| 1 |
# Copyright (C) 2016 and later: Unicode, Inc. and others. |
| 2 |
# License & terms of use: http://www.unicode.org/copyright.html |
| 3 |
# Copyright (c) 2012-2015 International Business Machines |
| 4 |
# Corporation and others. All Rights Reserved. |
| 5 |
# |
| 6 |
# This file should be in UTF-8 with a signature byte sequence ("BOM"). |
| 7 |
# |
| 8 |
# collationtest.txt: Collation test data. |
| 9 |
# |
| 10 |
# created on: 2012apr13 |
| 11 |
# created by: Markus W. Scherer |
| 12 |
|
| 13 |
# A line with "** test: description" is used for verbose and error output. |
| 14 |
|
| 15 |
# A collator can be set with "@ root" or "@ locale language-tag", |
| 16 |
# for example "@ locale de-u-co-phonebk". |
| 17 |
# An old-style locale ID can also be used, for example "@ locale de@collation=phonebook". |
| 18 |
|
| 19 |
# A collator can be built with "@ rules". |
| 20 |
# An "@ rules" line is followed by one or more lines with the tailoring rules. |
| 21 |
|
| 22 |
# A collator can be modified with "% attribute=value". |
| 23 |
|
| 24 |
# "* compare" tests the order (= or <) of the following strings. |
| 25 |
# The relation can be "=" or "<" (the level of the difference is not specified) |
| 26 |
# or "<1", "<2", "<c", "<3", "<4" (indicating the level of the difference). |
| 27 |
|
| 28 |
# Test sections ("* compare") are terminated by |
| 29 |
# definitions of new collators, changing attributes, or new test sections. |
| 30 |
|
| 31 |
** test: simple CEs & expansions |
| 32 |
# Many types of mappings are tested elsewhere, including via the UCA conformance tests. |
| 33 |
# Here we mostly cover a few unusual mappings. |
| 34 |
@ rules |
| 35 |
&\x01 # most control codes are ignorable |
| 36 |
<<<\u0300 # tertiary CE |
| 37 |
&9<\x00 # NUL not ignorable |
| 38 |
&\uA00A\uA00B=\uA002 # two long-primary CEs |
| 39 |
&\uA00A\uA00B\u00050005=\uA003 # three CEs, require 64 bits |
| 40 |
|
| 41 |
* compare |
| 42 |
= \x01 |
| 43 |
= \x02 |
| 44 |
<3 \u0300 |
| 45 |
<1 9 |
| 46 |
<1 \x00 |
| 47 |
= \x01\x00\x02 |
| 48 |
<1 a |
| 49 |
<3 a\u0300 |
| 50 |
<2 a\u0308 |
| 51 |
= ä |
| 52 |
<1 b |
| 53 |
<1 か # Hiragana Ka (U+304B) |
| 54 |
<2 か\u3099 # plus voiced sound mark |
| 55 |
= が # Hiragana Ga (U+304C) |
| 56 |
<1 \uA00A\uA00B |
| 57 |
= \uA002 |
| 58 |
<1 \uA00A\uA00B\u00050004 |
| 59 |
<1 \uA00A\uA00B\u00050005 |
| 60 |
= \uA003 |
| 61 |
<1 \uA00A\uA00B\u00050006 |
| 62 |
|
| 63 |
** test: contractions |
| 64 |
# Create some interesting mappings, and map some normalization-inert characters |
| 65 |
# (which are not subject to canonical reordering) |
| 66 |
# to some of the same CEs to check the sequence of CEs. |
| 67 |
@ rules |
| 68 |
|
| 69 |
# Contractions starting with 'a' should not continue with any character < U+0300 |
| 70 |
# so that we can test a shortcut for that. |
| 71 |
&a=ⓐ |
| 72 |
&b<bz=ⓑ |
| 73 |
&d<dz\u0301=ⓓ # d+z+acute |
| 74 |
&z |
| 75 |
<a\u0301=Ⓐ # a+acute sorts after z |
| 76 |
<a\u0301\u0301=Ⓑ # a+acute+acute |
| 77 |
<a\u0301\u0301\u0358=Ⓒ # a+acute+acute+dot above right |
| 78 |
<a\u030a=Ⓓ # a+ring |
| 79 |
<a\u0323=Ⓔ # a+dot below |
| 80 |
<a\u0323\u0358=Ⓕ # a+dot below+dot above right |
| 81 |
<a\u0327\u0323\u030a=Ⓖ # a+cedilla+dot below+ring |
| 82 |
<a\u0327\u0323bz=Ⓗ # a+cedilla+dot below+b+z |
| 83 |
|
| 84 |
&\U0001D158=⁰ # musical notehead black (has a symbol primary) |
| 85 |
<\U0001D158\U0001D165=¼ # musical quarter note |
| 86 |
|
| 87 |
# deliberately missing prefix contractions: |
| 88 |
# dz |
| 89 |
# a\u0327 |
| 90 |
# a\u0327\u0323 |
| 91 |
# a\u0327\u0323b |
| 92 |
|
| 93 |
&\x01 |
| 94 |
<<<\U0001D165=¹ # musical stem (ccc=216) |
| 95 |
<<<\U0001D16D=² # musical augmentation dot (ccc=226) |
| 96 |
<<<\U0001D165\U0001D16D=³ # stem+dot (ccc=216 226) |
| 97 |
&\u0301=❶ # acute (ccc=230) |
| 98 |
&\u030a=❷ # ring (ccc=230) |
| 99 |
&\u0308=❸ # diaeresis (ccc=230) |
| 100 |
<<\u0308\u0301=❹ # diaeresis+acute (=dialytika tonos) (ccc=230 230) |
| 101 |
&\u0327=❺ # cedilla (ccc=202) |
| 102 |
&\u0323=❻ # dot below (ccc=220) |
| 103 |
&\u0331=❼ # macron below (ccc=220) |
| 104 |
<<\u0331\u0358=❽ # macron below+dot above right (ccc=220 232) |
| 105 |
&\u0334=❾ # tilde overlay (ccc=1) |
| 106 |
&\u0358=❿ # dot above right (ccc=232) |
| 107 |
|
| 108 |
&\u0f71=① # tibetan vowel sign aa |
| 109 |
&\u0f72=② # tibetan vowel sign i |
| 110 |
# \u0f71\u0f72 # tibetan vowel sign aa + i = ii = U+0F73 |
| 111 |
&\u0f73=③ # tibetan vowel sign ii (ccc=0 but lccc=129) |
| 112 |
|
| 113 |
** test: simple contractions |
| 114 |
|
| 115 |
# Some strings are chosen to cause incremental contiguous contraction matching to |
| 116 |
# go into partial matches for prefixes of contractions |
| 117 |
# (where the prefixes are deliberately not also contractions). |
| 118 |
# When there is no complete match, then the matching code must back out of those |
| 119 |
# so that discontiguous contractions work as specified. |
| 120 |
|
| 121 |
* compare |
| 122 |
# contraction starter with no following text, or mismatch, or blocked |
| 123 |
<1 a |
| 124 |
= ⓐ |
| 125 |
<1 aa |
| 126 |
= ⓐⓐ |
| 127 |
<1 ab |
| 128 |
= ⓐb |
| 129 |
<1 az |
| 130 |
= ⓐz |
| 131 |
|
| 132 |
* compare |
| 133 |
<1 a |
| 134 |
<2 a\u0308\u030a # ring blocked by diaeresis |
| 135 |
= ⓐ❸❷ |
| 136 |
<2 a\u0327 |
| 137 |
= ⓐ❺ |
| 138 |
|
| 139 |
* compare |
| 140 |
<2 \u0308 |
| 141 |
= ❸ |
| 142 |
<2 \u0308\u030a\u0301 # acute blocked by ring |
| 143 |
= ❸❷❶ |
| 144 |
|
| 145 |
* compare |
| 146 |
<1 \U0001D158 |
| 147 |
= ⁰ |
| 148 |
<1 \U0001D158\U0001D165 |
| 149 |
= ¼ |
| 150 |
|
| 151 |
# no discontiguous contraction because of missing prefix contraction d+z, |
| 152 |
# and a starter ('z') after the 'd' |
| 153 |
* compare |
| 154 |
<1 dz\u0323\u0301 |
| 155 |
= dz❻❶ |
| 156 |
|
| 157 |
# contiguous contractions |
| 158 |
* compare |
| 159 |
<1 abz |
| 160 |
= ⓐⓑ |
| 161 |
<1 abzz |
| 162 |
= ⓐⓑz |
| 163 |
|
| 164 |
* compare |
| 165 |
<1 a |
| 166 |
<1 z |
| 167 |
<1 a\u0301 |
| 168 |
= Ⓐ |
| 169 |
<1 a\u0301\u0301 |
| 170 |
= Ⓑ |
| 171 |
<1 a\u0301\u0301\u0358 |
| 172 |
= Ⓒ |
| 173 |
<1 a\u030a |
| 174 |
= Ⓓ |
| 175 |
<1 a\u0323\u0358 |
| 176 |
= Ⓕ |
| 177 |
<1 a\u0327\u0323\u030a # match despite missing prefix |
| 178 |
= Ⓖ |
| 179 |
<1 a\u0327\u0323bz |
| 180 |
= Ⓗ |
| 181 |
|
| 182 |
* compare |
| 183 |
<2 \u0308\u0308\u0301 # acute blocked from first diaeresis, contracts with second |
| 184 |
= ❸❹ |
| 185 |
|
| 186 |
* compare |
| 187 |
<1 \U0001D158\U0001D165 |
| 188 |
= ¼ |
| 189 |
|
| 190 |
* compare |
| 191 |
<3 \U0001D165\U0001D16D |
| 192 |
= ³ |
| 193 |
|
| 194 |
** test: discontiguous contractions |
| 195 |
* compare |
| 196 |
<1 a\u0327\u030a # a+ring skips cedilla |
| 197 |
= Ⓓ❺ |
| 198 |
<2 a\u0327\u0327\u030a # a+ring skips 2 cedillas |
| 199 |
= Ⓓ❺❺ |
| 200 |
<2 a\u0327\u0327\u0327\u030a # a+ring skips 3 cedillas |
| 201 |
= Ⓓ❺❺❺ |
| 202 |
<2 a\u0334\u0327\u0327\u030a # a+ring skips tilde overlay & 2 cedillas |
| 203 |
= Ⓓ❾❺❺ |
| 204 |
<1 a\u0327\u0323 # a+dot below skips cedilla |
| 205 |
= Ⓔ❺ |
| 206 |
<1 a\u0323\u0301\u0358 # a+dot below+dot ab.r.: 2-char match, then skips acute |
| 207 |
= Ⓕ❶ |
| 208 |
<2 a\u0334\u0323\u0358 # a+dot below skips tilde overlay |
| 209 |
= Ⓕ❾ |
| 210 |
|
| 211 |
* compare |
| 212 |
<2 \u0331\u0331\u0358 # macron below+dot ab.r. skips the second macron below |
| 213 |
= ❽❼ |
| 214 |
|
| 215 |
* compare |
| 216 |
<1 a\u0327\u0331\u0323\u030a # a+ring skips cedilla, macron below, dot below (dot blocked by macron) |
| 217 |
= Ⓓ❺❼❻ |
| 218 |
<1 a\u0327\u0323\U0001D16D\u030a # a+dot below skips cedilla |
| 219 |
= Ⓔ❺²❷ |
| 220 |
<2 a\u0327\u0327\u0323\u030a # a+dot below skips 2 cedillas |
| 221 |
= Ⓔ❺❺❷ |
| 222 |
<2 a\u0327\u0323\u0323\u030a # a+dot below skips cedilla |
| 223 |
= Ⓔ❺❻❷ |
| 224 |
<2 a\u0334\u0327\u0323\u030a # a+dot below skips tilde overlay & cedilla |
| 225 |
= Ⓔ❾❺❷ |
| 226 |
|
| 227 |
* compare |
| 228 |
<1 \U0001D158\u0327\U0001D165 # quarter note skips cedilla |
| 229 |
= ¼❺ |
| 230 |
<1 a\U0001D165\u0323 # a+dot below skips stem |
| 231 |
= Ⓔ¹ |
| 232 |
|
| 233 |
# partial contiguous match, backs up, matches discontiguous contraction |
| 234 |
<1 a\u0327\u0323b |
| 235 |
= Ⓔ❺b |
| 236 |
<1 a\u0327\u0323ba |
| 237 |
= Ⓔ❺bⓐ |
| 238 |
|
| 239 |
# a+acute+acute+dot above right skips cedilla, continues matching 2 same-ccc combining marks |
| 240 |
* compare |
| 241 |
<1 a\u0327\u0301\u0301\u0358 |
| 242 |
= Ⓒ❺ |
| 243 |
|
| 244 |
# FCD but not NFD |
| 245 |
* compare |
| 246 |
<1 a\u0f73\u0301 # a+acute skips tibetan ii |
| 247 |
= Ⓐ③ |
| 248 |
|
| 249 |
# FCD but the 0f71 inside the 0f73 must be skipped |
| 250 |
# to match the discontiguous contraction of the first 0f71 with the trailing 0f72 inside the 0f73 |
| 251 |
* compare |
| 252 |
<1 \u0f71\u0f73 # == \u0f73\u0f71 == \u0f71\u0f71\u0f72 |
| 253 |
= ③① |
| 254 |
|
| 255 |
** test: discontiguous contractions with nested contractions |
| 256 |
* compare |
| 257 |
<1 a\u0323\u0308\u0301\u0358 |
| 258 |
= Ⓕ❹ |
| 259 |
<2 a\u0323\u0308\u0301\u0308\u0301\u0358 |
| 260 |
= Ⓕ❹❹ |
| 261 |
|
| 262 |
** test: discontiguous contractions with interleaved contractions |
| 263 |
* compare |
| 264 |
# a+ring & cedilla & macron below+dot above right |
| 265 |
<1 a\u0327\u0331\u030a\u0358 |
| 266 |
= Ⓓ❺❽ |
| 267 |
|
| 268 |
# a+ring & 1x..3x macron below+dot above right |
| 269 |
<2 a\u0331\u030a\u0358 |
| 270 |
= Ⓓ❽ |
| 271 |
<2 a\u0331\u0331\u030a\u0358\u0358 |
| 272 |
= Ⓓ❽❽ |
| 273 |
# also skips acute |
| 274 |
<2 a\u0331\u0331\u0331\u030a\u0301\u0358\u0358\u0358 |
| 275 |
= Ⓓ❽❽❽❶ |
| 276 |
|
| 277 |
# a+dot below & stem+augmentation dot, followed by contiguous d+z+acute |
| 278 |
<1 a\U0001D165\u0323\U0001D16Ddz\u0301 |
| 279 |
= Ⓔ³ⓓ |
| 280 |
|
| 281 |
** test: some simple string comparisons |
| 282 |
@ root |
| 283 |
* compare |
| 284 |
# first string compares against "" |
| 285 |
= \u0000 |
| 286 |
< a |
| 287 |
<1 b |
| 288 |
<3 B |
| 289 |
= \u0000B\u0000 |
| 290 |
|
| 291 |
** test: compare with strength=primary |
| 292 |
% strength=primary |
| 293 |
* compare |
| 294 |
<1 a |
| 295 |
<1 b |
| 296 |
= B |
| 297 |
|
| 298 |
** test: compare with strength=secondary |
| 299 |
% strength=secondary |
| 300 |
* compare |
| 301 |
<1 a |
| 302 |
<1 b |
| 303 |
= B |
| 304 |
|
| 305 |
** test: compare with strength=tertiary |
| 306 |
% strength=tertiary |
| 307 |
* compare |
| 308 |
<1 a |
| 309 |
<1 b |
| 310 |
<3 B |
| 311 |
|
| 312 |
** test: compare with strength=quaternary |
| 313 |
% strength=quaternary |
| 314 |
* compare |
| 315 |
<1 a |
| 316 |
<1 b |
| 317 |
<3 B |
| 318 |
|
| 319 |
** test: compare with strength=identical |
| 320 |
% strength=identical |
| 321 |
* compare |
| 322 |
<1 a |
| 323 |
<1 b |
| 324 |
<3 B |
| 325 |
|
| 326 |
** test: côté with forwards secondary |
| 327 |
@ root |
| 328 |
* compare |
| 329 |
<1 cote |
| 330 |
<2 coté |
| 331 |
<2 côte |
| 332 |
<2 côté |
| 333 |
|
| 334 |
** test: côté with forwards secondary vs. U+FFFE merge separator |
| 335 |
# Merged sort keys: On each level, any difference in the first segment |
| 336 |
# must trump any further difference. |
| 337 |
* compare |
| 338 |
<1 cote\uFFFEcôté |
| 339 |
<2 coté\uFFFEcôte |
| 340 |
<2 côte\uFFFEcoté |
| 341 |
<2 côté\uFFFEcote |
| 342 |
|
| 343 |
** test: côté with backwards secondary |
| 344 |
% backwards=on |
| 345 |
* compare |
| 346 |
<1 cote |
| 347 |
<2 côte |
| 348 |
<2 coté |
| 349 |
<2 côté |
| 350 |
|
| 351 |
** test: côté with backwards secondary vs. U+FFFE merge separator |
| 352 |
# Merged sort keys: On each level, any difference in the first segment |
| 353 |
# must trump any further difference. |
| 354 |
* compare |
| 355 |
<1 cote\uFFFEcôté |
| 356 |
<2 côte\uFFFEcoté |
| 357 |
<2 coté\uFFFEcôte |
| 358 |
<2 côté\uFFFEcote |
| 359 |
|
| 360 |
** test: U+FFFE on identical level |
| 361 |
@ root |
| 362 |
% strength=identical |
| 363 |
* compare |
| 364 |
# All of these control codes are completely-ignorable, so that |
| 365 |
# their low code points are compared with the merge separator. |
| 366 |
# The merge separator must compare less than any other character. |
| 367 |
<1 \uFFFE\u0001\u0002\u0003 |
| 368 |
<i \u0001\uFFFE\u0002\u0003 |
| 369 |
<i \u0001\u0002\uFFFE\u0003 |
| 370 |
<i \u0001\u0002\u0003\uFFFE |
| 371 |
|
| 372 |
* compare |
| 373 |
# The merge separator must even compare less than U+0000. |
| 374 |
<1 \uFFFE\u0000\u0000 |
| 375 |
<i \u0000\uFFFE\u0000 |
| 376 |
<i \u0000\u0000\uFFFE |
| 377 |
|
| 378 |
** test: Hani < surrogates < U+FFFD |
| 379 |
# Note: compareUTF8() treats unpaired surrogates like U+FFFD, |
| 380 |
# so with that the strings with surrogates will compare equal to each other |
| 381 |
# and equal to the string with U+FFFD. |
| 382 |
@ root |
| 383 |
% strength=identical |
| 384 |
* compare |
| 385 |
<1 abz |
| 386 |
<1 a\u4e00z |
| 387 |
<1 a\U00020000z |
| 388 |
<1 a\ud800z |
| 389 |
<1 a\udbffz |
| 390 |
<1 a\udc00z |
| 391 |
<1 a\udfffz |
| 392 |
<1 a\ufffdz |
| 393 |
|
| 394 |
** test: script reordering |
| 395 |
@ root |
| 396 |
% reorder Hani Zzzz digit |
| 397 |
* compare |
| 398 |
<1 ? |
| 399 |
<1 + |
| 400 |
<1 丂 |
| 401 |
<1 a |
| 402 |
<1 α |
| 403 |
<1 5 |
| 404 |
|
| 405 |
% reorder default |
| 406 |
* compare |
| 407 |
<1 ? |
| 408 |
<1 + |
| 409 |
<1 5 |
| 410 |
<1 a |
| 411 |
<1 α |
| 412 |
<1 丂 |
| 413 |
|
| 414 |
** test: empty rules |
| 415 |
@ rules |
| 416 |
* compare |
| 417 |
<1 a |
| 418 |
<2 ä |
| 419 |
<3 Ä |
| 420 |
<1 b |
| 421 |
|
| 422 |
** test: very simple rules |
| 423 |
@ rules |
| 424 |
&a=e<<<<q<<<<r<x<<<X<<y<<<Y;z,Z |
| 425 |
% strength=quaternary |
| 426 |
* compare |
| 427 |
<1 a |
| 428 |
= e |
| 429 |
<4 q |
| 430 |
<4 r |
| 431 |
<1 x |
| 432 |
<3 X |
| 433 |
<2 y |
| 434 |
<3 Y |
| 435 |
<2 z |
| 436 |
<3 Z |
| 437 |
|
| 438 |
** test: tailoring twice before a root position: primary |
| 439 |
@ rules |
| 440 |
&[before 1]b<p |
| 441 |
&[before 1]b<q |
| 442 |
* compare |
| 443 |
<1 a |
| 444 |
<1 p |
| 445 |
<1 q |
| 446 |
<1 b |
| 447 |
|
| 448 |
** test: tailoring twice before a root position: secondary |
| 449 |
@ rules |
| 450 |
&[before 2]ſ<<p |
| 451 |
&[before 2]ſ<<q |
| 452 |
* compare |
| 453 |
<1 s |
| 454 |
<2 p |
| 455 |
<2 q |
| 456 |
<2 ſ |
| 457 |
|
| 458 |
# secondary-before common weight |
| 459 |
@ rules |
| 460 |
&[before 2]b<<p |
| 461 |
&[before 2]b<<q |
| 462 |
* compare |
| 463 |
<1 a |
| 464 |
<1 p |
| 465 |
<2 q |
| 466 |
<2 b |
| 467 |
|
| 468 |
** test: tailoring twice before a root position: tertiary |
| 469 |
@ rules |
| 470 |
&[before 3]B<<<p |
| 471 |
&[before 3]B<<<q |
| 472 |
* compare |
| 473 |
<1 b |
| 474 |
<3 p |
| 475 |
<3 q |
| 476 |
<3 B |
| 477 |
|
| 478 |
# tertiary-before common weight |
| 479 |
@ rules |
| 480 |
&[before 3]b<<<p |
| 481 |
&[before 3]b<<<q |
| 482 |
* compare |
| 483 |
<1 a |
| 484 |
<1 p |
| 485 |
<3 q |
| 486 |
<3 b |
| 487 |
|
| 488 |
@ rules |
| 489 |
&[before 2]b<<s |
| 490 |
&[before 3]s<<<p |
| 491 |
&[before 3]s<<<q |
| 492 |
* compare |
| 493 |
<1 a |
| 494 |
<1 p |
| 495 |
<3 q |
| 496 |
<3 s |
| 497 |
<2 b |
| 498 |
|
| 499 |
** test: tailor after completely ignorable |
| 500 |
@ rules |
| 501 |
&\x00<<<x<<y |
| 502 |
* compare |
| 503 |
= \x00 |
| 504 |
= \x1F |
| 505 |
<3 x |
| 506 |
<2 y |
| 507 |
|
| 508 |
** test: secondary tailoring gaps, ICU ticket 9362 |
| 509 |
@ rules |
| 510 |
&[before 2]s<<'_' |
| 511 |
&s<<r # secondary between s and ſ (long s) |
| 512 |
&ſ<<*a-q # more than 15 between ſ and secondary CE boundary |
| 513 |
&[before 2][first primary ignorable]<<u<<v # between secondary CE boundary & lowest secondary CE |
| 514 |
&[last primary ignorable]<<y<<z |
| 515 |
|
| 516 |
* compare |
| 517 |
<2 u |
| 518 |
<2 v |
| 519 |
<2 \u0332 # lowest secondary CE |
| 520 |
<2 \u0308 |
| 521 |
<2 y |
| 522 |
<2 z |
| 523 |
<1 s_ |
| 524 |
<2 ss |
| 525 |
<2 sr |
| 526 |
<2 sſ |
| 527 |
<2 sa |
| 528 |
<2 sb |
| 529 |
<2 sp |
| 530 |
<2 sq |
| 531 |
<2 sus |
| 532 |
<2 svs |
| 533 |
<2 rs |
| 534 |
|
| 535 |
** test: tertiary tailoring gaps, ICU ticket 9362 |
| 536 |
@ rules |
| 537 |
&[before 3]t<<<'_' |
| 538 |
&t<<<r # tertiary between t and fullwidth t |
| 539 |
&ᵀ<<<*a-q # more than 15 between ᵀ (modifier letter T) and tertiary CE boundary |
| 540 |
&[before 3][first secondary ignorable]<<<u<<<v # between tertiary CE boundary & lowest tertiary CE |
| 541 |
&[last secondary ignorable]<<<y<<<z |
| 542 |
|
| 543 |
* compare |
| 544 |
<3 u |
| 545 |
<3 v |
| 546 |
# Note: The root collator currently does not map any characters to tertiary CEs. |
| 547 |
<3 y |
| 548 |
<3 z |
| 549 |
<1 t_ |
| 550 |
<3 tt |
| 551 |
<3 tr |
| 552 |
<3 tt |
| 553 |
<3 tᵀ |
| 554 |
<3 ta |
| 555 |
<3 tb |
| 556 |
<3 tp |
| 557 |
<3 tq |
| 558 |
<3 tut |
| 559 |
<3 tvt |
| 560 |
<3 rt |
| 561 |
|
| 562 |
** test: secondary & tertiary around root character |
| 563 |
@ rules |
| 564 |
&[before 2]m<<r |
| 565 |
&m<<s |
| 566 |
&[before 3]m<<<u |
| 567 |
&m<<<v |
| 568 |
* compare |
| 569 |
<1 l |
| 570 |
<1 r |
| 571 |
<2 u |
| 572 |
<3 m |
| 573 |
<3 v |
| 574 |
<2 s |
| 575 |
<1 n |
| 576 |
|
| 577 |
** test: secondary & tertiary around tailored item |
| 578 |
@ rules |
| 579 |
&m<x |
| 580 |
&[before 2]x<<r |
| 581 |
&x<<s |
| 582 |
&[before 3]x<<<u |
| 583 |
&x<<<v |
| 584 |
* compare |
| 585 |
<1 m |
| 586 |
<1 r |
| 587 |
<2 u |
| 588 |
<3 x |
| 589 |
<3 v |
| 590 |
<2 s |
| 591 |
<1 n |
| 592 |
|
| 593 |
** test: more nesting of secondary & tertiary before |
| 594 |
@ rules |
| 595 |
&[before 3]m<<<u |
| 596 |
&[before 2]m<<r |
| 597 |
&[before 3]r<<<q |
| 598 |
&m<<<w |
| 599 |
&m<<t |
| 600 |
&[before 3]w<<<v |
| 601 |
&w<<<x |
| 602 |
&w<<s |
| 603 |
* compare |
| 604 |
<1 l |
| 605 |
<1 q |
| 606 |
<3 r |
| 607 |
<2 u |
| 608 |
<3 m |
| 609 |
<3 v |
| 610 |
<3 w |
| 611 |
<3 x |
| 612 |
<2 s |
| 613 |
<2 t |
| 614 |
<1 n |
| 615 |
|
| 616 |
** test: case bits |
| 617 |
@ rules |
| 618 |
&w<x # tailored CE getting case bits |
| 619 |
=uv=uV=Uv=UV # 2 chars -> 1 CE |
| 620 |
&ae=ch=cH=Ch=CH # 2 chars -> 2 CEs |
| 621 |
&rst=yz=yZ=Yz=YZ # 2 chars -> 3 CEs |
| 622 |
% caseFirst=lower |
| 623 |
* compare |
| 624 |
<1 ae |
| 625 |
= ch |
| 626 |
<3 cH |
| 627 |
<3 Ch |
| 628 |
<3 CH |
| 629 |
<1 rst |
| 630 |
= yz |
| 631 |
<3 yZ |
| 632 |
<3 Yz |
| 633 |
<3 YZ |
| 634 |
<1 w |
| 635 |
<1 x |
| 636 |
= uv |
| 637 |
<3 uV |
| 638 |
= Uv # mixed case on single CE cannot distinguish variations |
| 639 |
<3 UV |
| 640 |
|
| 641 |
** test: tertiary CEs, tertiary, caseLevel=off, caseFirst=lower |
| 642 |
@ rules |
| 643 |
&\u0001<<<t<<<T # tertiary CEs |
| 644 |
% caseFirst=lower |
| 645 |
* compare |
| 646 |
<1 aa |
| 647 |
<3 aat |
| 648 |
<3 aaT |
| 649 |
<3 aA |
| 650 |
<3 aAt |
| 651 |
<3 ata |
| 652 |
<3 aTa |
| 653 |
|
| 654 |
** test: tertiary CEs, tertiary, caseLevel=off, caseFirst=upper |
| 655 |
% caseFirst=upper |
| 656 |
* compare |
| 657 |
<1 aA |
| 658 |
<3 aAt |
| 659 |
<3 aa |
| 660 |
<3 aat |
| 661 |
<3 aaT |
| 662 |
<3 ata |
| 663 |
<3 aTa |
| 664 |
|
| 665 |
** test: reset on expansion, ICU tickets 9415 & 9593 |
| 666 |
@ rules |
| 667 |
&æ<x # tailor the last primary CE so that x sorts between ae and af |
| 668 |
&æb=bæ # copy all reset CEs to make bæ sort the same |
| 669 |
&각<h # copy/tailor 3 CEs to make h sort before the next Hangul syllable 갂 |
| 670 |
&⒀<<y # copy/tailor 4 CEs to make y sort with only a secondary difference |
| 671 |
&l·=z # handle the pre-context for · when fetching reset CEs |
| 672 |
<<u # copy/tailor 2 CEs |
| 673 |
|
| 674 |
* compare |
| 675 |
<1 ae |
| 676 |
<2 æ |
| 677 |
<1 x |
| 678 |
<1 af |
| 679 |
|
| 680 |
* compare |
| 681 |
<1 aeb |
| 682 |
<2 æb |
| 683 |
= bæ |
| 684 |
|
| 685 |
* compare |
| 686 |
<1 각 |
| 687 |
<1 h |
| 688 |
<1 갂 |
| 689 |
<1 갃 |
| 690 |
|
| 691 |
* compare |
| 692 |
<1 · # by itself: primary CE |
| 693 |
<1 l |
| 694 |
<2 l· # l+middle dot has only a secondary difference from l |
| 695 |
= z |
| 696 |
<2 u |
| 697 |
|
| 698 |
* compare |
| 699 |
<1 (13) |
| 700 |
<3 ⒀ # DUCET sets special tertiary weights in all CEs |
| 701 |
<2 y |
| 702 |
<1 (13[ |
| 703 |
|
| 704 |
% alternate=shifted |
| 705 |
* compare |
| 706 |
<1 (13) |
| 707 |
= 13 |
| 708 |
<3 ⒀ |
| 709 |
= y # alternate=shifted removes the tailoring difference on the last CE |
| 710 |
<1 14 |
| 711 |
|
| 712 |
** test: contraction inside extension, ICU ticket 9378 |
| 713 |
@ rules |
| 714 |
&а<<х/й # all letters are Cyrillic |
| 715 |
* compare |
| 716 |
<1 ай |
| 717 |
<2 х |
| 718 |
|
| 719 |
** test: no duplicate tailored CEs for different reset positions with same CEs, ICU ticket 10104 |
| 720 |
@ rules |
| 721 |
&t<x &ᵀ<y # same primary weights |
| 722 |
&q<u &[before 1]ꝗ<v # q and ꝗ are primary adjacent |
| 723 |
* compare |
| 724 |
<1 q |
| 725 |
<1 u |
| 726 |
<1 v |
| 727 |
<1 ꝗ |
| 728 |
<1 t |
| 729 |
<3 ᵀ |
| 730 |
<1 y |
| 731 |
<1 x |
| 732 |
|
| 733 |
# Principle: Each rule builds on the state of preceding rules and ignores following rules. |
| 734 |
|
| 735 |
** test: later rule does not affect earlier reset position, ICU ticket 10105 |
| 736 |
@ rules |
| 737 |
&a < u < v < w &ov < x &b < v |
| 738 |
* compare |
| 739 |
<1 oa |
| 740 |
<1 ou |
| 741 |
<1 x # CE(o) followed by CE between u and w |
| 742 |
<1 ow |
| 743 |
<1 ob |
| 744 |
<1 ov |
| 745 |
|
| 746 |
** test: later rule does not affect earlier extension (1), ICU ticket 10105 |
| 747 |
@ rules |
| 748 |
&a=x/b &v=b |
| 749 |
% strength=secondary |
| 750 |
* compare |
| 751 |
<1 B |
| 752 |
<1 c |
| 753 |
<1 v |
| 754 |
= b |
| 755 |
* compare |
| 756 |
<1 AB |
| 757 |
= x |
| 758 |
<1 ac |
| 759 |
<1 av |
| 760 |
= ab |
| 761 |
|
| 762 |
** test: later rule does not affect earlier extension (2), ICU ticket 10105 |
| 763 |
@ rules |
| 764 |
&a <<< c / e &g <<< e / l |
| 765 |
% strength=secondary |
| 766 |
* compare |
| 767 |
<1 AE |
| 768 |
= c |
| 769 |
<2 æ |
| 770 |
<1 agl |
| 771 |
= ae |
| 772 |
|
| 773 |
** test: later rule does not affect earlier extension (3), ICU ticket 10105 |
| 774 |
@ rules |
| 775 |
&a = b / c &d = c / e |
| 776 |
% strength=secondary |
| 777 |
* compare |
| 778 |
<1 AC # C is still only tertiary different from the original c |
| 779 |
= b |
| 780 |
<1 ade |
| 781 |
= ac |
| 782 |
|
| 783 |
** test: extension contains tailored character, ICU ticket 10105 |
| 784 |
@ rules |
| 785 |
&a=e &b=u/e |
| 786 |
* compare |
| 787 |
<1 a |
| 788 |
= e |
| 789 |
<1 ba |
| 790 |
= be |
| 791 |
= u |
| 792 |
|
| 793 |
** test: add simple mappings for characters with root context |
| 794 |
@ rules |
| 795 |
&z=· # middle dot has a prefix mapping in the CLDR root |
| 796 |
&n=и # и (U+0438) has contractions in the root |
| 797 |
* compare |
| 798 |
<1 l |
| 799 |
<2 l· # root mapping for l|· still works |
| 800 |
<1 z |
| 801 |
= · |
| 802 |
* compare |
| 803 |
<1 n |
| 804 |
= и |
| 805 |
<1 И |
| 806 |
<1 и\u0306 # root mapping for й=и\u0306 still works |
| 807 |
= й |
| 808 |
<3 Й |
| 809 |
|
| 810 |
** test: add context mappings around characters with root context |
| 811 |
@ rules |
| 812 |
&z=·h # middle dot has a prefix mapping in the CLDR root |
| 813 |
&n=ә|и # и (U+0438) has contractions in the root |
| 814 |
* compare |
| 815 |
<1 l |
| 816 |
<2 l· # root mapping for l|· still works |
| 817 |
<1 z |
| 818 |
= ·h |
| 819 |
* compare |
| 820 |
<1 и |
| 821 |
<3 И |
| 822 |
<1 и\u0306 # root mapping for й=и\u0306 still works |
| 823 |
= й |
| 824 |
* compare |
| 825 |
<1 әn |
| 826 |
= әи |
| 827 |
<1 әo |
| 828 |
|
| 829 |
** test: many secondary CEs at the top of their range |
| 830 |
@ rules |
| 831 |
&[last primary ignorable]<<*\u2801-\u28ff |
| 832 |
* compare |
| 833 |
<2 \u0308 |
| 834 |
<2 \u2801 |
| 835 |
<2 \u2802 |
| 836 |
<2 \u2803 |
| 837 |
<2 \u2804 |
| 838 |
<2 \u28fd |
| 839 |
<2 \u28fe |
| 840 |
<2 \u28ff |
| 841 |
<1 \x20 |
| 842 |
|
| 843 |
** test: many tertiary CEs at the top of their range |
| 844 |
@ rules |
| 845 |
&[last secondary ignorable]<<<*a-z |
| 846 |
* compare |
| 847 |
<3 a |
| 848 |
<3 b |
| 849 |
<3 c |
| 850 |
<3 d |
| 851 |
# e..w |
| 852 |
<3 x |
| 853 |
<3 y |
| 854 |
<3 z |
| 855 |
<2 \u0308 |
| 856 |
|
| 857 |
** test: tailor contraction together with nearly equivalent prefix, ICU ticket 10101 |
| 858 |
@ rules |
| 859 |
&a=p|x &b=px &c=op |
| 860 |
* compare |
| 861 |
<1 b |
| 862 |
= px |
| 863 |
<3 B |
| 864 |
<1 c |
| 865 |
= op |
| 866 |
<3 C |
| 867 |
* compare |
| 868 |
<1 ca |
| 869 |
= opx # first contraction op, then prefix p|x |
| 870 |
<3 cA |
| 871 |
<3 Ca |
| 872 |
|
| 873 |
** test: reset position with prefix (pre-context), ICU ticket 10102 |
| 874 |
@ rules |
| 875 |
&a=p|x &px=y |
| 876 |
* compare |
| 877 |
<1 pa |
| 878 |
= px |
| 879 |
= y |
| 880 |
<3 pA |
| 881 |
<1 q |
| 882 |
<1 x |
| 883 |
|
| 884 |
** test: prefix+contraction together (1), ICU ticket 10071 |
| 885 |
@ rules |
| 886 |
&x=a|bc |
| 887 |
* compare |
| 888 |
<1 ab |
| 889 |
<1 Abc |
| 890 |
<1 abd |
| 891 |
<1 ac |
| 892 |
<1 aw |
| 893 |
<1 ax |
| 894 |
= abc |
| 895 |
<3 aX |
| 896 |
<3 Ax |
| 897 |
<1 b |
| 898 |
<1 bb |
| 899 |
<1 bc |
| 900 |
<3 bC |
| 901 |
<3 Bc |
| 902 |
<1 bd |
| 903 |
|
| 904 |
** test: prefix+contraction together (2), ICU ticket 10071 |
| 905 |
@ rules |
| 906 |
&w=bc &x=a|b |
| 907 |
* compare |
| 908 |
<1 w |
| 909 |
= bc |
| 910 |
<3 W |
| 911 |
* compare |
| 912 |
<1 aw |
| 913 |
<1 ax |
| 914 |
= ab |
| 915 |
<3 aX |
| 916 |
<1 axb |
| 917 |
<1 axc |
| 918 |
= abc # prefix match a|b takes precedence over contraction match bc |
| 919 |
<3 abC |
| 920 |
<1 abd |
| 921 |
<1 ay |
| 922 |
|
| 923 |
** test: prefix+contraction together (3), ICU ticket 10071 |
| 924 |
@ rules |
| 925 |
&x=a|b &w=bc # reverse order of rules as previous test, order should not matter here |
| 926 |
* compare # same "compare" sequences as previous test |
| 927 |
<1 w |
| 928 |
= bc |
| 929 |
<3 W |
| 930 |
* compare |
| 931 |
<1 aw |
| 932 |
<1 ax |
| 933 |
= ab |
| 934 |
<3 aX |
| 935 |
<1 axb |
| 936 |
<1 axc |
| 937 |
= abc # prefix match a|b takes precedence over contraction match bc |
| 938 |
<3 abC |
| 939 |
<1 abd |
| 940 |
<1 ay |
| 941 |
|
| 942 |
** test: no mapping p|c, falls back to contraction ch, CLDR ticket 5962 |
| 943 |
@ rules |
| 944 |
&d=ch &v=p|ci |
| 945 |
* compare |
| 946 |
<1 pc |
| 947 |
<3 pC |
| 948 |
<1 pcH |
| 949 |
<1 pcI |
| 950 |
<1 pd |
| 951 |
= pch # no-prefix contraction ch matches |
| 952 |
<3 pD |
| 953 |
<1 pv |
| 954 |
= pci # prefix+contraction p|ci matches |
| 955 |
<3 pV |
| 956 |
|
| 957 |
** test: tailor in & around compact ranges of root primaries |
| 958 |
# The Ogham characters U+1681..U+169A are in simple ascending order of primary CEs |
| 959 |
# which should be reliably encoded as one range in the root elements data. |
| 960 |
@ rules |
| 961 |
&[before 1]ᚁ<a |
| 962 |
&ᚁ<b |
| 963 |
&[before 1]ᚂ<c |
| 964 |
&ᚂ<d |
| 965 |
&[before 1]ᚚ<y |
| 966 |
&ᚚ<z |
| 967 |
&[before 2]ᚁ<<r |
| 968 |
&ᚁ<<s |
| 969 |
&[before 3]ᚚ<<<t |
| 970 |
&ᚚ<<<u |
| 971 |
* compare |
| 972 |
<1 ᣵ # U+18F5 last Canadian Aboriginal |
| 973 |
<1 a |
| 974 |
<1 r |
| 975 |
<2 ᚁ |
| 976 |
<2 s |
| 977 |
<1 b |
| 978 |
<1 c |
| 979 |
<1 ᚂ |
| 980 |
<1 d |
| 981 |
<1 ᚃ |
| 982 |
<1 ᚙ |
| 983 |
<1 y |
| 984 |
<1 t |
| 985 |
<3 ᚚ |
| 986 |
<3 u |
| 987 |
<1 z |
| 988 |
<1 ᚠ # U+16A0 first Runic |
| 989 |
|
| 990 |
** test: suppressContractions |
| 991 |
@ rules |
| 992 |
&z<ch<әж [suppressContractions [·cә]] |
| 993 |
* compare |
| 994 |
<1 ch |
| 995 |
<3 cH # ch was suppressed |
| 996 |
<1 l |
| 997 |
<1 l· # primary difference, not secondary, because l|· was suppressed |
| 998 |
<1 ә |
| 999 |
<2 ә\u0308 # secondary difference, not primary, because contractions for ә were suppressed |
| 1000 |
<1 әж |
| 1001 |
<3 әЖ |
| 1002 |
|
| 1003 |
** test: Hangul & Jamo |
| 1004 |
@ rules |
| 1005 |
&L=\u1100 # first Jamo L |
| 1006 |
&V=\u1161 # first Jamo V |
| 1007 |
&T=\u11A8 # first Jamo T |
| 1008 |
&\uAC01<<*\u4E00-\u4EFF # first Hangul LVT syllable & lots of secondary diffs |
| 1009 |
* compare |
| 1010 |
<1 Lv |
| 1011 |
<3 LV |
| 1012 |
= \u1100\u1161 |
| 1013 |
= \uAC00 |
| 1014 |
<1 LVt |
| 1015 |
<3 LVT |
| 1016 |
= \u1100\u1161\u11A8 |
| 1017 |
= \uAC00\u11A8 |
| 1018 |
= \uAC01 |
| 1019 |
<2 LVT\u0308 |
| 1020 |
<2 \u4E00 |
| 1021 |
<2 \u4E01 |
| 1022 |
<2 \u4E80 |
| 1023 |
<2 \u4EFF |
| 1024 |
<2 LV\u0308T |
| 1025 |
<1 \uAC02 |
| 1026 |
|
| 1027 |
** test: adjust special reset positions according to previous rules, CLDR ticket 6070 |
| 1028 |
@ rules |
| 1029 |
&[last variable]<x |
| 1030 |
[maxVariable space] # has effect only after building, no effect on following rules |
| 1031 |
&[last variable]<y |
| 1032 |
&[before 1][first regular]<z |
| 1033 |
* compare |
| 1034 |
<1 ? # some punctuation |
| 1035 |
<1 x |
| 1036 |
<1 y |
| 1037 |
<1 z |
| 1038 |
<1 $ # some symbol |
| 1039 |
|
| 1040 |
@ rules |
| 1041 |
&[last primary ignorable]<<x<<<y |
| 1042 |
&[last primary ignorable]<<z |
| 1043 |
* compare |
| 1044 |
<2 \u0358 |
| 1045 |
<2 x |
| 1046 |
<3 y |
| 1047 |
<2 z |
| 1048 |
<1 \x20 |
| 1049 |
|
| 1050 |
@ rules |
| 1051 |
&[last secondary ignorable]<<<x |
| 1052 |
&[last secondary ignorable]<<<y |
| 1053 |
* compare |
| 1054 |
<3 x |
| 1055 |
<3 y |
| 1056 |
<2 \u0358 |
| 1057 |
|
| 1058 |
@ rules |
| 1059 |
&[before 2][first variable]<<z |
| 1060 |
&[before 2][first variable]<<y |
| 1061 |
&[before 3][first variable]<<<x |
| 1062 |
&[before 3][first variable]<<<w |
| 1063 |
&[before 1][first variable]<v |
| 1064 |
&[before 2][first variable]<<u |
| 1065 |
&[before 3][first variable]<<<t |
| 1066 |
&[before 2]\uFDD1\xA0<<s # FractionalUCA.txt: FDD1 00A0, SPACE first primary |
| 1067 |
* compare |
| 1068 |
<2 \u0358 |
| 1069 |
<1 s |
| 1070 |
<2 \uFDD1\xA0 |
| 1071 |
<1 t |
| 1072 |
<3 u |
| 1073 |
<2 v |
| 1074 |
<1 w |
| 1075 |
<3 x |
| 1076 |
<3 y |
| 1077 |
<2 z |
| 1078 |
<2 \t |
| 1079 |
|
| 1080 |
@ rules |
| 1081 |
&[before 2][first regular]<<z |
| 1082 |
&[before 3][first regular]<<<y |
| 1083 |
&[before 1][first regular]<x |
| 1084 |
&[before 3][first regular]<<<w |
| 1085 |
&[before 2]\uFDD1\u263A<<v # FractionalUCA.txt: FDD1 263A, SYMBOL first primary |
| 1086 |
&[before 3][first regular]<<<u |
| 1087 |
&[before 1][first regular]<p # primary before the boundary: becomes variable |
| 1088 |
&[before 3][first regular]<<<t # not affected by p |
| 1089 |
&[last variable]<q # after p! |
| 1090 |
* compare |
| 1091 |
<1 ? |
| 1092 |
<1 p |
| 1093 |
<1 q |
| 1094 |
<1 t |
| 1095 |
<3 u |
| 1096 |
<3 v |
| 1097 |
<1 w |
| 1098 |
<3 x |
| 1099 |
<1 y |
| 1100 |
<3 z |
| 1101 |
<1 $ |
| 1102 |
|
| 1103 |
# check that p & q are indeed variable |
| 1104 |
% alternate=shifted |
| 1105 |
* compare |
| 1106 |
= ? |
| 1107 |
= p |
| 1108 |
= q |
| 1109 |
<1 t |
| 1110 |
<3 u |
| 1111 |
<3 v |
| 1112 |
<1 w |
| 1113 |
<3 x |
| 1114 |
<1 y |
| 1115 |
<3 z |
| 1116 |
<1 $ |
| 1117 |
|
| 1118 |
@ rules |
| 1119 |
&[before 2][first trailing]<<z |
| 1120 |
&[before 1][first trailing]<y |
| 1121 |
&[before 3][first trailing]<<<x |
| 1122 |
* compare |
| 1123 |
<1 \u4E00 # first Han, first implicit |
| 1124 |
<1 \uFDD1\uFDD0 # FractionalUCA.txt: unassigned first primary |
| 1125 |
# Note: The root collator currently does not map any characters to the trailing first boundary primary. |
| 1126 |
<1 x |
| 1127 |
<3 y |
| 1128 |
<1 z |
| 1129 |
<2 \uFFFD # The root collator currently maps U+FFFD to the first real trailing primary. |
| 1130 |
|
| 1131 |
@ rules |
| 1132 |
&[before 2][first primary ignorable]<<z |
| 1133 |
&[before 2][first primary ignorable]<<y |
| 1134 |
&[before 3][first primary ignorable]<<<x |
| 1135 |
&[before 3][first primary ignorable]<<<w |
| 1136 |
* compare |
| 1137 |
= \x01 |
| 1138 |
<2 w |
| 1139 |
<3 x |
| 1140 |
<3 y |
| 1141 |
<2 z |
| 1142 |
<2 \u0301 |
| 1143 |
|
| 1144 |
@ rules |
| 1145 |
&[before 3][first secondary ignorable]<<<y |
| 1146 |
&[before 3][first secondary ignorable]<<<x |
| 1147 |
* compare |
| 1148 |
= \x01 |
| 1149 |
<3 x |
| 1150 |
<3 y |
| 1151 |
<2 \u0301 |
| 1152 |
|
| 1153 |
** test: canonical closure |
| 1154 |
@ rules |
| 1155 |
&X=A &U=Â |
| 1156 |
* compare |
| 1157 |
<1 U |
| 1158 |
= Â |
| 1159 |
= A\u0302 |
| 1160 |
<2 Ú # U with acute |
| 1161 |
= U\u0301 |
| 1162 |
= Ấ # A with circumflex & acute |
| 1163 |
= Â\u0301 |
| 1164 |
= A\u0302\u0301 |
| 1165 |
<1 X |
| 1166 |
= A |
| 1167 |
<2 X\u030A # with ring above |
| 1168 |
= Å |
| 1169 |
= A\u030A |
| 1170 |
= \u212B # Angstrom sign |
| 1171 |
|
| 1172 |
@ rules |
| 1173 |
&x=\u5140\u55C0 |
| 1174 |
* compare |
| 1175 |
<1 x |
| 1176 |
= \u5140\u55C0 |
| 1177 |
= \u5140\uFA0D |
| 1178 |
= \uFA0C\u55C0 |
| 1179 |
= \uFA0C\uFA0D # CJK compatibility characters |
| 1180 |
<3 X |
| 1181 |
|
| 1182 |
# canonical closure on prefix rules, ICU ticket 9444 |
| 1183 |
@ rules |
| 1184 |
&x=ä|ŝ |
| 1185 |
* compare |
| 1186 |
<1 äs # not tailored |
| 1187 |
<1 äx |
| 1188 |
= äŝ |
| 1189 |
= a\u0308s\u0302 |
| 1190 |
= a\u0308ŝ |
| 1191 |
= äs\u0302 |
| 1192 |
<3 äX |
| 1193 |
|
| 1194 |
** test: conjoining Jamo map to expansions |
| 1195 |
@ rules |
| 1196 |
&gg=\u1101 # Jamo Lead consonant GG |
| 1197 |
&nj=\u11AC # Jamo Trail consonant NJ |
| 1198 |
* compare |
| 1199 |
<1 gg\u1161nj |
| 1200 |
= \u1101\u1161\u11AC |
| 1201 |
= \uAE4C\u11AC |
| 1202 |
= \uAE51 |
| 1203 |
<3 gg\u1161nJ |
| 1204 |
<1 \u1100\u1100 |
| 1205 |
|
| 1206 |
** test: canonical tail closure, ICU ticket 5913 |
| 1207 |
@ rules |
| 1208 |
&a<â |
| 1209 |
* compare |
| 1210 |
<1 a |
| 1211 |
<1 â # tailored |
| 1212 |
= a\u0302 |
| 1213 |
<2 a\u0323\u0302 # discontiguous contraction |
| 1214 |
= ạ\u0302 # equivalent |
| 1215 |
= ậ # equivalent |
| 1216 |
<1 b |
| 1217 |
|
| 1218 |
@ rules |
| 1219 |
&a<ạ |
| 1220 |
* compare |
| 1221 |
<1 a |
| 1222 |
<1 ạ # tailored |
| 1223 |
= a\u0323 |
| 1224 |
<2 a\u0323\u0302 # contiguous contraction plus extra diacritic |
| 1225 |
= ạ\u0302 # equivalent |
| 1226 |
= ậ # equivalent |
| 1227 |
<1 b |
| 1228 |
|
| 1229 |
# Tail closure should work even if there is a prefix and/or contraction. |
| 1230 |
@ rules |
| 1231 |
&a<\u5140|câ |
| 1232 |
# In order to find discontiguous contractions for \u5140|câ |
| 1233 |
# there must exist a mapping for \u5140|ca, regardless of what it maps to. |
| 1234 |
# (This follows from the UCA spec.) |
| 1235 |
&x=\u5140|ca |
| 1236 |
* compare |
| 1237 |
<1 \u5140a |
| 1238 |
= \uFA0Ca |
| 1239 |
<1 \u5140câ # tailored |
| 1240 |
= \uFA0Ccâ |
| 1241 |
= \u5140ca\u0302 |
| 1242 |
= \uFA0Cca\u0302 |
| 1243 |
<2 \u5140ca\u0323\u0302 # discontiguous contraction |
| 1244 |
= \uFA0Cca\u0323\u0302 |
| 1245 |
= \u5140cạ\u0302 |
| 1246 |
= \uFA0Ccạ\u0302 |
| 1247 |
= \u5140cậ |
| 1248 |
= \uFA0Ccậ |
| 1249 |
<1 \u5140b |
| 1250 |
= \uFA0Cb |
| 1251 |
<1 \u5140x |
| 1252 |
= \u5140ca |
| 1253 |
|
| 1254 |
# Double-check that without the extra mapping there will be no discontiguous match. |
| 1255 |
@ rules |
| 1256 |
&a<\u5140|câ |
| 1257 |
* compare |
| 1258 |
<1 \u5140a |
| 1259 |
= \uFA0Ca |
| 1260 |
<1 \u5140câ # tailored |
| 1261 |
= \uFA0Ccâ |
| 1262 |
= \u5140ca\u0302 |
| 1263 |
= \uFA0Cca\u0302 |
| 1264 |
<1 \u5140b |
| 1265 |
= \uFA0Cb |
| 1266 |
<1 \u5140ca\u0323\u0302 # no discontiguous contraction |
| 1267 |
= \uFA0Cca\u0323\u0302 |
| 1268 |
= \u5140cạ\u0302 |
| 1269 |
= \uFA0Ccạ\u0302 |
| 1270 |
= \u5140cậ |
| 1271 |
= \uFA0Ccậ |
| 1272 |
|
| 1273 |
@ rules |
| 1274 |
&a<cạ |
| 1275 |
* compare |
| 1276 |
<1 a |
| 1277 |
<1 cạ # tailored |
| 1278 |
= ca\u0323 |
| 1279 |
<2 ca\u0323\u0302 # contiguous contraction plus extra diacritic |
| 1280 |
= cạ\u0302 # equivalent |
| 1281 |
= cậ # equivalent |
| 1282 |
<1 b |
| 1283 |
|
| 1284 |
# ᾢ = U+1FA2 GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI |
| 1285 |
# = 03C9 0313 0300 0345 |
| 1286 |
# ccc = 0, 230, 230, 240 |
| 1287 |
@ rules |
| 1288 |
&δ=αῳ |
| 1289 |
# In order to find discontiguous contractions for αῳ |
| 1290 |
# there must exist a mapping for αω, regardless of what it maps to. |
| 1291 |
# (This follows from the UCA spec.) |
| 1292 |
&ε=αω |
| 1293 |
* compare |
| 1294 |
<1 δ |
| 1295 |
= αῳ |
| 1296 |
= αω\u0345 |
| 1297 |
<2 αω\u0313\u0300\u0345 # discontiguous contraction |
| 1298 |
= αὠ\u0300\u0345 |
| 1299 |
= αὢ\u0345 |
| 1300 |
= αᾢ |
| 1301 |
<2 αω\u0300\u0313\u0345 |
| 1302 |
= αὼ\u0313\u0345 |
| 1303 |
= αῲ\u0313 # not FCD |
| 1304 |
<1 ε |
| 1305 |
= αω |
| 1306 |
|
| 1307 |
# Double-check that without the extra mapping there will be no discontiguous match. |
| 1308 |
@ rules |
| 1309 |
&δ=αῳ |
| 1310 |
* compare |
| 1311 |
<1 αω\u0313\u0300\u0345 # no discontiguous contraction |
| 1312 |
= αὠ\u0300\u0345 |
| 1313 |
= αὢ\u0345 |
| 1314 |
= αᾢ |
| 1315 |
<2 αω\u0300\u0313\u0345 |
| 1316 |
= αὼ\u0313\u0345 |
| 1317 |
= αῲ\u0313 # not FCD |
| 1318 |
<1 δ |
| 1319 |
= αῳ |
| 1320 |
= αω\u0345 |
| 1321 |
|
| 1322 |
# Add U+0315 COMBINING COMMA ABOVE RIGHT which has ccc=232. |
| 1323 |
# Tests code paths where the tailored string has a combining mark |
| 1324 |
# that does not occur in any composite's decomposition. |
| 1325 |
@ rules |
| 1326 |
&δ=αὼ\u0315 |
| 1327 |
* compare |
| 1328 |
<1 αω\u0313\u0300\u0315 # Not tailored: The grave accent blocks the comma above. |
| 1329 |
= αὠ\u0300\u0315 |
| 1330 |
= αὢ\u0315 |
| 1331 |
<1 δ |
| 1332 |
= αὼ\u0315 |
| 1333 |
= αω\u0300\u0315 |
| 1334 |
<2 αω\u0300\u0315\u0345 |
| 1335 |
= αὼ\u0315\u0345 |
| 1336 |
= αῲ\u0315 # not FCD |
| 1337 |
|
| 1338 |
** test: danish a+a vs. a-umlaut, ICU ticket 9319 |
| 1339 |
@ rules |
| 1340 |
&z<aa |
| 1341 |
* compare |
| 1342 |
<1 z |
| 1343 |
<1 aa |
| 1344 |
<2 aa\u0308 |
| 1345 |
= aä |
| 1346 |
|
| 1347 |
** test: Jamo L with and in prefix |
| 1348 |
# Useful for the Korean "searchjl" tailoring (instead of contractions of pairs of Jamo L). |
| 1349 |
@ rules |
| 1350 |
# Jamo Lead consonant G after G or GG |
| 1351 |
&[last primary ignorable]<<\u1100|\u1100=\u1101|\u1100 |
| 1352 |
# Jamo Lead consonant GG sorts like G+G |
| 1353 |
&\u1100\u1100=\u1101 |
| 1354 |
# Note: Making G|GG and GG|GG sort the same as G|G+G |
| 1355 |
# would require the ability to reset on G|G+G, |
| 1356 |
# or we could make G-after-G equal to some secondary-CE character, |
| 1357 |
# and reset on a pair of those. |
| 1358 |
# (It does not matter much if there are at most two G in a row in real text.) |
| 1359 |
* compare |
| 1360 |
<1 \u1100 |
| 1361 |
<2 \u1100\u1100 # only one primary from a sequence of G lead consonants |
| 1362 |
= \u1101 |
| 1363 |
<2 \u1100\u1100\u1100 |
| 1364 |
= \u1101\u1100 |
| 1365 |
# but not = \u1100\u1101, see above |
| 1366 |
<1 \u1100\u1161 |
| 1367 |
= \uAC00 |
| 1368 |
<2 \u1100\u1100\u1161 |
| 1369 |
= \u1100\uAC00 # prefix match from the L of the LV syllable |
| 1370 |
= \u1101\u1161 |
| 1371 |
= \uAE4C |
| 1372 |
|
| 1373 |
** test: proposed Korean "searchjl" tailoring with prefixes, CLDR ticket 6546 |
| 1374 |
@ rules |
| 1375 |
# Low secondary CEs for Jamo V & T. |
| 1376 |
# Note: T should sort before V for proper syllable order. |
| 1377 |
&\u0332 # COMBINING LOW LINE (first primary ignorable) |
| 1378 |
<<\u1161<<\u1162 |
| 1379 |
|
| 1380 |
# Korean Jamo lead consonant search rules, part 2: |
| 1381 |
# Make modern compound L jamo primary equivalent to non-compound forms. |
| 1382 |
|
| 1383 |
# Secondary CEs for Jamo L-after-L, greater than Jamo V & T. |
| 1384 |
&\u0313 # COMBINING COMMA ABOVE (second primary ignorable) |
| 1385 |
=\u1100|\u1100 |
| 1386 |
=\u1103|\u1103 |
| 1387 |
=\u1107|\u1107 |
| 1388 |
=\u1109|\u1109 |
| 1389 |
=\u110C|\u110C |
| 1390 |
|
| 1391 |
# Compound L Jamo map to equivalent expansions of primary+secondary CE. |
| 1392 |
&\u1100\u0313=\u1101<<<\u3132 # HANGUL CHOSEONG SSANGKIYEOK, HANGUL LETTER SSANGKIYEOK |
| 1393 |
&\u1103\u0313=\u1104<<<\u3138 # HANGUL CHOSEONG SSANGTIKEUT, HANGUL LETTER SSANGTIKEUT |
| 1394 |
&\u1107\u0313=\u1108<<<\u3143 # HANGUL CHOSEONG SSANGPIEUP, HANGUL LETTER SSANGPIEUP |
| 1395 |
&\u1109\u0313=\u110A<<<\u3146 # HANGUL CHOSEONG SSANGSIOS, HANGUL LETTER SSANGSIOS |
| 1396 |
&\u110C\u0313=\u110D<<<\u3149 # HANGUL CHOSEONG SSANGCIEUC, HANGUL LETTER SSANGCIEUC |
| 1397 |
|
| 1398 |
* compare |
| 1399 |
<1 \u1100\u1161 |
| 1400 |
= \uAC00 |
| 1401 |
<2 \u1100\u1162 |
| 1402 |
= \uAC1C |
| 1403 |
<2 \u1100\u1100\u1161 |
| 1404 |
= \u1100\uAC00 |
| 1405 |
= \u1101\u1161 |
| 1406 |
= \uAE4C |
| 1407 |
<3 \u3132\u1161 |
| 1408 |
|
| 1409 |
** test: Hangul syllables in prefix & in the interior of a contraction |
| 1410 |
@ rules |
| 1411 |
&x=\u1100\u1161|a\u1102\u1162z |
| 1412 |
* compare |
| 1413 |
<1 \u1100\u1161x |
| 1414 |
= \u1100\u1161a\u1102\u1162z |
| 1415 |
= \u1100\u1161a\uB0B4z |
| 1416 |
= \uAC00a\u1102\u1162z |
| 1417 |
= \uAC00a\uB0B4z |
| 1418 |
|
| 1419 |
** test: digits are unsafe-backwards when numeric=on |
| 1420 |
@ root |
| 1421 |
% numeric=on |
| 1422 |
* compare |
| 1423 |
# If digits are not unsafe, then numeric collation sees "1"=="01" and "b">"a". |
| 1424 |
# We need to back up before the identical prefix "1" and compare the full numbers. |
| 1425 |
<1 11b |
| 1426 |
<1 101a |
| 1427 |
|
| 1428 |
** test: simple locale data test |
| 1429 |
@ locale de |
| 1430 |
* compare |
| 1431 |
<1 a |
| 1432 |
<2 ä |
| 1433 |
<1 ae |
| 1434 |
<2 æ |
| 1435 |
|
| 1436 |
@ locale de-u-co-phonebk |
| 1437 |
* compare |
| 1438 |
<1 a |
| 1439 |
<1 ae |
| 1440 |
<2 ä |
| 1441 |
<2 æ |
| 1442 |
|
| 1443 |
# The following test cases were moved here from ICU 52's DataDrivenCollationTest.txt. |
| 1444 |
|
| 1445 |
** test: DataDrivenCollationTest/TestMorePinyin |
| 1446 |
# Testing the primary strength. |
| 1447 |
@ locale zh |
| 1448 |
% strength=primary |
| 1449 |
* compare |
| 1450 |
< lā |
| 1451 |
= lĀ |
| 1452 |
= Lā |
| 1453 |
= LĀ |
| 1454 |
< lān |
| 1455 |
= lĀn |
| 1456 |
< lē |
| 1457 |
= lĒ |
| 1458 |
= Lē |
| 1459 |
= LĒ |
| 1460 |
< lēn |
| 1461 |
= lĒn |
| 1462 |
|
| 1463 |
** test: DataDrivenCollationTest/TestLithuanian |
| 1464 |
# Lithuanian sort order. |
| 1465 |
@ locale lt |
| 1466 |
* compare |
| 1467 |
< cz |
| 1468 |
< č |
| 1469 |
< d |
| 1470 |
< iz |
| 1471 |
< j |
| 1472 |
< sz |
| 1473 |
< š |
| 1474 |
< t |
| 1475 |
< zz |
| 1476 |
< ž |
| 1477 |
|
| 1478 |
** test: DataDrivenCollationTest/TestLatvian |
| 1479 |
# Latvian sort order. |
| 1480 |
@ locale lv |
| 1481 |
* compare |
| 1482 |
< cz |
| 1483 |
< č |
| 1484 |
< d |
| 1485 |
< gz |
| 1486 |
< ģ |
| 1487 |
< h |
| 1488 |
< iz |
| 1489 |
< j |
| 1490 |
< kz |
| 1491 |
< ķ |
| 1492 |
< l |
| 1493 |
< lz |
| 1494 |
< ļ |
| 1495 |
< m |
| 1496 |
< nz |
| 1497 |
< ņ |
| 1498 |
< o |
| 1499 |
< rz |
| 1500 |
< ŗ |
| 1501 |
< s |
| 1502 |
< sz |
| 1503 |
< š |
| 1504 |
< t |
| 1505 |
< zz |
| 1506 |
< ž |
| 1507 |
|
| 1508 |
** test: DataDrivenCollationTest/TestEstonian |
| 1509 |
# Estonian sort order. |
| 1510 |
@ locale et |
| 1511 |
* compare |
| 1512 |
< sy |
| 1513 |
< š |
| 1514 |
< šy |
| 1515 |
< z |
| 1516 |
< zy |
| 1517 |
< ž |
| 1518 |
< v |
| 1519 |
< va |
| 1520 |
< w |
| 1521 |
< õ |
| 1522 |
< õy |
| 1523 |
< ä |
| 1524 |
< äy |
| 1525 |
< ö |
| 1526 |
< öy |
| 1527 |
< ü |
| 1528 |
< üy |
| 1529 |
< x |
| 1530 |
|
| 1531 |
** test: DataDrivenCollationTest/TestAlbanian |
| 1532 |
# Albanian sort order. |
| 1533 |
@ locale sq |
| 1534 |
* compare |
| 1535 |
< cz |
| 1536 |
< ç |
| 1537 |
< d |
| 1538 |
< dz |
| 1539 |
< dh |
| 1540 |
< e |
| 1541 |
< ez |
| 1542 |
< ë |
| 1543 |
< f |
| 1544 |
< gz |
| 1545 |
< gj |
| 1546 |
< h |
| 1547 |
< lz |
| 1548 |
< ll |
| 1549 |
< m |
| 1550 |
< nz |
| 1551 |
< nj |
| 1552 |
< o |
| 1553 |
< rz |
| 1554 |
< rr |
| 1555 |
< s |
| 1556 |
< sz |
| 1557 |
< sh |
| 1558 |
< t |
| 1559 |
< tz |
| 1560 |
< th |
| 1561 |
< u |
| 1562 |
< xz |
| 1563 |
< xh |
| 1564 |
< y |
| 1565 |
< zz |
| 1566 |
< zh |
| 1567 |
|
| 1568 |
** test: DataDrivenCollationTest/TestSimplifiedChineseOrder |
| 1569 |
# Sorted file has different order. |
| 1570 |
@ root |
| 1571 |
# normalization=on turned on & off automatically. |
| 1572 |
* compare |
| 1573 |
< \u5F20 |
| 1574 |
< \u5F20\u4E00\u8E3F |
| 1575 |
|
| 1576 |
** test: DataDrivenCollationTest/TestTibetanNormalizedIterativeCrash |
| 1577 |
# This pretty much crashes. |
| 1578 |
@ root |
| 1579 |
* compare |
| 1580 |
< \u0f71\u0f72\u0f80\u0f71\u0f72 |
| 1581 |
< \u0f80 |
| 1582 |
|
| 1583 |
** test: DataDrivenCollationTest/TestThaiPartialSortKeyProblems |
| 1584 |
# These are examples of strings that caused trouble in partial sort key testing. |
| 1585 |
@ locale th-TH |
| 1586 |
* compare |
| 1587 |
< \u0E01\u0E01\u0E38\u0E18\u0E20\u0E31\u0E13\u0E11\u0E4C |
| 1588 |
< \u0E01\u0E01\u0E38\u0E2A\u0E31\u0E19\u0E42\u0E18 |
| 1589 |
* compare |
| 1590 |
< \u0E01\u0E07\u0E01\u0E32\u0E23 |
| 1591 |
< \u0E01\u0E07\u0E42\u0E01\u0E49 |
| 1592 |
* compare |
| 1593 |
< \u0E01\u0E23\u0E19\u0E17\u0E32 |
| 1594 |
< \u0E01\u0E23\u0E19\u0E19\u0E40\u0E0A\u0E49\u0E32 |
| 1595 |
* compare |
| 1596 |
< \u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E22\u0E27 |
| 1597 |
< \u0E01\u0E23\u0E30\u0E40\u0E08\u0E35\u0E4A\u0E22\u0E27 |
| 1598 |
* compare |
| 1599 |
< \u0E01\u0E23\u0E23\u0E40\u0E0A\u0E2D |
| 1600 |
< \u0E01\u0E23\u0E23\u0E40\u0E0A\u0E49\u0E32 |
| 1601 |
|
| 1602 |
** test: DataDrivenCollationTest/TestJavaStyleRule |
| 1603 |
# java.text allows rules to start as '<<<x<<<y...' |
| 1604 |
# we emulate this by assuming a &[first tertiary ignorable] in this case. |
| 1605 |
@ rules |
| 1606 |
&\u0001=equal<<<z<<x<<<w &[first tertiary ignorable]=a &[first primary ignorable]=b |
| 1607 |
* compare |
| 1608 |
= a |
| 1609 |
= equal |
| 1610 |
< z |
| 1611 |
< x |
| 1612 |
= b # x had become the new first primary ignorable |
| 1613 |
< w |
| 1614 |
|
| 1615 |
** test: DataDrivenCollationTest/TestShiftedIgnorable |
| 1616 |
# The UCA states that primary ignorables should be completely |
| 1617 |
# ignorable when following a shifted code point. |
| 1618 |
@ root |
| 1619 |
% alternate=shifted |
| 1620 |
% strength=quaternary |
| 1621 |
* compare |
| 1622 |
< a\u0020b |
| 1623 |
= a\u0020\u0300b |
| 1624 |
= a\u0020\u0301b |
| 1625 |
< a_b |
| 1626 |
= a_\u0300b |
| 1627 |
= a_\u0301b |
| 1628 |
< A\u0020b |
| 1629 |
= A\u0020\u0300b |
| 1630 |
= A\u0020\u0301b |
| 1631 |
< A_b |
| 1632 |
= A_\u0300b |
| 1633 |
= A_\u0301b |
| 1634 |
< a\u0301b |
| 1635 |
< A\u0301b |
| 1636 |
< a\u0300b |
| 1637 |
< A\u0300b |
| 1638 |
|
| 1639 |
** test: DataDrivenCollationTest/TestNShiftedIgnorable |
| 1640 |
# The UCA states that primary ignorables should be completely |
| 1641 |
# ignorable when following a shifted code point. |
| 1642 |
@ root |
| 1643 |
% alternate=non-ignorable |
| 1644 |
% strength=tertiary |
| 1645 |
* compare |
| 1646 |
< a\u0020b |
| 1647 |
< A\u0020b |
| 1648 |
< a\u0020\u0301b |
| 1649 |
< A\u0020\u0301b |
| 1650 |
< a\u0020\u0300b |
| 1651 |
< A\u0020\u0300b |
| 1652 |
< a_b |
| 1653 |
< A_b |
| 1654 |
< a_\u0301b |
| 1655 |
< A_\u0301b |
| 1656 |
< a_\u0300b |
| 1657 |
< A_\u0300b |
| 1658 |
< a\u0301b |
| 1659 |
< A\u0301b |
| 1660 |
< a\u0300b |
| 1661 |
< A\u0300b |
| 1662 |
|
| 1663 |
** test: DataDrivenCollationTest/TestSafeSurrogates |
| 1664 |
# It turned out that surrogates were not skipped properly |
| 1665 |
# when iterating backwards if they were in the middle of a |
| 1666 |
# contraction. This test assures that this is fixed. |
| 1667 |
@ rules |
| 1668 |
&a < x\ud800\udc00b |
| 1669 |
* compare |
| 1670 |
< a |
| 1671 |
< x\ud800\udc00b |
| 1672 |
|
| 1673 |
** test: DataDrivenCollationTest/da_TestPrimary |
| 1674 |
# This test goes through primary strength cases |
| 1675 |
@ locale da |
| 1676 |
% strength=primary |
| 1677 |
* compare |
| 1678 |
< Lvi |
| 1679 |
< Lwi |
| 1680 |
* compare |
| 1681 |
< L\u00e4vi |
| 1682 |
< L\u00f6wi |
| 1683 |
* compare |
| 1684 |
< L\u00fcbeck |
| 1685 |
= Lybeck |
| 1686 |
|
| 1687 |
** test: DataDrivenCollationTest/da_TestTertiary |
| 1688 |
# This test goes through tertiary strength cases |
| 1689 |
@ locale da |
| 1690 |
% strength=tertiary |
| 1691 |
* compare |
| 1692 |
< Luc |
| 1693 |
< luck |
| 1694 |
* compare |
| 1695 |
< luck |
| 1696 |
< L\u00fcbeck |
| 1697 |
* compare |
| 1698 |
< lybeck |
| 1699 |
< L\u00fcbeck |
| 1700 |
* compare |
| 1701 |
< L\u00e4vi |
| 1702 |
< L\u00f6we |
| 1703 |
* compare |
| 1704 |
< L\u00f6ww |
| 1705 |
< mast |
| 1706 |
|
| 1707 |
* compare |
| 1708 |
< A/S |
| 1709 |
< ANDRE |
| 1710 |
< ANDR\u00c9 |
| 1711 |
< ANDREAS |
| 1712 |
< AS |
| 1713 |
< CA |
| 1714 |
< \u00c7A |
| 1715 |
< CB |
| 1716 |
< \u00c7C |
| 1717 |
< D.S.B. |
| 1718 |
< DA |
| 1719 |
< \u00d0A |
| 1720 |
< DB |
| 1721 |
< \u00d0C |
| 1722 |
< DSB |
| 1723 |
< DSC |
| 1724 |
< EKSTRA_ARBEJDE |
| 1725 |
< EKSTRABUD0 |
| 1726 |
< H\u00d8ST |
| 1727 |
< HAAG |
| 1728 |
< H\u00c5NDBOG |
| 1729 |
< HAANDV\u00c6RKSBANKEN |
| 1730 |
< Karl |
| 1731 |
< karl |
| 1732 |
< NIELS\u0020J\u00d8RGEN |
| 1733 |
< NIELS-J\u00d8RGEN |
| 1734 |
< NIELSEN |
| 1735 |
< R\u00c9E,\u0020A |
| 1736 |
< REE,\u0020B |
| 1737 |
< R\u00c9E,\u0020L |
| 1738 |
< REE,\u0020V |
| 1739 |
< SCHYTT,\u0020B |
| 1740 |
< SCHYTT,\u0020H |
| 1741 |
< SCH\u00dcTT,\u0020H |
| 1742 |
< SCHYTT,\u0020L |
| 1743 |
< SCH\u00dcTT,\u0020M |
| 1744 |
< SS |
| 1745 |
< \u00df |
| 1746 |
< SSA |
| 1747 |
< STORE\u0020VILDMOSE |
| 1748 |
< STOREK\u00c6R0 |
| 1749 |
< STORM\u0020PETERSEN |
| 1750 |
< STORMLY |
| 1751 |
< THORVALD |
| 1752 |
< THORVARDUR |
| 1753 |
< \u00feORVAR\u00d0UR |
| 1754 |
< THYGESEN |
| 1755 |
< VESTERG\u00c5RD,\u0020A |
| 1756 |
< VESTERGAARD,\u0020A |
| 1757 |
< VESTERG\u00c5RD,\u0020B |
| 1758 |
< \u00c6BLE |
| 1759 |
< \u00c4BLE |
| 1760 |
< \u00d8BERG |
| 1761 |
< \u00d6BERG |
| 1762 |
|
| 1763 |
* compare |
| 1764 |
< andere |
| 1765 |
< chaque |
| 1766 |
< chemin |
| 1767 |
< cote |
| 1768 |
< cot\u00e9 |
| 1769 |
< c\u00f4te |
| 1770 |
< c\u00f4t\u00e9 |
| 1771 |
< \u010du\u010d\u0113t |
| 1772 |
< Czech |
| 1773 |
< hi\u0161a |
| 1774 |
< irdisch |
| 1775 |
< lie |
| 1776 |
< lire |
| 1777 |
< llama |
| 1778 |
< l\u00f5ug |
| 1779 |
< l\u00f2za |
| 1780 |
< lu\u010d |
| 1781 |
< luck |
| 1782 |
< L\u00fcbeck |
| 1783 |
< lye |
| 1784 |
< l\u00e4vi |
| 1785 |
< L\u00f6wen |
| 1786 |
< m\u00e0\u0161ta |
| 1787 |
< m\u00eer |
| 1788 |
< myndig |
| 1789 |
< M\u00e4nner |
| 1790 |
< m\u00f6chten |
| 1791 |
< pi\u00f1a |
| 1792 |
< pint |
| 1793 |
< pylon |
| 1794 |
< \u0161\u00e0ran |
| 1795 |
< savoir |
| 1796 |
< \u0160erb\u016bra |
| 1797 |
< Sietla |
| 1798 |
< \u015blub |
| 1799 |
< subtle |
| 1800 |
< symbol |
| 1801 |
< s\u00e4mtlich |
| 1802 |
< verkehrt |
| 1803 |
< vox |
| 1804 |
< v\u00e4ga |
| 1805 |
< waffle |
| 1806 |
< wood |
| 1807 |
< yen |
| 1808 |
< yuan |
| 1809 |
< yucca |
| 1810 |
< \u017eal |
| 1811 |
< \u017eena |
| 1812 |
< \u017den\u0113va |
| 1813 |
< zoo0 |
| 1814 |
< Zviedrija |
| 1815 |
< Z\u00fcrich |
| 1816 |
< zysk0 |
| 1817 |
< \u00e4ndere |
| 1818 |
|
| 1819 |
** test: DataDrivenCollationTest/hi_TestNewRules |
| 1820 |
# This test goes through new rules and tests against old rules |
| 1821 |
@ locale hi |
| 1822 |
* compare |
| 1823 |
< कॐ |
| 1824 |
< कं |
| 1825 |
< कँ |
| 1826 |
< कः |
| 1827 |
|
| 1828 |
** test: DataDrivenCollationTest/ro_TestNewRules |
| 1829 |
# This test goes through new rules and tests against old rules |
| 1830 |
@ locale ro |
| 1831 |
* compare |
| 1832 |
< xAx |
| 1833 |
< xă |
| 1834 |
< xĂ |
| 1835 |
< Xă |
| 1836 |
< XĂ |
| 1837 |
< xăx |
| 1838 |
< xĂx |
| 1839 |
< xâ |
| 1840 |
< x |
| 1841 |
< Xâ |
| 1842 |
< XÂ |
| 1843 |
< xâx |
| 1844 |
< xÂx |
| 1845 |
< xb |
| 1846 |
< xIx |
| 1847 |
< xî |
| 1848 |
< xÎ |
| 1849 |
< Xî |
| 1850 |
< XÎ |
| 1851 |
< xîx |
| 1852 |
< xÎx |
| 1853 |
< xj |
| 1854 |
< xSx |
| 1855 |
< xș |
| 1856 |
= xş |
| 1857 |
< xȘ |
| 1858 |
= xŞ |
| 1859 |
< Xș |
| 1860 |
= Xş |
| 1861 |
< XȘ |
| 1862 |
= XŞ |
| 1863 |
< xșx |
| 1864 |
= xşx |
| 1865 |
< xȘx |
| 1866 |
= xŞx |
| 1867 |
< xT |
| 1868 |
< xTx |
| 1869 |
< xț |
| 1870 |
= xţ |
| 1871 |
< xȚ |
| 1872 |
= xŢ |
| 1873 |
< Xț |
| 1874 |
= Xţ |
| 1875 |
< XȚ |
| 1876 |
= XŢ |
| 1877 |
< xțx |
| 1878 |
= xţx |
| 1879 |
< xȚx |
| 1880 |
= xŢx |
| 1881 |
< xU |
| 1882 |
|
| 1883 |
** test: DataDrivenCollationTest/testOffsets |
| 1884 |
# This tests cases where forwards and backwards iteration get different offsets |
| 1885 |
@ locale en |
| 1886 |
% strength=tertiary |
| 1887 |
* compare |
| 1888 |
< a\uD800\uDC00\uDC00 |
| 1889 |
< b\uD800\uDC00\uDC00 |
| 1890 |
* compare |
| 1891 |
< \u0301A\u0301\u0301 |
| 1892 |
< \u0301B\u0301\u0301 |
| 1893 |
* compare |
| 1894 |
< abcd\r\u0301 |
| 1895 |
< abce\r\u0301 |
| 1896 |
# TODO: test offsets in new CollationTest |
| 1897 |
|
| 1898 |
# End of test cases moved here from ICU 52's DataDrivenCollationTest.txt. |
| 1899 |
|
| 1900 |
** test: was ICU 52 cmsccoll/TestRedundantRules |
| 1901 |
@ rules |
| 1902 |
& a < b < c < d& [before 1] c < m |
| 1903 |
* compare |
| 1904 |
<1 a |
| 1905 |
<1 b |
| 1906 |
<1 m |
| 1907 |
<1 c |
| 1908 |
<1 d |
| 1909 |
|
| 1910 |
@ rules |
| 1911 |
& a < b <<< c << d <<< e& [before 3] e <<< x |
| 1912 |
* compare |
| 1913 |
<1 a |
| 1914 |
<1 b |
| 1915 |
<3 c |
| 1916 |
<2 d |
| 1917 |
<3 x |
| 1918 |
<3 e |
| 1919 |
|
| 1920 |
@ rules |
| 1921 |
& a < b <<< c << d <<< e <<< f < g& [before 1] g < x |
| 1922 |
* compare |
| 1923 |
<1 a |
| 1924 |
<1 b |
| 1925 |
<3 c |
| 1926 |
<2 d |
| 1927 |
<3 e |
| 1928 |
<3 f |
| 1929 |
<1 x |
| 1930 |
<1 g |
| 1931 |
|
| 1932 |
@ rules |
| 1933 |
& a <<< b << c < d& a < m |
| 1934 |
* compare |
| 1935 |
<1 a |
| 1936 |
<3 b |
| 1937 |
<2 c |
| 1938 |
<1 m |
| 1939 |
<1 d |
| 1940 |
|
| 1941 |
@ rules |
| 1942 |
&a<b<<b\u0301 &z<b |
| 1943 |
* compare |
| 1944 |
<1 a |
| 1945 |
<1 b\u0301 |
| 1946 |
<1 z |
| 1947 |
<1 b |
| 1948 |
|
| 1949 |
@ rules |
| 1950 |
&z<m<<<q<<<m |
| 1951 |
* compare |
| 1952 |
<1 z |
| 1953 |
<1 q |
| 1954 |
<3 m |
| 1955 |
|
| 1956 |
@ rules |
| 1957 |
&z<<<m<q<<<m |
| 1958 |
* compare |
| 1959 |
<1 z |
| 1960 |
<1 q |
| 1961 |
<3 m |
| 1962 |
|
| 1963 |
@ rules |
| 1964 |
& a < b < c < d& r < c |
| 1965 |
* compare |
| 1966 |
<1 a |
| 1967 |
<1 b |
| 1968 |
<1 d |
| 1969 |
<1 r |
| 1970 |
<1 c |
| 1971 |
|
| 1972 |
@ rules |
| 1973 |
& a < b < c < d& c < m |
| 1974 |
* compare |
| 1975 |
<1 a |
| 1976 |
<1 b |
| 1977 |
<1 c |
| 1978 |
<1 m |
| 1979 |
<1 d |
| 1980 |
|
| 1981 |
@ rules |
| 1982 |
& a < b < c < d& a < m |
| 1983 |
* compare |
| 1984 |
<1 a |
| 1985 |
<1 m |
| 1986 |
<1 b |
| 1987 |
<1 c |
| 1988 |
<1 d |
| 1989 |
|
| 1990 |
** test: was ICU 52 cmsccoll/TestExpansionSyntax |
| 1991 |
# The following two rules should sort the particular list of strings the same. |
| 1992 |
@ rules |
| 1993 |
&AE <<< a << b <<< c &d <<< f |
| 1994 |
* compare |
| 1995 |
<1 AE |
| 1996 |
<3 a |
| 1997 |
<2 b |
| 1998 |
<3 c |
| 1999 |
<1 d |
| 2000 |
<3 f |
| 2001 |
|
| 2002 |
@ rules |
| 2003 |
&A <<< a / E << b / E <<< c /E &d <<< f |
| 2004 |
* compare |
| 2005 |
<1 AE |
| 2006 |
<3 a |
| 2007 |
<2 b |
| 2008 |
<3 c |
| 2009 |
<1 d |
| 2010 |
<3 f |
| 2011 |
|
| 2012 |
# The following two rules should sort the particular list of strings the same. |
| 2013 |
@ rules |
| 2014 |
&AE <<< a <<< b << c << d < e < f <<< g |
| 2015 |
* compare |
| 2016 |
<1 AE |
| 2017 |
<3 a |
| 2018 |
<3 b |
| 2019 |
<2 c |
| 2020 |
<2 d |
| 2021 |
<1 e |
| 2022 |
<1 f |
| 2023 |
<3 g |
| 2024 |
|
| 2025 |
@ rules |
| 2026 |
&A <<< a / E <<< b / E << c / E << d / E < e < f <<< g |
| 2027 |
* compare |
| 2028 |
<1 AE |
| 2029 |
<3 a |
| 2030 |
<3 b |
| 2031 |
<2 c |
| 2032 |
<2 d |
| 2033 |
<1 e |
| 2034 |
<1 f |
| 2035 |
<3 g |
| 2036 |
|
| 2037 |
# The following two rules should sort the particular list of strings the same. |
| 2038 |
@ rules |
| 2039 |
&AE <<< B <<< C / D <<< F |
| 2040 |
* compare |
| 2041 |
<1 AE |
| 2042 |
<3 B |
| 2043 |
<3 F |
| 2044 |
<1 AED |
| 2045 |
<3 C |
| 2046 |
|
| 2047 |
@ rules |
| 2048 |
&A <<< B / E <<< C / ED <<< F / E |
| 2049 |
* compare |
| 2050 |
<1 AE |
| 2051 |
<3 B |
| 2052 |
<3 F |
| 2053 |
<1 AED |
| 2054 |
<3 C |
| 2055 |
|
| 2056 |
** test: never reorder trailing primaries |
| 2057 |
@ root |
| 2058 |
% reorder Zzzz Grek |
| 2059 |
* compare |
| 2060 |
<1 L |
| 2061 |
<1 字 |
| 2062 |
<1 Ω |
| 2063 |
<1 \uFFFD |
| 2064 |
<1 \uFFFF |
| 2065 |
|
| 2066 |
** test: fall back to mappings with shorter prefixes, not immediately to ones with no prefixes |
| 2067 |
@ rules |
| 2068 |
&u=ab|cd |
| 2069 |
&v=b|ce |
| 2070 |
* compare |
| 2071 |
<1 abc |
| 2072 |
<1 abcc |
| 2073 |
<1 abcf |
| 2074 |
<1 abcd |
| 2075 |
= abu |
| 2076 |
<1 abce |
| 2077 |
= abv |
| 2078 |
|
| 2079 |
# With the following rules, there is only one prefix per composite ĉ or ç, |
| 2080 |
# but both prefixes apply to just c in NFD form. |
| 2081 |
# We would get different results for composed vs. NFD input |
| 2082 |
# if we fell back directly from longest-prefix mappings to no-prefix mappings. |
| 2083 |
@ rules |
| 2084 |
&x=op|ĉ |
| 2085 |
&y=p|ç |
| 2086 |
* compare |
| 2087 |
<1 opc |
| 2088 |
<2 opć |
| 2089 |
<1 opcz |
| 2090 |
<1 opd |
| 2091 |
<1 opĉ |
| 2092 |
= opc\u0302 |
| 2093 |
= opx |
| 2094 |
<1 opç |
| 2095 |
= opc\u0327 |
| 2096 |
= opy |
| 2097 |
|
| 2098 |
# The mapping is used which has the longest matching prefix for which |
| 2099 |
# there is also a suffix match, with the longest suffix match among several for that prefix. |
| 2100 |
@ rules |
| 2101 |
&❶=d |
| 2102 |
&❷=de |
| 2103 |
&❸=def |
| 2104 |
&①=c|d |
| 2105 |
&②=c|de |
| 2106 |
&③=c|def |
| 2107 |
&④=bc|d |
| 2108 |
&⑤=bc|de |
| 2109 |
&⑥=bc|def |
| 2110 |
&⑦=abc|d |
| 2111 |
&⑧=abc|de |
| 2112 |
&⑨=abc|def |
| 2113 |
* compare |
| 2114 |
<1 9aadzz |
| 2115 |
= 9aa❶zz |
| 2116 |
<1 9aadez |
| 2117 |
= 9aa❷z |
| 2118 |
<1 9aadef |
| 2119 |
= 9aa❸ |
| 2120 |
<1 9acdzz |
| 2121 |
= 9ac①zz |
| 2122 |
<1 9acdez |
| 2123 |
= 9ac②z |
| 2124 |
<1 9acdef |
| 2125 |
= 9ac③ |
| 2126 |
<1 9bcdzz |
| 2127 |
= 9bc④zz |
| 2128 |
<1 9bcdez |
| 2129 |
= 9bc⑤z |
| 2130 |
<1 9bcdef |
| 2131 |
= 9bc⑥ |
| 2132 |
<1 abcdzz |
| 2133 |
= abc⑦zz |
| 2134 |
<1 abcdez |
| 2135 |
= abc⑧z |
| 2136 |
<1 abcdef |
| 2137 |
= abc⑨ |
| 2138 |
|
| 2139 |
** test: prefix + discontiguous contraction with missing prefix contraction |
| 2140 |
# Unfortunate terminology: The first "prefix" here is the pre-context, |
| 2141 |
# the second "prefix" refers to the contraction/relation string that is |
| 2142 |
# one shorter than the one being tested. |
| 2143 |
@ rules |
| 2144 |
&x=p|e |
| 2145 |
&y=p|ê |
| 2146 |
&z=op|ê |
| 2147 |
# No mapping for op|e: |
| 2148 |
# Discontiguous contraction matching should not match op|ê in opệ |
| 2149 |
# because it would have to skip the dot below and extend a match on op|e by the circumflex, |
| 2150 |
# but there is no match on op|e. |
| 2151 |
* compare |
| 2152 |
<1 oPe |
| 2153 |
<1 ope |
| 2154 |
= opx |
| 2155 |
<1 opệ |
| 2156 |
= opy\u0323 # y not z |
| 2157 |
<1 opê |
| 2158 |
= opz |
| 2159 |
|
| 2160 |
# We cannot test for fallback by whether the contraction default CE32 |
| 2161 |
# is for another contraction. With the following rules, there is no mapping for op|e, |
| 2162 |
# and the fallback to prefix p has no contractions. |
| 2163 |
@ rules |
| 2164 |
&x=p|e |
| 2165 |
&z=op|ê |
| 2166 |
* compare |
| 2167 |
<1 oPe |
| 2168 |
<1 ope |
| 2169 |
= opx |
| 2170 |
<2 opệ |
| 2171 |
= opx\u0323\u0302 # x not z |
| 2172 |
<1 opê |
| 2173 |
= opz |
| 2174 |
|
| 2175 |
# One more variation: Fallback to the simple code point, no shorter non-empty prefix. |
| 2176 |
@ rules |
| 2177 |
&x=e |
| 2178 |
&z=op|ê |
| 2179 |
* compare |
| 2180 |
<1 ope |
| 2181 |
= opx |
| 2182 |
<3 oPe |
| 2183 |
= oPx |
| 2184 |
<2 opệ |
| 2185 |
= opx\u0323\u0302 # x not z |
| 2186 |
<1 opê |
| 2187 |
= opz |
| 2188 |
|
| 2189 |
** test: maxVariable via rules |
| 2190 |
@ rules |
| 2191 |
[maxVariable space][alternate shifted] |
| 2192 |
* compare |
| 2193 |
= \u0020 |
| 2194 |
= \u000A |
| 2195 |
<1 . |
| 2196 |
<1 ° # degree sign |
| 2197 |
<1 $ |
| 2198 |
<1 0 |
| 2199 |
|
| 2200 |
** test: maxVariable via setting |
| 2201 |
@ root |
| 2202 |
% maxVariable=currency |
| 2203 |
% alternate=shifted |
| 2204 |
* compare |
| 2205 |
= \u0020 |
| 2206 |
= \u000A |
| 2207 |
= . |
| 2208 |
= ° # degree sign |
| 2209 |
= $ |
| 2210 |
<1 0 |
| 2211 |
|
| 2212 |
** test: ICU4J CollationMiscTest/TestContractionClosure (ää) |
| 2213 |
# This tests canonical closure, but it also tests that CollationFastLatin |
| 2214 |
# bails out properly for contractions with combining marks. |
| 2215 |
# For that we need pairs of strings that remain in the Latin fastpath |
| 2216 |
# long enough, hence the extra "= b" lines. |
| 2217 |
@ rules |
| 2218 |
&b=\u00e4\u00e4 |
| 2219 |
* compare |
| 2220 |
<1 b |
| 2221 |
= \u00e4\u00e4 |
| 2222 |
= b |
| 2223 |
= a\u0308a\u0308 |
| 2224 |
= b |
| 2225 |
= \u00e4a\u0308 |
| 2226 |
= b |
| 2227 |
= a\u0308\u00e4 |
| 2228 |
|
| 2229 |
** test: ICU4J CollationMiscTest/TestContractionClosure (Å) |
| 2230 |
@ rules |
| 2231 |
&b=\u00C5 |
| 2232 |
* compare |
| 2233 |
<1 b |
| 2234 |
= \u00C5 |
| 2235 |
= b |
| 2236 |
= A\u030A |
| 2237 |
= b |
| 2238 |
= \u212B |
| 2239 |
|
| 2240 |
** test: reset-before on already-tailored characters, ICU ticket 10108 |
| 2241 |
@ rules |
| 2242 |
&a<w<<x &[before 2]x<<y |
| 2243 |
* compare |
| 2244 |
<1 a |
| 2245 |
<1 w |
| 2246 |
<2 y |
| 2247 |
<2 x |
| 2248 |
|
| 2249 |
@ rules |
| 2250 |
&a<<w<<<x &[before 2]x<<y |
| 2251 |
* compare |
| 2252 |
<1 a |
| 2253 |
<2 y |
| 2254 |
<2 w |
| 2255 |
<3 x |
| 2256 |
|
| 2257 |
@ rules |
| 2258 |
&a<w<x &[before 2]x<<y |
| 2259 |
* compare |
| 2260 |
<1 a |
| 2261 |
<1 w |
| 2262 |
<1 y |
| 2263 |
<2 x |
| 2264 |
|
| 2265 |
@ rules |
| 2266 |
&a<w<<<x &[before 2]x<<y |
| 2267 |
* compare |
| 2268 |
<1 a |
| 2269 |
<1 y |
| 2270 |
<2 w |
| 2271 |
<3 x |
| 2272 |
|
| 2273 |
** test: numeric collation with other settings, ICU ticket 9092 |
| 2274 |
@ root |
| 2275 |
% strength=identical |
| 2276 |
% caseFirst=upper |
| 2277 |
% numeric=on |
| 2278 |
* compare |
| 2279 |
<1 100\u0020a |
| 2280 |
<1 101 |
| 2281 |
|
| 2282 |
** test: collation type fallback from unsupported type, ICU ticket 10149 |
| 2283 |
@ locale fr-CA-u-co-phonebk |
| 2284 |
# Expect the same result as with fr-CA, using backwards-secondary order. |
| 2285 |
# That is, we should fall back from the unsupported collation type |
| 2286 |
# to the locale's default collation type. |
| 2287 |
* compare |
| 2288 |
<1 cote |
| 2289 |
<2 côte |
| 2290 |
<2 coté |
| 2291 |
<2 côté |
| 2292 |
|
| 2293 |
** test: @ is equivalent to [backwards 2], ICU ticket 9956 |
| 2294 |
@ rules |
| 2295 |
&b<a @ &v<<w |
| 2296 |
* compare |
| 2297 |
<1 b |
| 2298 |
<1 a |
| 2299 |
<1 cote |
| 2300 |
<2 côte |
| 2301 |
<2 coté |
| 2302 |
<2 côté |
| 2303 |
<1 v |
| 2304 |
<2 w |
| 2305 |
<1 x |
| 2306 |
|
| 2307 |
** test: shifted+reordering, ICU ticket 9507 |
| 2308 |
@ root |
| 2309 |
% reorder Grek punct space |
| 2310 |
% alternate=shifted |
| 2311 |
% strength=quaternary |
| 2312 |
# Which primaries are "variable" should be determined without script reordering, |
| 2313 |
# and then primaries should be reordered whether they are shifted to quaternary or not. |
| 2314 |
* compare |
| 2315 |
<4 ( # punctuation |
| 2316 |
<4 ) |
| 2317 |
<4 \u0020 # space |
| 2318 |
<1 ` # symbol |
| 2319 |
<1 ^ |
| 2320 |
<1 $ # currency symbol |
| 2321 |
<1 € |
| 2322 |
<1 0 # numbers |
| 2323 |
<1 ε # Greek |
| 2324 |
<1 e # Latin |
| 2325 |
<1 e(e |
| 2326 |
<4 e)e |
| 2327 |
<4 e\u0020e |
| 2328 |
<4 ee |
| 2329 |
<3 e(E |
| 2330 |
<4 e)E |
| 2331 |
<4 e\u0020E |
| 2332 |
<4 eE |
| 2333 |
|
| 2334 |
** test: "uppercase first" could sort a string before its prefix, ICU ticket 9351 |
| 2335 |
@ rules |
| 2336 |
&\u0001<<<b<<<B |
| 2337 |
% caseFirst=upper |
| 2338 |
* compare |
| 2339 |
<1 aaa |
| 2340 |
<3 aaaB |
| 2341 |
|
| 2342 |
** test: secondary+case ignores secondary ignorables, ICU ticket 9355 |
| 2343 |
@ rules |
| 2344 |
&\u0001<<<b<<<B |
| 2345 |
% strength=secondary |
| 2346 |
% caseLevel=on |
| 2347 |
* compare |
| 2348 |
<1 a |
| 2349 |
= ab |
| 2350 |
= aB |
| 2351 |
|
| 2352 |
** test: custom collation rules involving tail of a contraction in Malayalam, ICU ticket 6328 |
| 2353 |
@ rules |
| 2354 |
&[before 2] ൌ << ൗ # U+0D57 << U+0D4C == 0D46+0D57 |
| 2355 |
* compare |
| 2356 |
<1 ൗx |
| 2357 |
<2 ൌx |
| 2358 |
<1 ൗy |
| 2359 |
<2 ൌy |
| 2360 |
|
| 2361 |
** test: quoted apostrophe in compact syntax, ICU ticket 8204 |
| 2362 |
@ rules |
| 2363 |
&q<<*a''c |
| 2364 |
* compare |
| 2365 |
<1 d |
| 2366 |
<1 p |
| 2367 |
<1 q |
| 2368 |
<2 a |
| 2369 |
<2 \u0027 |
| 2370 |
<2 c |
| 2371 |
<1 r |
| 2372 |
|
| 2373 |
# ICU ticket #8260 "Support all collation-related keywords in Collator.getInstance()" |
| 2374 |
** test: locale -u- with collation keywords, ICU ticket 8260 |
| 2375 |
@ locale de-u-kv-sPace-ka-shifTed-kn-kk-falsE-kf-Upper-kc-tRue-ks-leVel4 |
| 2376 |
* compare |
| 2377 |
<4 \u0020 # space is shifted, strength=quaternary |
| 2378 |
<1 ! # punctuation is regular |
| 2379 |
<1 2 |
| 2380 |
<1 12 # numeric sorting |
| 2381 |
<1 B |
| 2382 |
<c b # uppercase first on case level |
| 2383 |
<1 x\u0301\u0308 |
| 2384 |
<2 x\u0308\u0301 # normalization off |
| 2385 |
|
| 2386 |
** test: locale @ with collation keywords, ICU ticket 8260 |
| 2387 |
@ locale fr@colbAckwards=yes;ColStrength=Quaternary;kv=currencY;colalternate=shifted |
| 2388 |
* compare |
| 2389 |
<4 $ # currency symbols are shifted, strength=quaternary |
| 2390 |
<1 àla |
| 2391 |
<2 alà # backwards secondary level |
| 2392 |
|
| 2393 |
** test: locale -u- with script reordering, ICU ticket 8260 |
| 2394 |
@ locale el-u-kr-kana-SYMBOL-Grek-hani-cyrl-latn-digit-armn-deva-ethi-thai |
| 2395 |
* compare |
| 2396 |
<1 \u0020 |
| 2397 |
<1 あ |
| 2398 |
<1 ☂ |
| 2399 |
<1 Ω |
| 2400 |
<1 丂 |
| 2401 |
<1 ж |
| 2402 |
<1 L |
| 2403 |
<1 4 |
| 2404 |
<1 Ձ |
| 2405 |
<1 अ |
| 2406 |
<1 ሄ |
| 2407 |
<1 ฉ |
| 2408 |
|
| 2409 |
** test: locale @collation=type should be case-insensitive |
| 2410 |
@ locale de@coLLation=PhoneBook |
| 2411 |
* compare |
| 2412 |
<1 ae |
| 2413 |
<2 ä |
| 2414 |
<3 Ä |
| 2415 |
|
| 2416 |
** test: import root search rules plus German phonebook rules, ICU ticket 8962 |
| 2417 |
@ locale de-u-co-search |
| 2418 |
* compare |
| 2419 |
<1 = |
| 2420 |
<1 ≠ |
| 2421 |
<1 a |
| 2422 |
<1 ae |
| 2423 |
<2 ä |
| 2424 |
|
| 2425 |
# Once more, but with runtime builder. |
| 2426 |
@ rules |
| 2427 |
[import und-u-co-search][import de-u-co-phonebk] |
| 2428 |
* compare |
| 2429 |
<1 = |
| 2430 |
<1 ≠ |
| 2431 |
<1 a |
| 2432 |
<1 ae |
| 2433 |
<2 ä |
| 2434 |
|
| 2435 |
# Once again, with import from "root" not "und" (as in a proper language tag). |
| 2436 |
@ rules |
| 2437 |
[import root-u-co-search][import de-u-co-phonebk] |
| 2438 |
* compare |
| 2439 |
<1 = |
| 2440 |
<1 ≠ |
| 2441 |
<1 a |
| 2442 |
<1 ae |
| 2443 |
<2 ä |
| 2444 |
|
| 2445 |
** test: import rules from a language with non-Latin native script, and reset the reordering, ICU ticket 10998 |
| 2446 |
# Greek should sort Greek first. |
| 2447 |
@ rules |
| 2448 |
[import el] |
| 2449 |
* compare |
| 2450 |
<1 4 |
| 2451 |
<1 Ω |
| 2452 |
<1 L |
| 2453 |
|
| 2454 |
# Import Greek, and then reset the reordering. |
| 2455 |
@ rules |
| 2456 |
[import el][reorder Zzzz] |
| 2457 |
* compare |
| 2458 |
<1 4 |
| 2459 |
<1 L |
| 2460 |
<1 Ω |
| 2461 |
|
| 2462 |
# "others" is a synonym for Zzzz. |
| 2463 |
@ rules |
| 2464 |
[import el][reorder others] |
| 2465 |
* compare |
| 2466 |
<1 4 |
| 2467 |
<1 L |
| 2468 |
<1 Ω |
| 2469 |
|
| 2470 |
** test: regression test for CollationFastLatinBuilder, ICU ticket 11388 |
| 2471 |
@ rules |
| 2472 |
&x<<aa<<<Aa<<<AA |
| 2473 |
% strength=secondary |
| 2474 |
* compare |
| 2475 |
<1 AA |
| 2476 |
<2 Aẩ |
| 2477 |
<2 aą |
| 2478 |
* compare |
| 2479 |
<1 AA |
| 2480 |
<2 aą |
| 2481 |
|
| 2482 |
** test: tailor tertiary-after a common tertiary where there is a lower one |
| 2483 |
# Assume that Hiragana small A has a below-common tertiary, and Hiragana A has a common one. |
| 2484 |
# See ICU ticket 11448 & CLDR ticket 7222. |
| 2485 |
@ rules |
| 2486 |
&あ<<<x<<<y<<<z |
| 2487 |
* compare |
| 2488 |
<1 ぁ |
| 2489 |
<3 あ |
| 2490 |
<3 x |
| 2491 |
<3 y |
| 2492 |
<3 z |
| 2493 |
<3 ァ |
| 2494 |
<1 い |
| 2495 |
|
| 2496 |
** test: tailor tertiary-after a below-common tertiary |
| 2497 |
@ rules |
| 2498 |
&ぁ<<<x<<<y<<<z |
| 2499 |
* compare |
| 2500 |
<1 ぁ |
| 2501 |
<3 x |
| 2502 |
<3 y |
| 2503 |
<3 z |
| 2504 |
<3 あ |
| 2505 |
<3 ァ |
| 2506 |
<1 い |
| 2507 |
|
| 2508 |
** test: tailor tertiary-before a common tertiary where there is a lower one |
| 2509 |
@ rules |
| 2510 |
&[before 3]あ<<<x<<<y<<<z |
| 2511 |
* compare |
| 2512 |
<1 ぁ |
| 2513 |
<3 x |
| 2514 |
<3 y |
| 2515 |
<3 z |
| 2516 |
<3 あ |
| 2517 |
<3 ァ |
| 2518 |
<1 い |
| 2519 |
|
| 2520 |
** test: tailor tertiary-before a below-common tertiary |
| 2521 |
@ rules |
| 2522 |
&[before 3]ぁ<<<x<<<y<<<z |
| 2523 |
* compare |
| 2524 |
<1 x |
| 2525 |
<3 y |
| 2526 |
<3 z |
| 2527 |
<3 ぁ |
| 2528 |
<3 あ |
| 2529 |
<3 ァ |
| 2530 |
<1 い |
| 2531 |
|
| 2532 |
** test: reorder single scripts not groups, ICU ticket 11449 |
| 2533 |
@ root |
| 2534 |
% reorder Goth Latn |
| 2535 |
* compare |
| 2536 |
<1 4 |
| 2537 |
<1 𐌰 # Gothic |
| 2538 |
<1 L |
| 2539 |
<1 Ω |
| 2540 |
# Before ICU 55, the following reordered together with Gothic. |
| 2541 |
<1 𐌈 # Old Italic |
| 2542 |
<1 𐑐 # Shavian |
| 2543 |
|
| 2544 |
# Check for presence of certain chars 乛冂刂卜又小彑艹日月爫牛辶 in |
| 2545 |
# zh pinyin and stroke, ICU-13790 |
| 2546 |
# (bracket pinyin test with 卬..作, stroke test with 一..乾) |
| 2547 |
|
| 2548 |
** test: DataDrivenCollationTest/VerifyCertainCharsInPinyin |
| 2549 |
@ locale zh-u-co-pinyin |
| 2550 |
* compare |
| 2551 |
< 卬 |
| 2552 |
< 卜 |
| 2553 |
< 艹 |
| 2554 |
< 辶 |
| 2555 |
< 刂 |
| 2556 |
< 彑 |
| 2557 |
< 冂 |
| 2558 |
< 牛 |
| 2559 |
< 日 |
| 2560 |
< 小 |
| 2561 |
< 乛 |
| 2562 |
< 又 |
| 2563 |
< 月 |
| 2564 |
< 爫 |
| 2565 |
< 作 |
| 2566 |
|
| 2567 |
** test: DataDrivenCollationTest/VerifyCertainCharsInStroke |
| 2568 |
@ locale zh-u-co-stroke |
| 2569 |
* compare |
| 2570 |
< 一 |
| 2571 |
< 乛 |
| 2572 |
< 冂 |
| 2573 |
< 刂 |
| 2574 |
< 卜 |
| 2575 |
< 又 |
| 2576 |
< 小 |
| 2577 |
< 彑 |
| 2578 |
< 艹 |
| 2579 |
< 日 |
| 2580 |
< 月 |
| 2581 |
< 爫 |
| 2582 |
< 牛 |
| 2583 |
< 辶 |
| 2584 |
< 乾 |
| 2585 |
|