Regex language (#1682)

This adds a Regex language that adds itself to a few languages which have regex literals.

components.json

@@ -734,6 +734,18 @@
 			"require": "clike",
 			"owner": "Golmote"
 		},
+		"regex": {
+			"title": "Regex",
+			"peerDependencies": [
+				"actionscript",
+				"coffeescript",
+				"flow",
+				"javascript",
+				"typescript",
+				"vala"
+			],
+			"owner": "RunDevelopment"
+		},
 		"rest": {
 			"title": "reST (reStructuredText)",
 			"owner": "Golmote"

components/prism-regex.js

@@ -0,0 +1,97 @@
+(function (Prism) {
+
+	var specialEscape = {
+		pattern: /\\[\\(){}[\]^$+*?|.]/,
+		alias: 'escape'
+	};
+	var escape = /\\(?:x[\da-fA-F]{2}|u[\da-fA-F]{4}|u\{[\da-fA-F]+\}|c[a-zA-Z]|0[0-7]{0,2}|[123][0-7]{2}|.)/
+	var charClass = /\\[wsd]|\.|\\p{[^{}]+}/i
+
+	var rangeChar = '(?:[^\\\\-]|' + escape.source + ')';
+	var range = RegExp(rangeChar + '-' + rangeChar);
+
+	// the name of a capturing group
+	var groupName = {
+		pattern: /(<|')[^<>']+(?=[>']$)/,
+		lookbehind: true,
+		alias: 'variable'
+	};
+
+	var backreference = [
+		/\\(?![123][0-7]{2})[1-9]/, // a backreference which is not an octal escape
+		{
+			pattern: /\\k<[^<>']+>/,
+			inside: {
+				'group-name': groupName
+			}
+		}
+	];
+
+	Prism.languages.regex = {
+		'charset': {
+			pattern: /((?:^|[^\\])(?:\\\\)*)\[(?:[^\\\]]|\\[\s\S])*\]/,
+			lookbehind: true,
+			inside: {
+				'charset-negation': {
+					pattern: /(^\[)\^/,
+					lookbehind: true,
+				},
+				'charset-punctuation': /^\[|\]$/,
+				'range': {
+					pattern: range,
+					inside: {
+						'escape': escape,
+						'range-punctuation': /-/
+					}
+				},
+				'special-escape': specialEscape,
+				'charclass': charClass,
+				'backreference': backreference,
+				'escape': escape
+			}
+		},
+		'special-escape': specialEscape,
+		'charclass': charClass,
+		'backreference': backreference,
+		'anchor': /[$^]|\\[ABbGZz]/,
+		'escape': escape,
+		'group': [
+			{
+				// https://docs.oracle.com/javase/10/docs/api/java/util/regex/Pattern.html
+				// https://docs.microsoft.com/en-us/dotnet/standard/base-types/regular-expression-language-quick-reference?view=netframework-4.7.2#grouping-constructs
+
+				// (), (?<name>), (?'name'), (?>), (?:), (?=), (?!), (?<=), (?<!), (?is-m), (?i-m:)
+				pattern: /\((?:\?(?:<[^<>']+>|'[^<>']+'|[>:]|<?[=!]|[idmnsuxU]+(?:-[idmnsuxU]+)?:?))?/,
+				inside: {
+					'group-name': groupName
+				}
+			},
+			/\)/
+		],
+		'quantifier': /[+*?]|\{(?:\d+,?\d*)\}/,
+		'alternation': /\|/
+	};
+
+
+	[
+		'actionscript',
+		'coffescript',
+		'flow',
+		'javascript',
+		'typescript',
+		'vala'
+	].forEach(function (lang) {
+		var grammar = Prism.languages[lang];
+		if (grammar) {
+			grammar['regex'].inside = {
+				'regex-flags': /[a-z]+$/,
+				'regex-delimiter': /^\/|\/$/,
+				'language-regex': {
+					pattern: /[\s\S]+/,
+					inside: Prism.languages.regex
+				}
+			};
+		}
+	});
+
+}(Prism))

tests/languages/javascript!+regex/regex_inclusion.test

@@ -0,0 +1,34 @@
+/a+(?:[a-z]|\d)?/im;
+
+----------------------------------------------------
+
+[
+	["regex", [
+		["regex-delimiter", "/"],
+		["language-regex", [
+			"a",
+			["quantifier", "+"],
+			["group", ["(?:"]],
+			["charset", [
+				["charset-punctuation", "["],
+				["range", [
+					"a",
+					["range-punctuation", "-"],
+					"z"
+				]],
+				["charset-punctuation", "]"]
+			]],
+			["alternation", "|"],
+			["charclass", "\\d"],
+			["group", ")"],
+			["quantifier", "?"]
+		]],
+		["regex-delimiter", "/"],
+		["regex-flags", "im"]
+	]],
+	["punctuation", ";"]
+]
+
+----------------------------------------------------
+
+Checks for regex inclusion in JavaScript.

tests/languages/regex/anchor_feature.test

@@ -0,0 +1,25 @@
+^
+$
+\A
+\G
+\Z
+\z
+\b
+\B
+
+----------------------------------------------------
+
+[
+	["anchor", "^"],
+	["anchor", "$"],
+	["anchor", "\\A"],
+	["anchor", "\\G"],
+	["anchor", "\\Z"],
+	["anchor", "\\z"],
+	["anchor", "\\b"],
+	["anchor", "\\B"]
+]
+
+----------------------------------------------------
+
+Checks for anchors.

tests/languages/regex/backreference_feature.test

@@ -0,0 +1,26 @@
+\1 \2 \3 \4 \5 \6 \7 \8 \9
+\k<name>
+
+----------------------------------------------------
+
+[
+	["backreference", "\\1"],
+	["backreference", "\\2"],
+	["backreference", "\\3"],
+	["backreference", "\\4"],
+	["backreference", "\\5"],
+	["backreference", "\\6"],
+	["backreference", "\\7"],
+	["backreference", "\\8"],
+	["backreference", "\\9"],
+
+	["backreference", [
+		"\\k<",
+		["group-name", "name"],
+		">"
+	]]
+]
+
+----------------------------------------------------
+
+Checks for backreferences.

tests/languages/regex/charclass_feature.test

@@ -0,0 +1,25 @@
+.
+\w \W
+\s \S
+\d \D
+\p{ASCII}
+\P{ASCII}
+
+----------------------------------------------------
+
+[
+	["charclass", "."],
+	["charclass", "\\w"],
+	["charclass", "\\W"],
+	["charclass", "\\s"],
+	["charclass", "\\S"],
+	["charclass", "\\d"],
+	["charclass", "\\D"],
+
+	["charclass", "\\p{ASCII}"],
+	["charclass", "\\P{ASCII}"]
+]
+
+----------------------------------------------------
+
+Checks for character classes.

tests/languages/regex/charset_feature.test

@@ -0,0 +1,36 @@
+[]
+[^]
+[foo]
+[\]\b]
+
+----------------------------------------------------
+
+[
+	["charset", [
+		["charset-punctuation", "["],
+		["charset-punctuation", "]"]
+	]],
+
+	["charset", [
+		["charset-punctuation", "["],
+		["charset-negation", "^"],
+		["charset-punctuation", "]"]
+	]],
+
+	["charset", [
+		["charset-punctuation", "["],
+		"foo",
+		["charset-punctuation", "]"]
+	]],
+
+	["charset", [
+		["charset-punctuation", "["],
+		["special-escape", "\\]"],
+		["escape", "\\b"],
+		["charset-punctuation", "]"]
+	]]
+]
+
+----------------------------------------------------
+
+Checks for character sets.

tests/languages/regex/escape_feature.test

@@ -0,0 +1,42 @@
+\0 \\ \. \+
+\xFF
+\uFFFF \u{10FFFF}
+\cA \cZ
+\01 \077 \377
+\n \r \t \f \a
+
+\[ \]
+
+----------------------------------------------------
+
+[
+	["escape", "\\0"],
+	["special-escape", "\\\\"],
+	["special-escape", "\\."],
+	["special-escape", "\\+"],
+
+	["escape", "\\xFF"],
+
+	["escape", "\\uFFFF"],
+	["escape", "\\u{10FFFF}"],
+
+	["escape", "\\cA"],
+	["escape", "\\cZ"],
+
+	["escape", "\\01"],
+	["escape", "\\077"],
+	["escape", "\\377"],
+
+	["escape", "\\n"],
+	["escape", "\\r"],
+	["escape", "\\t"],
+	["escape", "\\f"],
+	["escape", "\\a"],
+
+	["special-escape", "\\["],
+	["special-escape", "\\]"]
+]
+
+----------------------------------------------------
+
+Checks for escapes.

tests/languages/regex/group_feature.test

@@ -0,0 +1,64 @@
+()
+(?:)
+(?>)
+(?=) (?!)
+(?<=) (?<!)
+
+(?<name>)
+(?'name')
+
+(?i)
+(?i:)
+(?idmsuxU-idmsuxU)
+(?idmsux-idmsux:X)
+
+----------------------------------------------------
+
+[
+	["group", ["("]],
+	["group", ")"],
+
+	["group", ["(?:"]],
+	["group", ")"],
+
+	["group", ["(?>"]],
+	["group", ")"],
+
+	["group", ["(?="]],
+	["group", ")"],
+	["group", ["(?!"]],
+	["group", ")"],
+
+	["group", ["(?<="]],
+	["group", ")"],
+	["group", ["(?<!"]],
+	["group", ")"],
+
+	["group", [
+		"(?<",
+		["group-name", "name"],
+		">"]
+	],
+	["group", ")"],
+
+	["group", [
+		"(?'",
+		["group-name", "name"],
+		"'"]
+	],
+	["group", ")"],
+
+	["group", ["(?i"]],
+	["group", ")"],
+	["group", ["(?i:"]],
+	["group", ")"],
+	["group", ["(?idmsuxU-idmsuxU"]],
+	["group", ")"],
+	["group", ["(?idmsux-idmsux:"]],
+	"X",
+	["group", ")"]
+]
+
+----------------------------------------------------
+
+Checks for groups.

tests/languages/regex/quantifier_feature.test

@@ -0,0 +1,17 @@
+* + ?
+{2} {2,} {0,1}
+
+----------------------------------------------------
+
+[
+	["quantifier", "*"],
+	["quantifier", "+"],
+	["quantifier", "?"],
+	["quantifier", "{2}"],
+	["quantifier", "{2,}"],
+	["quantifier", "{0,1}"]
+]
+
+----------------------------------------------------
+
+Checks for quantifiers.