~jaro/balkon

ref: 21f976aa18e99769db1e2b63313bd26ede47ca4f balkon/test/Data/Text/ParagraphLayout/Internal/BreakSpec.hs -rw-r--r-- 6.1 KiB
21f976aaJaro Support hard line breaks. 1 year, 25 days ago
                                                                                
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
module Data.Text.ParagraphLayout.Internal.BreakSpec (spec) where

import Control.Monad (forM_)
import Data.Text (empty, pack, singleton)
import Data.Text.ICU
    (LocaleName(Locale)
    ,breakCharacter
    ,breakLine
    ,breakSentence
    ,breakWord
    )
import qualified Data.Text.ICU as BreakStatus (Line(..), Word(..))

import Test.Hspec
import Data.Text.ParagraphLayout.Internal.Break

spec :: Spec
spec = do

    describe "breaksDesc" $ do

        -- One of the crucial building blocks of a text layout engine.
        describe "breakLine" $ do
            let b lang = breaksDesc $ breakLine (Locale lang)

            it "finds no breaks in empty input" $
                b "en" empty `shouldBe`
                    []

            it "finds break at offset 0 in non-empty input" $
                b "en" (singleton 'a') `shouldBe`
                    [(0, BreakStatus.Soft)]

            it "finds hard break after newline" $
                b "en" (pack "hello\nworld") `shouldBe`
                    [(6, BreakStatus.Hard)
                    ,(0, BreakStatus.Soft)
                    ]

            it "finds soft breaks after spaces and tabs" $
                b "en" (pack "a few\twords") `shouldBe`
                    [(6, BreakStatus.Soft)
                    ,(2, BreakStatus.Soft)
                    ,(0, BreakStatus.Soft)
                    ]

            it "finds soft breaks after spaces and hyphens" $
                b "cs" (pack "následuje stanice Frýdek-Místek") `shouldBe`
                    [(27, BreakStatus.Soft)
                    ,(19, BreakStatus.Soft)
                    ,(11, BreakStatus.Soft)
                    ,(0, BreakStatus.Soft)
                    ]

            it "finds soft breaks in Japanese kana" $
                b "ja" (pack "トイレはどこですか?") `shouldBe`
                    [(24, BreakStatus.Soft)
                    ,(21, BreakStatus.Soft)
                    ,(18, BreakStatus.Soft)
                    ,(15, BreakStatus.Soft)
                    ,(12, BreakStatus.Soft)
                    ,(9, BreakStatus.Soft)
                    ,(6, BreakStatus.Soft)
                    ,(3, BreakStatus.Soft)
                    ,(0, BreakStatus.Soft)
                    ]

            let jaText = pack "五ヶ月‡コード"
            let jaBreaksStrict =
                    [(18, BreakStatus.Soft)
                    ,(12, BreakStatus.Soft)
                    ,(9, BreakStatus.Soft)
                    ,(6, BreakStatus.Soft)
                    ,(0, BreakStatus.Soft)
                    ]
            let jaBreaksLoose =
                    [(18, BreakStatus.Soft)
                    ,(15, BreakStatus.Soft)
                    ,(12, BreakStatus.Soft)
                    ,(9, BreakStatus.Soft)
                    ,(6, BreakStatus.Soft)
                    ,(3, BreakStatus.Soft)
                    ,(0, BreakStatus.Soft)
                    ]

            -- Observed behaviour.
            -- Not sure why Chinese rules are stricter for Japanese text.
            -- This behaviour may change with future versions of ICU.
            let expectedStrictLocales =
                    [""
                    ,"en"
                    ,"ja@lb=strict"
                    ,"zh"
                    ,"zh_Hans"
                    ,"zh_Hant"
                    ,"zxx"
                    ,"zxx-any-invalid-suffix"
                    ]
            let expectedLooseLocales =
                    ["@lb=loose"
                    ,"en@lb=loose"
                    ,"ja"
                    ,"ja_JP"
                    ,"ja-JP"
                    ,"ja-any-invalid-suffix"
                    ,"zh@lb=loose"
                    ,"zxx-any-invalid-suffix@lb=loose"
                    ]

            expectedStrictLocales `forM_` \l ->
                it ("uses strict line breaks for " ++ l ++ " locale") $
                    b l jaText `shouldBe` jaBreaksStrict

            expectedLooseLocales `forM_` \l ->
                it ("uses loose line breaks for " ++ l ++ " locale") $
                    b l jaText `shouldBe` jaBreaksLoose

        -- Probably not useful for a web browser rendering engine.
        describe "breakSentence" $ do
            let b lang = breaksDesc $ breakSentence (Locale lang)

            it "finds no breaks in empty input" $
                b "en" empty `shouldBe`
                    []

            it "finds break at offset 0 in non-empty input" $
                b "en" (singleton 'a') `shouldBe`
                    [(0, ())]

        -- Probably not useful for a web browser rendering engine,
        -- but may be used for text search and selection.
        describe "breakWord" $ do
            let b lang = breaksDesc $ breakWord (Locale lang)

            it "finds no breaks in empty input" $
                b "en" empty `shouldBe`
                    []

            it "finds break at offset 0 in non-empty input" $
                b "en" (singleton 'a') `shouldBe`
                    [(0, BreakStatus.Uncategorized)]

            it "finds breaks after runs of letters and spaces" $
                b "en" (pack "a few   words") `shouldBe`
                    [(8, BreakStatus.Uncategorized)
                    ,(5, BreakStatus.Letter)
                    ,(2, BreakStatus.Uncategorized)
                    ,(1, BreakStatus.Letter)
                    ,(0, BreakStatus.Uncategorized)
                    ]

        -- Useful for breaking inside words for narrow output.
        -- This can result in breaking ligatures.
        describe "breakCharacter" $ do
            let b lang = breaksDesc $ breakCharacter (Locale lang)

            it "finds no breaks in empty input" $
                b "en" empty `shouldBe`
                    []

            it "finds break at offset 0 in non-empty input" $
                b "en" (singleton 'a') `shouldBe`
                    [(0, ())]

    describe "subOffsetsDesc" $ do

        let result = subOffsetsDesc 5 [(11, 'a'), (8, 'b'), (5, 'c'), (2, 'd')]

        it "should reduce offsets" $
            map fst result `shouldBe` [6, 3, 0]

        it "should preserve payload" $
            map snd result `shouldBe` ['a', 'b', 'c']