2015-04-01 20:45:00 +00:00
|
|
|
|
// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
|
2015-03-11 04:58:16 +00:00
|
|
|
|
// file at the top-level directory of this distribution and at
|
|
|
|
|
// http://rust-lang.org/COPYRIGHT.
|
|
|
|
|
//
|
|
|
|
|
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
|
|
|
|
|
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
|
|
|
|
|
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
|
|
|
|
|
// option. This file may not be copied, modified, or distributed
|
|
|
|
|
// except according to those terms.
|
|
|
|
|
|
2016-02-03 12:57:25 +00:00
|
|
|
|
use std::borrow::Cow;
|
2015-03-11 04:58:16 +00:00
|
|
|
|
use std::cmp::Ordering::{Equal, Greater, Less};
|
2015-06-10 20:33:52 +00:00
|
|
|
|
use std::str::from_utf8;
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_le() {
|
|
|
|
|
assert!("" <= "");
|
|
|
|
|
assert!("" <= "foo");
|
|
|
|
|
assert!("foo" <= "foo");
|
|
|
|
|
assert!("foo" != "bar");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_find() {
|
|
|
|
|
assert_eq!("hello".find('l'), Some(2));
|
|
|
|
|
assert_eq!("hello".find(|c:char| c == 'o'), Some(4));
|
|
|
|
|
assert!("hello".find('x').is_none());
|
|
|
|
|
assert!("hello".find(|c:char| c == 'x').is_none());
|
|
|
|
|
assert_eq!("ประเทศไทย中华Việt Nam".find('华'), Some(30));
|
|
|
|
|
assert_eq!("ประเทศไทย中华Việt Nam".find(|c: char| c == '华'), Some(30));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_rfind() {
|
|
|
|
|
assert_eq!("hello".rfind('l'), Some(3));
|
|
|
|
|
assert_eq!("hello".rfind(|c:char| c == 'o'), Some(4));
|
|
|
|
|
assert!("hello".rfind('x').is_none());
|
|
|
|
|
assert!("hello".rfind(|c:char| c == 'x').is_none());
|
|
|
|
|
assert_eq!("ประเทศไทย中华Việt Nam".rfind('华'), Some(30));
|
|
|
|
|
assert_eq!("ประเทศไทย中华Việt Nam".rfind(|c: char| c == '华'), Some(30));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_collect() {
|
2015-10-22 02:14:11 +00:00
|
|
|
|
let empty = "";
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let s: String = empty.chars().collect();
|
|
|
|
|
assert_eq!(empty, s);
|
2015-10-22 02:14:11 +00:00
|
|
|
|
let data = "ประเทศไทย中";
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let s: String = data.chars().collect();
|
|
|
|
|
assert_eq!(data, s);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_into_bytes() {
|
2015-06-08 14:55:35 +00:00
|
|
|
|
let data = String::from("asdf");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let buf = data.into_bytes();
|
2015-03-11 00:59:23 +00:00
|
|
|
|
assert_eq!(buf, b"asdf");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_find_str() {
|
|
|
|
|
// byte positions
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("".find(""), Some(0));
|
|
|
|
|
assert!("banana".find("apple pie").is_none());
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
let data = "abcabc";
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!(data[0..6].find("ab"), Some(0));
|
|
|
|
|
assert_eq!(data[2..6].find("ab"), Some(3 - 2));
|
|
|
|
|
assert!(data[2..4].find("ab").is_none());
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
let string = "ประเทศไทย中华Việt Nam";
|
2015-06-08 14:55:35 +00:00
|
|
|
|
let mut data = String::from(string);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
data.push_str(string);
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert!(data.find("ไท华").is_none());
|
|
|
|
|
assert_eq!(data[0..43].find(""), Some(0));
|
|
|
|
|
assert_eq!(data[6..43].find(""), Some(6 - 6));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!(data[0..43].find("ประ"), Some( 0));
|
|
|
|
|
assert_eq!(data[0..43].find("ทศไ"), Some(12));
|
|
|
|
|
assert_eq!(data[0..43].find("ย中"), Some(24));
|
|
|
|
|
assert_eq!(data[0..43].find("iệt"), Some(34));
|
|
|
|
|
assert_eq!(data[0..43].find("Nam"), Some(40));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!(data[43..86].find("ประ"), Some(43 - 43));
|
|
|
|
|
assert_eq!(data[43..86].find("ทศไ"), Some(55 - 43));
|
|
|
|
|
assert_eq!(data[43..86].find("ย中"), Some(67 - 43));
|
|
|
|
|
assert_eq!(data[43..86].find("iệt"), Some(77 - 43));
|
|
|
|
|
assert_eq!(data[43..86].find("Nam"), Some(83 - 43));
|
2015-08-02 17:03:01 +00:00
|
|
|
|
|
2015-10-07 22:11:25 +00:00
|
|
|
|
// find every substring -- assert that it finds it, or an earlier occurrence.
|
2015-08-02 17:03:01 +00:00
|
|
|
|
let string = "Việt Namacbaabcaabaaba";
|
|
|
|
|
for (i, ci) in string.char_indices() {
|
|
|
|
|
let ip = i + ci.len_utf8();
|
|
|
|
|
for j in string[ip..].char_indices()
|
|
|
|
|
.map(|(i, _)| i)
|
|
|
|
|
.chain(Some(string.len() - ip))
|
|
|
|
|
{
|
|
|
|
|
let pat = &string[i..ip + j];
|
|
|
|
|
assert!(match string.find(pat) {
|
|
|
|
|
None => false,
|
|
|
|
|
Some(x) => x <= i,
|
|
|
|
|
});
|
|
|
|
|
assert!(match string.rfind(pat) {
|
|
|
|
|
None => false,
|
|
|
|
|
Some(x) => x >= i,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
}
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn s(x: &str) -> String { x.to_string() }
|
|
|
|
|
|
|
|
|
|
macro_rules! test_concat {
|
|
|
|
|
($expected: expr, $string: expr) => {
|
|
|
|
|
{
|
|
|
|
|
let s: String = $string.concat();
|
|
|
|
|
assert_eq!($expected, s);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_concat_for_different_types() {
|
|
|
|
|
test_concat!("ab", vec![s("a"), s("b")]);
|
|
|
|
|
test_concat!("ab", vec!["a", "b"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_concat_for_different_lengths() {
|
|
|
|
|
let empty: &[&str] = &[];
|
|
|
|
|
test_concat!("", empty);
|
|
|
|
|
test_concat!("a", ["a"]);
|
|
|
|
|
test_concat!("ab", ["a", "b"]);
|
|
|
|
|
test_concat!("abc", ["", "a", "bc"]);
|
|
|
|
|
}
|
|
|
|
|
|
2015-07-10 12:19:21 +00:00
|
|
|
|
macro_rules! test_join {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
($expected: expr, $string: expr, $delim: expr) => {
|
|
|
|
|
{
|
2015-07-10 12:19:21 +00:00
|
|
|
|
let s = $string.join($delim);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!($expected, s);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
2015-07-10 12:19:21 +00:00
|
|
|
|
fn test_join_for_different_types() {
|
|
|
|
|
test_join!("a-b", ["a", "b"], "-");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let hyphen = "-".to_string();
|
2015-07-10 12:19:21 +00:00
|
|
|
|
test_join!("a-b", [s("a"), s("b")], &*hyphen);
|
|
|
|
|
test_join!("a-b", vec!["a", "b"], &*hyphen);
|
|
|
|
|
test_join!("a-b", &*vec!["a", "b"], "-");
|
|
|
|
|
test_join!("a-b", vec![s("a"), s("b")], "-");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
2015-07-10 12:19:21 +00:00
|
|
|
|
fn test_join_for_different_lengths() {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let empty: &[&str] = &[];
|
2015-07-10 12:19:21 +00:00
|
|
|
|
test_join!("", empty, "-");
|
|
|
|
|
test_join!("a", ["a"], "-");
|
|
|
|
|
test_join!("a-b", ["a", "b"], "-");
|
|
|
|
|
test_join!("-a-bc", ["", "a", "bc"], "-");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_unsafe_slice() {
|
|
|
|
|
assert_eq!("ab", unsafe {"abc".slice_unchecked(0, 2)});
|
|
|
|
|
assert_eq!("bc", unsafe {"abc".slice_unchecked(1, 3)});
|
|
|
|
|
assert_eq!("", unsafe {"abc".slice_unchecked(1, 1)});
|
|
|
|
|
fn a_million_letter_a() -> String {
|
|
|
|
|
let mut i = 0;
|
|
|
|
|
let mut rs = String::new();
|
|
|
|
|
while i < 100000 {
|
|
|
|
|
rs.push_str("aaaaaaaaaa");
|
|
|
|
|
i += 1;
|
|
|
|
|
}
|
|
|
|
|
rs
|
|
|
|
|
}
|
|
|
|
|
fn half_a_million_letter_a() -> String {
|
|
|
|
|
let mut i = 0;
|
|
|
|
|
let mut rs = String::new();
|
|
|
|
|
while i < 100000 {
|
|
|
|
|
rs.push_str("aaaaa");
|
|
|
|
|
i += 1;
|
|
|
|
|
}
|
|
|
|
|
rs
|
|
|
|
|
}
|
|
|
|
|
let letters = a_million_letter_a();
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!(half_a_million_letter_a(),
|
|
|
|
|
unsafe { letters.slice_unchecked(0, 500000)});
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_starts_with() {
|
2016-06-09 02:50:08 +00:00
|
|
|
|
assert!("".starts_with(""));
|
|
|
|
|
assert!("abc".starts_with(""));
|
|
|
|
|
assert!("abc".starts_with("a"));
|
|
|
|
|
assert!(!"a".starts_with("abc"));
|
|
|
|
|
assert!(!"".starts_with("abc"));
|
|
|
|
|
assert!(!"ödd".starts_with("-"));
|
|
|
|
|
assert!("ödd".starts_with("öd"));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_ends_with() {
|
2016-06-09 02:50:08 +00:00
|
|
|
|
assert!("".ends_with(""));
|
|
|
|
|
assert!("abc".ends_with(""));
|
|
|
|
|
assert!("abc".ends_with("c"));
|
|
|
|
|
assert!(!"a".ends_with("abc"));
|
|
|
|
|
assert!(!"".ends_with("abc"));
|
|
|
|
|
assert!(!"ddö".ends_with("-"));
|
|
|
|
|
assert!("ddö".ends_with("dö"));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_is_empty() {
|
|
|
|
|
assert!("".is_empty());
|
|
|
|
|
assert!(!"a".is_empty());
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-08 10:55:04 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_replacen() {
|
|
|
|
|
assert_eq!("".replacen('a', "b", 5), "");
|
|
|
|
|
assert_eq!("acaaa".replacen("a", "b", 3), "bcbba");
|
|
|
|
|
assert_eq!("aaaa".replacen("a", "b", 0), "aaaa");
|
|
|
|
|
|
|
|
|
|
let test = "test";
|
|
|
|
|
assert_eq!(" test test ".replacen(test, "toast", 3), " toast toast ");
|
|
|
|
|
assert_eq!(" test test ".replacen(test, "toast", 0), " test test ");
|
|
|
|
|
assert_eq!(" test test ".replacen(test, "", 5), " ");
|
|
|
|
|
|
|
|
|
|
assert_eq!("qwer123zxc789".replacen(char::is_numeric, "", 3), "qwerzxc789");
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace() {
|
|
|
|
|
let a = "a";
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!("".replace(a, "b"), "");
|
|
|
|
|
assert_eq!("a".replace(a, "b"), "b");
|
|
|
|
|
assert_eq!("ab".replace(a, "b"), "bb");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let test = "test";
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!(" test test ".replace(test, "toast"), " toast toast ");
|
|
|
|
|
assert_eq!(" test test ".replace(test, ""), " ");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace_2a() {
|
|
|
|
|
let data = "ประเทศไทย中华";
|
|
|
|
|
let repl = "دولة الكويت";
|
|
|
|
|
|
|
|
|
|
let a = "ประเ";
|
|
|
|
|
let a2 = "دولة الكويتทศไทย中华";
|
|
|
|
|
assert_eq!(data.replace(a, repl), a2);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace_2b() {
|
|
|
|
|
let data = "ประเทศไทย中华";
|
|
|
|
|
let repl = "دولة الكويت";
|
|
|
|
|
|
|
|
|
|
let b = "ะเ";
|
|
|
|
|
let b2 = "ปรدولة الكويتทศไทย中华";
|
|
|
|
|
assert_eq!(data.replace(b, repl), b2);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace_2c() {
|
|
|
|
|
let data = "ประเทศไทย中华";
|
|
|
|
|
let repl = "دولة الكويت";
|
|
|
|
|
|
|
|
|
|
let c = "中华";
|
|
|
|
|
let c2 = "ประเทศไทยدولة الكويت";
|
|
|
|
|
assert_eq!(data.replace(c, repl), c2);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace_2d() {
|
|
|
|
|
let data = "ประเทศไทย中华";
|
|
|
|
|
let repl = "دولة الكويت";
|
|
|
|
|
|
|
|
|
|
let d = "ไท华";
|
|
|
|
|
assert_eq!(data.replace(d, repl), data);
|
|
|
|
|
}
|
|
|
|
|
|
2015-11-01 04:21:47 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_replace_pattern() {
|
|
|
|
|
let data = "abcdαβγδabcdαβγδ";
|
|
|
|
|
assert_eq!(data.replace("dαβ", "😺😺😺"), "abc😺😺😺γδabc😺😺😺γδ");
|
|
|
|
|
assert_eq!(data.replace('γ', "😺😺😺"), "abcdαβ😺😺😺δabcdαβ😺😺😺δ");
|
|
|
|
|
assert_eq!(data.replace(&['a', 'γ'] as &[_], "😺😺😺"), "😺😺😺bcdαβ😺😺😺δ😺😺😺bcdαβ😺😺😺δ");
|
|
|
|
|
assert_eq!(data.replace(|c| c == 'γ', "😺😺😺"), "abcdαβ😺😺😺δabcdαβ😺😺😺δ");
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_slice() {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("ab", &"abc"[0..2]);
|
|
|
|
|
assert_eq!("bc", &"abc"[1..3]);
|
|
|
|
|
assert_eq!("", &"abc"[1..1]);
|
|
|
|
|
assert_eq!("\u{65e5}", &"\u{65e5}\u{672c}"[0..3]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
let data = "ประเทศไทย中华";
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("ป", &data[0..3]);
|
|
|
|
|
assert_eq!("ร", &data[3..6]);
|
|
|
|
|
assert_eq!("", &data[3..3]);
|
|
|
|
|
assert_eq!("华", &data[30..33]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
fn a_million_letter_x() -> String {
|
|
|
|
|
let mut i = 0;
|
|
|
|
|
let mut rs = String::new();
|
|
|
|
|
while i < 100000 {
|
|
|
|
|
rs.push_str("华华华华华华华华华华");
|
|
|
|
|
i += 1;
|
|
|
|
|
}
|
|
|
|
|
rs
|
|
|
|
|
}
|
|
|
|
|
fn half_a_million_letter_x() -> String {
|
|
|
|
|
let mut i = 0;
|
|
|
|
|
let mut rs = String::new();
|
|
|
|
|
while i < 100000 {
|
|
|
|
|
rs.push_str("华华华华华");
|
|
|
|
|
i += 1;
|
|
|
|
|
}
|
|
|
|
|
rs
|
|
|
|
|
}
|
|
|
|
|
let letters = a_million_letter_x();
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!(half_a_million_letter_x(), &letters[0..3 * 500000]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_slice_2() {
|
|
|
|
|
let ss = "中华Việt Nam";
|
|
|
|
|
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("华", &ss[3..6]);
|
|
|
|
|
assert_eq!("Việt Nam", &ss[6..16]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("ab", &"abc"[0..2]);
|
|
|
|
|
assert_eq!("bc", &"abc"[1..3]);
|
|
|
|
|
assert_eq!("", &"abc"[1..1]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!("中", &ss[0..3]);
|
|
|
|
|
assert_eq!("华V", &ss[3..7]);
|
|
|
|
|
assert_eq!("", &ss[3..3]);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
/*0: 中
|
|
|
|
|
3: 华
|
|
|
|
|
6: V
|
|
|
|
|
7: i
|
|
|
|
|
8: ệ
|
|
|
|
|
11: t
|
|
|
|
|
12:
|
|
|
|
|
13: N
|
|
|
|
|
14: a
|
|
|
|
|
15: m */
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
#[should_panic]
|
|
|
|
|
fn test_slice_fail() {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
&"中华Việt Nam"[0..2];
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
2016-04-10 18:09:26 +00:00
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_is_char_boundary() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam β-release 🐱123";
|
|
|
|
|
assert!(s.is_char_boundary(0));
|
|
|
|
|
assert!(s.is_char_boundary(s.len()));
|
|
|
|
|
assert!(!s.is_char_boundary(s.len() + 1));
|
|
|
|
|
for (i, ch) in s.char_indices() {
|
|
|
|
|
// ensure character locations are boundaries and continuation bytes are not
|
|
|
|
|
assert!(s.is_char_boundary(i), "{} is a char boundary in {:?}", i, s);
|
|
|
|
|
for j in 1..ch.len_utf8() {
|
|
|
|
|
assert!(!s.is_char_boundary(i + j),
|
|
|
|
|
"{} should not be a char boundary in {:?}", i + j, s);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
2016-03-05 17:09:14 +00:00
|
|
|
|
const LOREM_PARAGRAPH: &'static str = "\
|
|
|
|
|
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse quis lorem sit amet dolor \
|
|
|
|
|
ultricies condimentum. Praesent iaculis purus elit, ac malesuada quam malesuada in. Duis sed orci \
|
|
|
|
|
eros. Suspendisse sit amet magna mollis, mollis nunc luctus, imperdiet mi. Integer fringilla non \
|
|
|
|
|
sem ut lacinia. Fusce varius tortor a risus porttitor hendrerit. Morbi mauris dui, ultricies nec \
|
|
|
|
|
tempus vel, gravida nec quam.";
|
|
|
|
|
|
|
|
|
|
// check the panic includes the prefix of the sliced string
|
|
|
|
|
#[test]
|
|
|
|
|
#[should_panic(expected="Lorem ipsum dolor sit amet")]
|
|
|
|
|
fn test_slice_fail_truncated_1() {
|
|
|
|
|
&LOREM_PARAGRAPH[..1024];
|
|
|
|
|
}
|
|
|
|
|
// check the truncation in the panic message
|
|
|
|
|
#[test]
|
|
|
|
|
#[should_panic(expected="luctus, im`[...] do not lie on character boundary")]
|
|
|
|
|
fn test_slice_fail_truncated_2() {
|
|
|
|
|
&LOREM_PARAGRAPH[..1024];
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_slice_from() {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!(&"abcd"[0..], "abcd");
|
|
|
|
|
assert_eq!(&"abcd"[2..], "cd");
|
|
|
|
|
assert_eq!(&"abcd"[4..], "");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_slice_to() {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert_eq!(&"abcd"[..0], "");
|
|
|
|
|
assert_eq!(&"abcd"[..2], "ab");
|
|
|
|
|
assert_eq!(&"abcd"[..4], "abcd");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim_left_matches() {
|
|
|
|
|
let v: &[char] = &[];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_left_matches(v), " *** foo *** ");
|
|
|
|
|
let chars: &[char] = &['*', ' '];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_left_matches(chars), "foo *** ");
|
|
|
|
|
assert_eq!(" *** *** ".trim_left_matches(chars), "");
|
|
|
|
|
assert_eq!("foo *** ".trim_left_matches(chars), "foo *** ");
|
|
|
|
|
|
|
|
|
|
assert_eq!("11foo1bar11".trim_left_matches('1'), "foo1bar11");
|
|
|
|
|
let chars: &[char] = &['1', '2'];
|
|
|
|
|
assert_eq!("12foo1bar12".trim_left_matches(chars), "foo1bar12");
|
|
|
|
|
assert_eq!("123foo1bar123".trim_left_matches(|c: char| c.is_numeric()), "foo1bar123");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim_right_matches() {
|
|
|
|
|
let v: &[char] = &[];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_right_matches(v), " *** foo *** ");
|
|
|
|
|
let chars: &[char] = &['*', ' '];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_right_matches(chars), " *** foo");
|
|
|
|
|
assert_eq!(" *** *** ".trim_right_matches(chars), "");
|
|
|
|
|
assert_eq!(" *** foo".trim_right_matches(chars), " *** foo");
|
|
|
|
|
|
|
|
|
|
assert_eq!("11foo1bar11".trim_right_matches('1'), "11foo1bar");
|
|
|
|
|
let chars: &[char] = &['1', '2'];
|
|
|
|
|
assert_eq!("12foo1bar12".trim_right_matches(chars), "12foo1bar");
|
|
|
|
|
assert_eq!("123foo1bar123".trim_right_matches(|c: char| c.is_numeric()), "123foo1bar");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim_matches() {
|
|
|
|
|
let v: &[char] = &[];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_matches(v), " *** foo *** ");
|
|
|
|
|
let chars: &[char] = &['*', ' '];
|
|
|
|
|
assert_eq!(" *** foo *** ".trim_matches(chars), "foo");
|
|
|
|
|
assert_eq!(" *** *** ".trim_matches(chars), "");
|
|
|
|
|
assert_eq!("foo".trim_matches(chars), "foo");
|
|
|
|
|
|
|
|
|
|
assert_eq!("11foo1bar11".trim_matches('1'), "foo1bar");
|
|
|
|
|
let chars: &[char] = &['1', '2'];
|
|
|
|
|
assert_eq!("12foo1bar12".trim_matches(chars), "foo1bar");
|
|
|
|
|
assert_eq!("123foo1bar123".trim_matches(|c: char| c.is_numeric()), "foo1bar");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim_left() {
|
|
|
|
|
assert_eq!("".trim_left(), "");
|
|
|
|
|
assert_eq!("a".trim_left(), "a");
|
|
|
|
|
assert_eq!(" ".trim_left(), "");
|
|
|
|
|
assert_eq!(" blah".trim_left(), "blah");
|
|
|
|
|
assert_eq!(" \u{3000} wut".trim_left(), "wut");
|
|
|
|
|
assert_eq!("hey ".trim_left(), "hey ");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim_right() {
|
|
|
|
|
assert_eq!("".trim_right(), "");
|
|
|
|
|
assert_eq!("a".trim_right(), "a");
|
|
|
|
|
assert_eq!(" ".trim_right(), "");
|
|
|
|
|
assert_eq!("blah ".trim_right(), "blah");
|
|
|
|
|
assert_eq!("wut \u{3000} ".trim_right(), "wut");
|
|
|
|
|
assert_eq!(" hey".trim_right(), " hey");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_trim() {
|
|
|
|
|
assert_eq!("".trim(), "");
|
|
|
|
|
assert_eq!("a".trim(), "a");
|
|
|
|
|
assert_eq!(" ".trim(), "");
|
|
|
|
|
assert_eq!(" blah ".trim(), "blah");
|
|
|
|
|
assert_eq!("\nwut \u{3000} ".trim(), "wut");
|
|
|
|
|
assert_eq!(" hey dude ".trim(), "hey dude");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_is_whitespace() {
|
|
|
|
|
assert!("".chars().all(|c| c.is_whitespace()));
|
|
|
|
|
assert!(" ".chars().all(|c| c.is_whitespace()));
|
|
|
|
|
assert!("\u{2009}".chars().all(|c| c.is_whitespace())); // Thin space
|
|
|
|
|
assert!(" \n\t ".chars().all(|c| c.is_whitespace()));
|
|
|
|
|
assert!(!" _ ".chars().all(|c| c.is_whitespace()));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_is_utf8() {
|
|
|
|
|
// deny overlong encodings
|
|
|
|
|
assert!(from_utf8(&[0xc0, 0x80]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xc0, 0xae]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xe0, 0x80, 0x80]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xe0, 0x80, 0xaf]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xe0, 0x81, 0x81]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xf0, 0x82, 0x82, 0xac]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xf4, 0x90, 0x80, 0x80]).is_err());
|
|
|
|
|
|
|
|
|
|
// deny surrogates
|
|
|
|
|
assert!(from_utf8(&[0xED, 0xA0, 0x80]).is_err());
|
|
|
|
|
assert!(from_utf8(&[0xED, 0xBF, 0xBF]).is_err());
|
|
|
|
|
|
|
|
|
|
assert!(from_utf8(&[0xC2, 0x80]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xDF, 0xBF]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xE0, 0xA0, 0x80]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xED, 0x9F, 0xBF]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xEE, 0x80, 0x80]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xEF, 0xBF, 0xBF]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xF0, 0x90, 0x80, 0x80]).is_ok());
|
|
|
|
|
assert!(from_utf8(&[0xF4, 0x8F, 0xBF, 0xBF]).is_ok());
|
|
|
|
|
}
|
|
|
|
|
|
Add fast path for ASCII in UTF-8 validation
This speeds up the ascii case (and long stretches of ascii in otherwise
mixed UTF-8 data) when checking UTF-8 validity.
Benchmark results suggest that on purely ASCII input, we can improve
throughput (megabytes verified / second) by a factor of 13 to 14!
On xml and mostly english language input (en.wikipedia xml dump),
throughput increases by a factor 7.
On mostly non-ASCII input, performance increases slightly or is the
same.
The UTF-8 validation is rewritten to use indexed access; since all
access is preceded by a (mandatory for validation) length check, they
are statically elided by llvm and this formulation is in fact the best
for performance. A previous version had losses due to slice to iterator
conversions.
A large credit to Björn Steinbrink who improved this patch immensely,
writing this second version.
Benchmark results on x86-64 (Sandy Bridge) compiled with -C opt-level=3.
Old code is `regular`, this PR is called `fast`.
Datasets:
- `ascii` is just ascii (2.5 kB)
- `cyr` is cyrillic script with ascii spaces (5 kB)
- `dewik10` is 10MB of a de.wikipedia xml dump
- `enwik10` is 100MB of an en.wikipedia xml dump
- `jawik10` is 10MB of a ja.wikipedia xml dump
```
test from_utf8_ascii_fast ... bench: 140 ns/iter (+/- 4) = 18221 MB/s
test from_utf8_ascii_regular ... bench: 1,932 ns/iter (+/- 19) = 1320 MB/s
test from_utf8_cyr_fast ... bench: 10,025 ns/iter (+/- 245) = 511 MB/s
test from_utf8_cyr_regular ... bench: 12,250 ns/iter (+/- 437) = 418 MB/s
test from_utf8_dewik10_fast ... bench: 6,017,909 ns/iter (+/- 105,755) = 1740 MB/s
test from_utf8_dewik10_regular ... bench: 11,669,493 ns/iter (+/- 264,045) = 891 MB/s
test from_utf8_enwik8_fast ... bench: 14,085,692 ns/iter (+/- 1,643,316) = 7000 MB/s
test from_utf8_enwik8_regular ... bench: 93,657,410 ns/iter (+/- 5,353,353) = 1000 MB/s
test from_utf8_jawik10_fast ... bench: 29,154,073 ns/iter (+/- 4,659,534) = 340 MB/s
test from_utf8_jawik10_regular ... bench: 29,112,917 ns/iter (+/- 2,475,123) = 340 MB/s
```
Co-authored-by: Björn Steinbrink <bsteinbr@gmail.com>
2016-01-06 14:43:33 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn from_utf8_mostly_ascii() {
|
|
|
|
|
// deny invalid bytes embedded in long stretches of ascii
|
|
|
|
|
for i in 32..64 {
|
|
|
|
|
let mut data = [0; 128];
|
|
|
|
|
data[i] = 0xC0;
|
|
|
|
|
assert!(from_utf8(&data).is_err());
|
|
|
|
|
data[i] = 0xC2;
|
|
|
|
|
assert!(from_utf8(&data).is_err());
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_is_utf16() {
|
deprecate Unicode functions that will be moved to crates.io
This patch
1. renames libunicode to librustc_unicode,
2. deprecates several pieces of libunicode (see below), and
3. removes references to deprecated functions from
librustc_driver and libsyntax. This may change pretty-printed
output from these modules in cases involving wide or combining
characters used in filenames, identifiers, etc.
The following functions are marked deprecated:
1. char.width() and str.width():
--> use unicode-width crate
2. str.graphemes() and str.grapheme_indices():
--> use unicode-segmentation crate
3. str.nfd_chars(), str.nfkd_chars(), str.nfc_chars(), str.nfkc_chars(),
char.compose(), char.decompose_canonical(), char.decompose_compatible(),
char.canonical_combining_class():
--> use unicode-normalization crate
2015-04-14 19:52:37 +00:00
|
|
|
|
use rustc_unicode::str::is_utf16;
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
macro_rules! pos {
|
|
|
|
|
($($e:expr),*) => { { $(assert!(is_utf16($e));)* } }
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// non-surrogates
|
|
|
|
|
pos!(&[0x0000],
|
|
|
|
|
&[0x0001, 0x0002],
|
|
|
|
|
&[0xD7FF],
|
|
|
|
|
&[0xE000]);
|
|
|
|
|
|
|
|
|
|
// surrogate pairs (randomly generated with Python 3's
|
|
|
|
|
// .encode('utf-16be'))
|
|
|
|
|
pos!(&[0xdb54, 0xdf16, 0xd880, 0xdee0, 0xdb6a, 0xdd45],
|
|
|
|
|
&[0xd91f, 0xdeb1, 0xdb31, 0xdd84, 0xd8e2, 0xde14],
|
|
|
|
|
&[0xdb9f, 0xdc26, 0xdb6f, 0xde58, 0xd850, 0xdfae]);
|
|
|
|
|
|
|
|
|
|
// mixtures (also random)
|
|
|
|
|
pos!(&[0xd921, 0xdcc2, 0x002d, 0x004d, 0xdb32, 0xdf65],
|
|
|
|
|
&[0xdb45, 0xdd2d, 0x006a, 0xdacd, 0xddfe, 0x0006],
|
|
|
|
|
&[0x0067, 0xd8ff, 0xddb7, 0x000f, 0xd900, 0xdc80]);
|
|
|
|
|
|
|
|
|
|
// negative tests
|
|
|
|
|
macro_rules! neg {
|
|
|
|
|
($($e:expr),*) => { { $(assert!(!is_utf16($e));)* } }
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
neg!(
|
|
|
|
|
// surrogate + regular unit
|
|
|
|
|
&[0xdb45, 0x0000],
|
|
|
|
|
// surrogate + lead surrogate
|
|
|
|
|
&[0xd900, 0xd900],
|
|
|
|
|
// unterminated surrogate
|
|
|
|
|
&[0xd8ff],
|
|
|
|
|
// trail surrogate without a lead
|
|
|
|
|
&[0xddb7]);
|
|
|
|
|
|
|
|
|
|
// random byte sequences that Python 3's .decode('utf-16be')
|
|
|
|
|
// failed on
|
|
|
|
|
neg!(&[0x5b3d, 0x0141, 0xde9e, 0x8fdc, 0xc6e7],
|
|
|
|
|
&[0xdf5a, 0x82a5, 0x62b9, 0xb447, 0x92f3],
|
|
|
|
|
&[0xda4e, 0x42bc, 0x4462, 0xee98, 0xc2ca],
|
|
|
|
|
&[0xbe00, 0xb04a, 0x6ecb, 0xdd89, 0xe278],
|
|
|
|
|
&[0x0465, 0xab56, 0xdbb6, 0xa893, 0x665e],
|
|
|
|
|
&[0x6b7f, 0x0a19, 0x40f4, 0xa657, 0xdcc5],
|
|
|
|
|
&[0x9b50, 0xda5e, 0x24ec, 0x03ad, 0x6dee],
|
|
|
|
|
&[0x8d17, 0xcaa7, 0xf4ae, 0xdf6e, 0xbed7],
|
|
|
|
|
&[0xdaee, 0x2584, 0x7d30, 0xa626, 0x121a],
|
|
|
|
|
&[0xd956, 0x4b43, 0x7570, 0xccd6, 0x4f4a],
|
|
|
|
|
&[0x9dcf, 0x1b49, 0x4ba5, 0xfce9, 0xdffe],
|
|
|
|
|
&[0x6572, 0xce53, 0xb05a, 0xf6af, 0xdacf],
|
|
|
|
|
&[0x1b90, 0x728c, 0x9906, 0xdb68, 0xf46e],
|
|
|
|
|
&[0x1606, 0xbeca, 0xbe76, 0x860f, 0xdfa5],
|
|
|
|
|
&[0x8b4f, 0xde7a, 0xd220, 0x9fac, 0x2b6f],
|
|
|
|
|
&[0xb8fe, 0xebbe, 0xda32, 0x1a5f, 0x8b8b],
|
|
|
|
|
&[0x934b, 0x8956, 0xc434, 0x1881, 0xddf7],
|
|
|
|
|
&[0x5a95, 0x13fc, 0xf116, 0xd89b, 0x93f9],
|
|
|
|
|
&[0xd640, 0x71f1, 0xdd7d, 0x77eb, 0x1cd8],
|
|
|
|
|
&[0x348b, 0xaef0, 0xdb2c, 0xebf1, 0x1282],
|
|
|
|
|
&[0x50d7, 0xd824, 0x5010, 0xb369, 0x22ea]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_as_bytes() {
|
|
|
|
|
// no null
|
|
|
|
|
let v = [
|
|
|
|
|
224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
|
|
|
|
|
184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
|
|
|
|
|
109
|
|
|
|
|
];
|
|
|
|
|
let b: &[u8] = &[];
|
|
|
|
|
assert_eq!("".as_bytes(), b);
|
|
|
|
|
assert_eq!("abc".as_bytes(), b"abc");
|
|
|
|
|
assert_eq!("ศไทย中华Việt Nam".as_bytes(), v);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
#[should_panic]
|
|
|
|
|
fn test_as_bytes_fail() {
|
|
|
|
|
// Don't double free. (I'm not sure if this exercises the
|
|
|
|
|
// original problem code path anymore.)
|
2015-06-08 14:55:35 +00:00
|
|
|
|
let s = String::from("");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let _bytes = s.as_bytes();
|
|
|
|
|
panic!();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_as_ptr() {
|
|
|
|
|
let buf = "hello".as_ptr();
|
|
|
|
|
unsafe {
|
|
|
|
|
assert_eq!(*buf.offset(0), b'h');
|
|
|
|
|
assert_eq!(*buf.offset(1), b'e');
|
|
|
|
|
assert_eq!(*buf.offset(2), b'l');
|
|
|
|
|
assert_eq!(*buf.offset(3), b'l');
|
|
|
|
|
assert_eq!(*buf.offset(4), b'o');
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn vec_str_conversions() {
|
2015-06-08 14:55:35 +00:00
|
|
|
|
let s1: String = String::from("All mimsy were the borogoves");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
|
|
|
|
|
let v: Vec<u8> = s1.as_bytes().to_vec();
|
2015-06-08 14:55:35 +00:00
|
|
|
|
let s2: String = String::from(from_utf8(&v).unwrap());
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let mut i = 0;
|
|
|
|
|
let n1 = s1.len();
|
|
|
|
|
let n2 = v.len();
|
|
|
|
|
assert_eq!(n1, n2);
|
|
|
|
|
while i < n1 {
|
|
|
|
|
let a: u8 = s1.as_bytes()[i];
|
|
|
|
|
let b: u8 = s2.as_bytes()[i];
|
|
|
|
|
assert_eq!(a, b);
|
|
|
|
|
i += 1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_contains() {
|
|
|
|
|
assert!("abcde".contains("bcd"));
|
|
|
|
|
assert!("abcde".contains("abcd"));
|
|
|
|
|
assert!("abcde".contains("bcde"));
|
|
|
|
|
assert!("abcde".contains(""));
|
|
|
|
|
assert!("".contains(""));
|
|
|
|
|
assert!(!"abcde".contains("def"));
|
|
|
|
|
assert!(!"".contains("a"));
|
|
|
|
|
|
|
|
|
|
let data = "ประเทศไทย中华Việt Nam";
|
|
|
|
|
assert!(data.contains("ประเ"));
|
|
|
|
|
assert!(data.contains("ะเ"));
|
|
|
|
|
assert!(data.contains("中华"));
|
|
|
|
|
assert!(!data.contains("ไท华"));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_contains_char() {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
assert!("abc".contains('b'));
|
|
|
|
|
assert!("a".contains('a'));
|
|
|
|
|
assert!(!"abc".contains('d'));
|
|
|
|
|
assert!(!"".contains('a'));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
2015-06-09 09:23:22 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_split_at() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
for (index, _) in s.char_indices() {
|
|
|
|
|
let (a, b) = s.split_at(index);
|
|
|
|
|
assert_eq!(&s[..a.len()], a);
|
|
|
|
|
assert_eq!(&s[a.len()..], b);
|
|
|
|
|
}
|
|
|
|
|
let (a, b) = s.split_at(s.len());
|
|
|
|
|
assert_eq!(a, s);
|
|
|
|
|
assert_eq!(b, "");
|
|
|
|
|
}
|
|
|
|
|
|
2015-06-15 17:24:52 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_split_at_mut() {
|
|
|
|
|
use std::ascii::AsciiExt;
|
|
|
|
|
let mut s = "Hello World".to_string();
|
|
|
|
|
{
|
|
|
|
|
let (a, b) = s.split_at_mut(5);
|
|
|
|
|
a.make_ascii_uppercase();
|
|
|
|
|
b.make_ascii_lowercase();
|
|
|
|
|
}
|
|
|
|
|
assert_eq!(s, "HELLO world");
|
|
|
|
|
}
|
|
|
|
|
|
2015-06-09 09:23:22 +00:00
|
|
|
|
#[test]
|
|
|
|
|
#[should_panic]
|
|
|
|
|
fn test_split_at_boundscheck() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
2015-06-14 21:17:17 +00:00
|
|
|
|
s.split_at(1);
|
2015-06-09 09:23:22 +00:00
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_escape_unicode() {
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!("abc".escape_unicode(), "\\u{61}\\u{62}\\u{63}");
|
|
|
|
|
assert_eq!("a c".escape_unicode(), "\\u{61}\\u{20}\\u{63}");
|
|
|
|
|
assert_eq!("\r\n\t".escape_unicode(), "\\u{d}\\u{a}\\u{9}");
|
|
|
|
|
assert_eq!("'\"\\".escape_unicode(), "\\u{27}\\u{22}\\u{5c}");
|
|
|
|
|
assert_eq!("\x00\x01\u{fe}\u{ff}".escape_unicode(), "\\u{0}\\u{1}\\u{fe}\\u{ff}");
|
|
|
|
|
assert_eq!("\u{100}\u{ffff}".escape_unicode(), "\\u{100}\\u{ffff}");
|
|
|
|
|
assert_eq!("\u{10000}\u{10ffff}".escape_unicode(), "\\u{10000}\\u{10ffff}");
|
|
|
|
|
assert_eq!("ab\u{fb00}".escape_unicode(), "\\u{61}\\u{62}\\u{fb00}");
|
|
|
|
|
assert_eq!("\u{1d4ea}\r".escape_unicode(), "\\u{1d4ea}\\u{d}");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
2016-07-27 10:10:31 +00:00
|
|
|
|
fn test_escape_debug() {
|
|
|
|
|
assert_eq!("abc".escape_debug(), "abc");
|
|
|
|
|
assert_eq!("a c".escape_debug(), "a c");
|
|
|
|
|
assert_eq!("éèê".escape_debug(), "éèê");
|
|
|
|
|
assert_eq!("\r\n\t".escape_debug(), "\\r\\n\\t");
|
|
|
|
|
assert_eq!("'\"\\".escape_debug(), "\\'\\\"\\\\");
|
|
|
|
|
assert_eq!("\u{7f}\u{ff}".escape_debug(), "\\u{7f}\u{ff}");
|
|
|
|
|
assert_eq!("\u{100}\u{ffff}".escape_debug(), "\u{100}\\u{ffff}");
|
|
|
|
|
assert_eq!("\u{10000}\u{10ffff}".escape_debug(), "\u{10000}\\u{10ffff}");
|
|
|
|
|
assert_eq!("ab\u{200b}".escape_debug(), "ab\\u{200b}");
|
|
|
|
|
assert_eq!("\u{10d4ea}\r".escape_debug(), "\\u{10d4ea}\\r");
|
2016-07-25 23:39:54 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_escape_default() {
|
|
|
|
|
assert_eq!("abc".escape_default(), "abc");
|
|
|
|
|
assert_eq!("a c".escape_default(), "a c");
|
|
|
|
|
assert_eq!("éèê".escape_default(), "\\u{e9}\\u{e8}\\u{ea}");
|
|
|
|
|
assert_eq!("\r\n\t".escape_default(), "\\r\\n\\t");
|
|
|
|
|
assert_eq!("'\"\\".escape_default(), "\\'\\\"\\\\");
|
|
|
|
|
assert_eq!("\u{7f}\u{ff}".escape_default(), "\\u{7f}\\u{ff}");
|
|
|
|
|
assert_eq!("\u{100}\u{ffff}".escape_default(), "\\u{100}\\u{ffff}");
|
|
|
|
|
assert_eq!("\u{10000}\u{10ffff}".escape_default(), "\\u{10000}\\u{10ffff}");
|
|
|
|
|
assert_eq!("ab\u{200b}".escape_default(), "ab\\u{200b}");
|
|
|
|
|
assert_eq!("\u{10d4ea}\r".escape_default(), "\\u{10d4ea}\\r");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_total_ord() {
|
2015-10-22 02:19:14 +00:00
|
|
|
|
assert_eq!("1234".cmp("123"), Greater);
|
|
|
|
|
assert_eq!("123".cmp("1234"), Less);
|
|
|
|
|
assert_eq!("1234".cmp("1234"), Equal);
|
|
|
|
|
assert_eq!("12345555".cmp("123456"), Less);
|
|
|
|
|
assert_eq!("22".cmp("1234"), Greater);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_iterator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let v = ['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
|
|
|
|
|
|
|
|
|
|
let mut pos = 0;
|
|
|
|
|
let it = s.chars();
|
|
|
|
|
|
|
|
|
|
for c in it {
|
|
|
|
|
assert_eq!(c, v[pos]);
|
|
|
|
|
pos += 1;
|
|
|
|
|
}
|
|
|
|
|
assert_eq!(pos, v.len());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_rev_iterator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let v = ['m', 'a', 'N', ' ', 't', 'ệ','i','V','华','中','ย','ท','ไ','ศ'];
|
|
|
|
|
|
|
|
|
|
let mut pos = 0;
|
|
|
|
|
let it = s.chars().rev();
|
|
|
|
|
|
|
|
|
|
for c in it {
|
|
|
|
|
assert_eq!(c, v[pos]);
|
|
|
|
|
pos += 1;
|
|
|
|
|
}
|
|
|
|
|
assert_eq!(pos, v.len());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_chars_decoding() {
|
|
|
|
|
for c in (0..0x110000).filter_map(::std::char::from_u32) {
|
2016-03-11 19:01:46 +00:00
|
|
|
|
let bytes = c.encode_utf8();
|
|
|
|
|
let s = ::std::str::from_utf8(bytes.as_slice()).unwrap();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
if Some(c) != s.chars().next() {
|
|
|
|
|
panic!("character {:x}={} does not decode correctly", c as u32, c);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_chars_rev_decoding() {
|
|
|
|
|
for c in (0..0x110000).filter_map(::std::char::from_u32) {
|
2016-03-11 19:01:46 +00:00
|
|
|
|
let bytes = c.encode_utf8();
|
|
|
|
|
let s = ::std::str::from_utf8(bytes.as_slice()).unwrap();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
if Some(c) != s.chars().rev().next() {
|
|
|
|
|
panic!("character {:x}={} does not decode correctly", c as u32, c);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_iterator_clone() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let mut it = s.chars();
|
|
|
|
|
it.next();
|
|
|
|
|
assert!(it.clone().zip(it).all(|(x,y)| x == y));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_bytesator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let v = [
|
|
|
|
|
224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
|
|
|
|
|
184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
|
|
|
|
|
109
|
|
|
|
|
];
|
|
|
|
|
let mut pos = 0;
|
|
|
|
|
|
|
|
|
|
for b in s.bytes() {
|
|
|
|
|
assert_eq!(b, v[pos]);
|
|
|
|
|
pos += 1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_bytes_revator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let v = [
|
|
|
|
|
224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
|
|
|
|
|
184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
|
|
|
|
|
109
|
|
|
|
|
];
|
|
|
|
|
let mut pos = v.len();
|
|
|
|
|
|
|
|
|
|
for b in s.bytes().rev() {
|
|
|
|
|
pos -= 1;
|
|
|
|
|
assert_eq!(b, v[pos]);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2015-08-30 15:32:43 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_bytesator_nth() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let v = [
|
|
|
|
|
224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
|
|
|
|
|
184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
|
|
|
|
|
109
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
let mut b = s.bytes();
|
|
|
|
|
assert_eq!(b.nth(2).unwrap(), v[2]);
|
|
|
|
|
assert_eq!(b.nth(10).unwrap(), v[10]);
|
|
|
|
|
assert_eq!(b.nth(200), None);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_bytesator_count() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
|
|
|
|
|
let b = s.bytes();
|
|
|
|
|
assert_eq!(b.count(), 28)
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_bytesator_last() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
|
|
|
|
|
let b = s.bytes();
|
|
|
|
|
assert_eq!(b.last().unwrap(), 109)
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_char_indicesator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let p = [0, 3, 6, 9, 12, 15, 18, 19, 20, 23, 24, 25, 26, 27];
|
|
|
|
|
let v = ['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
|
|
|
|
|
|
|
|
|
|
let mut pos = 0;
|
|
|
|
|
let it = s.char_indices();
|
|
|
|
|
|
|
|
|
|
for c in it {
|
|
|
|
|
assert_eq!(c, (p[pos], v[pos]));
|
|
|
|
|
pos += 1;
|
|
|
|
|
}
|
|
|
|
|
assert_eq!(pos, v.len());
|
|
|
|
|
assert_eq!(pos, p.len());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_char_indices_revator() {
|
|
|
|
|
let s = "ศไทย中华Việt Nam";
|
|
|
|
|
let p = [27, 26, 25, 24, 23, 20, 19, 18, 15, 12, 9, 6, 3, 0];
|
|
|
|
|
let v = ['m', 'a', 'N', ' ', 't', 'ệ','i','V','华','中','ย','ท','ไ','ศ'];
|
|
|
|
|
|
|
|
|
|
let mut pos = 0;
|
|
|
|
|
let it = s.char_indices().rev();
|
|
|
|
|
|
|
|
|
|
for c in it {
|
|
|
|
|
assert_eq!(c, (p[pos], v[pos]));
|
|
|
|
|
pos += 1;
|
|
|
|
|
}
|
|
|
|
|
assert_eq!(pos, v.len());
|
|
|
|
|
assert_eq!(pos, p.len());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_splitn_char_iterator() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.splitn(4, ' ').collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(split, ["\nMäry", "häd", "ä", "little lämb\nLittle lämb\n"]);
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.splitn(4, |c: char| c == ' ').collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(split, ["\nMäry", "häd", "ä", "little lämb\nLittle lämb\n"]);
|
|
|
|
|
|
|
|
|
|
// Unicode
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.splitn(4, 'ä').collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(split, ["\nM", "ry h", "d ", " little lämb\nLittle lämb\n"]);
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.splitn(4, |c: char| c == 'ä').collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(split, ["\nM", "ry h", "d ", " little lämb\nLittle lämb\n"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_split_char_iterator_no_trailing() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.split('\n').collect();
|
|
|
|
|
assert_eq!(split, ["", "Märy häd ä little lämb", "Little lämb", ""]);
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.split_terminator('\n').collect();
|
|
|
|
|
assert_eq!(split, ["", "Märy häd ä little lämb", "Little lämb"]);
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-14 23:34:21 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_rsplit() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.rsplit(' ').collect();
|
|
|
|
|
assert_eq!(split, ["lämb\n", "lämb\nLittle", "little", "ä", "häd", "\nMäry"]);
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.rsplit("lämb").collect();
|
|
|
|
|
assert_eq!(split, ["\n", "\nLittle ", "\nMäry häd ä little "]);
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.rsplit(|c: char| c == 'ä').collect();
|
|
|
|
|
assert_eq!(split, ["mb\n", "mb\nLittle l", " little l", "d ", "ry h", "\nM"]);
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-15 00:07:13 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_rsplitn() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.rsplitn(2, ' ').collect();
|
2015-03-15 00:07:13 +00:00
|
|
|
|
assert_eq!(split, ["lämb\n", "\nMäry häd ä little lämb\nLittle"]);
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.rsplitn(2, "lämb").collect();
|
2015-03-15 00:07:13 +00:00
|
|
|
|
assert_eq!(split, ["\n", "\nMäry häd ä little lämb\nLittle "]);
|
|
|
|
|
|
2015-04-01 18:28:34 +00:00
|
|
|
|
let split: Vec<&str> = data.rsplitn(2, |c: char| c == 'ä').collect();
|
2015-03-15 00:07:13 +00:00
|
|
|
|
assert_eq!(split, ["mb\n", "\nMäry häd ä little lämb\nLittle l"]);
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
#[test]
|
2015-04-18 17:49:51 +00:00
|
|
|
|
fn test_split_whitespace() {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let data = "\n \tMäry häd\tä little lämb\nLittle lämb\n";
|
2015-04-18 17:49:51 +00:00
|
|
|
|
let words: Vec<&str> = data.split_whitespace().collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(words, ["Märy", "häd", "ä", "little", "lämb", "Little", "lämb"])
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_lines() {
|
2015-08-27 00:30:45 +00:00
|
|
|
|
let data = "\nMäry häd ä little lämb\n\r\nLittle lämb\n";
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let lines: Vec<&str> = data.lines().collect();
|
|
|
|
|
assert_eq!(lines, ["", "Märy häd ä little lämb", "", "Little lämb"]);
|
|
|
|
|
|
2015-08-27 00:30:45 +00:00
|
|
|
|
let data = "\r\nMäry häd ä little lämb\n\nLittle lämb"; // no trailing \n
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let lines: Vec<&str> = data.lines().collect();
|
|
|
|
|
assert_eq!(lines, ["", "Märy häd ä little lämb", "", "Little lämb"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
2015-03-30 18:00:05 +00:00
|
|
|
|
fn test_splitator() {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
fn t(s: &str, sep: &str, u: &[&str]) {
|
2015-03-30 18:00:05 +00:00
|
|
|
|
let v: Vec<&str> = s.split(sep).collect();
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(v, u);
|
|
|
|
|
}
|
|
|
|
|
t("--1233345--", "12345", &["--1233345--"]);
|
|
|
|
|
t("abc::hello::there", "::", &["abc", "hello", "there"]);
|
|
|
|
|
t("::hello::there", "::", &["", "hello", "there"]);
|
|
|
|
|
t("hello::there::", "::", &["hello", "there", ""]);
|
|
|
|
|
t("::hello::there::", "::", &["", "hello", "there", ""]);
|
|
|
|
|
t("ประเทศไทย中华Việt Nam", "中华", &["ประเทศไทย", "Việt Nam"]);
|
|
|
|
|
t("zzXXXzzYYYzz", "zz", &["", "XXX", "YYY", ""]);
|
|
|
|
|
t("zzXXXzYYYz", "XXX", &["zz", "zYYYz"]);
|
|
|
|
|
t(".XXX.YYY.", ".", &["", "XXX", "YYY", ""]);
|
|
|
|
|
t("", ".", &[""]);
|
|
|
|
|
t("zz", "zz", &["",""]);
|
|
|
|
|
t("ok", "z", &["ok"]);
|
|
|
|
|
t("zzz", "zz", &["","z"]);
|
|
|
|
|
t("zzzzz", "zz", &["","","z"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_str_default() {
|
|
|
|
|
use std::default::Default;
|
|
|
|
|
|
2015-03-30 16:22:46 +00:00
|
|
|
|
fn t<S: Default + AsRef<str>>() {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let s: S = Default::default();
|
2015-03-30 16:22:46 +00:00
|
|
|
|
assert_eq!(s.as_ref(), "");
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
t::<&str>();
|
|
|
|
|
t::<String>();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_str_container() {
|
|
|
|
|
fn sum_len(v: &[&str]) -> usize {
|
|
|
|
|
v.iter().map(|x| x.len()).sum()
|
|
|
|
|
}
|
|
|
|
|
|
2015-10-22 02:14:11 +00:00
|
|
|
|
let s = "01234";
|
2015-03-11 04:58:16 +00:00
|
|
|
|
assert_eq!(5, sum_len(&["012", "", "34"]));
|
2015-10-22 02:14:11 +00:00
|
|
|
|
assert_eq!(5, sum_len(&["01", "2", "34", ""]));
|
|
|
|
|
assert_eq!(5, sum_len(&[s]));
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_str_from_utf8() {
|
|
|
|
|
let xs = b"hello";
|
|
|
|
|
assert_eq!(from_utf8(xs), Ok("hello"));
|
|
|
|
|
|
|
|
|
|
let xs = "ศไทย中华Việt Nam".as_bytes();
|
|
|
|
|
assert_eq!(from_utf8(xs), Ok("ศไทย中华Việt Nam"));
|
|
|
|
|
|
|
|
|
|
let xs = b"hello\xFF";
|
2015-04-10 23:05:09 +00:00
|
|
|
|
assert!(from_utf8(xs).is_err());
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|
|
|
|
|
|
2015-04-01 20:45:00 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_pattern_deref_forward() {
|
|
|
|
|
let data = "aabcdaa";
|
|
|
|
|
assert!(data.contains("bcd"));
|
|
|
|
|
assert!(data.contains(&"bcd"));
|
|
|
|
|
assert!(data.contains(&"bcd".to_string()));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_empty_match_indices() {
|
|
|
|
|
let data = "aä中!";
|
|
|
|
|
let vec: Vec<_> = data.match_indices("").collect();
|
2015-09-24 15:38:48 +00:00
|
|
|
|
assert_eq!(vec, [(0, ""), (1, ""), (3, ""), (6, ""), (7, "")]);
|
2015-04-01 20:45:00 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_bool_from_str() {
|
|
|
|
|
assert_eq!("true".parse().ok(), Some(true));
|
|
|
|
|
assert_eq!("false".parse().ok(), Some(false));
|
|
|
|
|
assert_eq!("not even a boolean".parse::<bool>().ok(), None);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn check_contains_all_substrings(s: &str) {
|
|
|
|
|
assert!(s.contains(""));
|
|
|
|
|
for i in 0..s.len() {
|
|
|
|
|
for j in i+1..s.len() + 1 {
|
|
|
|
|
assert!(s.contains(&s[i..j]));
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn strslice_issue_16589() {
|
|
|
|
|
assert!("bananas".contains("nana"));
|
|
|
|
|
|
|
|
|
|
// prior to the fix for #16589, x.contains("abcdabcd") returned false
|
|
|
|
|
// test all substrings for good measure
|
|
|
|
|
check_contains_all_substrings("012345678901234567890123456789bcdabcdabcd");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn strslice_issue_16878() {
|
|
|
|
|
assert!(!"1234567ah012345678901ah".contains("hah"));
|
|
|
|
|
assert!(!"00abc01234567890123456789abc".contains("bcabc"));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_strslice_contains() {
|
|
|
|
|
let x = "There are moments, Jeeves, when one asks oneself, 'Do trousers matter?'";
|
|
|
|
|
check_contains_all_substrings(x);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_rsplitn_char_iterator() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
|
|
|
|
let mut split: Vec<&str> = data.rsplitn(4, ' ').collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["\nMäry häd ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut split: Vec<&str> = data.rsplitn(4, |c: char| c == ' ').collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["\nMäry häd ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
// Unicode
|
|
|
|
|
let mut split: Vec<&str> = data.rsplitn(4, 'ä').collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["\nMäry häd ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut split: Vec<&str> = data.rsplitn(4, |c: char| c == 'ä').collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["\nMäry häd ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_split_char_iterator() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.split(' ').collect();
|
|
|
|
|
assert_eq!( split, ["\nMäry", "häd", "ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut rsplit: Vec<&str> = data.split(' ').rev().collect();
|
|
|
|
|
rsplit.reverse();
|
|
|
|
|
assert_eq!(rsplit, ["\nMäry", "häd", "ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.split(|c: char| c == ' ').collect();
|
|
|
|
|
assert_eq!( split, ["\nMäry", "häd", "ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut rsplit: Vec<&str> = data.split(|c: char| c == ' ').rev().collect();
|
|
|
|
|
rsplit.reverse();
|
|
|
|
|
assert_eq!(rsplit, ["\nMäry", "häd", "ä", "little", "lämb\nLittle", "lämb\n"]);
|
|
|
|
|
|
|
|
|
|
// Unicode
|
|
|
|
|
let split: Vec<&str> = data.split('ä').collect();
|
|
|
|
|
assert_eq!( split, ["\nM", "ry h", "d ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut rsplit: Vec<&str> = data.split('ä').rev().collect();
|
|
|
|
|
rsplit.reverse();
|
|
|
|
|
assert_eq!(rsplit, ["\nM", "ry h", "d ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
|
|
|
|
|
let split: Vec<&str> = data.split(|c: char| c == 'ä').collect();
|
|
|
|
|
assert_eq!( split, ["\nM", "ry h", "d ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
|
|
|
|
|
let mut rsplit: Vec<&str> = data.split(|c: char| c == 'ä').rev().collect();
|
|
|
|
|
rsplit.reverse();
|
|
|
|
|
assert_eq!(rsplit, ["\nM", "ry h", "d ", " little l", "mb\nLittle l", "mb\n"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_rev_split_char_iterator_no_trailing() {
|
|
|
|
|
let data = "\nMäry häd ä little lämb\nLittle lämb\n";
|
|
|
|
|
|
|
|
|
|
let mut split: Vec<&str> = data.split('\n').rev().collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["", "Märy häd ä little lämb", "Little lämb", ""]);
|
|
|
|
|
|
|
|
|
|
let mut split: Vec<&str> = data.split_terminator('\n').rev().collect();
|
|
|
|
|
split.reverse();
|
|
|
|
|
assert_eq!(split, ["", "Märy häd ä little lämb", "Little lämb"]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_utf16_code_units() {
|
deprecate Unicode functions that will be moved to crates.io
This patch
1. renames libunicode to librustc_unicode,
2. deprecates several pieces of libunicode (see below), and
3. removes references to deprecated functions from
librustc_driver and libsyntax. This may change pretty-printed
output from these modules in cases involving wide or combining
characters used in filenames, identifiers, etc.
The following functions are marked deprecated:
1. char.width() and str.width():
--> use unicode-width crate
2. str.graphemes() and str.grapheme_indices():
--> use unicode-segmentation crate
3. str.nfd_chars(), str.nfkd_chars(), str.nfc_chars(), str.nfkc_chars(),
char.compose(), char.decompose_canonical(), char.decompose_compatible(),
char.canonical_combining_class():
--> use unicode-normalization crate
2015-04-14 19:52:37 +00:00
|
|
|
|
use rustc_unicode::str::Utf16Encoder;
|
2015-04-01 20:45:00 +00:00
|
|
|
|
assert_eq!(Utf16Encoder::new(vec!['é', '\u{1F4A9}'].into_iter()).collect::<Vec<u16>>(),
|
|
|
|
|
[0xE9, 0xD83D, 0xDCA9])
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn starts_with_in_unicode() {
|
|
|
|
|
assert!(!"├── Cargo.toml".starts_with("# "));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn starts_short_long() {
|
|
|
|
|
assert!(!"".starts_with("##"));
|
|
|
|
|
assert!(!"##".starts_with("####"));
|
|
|
|
|
assert!("####".starts_with("##"));
|
|
|
|
|
assert!(!"##ä".starts_with("####"));
|
|
|
|
|
assert!("####ä".starts_with("##"));
|
|
|
|
|
assert!(!"##".starts_with("####ä"));
|
|
|
|
|
assert!("##ä##".starts_with("##ä"));
|
|
|
|
|
|
|
|
|
|
assert!("".starts_with(""));
|
|
|
|
|
assert!("ä".starts_with(""));
|
|
|
|
|
assert!("#ä".starts_with(""));
|
|
|
|
|
assert!("##ä".starts_with(""));
|
|
|
|
|
assert!("ä###".starts_with(""));
|
|
|
|
|
assert!("#ä##".starts_with(""));
|
|
|
|
|
assert!("##ä#".starts_with(""));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn contains_weird_cases() {
|
|
|
|
|
assert!("* \t".contains(' '));
|
|
|
|
|
assert!(!"* \t".contains('?'));
|
|
|
|
|
assert!(!"* \t".contains('\u{1F4A9}'));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn trim_ws() {
|
|
|
|
|
assert_eq!(" \t a \t ".trim_left_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
"a \t ");
|
|
|
|
|
assert_eq!(" \t a \t ".trim_right_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
" \t a");
|
|
|
|
|
assert_eq!(" \t a \t ".trim_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
"a");
|
|
|
|
|
assert_eq!(" \t \t ".trim_left_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
"");
|
|
|
|
|
assert_eq!(" \t \t ".trim_right_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
"");
|
|
|
|
|
assert_eq!(" \t \t ".trim_matches(|c: char| c.is_whitespace()),
|
|
|
|
|
"");
|
|
|
|
|
}
|
|
|
|
|
|
2015-06-06 10:34:24 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn to_lowercase() {
|
|
|
|
|
assert_eq!("".to_lowercase(), "");
|
2015-06-08 17:43:04 +00:00
|
|
|
|
assert_eq!("AÉDžaé ".to_lowercase(), "aédžaé ");
|
|
|
|
|
|
2015-06-06 10:34:24 +00:00
|
|
|
|
// https://github.com/rust-lang/rust/issues/26035
|
2015-06-08 17:43:04 +00:00
|
|
|
|
assert_eq!("ΑΣ".to_lowercase(), "ας");
|
|
|
|
|
assert_eq!("Α'Σ".to_lowercase(), "α'ς");
|
|
|
|
|
assert_eq!("Α''Σ".to_lowercase(), "α''ς");
|
|
|
|
|
|
|
|
|
|
assert_eq!("ΑΣ Α".to_lowercase(), "ας α");
|
|
|
|
|
assert_eq!("Α'Σ Α".to_lowercase(), "α'ς α");
|
|
|
|
|
assert_eq!("Α''Σ Α".to_lowercase(), "α''ς α");
|
|
|
|
|
|
|
|
|
|
assert_eq!("ΑΣ' Α".to_lowercase(), "ας' α");
|
|
|
|
|
assert_eq!("ΑΣ'' Α".to_lowercase(), "ας'' α");
|
|
|
|
|
|
|
|
|
|
assert_eq!("Α'Σ' Α".to_lowercase(), "α'ς' α");
|
|
|
|
|
assert_eq!("Α''Σ'' Α".to_lowercase(), "α''ς'' α");
|
|
|
|
|
|
|
|
|
|
assert_eq!("Α Σ".to_lowercase(), "α σ");
|
|
|
|
|
assert_eq!("Α 'Σ".to_lowercase(), "α 'σ");
|
|
|
|
|
assert_eq!("Α ''Σ".to_lowercase(), "α ''σ");
|
|
|
|
|
|
|
|
|
|
assert_eq!("Σ".to_lowercase(), "σ");
|
|
|
|
|
assert_eq!("'Σ".to_lowercase(), "'σ");
|
|
|
|
|
assert_eq!("''Σ".to_lowercase(), "''σ");
|
|
|
|
|
|
|
|
|
|
assert_eq!("ΑΣΑ".to_lowercase(), "ασα");
|
|
|
|
|
assert_eq!("ΑΣ'Α".to_lowercase(), "ασ'α");
|
|
|
|
|
assert_eq!("ΑΣ''Α".to_lowercase(), "ασ''α");
|
2015-06-06 10:34:24 +00:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn to_uppercase() {
|
|
|
|
|
assert_eq!("".to_uppercase(), "");
|
|
|
|
|
assert_eq!("aéDžßfiᾀ".to_uppercase(), "AÉDŽSSFIἈΙ");
|
|
|
|
|
}
|
|
|
|
|
|
2015-07-10 07:04:06 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_into_string() {
|
|
|
|
|
// The only way to acquire a Box<str> in the first place is through a String, so just
|
|
|
|
|
// test that we can round-trip between Box<str> and String.
|
|
|
|
|
let string = String::from("Some text goes here");
|
2015-08-13 12:02:00 +00:00
|
|
|
|
assert_eq!(string.clone().into_boxed_str().into_string(), string);
|
2015-07-10 07:04:06 +00:00
|
|
|
|
}
|
|
|
|
|
|
2015-07-27 16:06:00 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_box_slice_clone() {
|
|
|
|
|
let data = String::from("hello HELLO hello HELLO yes YES 5 中ä华!!!");
|
2015-08-13 12:02:00 +00:00
|
|
|
|
let data2 = data.clone().into_boxed_str().clone().into_string();
|
2015-07-27 16:06:00 +00:00
|
|
|
|
|
|
|
|
|
assert_eq!(data, data2);
|
|
|
|
|
}
|
|
|
|
|
|
2016-02-03 12:57:25 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn test_cow_from() {
|
|
|
|
|
let borrowed = "borrowed";
|
|
|
|
|
let owned = String::from("owned");
|
|
|
|
|
match (Cow::from(owned.clone()), Cow::from(borrowed)) {
|
|
|
|
|
(Cow::Owned(o), Cow::Borrowed(b)) => assert!(o == owned && b == borrowed),
|
|
|
|
|
_ => panic!("invalid `Cow::from`"),
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2015-04-01 20:45:00 +00:00
|
|
|
|
mod pattern {
|
|
|
|
|
use std::str::pattern::Pattern;
|
|
|
|
|
use std::str::pattern::{Searcher, ReverseSearcher};
|
|
|
|
|
use std::str::pattern::SearchStep::{self, Match, Reject, Done};
|
|
|
|
|
|
|
|
|
|
macro_rules! make_test {
|
|
|
|
|
($name:ident, $p:expr, $h:expr, [$($e:expr,)*]) => {
|
2015-06-10 20:33:52 +00:00
|
|
|
|
#[allow(unused_imports)]
|
2015-04-01 20:45:00 +00:00
|
|
|
|
mod $name {
|
|
|
|
|
use std::str::pattern::SearchStep::{Match, Reject};
|
|
|
|
|
use super::{cmp_search_to_vec};
|
|
|
|
|
#[test]
|
|
|
|
|
fn fwd() {
|
|
|
|
|
cmp_search_to_vec(false, $p, $h, vec![$($e),*]);
|
|
|
|
|
}
|
|
|
|
|
#[test]
|
|
|
|
|
fn bwd() {
|
|
|
|
|
cmp_search_to_vec(true, $p, $h, vec![$($e),*]);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn cmp_search_to_vec<'a, P: Pattern<'a>>(rev: bool, pat: P, haystack: &'a str,
|
|
|
|
|
right: Vec<SearchStep>)
|
|
|
|
|
where P::Searcher: ReverseSearcher<'a>
|
|
|
|
|
{
|
|
|
|
|
let mut searcher = pat.into_searcher(haystack);
|
|
|
|
|
let mut v = vec![];
|
|
|
|
|
loop {
|
|
|
|
|
match if !rev {searcher.next()} else {searcher.next_back()} {
|
|
|
|
|
Match(a, b) => v.push(Match(a, b)),
|
|
|
|
|
Reject(a, b) => v.push(Reject(a, b)),
|
|
|
|
|
Done => break,
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
if rev {
|
|
|
|
|
v.reverse();
|
|
|
|
|
}
|
2015-04-01 23:12:58 +00:00
|
|
|
|
|
|
|
|
|
let mut first_index = 0;
|
|
|
|
|
let mut err = None;
|
|
|
|
|
|
|
|
|
|
for (i, e) in right.iter().enumerate() {
|
|
|
|
|
match *e {
|
|
|
|
|
Match(a, b) | Reject(a, b)
|
|
|
|
|
if a <= b && a == first_index => {
|
|
|
|
|
first_index = b;
|
|
|
|
|
}
|
|
|
|
|
_ => {
|
|
|
|
|
err = Some(i);
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if let Some(err) = err {
|
|
|
|
|
panic!("Input skipped range at {}", err);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if first_index != haystack.len() {
|
|
|
|
|
panic!("Did not cover whole input");
|
|
|
|
|
}
|
|
|
|
|
|
2015-04-01 20:45:00 +00:00
|
|
|
|
assert_eq!(v, right);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
make_test!(str_searcher_ascii_haystack, "bb", "abbcbbd", [
|
|
|
|
|
Reject(0, 1),
|
|
|
|
|
Match (1, 3),
|
|
|
|
|
Reject(3, 4),
|
|
|
|
|
Match (4, 6),
|
|
|
|
|
Reject(6, 7),
|
|
|
|
|
]);
|
2015-06-14 21:17:17 +00:00
|
|
|
|
make_test!(str_searcher_ascii_haystack_seq, "bb", "abbcbbbbd", [
|
|
|
|
|
Reject(0, 1),
|
|
|
|
|
Match (1, 3),
|
|
|
|
|
Reject(3, 4),
|
|
|
|
|
Match (4, 6),
|
|
|
|
|
Match (6, 8),
|
|
|
|
|
Reject(8, 9),
|
|
|
|
|
]);
|
2015-04-01 20:45:00 +00:00
|
|
|
|
make_test!(str_searcher_empty_needle_ascii_haystack, "", "abbcbbd", [
|
2015-04-01 23:12:58 +00:00
|
|
|
|
Match (0, 0),
|
|
|
|
|
Reject(0, 1),
|
|
|
|
|
Match (1, 1),
|
|
|
|
|
Reject(1, 2),
|
|
|
|
|
Match (2, 2),
|
|
|
|
|
Reject(2, 3),
|
|
|
|
|
Match (3, 3),
|
|
|
|
|
Reject(3, 4),
|
|
|
|
|
Match (4, 4),
|
|
|
|
|
Reject(4, 5),
|
|
|
|
|
Match (5, 5),
|
|
|
|
|
Reject(5, 6),
|
|
|
|
|
Match (6, 6),
|
|
|
|
|
Reject(6, 7),
|
|
|
|
|
Match (7, 7),
|
2015-04-01 20:45:00 +00:00
|
|
|
|
]);
|
|
|
|
|
make_test!(str_searcher_mulibyte_haystack, " ", "├──", [
|
|
|
|
|
Reject(0, 3),
|
|
|
|
|
Reject(3, 6),
|
|
|
|
|
Reject(6, 9),
|
|
|
|
|
]);
|
|
|
|
|
make_test!(str_searcher_empty_needle_mulibyte_haystack, "", "├──", [
|
2015-04-01 23:12:58 +00:00
|
|
|
|
Match (0, 0),
|
|
|
|
|
Reject(0, 3),
|
|
|
|
|
Match (3, 3),
|
|
|
|
|
Reject(3, 6),
|
|
|
|
|
Match (6, 6),
|
|
|
|
|
Reject(6, 9),
|
|
|
|
|
Match (9, 9),
|
2015-04-01 20:45:00 +00:00
|
|
|
|
]);
|
|
|
|
|
make_test!(str_searcher_empty_needle_empty_haystack, "", "", [
|
|
|
|
|
Match(0, 0),
|
|
|
|
|
]);
|
|
|
|
|
make_test!(str_searcher_nonempty_needle_empty_haystack, "├", "", [
|
|
|
|
|
]);
|
|
|
|
|
make_test!(char_searcher_ascii_haystack, 'b', "abbcbbd", [
|
|
|
|
|
Reject(0, 1),
|
|
|
|
|
Match (1, 2),
|
|
|
|
|
Match (2, 3),
|
|
|
|
|
Reject(3, 4),
|
|
|
|
|
Match (4, 5),
|
|
|
|
|
Match (5, 6),
|
|
|
|
|
Reject(6, 7),
|
|
|
|
|
]);
|
|
|
|
|
make_test!(char_searcher_mulibyte_haystack, ' ', "├──", [
|
|
|
|
|
Reject(0, 3),
|
|
|
|
|
Reject(3, 6),
|
|
|
|
|
Reject(6, 9),
|
|
|
|
|
]);
|
|
|
|
|
make_test!(char_searcher_short_haystack, '\u{1F4A9}', "* \t", [
|
|
|
|
|
Reject(0, 1),
|
|
|
|
|
Reject(1, 2),
|
|
|
|
|
Reject(2, 3),
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
2015-04-01 23:12:58 +00:00
|
|
|
|
macro_rules! generate_iterator_test {
|
|
|
|
|
{
|
|
|
|
|
$name:ident {
|
|
|
|
|
$(
|
|
|
|
|
($($arg:expr),*) -> [$($t:tt)*];
|
|
|
|
|
)*
|
|
|
|
|
}
|
|
|
|
|
with $fwd:expr, $bwd:expr;
|
|
|
|
|
} => {
|
|
|
|
|
#[test]
|
|
|
|
|
fn $name() {
|
|
|
|
|
$(
|
|
|
|
|
{
|
|
|
|
|
let res = vec![$($t)*];
|
|
|
|
|
|
|
|
|
|
let fwd_vec: Vec<_> = ($fwd)($($arg),*).collect();
|
|
|
|
|
assert_eq!(fwd_vec, res);
|
|
|
|
|
|
|
|
|
|
let mut bwd_vec: Vec<_> = ($bwd)($($arg),*).collect();
|
|
|
|
|
bwd_vec.reverse();
|
|
|
|
|
assert_eq!(bwd_vec, res);
|
|
|
|
|
}
|
|
|
|
|
)*
|
|
|
|
|
}
|
|
|
|
|
};
|
|
|
|
|
{
|
|
|
|
|
$name:ident {
|
|
|
|
|
$(
|
|
|
|
|
($($arg:expr),*) -> [$($t:tt)*];
|
|
|
|
|
)*
|
|
|
|
|
}
|
|
|
|
|
with $fwd:expr;
|
|
|
|
|
} => {
|
|
|
|
|
#[test]
|
|
|
|
|
fn $name() {
|
|
|
|
|
$(
|
|
|
|
|
{
|
|
|
|
|
let res = vec![$($t)*];
|
|
|
|
|
|
|
|
|
|
let fwd_vec: Vec<_> = ($fwd)($($arg),*).collect();
|
|
|
|
|
assert_eq!(fwd_vec, res);
|
|
|
|
|
}
|
|
|
|
|
)*
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
double_ended_split {
|
|
|
|
|
("foo.bar.baz", '.') -> ["foo", "bar", "baz"];
|
|
|
|
|
("foo::bar::baz", "::") -> ["foo", "bar", "baz"];
|
|
|
|
|
}
|
|
|
|
|
with str::split, str::rsplit;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
double_ended_split_terminator {
|
|
|
|
|
("foo;bar;baz;", ';') -> ["foo", "bar", "baz"];
|
|
|
|
|
}
|
|
|
|
|
with str::split_terminator, str::rsplit_terminator;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
double_ended_matches {
|
|
|
|
|
("a1b2c3", char::is_numeric) -> ["1", "2", "3"];
|
|
|
|
|
}
|
|
|
|
|
with str::matches, str::rmatches;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
double_ended_match_indices {
|
2015-09-24 15:38:48 +00:00
|
|
|
|
("a1b2c3", char::is_numeric) -> [(1, "1"), (3, "2"), (5, "3")];
|
2015-04-01 23:12:58 +00:00
|
|
|
|
}
|
|
|
|
|
with str::match_indices, str::rmatch_indices;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
not_double_ended_splitn {
|
|
|
|
|
("foo::bar::baz", 2, "::") -> ["foo", "bar::baz"];
|
|
|
|
|
}
|
|
|
|
|
with str::splitn;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
generate_iterator_test! {
|
|
|
|
|
not_double_ended_rsplitn {
|
|
|
|
|
("foo::bar::baz", 2, "::") -> ["baz", "foo::bar"];
|
|
|
|
|
}
|
|
|
|
|
with str::rsplitn;
|
|
|
|
|
}
|
|
|
|
|
|
2016-03-01 16:53:51 +00:00
|
|
|
|
#[test]
|
|
|
|
|
fn different_str_pattern_forwarding_lifetimes() {
|
|
|
|
|
use std::str::pattern::Pattern;
|
|
|
|
|
|
|
|
|
|
fn foo<'a, P>(p: P) where for<'b> &'b P: Pattern<'a> {
|
|
|
|
|
for _ in 0..3 {
|
|
|
|
|
"asdf".find(&p);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
foo::<&str>("x");
|
|
|
|
|
}
|
|
|
|
|
|
2015-03-11 04:58:16 +00:00
|
|
|
|
mod bench {
|
|
|
|
|
use test::{Bencher, black_box};
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_iterator(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
|
|
|
|
|
b.iter(|| s.chars().count());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_iterator_for(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
for ch in s.chars() { black_box(ch); }
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_iterator_ascii(b: &mut Bencher) {
|
|
|
|
|
let s = "Mary had a little lamb, Little lamb
|
|
|
|
|
Mary had a little lamb, Little lamb
|
|
|
|
|
Mary had a little lamb, Little lamb
|
|
|
|
|
Mary had a little lamb, Little lamb
|
|
|
|
|
Mary had a little lamb, Little lamb
|
|
|
|
|
Mary had a little lamb, Little lamb";
|
|
|
|
|
|
|
|
|
|
b.iter(|| s.chars().count());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_iterator_rev(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
|
|
|
|
|
b.iter(|| s.chars().rev().count());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_iterator_rev_for(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
for ch in s.chars().rev() { black_box(ch); }
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_indicesator(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
let len = s.chars().count();
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.char_indices().count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn char_indicesator_rev(b: &mut Bencher) {
|
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
let len = s.chars().count();
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.char_indices().rev().count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn split_unicode_ascii(b: &mut Bencher) {
|
|
|
|
|
let s = "ประเทศไทย中华Việt Namประเทศไทย中华Việt Nam";
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.split('V').count(), 3));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn split_ascii(b: &mut Bencher) {
|
|
|
|
|
let s = "Mary had a little lamb, Little lamb, little-lamb.";
|
|
|
|
|
let len = s.split(' ').count();
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.split(' ').count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn split_extern_fn(b: &mut Bencher) {
|
|
|
|
|
let s = "Mary had a little lamb, Little lamb, little-lamb.";
|
|
|
|
|
let len = s.split(' ').count();
|
|
|
|
|
fn pred(c: char) -> bool { c == ' ' }
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.split(pred).count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn split_closure(b: &mut Bencher) {
|
|
|
|
|
let s = "Mary had a little lamb, Little lamb, little-lamb.";
|
|
|
|
|
let len = s.split(' ').count();
|
|
|
|
|
|
|
|
|
|
b.iter(|| assert_eq!(s.split(|c: char| c == ' ').count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn split_slice(b: &mut Bencher) {
|
|
|
|
|
let s = "Mary had a little lamb, Little lamb, little-lamb.";
|
|
|
|
|
let len = s.split(' ').count();
|
|
|
|
|
|
|
|
|
|
let c: &[char] = &[' '];
|
|
|
|
|
b.iter(|| assert_eq!(s.split(c).count(), len));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
2015-07-10 12:19:21 +00:00
|
|
|
|
fn bench_join(b: &mut Bencher) {
|
2015-03-11 04:58:16 +00:00
|
|
|
|
let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
|
|
|
|
|
let sep = "→";
|
|
|
|
|
let v = vec![s, s, s, s, s, s, s, s, s, s];
|
|
|
|
|
b.iter(|| {
|
2015-07-10 12:19:21 +00:00
|
|
|
|
assert_eq!(v.join(sep).len(), s.len() * 10 + sep.len() * 9);
|
2015-03-11 04:58:16 +00:00
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn bench_contains_short_short(b: &mut Bencher) {
|
|
|
|
|
let haystack = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
|
|
|
|
|
let needle = "sit";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
assert!(haystack.contains(needle));
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn bench_contains_short_long(b: &mut Bencher) {
|
|
|
|
|
let haystack = "\
|
|
|
|
|
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse quis lorem sit amet dolor \
|
|
|
|
|
ultricies condimentum. Praesent iaculis purus elit, ac malesuada quam malesuada in. Duis sed orci \
|
|
|
|
|
eros. Suspendisse sit amet magna mollis, mollis nunc luctus, imperdiet mi. Integer fringilla non \
|
|
|
|
|
sem ut lacinia. Fusce varius tortor a risus porttitor hendrerit. Morbi mauris dui, ultricies nec \
|
|
|
|
|
tempus vel, gravida nec quam.
|
|
|
|
|
|
|
|
|
|
In est dui, tincidunt sed tempus interdum, adipiscing laoreet ante. Etiam tempor, tellus quis \
|
|
|
|
|
sagittis interdum, nulla purus mattis sem, quis auctor erat odio ac tellus. In nec nunc sit amet \
|
|
|
|
|
diam volutpat molestie at sed ipsum. Vestibulum laoreet consequat vulputate. Integer accumsan \
|
|
|
|
|
lorem ac dignissim placerat. Suspendisse convallis faucibus lorem. Aliquam erat volutpat. In vel \
|
|
|
|
|
eleifend felis. Sed suscipit nulla lorem, sed mollis est sollicitudin et. Nam fermentum egestas \
|
|
|
|
|
interdum. Curabitur ut nisi justo.
|
|
|
|
|
|
|
|
|
|
Sed sollicitudin ipsum tellus, ut condimentum leo eleifend nec. Cras ut velit ante. Phasellus nec \
|
|
|
|
|
mollis odio. Mauris molestie erat in arcu mattis, at aliquet dolor vehicula. Quisque malesuada \
|
|
|
|
|
lectus sit amet nisi pretium, a condimentum ipsum porta. Morbi at dapibus diam. Praesent egestas \
|
|
|
|
|
est sed risus elementum, eu rutrum metus ultrices. Etiam fermentum consectetur magna, id rutrum \
|
|
|
|
|
felis accumsan a. Aliquam ut pellentesque libero. Sed mi nulla, lobortis eu tortor id, suscipit \
|
|
|
|
|
ultricies neque. Morbi iaculis sit amet risus at iaculis. Praesent eget ligula quis turpis \
|
|
|
|
|
feugiat suscipit vel non arcu. Interdum et malesuada fames ac ante ipsum primis in faucibus. \
|
|
|
|
|
Aliquam sit amet placerat lorem.
|
|
|
|
|
|
|
|
|
|
Cras a lacus vel ante posuere elementum. Nunc est leo, bibendum ut facilisis vel, bibendum at \
|
|
|
|
|
mauris. Nullam adipiscing diam vel odio ornare, luctus adipiscing mi luctus. Nulla facilisi. \
|
|
|
|
|
Mauris adipiscing bibendum neque, quis adipiscing lectus tempus et. Sed feugiat erat et nisl \
|
|
|
|
|
lobortis pharetra. Donec vitae erat enim. Nullam sit amet felis et quam lacinia tincidunt. Aliquam \
|
|
|
|
|
suscipit dapibus urna. Sed volutpat urna in magna pulvinar volutpat. Phasellus nec tellus ac diam \
|
|
|
|
|
cursus accumsan.
|
|
|
|
|
|
|
|
|
|
Nam lectus enim, dapibus non nisi tempor, consectetur convallis massa. Maecenas eleifend dictum \
|
|
|
|
|
feugiat. Etiam quis mauris vel risus luctus mattis a a nunc. Nullam orci quam, imperdiet id \
|
|
|
|
|
vehicula in, porttitor ut nibh. Duis sagittis adipiscing nisl vitae congue. Donec mollis risus eu \
|
|
|
|
|
leo suscipit, varius porttitor nulla porta. Pellentesque ut sem nec nisi euismod vehicula. Nulla \
|
|
|
|
|
malesuada sollicitudin quam eu fermentum.";
|
|
|
|
|
let needle = "english";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
assert!(!haystack.contains(needle));
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn bench_contains_bad_naive(b: &mut Bencher) {
|
|
|
|
|
let haystack = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
|
|
|
|
|
let needle = "aaaaaaaab";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
assert!(!haystack.contains(needle));
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[bench]
|
|
|
|
|
fn bench_contains_equal(b: &mut Bencher) {
|
|
|
|
|
let haystack = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
|
|
|
|
|
let needle = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
|
|
|
|
|
|
|
|
|
|
b.iter(|| {
|
|
|
|
|
assert!(haystack.contains(needle));
|
|
|
|
|
})
|
|
|
|
|
}
|
2015-04-01 20:45:00 +00:00
|
|
|
|
|
|
|
|
|
macro_rules! make_test_inner {
|
|
|
|
|
($s:ident, $code:expr, $name:ident, $str:expr) => {
|
|
|
|
|
#[bench]
|
|
|
|
|
fn $name(bencher: &mut Bencher) {
|
|
|
|
|
let mut $s = $str;
|
|
|
|
|
black_box(&mut $s);
|
|
|
|
|
bencher.iter(|| $code);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
macro_rules! make_test {
|
|
|
|
|
($name:ident, $s:ident, $code:expr) => {
|
|
|
|
|
mod $name {
|
|
|
|
|
use test::Bencher;
|
|
|
|
|
use test::black_box;
|
|
|
|
|
|
|
|
|
|
// Short strings: 65 bytes each
|
|
|
|
|
make_test_inner!($s, $code, short_ascii,
|
|
|
|
|
"Mary had a little lamb, Little lamb Mary had a littl lamb, lamb!");
|
|
|
|
|
make_test_inner!($s, $code, short_mixed,
|
|
|
|
|
"ศไทย中华Việt Nam; Mary had a little lamb, Little lam!");
|
|
|
|
|
make_test_inner!($s, $code, short_pile_of_poo,
|
|
|
|
|
"💩💩💩💩💩💩💩💩💩💩💩💩💩💩💩💩!");
|
|
|
|
|
make_test_inner!($s, $code, long_lorem_ipsum,"\
|
|
|
|
|
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse quis lorem sit amet dolor \
|
|
|
|
|
ultricies condimentum. Praesent iaculis purus elit, ac malesuada quam malesuada in. Duis sed orci \
|
|
|
|
|
eros. Suspendisse sit amet magna mollis, mollis nunc luctus, imperdiet mi. Integer fringilla non \
|
|
|
|
|
sem ut lacinia. Fusce varius tortor a risus porttitor hendrerit. Morbi mauris dui, ultricies nec \
|
|
|
|
|
tempus vel, gravida nec quam.
|
|
|
|
|
|
|
|
|
|
In est dui, tincidunt sed tempus interdum, adipiscing laoreet ante. Etiam tempor, tellus quis \
|
|
|
|
|
sagittis interdum, nulla purus mattis sem, quis auctor erat odio ac tellus. In nec nunc sit amet \
|
|
|
|
|
diam volutpat molestie at sed ipsum. Vestibulum laoreet consequat vulputate. Integer accumsan \
|
|
|
|
|
lorem ac dignissim placerat. Suspendisse convallis faucibus lorem. Aliquam erat volutpat. In vel \
|
|
|
|
|
eleifend felis. Sed suscipit nulla lorem, sed mollis est sollicitudin et. Nam fermentum egestas \
|
|
|
|
|
interdum. Curabitur ut nisi justo.
|
|
|
|
|
|
|
|
|
|
Sed sollicitudin ipsum tellus, ut condimentum leo eleifend nec. Cras ut velit ante. Phasellus nec \
|
|
|
|
|
mollis odio. Mauris molestie erat in arcu mattis, at aliquet dolor vehicula. Quisque malesuada \
|
|
|
|
|
lectus sit amet nisi pretium, a condimentum ipsum porta. Morbi at dapibus diam. Praesent egestas \
|
|
|
|
|
est sed risus elementum, eu rutrum metus ultrices. Etiam fermentum consectetur magna, id rutrum \
|
|
|
|
|
felis accumsan a. Aliquam ut pellentesque libero. Sed mi nulla, lobortis eu tortor id, suscipit \
|
|
|
|
|
ultricies neque. Morbi iaculis sit amet risus at iaculis. Praesent eget ligula quis turpis \
|
|
|
|
|
feugiat suscipit vel non arcu. Interdum et malesuada fames ac ante ipsum primis in faucibus. \
|
|
|
|
|
Aliquam sit amet placerat lorem.
|
|
|
|
|
|
|
|
|
|
Cras a lacus vel ante posuere elementum. Nunc est leo, bibendum ut facilisis vel, bibendum at \
|
|
|
|
|
mauris. Nullam adipiscing diam vel odio ornare, luctus adipiscing mi luctus. Nulla facilisi. \
|
|
|
|
|
Mauris adipiscing bibendum neque, quis adipiscing lectus tempus et. Sed feugiat erat et nisl \
|
|
|
|
|
lobortis pharetra. Donec vitae erat enim. Nullam sit amet felis et quam lacinia tincidunt. Aliquam \
|
|
|
|
|
suscipit dapibus urna. Sed volutpat urna in magna pulvinar volutpat. Phasellus nec tellus ac diam \
|
|
|
|
|
cursus accumsan.
|
|
|
|
|
|
|
|
|
|
Nam lectus enim, dapibus non nisi tempor, consectetur convallis massa. Maecenas eleifend dictum \
|
|
|
|
|
feugiat. Etiam quis mauris vel risus luctus mattis a a nunc. Nullam orci quam, imperdiet id \
|
|
|
|
|
vehicula in, porttitor ut nibh. Duis sagittis adipiscing nisl vitae congue. Donec mollis risus eu \
|
|
|
|
|
leo suscipit, varius porttitor nulla porta. Pellentesque ut sem nec nisi euismod vehicula. Nulla \
|
|
|
|
|
malesuada sollicitudin quam eu fermentum!");
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
make_test!(chars_count, s, s.chars().count());
|
|
|
|
|
|
|
|
|
|
make_test!(contains_bang_str, s, s.contains("!"));
|
|
|
|
|
make_test!(contains_bang_char, s, s.contains('!'));
|
|
|
|
|
|
|
|
|
|
make_test!(match_indices_a_str, s, s.match_indices("a").count());
|
|
|
|
|
|
|
|
|
|
make_test!(split_a_str, s, s.split("a").count());
|
|
|
|
|
|
|
|
|
|
make_test!(trim_ascii_char, s, {
|
|
|
|
|
use std::ascii::AsciiExt;
|
|
|
|
|
s.trim_matches(|c: char| c.is_ascii())
|
|
|
|
|
});
|
|
|
|
|
make_test!(trim_left_ascii_char, s, {
|
|
|
|
|
use std::ascii::AsciiExt;
|
|
|
|
|
s.trim_left_matches(|c: char| c.is_ascii())
|
|
|
|
|
});
|
|
|
|
|
make_test!(trim_right_ascii_char, s, {
|
|
|
|
|
use std::ascii::AsciiExt;
|
|
|
|
|
s.trim_right_matches(|c: char| c.is_ascii())
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
make_test!(find_underscore_char, s, s.find('_'));
|
|
|
|
|
make_test!(rfind_underscore_char, s, s.rfind('_'));
|
|
|
|
|
make_test!(find_underscore_str, s, s.find("_"));
|
|
|
|
|
|
|
|
|
|
make_test!(find_zzz_char, s, s.find('\u{1F4A4}'));
|
|
|
|
|
make_test!(rfind_zzz_char, s, s.rfind('\u{1F4A4}'));
|
|
|
|
|
make_test!(find_zzz_str, s, s.find("\u{1F4A4}"));
|
|
|
|
|
|
|
|
|
|
make_test!(split_space_char, s, s.split(' ').count());
|
|
|
|
|
make_test!(split_terminator_space_char, s, s.split_terminator(' ').count());
|
|
|
|
|
|
|
|
|
|
make_test!(splitn_space_char, s, s.splitn(10, ' ').count());
|
|
|
|
|
make_test!(rsplitn_space_char, s, s.rsplitn(10, ' ').count());
|
|
|
|
|
|
|
|
|
|
make_test!(split_space_str, s, s.split(" ").count());
|
|
|
|
|
make_test!(split_ad_str, s, s.split("ad").count());
|
2015-03-11 04:58:16 +00:00
|
|
|
|
}
|