From d19a347fd5e93802e80e5bd8e13f29de74a53f3c Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Tue, 5 May 2015 12:41:35 -0700 Subject: UTF8: Better handling of bare CRs in input files. Previously we just stripped them out; now we convert other line ending styles to LF line endings. Closes #2132. --- src/Text/Pandoc/UTF8.hs | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/src/Text/Pandoc/UTF8.hs b/src/Text/Pandoc/UTF8.hs index c1bf84995..de3314a0d 100644 --- a/src/Text/Pandoc/UTF8.hs +++ b/src/Text/Pandoc/UTF8.hs @@ -93,10 +93,16 @@ dropBOM :: String -> String dropBOM ('\xFEFF':xs) = xs dropBOM xs = xs +filterCRs :: String -> String +filterCRs ('\r':'\n':xs) = '\n': filterCRs xs +filterCRs ('\r':xs) = '\n' : filterCRs xs +filterCRs (x:xs) = x : filterCRs xs +filterCRs [] = [] + -- | Convert UTF8-encoded ByteString to String, also -- removing '\r' characters. toString :: B.ByteString -> String -toString = filter (/='\r') . dropBOM . T.unpack . T.decodeUtf8 +toString = filterCRs . dropBOM . T.unpack . T.decodeUtf8 fromString :: String -> B.ByteString fromString = T.encodeUtf8 . T.pack @@ -104,7 +110,7 @@ fromString = T.encodeUtf8 . T.pack -- | Convert UTF8-encoded ByteString to String, also -- removing '\r' characters. toStringLazy :: BL.ByteString -> String -toStringLazy = filter (/='\r') . dropBOM . TL.unpack . TL.decodeUtf8 +toStringLazy = filterCRs . dropBOM . TL.unpack . TL.decodeUtf8 fromStringLazy :: String -> BL.ByteString fromStringLazy = TL.encodeUtf8 . TL.pack -- cgit v1.2.3