aboutsummaryrefslogtreecommitdiffstats
path: root/ELF/ScriptLexer.cpp
blob: 953a3df8a31c6a0fec8840eee2e55c50f27c14f8 (plain) (blame)
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
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
//===- ScriptLexer.cpp ----------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines a lexer for the linker script.
//
// The linker script's grammar is not complex but ambiguous due to the
// lack of the formal specification of the language. What we are trying to
// do in this and other files in LLD is to make a "reasonable" linker
// script processor.
//
// Among simplicity, compatibility and efficiency, we put the most
// emphasis on simplicity when we wrote this lexer. Compatibility with the
// GNU linkers is important, but we did not try to clone every tiny corner
// case of their lexers, as even ld.bfd and ld.gold are subtly different
// in various corner cases. We do not care much about efficiency because
// the time spent in parsing linker scripts is usually negligible.
//
// Our grammar of the linker script is LL(2), meaning that it needs at
// most two-token lookahead to parse. The only place we need two-token
// lookahead is labels in version scripts, where we need to parse "local :"
// as if "local:".
//
// Overall, this lexer works fine for most linker scripts. There might
// be room for improving compatibility, but that's probably not at the
// top of our todo list.
//
//===----------------------------------------------------------------------===//

#include "ScriptLexer.h"
#include "lld/Common/ErrorHandler.h"
#include "llvm/ADT/Twine.h"

using namespace llvm;
using namespace lld;
using namespace lld::elf;

// Returns a whole line containing the current token.
StringRef ScriptLexer::getLine() {
  StringRef s = getCurrentMB().getBuffer();
  StringRef tok = tokens[pos - 1];

  size_t pos = s.rfind('\n', tok.data() - s.data());
  if (pos != StringRef::npos)
    s = s.substr(pos + 1);
  return s.substr(0, s.find_first_of("\r\n"));
}

// Returns 1-based line number of the current token.
size_t ScriptLexer::getLineNumber() {
  StringRef s = getCurrentMB().getBuffer();
  StringRef tok = tokens[pos - 1];
  return s.substr(0, tok.data() - s.data()).count('\n') + 1;
}

// Returns 0-based column number of the current token.
size_t ScriptLexer::getColumnNumber() {
  StringRef tok = tokens[pos - 1];
  return tok.data() - getLine().data();
}

std::string ScriptLexer::getCurrentLocation() {
  std::string filename = getCurrentMB().getBufferIdentifier();
  return (filename + ":" + Twine(getLineNumber())).str();
}

ScriptLexer::ScriptLexer(MemoryBufferRef mb) { tokenize(mb); }

// We don't want to record cascading errors. Keep only the first one.
void ScriptLexer::setError(const Twine &msg) {
  if (errorCount())
    return;

  std::string s = (getCurrentLocation() + ": " + msg).str();
  if (pos)
    s += "\n>>> " + getLine().str() + "\n>>> " +
         std::string(getColumnNumber(), ' ') + "^";
  error(s);
}

// Split S into linker script tokens.
void ScriptLexer::tokenize(MemoryBufferRef mb) {
  std::vector<StringRef> vec;
  mbs.push_back(mb);
  StringRef s = mb.getBuffer();
  StringRef begin = s;

  for (;;) {
    s = skipSpace(s);
    if (s.empty())
      break;

    // Quoted token. Note that double-quote characters are parts of a token
    // because, in a glob match context, only unquoted tokens are interpreted
    // as glob patterns. Double-quoted tokens are literal patterns in that
    // context.
    if (s.startswith("\"")) {
      size_t e = s.find("\"", 1);
      if (e == StringRef::npos) {
        StringRef filename = mb.getBufferIdentifier();
        size_t lineno = begin.substr(0, s.data() - begin.data()).count('\n');
        error(filename + ":" + Twine(lineno + 1) + ": unclosed quote");
        return;
      }

      vec.push_back(s.take_front(e + 1));
      s = s.substr(e + 1);
      continue;
    }

    // ">foo" is parsed to ">" and "foo", but ">>" is parsed to ">>".
    // "|", "||", "&" and "&&" are different operators.
    if (s.startswith("<<") || s.startswith("<=") || s.startswith(">>") ||
        s.startswith(">=") || s.startswith("||") || s.startswith("&&")) {
      vec.push_back(s.substr(0, 2));
      s = s.substr(2);
      continue;
    }

    // Unquoted token. This is more relaxed than tokens in C-like language,
    // so that you can write "file-name.cpp" as one bare token, for example.
    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;
    vec.push_back(s.substr(0, pos));
    s = s.substr(pos);
  }

  tokens.insert(tokens.begin() + pos, vec.begin(), vec.end());
}

// Skip leading whitespace characters or comments.
StringRef ScriptLexer::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 ScriptLexer::atEOF() { return errorCount() || tokens.size() == pos; }

// Split a given string as an expression.
// This function returns "3", "*" and "5" for "3*5" for example.
static std::vector<StringRef> tokenizeExpr(StringRef s) {
  StringRef ops = "+-*/:!~=<>"; // List of operators

  // Quoted strings are literal strings, so we don't want to split it.
  if (s.startswith("\""))
    return {s};

  // Split S with operators as separators.
  std::vector<StringRef> ret;
  while (!s.empty()) {
    size_t e = s.find_first_of(ops);

    // No need to split if there is no operator.
    if (e == StringRef::npos) {
      ret.push_back(s);
      break;
    }

    // Get a token before the opreator.
    if (e != 0)
      ret.push_back(s.substr(0, e));

    // Get the operator as a token.
    // Keep !=, ==, >=, <=, << and >> operators as a single tokens.
    if (s.substr(e).startswith("!=") || s.substr(e).startswith("==") ||
        s.substr(e).startswith(">=") || s.substr(e).startswith("<=") ||
        s.substr(e).startswith("<<") || s.substr(e).startswith(">>")) {
      ret.push_back(s.substr(e, 2));
      s = s.substr(e + 2);
    } else {
      ret.push_back(s.substr(e, 1));
      s = s.substr(e + 1);
    }
  }
  return ret;
}

// In contexts where expressions are expected, the lexer should apply
// different tokenization rules than the default one. By default,
// arithmetic operator characters are regular characters, but in the
// expression context, they should be independent tokens.
//
// For example, "foo*3" should be tokenized to "foo", "*" and "3" only
// in the expression context.
//
// This function may split the current token into multiple tokens.
void ScriptLexer::maybeSplitExpr() {
  if (!inExpr || errorCount() || atEOF())
    return;

  std::vector<StringRef> v = tokenizeExpr(tokens[pos]);
  if (v.size() == 1)
    return;
  tokens.erase(tokens.begin() + pos);
  tokens.insert(tokens.begin() + pos, v.begin(), v.end());
}

StringRef ScriptLexer::next() {
  maybeSplitExpr();

  if (errorCount())
    return "";
  if (atEOF()) {
    setError("unexpected EOF");
    return "";
  }
  return tokens[pos++];
}

StringRef ScriptLexer::peek() {
  StringRef tok = next();
  if (errorCount())
    return "";
  pos = pos - 1;
  return tok;
}

StringRef ScriptLexer::peek2() {
  skip();
  StringRef tok = next();
  if (errorCount())
    return "";
  pos = pos - 2;
  return tok;
}

bool ScriptLexer::consume(StringRef tok) {
  if (peek() == tok) {
    skip();
    return true;
  }
  return false;
}

// Consumes Tok followed by ":". Space is allowed between Tok and ":".
bool ScriptLexer::consumeLabel(StringRef tok) {
  if (consume((tok + ":").str()))
    return true;
  if (tokens.size() >= pos + 2 && tokens[pos] == tok &&
      tokens[pos + 1] == ":") {
    pos += 2;
    return true;
  }
  return false;
}

void ScriptLexer::skip() { (void)next(); }

void ScriptLexer::expect(StringRef expect) {
  if (errorCount())
    return;
  StringRef tok = next();
  if (tok != expect)
    setError(expect + " expected, but got " + tok);
}

// Returns true if S encloses T.
static bool encloses(StringRef s, StringRef t) {
  return s.bytes_begin() <= t.bytes_begin() && t.bytes_end() <= s.bytes_end();
}

MemoryBufferRef ScriptLexer::getCurrentMB() {
  // Find input buffer containing the current token.
  assert(!mbs.empty() && pos > 0);
  for (MemoryBufferRef mb : mbs)
    if (encloses(mb.getBuffer(), tokens[pos - 1]))
      return mb;
  llvm_unreachable("getCurrentMB: failed to find a token");
}