String result1 = crawlingInfoHelper.generateId(input1);
        assertNotNull(result1);
        assertEquals(128, result1.length());

        String input2 = "http://example.com/path with spaces";
        String result2 = crawlingInfoHelper.generateId(input2);
        assertNotNull(result2);
        assertEquals(128, result2.length());

        String input3 = "http://example.com/path<with>special|chars";

        final Path result = indexExportJob.buildFilePath("/export", "https://example.com/path%20with%20spaces/file.html",
                new HtmlIndexExportFormatter());
        assertEquals(Path.of("/export/example.com/path with spaces/file.html"), result);
    }

    // --- buildHtml() tests ---

    @Test
    public void test_buildHtml_basicDocument() {
        final Map<String, Object> source = new LinkedHashMap<>();

r}function X(e,t,o,n){var i=[0,0],r=-1!==['right','left'].indexOf(n),p=e.split(/(\+|\-)/).map(function(e){return e.trim()}),s=p.indexOf(D(p,function(e){return-1!==e.search(/,|\s/)}));p[s]&&-1===p[s].indexOf(',')&&console.warn('Offsets separated by white space(s) are deprecated, use a comma (,) instead.');var d=/\s*,\s*|\s+/,a=-1===s?[p]:[p.slice(0,s).concat([p[s].split(d)[0]]),[p[s].split(d)[1]].concat(p.slice(s+1))];return a=a.map(function(e,n){var i=(1===n?!r:r)?'height':'width',p=!1;return e.reduce(...

ER)) {\n      return PLACEMENT_TOPCENTER\n    }\n\n    if (parentDropdown.classList.contains(CLASS_NAME_DROPDOWN_CENTER)) {\n      return PLACEMENT_BOTTOMCENTER\n    }\n\n    // We need to trim the value because custom properties can also include spaces\n    const isEnd = getComputedStyle(this._menu).getPropertyValue('--bs-position').trim() === 'end'\n\n    if (parentDropdown.classList.contains(CLASS_NAME_DROPUP)) {\n      return isEnd ? PLACEMENT_TOPEND : PLACEMENT_TOP\n    }\n\n    return isEnd...

# Maximum size of symbol terms in documents.
crawler.document.max.symbol.term.size=10
# Whether to remove duplicate terms in documents.
crawler.document.duplicate.term.removed=false
# Unicode space characters for document parsing.
crawler.document.space.chars=u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6

nt:"\f886"}.fa-sort-numeric-up:before{content:"\f163"}.fa-sort-numeric-up-alt:before{content:"\f887"}.fa-sort-up:before{content:"\f0de"}.fa-soundcloud:before{content:"\f1be"}.fa-sourcetree:before{content:"\f7d3"}.fa-spa:before{content:"\f5bb"}.fa-space-shuttle:before{content:"\f197"}.fa-speakap:before{content:"\f3f3"}.fa-speaker-deck:before{content:"\f83c"}.fa-spell-check:before{content:"\f891"}.fa-spider:before{content:"\f717"}.fa-spinner:before{content:"\f110"}.fa-splotch:before{content:"\f5bc...

",lengthTooShortStart:"The input value is shorter than ",notConfirmed:"Input values could not be confirmed",badDomain:"Incorrect domain value",badUrl:"The input value is not a correct URL",badCustomVal:"The input value is incorrect",andSpaces:" and spaces ",badInt:"The input value was not a correct number",badSecurityNumber:"Your social security number was incorrect",badUKVatAnswer:"Incorrect UK VAT Number",badUKNin:"Incorrect UK NIN",badUKUtr:"Incorrect UK UTR Number",badStrength:"The password isn't...

'bs.dropdown'\nconst EVENT_KEY = `.${DATA_KEY}`\nconst DATA_API_KEY = '.data-api'\nconst JQUERY_NO_CONFLICT = $.fn[NAME]\nconst ESCAPE_KEYCODE = 27 // KeyboardEvent.which value for Escape (Esc) key\nconst SPACE_KEYCODE = 32 // KeyboardEvent.which value for space key\nconst TAB_KEYCODE = 9 // KeyboardEvent.which value for tab key\nconst ARROW_UP_KEYCODE = 38 // KeyboardEvent.which value for up arrow key\nconst ARROW_DOWN_KEYCODE = 40 // KeyboardEvent.which value for down arrow key\nconst RIGHT_MOUSE_BUTTON_WHICH...

    /**
     * Get the value for the key 'crawler.document.space.chars'. <br>
     * The value is, e.g. u0009u000Au000Bu000Cu000Du001Cu001Du001Eu001Fu0020u00A0u1680u180Eu2000u2001u2002u2003u2004u2005u2006u2007u2008u2009u200Au200Bu200Cu202Fu205Fu3000uFEFFuFFFDu00B6 <br>
     * comment: Unicode space characters for document parsing.