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
|
//===- 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:
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() { ++Ptr; }
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; }
};
} // 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 lexIdentifier(Cursor C, MIToken &Token) {
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 lexPercent(Cursor C, MIToken &Token) {
auto Range = C;
C.advance(); // Skip '%'
while (isIdentifierChar(C.peek()))
C.advance();
Token = MIToken(MIToken::NamedRegister, Range.upto(C));
return C;
}
static Cursor lexIntegerLiteral(Cursor C, MIToken &Token) {
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 lexSymbol(Cursor C, MIToken::TokenKind Kind, MIToken &Token) {
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();
}
auto Char = C.peek();
if (isalpha(Char) || Char == '_')
return lexIdentifier(C, Token).remaining();
if (Char == '%')
return lexPercent(C, Token).remaining();
if (isdigit(Char) || (Char == '-' && isdigit(C.peek(1))))
return lexIntegerLiteral(C, Token).remaining();
MIToken::TokenKind Kind = symbolToken(Char);
if (Kind != MIToken::Error)
return lexSymbol(C, Kind, Token).remaining();
Token = MIToken(MIToken::Error, C.remaining());
ErrorCallback(C.location(),
Twine("unexpected character '") + Twine(Char) + "'");
return C.remaining();
}
|
