xref: /Lucene/lucene/analysis/icu/src/data/utr30/BasicFoldings.txt (revision 0eeba8d37cbc851d017c07a529279ac7e7e4236a)
1e8e4245dSRobert Muir# Copyright 2001-2010 Unicode, Inc.
2e8e4245dSRobert Muir#
3e8e4245dSRobert Muir# Disclaimer
4e8e4245dSRobert Muir#
5e8e4245dSRobert Muir# This source code is provided as is by Unicode, Inc. No claims are
6e8e4245dSRobert Muir# made as to fitness for any particular purpose. No warranties of any
7e8e4245dSRobert Muir# kind are expressed or implied. The recipient agrees to determine
8e8e4245dSRobert Muir# applicability of information provided. If this file has been
9e8e4245dSRobert Muir# purchased on magnetic or optical media from Unicode, Inc., the
10e8e4245dSRobert Muir# sole remedy for any claim will be exchange of defective media
11e8e4245dSRobert Muir# within 90 days of receipt.
12e8e4245dSRobert Muir#
13e8e4245dSRobert Muir# Limitations on Rights to Redistribute This Code
14e8e4245dSRobert Muir#
15e8e4245dSRobert Muir# Unicode, Inc. hereby grants the right to freely use the information
16e8e4245dSRobert Muir# supplied in this file in the creation of products supporting the
17e8e4245dSRobert Muir# Unicode Standard, and to make copies of this file in any form
18e8e4245dSRobert Muir# for internal or external distribution as long as this notice
19e8e4245dSRobert Muir# remains attached.
20e8e4245dSRobert Muir
21e8e4245dSRobert Muir### Custom Normalization mappings for UTR#30
22e8e4245dSRobert Muir### (http://www.unicode.org/reports/tr30/tr30-4.html)
235abc76eaSSteven Rowe
245abc76eaSSteven Rowe#### WARNING ####
255abc76eaSSteven Rowe#### Rule: lines direct content generation.
265abc76eaSSteven Rowe#### All non-comments will be REMOVED when this file's contents
275abc76eaSSteven Rowe#### are generated by 'ant gen-utr30-data-files'.
285abc76eaSSteven Rowe#### Use "# Rule: verbatim" to keep non-comments up until
295abc76eaSSteven Rowe#### the next "# Rule:" line.
305abc76eaSSteven Rowe#### WARNING ####
31e8e4245dSRobert Muir
32e8e4245dSRobert Muir## Accent removal
33e8e4245dSRobert Muir# See DiacriticFolding.txt
345abc76eaSSteven Rowe
35e8e4245dSRobert Muir## Case Folding (done by cf)
365abc76eaSSteven Rowe
37e8e4245dSRobert Muir## Canonical Duplicates Folding (done by cd)
385abc76eaSSteven Rowe
39e8e4245dSRobert Muir## Dashes folding
405abc76eaSSteven Rowe# Rule: [[[[:Dash:][:Pd:]]-[\u2053\uFE31\uFE32]] - [\u002D]] > 002D
41e8e4245dSRobert Muir058A>002D
42e8e4245dSRobert Muir05BE>002D
43e8e4245dSRobert Muir1400>002D
44e8e4245dSRobert Muir1806>002D
45e8e4245dSRobert Muir2010..2015>002D
465abc76eaSSteven Rowe207B>002D
475abc76eaSSteven Rowe208B>002D
485abc76eaSSteven Rowe2212>002D
49e8e4245dSRobert Muir2E17>002D
50e8e4245dSRobert Muir2E1A>002D
515abc76eaSSteven Rowe2E3A..2E3B>002D
5283d58d77SRobert Muir2E40>002D
53*0eeba8d3SDawid Weiss2E5D>002D
54e8e4245dSRobert Muir301C>002D
55e8e4245dSRobert Muir3030>002D
56e8e4245dSRobert Muir30A0>002D
575abc76eaSSteven RoweFE58>002D
585abc76eaSSteven RoweFE63>002D
595abc76eaSSteven RoweFF0D>002D
60dd91f5caSRobert Muir10EAD>002D
61e8e4245dSRobert Muir
62e8e4245dSRobert Muir## Greek letterforms folding (done by kd)
635abc76eaSSteven Rowe
64e8e4245dSRobert Muir## Hebrew alternates folding (done by kd)
655abc76eaSSteven Rowe
66e8e4245dSRobert Muir## Jamo folding (done by kd)
675abc76eaSSteven Rowe
68e8e4245dSRobert Muir## Math symbol folding (done by kd)
695abc76eaSSteven Rowe
70e8e4245dSRobert Muir## Native digit folding
71e8e4245dSRobert Muir# See NativeDigitFolding.txt
725abc76eaSSteven Rowe
73e8e4245dSRobert Muir## Nobreak folding (done by kd)
745abc76eaSSteven Rowe
755abc76eaSSteven Rowe## Overline Folding (done by kd)
765abc76eaSSteven Rowe
77e8e4245dSRobert Muir## Positional forms folding (done by kd)
785abc76eaSSteven Rowe
79e8e4245dSRobert Muir## Small forms folding (done by kd)
805abc76eaSSteven Rowe
81e8e4245dSRobert Muir## Space Folding
825abc76eaSSteven Rowe# Rule: [[:Zs:] - [:Changes_When_NFKC_Casefolded=Yes:] - [\u0020]] > 0020
83e8e4245dSRobert Muir1680>0020
845abc76eaSSteven Rowe
85e8e4245dSRobert Muir## Spacing Accents folding (done by kd)
865abc76eaSSteven Rowe
87e8e4245dSRobert Muir## Subscript folding (done by kd)
885abc76eaSSteven Rowe
89e8e4245dSRobert Muir## Symbol folding (done by kd)
905abc76eaSSteven Rowe
91e8e4245dSRobert Muir## Underline Folding
925abc76eaSSteven Rowe# Rule: verbatim
93e8e4245dSRobert Muir2017>005E
94e8e4245dSRobert MuirFE4D..FE4F>005E
955abc76eaSSteven Rowe
96e8e4245dSRobert Muir## Diacritic Folding
975abc76eaSSteven Rowe# See DiacriticFolding.txt
98e8e4245dSRobert Muir
99e8e4245dSRobert Muir## Vertical forms folding (done by kd)
1005abc76eaSSteven Rowe
101e8e4245dSRobert Muir## Han Radical Folding
102e8e4245dSRobert Muir# See HanRadicalFolding.txt
1035abc76eaSSteven Rowe
104e8e4245dSRobert Muir## Letter Form Folding (done by kd)
105e8e4245dSRobert Muir## Superscript folding
106e8e4245dSRobert Muir# Additions to kd:
1075abc76eaSSteven Rowe# Rule: verbatim
108e8e4245dSRobert Muir02C0>0294
109e8e4245dSRobert Muir02C1>0295
110e8e4245dSRobert Muir06E5>0648
111e8e4245dSRobert Muir06E6>064A
112e8e4245dSRobert Muir## Suzhou Numeral Folding
113e8e4245dSRobert Muir# Additions to kd:
1145abc76eaSSteven Rowe# Rule: verbatim
115e8e4245dSRobert Muir3021>4E00
116e8e4245dSRobert Muir3022>4E8C
117e8e4245dSRobert Muir3023>4E09
118e8e4245dSRobert Muir3024>56DB
119e8e4245dSRobert Muir3025>4E94
120e8e4245dSRobert Muir3026>516D
121e8e4245dSRobert Muir3027>4E03
122e8e4245dSRobert Muir3028>516B
123e8e4245dSRobert Muir3029>4E5D
124e8e4245dSRobert Muir## Width Folding (done by kd)
125e8e4245dSRobert Muir# Punctuation Folding
1265abc76eaSSteven Rowe# Rule: verbatim
127e8e4245dSRobert Muir00AB>0022
128e8e4245dSRobert Muir00BB>0022
129e8e4245dSRobert Muir201C..201E>0022
130e8e4245dSRobert Muir2018..201B>0027
131e8e4245dSRobert Muir2032>0027
132e8e4245dSRobert Muir2035>0027
133e8e4245dSRobert Muir2039..203A>0027
134e8e4245dSRobert Muir2045>005B
135e8e4245dSRobert Muir2046>005D
136e8e4245dSRobert Muir2E28>0028 0028
137e8e4245dSRobert Muir2E29>0029 0029
138e8e4245dSRobert Muir2052>0025
139e8e4245dSRobert Muir204E>002A
140e8e4245dSRobert Muir2044>002F
141e8e4245dSRobert Muir204F>003B
142e8e4245dSRobert Muir2038>005E
143e8e4245dSRobert Muir2053>007E
144