# HTML Tags
#
# Format:
#  Lines prefixed with `#` are comments, uninterpreted
#  Comma delimited columns: name, flags (see codes below), description
#
# Flag codes:
# E :: Empty Tag
# S :: In Strict HTML 4.01/XHTML 1.0
# T :: In Transitional HTML 4.01/XHTML 1.0
# F :: In frameset annex
# 5 :: In HTML5
# D :: Deprecated
# I :: Inline elements (Note <br/> is not labeled inline.)
# M :: Metadata elements (content not visible text), i.e. head
# B :: Banned/blacklisted elements from which text should not be extracted.
# U :: Currently undefined by our HTML parser provider
#
# Sources
#  https://developer.mozilla.org/en-US/docs/Web/HTML/Element
#  https://html.spec.whatwg.org/
#  https://www.w3.org/TR/html4/
#  https://www.w3.org/TR/xhtml11/

a            ,  S T F 5   I    , anchor
abbr         ,  S T F 5   I    , abbreviation
acronym      ,  S T F   D I    , acronym
address      ,  S T F 5        , contact information for the author or owner
applet       ,    T F   D      , embedded applet
area         ,E S T F 5        , area inside an image-map
article      ,        5        , Structure: an independent content element
aside        ,        5        , Structure: tengentially related content
audio        ,        5   I    , Sound content
b            ,  S T F 5   I    , bold text
base         ,E S T F 5     M  , default address or target for all links on a page
basefont     ,E   T F   D I M  , default font; color; or size for the text in a page
bdi          ,        5   I    , Text isolated from surrounding for BIDI formatting
bdo          ,  S T F 5   I    , the text direction
big          ,  S T F   D I    , big text
blink        ,          D I    , blinking text
blockquote   ,  S T F 5        , long quotation
body         ,  S T F 5        , the document's body
br           ,E S T F 5        , single line break
button       ,  S T F 5   I   B, push button
canvas       ,        5   I    , canvas for drawing graphics and animations
caption      ,  S T F 5        , table caption
center       ,    T F   D      , centered text
cite         ,  S T F 5   I    , citation
code         ,  S T F 5   I    , computer code text
col          ,E S T F 5        , attribute values for one or more columns in a table
colgroup     ,  S T F 5        , group of columns in a table for formatting
content      ,          D     B, Shadow DOM content placeholder element
data         ,        5   I    , adds machine-oriented data representation
datalist     ,        5   I   B, container for option elements
dd           ,  S T F 5        , description of a term in a definition list
del          ,  S T F 5   I    , deleted text
details      ,        5        , optional additional details (also: summary)
dfn          ,  S T F 5   I    , definition term
dialog       ,        5        , dialog box or other interactive component
dir          ,    T F   D      , directory list
div          ,  S T F 5        , section in a document
dl           ,  S T F 5        , definition list
dt           ,  S T F 5        , term (an item) in a definition list
em           ,  S T F 5   I    , emphasized text
embed        ,E       5   I    , embed content by external app or plug-in
fieldset     ,  S T F 5       B, border around elements in a form
figcaption   ,        5        , Structure: a figure caption
figure       ,        5        , Structure: self contained content that can be moved
font         ,    T F   D I    , font; color; or size for text
footer       ,        5        , Structure: a footer of a section
form         ,  S T F 5        , form for user input
frame        ,E     F   D     B, window (a frame) in a frameset
frameset     ,      F   D     B, set of frames
h1           ,  S T F 5        , heading level 1
h2           ,  S T F 5        , heading level 2
h3           ,  S T F 5        , heading level 3
h4           ,  S T F 5        , heading level 4
h5           ,  S T F 5        , heading level 5
h6           ,  S T F 5        , heading level 6
head         ,  S T F 5     M  , information about the document
header       ,        5        , Structure: a header of a section
hgroup       ,        5        , Structure: a group of headings
hr           ,E S T F 5        , horizontal line
html         ,  S T F 5        , document
i            ,  S T F 5   I    , italic text
iframe       ,    T F 5   I    , inline frame
img          ,E S T F 5   I    , image
input        ,E S T F 5   I   B, input control
ins          ,  S T F 5   I    , inserted text
isindex      ,    T F   D      , searchable index related to a document
kbd          ,  S T F 5   I    , keyboard text
label        ,  S T F 5   I   B, label for input or other element
legend       ,  S T F 5       B, caption for a fieldset element
li           ,  S T F 5        , list item
link         ,E S T F 5     M  , relationship with an external resource
listing      ,          D      , preformated text
main         ,        5        , identify central topic/functional content
map          ,  S T F 5   I    , image-map
mark         ,        5   I    , Text marked/highlighted for reference purposes
menu         ,    T F 5 D      , menu list
menuitem     ,E       5 D      , a command in a menu
meta         ,E S T F 5     M  , metadata
meter        ,        5   I    , a linear guage for a scaler value
nav          ,        5        , Structure: container for navigational links
nobr         ,          D I    , contained text; white-space: nowrap
noframes     ,    T F   D     B, alternate content where frames not supported
noscript     ,  S T F 5   I   B, alternate content script not supported
object       ,  S T F 5   I   B, embedded object
ol           ,  S T F 5        , ordered list
optgroup     ,  S T F 5       B, group of related options in a select list
option       ,  S T F 5       B, option in a select list
output       ,        5   I    , content is (scripted) outcome of a user action.
p            ,  S T F 5        , paragraph
param        ,E S T F 5        , parameter for an object
picture      ,        5   I    , container for multiple img/source DPI
plaintext    ,          D      , like xmp; no close tag
pre          ,  S T F 5        , preformatted text
progress     ,        5   I    , a progress bar
q            ,  S T F 5   I    , short quotation
rb           ,        5        , ruby base text
rbc          ,        5         U, ruby base container (complex)
rp           ,        5        , ruby simple text container
rt           ,        5        , ruby annotation text
rtc          ,        5        , ruby text container (complex)
ruby         ,        5   I    , ruby pronunciation aid
s            ,    T F 5 D I    , strikethrough text
samp         ,  S T F 5   I    , sample computer code
script       ,  S T F 5   I   B, client-side script
section      ,        5        , Structure: generic document/application section
select       ,  S T F 5   I   B, select list (drop-down list)
slot         ,        5   I   B, (Shadow) DOM placeholder element
small        ,  S T F 5   I    , small text
source       ,E       5        , source for picture/audio/video elements
span         ,  S T F 5   I    , section in a document
strike       ,    T F   D I    , strikethrough text
strong       ,  S T F 5   I    , strong text
style        ,  S T F 5       B, style information for a document
sub          ,  S T F 5   I    , subscripted text
summary      ,        5        , summary of details element
sup          ,  S T F 5   I    , superscripted text
svg          ,        5        , inline scalable vector graphics
table        ,  S T F 5        , table
tbody        ,  S T F 5        , Groups the body content in a table
td           ,  S T F 5        , cell in a table
template     ,        5       B, html sub-tree notrenderered except by script
textarea     ,  S T F 5   I   B, multi-line text input control
tfoot        ,  S T F 5        , Groups the footer content in a table
th           ,  S T F 5        , header cell in a table
thead        ,  S T F 5        , Groups the header content in a table
time         ,        5   I    , A date or time
title        ,  S T F 5     M  , the title of a document
tr           ,  S T F 5        , row in a table
tt           ,  S T F   D I    , teletype text
u            ,    T F 5 D I    , underlined text
ul           ,  S T F 5        , unordered list
var          ,  S T F 5   I    , variable part of a text
video        ,        5   I    , video container
wbr          ,E       5   I    , A line break opportunity
xmp          ,          D      , preformatted text
