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
|
#include "swift/AST/Module.h"
#include "swift/Basic/LangOptions.h"
#include "swift/Basic/SourceManager.h"
#include "swift/Parse/Lexer.h"
#include "swift/Parse/Parser.h"
#include "swift/Subsystems.h"
#include "llvm/Support/MemoryBuffer.h"
#include "gtest/gtest.h"
using namespace swift;
using namespace llvm;
// The test fixture.
class TokenizerTest : public ::testing::Test {
public:
LangOptions LangOpts;
SourceManager SM;
unsigned makeBuffer(StringRef Source) {
return SM.addMemBufferCopy(Source);
}
static void replaceNewLines(std::string &S) {
size_t Index = 0;
while (true) {
Index = S.find("\n", Index);
if (Index == std::string::npos) break;
S.erase(Index, 1);
S.insert(Index, "\\n");
Index += 3;
}
}
static std::string tokToString(swift::tok T) {
switch (T) {
#define KEYWORD(X) \
case swift::tok::kw_##X: return "kw_" #X; break;
#define PUNCTUATOR(X, Y) \
case swift::tok::X: return #X; break;
#define POUND(X, Y) \
case swift::tok::pound_##X: return "pound_" #X; break;
#include "swift/AST/TokenKinds.def"
#define OTHER(X) \
case swift::tok::X: return #X; break;
OTHER(unknown)
OTHER(eof)
OTHER(code_complete)
OTHER(identifier)
OTHER(oper_binary_unspaced)
OTHER(oper_binary_spaced)
OTHER(oper_postfix)
OTHER(oper_prefix)
OTHER(dollarident)
OTHER(integer_literal)
OTHER(floating_literal)
OTHER(string_literal)
OTHER(sil_local_name)
OTHER(comment)
default:
return "??? (" + std::to_string(static_cast<int>(tok())) + ")";
break;
}
}
void assertTokens(std::vector<Token> Ts, StringRef Expected) {
std::string Actual;
for (auto C = Ts.begin(), E = Ts.end(); C != E; ++C) {
Actual += tokToString(C->getKind());
Actual += ": ";
std::string Txt(C->getRawText());
replaceNewLines(Txt);
Actual += Txt;
Actual += "\n";
}
EXPECT_EQ(Expected, Actual)
<< "---- Expected: \n" << Expected << "\n"
<< "---- Actual: \n" << Actual << "\n";
}
std::vector<Token> parseAndGetSplitTokens(unsigned BufID) {
swift::ParserUnit PU(SM, SourceFileKind::Main, BufID, LangOpts,
TypeCheckerOptions(), SILOptions(), "unknown");
SmallVector<ASTNode, 8> items;
PU.getParser().parseTopLevelItems(items);
return PU.getParser().getSplitTokens();
}
std::vector<Token> tokenize(unsigned BufID, const std::vector<Token> &SplitTokens = {}) {
return swift::tokenize(LangOpts,
SM,
BufID,
/* Offset = */ 0,
/* EndOffset = */ 0,
/* Diags = */nullptr,
/* KeepComments = */ true,
/* TokenizeInterpolatedString = */ true,
SplitTokens);
}
};
TEST_F(TokenizerTest, ProperlySplitTokens) {
auto BufID = makeBuffer(
"infix operator ⊕ { associativity left precedence 100 }\n"
"func ⊕<T>(t1: T, t2: T) {}\n"
);
// Tokenize w/o fixing split tokens
auto Tokens = tokenize(BufID);
assertTokens(Tokens,
"identifier: infix\n"
"kw_operator: operator\n"
"oper_binary_spaced: ⊕\n"
"l_brace: {\n"
"identifier: associativity\n"
"identifier: left\n"
"identifier: precedence\n"
"integer_literal: 100\n"
"r_brace: }\n"
"kw_func: func\n"
"oper_prefix: ⊕<\n"
"identifier: T\n"
"oper_binary_unspaced: >\n"
"l_paren: (\n"
"identifier: t1\n"
"colon: :\n"
"identifier: T\n"
"comma: ,\n"
"identifier: t2\n"
"colon: :\n"
"identifier: T\n"
"r_paren: )\n"
"l_brace: {\n"
"r_brace: }\n"
);
// Parse the input and get split tokens info
auto SplitTokens = parseAndGetSplitTokens(BufID);
// Tokenize with fixing split tokens
Tokens = tokenize(BufID, SplitTokens);
assertTokens(Tokens,
"identifier: infix\n"
"kw_operator: operator\n"
"oper_binary_spaced: ⊕\n"
"l_brace: {\n"
"identifier: associativity\n"
"identifier: left\n"
"identifier: precedence\n"
"integer_literal: 100\n"
"r_brace: }\n"
"kw_func: func\n"
"oper_binary_spaced: ⊕\n"
"oper_binary_unspaced: <\n"
"identifier: T\n"
"oper_binary_unspaced: >\n"
"l_paren: (\n"
"identifier: t1\n"
"colon: :\n"
"identifier: T\n"
"comma: ,\n"
"identifier: t2\n"
"colon: :\n"
"identifier: T\n"
"r_paren: )\n"
"l_brace: {\n"
"r_brace: }\n"
);
}
|
