Added bqn language support (#3515)

components.json

@@ -251,6 +251,10 @@
 			},
 			"owner": "RunDevelopment"
 		},
+		"bqn": {
+			"title": "BQN",
+			"owner": "yewscion"
+		},
 		"brainfuck": {
 			"title": "Brainfuck",
 			"owner": "Golmote"

components/prism-bqn.js

@@ -0,0 +1,63 @@
+Prism.languages.bqn = {
+	'shebang': {
+		pattern: /^#![ \t]*\/.*/,
+		alias: 'important',
+		greedy: true
+	},
+	'comment': {
+		pattern: /#.*/,
+		greedy: true
+	},
+	'string-literal': {
+		pattern: /"(?:[^"]|"")*"/,
+		greedy: true,
+		alias: 'string'
+	},
+	'character-literal': {
+		pattern: /'(?:[\s\S]|[\uD800-\uDBFF][\uDC00-\uDFFF])'/,
+		greedy: true,
+		alias: 'char'
+	},
+	'function': /•[\w¯.∞π]+[\w¯.∞π]*/,
+	'dot-notation-on-brackets': {
+		pattern: /\{(?=.*\}\.)|\}\./,
+		alias: 'namespace'
+	},
+	'special-name': {
+		pattern: /(?:𝕨|𝕩|𝕗|𝕘|𝕤|𝕣|𝕎|𝕏|𝔽|𝔾|𝕊|_𝕣_|_𝕣)/,
+		alias: 'keyword'
+	},
+	'dot-notation-on-name': {
+		pattern: /[A-Za-z_][\w¯∞π]*\./,
+		alias: 'namespace'
+	},
+	'word-number-scientific': {
+		pattern: /\d+(?:\.\d+)?[eE]¯?\d+/,
+		alias: 'number'
+	},
+	'word-name': {
+		pattern: /[A-Za-z_][\w¯∞π]*/,
+		alias: 'symbol'
+	},
+	'word-number': {
+		pattern: /[¯∞π]?(?:\d*\.?\b\d+(?:e[+¯]?\d+|E[+¯]?\d+)?|¯|∞|π)(?:j¯?(?:(?:\d+(?:\.\d+)?|\.\d+)(?:e[+¯]?\d+|E[+¯]?\d+)?|¯|∞|π))?/,
+		alias: 'number'
+	},
+	'null-literal': {
+		pattern: /@/,
+		alias: 'char'
+	},
+	'primitive-functions': {
+		pattern: /[-+×÷⋆√⌊⌈|¬∧∨<>≠=≤≥≡≢⊣⊢⥊∾≍⋈↑↓↕«»⌽⍉/⍋⍒⊏⊑⊐⊒∊⍷⊔!]/,
+		alias: 'operator'
+	},
+	'primitive-1-operators': {
+		pattern: /[`˜˘¨⁼⌜´˝˙]/,
+		alias: 'operator'
+	},
+	'primitive-2-operators': {
+		pattern: /[∘⊸⟜○⌾⎉⚇⍟⊘◶⎊]/,
+		alias: 'operator'
+	},
+	'punctuation': /[←⇐↩(){}⟨⟩[\]‿·⋄,.;:?]/
+};

examples/prism-bqn.html

@@ -0,0 +1,125 @@
+<h2>Examples From Rosetta Code</h2>
+<h3>100 Doors</h3>
+<pre><code>
+swch ← ≠´{100⥊1«𝕩⥊0}¨1+↕100
+¯1↓∾{𝕩∾@+10}¨•Fmt¨⟨swch,/swch⟩
+</code></pre>
+<h3>Archimedean Spiral</h3>
+<pre><code>
+{(•math.Sin •Plot○(⊢×↕∘≠) •math.Cos) -(2×π) × 𝕩⥊(↕÷-⟜1)100}
+</code></pre>
+<h3>Damm Algorithm</h3>
+<pre><code>
+table ← >⟨ 0‿3‿1‿7‿5‿9‿8‿6‿4‿2
+	   7‿0‿9‿2‿1‿5‿4‿8‿6‿3
+	   4‿2‿0‿6‿8‿7‿1‿3‿5‿9
+	   1‿7‿5‿0‿9‿8‿3‿4‿2‿6
+	   6‿1‿2‿3‿0‿4‿5‿9‿7‿8
+	   3‿6‿7‿4‿2‿0‿9‿5‿8‿1
+	   5‿8‿6‿9‿7‿2‿0‿1‿3‿4
+	   8‿9‿4‿5‿3‿6‿2‿0‿1‿7
+	   9‿4‿3‿8‿6‿1‿7‿2‿0‿5
+	   2‿5‿8‿1‿4‿3‿6‿7‿9‿0 ⟩
+
+
+Digits ← 10{⌽𝕗|⌊∘÷⟜𝕗⍟(↕1+·⌊𝕗⋆⁼1⌈⊢)}
+
+Damm ← {0=0(table⊑˜⋈)˜´⌽Digits 𝕩}
+
+Damm¨5724‿5727‿112946
+</code></pre>
+<h3>Knuth/Fisher-Yates Shuffle</h3>
+<pre><code>
+Knuth ← {
+  𝕊 arr:
+  l ← ≠arr
+  {
+    arr ↩ ⌽⌾(⟨•rand.Range l, 𝕩⟩⊸⊏)arr
+  }¨↕l
+  arr
+}
+P ← •Show Knuth
+
+P ⟨⟩
+P ⟨10⟩
+P ⟨10, 20⟩
+P ⟨10, 20, 30⟩
+</code></pre>
+<h2>Comments</h2>
+<pre><code>#!/usr/bin/env bqn
+# Full Line Comment
+'#'  # The preceding should not be a comment.
+"BQN is #1" # The preceding should not be a comment.
+1 + 1 # Comment at End of Line.
+</code></pre>
+
+<h2>Literals</h2>
+<pre><code>
+"String Literal"
+'c'
+"""There is a double quote at the start of this string."
+"'c'"
+# "Comment, not String"
+"String, # Not Comment"
+@
+</code></pre>
+
+<h2>Tokens</h2>
+<h3>Primitive Functions</h3>
+<pre><code>
++-×÷⋆√⌊⌈|¬∧∨&lt;&gt;≠=≤≥≡≢⊣⊢⥊∾≍⋈↑↓↕«»⌽⍉/⍋⍒⊏⊑⊐⊒∊⍷⊔!
+</code></pre>
+<h3>1-Operators</h3>
+<pre><code>
+˙˜˘¨⌜⁼´˝`
+</code></pre>
+<h3>2-Operators</h3>
+<pre><code>
+∘○⊸⟜⌾⊘◶⎉⚇⍟⎊
+</code></pre>
+<h3>Special Names</h3>
+<pre><code>
+𝕨𝕩𝕗𝕘𝕤𝕎𝕏𝔽𝔾𝕊𝕣_𝕣
+_𝕣_
+</code></pre>
+<h3>Punctuation</h3>
+<pre><code>
+←⇐↩(){}⟨⟩[]‿·⋄,.;:?
+</code></pre>
+
+<h2>Words</h2>
+<h3>Numbers</h3>
+<pre><code>
+1464
+3.14159
+¯2
+∞
+π
+¯∞
+2.8e¯4
+1.618E2
+</code></pre>
+<h3>Names</h3>
+<pre><code>
+VariableName
+ThereAre4Symbols_¯∞πAllowedInNames
+</code></pre>
+<h2>Namespaces</h2>
+<pre><code>
+example.b
+{n⇐7}.n
+</code></pre>
+<h2>System Functions</h2>
+<pre><code>
+•Function
+ •function
+•_function_
+@•Function@
++•Function+
+˙•Function˙
+∘•Function∘
+𝕨•Function𝕩
+←•Function?
+•Function_.¯∞πCanHaveSymbols
+•0.0.0.0
+</code></pre>

plugins/show-language/prism-show-language.js

@@ -59,6 +59,7 @@
 		"bbj": "BBj",
 		"bnf": "BNF",
 		"rbnf": "RBNF",
+		"bqn": "BQN",
 		"bsl": "BSL (1C:Enterprise)",
 		"oscript": "OneScript",
 		"csharp": "C#",

tests/languages/bqn/comments.test

@@ -0,0 +1,79 @@
+#!/usr/bin/env bqn
+# Full Line Comment. The above is a shebang.
++-×÷⋆√⌊⌈|¬∧∨<>≠=≤≥≡≢⊣⊢⥊∾≍⋈↑↓↕«»⌽⍉/⍋⍒⊏⊑⊐⊒∊⍷⊔! # Comment at End of Line.
+'#'  # The preceding should not be a comment.
+"BQN is #1" # The preceding should not be a comment.
+# Comments # Continue # To # The # EOL #
+########################################
+Symbol
+
+----------------------------------------------------
+
+[
+	["shebang", "#!/usr/bin/env bqn"],
+
+	["comment", "# Full Line Comment. The above is a shebang."],
+
+	["primitive-functions", "+"],
+	["primitive-functions", "-"],
+	["primitive-functions", "×"],
+	["primitive-functions", "÷"],
+	["primitive-functions", "⋆"],
+	["primitive-functions", "√"],
+	["primitive-functions", "⌊"],
+	["primitive-functions", "⌈"],
+	["primitive-functions", "|"],
+	["primitive-functions", "¬"],
+	["primitive-functions", "∧"],
+	["primitive-functions", "∨"],
+	["primitive-functions", "<"],
+	["primitive-functions", ">"],
+	["primitive-functions", "≠"],
+	["primitive-functions", "="],
+	["primitive-functions", "≤"],
+	["primitive-functions", "≥"],
+	["primitive-functions", "≡"],
+	["primitive-functions", "≢"],
+	["primitive-functions", "⊣"],
+	["primitive-functions", "⊢"],
+	["primitive-functions", "⥊"],
+	["primitive-functions", "∾"],
+	["primitive-functions", "≍"],
+	["primitive-functions", "⋈"],
+	["primitive-functions", "↑"],
+	["primitive-functions", "↓"],
+	["primitive-functions", "↕"],
+	["primitive-functions", "«"],
+	["primitive-functions", "»"],
+	["primitive-functions", "⌽"],
+	["primitive-functions", "⍉"],
+	["primitive-functions", "/"],
+	["primitive-functions", "⍋"],
+	["primitive-functions", "⍒"],
+	["primitive-functions", "⊏"],
+	["primitive-functions", "⊑"],
+	["primitive-functions", "⊐"],
+	["primitive-functions", "⊒"],
+	["primitive-functions", "∊"],
+	["primitive-functions", "⍷"],
+	["primitive-functions", "⊔"],
+	["primitive-functions", "!"],
+	["comment", "# Comment at End of Line."],
+
+	["character-literal", "'#'"],
+	["comment", "# The preceding should not be a comment."],
+
+	["string-literal", "\"BQN is #1\""],
+	["comment", "# The preceding should not be a comment."],
+
+	["comment", "# Comments # Continue # To # The # EOL #"],
+
+	["comment", "########################################"],
+
+	["word-name", "Symbol"]
+]
+
+----------------------------------------------------
+
+Comments follow a '#' character only, on a single line, to the end of the
+line, unless in a shebang, character literal, or string literal.

tests/languages/bqn/namespace.test

@@ -0,0 +1,31 @@
+example.b
+{n⇐7}.n
+
+----------------------------------------------------
+
+[
+	["dot-notation-on-name", "example."],
+	["word-name", "b"],
+
+	["dot-notation-on-brackets", "{"],
+	["word-name", "n"],
+	["punctuation", "⇐"],
+	["word-number", "7"],
+	["dot-notation-on-brackets", "}."],
+	["word-name", "n"]
+]
+
+----------------------------------------------------
+
+A namespace is a type of value that groups together several variables
+(fields) from the same scope. A block or file returns a namespace if it
+contains any export arrows ⇐ at the top level, and fields from namespaces can
+be accessed with either dot syntax or destructuring assignment. A namespace
+can be mutable only if any of its source code uses ↩ to change the value of a
+field.
+
+There are also two ways to get values out of a namespace, such as example
+defined above. First, one field at a time can be retrieved with dot syntax:
+write the namespace, then a dot ., then another name.
+
+The second, destructuring assignments, does not require special highlighting.

tests/languages/bqn/strings.test

@@ -0,0 +1,61 @@
+"String Literal"
+'c'
+'not a string or character'
+""Not A String
+""Not A String""
+"""There is a double quote at the start of this string."
+"'this is a string'"
+"'c'"
+# "Comment, not String"
+"String, # Not Comment"
+"
+
+----------------------------------------------------
+
+[
+	["string-literal", "\"String Literal\""],
+
+	["character-literal", "'c'"],
+
+	"\r\n'",
+	["word-name", "not"],
+	["word-name", "a"],
+	["word-name", "string"],
+	["word-name", "or"],
+	["word-name", "character"],
+	"'\r\n",
+
+	["string-literal", "\"\""],
+	["word-name", "Not"],
+	["word-name", "A"],
+	["word-name", "String"],
+
+	["string-literal", "\"\""],
+	["word-name", "Not"],
+	["word-name", "A"],
+	["word-name", "String"],
+	["string-literal", "\"\""],
+
+	["string-literal", "\"\"\"There is a double quote at the start of this string.\""],
+
+	["string-literal", "\"'this is a string'\""],
+
+	["string-literal", "\"'c'\""],
+
+	["comment", "# \"Comment, not String\""],
+
+	["string-literal", "\"String, # Not Comment\""],
+
+	"\r\n\""
+]
+
+----------------------------------------------------
+
+Strings—lists of characters—are written with double quotes "", and characters
+with single quotes '' with a single character in between. Only one character
+ever needs to be escaped: a double quote in a string is written twice. So
+"""" is a one-character string of ", and if two string literals are next to
+each other, they have to be separated by a space. Character literals don't
+have even one escape, as the length is already known. Other than the double
+quote, character and string literals can contain any character directly:
+newlines, null characters, or other Unicode.

tests/languages/bqn/system-functions.test

@@ -0,0 +1,53 @@
+•Function
+ •function 
+•_function_
+@•Function@
++•Function+
+˙•Function˙
+∘•Function∘
+𝕨•Function𝕩
+←•Function?
+•Function_.¯∞πCanHaveSymbols
+•0.0.0.0
+
+----------------------------------------------------
+
+[
+	["function", "•Function"],
+
+	["function", "•function"],
+
+	["function", "•_function_"],
+
+	["null-literal", "@"],
+	["function", "•Function"],
+	["null-literal", "@"],
+
+	["primitive-functions", "+"],
+	["function", "•Function"],
+	["primitive-functions", "+"],
+
+	["primitive-1-operators", "˙"],
+	["function", "•Function"],
+	["primitive-1-operators", "˙"],
+
+	["primitive-2-operators", "∘"],
+	["function", "•Function"],
+	["primitive-2-operators", "∘"],
+
+	["special-name", "𝕨"],
+	["function", "•Function"],
+	["special-name", "𝕩"],
+
+	["punctuation", "←"],
+	["function", "•Function"],
+	["punctuation", "?"],
+
+	["function", "•Function_.¯∞πCanHaveSymbols"],
+
+	["function", "•0.0.0.0"]
+]
+
+----------------------------------------------------
+
+System Functions should be identified regardless of what is next to them.

tests/languages/bqn/tokens.test

@@ -0,0 +1,118 @@
+@
++-×÷⋆√⌊⌈|¬∧∨<>≠=≤≥≡≢⊣⊢⥊∾≍⋈↑↓↕«»⌽⍉/⍋⍒⊏⊑⊐⊒∊⍷⊔!
+˙˜˘¨⌜⁼´˝`
+∘○⊸⟜⌾⊘◶⎉⚇⍟⎊
+𝕨𝕩𝕗𝕘𝕤𝕣𝕎𝕏𝔽𝔾𝕊 _𝕣 _𝕣_
+←⇐↩(){}⟨⟩[]‿·⋄,.;:?
+
+----------------------------------------------------
+
+[
+	["null-literal", "@"],
+
+	["primitive-functions", "+"],
+	["primitive-functions", "-"],
+	["primitive-functions", "×"],
+	["primitive-functions", "÷"],
+	["primitive-functions", "⋆"],
+	["primitive-functions", "√"],
+	["primitive-functions", "⌊"],
+	["primitive-functions", "⌈"],
+	["primitive-functions", "|"],
+	["primitive-functions", "¬"],
+	["primitive-functions", "∧"],
+	["primitive-functions", "∨"],
+	["primitive-functions", "<"],
+	["primitive-functions", ">"],
+	["primitive-functions", "≠"],
+	["primitive-functions", "="],
+	["primitive-functions", "≤"],
+	["primitive-functions", "≥"],
+	["primitive-functions", "≡"],
+	["primitive-functions", "≢"],
+	["primitive-functions", "⊣"],
+	["primitive-functions", "⊢"],
+	["primitive-functions", "⥊"],
+	["primitive-functions", "∾"],
+	["primitive-functions", "≍"],
+	["primitive-functions", "⋈"],
+	["primitive-functions", "↑"],
+	["primitive-functions", "↓"],
+	["primitive-functions", "↕"],
+	["primitive-functions", "«"],
+	["primitive-functions", "»"],
+	["primitive-functions", "⌽"],
+	["primitive-functions", "⍉"],
+	["primitive-functions", "/"],
+	["primitive-functions", "⍋"],
+	["primitive-functions", "⍒"],
+	["primitive-functions", "⊏"],
+	["primitive-functions", "⊑"],
+	["primitive-functions", "⊐"],
+	["primitive-functions", "⊒"],
+	["primitive-functions", "∊"],
+	["primitive-functions", "⍷"],
+	["primitive-functions", "⊔"],
+	["primitive-functions", "!"],
+
+	["primitive-1-operators", "˙"],
+	["primitive-1-operators", "˜"],
+	["primitive-1-operators", "˘"],
+	["primitive-1-operators", "¨"],
+	["primitive-1-operators", "⌜"],
+	["primitive-1-operators", "⁼"],
+	["primitive-1-operators", "´"],
+	["primitive-1-operators", "˝"],
+	["primitive-1-operators", "`"],
+
+	["primitive-2-operators", "∘"],
+	["primitive-2-operators", "○"],
+	["primitive-2-operators", "⊸"],
+	["primitive-2-operators", "⟜"],
+	["primitive-2-operators", "⌾"],
+	["primitive-2-operators", "⊘"],
+	["primitive-2-operators", "◶"],
+	["primitive-2-operators", "⎉"],
+	["primitive-2-operators", "⚇"],
+	["primitive-2-operators", "⍟"],
+	["primitive-2-operators", "⎊"],
+
+	["special-name", "𝕨"],
+	["special-name", "𝕩"],
+	["special-name", "𝕗"],
+	["special-name", "𝕘"],
+	["special-name", "𝕤"],
+	["special-name", "𝕣"],
+	["special-name", "𝕎"],
+	["special-name", "𝕏"],
+	["special-name", "𝔽"],
+	["special-name", "𝔾"],
+	["special-name", "𝕊"],
+	["special-name", "_𝕣"],
+	["special-name", "_𝕣_"],
+
+	["punctuation", "←"],
+	["punctuation", "⇐"],
+	["punctuation", "↩"],
+	["punctuation", "("],
+	["punctuation", ")"],
+	["punctuation", "{"],
+	["punctuation", "}"],
+	["punctuation", "⟨"],
+	["punctuation", "⟩"],
+	["punctuation", "["],
+	["punctuation", "]"],
+	["punctuation", "‿"],
+	["punctuation", "·"],
+	["punctuation", "⋄"],
+	["punctuation", ","],
+	["punctuation", "."],
+	["punctuation", ";"],
+	["punctuation", ":"],
+	["punctuation", "?"]
+]
+
+----------------------------------------------------
+
+A test that all of the BQN primitive tokens are correctly identified,
+according to the spec at https://mlochbaum.github.io/BQN/spec/token.html

tests/languages/bqn/words.test

@@ -0,0 +1,54 @@
+1464
+1.618
+1.314E1
+∞
+π
+2π
+¯∞
+TheAboveAreNumbersNotNames
+ThereAre4Symbols_¯∞πAllowedInNames
+ThisIs.aNamespace
+•System_¯∞πFunction
+𝕣
+_𝕣
+_𝕣_
+This𝕣IsNotASingleName
+
+----------------------------------------------------
+
+[
+	["word-number", "1464"],
+	["word-number", "1.618"],
+	["word-number-scientific", "1.314E1"],
+	["word-number", "∞"],
+	["word-number", "π"],
+	["word-number", "2"],
+	["word-number", "π"],
+	["word-number", "¯∞"],
+	["word-name", "TheAboveAreNumbersNotNames"],
+	["word-name", "ThereAre4Symbols_¯∞πAllowedInNames"],
+	["dot-notation-on-name", "ThisIs."],
+	["word-name", "aNamespace"],
+	["function", "•System_¯∞πFunction"],
+	["special-name", "𝕣"],
+	["special-name", "_𝕣"],
+	["special-name", "_𝕣_"],
+	["word-name", "This"],
+	["special-name", "𝕣"],
+	["word-name", "IsNotASingleName"]
+]
+
+----------------------------------------------------
+
+Numbers and variable names share a token formation rule, and are collectively
+called words. A word is a number if it starts with a digit or numeric
+character ¯∞π, and a name otherwise.
+
+Words are formed from digits, letters, and the characters _.¯∞π. All these
+characters stick together, so that you need to separate words with whitespace
+in order to write them next to each other. But . only counts if it's followed
+by a digit: otherwise it forms its own token to support namespace syntax
+ns.field. A word may be preceded by • to form a system name.
+
+The character 𝕣 also sticks with other word-forming characters, but is only
+allowed form the special names 𝕣, _𝕣, and _𝕣_.