diff options
Diffstat (limited to 'node_modules/regjsparser')
| -rw-r--r-- | node_modules/regjsparser/LICENSE.BSD | 21 | ||||
| -rw-r--r-- | node_modules/regjsparser/README.md | 47 | ||||
| -rwxr-xr-x | node_modules/regjsparser/bin/parser | 63 | ||||
| l--------- | node_modules/regjsparser/node_modules/.bin/jsesc | 1 | ||||
| -rw-r--r-- | node_modules/regjsparser/node_modules/jsesc/LICENSE-MIT.txt | 20 | ||||
| -rw-r--r-- | node_modules/regjsparser/node_modules/jsesc/README.md | 375 | ||||
| -rwxr-xr-x | node_modules/regjsparser/node_modules/jsesc/bin/jsesc | 138 | ||||
| -rw-r--r-- | node_modules/regjsparser/node_modules/jsesc/jsesc.js | 265 | ||||
| -rw-r--r-- | node_modules/regjsparser/node_modules/jsesc/man/jsesc.1 | 90 | ||||
| -rw-r--r-- | node_modules/regjsparser/node_modules/jsesc/package.json | 55 | ||||
| -rw-r--r-- | node_modules/regjsparser/package.json | 37 | ||||
| -rw-r--r-- | node_modules/regjsparser/parser.d.ts | 183 | ||||
| -rw-r--r-- | node_modules/regjsparser/parser.js | 1634 |
13 files changed, 2929 insertions, 0 deletions
diff --git a/node_modules/regjsparser/LICENSE.BSD b/node_modules/regjsparser/LICENSE.BSD new file mode 100644 index 00000000..9aaf45cf --- /dev/null +++ b/node_modules/regjsparser/LICENSE.BSD @@ -0,0 +1,21 @@ +Copyright (c) Julian Viereck and Contributors, All Rights Reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY +DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES +(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; +LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND +ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF +THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/node_modules/regjsparser/README.md b/node_modules/regjsparser/README.md new file mode 100644 index 00000000..2b2818ce --- /dev/null +++ b/node_modules/regjsparser/README.md @@ -0,0 +1,47 @@ +# RegJSParser + +Parsing the JavaScript's RegExp in JavaScript. + +## Installation + +```bash +npm install regjsparser +``` + +## Usage + +```js +var parse = require('regjsparser').parse; + +var parseTree = parse('^a'); // /^a/ +console.log(parseTree); + +// Toggle on/off additional features: +var parseTree = parse('^a', '', { + // SEE: https://github.com/jviereck/regjsparser/pull/78 + unicodePropertyEscape: true, + + // SEE: https://github.com/jviereck/regjsparser/pull/83 + namedGroups: true, + + // SEE: https://github.com/jviereck/regjsparser/pull/89 + lookbehind: true +}); +console.log(parseTree); +``` + +## Testing + +To run the tests, run the following command: + +```bash +npm test +``` + +To create a new reference file, execute… + +```bash +node test/update-fixtures.js +``` + +…from the repo top directory. diff --git a/node_modules/regjsparser/bin/parser b/node_modules/regjsparser/bin/parser new file mode 100755 index 00000000..73549ac0 --- /dev/null +++ b/node_modules/regjsparser/bin/parser @@ -0,0 +1,63 @@ +#!/usr/bin/env node +(function() { + + var fs = require('fs'); + var path = require('path'); + var parse = require('../parser').parse; + var jsesc = require('jsesc'); + var regexes = process.argv.splice(2); + var first = regexes[0]; + var data; + var log = console.log; + var flags = ''; + var main = function() { + if (/^(?:-h|--help|undefined)$/.test(first)) { + log([ + '\nUsage:\n', + '\tregjsparser [regex ...]', + '\tregjsparser [-f | --flags] u [regex ...]', + '\tregjsparser [-v | --version]', + '\tregjsparser [-h | --help]', + '\nExamples:\n', + '\tregjsparser \'^foo.bar$\'', + '\tregjsparser \'[a-zA-Z0-9]\'' + ].join('\n')); + return process.exit(1); + } + + if (/^(?:-v|--version)$/.test(first)) { + log('v%s', require(path.resolve(__dirname, '../package.json')).version); + return process.exit(1); + } + + if (/^(?:-f|--flags)$/.test(first)) { + flags = regexes[1]; + regexes = regexes.slice(2); + } + + regexes.forEach(function(snippet) { + try { + result = parse(snippet, flags); + log(jsesc(result, { + 'json': true, + 'compact': false, + 'indent': '\t' + })); + } catch(error) { + log(error.message + '\n'); + log('Error: failed to parse. Make sure the regular expression is valid.'); + log('If you think this is a bug in regjsparser, please report it:'); + log('\thttps://github.com/jviereck/regjsparser/issues/new'); + log('\nStack trace:\n'); + log(error.stack); + return process.exit(1); + } + }); + // Return with exit status 0 outside of the `forEach` loop, in case + // multiple regular expressions were passed in. + return process.exit(0); + }; + + main(); + +}()); diff --git a/node_modules/regjsparser/node_modules/.bin/jsesc b/node_modules/regjsparser/node_modules/.bin/jsesc new file mode 120000 index 00000000..7237604c --- /dev/null +++ b/node_modules/regjsparser/node_modules/.bin/jsesc @@ -0,0 +1 @@ +../jsesc/bin/jsesc
\ No newline at end of file diff --git a/node_modules/regjsparser/node_modules/jsesc/LICENSE-MIT.txt b/node_modules/regjsparser/node_modules/jsesc/LICENSE-MIT.txt new file mode 100644 index 00000000..97067e54 --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/LICENSE-MIT.txt @@ -0,0 +1,20 @@ +Copyright Mathias Bynens <http://mathiasbynens.be/> + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff --git a/node_modules/regjsparser/node_modules/jsesc/README.md b/node_modules/regjsparser/node_modules/jsesc/README.md new file mode 100644 index 00000000..7a083c75 --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/README.md @@ -0,0 +1,375 @@ +# jsesc [](https://travis-ci.org/mathiasbynens/jsesc) [](https://coveralls.io/r/mathiasbynens/jsesc) [](https://gemnasium.com/mathiasbynens/jsesc) + +This is a JavaScript library for [escaping JavaScript strings](http://mathiasbynens.be/notes/javascript-escapes) while generating the shortest possible valid ASCII-only output. [Here’s an online demo.](http://mothereff.in/js-escapes) + +This can be used to avoid [mojibake](http://en.wikipedia.org/wiki/Mojibake) and other encoding issues, or even to [avoid errors](https://twitter.com/annevk/status/380000829643571200) when passing JSON-formatted data (which may contain U+2028 LINE SEPARATOR, U+2029 PARAGRAPH SEPARATOR, or [lone surrogates](http://esdiscuss.org/topic/code-points-vs-unicode-scalar-values#content-14)) to a JavaScript parser or an UTF-8 encoder, respectively. + +Feel free to fork if you see possible improvements! + +## Installation + +Via [Bower](http://bower.io/): + +```bash +bower install jsesc +``` + +Via [Component](https://github.com/component/component): + +```bash +component install mathiasbynens/jsesc +``` + +Via [npm](http://npmjs.org/): + +```bash +npm install jsesc +``` + +In a browser: + +```html +<script src="jsesc.js"></script> +``` + +In [Node.js](http://nodejs.org/) and [RingoJS](http://ringojs.org/): + +```js +var jsesc = require('jsesc'); +``` + +In [Narwhal](http://narwhaljs.org/): + +```js +var jsesc = require('jsesc').jsesc; +``` + +In [Rhino](http://www.mozilla.org/rhino/): + +```js +load('jsesc.js'); +``` + +Using an AMD loader like [RequireJS](http://requirejs.org/): + +```js +require( + { + 'paths': { + 'jsesc': 'path/to/jsesc' + } + }, + ['jsesc'], + function(jsesc) { + console.log(jsesc); + } +); +``` + +## API + +### `jsesc(value, options)` + +This function takes a value and returns an escaped version of the value where any characters that are not printable ASCII symbols are escaped using the shortest possible (but valid) [escape sequences for use in JavaScript strings](http://mathiasbynens.be/notes/javascript-escapes). The first supported value type is strings: + +```js +jsesc('Ich ♥ Bücher'); +// → 'Ich \\u2665 B\\xFCcher' + +jsesc('foo 𝌆 bar'); +// → 'foo \\uD834\\uDF06 bar' +``` + +Instead of a string, the `value` can also be an array, or an object. In such cases, `jsesc` will return a stringified version of the value where any characters that are not printable ASCII symbols are escaped in the same way. + +```js +// Escaping an array +jsesc([ + 'Ich ♥ Bücher', 'foo 𝌆 bar' +]); +// → '[\'Ich \\u2665 B\\xFCcher\',\'foo \\uD834\\uDF06 bar\']' + +// Escaping an object +jsesc({ + 'Ich ♥ Bücher': 'foo 𝌆 bar' +}); +// → '{\'Ich \\u2665 B\\xFCcher\':\'foo \\uD834\\uDF06 bar\'}' +``` + +The optional `options` argument accepts an object with the following options: + +#### `quotes` + +The default value for the `quotes` option is `'single'`. This means that any occurences of `'` in the input string will be escaped as `\'`, so that the output can be used in a string literal wrapped in single quotes. + +```js +jsesc('Lorem ipsum "dolor" sit \'amet\' etc.'); +// → 'Lorem ipsum "dolor" sit \\\'amet\\\' etc.' + +jsesc('Lorem ipsum "dolor" sit \'amet\' etc.', { + 'quotes': 'single' +}); +// → 'Lorem ipsum "dolor" sit \\\'amet\\\' etc.' +// → "Lorem ipsum \"dolor\" sit \\'amet\\' etc." +``` + +If you want to use the output as part of a string literal wrapped in double quotes, set the `quotes` option to `'double'`. + +```js +jsesc('Lorem ipsum "dolor" sit \'amet\' etc.', { + 'quotes': 'double' +}); +// → 'Lorem ipsum \\"dolor\\" sit \'amet\' etc.' +// → "Lorem ipsum \\\"dolor\\\" sit 'amet' etc." +``` + +This setting also affects the output for arrays and objects: + +```js +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'quotes': 'double' +}); +// → '{"Ich \\u2665 B\\xFCcher":"foo \\uD834\\uDF06 bar"}' + +jsesc([ 'Ich ♥ Bücher', 'foo 𝌆 bar' ], { + 'quotes': 'double' +}); +// → '["Ich \\u2665 B\\xFCcher","foo \\uD834\\uDF06 bar"]' +``` + +#### `wrap` + +The `wrap` option takes a boolean value (`true` or `false`), and defaults to `false` (disabled). When enabled, the output will be a valid JavaScript string literal wrapped in quotes. The type of quotes can be specified through the `quotes` setting. + +```js +jsesc('Lorem ipsum "dolor" sit \'amet\' etc.', { + 'quotes': 'single', + 'wrap': true +}); +// → '\'Lorem ipsum "dolor" sit \\\'amet\\\' etc.\'' +// → "\'Lorem ipsum \"dolor\" sit \\\'amet\\\' etc.\'" + +jsesc('Lorem ipsum "dolor" sit \'amet\' etc.', { + 'quotes': 'double', + 'wrap': true +}); +// → '"Lorem ipsum \\"dolor\\" sit \'amet\' etc."' +// → "\"Lorem ipsum \\\"dolor\\\" sit \'amet\' etc.\"" +``` + +#### `es6` + +The `es6` option takes a boolean value (`true` or `false`), and defaults to `false` (disabled). When enabled, any astral Unicode symbols in the input will be escaped using [ECMAScript 6 Unicode code point escape sequences](http://mathiasbynens.be/notes/javascript-escapes#unicode-code-point) instead of using separate escape sequences for each surrogate half. If backwards compatibility with ES5 environments is a concern, don’t enable this setting. If the `json` setting is enabled, the value for the `es6` setting is ignored (as if it was `false`). + +```js +// By default, the `es6` option is disabled: +jsesc('foo 𝌆 bar 💩 baz'); +// → 'foo \\uD834\\uDF06 bar \\uD83D\\uDCA9 baz' + +// To explicitly disable it: +jsesc('foo 𝌆 bar 💩 baz', { + 'es6': false +}); +// → 'foo \\uD834\\uDF06 bar \\uD83D\\uDCA9 baz' + +// To enable it: +jsesc('foo 𝌆 bar 💩 baz', { + 'es6': true +}); +// → 'foo \\u{1D306} bar \\u{1F4A9} baz' +``` + +#### `escapeEverything` + +The `escapeEverything` option takes a boolean value (`true` or `false`), and defaults to `false` (disabled). When enabled, all the symbols in the output will be escaped, even printable ASCII symbols. + +```js +jsesc('lolwat"foo\'bar', { + 'escapeEverything': true +}); +// → '\\x6C\\x6F\\x6C\\x77\\x61\\x74\\"\\x66\\x6F\\x6F\\\'\\x62\\x61\\x72' +// → "\\x6C\\x6F\\x6C\\x77\\x61\\x74\\\"\\x66\\x6F\\x6F\\'\\x62\\x61\\x72" +``` + +This setting also affects the output for arrays and objects: + +```js +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'escapeEverything': true +}); +// → '{\'\x49\x63\x68\x20\u2665\x20\x42\xFC\x63\x68\x65\x72\':\'\x66\x6F\x6F\x20\uD834\uDF06\x20\x62\x61\x72\'}' +// → "{'\x49\x63\x68\x20\u2665\x20\x42\xFC\x63\x68\x65\x72':'\x66\x6F\x6F\x20\uD834\uDF06\x20\x62\x61\x72'}" + +jsesc([ 'Ich ♥ Bücher': 'foo 𝌆 bar' ], { + 'escapeEverything': true +}); +// → '[\'\x49\x63\x68\x20\u2665\x20\x42\xFC\x63\x68\x65\x72\',\'\x66\x6F\x6F\x20\uD834\uDF06\x20\x62\x61\x72\']' +``` + +#### `compact` + +The `compact` option takes a boolean value (`true` or `false`), and defaults to `true` (enabled). When enabled, the output for arrays and objects will be as compact as possible; it won’t be formatted nicely. + +```js +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'compact': true // this is the default +}); +// → '{\'Ich \u2665 B\xFCcher\':\'foo \uD834\uDF06 bar\'}' + +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'compact': false +}); +// → '{\n\t\'Ich \u2665 B\xFCcher\': \'foo \uD834\uDF06 bar\'\n}' + +jsesc([ 'Ich ♥ Bücher', 'foo 𝌆 bar' ], { + 'compact': false +}); +// → '[\n\t\'Ich \u2665 B\xFCcher\',\n\t\'foo \uD834\uDF06 bar\'\n]' +``` + +This setting has no effect on the output for strings. + +#### `indent` + +The `indent` option takes a string value, and defaults to `'\t'`. When the `compact` setting is enabled (`true`), the value of the `indent` option is used to format the output for arrays and objects. + +```js +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'compact': false, + 'indent': '\t' // this is the default +}); +// → '{\n\t\'Ich \u2665 B\xFCcher\': \'foo \uD834\uDF06 bar\'\n}' + +jsesc({ 'Ich ♥ Bücher': 'foo 𝌆 bar' }, { + 'compact': false, + 'indent': ' ' +}); +// → '{\n \'Ich \u2665 B\xFCcher\': \'foo \uD834\uDF06 bar\'\n}' + +jsesc([ 'Ich ♥ Bücher', 'foo 𝌆 bar' ], { + 'compact': false, + 'indent': ' ' +}); +// → '[\n \'Ich \u2665 B\xFCcher\',\n\ t\'foo \uD834\uDF06 bar\'\n]' +``` + +This setting has no effect on the output for strings. + +#### `json` + +The `json` option takes a boolean value (`true` or `false`), and defaults to `false` (disabled). When enabled, the output is valid JSON. [Hexadecimal character escape sequences](http://mathiasbynens.be/notes/javascript-escapes#hexadecimal) and [the `\v` or `\0` escape sequences](http://mathiasbynens.be/notes/javascript-escapes#single) will not be used. Setting `json: true` implies `quotes: 'double', wrap: true, es6: false`, although these values can still be overridden if needed — but in such cases, the output won’t be valid JSON anymore. + +```js +jsesc('foo\x00bar\xFF\uFFFDbaz', { + 'json': true +}); +// → '"foo\\u0000bar\\u00FF\\uFFFDbaz"' + +jsesc({ 'foo\x00bar\xFF\uFFFDbaz': 'foo\x00bar\xFF\uFFFDbaz' }, { + 'json': true +}); +// → '{"foo\\u0000bar\\u00FF\\uFFFDbaz":"foo\\u0000bar\\u00FF\\uFFFDbaz"}' + +jsesc([ 'foo\x00bar\xFF\uFFFDbaz', 'foo\x00bar\xFF\uFFFDbaz' ], { + 'json': true +}); +// → '["foo\\u0000bar\\u00FF\\uFFFDbaz","foo\\u0000bar\\u00FF\\uFFFDbaz"]' + +// Values that are acceptable in JSON but aren’t strings, arrays, or object +// literals can’t be escaped, so they’ll just be preserved: +jsesc([ 'foo\x00bar', [1, '©', { 'foo': true, 'qux': null }], 42 ], { + 'json': true +}); +// → '["foo\\u0000bar",[1,"\\u00A9",{"foo":true,"qux":null}],42]' +// Values that aren’t allowed in JSON are run through `JSON.stringify()`: +jsesc([ undefined, -Infinity ], { + 'json': true +}); +// → '[null,null]' +``` + +**Note:** Using this option on objects or arrays that contain non-string values relies on `JSON.stringify()`. For legacy environments like IE ≤ 7, use [a `JSON` polyfill](http://bestiejs.github.io/json3/). + +### `jsesc.version` + +A string representing the semantic version number. + +### Using the `jsesc` binary + +To use the `jsesc` binary in your shell, simply install jsesc globally using npm: + +```bash +npm install -g jsesc +``` + +After that you will be able to escape strings from the command line: + +```bash +$ jsesc 'föo ♥ bår 𝌆 baz' +f\xF6o \u2665 b\xE5r \uD834\uDF06 baz +``` + +To escape arrays or objects containing string values, use the `-o`/`--object` option: + +```bash +$ jsesc --object '{ "föo": "♥", "bår": "𝌆 baz" }' +{'f\xF6o':'\u2665','b\xE5r':'\uD834\uDF06 baz'} +``` + +To prettify the output in such cases, use the `-p`/`--pretty` option: + +```bash +$ jsesc --pretty '{ "föo": "♥", "bår": "𝌆 baz" }' +{ + 'f\xF6o': '\u2665', + 'b\xE5r': '\uD834\uDF06 baz' +} +``` + +For valid JSON output, use the `-j`/`--json` option: + +```bash +$ jsesc --json --pretty '{ "föo": "♥", "bår": "𝌆 baz" }' +{ + "f\u00F6o": "\u2665", + "b\u00E5r": "\uD834\uDF06 baz" +} +``` + +Read a local JSON file, escape any non-ASCII symbols, and save the result to a new file: + +```bash +$ jsesc --json --object < data-raw.json > data-escaped.json +``` + +Or do the same with an online JSON file: + +```bash +$ curl -sL "http://git.io/aorKgQ" | jsesc --json --object > data-escaped.json +``` + +See `jsesc --help` for the full list of options. + +## Support + +This library has been tested in at least Chrome 27-29, Firefox 3-22, Safari 4-6, Opera 10-12, IE 6-10, Node.js v0.10.0, Narwhal 0.3.2, RingoJS 0.8-0.9, PhantomJS 1.9.0, and Rhino 1.7RC4. + +**Note:** Using the `json` option on objects or arrays that contain non-string values relies on `JSON.parse()`. For legacy environments like IE ≤ 7, use [a `JSON` polyfill](http://bestiejs.github.io/json3/). + +## Unit tests & code coverage + +After cloning this repository, run `npm install` to install the dependencies needed for development and testing. You may want to install Istanbul _globally_ using `npm install istanbul -g`. + +Once that’s done, you can run the unit tests in Node using `npm test` or `node tests/tests.js`. To run the tests in Rhino, Ringo, Narwhal, and web browsers as well, use `grunt test`. + +To generate the code coverage report, use `grunt cover`. + +## Author + +| [](https://twitter.com/mathias "Follow @mathias on Twitter") | +|---| +| [Mathias Bynens](http://mathiasbynens.be/) | + +## License + +This library is available under the [MIT](http://mths.be/mit) license. diff --git a/node_modules/regjsparser/node_modules/jsesc/bin/jsesc b/node_modules/regjsparser/node_modules/jsesc/bin/jsesc new file mode 100755 index 00000000..5900dd4a --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/bin/jsesc @@ -0,0 +1,138 @@ +#!/usr/bin/env node +(function() { + + var fs = require('fs'); + var stringEscape = require('../jsesc.js'); + var strings = process.argv.splice(2); + var stdin = process.stdin; + var data; + var timeout; + var isObject = false; + var options = {}; + var log = console.log; + + var main = function() { + var option = strings[0]; + + if (/^(?:-h|--help|undefined)$/.test(option)) { + log( + 'jsesc v%s - http://mths.be/jsesc', + stringEscape.version + ); + log([ + '\nUsage:\n', + '\tjsesc [string]', + '\tjsesc [-s | --single-quotes] [string]', + '\tjsesc [-d | --double-quotes] [string]', + '\tjsesc [-w | --wrap] [string]', + '\tjsesc [-e | --escape-everything] [string]', + '\tjsesc [-6 | --es6] [string]', + '\tjsesc [-j | --json] [string]', + '\tjsesc [-o | --object] [stringified_object]', // `JSON.parse()` the argument + '\tjsesc [-p | --pretty] [string]', // `compact: false` + '\tjsesc [-v | --version]', + '\tjsesc [-h | --help]', + '\nExamples:\n', + '\tjsesc \'f\xF6o \u2665 b\xE5r \uD834\uDF06 baz\'', + '\tjsesc --json \'f\xF6o \u2665 b\xE5r \uD834\uDF06 baz\'', + '\tjsesc --json --escape-everything \'f\xF6o \u2665 b\xE5r \uD834\uDF06 baz\'', + '\tjsesc --double-quotes --wrap \'f\xF6o \u2665 b\xE5r \uD834\uDF06 baz\'', + '\techo \'f\xF6o \u2665 b\xE5r \uD834\uDF06 baz\' | jsesc' + ].join('\n')); + return process.exit(1); + } + + if (/^(?:-v|--version)$/.test(option)) { + log('v%s', stringEscape.version); + return process.exit(1); + } + + strings.forEach(function(string) { + // Process options + if (/^(?:-s|--single-quotes)$/.test(string)) { + options.quotes = 'single'; + return; + } + if (/^(?:-d|--double-quotes)$/.test(string)) { + options.quotes = 'double'; + return; + } + if (/^(?:-w|--wrap)$/.test(string)) { + options.wrap = true; + return; + } + if (/^(?:-6|--es6)$/.test(string)) { + options.es6 = true; + return; + } + if (/^(?:-e|--escape-everything)$/.test(string)) { + options.escapeEverything = true; + return; + } + if (/^(?:-j|--json)$/.test(string)) { + options.json = true; + return; + } + if (/^(?:-o|--object)$/.test(string)) { + isObject = true; + return; + } + if (/^(?:-p|--pretty)$/.test(string)) { + isObject = true; + options.compact = false; + return; + } + + // Process string(s) + var result; + try { + if (isObject) { + string = JSON.parse(string); + } + result = stringEscape(string, options); + log(result); + } catch(error) { + log(error.message + '\n'); + log('Error: failed to escape.'); + log('If you think this is a bug in jsesc, please report it:'); + log('https://github.com/mathiasbynens/jsesc/issues/new'); + log( + '\nStack trace using jsesc@%s:\n', + stringEscape.version + ); + log(error.stack); + return process.exit(1); + } + }); + // Return with exit status 0 outside of the `forEach` loop, in case + // multiple strings were passed in. + return process.exit(0); + + }; + + if (stdin.isTTY) { + // handle shell arguments + main(); + } else { + // Either the script is called from within a non-TTY context, + // or `stdin` content is being piped in. + if (!process.stdout.isTTY) { // called from a non-TTY context + timeout = setTimeout(function() { + // if no piped data arrived after a while, handle shell arguments + main(); + }, 250); + } + + data = ''; + stdin.on('data', function(chunk) { + clearTimeout(timeout); + data += chunk; + }); + stdin.on('end', function() { + strings.push(data.trim()); + main(); + }); + stdin.resume(); + } + +}()); diff --git a/node_modules/regjsparser/node_modules/jsesc/jsesc.js b/node_modules/regjsparser/node_modules/jsesc/jsesc.js new file mode 100644 index 00000000..03bbd683 --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/jsesc.js @@ -0,0 +1,265 @@ +/*! http://mths.be/jsesc v0.5.0 by @mathias */ +;(function(root) { + + // Detect free variables `exports` + var freeExports = typeof exports == 'object' && exports; + + // Detect free variable `module` + var freeModule = typeof module == 'object' && module && + module.exports == freeExports && module; + + // Detect free variable `global`, from Node.js or Browserified code, + // and use it as `root` + var freeGlobal = typeof global == 'object' && global; + if (freeGlobal.global === freeGlobal || freeGlobal.window === freeGlobal) { + root = freeGlobal; + } + + /*--------------------------------------------------------------------------*/ + + var object = {}; + var hasOwnProperty = object.hasOwnProperty; + var forOwn = function(object, callback) { + var key; + for (key in object) { + if (hasOwnProperty.call(object, key)) { + callback(key, object[key]); + } + } + }; + + var extend = function(destination, source) { + if (!source) { + return destination; + } + forOwn(source, function(key, value) { + destination[key] = value; + }); + return destination; + }; + + var forEach = function(array, callback) { + var length = array.length; + var index = -1; + while (++index < length) { + callback(array[index]); + } + }; + + var toString = object.toString; + var isArray = function(value) { + return toString.call(value) == '[object Array]'; + }; + var isObject = function(value) { + // This is a very simple check, but it’s good enough for what we need. + return toString.call(value) == '[object Object]'; + }; + var isString = function(value) { + return typeof value == 'string' || + toString.call(value) == '[object String]'; + }; + var isFunction = function(value) { + // In a perfect world, the `typeof` check would be sufficient. However, + // in Chrome 1–12, `typeof /x/ == 'object'`, and in IE 6–8 + // `typeof alert == 'object'` and similar for other host objects. + return typeof value == 'function' || + toString.call(value) == '[object Function]'; + }; + + /*--------------------------------------------------------------------------*/ + + // http://mathiasbynens.be/notes/javascript-escapes#single + var singleEscapes = { + '"': '\\"', + '\'': '\\\'', + '\\': '\\\\', + '\b': '\\b', + '\f': '\\f', + '\n': '\\n', + '\r': '\\r', + '\t': '\\t' + // `\v` is omitted intentionally, because in IE < 9, '\v' == 'v'. + // '\v': '\\x0B' + }; + var regexSingleEscape = /["'\\\b\f\n\r\t]/; + + var regexDigit = /[0-9]/; + var regexWhitelist = /[ !#-&\(-\[\]-~]/; + + var jsesc = function(argument, options) { + // Handle options + var defaults = { + 'escapeEverything': false, + 'quotes': 'single', + 'wrap': false, + 'es6': false, + 'json': false, + 'compact': true, + 'indent': '\t', + '__indent__': '' + }; + var json = options && options.json; + if (json) { + defaults.quotes = 'double'; + defaults.wrap = true; + } + options = extend(defaults, options); + if (options.quotes != 'single' && options.quotes != 'double') { + options.quotes = 'single'; + } + var quote = options.quotes == 'double' ? '"' : '\''; + var compact = options.compact; + var indent = options.indent; + var oldIndent; + var newLine = compact ? '' : '\n'; + var result; + var isEmpty = true; + + if (json && argument && isFunction(argument.toJSON)) { + argument = argument.toJSON(); + } + + if (!isString(argument)) { + if (isArray(argument)) { + result = []; + options.wrap = true; + oldIndent = options.__indent__; + indent += oldIndent; + options.__indent__ = indent; + forEach(argument, function(value) { + isEmpty = false; + result.push( + (compact ? '' : indent) + + jsesc(value, options) + ); + }); + if (isEmpty) { + return '[]'; + } + return '[' + newLine + result.join(',' + newLine) + newLine + + (compact ? '' : oldIndent) + ']'; + } else if (!isObject(argument)) { + if (json) { + // For some values (e.g. `undefined`, `function` objects), + // `JSON.stringify(value)` returns `undefined` (which isn’t valid + // JSON) instead of `'null'`. + return JSON.stringify(argument) || 'null'; + } + return String(argument); + } else { // it’s an object + result = []; + options.wrap = true; + oldIndent = options.__indent__; + indent += oldIndent; + options.__indent__ = indent; + forOwn(argument, function(key, value) { + isEmpty = false; + result.push( + (compact ? '' : indent) + + jsesc(key, options) + ':' + + (compact ? '' : ' ') + + jsesc(value, options) + ); + }); + if (isEmpty) { + return '{}'; + } + return '{' + newLine + result.join(',' + newLine) + newLine + + (compact ? '' : oldIndent) + '}'; + } + } + + var string = argument; + // Loop over each code unit in the string and escape it + var index = -1; + var length = string.length; + var first; + var second; + var codePoint; + result = ''; + while (++index < length) { + var character = string.charAt(index); + if (options.es6) { + first = string.charCodeAt(index); + if ( // check if it’s the start of a surrogate pair + first >= 0xD800 && first <= 0xDBFF && // high surrogate + length > index + 1 // there is a next code unit + ) { + second = string.charCodeAt(index + 1); + if (second >= 0xDC00 && second <= 0xDFFF) { // low surrogate + // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae + codePoint = (first - 0xD800) * 0x400 + second - 0xDC00 + 0x10000; + result += '\\u{' + codePoint.toString(16).toUpperCase() + '}'; + index++; + continue; + } + } + } + if (!options.escapeEverything) { + if (regexWhitelist.test(character)) { + // It’s a printable ASCII character that is not `"`, `'` or `\`, + // so don’t escape it. + result += character; + continue; + } + if (character == '"') { + result += quote == character ? '\\"' : character; + continue; + } + if (character == '\'') { + result += quote == character ? '\\\'' : character; + continue; + } + } + if ( + character == '\0' && + !json && + !regexDigit.test(string.charAt(index + 1)) + ) { + result += '\\0'; + continue; + } + if (regexSingleEscape.test(character)) { + // no need for a `hasOwnProperty` check here + result += singleEscapes[character]; + continue; + } + var charCode = character.charCodeAt(0); + var hexadecimal = charCode.toString(16).toUpperCase(); + var longhand = hexadecimal.length > 2 || json; + var escaped = '\\' + (longhand ? 'u' : 'x') + + ('0000' + hexadecimal).slice(longhand ? -4 : -2); + result += escaped; + continue; + } + if (options.wrap) { + result = quote + result + quote; + } + return result; + }; + + jsesc.version = '0.5.0'; + + /*--------------------------------------------------------------------------*/ + + // Some AMD build optimizers, like r.js, check for specific condition patterns + // like the following: + if ( + typeof define == 'function' && + typeof define.amd == 'object' && + define.amd + ) { + define(function() { + return jsesc; + }); + } else if (freeExports && !freeExports.nodeType) { + if (freeModule) { // in Node.js or RingoJS v0.8.0+ + freeModule.exports = jsesc; + } else { // in Narwhal or RingoJS v0.7.0- + freeExports.jsesc = jsesc; + } + } else { // in Rhino or a web browser + root.jsesc = jsesc; + } + +}(this)); diff --git a/node_modules/regjsparser/node_modules/jsesc/man/jsesc.1 b/node_modules/regjsparser/node_modules/jsesc/man/jsesc.1 new file mode 100644 index 00000000..5257768f --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/man/jsesc.1 @@ -0,0 +1,90 @@ +.Dd October 25, 2013 +.Dt jsesc 1 +.Sh NAME +.Nm jsesc +.Nd escape strings for use in JavaScript string literals +.Sh SYNOPSIS +.Nm +.Op Fl s | -single-quotes Ar string +.br +.Op Fl d | -double-quotes Ar string +.br +.Op Fl w | -wrap Ar string +.br +.Op Fl 6 | -es6 Ar string +.br +.Op Fl e | -escape-everything Ar string +.br +.Op Fl j | -json Ar string +.br +.Op Fl p | -object Ar string +.br +.Op Fl p | -pretty Ar string +.br +.Op Fl v | -version +.br +.Op Fl h | -help +.Sh DESCRIPTION +.Nm +escapes strings for use in JavaScript string literals while generating the shortest possible valid ASCII-only output. +.Sh OPTIONS +.Bl -ohang -offset +.It Sy "-s, --single-quotes" +Escape any occurences of ' in the input string as \\', so that the output can be used in a JavaScript string literal wrapped in single quotes. +.It Sy "-d, --double-quotes" +Escape any occurences of " in the input string as \\", so that the output can be used in a JavaScript string literal wrapped in double quotes. +.It Sy "-w, --wrap" +Make sure the output is a valid JavaScript string literal wrapped in quotes. The type of quotes can be specified using the +.Ar -s | --single-quotes +or +.Ar -d | --double-quotes +settings. +.It Sy "-6, --es6" +Escape any astral Unicode symbols using ECMAScript 6 Unicode code point escape sequences. +.It Sy "-e, --escape-everything" +Escape all the symbols in the output, even printable ASCII symbols. +.It Sy "-j, --json" +Make sure the output is valid JSON. Hexadecimal character escape sequences and the \\v or \\0 escape sequences will not be used. Setting this flag enables the +.Ar -d | --double-quotes +and +.Ar -w | --wrap +settings. +.It Sy "-o, --object" +Treat the input as a JavaScript object rather than a string. Accepted values are flat arrays containing only string values, and flat objects containing only string values. +.It Sy "-p, --pretty" +Pretty-print the output for objects, using whitespace to make it more readable. Setting this flag enables the +.Ar -o | --object +setting. +.It Sy "-v, --version" +Print jsesc's version. +.It Sy "-h, --help" +Show the help screen. +.El +.Sh EXIT STATUS +The +.Nm jsesc +utility exits with one of the following values: +.Pp +.Bl -tag -width flag -compact +.It Li 0 +.Nm +successfully escaped the given string and printed the result. +.It Li 1 +.Nm +wasn't instructed to escape anything (for example, the +.Ar --help +flag was set); or, an error occurred. +.El +.Sh EXAMPLES +.Bl -ohang -offset +.It Sy "jsesc 'foo bar baz'" +Print an escaped version of the given string. +.It Sy echo\ 'foo bar baz'\ |\ jsesc +Print an escaped version of the string that gets piped in. +.El +.Sh BUGS +jsesc's bug tracker is located at <https://github.com/mathiasbynens/jsesc/issues>. +.Sh AUTHOR +Mathias Bynens <http://mathiasbynens.be/> +.Sh WWW +<http://mths.be/jsesc> diff --git a/node_modules/regjsparser/node_modules/jsesc/package.json b/node_modules/regjsparser/node_modules/jsesc/package.json new file mode 100644 index 00000000..1216eefd --- /dev/null +++ b/node_modules/regjsparser/node_modules/jsesc/package.json @@ -0,0 +1,55 @@ +{ + "name": "jsesc", + "version": "0.5.0", + "description": "A JavaScript library for escaping JavaScript strings while generating the shortest possible valid output.", + "homepage": "http://mths.be/jsesc", + "main": "jsesc.js", + "bin": "bin/jsesc", + "man": "man/jsesc.1", + "keywords": [ + "string", + "escape", + "javascript", + "tool" + ], + "licenses": [ + { + "type": "MIT", + "url": "http://mths.be/mit" + } + ], + "author": { + "name": "Mathias Bynens", + "url": "http://mathiasbynens.be/" + }, + "repository": { + "type": "git", + "url": "https://github.com/mathiasbynens/jsesc.git" + }, + "bugs": { + "url": "https://github.com/mathiasbynens/jsesc/issues" + }, + "files": [ + "LICENSE-MIT.txt", + "jsesc.js", + "bin/", + "man/" + ], + "directories": { + "test": "tests" + }, + "scripts": { + "test": "node tests/tests.js" + }, + "devDependencies": { + "coveralls": "^2.10.0", + "grunt": "^0.4.5", + "grunt-shell": "^0.7.0", + "grunt-template": "^0.2.3", + "istanbul": "^0.3.0", + "qunit-extras": "^1.2.0", + "qunitjs": "~1.11.0", + "regenerate": "^0.6.2", + "requirejs": "^2.1.14" + } +} diff --git a/node_modules/regjsparser/package.json b/node_modules/regjsparser/package.json new file mode 100644 index 00000000..df69005a --- /dev/null +++ b/node_modules/regjsparser/package.json @@ -0,0 +1,37 @@ +{ + "name": "regjsparser", + "version": "0.9.1", + "author": "'Julian Viereck' <julian.viereck@gmail.com>", + "license": "BSD-2-Clause", + "main": "./parser", + "types": "./parser.d.ts", + "bin": "bin/parser", + "homepage": "https://github.com/jviereck/regjsparser", + "repository": { + "type": "git", + "url": "git@github.com:jviereck/regjsparser.git" + }, + "scripts": { + "lint": "eslint --ext .js --max-warnings 0 .", + "test": "run-p test:* && npm run lint", + "test:src": "node test/index.js", + "test:types": "tsc test/types.ts --noEmit" + }, + "files": [ + "bin/", + "LICENSE.BSD", + "parser.js", + "parser.d.ts", + "README.md" + ], + "dependencies": { + "jsesc": "~0.5.0" + }, + "devDependencies": { + "eslint": "^8.8.0", + "npm-run-all": "^4.1.5", + "regenerate": "~1.0.1", + "typescript": "^4.5.2", + "unicode-11.0.0": "^0.7.8" + } +} diff --git a/node_modules/regjsparser/parser.d.ts b/node_modules/regjsparser/parser.d.ts new file mode 100644 index 00000000..4edef64f --- /dev/null +++ b/node_modules/regjsparser/parser.d.ts @@ -0,0 +1,183 @@ +type _If<Test, Then, Else> = Test extends true ? Then : Else; + +export type Features = { + lookbehind?: boolean; + namedGroups?: boolean; + unicodePropertyEscape?: boolean; + unicodeSet?: boolean; + modifiers?: boolean; +}; + +export type AstNodeType = + | "alternative" + | "anchor" + | "characterClass" + | "characterClassEscape" + | "characterClassRange" + | "disjunction" + | "dot" + | "group" + | "quantifier" + | "reference" + | "unicodePropertyEscape" + | "value"; + +export type Base<T extends AstNodeType> = { + range: [number, number]; + raw: string; + type: T; +}; + +export type AstNode<F extends Features = {}> = + | Alternative<F> + | Anchor + | CharacterClass<F> + | CharacterClassEscape + | CharacterClassRange + | Disjunction<F> + | Dot + | Group<F> + | Quantifier<F> + | Reference<F> + | _If<F["unicodePropertyEscape"], UnicodePropertyEscape, never> + | Value; + +export type RootNode<F extends Features = {}> = Exclude< + AstNode<F>, + CharacterClassRange +>; + +export type Anchor = Base<"anchor"> & { + kind: "boundary" | "end" | "not-boundary" | "start"; +}; + +export type CharacterClassEscape = Base<"characterClassEscape"> & { + value: string; +}; + +export type Value = Base<"value"> & { + codePoint: number; + kind: + | "controlLetter" + | "hexadecimalEscape" + | "identifier" + | "null" + | "octal" + | "singleEscape" + | "symbol" + | "unicodeCodePointEscape" + | "unicodeEscape"; +}; + +export type Identifier = Base<"value"> & { + value: string; +}; + +export type Alternative<F extends Features = {}> = Base<"alternative"> & { + body: RootNode<F>[]; +}; + +export type CharacterClassRange = Base<"characterClassRange"> & { + max: Value; + min: Value; +}; + +export type UnicodePropertyEscape = Base<"unicodePropertyEscape"> & { + negative: boolean; + value: string; +}; + +export type CharacterClassBody = + | CharacterClassEscape + | CharacterClassRange + | UnicodePropertyEscape + | Value; + +export type CharacterClass<F extends Features = {}> = Base<"characterClass"> & { + body: CharacterClassBody[]; + negative: boolean; + kind: "union" | _If<F["unicodeSet"], "intersection" | "subtraction", never>; +}; + +export type ModifierFlags = { + enabling: string, + disabling: string +} + +export type NonCapturingGroup<F extends Features = {}> = Base<"group"> & + ( + | { + behavior: + | "lookahead" + | "lookbehind" + | "negativeLookahead" + | "negativeLookbehind"; + body: RootNode<F>[]; + } + | ({ + behavior: "ignore"; + body: RootNode<F>[]; + } & _If< + F["modifiers"], + { + modifierFlags?: ModifierFlags; + }, + { + modifierFlags: undefined; + } + >) + ); + + +export type CapturingGroup<F extends Features = {}> = Base<"group"> & { + behavior: "normal"; + body: RootNode<F>[]; +} & _If< + F["namedGroups"], + { + name?: Identifier; + }, + { + name: undefined; + } + >; + +export type Group<F extends Features = {}> = + | CapturingGroup<F> + | NonCapturingGroup<F>; + +export type Quantifier<F extends Features = {}> = Base<"quantifier"> & { + body: [RootNode<F>]; + greedy: boolean; + max?: number; + min: number; + symbol?: '?' | '*' | '+'; +}; + +export type Disjunction<F extends Features = {}> = Base<"disjunction"> & { + body: [RootNode<F>, RootNode<F>, ...RootNode<F>[]]; +}; + +export type Dot = Base<"dot">; + +export type NamedReference = Base<"reference"> & { + matchIndex: undefined; + name: Identifier; +}; + +export type IndexReference = Base<"reference"> & { + matchIndex: number; + name: undefined; +}; + +export type Reference<F extends Features = {}> = _If< + F["namedGroups"], + NamedReference, + IndexReference +>; + +export function parse<F extends Features = {}>( + str: string, + flags: string, + features?: F +): RootNode<F>; diff --git a/node_modules/regjsparser/parser.js b/node_modules/regjsparser/parser.js new file mode 100644 index 00000000..6f20b712 --- /dev/null +++ b/node_modules/regjsparser/parser.js @@ -0,0 +1,1634 @@ +// regjsparser +// +// ================================================================== +// +// See ECMA-262 Standard: 15.10.1 +// +// NOTE: The ECMA-262 standard uses the term "Assertion" for /^/. Here the +// term "Anchor" is used. +// +// Pattern :: +// Disjunction +// +// Disjunction :: +// Alternative +// Alternative | Disjunction +// +// Alternative :: +// [empty] +// Alternative Term +// +// Term :: +// Anchor +// Atom +// Atom Quantifier +// +// Anchor :: +// ^ +// $ +// \ b +// \ B +// ( ? = Disjunction ) +// ( ? ! Disjunction ) +// ( ? < = Disjunction ) +// ( ? < ! Disjunction ) +// +// Quantifier :: +// QuantifierPrefix +// QuantifierPrefix ? +// +// QuantifierPrefix :: +// * +// + +// ? +// { DecimalDigits } +// { DecimalDigits , } +// { DecimalDigits , DecimalDigits } +// +// Atom :: +// PatternCharacter +// . +// \ AtomEscape +// CharacterClass +// ( GroupSpecifier Disjunction ) +// ( ? : Disjunction ) +// +// PatternCharacter :: +// SourceCharacter but not any of: ^ $ \ . * + ? ( ) [ ] { } | +// +// AtomEscape :: +// DecimalEscape +// CharacterClassEscape +// CharacterEscape +// k GroupName +// +// CharacterEscape[U] :: +// ControlEscape +// c ControlLetter +// HexEscapeSequence +// RegExpUnicodeEscapeSequence[?U] (ES6) +// IdentityEscape[?U] +// +// ControlEscape :: +// one of f n r t v +// ControlLetter :: +// one of +// a b c d e f g h i j k l m n o p q r s t u v w x y z +// A B C D E F G H I J K L M N O P Q R S T U V W X Y Z +// +// IdentityEscape :: +// SourceCharacter but not c +// +// DecimalEscape :: +// DecimalIntegerLiteral [lookahead ∉ DecimalDigit] +// +// CharacterClassEscape :: +// one of d D s S w W +// +// CharacterClass :: +// [ [lookahead ∉ {^}] ClassRanges ] +// [ ^ ClassRanges ] +// +// ClassRanges :: +// [empty] +// [~V] NonemptyClassRanges +// [+V] ClassContents +// +// NonemptyClassRanges :: +// ClassAtom +// ClassAtom NonemptyClassRangesNoDash +// ClassAtom - ClassAtom ClassRanges +// +// NonemptyClassRangesNoDash :: +// ClassAtom +// ClassAtomNoDash NonemptyClassRangesNoDash +// ClassAtomNoDash - ClassAtom ClassRanges +// +// ClassAtom :: +// - +// ClassAtomNoDash +// +// ClassAtomNoDash :: +// SourceCharacter but not one of \ or ] or - +// \ ClassEscape +// +// ClassEscape :: +// DecimalEscape +// b +// CharacterEscape +// CharacterClassEscape +// +// GroupSpecifier :: +// [empty] +// ? GroupName +// +// GroupName :: +// < RegExpIdentifierName > +// +// RegExpIdentifierName :: +// RegExpIdentifierStart +// RegExpIdentifierName RegExpIdentifierContinue +// +// RegExpIdentifierStart :: +// UnicodeIDStart +// $ +// _ +// \ RegExpUnicodeEscapeSequence +// +// RegExpIdentifierContinue :: +// UnicodeIDContinue +// $ +// _ +// \ RegExpUnicodeEscapeSequence +// <ZWNJ> +// <ZWJ> +// +// -------------------------------------------------------------- +// NOTE: The following productions refer to the "set notation and +// properties of strings" proposal. +// https://github.com/tc39/proposal-regexp-set-notation +// -------------------------------------------------------------- +// +// ClassContents :: +// ClassUnion +// ClassIntersection +// ClassSubtraction +// +// ClassUnion :: +// ClassRange ClassUnion? +// ClassOperand ClassUnion? +// +// ClassIntersection :: +// ClassOperand && [lookahead ≠ &] ClassOperand +// ClassIntersection && [lookahead ≠ &] ClassOperand +// +// ClassSubtraction :: +// ClassOperand -- ClassOperand +// ClassSubtraction -- ClassOperand +// +// ClassOperand :: +// ClassCharacter +// ClassStrings +// NestedClass +// +// NestedClass :: +// [ [lookahead ≠ ^] ClassRanges[+U,+V] ] +// [ ^ ClassRanges[+U,+V] ] +// \ CharacterClassEscape[+U, +V] +// +// ClassRange :: +// ClassCharacter - ClassCharacter +// +// ClassCharacter :: +// [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter +// \ CharacterEscape[+U] +// \ ClassHalfOfDouble +// \ b +// +// ClassSyntaxCharacter :: +// one of ( ) [ ] { } / - \ | +// +// ClassStrings :: +// ( ClassString MoreClassStrings? ) +// +// MoreClassStrings :: +// | ClassString MoreClassStrings? +// +// ClassString :: +// [empty] +// NonEmptyClassString +// +// NonEmptyClassString :: +// ClassCharacter NonEmptyClassString? +// +// ClassReservedDouble :: +// one of && !! ## $$ %% ** ++ ,, .. :: ;; << == >> ?? @@ ^^ __ `` ~~ +// +// ClassHalfOfDouble :: +// one of & - ! # % , : ; < = > @ _ ` ~ +// +// -------------------------------------------------------------- +// NOTE: The following productions refer to the +// "Regular Expression Pattern Modifiers for ECMAScript" proposal. +// https://github.com/tc39/proposal-regexp-modifiers +// -------------------------------------------------------------- +// +// Atom :: +// ( ? RegularExpressionFlags : Disjunction ) +// ( ? RegularExpressionFlags - RegularExpressionFlags : Disjunction ) +// + +"use strict"; +(function() { + + var fromCodePoint = String.fromCodePoint || (function() { + // Implementation taken from + // https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/fromCodePoint + + var stringFromCharCode = String.fromCharCode; + var floor = Math.floor; + + return function fromCodePoint() { + var MAX_SIZE = 0x4000; + var codeUnits = []; + var highSurrogate; + var lowSurrogate; + var index = -1; + var length = arguments.length; + if (!length) { + return ''; + } + var result = ''; + while (++index < length) { + var codePoint = Number(arguments[index]); + if ( + !isFinite(codePoint) || // `NaN`, `+Infinity`, or `-Infinity` + codePoint < 0 || // not a valid Unicode code point + codePoint > 0x10FFFF || // not a valid Unicode code point + floor(codePoint) != codePoint // not an integer + ) { + throw RangeError('Invalid code point: ' + codePoint); + } + if (codePoint <= 0xFFFF) { // BMP code point + codeUnits.push(codePoint); + } else { // Astral code point; split in surrogate halves + // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae + codePoint -= 0x10000; + highSurrogate = (codePoint >> 10) + 0xD800; + lowSurrogate = (codePoint % 0x400) + 0xDC00; + codeUnits.push(highSurrogate, lowSurrogate); + } + if (index + 1 == length || codeUnits.length > MAX_SIZE) { + result += stringFromCharCode.apply(null, codeUnits); + codeUnits.length = 0; + } + } + return result; + }; + }()); + + function parse(str, flags, features) { + if (!features) { + features = {}; + } + function addRaw(node) { + node.raw = str.substring(node.range[0], node.range[1]); + return node; + } + + function updateRawStart(node, start) { + node.range[0] = start; + return addRaw(node); + } + + function createAnchor(kind, rawLength) { + return addRaw({ + type: 'anchor', + kind: kind, + range: [ + pos - rawLength, + pos + ] + }); + } + + function createValue(kind, codePoint, from, to) { + return addRaw({ + type: 'value', + kind: kind, + codePoint: codePoint, + range: [from, to] + }); + } + + function createEscaped(kind, codePoint, value, fromOffset) { + fromOffset = fromOffset || 0; + return createValue(kind, codePoint, pos - (value.length + fromOffset), pos); + } + + function createCharacter(matches) { + var _char = matches[0]; + var first = _char.charCodeAt(0); + if (isUnicodeMode) { + var second; + if (_char.length === 1 && first >= 0xD800 && first <= 0xDBFF) { + second = lookahead().charCodeAt(0); + if (second >= 0xDC00 && second <= 0xDFFF) { + // Unicode surrogate pair + pos++; + return createValue( + 'symbol', + (first - 0xD800) * 0x400 + second - 0xDC00 + 0x10000, + pos - 2, pos); + } + } + } + return createValue('symbol', first, pos - 1, pos); + } + + function createDisjunction(alternatives, from, to) { + return addRaw({ + type: 'disjunction', + body: alternatives, + range: [ + from, + to + ] + }); + } + + function createDot() { + return addRaw({ + type: 'dot', + range: [ + pos - 1, + pos + ] + }); + } + + function createCharacterClassEscape(value) { + return addRaw({ + type: 'characterClassEscape', + value: value, + range: [ + pos - 2, + pos + ] + }); + } + + function createReference(matchIndex) { + return addRaw({ + type: 'reference', + matchIndex: parseInt(matchIndex, 10), + range: [ + pos - 1 - matchIndex.length, + pos + ] + }); + } + + function createNamedReference(name) { + return addRaw({ + type: 'reference', + name: name, + range: [ + name.range[0] - 3, + pos + ] + }); + } + + function createGroup(behavior, disjunction, from, to) { + return addRaw({ + type: 'group', + behavior: behavior, + body: disjunction, + range: [ + from, + to + ] + }); + } + + function createQuantifier(min, max, from, to, symbol) { + if (to == null) { + from = pos - 1; + to = pos; + } + + return addRaw({ + type: 'quantifier', + min: min, + max: max, + greedy: true, + body: null, // set later on + symbol: symbol, + range: [ + from, + to + ] + }); + } + + function createAlternative(terms, from, to) { + return addRaw({ + type: 'alternative', + body: terms, + range: [ + from, + to + ] + }); + } + + function createCharacterClass(contents, negative, from, to) { + return addRaw({ + type: 'characterClass', + kind: contents.kind, + body: contents.body, + negative: negative, + range: [ + from, + to + ] + }); + } + + function createClassRange(min, max, from, to) { + // See 15.10.2.15: + if (min.codePoint > max.codePoint) { + bail('invalid range in character class', min.raw + '-' + max.raw, from, to); + } + + return addRaw({ + type: 'characterClassRange', + min: min, + max: max, + range: [ + from, + to + ] + }); + } + + function createClassStrings(strings, from, to) { + return addRaw({ + type: 'classStrings', + strings: strings, + range: [from, to] + }); + } + + function createClassString(characters, from, to) { + return addRaw({ + type: 'classString', + characters: characters, + range: [from, to] + }); + } + + function flattenBody(body) { + if (body.type === 'alternative') { + return body.body; + } else { + return [body]; + } + } + + function incr(amount) { + amount = (amount || 1); + var res = str.substring(pos, pos + amount); + pos += (amount || 1); + return res; + } + + function skip(value) { + if (!match(value)) { + bail('character', value); + } + } + + function match(value) { + if (str.indexOf(value, pos) === pos) { + return incr(value.length); + } + } + + function lookahead() { + return str[pos]; + } + + function current(value) { + return str.indexOf(value, pos) === pos; + } + + function next(value) { + return str[pos + 1] === value; + } + + function matchReg(regExp) { + var subStr = str.substring(pos); + var res = subStr.match(regExp); + if (res) { + res.range = []; + res.range[0] = pos; + incr(res[0].length); + res.range[1] = pos; + } + return res; + } + + function parseDisjunction() { + // Disjunction :: + // Alternative + // Alternative | Disjunction + var res = [], from = pos; + res.push(parseAlternative()); + + while (match('|')) { + res.push(parseAlternative()); + } + + if (res.length === 1) { + return res[0]; + } + + return createDisjunction(res, from, pos); + } + + function parseAlternative() { + var res = [], from = pos; + var term; + + // Alternative :: + // [empty] + // Alternative Term + while (term = parseTerm()) { + res.push(term); + } + + if (res.length === 1) { + return res[0]; + } + + return createAlternative(res, from, pos); + } + + function parseTerm() { + // Term :: + // Anchor + // Atom + // Atom Quantifier + + if (pos >= str.length || current('|') || current(')')) { + return null; /* Means: The term is empty */ + } + + var anchor = parseAnchor(); + + if (anchor) { + return anchor; + } + + var atom = parseAtomAndExtendedAtom(); + var quantifier; + if (!atom) { + // Check if a quantifier is following. A quantifier without an atom + // is an error. + var pos_backup = pos + quantifier = parseQuantifier() || false; + if (quantifier) { + pos = pos_backup + bail('Expected atom'); + } + + // If no unicode flag, then try to parse ExtendedAtom -> ExtendedPatternCharacter. + // ExtendedPatternCharacter + var res; + if (!isUnicodeMode && (res = matchReg(/^{/))) { + atom = createCharacter(res); + } else { + bail('Expected atom'); + } + } + quantifier = parseQuantifier() || false; + if (quantifier) { + quantifier.body = flattenBody(atom); + // The quantifier contains the atom. Therefore, the beginning of the + // quantifier range is given by the beginning of the atom. + updateRawStart(quantifier, atom.range[0]); + return quantifier; + } + return atom; + } + + function parseGroup(matchA, typeA, matchB, typeB) { + var type = null, from = pos; + + if (match(matchA)) { + type = typeA; + } else if (match(matchB)) { + type = typeB; + } else { + return false; + } + + return finishGroup(type, from); + } + + function finishGroup(type, from) { + var body = parseDisjunction(); + if (!body) { + bail('Expected disjunction'); + } + skip(')'); + var group = createGroup(type, flattenBody(body), from, pos); + + if (type == 'normal') { + // Keep track of the number of closed groups. This is required for + // parseDecimalEscape(). In case the string is parsed a second time the + // value already holds the total count and no incrementation is required. + if (firstIteration) { + closedCaptureCounter++; + } + } + return group; + } + + function parseAnchor() { + // Anchor :: + // ^ + // $ + // \ b + // \ B + // ( ? = Disjunction ) + // ( ? ! Disjunction ) + + if (match('^')) { + return createAnchor('start', 1 /* rawLength */); + } else if (match('$')) { + return createAnchor('end', 1 /* rawLength */); + } else if (match('\\b')) { + return createAnchor('boundary', 2 /* rawLength */); + } else if (match('\\B')) { + return createAnchor('not-boundary', 2 /* rawLength */); + } else { + return parseGroup('(?=', 'lookahead', '(?!', 'negativeLookahead'); + } + } + + function parseQuantifier() { + // Quantifier :: + // QuantifierPrefix + // QuantifierPrefix ? + // + // QuantifierPrefix :: + // * + // + + // ? + // { DecimalDigits } + // { DecimalDigits , } + // { DecimalDigits , DecimalDigits } + + var res, from = pos; + var quantifier; + var min, max; + + if (match('*')) { + quantifier = createQuantifier(0, undefined, undefined, undefined, '*'); + } + else if (match('+')) { + quantifier = createQuantifier(1, undefined, undefined, undefined, "+"); + } + else if (match('?')) { + quantifier = createQuantifier(0, 1, undefined, undefined, "?"); + } + else if (res = matchReg(/^\{([0-9]+)\}/)) { + min = parseInt(res[1], 10); + quantifier = createQuantifier(min, min, res.range[0], res.range[1]); + } + else if (res = matchReg(/^\{([0-9]+),\}/)) { + min = parseInt(res[1], 10); + quantifier = createQuantifier(min, undefined, res.range[0], res.range[1]); + } + else if (res = matchReg(/^\{([0-9]+),([0-9]+)\}/)) { + min = parseInt(res[1], 10); + max = parseInt(res[2], 10); + if (min > max) { + bail('numbers out of order in {} quantifier', '', from, pos); + } + quantifier = createQuantifier(min, max, res.range[0], res.range[1]); + } + + if ((min && !Number.isSafeInteger(min)) || (max && !Number.isSafeInteger(max))) { + bail("iterations outside JS safe integer range in quantifier", "", from, pos); + } + + if (quantifier) { + if (match('?')) { + quantifier.greedy = false; + quantifier.range[1] += 1; + } + } + + return quantifier; + } + + function parseAtomAndExtendedAtom() { + // Parsing Atom and ExtendedAtom together due to redundancy. + // ExtendedAtom is defined in Apendix B of the ECMA-262 standard. + // + // SEE: https://www.ecma-international.org/ecma-262/10.0/index.html#prod-annexB-ExtendedPatternCharacter + // + // Atom :: + // PatternCharacter + // . + // \ AtomEscape + // CharacterClass + // ( GroupSpecifier Disjunction ) + // ( ? RegularExpressionFlags : Disjunction ) + // ( ? RegularExpressionFlags - RegularExpressionFlags : Disjunction ) + // ExtendedAtom :: + // ExtendedPatternCharacter + // ExtendedPatternCharacter :: + // SourceCharacter but not one of ^$\.*+?()[| + + var res; + + // jviereck: allow ']', '}' here as well to be compatible with browser's + // implementations: ']'.match(/]/); + if (res = matchReg(/^[^^$\\.*+?()[\]{}|]/)) { + // PatternCharacter + return createCharacter(res); + } + else if (!isUnicodeMode && (res = matchReg(/^(?:]|})/))) { + // ExtendedPatternCharacter, first part. See parseTerm. + return createCharacter(res); + } + else if (match('.')) { + // . + return createDot(); + } + else if (match('\\')) { + // \ AtomEscape + res = parseAtomEscape(); + if (!res) { + if (!isUnicodeMode && lookahead() == 'c') { + // B.1.4 ExtendedAtom + // \[lookahead = c] + return createValue('symbol', 92, pos - 1, pos); + } + bail('atomEscape'); + } + return res; + } + else if (res = parseCharacterClass()) { + return res; + } + else if (features.lookbehind && (res = parseGroup('(?<=', 'lookbehind', '(?<!', 'negativeLookbehind'))) { + return res; + } + else if (features.namedGroups && match("(?<")) { + var name = parseIdentifier(); + skip(">"); + var group = finishGroup("normal", name.range[0] - 3); + group.name = name; + return group; + } + else if (features.modifiers && str.indexOf("(?") == pos && str[pos+2] != ":") { + return parseModifiersGroup(); + } + else { + // ( Disjunction ) + // ( ? : Disjunction ) + return parseGroup('(?:', 'ignore', '(', 'normal'); + } + } + + function parseModifiersGroup() { + function hasDupChar(str) { + var i = 0; + while (i < str.length) { + if (str.indexOf(str[i], i + 1) != -1) { + return true; + } + i++; + } + return false; + } + + var from = pos; + incr(2); + + var enablingFlags = matchReg(/^[sim]+/); + var disablingFlags; + if(match("-")){ + disablingFlags = matchReg(/^[sim]+/); + if (!disablingFlags) { + bail('Invalid flags for modifiers group'); + } + } else if(!enablingFlags){ + bail('Invalid flags for modifiers group'); + } + + enablingFlags = enablingFlags ? enablingFlags[0] : ""; + disablingFlags = disablingFlags ? disablingFlags[0] : ""; + + var flags = enablingFlags + disablingFlags; + if(flags.length > 3 || hasDupChar(flags)) { + bail('flags cannot be duplicated for modifiers group'); + } + + skip(":"); + + var modifiersGroup = finishGroup("ignore", from); + + modifiersGroup.modifierFlags = { + enabling: enablingFlags, + disabling: disablingFlags + }; + + return modifiersGroup; + } + + function parseUnicodeSurrogatePairEscape(firstEscape) { + if (isUnicodeMode) { + var first, second; + if (firstEscape.kind == 'unicodeEscape' && + (first = firstEscape.codePoint) >= 0xD800 && first <= 0xDBFF && + current('\\') && next('u') ) { + var prevPos = pos; + pos++; + var secondEscape = parseClassEscape(); + if (secondEscape.kind == 'unicodeEscape' && + (second = secondEscape.codePoint) >= 0xDC00 && second <= 0xDFFF) { + // Unicode surrogate pair + firstEscape.range[1] = secondEscape.range[1]; + firstEscape.codePoint = (first - 0xD800) * 0x400 + second - 0xDC00 + 0x10000; + firstEscape.type = 'value'; + firstEscape.kind = 'unicodeCodePointEscape'; + addRaw(firstEscape); + } + else { + pos = prevPos; + } + } + } + return firstEscape; + } + + function parseClassEscape() { + return parseAtomEscape(true); + } + + function parseAtomEscape(insideCharacterClass) { + // AtomEscape :: + // DecimalEscape + // CharacterEscape + // CharacterClassEscape + // k GroupName + + var res, from = pos; + + res = parseDecimalEscape(insideCharacterClass) || parseNamedReference(); + if (res) { + return res; + } + + // For ClassEscape + if (insideCharacterClass) { + // b + if (match('b')) { + // 15.10.2.19 + // The production ClassEscape :: b evaluates by returning the + // CharSet containing the one character <BS> (Unicode value 0008). + return createEscaped('singleEscape', 0x0008, '\\b'); + } else if (match('B')) { + bail('\\B not possible inside of CharacterClass', '', from); + } else if (!isUnicodeMode && (res = matchReg(/^c([0-9])/))) { + // B.1.4 + // c ClassControlLetter, ClassControlLetter = DecimalDigit + return createEscaped('controlLetter', res[1] + 16, res[1], 2); + } else if (!isUnicodeMode && (res = matchReg(/^c_/))) { + // B.1.4 + // c ClassControlLetter, ClassControlLetter = _ + return createEscaped('controlLetter', 31, '_', 2); + } + // [+U] - + if (isUnicodeMode && match('-')) { + return createEscaped('singleEscape', 0x002d, '\\-'); + } + } + + res = parseCharacterClassEscape() || parseCharacterEscape(); + + return res; + } + + + function parseDecimalEscape(insideCharacterClass) { + // DecimalEscape :: + // DecimalIntegerLiteral [lookahead ∉ DecimalDigit] + + var res, match, from = pos; + + if (res = matchReg(/^(?!0)\d+/)) { + match = res[0]; + var refIdx = parseInt(res[0], 10); + if (refIdx <= closedCaptureCounter && !insideCharacterClass) { + // If the number is smaller than the normal-groups found so + // far, then it is a reference... + return createReference(res[0]); + } else { + // ... otherwise it needs to be interpreted as a octal (if the + // number is in an octal format). If it is NOT octal format, + // then the slash is ignored and the number is matched later + // as normal characters. + + // Recall the negative decision to decide if the input must be parsed + // a second time with the total normal-groups. + backrefDenied.push(refIdx); + + // \1 octal escapes are disallowed in unicode mode, but they might + // be references to groups which haven't been parsed yet. + // We must parse a second time to determine if \1 is a reference + // or an octal scape, and then we can report the error. + if (firstIteration) { + shouldReparse = true; + } else { + bailOctalEscapeIfUnicode(from, pos); + } + + // Reset the position again, as maybe only parts of the previous + // matched numbers are actual octal numbers. E.g. in '019' only + // the '01' should be matched. + incr(-res[0].length); + if (res = matchReg(/^[0-7]{1,3}/)) { + return createEscaped('octal', parseInt(res[0], 8), res[0], 1); + } else { + // If we end up here, we have a case like /\91/. Then the + // first slash is to be ignored and the 9 & 1 to be treated + // like ordinary characters. Create a character for the + // first number only here - other number-characters + // (if available) will be matched later. + res = createCharacter(matchReg(/^[89]/)); + return updateRawStart(res, res.range[0] - 1); + } + } + } + // Only allow octal numbers in the following. All matched numbers start + // with a zero (if the do not, the previous if-branch is executed). + // If the number is not octal format and starts with zero (e.g. `091`) + // then only the zeros `0` is treated here and the `91` are ordinary + // characters. + // Example: + // /\091/.exec('\091')[0].length === 3 + else if (res = matchReg(/^[0-7]{1,3}/)) { + match = res[0]; + if (match !== '0') { + bailOctalEscapeIfUnicode(from, pos); + } + if (/^0{1,3}$/.test(match)) { + // If they are all zeros, then only take the first one. + return createEscaped('null', 0x0000, '0', match.length); + } else { + return createEscaped('octal', parseInt(match, 8), match, 1); + } + } + return false; + } + + function bailOctalEscapeIfUnicode(from, pos) { + if (isUnicodeMode) { + bail("Invalid decimal escape in unicode mode", null, from, pos); + } + } + + function parseCharacterClassEscape() { + // CharacterClassEscape :: one of d D s S w W + var res; + if (res = matchReg(/^[dDsSwW]/)) { + return createCharacterClassEscape(res[0]); + } else if (features.unicodePropertyEscape && isUnicodeMode && (res = matchReg(/^([pP])\{([^\}]+)\}/))) { + // https://github.com/jviereck/regjsparser/issues/77 + return addRaw({ + type: 'unicodePropertyEscape', + negative: res[1] === 'P', + value: res[2], + range: [res.range[0] - 1, res.range[1]], + raw: res[0] + }); + } else if (features.unicodeSet && hasUnicodeSetFlag && match('q{')) { + return parseClassStrings(); + } + return false; + } + + function parseNamedReference() { + if (features.namedGroups && matchReg(/^k<(?=.*?>)/)) { + var name = parseIdentifier(); + skip('>'); + return createNamedReference(name); + } + } + + function parseRegExpUnicodeEscapeSequence() { + var res; + if (res = matchReg(/^u([0-9a-fA-F]{4})/)) { + // UnicodeEscapeSequence + return parseUnicodeSurrogatePairEscape( + createEscaped('unicodeEscape', parseInt(res[1], 16), res[1], 2) + ); + } else if (isUnicodeMode && (res = matchReg(/^u\{([0-9a-fA-F]+)\}/))) { + // RegExpUnicodeEscapeSequence (ES6 Unicode code point escape) + return createEscaped('unicodeCodePointEscape', parseInt(res[1], 16), res[1], 4); + } + } + + function parseCharacterEscape() { + // CharacterEscape :: + // ControlEscape + // c ControlLetter + // HexEscapeSequence + // UnicodeEscapeSequence + // IdentityEscape + + var res; + var from = pos; + if (res = matchReg(/^[fnrtv]/)) { + // ControlEscape + var codePoint = 0; + switch (res[0]) { + case 't': codePoint = 0x009; break; + case 'n': codePoint = 0x00A; break; + case 'v': codePoint = 0x00B; break; + case 'f': codePoint = 0x00C; break; + case 'r': codePoint = 0x00D; break; + } + return createEscaped('singleEscape', codePoint, '\\' + res[0]); + } else if (res = matchReg(/^c([a-zA-Z])/)) { + // c ControlLetter + return createEscaped('controlLetter', res[1].charCodeAt(0) % 32, res[1], 2); + } else if (res = matchReg(/^x([0-9a-fA-F]{2})/)) { + // HexEscapeSequence + return createEscaped('hexadecimalEscape', parseInt(res[1], 16), res[1], 2); + } else if (res = parseRegExpUnicodeEscapeSequence()) { + if (!res || res.codePoint > 0x10FFFF) { + bail('Invalid escape sequence', null, from, pos); + } + return res; + } else { + // IdentityEscape + return parseIdentityEscape(); + } + } + + function parseIdentifierAtom(check) { + var ch = lookahead(); + var from = pos; + if (ch === '\\') { + incr(); + var esc = parseRegExpUnicodeEscapeSequence(); + if (!esc || !check(esc.codePoint)) { + bail('Invalid escape sequence', null, from, pos); + } + return fromCodePoint(esc.codePoint); + } + var code = ch.charCodeAt(0); + if (code >= 0xD800 && code <= 0xDBFF) { + ch += str[pos + 1]; + var second = ch.charCodeAt(1); + if (second >= 0xDC00 && second <= 0xDFFF) { + // Unicode surrogate pair + code = (code - 0xD800) * 0x400 + second - 0xDC00 + 0x10000; + } + } + if (!check(code)) return; + incr(); + if (code > 0xFFFF) incr(); + return ch; + } + + function parseIdentifier() { + // RegExpIdentifierName :: + // RegExpIdentifierStart + // RegExpIdentifierName RegExpIdentifierContinue + // + // RegExpIdentifierStart :: + // UnicodeIDStart + // $ + // _ + // \ RegExpUnicodeEscapeSequence + // + // RegExpIdentifierContinue :: + // UnicodeIDContinue + // $ + // _ + // \ RegExpUnicodeEscapeSequence + // <ZWNJ> + // <ZWJ> + + var start = pos; + var res = parseIdentifierAtom(isIdentifierStart); + if (!res) { + bail('Invalid identifier'); + } + + var ch; + while (ch = parseIdentifierAtom(isIdentifierPart)) { + res += ch; + } + + return addRaw({ + type: 'identifier', + value: res, + range: [start, pos] + }); + } + + function isIdentifierStart(ch) { + // Generated by `tools/generate-identifier-regex.js`. + var NonAsciiIdentifierStart = /[\$A-Z_a-z\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\u0560-\u0588\u05D0-\u05EA\u05EF-\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\u0860-\u086A\u08A0-\u08B4\u08B6-\u08BD\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\u09FC\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\u0AF9\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-\u0C5A\u0C60\u0C61\u0C80\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D54-\u0D56\u0D5F-\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-\u13F5\u13F8-\u13FD\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-\u1878\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1C80-\u1C88\u1C90-\u1CBA\u1CBD-\u1CBF\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-\u312F\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FEF\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6EF\uA717-\uA71F\uA722-\uA788\uA78B-\uA7B9\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA8FE\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-\uAB65\uAB70-\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]|\uD800[\uDC00-\uDC0B\uDC0D-\uDC26\uDC28-\uDC3A\uDC3C\uDC3D\uDC3F-\uDC4D\uDC50-\uDC5D\uDC80-\uDCFA\uDD40-\uDD74\uDE80-\uDE9C\uDEA0-\uDED0\uDF00-\uDF1F\uDF2D-\uDF4A\uDF50-\uDF75\uDF80-\uDF9D\uDFA0-\uDFC3\uDFC8-\uDFCF\uDFD1-\uDFD5]|\uD801[\uDC00-\uDC9D\uDCB0-\uDCD3\uDCD8-\uDCFB\uDD00-\uDD27\uDD30-\uDD63\uDE00-\uDF36\uDF40-\uDF55\uDF60-\uDF67]|\uD802[\uDC00-\uDC05\uDC08\uDC0A-\uDC35\uDC37\uDC38\uDC3C\uDC3F-\uDC55\uDC60-\uDC76\uDC80-\uDC9E\uDCE0-\uDCF2\uDCF4\uDCF5\uDD00-\uDD15\uDD20-\uDD39\uDD80-\uDDB7\uDDBE\uDDBF\uDE00\uDE10-\uDE13\uDE15-\uDE17\uDE19-\uDE35\uDE60-\uDE7C\uDE80-\uDE9C\uDEC0-\uDEC7\uDEC9-\uDEE4\uDF00-\uDF35\uDF40-\uDF55\uDF60-\uDF72\uDF80-\uDF91]|\uD803[\uDC00-\uDC48\uDC80-\uDCB2\uDCC0-\uDCF2\uDD00-\uDD23\uDF00-\uDF1C\uDF27\uDF30-\uDF45]|\uD804[\uDC03-\uDC37\uDC83-\uDCAF\uDCD0-\uDCE8\uDD03-\uDD26\uDD44\uDD50-\uDD72\uDD76\uDD83-\uDDB2\uDDC1-\uDDC4\uDDDA\uDDDC\uDE00-\uDE11\uDE13-\uDE2B\uDE80-\uDE86\uDE88\uDE8A-\uDE8D\uDE8F-\uDE9D\uDE9F-\uDEA8\uDEB0-\uDEDE\uDF05-\uDF0C\uDF0F\uDF10\uDF13-\uDF28\uDF2A-\uDF30\uDF32\uDF33\uDF35-\uDF39\uDF3D\uDF50\uDF5D-\uDF61]|\uD805[\uDC00-\uDC34\uDC47-\uDC4A\uDC80-\uDCAF\uDCC4\uDCC5\uDCC7\uDD80-\uDDAE\uDDD8-\uDDDB\uDE00-\uDE2F\uDE44\uDE80-\uDEAA\uDF00-\uDF1A]|\uD806[\uDC00-\uDC2B\uDCA0-\uDCDF\uDCFF\uDE00\uDE0B-\uDE32\uDE3A\uDE50\uDE5C-\uDE83\uDE86-\uDE89\uDE9D\uDEC0-\uDEF8]|\uD807[\uDC00-\uDC08\uDC0A-\uDC2E\uDC40\uDC72-\uDC8F\uDD00-\uDD06\uDD08\uDD09\uDD0B-\uDD30\uDD46\uDD60-\uDD65\uDD67\uDD68\uDD6A-\uDD89\uDD98\uDEE0-\uDEF2]|\uD808[\uDC00-\uDF99]|\uD809[\uDC00-\uDC6E\uDC80-\uDD43]|[\uD80C\uD81C-\uD820\uD840-\uD868\uD86A-\uD86C\uD86F-\uD872\uD874-\uD879][\uDC00-\uDFFF]|\uD80D[\uDC00-\uDC2E]|\uD811[\uDC00-\uDE46]|\uD81A[\uDC00-\uDE38\uDE40-\uDE5E\uDED0-\uDEED\uDF00-\uDF2F\uDF40-\uDF43\uDF63-\uDF77\uDF7D-\uDF8F]|\uD81B[\uDE40-\uDE7F\uDF00-\uDF44\uDF50\uDF93-\uDF9F\uDFE0\uDFE1]|\uD821[\uDC00-\uDFF1]|\uD822[\uDC00-\uDEF2]|\uD82C[\uDC00-\uDD1E\uDD70-\uDEFB]|\uD82F[\uDC00-\uDC6A\uDC70-\uDC7C\uDC80-\uDC88\uDC90-\uDC99]|\uD835[\uDC00-\uDC54\uDC56-\uDC9C\uDC9E\uDC9F\uDCA2\uDCA5\uDCA6\uDCA9-\uDCAC\uDCAE-\uDCB9\uDCBB\uDCBD-\uDCC3\uDCC5-\uDD05\uDD07-\uDD0A\uDD0D-\uDD14\uDD16-\uDD1C\uDD1E-\uDD39\uDD3B-\uDD3E\uDD40-\uDD44\uDD46\uDD4A-\uDD50\uDD52-\uDEA5\uDEA8-\uDEC0\uDEC2-\uDEDA\uDEDC-\uDEFA\uDEFC-\uDF14\uDF16-\uDF34\uDF36-\uDF4E\uDF50-\uDF6E\uDF70-\uDF88\uDF8A-\uDFA8\uDFAA-\uDFC2\uDFC4-\uDFCB]|\uD83A[\uDC00-\uDCC4\uDD00-\uDD43]|\uD83B[\uDE00-\uDE03\uDE05-\uDE1F\uDE21\uDE22\uDE24\uDE27\uDE29-\uDE32\uDE34-\uDE37\uDE39\uDE3B\uDE42\uDE47\uDE49\uDE4B\uDE4D-\uDE4F\uDE51\uDE52\uDE54\uDE57\uDE59\uDE5B\uDE5D\uDE5F\uDE61\uDE62\uDE64\uDE67-\uDE6A\uDE6C-\uDE72\uDE74-\uDE77\uDE79-\uDE7C\uDE7E\uDE80-\uDE89\uDE8B-\uDE9B\uDEA1-\uDEA3\uDEA5-\uDEA9\uDEAB-\uDEBB]|\uD869[\uDC00-\uDED6\uDF00-\uDFFF]|\uD86D[\uDC00-\uDF34\uDF40-\uDFFF]|\uD86E[\uDC00-\uDC1D\uDC20-\uDFFF]|\uD873[\uDC00-\uDEA1\uDEB0-\uDFFF]|\uD87A[\uDC00-\uDFE0]|\uD87E[\uDC00-\uDE1D]/; + + return (ch === 36) || (ch === 95) || // $ (dollar) and _ (underscore) + (ch >= 65 && ch <= 90) || // A..Z + (ch >= 97 && ch <= 122) || // a..z + ((ch >= 0x80) && NonAsciiIdentifierStart.test(fromCodePoint(ch))); + } + + // Taken from the Esprima parser. + function isIdentifierPart(ch) { + // Generated by `tools/generate-identifier-regex.js`. + // eslint-disable-next-line no-misleading-character-class + var NonAsciiIdentifierPartOnly = /[0-9_\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\u07FD\u0816-\u0819\u081B-\u0823\u0825-\u0827\u0829-\u082D\u0859-\u085B\u08D3-\u08E1\u08E3-\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\u09FE\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\u0AFA-\u0AFF\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-\u0C04\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\u0D00-\u0D03\u0D3B\u0D3C\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\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\u1CF7-\u1CF9\u1DC0-\u1DF9\u1DFB-\u1DFF\u200C\u200D\u203F\u2040\u2054\u20D0-\u20DC\u20E1\u20E5-\u20F0\u2CEF-\u2CF1\u2D7F\u2DE0-\u2DFF\u302A-\u302F\u3099\u309A\uA620-\uA629\uA66F\uA674-\uA67D\uA69E\uA69F\uA6F0\uA6F1\uA802\uA806\uA80B\uA823-\uA827\uA880\uA881\uA8B4-\uA8C5\uA8D0-\uA8D9\uA8E0-\uA8F1\uA8FF-\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-\uFE2F\uFE33\uFE34\uFE4D-\uFE4F\uFF10-\uFF19\uFF3F]|\uD800[\uDDFD\uDEE0\uDF76-\uDF7A]|\uD801[\uDCA0-\uDCA9]|\uD802[\uDE01-\uDE03\uDE05\uDE06\uDE0C-\uDE0F\uDE38-\uDE3A\uDE3F\uDEE5\uDEE6]|\uD803[\uDD24-\uDD27\uDD30-\uDD39\uDF46-\uDF50]|\uD804[\uDC00-\uDC02\uDC38-\uDC46\uDC66-\uDC6F\uDC7F-\uDC82\uDCB0-\uDCBA\uDCF0-\uDCF9\uDD00-\uDD02\uDD27-\uDD34\uDD36-\uDD3F\uDD45\uDD46\uDD73\uDD80-\uDD82\uDDB3-\uDDC0\uDDC9-\uDDCC\uDDD0-\uDDD9\uDE2C-\uDE37\uDE3E\uDEDF-\uDEEA\uDEF0-\uDEF9\uDF00-\uDF03\uDF3B\uDF3C\uDF3E-\uDF44\uDF47\uDF48\uDF4B-\uDF4D\uDF57\uDF62\uDF63\uDF66-\uDF6C\uDF70-\uDF74]|\uD805[\uDC35-\uDC46\uDC50-\uDC59\uDC5E\uDCB0-\uDCC3\uDCD0-\uDCD9\uDDAF-\uDDB5\uDDB8-\uDDC0\uDDDC\uDDDD\uDE30-\uDE40\uDE50-\uDE59\uDEAB-\uDEB7\uDEC0-\uDEC9\uDF1D-\uDF2B\uDF30-\uDF39]|\uD806[\uDC2C-\uDC3A\uDCE0-\uDCE9\uDE01-\uDE0A\uDE33-\uDE39\uDE3B-\uDE3E\uDE47\uDE51-\uDE5B\uDE8A-\uDE99]|\uD807[\uDC2F-\uDC36\uDC38-\uDC3F\uDC50-\uDC59\uDC92-\uDCA7\uDCA9-\uDCB6\uDD31-\uDD36\uDD3A\uDD3C\uDD3D\uDD3F-\uDD45\uDD47\uDD50-\uDD59\uDD8A-\uDD8E\uDD90\uDD91\uDD93-\uDD97\uDDA0-\uDDA9\uDEF3-\uDEF6]|\uD81A[\uDE60-\uDE69\uDEF0-\uDEF4\uDF30-\uDF36\uDF50-\uDF59]|\uD81B[\uDF51-\uDF7E\uDF8F-\uDF92]|\uD82F[\uDC9D\uDC9E]|\uD834[\uDD65-\uDD69\uDD6D-\uDD72\uDD7B-\uDD82\uDD85-\uDD8B\uDDAA-\uDDAD\uDE42-\uDE44]|\uD835[\uDFCE-\uDFFF]|\uD836[\uDE00-\uDE36\uDE3B-\uDE6C\uDE75\uDE84\uDE9B-\uDE9F\uDEA1-\uDEAF]|\uD838[\uDC00-\uDC06\uDC08-\uDC18\uDC1B-\uDC21\uDC23\uDC24\uDC26-\uDC2A]|\uD83A[\uDCD0-\uDCD6\uDD44-\uDD4A\uDD50-\uDD59]|\uDB40[\uDD00-\uDDEF]/; + + return isIdentifierStart(ch) || + (ch >= 48 && ch <= 57) || // 0..9 + ((ch >= 0x80) && NonAsciiIdentifierPartOnly.test(fromCodePoint(ch))); + } + + function parseIdentityEscape() { + // IdentityEscape :: + // [+U] SyntaxCharacter + // [+U] / + // [~U] SourceCharacterIdentityEscape[?N] + // SourceCharacterIdentityEscape[?N] :: + // [~N] SourceCharacter but not c + // [+N] SourceCharacter but not one of c or k + + + var tmp; + var l = lookahead(); + if ( + (isUnicodeMode && /[\^\$\.\*\+\?\(\)\\\[\]\{\}\|\/]/.test(l)) || + (!isUnicodeMode && l !== "c") + ) { + if (l === "k" && features.lookbehind) { + return null; + } + tmp = incr(); + return createEscaped('identifier', tmp.charCodeAt(0), tmp, 1); + } + + return null; + } + + function parseCharacterClass() { + // CharacterClass :: + // [ [lookahead ∉ {^}] ClassRanges ] + // [ ^ ClassRanges ] + + var res, from = pos; + if (res = matchReg(/^\[\^/)) { + res = parseClassRanges(); + skip(']'); + return createCharacterClass(res, true, from, pos); + } else if (match('[')) { + res = parseClassRanges(); + skip(']'); + return createCharacterClass(res, false, from, pos); + } + + return null; + } + + function parseClassRanges() { + // ClassRanges :: + // [empty] + // [~V] NonemptyClassRanges + // [+V] ClassContents + + var res; + if (current(']')) { + // Empty array means nothing inside of the ClassRange. + return { kind: 'union', body: [] }; + } else if (hasUnicodeSetFlag) { + return parseClassContents(); + } else { + res = parseNonemptyClassRanges(); + if (!res) { + bail('nonEmptyClassRanges'); + } + return { kind: 'union', body: res }; + } + } + + function parseHelperClassRanges(atom) { + var from, to, res, atomTo, dash; + if (current('-') && !next(']')) { + // ClassAtom - ClassAtom ClassRanges + from = atom.range[0]; + dash = createCharacter(match('-')); + + atomTo = parseClassAtom(); + if (!atomTo) { + bail('classAtom'); + } + to = pos; + + // Parse the next class range if exists. + var classRanges = parseClassRanges(); + if (!classRanges) { + bail('classRanges'); + } + + // Check if both the from and atomTo have codePoints. + if (!('codePoint' in atom) || !('codePoint' in atomTo)) { + if (!isUnicodeMode) { + // If not, don't create a range but treat them as + // `atom` `-` `atom` instead. + // + // SEE: https://tc39.es/ecma262/#sec-regular-expression-patterns-semantics + // NonemptyClassRanges::ClassAtom-ClassAtomClassRanges + // CharacterRangeOrUnion + res = [atom, dash, atomTo]; + } else { + // With unicode flag, both sides must have codePoints if + // one side has a codePoint. + // + // SEE: https://tc39.es/ecma262/#sec-patterns-static-semantics-early-errors + // NonemptyClassRanges :: ClassAtom - ClassAtom ClassRanges + bail('invalid character class'); + } + } else { + res = [createClassRange(atom, atomTo, from, to)]; + } + + if (classRanges.type === 'empty') { + return res; + } + return res.concat(classRanges.body); + } + + res = parseNonemptyClassRangesNoDash(); + if (!res) { + bail('nonEmptyClassRangesNoDash'); + } + + return [atom].concat(res); + } + + function parseNonemptyClassRanges() { + // NonemptyClassRanges :: + // ClassAtom + // ClassAtom NonemptyClassRangesNoDash + // ClassAtom - ClassAtom ClassRanges + + var atom = parseClassAtom(); + if (!atom) { + bail('classAtom'); + } + + if (current(']')) { + // ClassAtom + return [atom]; + } + + // ClassAtom NonemptyClassRangesNoDash + // ClassAtom - ClassAtom ClassRanges + return parseHelperClassRanges(atom); + } + + function parseNonemptyClassRangesNoDash() { + // NonemptyClassRangesNoDash :: + // ClassAtom + // ClassAtomNoDash NonemptyClassRangesNoDash + // ClassAtomNoDash - ClassAtom ClassRanges + + var res = parseClassAtom(); + if (!res) { + bail('classAtom'); + } + if (current(']')) { + // ClassAtom + return res; + } + + // ClassAtomNoDash NonemptyClassRangesNoDash + // ClassAtomNoDash - ClassAtom ClassRanges + return parseHelperClassRanges(res); + } + + function parseClassAtom() { + // ClassAtom :: + // - + // ClassAtomNoDash + if (match('-')) { + return createCharacter('-'); + } else { + return parseClassAtomNoDash(); + } + } + + function parseClassAtomNoDash() { + // ClassAtomNoDash :: + // SourceCharacter but not one of \ or ] or - + // \ ClassEscape + + var res; + if (res = matchReg(/^[^\\\]-]/)) { + return createCharacter(res[0]); + } else if (match('\\')) { + res = parseClassEscape(); + if (!res) { + bail('classEscape'); + } + + return parseUnicodeSurrogatePairEscape(res); + } + } + + function parseClassContents() { + // ClassContents :: + // ClassUnion + // ClassIntersection + // ClassSubtraction + // + // ClassUnion :: + // ClassRange ClassUnion? + // ClassOperand ClassUnion? + // + // ClassIntersection :: + // ClassOperand && [lookahead ≠ &] ClassOperand + // ClassIntersection && [lookahead ≠ &] ClassOperand + // + // ClassSubtraction :: + // ClassOperand -- ClassOperand + // ClassSubtraction -- ClassOperand + + var body = []; + var kind; + + var operand = parseClassOperand(/* allowRanges*/ true); + body.push(operand); + + if (operand.type === 'classRange') { + kind = 'union'; + } else if (current('&')) { + kind = 'intersection'; + } else if (current('-')) { + kind = 'subtraction'; + } else { + kind = 'union'; + } + + while (!current(']')) { + if (kind === 'intersection') { + skip('&'); + skip('&'); + if (current('&')) { + bail('&& cannot be followed by &. Wrap it in brackets: &&[&].'); + } + } else if (kind === 'subtraction') { + skip('-'); + skip('-'); + } + + operand = parseClassOperand(/* allowRanges*/ kind === 'union'); + body.push(operand); + } + + return { kind: kind, body: body }; + } + + function parseClassOperand(allowRanges) { + // ClassOperand :: + // ClassCharacter + // ClassStrings + // NestedClass + // + // NestedClass :: + // [ [lookahead ≠ ^] ClassRanges[+U,+V] ] + // [ ^ ClassRanges[+U,+V] ] + // \ CharacterClassEscape[+U, +V] + // + // ClassRange :: + // ClassCharacter - ClassCharacter + // + // ClassCharacter :: + // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter + // \ CharacterEscape[+U] + // \ ClassHalfOfDouble + // \ b + // + // ClassSyntaxCharacter :: + // one of ( ) [ ] { } / - \ | + + var from = pos; + var start, res; + + if (match('\\')) { + // ClassOperand :: + // ... + // ClassStrings + // NestedClass + // + // NestedClass :: + // ... + // \ CharacterClassEscape[+U, +V] + if (res = parseClassEscape()) { + start = res; + } else if (res = parseClassCharacterEscapedHelper()) { + return res; + } else { + bail('Invalid escape', '\\' + lookahead(), from); + } + } else if (res = parseClassCharacterUnescapedHelper()) { + start = res; + } else if (res = parseCharacterClass()) { + // ClassOperand :: + // ... + // NestedClass + // + // NestedClass :: + // [ [lookahead ≠ ^] ClassRanges[+U,+V] ] + // [ ^ ClassRanges[+U,+V] ] + // ... + return res; + } else { + bail('Invalid character', lookahead()); + } + + if (allowRanges && current('-') && !next('-')) { + skip('-'); + + if (res = parseClassCharacter()) { + // ClassRange :: + // ClassCharacter - ClassCharacter + return createClassRange(start, res, from, pos); + } + + bail('Invalid range end', lookahead()); + } + + // ClassOperand :: + // ClassCharacter + // ... + return start; + } + + function parseClassCharacter() { + // ClassCharacter :: + // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter + // \ CharacterEscape[+U] + // \ ClassHalfOfDouble + // \ b + + if (match('\\')) { + var res, from = pos; + if (res = parseClassCharacterEscapedHelper()) { + return res; + } else { + bail('Invalid escape', '\\' + lookahead(), from); + } + } + + return parseClassCharacterUnescapedHelper(); + } + + function parseClassCharacterUnescapedHelper() { + // ClassCharacter :: + // [lookahead ∉ ClassReservedDouble] SourceCharacter but not ClassSyntaxCharacter + // ... + + var res; + if (res = matchReg(/^[^()[\]{}/\-\\|]/)) { + return createCharacter(res); + } + } + + function parseClassCharacterEscapedHelper() { + // ClassCharacter :: + // ... + // \ CharacterEscape[+U] + // \ ClassHalfOfDouble + // \ b + + var res; + if (match('b')) { + return createEscaped('singleEscape', 0x0008, '\\b'); + } else if (match('B')) { + bail('\\B not possible inside of ClassContents', '', pos - 2); + } else if (res = matchReg(/^[&\-!#%,:;<=>@_`~]/)) { + return createEscaped('identifier', res[0].codePointAt(0), res[0]); + } else if (res = parseCharacterEscape()) { + return res; + } else { + return null; + } + } + + function parseClassStrings() { + // ClassStrings :: + // \q{ ClassString MoreClassStrings? } + + // When calling this function, \q{ has already been consumed. + var from = pos - 3; + + var res = []; + do { + res.push(parseClassString()); + } while (match('|')); + + skip('}'); + + return createClassStrings(res, from, pos); + } + + function parseClassString() { + // ClassString :: + // [empty] + // NonEmptyClassString + // + // NonEmptyClassString :: + // ClassCharacter NonEmptyClassString? + + var res = [], from = pos; + var char; + + while (char = parseClassCharacter()) { + res.push(char); + } + + return createClassString(res, from, pos); + } + + function bail(message, details, from, to) { + from = from == null ? pos : from; + to = to == null ? from : to; + + var contextStart = Math.max(0, from - 10); + var contextEnd = Math.min(to + 10, str.length); + + // Output a bit of context and a line pointing to where our error is. + // + // We are assuming that there are no actual newlines in the content as this is a regular expression. + var context = ' ' + str.substring(contextStart, contextEnd); + var pointer = ' ' + new Array(from - contextStart + 1).join(' ') + '^'; + + throw SyntaxError(message + ' at position ' + from + (details ? ': ' + details : '') + '\n' + context + '\n' + pointer); + } + + var backrefDenied = []; + var closedCaptureCounter = 0; + var firstIteration = true; + var shouldReparse = false; + var hasUnicodeFlag = (flags || "").indexOf("u") !== -1; + var hasUnicodeSetFlag = (flags || "").indexOf("v") !== -1; + var isUnicodeMode = hasUnicodeFlag || hasUnicodeSetFlag; + var pos = 0; + + if (hasUnicodeSetFlag && !features.unicodeSet) { + throw new Error('The "v" flag is only supported when the .unicodeSet option is enabled.'); + } + + if (hasUnicodeFlag && hasUnicodeSetFlag) { + throw new Error('The "u" and "v" flags are mutually exclusive.'); + } + + // Convert the input to a string and treat the empty string special. + str = String(str); + if (str === '') { + str = '(?:)'; + } + + var result = parseDisjunction(); + + if (result.range[1] !== str.length) { + bail('Could not parse entire input - got stuck', '', result.range[1]); + } + + // The spec requires to interpret the `\2` in `/\2()()/` as backreference. + // As the parser collects the number of capture groups as the string is + // parsed it is impossible to make these decisions at the point when the + // `\2` is handled. In case the local decision turns out to be wrong after + // the parsing has finished, the input string is parsed a second time with + // the total number of capture groups set. + // + // SEE: https://github.com/jviereck/regjsparser/issues/70 + shouldReparse = shouldReparse || backrefDenied.some(function (ref) { + return ref <= closedCaptureCounter; + }); + if (shouldReparse) { + // Parse the input a second time. + pos = 0; + firstIteration = false; + return parseDisjunction(); + } + + return result; + } + + var regjsparser = { + parse: parse + }; + + if (typeof module !== 'undefined' && module.exports) { + module.exports = regjsparser; + } else { + window.regjsparser = regjsparser; + } + +}()); |