Added Hoon programming language (#2978)

Co-authored-by: Michael Schmidt <mitchi5000.ms@googlemail.com>

components.json

@@ -518,6 +518,10 @@
 			"require": "c",
 			"owner": "RunDevelopment"
 		},
+		"hoon": {
+			"title": "Hoon",
+			"owner": "matildepark"
+		},
 		"http": {
 			"title": "HTTP",
 			"optional": [

components/prism-hoon.js

@@ -0,0 +1,19 @@
+Prism.languages.hoon = {
+	'constant': /%(?:\.[ny]|[\w-]+)/,
+	'comment': {
+		pattern: /::.*/,
+		greedy: true
+	},
+	'function': /(?:\+[-+] {2})?(?:[a-z](?:[a-z0-9-]*[a-z0-9])?)/,
+	'class-name': [
+		{
+			pattern: /@(?:[A-Za-z0-9-]*[A-Za-z0-9])?/,
+		},
+		/\*/
+	],
+	'string': {
+		pattern: /"[^"]*"|'[^']*'/,
+		greedy: true
+	},
+	'keyword': /:_|\.[\^\+\*=\?]|![><:\.=\?!]|=[>|:,\.\-\^<+;/~\*\?]|\?[>|:\.\-\^<\+&~=@!]|\|[\$_%:\.\-\^~\*=@\?]|\+[|\$\+\*]|:[_\-\^\+~\*]|%[_:\.\-\^\+~\*=]|\^[|:\.\-\+&~\*=\?]|\$[|_%:<>\-\^&~@=\?]|;[:<\+;\/~\*=]|~[>|\$_%<\+\/&=\?!]|--|==/
+};

examples/prism-hoon.html

@@ -0,0 +1,17 @@
+<h2>Caesar cipher</h2>
+
+<pre><code>|= [a=@ b=tape]
+^- tape
+?: (gth a 25)
+$(a (sub a 26))
+%+ turn b
+|= c=@tD
+?: &((gte c 'A') (lte c 'Z'))
+=. c (add c a)
+?. (gth c 'Z') c
+(sub c 26)
+?: &((gte c 'a') (lte c 'z'))
+=. c (add c a)
+?. (gth c 'z') c
+(sub c 26)
+c</code></pre>

tests/identifier-test.js

@@ -39,6 +39,11 @@ const testOptions = {
 		word: false,
 		template: false
 	},
+	// Hoon uses _ in its keywords
+	'hoon': {
+		word: false,
+		template: false
+	},
 
 	// LilyPond doesn't tokenize based on words
 	'lilypond': {

tests/languages/hoon/comments_and_leaves.test

@@ -0,0 +1,59 @@
+::  Arvo formal interface
+    ::
+    ::    this lifecycle wrapper makes the arvo door (multi-armed core)
+    ::    look like a gate (function or single-armed core), to fit
+    ::    urbit's formal lifecycle function. a practical interpreter
+    ::    can ignore it.
+    ::
+    |=  [now=@da ovo=*]
+    ^-  *
+    ~>  %slog.[0 leaf+"arvo-event"]
+    .(+> +:(poke now ovo))
+
+----------------------------------------------------
+
+[
+	["comment", "::  Arvo formal interface"],
+
+	["comment", "::"],
+
+	["comment", "::    this lifecycle wrapper makes the arvo door (multi-armed core)"],
+
+	["comment", "::    look like a gate (function or single-armed core), to fit"],
+
+	["comment", "::    urbit's formal lifecycle function. a practical interpreter"],
+
+	["comment", "::    can ignore it."],
+
+	["comment", "::"],
+
+	["keyword", "|="],
+	"  [",
+	["function", "now"],
+	"=",
+	["class-name", "@"],
+	["function", "da"],
+	["function", "ovo"],
+	"=",
+	["class-name", "*"],
+	"]\r\n    ",
+
+	["keyword", "^-"],
+	["class-name", "*"],
+
+	["keyword", "~>"],
+	["constant", "%slog"],
+	".[0 ",
+	["function", "leaf"],
+	"+",
+	["string", "\"arvo-event\""],
+	"]\r\n    .(+> +:(",
+	["function", "poke"],
+	["function", "now"],
+	["function", "ovo"],
+	"))"
+]
+
+----------------------------------------------------
+
+Tests for block comments and the inclusion of tapes and leaves inline in cells.

tests/languages/hoon/core_with_arms.test

@@ -0,0 +1,83 @@
+|%
+::  #  %math
+::    unsigned arithmetic
++|  %math
+++  add
+  ~/  %add
+  ::  unsigned addition
+  ::
+  ::  a: augend
+  ::  b: addend
+  |=  [a=@ b=@]
+  ::  sum
+  ^-  @
+  ?:  =(0 a)  b
+  $(a (dec a), b +(b))
+::
+++  dec
+
+----------------------------------------------------
+
+[
+	["keyword", "|%"],
+
+	["comment", "::  #  %math"],
+
+	["comment", "::    unsigned arithmetic"],
+
+	["keyword", "+|"],
+	["constant", "%math"],
+
+	["function", "++  add"],
+
+	["keyword", "~/"],
+	["constant", "%add"],
+
+	["comment", "::  unsigned addition"],
+
+	["comment", "::"],
+
+	["comment", "::  a: augend"],
+
+	["comment", "::  b: addend"],
+
+	["keyword", "|="],
+	"  [",
+	["function", "a"],
+	"=",
+	["class-name", "@"],
+	["function", "b"],
+	"=",
+	["class-name", "@"],
+	"]\r\n  ",
+
+	["comment", "::  sum"],
+
+	["keyword", "^-"],
+	["class-name", "@"],
+
+	["keyword", "?:"],
+	"  =(0 ",
+	["function", "a"],
+	")  ",
+	["function", "b"],
+
+	"\r\n  $(",
+	["function", "a"],
+	" (",
+	["function", "dec"],
+	["function", "a"],
+	"), ",
+	["function", "b"],
+	" +(",
+	["function", "b"],
+	"))\r\n",
+
+	["comment", "::"],
+
+	["function", "++  dec"]
+]
+
+----------------------------------------------------
+
+Tests for a sample definition of a core with an arm.

tests/languages/hoon/nested_strings.test

@@ -0,0 +1,124 @@
+|=  [a=@ b=tape]
+^-  tape
+?:  (gth a 25)
+  $(a (sub a 26))
+%+  turn  b
+|=  c=@tD
+?:  &((gte c 'A') (lte c 'Z'))
+  =.  c  (add c a)
+  ?.  (gth c 'Z')  c
+  (sub c 26)
+?:  &((gte c 'a') (lte c 'z'))
+  =.  c  (add c a)
+  ?.  (gth c 'z')  c
+  (sub c 26)
+c
+
+----------------------------------------------------
+
+[
+	["keyword", "|="],
+	"  [",
+	["function", "a"],
+	"=",
+	["class-name", "@"],
+	["function", "b"],
+	"=",
+	["function", "tape"],
+	"]\r\n",
+
+	["keyword", "^-"],
+	["function", "tape"],
+
+	["keyword", "?:"],
+	"  (",
+	["function", "gth"],
+	["function", "a"],
+	" 25)\r\n  $(",
+	["function", "a"],
+	" (",
+	["function", "sub"],
+	["function", "a"],
+	" 26))\r\n",
+
+	["keyword", "%+"],
+	["function", "turn"],
+	["function", "b"],
+
+	["keyword", "|="],
+	["function", "c"],
+	"=",
+	["class-name", "@"],
+	["function", "t"],
+	"D\r\n",
+
+	["keyword", "?:"],
+	"  &((",
+	["function", "gte"],
+	["function", "c"],
+	["string", "'A'"],
+	") (",
+	["function", "lte"],
+	["function", "c"],
+	["string", "'Z'"],
+	"))\r\n  ",
+
+	["keyword", "=."],
+	["function", "c"],
+	"  (",
+	["function", "add"],
+	["function", "c"],
+	["function", "a"],
+	")\r\n  ",
+
+	["keyword", "?."],
+	"  (",
+	["function", "gth"],
+	["function", "c"],
+	["string", "'Z'"],
+	")  ",
+	["function", "c"],
+
+	"\r\n  (",
+	["function", "sub"],
+	["function", "c"],
+	" 26)\r\n",
+
+	["keyword", "?:"],
+	"  &((",
+	["function", "gte"],
+	["function", "c"],
+	["string", "'a'"],
+	") (",
+	["function", "lte"],
+	["function", "c"],
+	["string", "'z'"],
+	"))\r\n  ",
+
+	["keyword", "=."],
+	["function", "c"],
+	"  (",
+	["function", "add"],
+	["function", "c"],
+	["function", "a"],
+	")\r\n  ",
+
+	["keyword", "?."],
+	"  (",
+	["function", "gth"],
+	["function", "c"],
+	["string", "'z'"],
+	")  ",
+	["function", "c"],
+
+	"\r\n  (",
+	["function", "sub"],
+	["function", "c"],
+	" 26)\r\n",
+
+	["function", "c"]
+]
+
+----------------------------------------------------
+
+Tests using the Caesar cipher to demonstrate multiple occasions of cords and tapes on the same line, correcting avoiding clobbering two cord and tape definitions into one.