sizzle源码分析 （1）sizzle架构

sizzle是jquery的核心，它用来选择匹配的元素，其代码包含在一个匿名函数中，并以window作为其上下文环境：

(function( window, undefined ) {

//此处为sizzle代码

})( window );

匿名函数体内，首先申明了很多变量，比如下边这些正则表达式：

classCache = createCache(),
    /*classCache:
    function cache( key, value ) {
        // Use (key + " ") to avoid collision with native prototype properties (see Issue #157)
        if ( keys.push( key += " " ) > Expr.cacheLength ) {
            // Only keep the most recent entries
            delete cache[ keys.shift() ];
        }
        return (cache[ key ] = value);
    }
    */
    tokenCache = createCache(),
    /*tokenCache:
    function cache( key, value ) {
        // Use (key + " ") to avoid collision with native prototype properties (see Issue #157)
        if ( keys.push( key += " " ) > Expr.cacheLength ) {
            // Only keep the most recent entries
            delete cache[ keys.shift() ];
        }
        return (cache[ key ] = value);
    }
    */
    compilerCache = createCache(),
    /*compilerCache:
    function cache( key, value ) {
        // Use (key + " ") to avoid collision with native prototype properties (see Issue #157)
        if ( keys.push( key += " " ) > Expr.cacheLength ) {
            // Only keep the most recent entries
            delete cache[ keys.shift() ];
        }
        return (cache[ key ] = value);
    }
    */
    hasDuplicate = false,
    sortOrder = function( a, b ) {
        if ( a === b ) {
            hasDuplicate = true;
            return 0;
        }
        return 0;
    },
 
    // General-purpose constants
    strundefined = typeof undefined,
    MAX_NEGATIVE = 1 << 31,
 
    // Instance methods
    hasOwn = ({}).hasOwnProperty,
    arr = [],
    pop = arr.pop,
    push_native = arr.push,
    push = arr.push,
    slice = arr.slice,
    // Use a stripped-down indexOf if we can't use a native one
    indexOf = arr.indexOf || function( elem ) {
        var i = 0,
            len = this.length;
        for ( ; i < len; i++ ) {
            if ( this[i] === elem ) {
                return i;
            }
        }
        return -1;
    },
 
    booleans = "checked|selected|async|autofocus|autoplay|controls|defer|disabled|hidden|ismap|loop|multiple|open|readonly|required|scoped",
 
    // Regular expressions
 
    // Whitespace characters http://www.w3.org/TR/css3-selectors/#whitespace
    //匹配空白 水平制表符 回车 换行 换页
    whitespace = "[\\x20\\t\\r\\n\\f]",
    // http://www.w3.org/TR/css3-syntax/#characters
    //可以匹配 由\\. 或 单词字符(所有字母数字下划线) 或 汉字（包括汉字标点符号），这里也可以说是全角符号组成
    characterEncoding = "(?:\\\\.|[\\w-]|[^\\x00-\\xa0])+",
 
    // Loosely modeled on CSS identifier characters
    // An unquoted value should be a CSS identifier http://www.w3.org/TR/css3-selectors/#attribute-selectors
    // Proper syntax: http://www.w3.org/TR/CSS21/syndata.html#value-def-identifier
    //识别码
    identifier = characterEncoding.replace( "w", "w#" ),
 
    // Acceptable operators http://www.w3.org/TR/selectors/#attribute-selectors
    //attributes ="\[[\x20\t\r\n\f]*((?:\\.|[\w-]|[^\x00-\xa0])+)[\x20\t\r\n\f]*(?:([*^$|!~]?=)[\x20\t\r\n\f]*(?:(['"])((?:\\.|[^\\])*?)\3|((?:\\.|[\w#-]|[^\x00-\xa0])+)|)|)[\x20\t\r\n\f]*\]"
    //匹配属性 例如：[a="b"] [a=b] [a|='er']
    attributes = "\\[" + whitespace + "*(" + characterEncoding + ")" + whitespace +
        "*(?:([*^$|!~]?=)" + whitespace + "*(?:(['\"])((?:\\\\.|[^\\\\])*?)\\3|(" + identifier + ")|)|)" + whitespace + "*\\]",
 
    // Prefer arguments quoted,
    //   then not containing pseudos/brackets,
    //   then attribute selectors/non-parenthetical expressions,
    //   then anything else
    // These preferences are here to reduce the number of selectors
    //   needing tokenize in the PSEUDO preFilter
    pseudos = ":(" + characterEncoding + ")(?:\\(((['\"])((?:\\\\.|[^\\\\])*?)\\3|((?:\\\\.|[^\\\\()[\\]]|" + attributes.replace( 3, 8 ) + ")*)|.*)\\)|)",
 
    // Leading and non-escaped trailing whitespace, capturing some non-whitespace characters preceding the latter
    //匹配开始或结束的空白字符
    rtrim = new RegExp( "^" + whitespace + "+|((?:^|[^\\\\])(?:\\\\.)*)" + whitespace + "+$", "g" ),
    //匹配逗号
    rcomma = new RegExp( "^" + whitespace + "*," + whitespace + "*" ),
    //匹配组合器 包括> + ~ 及"[\\x20\\t\\r\\n\\f]"
    rcombinators = new RegExp( "^" + whitespace + "*([>+~]|" + whitespace + ")" + whitespace + "*" ),
    //兄弟节点？
    rsibling = new RegExp( whitespace + "*[+~]" ),
    //属性选择器的等号后边部分，如：=aa]
    rattributeQuotes = new RegExp( "=" + whitespace + "*([^\\]'\"]*)" + whitespace + "*\\]", "g" ),
    //rpseudo=/:((?:\\.|[\w-]|[^\x00-\xa0])+)(?:\(((['"])((?:\\.|[^\\])*?)\3|((?:\\.|[^\\()[\]]|\[[\x20\t\r\n\f]*((?:\\.|[\w-]|[^\x00-\xa0])+)[\x20\t\r\n\f]*(?:([*^$|!~]?=)[\x20\t\r\n\f]*(?:(['"])((?:\\.|[^\\])*?)\8|((?:\\.|[\w#-]|[^\x00-\xa0])+)|)|)[\x20\t\r\n\f]*\])*)|.*)\)|)/
    //伪类选择器 如：:nth-child(3)
    rpseudo = new RegExp( pseudos ),
    //匹配识别码
    ridentifier = new RegExp( "^" + identifier + "$" ),
 
    matchExpr = {//匹配各种选择器的正则表达式
        "ID": new RegExp( "^#(" + characterEncoding + ")" ),//ID选择器
        "CLASS": new RegExp( "^\\.(" + characterEncoding + ")" ),//类
        "TAG": new RegExp( "^(" + characterEncoding.replace( "w", "w*" ) + ")" ),
        "ATTR": new RegExp( "^" + attributes ),
        "PSEUDO": new RegExp( "^" + pseudos ),
        "CHILD": new RegExp( "^:(only|first|last|nth|nth-last)-(child|of-type)(?:\\(" + whitespace +
            "*(even|odd|(([+-]|)(\\d*)n|)" + whitespace + "*(?:([+-]|)" + whitespace +
            "*(\\d+)|))" + whitespace + "*\\)|)", "i" ),
        "bool": new RegExp( "^(?:" + booleans + ")$", "i" ),
        // For use in libraries implementing .is()
        // We use this for POS matching in `select`
        "needsContext": new RegExp( "^" + whitespace + "*[>+~]|:(even|odd|eq|gt|lt|nth|first|last)(?:\\(" +
            whitespace + "*((?:-\\d)?\\d*)" + whitespace + "*\\)|)(?=[^-]|$)", "i" )
    },
    //检查是否原生代码
    rnative = /^[^{]+\{\s*\[native \w/,
 
    // Easily-parseable/retrievable ID or TAG or CLASS selectors
    rquickExpr = /^(?:#([\w-]+)|(\w+)|\.([\w-]+))$/,
    //匹配input元素，其实包含了四种：input|select|textarea|button
    rinputs = /^(?:input|select|textarea|button)$/i,
    rheader = /^h\d$/i,
 
    rescape = /'|\\/g,
 
    // CSS escapes http://www.w3.org/TR/CSS21/syndata.html#escaped-characters
    //匹配解码字符
    runescape = new RegExp( "\\\\([\\da-f]{1,6}" + whitespace + "?|(" + whitespace + ")|.)", "ig" ),
    funescape = function( _, escaped, escapedWhitespace ) {//_代表整个匹配项，escaped代表第一个匹配项，escapedWhitespace代表第二个分组匹配项，即空白匹配项
        var high = "0x" + escaped - 0x10000;
        // NaN means non-codepoint
        // Support: Firefox
        // Workaround erroneous numeric interpretation of +"0x"
        return high !== high || escapedWhitespace ?
            escaped :
            // BMP codepoint
            high < 0 ?
                String.fromCharCode( high + 0x10000 ) :
                // Supplemental Plane codepoint (surrogate pair)
                String.fromCharCode( high >> 10 | 0xD800, high & 0x3FF | 0xDC00 );
    };

接下来就是一些功能函数，下边这张图说明了其中的功能函数的作用：

 

最后把sizzle和jquery关联起来：

jQuery.find = Sizzle;

jQuery.expr = Sizzle.selectors;

jQuery.expr[":"] = jQuery.expr.pseudos;

jQuery.unique = Sizzle.uniqueSort;

jQuery.text = Sizzle.getText;

jQuery.isXMLDoc = Sizzle.isXML;

jQuery.contains = Sizzle.contains;