Added support for Factor (#2203)

This adds support for the [Factor](https://factorcode.org) language.

components.json

@@ -313,6 +313,10 @@
 			"require": "clike",
 			"owner": "simonreynolds7"
 		},
+		"factor": {
+			"title": "Factor",
+			"owner": "catb0t"
+		},
 		"firestore-security-rules": {
 			"title": "Firestore security rules",
 			"require": "clike",

examples/prism-factor.html

@@ -0,0 +1,128 @@
+<h2>Comments</h2>
+<pre><code>! FIXME: a comment
+
+USE: multiline
+
+![[ comment ]]
+/* comment */</code></pre>
+
+<h2>Strings</h2>
+<pre><code>"a string" "\"" "\x8" "%s"
+
+SBUF" asbdef"
+
+USE: multiline
+
+STRING: name
+content
+;
+
+HEREDOC: marker
+text
+marker
+
+[==[
+	str
+	ing
+]==]
+</code></pre>
+
+<h2>Numbers</h2>
+<pre><code>5 1/5 +9 -9 +1/5 -1/5 -1/5. 23+1/5 -23-1/5 23-1/5 ! NOTE: last one = word
+
++12.13 0.01 0e0 3E4 3e-4 3E-4 030 0xd 0o30 0b1100
+-12.13 -0 -0.01 -0e0 -3E4 -3E-4 -030 -0xd -0o30 -0b1100
+
+348756424956392657834385437598743583648756332457
+-348756424956392657834385437598743583648756332457
+
+NAN: a
+NAN: 80000deadbeef
+
+0b1.010p2 0x1.0p3 0x1.p1 0b1.111111p1111 ...</code></pre>
+
+<h2>Sequences</h2>
+<pre><code>{ 1 2 3 4 }
+{ a b c d e t f }
+{ "a" "b" "c" }
+
+{ { a b } { c d } }
+H{ { a b } { c d } }
+H{ { "a" "b" } { "c" "d" } }
+V{ 1 2 3 4 }
+V{ "1" "2" "3" "4" }
+BV{ 1 2 3 4 }</code></pre>
+
+<h2>Regular Expressions</h2>
+<pre><code>USE: regexp
+R/ abcde?.*+\?\.\*\+\/\\\/idmsr-idmsr/idmsr-idmsr</code>
+</pre>
+
+<h2>Colon parsing words</h2>
+<pre><code>: a ( -- ) ;
+:: ; ! ; is not a word name
+:: ;a ! ;a is a word name
+USING: a b c ;
+USE: a
+IN: a.b
+CHAR: a
+GENERIC#: x 1 ( x: integer quot: ( x -- y ) -- )</code></pre>
+
+<h2>Special words (builtins, conventions)</h2>
+<pre><code>and not with map filter
+
+new last-index + - neg
+
+&lt;array&gt; <=> SYNTAX: x $[ xyz ]
+
+set-x change-x with-variable ?of if* (gensym) hex. $description reader>> >>setter writer<<
+
+string>number >hex base> mutater!
+</code></pre>
+
+<h2>Full example</h2>
+<pre><code>USING: accessors arrays assocs combinators
+combinators.short-circuit effects io kernel sequences
+sequences.deep splitting strings vocabs words ;
+IN: prism
+
+: make-prism-syntax ( syntax-vocab -- seq )
+ 	vocab-words [
+		dup name>> ">>" = [ drop t ] [
+			{
+				[ "delimiter" word-prop ]
+				[ name>> last { CHAR: : CHAR: { CHAR: [ CHAR: ( CHAR: ) CHAR: ? CHAR: " } member? ]
+				[ name>> { "t" "f" } member? ]
+			} 1|| not
+		] if
+	] filter ;
+
+: combinator? ( word -- ? )
+	[ "declared-effect" word-prop in>> flatten
+		[
+			[ effect? ] [ { "quots" "quot" } member? ] bi or
+		] any?
+	] [
+		"help" word-prop ?first flatten [ dup word? [ name>> ] when "quot" swap subseq? ] any?
+	] bi or ;
+
+: classify ( vocab-spec -- seq )
+	vocab-words [
+		dup {
+			{ [ dup combinator? ] [ drop "combinator" ] }
+			{ [ dup "macro" word-prop ] [ drop "macro" ] }
+			[ drop "ordinary" ]
+		} cond 2array
+	] map ;
+
+: print-strings ( strs -- )
+	[ name>> "'" dup surround ] map ", " join print ; recursive ! WARN: not recursive
+
+: combinators. ( vocab-spec -- )
+	classify [ nip "combinator" = ] assoc-filter keys print-strings ; flushable
+
+: ordinaries. ( vocab-spec -- )
+	classify [ nip "ordinary" = ] assoc-filter keys print-strings ; foldable
+
+: macros. ( vocab-spec -- )
+	classify [ nip "macro" = ] assoc-filter keys print-strings ; inline</code></pre>

tests/languages/factor/builtin_words_feature.test

@@ -0,0 +1,15 @@
+and not with map filter
+
+----------------------------------------------------
+
+[
+	[ "kernel-builtin", "and" ],
+	[ "kernel-builtin", "not" ],
+	[ "combinators", "with" ],
+	[ "combinators", "map" ],
+	[ "combinators", "filter" ]
+]
+
+----------------------------------------------------
+
+some builtins

tests/languages/factor/colon_words_feature.test

@@ -0,0 +1,47 @@
+: a ( -- ) ;
+:: ; ! ; is not a word name
+:: ;a ! ;a is a word name
+USING: a b c ;
+USE: a
+IN: a.b
+CHAR: a
+#: a
+GENERIC#: a
+
+----------------------------------------------------
+
+[
+	[ "colon-syntax", ": a" ],
+
+	[ "stack-effect-delimiter", "(" ],
+	[ "stack-effect-delimiter", "--" ],
+	[ "stack-effect-delimiter", ")" ],
+
+	[ "semicolon-or-setlocal", ";" ],
+
+	[ "normal-word", "::" ],
+	[ "semicolon-or-setlocal", ";" ],
+	[ "comment", [ "! ; is not a word name" ] ],
+
+	[ "colon-syntax", ":: ;a" ],
+	[ "comment", [ "! ;a is a word name" ] ],
+
+	[ "special-using",
+		[ "USING: ",
+			[ "string", "a" ],
+			[ "string", "b" ],
+			[ "string", "c" ]
+		]
+	],
+	[ "semicolon-or-setlocal", ";" ],
+	[ "colon-syntax", "USE: a" ],
+	[ "colon-syntax", "IN: a.b" ],
+	[ "colon-syntax", "CHAR: a" ],
+	[ "normal-word", "#:" ],
+	[ "normal-word", "a" ],
+	[ "colon-syntax", "GENERIC#: a" ]
+]
+
+----------------------------------------------------
+
+colon-ended parsing words

tests/languages/factor/comments_feature.test

@@ -0,0 +1,74 @@
+a! ! word
+!a ! word
+! comment
+!	bad
+! 	fine
+! "also a comment"
+! : ( -- ) ;
+! ! leading comment-like token
+   ! whitespace before
+words blah ! comment after code on a line
+
+![[ comment ]]
+"![[ string ]]"
+![[ "comment" ]]
+
+![[ comment]]
+![==[ comment ]==]
+![==[ comment]==]
+![=[word ]=]
+![=======[ words ]=======]
+
+/* com
+ment */
+/* com
+ment*/
+/*word */
+
+/* "comment" */
+"/* "strings" */"
+
+
+----------------------------------------------------
+
+[
+	[ "conventionally-named-word", "a!"],
+	[ "comment", [ "! word" ] ],
+	[ "normal-word", "!a"],
+	[ "comment", [ "! word" ] ],
+	[ "comment", [ "! comment" ] ],
+
+	[ "normal-word", "!" ], [ "normal-word", "bad" ],
+	[ "comment", [ "! \tfine" ] ],
+
+	[ "comment", [ "! \"also a comment\"" ] ],
+	[ "comment", [ "! : ( -- ) ;" ] ],
+	[ "comment", [ "! ! leading comment-like token" ] ],
+	[ "comment", [ "! whitespace before" ] ],
+	[ "normal-word", "words" ],
+	[ "normal-word", "blah" ],
+	[ "comment", [ "! comment after code on a line" ] ],
+
+	[ "comment", [ "![[ comment ]]" ] ],
+	[ "string", [ "\"![[ string ]]\"" ] ],
+	[ "comment", [ "![[ \"comment\" ]]" ] ],
+	[ "comment", [ "![[ comment]]" ] ],
+	[ "comment", [ "![==[ comment ]==]" ] ],
+	[ "comment", [ "![==[ comment]==]" ] ],
+
+	[ "normal-word", "![=[word" ],
+	[ "normal-word", "]=]" ],
+	[ "normal-word", "![=======[" ],
+	[ "normal-word", "words" ],
+	[ "normal-word", "]=======]" ],
+	[ "comment", [ "/* com\r\nment */" ] ],
+	[ "comment", [ "/* com\r\nment*/" ] ],
+	[ "normal-word", "/*word" ],
+ 	[ "normal-word", "*/" ],
+	[ "comment", ["/* \"comment\" */"] ],
+	[ "string", ["\"/* \""] ],
+	"strings",
+	[ "string", ["\" */\""] ]
+]
+
+----------------------------------------------------

tests/languages/factor/constructors_feature.test

@@ -0,0 +1,18 @@
+<array> <byte-array> <string>
+
+<=> <-->
+
+----------------------------------------------------
+
+[
+	[ "constructor-word", "<array>" ],
+	[ "constructor-word", "<byte-array>" ],
+	[ "constructor-word", "<string>" ],
+
+	[ "conventionally-named-word", "<=>" ],
+	[ "conventionally-named-word", "<-->" ]
+]
+
+----------------------------------------------------
+
+ctors

tests/languages/factor/normal_words_feature.test

@@ -0,0 +1,56 @@
+commas, primes'
+set-x
+change-x
+with-x
+new-x
+>string
+base>
+string>number
++symbol+
+que?
+?of
+?of*
+reader>>
+>>setter
+writer<<
+(detail)
+mutater!
+variant*
+prettyprint.
+$help
+
+"no
+
+----------------------------------------------------
+
+[
+	[ "normal-word", "commas," ],
+	[ "normal-word", "primes'" ],
+	[ "conventionally-named-word", "set-x" ],
+	[ "conventionally-named-word", "change-x" ],
+	[ "conventionally-named-word", "with-x" ],
+	[ "conventionally-named-word", "new-x" ],
+	[ "conventionally-named-word", ">string" ],
+	[ "conventionally-named-word", "base>" ],
+	[ "conventionally-named-word", "string>number" ],
+	[ "conventionally-named-word", "+symbol+" ],
+	[ "conventionally-named-word", "que?" ],
+	[ "conventionally-named-word", "?of" ],
+	[ "conventionally-named-word", "?of*" ],
+	[ "conventionally-named-word", "reader>>" ],
+	[ "conventionally-named-word", ">>setter" ],
+	[ "conventionally-named-word", "writer<<" ],
+	[ "conventionally-named-word", "(detail)" ],
+	[ "conventionally-named-word", "mutater!" ],
+	[ "conventionally-named-word", "variant*" ],
+	[ "conventionally-named-word", "prettyprint." ],
+	[ "conventionally-named-word", "$help" ],
+	"\r\n\r\n\"no"
+]
+
+----------------------------------------------------
+
+"Normal" words are not builtin well-known ones like "not", "and", "<=>", though they may be in the standard library or user-defined.
+They may start with any character except `"` (double-quote), but may contain or end with double-quotes or any other non-whitespace character.
+
+Conventionally named words follow the conventions outlined in prism-factor.js.