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
|
{-# LANGUAGE OverloadedStrings #-}
{- |
Module : Text.Pandoc.Readers.HTML.TagCategories
Copyright : Copyright (C) 2006-2020 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Categories of tags.
-}
module Text.Pandoc.Readers.HTML.TagCategories
( blockHtmlTags
, blockDocBookTags
, eitherBlockOrInline
, epubTags
, blockTags
, sectioningContent
, groupingContent
)
where
import Data.Set (Set, fromList, unions)
import Data.Text (Text)
eitherBlockOrInline :: Set Text
eitherBlockOrInline = fromList
["audio", "applet", "button", "iframe", "embed",
"del", "ins", "progress", "map", "area", "noscript", "script",
"object", "svg", "video", "source"]
blockHtmlTags :: Set Text
blockHtmlTags = fromList
["?xml", "!DOCTYPE", "address", "article", "aside",
"blockquote", "body", "canvas",
"caption", "center", "col", "colgroup", "dd", "details",
"dir", "div", "dl", "dt", "fieldset", "figcaption", "figure",
"footer", "form", "h1", "h2", "h3", "h4",
"h5", "h6", "head", "header", "hgroup", "hr", "html",
"isindex", "main", "menu", "meta", "noframes", "nav",
"ol", "output", "p", "pre",
"section", "summary", "table", "tbody", "textarea",
"thead", "tfoot", "ul", "dd",
"dt", "frameset", "li", "tbody", "td", "tfoot",
"th", "thead", "tr", "script", "style"]
-- We want to allow raw docbook in markdown documents, so we
-- include docbook block tags here too.
blockDocBookTags :: Set Text
blockDocBookTags = fromList
["calloutlist", "bibliolist", "glosslist", "itemizedlist",
"orderedlist", "segmentedlist", "simplelist",
"variablelist", "caution", "important", "note", "tip",
"warning", "address", "literallayout", "programlisting",
"programlistingco", "screen", "screenco", "screenshot",
"synopsis", "example", "informalexample", "figure",
"informalfigure", "table", "informaltable", "para",
"simpara", "formalpara", "equation", "informalequation",
"figure", "screenshot", "mediaobject", "qandaset",
"procedure", "task", "cmdsynopsis", "funcsynopsis",
"classsynopsis", "blockquote", "epigraph", "msgset",
"sidebar", "title"]
epubTags :: Set Text
epubTags = fromList ["case", "switch", "default"]
blockTags :: Set Text
blockTags = unions [blockHtmlTags, blockDocBookTags, epubTags]
sectioningContent :: [Text]
sectioningContent = ["article", "aside", "nav", "section"]
groupingContent :: [Text]
groupingContent = ["p", "hr", "pre", "blockquote", "ol"
, "ul", "li", "dl", "dt", "dt", "dd"
, "figure", "figcaption", "div", "main"]
|
