Example usage for org.apache.commons.lang3 StringEscapeUtils unescapeHtml4

List of usage examples for org.apache.commons.lang3 StringEscapeUtils unescapeHtml4

  1. HOME
  2. Java
  3. org.apache.commons
  4. org.apache.commons.lang3.*
  5. StringEscapeUtils
  6. unescapeHtml4

Introduction

In this page you can find the example usage for org.apache.commons.lang3 StringEscapeUtils unescapeHtml4.

Prototype

public static final String unescapeHtml4(final String input)

Source Link

Document

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

Usage

From source file:org.spdx.rdfparser.license.License.java

/**
 * @return the standardLicenseHeader//from w w w  .  java 2s. co  m
 */
public String getStandardLicenseHeader() {
    if (this.resource != null && this.refreshOnGet) {
        this.standardLicenseHeader = findSinglePropertyValue(SpdxRdfConstants.SPDX_NAMESPACE,
                SpdxRdfConstants.PROP_STD_LICENSE_NOTICE);
        if (this.standardLicenseHeader == null) {
            this.standardLicenseHeader = findSinglePropertyValue(SpdxRdfConstants.SPDX_NAMESPACE,
                    SpdxRdfConstants.PROP_STD_LICENSE_HEADER_VERSION_1);
        }
        if (this.standardLicenseHeader != null) {
            this.standardLicenseHeader = StringEscapeUtils.unescapeHtml4(this.standardLicenseHeader);
        }
    }
    return standardLicenseHeader;
}

From source file:org.spdx.rdfparser.license.License.java

/**
 * @return standard license header template
 */// w w w  .ja v a  2  s  .co m
public String getStandardLicenseHeaderTemplate() {
    if (this.resource != null && this.refreshOnGet) {
        standardLicenseHeaderTemplate = findSinglePropertyValue(SpdxRdfConstants.SPDX_NAMESPACE,
                SpdxRdfConstants.PROP_STD_LICENSE_HEADER_TEMPLATE);
        if (standardLicenseHeaderTemplate != null) {
            standardLicenseHeaderTemplate = StringEscapeUtils.unescapeHtml4(standardLicenseHeaderTemplate);
        }
    }
    return standardLicenseHeaderTemplate;
}

From source file:org.spdx.rdfparser.SPDXStandardLicense.java

/**
 * Constructs an SPDX License from the licenseNode
 * @param licenseNode RDF graph node representing the SPDX License
 * @throws InvalidSPDXAnalysisException 
 *//*  w  w  w .  j  a v a  2  s  .c om*/
public SPDXStandardLicense(Model spdxModel, Node licenseNode) throws InvalidSPDXAnalysisException {
    super(spdxModel, licenseNode);
    // name
    this.name = null;
    Node p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_NAME)
            .asNode();
    Triple m = Triple.createMatch(licenseNode, p, null);
    ExtendedIterator<Triple> tripleIter = model.getGraph().find(m);
    if (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        this.name = t.getObject().toString(false);
    } else {
        // try the pre 1.1 name - for backwards compatibility
        p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_NAME_VERSION_1)
                .asNode();
        m = Triple.createMatch(licenseNode, p, null);
        tripleIter = model.getGraph().find(m);
        if (tripleIter.hasNext()) {
            Triple t = tripleIter.next();
            this.name = t.getObject().toString(false);
        } else {
            this.name = id; // No name hsa been found, default is the ID
        }
    }
    // text
    p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_LICENSE_TEXT).asNode();
    m = Triple.createMatch(licenseInfoNode, p, null);
    tripleIter = model.getGraph().find(m);
    while (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        this.text = t.getObject().toString(false);
        if (this.text.endsWith(XML_LITERAL)) {
            this.text = this.text.substring(0, this.text.length() - XML_LITERAL.length());
        }
        if (this.textInHtml) {
            this.text = SpdxLicenseTemplateHelper.HtmlToText(this.text);
        }
    }

    // SourceUrl/seeAlso
    ArrayList<String> alsourceUrls = new ArrayList<String>();
    p = model.getProperty(SpdxRdfConstants.RDFS_NAMESPACE, SpdxRdfConstants.RDFS_PROP_SEE_ALSO).asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    while (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        alsourceUrls.add(t.getObject().toString(false));
    }
    // The following is added for compatibility with earlier versions
    p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_URL_VERSION_1)
            .asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    while (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        alsourceUrls.add(t.getObject().toString(false));
    }
    this.sourceUrl = alsourceUrls.toArray(new String[alsourceUrls.size()]);
    // notes
    p = model.getProperty(SpdxRdfConstants.RDFS_NAMESPACE, SpdxRdfConstants.RDFS_PROP_COMMENT).asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    if (!tripleIter.hasNext()) {
        // check the old property name for compatibility with pre-1.1 generated RDF files
        p = model
                .getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_NOTES_VERSION_1)
                .asNode();
        m = Triple.createMatch(licenseNode, p, null);
        tripleIter = model.getGraph().find(m);
    }
    if (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        this.comments = t.getObject().toString(false);
    } else {
        this.comments = null;
    }
    // standardLicenseHeader
    p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_NOTICE).asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    if (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        this.standardLicenseHeader = t.getObject().toString(false);
    } else {
        // try the 1.0 version name
        p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE,
                SpdxRdfConstants.PROP_STD_LICENSE_HEADER_VERSION_1).asNode();
        m = Triple.createMatch(licenseNode, p, null);
        tripleIter = model.getGraph().find(m);
        if (tripleIter.hasNext()) {
            Triple t = tripleIter.next();
            this.standardLicenseHeader = t.getObject().toString(false);
        } else {
            this.standardLicenseHeader = null;
        }
    }
    if (this.standardLicenseHeader != null) {
        this.standardLicenseHeader = StringEscapeUtils.unescapeHtml4(this.standardLicenseHeader);
    }
    // template
    p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_TEMPLATE).asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    if (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        this.template = t.getObject().toString(false);
        if (template.endsWith(XML_LITERAL)) {
            this.template = this.template.substring(0, this.template.length() - XML_LITERAL.length());
        }
        if (this.templateInHtml) {
            this.template = SpdxLicenseTemplateHelper.HtmlToText(this.template);
        }
    } else {
        // try version 1
        p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE,
                SpdxRdfConstants.PROP_STD_LICENSE_TEMPLATE_VERSION_1).asNode();
        m = Triple.createMatch(licenseNode, p, null);
        tripleIter = model.getGraph().find(m);
        if (tripleIter.hasNext()) {
            Triple t = tripleIter.next();
            this.template = t.getObject().toString(false);
            if (template.endsWith(XML_LITERAL)) {
                this.template = this.template.substring(0, this.template.length() - XML_LITERAL.length());
            }
            if (this.templateInHtml) {
                this.template = SpdxLicenseTemplateHelper.HtmlToText(this.template);
            }
        } else {
            this.template = null;
        }
    }
    // OSI Approved
    p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE, SpdxRdfConstants.PROP_STD_LICENSE_OSI_APPROVED)
            .asNode();
    m = Triple.createMatch(licenseNode, p, null);
    tripleIter = model.getGraph().find(m);
    if (!tripleIter.hasNext()) {
        // for compatibility, check the version 1 property name
        p = model.getProperty(SpdxRdfConstants.SPDX_NAMESPACE,
                SpdxRdfConstants.PROP_STD_LICENSE_OSI_APPROVED_VERSION_1).asNode();
        m = Triple.createMatch(licenseNode, p, null);
        tripleIter = model.getGraph().find(m);
    }
    if (tripleIter.hasNext()) {
        Triple t = tripleIter.next();
        String osiTextValue = t.getObject().toString(false);
        if (osiTextValue.equals("true") || osiTextValue.equals("1")) {
            this.osiApproved = true;
        } else if (osiTextValue.equals("false") || osiTextValue.equals("0")) {
            this.osiApproved = false;
        } else {
            throw (new InvalidSPDXAnalysisException(
                    "Invalid value for OSI Approved - must be {true, false, 0, 1}"));
        }
    } else {
        this.osiApproved = false;
    }
}

From source file:org.springframework.web.util.HtmlUtilsTest.java

/**
 * Test html utils./*from  w  w w.ja va  2  s  .c  o m*/
 */
@Test
public void testHtmlUtils() {
    String specialStr = "<div id=\"testDiv\">test1;test2</div>";
    String str1 = HtmlUtils.htmlEscape(specialStr); //  HTML  HTML ?
    log.info(str1);

    String str2 = HtmlUtils.htmlEscapeDecimal(specialStr);//  HTML  # ????
    log.info(str2);

    String str3 = HtmlUtils.htmlEscapeHex(specialStr);//  HTML  # ????
    log.info(str3);

    // ??????
    log.info(HtmlUtils.htmlUnescape(str1));
    log.info(HtmlUtils.htmlUnescape(str2));
    log.info(HtmlUtils.htmlUnescape(str3));

    log.info(StringEscapeUtils.unescapeHtml4(str1));
    log.info(StringEscapeUtils.unescapeHtml4(str2));
    log.info(StringEscapeUtils.unescapeHtml4(str3));

    log.info(org.apache.commons.lang.StringEscapeUtils.unescapeHtml(str1));
    log.info(org.apache.commons.lang.StringEscapeUtils.unescapeHtml(str2));
    log.info(org.apache.commons.lang.StringEscapeUtils.unescapeHtml(str3));
}

From source file:org.springframework.web.util.HtmlUtilsTest.java

/**
 * String escape utils.
 */
@Test
public void stringEscapeUtils() {
    log.info(StringEscapeUtils.unescapeHtml4(a));
}

From source file:org.tinymediamanager.scraper.aebn.AebnMetadataProvider.java

/**
 * Search for movies at aebn.net.//from ww  w .  j a  v  a  2  s. c  om
 *
 */
@Override
public List<MediaSearchResult> search(MediaSearchOptions query) throws Exception {
    LOGGER.debug("AEBN: search() {}", query);
    List<MediaSearchResult> resultList = new ArrayList<MediaSearchResult>();
    Elements movies = null;
    String searchString = "";

    // Search for query
    if (StringUtils.isNotEmpty(query.get(MediaSearchOptions.SearchParam.QUERY))) {
        searchString = query.get(MediaSearchOptions.SearchParam.QUERY);
    }

    // Search
    String searchUrl = BASE_DATAURL + "/dispatcher/fts?userQuery="
            + URLEncoder.encode(cleanSearchQuery(searchString), "UTF-8")
            + "&targetSearchMode=basic&isAdvancedSearch=true&isFlushAdvancedSearchCriteria=false" + "&count="
            + SEARCH_COUNT.toString() + "&imageType=Large&sortType=Relevance";
    try {
        LOGGER.info("========= BEGIN AEBN Scraper Search for: {}", searchString);
        Url url = new Url(searchUrl);
        InputStream in = url.getInputStream();
        Document doc = Jsoup.parse(in, "UTF-8", "");
        in.close();

        // only look for movie links like
        // <a id="FTSMovieSearch_link_title_detail_30" ... </a>
        movies = doc.getElementsByAttributeValueMatching("id", "FTSMovieSearch_link_title_detail_\\d+");
        LOGGER.debug("AEBN: found {} search results", movies.size());
    } catch (Exception e) {
        LOGGER.error("AEBN: failed to search for {}: ", searchString, e);
    }

    if (movies == null || movies.isEmpty()) {
        LOGGER.debug("AEBN: no movie found");
        return resultList;
    }

    // there are search results, so fill media data structure
    HashSet<String> foundResultUrls = new HashSet<String>();
    for (Element anchor : movies) {
        try {
            String movieUrl = BASE_DATAURL + StrgUtils.substr(anchor.toString(), "href=\\\"(.*?)\\\"");
            String movieId = StrgUtils.substr(anchor.toString(), "movieId=(\\d+)");
            String movieName = StringEscapeUtils.unescapeHtml4(anchor.text());
            String posterUrl = BASE_IMGURL + "/Stream/Movie/Boxcovers/a" + movieId + "_160w.jpg";
            LOGGER.debug("AEBN: found movie {} (id{})", movieName, movieId);

            // check if it is a valid AEBN id
            if (!isValidAebnId(Integer.parseInt(movieId))) {
                LOGGER.error("AEBN: id({}) is not a valid aebn id", movieId);
            }

            MediaSearchResult sr = new MediaSearchResult(providerInfo.getId());
            sr.setId(movieId);
            sr.setIMDBId("");
            sr.setTitle(movieName);
            sr.setOriginalTitle(movieName);
            // sr.setYear not possible, no data at this point
            sr.setYear(null);
            sr.setMediaType(MediaType.MOVIE);
            sr.setUrl(movieUrl);
            sr.setPosterUrl(posterUrl);

            // compare score based on names
            float score = MetadataUtil.calculateScore(searchString, movieName);
            if (posterUrl.isEmpty() || posterUrl.contains("nopicture")) {
                LOGGER.debug("AEBN: no poster - downgrading score by 0.01");
                score = score - 0.01f;
            }
            sr.setScore(score);

            // check if result has at least a title and id
            if (StringUtils.isBlank(sr.getTitle()) || StringUtils.isBlank(sr.getId())) {
                LOGGER.warn("AEBN: no title nor id, skipping");
                continue;
            }

            // check if the movie has been already added to the search results
            if (foundResultUrls.contains(sr.getUrl())) {
                continue;
            }
            foundResultUrls.add(sr.getUrl());

            // populate extra arguments (deprecated)
            // MetadataUtil.copySearchQueryToSearchResult(query, sr);

            resultList.add(sr);
        } catch (Exception e) {
            LOGGER.warn("AEBN: error parsing search result: {}", e);
        }
    }
    Collections.sort(resultList);
    Collections.reverse(resultList);

    return resultList;
}

From source file:org.tinymediamanager.scraper.ofdb.OfdbMetadataProvider.java

@Override
public List<MediaSearchResult> search(MediaSearchOptions options) throws Exception {
    LOGGER.debug("search() " + options.toString());

    if (options.getMediaType() != MediaType.MOVIE) {
        throw new UnsupportedMediaTypeException(options.getMediaType());
    }//ww  w .jav a 2 s .co m

    List<MediaSearchResult> resultList = new ArrayList<>();
    String searchString = "";
    String searchQuery = "";
    String imdb = "";
    Elements filme = null;
    int myear = options.getYear();

    /*
     * Kat = All | Titel | Person | DTitel | OTitel | Regie | Darsteller | Song | Rolle | EAN| IMDb | Google
     * http://www.ofdb.de//view.php?page=suchergebnis &Kat=xxxxxxxxx&SText=yyyyyyyyyyy
     */
    // 1. search with imdbId
    if (StringUtils.isNotEmpty(options.getImdbId()) && (filme == null || filme.isEmpty())) {
        try {
            imdb = options.getImdbId();
            searchString = BASE_URL + "/view.php?page=suchergebnis&Kat=IMDb&SText=" + imdb;
            LOGGER.debug("search with imdbId: " + imdb);

            Url url = new Url(searchString);
            InputStream in = url.getInputStream();
            Document doc = Jsoup.parse(in, "UTF-8", "");
            in.close();
            // only look for movie links
            filme = doc.getElementsByAttributeValueMatching("href", "film\\/\\d+,");
            LOGGER.debug("found " + filme.size() + " search results");
        } catch (Exception e) {
            LOGGER.error("failed to search for imdb Id " + imdb + ": " + e.getMessage());
        }
    }

    // 2. search for search string
    if (StringUtils.isNotEmpty(options.getQuery()) && (filme == null || filme.isEmpty())) {
        try {
            String query = options.getQuery();
            searchQuery = query;
            query = MetadataUtil.removeNonSearchCharacters(query);
            searchString = BASE_URL + "/view.php?page=suchergebnis&Kat=All&SText="
                    + URLEncoder.encode(cleanSearch(query), "UTF-8");
            LOGGER.debug("search for everything: " + query);

            Url url = new Url(searchString);
            InputStream in = url.getInputStream();
            Document doc = Jsoup.parse(in, "UTF-8", "");
            in.close();
            // only look for movie links
            filme = doc.getElementsByAttributeValueMatching("href", "film\\/\\d+,");
            LOGGER.debug("found " + filme.size() + " search results");
        } catch (Exception e) {
            LOGGER.error("failed to search for " + searchQuery + ": " + e.getMessage());
        }
    }

    if (filme == null || filme.isEmpty()) {
        LOGGER.debug("nothing found :(");
        return resultList;
    }

    // <a href="film/22523,Die-Bourne-Identitt"
    // onmouseover="Tip('<img src=&quot;images/film/22/22523.jpg&quot;
    // width=&quot;120&quot; height=&quot;170&quot;>',SHADOW,true)">Bourne
    // Identitt, Die<font size="1"> / Bourne Identity, The</font> (2002)</a>
    HashSet<String> foundResultUrls = new HashSet<>();
    for (Element a : filme) {
        try {
            MediaSearchResult sr = new MediaSearchResult(providerInfo.getId(), MediaType.MOVIE);
            if (StringUtils.isNotEmpty(imdb)) {
                sr.setIMDBId(imdb);
            }
            sr.setId(StrgUtils.substr(a.toString(), "film\\/(\\d+),")); // OFDB ID
            sr.setTitle(StringEscapeUtils.unescapeHtml4(StrgUtils
                    .removeCommonSortableName(StrgUtils.substr(a.toString(), ".*>(.*?)(\\[.*?\\])?<font"))));
            LOGGER.debug("found movie " + sr.getTitle());
            sr.setOriginalTitle(StringEscapeUtils.unescapeHtml4(
                    StrgUtils.removeCommonSortableName(StrgUtils.substr(a.toString(), ".*> / (.*?)</font"))));
            try {
                sr.setYear(Integer.parseInt(StrgUtils.substr(a.toString(), "font> \\((.*?)\\)<\\/a")));
            } catch (Exception ignored) {
            }

            sr.setUrl(BASE_URL + "/" + StrgUtils.substr(a.toString(), "href=\\\"(.*?)\\\""));
            sr.setPosterUrl(BASE_URL + "/images" + StrgUtils.substr(a.toString(), "images(.*?)\\&quot"));

            // check if it has at least a title and url
            if (StringUtils.isBlank(sr.getTitle()) || StringUtils.isBlank(sr.getUrl())) {
                continue;
            }

            // OFDB could provide linke twice - check if that has been already added
            if (foundResultUrls.contains(sr.getUrl())) {
                continue;
            }
            foundResultUrls.add(sr.getUrl());

            if (imdb.equals(sr.getIMDBId())) {
                // perfect match
                sr.setScore(1);
            } else {
                // compare score based on names
                float score = MetadataUtil.calculateScore(searchQuery, sr.getTitle());

                if (yearDiffers(myear, sr.getYear())) {
                    float diff = (float) Math.abs(myear - sr.getYear()) / 100;
                    LOGGER.debug(
                            "parsed year does not match search result year - downgrading score by " + diff);
                    score -= diff;
                }
                sr.setScore(score);

            }
            resultList.add(sr);
        } catch (Exception e) {
            LOGGER.warn("error parsing movie result: " + e.getMessage());
        }
    }
    Collections.sort(resultList);
    Collections.reverse(resultList);

    return resultList;
}

From source file:org.tinymediamanager.ui.actions.DonateAction.java

@Override
public void actionPerformed(ActionEvent e) {
    String url = StringEscapeUtils.unescapeHtml4("http://tinymediamanager.org/donate.php");
    try {// ww  w .  ja  v  a2s.co  m
        TmmUIHelper.browseUrl(url);
    } catch (Exception e1) {
        LOGGER.error("Donate", e1);
        MessageManager.instance.pushMessage(new Message(MessageLevel.ERROR, url, "message.erroropenurl",
                new String[] { ":", e1.getLocalizedMessage() }));
    }
}

From source file:org.tinymediamanager.ui.actions.FaqAction.java

@Override
public void actionPerformed(ActionEvent e) {
    String url = StringEscapeUtils
            .unescapeHtml4("https://github.com/tinyMediaManager/tinyMediaManager/wiki/FAQ");
    try {/*ww w. j av a2 s .c om*/
        TmmUIHelper.browseUrl(url);
    } catch (Exception e1) {
        LOGGER.error("FAQ", e1);
        MessageManager.instance.pushMessage(new Message(MessageLevel.ERROR, url, "message.erroropenurl",
                new String[] { ":", e1.getLocalizedMessage() }));
    }
}

From source file:org.tinymediamanager.ui.actions.FeedbackAction.java

@Override
public void actionPerformed(ActionEvent e) {
    String url = StringEscapeUtils.unescapeHtml4("http://forum.xbmc.org/forumdisplay.php?fid=204");
    try {// w  w w .  ja va2 s. c om
        TmmUIHelper.browseUrl(url);
    } catch (Exception e1) {
        LOGGER.error("FAQ", e1);
        MessageManager.instance.pushMessage(new Message(MessageLevel.ERROR, url, "message.erroropenurl",
                new String[] { ":", e1.getLocalizedMessage() }));
    }
}