Example usage for org.apache.commons.lang3 StringEscapeUtils unescapeXml

List of usage examples for org.apache.commons.lang3 StringEscapeUtils unescapeXml

  1. HOME
  2. Java
  3. org.apache.commons
  4. org.apache.commons.lang3.*
  5. StringEscapeUtils
  6. unescapeXml

Introduction

In this page you can find the example usage for org.apache.commons.lang3 StringEscapeUtils unescapeXml.

Prototype

public static final String unescapeXml(final String input)

Source Link

Document

Unescapes a string containing XML entity escapes to a string containing the actual Unicode characters corresponding to the escapes.

Supports only the five basic XML entities (gt, lt, quot, amp, apos).

Usage

From source file:de.fatalix.book.importer.BookMigrator.java

private static BookEntry parseOPF(File pathToOPF, BookEntry bmd) throws IOException {
    List<String> lines = Files.readAllLines(pathToOPF.toPath(), Charset.forName("UTF-8"));
    boolean multiLineDescription = false;
    String description = "";
    for (String line : lines) {
        if (multiLineDescription) {
            multiLineDescription = false;
            if (line.split("<").length == 1) {
                multiLineDescription = true;
                description = description + line;
            } else {
                description = description + line.split("<")[0];
                description = StringEscapeUtils.unescapeXml(description);
                bmd.setDescription(description);
            }//from   www. j  a v  a  2s  . c  o m
        } else if (line.contains("dc:title")) {
            String title = line.split(">")[1].split("<")[0];
            bmd.setTitle(title);
        } else if (line.contains("dc:creator")) {
            String creator = line.split(">")[1].split("<")[0];
            bmd.setAuthor(creator);
        } else if (line.contains("dc:description")) {
            String value = line.split(">")[1];
            if (value.split("<").length == 1) {
                multiLineDescription = true;
                description = value;
            } else {
                value = value.split("<")[0];
                value = StringEscapeUtils.unescapeXml(value);
                bmd.setDescription(value);
            }
        } else if (line.contains("dc:publisher")) {
            String value = line.split(">")[1].split("<")[0];
            bmd.setPublisher(value);
        } else if (line.contains("dc:date")) {
            String value = line.split(">")[1].split("<")[0];
            DateTime dtReleaseDate = new DateTime(value, DateTimeZone.UTC);
            if (dtReleaseDate.getYear() != 101) {
                bmd.setReleaseDate(dtReleaseDate.toDate());
            }
        } else if (line.contains("dc:language")) {
            String value = line.split(">")[1].split("<")[0];
            bmd.setLanguage(value);
        } else if (line.contains("opf:scheme=\"ISBN\"")) {
            String value = line.split(">")[1].split("<")[0];
            bmd.setIsbn(value);
        }
    }
    return bmd;
}

From source file:com.daphne.es.maintain.staticresource.web.controller.StaticResourceVersionController.java

private String versionedStaticResourceContent(String fileRealPath, String content, String newVersion)
        throws IOException {

    content = StringEscapeUtils.unescapeXml(content);
    if (newVersion != null && newVersion.equals("1")) {
        newVersion = "?" + newVersion;
    }/*w w w .ja  va 2  s  .  c  o  m*/

    File file = new File(fileRealPath);

    List<String> contents = FileUtils.readLines(file);

    for (int i = 0, l = contents.size(); i < l; i++) {
        String fileContent = contents.get(i);
        if (content.equals(fileContent)) {
            Matcher matcher = scriptPattern.matcher(content);
            if (!matcher.matches()) {
                matcher = linkPattern.matcher(content);
            }
            if (newVersion == null) { //
                content = matcher.replaceAll("$1$2$5");
            } else {
                content = matcher.replaceAll("$1$2$3" + newVersion + "$5");
            }
            contents.set(i, content);
            break;
        }
    }
    FileUtils.writeLines(file, contents);

    return content;
}

From source file:com.zyz.mobile.book.UserBookData.java

@SuppressWarnings("UnusedAssignment")
@Override//ww  w. j  av a  2 s  .  c  o  m
public void startElement(String namespaceURI, String localName, String qName, Attributes atts)
        throws SAXException {
    if (localName.equals(Element.BOOK)) {
        mStatus.in_book = true;
        try {
            if (atts.getLength() >= 1) {
                setOffset(Integer.parseInt(atts.getValue(0)));
            }
            if (atts.getLength() >= 2) {
                mVersion = Integer.parseInt(atts.getValue(1));
            }
        } catch (NumberFormatException e) {

        }
    } else if (localName.equals(Element.SPANS)) {
        mStatus.in_spans = true;
    } else if (localName.equals(Element.SPAN)) {
        mStatus.in_span = true;

        try {
            int i = 0;
            if (atts.getLength() >= 4) {
                int type = Integer.parseInt(atts.getValue(i++));
                int color = Integer.parseInt(atts.getValue(i++));
                int start = Integer.parseInt(atts.getValue(i++));
                int end = Integer.parseInt(atts.getValue(i++));

                mCurrentSpanObj = new UserSpan(UserSpanType.toEnum(type), color, start, end);
                insertSpan(mCurrentSpanObj);
            }
            if (atts.getLength() >= 5) {
                mCurrentSpanObj.setDescription(StringEscapeUtils.unescapeXml(atts.getValue(i)));
            }
        } catch (NumberFormatException e) {
            // should not happen unless the file is corrupted or modified incorrectly
        }
    } else if (localName.equals(Element.NOTE)) {
        mStatus.in_note = true;
    } else if (localName.equals(Element.BOOKMARKS)) {
        mStatus.in_bookmarks = true;
    } else if (localName.equals(Element.BOOKMARK)) {
        mStatus.in_bookmark = true;
        int i = 0;

        try {
            if (mStatus.in_bookmarks) {
                if (atts.getLength() >= 1) {
                    int start = Integer.parseInt(atts.getValue(i++));
                    mCurrentSpanObj = (new UserSpan.Builder()).setType(UserSpanType.BOOKMARK).setStart(start)
                            .create();
                    insertSpan(mCurrentSpanObj);
                }
                if (atts.getLength() >= 2) {
                    mCurrentSpanObj.setDescription(StringEscapeUtils.unescapeXml(atts.getValue(i)));
                }
            } else if (mStatus.in_history) {
                if (atts.getLength() >= 1) {
                    int offset = Integer.parseInt(atts.getValue(i++));
                    mLocationHistory.add(offset);
                }
            }
        } catch (NumberFormatException e) {

        }

    } else if (localName.equals(Element.HISTORY)) {
        mStatus.in_history = true;
    }
}

From source file:com.erbjuder.logger.server.soap.services.LogMessageServiceBase.java

private LogMessage addTransactioLogData(Transactions.Transaction.TransactionLogData transactionLogData,
        LogMessage logMessage) {//w w  w .j av a  2  s .c  o  m

    String base64 = MimeTypes.BASE64;
    String label = StringEscapeUtils.unescapeXml(transactionLogData.getContentLabel().trim().toLowerCase());
    String mimeType = transactionLogData.getContentMimeType().trim().toLowerCase();
    String content = StringEscapeUtils.unescapeXml(transactionLogData.getContent().trim());
    long size = 0;
    if (base64.equalsIgnoreCase(mimeType)) {
        content = this.XMLFormatter(content);
        size = content.getBytes().length;

    } else {
        size = content.getBytes().length;
    }

    // 
    // Bind data to logmessage
    return this.updateLogMessage(label, mimeType, content, size, logMessage);

}

From source file:android.databinding.tool.util.XmlEditor.java

private static String defaultReplacement(XMLParser.AttributeContext attr) {
    String textWithQuotes = attr.attrValue.getText();
    String escapedText = textWithQuotes.substring(1, textWithQuotes.length() - 1);
    if (!escapedText.startsWith("@{") || !escapedText.endsWith("}")) {
        return null;
    }/* w w  w.j a  va 2  s .c om*/
    String text = StringEscapeUtils.unescapeXml(escapedText.substring(2, escapedText.length() - 1));
    ANTLRInputStream inputStream = new ANTLRInputStream(text);
    BindingExpressionLexer lexer = new BindingExpressionLexer(inputStream);
    CommonTokenStream tokenStream = new CommonTokenStream(lexer);
    BindingExpressionParser parser = new BindingExpressionParser(tokenStream);
    BindingExpressionParser.BindingSyntaxContext root = parser.bindingSyntax();
    BindingExpressionParser.DefaultsContext defaults = root.defaults();
    if (defaults != null) {
        BindingExpressionParser.ConstantValueContext constantValue = defaults.constantValue();
        BindingExpressionParser.LiteralContext literal = constantValue.literal();
        if (literal != null) {
            BindingExpressionParser.StringLiteralContext stringLiteral = literal.stringLiteral();
            if (stringLiteral != null) {
                TerminalNode doubleQuote = stringLiteral.DoubleQuoteString();
                if (doubleQuote != null) {
                    String quotedStr = doubleQuote.getText();
                    String unquoted = quotedStr.substring(1, quotedStr.length() - 1);
                    return StringEscapeUtils.escapeXml10(unquoted);
                } else {
                    String quotedStr = stringLiteral.SingleQuoteString().getText();
                    String unquoted = quotedStr.substring(1, quotedStr.length() - 1);
                    String unescaped = unquoted.replace("\"", "\\\"").replace("\\`", "`");
                    return StringEscapeUtils.escapeXml10(unescaped);
                }
            }
        }
        return constantValue.getText();
    }
    return null;
}

From source file:com.jaeksoft.searchlib.crawler.web.spider.HtmlArchiver.java

final private void checkStyleCSS(TagNode node) throws ClientProtocolException, IllegalStateException,
        IOException, SearchLibException, URISyntaxException {
    if (!("style".equalsIgnoreCase(node.getName())))
        return;//from  w w  w. j  a  v a2 s.c  o  m
    String attr = node.getAttributeByName("type");
    if (!StringUtils.isEmpty(attr) && !"text/css".equalsIgnoreCase(attr))
        return;
    attr = node.getAttributeByName("media");
    if (!StringUtils.isEmpty(attr) && !"screen".equalsIgnoreCase(attr) && !"all".equalsIgnoreCase(attr))
        return;
    StringBuilder builder = (StringBuilder) node.getText();
    if (builder == null)
        return;
    String content = builder.toString();
    String newContent = StringEscapeUtils.unescapeXml(content);
    StringBuffer sb = checkCSSContent(baseUrl, newContent);
    if (sb != null)
        newContent = sb.toString();
    if (newContent.equals(content))
        return;
    node.removeAllChildren();
    node.addChild(new ContentNode(newContent));
}

From source file:com.jaeksoft.searchlib.crawler.web.spider.HtmlArchiver.java

final private void checkScriptContent(TagNode node, Set<TagNode> disableScriptNodeSet) {
    if (!("script".equalsIgnoreCase(node.getName())))
        return;/*from w  w  w.  ja  v  a  2 s.com*/
    if (disableScriptNodeSet != null && hasAncestorXPath(disableScriptNodeSet, node)) {
        node.removeFromTree();
        return;
    }
    StringBuilder builder = (StringBuilder) node.getText();
    if (builder == null)
        return;
    String content = builder.toString();
    if (content == null)
        return;
    String newContent = StringEscapeUtils.unescapeXml(content);
    if (newContent.equals(content))
        return;
    node.removeAllChildren();
    node.addChild(new ContentNode(newContent));
}

From source file:com.screenslicer.core.scrape.type.Result.java

public void addUrl(Node node, String href, String title, boolean textSibling, boolean anchorSibling,
        boolean loneBlock, boolean image) {
    ++numUrls;//from w  w w.j a  va2  s.  co m
    String cleanHref = CommonUtil.strip(href, false);
    String cleanTitle = StringEscapeUtils
            .unescapeHtml4(StringEscapeUtils.unescapeXml(CommonUtil.strip(title, false)));
    cleanTitle = titleJunk.matcher(cleanTitle).replaceAll("");
    String noPunctTitle = cleanTitle.replaceAll("\\p{Punct}", "");
    if (CommonUtil.isEmpty(noPunctTitle)) {
        cleanTitle = "";
    }
    String coreTitle = cleanTitle.replace(" ", "").replace(" ...", "");
    if (!cleanHref.isEmpty() && !"#".equals(cleanHref) && !cleanTitle.isEmpty()
            && (!coreTitle.contains("/") || coreTitle.contains(" ") || !coreTitle.contains("."))) {
        int existingScore = 0;
        existingScore += titleHasTextSibling ? 0 : 1;
        existingScore += titleHasAnchorSibling ? 0 : 1;
        existingScore += !titleHasLoneBlock ? 0 : 1;
        existingScore += urlTitle == null || urlTitle.matches("^\\p{Punct}.*$") ? -10 : 0;
        int curScore = 0;
        curScore += textSibling ? 0 : 1;
        curScore += anchorSibling ? 0 : 1;
        curScore += !loneBlock ? 0 : 1;
        curScore += cleanTitle.matches("^\\p{Punct}.*$") ? -10 : 0;
        int curCompare = 0;
        if (url != null) {
            curCompare += cleanTitle.matches("^\\p{Punct}.*$") ? -5 : 0;
            curCompare += urlTitle == null || urlTitle.matches("^\\p{Punct}.*$") ? 9 : 0;
            curCompare += curScore < existingScore ? -2 : curScore > existingScore ? 2 : 0;
            curCompare += curScore <= 1 && curScore <= existingScore ? -1 : 0;
            curCompare += cleanTitle.length() <= urlTitle.length() / 2 ? -2
                    : cleanTitle.length() > urlTitle.length() * 2 ? 2 : 0;
            curCompare += cleanHref.contains("#") && !url.contains("#") ? -2
                    : !cleanHref.contains("#") && url.contains("#") ? 2 : 0;
            int nearestBlock = Util.nearestBlock(node);
            int existingBlock = Util.nearestBlock(urlNodes.get(url));
            curCompare += nearestBlock > existingBlock ? -2 : nearestBlock == existingBlock ? 0 : 2;
        }
        if (!hasImgUrl && CommonUtil.isEmpty(altUrl) && CommonUtil.isEmpty(altUrlTitle)
                && (isImg(cleanTitle) || isImg(cleanHref))) {
            altUrl = cleanHref;
            altUrlTitle = cleanTitle;
            urlNodes.put(cleanHref, node);
            hasImgUrl = true;
        } else if (url == null || !image && titleHasImage || curCompare > 1) {
            if (url != null) {
                priorUrl = url;
                priorUrlTitle = urlTitle;
                addToSummary(urlTitle, true, urlNodes.get(url));
                fallbackUrls.add(url);
                fallbackUrlTitles.add(urlTitle);
            }
            url = cleanHref;
            urlNodes.put(url, node);
            urlTitle = cleanTitle;
            titleHasTextSibling = textSibling;
            titleHasAnchorSibling = anchorSibling;
            titleHasLoneBlock = loneBlock;
            titleHasImage = image;
        } else if (curCompare > -1) {
            fallbackUrls.add(cleanHref);
            urlNodes.put(cleanHref, node);
            fallbackUrlTitles.add(cleanTitle);
            addToSummary(cleanTitle, true, node);
        } else {
            addToSummary(cleanTitle, true, node);
        }
    }
}

From source file:com.screenslicer.core.scrape.type.ScrapeResult.java

public void addUrl(Node node, String href, String title, boolean textSibling, boolean anchorSibling,
        boolean loneBlock, boolean image) {
    ++numUrls;/*from w  w w  . j  a va 2 s.  c  om*/
    String cleanHref = CommonUtil.strip(href, false);
    String cleanTitle = StringEscapeUtils
            .unescapeHtml4(StringEscapeUtils.unescapeXml(CommonUtil.strip(title, false)));
    cleanTitle = titleJunk.matcher(cleanTitle).replaceAll("");
    String noPunctTitle = cleanTitle.replaceAll("\\p{Punct}", "");
    if (CommonUtil.isEmpty(noPunctTitle)) {
        cleanTitle = "";
    }
    String coreTitle = cleanTitle.replace(" ", "").replace(" ...", "");
    if (!cleanHref.isEmpty() && !"#".equals(cleanHref) && !cleanTitle.isEmpty()
            && (!coreTitle.contains("/") || coreTitle.contains(" ") || !coreTitle.contains("."))) {
        int existingScore = 0;
        existingScore += titleHasTextSibling ? 0 : 1;
        existingScore += titleHasAnchorSibling ? 0 : 1;
        existingScore += !titleHasLoneBlock ? 0 : 1;
        existingScore += urlTitle == null || urlTitle.matches("^\\p{Punct}.*$") ? -10 : 0;
        int curScore = 0;
        curScore += textSibling ? 0 : 1;
        curScore += anchorSibling ? 0 : 1;
        curScore += !loneBlock ? 0 : 1;
        curScore += cleanTitle.matches("^\\p{Punct}.*$") ? -10 : 0;
        int curCompare = 0;
        if (url != null) {
            curCompare += cleanTitle.matches("^\\p{Punct}.*$") ? -5 : 0;
            curCompare += urlTitle == null || urlTitle.matches("^\\p{Punct}.*$") ? 9 : 0;
            curCompare += curScore < existingScore ? -2 : curScore > existingScore ? 2 : 0;
            curCompare += curScore <= 1 && curScore <= existingScore ? -1 : 0;
            curCompare += cleanTitle.length() <= urlTitle.length() / 2 ? -2
                    : cleanTitle.length() > urlTitle.length() * 2 ? 2 : 0;
            curCompare += cleanHref.contains("#") && !url.contains("#") ? -2
                    : !cleanHref.contains("#") && url.contains("#") ? 2 : 0;
            int nearestBlock = NodeUtil.nearestBlock(node);
            int existingBlock = NodeUtil.nearestBlock(urlNodes.get(url));
            curCompare += nearestBlock > existingBlock ? -2 : nearestBlock == existingBlock ? 0 : 2;
        }
        if (!hasImgUrl && CommonUtil.isEmpty(altUrl) && CommonUtil.isEmpty(altUrlTitle)
                && (isImg(cleanTitle) || isImg(cleanHref))) {
            altUrl = cleanHref;
            altUrlTitle = cleanTitle;
            urlNodes.put(cleanHref, node);
            hasImgUrl = true;
        } else if (url == null || !image && titleHasImage || curCompare > 1) {
            if (url != null) {
                priorUrl = url;
                priorUrlTitle = urlTitle;
                addToSummary(urlTitle, true, urlNodes.get(url));
                fallbackUrls.add(url);
                fallbackUrlTitles.add(urlTitle);
            }
            url = cleanHref;
            urlNodes.put(url, node);
            urlTitle = cleanTitle;
            titleHasTextSibling = textSibling;
            titleHasAnchorSibling = anchorSibling;
            titleHasLoneBlock = loneBlock;
            titleHasImage = image;
        } else if (curCompare > -1) {
            fallbackUrls.add(cleanHref);
            urlNodes.put(cleanHref, node);
            fallbackUrlTitles.add(cleanTitle);
            addToSummary(cleanTitle, true, node);
        } else {
            addToSummary(cleanTitle, true, node);
        }
    }
}

From source file:edu.isistan.carcha.plugin.editors.TraceabilityEditor.java

/**
 * Gets the line number for a given cross cutting concern or design decision.
 *
 * @param name the name/*from   w  w w.j a va 2 s.  c o  m*/
 * @param kind the kind
 * @return line number
 */
int getLineFor(String name, String kind) {
    int i = 0;
    String editorText = editor.getDocumentProvider().getDocument(editor.getEditorInput()).get();
    String[] lines = editorText.split(System.getProperty("line.separator"));

    int temp = 1;
    String lineEscaped;
    boolean find = false;
    for (int j = 0; j < lines.length && !find; j++) {
        lineEscaped = StringEscapeUtils.unescapeXml(lines[j]);
        if (lineEscaped.contains(name) && lineEscaped.contains(kind)) {
            i = temp;
            find = true;
        }
        temp++;
    }
    return i;
}