Add interface for custom readers written in Lua. (#7671)

New module Text.Pandoc.Readers.Custom, exporting
readCustom [API change].

Users can now do `-f myreader.lua` and pandoc will treat the
script myreader.lua as a custom reader, which parses an input
string to a pandoc AST, using the pandoc module defined for
Lua filters.

A sample custom reader can be found in data/reader.lua.

Closes #7669.

2 files changed, 63 insertions, 5 deletions

diff --git a/src/Text/Pandoc/App.hs b/src/Text/Pandoc/App.hs
index 20e647456..9eb9c2cf3 100644
--- a/src/Text/Pandoc/App.hs
+++ b/src/Text/Pandoc/App.hs
@@ -68,6 +68,7 @@ import Text.Pandoc.Shared (eastAsianLineBreakFilter, stripEmptyParagraphs,
          defaultUserDataDir, tshow)
 import Text.Pandoc.Writers.Shared (lookupMetaString)
 import Text.Pandoc.Readers.Markdown (yamlToMeta)
+import Text.Pandoc.Readers.Custom (readCustom)
 import qualified Text.Pandoc.UTF8 as UTF8
 #ifndef _WINDOWS
 import System.Posix.IO (stdOutput)
@@ -154,11 +155,13 @@ convertWithOpts opts = do
                             -> ByteStringReader $ \o t -> sandbox files (r o t)
 
     (reader, readerExts) <-
-      if optSandbox opts
-         then case runPure (getReader readerName) of
-                Left e -> throwError e
-                Right (r, rexts) -> return (makeSandboxed r, rexts)
-         else getReader readerName
+      if ".lua" `T.isSuffixOf` readerName
+         then return (TextReader (readCustom (T.unpack readerName)), mempty)
+         else if optSandbox opts
+                 then case runPure (getReader readerName) of
+                        Left e -> throwError e
+                        Right (r, rexts) -> return (makeSandboxed r, rexts)
+                 else getReader readerName
 
     outputSettings <- optToOutputSettings opts
     let format = outputFormat outputSettings
diff --git a/src/Text/Pandoc/Readers/Custom.hs b/src/Text/Pandoc/Readers/Custom.hs
new file mode 100644
index 000000000..83d82a9cc
--- /dev/null
+++ b/src/Text/Pandoc/Readers/Custom.hs
@@ -0,0 +1,55 @@
+{-# LANGUAGE FlexibleContexts    #-}
+{-# LANGUAGE FlexibleInstances   #-}
+{-# LANGUAGE OverloadedStrings   #-}
+{-# LANGUAGE ScopedTypeVariables #-}
+{-# LANGUAGE TypeApplications    #-}
+{- |
+   Module      : Text.Pandoc.Readers.Custom
+   Copyright   : Copyright (C) 2021 John MacFarlane
+   License     : GNU GPL, version 2 or above
+
+   Maintainer  : John MacFarlane <jgm@berkeley.edu>
+   Stability   : alpha
+   Portability : portable
+
+Supports custom parsers written in Lua which produce a Pandoc AST.
+-}
+module Text.Pandoc.Readers.Custom ( readCustom ) where
+import Control.Exception
+import Control.Monad (when)
+import Data.Text (Text)
+import HsLua as Lua hiding (Operation (Div), render)
+import HsLua.Class.Peekable (PeekError)
+import Control.Monad.IO.Class (MonadIO)
+import Text.Pandoc.Definition
+import Text.Pandoc.Lua (Global (..), runLua, setGlobals)
+import Text.Pandoc.Lua.Util (dofileWithTraceback)
+import Text.Pandoc.Options
+import Text.Pandoc.Class (PandocMonad)
+import Text.Pandoc.Sources (ToSources(..), sourcesToText)
+
+-- | Convert custom markup to Pandoc.
+readCustom :: (PandocMonad m, MonadIO m, ToSources s)
+            => FilePath -> ReaderOptions -> s -> m Pandoc
+readCustom luaFile opts sources = do
+  let input = sourcesToText $ toSources sources
+  let globals = [ PANDOC_SCRIPT_FILE luaFile
+                , PANDOC_READER_OPTIONS opts
+                ]
+  res <- runLua $ do
+    setGlobals globals
+    stat <- dofileWithTraceback luaFile
+    -- check for error in lua script (later we'll change the return type
+    -- to handle this more gracefully):
+    when (stat /= Lua.OK)
+      Lua.throwErrorAsException
+    parseCustom input
+  case res of
+    Left msg -> throw msg
+    Right doc -> return doc
+
+parseCustom :: forall e. PeekError e
+            => Text
+            -> LuaE e Pandoc
+parseCustom = invoke @e "Reader"
+