blob: 5783a728431b61073dbdb2db4105afca8f427ce3 (
plain)
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
|
module Main where
import Control.Exception
import Data.Char
import System.IO
import StringBuffer
twoBOMs = "T6016-twoBOMs"
ignoreFirstBOM = do
-- StringBuffer should not contain initial byte-order mark.
--
-- Just skipping over it, but leaving it in the Stringbuffer, is not
-- sufficient. The Lexer calls prevChar when a regular expression
-- starts with '^' (which is a shorthand for '\n^'). It would never
-- match on the first line, since instead of '\n', prevChar would
-- still return '\xfeff'.
s <- hGetStringBuffer twoBOMs
assert (prevChar s '\n' == '\n') return ()
dontIgnoreSecondBOM = do
-- U+FEFF is considered a BOM only if it appears as the first
-- character of a file.
h <- openBinaryFile twoBOMs ReadMode
hSeek h AbsoluteSeek 3
s <- hGetStringBufferBlock h 3
hClose h
assert (currentChar s == '\xfeff') return ()
main = do
writeFile twoBOMs "\xfeff\xfeff"
ignoreFirstBOM
dontIgnoreSecondBOM
|
