blob: b7087c3b00395a91f0bd8a90cfa111a96e03c135 (
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
|
(define-module (test cpp lex2)
:use-module (srfi srfi-64)
:use-module (srfi srfi-88)
:use-module (ice-9 peg)
:use-module (c lex2))
(test-equal "Integer literal"
(list (lexeme type: 'preprocessing-token body: '(pp-number "10")))
(lex "10"))
(test-equal "String literal"
(list (lexeme type: 'preprocessing-token body: '(string-literal "Hello")))
(lex "\"Hello\""))
(test-equal "Mulitple tokens, including whitespace"
(list (lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(pp-number "10"))
(lexeme type: 'whitespace body: " "))
(lex " 10 "))
(test-equal "Char literal"
(list (lexeme type: 'preprocessing-token body: '(character-constant "a")))
(lex "'a'"))
(test-equal "Comment inside string"
(list (lexeme type: 'preprocessing-token body: '(string-literal "Hel/*lo")))
(lex "\"Hel/*lo\""))
(test-equal "#define line"
(list
(lexeme type: 'preprocessing-token body: '(punctuator "#"))
(lexeme type: 'preprocessing-token body: '(identifier "define"))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(identifier "f"))
(lexeme type: 'preprocessing-token body: '(punctuator "("))
(lexeme type: 'preprocessing-token body: '(identifier "x"))
(lexeme type: 'preprocessing-token body: '(punctuator ")"))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(pp-number "10")))
(lex "#define f(x) 10"))
(test-equal "Nested parenthesis"
(list
(lexeme type: 'preprocessing-token body: '(identifier "f"))
(lexeme type: 'preprocessing-token body: '(punctuator "("))
(lexeme type: 'preprocessing-token body: '(pp-number "1"))
(lexeme type: 'preprocessing-token body: '(punctuator ","))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(punctuator "("))
(lexeme type: 'preprocessing-token body: '(pp-number "2"))
(lexeme type: 'preprocessing-token body: '(punctuator ","))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(pp-number "3"))
(lexeme type: 'preprocessing-token body: '(punctuator ")"))
(lexeme type: 'preprocessing-token body: '(punctuator ","))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(pp-number "4"))
(lexeme type: 'preprocessing-token body: '(punctuator ")")))
(lex "f(1, (2, 3), 4)"))
;; Generating a single lexeme
;; (whitespace " ")
;; would also be ok
(test-equal "Grouped whitespace"
(list (lexeme type: 'whitespace body: " ")
(lexeme type: 'whitespace body: " "))
(lex " "))
(test-equal "Newlines get sepparate whitespace tokens"
(list (lexeme type: 'whitespace body: " ")
(lexeme type: 'whitespace body: " ")
(lexeme type: 'whitespace body: "\n")
(lexeme type: 'whitespace body: " "))
(lex " \n "))
;; Refer to 6.4 p.1 for the syntax requirement
;; 6.10.9 p. 2 for the sample string
(test-equal "each non-white-space character that cannot be one of the above"
(list (lexeme type: 'preprocessing-token body: '(punctuator "."))
(lexeme type: 'preprocessing-token body: '(punctuator "."))
(lexeme type: 'other body: "\\") ; <- Interesting part
(lexeme type: 'preprocessing-token body: '(identifier "listing"))
(lexeme type: 'preprocessing-token body: '(punctuator "."))
(lexeme type: 'preprocessing-token body: '(identifier "dir")))
(lex "..\\listing.dir"))
(test-equal "Propper H-string"
(list (lexeme type: 'preprocessing-token body: '(header-name (h-string "a"))))
(lex "<a>"))
(test-equal "Unexpected h-string"
(list (lexeme type: 'preprocessing-token body: '(pp-number "1"))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(header-name (h-string " 2 ")))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(pp-number "3")))
(lex "1 < 2 > 3"))
(test-equal "Quotation mark inside h-string"
(list (lexeme type: 'preprocessing-token body: '(header-name (h-string "a\"b"))))
(lex "<a\"b>"))
(test-equal "Interaction of h-strings and regular strings"
(test-equal "Less than string, not h-string"
(list (lexeme type: 'preprocessing-token body: '(pp-number "1"))
(lexeme type: 'preprocessing-token body: '(string-literal "<"))
(lexeme type: 'preprocessing-token body: '(punctuator ">")))
(lex "1\"<\">"))
(test-equal "H-string, not string"
(list (lexeme type: 'preprocessing-token body: '(pp-number "1"))
(lexeme type: 'preprocessing-token body: '(header-name (h-string "\"")))
(lexeme type: 'other body: "\""))
(lex "1<\">\"")))
(test-equal "Q-strings are lexed as regular strings"
(list (lexeme type: 'preprocessing-token body: '(punctuator "#"))
(lexeme type: 'preprocessing-token body: '(identifier "include"))
(lexeme type: 'whitespace body: " ")
(lexeme type: 'preprocessing-token body: '(string-literal "test")))
;; # include here, since generated tokens could possible depend on that context,
;; and the reason regular strings are returned is since the lexer doesn't check
;; that context
(lex "#include \"test\"")
)
(test-group "Unicode"
(test-equal "In string literals"
(list (lexeme type: 'preprocessing-token body: '(string-literal "åäö")))
(lex "\"åäö\""))
(test-equal "Outside string literals"
(list (lexeme type: 'other body: "å")
(lexeme type: 'other body: "ä")
(lexeme type: 'other body: "ö"))
(lex "åäö")))
|
