1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
|
{
open Tokens
module T = Qsp_syntax.T
exception UnclosedQuote of { content: string ; line : int}
(* The comment system is terrible. The same symbol can be used for :
- starting a comment
- inequality operation
In order to manage this, I try to identify the context in a very basic way,
using a flag True False for determining the token to send.
*)
module Bucket = Ephemeron.K1.Bucket
type bucket = (Lexing.lexbuf, int) Bucket.t
let is_expression : bucket = Bucket.make ()
let incr_level lexbuf =
match Bucket.find is_expression lexbuf with
| None -> Bucket.add is_expression lexbuf 1
| Some v -> Bucket.add is_expression lexbuf (v+1)
let decr_level lexbuf =
match Bucket.find is_expression lexbuf with
| None -> ()
| Some v ->
if v > 1 then
Bucket.add is_expression lexbuf (v-1)
else
Bucket.remove is_expression lexbuf
let keyword_table = Hashtbl.create 53
let _ =
List.iter (fun (kwd, tok) -> Hashtbl.add keyword_table kwd tok)
[ "ACT", ACT
; "ADDLIB", KEYWORD "INCLIB"
; "ADDOBJ", KEYWORD "ADDOBJ"
; "ADD OBJ", KEYWORD "ADDOBJ"
; "ADDQST", KEYWORD "INCLIB"
; "AND", AND
; "ARRCOMP", FUNCTION T.Arrcomp
; "ARRPOS", FUNCTION T.Arrpos
; "ARRSIZE", FUNCTION T.Arrsize
(*
; "BACKIMAGE", KEYWORD "BACKIMAGE"
; "$BACKIMAGE", KEYWORD "BACKIMAGE"
; "BCOLOR", KEYWORD "BCOLOR"
*)
; "CLA", KEYWORD "CLA"
; "CLEAR", KEYWORD "CLEAR"
; "*CLEAR", KEYWORD "*CLEAR"
; "CLOSE", KEYWORD "CLOSE"
; "CLOSE ALL", KEYWORD "CLOSEALL"
; "CLR", KEYWORD "CLEAR"
; "*CLR", KEYWORD "*CLEAR"
; "CLS", KEYWORD "CLS"
; "CMDCLEAR", KEYWORD "CMDCLEAR"
; "CMDCLR", KEYWORD "CMDCLEAR"
; "COPYARR", KEYWORD "COPYARR"
; "COUNTOBJ", FUNCTION T.Countobj
; "CURACTS", IDENT "CURACTS"
; "$CURACTS", IDENT "CURACTS"
; "CURLOC", IDENT "CURLOC"
; "$CURLOC", IDENT "CURLOC"
(*
; "DEBUG", KEYWORD "DEBUG"
*)
; "DELACT", KEYWORD "DELACT"
; "DEL ACT", KEYWORD "DELACT"
; "DELLIB", KEYWORD "FREELIB"
; "DELOBJ", KEYWORD "DELOBJ"
; "DEL OBJ", KEYWORD "DELOBJ"
; "DESC", FUNCTION T.Desc
; "$DESC", FUNCTION T.Desc'
(*
; "DISABLESCROLL", KEYWORD "DISABLESCROLL"
; "DISABLESUBEX", KEYWORD "DISABLESUBEX"
*)
; "DYNAMIC", KEYWORD "DYNAMIC"
; "DYNEVAL", FUNCTION T.Dyneval
; "$DYNEVAL", FUNCTION T.Dyneval'
; "ELSE", ELSE
; "ELSEIF", ELIF
; "END", END
; "EXEC", KEYWORD "EXEC"
; "EXIT", KEYWORD "EXIT"
(*
; "FCOLOR", KEYWORD "FCOLOR"
; "$FNAME", KEYWORD "$FNAME"
*)
; "FREELIB", KEYWORD "FREELIB"
(*
; "FSIZE", KEYWORD "FSIZE"
*)
; "FUNC", FUNCTION T.Func
; "$FUNC", FUNCTION T.Func'
; "GETOBJ", FUNCTION T.Getobj
; "$GETOBJ", FUNCTION T.Getobj'
; "GOSUB", KEYWORD "GOSUB"
; "GOTO", KEYWORD "GOTO"
(*
; "GC", KEYWORD "GC"
*)
; "GS", KEYWORD "GOSUB"
; "GT", KEYWORD "GOTO"
; "IF", IF
; "IIF", FUNCTION T.Iif
; "$IIF", FUNCTION T.Iif'
; "INCLIB", KEYWORD "INCLIB"
; "INPUT", FUNCTION T.Input
; "$INPUT", FUNCTION T.Input'
; "INSTR", FUNCTION T.Instr
; "ISNUM", FUNCTION T.Isnum
; "ISPLAY", FUNCTION T.Isplay
; "JUMP", KEYWORD "JUMP"
; "KILLALL", KEYWORD "KILLALL"
; "KILLOBJ", KEYWORD "KILLOBJ"
; "KILLQST", KEYWORD "FREELIB"
; "KILLVAR", KEYWORD "KILLVAR"
; "LCASE", FUNCTION T.Lcase
; "$LCASE", FUNCTION T.Lcase'
(*
; "LCOLOR", KEYWORD "LCOLOR"
*)
; "LEN", FUNCTION T.Len
; "LET", LET
; "LOC", LOC
; "MAINTXT", IDENT "MAINTXT"
; "$MAINTXT", IDENT "MAINTXT"
; "MAX", FUNCTION T.Max
; "$MAX", FUNCTION T.Max'
; "MENU", KEYWORD "MENU"
; "MID", FUNCTION T.Mid
; "$MID", FUNCTION T.Mid'
; "MIN", FUNCTION T.Min
; "$MIN", FUNCTION T.Min'
; "MOD", MOD
; "MSECSCOUNT", FUNCTION T.Msecscount
; "MSG", KEYWORD "MSG"
; "NL", KEYWORD "NL"
; "*NL", KEYWORD "*NL"
; "NO", NO
(*
; "NOSAVE", KEYWORD "NOSAVE"
*)
; "OBJ", OBJ
; "$ONACTSEL", IDENT "$ONACTSEL"
; "$ONGLOAD", IDENT "$ONGLOAD"
; "$ONGSAVE", IDENT "$ONGSAVE"
; "$ONNEWLOC", IDENT "$ONNEWLOC"
; "$ONOBJADD", IDENT "$ONOBJADD"
; "$ONOBJDEL", IDENT "$ONOBJDEL"
; "$ONOBJSEL", IDENT "$ONOBJSEL"
; "OPENGAME", KEYWORD "OPENGAME"
; "OPENQST", KEYWORD "OPENQST"
; "OR", OR
; "P", KEYWORD "P"
; "*P", KEYWORD "*P"
; "PL", KEYWORD "PL"
; "*PL", KEYWORD "*PL"
; "PLAY", KEYWORD "PLAY"
; "QSPVER", FUNCTION T.Qspver
; "$QSPVER", FUNCTION T.Qspver'
; "RAND", FUNCTION T.Rand
; "REFINT", KEYWORD "REFINT"
; "REPLACE", FUNCTION T.Replace
; "$REPLACE", FUNCTION T.Replace'
; "RGB", FUNCTION T.Rgb
; "RND", FUNCTION T.Rnd
; "SAVEGAME", KEYWORD "SAVEGAME"
; "SELACT", FUNCTION T.Selact
; "$SELACT", IDENT "SELACT"
; "SELOBJ", IDENT "SELOBJ"
; "$SELOBJ", IDENT "SELOBJ"
; "SET", SET
; "SETTIMER", KEYWORD "SETTIMER"
; "SHOWACTS", KEYWORD "SHOWACTS"
; "SHOWINPUT", KEYWORD "SHOWINPUT"
; "SHOWOBJS", KEYWORD "SHOWOBJS"
; "SHOWSTAT", KEYWORD "SHOWSTAT"
; "STATTXT", FUNCTION T.Stattxt
; "$STATTXT", FUNCTION T.Stattxt'
; "STR", FUNCTION T.Str
; "$STR", FUNCTION T.Str'
; "STRCOMP", FUNCTION T.Strcomp
; "STRFIND", FUNCTION T.Strfind
; "$STRFIND", FUNCTION T.Strfind'
; "STRPOS", FUNCTION T.Strpos
; "TRIM", FUNCTION T.Trim
; "$TRIM", FUNCTION T.Trim'
; "UCASE", FUNCTION T.Ucase
; "$UCASE", FUNCTION T.Ucase'
; "UNSEL", KEYWORD "UNSELECT"
; "UNSELECT", KEYWORD "UNSELECT"
; "USEHTML", IDENT "USEHTML"
; "USERCOM", IDENT "USERCOM"
; "$USERCOM", IDENT "USERCOM"
; "USER_TEXT", IDENT "USER_TEXT"
; "$USER_TEXT", IDENT "USER_TEXT"
; "USRTXT", IDENT "USER_TEXT"
; "$USRTXT", IDENT "USER_TEXT"
; "VAL", FUNCTION T.Val
; "VIEW", KEYWORD "VIEW"
; "WAIT", KEYWORD "WAIT"
; "XGOTO", KEYWORD "XGOTO"
; "XGT", KEYWORD "XGOTO"
]
let ident lexbuf id =
let id = String.uppercase_ascii id in
try
let value = Hashtbl.find keyword_table id in
let _ = match value with
| IF | ELIF -> incr_level lexbuf
| _ -> () in
value
with Not_found -> IDENT id
let wait_balance rule lexbuf =
try[@warning "-52"]
rule (Buffer.create 17) lexbuf
with
Failure "lexing: empty token" ->
let line = lexbuf.Lexing.lex_curr_p.pos_lnum
and content = Bytes.to_string lexbuf.Lexing.lex_buffer in
raise (UnclosedQuote {line; content})
[@warning "+52"]
}
let space = [ ' ' '\t' ]
let coma = ','
let letters = [^ '!' ':' '&' '=' '<' '>' '+' '-' '*' '/' ',' '"' '\'' '(' ')' '[' ']' ' ' '\t' '\n' '\r' '{' '}']
let digit = [ '0'-'9' ]
let eol = [ '\r' '\n' ]
let spaces = space+
let ident = (letters # digit) letters*
rule token = parse
| '#' spaces* (('!' | '$' | '#' | '^')+)? (ident as loc) {
Lexing.set_filename lexbuf loc;
LOCATION_START loc}
| (digit+) as l { INTEGER l}
| '+' { PLUS }
| '-' { MINUS }
| "+=" { INCR }
| "-=" { DECR }
| '/' { DIV }
| '*' { STAR }
| ':' {
(* We are leaving the block, the comment will be handled again *)
decr_level lexbuf;
COLUMN }
| '-' '-'+ [ ^ '\r' '\n']* { LOCATION_END }
| '[' { L_BRACKET }
| ']' { R_BRACKET }
| '(' {
incr_level lexbuf;
L_PAREN }
| ')' {
decr_level lexbuf;
R_PAREN }
| '<' { LT }
| '>' { GT }
| coma { COMA }
| eof {
Bucket.remove is_expression lexbuf;
EOF }
| '=' {
incr_level lexbuf;
EQUAL }
| ident as l { ident lexbuf l}
| eol {
Bucket.add is_expression lexbuf 0;
Lexing.new_line lexbuf; EOL }
| '&' {
Bucket.add is_expression lexbuf 0;
AMPERSAND }
| '!' {
match Bucket.find is_expression lexbuf with
| Some i when i <> 0 -> EXCLAMATION
| _ -> skip_comment lexbuf
}
| spaces { token lexbuf }
| '\'' { LITERAL (wait_balance read_quoted_string lexbuf) }
| '"' { LITERAL (wait_balance read_dquoted_string lexbuf) }
| '{' { LITERAL (wait_balance (read_long_string 0) lexbuf) }
and skip_comment = parse
| [^ '\'' '"' '{' '\r' '\n' ] { skip_comment lexbuf }
| '{' {
let _ = wait_balance (read_long_string 0) lexbuf in
skip_comment lexbuf }
| '\'' {
let _ = wait_balance read_quoted_string lexbuf in
skip_comment lexbuf
}
| '"' {
let _ = wait_balance read_dquoted_string lexbuf in
skip_comment lexbuf
}
| eol {
(* Ugly hack used in order to put the eol in the front of the next
parsing. *)
lexbuf.lex_curr_pos <- lexbuf.lex_curr_pos - 1;
(*Lexing.new_line lexbuf;*)
COMMENT
}
(* Read the content until we got another one quote *)
and read_quoted_string buf = parse
| "''"
{ Buffer.add_char buf '\'';
read_quoted_string buf lexbuf
}
| [^ '\'' '\n' '\r']+
{ Buffer.add_string buf (Lexing.lexeme lexbuf);
read_quoted_string buf lexbuf
}
| '\''
{ (Buffer.contents buf)
}
| ['\n' '\r']
{ Buffer.add_string buf (Lexing.lexeme lexbuf);
Lexing.new_line lexbuf ;
read_quoted_string buf lexbuf
}
and read_dquoted_string buf = parse
| [^ '"' ]+
{ Buffer.add_string buf (Lexing.lexeme lexbuf);
read_dquoted_string buf lexbuf
}
| "\"\""
{ Buffer.add_char buf '"';
read_dquoted_string buf lexbuf
}
| '"'
{ (Buffer.contents buf)
}
and read_long_string level buf = parse
| [^ '{' '}' '\r' '\n' ]+
{ Buffer.add_string buf (Lexing.lexeme lexbuf);
read_long_string level buf lexbuf
}
| '{'
{ Buffer.add_string buf (Lexing.lexeme lexbuf);
read_long_string (level + 1) buf lexbuf }
| '}'
{ match level with
| 0 -> (Buffer.contents buf)
| _ -> Buffer.add_string buf (Lexing.lexeme lexbuf);
read_long_string (level - 1) buf lexbuf
}
| eol
{
Lexing.new_line lexbuf;
Buffer.add_string buf (Lexing.lexeme lexbuf);
read_long_string level buf lexbuf
}
|
