aboutsummaryrefslogtreecommitdiff
path: root/build2/test/script/lexer.cxx
blob: ed0bd15937a4ef5cce40b5d61308c4a21d906df2 (plain)
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
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
// file      : build2/test/script/lexer.cxx -*- C++ -*-
// copyright : Copyright (c) 2014-2018 Code Synthesis Ltd
// license   : MIT; see accompanying LICENSE file

#include <build2/test/script/lexer.hxx>

#include <cstring> // strchr()

using namespace std;

namespace build2
{
  namespace test
  {
    namespace script
    {
      using type = token_type;

      void lexer::
      mode (base_mode m, char ps, optional<const char*> esc)
      {
        const char* s1 (nullptr);
        const char* s2 (nullptr);
        bool s (true);
        bool n (true);
        bool q (true);

        if (!esc)
        {
          assert (!state_.empty ());
          esc = state_.top ().escapes;
        }

        switch (m)
        {
        case lexer_mode::command_line:
          {
            s1 = ":;=!|&<> $(#\t\n";
            s2 = "  ==          ";
            break;
          }
        case lexer_mode::first_token:
          {
            // First token on the script line. Like command_line but
            // recognizes leading '.+-{}' as tokens as well as variable
            // assignments as separators.
            //
            // Note that to recognize only leading '.+-{}' we shouldn't add
            // them to the separator strings.
            //
            s1 = ":;=+!|&<> $(#\t\n";
            s2 = "   ==          ";
            break;
          }
        case lexer_mode::second_token:
          {
            // Second token on the script line. Like command_line but
            // recognizes leading variable assignments.
            //
            // Note that to recognize only leading assignments we shouldn't
            // add them to the separator strings (so this is identical to
            // command_line).
            //
            s1 = ":;=!|&<> $(#\t\n";
            s2 = "  ==          ";
            break;
          }
        case lexer_mode::variable_line:
          {
            // Like value except we recognize ';' and don't recognize '{'.
            // Note that we don't recognize ':' since having a trailing
            // variable assignment is illegal.
            //
            s1 = "; $([]#\t\n";
            s2 = "         ";
            break;
          }

        case lexer_mode::command_expansion:
          {
            // Note that whitespaces are not word separators in this mode.
            //
            s1 = "|&<>";
            s2 = "    ";
            s = false;
            break;
          }
        case lexer_mode::here_line_single:
          {
            // This one is like a single-quoted string except it treats
            // newlines as a separator. We also treat quotes as literals.
            //
            // Note that it might be tempting to enable line continuation
            // escapes. However, we will then have to also enable escaping of
            // the backslash, which makes it a lot less tempting.
            //
            s1 = "\n";
            s2 = " ";
            esc = ""; // Disable escape sequences.
            s = false;
            q = false;
            break;
          }
        case lexer_mode::here_line_double:
          {
            // This one is like a double-quoted string except it treats
            // newlines as a separator. We also treat quotes as literals.
            //
            s1 = "$(\n";
            s2 = "   ";
            s = false;
            q = false;
            break;
          }
        case lexer_mode::description_line:
          {
            // This one is like a single-quoted string and has an ad hoc
            // implementation.
            //
            break;
          }
        default:
          {
            // Make sure pair separators are only enabled where we expect
            // them.
            //
            // @@ Should we disable pair separators in the eval mode?
            //
            assert (ps == '\0' ||
                    m == lexer_mode::eval ||
                    m == lexer_mode::attribute);

            base_lexer::mode (m, ps, esc);
            return;
          }
        }

        assert (ps == '\0');
        state_.push (state {m, ps, s, n, q, *esc, s1, s2});
      }

      token lexer::
      next ()
      {
        token r;

        switch (state_.top ().mode)
        {
        case lexer_mode::command_line:
        case lexer_mode::first_token:
        case lexer_mode::second_token:
        case lexer_mode::variable_line:
        case lexer_mode::command_expansion:
        case lexer_mode::here_line_single:
        case lexer_mode::here_line_double:
          r = next_line ();
          break;
        case lexer_mode::description_line:
          r = next_description ();
          break;
        default:
          r = base_lexer::next ();
          break;
        }

        if (r.qtype != quote_type::unquoted)
          ++quoted_;

        return r;
      }

      token lexer::
      next_line ()
      {
        bool sep (skip_spaces ());

        xchar c (get ());
        uint64_t ln (c.line), cn (c.column);

        if (eos (c))
          return token (type::eos, sep, ln, cn, token_printer);

        state st (state_.top ()); // Make copy (see first/second_token).
        lexer_mode m (st.mode);

        auto make_token = [&sep, &m, ln, cn] (type t, string v = string ())
        {
          bool q (m == lexer_mode::here_line_double);

          return token (t, move (v), sep,
                        (q ? quote_type::double_ : quote_type::unquoted), q,
                        ln, cn,
                        token_printer);
        };

        auto make_token_with_modifiers =
          [&make_token, this] (type t,
                               const char* mods,           // To recorgnize.
                               const char* stop = nullptr) // To stop after.
        {
          string v;
          if (mods != nullptr)
          {
            for (xchar p (peek ());
                 (strchr (mods, p) != nullptr &&      // Modifier.
                  strchr (v.c_str (), p) == nullptr); // Not already seen.
                 p = peek ())
            {
              get ();
              v += p;

              if (stop != nullptr && strchr (stop, p) != nullptr)
                break;
            }
          }

          return make_token (t, move (v));
        };

        // Expire certain modes at the end of the token. Do it early in case
        // we push any new mode (e.g., double quote).
        //
        if (m == lexer_mode::first_token || m == lexer_mode::second_token)
          state_.pop ();

        // NOTE: remember to update mode() if adding new special characters.

        if (m != lexer_mode::command_expansion)
        {
          switch (c)
          {
          case '\n':
            {
              // Expire variable value mode at the end of the line.
              //
              if (m == lexer_mode::variable_line)
                state_.pop ();

              sep = true; // Treat newline as always separated.
              return make_token (type::newline);
            }
          }
        }

        if (m != lexer_mode::here_line_single)
        {
          switch (c)
          {
            // Variable expansion, function call, and evaluation context.
            //
          case '$': return make_token (type::dollar);
          case '(': return make_token (type::lparen);
          }
        }


        if (m == lexer_mode::variable_line)
        {
          switch (c)
          {
            // Attributes.
            //
          case '[': return make_token (type::lsbrace);
          case ']': return make_token (type::rsbrace);
          }
        }

        // Line separators.
        //
        if (m == lexer_mode::command_line ||
            m == lexer_mode::first_token  ||
            m == lexer_mode::second_token ||
            m == lexer_mode::variable_line)
        {
          switch (c)
          {
          case ';': return make_token (type::semi);
          }
        }

        if (m == lexer_mode::command_line ||
            m == lexer_mode::first_token  ||
            m == lexer_mode::second_token)
        {
          switch (c)
          {
          case ':': return make_token (type::colon);
          }
        }

        // Command line operator/separators.
        //
        if (m == lexer_mode::command_line ||
            m == lexer_mode::first_token  ||
            m == lexer_mode::second_token)
        {
          switch (c)
          {
            // Comparison (==, !=).
            //
          case '=':
          case '!':
            {
              if (peek () == '=')
              {
                get ();
                return make_token (c == '=' ? type::equal : type::not_equal);
              }
            }
          }
        }

        // Command operators/separators.
        //
        if (m == lexer_mode::command_line ||
            m == lexer_mode::first_token  ||
            m == lexer_mode::second_token ||
            m == lexer_mode::command_expansion)
        {
          switch (c)
          {
            // |, ||
            //
          case '|':
            {
              if (peek () == '|')
              {
                get ();
                return make_token (type::log_or);
              }
              else
                return make_token (type::pipe);
            }
            // &, &&
            //
          case '&':
            {
              xchar p (peek ());

              if (p == '&')
              {
                get ();
                return make_token (type::log_and);
              }

              // These modifiers are mutually exclusive so stop after seeing
              // either one.
              //
              return make_token_with_modifiers (type::clean, "!?", "!?");
            }
            // <
            //
          case '<':
            {
              type r (type::in_str);
              xchar p (peek ());

              if (p == '|' || p == '-' || p == '<')
              {
                get ();

                switch (p)
                {
                case '|': return make_token (type::in_pass);
                case '-': return make_token (type::in_null);
                case '<':
                  {
                    r = type::in_doc;
                    p = peek ();

                    if (p == '<')
                    {
                      get ();
                      r = type::in_file;
                    }
                    break;
                  }
                }
              }

              // Handle modifiers.
              //
              const char* mods (nullptr);
              switch (r)
              {
              case type::in_str:
              case type::in_doc: mods = ":/"; break;
              }

              return make_token_with_modifiers (r, mods);
            }
            // >
            //
          case '>':
            {
              type r (type::out_str);
              xchar p (peek ());

              if (p == '|' || p == '-' || p == '!' || p == '&' ||
                  p == '=' || p == '+' || p == '>')
              {
                get ();

                switch (p)
                {
                case '|': return make_token (type::out_pass);
                case '-': return make_token (type::out_null);
                case '!': return make_token (type::out_trace);
                case '&': return make_token (type::out_merge);
                case '=': return make_token (type::out_file_ovr);
                case '+': return make_token (type::out_file_app);
                case '>':
                  {
                    r = type::out_doc;
                    p = peek ();

                    if (p == '>')
                    {
                      get ();
                      r = type::out_file_cmp;
                    }
                    break;
                  }
                }
              }

              // Handle modifiers.
              //
              const char* mods (nullptr);
              const char* stop (nullptr);
              switch (r)
              {
              case type::out_str:
              case type::out_doc:  mods = ":/~"; stop = "~"; break;
              }

              return make_token_with_modifiers (r, mods, stop);
            }
          }
        }

        // Dot, plus/minus, and left/right curly braces.
        //
        if (m == lexer_mode::first_token)
        {
          switch (c)
          {
          case '.': return make_token (type::dot);
          case '+': return make_token (type::plus);
          case '-': return make_token (type::minus);
          case '{': return make_token (type::lcbrace);
          case '}': return make_token (type::rcbrace);
          }
        }

        // Variable assignment (=, +=, =+).
        //
        if (m == lexer_mode::second_token)
        {
          switch (c)
          {
          case '=':
            {
              if (peek () == '+')
              {
                get ();
                return make_token (type::prepend);
              }
              else
                return make_token (type::assign);
            }
          case '+':
            {
              if (peek () == '=')
              {
                get ();
                return make_token (type::append);
              }
            }
          }
        }

        // Otherwise it is a word.
        //
        unget (c);
        return word (st, sep);
      }

      token lexer::
      next_description ()
      {
        xchar c (peek ());

        if (eos (c))
          fail (c) << "expected newline at the end of description line";

        uint64_t ln (c.line), cn (c.column);

        if (c == '\n')
        {
          get ();
          state_.pop (); // Expire the description mode.
          return token (type::newline, true, ln, cn, token_printer);
        }

        string lexeme;

        // For now no line continutions though we could support them.
        //
        for (; !eos (c) && c != '\n'; c = peek ())
        {
          get ();
          lexeme += c;
        }

        return token (move (lexeme),
                      false,
                      quote_type::unquoted, false,
                      ln, cn);
      }

      token lexer::
      word (state st, bool sep)
      {
        lexer_mode m (st.mode);

        // Customized implementation that handles special variable names ($*,
        // $N, $~, $@).
        //
        if (m != lexer_mode::variable)
          return base_lexer::word (st, sep);

        xchar c (peek ());

        if (c != '*' && c != '~' && c != '@' && !digit (c))
          return base_lexer::word (st, sep);

        get ();

        if (digit (c) && digit (peek ()))
          fail (c) << "multi-digit special variable name";

        state_.pop (); // Expire the variable mode.
        return token (string (1, c),
                      sep,
                      quote_type::unquoted, false,
                      c.line, c.column);
      }
    }
  }
}