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
|
#include "stdafx.h"
#include "Tokenizer.h"
#include "Compiler/Exception.h"
#include "Core/StrBuf.h"
#include "Decl.h"
namespace storm {
namespace syntax {
Token::Token(Str *str, Nat len, const SrcPos &pos) : pos(pos), str(str), len(len) {}
bool Token::empty() const {
return len == 0;
}
const wchar *Token::start() const {
return str->c_str() + pos.start;
}
bool Token::operator ==(const wchar *t) const {
const wchar *s = start();
for (nat i = 0; i < len; i++) {
if (s[i] == 0)
return false;
if (s[i] != t[i])
return false;
}
return true;
}
bool Token::isStrLiteral() const {
const wchar *s = start();
if (*s != '"')
return false;
return s[len-1] == '"';
}
Str *Token::strLiteral() const {
if (!isStrLiteral())
return new (str) Str();
Str *r = new (str) Str(start() + 1, start() + len - 1);
// This is the same function as is used by the "real" grammar.
return unescapeStr(r);
}
Str *Token::toS() const {
const wchar *start = this->start();
const wchar *end = start + len;
return new (str) Str(start, end);
}
wostream &operator <<(wostream &to, const Token &t) {
return to << t.toS()->c_str();
}
static const wchar *operators = S("-?*=><.+");
static const wchar *specials = S("(){}[],;:@#");
static bool isOperator(wchar c) {
for (const wchar *p = operators; *p; p++)
if (c == *p)
return true;
return false;
}
static bool isSpecial(wchar c) {
for (const wchar *p = specials; *p; p++)
if (c == *p)
return true;
return false;
}
static bool isWhitespace(wchar c) {
switch (c) {
case ' ':
case '\n':
case '\r':
case '\t':
return true;
}
return false;
}
Tokenizer::Tokenizer(Url *path, Str *src, Nat start)
: src(src),
file(path),
pos(start),
commentStart(invalid),
lookahead(src, 0, SrcPos(path, 0, 0)) {
lookahead = findNext();
}
Token Tokenizer::next() {
Token t = peek();
skip();
return t;
}
Token Tokenizer::peek() const {
if (!more())
throw new (src) SyntaxError(position(), S("Unexpected end of file."));
return lookahead;
}
void Tokenizer::skip() {
lookahead = findNext();
}
bool Tokenizer::skipIf(const wchar *token) {
if (!more())
throw new (src) SyntaxError(position(), S("Unexpected end of file."));
if (lookahead == token) {
skip();
return true;
} else {
return false;
}
}
void Tokenizer::expect(const wchar *token) {
if (!more())
throw new (src) SyntaxError(position(), S("Unexpected end of file."));
if (lookahead != token)
throw new (src) SyntaxError(lookahead.pos,
TO_S(src, S("Expected ") << token << S(" but got ") << lookahead.toS()));
skip();
}
bool Tokenizer::more() const {
return !lookahead.empty();
}
SrcPos Tokenizer::position() const {
return lookahead.pos;
}
Nat Tokenizer::invalid = Nat(-1);
SrcPos Tokenizer::comment() const {
if (commentStart == invalid)
return SrcPos();
else
return SrcPos(file, commentStart, commentStart);
}
void Tokenizer::clearComment() {
commentStart = invalid;
}
Token Tokenizer::findNext() {
State state = sStart;
nat start = pos;
bool firstComment = true;
while (state != sDone)
processChar(start, state, firstComment);
return Token(src, pos - start, SrcPos(file, start, pos));
}
void Tokenizer::processChar(Nat &start, State &state, bool &firstComment) {
const wchar *str = src->c_str();
wchar ch = str[pos];
if (ch == 0) {
state = sDone;
return;
}
if (ch == '/' && str[pos+1] == '/') {
switch (state) {
case sStart:
state = sComment;
if (firstComment) {
commentStart = pos;
firstComment = false;
}
break;
case sString:
case sComment:
break;
default:
state = sDone;
return;
}
}
switch (state) {
case sStart:
pos++;
if (isWhitespace(ch)) {
start = pos;
// If there is a space inside the block, they are considered two blocks and we
// are only interested in the last one.
if (ch == '\n')
firstComment = true;
} else if (isSpecial(ch)) {
state = sDone;
} else if (isOperator(ch)) {
state = sOperator;
} else if (ch == '"') {
state = sString;
} else {
state = sText;
}
break;
case sText:
if (isOperator(ch) || isWhitespace(ch) || isSpecial(ch) || ch == '"') {
state = sDone;
} else {
pos++;
}
break;
case sOperator:
if (!isOperator(ch)) {
state = sDone;
} else {
pos++;
}
break;
case sString:
pos++;
if (ch == '"') {
state = sDone;
} else if (ch == '\\') {
pos++;
}
break;
case sComment:
start = ++pos;
if (ch == '\n')
state = sStart;
break;
case sDone:
if (pos > 0)
pos--;
break;
}
}
}
}
|
