1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
{-# LANGUAGE OverloadedStrings #-}
{- |
Module : Text.Pandoc.Readers.OPML
Copyright : Copyright (C) 2013-2021 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Conversion of OPML to 'Pandoc' document.
-}
module Text.Pandoc.Readers.OPML ( readOPML ) where
import Control.Monad.State.Strict
import Data.Default
import Data.Maybe (fromMaybe)
import Data.Text (Text)
import qualified Data.Text as T
import qualified Data.Text.Lazy as TL
import Text.Pandoc.Builder
import Text.Pandoc.Class.PandocMonad (PandocMonad)
import Text.Pandoc.Options
import Text.Pandoc.Error (PandocError(..))
import Text.Pandoc.Readers.HTML (readHtml)
import Text.Pandoc.Readers.Markdown (readMarkdown)
import Text.Pandoc.Shared (crFilter, blocksToInlines')
import Text.Pandoc.XML.Light
import Control.Monad.Except (throwError)
type OPML m = StateT OPMLState m
data OPMLState = OPMLState{
opmlSectionLevel :: Int
, opmlDocTitle :: Inlines
, opmlDocAuthors :: [Inlines]
, opmlDocDate :: Inlines
, opmlOptions :: ReaderOptions
} deriving Show
instance Default OPMLState where
def = OPMLState{ opmlSectionLevel = 0
, opmlDocTitle = mempty
, opmlDocAuthors = []
, opmlDocDate = mempty
, opmlOptions = def
}
readOPML :: PandocMonad m => ReaderOptions -> Text -> m Pandoc
readOPML opts inp = do
(bs, st') <- runStateT
(case parseXMLContents (TL.fromStrict (crFilter inp)) of
Left msg -> throwError $ PandocXMLError "" msg
Right ns -> mapM parseBlock ns)
def{ opmlOptions = opts }
return $
setTitle (opmlDocTitle st') $
setAuthors (opmlDocAuthors st') $
setDate (opmlDocDate st') $
doc $ mconcat bs
-- convenience function to get an attribute value, defaulting to ""
attrValue :: Text -> Element -> Text
attrValue attr elt =
fromMaybe "" (lookupAttrBy (\x -> qName x == attr) (elAttribs elt))
-- exceptT :: PandocMonad m => Either PandocError a -> OPML m a
-- exceptT = either throwError return
asHtml :: PandocMonad m => Text -> OPML m Inlines
asHtml s = do
opts <- gets opmlOptions
Pandoc _ bs <- readHtml def{ readerExtensions = readerExtensions opts } s
return $ blocksToInlines' bs
asMarkdown :: PandocMonad m => Text -> OPML m Blocks
asMarkdown s = do
opts <- gets opmlOptions
Pandoc _ bs <- readMarkdown def{ readerExtensions = readerExtensions opts } s
return $ fromList bs
getBlocks :: PandocMonad m => Element -> OPML m Blocks
getBlocks e = mconcat <$> mapM parseBlock (elContent e)
parseBlock :: PandocMonad m => Content -> OPML m Blocks
parseBlock (Elem e) =
case qName (elName e) of
"ownerName" -> mempty <$ modify (\st ->
st{opmlDocAuthors = [text $ strContent e]})
"dateModified" -> mempty <$ modify (\st ->
st{opmlDocDate = text $ strContent e})
"title" -> mempty <$ modify (\st ->
st{opmlDocTitle = text $ strContent e})
"outline" -> gets opmlSectionLevel >>= sect . (+1)
"?xml" -> return mempty
_ -> getBlocks e
where sect n = do headerText <- asHtml $ attrValue "text" e
noteBlocks <- asMarkdown $ attrValue "_note" e
modify $ \st -> st{ opmlSectionLevel = n }
bs <- getBlocks e
modify $ \st -> st{ opmlSectionLevel = n - 1 }
let headerText' = case T.toUpper (attrValue "type" e) of
"LINK" -> link
(attrValue "url" e) "" headerText
_ -> headerText
return $ header n headerText' <> noteBlocks <> bs
parseBlock _ = return mempty
|
