-
Notifications
You must be signed in to change notification settings - Fork 47
/
Copy pathLexer.hs
196 lines (153 loc) Β· 9.83 KB
/
Lexer.hs
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
module Test.Language.Javascript.Lexer
( testLexer
) where
import Test.Hspec
import Data.List (intercalate)
import Language.JavaScript.Parser.Lexer
testLexer :: Spec
testLexer = describe "Lexer:" $ do
describe "with Alex rules" $ do
it "comments" $ do
alexTestLex "// πππππππππ π‘ " `shouldBe` "[CommentToken]"
alexTestLex "/* πππππππππ π‘ */" `shouldBe` "[CommentToken]"
it "return mixed with comments" $ do
alexTestLex "return 1" `shouldBe` "[ReturnToken,WsToken,DecimalToken 1]"
alexTestLex "return \n 1" `shouldBe` "[ReturnToken,WsToken,DecimalToken 1]"
alexTestLex "return //hello" `shouldBe` "[ReturnToken,WsToken,CommentToken]"
alexTestLex "return /*hello*/" `shouldBe` "[ReturnToken,WsToken,CommentToken]"
alexTestLex "return //hello\n 1" `shouldBe` "[ReturnToken,WsToken,CommentToken,WsToken,DecimalToken 1]"
alexTestLex "return /*hello*/\n 1" `shouldBe` "[ReturnToken,WsToken,CommentToken,WsToken,DecimalToken 1]"
alexTestLex "return /*hello 1*/\n" `shouldBe` "[ReturnToken,WsToken,CommentToken,WsToken]"
it "numbers" $ do
alexTestLex "123" `shouldBe` "[DecimalToken 123]"
alexTestLex "037" `shouldBe` "[OctalToken 037]"
alexTestLex "0xab" `shouldBe` "[HexIntegerToken 0xab]"
alexTestLex "0xCD" `shouldBe` "[HexIntegerToken 0xCD]"
it "invalid numbers" $ do
alexTestLex "089" `shouldBe` "[DecimalToken 0,DecimalToken 89]"
alexTestLex "0xGh" `shouldBe` "[DecimalToken 0,IdentifierToken 'xGx']"
it "string" $ do
alexTestLex "'cat'" `shouldBe` "[StringToken 'cat']"
alexTestLex "\"dog\"" `shouldBe` "[StringToken \"dog\"]"
it "strings with escape chars" $ do
alexTestLex "'\t'" `shouldBe` "[StringToken '\t']"
alexTestLex "'\\n'" `shouldBe` "[StringToken '\\n']"
alexTestLex "'\\\\n'" `shouldBe` "[StringToken '\\\\n']"
alexTestLex "'\\\\'" `shouldBe` "[StringToken '\\\\']"
alexTestLex "'\\0'" `shouldBe` "[StringToken '\\0']"
alexTestLex "'\\12'" `shouldBe` "[StringToken '\\12']"
alexTestLex "'\\s'" `shouldBe` "[StringToken '\\s']"
alexTestLex "'\\-'" `shouldBe` "[StringToken '\\-']"
it "strings with non-escaped chars" $
alexTestLex "'\\/'" `shouldBe` "[StringToken '\\/']"
it "strings with escaped quotes" $ do
alexTestLex "'\"'" `shouldBe` "[StringToken '\"']"
alexTestLex "\"\\\"\"" `shouldBe` "[StringToken \"\\\\\"\"]"
alexTestLex "'\\\''" `shouldBe` "[StringToken '\\\\'']"
alexTestLex "'\"'" `shouldBe` "[StringToken '\"']"
alexTestLex "\"\\'\"" `shouldBe` "[StringToken \"\\'\"]"
it "spread token" $ do
alexTestLex "...a" `shouldBe` "[SpreadToken,IdentifierToken 'a']"
it "assignment" $ do
alexTestLex "x=1" `shouldBe` "[IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
alexTestLex "x=1\ny=2" `shouldBe` "[IdentifierToken 'x',SimpleAssignToken,DecimalToken 1,WsToken,IdentifierToken 'y',SimpleAssignToken,DecimalToken 2]"
it "break/continue/return" $ do
alexTestLex "break\nx=1" `shouldBe` "[BreakToken,WsToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
alexTestLex "continue\nx=1" `shouldBe` "[ContinueToken,WsToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
alexTestLex "return\nx=1" `shouldBe` "[ReturnToken,WsToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
it "var/let" $ do
alexTestLex "var\n" `shouldBe` "[VarToken,WsToken]"
alexTestLex "let\n" `shouldBe` "[LetToken,WsToken]"
it "in/of" $ do
alexTestLex "in\n" `shouldBe` "[InToken,WsToken]"
alexTestLex "of\n" `shouldBe` "[OfToken,WsToken]"
it "function" $ do
alexTestLex "async function\n" `shouldBe` "[AsyncToken,WsToken,FunctionToken,WsToken]"
describe "with Happy rules" $ do
it "comments" $ do
happyTestLex "// πππππππππ π‘ " `shouldBe` "[]"
happyTestLex "/* πππππππππ π‘ */" `shouldBe` "[]"
happyTestLex "/* πππππππππ π‘ */ // foo" `shouldBe` "[]"
it "return that doesn't produce autosemi" $ do
happyTestLex "return 1" `shouldBe` "[ReturnToken,DecimalToken 1]"
happyTestLex "return //hello" `shouldBe` "[ReturnToken]"
happyTestLex "return/*hello*/1" `shouldBe` "[ReturnToken,DecimalToken 1]"
it "return mixed with newlines that produce autosemi" $ do
happyTestLex "return \n 1" `shouldBe` "[ReturnToken,AutoSemiToken,DecimalToken 1]"
it "return mixed with comments that produce autosemi and trailing expressions" $ do
happyTestLex "return /*hello \n */" `shouldBe` "[ReturnToken,AutoSemiToken]"
happyTestLex "return /*hello \n 1*/" `shouldBe` "[ReturnToken,AutoSemiToken]"
happyTestLex "return //hello\n" `shouldBe` "[ReturnToken,AutoSemiToken]"
it "return mixed with comments that produce autosemi but no trailing expressions" $ do
happyTestLex "return //hello\n 1" `shouldBe` "[ReturnToken,AutoSemiToken,DecimalToken 1]"
happyTestLex "return /*hello*/\n 1" `shouldBe` "[ReturnToken,AutoSemiToken,DecimalToken 1]"
happyTestLex "return//hello\n1" `shouldBe` "[ReturnToken,AutoSemiToken,DecimalToken 1]"
it "numbers" $ do
happyTestLex "123" `shouldBe` "[DecimalToken 123]"
happyTestLex "037" `shouldBe` "[OctalToken 037]"
happyTestLex "0xab" `shouldBe` "[HexIntegerToken 0xab]"
happyTestLex "0xCD" `shouldBe` "[HexIntegerToken 0xCD]"
it "invalid numbers" $ do
happyTestLex "089" `shouldBe` "[DecimalToken 0,DecimalToken 89]"
happyTestLex "0xGh" `shouldBe` "[DecimalToken 0,IdentifierToken 'xGx']"
it "string" $ do
happyTestLex "'cat'" `shouldBe` "[StringToken 'cat']"
happyTestLex "\"dog\"" `shouldBe` "[StringToken \"dog\"]"
it "strings with escape chars" $ do
happyTestLex "'\t'" `shouldBe` "[StringToken '\t']"
happyTestLex "'\\n'" `shouldBe` "[StringToken '\\n']"
happyTestLex "'\\\\n'" `shouldBe` "[StringToken '\\\\n']"
happyTestLex "'\\\\'" `shouldBe` "[StringToken '\\\\']"
happyTestLex "'\\0'" `shouldBe` "[StringToken '\\0']"
happyTestLex "'\\12'" `shouldBe` "[StringToken '\\12']"
happyTestLex "'\\s'" `shouldBe` "[StringToken '\\s']"
happyTestLex "'\\-'" `shouldBe` "[StringToken '\\-']"
it "strings with non-escaped chars" $
happyTestLex "'\\/'" `shouldBe` "[StringToken '\\/']"
it "strings with escaped quotes" $ do
happyTestLex "'\"'" `shouldBe` "[StringToken '\"']"
happyTestLex "\"\\\"\"" `shouldBe` "[StringToken \"\\\\\"\"]"
happyTestLex "'\\\''" `shouldBe` "[StringToken '\\\\'']"
happyTestLex "'\"'" `shouldBe` "[StringToken '\"']"
happyTestLex "\"\\'\"" `shouldBe` "[StringToken \"\\'\"]"
it "spread token" $ do
happyTestLex "...a" `shouldBe` "[SpreadToken,IdentifierToken 'a']"
it "assignment" $ do
happyTestLex "x=1" `shouldBe` "[IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
happyTestLex "x=1\ny=2" `shouldBe` "[IdentifierToken 'x',SimpleAssignToken,DecimalToken 1,IdentifierToken 'y',SimpleAssignToken,DecimalToken 2]"
it "break/continue/return" $ do
happyTestLex "break\nx=1" `shouldBe` "[BreakToken,AutoSemiToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
happyTestLex "continue\nx=1" `shouldBe` "[ContinueToken,AutoSemiToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
happyTestLex "return\nx=1" `shouldBe` "[ReturnToken,AutoSemiToken,IdentifierToken 'x',SimpleAssignToken,DecimalToken 1]"
it "var/let" $ do
happyTestLex "var\n" `shouldBe` "[VarToken]"
happyTestLex "let\n" `shouldBe` "[LetToken]"
it "in/of" $ do
happyTestLex "in\n" `shouldBe` "[InToken]"
happyTestLex "of\n" `shouldBe` "[OfToken]"
it "function" $ do
happyTestLex "async function\n" `shouldBe` "[AsyncToken,FunctionToken]"
alexTestLex :: String -> String
alexTestLex = genericTestLex alexTestTokenizer
happyTestLex :: String -> String
happyTestLex = genericTestLex happyTestTokenizer
genericTestLex :: (String -> Either String [Token]) -> String -> String
genericTestLex lexer str =
either id stringify $ lexer str
where
stringify xs = "[" ++ intercalate "," (map showToken xs) ++ "]"
showToken :: Token -> String
showToken (StringToken _ lit _) = "StringToken " ++ stringEscape lit
showToken (IdentifierToken _ lit _) = "IdentifierToken '" ++ stringEscape lit ++ "'"
showToken (DecimalToken _ lit _) = "DecimalToken " ++ lit
showToken (OctalToken _ lit _) = "OctalToken " ++ lit
showToken (HexIntegerToken _ lit _) = "HexIntegerToken " ++ lit
showToken token = takeWhile (/= ' ') $ show token
stringEscape [] = []
stringEscape (term:rest) =
let escapeTerm [] = []
escapeTerm [_] = [term]
escapeTerm (x:xs)
| term == x = "\\" ++ x : escapeTerm xs
| otherwise = x : escapeTerm xs
in term : escapeTerm rest