~alcinnz/hurl

ref: e2baa089b2804d10074262a84260914bfe3d8590 hurl/src/Network/URI/Charset.hs -rw-r--r-- 2.0 KiB
e2baa089 — Adrian Cochrane Research how to implement additional protocols. 4 years ago
                                                                                
a7eb27a9 Adrian Cochrane
e0988f7e Adrian Cochrane
a7eb27a9 Adrian Cochrane
47f9ef33 Adrian Cochrane
a7eb27a9 Adrian Cochrane
e0988f7e Adrian Cochrane
a7eb27a9 Adrian Cochrane
e0988f7e Adrian Cochrane
a7eb27a9 Adrian Cochrane
47f9ef33 Adrian Cochrane
e0988f7e Adrian Cochrane
a7eb27a9 Adrian Cochrane
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
{-# LANGUAGE OverloadedStrings #-}

-- | Handles server-specified text decoding.
module Network.URI.Charset(resolveCharset, convertCharset, charsets) where
import           Data.Text (Text)
import           Data.ByteString.Lazy (ByteString)
import qualified Data.ByteString.Lazy as B
import           Data.Text.Encoding
import           Debug.Trace (trace)

-- | If the MIMEtype specifies a charset parameter, apply it.
resolveCharset :: [String] -- ^ The MIMEtype, split by ';'
    -> ByteString -- ^ The bytes received from the server
    -> (String, Either Text ByteString) -- ^ The MIMEtype (minus parameters) & possibly decoded text, to be returned from protocol handlers.
resolveCharset (mime:('c':'h':'a':'r':'s':'e':'t':'=':charset):_) response =
    (mime, Left $ convertCharset charset $ B.toStrict response)
resolveCharset (mime:_:params) response = resolveCharset (mime:params) response
resolveCharset [mime] response = (mime, Right $ response)
resolveCharset [] response = ("text/plain", Left "Filetype unspecified")

-- | Decodes bytes according to a charset identified by it's IANA-assigned name(s).
convertCharset "iso-8859-1" = decodeLatin1
convertCharset "latin1" = decodeLatin1
convertCharset "us-ascii" = decodeUtf8With replaceChar
convertCharset "utf-8" = decodeUtf8With replaceChar
convertCharset "utf-16be" = decodeUtf16BEWith replaceChar
convertCharset "utf-16le" = decodeUtf16LEWith replaceChar
convertCharset "utf-16" = decodeUtf16LEWith replaceChar
convertCharset "utf-32be" = decodeUtf32BEWith replaceChar
convertCharset "utf-32le" = decodeUtf32LEWith replaceChar
convertCharset "utf-32" = decodeUtf32LEWith replaceChar
convertCharset charset = -- FIXME Is this the best fallback for unsupported charsets?
    trace ("Unsupported text encoding" ++ charset) $ decodeUtf8With replaceChar

replaceChar error _ = trace error $ Just '�'

-- | Lists all charsets supported by convertCharset
charsets :: [Text]
charsets = ["iso-8859-1", "latin1", "us-ascii", "utf-8", "utf-16be", "utf-16le", "utf-16", "utf-32be", "utf-32le", "utf-32"]