From 980845994016f67f7c4b4ac606355477e487d441 Mon Sep 17 00:00:00 2001 From: Marijn Haverbeke Date: Thu, 19 Mar 2015 15:40:12 +0100 Subject: [PATCH] Start on ES6 port --- src/index.js | 2743 ++++++++++++++++++++++++++++++++++++++++++++++ src/tokentype.js | 142 +++ src/util.js | 9 + 3 files changed, 2894 insertions(+) create mode 100644 src/index.js create mode 100644 src/tokentype.js create mode 100644 src/util.js diff --git a/src/index.js b/src/index.js new file mode 100644 index 0000000000..cdb1db1a7f --- /dev/null +++ b/src/index.js @@ -0,0 +1,2743 @@ +// Acorn is a tiny, fast JavaScript parser written in JavaScript. +// +// Acorn was written by Marijn Haverbeke, Ingvar Stepanyan, and +// various contributors and released under an MIT license. +// +// Git repositories for Acorn are available at +// +// http://marijnhaverbeke.nl/git/acorn +// https://github.com/marijnh/acorn.git +// +// Please use the [github bug tracker][ghbt] to report issues. +// +// [ghbt]: https://github.com/marijnh/acorn/issues +// +// This file defines the main parser interface. The library also comes +// with a [error-tolerant parser][dammit] and an +// [abstract syntax tree walker][walk], defined in other files. +// +// [dammit]: acorn_loose.js +// [walk]: util/walk.js + +import {has, isArray} from "./util" +import {types as tt, keywords as keywordTypes} from "./tokentype" + +export const version = "0.12.1" + +// The main exported interface (under `self.acorn` when in the +// browser) is a `parse` function that takes a code string and +// returns an abstract syntax tree as specified by [Mozilla parser +// API][api]. +// +// [api]: https://developer.mozilla.org/en-US/docs/SpiderMonkey/Parser_API + +export function parse(input, options) { + let p = parser(options, input) + let startPos = p.options.locations ? [p.pos, p.curPosition()] : p.pos + p.nextToken() + return p.parseTopLevel(p.options.program || p.startNodeAt(startPos)) +} + +// A second optional argument can be given to further configure +// the parser process. These options are recognized: + +export const defaultOptions = { + // `ecmaVersion` indicates the ECMAScript version to parse. Must + // be either 3, or 5, or 6. This influences support for strict + // mode, the set of reserved words, support for getters and + // setters and other features. + ecmaVersion: 5, + // Source type ("script" or "module") for different semantics + sourceType: "script", + // `onInsertedSemicolon` can be a callback that will be called + // when a semicolon is automatically inserted. It will be passed + // th position of the comma as an offset, and if `locations` is + // enabled, it is given the location as a `{line, column}` object + // as second argument. + onInsertedSemicolon: null, + // `onTrailingComma` is similar to `onInsertedSemicolon`, but for + // trailing commas. + onTrailingComma: null, + // By default, reserved words are not enforced. Disable + // `allowReserved` to enforce them. When this option has the + // value "never", reserved words and keywords can also not be + // used as property names. + allowReserved: true, + // When enabled, a return at the top level is not considered an + // error. + allowReturnOutsideFunction: false, + // When enabled, import/export statements are not constrained to + // appearing at the top of the program. + allowImportExportEverywhere: false, + // When enabled, hashbang directive in the beginning of file + // is allowed and treated as a line comment. + allowHashBang: false, + // When `locations` is on, `loc` properties holding objects with + // `start` and `end` properties in `{line, column}` form (with + // line being 1-based and column 0-based) will be attached to the + // nodes. + locations: false, + // A function can be passed as `onToken` option, which will + // cause Acorn to call that function with object in the same + // format as tokenize() returns. Note that you are not + // allowed to call the parser from the callback—that will + // corrupt its internal state. + onToken: null, + // A function can be passed as `onComment` option, which will + // cause Acorn to call that function with `(block, text, start, + // end)` parameters whenever a comment is skipped. `block` is a + // boolean indicating whether this is a block (`/* */`) comment, + // `text` is the content of the comment, and `start` and `end` are + // character offsets that denote the start and end of the comment. + // When the `locations` option is on, two more parameters are + // passed, the full `{line, column}` locations of the start and + // end of the comments. Note that you are not allowed to call the + // parser from the callback—that will corrupt its internal state. + onComment: null, + // Nodes have their start and end characters offsets recorded in + // `start` and `end` properties (directly on the node, rather than + // the `loc` object, which holds line/column data. To also add a + // [semi-standardized][range] `range` property holding a `[start, + // end]` array with the same numbers, set the `ranges` option to + // `true`. + // + // [range]: https://bugzilla.mozilla.org/show_bug.cgi?id=745678 + ranges: false, + // It is possible to parse multiple files into a single AST by + // passing the tree produced by parsing the first file as + // `program` option in subsequent parses. This will add the + // toplevel forms of the parsed file to the `Program` (top) node + // of an existing parse tree. + program: null, + // When `locations` is on, you can pass this to record the source + // file in every node's `loc` object. + sourceFile: null, + // This value, if given, is stored in every node, whether + // `locations` is on or off. + directSourceFile: null, + // When enabled, parenthesized expressions are represented by + // (non-standard) ParenthesizedExpression nodes + preserveParens: false, + plugins: {} +} + +// Registered plugins + +export const plugins = {} + +// Interpret and default an options object + +function getOptions(opts) { + let options = {} + for (let opt in defaultOptions) + options[opt] = opts && has(opts, opt) ? opts[opt] : defaultOptions[opt] + + if (isArray(options.onToken)) { + var tokens = options.onToken; + options.onToken = (token) => tokens.push(token) + } + if (isArray(options.onComment)) + options.onComment = pushComment(options, options.onComment); + + return options; +} + +function pushComment(options, array) { + return function (block, text, start, end, startLoc, endLoc) { + let comment = { + type: block ? 'Block' : 'Line', + value: text, + start: start, + end: end + } + if (options.locations) + comment.loc = new SourceLocation(this, startLoc, endLoc) + if (options.ranges) + comment.range = [start, end] + array.push(comment) + } +} + +function parser(options, input) { + return new Parser(getOptions(options), String(input)) +} + +// This function tries to parse a single expression at a given +// offset in a string. Useful for parsing mixed-language formats +// that embed JavaScript expressions. + +export function parseExpressionAt(input, pos, options) { + let p = parser(options, input, pos) + p.nextToken() + return p.parseExpression() +} + +// The `getLineInfo` function is mostly useful when the +// `locations` 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. + +export function getLineInfo(input, offset) { + for (let line = 1, cur = 0;;) { + lineBreak.lastIndex = cur + let match = lineBreak.exec(input) + if (match && match.index < offset) { + ++line + cur = match.index + match[0].length + } else { + return new Position(line, offset - cur) + } + } +} + +// Acorn is organized as a tokenizer and a recursive-descent parser. +// The `tokenize` export provides an interface to the tokenizer. +// Because the tokenizer is optimized for being efficiently used by +// the Acorn parser itself, this interface is somewhat crude and not +// very modular. + +export function tokenizer(input, options) { + return parser(options, input) +} + +// Object type used to represent tokens. Note that normally, tokens +// simply exist as properties on the parser object. This is only +// used for the onToken callback and the external tokenizer. + +class Token { + constructor(p) { + this.type = p.type; + this.value = p.value; + this.start = p.start; + this.end = p.end; + if (p.options.locations) + this.loc = new SourceLocation(p, p.startLoc, p.endLoc); + if (p.options.ranges) + this.range = [p.start, p.end]; + } +} + +// 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 = "", 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); +} + +// The ECMAScript 3 reserved word list. + +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"); + +// ECMAScript 5 reserved words. + +var isReservedWord5 = makePredicate("class enum extends super const export import"); + +// ECMAScript 6 reserved words. + +var isReservedWord6 = makePredicate("enum await"); + +// The additional reserved words in strict mode. + +var isStrictReservedWord = makePredicate("implements interface let package private protected public static yield"); + +// The forbidden variable names in strict mode. + +var isStrictBadIdWord = makePredicate("eval arguments"); + +// And the keywords. + +var ecma5AndLessKeywords = "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 this"; + +var isEcma5AndLessKeyword = makePredicate(ecma5AndLessKeywords); + +var isEcma6Keyword = makePredicate(ecma5AndLessKeywords + " let const class extends export import yield super"); + +// ## Character categories + +// 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. +// Generated by `tools/generate-identifier-regex.js`. + +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\u037f\u0386\u0388-\u038a\u038c\u038e-\u03a1\u03a3-\u03f5\u03f7-\u0481\u048a-\u052f\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\u08a0-\u08b2\u0904-\u0939\u093d\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098c\u098f\u0990\u0993-\u09a8\u09aa-\u09b0\u09b2\u09b6-\u09b9\u09bd\u09ce\u09dc\u09dd\u09df-\u09e1\u09f0\u09f1\u0a05-\u0a0a\u0a0f\u0a10\u0a13-\u0a28\u0a2a-\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59-\u0a5c\u0a5e\u0a72-\u0a74\u0a85-\u0a8d\u0a8f-\u0a91\u0a93-\u0aa8\u0aaa-\u0ab0\u0ab2\u0ab3\u0ab5-\u0ab9\u0abd\u0ad0\u0ae0\u0ae1\u0b05-\u0b0c\u0b0f\u0b10\u0b13-\u0b28\u0b2a-\u0b30\u0b32\u0b33\u0b35-\u0b39\u0b3d\u0b5c\u0b5d\u0b5f-\u0b61\u0b71\u0b83\u0b85-\u0b8a\u0b8e-\u0b90\u0b92-\u0b95\u0b99\u0b9a\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8-\u0baa\u0bae-\u0bb9\u0bd0\u0c05-\u0c0c\u0c0e-\u0c10\u0c12-\u0c28\u0c2a-\u0c39\u0c3d\u0c58\u0c59\u0c60\u0c61\u0c85-\u0c8c\u0c8e-\u0c90\u0c92-\u0ca8\u0caa-\u0cb3\u0cb5-\u0cb9\u0cbd\u0cde\u0ce0\u0ce1\u0cf1\u0cf2\u0d05-\u0d0c\u0d0e-\u0d10\u0d12-\u0d3a\u0d3d\u0d4e\u0d60\u0d61\u0d7a-\u0d7f\u0d85-\u0d96\u0d9a-\u0db1\u0db3-\u0dbb\u0dbd\u0dc0-\u0dc6\u0e01-\u0e30\u0e32\u0e33\u0e40-\u0e46\u0e81\u0e82\u0e84\u0e87\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa\u0eab\u0ead-\u0eb0\u0eb2\u0eb3\u0ebd\u0ec0-\u0ec4\u0ec6\u0edc-\u0edf\u0f00\u0f40-\u0f47\u0f49-\u0f6c\u0f88-\u0f8c\u1000-\u102a\u103f\u1050-\u1055\u105a-\u105d\u1061\u1065\u1066\u106e-\u1070\u1075-\u1081\u108e\u10a0-\u10c5\u10c7\u10cd\u10d0-\u10fa\u10fc-\u1248\u124a-\u124d\u1250-\u1256\u1258\u125a-\u125d\u1260-\u1288\u128a-\u128d\u1290-\u12b0\u12b2-\u12b5\u12b8-\u12be\u12c0\u12c2-\u12c5\u12c8-\u12d6\u12d8-\u1310\u1312-\u1315\u1318-\u135a\u1380-\u138f\u13a0-\u13f4\u1401-\u166c\u166f-\u167f\u1681-\u169a\u16a0-\u16ea\u16ee-\u16f8\u1700-\u170c\u170e-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176c\u176e-\u1770\u1780-\u17b3\u17d7\u17dc\u1820-\u1877\u1880-\u18a8\u18aa\u18b0-\u18f5\u1900-\u191e\u1950-\u196d\u1970-\u1974\u1980-\u19ab\u19c1-\u19c7\u1a00-\u1a16\u1a20-\u1a54\u1aa7\u1b05-\u1b33\u1b45-\u1b4b\u1b83-\u1ba0\u1bae\u1baf\u1bba-\u1be5\u1c00-\u1c23\u1c4d-\u1c4f\u1c5a-\u1c7d\u1ce9-\u1cec\u1cee-\u1cf1\u1cf5\u1cf6\u1d00-\u1dbf\u1e00-\u1f15\u1f18-\u1f1d\u1f20-\u1f45\u1f48-\u1f4d\u1f50-\u1f57\u1f59\u1f5b\u1f5d\u1f5f-\u1f7d\u1f80-\u1fb4\u1fb6-\u1fbc\u1fbe\u1fc2-\u1fc4\u1fc6-\u1fcc\u1fd0-\u1fd3\u1fd6-\u1fdb\u1fe0-\u1fec\u1ff2-\u1ff4\u1ff6-\u1ffc\u2071\u207f\u2090-\u209c\u2102\u2107\u210a-\u2113\u2115\u2118-\u211d\u2124\u2126\u2128\u212a-\u2139\u213c-\u213f\u2145-\u2149\u214e\u2160-\u2188\u2c00-\u2c2e\u2c30-\u2c5e\u2c60-\u2ce4\u2ceb-\u2cee\u2cf2\u2cf3\u2d00-\u2d25\u2d27\u2d2d\u2d30-\u2d67\u2d6f\u2d80-\u2d96\u2da0-\u2da6\u2da8-\u2dae\u2db0-\u2db6\u2db8-\u2dbe\u2dc0-\u2dc6\u2dc8-\u2dce\u2dd0-\u2dd6\u2dd8-\u2dde\u3005-\u3007\u3021-\u3029\u3031-\u3035\u3038-\u303c\u3041-\u3096\u309b-\u309f\u30a1-\u30fa\u30fc-\u30ff\u3105-\u312d\u3131-\u318e\u31a0-\u31ba\u31f0-\u31ff\u3400-\u4db5\u4e00-\u9fcc\ua000-\ua48c\ua4d0-\ua4fd\ua500-\ua60c\ua610-\ua61f\ua62a\ua62b\ua640-\ua66e\ua67f-\ua69d\ua6a0-\ua6ef\ua717-\ua71f\ua722-\ua788\ua78b-\ua78e\ua790-\ua7ad\ua7b0\ua7b1\ua7f7-\ua801\ua803-\ua805\ua807-\ua80a\ua80c-\ua822\ua840-\ua873\ua882-\ua8b3\ua8f2-\ua8f7\ua8fb\ua90a-\ua925\ua930-\ua946\ua960-\ua97c\ua984-\ua9b2\ua9cf\ua9e0-\ua9e4\ua9e6-\ua9ef\ua9fa-\ua9fe\uaa00-\uaa28\uaa40-\uaa42\uaa44-\uaa4b\uaa60-\uaa76\uaa7a\uaa7e-\uaaaf\uaab1\uaab5\uaab6\uaab9-\uaabd\uaac0\uaac2\uaadb-\uaadd\uaae0-\uaaea\uaaf2-\uaaf4\uab01-\uab06\uab09-\uab0e\uab11-\uab16\uab20-\uab26\uab28-\uab2e\uab30-\uab5a\uab5c-\uab5f\uab64\uab65\uabc0-\uabe2\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uf900-\ufa6d\ufa70-\ufad9\ufb00-\ufb06\ufb13-\ufb17\ufb1d\ufb1f-\ufb28\ufb2a-\ufb36\ufb38-\ufb3c\ufb3e\ufb40\ufb41\ufb43\ufb44\ufb46-\ufbb1\ufbd3-\ufd3d\ufd50-\ufd8f\ufd92-\ufdc7\ufdf0-\ufdfb\ufe70-\ufe74\ufe76-\ufefc\uff21-\uff3a\uff41-\uff5a\uff66-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc"; +var nonASCIIidentifierChars = "\u200c\u200d\xb7\u0300-\u036f\u0387\u0483-\u0487\u0591-\u05bd\u05bf\u05c1\u05c2\u05c4\u05c5\u05c7\u0610-\u061a\u064b-\u0669\u0670\u06d6-\u06dc\u06df-\u06e4\u06e7\u06e8\u06ea-\u06ed\u06f0-\u06f9\u0711\u0730-\u074a\u07a6-\u07b0\u07c0-\u07c9\u07eb-\u07f3\u0816-\u0819\u081b-\u0823\u0825-\u0827\u0829-\u082d\u0859-\u085b\u08e4-\u0903\u093a-\u093c\u093e-\u094f\u0951-\u0957\u0962\u0963\u0966-\u096f\u0981-\u0983\u09bc\u09be-\u09c4\u09c7\u09c8\u09cb-\u09cd\u09d7\u09e2\u09e3\u09e6-\u09ef\u0a01-\u0a03\u0a3c\u0a3e-\u0a42\u0a47\u0a48\u0a4b-\u0a4d\u0a51\u0a66-\u0a71\u0a75\u0a81-\u0a83\u0abc\u0abe-\u0ac5\u0ac7-\u0ac9\u0acb-\u0acd\u0ae2\u0ae3\u0ae6-\u0aef\u0b01-\u0b03\u0b3c\u0b3e-\u0b44\u0b47\u0b48\u0b4b-\u0b4d\u0b56\u0b57\u0b62\u0b63\u0b66-\u0b6f\u0b82\u0bbe-\u0bc2\u0bc6-\u0bc8\u0bca-\u0bcd\u0bd7\u0be6-\u0bef\u0c00-\u0c03\u0c3e-\u0c44\u0c46-\u0c48\u0c4a-\u0c4d\u0c55\u0c56\u0c62\u0c63\u0c66-\u0c6f\u0c81-\u0c83\u0cbc\u0cbe-\u0cc4\u0cc6-\u0cc8\u0cca-\u0ccd\u0cd5\u0cd6\u0ce2\u0ce3\u0ce6-\u0cef\u0d01-\u0d03\u0d3e-\u0d44\u0d46-\u0d48\u0d4a-\u0d4d\u0d57\u0d62\u0d63\u0d66-\u0d6f\u0d82\u0d83\u0dca\u0dcf-\u0dd4\u0dd6\u0dd8-\u0ddf\u0de6-\u0def\u0df2\u0df3\u0e31\u0e34-\u0e3a\u0e47-\u0e4e\u0e50-\u0e59\u0eb1\u0eb4-\u0eb9\u0ebb\u0ebc\u0ec8-\u0ecd\u0ed0-\u0ed9\u0f18\u0f19\u0f20-\u0f29\u0f35\u0f37\u0f39\u0f3e\u0f3f\u0f71-\u0f84\u0f86\u0f87\u0f8d-\u0f97\u0f99-\u0fbc\u0fc6\u102b-\u103e\u1040-\u1049\u1056-\u1059\u105e-\u1060\u1062-\u1064\u1067-\u106d\u1071-\u1074\u1082-\u108d\u108f-\u109d\u135d-\u135f\u1369-\u1371\u1712-\u1714\u1732-\u1734\u1752\u1753\u1772\u1773\u17b4-\u17d3\u17dd\u17e0-\u17e9\u180b-\u180d\u1810-\u1819\u18a9\u1920-\u192b\u1930-\u193b\u1946-\u194f\u19b0-\u19c0\u19c8\u19c9\u19d0-\u19da\u1a17-\u1a1b\u1a55-\u1a5e\u1a60-\u1a7c\u1a7f-\u1a89\u1a90-\u1a99\u1ab0-\u1abd\u1b00-\u1b04\u1b34-\u1b44\u1b50-\u1b59\u1b6b-\u1b73\u1b80-\u1b82\u1ba1-\u1bad\u1bb0-\u1bb9\u1be6-\u1bf3\u1c24-\u1c37\u1c40-\u1c49\u1c50-\u1c59\u1cd0-\u1cd2\u1cd4-\u1ce8\u1ced\u1cf2-\u1cf4\u1cf8\u1cf9\u1dc0-\u1df5\u1dfc-\u1dff\u203f\u2040\u2054\u20d0-\u20dc\u20e1\u20e5-\u20f0\u2cef-\u2cf1\u2d7f\u2de0-\u2dff\u302a-\u302f\u3099\u309a\ua620-\ua629\ua66f\ua674-\ua67d\ua69f\ua6f0\ua6f1\ua802\ua806\ua80b\ua823-\ua827\ua880\ua881\ua8b4-\ua8c4\ua8d0-\ua8d9\ua8e0-\ua8f1\ua900-\ua909\ua926-\ua92d\ua947-\ua953\ua980-\ua983\ua9b3-\ua9c0\ua9d0-\ua9d9\ua9e5\ua9f0-\ua9f9\uaa29-\uaa36\uaa43\uaa4c\uaa4d\uaa50-\uaa59\uaa7b-\uaa7d\uaab0\uaab2-\uaab4\uaab7\uaab8\uaabe\uaabf\uaac1\uaaeb-\uaaef\uaaf5\uaaf6\uabe3-\uabea\uabec\uabed\uabf0-\uabf9\ufb1e\ufe00-\ufe0f\ufe20-\ufe2d\ufe33\ufe34\ufe4d-\ufe4f\uff10-\uff19\uff3f"; + +var nonASCIIidentifierStart = new RegExp("[" + nonASCIIidentifierStartChars + "]"); +var nonASCIIidentifier = new RegExp("[" + nonASCIIidentifierStartChars + nonASCIIidentifierChars + "]"); +nonASCIIidentifierStartChars = nonASCIIidentifierChars = null; + +// These are a run-length and offset encoded representation of the +// >0xffff code points that are a valid part of identifiers. The +// offset starts at 0x10000, and each pair of numbers represents an +// offset to the next range, and then a size of the range. They were +// generated by tools/generate-identifier-regex.js +var astralIdentifierStartCodes = [0,11,2,25,2,18,2,1,2,14,3,13,35,122,70,52,268,28,4,48,48,31,17,26,6,37,11,29,3,35,5,7,2,4,43,157,99,39,9,51,157,310,10,21,11,7,153,5,3,0,2,43,2,1,4,0,3,22,11,22,10,30,98,21,11,25,71,55,7,1,65,0,16,3,2,2,2,26,45,28,4,28,36,7,2,27,28,53,11,21,11,18,14,17,111,72,955,52,76,44,33,24,27,35,42,34,4,0,13,47,15,3,22,0,38,17,2,24,133,46,39,7,3,1,3,21,2,6,2,1,2,4,4,0,32,4,287,47,21,1,2,0,185,46,82,47,21,0,60,42,502,63,32,0,449,56,1288,920,104,110,2962,1070,13266,568,8,30,114,29,19,47,17,3,32,20,6,18,881,68,12,0,67,12,16481,1,3071,106,6,12,4,8,8,9,5991,84,2,70,2,1,3,0,3,1,3,3,2,11,2,0,2,6,2,64,2,3,3,7,2,6,2,27,2,3,2,4,2,0,4,6,2,339,3,24,2,24,2,30,2,24,2,30,2,24,2,30,2,24,2,30,2,24,2,7,4149,196,1340,3,2,26,2,1,2,0,3,0,2,9,2,3,2,0,2,0,7,0,5,0,2,0,2,0,2,2,2,1,2,0,3,0,2,0,2,0,2,0,2,0,2,1,2,0,3,3,2,6,2,3,2,3,2,0,2,9,2,16,6,2,2,4,2,16,4421,42710,42,4148,12,221,16355,541]; +var astralIdentifierCodes = [509,0,227,0,150,4,294,9,1368,2,2,1,6,3,41,2,5,0,166,1,1306,2,54,14,32,9,16,3,46,10,54,9,7,2,37,13,2,9,52,0,13,2,49,13,16,9,83,11,168,11,6,9,8,2,57,0,2,6,3,1,3,2,10,0,11,1,3,6,4,4,316,19,13,9,214,6,3,8,112,16,16,9,82,12,9,9,535,9,20855,9,135,4,60,6,26,9,1016,45,17,3,19723,1,5319,4,4,5,9,7,3,6,31,3,149,2,1418,49,4305,6,792618,239]; + +// This has a complexity linear to the value of the code. The +// assumption is that looking up astral identifier characters is +// rare. +function isInAstralSet(code, set) { + var pos = 0x10000; + for (var i = 0; i < set.length; i += 2) { + pos += set[i]; + if (pos > code) return false; + pos += set[i + 1]; + if (pos >= code) return true; + } +} + +// Whether a single character denotes a newline. + +var newline = exports.newline = /[\n\r\u2028\u2029]/; + +var isNewLine = exports.isNewLine = function(code) { + return code === 10 || code === 13 || code === 0x2028 || code == 0x2029; +}; + +// Matches a whole line break (where CRLF is considered a single +// line break). Used to count lines. + +var lineBreak = exports.lineBreak = /\r\n|[\n\r\u2028\u2029]/g; + +// Test whether a given character code starts an identifier. + +var isIdentifierStart = exports.isIdentifierStart = function(code, astral) { + if (code < 65) return code === 36; + if (code < 91) return true; + if (code < 97) return code === 95; + if (code < 123) return true; + if (code <= 0xffff) return code >= 0xaa && nonASCIIidentifierStart.test(String.fromCharCode(code)); + if (astral === false) return false; + return isInAstralSet(code, astralIdentifierStartCodes); +}; + +// Test whether a given character is part of an identifier. + +var isIdentifierChar = exports.isIdentifierChar = function(code, astral) { + if (code < 48) return code === 36; + if (code < 58) return true; + if (code < 65) return false; + if (code < 91) return true; + if (code < 97) return code === 95; + if (code < 123) return true; + if (code <= 0xffff) return code >= 0xaa && nonASCIIidentifier.test(String.fromCharCode(code)); + if (astral === false) return false; + return isInAstralSet(code, astralIdentifierStartCodes) || isInAstralSet(code, astralIdentifierCodes); +}; + +// ## Tokenizer + +// These are used when `options.locations` is on, for the +// `startLoc` and `endLoc` properties. + +function Position(line, col) { + this.line = line; + this.column = col; +} + +Position.prototype.offset = function(n) { + return new Position(this.line, this.column + n); +}; + +// ## Parser + +// A recursive descent parser operates by defining functions for all +// syntactic elements, and recursively calling those, each function +// advancing the input stream and returning an AST node. Precedence +// of constructs (for example, the fact that `!x[1]` means `!(x[1])` +// instead of `(!x)[1]` is handled by the fact that the parser +// function that parses unary prefix operators is called first, and +// in turn calls the function that parses `[]` subscripts — that +// way, it'll receive the node for `x[1]` already parsed, and wraps +// *that* in the unary operator node. +// +// Acorn uses an [operator precedence parser][opp] to handle binary +// operator precedence, because it is much more compact than using +// the technique outlined above, which uses different, nesting +// functions to specify precedence, for all of the ten binary +// precedence levels that JavaScript defines. +// +// [opp]: http://en.wikipedia.org/wiki/Operator-precedence_parser + +var Parser = exports.Parser = function(options, input, startPos) { + this.options = options + this.loadPlugins(this.options.plugins) + this.sourceFile = this.options.sourceFile || null + this.isKeyword = this.options.ecmaVersion >= 6 ? isEcma6Keyword : isEcma5AndLessKeyword + this.isReservedWord = + this.options.ecmaVersion === 3 ? isReservedWord3 + : this.options.ecmaVersion === 5 ? isReservedWord5 + : isReservedWord6 + this.input = input + + // Set up token state + + // The current position of the tokenizer in the input. + if (startPos) { + this.pos = startPos; + this.lineStart = Math.max(0, this.input.lastIndexOf("\n", startPos)); + this.curLine = this.input.slice(0, this.lineStart).split(newline).length; + } else { + this.pos = this.lineStart = 0; + this.curLine = 1; + } + + // Properties of the current token: + // Its type + this.type = tt.eof; + // For tokens that include more information than their type, the value + this.value = null; + // Its start and end offset + this.start = this.end = this.pos; + // And, if locations are used, the {line, column} object + // corresponding to those offsets + this.startLoc = this.endLoc = null; + + // Position information for the previous token + this.lastTokEndLoc = this.lastTokStartLoc = null; + this.lastTokStart = this.lastTokEnd = this.pos; + + // The context stack is used to superficially track syntactic + // context to predict whether a regular expression is allowed in a + // given position. + this.context = [tc.b_stat]; + this.exprAllowed = true; + + // Figure out if it's a module code. + this.strict = this.inModule = this.options.sourceType === "module"; + + // Flags to track whether we are in a function, a generator. + this.inFunction = this.inGenerator = false; + // Labels in scope. + this.labels = []; + + // If enabled, skip leading hashbang line. + if (this.pos === 0 && this.options.allowHashBang && this.input.slice(0, 2) === '#!') + this.skipLineComment(2); +}; + +// Shorthand because we are going to be adding a _lot_ of methods to +// this. +var pp = Parser.prototype; + +pp.extend = function(name, f) { + this[name] = f(this[name]); +}; + +pp.loadPlugins = function(plugins) { + for (var name in plugins) { + var plugin = exports.plugins[name]; + if (!plugin) throw new Error("Plugin '" + name + "' not found"); + plugin(this, plugins[name]); + } +}; + +// Move to the next token + +pp.next = function() { + if (this.options.onToken) + this.options.onToken(new Token(this)); + + this.lastTokEnd = this.end; + this.lastTokStart = this.start; + this.lastTokEndLoc = this.endLoc; + this.lastTokStartLoc = this.startLoc; + this.nextToken(); +}; + +pp.getToken = function() { + this.next(); + return new Token(this); +}; + +// If we're in an ES6 environment, make parsers iterable +if (typeof Symbol !== "undefined") + pp[Symbol.iterator] = function () { + var self = this; + return {next: function () { + var token = self.getToken(); + return { + done: token.type === tt.eof, + value: token + }; + }}; + }; + +// Toggle strict mode. Re-reads the next number or string to please +// pedantic tests (`"use strict"; 010;` should fail). + +pp.setStrict = function(strict) { + this.strict = strict; + if (this.type !== tt.num && this.type !== tt.string) return; + this.pos = this.start; + if (this.options.locations) { + while (this.pos < this.lineStart) { + this.lineStart = this.input.lastIndexOf("\n", this.lineStart - 2) + 1; + --this.curLine; + } + } + this.nextToken(); +}; + +pp.curContext = function() { + return this.context[this.context.length - 1]; +}; + +// Read a single token, updating the parser object's token-related +// properties. + +pp.nextToken = function() { + var curContext = this.curContext(); + if (!curContext || !curContext.preserveSpace) this.skipSpace(); + + this.start = this.pos; + if (this.options.locations) this.startLoc = this.curPosition(); + if (this.pos >= this.input.length) return this.finishToken(tt.eof); + + if (curContext === tc.q_tmpl) return this.readTmplToken(); + + this.readToken(this.fullCharCodeAtPos()); +}; + +pp.readToken = function(code) { + // Identifier or keyword. '\uXXXX' sequences are allowed in + // identifiers, so '\' also dispatches to that. + if (isIdentifierStart(code, this.options.ecmaVersion >= 6) || code === 92 /* '\' */) + return this.readWord(); + + return this.getTokenFromCode(code); +}; + +pp.fullCharCodeAtPos = function() { + var code = this.input.charCodeAt(this.pos); + if (code <= 0xd7ff || code >= 0xe000) return code; + var next = this.input.charCodeAt(this.pos + 1); + return (code << 10) + next - 0x35fdc00; +}; + +pp.skipBlockComment = function() { + var startLoc = this.options.onComment && this.options.locations && this.curPosition(); + var start = this.pos, end = this.input.indexOf("*/", this.pos += 2); + if (end === -1) this.raise(this.pos - 2, "Unterminated comment"); + this.pos = end + 2; + if (this.options.locations) { + lineBreak.lastIndex = start; + var match; + while ((match = lineBreak.exec(this.input)) && match.index < this.pos) { + ++this.curLine; + this.lineStart = match.index + match[0].length; + } + } + if (this.options.onComment) + this.options.onComment(true, this.input.slice(start + 2, end), start, this.pos, + startLoc, this.options.locations && this.curPosition()); +}; + +pp.skipLineComment = function(startSkip) { + var start = this.pos; + var startLoc = this.options.onComment && this.options.locations && this.curPosition(); + var ch = this.input.charCodeAt(this.pos+=startSkip); + while (this.pos < this.input.length && ch !== 10 && ch !== 13 && ch !== 8232 && ch !== 8233) { + ++this.pos; + ch = this.input.charCodeAt(this.pos); + } + if (this.options.onComment) + this.options.onComment(false, this.input.slice(start + startSkip, this.pos), start, this.pos, + startLoc, this.options.locations && this.curPosition()); +}; + +// Called at the start of the parse and after every token. Skips +// whitespace and comments, and. + +pp.skipSpace = function() { + while (this.pos < this.input.length) { + var ch = this.input.charCodeAt(this.pos); + if (ch === 32) { // ' ' + ++this.pos; + } else if (ch === 13) { + ++this.pos; + var next = this.input.charCodeAt(this.pos); + if (next === 10) { + ++this.pos; + } + if (this.options.locations) { + ++this.curLine; + this.lineStart = this.pos; + } + } else if (ch === 10 || ch === 8232 || ch === 8233) { + ++this.pos; + if (this.options.locations) { + ++this.curLine; + this.lineStart = this.pos; + } + } else if (ch > 8 && ch < 14) { + ++this.pos; + } else if (ch === 47) { // '/' + var next = this.input.charCodeAt(this.pos + 1); + if (next === 42) { // '*' + this.skipBlockComment(); + } else if (next === 47) { // '/' + this.skipLineComment(2); + } else break; + } else if (ch === 160) { // '\xa0' + ++this.pos; + } else if (ch >= 5760 && nonASCIIwhitespace.test(String.fromCharCode(ch))) { + ++this.pos; + } else { + break; + } + } +}; + +pp.curPosition = function() { + return new Position(this.curLine, this.pos - this.lineStart); +}; + +// The algorithm used to determine whether a regexp can appear at a +// given point in the program is loosely based on sweet.js' approach. +// See https://github.com/mozilla/sweet.js/wiki/design + +var TokContext = exports.TokContext = function(token, isExpr, preserveSpace) { + this.token = token; + this.isExpr = isExpr; + this.preserveSpace = preserveSpace; +}; + +var tc = exports.tokContexts = { + b_stat: new TokContext("{", false), + b_expr: new TokContext("{", true), + b_tmpl: new TokContext("${", true), + p_stat: new TokContext("(", false), + p_expr: new TokContext("(", true), + q_tmpl: new TokContext("`", true, true), + f_expr: new TokContext("function", true) +}; + +pp.braceIsBlock = function(prevType) { + var parent; + if (prevType === tt.colon && (parent = this.curContext()).token == "{") + return !parent.isExpr; + if (prevType === tt._return) + return newline.test(this.input.slice(this.lastTokEnd, this.start)); + if (prevType === tt._else || prevType === tt.semi || prevType === tt.eof) + return true; + if (prevType == tt.braceL) + return this.curContext() === tc.b_stat; + return !this.exprAllowed; +}; + +// Called at the end of every token. Sets `end`, `val`, and +// maintains `context` and `exprAllowed`, and skips the space after +// the token, so that the next one's `start` will point at the +// right position. + +pp.finishToken = function(type, val) { + this.end = this.pos; + if (this.options.locations) this.endLoc = this.curPosition(); + var prevType = this.type; + this.type = type; + this.value = val; + + this.updateContext(prevType); +}; + +pp.updateContext = function(prevType) { + var update, type = this.type; + if (type.keyword && prevType == tt.dot) + this.exprAllowed = false; + else if (update = type.updateContext) + update.call(this, prevType); + else + this.exprAllowed = type.beforeExpr; +}; + +// Token-specific context update code + +tt.parenR.updateContext = tt.braceR.updateContext = function() { + var out = this.context.pop(); + if (out === tc.b_stat && this.curContext() === tc.f_expr) { + this.context.pop(); + this.exprAllowed = false; + } else if (out === tc.b_tmpl) { + this.exprAllowed = true; + } else { + this.exprAllowed = !(out && out.isExpr); + } +}; + +tt.braceL.updateContext = function(prevType) { + this.context.push(this.braceIsBlock(prevType) ? tc.b_stat : tc.b_expr); + this.exprAllowed = true; +}; + +tt.dollarBraceL.updateContext = function() { + this.context.push(tc.b_tmpl); + this.exprAllowed = true; +}; + +tt.parenL.updateContext = function(prevType) { + var statementParens = prevType === tt._if || prevType === tt._for || prevType === tt._with || prevType === tt._while; + this.context.push(statementParens ? tc.p_stat : tc.p_expr); + this.exprAllowed = true; +}; + +tt.incDec.updateContext = function() { + // tokExprAllowed stays unchanged +}; + +tt._function.updateContext = function() { + if (this.curContext() !== tc.b_stat) + this.context.push(tc.f_expr); + this.exprAllowed = false; +}; + +tt.backQuote.updateContext = function() { + if (this.curContext() === tc.q_tmpl) + this.context.pop(); + else + this.context.push(tc.q_tmpl); + this.exprAllowed = false; +}; + +// ### 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. +// +pp.readToken_dot = function() { + var next = this.input.charCodeAt(this.pos + 1); + if (next >= 48 && next <= 57) return this.readNumber(true); + var next2 = this.input.charCodeAt(this.pos + 2); + if (this.options.ecmaVersion >= 6 && next === 46 && next2 === 46) { // 46 = dot '.' + this.pos += 3; + return this.finishToken(tt.ellipsis); + } else { + ++this.pos; + return this.finishToken(tt.dot); + } +}; + +pp.readToken_slash = function() { // '/' + var next = this.input.charCodeAt(this.pos + 1); + if (this.exprAllowed) {++this.pos; return this.readRegexp();} + if (next === 61) return this.finishOp(tt.assign, 2); + return this.finishOp(tt.slash, 1); +}; + +pp.readToken_mult_modulo = function(code) { // '%*' + var next = this.input.charCodeAt(this.pos + 1); + if (next === 61) return this.finishOp(tt.assign, 2); + return this.finishOp(code === 42 ? tt.star : tt.modulo, 1); +}; + +pp.readToken_pipe_amp = function(code) { // '|&' + var next = this.input.charCodeAt(this.pos + 1); + if (next === code) return this.finishOp(code === 124 ? tt.logicalOR : tt.logicalAND, 2); + if (next === 61) return this.finishOp(tt.assign, 2); + return this.finishOp(code === 124 ? tt.bitwiseOR : tt.bitwiseAND, 1); +}; + +pp.readToken_caret = function() { // '^' + var next = this.input.charCodeAt(this.pos + 1); + if (next === 61) return this.finishOp(tt.assign, 2); + return this.finishOp(tt.bitwiseXOR, 1); +}; + +pp.readToken_plus_min = function(code) { // '+-' + var next = this.input.charCodeAt(this.pos + 1); + if (next === code) { + if (next == 45 && this.input.charCodeAt(this.pos + 2) == 62 && + newline.test(this.input.slice(this.lastTokEnd, this.pos))) { + // A `-->` line comment + this.skipLineComment(3); + this.skipSpace(); + return this.nextToken(); + } + return this.finishOp(tt.incDec, 2); + } + if (next === 61) return this.finishOp(tt.assign, 2); + return this.finishOp(tt.plusMin, 1); +}; + +pp.readToken_lt_gt = function(code) { // '<>' + var next = this.input.charCodeAt(this.pos + 1); + var size = 1; + if (next === code) { + size = code === 62 && this.input.charCodeAt(this.pos + 2) === 62 ? 3 : 2; + if (this.input.charCodeAt(this.pos + size) === 61) return this.finishOp(tt.assign, size + 1); + return this.finishOp(tt.bitShift, size); + } + if (next == 33 && code == 60 && this.input.charCodeAt(this.pos + 2) == 45 && + this.input.charCodeAt(this.pos + 3) == 45) { + if (this.inModule) unexpected(); + // `