ne 2.5-1 / usr / share / ne / syntax / sml.jsf

# JOE syntax highlight file for SML

# A (deterministic) state machine which performs lexical analysis of SML.
# (This is the "assembly language" of syntax highlighting.  A separate
# program could be used to convert a regular expression NFA syntax into this
# format).

# Each state begins with ':<name> <color-name>'
# <color-name> is the color used for characters eaten by the state
# (really a symbol for a user definable color).

# The first state defined is the initial state.

# Within a state, define transitions (jumps) to other states.  Each
# jump has the form: <character-list> <target-state> [<option>s]

# There are two ways to specify <character-list>s, either * for any
# character not otherwise specified, or a literal list of characters within
# quotes (ranges and escape sequences allows).  When the next character
# matches any in the list, a jump to the target-state is taken and the
# character is eaten (we advance to the next character of the file to be
# colored).
#
# The * transition should be the first transition specified in the state.
#
# There are several options:
#   noeat     	do not eat the character, instead feed it to the next state
#             	(this tends to make the states smaller, but be careful: you
#		can make infinite loops).  'noeat' implies 'recolor=-1'.
#
#   recolor=-N	Recolor the past N characters with the color of the
#		target-state.  For example once /* is recognized as the
#		start of C comment, you want to color the /* with the C
#		comment color.
#
#   buffer    	start copying characters to a buffer, beginning with this
#		one (it's ok to not terminate buffering with a matching
#		'strings' option- the buffer is limited to leading 19
#		characters).
#
#   strings	A list of strings follows.  If the buffer matches any of the
#		given strings, a jump to the target-state in the string list
#		is taken instead of the normal jump.
#
#   istrings	Same as strings, but case is ignored.
#
#   hold        Stop buffering string- a future 'strings' or 'istrings' will
#               look at contents of buffer at this point.  Useful for distinguishing
#               commands and function calls in some languages 'write 7' is a command
#               'write (' is a function call- hold lets us stop at the space and delay
#               the string lookup until the ( or 7.
#
#   The format of the string list is:
#
#      "string"   <target-state> [<options>s]
#      "string"   <target-state> [<options>s]
#      done
#
#   (all of the options above are allowed except "strings", "istrings" and "noeat".  noeat is
#    always implied after a matched string).
#
# Weirdness: only states have colors, not transitions.  This means that you
# sometimes have to make dummy states with '* next-state noeat' just to get
# a color specification.

# Define no. sync lines
# You can say:
# -200     means 200 lines
# -        means always start parsing from beginning of file when we lose sync
#          if nothing is specified, the default is -50

# Define colors
#
# bold inverse blink dim underline
# white cyan magenta blue yellow green red black
# bg_white bg_cyan bg_magenta bg_blue bg_yellow bg_green bg_red bg_black

=Expr
=Bad		bg_red
=Comment 	green
=Literal 	cyan
=Escape 	bold cyan
=Type 		blue
=Keyword 	bold
=Operator	bold black
=Control	green
=Id

:expr Expr
	*		expr
	".,[{})];"	control		recolor=-1 # . or ... both control
	"("		bracket		recolor=-1
	"_"		underline	recolor=-1
	"!%&$+/:<=>?@`^|*\-" operator	buffer recolor=-1
	"#"		hash		recolor=-1
	"~"		tilde		recolor=-1
	"0"		zero		recolor=-1
	"1-9"		decimal		recolor=-1
	"\""		string		recolor=-1
	"a-zA-Z"	id		buffer recolor=-1

:bad Bad
	*		expr

:control Control
	*		expr		noeat

:bracket Control
	*		expr		noeat
	"*"		comment1	recolor=-2

:underline Keyword
	*		expr		noeat
	"a-zA-Z"	kw

:operator Operator
	*		expr 		noeat strings
	":>"		colon
	":"		colon
	"::"		control # can be overloaded, but you would burn in hell
	":="		control # ditto
	"="		control # only in some contexts is it _really_ control
	"->"		control
	"=>"		control
	"|"		control
done
	"!%&$+/:<=>?@~`^|#*\-" operator

:colon Control
	*		type1		noeat

:hash Control
	*		expr		noeat
	"!%&$+/:<=>?@~`^|#*\-" operator	recolor=-2
	"\""		string		recolor=-2
	
:tilde Operator
	*		expr		noeat
	"!%&$+/:<=>?@~`^|#*\-" operator
	"0"		zero		recolor=-2
	"1-9"		decimal		recolor=-2

:zero Literal
	*		expr		noeat
	"0-9"		decimal
	"w"		word		buffer
	"x"		hex1		buffer
	"e"		epart		buffer
	"E"		epart		buffer
	"."		float1

:word Literal
	*		id		noeat recolor=-2
	"0-9"		decimal
	"x"		hexword

:hexword Literal
	*		id		noeat recolor=-3
	"0-9a-fA-F"	hex

:hex1 Literal
	*		id		noeat recolor=-2
	"0-9a-fA-F"	hex

:hex Literal
	*		expr		noeat
	"0-9a-fA-F"	hex

:decimal Literal
	*		expr		noeat
	"0-9"		decimal
	"."		float1
	"e"		epart		buffer
	"E"		epart		buffer

# trailing digits required in SML (unlike OCaml)
:float1 Literal
	*		bad		noeat
	"0-9"		float

:float Literal
	*		expr		noeat
	"0-9"		float
	"e"		epart		buffer
	"E"		epart		buffer

:epart Literal
	*		id		noeat recolor=-2
	"0-9"		enum
	"~"		epart		# bug: 3e~~3

:enum Literal
	*		expr		noeat
	"0-9"		enum

:string	Literal
	*		string
	"\""		expr
	"\n"		bad
	"\\"		string_escape	recolor=-1

:string_escape Escape
	*		bad		noeat
	"abfnrtv\"\\"	string
	"^"		string_carret
	"u"		string_hex1
	"0-9"		string_decimal2
	"\n\r\f\t "	string_eatws

:string_carret Escape
	*		bad		noeat
	"ABCDEFGHIJKLMNOPQRSTUVWXYZ\\^_" string

:string_eatws Escape
	*		bad 		noeat
	"\n\r\f\t "	string_eatws
	"\\"		string

:string_hex1 Escape
	*		bad		noeat
	"0-9a-fA-F"	string_hex2

:string_hex2 Escape
	*		bad		noeat
	"0-9a-fA-F"	string_hex3

:string_hex3 Escape
	*		bad		noeat
	"0-9a-fA-F"	string_hex4

:string_hex4 Escape
	*		bad		noeat
	"0-9a-fA-F"	string

:string_decimal2 Escape
	*		bad		noeat
	"0-9"		string_decimal3

:string_decimal3 Escape
	*		bad		noeat
	"0-9"		string

:id Id
	*		expr		noeat strings
	"_"		kw
	"ann"		kw
	"and"		kw
	"as"		kw
	"case"		kw
	"do"		kw
	"else"		kw
	"end"		kw
	"exception"	kw
	"fn"		kw
	"fun"		kw
	"functor"	kw
	"handle"	kw
	"if"		kw
	"in"		kw
	"include"	kw
	"infix"		kw
	"infixr"	kw
	"let"		kw
	"local"		kw
	"nil"		kw
	"nonfix"	kw
	"of"		kw
	"op"		kw
	"open"		kw
	"raise"		kw
	"rec"		kw
	"sharing"	kw
	"sig"		kw
	"signature"	kw
	"struct"	kw
	"structure"	kw
	"then"		kw
	"val"		kw
	"where"		kw
	"while"		kw
	"with"		kw
	"abstype"	kwtype
	"datatype"	kwtype
	"eqtype"	kwtype
	"type"		kwtype
	"withtype"	kwtype
	"before"	operatorkw
	"o"		operatorkw
	"orelse"	operatorkw
	"andalso"	operatorkw
	"div"		operatorkw
	"mod"		operatorkw
done
	"a-zA-Z0-9_'"	id

:kw Keyword
	*		expr		noeat
	"a-zA-Z0-9_'"	kw

:operatorkw Operator
	*		expr		noeat

:kwtype Keyword
	*		kwtype1		noeat

:kwtype1 Type
	*		expr		noeat
	"="		typeval		recolor=-1
	"a-zA-Z0-9_'., :|*>\t\-" kwtype1
	"({"		kwtype2

:kwtype2 Type
	*		expr		noeat
	")}"		kwtype1
	"a-zA-Z0-9_'., :|*>\t\n\-" kwtype2
	"({"		kwtype3

:kwtype3 Type
	*		expr		noeat
	")}"		kwtype2
	"a-zA-Z0-9_'., :|*>\t\n\-" kwtype3
	"({"		expr				# too deep nesting

:typeval Control
	*		type1		noeat
	" \t\n"		typeval

:type1 Type
	*		expr		noeat
	"a-zA-Z0-9_'., :|*>\t\-" type1
	"({"		type2

:type2 Type
	*		expr		noeat
	")}"		type1
	"a-zA-Z0-9_'., :|*>\t\n\-" type2
	"({"		type3

:type3 Type
	*		expr		noeat
	")}"		type2
	"a-zA-Z0-9_'., :|*>\t\n\-" type3
	"({"		type4

:type4 Type
	*		expr		noeat
	")}"		type3
	"a-zA-Z0-9_'., :|*>\t\n\-" type4
	"({"		expr 				# too deep nesting

:comment1 Comment
	*		comment1
	"("		nestcomment1
	"*"		endcomment1

:nestcomment1 Comment
	*		comment1
	"*"		comment2

:endcomment1 Comment
	*		comment1
	")"		expr
	"*"		endcomment1

:comment2 Comment
	*		comment2
	"("		nestcomment2
	"*"		endcomment2

:nestcomment2 Comment
	*		comment2
	"*"		comment3

:endcomment2 Comment
	*		comment2
	")"		comment1
	"*"		endcomment2

:comment3 Comment
	*		comment3
	"("		nestcomment3
	"*"		endcomment3

:nestcomment3 Comment
	*		comment3
	"*"		expr				# too deep nesting

:endcomment3 Comment
	*		comment3
	")"		comment2
	"*"		endcomment3