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
|
// Copyright (C) 2013-2014, Gabriel Dos Reis.
// All rights reserved.
// Written by Gabriel Dos Reis.
//
// 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 OpenAxiom. 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.
#include <open-axiom/token>
#include <ostream>
#include <iostream>
namespace OpenAxiom {
std::ostream& operator<<(std::ostream& os, const Locus& l) {
return os << '{' << l.line << ", " << l.column << '}';
}
std::ostream&
operator<<(std::ostream& os, TokenCategory tc) {
switch (tc) {
case TokenCategory::Unclassified: os << "UNCLASSIFIED"; break;
case TokenCategory::Whitespace: os << "WHITESPACE"; break;
case TokenCategory::Comment: os << "COMMENT"; break;
case TokenCategory::Punctuator: os << "PUNCTUATOR"; break;
case TokenCategory::Operator: os << "OPERATOR"; break;
case TokenCategory::Integer: os << "INTEGER"; break;
case TokenCategory::FloatingPoint: os << "FLOATINGPOINT"; break;
case TokenCategory::String: os << "STRING"; break;
case TokenCategory::Keyword: os << "KEYWORD"; break;
case TokenCategory::Identifier: os << "IDENTIFIER"; break;
case TokenCategory::Formatting: os << "FORMATTING"; break;
case TokenCategory::Junk: os << "JUNK"; break;
default: os << "????"; break;
}
return os;
}
bool separator_or_punctuator(uint8_t c) {
switch (c) {
case '.': case '`': case '^': case '&': case '~': case '*':
case '-': case '+': case ';': case ',': case '@': case '|':
case '\'': case ':': case '=': case '\\': case '"': case '/':
case '(': case ')': case '{': case '}': case '[': case ']':
case '<': case '>': case '#': case ' ':
return true;
default:
return false;
}
}
namespace {
struct TokenMapEntry {
const char* const text;
const TokenCategory category;
const TokenValue value;
const Language dialect; // = Language::Spad
};
}
const TokenMapEntry token_map[] {
#undef OPENAXIOM_DEFINE_TOKEN
#define OPENAXIOM_DEFINE_TOKEN(T, N, C, ...) \
{ N, TokenCategory::C, TokenValue::T, __VA_ARGS__ },
#include <open-axiom/token-value>
#undef OPENAXIOM_DEFINE_TOKEN
};
TokenClassification
classify(const std::string& s) {
for (auto& t : token_map) {
if (t.text == s)
return { t.category, t.value };
}
return { TokenCategory::Identifier, TokenValue::Unknown };
}
std::ostream&
operator<<(std::ostream& os, TokenValue tv) {
if (tv < TokenValue::Artificial)
os << token_map[uint8_t(tv)].text;
else switch (tv) {
case TokenValue::Indent: os << "%INDENT"; break;
case TokenValue::Unindent: os << "%UNIDENT"; break;
case TokenValue::Justify: os << "%JUSTIFY"; break;
default: os << "%ALIEN"; break;
}
return os;
}
}
|
