the-forest/client/node_modules/regjsparser/parser.js

1635 lines
56 KiB
JavaScript
Raw Normal View History

2024-09-17 20:35:18 -04:00
// 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\uFB1
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-\uDD5
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;
}
}());