summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/test/testdata/break_rules/line_loose_cj.txt
blob: 9d7b2cc12c6d84efbe5955fd2c72f1768a4743da (plain)
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
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
#
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Copyright (c) 2016, International Business Machines Corporation and others. All Rights Reserved.
#
#  file:  line_loose_cj.txt
#
# Reference Line Break rules for intltest rbbi/RBBIMonkeyTest.
# Rules derived from Unicode Standard Annex #14 for Unicode 14.0.
#
# Note: Rule syntax and the monkey test itself are still a work in progress.
#       They are expected to change with review and the addition of support for rule tailoring.
#
#         Line Breaking Rules
#         Implement default line breaking as defined by
#         Unicode Standard Annex #14
#         http://www.unicode.org/reports/tr14/, tailored as noted below.
#
#         This tailors the line break behavior to correspond to CSS
#         line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese.
#         It sets characters of class CJ to behave like ID.
#         In addition, it allows breaks:
#         * between ID and hyphens 2010 & 2013 (both BA)
#         * before 301C, 30A0 (both NS)
#         * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS)
#         * between characters of LineBreak class IN such as 2026
#         * before some centered punct 203C, 2047, 2048, 2049, 30FB, FF1A, FF1B,
#           FF65 (all NS) and FF01, FF1F (both EX).
#         * before suffix characters with LineBreak class PO and EastAsianWidth A,F,W;
#           this includes: 00B0 2030 2032 2033 2035 2103 2109 FE6A FF05 FFE0
#         * after prefix characters with LineBreak class PR and EastAsianWidth A,F,W;
#           this includes: 00A4 00B1 20AC 2116 FE69 FF04 FFE1 FFE5 FFE6
#         It allows breaking before 201C and after 201D, for zh_Hans, zh_Hant, and ja.


type = line;
locale = ja@lb=loose;


AI = [:LineBreak =  Ambiguous:];
AL = [:LineBreak =  Alphabetic:];
BAX = [\u2010 \u2013];
BA = [[:LineBreak =  Break_After:] - BAX];
HH = [\u2010];      # \u2010 is HYPHEN, default line break is BA.
BB = [:LineBreak =  Break_Before:];
BK = [:LineBreak =  Mandatory_Break:];
B2 = [:LineBreak =  Break_Both:];
CB = [:LineBreak =  Contingent_Break:];
CJ = [:LineBreak =  Conditional_Japanese_Starter:];
CL = [[:LineBreak =  Close_Punctuation:] \u201d];
CMS = [:LineBreak =  Combining_Mark:];
CP = [:LineBreak =  Close_Parenthesis:];
CR = [:LineBreak =  Carriage_Return:];
EB = [:LineBreak =  EB:];
EM = [:LineBreak =  EM:];
EXX = [\uFF01 \uFF1F];
EX = [[:LineBreak =  Exclamation:] - EXX];
GL = [:LineBreak =  Glue:];
HL = [:LineBreak =  Hebrew_Letter:];
HY = [:LineBreak =  Hyphen:];
H2 = [:LineBreak =  H2:];
H3 = [:LineBreak =  H3:];
ID = [[:LineBreak =  Ideographic:] CJ];  # CSS Loose tailoring: CJ resolves to ID
IN = [:LineBreak =  Inseperable:];
IS = [:LineBreak =  Infix_Numeric:];
JL = [:LineBreak =  JL:];
JV = [:LineBreak =  JV:];
JT = [:LineBreak =  JT:];
LF = [:LineBreak =  Line_Feed:];
NL = [:LineBreak =  Next_Line:];
NSX = [\u301C \u30A0 \u3005 \u303B \u309D \u309E \u30FD \u30FE \u203C \u2047 \u2048 \u2049 \u30FB \uFF1A \uFF1B \uFF65];
NS = [[:LineBreak =  Nonstarter:] - NSX];
NU = [:LineBreak =  Numeric:];
OP = [[:LineBreak =  Open_Punctuation:] \u201c];
POX = [\u00B0 \u2030 \u2032 \u2033 \u2035 \u2103 \u2109 \uFE6A \uFF05 \uFFE0];
PO = [[:LineBreak =  Postfix_Numeric:] - POX];
PRX = [\u00A4 \u00B1 \u20AC \u2116 \uFE69 \uFF04 \uFFE1 \uFFE5 \uFFE6];
PR = [[:LineBreak =  Prefix_Numeric:] - PRX];
QU = [[:LineBreak =  Quotation:] - [\u201c\u201d]];
RI = [:LineBreak =  Regional_Indicator:];
SA = [:LineBreak =  Complex_Context:];
SG = [:LineBreak =  Surrogate:];
SP = [:LineBreak =  Space:];
SY = [:LineBreak =  Break_Symbols:];
WJ = [:LineBreak =  Word_Joiner:];
XX = [:LineBreak =  Unknown:];
ZW = [:LineBreak =  ZWSpace:];
ZWJ = [:LineBreak =  ZWJ:];

# OP30 and CP30 are variants of OP and CP that appear in rule LB30 from UAX 14.
# Limitations of this monkey test rule parser require that these definitions be pulled out
# rather than appearing in-line in LB 30.

OP30 = [OP - [\p{ea=F}\p{ea=W}\p{ea=H}]];
CP30 = [CP - [\p{ea=F}\p{ea=W}\p{ea=H}]];

# The redundant-looking inner brackets are required for the current parser in the test code.
ExtPictUnassigned = [[\p{Extended_Pictographic}]&[\p{Cn}]];

# LB1 - Resolve AI, CB, CJ, SA, SG, and XX into other line breaking classes
AL = [AL AI SG XX ];
dictionary = SA;

# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
#         list it in the numerous rules that use CM.
CM = [CMS ZWJ];

LB4:        BK ÷;
LB5:        CR LF;
LB5.1:      CR ÷;
LB5.2:      LF ÷;
LB5.3:      NL ÷;

LB6:        . (BK | CR | LF | NL);
LB6.1:      [^BK CR LF NL SP ZW] CM* (BK | CR | LF | NL);

# LB8   break after ZW SP*.
# Precedes LB7 because both rules will match the sequences like ZW SP,
# and LB8 must take precedence.

LB8:        ZW SP* ÷ [^ZW SP BK CR LF NL];

# Numbers. Equivalent to Tailoring example 8 from UAX 14.
# Moved up, before LB14, because it can match longer sequences which must take precedence.
#          Loose_cj tailoring: do not include $PRX at the beginning or $POX at the end.
LB25:        ((PR | PO | POX)CM*)? ((OP | HY)CM*)? (IS CM*)? NU (CM*(NU | SY | IS))* (CM*(CL | CP))? (CM*(PR | PRX | PO))?;

# Rules LB14 - LB17.
# Moved up, before LB7, because they can match a longer sequence that would also match LB7.
# For example, the sequence "OP CM SP AL" matches LB14
# while the prefix of it, "OP CM SP" matches LB7.1
LB14:        OP CM* SP* .;

# LB 14a Break before an IS that begins a number and follows a space.
LB14a:       SP ÷ IS CM* NU;

# LB14b       × IS
LB14b.1:     [^SP] CM* IS;
LB14b.2:     SP IS;

LB15:        QU CM* SP* OP;
LB16:        (CL | CP)CM* SP* NS;
LB17:        B2 CM* SP* B2;


# LB7 Do not break before spaces or zero width space.

LB7.1:      [^ZW SP] CM* [SP ZW];
LB7.2:      [ZW SP] [SP ZW];

# LB8a
#      ZWJ x
#      Don't match a CM on the right - let other rules pick up CM sequences, where
#      the ZWJ behaves as just another generic CM.
LB8a:       ZWJ [^CM];


# LB9:  X CM -> X
# LB10: Unattached CM -> AL

#LB11:       × WJ;
#            WJ ×

LB11.1:      [^SP] CM* WJ;
LB11.2:      SP WJ;
LB11.3:      WJ CM* [^CM];

LB12:        GL CM* [^CM];

LB12a:       [^SP BA BAX HY] CM* GL;

# LB 13 Do not break before ‘]’ or ‘!’ or ‘/’, even after spaces.
LB13.1: [^SP] CM* [CL CP EX SY];
LB13.2: SP [CL CP EX SY];


# LB 14-17 are moved above LB 7.

LB18:        SP ÷;

LB19:        . CM* QU;
LB19.1:      QU CM* [^CM];

# LB 20   Break before and after CB.
#         Interaction with LB8a:  ZWJ x . is tricky because CM includes ZWJ.
#                                 ZWJ acts like a CM to the left, combining with CB.
#                                 ZWJ acts independently to the right, no break after by LB8a.
LB20.1:      . CM* ZWJ CB;
LB20.2:      . CM* ÷ CB;

LB20.3:      CB CM* ZWJ [^CM];
LB20.4:      CB CM* ÷;

# LB 20.09    Don't break between Hyphens and Letters when there is a break preceding the hyphen.
LB20.09:     ^(HY | HH) CM* AL;

# Note: Rule 21a must come before 21 to prevent 21.1 from matching HL BA, then
#       not picking up the continuing match after the BA from 21a.
# LB 21a Don't break after Hebrew + Hyphen
#   HL (HY | BA) x

LB21a:       HL CM* (HY | BA | BAX) CM* [^CM CB]?;

LB21.1:      [^ID] CM* [BA BAX HY NS];
LB21.2:      ID CM* [BA HY NS];
LB21.3:      BB CM* [^CM CB];

LB21b:       SY CM* HL;


LB22:        [^IN] CM* IN;   # For CSS Loose, allow breaks between adjacent ellipses characters.

LB23.1:      (AL | HL | CM) CM* NU;
LB23.2:      NU CM* (AL | HL);

LB23a.1:     PR CM* (ID | EB | EM);
LB23a.2:     (ID | EB | EM) CM* PO;

LB24.2:      (PR | PO | POX) CM* (AL | HL);
LB24.3:      (AL | HL | CM) CM* (PR | PO | POX);


LB26.1:      JL CM* (JL | JV | H2 | H3);
LB26.2:      (JV | H2) CM* (JV | JT);
LB26.3:      (JT | H3) CM* JT;

LB27.1:      (JL | JV | JT | H2 | H3) CM* PO;
LB27.2:      PR CM* (JL | JV | JT | H2 | H3);

# LB28 Do not break between Alphabetics.
#      Unattached (leading) CM treated as AL.
LB28:        (AL | HL | CM)CM* (AL | HL);

LB29:        IS CM* (AL | HL);

# LB30  is adjusted for unattached leading CM being treated as AL.
LB30.1:      (AL | CM | HL | NU) CM* OP30;
LB30.2:      CP30 CM* (AL | HL | NU);

# LB30a  keep pairs of RI together.
LB30a.1:     RI CM* RI         ÷ [^BK CR LF NL SP ZW WJ CL CP EX IS SY GL QU BA BAX HY NS IN CM];
LB30a.2:     RI CM* RI CM* CMS ÷ [^BK CR LF NL SP ZW WJ CL CP EX IS SY GL QU BA BAX HY NS IN CM];
LB30a.3:     RI CM* RI CM* [BK CR LF NL SP ZW WJ GL CL CP EX IS SY QU BA BAX HY NS IN ZWJ]?;

# LB30b Do not break between Emoji Base (or potential emoji) and Emoji Modifier
LB30b.1:       EB CM* EM;
LB30b.2:       ExtPictUnassigned CM* EM;

# LB31 Break Everywhere Else.
#      Include combining marks
LB31.1:        . CM* ZWJ [^CM];
LB31.2:        . CM* ÷;