[Pkg-javascript-commits] [node-acorn-jsx] 12/484: Comment tokenizer
Bastien Roucariès
rouca at moszumanska.debian.org
Sat Aug 19 14:19:56 UTC 2017
This is an automated email from the git hooks/post-receive script.
rouca pushed a commit to branch master
in repository node-acorn-jsx.
commit 237bfbfb9b15f66d96dde2dce6367158da8d9b03
Author: Marijn Haverbeke <marijnh at gmail.com>
Date: Tue Oct 2 08:44:41 2012 +0200
Comment tokenizer
---
acorn.js | 1924 +++++++++++++++++++++++++++++++++++---------------------------
1 file changed, 1091 insertions(+), 833 deletions(-)
diff --git a/acorn.js b/acorn.js
index 5cfca5b..9d6e6ab 100644
--- a/acorn.js
+++ b/acorn.js
@@ -1,731 +1,358 @@
-// Some regexps (identifierchars, whitespace) and error message
-// strings from esprima(.org) by Ariya Hidayat.
+// Acorn is a tiny, fast JavaScript parser written in JavaScript.
+//
+// Acorn was written by Marijn Haverbeke and released under an MIT
+// license. The Unicode regexps (for identifiers and whitespace) were
+// taken from [Esprima](http://esprima.org) by Ariya Hidayat.
(function(exports) {
"strict mode";
exports.version = "0.0.1";
- // State variables
+ // The main exported interface (under `window.acorn` when in the
+ // browser) a `parse` function that takes a code string and returns
+ // an abstract syntax tree as specified by [Mozilla parser
+ // API][api], with the caveat that the SpiderMonkey-specific syntax
+ // (`let`, `yield`, inline XML, etc) is not recognized, and that
+ // range information is attached directly to the AST nodes as
+ // `start` and `end` properties, rather than wrapped in an
+ // additional object under a `loc` property.
+ //
+ // [api]: https://developer.mozilla.org/en-US/docs/SpiderMonkey/Parser_API
var options, input, inputLen;
- var next, last;
- var lastStart, lastEnd, lastCommentsAfter;
- var inFunction, labels, strict;
- // PARSER
+ exports.parse = function(inpt, opts) {
+ input = String(inpt); inputLen = input.length;
+ options = opts || {};
+ for (var opt in defaultOptions) if (!options.hasOwnProperty(opt))
+ options[opt] = defaultOptions[opt];
+ return parseTopLevel();
+ };
+
+ // A second optional argument can be given to further configure
+ // the parser process. These options are recognized:
var defaultOptions = exports.defaultOptions = {
+ // `ecmaVersion` indicates the ECMAScript version to parse. Must
+ // be either 3 or 5. This
+ // influences support for strict mode, the set of reserved words, and
+ // support for getters and setter.
ecmaVersion: 5,
+ // Turn on `strictSemicolons` to prevent the parser from doing
+ // automatic semicolon insertion.
strictSemicolons: false,
+ // When `allowTrailingCommas` is false, the parser will not allow
+ // trailing commas in array and object literals.
allowTrailingCommas: true,
+ // By default, reserved words are not enforced. Enable
+ // `forbidReserved` to enforce them.
forbidReserved: false,
+ // When `trackComments` is turned on, the parser will attach
+ // `commentsBefore` and `commentsAfter` properties to AST nodes
+ // holding arrays of strings. A single comment may appear in both
+ // a `commentsBefore` and `commentsAfter` array (of the nodes
+ // after and before it), but never twice in the before (or after)
+ // array of different nodes.
trackComments: false,
+ // By default, the `start` and `end` properties attached to nodes hold
+ // offsets into the file. When `linePositions` is on, they will hold
+ // `{offset, line, column}` (with line being 1-based and column
+ // 0-based) instead.
linePositions: false
};
- function next() {
- lastStart = tokStart;
- lastEnd = tokEnd;
- lastCommentsAfter = tokCommentsAfter;
- readToken();
- }
-
- function setStrict(strct) {
- strict = strct;
- tokPos = options.linePositions ? lastEnd.offset : lastEnd;
- skipSpace();
- readToken();
- }
+ // The `getLineInfo` function is mostly useful when the
+ // `linePositions` option is off (for performance reasons) and you
+ // want to find the line/column position for a given character
+ // offset. `input` should be the code string that the offset refers
+ // into.
- function startNode() {
- var node = {type: null, start: tokStart};
- if (options.trackComments && tokCommentsBefore) {
- node.commentsBefore = tokCommentsBefore;
- tokCommentsBefore = null;
+ var getLineInfo = exports.getLineInfo = function(input, offset) {
+ for (var line = 1, cur = 0;;) {
+ lineBreak.lastIndex = cur;
+ var match = lineBreak.exec(input);
+ if (match && match.index < offset) {
+ ++line;
+ cur = match.index + match[0].length;
+ } else break;
}
- return node;
- }
+ return {line: line, column: offset - cur};
+ };
- function startNodeFrom(other) {
- var node = {type: null, start: other.start};
- if (other.commentsBefore) {
- node.commentsBefore = other.commentsBefore;
- other.commentsBefore = null;
- }
- return node;
- }
+ // Acorn is organized as a tokenizer and a recursive-descent parser.
+ // Both use (closure-)global variables to keep their state and
+ // communicate. We already saw the `options`, `input`, and
+ // `inputLen` variables above (set in `parse`).
- function finishNode(node, type) {
- if (type != null) node.type = type;
- node.end = lastEnd;
- if (options.trackComments && lastCommentsAfter)
- node.commentsAfter = tokCommentsAfter;
- return node;
- }
+ // The current position of the tokenizer in the input.
- exports.parse = function(inpt, opts) {
- input = String(inpt); inputLen = input.length;
- options = opts || {};
- for (var opt in defaultOptions) if (!options.hasOwnProperty(opt))
- options[opt] = defaultOptions[opt];
- initTokenState();
- lastStart = lastEnd = options.linePositions ? curLinePos() : tokPos;
- lastCommentsAfter = inFunction = strict = null;
- labels = [];
- readToken();
+ var tokPos;
- var node = startNode(), first = true;
- node.body = [];
- while (tokType !== _eof) {
- var stmt = parseStatement();
- node.body.push(stmt);
- if (first && isUseStrict(stmt)) setStrict(true);
- first = false;
- }
- return finishNode(node, "Program");
- };
+ // The start and end positions of the current token. These hold
+ // integers when `options.linePositions` is false, and objects
+ // otherwise.
- function isUseStrict(stmt) {
- return stmt.type === "ExpressionStatement" && stmt.expression.type === "Literal" &&
- stmt.expression.value === "use strict";
- }
+ var tokStart, tokEnd;
- function eat(type) {
- if (tokType === type) {
- next();
- return true;
- }
- }
+ // The type and value of the current token. Token types are objects,
+ // named by variables against which they can be compared, and
+ // holding properties that describe them (indicating, for example,
+ // the precedence of an infix operator, and the original name of a
+ // keyword token). The kind of value that's held in `tokVal` depends
+ // on the type of the token. For literals, it is the literal value,
+ // for operators, the operator name, and so on.
- function canInsertSemicolon() {
- return tokType === _eof || tokType === _braceR ||
- !options.strictSemicolons &&
- newline.test(options.linePositions ? input.slice(lastEnd.offset, tokStart.offset)
- : input.slice(lastEnd, tokStart));
- }
+ var tokType, tokVal;
- function semicolon() {
- if (!eat(_semi) && !canInsertSemicolon()) unexpected();
- }
+ // These are used to hold arrays of comments when
+ // `options.trackComments` is true.
- function expect(type) {
- if (tokType === type) next();
- else unexpected();
- }
+ var tokCommentsBefore, tokCommentsAfter;
- function unexpected() {
- raise(tokStart, "Unexpected token");
- }
+ // Interal state for the tokenizer. To distinguish between division
+ // operators and regular expressions, it remembers whether the last
+ // token was one that is allowed to be followed by an expression.
+ // (If it is, a slash is probably a regexp, if it isn't it's a
+ // division operator. See the `parseStatement` function for a
+ // caveat.)
- function parseStatement() {
- // if expecting a statement and found a slash as operator,
- // it must be a literal regexp.
- if (tokType === _slash)
- readToken(true);
+ var tokRegexpAllowed, tokComments;
- var starttype = tokType, node = startNode();
+ // When `options.linePositions` is true, these are used to keep
+ // track of the current line, and know when a new line has been
+ // entered. See the `curLinePos` function.
- switch (starttype) {
- case _break: case _continue:
- next();
- var isBreak = starttype === _break;
- if (eat(_semi) || canInsertSemicolon()) node.label = null;
- else if (tokType !== _name) unexpected();
- else {
- node.label = parseIdent();
- semicolon();
- }
- for (var i = 0; i < labels.length; ++i) {
- var lab = labels[i];
- if ((node.label == null || lab.name === node.label.name) &&
- lab.kind != null && (isBreak || lab.kind === "loop")) break;
- }
- if (i === labels.length) raise(node.start, "Unsyntactic " + starttype.keyword);
- return finishNode(node, isBreak ? "BreakStatement" : "ContinueStatement");
+ var tokCurLine, tokLineStart, tokLineStartNext;
- case _debugger:
- next();
- return finishNode(node, "DebuggerStatement");
+ // These store the position of the previous token, which is useful
+ // when finishing a node and assigning its `end` position.
- case _do:
- next();
- labels.push({kind: "loop"});
- node.body = parseStatement();
- labels.pop();
- expect(_while);
- node.test = parseParenExpression();
- return finishNode(node, "DoWhileStatement");
+ var lastStart, lastEnd;
- case _for:
- next();
- expect(_parenL);
- if (tokType === _semi) return parseFor(node, null);
- if (tokType === _var) {
- var init = startNode();
- next();
- parseVar(init, true);
- if (init.declarations.length === 1 && eat(_in))
- return parseForIn(node, init);
- return parseFor(node, init);
- }
- var init = parseExpression(false, true);
- if (eat(_in)) {checkLVal(init); return parseForIn(node, init);}
- return parseFor(node, init);
+ // This is the parser's state. `inFunction` is used to reject
+ // `return` statements outside of functions, `labels` to verify that
+ // `break` and `continue` have somewhere to jump to, and `strict`
+ // indicates whether strict mode is on.
- case _function:
- next();
- return parseFunction(node, true);
+ var inFunction, labels, strict;
- case _if:
- next();
- node.test = parseParenExpression();
- node.consequent = parseStatement();
- node.alternate = eat(_else) ? parseStatement() : null;
- return finishNode(node, "IfStatement");
+ // This function is used to raise exceptions on parse errors. It
+ // takes either a `{line, column}` object or an offset integer (into
+ // the current `input`) as `pos` argument. It attaches the position
+ // to the end of the error message, and then raises a `SyntaxError`
+ // with that message.
- case _return:
- if (!inFunction) raise(tokStart, "'return' outside of function");
- next();
- if (eat(_semi) || canInsertSemicolon()) node.argument = null;
- else { node.argument = parseExpression(); semicolon(); }
- return finishNode(node, "ReturnStatement");
+ function raise(pos, message) {
+ if (typeof pos == "number") pos = getLineInfo(input, pos);
+ message += " (" + pos.line + ":" + pos.column + ")";
+ throw new SyntaxError(message);
+ }
- case _switch:
- next();
- node.discriminant = parseParenExpression();
- node.cases = [];
- expect(_braceL);
- labels.push({kind: "switch"});
- for (var cur, sawDefault; !eat(_braceR);) {
- if (tokType === _case || tokType === _default) {
- var isCase = tokType === _case;
- if (cur) finishNode(cur, "SwitchCase");
- node.cases.push(cur = startNode());
- cur.consequent = [];
- next();
- if (isCase) cur.test = parseExpression();
- else {
- if (sawDefault) raise(lastStart, "Multiple default clauses"); sawDefault = true;
- cur.test = null;
- }
- expect(_colon);
- } else {
- if (!cur) unexpected();
- cur.consequent.push(parseStatement());
- }
- }
- if (cur) finishNode(cur, "SwitchCase");
- labels.pop();
- return finishNode(node, "SwitchStatement");
+ // ## Token types
- case _throw:
- next();
- node.argument = parseExpression();
- return finishNode(node, "ThrowStatement");
+ // The assignment of fine-grained, information-carrying type objects
+ // allows the tokenizer to store the information it has about a
+ // token in a way that is very cheap for the parser to look up.
- case _try:
- next();
- node.block = parseBlock();
- node.handlers = [];
- while (tokType === _catch) {
- var clause = startNode();
- next();
- expect(_parenL);
- clause.param = parseIdent();
- if (strict && isStrictBadIdWord(clause.param.name))
- raise(clause.param.start, "Binding " + clause.param.name + " in strict mode");
- expect(_parenR);
- clause.guard = null;
- clause.body = parseBlock();
- node.handlers.push(finishNode(clause, "CatchClause"));
- }
- node.finalizer = eat(_finally) ? parseBlock() : null;
- if (!node.handlers.length && !node.finalizer)
- raise(node.start, "Missing catch or finally clause");
- return finishNode(node, "TryStatement");
+ // All token type variables start with an underscore, to make them
+ // easy to recognize.
- case _var:
- next();
- node = parseVar(node);
- semicolon();
- return node;
+ // These are the general types. The `type` property is only used to
+ // make them recognizeable when debugging.
- case _while:
- next();
- node.test = parseParenExpression();
- labels.push({kind: "loop"});
- node.body = parseStatement();
- labels.pop();
- return finishNode(node, "WhileStatement");
+ var _num = {type: "num"}, _regexp = {type: "regexp"}, _string = {type: "string"};
+ var _name = {type: "name"}, _eof = {type: "eof"};
- case _with:
- if (strict) raise(tokStart, "'with' in strict mode");
- next();
- node.object = parseParenExpression();
- node.body = parseStatement();
- return finishNode(node, "WithStatement");
+ // Keyword tokens. The `keyword` property (also used in keyword-like
+ // operators) indicates that the token originated from an
+ // identifier-like word, which is used when parsing property names.
+ //
+ // The `beforeExpr` property is used to disambiguate between regular
+ // expressions and divisions. It is set on all token types that can
+ // be followed by an expression (thus, a slash after them would be a
+ // regular expression).
+ //
+ // `isLoop` marks a keyword as starting a loop, which is important
+ // to know when parsing a label, in order to allow or disallow
+ // continue jumps to that label.
- case _braceL:
- return parseBlock();
+ var _break = {keyword: "break"}, _case = {keyword: "case", beforeExpr: true}, _catch = {keyword: "catch"};
+ var _continue = {keyword: "continue"}, _debugger = {keyword: "debugger"}, _default = {keyword: "default"};
+ var _do = {keyword: "do", isLoop: true}, _else = {keyword: "else", beforeExpr: true};
+ var _finally = {keyword: "finally"}, _for = {keyword: "for", isLoop: true}, _function = {keyword: "function"};
+ var _if = {keyword: "if"}, _return = {keyword: "return", beforeExpr: true}, _switch = {keyword: "switch"};
+ var _throw = {keyword: "throw", beforeExpr: true}, _try = {keyword: "try"}, _var = {keyword: "var"};
+ var _while = {keyword: "while", isLoop: true}, _with = {keyword: "with"}, _new = {keyword: "new", beforeExpr: true};
- case _semi:
- next();
- return finishNode(node, "EmptyStatement");
+ // The keywords that denote values.
- default:
- var maybeName = tokVal, expr = parseExpression();
- if (starttype === _name && expr.type === "Identifier" && eat(_colon)) {
- for (var i = 0; i < labels.length; ++i)
- if (labels[i].name === maybeName) raise(expr.start, "Label '" + maybeName + "' is already declared");
- var kind = tokType.isLoop ? "loop" : tokType === _switch ? "switch" : null;
- labels.push({name: maybeName, kind: kind});
- node.body = parseStatement();
- node.label = expr;
- return finishNode(node, "LabeledStatement");
- } else {
- node.expression = expr;
- semicolon();
- return finishNode(node, "ExpressionStatement");
- }
- }
- }
+ var _null = {keyword: "null", atomValue: null}, _true = {keyword: "true", atomValue: true};
+ var _false = {keyword: "false", atomValue: false};
- function parseParenExpression() {
- expect(_parenL);
- var val = parseExpression();
- expect(_parenR);
- return val;
- }
+ // Some keywords are treated as regular operators. `in` sometimes
+ // (when parsing `for`) needs to be tested against specifically, so
+ // we assign a variable name to it for quick comparing.
- function parseBlock(allowStrict) {
- var node = startNode(), first = true, strict = false, oldStrict;
- node.body = [];
- expect(_braceL);
- while (!eat(_braceR)) {
- var stmt = parseStatement();
- node.body.push(stmt);
- if (first && isUseStrict(stmt)) {
- oldStrict = strict;
- setStrict(strict = true);
- }
- first = false
- }
- if (strict && !oldStrict) setStrict(false);
- return finishNode(node, "BlockStatement");
- }
+ var _in = {keyword: "in", binop: 7, beforeExpr: true};
- function parseFor(node, init) {
- node.init = init;
- expect(_semi);
- node.test = tokType === _semi ? null : parseExpression();
- expect(_semi);
- node.update = tokType === _parenR ? null : parseExpression();
- expect(_parenR);
- labels.push({kind: "loop"});
- node.body = parseStatement();
- labels.pop();
- return finishNode(node, "ForStatement");
- }
+ // Map keyword names to token types.
- function parseForIn(node, init) {
- node.left = init;
- node.right = parseExpression();
- expect(_parenR);
- labels.push({kind: "loop"});
- node.body = parseStatement();
- labels.pop();
- return finishNode(node, "ForInStatement");
- }
+ var keywordTypes = {"break": _break, "case": _case, "catch": _catch,
+ "continue": _continue, "debugger": _debugger, "default": _default,
+ "do": _do, "else": _else, "finally": _finally, "for": _for,
+ "function": _function, "if": _if, "return": _return, "switch": _switch,
+ "throw": _throw, "try": _try, "var": _var, "while": _while, "with": _with,
+ "null": _null, "true": _true, "false": _false, "new": _new, "in": _in,
+ "instanceof": {keyword: "instanceof", binop: 7},
+ "typeof": {keyword: "typeof", prefix: true},
+ "void": {keyword: "void", prefix: true},
+ "delete": {keyword: "delete", prefix: true}};
- function parseVar(node, noIn) {
- node.declarations = [];
- node.kind = "var";
- for (;;) {
- var decl = startNode();
- decl.id = parseIdent();
- if (strict && isStrictBadIdWord(decl.id.name))
- raise(decl.id.start, "Binding " + decl.id.name + " in strict mode");
- decl.init = eat(_eq) ? parseExpression(true, noIn) : null;
- node.declarations.push(finishNode(decl, "VariableDeclarator"));
- if (!eat(_comma)) break;
- }
- return finishNode(node, "VariableDeclaration");
- }
+ // Punctuation token types. Again, the `type` property is purely for debugging.
- function parsePropertyName() {
- if (tokType === _num || tokType === _string) return parseExprAtom();
- return parseIdent(true);
- }
+ var _bracketL = {type: "[", beforeExpr: true}, _bracketR = {type: "]"}, _braceL = {type: "{", beforeExpr: true};
+ var _braceR = {type: "}"}, _parenL = {type: "(", beforeExpr: true}, _parenR = {type: ")"};
+ var _comma = {type: ",", beforeExpr: true}, _semi = {type: ";", beforeExpr: true};
+ var _colon = {type: ":", beforeExpr: true}, _dot = {type: "."}, _question = {type: "?", beforeExpr: true};
- function parseIdent(liberal) {
- var node = startNode();
- if (tokType !== _name) {
- if (liberal && tokType.keyword) node.name = tokType.keyword;
- else unexpected();
- } else node.name = tokVal;
- next();
- return finishNode(node, "Identifier");
- }
+ // Operators. These carry several kinds of properties to help the
+ // parser use them properly (the presence of these properties is
+ // what categorizes them as operators).
+ //
+ // `binop`, when present, specifies that this operator is a binary
+ // operator, and will refer to its precedence.
+ //
+ // `prefix` and `postfix` mark the operator as a prefix or postfix
+ // unary operator. `isUpdate` specifies that the node produced by
+ // the operator should be of type UpdateExpression rather than
+ // simply UnaryExpression (`++` and `--`).
+ //
+ // `isAssign` marks all of `=`, `+=`, `-=` etcetera, which act as
+ // binary operators with a very low precedence, that should result
+ // in AssignmentExpression nodes.
- function parseFunction(node, isStatement) {
- if (tokType === _name) node.id = parseIdent();
- else if (isStatement) unexpected();
- else node.id = null;
- node.params = [];
- var first = true;
- expect(_parenL);
- while (!eat(_parenR)) {
- if (!first) expect(_comma); else first = false;
- node.params.push(parseIdent());
- }
+ var _slash = {binop: 10, beforeExpr: true}, _eq = {isAssign: true, beforeExpr: true};
+ var _assign = {isAssign: true, beforeExpr: true}, _plusmin = {binop: 9, prefix: true, beforeExpr: true};
+ var _incdec = {postfix: true, prefix: true, isUpdate: true}, _prefix = {prefix: true, beforeExpr: true};
+ var _bin1 = {binop: 1, beforeExpr: true}, _bin2 = {binop: 2, beforeExpr: true};
+ var _bin3 = {binop: 3, beforeExpr: true}, _bin4 = {binop: 4, beforeExpr: true};
+ var _bin5 = {binop: 5, beforeExpr: true}, _bin6 = {binop: 6, beforeExpr: true};
+ var _bin7 = {binop: 7, beforeExpr: true}, _bin8 = {binop: 8, beforeExpr: true};
+ var _bin10 = {binop: 10, beforeExpr: true};
- var oldInFunc = inFunction, oldLabels = labels;
- inFunction = true; labels = [];
- node.body = parseBlock(true);
- if (strict || node.body.body.length && isUseStrict(node.body.body[0])) {
- for (var i = node.id ? -1 : 0; i < node.params.length; ++i) {
- var id = i < 0 ? node.id : node.params[i];
- if (isStrictReservedWord(id.name) || isStrictBadIdWord(id.name))
- raise(id.start, "Defining '" + id.name + "' in strict mode");
- if (i >= 0) for (var j = 0; j < i; ++j) if (id.name === node.params[j].name)
- raise(id.start, "Argument name clash in strict mode");
- }
+ // This is a trick taken from Esprima. It turns out that, on
+ // non-Chrome browsers, to check whether a string is in a set, a
+ // predicate containing a big ugly `switch` statement is faster than
+ // a regular expression, and on Chrome the two are about on par.
+ // This function uses `eval` (non-lexical) to produce such a
+ // predicate from a space-separated string of words.
+ //
+ // It starts by sorting the words by length.
+
+ function makePredicate(words) {
+ words = words.split(" ");
+ var f = "(function(str){", 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;";
}
- inFunction = oldInFunc; labels = oldLabels;
- return finishNode(node, isStatement ? "FunctionDeclaration" : "FunctionExpression");
- }
+ // When there are more than three length categories, an outer
+ // switch first dispatches on the lengths, to save on comparisons.
- // EXPRESSION PARSING
+ 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 += "}";
- function parseExprList(close, allowTrailingComma, allowEmpty) {
- var elts = [], first = true;
- while (!eat(close)) {
- if (!first) {
- expect(_comma);
- if (allowTrailingComma && options.allowTrailingCommas && eat(close)) break;
- } else first = false;
+ // Otherwise, simply generate a flat `switch` statement.
- if (allowEmpty && tokType === _comma) elts.push(null);
- else elts.push(parseExpression(true));
+ } else {
+ compareTo(words);
}
- return elts;
+ return (1, eval)(f + "})");
}
- function parseNew() {
- var node = startNode();
- next();
- node.callee = parseSubscripts(parseExprAtom(false), false);
- if (eat(_parenL)) node.arguments = parseExprList(_parenR, false);
- else node.arguments = [];
- return finishNode(node, "NewExpression");
- }
+ // The ECMAScript 3 reserved word list.
- function parseObj() {
- var node = startNode(), first = true;
- node.properties = [];
- next();
- while (!eat(_braceR)) {
- if (!first) {
- expect(_comma);
- if (options.allowTrailingCommas && eat(_braceR)) break;
- } else first = false;
+ var isReservedWord3 = makePredicate("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 prop = {key: parsePropertyName()}, isGetSet, kind;
- if (eat(_colon)) {
- prop.value = parseExpression(true);
- kind = prop.kind = "init";
- } else if (options.ecmaVersion >= 5 && prop.key.type === "Identifier" &&
- (prop.key.name === "get" || prop.key.name === "set")) {
- isGetSet = true;
- kind = prop.kind = prop.key.name;
- prop.key = parsePropertyName();
- if (!tokType === _parenL) unexpected();
- prop.value = parseFunction(startNode(), false);
- } else unexpected();
- if (prop.key.type === "Identifier" && (strict || isGetSet)) {
- for (var i = 0; i < node.properties.length; ++i) {
- var other = node.properties[i];
- if (other.key.name === prop.key.name) {
- var conflict = kind == other.kind || isGetSet && other.kind === "init" ||
- kind === "init" && (other.kind === "get" || other.kind === "set");
- if (conflict && !strict && kind === "init" && other.kind === "init") conflict = false;
- if (conflict) raise(prop.key.start, "Redefinition of property");
- }
- }
- }
- node.properties.push(prop);
- }
- return finishNode(node, "ObjectExpression");
- }
+ // ECMAScript 5 reserved words.
- function parseExprAtom() {
- switch (tokType) {
- case _name:
- if (tokVal === "this") {
- var node = startNode();
- next();
- return finishNode(node, "ThisExpression");
- } else return parseIdent();
+ var isReservedWord5 = makePredicate("class enum extends super const export import");
- case _num: case _string: case _regexp:
- var node = startNode();
- node.value = tokVal;
- next();
- return finishNode(node, "Literal");
+ // The additional reserved words in strict mode.
- case _null: case _true: case _false:
- var node = startNode();
- node.value = tokType.atomValue;
- next();
- return finishNode(node, "Literal");
+ var isStrictReservedWord = makePredicate("implements interface let package private protected public static yield");
- case _parenL:
- next();
- var val = parseExpression();
- expect(_parenR);
- return val;
+ // The forbidden variable names in strict mode.
- case _bracketL:
- var node = startNode();
- next();
- node.elements = parseExprList(_bracketR, true, true);
- return finishNode(node, "ArrayExpression");
+ var isStrictBadIdWord = makePredicate("eval arguments");
- case _braceL:
- return parseObj();
+ // And the keywords.
- case _function:
- var node = startNode();
- next();
- return parseFunction(node, false);
+ var isKeyword = makePredicate("break case catch continue debugger default do else finally for function if return switch throw try var while with null true false instanceof typeof void delete new in");
- case _new:
- return parseNew();
+ // ## Character categories
- default:
- unexpected();
- }
- }
+ // Big ugly regular expressions that match characters in the
+ // whitespace, identifier, and identifier-start categories. These
+ // are only applied when a character is found to actually have a
+ // code point above 128.
- function parseSubscripts(base, allowCalls) {
- if (eat(_dot)) {
- var node = startNodeFrom(base);
- node.object = base;
- node.property = parseIdent(true);
- node.computed = false;
- return parseSubscripts(finishNode(node, "MemberExpression"), allowCalls);
- } else if (eat(_bracketL)) {
- var node = startNodeFrom(base);
- node.object = base;
- node.property = parseExpression();
- node.computed = true;
- expect(_bracketR);
- return parseSubscripts(finishNode(node, "MemberExpression"), allowCalls);
- } else if (allowCalls && eat(_parenL)) {
- var node = startNodeFrom(base);
- node.callee = base;
- node.arguments = parseExprList(_parenR, false);
- return parseSubscripts(finishNode(node, "CallExpression"), allowCalls);
- } else return base;
- }
-
- function parseExprSubscripts(allowCalls) {
- return parseSubscripts(parseExprAtom(allowCalls), allowCalls);
- }
-
- function parseMaybeUnary(noIn) {
- if (tokType.prefix) {
- var node = startNode(), update = tokType.isUpdate;
- node.operator = tokVal;
- node.prefix = true;
- next();
- node.argument = parseMaybeUnary(noIn);
- if (update) checkLVal(node.argument);
- else if (strict && node.operator === "delete" &&
- node.argument.type === "Identifier")
- raise(node.start, "Deleting local variable in strict mode");
- return finishNode(node, update ? "UpdateExpression" : "UnaryExpression");
- }
- var expr = parseExprSubscripts(true);
- while (tokType.postfix && !canInsertSemicolon()) {
- var node = startNodeFrom(expr);
- node.operator = tokVal;
- node.prefix = false;
- node.argument = expr;
- checkLVal(expr);
- next();
- expr = finishNode(node, "UpdateExpression");
- }
- return expr;
- }
+ var nonASCIIwhitespace = /[\u1680\u180E\u2000-\u200A\u202F\u205F\u3000\uFEFF]/;
+ var nonASCIIidentifierStartChars = "\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0370-\u0374\u0376\u0377\u037a-\u037d\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u048a-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05d0-\u05ea\u05f0-\u05f2\u0620-\u064a\u066e\u066f\u0671-\u06d3\u06d5\u06e5\u06e6\u06ee\u06ef\u06fa-\u06fc\u06ff\u0710\u0712-\u072f\u074d-\u07a5\u07b1\u07ca-\u07ea\u07f4\u07f5\u07fa\u0800-\u0815\u081a\u0824\u0828\u0840-\u0858\u [...]
+ var nonASCIIidentifierChars = "\u0371-\u0374\u0483-\u0487\u0591-\u05bd\u05bf\u05c1\u05c2\u05c4\u05c5\u05c7\u0610-\u061a\u0620-\u0649\u0672-\u06d3\u06e7-\u06e8\u06fb-\u06fc\u0730-\u074a\u0800-\u0814\u081b-\u0823\u0825-\u0827\u0829-\u082d\u0840-\u0857\u08e4-\u08fe\u0900-\u0903\u093a-\u093c\u093e-\u094f\u0951-\u0957\u0962-\u0963\u0966-\u096f\u0981-\u0983\u09bc\u09be-\u09c4\u09c7\u09c8\u09d7\u09df-\u09e0\u0a01-\u0a03\u0a3c\u0a3e-\u0a42\u0a47\u0a48\u0a4b-\u0a4d\u0a51\u0a66-\u0a71\u0a75\u0a8 [...]
+ var nonASCIIidentifierStart = new RegExp("[" + nonASCIIidentifierStartChars + "]");
+ var nonASCIIidentifier = new RegExp("[" + nonASCIIidentifierStartChars + nonASCIIidentifierChars + "]");
- function parseExprOp(left, minPrec, noIn) {
- var prec = tokType.binop;
- if (prec != null && (!noIn || tokType !== _in)) {
- if (prec > minPrec) {
- var node = startNodeFrom(left);
- node.left = left;
- node.operator = tokVal;
- next();
- node.right = parseExprOp(parseMaybeUnary(noIn), prec, noIn);
- var node = finishNode(node, /&&|\|\|/.test(node.operator) ? "LogicalExpression" : "BinaryExpression");
- return parseExprOp(node, minPrec, noIn);
- }
- }
- return left;
- }
+ // Whether a single character denotes a newline.
- function parseExprOps(noIn) {
- return parseExprOp(parseMaybeUnary(noIn), -1, noIn);
- }
+ var newline = /[\n\r\u2028\u2029]/;
- function parseMaybeConditional(noIn) {
- var expr = parseExprOps(noIn);
- if (eat(_question)) {
- var node = startNodeFrom(expr);
- node.test = expr;
- node.consequent = parseExpression(true);
- expect(_colon);
- node.alternate = parseExpression(true, noIn);
- return finishNode(node, "ConditionalExpression");
- }
- return expr;
- }
+ // Matches a whole line break (where CRLF is considered a single
+ // line break). Used to count lines.
- function parseMaybeAssign(noIn) {
- var left = parseMaybeConditional(noIn);
- if (tokType.isAssign) {
- var node = startNodeFrom(left);
- node.operator = tokVal;
- node.left = left;
- next();
- node.right = parseMaybeAssign(noIn);
- checkLVal(left);
- return finishNode(node, "AssignmentExpression");
- }
- return left;
- }
+ var lineBreak = /\r\n?|[\n\r\u2028\u2029]/g;
- function parseExpression(noComma, noIn) {
- var expr = parseMaybeAssign(noIn);
- if (!noComma && tokType === _comma) {
- var node = startNodeFrom(expr);
- node.expressions = [expr];
- while (eat(_comma)) node.expressions.push(parseMaybeAssign(noIn));
- return finishNode(node, "SequenceExpression");
- }
- return expr;
- }
+ // Test whether a given character code starts an identifier.
- function checkLVal(expr) {
- if (expr.type !== "Identifier" && expr.type !== "MemberExpression")
- raise(expr.start, "Assigning to rvalue");
- if (strict && expr.type === "Identifier" && isStrictBadIdWord(expr.name))
- raise(expr.start, "Assigning to " + expr.name + " in strict mode");
+ function isIdentifierStart(code) {
+ return (code >= 65 && code <= 90) || (code >= 97 && code <= 122) ||
+ code === 36 || code === 95 ||
+ (code >= 0xaa && nonASCIIidentifierStart.test(String.fromCharCode(code)));
}
- // TOKENIZER DEFINITIONS
-
- // Token types
- var _name = {type: "name"}, _eof = {type: "eof"};
- var _num = {type: "num"}, _regexp = {type: "regexp"}, _string = {type: "string"};
-
- var _break = {keyword: "break"}, _case = {keyword: "case", beforeExpr: true}, _catch = {keyword: "catch"};
- var _continue = {keyword: "continue"}, _debugger = {keyword: "debugger"}, _default = {keyword: "default"};
- var _do = {keyword: "do", isLoop: true}, _else = {keyword: "else", beforeExpr: true};
- var _finally = {keyword: "finally"}, _for = {keyword: "for", isLoop: true}, _function = {keyword: "function"};
- var _if = {keyword: "if"}, _return = {keyword: "return", beforeExpr: true}, _switch = {keyword: "switch"};
- var _throw = {keyword: "throw", beforeExpr: true}, _try = {keyword: "try"}, _var = {keyword: "var"};
- var _while = {keyword: "while", isLoop: true}, _with = {keyword: "with"}, _new = {keyword: "new", beforeExpr: true};
- var _null = {keyword: "null", atomValue: null}, _true = {keyword: "true", atomValue: true};
- var _false = {keyword: "false", atomValue: false}, _in = {keyword: "in", binop: 7, beforeExpr: true};
- var keywordTypes = {"break": _break, "case": _case, "catch": _catch,
- "continue": _continue, "debugger": _debugger, "default": _default,
- "do": _do, "else": _else, "finally": _finally, "for": _for,
- "function": _function, "if": _if, "return": _return, "switch": _switch,
- "throw": _throw, "try": _try, "var": _var, "while": _while, "with": _with,
- "null": _null, "true": _true, "false": _false, "new": _new, "in": _in,
- "instanceof": {keyword: "instanceof", binop: 7},
- "typeof": {keyword: "typeof", prefix: true},
- "void": {keyword: "void", prefix: true},
- "delete": {keyword: "delete", prefix: true}};
- var isKeyword = makePredicate("break case catch continue debugger default do else finally for function if return switch throw try var while with null true false instanceof typeof void delete new in");
-
- var _bracketL = {type: "[", beforeExpr: true}, _bracketR = {type: "]"}, _braceL = {type: "{", beforeExpr: true};
- var _braceR = {type: "}"}, _parenL = {type: "(", beforeExpr: true}, _parenR = {type: ")"};
- var _comma = {type: ",", beforeExpr: true}, _semi = {type: ";", beforeExpr: true};
- var _colon = {type: ":", beforeExpr: true}, _dot = {type: "."}, _question = {type: "?", beforeExpr: true};
-
- var _slash = {binop: 10, beforeExpr: true}, _eq = {isAssign: true, beforeExpr: true};
- var _assign = {isAssign: true, beforeExpr: true}, _plusmin = {binop: 9, prefix: true, beforeExpr: true};
- var _incdec = {postfix: true, prefix: true, isUpdate: true}, _prefix = {prefix: true, beforeExpr: true};
- var _bin1 = {binop: 1, beforeExpr: true}, _bin2 = {binop: 2, beforeExpr: true};
- var _bin3 = {binop: 3, beforeExpr: true}, _bin4 = {binop: 4, beforeExpr: true};
- var _bin5 = {binop: 5, beforeExpr: true}, _bin6 = {binop: 6, beforeExpr: true};
- var _bin7 = {binop: 7, beforeExpr: true}, _bin8 = {binop: 8, beforeExpr: true};
- var _bin10 = {binop: 10, beforeExpr: true};
-
- var isReservedWord3 = makePredicate("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 isReservedWord5 = makePredicate("class enum extends super const export import");
-
- function isStrictBadIdWord(str) {
- return str === "eval" || str === "arguments";
- }
- var isStrictReservedWord = makePredicate("implements interface let package private protected public static yield");
+ // Test whether a given character is part of an identifier.
- function makePredicate(words) {
- words = words.split(" ");
- var f = "(function(str){", 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;";
- }
- 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 += "}";
- } else {
- compareTo(words);
- }
- return (1, eval)(f + "})");
+ function isIdentifierChar(ch) {
+ return ((ch >= "a" && ch <= "z") || (ch >= "A" && ch <= "Z") ||
+ (ch >= "0" && ch <= "9") || ch === "$" || ch === "_" ||
+ (ch >= "\xaa" && nonASCIIidentifier.test(ch)));
}
- // CHARACTER CATEGORIES
-
- var operatorChar = /[+\-\*\/&%=<>!|~^]/;
- var reModifiers = /^[gmsiy]*$/;
-
- var nonASCIIwhitespace = /[\u1680\u180E\u2000-\u200A\u202F\u205F\u3000\uFEFF]/;
- var nonASCIIidentifierStartChars = "\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\u02c1\u02c6-\u02d1\u02e0-\u02e4\u02ec\u02ee\u0370-\u0374\u0376\u0377\u037a-\u037d\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u048a-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05d0-\u05ea\u05f0-\u05f2\u0620-\u064a\u066e\u066f\u0671-\u06d3\u06d5\u06e5\u06e6\u06ee\u06ef\u06fa-\u06fc\u06ff\u0710\u0712-\u072f\u074d-\u07a5\u07b1\u07ca-\u07ea\u07f4\u07f5\u07fa\u0800-\u0815\u081a\u0824\u0828\u0840-\u0858\u [...]
- var nonASCIIidentifierChars = "\u0371-\u0374\u0483-\u0487\u0591-\u05bd\u05bf\u05c1\u05c2\u05c4\u05c5\u05c7\u0610-\u061a\u0620-\u0649\u0672-\u06d3\u06e7-\u06e8\u06fb-\u06fc\u0730-\u074a\u0800-\u0814\u081b-\u0823\u0825-\u0827\u0829-\u082d\u0840-\u0857\u08e4-\u08fe\u0900-\u0903\u093a-\u093c\u093e-\u094f\u0951-\u0957\u0962-\u0963\u0966-\u096f\u0981-\u0983\u09bc\u09be-\u09c4\u09c7\u09c8\u09d7\u09df-\u09e0\u0a01-\u0a03\u0a3c\u0a3e-\u0a42\u0a47\u0a48\u0a4b-\u0a4d\u0a51\u0a66-\u0a71\u0a75\u0a8 [...]
- var nonASCIIidentifierStart = new RegExp("[" + nonASCIIidentifierStartChars + "]");
- var nonASCIIidentifier = new RegExp("[" + nonASCIIidentifierStartChars + nonASCIIidentifierChars + "]");
- var newline = /[\n\r\u2028\u2029]/;
- var lineBreak = /\r\n?|[\n\r\u2028\u2029]/g;
-
- // TOKENIZER STATE
-
- var tokStart, tokEnd, tokType, tokVal, tokCommentsBefore, tokCommentsAfter;
+ // ## Tokenizer
- var tokPos, tokRegexpAllowed, tokComments;
- var tokCurLine, tokLineStart, tokLineStartNext;
+ // These are used when `options.linePositions` is on, in order to
+ // track the current line number and start of line offset, so that
+ // `tokStart` and `tokEnd` refer to position objects indead of
+ // integer offsets.
function nextLineStart() {
lineBreak.lastIndex = tokLineStart;
@@ -742,6 +369,8 @@
return {offset: tokPos, line: tokCurLine, column: tokPos - tokLineStart};
}
+ // Reset the token state. Used at the start of a parse.
+
function initTokenState() {
tokCurLine = 1;
tokPos = tokLineStart = 0;
@@ -751,6 +380,11 @@
skipSpace();
}
+ // Called at the end of every token. Sets `tokEnd`, `tokVal`,
+ // `tokCommentsAfter`, and `tokRegexpAllowed`, and skips the space
+ // after the token, so that the next one's `tokStart` will point at
+ // the right position.
+
function finishToken(type, val) {
tokEnd = options.linePositions ? curLinePos() : tokPos;
tokType = type;
@@ -760,19 +394,7 @@
tokRegexpAllowed = type.beforeExpr;
}
- var getLineInfo = exports.getLineInfo = function(input, pos) {
- for (var line = 1, cur = 0;;) {
- lineBreak.lastIndex = cur;
- var match = lineBreak.exec(input);
- if (match && match.index < pos) {
- ++line;
- cur = match.index + match[0].length;
- } else break;
- }
- return {line: line, column: pos - cur};
- };
-
- function readBlockComment() {
+ function skipBlockComment() {
var end = input.indexOf("*/", tokPos += 2);
if (end === -1) raise(tokPos - 2, "Unterminated comment");
if (options.trackComments)
@@ -780,7 +402,7 @@
tokPos = end + 2;
}
- function readLineComment() {
+ function skipLineComment() {
var start = tokPos;
tokPos += 2;
while (tokPos < inputLen && !newline.test(input.charAt(tokPos))) ++tokPos;
@@ -788,6 +410,10 @@
(tokComments || (tokComments = [])).push(input.slice(start, tokPos));
}
+ // Called at the start of the parse and after every token. Skips
+ // whitespace and comments, and, if `options.trackComments` is on,
+ // will store all skipped comments in `tokComments`.
+
function skipSpace() {
tokComments = null;
while (tokPos < inputLen) {
@@ -795,9 +421,9 @@
if (ch === "/") {
var nextCh = input.charAt(tokPos+1);
if (nextCh === "*") {
- readBlockComment();
+ skipBlockComment();
} else if (nextCh === "/") {
- readLineComment();
+ skipLineComment();
} else break;
} else if (ch === " " || ch === '\t' || ch === "\n" || ch === "\r" || ch === "\f" ||
ch === "\xa0" || ch === "\x0b" || (ch >= "\u1680" && nonASCIIwhitespace.test(ch))) {
@@ -808,7 +434,17 @@
}
}
- // TOKENIZER READING
+ // ### Token reading
+
+ // This is the function that is called to fetch the next token. It
+ // is somewhat obscure, because it works in character codes rather
+ // than characters, and because operator parsing has been inlined
+ // into it.
+ //
+ // All in the name of speed.
+ //
+ // The `forceRegexp` parameter is used in the one case where the
+ // `tokRegexpAllowed` trick does not work. See `parseStatement`.
function readToken(forceRegexp) {
tokStart = options.linePositions ? curLinePos() : tokPos;
@@ -816,14 +452,21 @@
if (forceRegexp) return readRegexp();
if (tokPos >= inputLen) return finishToken(_eof);
- var code = input.charCodeAt(tokPos), next = input.charCodeAt(tokPos+1);
- if (isIdentifierStart(code) || code === 92) return readWord();
+ var code = input.charCodeAt(tokPos);
+ // Identifier or keyword. '\uXXXX' sequences are allowed in
+ // identifiers, so '\' also dispatches to that.
+ if (isIdentifierStart(code) || code === 92 /* '\' */) return readWord();
+ var next = input.charCodeAt(tokPos+1);
switch(code) {
+ // The interpretation of a dot depends on whether it is followed
+ // by a digit.
case 46: // '.'
if (next >= 48 && next <= 57) return readNumber(String.fromCharCode(code));
++tokPos;
return finishToken(_dot);
+
+ // Punctuation tokens.
case 40: ++tokPos; return finishToken(_parenL);
case 41: ++tokPos; return finishToken(_parenR);
case 59: ++tokPos; return finishToken(_semi);
@@ -834,13 +477,23 @@
case 125: ++tokPos; return finishToken(_braceR);
case 58: ++tokPos; return finishToken(_colon);
case 63: ++tokPos; return finishToken(_question);
- case 48: case 49: case 50: case 51: case 52: case 53: case 54: case 55: case 56: case 57: // 0-9
- if (code === 48 && (next === 120 || next === 88)) return readHexNumber();
+
+ // '0x' is a hexadecimal number.
+ case 48: // '0'
+ if (next === 120 || next === 88) return readHexNumber();
+ // Anything else beginning with a digit is an integer, octal
+ // number, or float.
+ case 49: case 50: case 51: case 52: case 53: case 54: case 55: case 56: case 57: // 1-9
return readNumber(String.fromCharCode(code));
+
+ // Quotes produce strings.
case 34: case 39: // '"', "'"
return readString(String.fromCharCode(code));
- // Operators
+ // Operators are parsed inline in tiny state machines. '=' (61) is
+ // often referred to. `finishOp` simply skips the amount of
+ // characters it is given as second argument, and returns a token
+ // of the type given by its first argument.
case 47: // '/'
if (tokRegexpAllowed) {++tokPos; return readRegexp();}
@@ -885,205 +538,810 @@
return finishOp(_prefix, 1);
}
- var ch = String.fromCharCode(code);
- if (ch === "\\" || nonASCIIidentifierStart.test(ch)) return readWord();
- raise(tokPos, "Unexpected character '" + ch + "'");
- }
+ // If we are here, we either found a non-ASCII identifier
+ // character, or something that's entirely disallowed.
+ var ch = String.fromCharCode(code);
+ if (ch === "\\" || nonASCIIidentifierStart.test(ch)) return readWord();
+ raise(tokPos, "Unexpected character '" + ch + "'");
+ }
+
+ function finishOp(type, size) {
+ var str = input.slice(tokPos, tokPos + size);
+ tokPos += size;
+ finishToken(type, str);
+ }
+
+ // Parse a regular expression. Some context-awareness is necessary,
+ // since a '/' inside a '[]' set does not end the expression.
+
+ function readRegexp() {
+ var content = "", escaped, inClass, start = tokPos;
+ for (;;) {
+ if (tokPos >= inputLen) raise(start, "Unterminated regular expression");
+ var ch = input.charAt(tokPos);
+ if (newline.test(ch)) raise(start, "Unterminated regular expression");
+ if (!escaped) {
+ if (ch === "[") inClass = true;
+ else if (ch === "]" && inClass) inClass = false;
+ else if (ch === "/" && !inClass) break;
+ escaped = ch === "\\";
+ } else escaped = false;
+ ++tokPos;
+ }
+ var content = input.slice(start, tokPos);
+ ++tokPos;
+ // Need to use `readWord1` because '\uXXXX' sequences are allowed
+ // here (don't ask).
+ var mods = readWord1();
+ if (mods && !/^[gmsiy]*$/.test(mods)) raise(start, "Invalid regexp flag");
+ return finishToken(_regexp, new RegExp(content, mods));
+ }
+
+ // Read an integer in the given radix. Return null if zero digits
+ // were read, the integer value otherwise. When `len` is given, this
+ // will return `null` unless the integer has exactly `len` digits.
+
+ function readInt(radix, len) {
+ var start = tokPos, total = 0;
+ for (;;) {
+ var code = input.charCodeAt(tokPos), val;
+ if (code >= 97) val = code - 97 + 10; // a
+ else if (code >= 65) val = code - 65 + 10; // A
+ else if (code >= 48 && code <= 57) val = code - 48; // 0-9
+ else val = Infinity;
+ if (val >= radix) break;
+ ++tokPos;
+ total = total * radix + val;
+ }
+ if (tokPos === start || len != null && tokPos - start !== len) return null;
+
+ return total;
+ }
+
+ function readHexNumber() {
+ tokPos += 2; // 0x
+ var val = readInt(16);
+ if (val == null) raise(tokStart + 2, "Expected hexadecimal number");
+ if (isIdentifierStart(input.charCodeAt(tokPos))) raise(tokPos, "Identifier directly after number");
+ return finishToken(_num, val);
+ }
+
+ // Read an integer, octal integer, or floating-point number.
+
+ function readNumber(ch) {
+ var start = tokPos, isFloat = ch === ".";
+ if (!isFloat && readInt(10) == null) raise(start, "Invalid number");
+ if (isFloat || input.charAt(tokPos) === ".") {
+ var next = input.charAt(++tokPos);
+ if (next === "-" || next === "+") ++tokPos;
+ if (readInt(10) === null) raise(start, "Invalid number");
+ isFloat = true;
+ }
+ if (/e/i.test(input.charAt(tokPos))) {
+ var next = input.charAt(++tokPos);
+ if (next === "-" || next === "+") ++tokPos;
+ if (readInt(10) === null) raise(start, "Invalid number")
+ isFloat = true;
+ }
+ if (isIdentifierStart(input.charCodeAt(tokPos))) raise(tokPos, "Identifier directly after number");
+
+ var str = input.slice(start, tokPos), val;
+ if (isFloat) val = parseFloat(str);
+ else if (ch !== "0" || str.length === 1) val = parseInt(str, 10);
+ else if (/[89]/.test(str) || strict) raise(start, "Invalid number");
+ else val = parseInt(str, 8);
+ return finishToken(_num, val);
+ }
+
+ // Read a string value, interpreting backslash-escapes.
+
+ function readString(quote) {
+ tokPos++;
+ var str = "";
+ for (;;) {
+ if (tokPos >= inputLen) raise(tokStart, "Unterminated string constant");
+ var ch = input.charAt(tokPos);
+ if (ch === quote) {
+ ++tokPos;
+ return finishToken(_string, str);
+ }
+ if (ch === "\\") {
+ ch = input.charAt(++tokPos);
+ var octal = /^[0-7]+/.exec(input.slice(tokPos, tokPos + 3));
+ if (octal) octal = octal[0];
+ while (octal && parseInt(octal, 8) > 255) octal = octal.slice(0, octal.length - 1);
+ ++tokPos;
+ if (octal) {
+ if (strict) raise(tokPos - 2, "Octal literal in strict mode");
+ str += String.fromCharCode(parseInt(octal, 8));
+ tokPos += octal.length - 1;
+ } else if (ch === "x") {
+ str += readHexChar(2);
+ } else if (ch === "u") {
+ str += readHexChar(4);
+ } else if (ch === "U") {
+ str += readHexChar(8);
+ } else {
+ switch (ch) {
+ case "n" : str += "\n"; break;
+ case "r" : str += "\r"; break;
+ case "t" : str += "\t"; break;
+ case "b" : str += "\b"; break;
+ case "v" : str += "\u000b"; break;
+ case "f" : str += "\f"; break;
+ case "0" : str += "\0"; break;
+ case "\r": if (input.charAt(tokPos) === "\n") ++tokPos;
+ case "\n": break;
+ default: str += ch; break;
+ }
+ }
+ } else {
+ if (newline.test(ch)) raise(tokStart, "Unterminated string constant");
+ if (ch !== "\\") str += ch;
+ ++tokPos;
+ }
+ }
+ }
+
+ // Used to read character escape sequences ('\x', '\u', '\U').
+
+ function readHexChar(len) {
+ var n = readInt(16, len);
+ if (n === null) raise(tokStart, "Bad character escape sequence");
+ return String.fromCharCode(n);
+ }
+
+ // Used to signal to callers of `readWord1` whether the word
+ // contained any escape sequences. This is needed because words with
+ // escape sequences must not be interpreted as keywords.
+
+ var containsEsc;
+
+ // Read an identifier, and return it as a string. Sets `containsEsc`
+ // to whether the word contained a '\u' escape.
+ //
+ // Only builds up the word character-by-character when it actually
+ // containeds an escape, as a micro-optimization.
+
+ function readWord1() {
+ containsEsc = false;
+ var word, first = true, start = tokPos;
+ for (;;) {
+ var ch = input.charAt(tokPos);
+ if (isIdentifierChar(ch)) {
+ if (containsEsc) word += ch;
+ ++tokPos;
+ } else if (ch === "\\") {
+ if (!containsEsc) word = input.slice(start, tokPos);
+ containsEsc = true;
+ if (input.charAt(++tokPos) != "u")
+ raise(tokPos, "Expecting Unicode escape sequence \\uXXXX");
+ ++tokPos;
+ var esc = readHexChar(4);
+ if (!esc) raise(tokPos - 1, "Invalid Unicode escape");
+ if (!(first ? isIdentifierStart(esc.charCodeAt(0)) : isIdentifierChar(esc)))
+ raise(tokPos - 4, "Invalid Unicode escape");
+ word += esc;
+ } else {
+ break;
+ }
+ first = false;
+ }
+ return containsEsc ? word : input.slice(start, tokPos);
+ }
+
+ // Read an identifier or keyword token. Will check for reserved
+ // words when necessary.
+
+ function readWord() {
+ var word = readWord1();
+ var type = _name;
+ if (!containsEsc) {
+ if (isKeyword(word)) type = keywordTypes[word];
+ else if (options.forbidReserved &&
+ (options.ecmaVersion === 3 ? isReservedWord3 : isReservedWord5)(word) ||
+ strict && isStrictReservedWord(word))
+ raise(tokStart, "The keyword '" + word + "' is reserved");
+ }
+ return finishToken(type, word);
+ }
+
+ // ## Parser
+
+ function next() {
+ lastStart = tokStart;
+ lastEnd = tokEnd;
+ readToken();
+ }
+
+ function setStrict(strct) {
+ strict = strct;
+ tokPos = options.linePositions ? lastEnd.offset : lastEnd;
+ skipSpace();
+ readToken();
+ }
+
+ function startNode() {
+ var node = {type: null, start: tokStart};
+ if (options.trackComments && tokCommentsBefore) {
+ node.commentsBefore = tokCommentsBefore;
+ tokCommentsBefore = null;
+ }
+ return node;
+ }
+
+ function startNodeFrom(other) {
+ var node = {type: null, start: other.start};
+ if (other.commentsBefore) {
+ node.commentsBefore = other.commentsBefore;
+ other.commentsBefore = null;
+ }
+ return node;
+ }
+
+ function finishNode(node, type) {
+ if (type != null) node.type = type;
+ node.end = lastEnd;
+ if (options.trackComments && tokCommentsAfter)
+ node.commentsAfter = tokCommentsAfter;
+ return node;
+ }
+
+ function parseTopLevel() {
+ initTokenState();
+ lastStart = lastEnd = options.linePositions ? curLinePos() : tokPos;
+ inFunction = strict = null;
+ labels = [];
+ readToken();
+
+ var node = startNode(), first = true;
+ node.body = [];
+ while (tokType !== _eof) {
+ var stmt = parseStatement();
+ node.body.push(stmt);
+ if (first && isUseStrict(stmt)) setStrict(true);
+ first = false;
+ }
+ return finishNode(node, "Program");
+ };
+
+ function isUseStrict(stmt) {
+ return options.ecmaVersion >= 5 && stmt.type === "ExpressionStatement" &&
+ stmt.expression.type === "Literal" && stmt.expression.value === "use strict";
+ }
+
+ function eat(type) {
+ if (tokType === type) {
+ next();
+ return true;
+ }
+ }
+
+ function canInsertSemicolon() {
+ return tokType === _eof || tokType === _braceR ||
+ !options.strictSemicolons &&
+ newline.test(options.linePositions ? input.slice(lastEnd.offset, tokStart.offset)
+ : input.slice(lastEnd, tokStart));
+ }
+
+ function semicolon() {
+ if (!eat(_semi) && !canInsertSemicolon()) unexpected();
+ }
+
+ function expect(type) {
+ if (tokType === type) next();
+ else unexpected();
+ }
+
+ function unexpected() {
+ raise(tokStart, "Unexpected token");
+ }
+
+ function parseStatement() {
+ // if expecting a statement and found a slash as operator,
+ // it must be a literal regexp.
+ if (tokType === _slash)
+ readToken(true);
+
+ var starttype = tokType, node = startNode();
+
+ switch (starttype) {
+ case _break: case _continue:
+ next();
+ var isBreak = starttype === _break;
+ if (eat(_semi) || canInsertSemicolon()) node.label = null;
+ else if (tokType !== _name) unexpected();
+ else {
+ node.label = parseIdent();
+ semicolon();
+ }
+ for (var i = 0; i < labels.length; ++i) {
+ var lab = labels[i];
+ if ((node.label == null || lab.name === node.label.name) &&
+ lab.kind != null && (isBreak || lab.kind === "loop")) break;
+ }
+ if (i === labels.length) raise(node.start, "Unsyntactic " + starttype.keyword);
+ return finishNode(node, isBreak ? "BreakStatement" : "ContinueStatement");
+
+ case _debugger:
+ next();
+ return finishNode(node, "DebuggerStatement");
+
+ case _do:
+ next();
+ labels.push({kind: "loop"});
+ node.body = parseStatement();
+ labels.pop();
+ expect(_while);
+ node.test = parseParenExpression();
+ return finishNode(node, "DoWhileStatement");
+
+ case _for:
+ next();
+ expect(_parenL);
+ if (tokType === _semi) return parseFor(node, null);
+ if (tokType === _var) {
+ var init = startNode();
+ next();
+ parseVar(init, true);
+ if (init.declarations.length === 1 && eat(_in))
+ return parseForIn(node, init);
+ return parseFor(node, init);
+ }
+ var init = parseExpression(false, true);
+ if (eat(_in)) {checkLVal(init); return parseForIn(node, init);}
+ return parseFor(node, init);
+
+ case _function:
+ next();
+ return parseFunction(node, true);
+
+ case _if:
+ next();
+ node.test = parseParenExpression();
+ node.consequent = parseStatement();
+ node.alternate = eat(_else) ? parseStatement() : null;
+ return finishNode(node, "IfStatement");
+
+ case _return:
+ if (!inFunction) raise(tokStart, "'return' outside of function");
+ next();
+ if (eat(_semi) || canInsertSemicolon()) node.argument = null;
+ else { node.argument = parseExpression(); semicolon(); }
+ return finishNode(node, "ReturnStatement");
+
+ case _switch:
+ next();
+ node.discriminant = parseParenExpression();
+ node.cases = [];
+ expect(_braceL);
+ labels.push({kind: "switch"});
+ for (var cur, sawDefault; !eat(_braceR);) {
+ if (tokType === _case || tokType === _default) {
+ var isCase = tokType === _case;
+ if (cur) finishNode(cur, "SwitchCase");
+ node.cases.push(cur = startNode());
+ cur.consequent = [];
+ next();
+ if (isCase) cur.test = parseExpression();
+ else {
+ if (sawDefault) raise(lastStart, "Multiple default clauses"); sawDefault = true;
+ cur.test = null;
+ }
+ expect(_colon);
+ } else {
+ if (!cur) unexpected();
+ cur.consequent.push(parseStatement());
+ }
+ }
+ if (cur) finishNode(cur, "SwitchCase");
+ labels.pop();
+ return finishNode(node, "SwitchStatement");
+
+ case _throw:
+ next();
+ node.argument = parseExpression();
+ return finishNode(node, "ThrowStatement");
+
+ case _try:
+ next();
+ node.block = parseBlock();
+ node.handlers = [];
+ while (tokType === _catch) {
+ var clause = startNode();
+ next();
+ expect(_parenL);
+ clause.param = parseIdent();
+ if (strict && isStrictBadIdWord(clause.param.name))
+ raise(clause.param.start, "Binding " + clause.param.name + " in strict mode");
+ expect(_parenR);
+ clause.guard = null;
+ clause.body = parseBlock();
+ node.handlers.push(finishNode(clause, "CatchClause"));
+ }
+ node.finalizer = eat(_finally) ? parseBlock() : null;
+ if (!node.handlers.length && !node.finalizer)
+ raise(node.start, "Missing catch or finally clause");
+ return finishNode(node, "TryStatement");
+
+ case _var:
+ next();
+ node = parseVar(node);
+ semicolon();
+ return node;
+
+ case _while:
+ next();
+ node.test = parseParenExpression();
+ labels.push({kind: "loop"});
+ node.body = parseStatement();
+ labels.pop();
+ return finishNode(node, "WhileStatement");
+
+ case _with:
+ if (strict) raise(tokStart, "'with' in strict mode");
+ next();
+ node.object = parseParenExpression();
+ node.body = parseStatement();
+ return finishNode(node, "WithStatement");
+
+ case _braceL:
+ return parseBlock();
+
+ case _semi:
+ next();
+ return finishNode(node, "EmptyStatement");
+
+ default:
+ var maybeName = tokVal, expr = parseExpression();
+ if (starttype === _name && expr.type === "Identifier" && eat(_colon)) {
+ for (var i = 0; i < labels.length; ++i)
+ if (labels[i].name === maybeName) raise(expr.start, "Label '" + maybeName + "' is already declared");
+ var kind = tokType.isLoop ? "loop" : tokType === _switch ? "switch" : null;
+ labels.push({name: maybeName, kind: kind});
+ node.body = parseStatement();
+ node.label = expr;
+ return finishNode(node, "LabeledStatement");
+ } else {
+ node.expression = expr;
+ semicolon();
+ return finishNode(node, "ExpressionStatement");
+ }
+ }
+ }
+
+ function parseParenExpression() {
+ expect(_parenL);
+ var val = parseExpression();
+ expect(_parenR);
+ return val;
+ }
+
+ function parseBlock(allowStrict) {
+ var node = startNode(), first = true, strict = false, oldStrict;
+ node.body = [];
+ expect(_braceL);
+ while (!eat(_braceR)) {
+ var stmt = parseStatement();
+ node.body.push(stmt);
+ if (first && isUseStrict(stmt)) {
+ oldStrict = strict;
+ setStrict(strict = true);
+ }
+ first = false
+ }
+ if (strict && !oldStrict) setStrict(false);
+ return finishNode(node, "BlockStatement");
+ }
+
+ function parseFor(node, init) {
+ node.init = init;
+ expect(_semi);
+ node.test = tokType === _semi ? null : parseExpression();
+ expect(_semi);
+ node.update = tokType === _parenR ? null : parseExpression();
+ expect(_parenR);
+ labels.push({kind: "loop"});
+ node.body = parseStatement();
+ labels.pop();
+ return finishNode(node, "ForStatement");
+ }
+
+ function parseForIn(node, init) {
+ node.left = init;
+ node.right = parseExpression();
+ expect(_parenR);
+ labels.push({kind: "loop"});
+ node.body = parseStatement();
+ labels.pop();
+ return finishNode(node, "ForInStatement");
+ }
+
+ function parseVar(node, noIn) {
+ node.declarations = [];
+ node.kind = "var";
+ for (;;) {
+ var decl = startNode();
+ decl.id = parseIdent();
+ if (strict && isStrictBadIdWord(decl.id.name))
+ raise(decl.id.start, "Binding " + decl.id.name + " in strict mode");
+ decl.init = eat(_eq) ? parseExpression(true, noIn) : null;
+ node.declarations.push(finishNode(decl, "VariableDeclarator"));
+ if (!eat(_comma)) break;
+ }
+ return finishNode(node, "VariableDeclaration");
+ }
+
+ function parsePropertyName() {
+ if (tokType === _num || tokType === _string) return parseExprAtom();
+ return parseIdent(true);
+ }
+
+ function parseIdent(liberal) {
+ var node = startNode();
+ if (tokType !== _name) {
+ if (liberal && tokType.keyword) node.name = tokType.keyword;
+ else unexpected();
+ } else node.name = tokVal;
+ next();
+ return finishNode(node, "Identifier");
+ }
+
+ function parseFunction(node, isStatement) {
+ if (tokType === _name) node.id = parseIdent();
+ else if (isStatement) unexpected();
+ else node.id = null;
+ node.params = [];
+ var first = true;
+ expect(_parenL);
+ while (!eat(_parenR)) {
+ if (!first) expect(_comma); else first = false;
+ node.params.push(parseIdent());
+ }
+
+ var oldInFunc = inFunction, oldLabels = labels;
+ inFunction = true; labels = [];
+ node.body = parseBlock(true);
+ if (strict || node.body.body.length && isUseStrict(node.body.body[0])) {
+ for (var i = node.id ? -1 : 0; i < node.params.length; ++i) {
+ var id = i < 0 ? node.id : node.params[i];
+ if (isStrictReservedWord(id.name) || isStrictBadIdWord(id.name))
+ raise(id.start, "Defining '" + id.name + "' in strict mode");
+ if (i >= 0) for (var j = 0; j < i; ++j) if (id.name === node.params[j].name)
+ raise(id.start, "Argument name clash in strict mode");
+ }
+ }
+
+ inFunction = oldInFunc; labels = oldLabels;
+ return finishNode(node, isStatement ? "FunctionDeclaration" : "FunctionExpression");
+ }
+
+ // EXPRESSION PARSING
+
+ function parseExprList(close, allowTrailingComma, allowEmpty) {
+ var elts = [], first = true;
+ while (!eat(close)) {
+ if (!first) {
+ expect(_comma);
+ if (allowTrailingComma && options.allowTrailingCommas && eat(close)) break;
+ } else first = false;
+
+ if (allowEmpty && tokType === _comma) elts.push(null);
+ else elts.push(parseExpression(true));
+ }
+ return elts;
+ }
+
+ function parseNew() {
+ var node = startNode();
+ next();
+ node.callee = parseSubscripts(parseExprAtom(false), false);
+ if (eat(_parenL)) node.arguments = parseExprList(_parenR, false);
+ else node.arguments = [];
+ return finishNode(node, "NewExpression");
+ }
+
+ function parseObj() {
+ var node = startNode(), first = true;
+ node.properties = [];
+ next();
+ while (!eat(_braceR)) {
+ if (!first) {
+ expect(_comma);
+ if (options.allowTrailingCommas && eat(_braceR)) break;
+ } else first = false;
+
+ var prop = {key: parsePropertyName()}, isGetSet, kind;
+ if (eat(_colon)) {
+ prop.value = parseExpression(true);
+ kind = prop.kind = "init";
+ } else if (options.ecmaVersion >= 5 && prop.key.type === "Identifier" &&
+ (prop.key.name === "get" || prop.key.name === "set")) {
+ isGetSet = true;
+ kind = prop.kind = prop.key.name;
+ prop.key = parsePropertyName();
+ if (!tokType === _parenL) unexpected();
+ prop.value = parseFunction(startNode(), false);
+ } else unexpected();
+ if (prop.key.type === "Identifier" && (strict || isGetSet)) {
+ for (var i = 0; i < node.properties.length; ++i) {
+ var other = node.properties[i];
+ if (other.key.name === prop.key.name) {
+ var conflict = kind == other.kind || isGetSet && other.kind === "init" ||
+ kind === "init" && (other.kind === "get" || other.kind === "set");
+ if (conflict && !strict && kind === "init" && other.kind === "init") conflict = false;
+ if (conflict) raise(prop.key.start, "Redefinition of property");
+ }
+ }
+ }
+ node.properties.push(prop);
+ }
+ return finishNode(node, "ObjectExpression");
+ }
+
+ function parseExprAtom() {
+ switch (tokType) {
+ case _name:
+ if (tokVal === "this") {
+ var node = startNode();
+ next();
+ return finishNode(node, "ThisExpression");
+ } else return parseIdent();
+
+ case _num: case _string: case _regexp:
+ var node = startNode();
+ node.value = tokVal;
+ next();
+ return finishNode(node, "Literal");
+
+ case _null: case _true: case _false:
+ var node = startNode();
+ node.value = tokType.atomValue;
+ next();
+ return finishNode(node, "Literal");
+
+ case _parenL:
+ next();
+ var val = parseExpression();
+ expect(_parenR);
+ return val;
+
+ case _bracketL:
+ var node = startNode();
+ next();
+ node.elements = parseExprList(_bracketR, true, true);
+ return finishNode(node, "ArrayExpression");
+
+ case _braceL:
+ return parseObj();
+
+ case _function:
+ var node = startNode();
+ next();
+ return parseFunction(node, false);
- function finishOp(type, size) {
- var str = input.slice(tokPos, tokPos + size);
- tokPos += size;
- finishToken(type, str);
- }
+ case _new:
+ return parseNew();
- function readRegexp() {
- var content = "", escaped, inClass, start = tokPos;
- for (;;) {
- if (tokPos >= inputLen) raise(start, "Unterminated regular expression");
- var ch = input.charAt(tokPos);
- if (newline.test(ch)) raise(start, "Unterminated regular expression");
- if (!escaped) {
- if (ch === "[") inClass = true;
- else if (ch === "]" && inClass) inClass = false;
- else if (ch === "/" && !inClass) break;
- escaped = ch === "\\";
- } else escaped = false;
- ++tokPos;
+ default:
+ unexpected();
}
- var content = input.slice(start, tokPos);
- ++tokPos;
- var mods = readWord1();
- if (!reModifiers.test(mods)) raise(start, "Invalid regexp flag");
- return finishToken(_regexp, new RegExp(content, mods));
}
- function readInt(radix, len) {
- var start = tokPos, total = 0;
- for (;;) {
- var code = input.charCodeAt(tokPos), val;
- if (code >= 97) val = code - 97 + 10; // a
- else if (code >= 65) val = code - 65 + 10; // A
- else if (code >= 48 && code <= 57) val = code - 48; // 0-9
- else val = Infinity;
- if (val >= radix) break;
- ++tokPos;
- total = total * radix + val;
- }
- if (tokPos === start || len != null && tokPos - start !== len) return null;
-
- return total;
+ function parseSubscripts(base, allowCalls) {
+ if (eat(_dot)) {
+ var node = startNodeFrom(base);
+ node.object = base;
+ node.property = parseIdent(true);
+ node.computed = false;
+ return parseSubscripts(finishNode(node, "MemberExpression"), allowCalls);
+ } else if (eat(_bracketL)) {
+ var node = startNodeFrom(base);
+ node.object = base;
+ node.property = parseExpression();
+ node.computed = true;
+ expect(_bracketR);
+ return parseSubscripts(finishNode(node, "MemberExpression"), allowCalls);
+ } else if (allowCalls && eat(_parenL)) {
+ var node = startNodeFrom(base);
+ node.callee = base;
+ node.arguments = parseExprList(_parenR, false);
+ return parseSubscripts(finishNode(node, "CallExpression"), allowCalls);
+ } else return base;
}
- function readHexNumber() {
- tokPos += 2; // 0x
- var val = readInt(16);
- if (val == null) raise(tokStart + 2, "Expected hexadecimal number");
- if (isIdentifierStart(input.charCodeAt(tokPos))) raise(tokPos, "Identifier directly after number");
- return finishToken(_num, val);
+ function parseExprSubscripts(allowCalls) {
+ return parseSubscripts(parseExprAtom(allowCalls), allowCalls);
}
- function readNumber(ch) {
- var start = tokPos, isFloat = ch === ".";
- if (!isFloat && readInt(10) == null) raise(start, "Invalid number");
- if (isFloat || input.charAt(tokPos) === ".") {
- var next = input.charAt(++tokPos);
- if (next === "-" || next === "+") ++tokPos;
- if (readInt(10) === null) raise(start, "Invalid number");
- isFloat = true;
+ function parseMaybeUnary(noIn) {
+ if (tokType.prefix) {
+ var node = startNode(), update = tokType.isUpdate;
+ node.operator = tokVal;
+ node.prefix = true;
+ next();
+ node.argument = parseMaybeUnary(noIn);
+ if (update) checkLVal(node.argument);
+ else if (strict && node.operator === "delete" &&
+ node.argument.type === "Identifier")
+ raise(node.start, "Deleting local variable in strict mode");
+ return finishNode(node, update ? "UpdateExpression" : "UnaryExpression");
}
- if (/e/i.test(input.charAt(tokPos))) {
- var next = input.charAt(++tokPos);
- if (next === "-" || next === "+") ++tokPos;
- if (readInt(10) === null) raise(start, "Invalid number")
- isFloat = true;
+ var expr = parseExprSubscripts(true);
+ while (tokType.postfix && !canInsertSemicolon()) {
+ var node = startNodeFrom(expr);
+ node.operator = tokVal;
+ node.prefix = false;
+ node.argument = expr;
+ checkLVal(expr);
+ next();
+ expr = finishNode(node, "UpdateExpression");
}
- if (isIdentifierStart(input.charCodeAt(tokPos))) raise(tokPos, "Identifier directly after number");
-
- var str = input.slice(start, tokPos), val;
- if (isFloat) val = parseFloat(str);
- else if (ch !== "0" || str.length === 1) val = parseInt(str, 10);
- else if (/[89]/.test(str) || strict) raise(start, "Invalid number");
- else val = parseInt(str, 8);
- return finishToken(_num, val);
+ return expr;
}
- function readString(quote) {
- tokPos++;
- var escaped, str = "";
- for (;;) {
- if (tokPos >= inputLen) raise(tokStart, "Unterminated string constant");
- var ch = input.charAt(tokPos);
- if (ch === quote && !escaped) {
- ++tokPos;
- return finishToken(_string, str);
- }
- if (escaped) {
- var octal = /^[0-7]+/.exec(input.slice(tokPos, tokPos + 3));
- if (octal) octal = octal[0];
- while (octal && parseInt(octal, 8) > 255) octal = octal.slice(0, octal.length - 1);
- if (octal) {
- if (strict) raise(tokPos - 1, "Octal literal in strict mode");
- str += String.fromCharCode(parseInt(octal, 8));
- tokPos += octal.length;
- } else if (ch === "x") {
- ++tokPos;
- str += readHexChar(2);
- } else if (ch === "u") {
- ++tokPos;
- str += readHexChar(4);
- } else if (ch === "U") {
- ++tokPos;
- str += readHexChar(8);
- } else {
- ++tokPos;
- switch (ch) {
- case "n" : str += "\n"; break;
- case "r" : str += "\r"; break;
- case "t" : str += "\t"; break;
- case "b" : str += "\b"; break;
- case "v" : str += "\u000b"; break;
- case "f" : str += "\f"; break;
- case "0" : str += "\0"; break;
- case "\r": if (input.charAt(tokPos) === "\n") ++tokPos;
- case "\n": break;
- default: str += ch; break;
- }
- }
- escaped = false;
- } else {
- if (newline.test(ch)) raise(tokStart, "Unterminated string constant");
- if (ch !== "\\") str += ch;
- ++tokPos;
- escaped = ch === "\\";
+ function parseExprOp(left, minPrec, noIn) {
+ var prec = tokType.binop;
+ if (prec != null && (!noIn || tokType !== _in)) {
+ if (prec > minPrec) {
+ var node = startNodeFrom(left);
+ node.left = left;
+ node.operator = tokVal;
+ next();
+ node.right = parseExprOp(parseMaybeUnary(noIn), prec, noIn);
+ var node = finishNode(node, /&&|\|\|/.test(node.operator) ? "LogicalExpression" : "BinaryExpression");
+ return parseExprOp(node, minPrec, noIn);
}
}
+ return left;
}
- function readHexChar(len) {
- var aa = tokPos;
- var n = readInt(16, len);
- if (n === null) raise(tokStart, "Bad character escape sequence");
- return String.fromCharCode(n);
- }
-
- function isIdentifierStart(code) {
- return (code >= 65 && code <= 90) || (code >= 97 && code <= 122) ||
- code === 36 || code === 95 ||
- (code >= 0xaa && nonASCIIidentifierStart.test(String.fromCharCode(code)));
+ function parseExprOps(noIn) {
+ return parseExprOp(parseMaybeUnary(noIn), -1, noIn);
}
- function isIdentifierChar(ch) {
- return ((ch >= "a" && ch <= "z") || (ch >= "A" && ch <= "Z") ||
- (ch >= "0" && ch <= "9") || ch === "$" || ch === "_" ||
- (ch >= "\xaa" && nonASCIIidentifier.test(ch)));
+ function parseMaybeConditional(noIn) {
+ var expr = parseExprOps(noIn);
+ if (eat(_question)) {
+ var node = startNodeFrom(expr);
+ node.test = expr;
+ node.consequent = parseExpression(true);
+ expect(_colon);
+ node.alternate = parseExpression(true, noIn);
+ return finishNode(node, "ConditionalExpression");
+ }
+ return expr;
}
- var containsEsc;
- function readWord1() {
- containsEsc = false;
- var word = "", first = true;
- for (;;) {
- var ch = input.charAt(tokPos);
- if ((ch >= "a" && ch <= "z") || (ch >= "A" && ch <= "Z") ||
- (ch >= "0" && ch <= "9") || ch === "$" || ch === "_" ||
- (ch >= "\xaa" && nonASCIIidentifier.test(ch))) {
- word += ch;
- ++tokPos;
- } else if (ch === "\\") {
- containsEsc = true;
- if (input.charAt(++tokPos) != "u")
- raise(tokPos, "Expecting Unicode escape sequence \\uXXXX");
- ++tokPos;
- var esc = readHexChar(4);
- if (!esc) raise(tokPos - 1, "Invalid Unicode escape");
- if (!(first ? isIdentifierStart(esc.charCodeAt(0)) : isIdentifierChar(esc)))
- raise(tokPos - 4, "Invalid Unicode escape");
- word += esc;
- } else {
- break;
- }
- first = false;
+ function parseMaybeAssign(noIn) {
+ var left = parseMaybeConditional(noIn);
+ if (tokType.isAssign) {
+ var node = startNodeFrom(left);
+ node.operator = tokVal;
+ node.left = left;
+ next();
+ node.right = parseMaybeAssign(noIn);
+ checkLVal(left);
+ return finishNode(node, "AssignmentExpression");
}
- return word;
+ return left;
}
- function readWord() {
- var word = readWord1();
- var type = _name;
- if (!containsEsc) {
- if (isKeyword(word)) type = keywordTypes[word];
- else if (options.forbidReserved &&
- (options.ecmaVersion === 3 ? isReservedWord3 : isReservedWord5)(word) ||
- strict && isStrictReservedWord(word))
- raise(tokStart, "The keyword '" + word + "' is reserved");
+ function parseExpression(noComma, noIn) {
+ var expr = parseMaybeAssign(noIn);
+ if (!noComma && tokType === _comma) {
+ var node = startNodeFrom(expr);
+ node.expressions = [expr];
+ while (eat(_comma)) node.expressions.push(parseMaybeAssign(noIn));
+ return finishNode(node, "SequenceExpression");
}
- return finishToken(type, word);
+ return expr;
}
- function raise(pos, message) {
- if (typeof pos == "number") pos = getLineInfo(input, pos);
- message += " (" + pos.line + ":" + pos.column + ")";
- throw new SyntaxError(message);
+ function checkLVal(expr) {
+ if (expr.type !== "Identifier" && expr.type !== "MemberExpression")
+ raise(expr.start, "Assigning to rvalue");
+ if (strict && expr.type === "Identifier" && isStrictBadIdWord(expr.name))
+ raise(expr.start, "Assigning to " + expr.name + " in strict mode");
}
-
})(typeof exports === "undefined" ? (window.acorn = {}) : exports);
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-javascript/node-acorn-jsx.git
More information about the Pkg-javascript-commits
mailing list