File size: 7,553 Bytes
a10b189 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | {-|
Module : Test.Surface.Lexer
Description : Unit tests for the lexer
Copyright : (c) 2026 Ahmad Ali Parr
License : BSL-1.0
-}
module Test.Surface.Lexer (tests) where
import Test.Tasty (TestTree, testGroup)
import Test.Tasty.HUnit (testCase, (@?=), Assertion)
import Assertica.Surface.Lexer
import Assertica.Surface.AST (SourceLoc(..))
-- ============================================================================
-- LEXER TESTS
-- ============================================================================
tests :: TestTree
tests = testGroup "Assertica.Surface.Lexer"
[ testGroup "Keywords"
[ testCase "lex 'let'" $
lexKeyword "let" KwLet
, testCase "lex 'in'" $
lexKeyword "in" KwIn
, testCase "lex 'forall'" $
lexKeyword "forall" KwForall
, testCase "lex 'assert'" $
lexKeyword "assert" KwAssert
, testCase "lex 'proof'" $
lexKeyword "proof" KwProof
, testCase "lex 'data'" $
lexKeyword "data" KwData
, testCase "lex 'type'" $
lexKeyword "type" KwType
]
, testGroup "Identifiers"
[ testCase "lex simple identifier" $
lexIdent "x" (Ident "x")
, testCase "lex longer identifier" $
lexIdent "join" (Ident "join")
, testCase "lex identifier with underscores" $
lexIdent "my_var" (Ident "my_var")
, testCase "lex qualified name" $
lexIdent "Prelude.Bool" (QualIdent ["Prelude", "Bool"])
]
, testGroup "Operators"
[ testCase "lex '->' arrow" $
lexOp "->" OpArrow
, testCase "lex '=>' fat arrow" $
lexOp "=>" OpFatArrow
, testCase "lex ':=' colon equals" $
lexOp ":=" OpColonEq
, testCase "lex '==' equality" $
lexOp "==" OpEq
, testCase "lex '/=' not equal" $
lexOp "/=" OpNeq
, testCase "lex '+' plus" $
lexOp "+" OpPlus
, testCase "lex '-' minus" $
lexOp "-" OpMinus
, testCase "lex '*' multiply" $
lexOp "*" OpMul
, testCase "lex '/' divide" $
lexOp "/" OpDiv
, testCase "lex '/\\' and" $
lexOp "/\\" OpAnd
, testCase "lex '\\/' or" $
lexOp "\\/" OpOr
]
, testGroup "Literals"
[ testCase "lex integer literal" $
lexNum "42" (IntLiteral 42)
, testCase "lex large integer" $
lexNum "123456789" (IntLiteral 123456789)
, testCase "lex string literal" $
lexStr "\"hello\"" (StringLiteral "hello")
, testCase "lex string with spaces" $
lexStr "\"hello world\"" (StringLiteral "hello world")
]
, testGroup "Delimiters"
[ testCase "lex '('" $
lexDelim "(" LParen
, testCase "lex ')'" $
lexDelim ")" RParen
, testCase "lex '['" $
lexDelim "[" LBracket
, testCase "lex ']'" $
lexDelim "]" RBracket
, testCase "lex '{'" $
lexDelim "{" LBrace
, testCase "lex '}'" $
lexDelim "}" RBrace
, testCase "lex ','" $
lexDelim "," Comma
, testCase "lex ';'" $
lexDelim ";" Semicolon
]
, testGroup "Comments"
[ testCase "skip line comment" $
lexSkipLineComment "x -- comment\ny" [Ident "x", Ident "y"]
, testCase "skip block comment" $
lexSkipBlockComment "x {- comment -} y" [Ident "x", Ident "y"]
, testCase "skip nested block comments" $
lexSkipBlockComment "x {- a {- b -} c -} y" [Ident "x", Ident "y"]
]
, testGroup "Complex programs"
[ testCase "lex lambda expression" $
lexProgram "\\x -> x + 1"
[Backslash, Ident "x", OpArrow, Ident "x", OpPlus, IntLiteral 1]
, testCase "lex assertion" $
lexProgram "assert comm: forall x y. x == y"
[KwAssert, Ident "comm", OpColon, KwForall, Ident "x", Ident "y", OpDot, Ident "x", OpEq, Ident "y"]
, testCase "lex let binding" $
lexProgram "let x = 42 in x"
[KwLet, Ident "x", OpEq, IntLiteral 42, KwIn, Ident "x"]
]
, testGroup "Error cases"
[ testCase "unterminated string" $
case lexer "\"hello" of
Left _ -> return ()
Right _ -> fail "Should fail on unterminated string"
, testCase "unterminated block comment" $
case lexer "x {- comment" of
Left _ -> return ()
Right _ -> fail "Should fail on unterminated block comment"
]
]
-- ============================================================================
-- HELPER FUNCTIONS
-- ============================================================================
{-| Test lexing a single keyword.
-}
lexKeyword :: String -> TokenType -> Assertion
lexKeyword input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test lexing a single identifier.
-}
lexIdent :: String -> TokenType -> Assertion
lexIdent input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test lexing a single operator.
-}
lexOp :: String -> TokenType -> Assertion
lexOp input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test lexing a number.
-}
lexNum :: String -> TokenType -> Assertion
lexNum input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test lexing a string.
-}
lexStr :: String -> TokenType -> Assertion
lexStr input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test lexing a delimiter.
-}
lexDelim :: String -> TokenType -> Assertion
lexDelim input expected = do
case lexer input of
Right tokens ->
case filter (\t -> tokenType t /= EOF) tokens of
[Token tt _] -> tt @?= expected
_ -> fail "Expected exactly one non-EOF token"
Left err -> fail err
{-| Test skipping line comments.
-}
lexSkipLineComment :: String -> [TokenType] -> Assertion
lexSkipLineComment input expectedTypes = do
case lexer input of
Right tokens ->
let types = map tokenType (filter (\t -> tokenType t /= EOF) tokens)
in types @?= expectedTypes
Left err -> fail err
{-| Test skipping block comments.
-}
lexSkipBlockComment :: String -> [TokenType] -> Assertion
lexSkipBlockComment input expectedTypes = do
case lexer input of
Right tokens ->
let types = map tokenType (filter (\t -> tokenType t /= EOF) tokens)
in types @?= expectedTypes
Left err -> fail err
{-| Test lexing a complete program.
-}
lexProgram :: String -> [TokenType] -> Assertion
lexProgram input expectedTypes = do
case lexer input of
Right tokens ->
let types = map tokenType (filter (\t -> tokenType t /= EOF) tokens)
in types @?= expectedTypes
Left err -> fail err
|