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
|
package bjc.dicelang;
import bjc.dicelang.dice.DiceBox;
import bjc.utils.funcdata.FunctionalMap;
import bjc.utils.funcdata.IMap;
import bjc.utils.funcutils.StringUtils;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import static bjc.dicelang.Errors.ErrorKey.*;
import static bjc.dicelang.Token.Type.*;
public class Tokenizer {
// Literal tokens for tokenization
private IMap<String, Token.Type> litTokens;
private DiceLangEngine eng;
private int nextSym = 0;
public Tokenizer(DiceLangEngine engine) {
eng = engine;
litTokens = new FunctionalMap<>();
litTokens.put("+", ADD);
litTokens.put("-", SUBTRACT);
litTokens.put("*", MULTIPLY);
litTokens.put("/", DIVIDE);
litTokens.put("//", IDIVIDE);
litTokens.put("sd", DICESCALAR);
litTokens.put("df", DICEFUDGE);
litTokens.put("dg", DICEGROUP);
litTokens.put("dc", DICECONCAT);
litTokens.put("dl", DICELIST);
litTokens.put("=>", LET);
litTokens.put(":=", BIND);
litTokens.put(".+.", STRCAT);
litTokens.put(".*.", STRREP);
litTokens.put(",", GROUPSEP);
litTokens.put("crc", COERCE);
}
public Token lexToken(String token, IMap<String, String> stringLts) {
if(token.equals("")) return null;
Token tk = Token.NIL_TOKEN;
if(litTokens.containsKey(token)) {
tk = new Token(litTokens.get(token));
} else {
switch(token.charAt(0)) {
case '(':
case ')':
case '[':
case ']':
case '{':
case '}':
tk = tokenizeGrouping(token);
break;
default:
tk = tokenizeLiteral(token, stringLts);
}
}
return tk;
}
private Token tokenizeGrouping(String token) {
Token tk = Token.NIL_TOKEN;
if(StringUtils.containsOnly(token, "\\" + token.charAt(0))) {
switch(token.charAt(0)) {
case '(':
tk = new Token(OPAREN, token.length());
break;
case ')':
tk = new Token(CPAREN, token.length());
break;
case '[':
tk = new Token(OBRACKET, token.length());
break;
case ']':
tk = new Token(CBRACKET, token.length());
break;
case '{':
tk = new Token(OBRACE, token.length());
break;
case '}':
tk = new Token(CBRACE, token.length());
break;
default:
Errors.inst.printError(EK_TOK_UNGROUP, token);
break;
}
}
return tk;
}
private Pattern hexadecimalMatcher = Pattern.compile("\\A[\\-\\+]?0x[0-9A-Fa-f]+\\Z");
private Pattern flexadecimalMatcher = Pattern.compile("\\A[\\-\\+]?[0-9][0-9A-Za-z]+B\\d{1,2}\\Z");
private Pattern stringLitMatcher = Pattern.compile("\\AstringLiteral(\\d+)\\Z");
private Token tokenizeLiteral(String token, IMap<String, String> stringLts) {
Token tk = Token.NIL_TOKEN;
if(StringUtils.isInt(token)) {
tk = new Token(INT_LIT, Long.parseLong(token));
} else if(hexadecimalMatcher.matcher(token).matches()) {
String newToken = token.substring(0, 1) + token.substring(token.indexOf('x'));
tk = new Token(INT_LIT, Long.parseLong(newToken.substring(2).toUpperCase(), 16));
} else if(flexadecimalMatcher.matcher(token).matches()) {
int parseBase = Integer.parseInt(token.substring(token.lastIndexOf('B') + 1));
if(parseBase < Character.MIN_RADIX || parseBase > Character.MAX_RADIX) {
Errors.inst.printError(EK_TOK_INVBASE, Integer.toString(parseBase));
return Token.NIL_TOKEN;
}
String flexNum = token.substring(0, token.lastIndexOf('B'));
try {
tk = new Token(INT_LIT, Long.parseLong(flexNum, parseBase));
} catch (NumberFormatException nfex) {
Errors.inst.printError(EK_TOK_INVFLEX, flexNum, Integer.toString(parseBase));
return Token.NIL_TOKEN;
}
} else if(StringUtils.isDouble(token)) {
tk = new Token(FLOAT_LIT, Double.parseDouble(token));
} else if(DiceBox.isValidExpression(token)) {
tk = new Token(DICE_LIT, DiceBox.parseExpression(token));
} else {
Matcher stringLit = stringLitMatcher.matcher(token);
if(stringLit.matches()) {
int litNum = Integer.parseInt(stringLit.group(1));
eng.stringLits.put(litNum, stringLts.get(token));
tk = new Token(STRING_LIT, litNum);
} else {
// @TODO define what a valid identifier is
eng.symTable.put(nextSym++, token);
tk = new Token(VREF, nextSym - 1);
}
// @TODO uncomment when we have a defn. for var names
// System.out.printf("\tERROR: Unrecognized token:"
// + "%s\n", token);
}
return tk;
}
}
|
