文本文件  |  84行  |  1.82 KB

# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
#   Copyright (C) 2010, International Business Machines
#   Corporation and others.  All Rights Reserved.
#
#   file name:  testnorm.txt
#   encoding:   US-ASCII
#   tab size:   8 (not used)
#   indentation:4
#
#   created on: 2010feb15
#   created by: Markus W. Scherer
#
# Normalization test data, for improving code coverage.

# Selection of Canonical_Combining_Class (ccc) values
0300..0314:230
0315:232
0316..0319:220
031A:232
031B:216
031C..0320:220
0321..0322:202
0323..0326:220
0327..0328:202
0329..0333:220
0334..0338:1
0339..033C:220
033D..0344:230
0345:240
0346:230
0347..0349:220
034A..034C:230
034D..034E:220
0350..0352:230
0353..0356:220
0357:230
0358:232
0359..035A:220
035B:230
035C:233
035D..035E:234
035F:233
0360..0361:234
0362:233
0363..036F:230
# ICU 63 normalization with UCPTrie requires inert surrogate code points.
# D802:2  # surrogates with non-zero combining classes
# D803:3
# D804:4
110B9:9
110BA:7

# Some interesting mappings
00C0=0041 0300
00C1=0041 0301
00C2=0041 0302
00C3=0041 0303
00C4=0041 0308
00C5=0041 030A
00C7=0043 0327
# ICU 63 normalization with UCPTrie requires inert surrogate code points.
# D800>D7FF  # surrogates with mappings, and mappings to empty strings
# D801>
# DFFE>
# DFFF>FFFF
E000>
E001=61 338  # composition with trail<=33FF and composite>7FFF
E002=E001 308  # recursive mapping needs reordering
E003>62 307 327 337  # mapping needs reordering
E011=E010 F0011  # composition of BMP+supplementary, and F0011 is maybe & combines-fwd
E111>1101  # mapping ends in Jamo L
E112>1102 62  # mapping starts with Jamo L
FFF3>FFF4
FFF4>FFF5
FFF5>FFF7
FFF7>10037
10036>FFF6
10077>10037
1109A=11099 110BA
1109C=1109B 110BA
110AB=110A5 110BA
F0010=F0011 E012  # composition of supplementary+BMP