Skip to content

PROPOSAL: Follow the DOM spec instead of HTML 5 spec for Attributes. #20

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

PROPOSAL: Follow the DOM spec instead of HTML 5 spec for Attributes. #20

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 46 additions & 4 deletions src/Html/Parser.elm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,10 @@ tagAttribute =

tagAttributeName : Parser String
tagAttributeName =
Parser.getChompedString (chompOneOrMore isTagAttributeCharacter)
Parser.getChompedString
(Parser.chompIf isTagAttributeNameHeadCharacter
|. Parser.chompWhile isTagAttributeNameTailCharacter
)
|> Parser.map String.toLower


Expand Down Expand Up @@ -477,9 +480,48 @@ voidElements =
-- Character validators


isTagAttributeCharacter : Char -> Bool
isTagAttributeCharacter c =
not (isSpaceCharacter c) && c /= '"' && c /= '\'' && c /= '>' && c /= '/' && c /= '='
isTagAttributeNameHeadCharacter : Char -> Bool
isTagAttributeNameHeadCharacter c =
Char.isAlpha c || c == ':' || c == '_' || isExtendedTagAttributeNameHeadCharacter c


isExtendedTagAttributeNameHeadCharacter : Char -> Bool
isExtendedTagAttributeNameHeadCharacter c =
let
code =
Char.toCode c
in
-- Latin extended + Greek
(code >= 0xC0 && code <= 0x02FF)
-- More scripts
|| (code >= 0x0370 && code <= 0x1FFF)
-- Superscripts
|| (code >= 0x2070 && code <= 0x218F)
-- Various scripts + CJK
|| (code >= 0x2C00 && code <= 0xD7FF)
-- Compatibility + presentation
|| (code >= 0xF900 && code <= 0xFFFD)
-- All supplementary planes
|| (code >= 0x00010000)


isTagAttributeNameTailCharacter : Char -> Bool
isTagAttributeNameTailCharacter c =
isTagAttributeNameHeadCharacter c || Char.isDigit c || c == '-' || c == '.' || isExtendedTagAttributeNameTailCharacter c


isExtendedTagAttributeNameTailCharacter : Char -> Bool
isExtendedTagAttributeNameTailCharacter c =
let
code =
Char.toCode c
in
-- Middle dot
(code == 0xB7)
-- Combining marks
|| (code >= 0x0300 && code <= 0x036F)
-- Ties
|| (code >= 0x203F && code <= 0x2040)


isSpaceCharacter : Char -> Bool
Expand Down