String CRAWLER_DOCUMENT_SPACE_CHARS = "crawler.document.space.chars";

    /** The key of the configuration. e.g. u002eu06d4u2e3cu3002 */
    String CRAWLER_DOCUMENT_FULLSTOP_CHARS = "crawler.document.fullstop.chars";

    /** The key of the configuration. e.g. UTF-8 */
    String CRAWLER_CRAWLING_DATA_ENCODING = "crawler.crawling.data.encoding";

crawler.document.max.symbol.term.size=10
crawler.document.duplicate.term.removed=false
crawler.document.space.chars=u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6
crawler.document.fullstop.chars=u002eu06d4u2e3cu3002
crawler.crawling.data.encoding=UTF-8
crawler.web.protocols=http,https

            return path;
        }

        try {
            final StringBuilder buf = new StringBuilder(path.length() + 100);
            for (int i = 0; i < path.length(); i++) {
                final char c = path.charAt(i);
                if (CharUtil.isUrlChar(c) || c == '^' || c == '{' || c == '}' || c == '|' || c == '\\') {
                    buf.append(c);
                } else {