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
|
//===- MILexer.cpp - Machine instructions lexer implementation ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the lexing of machine instructions.
//
//===----------------------------------------------------------------------===//
#include "MILexer.h"
#include "llvm/ADT/Twine.h"
#include <cctype>
using namespace llvm;
namespace {
/// This class provides a way to iterate and get characters from the source
/// string.
class Cursor {
const char *Ptr;
const char *End;
public:
Cursor(NoneType) : Ptr(nullptr), End(nullptr) {}
explicit Cursor(StringRef Str) {
Ptr = Str.data();
End = Ptr + Str.size();
}
bool isEOF() const { return Ptr == End; }
char peek(int I = 0) const { return End - Ptr <= I ? 0 : Ptr[I]; }
void advance(unsigned I = 1) { Ptr += I; }
StringRef remaining() const { return StringRef(Ptr, End - Ptr); }
StringRef upto(Cursor C) const {
assert(C.Ptr >= Ptr && C.Ptr <= End);
return StringRef(Ptr, C.Ptr - Ptr);
}
StringRef::iterator location() const { return Ptr; }
operator bool() const { return Ptr != nullptr; }
};
} // end anonymous namespace
/// Skip the leading whitespace characters and return the updated cursor.
static Cursor skipWhitespace(Cursor C) {
while (isspace(C.peek()))
C.advance();
return C;
}
static bool isIdentifierChar(char C) {
return isalpha(C) || isdigit(C) || C == '_' || C == '-' || C == '.';
}
static Cursor maybeLexIdentifier(Cursor C, MIToken &Token) {
if (!isalpha(C.peek()) && C.peek() != '_')
return None;
auto Range = C;
while (isIdentifierChar(C.peek()))
C.advance();
auto Identifier = Range.upto(C);
Token = MIToken(Identifier == "_" ? MIToken::underscore : MIToken::Identifier,
Identifier);
return C;
}
static Cursor maybeLexMachineBasicBlock(
Cursor C, MIToken &Token,
function_ref<void(StringRef::iterator Loc, const Twine &)> ErrorCallback) {
if (!C.remaining().startswith("%bb."))
return None;
auto Range = C;
C.advance(4); // Skip '%bb.'
if (!isdigit(C.peek())) {
Token = MIToken(MIToken::Error, C.remaining());
ErrorCallback(C.location(), "expected a number after '%bb.'");
return C;
}
auto NumberRange = C;
while (isdigit(C.peek()))
C.advance();
StringRef Number = NumberRange.upto(C);
unsigned StringOffset = 4 + Number.size(); // Drop '%bb.<id>'
if (C.peek() == '.') {
C.advance(); // Skip '.'
++StringOffset;
while (isIdentifierChar(C.peek()))
C.advance();
}
Token = MIToken(MIToken::MachineBasicBlock, Range.upto(C), APSInt(Number),
StringOffset);
return C;
}
static Cursor maybeLexRegister(Cursor C, MIToken &Token) {
if (C.peek() != '%')
return None;
auto Range = C;
C.advance(); // Skip '%'
while (isIdentifierChar(C.peek()))
C.advance();
Token = MIToken(MIToken::NamedRegister, Range.upto(C),
/*StringOffset=*/1); // Drop the '%'
return C;
}
static Cursor maybeLexGlobalValue(Cursor C, MIToken &Token) {
if (C.peek() != '@')
return None;
auto Range = C;
C.advance(); // Skip the '@'
// TODO: add support for quoted names.
if (!isdigit(C.peek())) {
while (isIdentifierChar(C.peek()))
C.advance();
Token = MIToken(MIToken::NamedGlobalValue, Range.upto(C),
/*StringOffset=*/1); // Drop the '@'
return C;
}
auto NumberRange = C;
while (isdigit(C.peek()))
C.advance();
Token =
MIToken(MIToken::GlobalValue, Range.upto(C), APSInt(NumberRange.upto(C)));
return C;
}
static Cursor maybeLexIntegerLiteral(Cursor C, MIToken &Token) {
if (!isdigit(C.peek()) && (C.peek() != '-' || !isdigit(C.peek(1))))
return None;
auto Range = C;
C.advance();
while (isdigit(C.peek()))
C.advance();
StringRef StrVal = Range.upto(C);
Token = MIToken(MIToken::IntegerLiteral, StrVal, APSInt(StrVal));
return C;
}
static MIToken::TokenKind symbolToken(char C) {
switch (C) {
case ',':
return MIToken::comma;
case '=':
return MIToken::equal;
default:
return MIToken::Error;
}
}
static Cursor maybeLexSymbol(Cursor C, MIToken &Token) {
auto Kind = symbolToken(C.peek());
if (Kind == MIToken::Error)
return None;
auto Range = C;
C.advance();
Token = MIToken(Kind, Range.upto(C));
return C;
}
StringRef llvm::lexMIToken(
StringRef Source, MIToken &Token,
function_ref<void(StringRef::iterator Loc, const Twine &)> ErrorCallback) {
auto C = skipWhitespace(Cursor(Source));
if (C.isEOF()) {
Token = MIToken(MIToken::Eof, C.remaining());
return C.remaining();
}
if (Cursor R = maybeLexIdentifier(C, Token))
return R.remaining();
if (Cursor R = maybeLexMachineBasicBlock(C, Token, ErrorCallback))
return R.remaining();
if (Cursor R = maybeLexRegister(C, Token))
return R.remaining();
if (Cursor R = maybeLexGlobalValue(C, Token))
return R.remaining();
if (Cursor R = maybeLexIntegerLiteral(C, Token))
return R.remaining();
if (Cursor R = maybeLexSymbol(C, Token))
return R.remaining();
Token = MIToken(MIToken::Error, C.remaining());
ErrorCallback(C.location(),
Twine("unexpected character '") + Twine(C.peek()) + "'");
return C.remaining();
}
|
