Mirrors/servo
1
0
Fork 0
mirror of https://github.com/servo/servo.git synced 2025-07-30 02:30:21 +01:00
Code Issues Projects Releases Packages Wiki Activity

Use byte indices instead of char indices for text runs

Browse source 
Replace character indices with UTF-8 byte offsets throughout the code dealing
with text shaping and breaking.  This eliminates a lot of complexity when
converting from one to the other, and interoperates better with the rest of
the Rust ecosystem.
This commit is contained in:
Matt Brubeck 2016-04-27 11:22:02 -07:00
parent dba878dfb2
commit 659305fe0a
15 changed files with 259 additions and 437 deletions
Download patch file Download diff file Expand all files Collapse all files

39
components/util/str.rs
View file

@ -11,7 +11,7 @@ use std::ffi::CStr;
use std::fmt;
use std::iter::{Filter, Peekable};
use std::ops::{Deref, DerefMut};
use std::str::{Bytes, CharIndices, Split, from_utf8};
use std::str::{Bytes, Split, from_utf8};
use string_cache::Atom;
#[derive(Clone, Debug, Deserialize, Eq, Hash, HeapSizeOf, Ord, PartialEq, PartialOrd, Serialize)]
@ -271,40 +271,3 @@ pub fn str_join<I, T>(strs: I, join: &str) -> String
acc
})
}
// Lifted from Rust's StrExt implementation, which is being removed.
pub fn slice_chars(s: &str, begin: usize, end: usize) -> &str {
assert!(begin <= end);
let mut count = 0;
let mut begin_byte = None;
let mut end_byte = None;
// This could be even more efficient by not decoding,
// only finding the char boundaries
for (idx, _) in s.char_indices() {
if count == begin { begin_byte = Some(idx); }
if count == end { end_byte = Some(idx); break; }
count += 1;
}
if begin_byte.is_none() && count == begin { begin_byte = Some(s.len()) }
if end_byte.is_none() && count == end { end_byte = Some(s.len()) }
match (begin_byte, end_byte) {
(None, _) => panic!("slice_chars: `begin` is beyond end of string"),
(_, None) => panic!("slice_chars: `end` is beyond end of string"),
(Some(a), Some(b)) => unsafe { s.slice_unchecked(a, b) }
}
}
// searches a character index in CharIndices
// returns indices.count if not found
pub fn search_index(index: usize, indices: CharIndices) -> isize {
let mut character_count = 0;
for (character_index, _) in indices {
if character_index == index {
return character_count;
}
character_count += 1
}
character_count
}