Examples with VTDUtils net.heartsome.xml.vtdimpl.VTDUtils used on opensource projects

Example 31 with VTDUtils

use of net.heartsome.xml.vtdimpl.VTDUtils in project translationstudio8 by heartsome.

the class QAXmlHandler method getNonTransElementsRegex.

/**
	 * 只获取非译元素的正则表达式
	 * @param filePath
	 * @return
	 */
public List<String> getNonTransElementsRegex(String filePath) {
    List<String> regexList = new ArrayList<String>();
    VTDNav vn = vnMap.get(filePath);
    AutoPilot ap = new AutoPilot(vn);
    validNull(vn, ap, filePath);
    try {
        VTDUtils vUtils = new VTDUtils(vn);
        ap.selectXPath("/nonTrans/element/regular");
        while (ap.evalXPath() != -1) {
            regexList.add(vUtils.getElementContent());
        }
    } catch (Exception e) {
        e.printStackTrace();
        logger.error(Messages.getString("qa.QAXmlHandler.logger19"), e);
    }
    return regexList;
}

Example 32 with VTDUtils

use of net.heartsome.xml.vtdimpl.VTDUtils in project translationstudio8 by heartsome.

the class QAXmlHandler method getFilteredTUTextForMultiParaConsis.

/**
	 * 针对合并打开的文本段一致性检查的情况，获取trans-unit节点过滤后的值，过滤条件为不包括上下文匹配，不包括完全匹配，不包括已锁文本，过滤条件在首选项中设置
	 * @param xlfPath	
	 * @param nodeXpath	
	 * @param filterMap	过滤条件
	 * @return ;
	 */
public Map<String, ParaConsisDataBean> getFilteredTUTextForMultiParaConsis(List<String> rowIdList, Map<String, Boolean> filterMap, boolean checkSameSource, boolean checkSameTarget, boolean srcIgnoreTag, boolean tarIgnoreTag) {
    Map<String, ParaConsisDataBean> filteredTuTextMap = new HashMap<String, ParaConsisDataBean>();
    try {
        //检查项有两个，即相同源文不同译文，相同译文不同源文，如果某项不检查，那么它的忽略标记为false
        if (!checkSameSource) {
            srcIgnoreTag = false;
        }
        if (!checkSameTarget) {
            tarIgnoreTag = false;
        }
        for (String rowId : rowIdList) {
            String xlfPath = RowIdUtil.getFileNameByRowId(rowId);
            VTDNav vn = vnMap.get(xlfPath);
            AutoPilot ap = new AutoPilot(vn);
            Assert.isNotNull(vn, Messages.getString("qa.QAXmlHandler.msg1") + xlfPath);
            AutoPilot childAp = new AutoPilot(vn);
            VTDUtils vUtils = new VTDUtils(vn);
            ap.selectXPath(RowIdUtil.parseRowIdToXPath(rowId));
            if (ap.evalXPath() != -1) {
                ParaConsisDataBean dataBean = new ParaConsisDataBean();
                vn.push();
                //取出源文本的纯文本之前，先查看其内容是否为空，若为空，则返回null，没有source节点，也返回null
                childAp.selectXPath("./source");
                if (childAp.evalXPath() != -1) {
                    //因为标准里面只有一个source，因此此处用if不用while
                    String srcContent = vUtils.getElementContent();
                    //如果源文本为空或无值，则返回null
                    if (srcContent == null || "".equals(srcContent)) {
                        continue;
                    } else {
                        //两个检查项中的忽略标记，若有一项为true，那么就必须获取纯文本
                        if (srcIgnoreTag || tarIgnoreTag) {
                            dataBean.setSrcContent(srcContent.trim());
                            dataBean.setSrcPureText(getTUPureText(vn).trim());
                        } else {
                            dataBean.setSrcContent(srcContent.trim());
                        }
                    }
                } else {
                    continue;
                }
                childAp.resetXPath();
                vn.pop();
                //首先过滤，如果有不应包括的文本段，则返回一个空对象
                if (!filterTheTU(vn, filterMap)) {
                    continue;
                }
                vn.push();
                //下面获取目标文本的纯文本，在之前先检查目标文本是否为空或为空值，若是，则返回null，若没有target节点，也返回空
                childAp.selectXPath("./target");
                if (childAp.evalXPath() != -1) {
                    //因为标准里面只有一个target，因此此处用if不用while
                    String tgtContent = vUtils.getElementContent();
                    //如果源文本为空或无值，则返回空对象
                    if (tgtContent == null || "".equals(tgtContent)) {
                        continue;
                    } else {
                        //两个检查项中的忽略标记，若有一项为true，那么就必须获取纯文本
                        if (srcIgnoreTag || tarIgnoreTag) {
                            dataBean.setTgtContent(tgtContent.trim());
                            dataBean.setTgtPureText(getTUPureText(vn).trim());
                        } else {
                            dataBean.setTgtContent(tgtContent.trim());
                        }
                    }
                } else {
                    continue;
                }
                dataBean.setLineNumber(rowIdList.indexOf(rowId) + 1);
                vn.pop();
                filteredTuTextMap.put(rowId, dataBean);
            }
        }
    } catch (Exception e) {
        e.printStackTrace();
        logger.error(Messages.getString("qa.QAXmlHandler.logger13"), e);
    }
    return filteredTuTextMap;
}

Example 33 with VTDUtils

use of net.heartsome.xml.vtdimpl.VTDUtils in project translationstudio8 by heartsome.

the class QAXmlHandler method getTuProp.

/**
	 * 得到翻译单元的属性值	,来自XLFHandler
	 * @param rowId
	 *            行的唯一标识
	 * @param propName
	 *            属性名
	 * @return 属性值;
	 */
public String getTuProp(String rowId, String propName) {
    VTDNav vn = getVTDNavByRowId(rowId);
    String tuXPath = RowIdUtil.parseRowIdToXPath(rowId);
    try {
        VTDUtils vu = new VTDUtils(vn);
        return vu.getValue(tuXPath + "/@" + propName);
    } catch (NavException e) {
        e.printStackTrace();
        logger.error(Messages.getString("qa.QAXmlHandler.logger7"), e);
    }
    return null;
}

Example 34 with VTDUtils

use of net.heartsome.xml.vtdimpl.VTDUtils in project translationstudio8 by heartsome.

the class TSFileHandler method analysisTranslatorProgress.

// 分析翻译进度。直接返回报告内容的 XML 字符串。
protected String analysisTranslatorProgress(VTDNav vn, final String filepath, float eqvFactor) throws NavException, XPathParseException, XPathEvalException {
    VTDUtils vu = new VTDUtils(vn);
    StringBuilder sb = new StringBuilder();
    sb.append("\t<status-infos purpose=\"");
    sb.append(Messages.getString("file.TSFileHandler.analysisTranslatorProgress"));
    sb.append("\" filepath=\"" + filepath + "\">\n");
    int translatedSegs = 0;
    int untranslatedSegs = 0;
    int translatedWords = 0;
    int untranslatedWords = 0;
    boolean isTranslated = false;
    AutoPilot ap = new AutoPilot(vn);
    ap.selectXPath("//trans-unit");
    while (ap.evalXPath() != -1) {
        String tgtText = vu.getChildPureText("target");
        // 目标文本为空或 null 表示未翻译，反之为已翻译
        if (tgtText == null || tgtText.trim().equals("")) {
            isTranslated = false;
        } else {
            isTranslated = true;
        }
        vn.push();
        // 开始统计分析。
        String srcText = vu.getChildPureText("source");
        String lang = vu.getElementAttribute("source", "xml:lang");
        int words = wordCount(srcText, lang);
        if (isTranslated) {
            translatedSegs++;
            translatedWords += words;
        } else {
            untranslatedSegs++;
            untranslatedWords += words;
        }
        vn.pop();
    }
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.translatedSegs"));
    sb.append("\" statisticunits=\"segment\">");
    sb.append(translatedSegs);
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.untranslatedSegs"));
    sb.append("\" statisticunits=\"segment\">");
    sb.append(untranslatedSegs);
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.percent1"));
    sb.append("\" statisticunits=\"segment\">");
    sb.append(translatedSegs * 100 / (translatedSegs + untranslatedSegs));
    sb.append("%");
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.total1"));
    sb.append("\" statisticunits=\"segment\">");
    sb.append(translatedSegs + untranslatedSegs);
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.translatedWords"));
    sb.append("\" statisticunits=\"word\">");
    sb.append(translatedWords);
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.untranslatedWords"));
    sb.append("\" statisticunits=\"word\">");
    sb.append(untranslatedWords);
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.percent2"));
    sb.append("\" statisticunits=\"word\">");
    sb.append(translatedWords * 100 / (translatedWords + untranslatedWords));
    sb.append("%");
    sb.append("</status-info>\n");
    sb.append("\t\t<status-info type=\"");
    sb.append(Messages.getString("file.TSFileHandler.total2"));
    sb.append("\" statisticunits=\"word\">");
    sb.append(translatedWords + untranslatedWords);
    sb.append("</status-info>\n");
    sb.append("\t</status-infos>\n");
    return sb.toString();
}

Example 35 with VTDUtils

use of net.heartsome.xml.vtdimpl.VTDUtils in project translationstudio8 by heartsome.

the class TSFileHandler method openFile.

@Override
public Map<String, Object> openFile(File file, int tuCount) {
    long start = System.currentTimeMillis();
    // 验证文件是否存在
    if (file == null || !file.exists()) {
        String errorMsg = Messages.getString("file.TSFileHandler.logger5");
        logger.error(errorMsg);
        return getErrorResult(errorMsg, null);
    }
    // 判断是否还有缓存空间。
    boolean canCache = tuCount < TU_CACHE_SIZE;
    // 当前文件中解析并缓存翻译单元计数器。
    int parsedTuCount = 0;
    // 当前文件未解析缓存的翻译单元计数器。
    int noParseTuCount = 0;
    String filename = file.getAbsolutePath();
    int fileIndex = 1;
    // 解析文件并获取索引
    VTDGen vgRead = new VTDGen();
    if (vgRead.parseFile(filename, true)) {
        VTDNav vnRead = vgRead.getNav();
        VTDUtils vu = null;
        try {
            vu = new VTDUtils(vnRead);
            // 创建临时文件
            File tmpFile = createTmpFile();
            XMLModifier xm = new XMLModifier(vnRead);
            FileOutputStream fos = new FileOutputStream(tmpFile);
            xm.output(fos);
            fos.close();
            tmpFileMap.put(filename, tmpFile.getAbsolutePath());
            filesChangeStatus.put(filename, false);
        } catch (ModifyException e) {
            String errorMsg = MessageFormat.format(Messages.getString("file.TSFileHandler.logger6"), filename);
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        } catch (TranscodeException e) {
            String errorMsg = MessageFormat.format(Messages.getString("file.TSFileHandler.logger7"), filename);
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        } catch (IOException e) {
            String errorMsg = MessageFormat.format(Messages.getString("file.TSFileHandler.logger8"), filename);
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        } catch (NavException e) {
            String errorMsg = Messages.getString("file.TSFileHandler.logger9");
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        }
        // 创建翻译单元集合缓存。
        Vector<TransUnitBean> tusCache = new Vector<TransUnitBean>();
        // 创建翻译单元索引集合缓存。
        Vector<String> tuIndexCache = new Vector<String>();
        // 初始化文件节点属性集合。
        fileAttrs = new Hashtable<Integer, Hashtable<String, String>>();
        AutoPilot apFile = new AutoPilot(vnRead);
        String fileNode = "/xliff/file";
        try {
            apFile.selectXPath(fileNode);
            while (apFile.evalXPath() != -1) {
                fileAttrs.put(fileIndex, vu.getCurrentElementAttributs());
                AutoPilot apTU = new AutoPilot(vnRead);
                apTU.selectXPath("body//trans-unit");
                vnRead.push();
                while (apTU.evalXPath() != -1) {
                    // 如果缓冲区未满，则解析文件内容并缓存，否则只计数，不解析内容。
                    if (canCache) {
                        String tuid = "";
                        String srcText = "";
                        String srcContent = "";
                        String tgtText = "";
                        String tgtContent = "";
                        Hashtable<String, String> srcProps = null;
                        Hashtable<String, String> tgtProps = null;
                        // 取翻译单元所有属性
                        String tmpNode = "";
                        vnRead.push();
                        Hashtable<String, String> tuProps = vu.getCurrentElementAttributs();
                        vnRead.pop();
                        tuid = tuProps.get("id");
                        // 取翻译单元源节点完整文本，含内部标记。
                        vnRead.push();
                        tmpNode = "./source";
                        srcContent = vu.getElementContent(tmpNode);
                        // vnRead.pop();
                        // 取翻译单元源文本。
                        // vnRead.push();
                        srcText = vu.getElementPureText();
                        // 取翻译单元源节点属性。
                        srcProps = vu.getCurrentElementAttributs();
                        vnRead.pop();
                        // 取翻译单元目标节点完整文本，含内部标记。
                        vnRead.push();
                        tmpNode = "./target";
                        tgtContent = vu.getElementContent(tmpNode);
                        // vnRead.pop();
                        // 取翻译单元目标文本。
                        // vnRead.push();
                        tgtText = vu.getElementPureText();
                        // 取翻译单元目标节点属性。
                        tgtProps = vu.getCurrentElementAttributs();
                        vnRead.pop();
                        // 获取所有的 alttrans 匹配节点。
                        vnRead.push();
                        Vector<AltTransBean> matches = getAltTrans(vu);
                        vnRead.pop();
                        // 构建翻译单元对象，存储节点信息
                        TransUnitBean tub = new TransUnitBean(tuid, srcContent, srcText);
                        tub.setTuProps(tuProps);
                        tub.setSrcProps(srcProps);
                        tub.setTgtContent(tgtContent);
                        tub.setTgtText(tgtText);
                        tub.setTgtProps(tgtProps);
                        tub.setMatches(matches);
                        vnRead.push();
                        tub.setNotes(getNotes(vu));
                        vnRead.pop();
                        vnRead.push();
                        tub.setPropgroups(getPrpoGroups(vu));
                        vnRead.pop();
                        tusCache.add(tub);
                        tuIndexCache.add(filename + ";" + fileIndex + ";" + tuid);
                        // 解析的翻译单元节点计数
                        parsedTuCount++;
                        if (tuCount + parsedTuCount == TU_CACHE_SIZE) {
                            canCache = false;
                        }
                    } else {
                        // 未解析的翻译单元节点计数
                        noParseTuCount++;
                    }
                }
                vnRead.pop();
                // 文件节点索引计数
                fileIndex++;
            }
            transunits.put(filename, tusCache);
            tuIndexs.put(filename, tuIndexCache);
            actualTuCount.put(filename, parsedTuCount + noParseTuCount);
            accessHistory.put(filename, "");
        } catch (XPathEvalException e) {
            String errorMsg = Messages.getString("file.TSFileHandler.logger10");
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        } catch (NavException e) {
            String errorMsg = Messages.getString("file.TSFileHandler.logger11");
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        } catch (XPathParseException e) {
            String errorMsg = Messages.getString("file.TSFileHandler.logger12");
            logger.error(errorMsg, e);
            return getErrorResult(errorMsg, e);
        }
    } else {
        String errorMsg = MessageFormat.format(Messages.getString("file.TSFileHandler.logger13"), filename);
        logger.error(errorMsg);
        return getErrorResult(errorMsg, null);
    }
    long end = System.currentTimeMillis();
    // 输出结果
    long resultMS = end - start;
    long resultS = resultMS / 1000;
    long resultM = resultMS / (1000 * 60);
    System.gc();
    logger.info(Messages.getString("file.TSFileHandler.logger14"), new Object[] { resultM, resultS, resultMS });
    Map<String, Object> result = getSuccessResult();
    result.put("CurCachedTuCount", Integer.valueOf(parsedTuCount));
    result.put("TotalCachedTuCount", Integer.valueOf(parsedTuCount + tuCount));
    return result;
}