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
|
package org.shedlang.compiler.tokeniser;
import org.junit.jupiter.api.Test;
import org.zwobble.sourcetext.SourceText;
import java.util.List;
import static org.zwobble.precisely.AssertThat.assertThat;
import static org.zwobble.precisely.Matchers.equalTo;
import static org.zwobble.precisely.Matchers.isSequence;
public class RegexTokeniserTests {
enum TokenType {
UNKNOWN,
KEYWORD,
IDENTIFIER,
WHITESPACE
}
@Test
public void emptyStringIsTokenisedToNoTokens() {
var tokeniser = new RegexTokeniser<>(TokenType.UNKNOWN, List.of());
var sourceText = sourceText("");
var result = tokeniser.tokenise(sourceText);
assertThat(result, isSequence());
}
@Test
public void regexIsAppliedToGenerateToken() {
var tokeniser = new RegexTokeniser<>(TokenType.UNKNOWN, List.of(
RegexTokeniser.rule(TokenType.IDENTIFIER, "[A-Za-z0-9]+")
));
var sourceText = sourceText("count");
var result = tokeniser.tokenise(sourceText);
assertThat(result, isSequence(
equalTo(new Token<>(
sourceText.characterPosition(0).to(sourceText.characterPosition(5)),
TokenType.IDENTIFIER
))
));
}
@Test
public void firstMatchingRegexIsUsed() {
var tokeniser = new RegexTokeniser<>(TokenType.UNKNOWN, List.of(
RegexTokeniser.rule(TokenType.KEYWORD, "if"),
RegexTokeniser.rule(TokenType.IDENTIFIER, "[A-Za-z0-9]+")
));
var sourceText = sourceText("if");
var result = tokeniser.tokenise(sourceText);
assertThat(result, isSequence(
equalTo(new Token<>(
sourceText.characterPosition(0).to(sourceText.characterPosition(2)),
TokenType.KEYWORD
))
));
}
@Test
public void sequenceOfTokensCanBeGenerated() {
var tokeniser = new RegexTokeniser<>(TokenType.UNKNOWN, List.of(
RegexTokeniser.rule(TokenType.IDENTIFIER, "[A-Za-z0-9]+"),
RegexTokeniser.rule(TokenType.WHITESPACE, "\\s")
));
var sourceText = sourceText("one two");
var result = tokeniser.tokenise(sourceText);
assertThat(result, isSequence(
equalTo(new Token<>(
sourceText.characterPosition(0).to(sourceText.characterPosition(3)),
TokenType.IDENTIFIER
)),
equalTo(new Token<>(
sourceText.characterPosition(3).to(sourceText.characterPosition(4)),
TokenType.WHITESPACE
)),
equalTo(new Token<>(
sourceText.characterPosition(4).to(sourceText.characterPosition(7)),
TokenType.IDENTIFIER
))
));
}
@Test
public void whenNoRulesMatchThenUnknownTokensAreGenerated() {
var tokeniser = new RegexTokeniser<>(TokenType.UNKNOWN, List.of(
RegexTokeniser.rule(TokenType.IDENTIFIER, "[A-Za-z0-9]+")
));
var sourceText = sourceText("!!a!");
var result = tokeniser.tokenise(sourceText);
assertThat(result, isSequence(
equalTo(new Token<>(
sourceText.characterPosition(0).to(sourceText.characterPosition(1)),
TokenType.UNKNOWN
)),
equalTo(new Token<>(
sourceText.characterPosition(1).to(sourceText.characterPosition(2)),
TokenType.UNKNOWN
)),
equalTo(new Token<>(
sourceText.characterPosition(2).to(sourceText.characterPosition(3)),
TokenType.IDENTIFIER
)),
equalTo(new Token<>(
sourceText.characterPosition(3).to(sourceText.characterPosition(4)),
TokenType.UNKNOWN
))
));
}
private SourceText sourceText(String sourceContents) {
return SourceText.fromString("<filename>", sourceContents);
}
}
|
