DOMParser - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlXpathExtractor.java

     *
     * @return a configured DOM parser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        final DOMParser parser = new DOMParser();
        try {
            // feature
            for (final Map.Entry<String, String> entry : featureMap.entrySet()) {

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 10.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlExtractor.java

    }

    /**
     * Creates and configures a DOM parser for parsing HTML content.
     *
     * @return a configured DOMParser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        final DOMParser parser = new DOMParser();
        try {
            // feature
            for (final Map.Entry<String, String> entry : featureMap.entrySet()) {

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 9.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

     *
     * @return a configured DOM parser
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        final DOMParser parser = new DOMParser();
        try {
            // feature
            for (final Map.Entry<String, String> entry : featureMap.entrySet()) {

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 28.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/test/java/org/codelibs/fess/mylasta/direction/FessPropTest.java

        assertEquals(2, fessConfig.getAvailableSmbSidType(5));
    }

    private boolean matchesTag(final PrunedTag tag, final String text) throws Exception {
        final DOMParser parser = new DOMParser();
        final String html = "<html><body>" + text + "</body></html>";
        final ByteArrayInputStream is = new ByteArrayInputStream(html.getBytes("UTF-8"));
        parser.parse(new InputSource(is));

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Tue Aug 19 14:09:36 UTC 2025

- 13K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.util.XmlUtil;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 13.1K bytes

- Viewed (0)

github.com/codelibs/fess

src/test/java/org/codelibs/fess/crawler/transformer/FessXpathTransformerTest.java

        assertTrue(responseData.isNoFollow());
    }

    private Document getDocument(final String data) throws Exception {
        final DOMParser parser = new DOMParser();
        final ByteArrayInputStream is = new ByteArrayInputStream(data.getBytes("UTF-8"));
        parser.parse(new InputSource(is));
        return parser.getDocument();
    }

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Sat Jul 19 23:49:30 UTC 2025

- 41.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/transformer/FessXpathTransformer.java

import org.codelibs.fess.opensearch.config.exentity.CrawlingConfig.Param.XPath;
import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.PrunedTag;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;

import jakarta.annotation.PostConstruct;

/**

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Thu Aug 07 03:06:29 UTC 2025

- 54.4K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/webapp/js/bootstrap.min.js

tInTemplate(c(e),i):this._config.html?i.innerHTML=this._maybeSanitize(e):i.textContent=e:i.remove())}_maybeSanitize(t){return this._config.sanitize?function(t,e,s){if(!t.length)return t;if(s&&"function"==typeof s)return s(t);const i=(new window.DOMParser).parseFromString(t,"text/html"),n=[].concat(...i.body.querySelectorAll("*"));for(const t of n){const s=t.nodeName.toLowerCase();if(!Object.keys(e).includes(s)){t.remove();continue}const i=[].concat(...t.attributes),n=[].concat(e["*"]||[],e[s]||[]);for(const...

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Sun Jan 12 06:14:02 UTC 2025

- 58.9K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/webapp/js/admin/bootstrap.min.js.map

sanitizeHtml(unsafeHtml, whiteList, sanitizeFn) {\n  if (unsafeHtml.length === 0) {\n    return unsafeHtml\n  }\n\n  if (sanitizeFn && typeof sanitizeFn === 'function') {\n    return sanitizeFn(unsafeHtml)\n  }\n\n  const domParser = new window.DOMParser()\n  const createdDocument = domParser.parseFromString(unsafeHtml, 'text/html')\n  const whitelistKeys = Object.keys(whiteList)\n  const elements = [].slice.call(createdDocument.body.querySelectorAll('*'))\n\n  for (let i = 0, len = elements.length; i <...

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Sat Oct 26 01:49:09 UTC 2024

- 180.9K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/webapp/js/bootstrap.min.js.map

allowList, sanitizeFunction) {\n  if (!unsafeHtml.length) {\n    return unsafeHtml\n  }\n\n  if (sanitizeFunction && typeof sanitizeFunction === 'function') {\n    return sanitizeFunction(unsafeHtml)\n  }\n\n  const domParser = new window.DOMParser()\n  const createdDocument = domParser.parseFromString(unsafeHtml, 'text/html')\n  const elements = [].concat(...createdDocument.body.querySelectorAll('*'))\n\n  for (const element of elements) {\n    const elementName = element.nodeName.toLowerCase()\n\n...

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Sun Jan 12 06:14:02 UTC 2025

- 211.9K bytes

- Viewed (0)

Search Options