module Ulexing:sig
..end
This is a lexing buffer for ulex
.
type
lexbuf
exception Error
Lexical error
val from_ulb_lexbuf : Netulex.ULB.unicode_lexbuf -> lexbuf
Creates a new lexbuf
from the unicode_lexbuf
. After that,
the unicode_lexbuf
must no longer be modified.
val lexeme_start : lexbuf -> int
The character position of the start of the lexeme
val lexeme_end : lexbuf -> int
The character position of the end of the lexeme
val lexeme_length : lexbuf -> int
The length of the lexeme in characters
val lexeme : lexbuf -> int array
Returns the lexeme as array of Unicode code points
val lexeme_char : lexbuf -> int -> int
Returns the code point of a certain character of the lexeme
val sub_lexeme : lexbuf -> int -> int -> int array
Returns a substring of the lexeme as array of Unicode
code points. The first int
is the characater position
where to start, the second int
is the number of
characters.
val utf8_lexeme : lexbuf -> string
Returns the lexeme as UTF-8 encoded string
val utf8_sub_lexeme : lexbuf -> int -> int -> string
Returns a substring of the lexeme as UTF-8 encoded
string. The first int
is the characater position
where to start, the second int
is the number of
characters.
val utf8_sub_lexeme_length : lexbuf -> int -> int -> int
Same as String.length(utf8_sub_lexeme args), i.e. returns the number of bytes a certain sub lexeme will have when encoded as UTF-8 string.