Mercurial > projects > dang
annotate lexer/Token.d @ 72:628cb46ab13b new_gen
First update on the way to Arrays! :)
Lexer and ast/Exp now have the types needed.
All that needs to be updated now is the Parser. I suggest two options:
1) Making the Id a class that we can make a ArrayId and PointerId for at some point.
2) Use a struct as now, but adding some bools / ints to give a more abstract description of the type
2) is messy and 1) is slower... :/
author | Anders Johnsen <skabet@gmail.com> |
---|---|
date | Thu, 01 May 2008 23:08:41 +0200 |
parents | 381975d76baf |
children | 192da4976daa |
rev | line source |
---|---|
1 | 1 module lexer.Token; |
2 | |
3 public | |
4 import misc.Location; | |
5 | |
6 import Integer = tango.text.convert.Integer; | |
7 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
8 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
9 The Token struct will be used through the Lexer, Parser and other |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
10 modules as a location into source. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
11 |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
12 The Token should always be optimized for size to limit unnecessary |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
13 memory usage. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
14 */ |
1 | 15 struct Token |
16 { | |
17 Tok type; | |
18 Location location; | |
19 uint length; | |
20 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
21 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
22 Create a new token with a Tok type, Location in source and a |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
23 length of how many chars the Token span in the source |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
24 */ |
1 | 25 static Token opCall (Tok type, Location location, uint length) |
26 { | |
27 Token t; | |
28 t.type = type; | |
29 t.location = location; | |
30 t.length = length; | |
31 return t; | |
32 } | |
33 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
34 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
35 Get the type of the Token as a string |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
36 */ |
1 | 37 char[] getType () |
38 { | |
39 return typeToString[this.type]; | |
40 } | |
41 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
42 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
43 A human readable dump of a Token |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
44 */ |
1 | 45 char[] toString () |
46 { | |
47 return this.getType()~": Len: "~Integer.toString(this.length) | |
48 ~", Loc: "~location.toString; | |
49 } | |
50 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
51 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
52 Get the string in the source that matches what this Token is |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
53 covering. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
54 */ |
1 | 55 char[] get () |
56 { | |
57 return location.get(length); | |
58 } | |
44
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
59 |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
60 /** |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
61 Returns true if the type of this token is a basic type (int, float, ...). |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
62 Void is included, although a void in it self is not really a type. |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
63 */ |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
64 bool isBasicType() |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
65 { |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
66 return type >= Tok.Byte && type <= Tok.Void; |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
67 } |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
68 |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
69 /** |
48
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
70 Returns true for all the various assignments (=, +=, *= ...) |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
71 */ |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
72 bool isAssignment() |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
73 { |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
74 return type == Tok.Assign; |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
75 } |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
76 |
b6c1dc30ca4b
Only tests that dont pass now are structs and switches
Anders Halager <halager@gmail.com>
parents:
44
diff
changeset
|
77 /** |
44
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
78 Just a shortcut to avoid `token.type == Tok.Identifier`. |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
79 */ |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
80 bool isIdentifier() |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
81 { |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
82 return type == Tok.Identifier; |
495188f9078e
Big update - Moving towards a better, more seperated parser
Anders Halager <halager@gmail.com>
parents:
42
diff
changeset
|
83 } |
1 | 84 } |
85 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
86 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
87 Tok is short for TokenType. This enum list is to supply the Token |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
88 with a type. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
89 |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
90 This enum is used to switch over "many" places. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
91 */ |
1 | 92 enum Tok : ushort |
93 { | |
94 /* Non-code related tokens */ | |
95 EOF, | |
96 | |
97 /* Basic types */ | |
98 Identifier, | |
99 Integer, | |
100 | |
101 /* Basic operators */ | |
102 Assign, | |
103 Add, Sub, | |
62
78a6808b2e0f
Added support for "%" - modulus / reminder
Anders Johnsen <skabet@gmail.com>
parents:
48
diff
changeset
|
104 Mul, Div, Mod, |
1 | 105 Comma, |
106 | |
107 /* Symbols */ | |
108 OpenParentheses, | |
109 CloseParentheses, | |
110 OpenBrace, | |
111 CloseBrace, | |
72
628cb46ab13b
First update on the way to Arrays! :)
Anders Johnsen <skabet@gmail.com>
parents:
68
diff
changeset
|
112 OpenBracket, |
628cb46ab13b
First update on the way to Arrays! :)
Anders Johnsen <skabet@gmail.com>
parents:
68
diff
changeset
|
113 CloseBracket, |
1 | 114 Seperator, |
36
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
115 Colon, |
28
69464d465284
Now supporting structs - both read and write. Still a few errors though, so watch out.
Anders Johnsen <skabet@gmail.com>
parents:
22
diff
changeset
|
116 Dot, |
1 | 117 |
8
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
118 /* Comparator operators */ |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
119 Eq, Ne, |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
120 Lt, Gt, |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
121 Le, Ge, |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
122 |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
123 Not, |
6 | 124 |
1 | 125 /* Keywords */ |
126 Byte, Ubyte, | |
127 Short, Ushort, | |
128 Int, Uint, | |
129 Long, Ulong, | |
130 | |
131 Float, Double, | |
132 | |
5
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
133 Bool, |
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
134 |
37 | 135 Void, |
136 | |
22 | 137 Struct, |
138 | |
11
642c6a998fd9
Support for while statements and fixed scope for if
Anders Halager <halager@gmail.com>
parents:
8
diff
changeset
|
139 If, Else, |
642c6a998fd9
Support for while statements and fixed scope for if
Anders Halager <halager@gmail.com>
parents:
8
diff
changeset
|
140 While, |
36
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
141 Switch, Case, Default, |
68
381975d76baf
A LOT of bug fixing - also implemented implicit casts. If you do a --ast-dump-code on a target with some algebra of differant types, you should now see the type casts being made. Also, Tests are again back with only switches failing...
Anders Johnsen <skabet@gmail.com>
parents:
62
diff
changeset
|
142 Return, Cast, |
1 | 143 |
144 } | |
145 | |
42
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
146 /** |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
147 An associative array to supply a Tok to String function. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
148 |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
149 Keep always this list updated when adding a new Tok. |
4e879f82dd64
Added some docs for the lexer - now you can understand _some_ of the madness going on here :)
Anders Johnsen <skabet@gmail.com>
parents:
37
diff
changeset
|
150 */ |
1 | 151 public char[][Tok] typeToString; |
152 | |
153 static this() | |
154 { | |
155 typeToString = | |
156 [ | |
157 Tok.EOF:"EOF"[], | |
158 Tok.Identifier:"Identifier", | |
159 Tok.Byte:"Byte", | |
160 Tok.Short:"Short", | |
161 Tok.Int:"Int", | |
162 Tok.Long:"Long", | |
5
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
163 Tok.Bool:"Bool", |
37 | 164 Tok.Void:"Void", |
8
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
165 Tok.Eq:"Eq", |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
166 Tok.Ne:"Ne", |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
167 Tok.Lt:"Lt", |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
168 Tok.Le:"Le", |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
169 Tok.Gt:"Gt", |
2e1069ee21af
Added Ne, Lt, Le, Gt, Ge and Not in lexer
johnsen@johnsen-desktop
parents:
6
diff
changeset
|
170 Tok.Ge:"Ge", |
1 | 171 Tok.OpenParentheses:"OpenParentheses", |
172 Tok.CloseParentheses:"CloseParentheses", | |
173 Tok.OpenBrace:"OpenBrace", | |
174 Tok.CloseBrace:"CloseBrace", | |
72
628cb46ab13b
First update on the way to Arrays! :)
Anders Johnsen <skabet@gmail.com>
parents:
68
diff
changeset
|
175 Tok.OpenBracket:"OpenBracket", |
628cb46ab13b
First update on the way to Arrays! :)
Anders Johnsen <skabet@gmail.com>
parents:
68
diff
changeset
|
176 Tok.CloseBracket:"CloseBracket", |
28
69464d465284
Now supporting structs - both read and write. Still a few errors though, so watch out.
Anders Johnsen <skabet@gmail.com>
parents:
22
diff
changeset
|
177 Tok.Dot:"Dot", |
1 | 178 Tok.Assign:"Assign", |
179 Tok.Add:"Add", | |
180 Tok.Sub:"Sub", | |
181 Tok.Mul:"Mul", | |
182 Tok.Div:"Div", | |
62
78a6808b2e0f
Added support for "%" - modulus / reminder
Anders Johnsen <skabet@gmail.com>
parents:
48
diff
changeset
|
183 Tok.Mod:"Mod", |
5
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
184 Tok.Integer:"Integer", |
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
185 Tok.If:"If", |
11
642c6a998fd9
Support for while statements and fixed scope for if
Anders Halager <halager@gmail.com>
parents:
8
diff
changeset
|
186 Tok.While:"While", |
36
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
187 Tok.Switch:"Switch", |
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
188 Tok.Case:"Case", |
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
189 Tok.Default:"Default", |
21
0fb2d13dce37
Now working with gdc also (gdc use reverse paremeter validating on function calls)
johnsen@johnsen-laptop
parents:
11
diff
changeset
|
190 Tok.Comma:"Comma", |
5
2c5a8f4c254a
Added very simple if support.
Anders Halager <halager@gmail.com>
parents:
1
diff
changeset
|
191 Tok.Return:"Return", |
22 | 192 Tok.Struct:"Struct", |
36
ce17bea8e9bd
Switch statements support
Anders Halager <halager@gmail.com>
parents:
28
diff
changeset
|
193 Tok.Colon:"Colon", |
68
381975d76baf
A LOT of bug fixing - also implemented implicit casts. If you do a --ast-dump-code on a target with some algebra of differant types, you should now see the type casts being made. Also, Tests are again back with only switches failing...
Anders Johnsen <skabet@gmail.com>
parents:
62
diff
changeset
|
194 Tok.Seperator:"Seperator", |
381975d76baf
A LOT of bug fixing - also implemented implicit casts. If you do a --ast-dump-code on a target with some algebra of differant types, you should now see the type casts being made. Also, Tests are again back with only switches failing...
Anders Johnsen <skabet@gmail.com>
parents:
62
diff
changeset
|
195 Tok.Cast:"Cast" |
1 | 196 ]; |
197 } |