summaryrefslogtreecommitdiffstats
path: root/i18npool/source/collator/data/vro_alphanumeric.txt
blob: 203e3765d666212210a8bf475076a75dc7bfe555 (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
#
# This file is part of the LibreOffice project.
#
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.
#
# Võro sort order

# There is notable inconsistency between publications/users concerning:
# palatalisation marker:
#   a) acute above (or slightly after) the letter (preferred)
#   b) apostrophe (or non-combining acute) after the letter
#   c) nothing
# glottal stop letter:
#   a) q
#   b) apostrophe
#   c) nothing
#   d) in dictionaries also ˀ or ʔ (usually superscripted to look like ˀ)

# Some typographical notes
#
# Several letters don't have precomposed glyphs: B́, D́, F́, H́, T́, V́.
# The online Võro-Estonian dictionary uses a font where dot-above is
# rendered as acute for b, f, h; combining acute accent is used for v.
#
# Lowercase ď, ľ, ť and uppercase Ľ are in principle composed with
# caron, not acute, however those forms are used more than d́, ĺ, t́, Ĺ
# (uppercase Ď and Ť with obvious caron are not used, but are included
# here for case insensitivity's sake).
#
# Non-combining acute accent ´ (\u00b4) after the letter makes the text
# look jagged, so those combinations are not included in the collation
# rules below - instead, we provide autocorrect rules to replace them
# with precomposed glyphs (if available) or with letter plus combining
# acute accent.

# Palatalized consonants
#
# Precomposed letter (with either acute or dot-above (see notes above),
# or in case of L, with acute and caron (see notes above);
# with combining acute accent  ́ (\u0301) if there's no precomposed glyph;
# with apostrophe ' (straight/ASCII; \u0027; NB: has to be escaped: '');
# with right single quotation mark ’ (typographic apostrophe; \u2019).

& b << ḃ = b́ = b'' = b’ <<< B << Ḃ = B́ = B'' = B’
& d << ď = d́ = d'' = d’ <<< D << Ď = D́ = D'' = D’
& f << ḟ = f́ = f'' = f’ <<< F << Ḟ = F́ = F'' = F’
& g <<   ǵ   = g'' = g’ <<< G <<   Ǵ   = G'' = G’
& h << ḣ = h́ = h'' = h’ <<< H << Ḣ = H́ = H'' = H’
& k <<   ḱ   = k'' = k’ <<< K <<   Ḱ   = K'' = K’
& l << ĺ = ľ = l'' = l’ <<< L << Ĺ = Ľ = L'' = L’
& m <<   ḿ   = m'' = m’ <<< M <<   Ḿ   = M'' = M’
& n <<   ń   = n'' = n’ <<< N <<   Ń   = N'' = N’
& p <<   ṕ   = p'' = p’ <<< P <<   Ṕ   = P'' = P’
& r <<   ŕ   = r'' = r’ <<< R <<   Ŕ   = R'' = R’
& s <<   ś   = s'' = s’ <<< S <<   Ś   = S'' = S’ < š <<< Š
& t << ť = t́ = t'' = t’ <<< T << Ť = T́ = T'' = T’
& v <<   v́   = v'' = v’ <<< V <<   V́   = V'' = V’

# Glottal stop
#
# After a vowel, apostrophe is used as a glottal stop marker, as is Q.
# NB: straight/ASCII apostrophe has to be escaped: ''

& q = ˀ = a|'' = a|’ = e|'' = e|’ = i|'' = i|’ = o|'' = o|’ = u|'' = u|’ = õ|'' = õ|’ = ä|'' = ä|’ = ö|'' = ö|’ = ü|'' = ü|’ = y|'' = y|’ <<< Q = ʔ = A|'' = A|’ = E|'' = E|’ = I|'' = I|’ = O|'' = O|’ = U|'' = U|’ = Õ|'' = Õ|’ = Ä|'' = Ä|’ = Ö|'' = Ö|’ = Ü|'' = Ü|’ = Y|'' = Y|’

# Final letters of the alphabet
#
# Just like in Estonian (et), except that Z & Ž are at the very end

& W < õ <<< Õ < ä <<< Ä < ö <<< Ö < ü <<< Ü
& Z < ž <<< Ž