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
|
module Unicode.Char.GeneralBench
( benchmarks
) where
import qualified Data.Char as Char
import Test.Tasty.Bench (Benchmark)
import Unicode.Char.Bench (
Bench (..),
CharRange,
bgroupWithCharRange,
bgroupWithChars,
)
import qualified Unicode.Char.General as G
{-# NOINLINE benchmarks #-}
benchmarks :: CharRange -> Benchmark
benchmarks r = bgroupWithCharRange "Unicode.Char.General" r $ \chars ->
-- Character classification
[ bgroupWithChars "generalCategory" chars
-- We use `fromEnum` because of incompatible GeneralCategory types
[ Bench "base" (fromEnum . Char.generalCategory)
, Bench "unicode-data" (fromEnum . G.generalCategory)
]
, bgroupWithChars "isAlphabetic" chars
[ Bench "unicode-data" G.isAlphabetic
]
, bgroupWithChars "isControl" chars
[ Bench "base" Char.isControl
, Bench "unicode-data" G.isControl
]
, bgroupWithChars "isMark" chars
[ Bench "base" Char.isMark
, Bench "unicode-data" G.isMark
]
, bgroupWithChars "isPrint" chars
[ Bench "base" Char.isPrint
, Bench "unicode-data" G.isPrint
]
, bgroupWithChars "isPunctuation" chars
[ Bench "base" Char.isPunctuation
, Bench "unicode-data" G.isPunctuation
]
, bgroupWithChars "isSeparator" chars
[ Bench "base" Char.isSeparator
, Bench "unicode-data" G.isSeparator
]
, bgroupWithChars "isSymbol" chars
[ Bench "base" Char.isSymbol
, Bench "unicode-data" G.isSymbol
]
, bgroupWithChars "isWhiteSpace" chars
[ Bench "unicode-data" G.isWhiteSpace
]
-- Korean Hangul Characters
, bgroupWithChars "isHangul" chars
[ Bench "unicode-data" G.isHangul
]
, bgroupWithChars "isHangulLV" chars
[ Bench "unicode-data" G.isHangul
]
, bgroupWithChars "isJamo" chars
[ Bench "unicode-data" G.isJamo
]
, bgroupWithChars "jamoLIndex" chars
[ Bench "unicode-data" G.jamoLIndex
]
, bgroupWithChars "jamoVIndex" chars
[ Bench "unicode-data" G.jamoVIndex
]
, bgroupWithChars "jamoTIndex" chars
[ Bench "unicode-data" G.jamoTIndex
]
]
|
