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 | with Ada.Characters.Handling;
with Ada.Strings.Equal_Case_Insensitive;
package body Jintp.Scanner is
use Jintp.Input;
use Ada.Characters.Handling;
procedure To_Token (Source : Unbounded_String; Result : out Token) is
subtype Symbolic_Token_Kind is Token_Kind range In_Token .. Not_Token;
begin
if Ada.Strings.Equal_Case_Insensitive (To_String (Source), "false") then
Result := (Kind => Boolean_Literal_Token,
Boolean_Value => False);
return;
elsif Ada.Strings.Equal_Case_Insensitive (To_String (Source), "true") then
Result := (Kind => Boolean_Literal_Token,
Boolean_Value => True);
return;
end if;
declare
Tok_Kind : constant Symbolic_Token_Kind := Symbolic_Token_Kind'Value
(To_Upper (To_String (Source)) & "_TOKEN");
New_Token : Token (Kind => Tok_Kind);
begin
Result := New_Token;
end;
exception
when Constraint_Error =>
Result := (Kind => Identifier_Token,
Identifier => Source
);
end To_Token;
function Is_Whitespace (C : Character) return Boolean is
begin
case C is
when ' ' | ASCII.LF | ASCII.HT | ASCII.VT | ASCII.FF | ASCII.CR =>
return True;
when others =>
return False;
end case;
end Is_Whitespace;
procedure Next_Token (
State : in out Scanner_State;
Input : in out Character_Iterator'Class;
Result : out Token;
Settings : Environment'Class) is
C : Character := Next (Input);
Buffer : Unbounded_String;
Matches : Boolean;
E_Found : Boolean := False;
begin
while Is_Whitespace (C) loop
C := Next (Input);
end loop;
if C = Element (Settings.Expression_End, 1) then
Match (Input, Slice (Settings.Expression_End,
2, Length (Settings.Expression_End)),
Matches);
if Matches then
Result := (Kind => Expression_End_Token);
State.Current_Token := Result;
return;
end if;
end if;
if C = Element (Settings.Statement_End, 1) then
Match (Input, Slice (Settings.Statement_End,
2, Length (Settings.Statement_End)),
Matches);
if Matches then
Result := (Kind => Statement_End_Token,
Modifier => ' '
);
State.Current_Token := Result;
return;
end if;
end if;
if Is_Letter (C) or else C = '_' then
Buffer := To_Unbounded_String ((1 => C));
C := Next (Input);
while Is_Alphanumeric (C) or else C = '_' loop
Append (Buffer, C);
C := Next (Input);
end loop;
Back (Input);
To_Token (Buffer, Result);
State.Current_Token := Result;
return;
end if;
if Is_Digit (C) then
loop
Append (Buffer, C);
C := Next (Input);
if C = '.' then
loop
Append (Buffer, C);
C := Next (Input);
if not Is_Digit (C) then
if C = 'e' or else C = 'E' then
if E_Found then
exit;
end if;
Append (Buffer, C);
C := Next (Input);
if not Is_Digit (C) and then C /= '+' and then C /= '-'
then
exit;
end if;
E_Found := True;
else
exit;
end if;
end if;
end loop;
Back (Input);
Result := (Kind => Float_Literal_Token,
Float_Value => Long_Float'Value (To_String (Buffer)));
State.Current_Token := Result;
return;
end if;
if not Is_Digit (C) then
exit;
end if;
end loop;
Back (Input);
Result := (Kind => Integer_Literal_Token,
Integer_Value => Integer'Value (To_String (Buffer)));
State.Current_Token := Result;
return;
end if;
case C is
when '=' =>
C := Next (Input);
if C = '=' then
Result := (Kind => Eq_Token);
State.Current_Token := Result;
return;
else
Back (Input);
Result := (Kind => Assign_Token);
State.Current_Token := Result;
return;
end if;
when '!' =>
C := Next (Input);
if C = '=' then
Result := (Kind => Ineq_Token);
State.Current_Token := Result;
return;
else
raise Template_Error with "'=' expected after '!'";
end if;
when '<' =>
C := Next (Input);
if C = '=' then
Result := (Kind => Le_Token);
State.Current_Token := Result;
return;
end if;
Back (Input);
Result := (Kind => Lt_Token);
State.Current_Token := Result;
return;
when '>' =>
C := Next (Input);
if C = '=' then
Result := (Kind => Ge_Token);
State.Current_Token := Result;
return;
end if;
Back (Input);
Result := (Kind => Gt_Token);
State.Current_Token := Result;
return;
when ',' =>
Result := (Kind => Comma_Token);
State.Current_Token := Result;
return;
when '.' =>
Result := (Kind => Period_Token);
State.Current_Token := Result;
return;
when ':' =>
Result := (Kind => Colon_Token);
State.Current_Token := Result;
return;
when '(' =>
Result := (Kind => Left_Paren_Token);
State.Current_Token := Result;
return;
when ')' =>
Result := (Kind => Right_Paren_Token);
State.Current_Token := Result;
return;
when '[' =>
Result := (Kind => Left_Bracket_Token);
State.Current_Token := Result;
return;
when ']' =>
Result := (Kind => Right_Bracket_Token);
State.Current_Token := Result;
return;
when '{' =>
Result := (Kind => Left_Brace_Token);
State.Current_Token := Result;
return;
when '}' =>
Result := (Kind => Right_Brace_Token);
State.Current_Token := Result;
return;
when '+' =>
Match (Input, To_String (Settings.Statement_End), Matches);
if Matches then
Result := (Kind => Statement_End_Token,
Modifier => '+'
);
State.Current_Token := Result;
return;
end if;
Result := (Kind => Plus_Token);
State.Current_Token := Result;
return;
when '-' =>
Match (Input, To_String (Settings.Statement_End), Matches);
if Matches then
Result := (Kind => Statement_End_Token,
Modifier => '-'
);
State.Current_Token := Result;
return;
end if;
Result := (Kind => Minus_Token);
State.Current_Token := Result;
return;
when '*' =>
C := Next (Input);
if C = '*' then
Result := (Kind => Power_Token);
State.Current_Token := Result;
return;
end if;
Back (Input);
Result := (Kind => Mul_Token);
State.Current_Token := Result;
return;
when '/' =>
C := Next (Input);
if C = '/' then
Result := (Kind => Integer_Div_Token);
State.Current_Token := Result;
return;
end if;
Back (Input);
Result := (Kind => Div_Token);
State.Current_Token := Result;
return;
when '%' =>
Result := (Kind => Remainder_Token);
State.Current_Token := Result;
return;
when '~' =>
Result := (Kind => Tilde_Token);
State.Current_Token := Result;
return;
when '|' =>
Result := (Kind => Pipe_Token);
State.Current_Token := Result;
return;
when ''' | '"' =>
declare
Str_Buf : Unbounded_String;
Delimiter : constant Character := C;
begin
C := Next (Input);
while C /= Delimiter loop
if C = '\' then
C := Next (Input);
case C is
when ASCII.CR =>
C := Next (Input);
if C = ASCII.LF then
C := Next (Input);
end if;
when ASCII.LF =>
C := Next (Input);
when '\' =>
C := '\';
when ''' =>
C := ''';
when '"' =>
C := '\';
when 'a' =>
C := ASCII.BEL;
when 'b' =>
C := ASCII.BS;
when 'f' =>
C := ASCII.FF;
when 'n' =>
C := ASCII.LF;
when 'r' =>
C := ASCII.CR;
when 't' =>
C := ASCII.HT;
when 'v' =>
C := ASCII.VT;
when others =>
Append (Str_Buf, '\');
end case;
end if;
Append (Str_Buf, C);
C := Next (Input);
end loop;
Result := (Kind => String_Literal_Token,
String_Value => Str_Buf);
State.Current_Token := Result;
return;
end;
when others =>
null;
end case;
raise Template_Error with "unexpected char '" & C & ''';
exception
when Constraint_Error =>
raise Template_Error with "unexpected end of input";
end Next_Token;
function Current_Token (State : Scanner_State) return Token is
begin
return State.Current_Token;
end Current_Token;
end Jintp.Scanner;
|