2 files changed, 354 insertions, 348 deletions

diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs
index a393df6d0..6f78242b7 100644
--- a/src/Text/Pandoc/Writers/HTML.hs
+++ b/src/Text/Pandoc/Writers/HTML.hs
@@ -54,7 +54,8 @@ import Text.Pandoc.Templates (renderTemplate)
 import Text.Pandoc.Walk
 import Text.Pandoc.Writers.Math
 import Text.Pandoc.Writers.Shared
-import Text.Pandoc.XML (escapeStringForXML, fromEntities, toEntities)
+import Text.Pandoc.XML (escapeStringForXML, fromEntities, toEntities,
+                        html5Attributes, html4Attributes, rdfaAttributes)
 import qualified Text.Blaze.XHtml5 as H5
 import qualified Text.Blaze.XHtml5.Attributes as A5
 import Control.Monad.Except (throwError)
@@ -1310,349 +1311,3 @@ isRawHtml f = do
   return $ f == Format "html" ||
            ((html5 && f == Format "html5") || f == Format "html4")
 
-html5Attributes :: Set.Set Text
-html5Attributes = Set.fromList
-  [ "abbr"
-  , "accept"
-  , "accept-charset"
-  , "accesskey"
-  , "action"
-  , "allowfullscreen"
-  , "allowpaymentrequest"
-  , "allowusermedia"
-  , "alt"
-  , "as"
-  , "async"
-  , "autocomplete"
-  , "autofocus"
-  , "autoplay"
-  , "charset"
-  , "checked"
-  , "cite"
-  , "class"
-  , "color"
-  , "cols"
-  , "colspan"
-  , "content"
-  , "contenteditable"
-  , "controls"
-  , "coords"
-  , "crossorigin"
-  , "data"
-  , "datetime"
-  , "default"
-  , "defer"
-  , "dir"
-  , "dirname"
-  , "disabled"
-  , "download"
-  , "draggable"
-  , "enctype"
-  , "for"
-  , "form"
-  , "formaction"
-  , "formenctype"
-  , "formmethod"
-  , "formnovalidate"
-  , "formtarget"
-  , "headers"
-  , "height"
-  , "hidden"
-  , "high"
-  , "href"
-  , "hreflang"
-  , "http-equiv"
-  , "id"
-  , "inputmode"
-  , "integrity"
-  , "is"
-  , "ismap"
-  , "itemid"
-  , "itemprop"
-  , "itemref"
-  , "itemscope"
-  , "itemtype"
-  , "kind"
-  , "label"
-  , "lang"
-  , "list"
-  , "loop"
-  , "low"
-  , "manifest"
-  , "max"
-  , "maxlength"
-  , "media"
-  , "method"
-  , "min"
-  , "minlength"
-  , "multiple"
-  , "muted"
-  , "name"
-  , "nomodule"
-  , "nonce"
-  , "novalidate"
-  , "onabort"
-  , "onafterprint"
-  , "onauxclick"
-  , "onbeforeprint"
-  , "onbeforeunload"
-  , "onblur"
-  , "oncancel"
-  , "oncanplay"
-  , "oncanplaythrough"
-  , "onchange"
-  , "onclick"
-  , "onclose"
-  , "oncontextmenu"
-  , "oncopy"
-  , "oncuechange"
-  , "oncut"
-  , "ondblclick"
-  , "ondrag"
-  , "ondragend"
-  , "ondragenter"
-  , "ondragexit"
-  , "ondragleave"
-  , "ondragover"
-  , "ondragstart"
-  , "ondrop"
-  , "ondurationchange"
-  , "onemptied"
-  , "onended"
-  , "onerror"
-  , "onfocus"
-  , "onhashchange"
-  , "oninput"
-  , "oninvalid"
-  , "onkeydown"
-  , "onkeypress"
-  , "onkeyup"
-  , "onlanguagechange"
-  , "onload"
-  , "onloadeddata"
-  , "onloadedmetadata"
-  , "onloadend"
-  , "onloadstart"
-  , "onmessage"
-  , "onmessageerror"
-  , "onmousedown"
-  , "onmouseenter"
-  , "onmouseleave"
-  , "onmousemove"
-  , "onmouseout"
-  , "onmouseover"
-  , "onmouseup"
-  , "onoffline"
-  , "ononline"
-  , "onpagehide"
-  , "onpageshow"
-  , "onpaste"
-  , "onpause"
-  , "onplay"
-  , "onplaying"
-  , "onpopstate"
-  , "onprogress"
-  , "onratechange"
-  , "onrejectionhandled"
-  , "onreset"
-  , "onresize"
-  , "onscroll"
-  , "onsecuritypolicyviolation"
-  , "onseeked"
-  , "onseeking"
-  , "onselect"
-  , "onstalled"
-  , "onstorage"
-  , "onsubmit"
-  , "onsuspend"
-  , "ontimeupdate"
-  , "ontoggle"
-  , "onunhandledrejection"
-  , "onunload"
-  , "onvolumechange"
-  , "onwaiting"
-  , "onwheel"
-  , "open"
-  , "optimum"
-  , "pattern"
-  , "ping"
-  , "placeholder"
-  , "playsinline"
-  , "poster"
-  , "preload"
-  , "readonly"
-  , "referrerpolicy"
-  , "rel"
-  , "required"
-  , "reversed"
-  , "role"
-  , "rows"
-  , "rowspan"
-  , "sandbox"
-  , "scope"
-  , "selected"
-  , "shape"
-  , "size"
-  , "sizes"
-  , "slot"
-  , "span"
-  , "spellcheck"
-  , "src"
-  , "srcdoc"
-  , "srclang"
-  , "srcset"
-  , "start"
-  , "step"
-  , "style"
-  , "tabindex"
-  , "target"
-  , "title"
-  , "translate"
-  , "type"
-  , "typemustmatch"
-  , "updateviacache"
-  , "usemap"
-  , "value"
-  , "width"
-  , "workertype"
-  , "wrap"
-  ]
-
--- See https://en.wikipedia.org/wiki/RDFa, https://www.w3.org/TR/rdfa-primer/
-rdfaAttributes :: Set.Set Text
-rdfaAttributes = Set.fromList
-  [ "about"
-  , "rel"
-  , "rev"
-  , "src"
-  , "href"
-  , "resource"
-  , "property"
-  , "content"
-  , "datatype"
-  , "typeof"
-  , "vocab"
-  , "prefix"
-  ]
-
-html4Attributes :: Set.Set Text
-html4Attributes = Set.fromList
-  [ "abbr"
-  , "accept"
-  , "accept-charset"
-  , "accesskey"
-  , "action"
-  , "align"
-  , "alink"
-  , "alt"
-  , "archive"
-  , "axis"
-  , "background"
-  , "bgcolor"
-  , "border"
-  , "cellpadding"
-  , "cellspacing"
-  , "char"
-  , "charoff"
-  , "charset"
-  , "checked"
-  , "cite"
-  , "class"
-  , "classid"
-  , "clear"
-  , "code"
-  , "codebase"
-  , "codetype"
-  , "color"
-  , "cols"
-  , "colspan"
-  , "compact"
-  , "content"
-  , "coords"
-  , "data"
-  , "datetime"
-  , "declare"
-  , "defer"
-  , "dir"
-  , "disabled"
-  , "enctype"
-  , "face"
-  , "for"
-  , "frame"
-  , "frameborder"
-  , "headers"
-  , "height"
-  , "href"
-  , "hreflang"
-  , "hspace"
-  , "http-equiv"
-  , "id"
-  , "ismap"
-  , "label"
-  , "lang"
-  , "language"
-  , "link"
-  , "longdesc"
-  , "marginheight"
-  , "marginwidth"
-  , "maxlength"
-  , "media"
-  , "method"
-  , "multiple"
-  , "name"
-  , "nohref"
-  , "noresize"
-  , "noshade"
-  , "nowrap"
-  , "object"
-  , "onblur"
-  , "onchange"
-  , "onclick"
-  , "ondblclick"
-  , "onfocus"
-  , "onkeydown"
-  , "onkeypress"
-  , "onkeyup"
-  , "onload"
-  , "onmousedown"
-  , "onmousemove"
-  , "onmouseout"
-  , "onmouseover"
-  , "onmouseup"
-  , "onreset"
-  , "onselect"
-  , "onsubmit"
-  , "onunload"
-  , "profile"
-  , "prompt"
-  , "readonly"
-  , "rel"
-  , "rev"
-  , "rows"
-  , "rowspan"
-  , "rules"
-  , "scheme"
-  , "scope"
-  , "scrolling"
-  , "selected"
-  , "shape"
-  , "size"
-  , "span"
-  , "src"
-  , "standby"
-  , "start"
-  , "style"
-  , "summary"
-  , "tabindex"
-  , "target"
-  , "text"
-  , "title"
-  , "usemap"
-  , "valign"
-  , "value"
-  , "valuetype"
-  , "version"
-  , "vlink"
-  , "vspace"
-  , "width"
-  ]
diff --git a/src/Text/Pandoc/XML.hs b/src/Text/Pandoc/XML.hs
index 21f6d4d46..64dd62c0f 100644
--- a/src/Text/Pandoc/XML.hs
+++ b/src/Text/Pandoc/XML.hs
@@ -20,7 +20,10 @@ module Text.Pandoc.XML ( escapeCharForXML,
                          inTagsIndented,
                          toEntities,
                          toHtml5Entities,
-                         fromEntities ) where
+                         fromEntities,
+                         html4Attributes,
+                         html5Attributes,
+                         rdfaAttributes ) where
 
 import Prelude
 import Data.Char (isAscii, isSpace, ord)
@@ -31,6 +34,7 @@ import Text.DocLayout
 import Text.Printf (printf)
 import qualified Data.Map as M
 import Data.String
+import qualified Data.Set as Set
 
 -- | Escape one character as needed for XML.
 escapeCharForXML :: Char -> Text
@@ -137,3 +141,350 @@ fromEntities' (T.uncons -> Just ('&', xs)) =
 fromEntities' t = case T.uncons t of
   Just (x, xs) -> x : fromEntities' xs
   Nothing      -> ""
+
+html5Attributes :: Set.Set Text
+html5Attributes = Set.fromList
+  [ "abbr"
+  , "accept"
+  , "accept-charset"
+  , "accesskey"
+  , "action"
+  , "allowfullscreen"
+  , "allowpaymentrequest"
+  , "allowusermedia"
+  , "alt"
+  , "as"
+  , "async"
+  , "autocomplete"
+  , "autofocus"
+  , "autoplay"
+  , "charset"
+  , "checked"
+  , "cite"
+  , "class"
+  , "color"
+  , "cols"
+  , "colspan"
+  , "content"
+  , "contenteditable"
+  , "controls"
+  , "coords"
+  , "crossorigin"
+  , "data"
+  , "datetime"
+  , "default"
+  , "defer"
+  , "dir"
+  , "dirname"
+  , "disabled"
+  , "download"
+  , "draggable"
+  , "enctype"
+  , "for"
+  , "form"
+  , "formaction"
+  , "formenctype"
+  , "formmethod"
+  , "formnovalidate"
+  , "formtarget"
+  , "headers"
+  , "height"
+  , "hidden"
+  , "high"
+  , "href"
+  , "hreflang"
+  , "http-equiv"
+  , "id"
+  , "inputmode"
+  , "integrity"
+  , "is"
+  , "ismap"
+  , "itemid"
+  , "itemprop"
+  , "itemref"
+  , "itemscope"
+  , "itemtype"
+  , "kind"
+  , "label"
+  , "lang"
+  , "list"
+  , "loop"
+  , "low"
+  , "manifest"
+  , "max"
+  , "maxlength"
+  , "media"
+  , "method"
+  , "min"
+  , "minlength"
+  , "multiple"
+  , "muted"
+  , "name"
+  , "nomodule"
+  , "nonce"
+  , "novalidate"
+  , "onabort"
+  , "onafterprint"
+  , "onauxclick"
+  , "onbeforeprint"
+  , "onbeforeunload"
+  , "onblur"
+  , "oncancel"
+  , "oncanplay"
+  , "oncanplaythrough"
+  , "onchange"
+  , "onclick"
+  , "onclose"
+  , "oncontextmenu"
+  , "oncopy"
+  , "oncuechange"
+  , "oncut"
+  , "ondblclick"
+  , "ondrag"
+  , "ondragend"
+  , "ondragenter"
+  , "ondragexit"
+  , "ondragleave"
+  , "ondragover"
+  , "ondragstart"
+  , "ondrop"
+  , "ondurationchange"
+  , "onemptied"
+  , "onended"
+  , "onerror"
+  , "onfocus"
+  , "onhashchange"
+  , "oninput"
+  , "oninvalid"
+  , "onkeydown"
+  , "onkeypress"
+  , "onkeyup"
+  , "onlanguagechange"
+  , "onload"
+  , "onloadeddata"
+  , "onloadedmetadata"
+  , "onloadend"
+  , "onloadstart"
+  , "onmessage"
+  , "onmessageerror"
+  , "onmousedown"
+  , "onmouseenter"
+  , "onmouseleave"
+  , "onmousemove"
+  , "onmouseout"
+  , "onmouseover"
+  , "onmouseup"
+  , "onoffline"
+  , "ononline"
+  , "onpagehide"
+  , "onpageshow"
+  , "onpaste"
+  , "onpause"
+  , "onplay"
+  , "onplaying"
+  , "onpopstate"
+  , "onprogress"
+  , "onratechange"
+  , "onrejectionhandled"
+  , "onreset"
+  , "onresize"
+  , "onscroll"
+  , "onsecuritypolicyviolation"
+  , "onseeked"
+  , "onseeking"
+  , "onselect"
+  , "onstalled"
+  , "onstorage"
+  , "onsubmit"
+  , "onsuspend"
+  , "ontimeupdate"
+  , "ontoggle"
+  , "onunhandledrejection"
+  , "onunload"
+  , "onvolumechange"
+  , "onwaiting"
+  , "onwheel"
+  , "open"
+  , "optimum"
+  , "pattern"
+  , "ping"
+  , "placeholder"
+  , "playsinline"
+  , "poster"
+  , "preload"
+  , "readonly"
+  , "referrerpolicy"
+  , "rel"
+  , "required"
+  , "reversed"
+  , "role"
+  , "rows"
+  , "rowspan"
+  , "sandbox"
+  , "scope"
+  , "selected"
+  , "shape"
+  , "size"
+  , "sizes"
+  , "slot"
+  , "span"
+  , "spellcheck"
+  , "src"
+  , "srcdoc"
+  , "srclang"
+  , "srcset"
+  , "start"
+  , "step"
+  , "style"
+  , "tabindex"
+  , "target"
+  , "title"
+  , "translate"
+  , "type"
+  , "typemustmatch"
+  , "updateviacache"
+  , "usemap"
+  , "value"
+  , "width"
+  , "workertype"
+  , "wrap"
+  ]
+
+-- See https://en.wikipedia.org/wiki/RDFa, https://www.w3.org/TR/rdfa-primer/
+rdfaAttributes :: Set.Set Text
+rdfaAttributes = Set.fromList
+  [ "about"
+  , "rel"
+  , "rev"
+  , "src"
+  , "href"
+  , "resource"
+  , "property"
+  , "content"
+  , "datatype"
+  , "typeof"
+  , "vocab"
+  , "prefix"
+  ]
+
+html4Attributes :: Set.Set Text
+html4Attributes = Set.fromList
+  [ "abbr"
+  , "accept"
+  , "accept-charset"
+  , "accesskey"
+  , "action"
+  , "align"
+  , "alink"
+  , "alt"
+  , "archive"
+  , "axis"
+  , "background"
+  , "bgcolor"
+  , "border"
+  , "cellpadding"
+  , "cellspacing"
+  , "char"
+  , "charoff"
+  , "charset"
+  , "checked"
+  , "cite"
+  , "class"
+  , "classid"
+  , "clear"
+  , "code"
+  , "codebase"
+  , "codetype"
+  , "color"
+  , "cols"
+  , "colspan"
+  , "compact"
+  , "content"
+  , "coords"
+  , "data"
+  , "datetime"
+  , "declare"
+  , "defer"
+  , "dir"
+  , "disabled"
+  , "enctype"
+  , "face"
+  , "for"
+  , "frame"
+  , "frameborder"
+  , "headers"
+  , "height"
+  , "href"
+  , "hreflang"
+  , "hspace"
+  , "http-equiv"
+  , "id"
+  , "ismap"
+  , "label"
+  , "lang"
+  , "language"
+  , "link"
+  , "longdesc"
+  , "marginheight"
+  , "marginwidth"
+  , "maxlength"
+  , "media"
+  , "method"
+  , "multiple"
+  , "name"
+  , "nohref"
+  , "noresize"
+  , "noshade"
+  , "nowrap"
+  , "object"
+  , "onblur"
+  , "onchange"
+  , "onclick"
+  , "ondblclick"
+  , "onfocus"
+  , "onkeydown"
+  , "onkeypress"
+  , "onkeyup"
+  , "onload"
+  , "onmousedown"
+  , "onmousemove"
+  , "onmouseout"
+  , "onmouseover"
+  , "onmouseup"
+  , "onreset"
+  , "onselect"
+  , "onsubmit"
+  , "onunload"
+  , "profile"
+  , "prompt"
+  , "readonly"
+  , "rel"
+  , "rev"
+  , "rows"
+  , "rowspan"
+  , "rules"
+  , "scheme"
+  , "scope"
+  , "scrolling"
+  , "selected"
+  , "shape"
+  , "size"
+  , "span"
+  , "src"
+  , "standby"
+  , "start"
+  , "style"
+  , "summary"
+  , "tabindex"
+  , "target"
+  , "text"
+  , "title"
+  , "usemap"
+  , "valign"
+  , "value"
+  , "valuetype"
+  , "version"
+  , "vlink"
+  , "vspace"
+  , "width"
+  ]