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
|
//===- ScriptParser.cpp ---------------------------------------------------===//
//
// The LLVM Linker
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains the base parser class for linker script and dynamic
// list.
//
//===----------------------------------------------------------------------===//
#include "ScriptParser.h"
#include "Error.h"
#include "llvm/ADT/Twine.h"
using namespace llvm;
using namespace lld;
using namespace lld::elf;
// Returns the line that the character S[Pos] is in.
static StringRef getLine(StringRef S, size_t Pos) {
size_t Begin = S.rfind('\n', Pos);
size_t End = S.find('\n', Pos);
Begin = (Begin == StringRef::npos) ? 0 : Begin + 1;
if (End == StringRef::npos)
End = S.size();
// rtrim for DOS-style newlines.
return S.substr(Begin, End - Begin).rtrim();
}
void ScriptParserBase::printErrorPos() {
StringRef Tok = Tokens[Pos == 0 ? 0 : Pos - 1];
StringRef Line = getLine(Input, Tok.data() - Input.data());
size_t Col = Tok.data() - Line.data();
error(Line);
error(std::string(Col, ' ') + "^");
}
// We don't want to record cascading errors. Keep only the first one.
void ScriptParserBase::setError(const Twine &Msg) {
if (Error)
return;
if (Input.empty() || Tokens.empty()) {
error(Msg);
} else {
error("line " + Twine(getPos()) + ": " + Msg);
printErrorPos();
}
Error = true;
}
// Split S into linker script tokens.
std::vector<StringRef> ScriptParserBase::tokenize(StringRef S) {
std::vector<StringRef> Ret;
for (;;) {
S = skipSpace(S);
if (S.empty())
return Ret;
// Quoted token
if (S.startswith("\"")) {
size_t E = S.find("\"", 1);
if (E == StringRef::npos) {
error("unclosed quote");
return {};
}
Ret.push_back(S.substr(1, E - 1));
S = S.substr(E + 1);
continue;
}
// Unquoted token
size_t Pos = S.find_first_not_of(
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
"0123456789_.$/\\~=+[]*?-:!<>");
// A character that cannot start a word (which is usually a
// punctuation) forms a single character token.
if (Pos == 0)
Pos = 1;
Ret.push_back(S.substr(0, Pos));
S = S.substr(Pos);
}
}
// Skip leading whitespace characters or comments.
StringRef ScriptParserBase::skipSpace(StringRef S) {
for (;;) {
if (S.startswith("/*")) {
size_t E = S.find("*/", 2);
if (E == StringRef::npos) {
error("unclosed comment in a linker script");
return "";
}
S = S.substr(E + 2);
continue;
}
if (S.startswith("#")) {
size_t E = S.find('\n', 1);
if (E == StringRef::npos)
E = S.size() - 1;
S = S.substr(E + 1);
continue;
}
size_t Size = S.size();
S = S.ltrim();
if (S.size() == Size)
return S;
}
}
// An erroneous token is handled as if it were the last token before EOF.
bool ScriptParserBase::atEOF() { return Error || Tokens.size() == Pos; }
StringRef ScriptParserBase::next() {
if (Error)
return "";
if (atEOF()) {
setError("unexpected EOF");
return "";
}
return Tokens[Pos++];
}
StringRef ScriptParserBase::peek() {
StringRef Tok = next();
if (Error)
return "";
--Pos;
return Tok;
}
bool ScriptParserBase::skip(StringRef Tok) {
if (Error)
return false;
if (atEOF()) {
setError("unexpected EOF");
return false;
}
if (Tokens[Pos] != Tok)
return false;
++Pos;
return true;
}
void ScriptParserBase::expect(StringRef Expect) {
if (Error)
return;
StringRef Tok = next();
if (Tok != Expect)
setError(Expect + " expected, but got " + Tok);
}
// Returns the current line number.
size_t ScriptParserBase::getPos() {
if (Pos == 0)
return 1;
const char *Begin = Input.data();
const char *Tok = Tokens[Pos - 1].data();
return StringRef(Begin, Tok - Begin).count('\n') + 1;
}
|
