using makeComparator from acorn to generate functions that tests whether a

string is keyword, reserved etc.

speeds up the parser a bit, though not spectacular.. still far from acorn.

2 files changed, 63 insertions, 97 deletions

diff --git a/lib/parse.js b/lib/parse.js
index 65bde146..82fc2fd5 100644
--- a/lib/parse.js
+++ b/lib/parse.js
@@ -44,89 +44,24 @@
 
 "use strict";
 
-var KEYWORDS = array_to_hash([
-    "break",
-    "case",
-    "catch",
-    "const",
-    "continue",
-    "debugger",
-    "default",
-    "delete",
-    "do",
-    "else",
-    "finally",
-    "for",
-    "function",
-    "if",
-    "in",
-    "instanceof",
-    "new",
-    "return",
-    "switch",
-    "throw",
-    "try",
-    "typeof",
-    "var",
-    "void",
-    "while",
-    "with"
-]);
+var KEYWORDS = 'break case catch const continue debugger default delete do else finally for function if in instanceof new return switch throw try typeof var void while with';
+var KEYWORDS_ATOM = 'false null true';
+var RESERVED_WORDS = 'abstract boolean byte char class double enum export extends final float goto implements import int interface long native package private protected public short static super synchronized this throws transient volatile'
+    + " " + KEYWORDS_ATOM + " " + KEYWORDS;
+var KEYWORDS_BEFORE_EXPRESSION = 'return new delete throw else case';
 
-var RESERVED_WORDS = array_to_hash([
-    "abstract",
-    "boolean",
-    "byte",
-    "char",
-    "class",
-    "double",
-    "enum",
-    "export",
-    "extends",
-    "final",
-    "float",
-    "goto",
-    "implements",
-    "import",
-    "int",
-    "interface",
-    "long",
-    "native",
-    "package",
-    "private",
-    "protected",
-    "public",
-    "short",
-    "static",
-    "super",
-    "synchronized",
-    "throws",
-    "transient",
-    "volatile"
-]);
-
-var KEYWORDS_BEFORE_EXPRESSION = array_to_hash([
-    "return",
-    "new",
-    "delete",
-    "throw",
-    "else",
-    "case"
-]);
-
-var KEYWORDS_ATOM = array_to_hash([
-    "false",
-    "null",
-    "true"
-]);
+KEYWORDS = makePredicate(KEYWORDS);
+RESERVED_WORDS = makePredicate(RESERVED_WORDS);
+KEYWORDS_BEFORE_EXPRESSION = makePredicate(KEYWORDS_BEFORE_EXPRESSION);
+KEYWORDS_ATOM = makePredicate(KEYWORDS_ATOM);
 
-var OPERATOR_CHARS = array_to_hash(characters("+-*&%=<>!?|~^"));
+var OPERATOR_CHARS = makePredicate(characters("+-*&%=<>!?|~^"));
 
 var RE_HEX_NUMBER = /^0x[0-9a-f]+$/i;
 var RE_OCT_NUMBER = /^0[0-7]+$/;
 var RE_DEC_NUMBER = /^\d*\.?\d*(?:e[+-]?\d*(?:\d\.?|\.?\d)\d*)?$/i;
 
-var OPERATORS = array_to_hash([
+var OPERATORS = makePredicate([
     "in",
     "instanceof",
     "typeof",
@@ -173,13 +108,13 @@ var OPERATORS = array_to_hash([
     "||"
 ]);
 
-var WHITESPACE_CHARS = array_to_hash(characters(" \u00a0\n\r\t\f\u000b\u200b\u180e\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u202f\u205f\u3000"));
+var WHITESPACE_CHARS = makePredicate(characters(" \u00a0\n\r\t\f\u000b\u200b\u180e\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u202f\u205f\u3000"));
 
-var PUNC_BEFORE_EXPRESSION = array_to_hash(characters("[{(,.;:"));
+var PUNC_BEFORE_EXPRESSION = makePredicate(characters("[{(,.;:"));
 
-var PUNC_CHARS = array_to_hash(characters("[]{}(),;:"));
+var PUNC_CHARS = makePredicate(characters("[]{}(),;:"));
 
-var REGEXP_MODIFIERS = array_to_hash(characters("gmsiy"));
+var REGEXP_MODIFIERS = makePredicate(characters("gmsiy"));
 
 /* -----[ Tokenizer ]----- */
 
@@ -214,10 +149,7 @@ function is_unicode_connector_punctuation(ch) {
 
 function is_identifier(name) {
     return /^[a-z_$][a-z0-9_$]*$/i.test(name)
-        && name != "this"
-        && !KEYWORDS_ATOM[name]
-        && !RESERVED_WORDS[name]
-        && !KEYWORDS[name];
+        && !RESERVED_WORDS(name)
 };
 
 function is_identifier_start(ch) {
@@ -318,8 +250,8 @@ function tokenizer($TEXT, filename) {
 
     function token(type, value, is_comment) {
         S.regex_allowed = ((type == "operator" && !UNARY_POSTFIX[value]) ||
-                           (type == "keyword" && KEYWORDS_BEFORE_EXPRESSION[value]) ||
-                           (type == "punc" && PUNC_BEFORE_EXPRESSION[value]));
+                           (type == "keyword" && KEYWORDS_BEFORE_EXPRESSION(value)) ||
+                           (type == "punc" && PUNC_BEFORE_EXPRESSION(value)));
         var ret = {
             type   : type,
             value  : value,
@@ -343,7 +275,7 @@ function tokenizer($TEXT, filename) {
     };
 
     function skip_whitespace() {
-        while (WHITESPACE_CHARS[peek()])
+        while (WHITESPACE_CHARS(peek()))
             next();
     };
 
@@ -493,7 +425,7 @@ function tokenizer($TEXT, filename) {
                 backslash = false;
             }
         }
-        if (KEYWORDS[name] && escaped) {
+        if (KEYWORDS(name) && escaped) {
             hex = name.charCodeAt(0).toString(16).toUpperCase();
             name = "\\u" + "0000".substr(hex.length) + hex + name.slice(1);
         }
@@ -528,7 +460,7 @@ function tokenizer($TEXT, filename) {
         function grow(op) {
             if (!peek()) return op;
             var bigger = op + peek();
-            if (OPERATORS[bigger]) {
+            if (OPERATORS(bigger)) {
                 next();
                 return grow(bigger);
             } else {
@@ -563,12 +495,9 @@ function tokenizer($TEXT, filename) {
 
     function read_word() {
         var word = read_name();
-        return KEYWORDS_ATOM[word]
-            ? token("atom", word)
-            : !KEYWORDS[word]
-            ? token("name", word)
-            : OPERATORS[word]
-            ? token("operator", word)
+        return KEYWORDS_ATOM(word) ? token("atom", word)
+            : !KEYWORDS(word) ? token("name", word)
+            : OPERATORS(word) ? token("operator", word)
             : token("keyword", word);
     };
 
@@ -590,10 +519,10 @@ function tokenizer($TEXT, filename) {
         if (!ch) return token("eof");
         if (is_digit(ch)) return read_num();
         if (ch == '"' || ch == "'") return read_string();
-        if (PUNC_CHARS[ch]) return token("punc", next());
+        if (PUNC_CHARS(ch)) return token("punc", next());
         if (ch == ".") return handle_dot();
         if (ch == "/") return handle_slash();
-        if (OPERATOR_CHARS[ch]) return read_operator();
+        if (OPERATOR_CHARS(ch)) return read_operator();
         if (ch == "\\" || is_identifier_start(ch)) return read_word();
         parse_error("Unexpected character '" + ch + "'");
     };
diff --git a/lib/utils.js b/lib/utils.js
index 33dc8ff2..d18e62ee 100644
--- a/lib/utils.js
+++ b/lib/utils.js
@@ -214,3 +214,40 @@ function set_intersection(a, b) {
         return b.indexOf(el) >= 0;
     });
 };
+
+// this function is taken from Acorn [1], written by Marijn Haverbeke
+// [1] https://github.com/marijnh/acorn
+function makePredicate(words) {
+    if (!(words instanceof Array)) words = words.split(" ");
+    var f = "", cats = [];
+    out: for (var i = 0; i < words.length; ++i) {
+        for (var j = 0; j < cats.length; ++j)
+            if (cats[j][0].length == words[i].length) {
+                cats[j].push(words[i]);
+                continue out;
+            }
+        cats.push([words[i]]);
+    }
+    function compareTo(arr) {
+        if (arr.length == 1) return f += "return str === " + JSON.stringify(arr[0]) + ";";
+        f += "switch(str){";
+        for (var i = 0; i < arr.length; ++i) f += "case " + JSON.stringify(arr[i]) + ":";
+        f += "return true}return false;";
+    }
+    // When there are more than three length categories, an outer
+    // switch first dispatches on the lengths, to save on comparisons.
+    if (cats.length > 3) {
+        cats.sort(function(a, b) {return b.length - a.length;});
+        f += "switch(str.length){";
+        for (var i = 0; i < cats.length; ++i) {
+            var cat = cats[i];
+            f += "case " + cat[0].length + ":";
+            compareTo(cat);
+        }
+        f += "}";
+        // Otherwise, simply generate a flat `switch` statement.
+    } else {
+        compareTo(words);
+    }
+    return new Function("str", f);
+};