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
|
module Unicode.Char.NormalizationBench
( benchmarks
) where
import Test.Tasty.Bench ( bgroup, Benchmark )
import Unicode.Char.Bench (
Bench (..),
CharRange,
bgroupWithCharRange,
bgroupWithChars,
bgroupWithValidCharRange',
)
import qualified Unicode.Char.General as G
import qualified Unicode.Char.Normalization as N
{-# NOINLINE benchmarks #-}
benchmarks :: CharRange -> Benchmark
benchmarks r = bgroupWithCharRange "Unicode.Char.Normalization" r $ \chars ->
[ bgroupWithChars "isCombining" chars
[ Bench "unicode-data" N.isCombining
]
, bgroupWithChars "combiningClass" chars
[ Bench "unicode-data" N.combiningClass
]
, bgroupWithChars "isCombiningStarter" chars
[ Bench "unicode-data" N.isCombiningStarter
]
-- [TODO] compose, composeStarters
, bgroup "isDecomposable"
[ bgroupWithChars "Canonical" chars
[ Bench "unicode-data" (N.isDecomposable N.Canonical)
]
, bgroupWithChars "Kompat" chars
[ Bench "unicode-data" (N.isDecomposable N.Kompat)
]
]
, bgroup "decompose"
[ bgroupWithValidCharRange' "Canonical" r (isValid N.Canonical)
[ Bench "unicode-data" (N.decompose N.Canonical)
]
, bgroupWithValidCharRange' "Kompat" r (isValid N.Kompat)
[ Bench "unicode-data" (N.decompose N.Kompat)
]
]
, bgroupWithChars "decomposeHangul" chars
[ Bench "unicode-data" N.decomposeHangul
]
]
-- Filter out: Surrogates, Private Use Areas and unsassigned code points
-- and non-decomposable characters
isValid :: N.DecomposeMode -> Char -> Bool
isValid mode c = G.generalCategory c < G.Surrogate && N.isDecomposable mode c
|
