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
|
-- Copyright 2006-2018 Mitchell mitchell.att.foicica.com. See License.txt.
-- HTML LPeg lexer.
local lexer = require('lexer')
local token, word_match = lexer.token, lexer.word_match
local P, R, S, V = lpeg.P, lpeg.R, lpeg.S, lpeg.V
local lex = lexer.new('html')
-- Whitespace.
local ws = token(lexer.WHITESPACE, lexer.space^1)
lex:add_rule('whitespace', ws)
-- Comments.
lex:add_rule('comment', token(lexer.COMMENT, '<!--' * (lexer.any - '-->')^0 *
P('-->')^-1))
-- Doctype.
lex:add_rule('doctype', token('doctype', '<!' * word_match([[doctype]], true) *
(lexer.any - '>')^1 * '>'))
lex:add_style('doctype', lexer.STYLE_COMMENT)
-- Elements.
local known_element = token('element', '<' * P('/')^-1 * word_match([[
a abbr address area article aside audio b base bdi bdo blockquote body br
button canvas caption cite code col colgroup content data datalist dd
decorator del details dfn div dl dt element em embed fieldset figcaption
figure footer form h1 h2 h3 h4 h5 h6 head header hr html i iframe img input
ins kbd keygen label legend li link main map mark menu menuitem meta meter nav
noscript object ol optgroup option output p param pre progress q rp rt ruby s
samp script section select shadow small source spacer span strong style sub
summary sup table tbody td template textarea tfoot th thead time title tr
track u ul var video wbr
]], true))
local unknown_element = token('unknown_element', '<' * P('/')^-1 * lexer.word)
local element = known_element + unknown_element
lex:add_rule('element', element)
lex:add_style('element', lexer.STYLE_KEYWORD)
lex:add_style('unknown_element', lexer.STYLE_KEYWORD..',italics')
-- Closing tags.
local tag_close = token('element', P('/')^-1 * '>')
lex:add_rule('tag_close', tag_close)
-- Attributes.
local known_attribute = token('attribute', word_match([[
accept accept-charset accesskey action align alt async autocomplete autofocus
autoplay bgcolor border buffered challenge charset checked cite class code
codebase color cols colspan content contenteditable contextmenu controls
coords data data- datetime default defer dir dirname disabled download
draggable dropzone enctype for form headers height hidden high href hreflang
http-equiv icon id ismap itemprop keytype kind label lang language list loop
low manifest max maxlength media method min multiple name novalidate open
optimum pattern ping placeholder poster preload pubdate radiogroup readonly
rel required reversed role rows rowspan sandbox scope scoped seamless selected
shape size sizes span spellcheck src srcdoc srclang start step style summary
tabindex target title type usemap value width wrap
]], true) + ((P('data-') + 'aria-') * (lexer.alnum + '-')^1))
local unknown_attribute = token('unknown_attribute', lexer.word)
local attribute = (known_attribute + unknown_attribute) * #(lexer.space^0 * '=')
lex:add_rule('attribute', attribute)
lex:add_style('attribute', lexer.STYLE_TYPE)
lex:add_style('unknown_attribute', lexer.STYLE_TYPE..',italics')
-- TODO: performance is terrible on large files.
local in_tag = P(function(input, index)
local before = input:sub(1, index - 1)
local s, e = before:find('<[^>]-$'), before:find('>[^<]-$')
if s and e then return s > e and index or nil end
if s then return index end
return input:find('^[^<]->', index) and index or nil
end)
-- Equals.
local equals = token(lexer.OPERATOR, '=') --* in_tag
--lex:add_rule('equals', equals)
-- Strings.
local string = #S('\'"') * lexer.last_char_includes('=') *
token(lexer.STRING, lexer.delimited_range("'") +
lexer.delimited_range('"'))
lex:add_rule('string', string)
-- Numbers.
lex:add_rule('number', #lexer.digit * lexer.last_char_includes('=') *
token(lexer.NUMBER, lexer.digit^1 * P('%')^-1))--*in_tag)
-- Entities.
lex:add_rule('entity', token('entity', '&' * (lexer.any - lexer.space - ';')^1 *
';'))
lex:add_style('entity', lexer.STYLE_COMMENT)
-- Fold points.
local function disambiguate_lt(text, pos, line, s)
return not line:find('^</', s) and 1 or -1
end
lex:add_fold_point('element', '<', disambiguate_lt)
lex:add_fold_point('element', '/>', -1)
lex:add_fold_point('unknown_element', '<', disambiguate_lt)
lex:add_fold_point('unknown_element', '/>', -1)
lex:add_fold_point(lexer.COMMENT, '<!--', '-->')
-- Tags that start embedded languages.
-- Export these patterns for proxy lexers (e.g. ASP) that need them.
lex.embed_start_tag = element *
(ws * attribute * ws^-1 * equals * ws^-1 * string)^0 *
ws^-1 * tag_close
lex.embed_end_tag = element * tag_close
-- Embedded CSS (<style type="text/css"> ... </style>).
local css = lexer.load('css')
local style_element = word_match([[style]], true)
local css_start_rule = #(P('<') * style_element *
('>' + P(function(input, index)
if input:find('^%s+type%s*=%s*(["\'])text/css%1', index) then
return index
end
end))) * lex.embed_start_tag
local css_end_rule = #('</' * style_element * ws^-1 * '>') * lex.embed_end_tag
lex:embed(css, css_start_rule, css_end_rule)
-- Embedded JavaScript (<script type="text/javascript"> ... </script>).
local js = lexer.load('javascript')
local script_element = word_match([[script]], true)
local js_start_rule = #(P('<') * script_element *
('>' + P(function(input, index)
if input:find('^%s+type%s*=%s*(["\'])text/javascript%1', index) then
return index
end
end))) * lex.embed_start_tag
local js_end_rule = #('</' * script_element * ws^-1 * '>') * lex.embed_end_tag
local js_line_comment = '//' * (lexer.nonnewline_esc - js_end_rule)^0
local js_block_comment = '/*' * (lexer.any - '*/' - js_end_rule)^0 * P('*/')^-1
js:modify_rule('comment', token(lexer.COMMENT, js_line_comment +
js_block_comment))
lex:embed(js, js_start_rule, js_end_rule)
-- Embedded CoffeeScript (<script type="text/coffeescript"> ... </script>).
local cs = lexer.load('coffeescript')
local script_element = word_match([[script]], true)
local cs_start_rule = #(P('<') * script_element * P(function(input, index)
if input:find('^[^>]+type%s*=%s*(["\'])text/coffeescript%1', index) then
return index
end
end)) * lex.embed_start_tag
local cs_end_rule = #('</' * script_element * ws^-1 * '>') * lex.embed_end_tag
lex:embed(cs, cs_start_rule, cs_end_rule)
return lex
|
