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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
|
-- filename : l-unicode.lua
-- comment : split off from luat-inp
-- author : Hans Hagen, PRAGMA-ADE, Hasselt NL
-- copyright: PRAGMA ADE / ConTeXt Development Team
-- license : see context related readme files
if not versions then versions = { } end versions['l-unicode'] = 1.001
if not unicode then unicode = { } end
if not garbagecollector then
garbagecollector = {
push = function() collectgarbage("stop") end,
pop = function() collectgarbage("restart") end,
}
end
-- 0 EF BB BF UTF-8
-- 1 FF FE UTF-16-little-endian
-- 2 FE FF UTF-16-big-endian
-- 3 FF FE 00 00 UTF-32-little-endian
-- 4 00 00 FE FF UTF-32-big-endian
unicode.utfname = {
[0] = 'utf-8',
[1] = 'utf-16-le',
[2] = 'utf-16-be',
[3] = 'utf-32-le',
[4] = 'utf-32-be'
}
function unicode.utftype(f) -- \000 fails !
local str = f:read(4)
if not str then
f:seek('set')
return 0
elseif str:find("^%z%z\254\255") then
return 4
elseif str:find("^\255\254%z%z") then
return 3
elseif str:find("^\254\255") then
f:seek('set',2)
return 2
elseif str:find("^\255\254") then
f:seek('set',2)
return 1
elseif str:find("^\239\187\191") then
f:seek('set',3)
return 0
else
f:seek('set')
return 0
end
end
function unicode.utf16_to_utf8(str, endian)
garbagecollector.push()
local result = { }
local tc, uc = table.concat, unicode.utf8.char
local tmp, n, m, p = { }, 0, 0, 0
-- lf | cr | crlf / (cr:13, lf:10)
local function doit()
if n == 10 then
if p ~= 13 then
result[#result+1] = tc(tmp,"")
tmp = { }
p = 0
end
elseif n == 13 then
result[#result+1] = tc(tmp,"")
tmp = { }
p = n
else
tmp[#tmp+1] = uc(n)
p = 0
end
end
for l,r in str:bytepairs() do
if endian then
n = l*256 + r
else
n = r*256 + l
end
if m > 0 then
n = (m-0xD800)*0x400 + (n-0xDC00) + 0x10000
m = 0
doit()
elseif n >= 0xD800 and n <= 0xDBFF then
m = n
else
doit()
end
end
if #tmp > 0 then
result[#result+1] = tc(tmp,"")
end
garbagecollector.pop()
return result
end
function unicode.utf32_to_utf8(str, endian)
garbagecollector.push()
local result = { }
local tc, uc = table.concat, unicode.utf8.char
local tmp, n, m, p = { }, 0, -1, 0
-- lf | cr | crlf / (cr:13, lf:10)
local function doit()
if n == 10 then
if p ~= 13 then
result[#result+1] = tc(tmp,"")
tmp = { }
p = 0
end
elseif n == 13 then
result[#result+1] = tc(tmp,"")
tmp = { }
p = n
else
tmp[#tmp+1] = uc(n)
p = 0
end
end
for a,b in str:bytepairs() do
if a and b then
if m < 0 then
if endian then
m = a*256*256*256 + b*256*256
else
m = b*256 + a
end
else
if endian then
n = m + a*256 + b
else
n = m + b*256*256*256 + a*256*256
end
m = -1
doit()
end
else
break
end
end
if #tmp > 0 then
result[#result+1] = tc(tmp,"")
end
garbagecollector.pop()
return result
end
|