aboutsummaryrefslogtreecommitdiff
path: root/src/utils/sexpr.H
blob: 5139b453dbb66a22edc0c48e1e933b6b06b7e237 (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
// Copyright (C) 2010, Gabriel Dos Reis.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     - Redistributions of source code must retain the above copyright
//       notice, this list of conditions and the following disclaimer.
//
//     - Redistributions in binary form must reproduce the above copyright
//       notice, this list of conditions and the following disclaimer in
//       the documentation and/or other materials provided with the
//       distribution.
//
//     - Neither the name of The Numerical Algorithms Group Ltd. nor the
//       names of its contributors may be used to endorse or promote products
//       derived from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
// IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
// TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
// PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
// OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#ifndef OPENAXIOM_SEXPR_INCLUDED
#define OPENAXIOM_SEXPR_INCLUDED

// --% Author: Gabriel Dos Reis.
// --% Description:
// --%   A simple support for s-expressions.  By design, no ambition
// --%   for full-fledged Common Lisp reader capability.  Rather,
// --%   the aim is a simple data structure for exchanging data
// --%   between several components of the OpenAxiom system.
// --%   Users interested in fullblown Lisp syntax should seek
// --%   to acquire Lisp systems, many of which are freely available.

#include <iosfwd>
#include <vector>
#include <set>
#include "string-pool.H"

// Helpers for defining token type values for lexeme with more
// than characters.
#define OPENAXIOM_SEXPR_TOKEN1(C)  (C)
#define OPENAXIOM_SEXPR_TOKEN2(C1,C2) (C1 * 256 + C2)

namespace OpenAxiom {
   namespace Sexpr {
      // -----------
      // -- Token --
      // -----------
      struct Token {
         enum Type {
            unknown,                 // unidentified token
            dot              = OPENAXIOM_SEXPR_TOKEN1('.'),      // "."
            comma            = OPENAXIOM_SEXPR_TOKEN1(','),      // ","
            open_paren       = OPENAXIOM_SEXPR_TOKEN1('('),      // "("
            close_paren      = OPENAXIOM_SEXPR_TOKEN1(')'),      // ")"
            apostrophe       = OPENAXIOM_SEXPR_TOKEN1('\''),     // "'"
            backquote        = OPENAXIOM_SEXPR_TOKEN1('`'),      // "`"
            backslash        = OPENAXIOM_SEXPR_TOKEN1('\\'),     // "\\"
            sharp_open_paren = OPENAXIOM_SEXPR_TOKEN2('#','('),  // "#("
            sharp_apostrophe = OPENAXIOM_SEXPR_TOKEN2('#','\''), // "#'"
            sharp_colon      = OPENAXIOM_SEXPR_TOKEN2('#',':'),  // "#:"
            digraph_end      = OPENAXIOM_SEXPR_TOKEN2(256,256),
            integer,                // integer literal
            string,                 // string literal
            identifier,             // plain identifier
            sharp_integer_equal,    // anchor definition, #n=<form>
            sharp_integer_sharp     // back reference, #n#
         };

         Type type;             // class of this token
         BasicString lexeme;    // characters making up this token
      };

      // Print a token object on an output stream.
      // Note: this function is for debugging purpose; in particular
      // it does not `prettyprint' tokens.
      std::ostream& operator<<(std::ostream&, const Token&);

      // -----------
      // -- Lexer --
      // -----------
      // An object of this type transforms a sequence of characters
      // into a sequence of tokens as defined above.
      // A lexer does not manage memory itself.  Rather, it delegates
      // storage allocation for lexemes and tokens to specialized
      // agents used to construct it.
      struct Lexer {
         Lexer(StringPool& pool, std::vector<Token>& toks)
               : strings(pool), tokens(toks) { }

         const char* tokenize(const char*, const char*);

      private:
         StringPool& strings;        // where to allocate lexemes from
         std::vector<Token>& tokens; // where to deposite tokens.
      };

      // ------------
      // -- Syntax --
      // ------------
      struct Syntax {
         struct Visitor;        // base class of syntax visitors
         virtual void accept(Visitor&) const = 0;
      };

      // ----------
      // -- Atom --
      // ----------
      // An atom is a syntax object consisting of exatly one token.
      // This should not be confused with the notion of atom
      // in Lisp languages. 
      struct Atom : Syntax {
         const Token& token() const { return tok; }
         BasicString lexeme() const { return tok.lexeme; }
         void accept(Visitor&) const;
      protected:
         const Token tok;
         Atom(const Token&);
      };

      // -------------
      // -- Integer --
      // -------------
      struct Integer : Atom {
         explicit Integer(const Token&);
         void accept(Visitor&) const;
      };

      // ------------
      // -- String --
      // ------------
      struct String : Atom {
         explicit String(const Token&);
         void accept(Visitor&) const;
      };

      // ------------
      // -- Symbol --
      // ------------
      struct Symbol : Atom {
         enum Kind {
            uninterned,         // uninterned symbol
            ordinary,           // an interned symbol
            keyword             // a keyword symbol
         };
         Symbol(const Token&, Kind);
         Kind kin() const { return sort; }
         void accept(Visitor&) const;
      private:
         const Kind sort;
      };

      // ---------------
      // -- Reference --
      // ---------------
      struct Reference : Atom {
         Reference(const Token&, size_t);
         size_t tag() const { return pos; }
         void accept(Visitor&) const;
      private:
         const size_t pos;
      };

      // ------------
      // -- Anchor --
      // ------------
      struct Anchor : Syntax {
         Anchor(size_t, const Syntax*);
         size_t ref() const { return tag; }
         const Syntax* value() const { return val; }
         void accept(Visitor&) const;
      private:
         const size_t tag;
         const Syntax* const val;
      };

      // -----------
      // -- Quote --
      // -----------
      struct Quote : Syntax {
         explicit Quote(const Syntax*);
         const Syntax* body() const { return form; }
         void accept(Visitor&) const;
      private:
         const Syntax* const form;
      };
      
      // --------------
      // -- Function --
      // --------------
      struct Function : Syntax {
         explicit Function(const Syntax*);
         const Syntax* code() const { return form; }
         void accept(Visitor&) const;
      private:
         const Syntax* const form;
      };

      // ----------
      // -- Pair --
      // ----------
      struct Pair : Syntax {
         Pair(const Syntax*, const Syntax*);
         const Syntax* first() const { return elts.first; }
         const Syntax* second() const { return elts.second; }
         void accept(Visitor&) const;
      private:
         const std::pair<const Syntax*, const Syntax*> elts;
      };

      // ----------
      // -- List --
      // ----------
      struct List : Syntax, private std::vector<const Syntax*> {
         typedef std::vector<const Syntax*> base;
         using base::const_iterator;
         using base::begin;
         using base::end;
         using base::size;
         using base::empty;

         List();
         explicit List(const base&);
         ~List();
         void accept(Visitor&) const;
      };
      
      // ------------
      // -- Vector --
      // ------------
      struct Vector : Syntax, private std::vector<const Syntax*> {
         typedef std::vector<const Syntax*> base;
         using base::const_iterator;
         using base::begin;
         using base::end;
         using base::size;
         using base::operator[];
         using base::empty;

         Vector();
         explicit Vector(const base&);
         ~Vector();
         void accept(Visitor&) const;
      };

      // ---------------------
      // -- Syntax::Visitor --
      // ---------------------
      struct Syntax::Visitor {
         virtual void visit(const Atom&) = 0;
         virtual void visit(const Integer&);
         virtual void visit(const String&);
         virtual void visit(const Symbol&);
         virtual void visit(const Reference&);
         virtual void visit(const Anchor&) = 0;
         virtual void visit(const Quote&) = 0;
         virtual void visit(const Function&) = 0;
         virtual void visit(const Pair&) = 0;
         virtual void visit(const List&) = 0;
         virtual void visit(const Vector&) = 0;
      };

      // ---------------
      // -- Allocator --
      // ---------------

      // The next two classes are helper classes for the main
      // allocation class Allocator.  We use std::set as allocator
      // that guarantee uuniqueness of atomic syntax object with
      // respect to the constituent token.  That container needs
      // a relational comparator.  In an ideal world, this class
      // should not exist.
      struct SyntaxComparator {
         bool operator()(const Atom& lhs, const Atom& rhs) const {
            return std::less<BasicString>()(lhs.lexeme(), rhs.lexeme());
         }

         bool operator()(const Quote& lhs, const Quote& rhs) const {
            return std::less<const void*>()(lhs.body(), rhs.body());
         }

         bool operator()(const Anchor& lhs, const Anchor& rhs) const {
            return std::less<size_t>()(lhs.ref(), rhs.ref());
         }

         bool operator()(const Function& lhs, const Function& rhs) const {
            return std::less<const void*>()(lhs.code(), rhs.code());
         }

         bool operator()(const Pair& lhs, const Pair& rhs) const {
            std::less<const void*> cmp;
            if (cmp(lhs.first(), rhs.first()))
               return true;
            if (cmp(rhs.first(), lhs.first()))
               return false;
            return cmp(lhs.second(), rhs.second());
         }
      };

      template<typename T>
      struct UniqueAllocator : std::set<T, SyntaxComparator> {
         typedef std::set<T, SyntaxComparator> base;
         typedef typename base::const_iterator const_iterator;

         template<typename U>
         const T* allocate(const U& u) {
            return &*this->insert(T(u)).first;
         }
         
         template<typename U, typename V>
         const T* allocate(const U& u, const V& v) {
            return &*this->insert(T(u, v)).first;
         }
      };
      
      // Allocator of syntax objects.
      struct Allocator {
         Allocator();
         ~Allocator();

         const Integer* make_integer(const Token&);
         const String* make_string(const Token&);
         const Symbol* make_symbol(const Token&, Symbol::Kind);
         const Reference* make_reference(const Token&, size_t);
         const Anchor* make_anchor(size_t, const Syntax*);
         const Quote* make_quote(const Syntax*);
         const Function* make_function(const Syntax*);
         const Pair* make_pair(const Syntax*, const Syntax*);
         const List* make_list(const std::vector<const Syntax*>&);
         const Vector* make_vector(const std::vector<const Syntax*>&);
         
      private:
         UniqueAllocator<Integer> ints;
         UniqueAllocator<String> strs;
         UniqueAllocator<Symbol> syms;
         UniqueAllocator<Anchor> ancs;
         UniqueAllocator<Reference> refs;
         UniqueAllocator<Quote> quotes;
         UniqueAllocator<Function> funs;
         UniqueAllocator<Pair> pairs;
         Memory::Arena<List> lists;
         Memory::Arena<Vector> vectors;
         List empty_list;
         Vector empty_vector;
      };

      // ------------
      // -- Parser --
      // ------------
      // An object of this type transforms a sequence of tokens
      // into a sequence of syntax objects.
      // A parser object does not manage memory itself.  Rather, it delegates
      // storage allocation for syntax objects to specialized
      // agents used to construct it.
      struct Parser {
         Parser(Allocator&, std::vector<const Syntax*>&);
         const Token* parse(const Token*, const Token*);
      private:
         Allocator& alloc;
         std::vector<const Syntax*>& syns;

         const Symbol* parse_symbol(const Token*&, const Token*);
         const Anchor* parse_anchor(const Token*&, const Token*);
         const Reference* parse_reference(const Token*&, const Token*);
         const Symbol* parse_uninterned(const Token*&, const Token*);
         const Function* parse_function(const Token*&, const Token*);
         const Quote* parse_quote(const Token*&, const Token*);
         const Vector* parse_vector(const Token*&, const Token*);
         const Syntax* parse_list_or_pair(const Token*&, const Token*);
         const Syntax* parse_syntax(const Token*&, const Token*);
      };
   }
}

#endif  // OPENAXIOM_SEXPR_INCLUDED