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

Example 76 with VTDUtils

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

the class DocUtils method isTMX.

/**
	 * 判断是否是正确的 TMX 文件
	 * @param fileName
	 * @return ;
	 * @throws FileNotFoundException
	 * @throws ParseException
	 * @throws EntityException
	 * @throws EOFException
	 * @throws EncodingException
	 */
public static VTDUtils isTMX(String fileName) throws FileNotFoundException, EncodingException, ParseException {
    VTDGen vg = new VTDGen();
    FileInputStream fis = null;
    File f = null;
    try {
        f = new File(fileName);
        fis = new FileInputStream(f);
        byte[] b = new byte[(int) f.length()];
        int offset = 0;
        int numRead = 0;
        // I choose this value randomally,
        int numOfBytes = 1048576;
        // any other (not too big) value also can be here.
        if (b.length - offset < numOfBytes) {
            numOfBytes = b.length - offset;
        }
        while (offset < b.length && (numRead = fis.read(b, offset, numOfBytes)) >= 0) {
            offset += numRead;
            if (b.length - offset < numOfBytes) {
                numOfBytes = b.length - offset;
            }
        }
        vg.setDoc(b);
        vg.parse(true);
    } catch (IOException e) {
        LOGGER.error(Messages.getString("document.DocUtils.logger1"), e);
    } finally {
        if (fis != null) {
            try {
                fis.close();
            } catch (Exception e) {
            }
        }
    }
    VTDNav vn = vg.getNav();
    AutoPilot ap = new AutoPilot(vn);
    String rootPath = "/tmx";
    VTDUtils vu = new VTDUtils();
    try {
        vu.bind(vn);
        ap.selectXPath(rootPath);
        if (ap.evalXPath() == -1) {
            return null;
        }
    } catch (NavException e) {
        LOGGER.error(Messages.getString("document.DocUtils.logger2"), e);
        return null;
    } catch (XPathEvalException e) {
        LOGGER.error(Messages.getString("document.DocUtils.logger2"), e);
        return null;
    } catch (XPathParseException e) {
        LOGGER.error(Messages.getString("document.DocUtils.logger2"), e);
        return null;
    } finally {
        vg.clear();
    }
    return vu;
}

Example 77 with VTDUtils

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

the class TmxReader method validateTmxAndParseHeader.

/**
	 * Validate TMX Format,and pilot to Body XMLElement
	 * @param vg
	 * @throws TmxReadException
	 *             ;
	 */
private void validateTmxAndParseHeader(VTDGen vg) throws TmxReadException {
    VTDNav vn = vg.getNav();
    AutoPilot ap = new AutoPilot(vn);
    String rootPath = "/tmx";
    vu = new VTDUtils();
    try {
        vu.bind(vn);
        ap.selectXPath(rootPath);
        if (ap.evalXPath() == -1) {
            throw new TmxReadException(Messages.getString("document.TmxReader.validateTmxFileError"));
        }
        ap.resetXPath();
        ap.selectXPath("/tmx/header");
        if (ap.evalXPath() == -1) {
            throw new TmxReadException(Messages.getString("document.TmxReader.validateTmxFileError"));
        }
        int id = vu.getVTDNav().getAttrVal("srclang");
        if (id == -1) {
            throw new TmxReadException(Messages.getString("document.TmxReader.validateTmxFileError"));
        }
        header.setSrclang(vu.getVTDNav().toString(id).trim());
        if (vu.pilot("/tmx/body") == -1) {
            throw new TmxReadException(Messages.getString("document.TmxReader.validateTmxFileError"));
        }
        // compute total tu number
        this.totalTu = vu.getChildElementsCount();
    } catch (VTDException e) {
        logger.error("", e);
        throw new TmxReadException(Messages.getString("document.TmxReader.parseTmxFileError") + e.getMessage());
    } finally {
        vg.clear();
    }
}

Example 78 with VTDUtils

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

the class Docx2Xliff method idealizeGTag.

/**
	 * 简化 xliff 文件的标记，主要功能是将一个源文中的 g 标记进行抽取到骨架的操作。针对一个源文中只有一个 g 标记，并且该 g 标记包褒全文本段
	 * 生成一个 名为 interTag.xml 的文件，存放于骨架文件的第一级子目录，与 word 文件夹同目录
	 * 其结构大致为<br>
	 * &lt;docxTags&gt;<br>
	 * 		&lt;tag tuId="0" &gt;this is a tag&lt;/tag&gt;<br>
	 * &lt;/docxTags&gt;<br>
	 * <div style="color:red">备注：interTag.xml 介绍： 此文件并非 docx 的内部文件，而是保存转换 docx 文件时的部份 g标记(源文中只有一对 g 标记，并且是它包褒一整个文本段)</div>
	 */
private static void idealizeGTag(String xliffPath, String interTagPath) throws Exception {
    final String constantGHeader = "<g";
    final String constantGEnd = "</g>";
    VTDGen vg = new VTDGen();
    if (!vg.parseFile(xliffPath, true)) {
        throw new Exception();
    }
    VTDNav vn = vg.getNav();
    String xpath = "/xliff/file/body/descendant::trans-unit[source/text()!=''  or source/*]";
    AutoPilot ap = new AutoPilot(vn);
    AutoPilot childAP = new AutoPilot(vn);
    VTDUtils vu = new VTDUtils(vn);
    XMLModifier xm = new XMLModifier(vn);
    ap.selectXPath(xpath);
    int index = -1;
    String id = null;
    StringBuffer tagContentSB = new StringBuffer();
    while (ap.evalXPath() != -1) {
        id = null;
        index = vn.getAttrVal("id");
        if (index != -1) {
            id = vn.toString(index);
        }
        if (id == null) {
            vn.pop();
            continue;
        }
        vn.push();
        childAP.selectXPath("./source");
        if (childAP.evalXPath() == -1) {
            vn.pop();
            continue;
        }
        String srcText = vu.getElementContent();
        childAP.selectXPath("count(./g)");
        // 如果 g 标签个数为 1 ,并且包褒整个文本段，那么便可进行清理
        if (childAP.evalXPathToNumber() == 1) {
            if (srcText.indexOf(constantGHeader) == 0 && srcText.indexOf(constantGEnd) == (srcText.length() - 4)) {
                childAP.selectXPath("./g");
                if (childAP.evalXPath() != -1) {
                    String header = vu.getElementHead();
                    String content = vu.getElementContent();
                    // 删除 g 标记
                    xm.remove();
                    xm.insertAfterElement(content);
                    // 将删除的 g 标记保存至 interTag.xml 文件中
                    tagContentSB.append("\t<tag tuId=\"" + id + "\">" + header + "</g>" + "</tag>\n");
                }
            }
        }
        vn.pop();
    }
    xm.output(xliffPath);
    if (tagContentSB.length() > 0) {
        // 开始创建 interTag.xml 文件
        File file = new File(interTagPath);
        if (!file.exists()) {
            FileOutputStream output;
            output = new FileOutputStream(interTagPath);
            output.write("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n".getBytes("UTF-8"));
            output.write("<docxTags>\n".getBytes("UTF-8"));
            output.write(tagContentSB.toString().getBytes("UTF-8"));
            output.write("</docxTags>".getBytes("UTF-8"));
            output.close();
        }
    }
}

Example 79 with VTDUtils

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

the class XliffInputer method loadXliff.

/**
	 * 解析 hsxliff 文件
	 * @throws Exception
	 */
private void loadXliff() throws Exception {
    VTDGen vg = new VTDGen();
    if (vg.parseFile(xliffFile, true)) {
        vn = vg.getNav();
        ap = new AutoPilot(vn);
        childAP = new AutoPilot(vn);
        ap.declareXPathNameSpace("hs", "http://www.heartsome.net.cn/2008/XLFExtension");
        childAP.declareXPathNameSpace("hs", "http://www.heartsome.net.cn/2008/XLFExtension");
        vu = new VTDUtils(vn);
    } else {
        throw new Exception(MessageFormat.format(Messages.getString("docxConvert.msg2"), xliffFile));
    }
}

Example 80 with VTDUtils

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

the class XLFHandler method getFullAndPureText.

/**
	 * 获取trans-unit节点下source或target节点的全文本或纯文本 robert 2011-12-14
	 * @param xlfPath
	 *            : xliff文件路径
	 * @param nodeXpath
	 *            : trans-unit子节点source或target的xpath值 如果返回null,则证明这个节点是个空节点,要么没有这个节点，要么这个节点没有值
	 * @return textMap：两个值，key1 --> fullText:全文本，key2 --> pureText：纯文本。
	 */
public Map<String, String> getFullAndPureText(String xlfPath, String nodeXpath) {
    Map<String, String> textMap = new HashMap<String, String>();
    VTDNav vn = vnMap.get(xlfPath);
    vn.push();
    AutoPilot ap = new AutoPilot(vn);
    Assert.isNotNull(vn, Messages.getString("file.XLFHandler.msg4") + xlfPath);
    try {
        VTDUtils vUtils = new VTDUtils(vn);
        ap.selectXPath(nodeXpath);
        if (ap.evalXPath() != -1) {
            String content = vUtils.getElementContent();
            if (content != null && !"".equals(content)) {
                textMap.put("fullText", content);
                textMap.put("pureText", getTUPureText(vn));
            }
        }
    } catch (Exception e) {
        LOGGER.error("", e);
        e.printStackTrace();
    }
    vn.pop();
    return textMap;
}