02dfcda · typeable/pandoc

git.iko.soy/typeable/pandoc

Ipnyb: allow lossless round-tripping of markdown cell content.

The reader now parses the contents of the markdown cell to a Pandoc structure, but *also* stores the raw markdown in a `source` attribute on the cell Div. When we convert back to markdown, this attribute is stripped off and the original source is used. When we convert to other formats, the attribute is usually ignored (though it will come through in HTML as a `data-source` attribute, not unhelpfully). I'll note some potential drawbacks of this approach: - It makes it impossible to use pandoc to clean up or change the contents of markdown cells, e.g. going from `+smart` to `-smart`. - There may be formats where the addition of the `source` attribute is problematic. I can't think of any, though. Closes #5408.

commit02dfcdafb9ee237276dd29a556346b86e78587fd authorJohn MacFarlane <jgm@berkeley.edu> dateTue 30 Jun 2020, 12:12 (6 years ago) parentd3db10b

3 files changed+10−6

compare with master

unifiedsplit

src/Text/Pandoc/Readers/Ipynb.hs+2−1 src/Text/Pandoc/Writers/Ipynb.hs+5−2 test/ipynb/simple.out.native+3−3

src/Text/Pandoc/Readers/Ipynb.hs+2−1

@@ -79,7 +79,8 @@ cellToBlocks opts lang c = do

7979 case cellType c of

8080 Ipynb.Markdown -> do

8181 Pandoc _ bs <- walk fixImage <$> readMarkdown opts source

82− return $ B.divWith ("",["cell","markdown"],kvs)

82+ let kvs' = ("source", source) : kvs

83+ return $ B.divWith ("",["cell","markdown"],kvs')

8384 $ B.fromList bs

8485 Ipynb.Heading lev -> do

8586 Pandoc _ bs <- readMarkdown opts

src/Text/Pandoc/Writers/Ipynb.hs+5−2

@@ -102,10 +102,13 @@ extractCells _ [] = return []

102102extractCells opts (Div (_id,classes,kvs) xs : bs)

103103 | "cell" `elem` classes

104104 , "markdown" `elem` classes = do

105− let meta = pairsToJSONMeta kvs

105+ let meta = pairsToJSONMeta [(k,v) | (k,v) <- kvs, k /= "source"]

106106 (newdoc, attachments) <-

107107 runStateT (walkM addAttachment (Pandoc nullMeta xs)) mempty

108− source <- writeMarkdown opts{ writerTemplate = Nothing } newdoc

108+ source <- case lookup "source" kvs of

109+ Just s -> return s

110+ Nothing -> writeMarkdown opts{ writerTemplate = Nothing }

111+ newdoc

109112 (Ipynb.Cell{

110113 cellType = Markdown

111114 , cellSource = Source $ breakLines $ T.stripEnd source

test/ipynb/simple.out.native+3−3

@@ -1,15 +1,15 @@

11Pandoc (Meta {unMeta = fromList [("jupyter",MetaMap (fromList [("nbformat",MetaString "4"),("nbformat_minor",MetaString "5")]))]})

2−[Div ("",["cell","markdown"],[])

2+[Div ("",["cell","markdown"],[("source","Lorem ipsum\n===========\n\n**Lorem ipsum** dolor sit amet, consectetur adipiscing elit. Nunc luctus\nbibendum felis dictum sodales.")])

33 [Header 1 ("lorem-ipsum",[],[]) [Str "Lorem",Space,Str "ipsum"]

44 ,Para [Strong [Str "Lorem",Space,Str "ipsum"],Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipiscing",Space,Str "elit.",Space,Str "Nunc",Space,Str "luctus",SoftBreak,Str "bibendum",Space,Str "felis",Space,Str "dictum",Space,Str "sodales."]]

55,Div ("",["cell","code"],[])

66 [CodeBlock ("",["python"],[]) "print(\"hello\")"]

7−,Div ("",["cell","markdown"],[])

7+,Div ("",["cell","markdown"],[("source","Pyout\n-----")])

88 [Header 2 ("pyout",[],[]) [Str "Pyout"]]

99,Div ("",["cell","code"],[("execution_count","2")])

1010 [CodeBlock ("",["python"],[]) "from IPython.display import HTML\nHTML(\"\"\"\n<script>\nconsole.log(\"hello\");\n</script>\n<b>HTML</b>\n\"\"\")"

1111 ,Div ("",["output","execute_result"],[("execution_count","2")])

1212 [RawBlock (Format "html") "<script>\nconsole.log(\"hello\");\n</script>\n<b>HTML</b>\nhello"]]

13−,Div ("",["cell","markdown"],[("tags","[\"foo\",\"bar\"]")])

13+,Div ("",["cell","markdown"],[("source","Image\n-----\n\nThis image ![the moon](attachment:lalune.jpg) will be included as a cell\nattachment."),("tags","[\"foo\",\"bar\"]")])

1414 [Header 2 ("image",[],[]) [Str "Image"]

1515 ,Para [Str "This",Space,Str "image",Space,Image ("",[],[]) [Str "the",Space,Str "moon"] ("lalune.jpg",""),Space,Str "will",Space,Str "be",Space,Str "included",Space,Str "as",Space,Str "a",Space,Str "cell",SoftBreak,Str "attachment."]]]