;
    }

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

    // Reset list of locales found in the file.
    m_sourceLocales = new HashSet();
    m_targetLocales = new HashSet();

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

    // Read the DTD and validate.
    reader.setEntityResolver(DtdResolver.getInstance());
    reader.setValidation(true);

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx", new ElementHandler() {
        public void onStart(ElementPath path) {
            Element element = path.getCurrent();

            m_tmxVersion = element.attributeValue(Tmx.VERSION);
        }

        public void onEnd(ElementPath path) {
        }
    });

    reader.addHandler("/tmx/header", new ElementHandler() {
        public void onStart(ElementPath path) {
        }

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

            m_header = new Tmx(element);
            m_header.setTmxVersion(m_tmxVersion);

            element.detach();
        }
    });

    reader.addHandler("/tmx/body/tu", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_entryCount;
        }

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

            // Record optional source language declared on TU.
            String srclang = element.attributeValue(Tmx.SRCLANG);
            if (srclang != null) {
                m_sourceLocales.add(ImportUtil.normalizeLocale(srclang));
            }

            // Find target languages
            HashSet langs = new HashSet();
            List tuvs = element.selectNodes("./tuv");

            for (int i = 0, max = tuvs.size(); i < max; i++) {
                Element tuv = (Element) tuvs.get(i);

                String lang = tuv.attributeValue(Tmx.LANG);

                // Collect TUV locales
                langs.add(ImportUtil.normalizeLocale(lang));
            }

            langs.remove(srclang);
            m_targetLocales.addAll(langs);

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

    Document document = reader.read(p_url);

    // Add declared source language from header.
    String sourceLocale = ImportUtil.normalizeLocale(m_header.getSourceLang());

    m_sourceLocales.add(sourceLocale);
}

From source file:com.globalsight.everest.tm.importer.TmxReaderThread.java

License:Apache License

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

        // Read the DTD and validate.
        reader.setEntityResolver(DtdResolver.getInstance());
        reader.setValidation(true);

        reader.addHandler("/tmx", new ElementHandler() {
            public void onStart(ElementPath path) {
                Element element = path.getCurrent();

                m_tmxVersion = element.attributeValue(Tmx.VERSION);
            }

            public void onEnd(ElementPath path) {
            }
        });

        reader.addHandler("/tmx/header", new ElementHandler() {
            public void onStart(ElementPath path) {
            }

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

                m_tmx = new Tmx(element);
                m_tmx.setTmxVersion(m_tmxVersion);

                m_defaultSrcLang = ImportUtil.normalizeLocale(m_tmx.getSourceLang());
            }
        });

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

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

                m_result = m_results.hireResult();

                try {
                    // Normalize spelling of locales.
                    normalizeTu(element);
                    // Filter out targets not to be imported.
                    filterTu(element);
                    // Validate we have source and target.
                    validateTu(element);

                    // Create TU objects
                    SegmentTmTu tu = createTu(element);

                    if (CATEGORY.isDebugEnabled()) {
                        CATEGORY.debug(tu.toDebugString(true));
                    }

                    m_result.setResultObject(tu);
                } 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);
                    }
                }

                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.
        CATEGORY.error("unexpected error", ignore);
    } finally {
        if (m_result != null) {
            m_results.fireResult(m_result);
        }

        m_results.producerDone();
        m_results = null;

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

From source file:com.globalsight.everest.tm.util.TmxAnalyzer.java

License:Apache License

public void analyze(String p_url) throws Exception {
    m_tuCount = 0;//from  w  w  w.j a  v a 2s.co m
    m_tuvCount = 0;
    m_localeCount = 0;
    m_locales = new HashSet();
    m_tmxVersion = "";
    m_tmx = null;

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

    reader.setEntityResolver(DtdResolver.getInstance());
    reader.setValidation(true);

    log("Analyzing document: " + p_url);

    reader.addHandler("/tmx", new ElementHandler() {
        public void onStart(ElementPath path) {
            Element element = path.getCurrent();

            m_tmxVersion = element.attributeValue("version");
        }

        public void onEnd(ElementPath path) {
        }
    });

    reader.addHandler("/tmx/header", new ElementHandler() {
        public void onStart(ElementPath path) {
        }

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

            element.detach();

            m_tmx = new Tmx(element);
            m_tmx.setTmxVersion(m_tmxVersion);
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/body/tu", new ElementHandler() {
        public void onStart(ElementPath path) {
            ++m_tuCount;

            if (m_tuCount % 1000 == 0) {
                log("TU " + m_tuCount);
            }
        }

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

            List tuvs = element.selectNodes("//tuv");

            m_tuvCount += tuvs.size();

            for (int i = 0, max = tuvs.size(); i < max; i++) {
                Element tuv = (Element) tuvs.get(i);

                String locale = tuv.attributeValue("lang");
                m_locales.add(locale);
            }

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

            element = null;
        }
    });

    Document document = reader.read(p_url);

    m_localeCount = m_locales.size();

    log("File: " + p_url);
    log("TMX version: " + m_tmxVersion);
    log("Total TUs: " + m_tuCount);
    log("Total TUVs: " + m_tuvCount);
    log("Total Locales: " + m_localeCount);

    for (Iterator it = m_locales.iterator(); it.hasNext();) {
        String locale = (String) it.next();

        log(locale);
    }

    // all done
}

From source file:com.globalsight.everest.tm.util.TmxLevelSplitter.java

License:Apache License

public void split(String p_url) throws Exception {
    final String baseName = getBaseName(p_url);
    final String extension = getExtension(p_url);

    m_entryCount = 0;//from  www . j a va 2  s .  c  o  m

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

    reader.setEntityResolver(DtdResolver.getInstance());
    reader.setValidation(true);

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

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx", new ElementHandler() {
        public void onStart(ElementPath path) {
            Element element = path.getCurrent();

            m_version = element.attributeValue("version");
        }

        public void onEnd(ElementPath path) {
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/header", new ElementHandler() {
        public void onStart(ElementPath path) {
        }

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

            m_header = element;

            try {
                startFiles(baseName, extension);
            } catch (Exception ex) {
                log(ex.toString());
                System.exit(1);
            }

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

            element = null;
        }
    });

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

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

            if (containsTags(element)) {
                writeTagsEntry(element.asXML());

                m_tagsCount++;
            } else {
                writeTextEntry(element.asXML());

                m_textCount++;
            }

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

            element = null;
        }
    });

    Document document = reader.read(p_url);

    closeFiles();

    log("Processed " + m_entryCount + " TUs, " + m_textCount + " level 1 (text), " + m_tagsCount
            + " level 2 (tags)");

    // all done
}

From source file:com.globalsight.everest.tm.util.TmxSplitter.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;/*  ww w. ja  va  2  s  . c  om*/

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

    reader.setEntityResolver(DtdResolver.getInstance());
    reader.setValidation(true);

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

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx", new ElementHandler() {
        public void onStart(ElementPath path) {
            Element element = path.getCurrent();

            m_version = element.attributeValue("version");
        }

        public void onEnd(ElementPath path) {
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/header", new ElementHandler() {
        public void onStart(ElementPath path) {
        }

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

            m_header = element;

            try {
                startFile(baseName, extension);
            } catch (Exception ex) {
                log(ex.toString());
                System.exit(1);
            }

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

            element = null;
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/body/tu", 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.everest.tm.util.trados.TradosFmSgmlTmxToGxml.java

License:Apache License

/**
 * Main method to call, returns the new filename of the result.
 *//*from ww w  . j  a v a  2 s . co m*/
public String convertToGxml(String p_url) throws Exception {
    final String baseName = getBaseName(p_url);
    final String extension = getExtension(p_url);

    info("Converting TMX file to GXML: `" + p_url + "'");
    startOutputFile(baseName);

    m_entryCount = 0;

    // Reading from a file, need to use Xerces.
    SAXReader reader = new SAXReader();
    reader.setXMLReaderClassName("org.apache.xerces.parsers.SAXParser");
    reader.setEntityResolver(DtdResolver.getInstance());
    reader.setValidation(true);

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx", new ElementHandler() {
        final public void onStart(ElementPath path) {
            Element element = path.getCurrent();

            m_version = element.attributeValue("version");
        }

        final public void onEnd(ElementPath path) {
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/header", new ElementHandler() {
        final public void onStart(ElementPath path) {
        }

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

            setOldHeader(element);
            createNewHeader();

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

            element = null;
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/body/tu", new ElementHandler() {
        final public void onStart(ElementPath path) {
            ++m_entryCount;
            m_tuError = false;
        }

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

            if (m_tuError) {
                m_errorCount++;
            } else {
                writeEntry(element.asXML());
            }

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

            element = null;

            if (m_entryCount % 1000 == 0) {
                debug("Entry " + m_entryCount);
            }
        }
    });

    // enable element complete notifications to conserve memory
    reader.addHandler("/tmx/body/tu/tuv/seg", new ElementHandler() {
        final public void onStart(ElementPath path) {
        }

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

            try {
                String gxml = handleTuv(element);
                Document doc = parse("<root>" + gxml + "</root>");

                // Remove old content of seg
                List content = element.content();
                for (int i = content.size() - 1; i >= 0; --i) {
                    ((Node) content.get(i)).detach();
                }

                // Add new GXML content (backwards)
                content = doc.getRootElement().content();
                Collections.reverse(content);
                for (int i = content.size() - 1; i >= 0; --i) {
                    Node node = (Node) content.get(i);
                    element.add(node.detach());
                }
            } catch (Throwable ex) {
                m_tuError = true;
            }
        }
    });

    Document document = reader.read(p_url);

    closeOutputFile();

    info("Processed " + m_entryCount + " TUs " + "into file `" + m_filename + "', " + m_errorCount
            + " errors.");

    return m_filename;
}