module Utf16:sig..end
type byte_order =
| |
Little_endian |
| |
Big_endian |
val from_gen : char Gen.t -> byte_order option -> Sedlexing.lexbufUtf16.from_gen s opt_bo creates a lexbuf from an UTF-16 encoded stream.
If opt_bo matches with None the function expects a BOM (Byte Order
Mark), and takes the byte order as Utf16.Big_endian if it cannot find
one. When opt_bo matches with Some bo, bo is taken as byte order. In
this case a leading BOM is kept in the stream - the lexer has to ignore it
and a `wrong' BOM (0xfffe) will raise Utf16.InvalidCodepoint.
val from_channel : Stdlib.in_channel -> byte_order option -> Sedlexing.lexbufWorks as Utf16.from_gen with an in_channel.
val from_string : string -> byte_order option -> Sedlexing.lexbufWorks as Utf16.from_gen with a string.
val lexeme : Sedlexing.lexbuf -> byte_order -> bool -> stringutf16_lexeme lb bo bom as Sedlexing.lexeme with a result encoded in
UTF-16 in byte_order bo and starting with a BOM if bom = true.
val sub_lexeme : Sedlexing.lexbuf ->
int -> int -> byte_order -> bool -> stringsub_lexeme lb pos len bo bom as Sedlexing.sub_lexeme with a result
encoded in UTF-16 with byte order bo and starting with a BOM if
bom=true