Skip to content

Optimize str::each_split_within when it is called with large limits #7475

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 30, 2013
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion src/libstd/str.rs
Original file line number Diff line number Diff line change
Expand Up @@ -434,10 +434,17 @@ pub fn each_split_within<'a>(ss: &'a str,
let mut last_start = 0;
let mut last_end = 0;
let mut state = A;
let mut fake_i = ss.len();
let mut lim = lim;

let mut cont = true;
let slice: &fn() = || { cont = it(ss.slice(slice_start, last_end)) };

// if the limit is larger than the string, lower it to save cycles
if (lim >= fake_i) {
lim = fake_i;
}

let machine: &fn((uint, char)) -> bool = |(i, c)| {
let whitespace = if char::is_whitespace(c) { Ws } else { Cr };
let limit = if (i - slice_start + 1) <= lim { UnderLim } else { OverLim };
Expand Down Expand Up @@ -466,7 +473,6 @@ pub fn each_split_within<'a>(ss: &'a str,
ss.iter().enumerate().advance(machine);

// Let the automaton 'run out' by supplying trailing whitespace
let mut fake_i = ss.len();
while cont && match state { B | C => true, A => false } {
machine((fake_i, ' '));
fake_i += 1;
Expand Down Expand Up @@ -2299,6 +2305,7 @@ mod tests {
use libc;
use ptr;
use str::*;
use uint;
use vec;
use vec::{ImmutableVector, CopyableVector};
use cmp::{TotalOrd, Less, Equal, Greater};
Expand Down Expand Up @@ -2444,6 +2451,8 @@ mod tests {
t("hello", 15, [~"hello"]);
t("\nMary had a little lamb\nLittle lamb\n", 15,
[~"Mary had a", ~"little lamb", ~"Little lamb"]);
t("\nMary had a little lamb\nLittle lamb\n", uint::max_value,
[~"Mary had a little lamb\nLittle lamb"]);
}

#[test]
Expand Down