Tissevert/pandoc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

HTML reader: keep h1 tags as normal headers (#7274)

Browse source 
The tags `<title>` and `<h1 class="title">` often contain the same
information, so the latter was dropped from the document. However, as
this can lead to loss of information, the heading is now always
retained.

Use `--shift-heading-level-by=-1` to turn the `<h1>` into the document
title, or a filter to restore the previous behavior.

Closes: #2293
This commit is contained in:
Albert Krewinkel 2021-05-14 21:31:24 +02:00 committed by GitHub
parent 247b1cd18b
commit 013e4a3164
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
src/Text/Pandoc/Readers/HTML.hs
View file

@ -499,17 +499,13 @@ pHeader = try $ do
tagOpen (`elem` ["h1","h2","h3","h4","h5","h6"])
(const True)
let attr = toStringAttr attr'
let bodyTitle = TagOpen tagtype attr' ~== TagOpen ("h1" :: Text)
[("class","title")]
level <- headerLevel tagtype
contents <- trimInlines . mconcat <$> manyTill inline (pCloses tagtype <|> eof)
let ident = fromMaybe "" $ lookup "id" attr
let classes = maybe [] T.words $ lookup "class" attr
let keyvals = [(k,v) | (k,v) <- attr, k /= "class", k /= "id"]
attr'' <- registerHeader (ident, classes, keyvals) contents
return $ if bodyTitle
then mempty -- skip a representation of the title in the body
else B.headerWith attr'' level contents
return $ B.headerWith attr'' level contents
pHrule :: PandocMonad m => TagParser m Blocks
pHrule = do

3
test/html-reader.native
View file

@ -1,5 +1,6 @@
Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]})
[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."]
[Header 1 ("pandoc-test-suite",["title"],[]) [Str "Pandoc",Space,Str "Test",Space,Str "Suite"]
,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."]
,HorizontalRule
,Header 1 ("headers",[],[]) [Str "Headers"]
,Header 2 ("level-2-with-an-embedded-link",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link ("",[],[]) [Str "embedded",Space,Str "link"] ("/url","")]