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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
|
if not modules then modules = { } end modules ['l-string'] = {
version = 1.001,
comment = "companion to luat-lib.mkiv",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files"
}
local string = string
local sub, gsub, find, match, gmatch, format, char, byte, rep, lower = string.sub, string.gsub, string.find, string.match, string.gmatch, string.format, string.char, string.byte, string.rep, string.lower
local lpegmatch, S, C, Ct = lpeg.match, lpeg.S, lpeg.C, lpeg.Ct
-- some functions may disappear as they are not used anywhere
if not string.split then
-- this will be overloaded by a faster lpeg variant
function string.split(str,pattern)
local t = { }
if #str > 0 then
local n = 1
for s in gmatch(str..pattern,"(.-)"..pattern) do
t[n] = s
n = n + 1
end
end
return t
end
end
function string.unquoted(str)
return (gsub(str,"^([\"\'])(.*)%1$","%2"))
end
--~ function stringunquoted(str)
--~ if find(str,"^[\'\"]") then
--~ return sub(str,2,-2)
--~ else
--~ return str
--~ end
--~ end
function string.quoted(str)
return format("%q",str) -- always "
end
function string.count(str,pattern) -- variant 3
local n = 0
for _ in gmatch(str,pattern) do -- not for utf
n = n + 1
end
return n
end
function string.limit(str,n,sentinel)
if #str > n then
sentinel = sentinel or " ..."
return sub(str,1,(n-#sentinel)) .. sentinel
else
return str
end
end
local space = S(" \t\v\n")
local nospace = 1 - space
local stripper = space^0 * C((space^0 * nospace^1)^0) -- roberto's code
function string.strip(str)
return lpegmatch(stripper,str) or ""
end
function string.is_empty(str)
return not find(str,"%S")
end
local patterns_escapes = {
["%"] = "%%",
["."] = "%.",
["+"] = "%+", ["-"] = "%-", ["*"] = "%*",
["["] = "%[", ["]"] = "%]",
["("] = "%)", [")"] = "%)",
-- ["{"] = "%{", ["}"] = "%}"
-- ["^"] = "%^", ["$"] = "%$",
}
local simple_escapes = {
["-"] = "%-",
["."] = "%.",
["?"] = ".",
["*"] = ".*",
}
function string.escapedpattern(str,simple)
if simple then
return (gsub(str,".",simple_escapes))
else
return (gsub(str,".",patterns_escapes))
end
end
function string.topattern(str,lowercase,strict)
if str == "" then
return ".*"
else
str = gsub(str,".",simple_escapes)
if lowercase then
str = lower(str)
end
if strict then
return "^" .. str .. "$"
else
return str
end
end
end
--~ local t = {
--~ "1234567123456712345671234567",
--~ "a\tb\tc",
--~ "aa\tbb\tcc",
--~ "aaa\tbbb\tccc",
--~ "aaaa\tbbbb\tcccc",
--~ "aaaaa\tbbbbb\tccccc",
--~ "aaaaaa\tbbbbbb\tcccccc",
--~ }
--~ for k,v do
--~ print(string.tabtospace(t[k]))
--~ end
-- The following functions might end up in another namespace.
function string.tabtospace(str,tab)
-- we don't handle embedded newlines
while true do
local s = find(str,"\t")
if s then
if not tab then tab = 7 end -- only when found
local d = tab-(s-1) % tab
if d > 0 then
str = gsub(str,"\t",rep(" ",d),1)
else
str = gsub(str,"\t","",1)
end
else
break
end
end
return str
end
--~ local template = string.striplong([[
--~ aaaa
--~ bb
--~ cccccc
--~ ]])
function string.striplong(str) -- strips all leading spaces
str = gsub(str,"^%s*","")
str = gsub(str,"[\n\r]+ *","\n")
return str
end
-- obsolete names:
string.quote = string.quoted
string.unquote = string.unquoted
|