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
|
local info = {
version = 1.002,
comment = "scintilla lpeg lexer for plain text (with spell checking)",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files",
}
if not lexer._CONTEXTEXTENSIONS then require("scite-context-lexer") end
local lexer = lexer
local token = lexer.token
local P, S, Cmt, Cp, Ct = lpeg.P, lpeg.S, lpeg.Cmt, lpeg.Cp, lpeg.Ct
local find, match = string.find, string.match
local textlexer = { _NAME = "txt", _FILENAME = "scite-context-lexer-txt" }
local whitespace = lexer.WHITESPACE
local context = lexer.context
local space = lexer.space
local any = lexer.any
local wordtoken = context.patterns.wordtoken
local wordpattern = context.patterns.wordpattern
local checkedword = context.checkedword
local styleofword = context.styleofword
local setwordlist = context.setwordlist
local validwords = false
-- local styleset = context.newstyleset {
-- "default",
-- "text", "okay", "error", "warning",
-- "preamble",
-- }
-- [#!-%] language=uk
local p_preamble = Cmt(#(S("#!-%") * P(" ")), function(input,i,_) -- todo: utf bomb
if i == 1 then -- < 10 then
validwords = false
local s, e, line = find(input,'^[#!%-%%](.+)[\n\r]',i)
if line then
local language = match(line,"language=([a-z]+)")
if language then
validwords = setwordlist(language)
end
end
end
return false
end)
local t_preamble =
token("preamble", p_preamble)
-- local t_word =
-- Cmt(wordpattern, function(_,i,s)
-- if validwords then
-- return checkedword(validwords,s,i)
-- else
-- return true, { "text", i }
-- end
-- end)
local t_word =
Ct( wordpattern / function(s) return styleofword(validwords,s) end * Cp() ) -- the function can be inlined
local t_text =
token("default", wordtoken^1)
local t_rest =
token("default", (1-wordtoken-space)^1)
local t_spacing =
token(whitespace, space^1)
textlexer._rules = {
{ "whitespace", t_spacing },
{ "preamble", t_preamble },
{ "word", t_word }, -- words >= 3
{ "text", t_text }, -- non words
{ "rest", t_rest },
}
textlexer._tokenstyles = context.styleset
return textlexer
|