aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/tools/bison/src/gram.c
blob: 71e65eda3b810d7cbfd0aa8a595bcbbcdc436bed (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
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
/* Allocate input grammar variables for Bison.

   Copyright (C) 1984, 1986, 1989, 2001-2003, 2005-2015, 2018-2021 Free
   Software Foundation, Inc.

   This file is part of Bison, the GNU Compiler Compiler.

   This program is free software: you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation, either version 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <https://www.gnu.org/licenses/>.  */

#include <config.h>
#include "system.h"

#include "complain.h"
#include "getargs.h"
#include "glyphs.h"
#include "gram.h"
#include "print-xml.h"
#include "reader.h"
#include "reduce.h"
#include "symtab.h"

/* Comments for these variables are in gram.h.  */

item_number *ritem = NULL;
int nritems = 0;

rule *rules = NULL;
rule_number nrules = 0;

symbol **symbols = NULL;
int nsyms = 0;
int ntokens = 1;
int nnterms = 0;

symbol_number *token_translations = NULL;

int max_code = 256;

int required_version = 0;

void
item_print (item_number *item, rule const *previous_rule, FILE *out)
{
  rule const *r = item_rule (item);
  rule_lhs_print (r, previous_rule ? previous_rule->lhs : NULL, out);

  for (item_number *sp = r->rhs; sp < item; sp++)
    fprintf (out, " %s", symbols[*sp]->tag);
  fprintf (out, " %s", dot);
  if (0 <= *r->rhs)
    for (item_number *sp = item; 0 <= *sp; ++sp)
      fprintf (out, " %s", symbols[*sp]->tag);
  else
    fprintf (out, " %%empty");
}


bool
rule_useful_in_grammar_p (rule const *r)
{
  return r->number < nrules;
}

bool
rule_useless_in_grammar_p (rule const *r)
{
  return !rule_useful_in_grammar_p (r);
}

bool
rule_useless_in_parser_p (rule const *r)
{
  return !r->useful && rule_useful_in_grammar_p (r);
}

bool
rule_useless_chain_p (rule const *r)
{
  return rule_rhs_length (r) == 1 && !r->action;
}

void
rule_lhs_print (rule const *r, sym_content const *previous_lhs, FILE *out)
{
  fprintf (out, "  %3d ", r->number);
  if (previous_lhs != r->lhs)
    fprintf (out, "%s:", r->lhs->symbol->tag);
  else
    fprintf (out, "%*s|", (int) strlen (previous_lhs->symbol->tag), "");
}

void
rule_lhs_print_xml (rule const *r, FILE *out, int level)
{
  xml_printf (out, level, "<lhs>%s</lhs>", r->lhs->symbol->tag);
}

size_t
rule_rhs_length (rule const *r)
{
  size_t res = 0;
  for (item_number *rhsp = r->rhs; 0 <= *rhsp; ++rhsp)
    ++res;
  return res;
}

void
rule_rhs_print (rule const *r, FILE *out)
{
  if (0 <= *r->rhs)
    for (item_number *rhsp = r->rhs; 0 <= *rhsp; ++rhsp)
      fprintf (out, " %s", symbols[*rhsp]->tag);
  else
    fputs (" %empty", out);
}

static void
rule_rhs_print_xml (rule const *r, FILE *out, int level)
{
  if (*r->rhs >= 0)
    {
      xml_puts (out, level, "<rhs>");
      for (item_number *rhsp = r->rhs; 0 <= *rhsp; ++rhsp)
        xml_printf (out, level + 1, "<symbol>%s</symbol>",
                    xml_escape (symbols[*rhsp]->tag));
      xml_puts (out, level, "</rhs>");
    }
  else
    {
      xml_puts (out, level, "<rhs>");
      xml_puts (out, level + 1, "<empty/>");
      xml_puts (out, level, "</rhs>");
    }
}

void
rule_print (rule const *r, rule const *prev_rule, FILE *out)
{
  rule_lhs_print (r, prev_rule ? prev_rule->lhs : NULL, out);
  rule_rhs_print (r, out);
}

void
ritem_print (FILE *out)
{
  fputs ("RITEM\n", out);
  for (int i = 0; i < nritems; ++i)
    if (ritem[i] >= 0)
      fprintf (out, "  %s", symbols[ritem[i]]->tag);
    else
      fprintf (out, "  (rule %d)\n", item_number_as_rule_number (ritem[i]));
  fputs ("\n\n", out);
}

size_t
ritem_longest_rhs (void)
{
  int max = 0;
  for (rule_number r = 0; r < nrules; ++r)
    {
      size_t length = rule_rhs_length (&rules[r]);
      if (length > max)
        max = length;
    }

  return max;
}

void
grammar_rules_partial_print (FILE *out, const char *title,
                             rule_filter filter)
{
  bool first = true;
  rule *previous_rule = NULL;

  /* rule # : LHS -> RHS */
  for (rule_number r = 0; r < nrules + nuseless_productions; r++)
    {
      if (filter && !filter (&rules[r]))
        continue;
      if (first)
        fprintf (out, "%s\n\n", title);
      else if (previous_rule && previous_rule->lhs != rules[r].lhs)
        putc ('\n', out);
      first = false;
      rule_print (&rules[r], previous_rule, out);
      putc ('\n', out);
      previous_rule = &rules[r];
    }
  if (!first)
    fputs ("\n\n", out);
}

void
grammar_rules_print (FILE *out)
{
  grammar_rules_partial_print (out, _("Grammar"), rule_useful_in_grammar_p);
}

void
grammar_rules_print_xml (FILE *out, int level)
{
  bool first = true;

  for (rule_number r = 0; r < nrules + nuseless_productions; r++)
    {
      if (first)
        xml_puts (out, level + 1, "<rules>");
      first = false;
      {
        char const *usefulness
          = rule_useless_in_grammar_p (&rules[r]) ? "useless-in-grammar"
          : rule_useless_in_parser_p (&rules[r])  ? "useless-in-parser"
          :                                         "useful";
        xml_indent (out, level + 2);
        fprintf (out, "<rule number=\"%d\" usefulness=\"%s\"",
                 rules[r].number, usefulness);
        if (rules[r].precsym)
          fprintf (out, " percent_prec=\"%s\"",
                   xml_escape (rules[r].precsym->symbol->tag));
        fputs (">\n", out);
      }
      rule_lhs_print_xml (&rules[r], out, level + 3);
      rule_rhs_print_xml (&rules[r], out, level + 3);
      xml_puts (out, level + 2, "</rule>");
    }
  if (!first)
    xml_puts (out, level + 1, "</rules>");
  else
   xml_puts (out, level + 1, "<rules/>");
}

static void
section (FILE *out, const char *s)
{
  fprintf (out, "%s\n", s);
  for (int i = strlen (s); 0 < i; --i)
    putc ('-', out);
  putc ('\n', out);
  putc ('\n', out);
}

void
grammar_dump (FILE *out, const char *title)
{
  fprintf (out, "%s\n\n", title);
  fprintf (out,
           "ntokens = %d, nnterms = %d, nsyms = %d, nrules = %d, nritems = %d\n\n",
           ntokens, nnterms, nsyms, nrules, nritems);

  section (out, "Tokens");
  {
    fprintf (out, "Value  Sprec  Sassoc  Tag\n");

    for (symbol_number i = 0; i < ntokens; i++)
      fprintf (out, "%5d  %5d   %5d  %s\n",
               i,
               symbols[i]->content->prec, symbols[i]->content->assoc,
               symbols[i]->tag);
    fprintf (out, "\n\n");
  }

  section (out, "Nonterminals");
  {
    fprintf (out, "Value  Tag\n");

    for (symbol_number i = ntokens; i < nsyms; i++)
      fprintf (out, "%5d  %s\n",
               i, symbols[i]->tag);
    fprintf (out, "\n\n");
  }

  section (out, "Rules");
  {
    fprintf (out,
             "Num (Prec, Assoc, Useful, UselessChain) Lhs"
             " -> (Ritem Range) Rhs\n");
    for (rule_number i = 0; i < nrules + nuseless_productions; ++i)
      {
        rule const *rule_i = &rules[i];
        int const rhs_itemno = rule_i->rhs - ritem;
        int length = rule_rhs_length (rule_i);
        aver (item_number_as_rule_number (rule_i->rhs[length]) == i);
        fprintf (out, "%3d (%2d, %2d, %2s, %2s)   %2d -> (%2u-%2u)",
                 i,
                 rule_i->prec ? rule_i->prec->prec : 0,
                 rule_i->prec ? rule_i->prec->assoc : 0,
                 rule_i->useful ? "t" : "f",
                 rule_useless_chain_p (rule_i) ? "t" : "f",
                 rule_i->lhs->number,
                 rhs_itemno, rhs_itemno + length - 1);
        /* Dumped the RHS. */
        for (item_number *rhsp = rule_i->rhs; 0 <= *rhsp; ++rhsp)
          fprintf (out, " %3d", *rhsp);
        putc ('\n', out);
      }
  }
  fprintf (out, "\n\n");

  section (out, "Rules interpreted");
  for (rule_number r = 0; r < nrules + nuseless_productions; ++r)
    {
      fprintf (out, "%-5d  %s:", r, rules[r].lhs->symbol->tag);
      rule_rhs_print (&rules[r], out);
      putc ('\n', out);
    }
  fprintf (out, "\n\n");
}

void
grammar_rules_useless_report (const char *message)
{
  for (rule_number r = 0; r < nrules; ++r)
    /* Don't complain about rules whose LHS is useless, we already
       complained about it.  */
    if (!reduce_nonterminal_useless_in_grammar (rules[r].lhs)
        && !rules[r].useful)
      complain (&rules[r].location, Wother, "%s", message);
}

void
grammar_free (void)
{
  if (ritem)
    free (ritem - 1);
  free (rules);
  free (token_translations);
  /* Free the symbol table data structure.  */
  symbols_free ();
  free_merger_functions ();
}