# JOE syntax highlight file for OCaml

# A (deterministic) state machine which performs lexical analysis of OCaml.
# (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		bold red
=Comment 	green
=Literal 	cyan
=Escape 	bold cyan
=Type 		bold
=Keyword 	bold
=Operator	blue
=Control	magenta
=CapId		blue
=LowId
=Stdlib		bold blue

# Bugs:
# = in some contexts is a control, not an operator (let, etc)
# "type" keyword introduces a type = type

:expr Expr
	*		expr
	"#.,)];"	control		recolor=-1
	"!?"		prefixop	recolor=-1
	"=<>@^&+*/$%"	infixop		recolor=-1
	"\-"		minus		recolor=-1
	"~"		tilde		recolor=-1
	"["		brace		recolor=-1
	"|"		pipe		recolor=-1
	":"		colon		recolor=-1
	"("		bracket		recolor=-1
	"0"		zero		recolor=-1
	"1-9"		decimal		recolor=-1
	"\""		string		recolor=-1
	"\'"		char		recolor=-1
	"a-z_"		lowid		buffer recolor=-1
	"A-Z`"		capid		buffer recolor=-1

:bad Bad
	*		expr

:control Control
	*		expr		noeat

:prefixop Operator
	*		operator	noeat

:infixop Operator
	*		operator	noeat

:operator Operator
	*		expr 		noeat
	"!?~=<>@^|&+*/$%.:\-"	operator

:minus Operator
	*		operator	noeat
	"0"		zero		recolor=-2
	"1-9"		decimal		recolor=-2

:tilde Operator
	*		prefixop	noeat
	"a-z"		opparam		noeat

:opparam LowId
	*		expr		noeat
	"a-zA-Z0-9_'"	opparam
	":"		control

:brace Control
	*		expr		noeat
	"|"		expr

:pipe Operator
	*		infixop		noeat
	"]"		pipeclose	recolor=-2

:pipeclose Control
	*		expr		noeat	

:colon Operator
	*		type1		noeat
	"="		assign		recolor=-2

:assign Operator
	*		expr		noeat

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

:zero Literal
	*		expr		noeat
	"0-9_"		decimal
	"b"		binaryl		buffer
	"B"		binaryh		buffer
	"o"		octall		buffer
	"O"		octalh		buffer
	"x"		hexl		buffer
	"X"		hexh		buffer
	"e"		epartl		buffer
	"E"		eparth		buffer
	"."		float

:decimal Literal
	*		expr		noeat
	"0-9_"		decimal
	"."		float
	"e"		epartl		buffer
	"E"		eparth		buffer

:binaryl Literal
	*		lowid		noeat recolor=-2
	"01"		binary
:binaryh Literal
	*		capid		noeat recolor=-2
	"01"		binary
:binary Literal
	*		expr		noeat
	"01_"		binary

:octall Literal
	*		lowid		noeat recolor=-2
	"0-7"		octal
:octalh Literal
	*		capid		noeat recolor=-2
	"0-7"		octal
:octal Literal
	*		expr		noeat
	"0-7_"		octal

:hexl Literal
	*		lowid		noeat recolor=-2
	"0-9a-fA-F"	hex
:hexh Literal
	*		capid		noeat recolor=-2
	"0-9a-fA-F"	hex
:hex Literal
	*		expr		noeat
	"0-9a-fA-F_"	hex

:float Literal
	*		expr		noeat
	"0-9_"		float
	"e"		epartl		buffer
	"E"		eparth		buffer

:epartl Literal
	*		lowid		noeat recolor=-2
	"0-9"		enum
	"+\-"		enum1
:eparth Literal
	*		capid		noeat recolor=-2
	"0-9"		enum
	"+\-"		enum1

:enum1 Literal
	*		bad		noeat
	"0-9_"		enum
:enum Literal
	*		expr		noeat
	"0-9_"		enum

:string	Literal
	*		string
	"\""		expr
	"\\"		string_escape	recolor=-1
	"%"		string_control	recolor=-1

:string_escape Escape
	*		string
	"x"		string_hex1
	"0-7"		string_octal2

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

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

:string_octal2 Escape
	*		string		noeat
	"0-7"		string_octal3

:string_octal3 Escape
	*		string		noeat
	"0-7"		string

:string_control Escape
	*		string_control
	"\""		string		noeat
	"diouxXeEfFgGaAcspn%SC"	string

:char Literal
	*		charend
	"\\"		char_escape	recolor=-1

:charend Literal
	*		bad		noeat
	"\'"		expr

:char_escape Escape
	*		charend
	"x"		char_hex1
	"0-7"		char_octal2

:char_hex1 Escape
	*		bad		noeat
	"0-9a-fA-F"	char_hex2

:char_hex2 Escape
	*		charend		noeat
	"0-9a-fA-F"	charend

:char_octal2 Escape
	*		charend		noeat
	"0-7"		char_octal3

:char_octal3 Escape
	*		charend		noeat
	"0-7"		charend

:lowid LowId
	*		expr		noeat strings
	"_"		kw
	"and"		kw
	"as"		kw
	"assert"	kw
	"begin"		kw
	"class"		kw
	"constraint"	kw
	"do"		kw
	"done"		kw
	"downto"	kw
	"else"		kw
	"end"		kw
	"exception"	kw
	"external"	kw
	"false"		kw
	"for"		kw
	"fun"		kw
	"function"	kw
	"functor"	kw
	"if"		kw
	"in"		kw
	"include"	kw
	"inherit"	kw
	"initializer"	kw
	"lazy"		kw
	"let"		kw
	"match"		kw
	"method"	kw
	"module"	kw
	"mutable"	kw
	"new"		kw
	"object"	kw
	"of"		kw
	"open"		kw
	"private"	kw
	"raise"		kw # technically not, but ...
	"rec"		kw
	"sig"		kw
	"struct"	kw
	"then"		kw
	"to"		kw
	"true"		kw
	"try"		kw
	"type"		kw
	"val"		kw
	"virtual"	kw
	"when"		kw
	"while"		kw
	"with"		kw
	"asr"		operatorkw
	"land"		operatorkw
	"lor"		operatorkw
	"lsl"		operatorkw
	"lsr"		operatorkw
	"lxor"		operatorkw
	"mod"		operatorkw
	"or"		operatorkw
done
	"a-zA-Z0-9_'"	lowid

:kw Keyword
	*		expr		noeat

:operatorkw Operator
	*		expr		noeat

:capid CapId
	*		expr		noeat strings
	"Arg"		stdlib
	"Array"		stdlib
	"ArrayLabels"	stdlib
	"Buffer"	stdlib
	"Callback"	stdlib
	"Char"		stdlib
	"Complex"	stdlib
	"Digest"	stdlib
	"Filename"	stdlib
	"Format"	stdlib
	"Gc"		stdlib
	"Genlex"	stdlib
	"Hashtbl"	stdlib
	"Int32"		stdlib
	"Int64"		stdlib
	"Lazy"		stdlib
	"Lexing"	stdlib
	"List"		stdlib
	"ListLabels"	stdlib
	"Map"		stdlib
	"Marshal"	stdlib
	"MoreLabels"	stdlib
	"Nativeint"	stdlib
	"Oo"		stdlib
	"Parsing"	stdlib
	"Printexc"	stdlib
	"Printf"	stdlib
	"Queue"		stdlib
	"Random"	stdlib
	"Scanf"		stdlib
	"Set"		stdlib
	"Sort"		stdlib
	"Stack"		stdlib
	"StdLabels"	stdlib
	"Stream"	stdlib
	"String"	stdlib
	"StringLabels"	stdlib
	"Sys"		stdlib
	"Weak"		stdlib
done
	"a-zA-Z0-9_'"	capid

:stdlib Stdlib
	*		expr		noeat

:type1	Type
	*		expr		noeat
	"a-z *>'\t\-"	type1
	"("		type2

:type2	Type
	*		expr		noeat
	"a-z *>'\t\-"	type2
	"("		type3
	")"		type1

:type3	Type
	*		expr		noeat
	"a-z *>'\t\-"	type3
	"("		type4
	")"		type2

:type4	Type
	*		expr		noeat
	"a-z *>'\t\-"	type4
	"("		expr 				# too deep nesting
	")"		type2

: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