1
0
Fork 0
mirror of https://codeberg.org/icewind/bitbuffer.git synced 2026-06-03 16:44:06 +02:00

add feature to disable checking strings for valid utf8

This commit is contained in:
Robin Appelman 2019-03-08 22:28:06 +01:00
commit bb54b1c917
2 changed files with 68 additions and 48 deletions

View file

@ -17,4 +17,7 @@ bitstream_reader_derive = { version = "0.4", path = "bitstream_reader_derive" }
[dev-dependencies]
maplit = "1.0.1"
[features]
unchecked_utf8 = []
[workspace]

View file

@ -8,10 +8,10 @@ use std::rc::Rc;
use num_traits::{Float, PrimInt};
use crate::{ReadError, Result};
use crate::endianness::Endianness;
use crate::is_signed::IsSigned;
use crate::unchecked_primitive::{UncheckedPrimitiveFloat, UncheckedPrimitiveInt};
use crate::{ReadError, Result};
const USIZE_SIZE: usize = size_of::<usize>();
@ -349,6 +349,12 @@ where
///
/// You can either read a fixed number of bytes, or a dynamic length null-terminated string
///
/// # Features
///
/// To disable the overhead of checking if the read bytes are valid you can enable the `unchecked_utf8`
/// feature of the crate to use `String::from_utf8_unchecked` instead of `String::from_utf8`
/// to create the string from the read bytes.
///
/// # Errors
///
/// - [`ReadError::NotEnoughData`]: not enough bits available in the buffer
@ -381,19 +387,32 @@ where
/// [`ReadError::NotEnoughData`]: enum.ReadError.html#variant.NotEnoughData
/// [`ReadError::Utf8Error`]: enum.ReadError.html#variant.Utf8Error
pub fn read_string(&self, position: usize, byte_len: Option<usize>) -> Result<String> {
let bytes = self.read_string_bytes(position, byte_len)?;
let raw_string = String::from_utf8(bytes)?;
if byte_len.is_some() {
Ok(raw_string.trim_end_matches(char::from(0)).to_owned())
match byte_len {
Some(byte_len) => {
let bytes = self.read_bytes(position, byte_len)?;
let raw_string = if cfg!(feature = "unchecked_utf8") {
unsafe {
String::from_utf8_unchecked(bytes)
}
} else {
Ok(raw_string)
String::from_utf8(bytes)?
};
Ok(raw_string.trim_end_matches(char::from(0)).to_owned())
},
None => {
let bytes = self.read_string_bytes(position);
if cfg!(feature = "unchecked_utf8") {
unsafe {
Ok(String::from_utf8_unchecked(bytes))
}
} else {
String::from_utf8(bytes).map_err(ReadError::from)
}
}
}
}
fn read_string_bytes(&self, position: usize, byte_len: Option<usize>) -> Result<Vec<u8>> {
match byte_len {
Some(len) => return self.read_bytes(position, len),
None => {
fn read_string_bytes(&self, position: usize) -> Vec<u8> {
let mut acc = Vec::with_capacity(25);
let mut pos = position;
loop {
@ -409,15 +428,13 @@ where
let byte = if E::is_le() { bytes[i] } else { bytes[1 + i] };
if byte == 0 {
return Ok(acc);
return acc;
}
acc.push(byte);
}
pos += read;
}
}
};
}
/// Read a sequence of bits from the buffer as float
///