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
|
#include "lang_analysis/token.h"
#include <string>
#include <iostream>
#include <print>
#include "lang_analysis/lexer_class.h"
#include "lang_analysis/enum_type.h"
#include "lang_analysis/symbol_property.h"
#include "util/io.h"
#include "error.h"
using namespace std; // remove this
constexpr bool TOKEN_DEBUG = false;
namespace ov4
{
/*
* remove leading chars
* by default remove " \t"
*/
string T_lexer::trim(const string &s, const string &trim_target) // trim_target = " \t"
{
size_t b = s.find_first_not_of(trim_target);
if (b == string::npos)
return "";
size_t e = s.find_last_not_of(trim_target);
return s.substr(b, e - b + 1);
}
bool T_lexer::is_single_symbol(char c)
{
string s = " ";
s[0] = c;
// quotation marks are treated as text
if (symbol_property.contains(s) && c != '\'' && c != '\"')
return true;
return false;
}
void T_lexer::bracket_depth_changer(char c, int &bracket_depth)
{
if (c == '(')
{
bracket_depth++;
if constexpr (TOKEN_DEBUG) loggerln("changed depth: {}", bracket_depth);
return;
}
if (c == ')')
{
bracket_depth--;
loggerln("changed depth: {}", bracket_depth);
if (bracket_depth < 0)
{
throw T_error{error_code::TOKEN_UNMATCHED_BRACKET, "tokenizer: unmatched bracket(s)"};
}
return;
}
}
/*
* determine whether `s` and `next` can be combined to form a token
*/
bool T_lexer::token_continue(const string &s, char next)
{
if constexpr (TOKEN_DEBUG) loggerln("token_continue: receiving {} {}", s, next);
// s is empty, so next can be part of the token
if (s.size() == 0) return true;
// text -> text/symbol
if (!is_single_symbol(s[s.size()-1]))
{
// text -> symbol
if (is_single_symbol(next))
return false;
// text still
return true;
}
// symbol -> symbol
T_property tmp;
if (symbol_property.contains(s))
{
tmp = symbol_property.at(s);
if (tmp.continuable)
{
string prev_and_next = s + next;
if (symbol_property.contains(prev_and_next))
return true;
return false;
}
return false;
}
else
{
if constexpr (TOKEN_DEBUG) loggerln("symbol not found in map");
return false;
}
}
// handle [prev, current)
void T_lexer::token_push(const string &push_s, int bracket_depth, bool force_text) // force_text = false
{
T_token tmp;
tmp.bracket_depth = bracket_depth;
string trimmed = trim(push_s);
if (trimmed == "") return;
if constexpr (TOKEN_DEBUG) loggerln("finding {} in map", trimmed);
if (symbol_property.contains(trimmed) && !force_text) // symbol
{
if constexpr (TOKEN_DEBUG) loggerln("token_push: adding symbol");
tmp.token_type = symbol_property.at(trimmed).enum_type;
}
else
{
if constexpr (TOKEN_DEBUG) loggerln("token_push: adding text");
// if (force_text)
// trimmed = trim(trimmed, "\'\"");
tmp.token_type = TEXT;
tmp.text = trimmed;
}
token.push_back(tmp);
}
int T_lexer::tokenizer(const string &s)
{
if (s.size() == 0) return -1;
size_t len = s.size();
string prev_str = "";
bool force_text = false;
int bracket_depth = 0;
guard_type guard = GUARD_OFF;
for (size_t i = 0; i < len; i++)
{
char c = s[i];
prev_str += c;
if constexpr (TOKEN_DEBUG) loggerln("---");
if constexpr (TOKEN_DEBUG) loggerln("prev_str .{}. next char {}", prev_str, s[i+1]);
if (c == '\'' || c == '\"')
{
if constexpr (TOKEN_DEBUG) loggerln("quotation");
// turn on GUARD
if (guard == GUARD_OFF)
{
guard = (c == '\'') ? GUARD_STRONG : GUARD_WEAK;
if constexpr (TOKEN_DEBUG) loggerln("set guard {}", (c == '\'') ? "GUARD_STRONG" : "GUARD_WEAK");
continue;
}
// turn off
else if (guard == GUARD_STRONG && c == '\'')
{
guard = GUARD_OFF;
if constexpr (TOKEN_DEBUG) loggerln("quitting strong guard");
force_text = true;
}
//turn off
else if (guard == GUARD_WEAK && c == '\"')
{
guard = GUARD_OFF;
if constexpr (TOKEN_DEBUG) loggerln("quitting weak guard");
force_text = true;
} else
continue;
}
// not quotation mark
else if ((guard == GUARD_STRONG || guard == GUARD_WEAK))
{
if constexpr (TOKEN_DEBUG) loggerln("tokenizer: guarded, continue");
continue;
}
bracket_depth_changer(c, bracket_depth);
if ((i+1 == len) || !token_continue(prev_str, s[i+1]))
{
token_push(prev_str, bracket_depth, force_text);
force_text = false;
prev_str = "";
continue;
}
}
if (bracket_depth != 0)
throw T_error{error_code::TOKEN_UNMATCHED_BRACKET, "tokenizer: unmatched bracket(s)"};
return 0;
}
}
|
