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
|
if not modules then modules = { } end modules ['char-tex'] = {
version = 1.001,
comment = "companion to char-ini.mkiv",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files"
}
local find = string.find
local lpeg = lpeg
local P, C, R, S, Cs, Cc = lpeg.P, lpeg.C, lpeg.R, lpeg.S, lpeg.Cs, lpeg.Cc
local U, lpegmatch = lpeg.patterns.utf8, lpeg.match
local allocate, mark = utilities.storage.allocate, utilities.storage.mark
characters = characters or { }
local characters = characters
characters.tex = characters.tex or { }
local accent_map = allocate {
['~'] = "̃" , -- ̃ Ẽ
['"'] = "̈" , -- ̈ Ë
["`"] = "̀" , -- ̀ È
["'"] = "́" , -- ́ É
["^"] = "̂" , -- ̂ Ê
-- ̄ Ē
-- ̆ Ĕ
-- ̇ Ė
-- ̉ Ẻ
-- ̌ Ě
-- ̏ Ȅ
-- ̑ Ȇ
-- ̣ Ẹ
-- ̧ Ȩ
-- ̨ Ę
-- ̭ Ḙ
-- ̰ Ḛ
}
local accents = table.concat(table.keys(accent_map))
local function remap_accents(a,c,braced)
local m = accent_map[a]
if m then
return c .. m
elseif braced then
return "\\" .. a .. "{" .. c .. "}"
else
return "\\" .. a .. c
end
end
local command_map = allocate {
["i"] = "ı"
}
local function remap_commands(c)
local m = command_map[c]
if m then
return m
else
return "\\" .. c
end
end
local accents = (P('\\') * C(S(accents)) * (P("{") * C(U) * P("}" * Cc(true)) + C(U) * Cc(false))) / remap_accents
local commands = (P('\\') * C(R("az","AZ")^1)) / remap_commands
local convert_accents = Cs((accents + P(1))^0)
local convert_commands = Cs((commands + P(1))^0)
local no_l = P("{") / ""
local no_r = P("}") / ""
local convert_accents_strip = Cs((no_l * accents * no_r + accents + P(1))^0)
local convert_commands_strip = Cs((no_l * commands * no_r + commands + P(1))^0)
function characters.tex.toutf(str,strip)
if find(str,"\\") then -- we can start at teh found position
if strip then
str = lpegmatch(convert_commands_strip,str)
str = lpegmatch(convert_accents_strip,str)
else
str = lpegmatch(convert_commands,str)
str = lpegmatch(convert_accents,str)
end
end
return str
end
--~ print(characters.tex.toutf([[\"{e}]]),true)
--~ print(characters.tex.toutf([[{\"{e}}]],true))
|
