上篇说道,tokenize方法会把selector分割成一个个selector逻辑单元(如div>a是三个逻辑单元 ‘div‘,‘>‘,‘a‘)并为之片段赋予对应类型的过滤函数。
for ( type in Expr.filter ) { if ( (match = matchExpr[ type ].exec( soFar )) && (!preFilters[ type ] || (match = preFilters[ type ]( match ))) ) { matched = match.shift(); tokens.push({ value: matched, type: type, matches: match }); soFar = soFar.slice( matched.length ); } }
然后选出最后selector逻辑单元(是指由需要上下文的选择器,如id,tag,class等)所对应的元素集作为从右向左(一般情况)过滤的候选元素集,match(正则捕获组)是selector逻辑片段的解析结果(如[arr="111"]根据正则解析为arr,",=,111 ),在selector逻辑片段是ATTR、CHILD、PSEUDO是需要调用preFilter对match进行修正.
preFilter: { //match是捕获组 //假设:[arr^=‘val‘] "ATTR": function( match ) { //attr的第一个捕获 组是arr,将其中的转码变成原来的字符 match[1] = match[1].replace( runescape, funescape ); // Move the given value to match[3] whether quoted or unquoted // 将val放到捕获组3里,原来的捕获组3捕获‘或" match[3] = ( match[4] || match[5] || "" ).replace( runescape, funescape ); //如果捕获组2是~=,在match[3]前后加空格,以方便匹配单个单词 if ( match[2] === "~=" ) { match[3] = " " + match[3] + " "; } //match[0] = ‘[arr^=‘val‘]‘ //match[1] = ‘arr‘ //match[2] = ‘=‘ //match[3] = ‘111‘ return match.slice( 0, 4 ); }, "CHILD": function( match ) { /* 例如nth-child(-2n+1)的捕获组 mathc[1] nth mathc[2] child mathc[3] 2n+1 mathc[4] 2n mathc[5] - mathc[6] 2 mathc[7] + mathc[8] 1 */ match[1] = match[1].toLowerCase(); // nth必须需要参数 if ( match[1].slice( 0, 3 ) === "nth" ) { // nth-* requires argument if ( !match[3] ) { Sizzle.error( match[0] ); } // numeric x and y parameters for Expr.filter.CHILD // remember that false/true cast respectively to 0/1 // xn + y // 将even,odd修正为xn+y,match[4]修正为+-x match[4] = +( match[4] ? match[5] + (match[6] || 1) : 2 * ( match[3] === "even" || match[3] === "odd" ) ); // 将match[5]替换为+-y match[5] = +( ( match[7] + match[8] ) || match[3] === "odd" ); // other types prohibit arguments // 除nth外其他类型禁止参数 } else if ( match[3] ) { Sizzle.error( match[0] ); } // match[0] :nth-child(-2n+1) // match[1] nth // match[2] child // match[3] -2n+1 // match[4] -2 // match[5] 1 // match[6] 2 // match[7] + // match[8] 1 return match; }, /** * match[1] :后伪类类型 * match[2] 伪类参数 * match[3] 参数中的‘或者" * match[4] 除去‘或"的伪类 */ "PSEUDO": function( match ) { var excess, unquoted = !match[5] && match[2]; //是CHILD伪类,返回null if ( matchExpr[ "CHILD"].test( match[0] ) ) { return null; } // Accept quoted arguments as-is // 参数有引号 //将match[2]替换为无引号的match[4]参数 if ( match[3] && match[4] !== undefined ) { match[2] = match[4]; // Strip excess characters from unquoted arguments // 除去带引号的参数的多余字符 } else if ( unquoted && rpseudo.test( unquoted ) && // Get excess from tokenize (recursively) //excess多余字符的长度 (excess = tokenize( unquoted, true )) && //excess多余参数的索引位置,excess是个负值,以便截取到多余字符之前 (excess = unquoted.indexOf( ")", unquoted.length - excess ) - unquoted.length) ) { // excess is a negative index match[0] = match[0].slice( 0, excess ); match[2] = unquoted.slice( 0, excess ); } // Return only captures needed by the pseudo filter method (type and argument) return match.slice( 0, 3 ); } }