rust/src/libcoretest/char.rs

266 lines
7.7 KiB
Rust
Raw Normal View History

// Copyright 2014 The Rust Project Developers. See the COPYRIGHT
// 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.
std: Stabilize APIs for the 1.9 release This commit applies all stabilizations, renamings, and deprecations that the library team has decided on for the upcoming 1.9 release. All tracking issues have gone through a cycle-long "final comment period" and the specific APIs stabilized/deprecated are: Stable * `std::panic` * `std::panic::catch_unwind` (renamed from `recover`) * `std::panic::resume_unwind` (renamed from `propagate`) * `std::panic::AssertUnwindSafe` (renamed from `AssertRecoverSafe`) * `std::panic::UnwindSafe` (renamed from `RecoverSafe`) * `str::is_char_boundary` * `<*const T>::as_ref` * `<*mut T>::as_ref` * `<*mut T>::as_mut` * `AsciiExt::make_ascii_uppercase` * `AsciiExt::make_ascii_lowercase` * `char::decode_utf16` * `char::DecodeUtf16` * `char::DecodeUtf16Error` * `char::DecodeUtf16Error::unpaired_surrogate` * `BTreeSet::take` * `BTreeSet::replace` * `BTreeSet::get` * `HashSet::take` * `HashSet::replace` * `HashSet::get` * `OsString::with_capacity` * `OsString::clear` * `OsString::capacity` * `OsString::reserve` * `OsString::reserve_exact` * `OsStr::is_empty` * `OsStr::len` * `std::os::unix::thread` * `RawPthread` * `JoinHandleExt` * `JoinHandleExt::as_pthread_t` * `JoinHandleExt::into_pthread_t` * `HashSet::hasher` * `HashMap::hasher` * `CommandExt::exec` * `File::try_clone` * `SocketAddr::set_ip` * `SocketAddr::set_port` * `SocketAddrV4::set_ip` * `SocketAddrV4::set_port` * `SocketAddrV6::set_ip` * `SocketAddrV6::set_port` * `SocketAddrV6::set_flowinfo` * `SocketAddrV6::set_scope_id` * `<[T]>::copy_from_slice` * `ptr::read_volatile` * `ptr::write_volatile` * The `#[deprecated]` attribute * `OpenOptions::create_new` Deprecated * `std::raw::Slice` - use raw parts of `slice` module instead * `std::raw::Repr` - use raw parts of `slice` module instead * `str::char_range_at` - use slicing plus `chars()` plus `len_utf8` * `str::char_range_at_reverse` - use slicing plus `chars().rev()` plus `len_utf8` * `str::char_at` - use slicing plus `chars()` * `str::char_at_reverse` - use slicing plus `chars().rev()` * `str::slice_shift_char` - use `chars()` plus `Chars::as_str` * `CommandExt::session_leader` - use `before_exec` instead. Closes #27719 cc #27751 (deprecating the `Slice` bits) Closes #27754 Closes #27780 Closes #27809 Closes #27811 Closes #27830 Closes #28050 Closes #29453 Closes #29791 Closes #29935 Closes #30014 Closes #30752 Closes #31262 cc #31398 (still need to deal with `before_exec`) Closes #31405 Closes #31572 Closes #31755 Closes #31756
2016-04-07 12:42:53 -05:00
use std::char;
#[test]
fn test_is_lowercase() {
assert!('a'.is_lowercase());
assert!('ö'.is_lowercase());
assert!('ß'.is_lowercase());
assert!(!'Ü'.is_lowercase());
assert!(!'P'.is_lowercase());
}
#[test]
fn test_is_uppercase() {
assert!(!'h'.is_uppercase());
assert!(!'ä'.is_uppercase());
assert!(!'ß'.is_uppercase());
assert!('Ö'.is_uppercase());
assert!('T'.is_uppercase());
}
#[test]
fn test_is_whitespace() {
assert!(' '.is_whitespace());
assert!('\u{2007}'.is_whitespace());
assert!('\t'.is_whitespace());
assert!('\n'.is_whitespace());
assert!(!'a'.is_whitespace());
assert!(!'_'.is_whitespace());
assert!(!'\u{0}'.is_whitespace());
}
#[test]
fn test_to_digit() {
assert_eq!('0'.to_digit(10), Some(0));
assert_eq!('1'.to_digit(2), Some(1));
assert_eq!('2'.to_digit(3), Some(2));
assert_eq!('9'.to_digit(10), Some(9));
assert_eq!('a'.to_digit(16), Some(10));
assert_eq!('A'.to_digit(16), Some(10));
assert_eq!('b'.to_digit(16), Some(11));
assert_eq!('B'.to_digit(16), Some(11));
assert_eq!('z'.to_digit(36), Some(35));
assert_eq!('Z'.to_digit(36), Some(35));
assert_eq!(' '.to_digit(10), None);
assert_eq!('$'.to_digit(36), None);
}
#[test]
fn test_to_lowercase() {
fn lower(c: char) -> Vec<char> {
c.to_lowercase().collect()
}
assert_eq!(lower('A'), ['a']);
assert_eq!(lower('Ö'), ['ö']);
assert_eq!(lower('ß'), ['ß']);
assert_eq!(lower('Ü'), ['ü']);
assert_eq!(lower('💩'), ['💩']);
assert_eq!(lower('Σ'), ['σ']);
assert_eq!(lower('Τ'), ['τ']);
assert_eq!(lower('Ι'), ['ι']);
assert_eq!(lower('Γ'), ['γ']);
assert_eq!(lower('Μ'), ['μ']);
assert_eq!(lower('Α'), ['α']);
assert_eq!(lower('Σ'), ['σ']);
assert_eq!(lower('Dž'), ['dž']);
assert_eq!(lower('fi'), ['fi']);
assert_eq!(lower('İ'), ['i', '\u{307}']);
}
#[test]
fn test_to_uppercase() {
fn upper(c: char) -> Vec<char> {
c.to_uppercase().collect()
}
assert_eq!(upper('a'), ['A']);
assert_eq!(upper('ö'), ['Ö']);
assert_eq!(upper('ß'), ['S', 'S']); // not ẞ: Latin capital letter sharp s
assert_eq!(upper('ü'), ['Ü']);
assert_eq!(upper('💩'), ['💩']);
assert_eq!(upper('σ'), ['Σ']);
assert_eq!(upper('τ'), ['Τ']);
assert_eq!(upper('ι'), ['Ι']);
assert_eq!(upper('γ'), ['Γ']);
assert_eq!(upper('μ'), ['Μ']);
assert_eq!(upper('α'), ['Α']);
assert_eq!(upper('ς'), ['Σ']);
assert_eq!(upper('Dž'), ['DŽ']);
assert_eq!(upper('fi'), ['F', 'I']);
assert_eq!(upper('ᾀ'), ['Ἀ', 'Ι']);
}
#[test]
fn test_is_control() {
assert!('\u{0}'.is_control());
assert!('\u{3}'.is_control());
assert!('\u{6}'.is_control());
assert!('\u{9}'.is_control());
assert!('\u{7f}'.is_control());
assert!('\u{92}'.is_control());
assert!(!'\u{20}'.is_control());
assert!(!'\u{55}'.is_control());
assert!(!'\u{68}'.is_control());
}
#[test]
fn test_is_digit() {
assert!('2'.is_numeric());
assert!('7'.is_numeric());
assert!(!'c'.is_numeric());
assert!(!'i'.is_numeric());
assert!(!'z'.is_numeric());
assert!(!'Q'.is_numeric());
}
#[test]
fn test_escape_default() {
fn string(c: char) -> String {
c.escape_default().collect()
}
let s = string('\n');
assert_eq!(s, "\\n");
let s = string('\r');
assert_eq!(s, "\\r");
let s = string('\'');
assert_eq!(s, "\\'");
let s = string('"');
assert_eq!(s, "\\\"");
let s = string(' ');
assert_eq!(s, " ");
let s = string('a');
assert_eq!(s, "a");
let s = string('~');
assert_eq!(s, "~");
let s = string('\x00');
assert_eq!(s, "\\u{0}");
let s = string('\x1f');
assert_eq!(s, "\\u{1f}");
let s = string('\x7f');
assert_eq!(s, "\\u{7f}");
let s = string('\u{ff}');
assert_eq!(s, "\\u{ff}");
let s = string('\u{11b}');
assert_eq!(s, "\\u{11b}");
let s = string('\u{1d4b6}');
assert_eq!(s, "\\u{1d4b6}");
}
#[test]
fn test_escape_unicode() {
fn string(c: char) -> String { c.escape_unicode().collect() }
let s = string('\x00');
assert_eq!(s, "\\u{0}");
let s = string('\n');
assert_eq!(s, "\\u{a}");
let s = string(' ');
assert_eq!(s, "\\u{20}");
let s = string('a');
assert_eq!(s, "\\u{61}");
let s = string('\u{11b}');
assert_eq!(s, "\\u{11b}");
let s = string('\u{1d4b6}');
assert_eq!(s, "\\u{1d4b6}");
}
#[test]
fn test_encode_utf8() {
fn check(input: char, expect: &[u8]) {
assert_eq!(input.encode_utf8().as_slice(), expect);
for (a, b) in input.encode_utf8().zip(expect) {
assert_eq!(a, *b);
}
}
2014-11-17 02:39:01 -06:00
check('x', &[0x78]);
check('\u{e9}', &[0xc3, 0xa9]);
check('\u{a66e}', &[0xea, 0x99, 0xae]);
check('\u{1f4a9}', &[0xf0, 0x9f, 0x92, 0xa9]);
}
#[test]
fn test_encode_utf16() {
fn check(input: char, expect: &[u16]) {
assert_eq!(input.encode_utf16().as_slice(), expect);
for (a, b) in input.encode_utf16().zip(expect) {
assert_eq!(a, *b);
}
}
2014-11-17 02:39:01 -06:00
check('x', &[0x0078]);
check('\u{e9}', &[0x00e9]);
check('\u{a66e}', &[0xa66e]);
check('\u{1f4a9}', &[0xd83d, 0xdca9]);
}
Add libunicode; move unicode functions from core - created new crate, libunicode, below libstd - split Char trait into Char (libcore) and UnicodeChar (libunicode) - Unicode-aware functions now live in libunicode - is_alphabetic, is_XID_start, is_XID_continue, is_lowercase, is_uppercase, is_whitespace, is_alphanumeric, is_control, is_digit, to_uppercase, to_lowercase - added width method in UnicodeChar trait - determines printed width of character in columns, or None if it is a non-NULL control character - takes a boolean argument indicating whether the present context is CJK or not (characters with 'A'mbiguous widths are double-wide in CJK contexts, single-wide otherwise) - split StrSlice into StrSlice (libcore) and UnicodeStrSlice (libunicode) - functionality formerly in StrSlice that relied upon Unicode functionality from Char is now in UnicodeStrSlice - words, is_whitespace, is_alphanumeric, trim, trim_left, trim_right - also moved Words type alias into libunicode because words method is in UnicodeStrSlice - unified Unicode tables from libcollections, libcore, and libregex into libunicode - updated unicode.py in src/etc to generate aforementioned tables - generated new tables based on latest Unicode data - added UnicodeChar and UnicodeStrSlice traits to prelude - libunicode is now the collection point for the std::char module, combining the libunicode functionality with the Char functionality from libcore - thus, moved doc comment for char from core::char to unicode::char - libcollections remains the collection point for std::str The Unicode-aware functions that previously lived in the Char and StrSlice traits are no longer available to programs that only use libcore. To regain use of these methods, include the libunicode crate and use the UnicodeChar and/or UnicodeStrSlice traits: extern crate unicode; use unicode::UnicodeChar; use unicode::UnicodeStrSlice; use unicode::Words; // if you want to use the words() method NOTE: this does *not* impact programs that use libstd, since UnicodeChar and UnicodeStrSlice have been added to the prelude. closes #15224 [breaking-change]
2014-06-30 16:04:10 -05:00
#[test]
fn test_len_utf16() {
assert!('x'.len_utf16() == 1);
assert!('\u{e9}'.len_utf16() == 1);
assert!('\u{a66e}'.len_utf16() == 1);
assert!('\u{1f4a9}'.len_utf16() == 2);
}
#[test]
fn test_decode_utf16() {
fn check(s: &[u16], expected: &[Result<char, u16>]) {
std: Stabilize APIs for the 1.9 release This commit applies all stabilizations, renamings, and deprecations that the library team has decided on for the upcoming 1.9 release. All tracking issues have gone through a cycle-long "final comment period" and the specific APIs stabilized/deprecated are: Stable * `std::panic` * `std::panic::catch_unwind` (renamed from `recover`) * `std::panic::resume_unwind` (renamed from `propagate`) * `std::panic::AssertUnwindSafe` (renamed from `AssertRecoverSafe`) * `std::panic::UnwindSafe` (renamed from `RecoverSafe`) * `str::is_char_boundary` * `<*const T>::as_ref` * `<*mut T>::as_ref` * `<*mut T>::as_mut` * `AsciiExt::make_ascii_uppercase` * `AsciiExt::make_ascii_lowercase` * `char::decode_utf16` * `char::DecodeUtf16` * `char::DecodeUtf16Error` * `char::DecodeUtf16Error::unpaired_surrogate` * `BTreeSet::take` * `BTreeSet::replace` * `BTreeSet::get` * `HashSet::take` * `HashSet::replace` * `HashSet::get` * `OsString::with_capacity` * `OsString::clear` * `OsString::capacity` * `OsString::reserve` * `OsString::reserve_exact` * `OsStr::is_empty` * `OsStr::len` * `std::os::unix::thread` * `RawPthread` * `JoinHandleExt` * `JoinHandleExt::as_pthread_t` * `JoinHandleExt::into_pthread_t` * `HashSet::hasher` * `HashMap::hasher` * `CommandExt::exec` * `File::try_clone` * `SocketAddr::set_ip` * `SocketAddr::set_port` * `SocketAddrV4::set_ip` * `SocketAddrV4::set_port` * `SocketAddrV6::set_ip` * `SocketAddrV6::set_port` * `SocketAddrV6::set_flowinfo` * `SocketAddrV6::set_scope_id` * `<[T]>::copy_from_slice` * `ptr::read_volatile` * `ptr::write_volatile` * The `#[deprecated]` attribute * `OpenOptions::create_new` Deprecated * `std::raw::Slice` - use raw parts of `slice` module instead * `std::raw::Repr` - use raw parts of `slice` module instead * `str::char_range_at` - use slicing plus `chars()` plus `len_utf8` * `str::char_range_at_reverse` - use slicing plus `chars().rev()` plus `len_utf8` * `str::char_at` - use slicing plus `chars()` * `str::char_at_reverse` - use slicing plus `chars().rev()` * `str::slice_shift_char` - use `chars()` plus `Chars::as_str` * `CommandExt::session_leader` - use `before_exec` instead. Closes #27719 cc #27751 (deprecating the `Slice` bits) Closes #27754 Closes #27780 Closes #27809 Closes #27811 Closes #27830 Closes #28050 Closes #29453 Closes #29791 Closes #29935 Closes #30014 Closes #30752 Closes #31262 cc #31398 (still need to deal with `before_exec`) Closes #31405 Closes #31572 Closes #31755 Closes #31756
2016-04-07 12:42:53 -05:00
let v = char::decode_utf16(s.iter().cloned())
.map(|r| r.map_err(|e| e.unpaired_surrogate()))
.collect::<Vec<_>>();
assert_eq!(v, expected);
}
check(&[0xD800, 0x41, 0x42], &[Err(0xD800), Ok('A'), Ok('B')]);
check(&[0xD800, 0], &[Err(0xD800), Ok('\0')]);
}
#[test]
fn ed_iterator_specializations() {
// Check counting
assert_eq!('\n'.escape_default().count(), 2);
assert_eq!('c'.escape_default().count(), 1);
assert_eq!(' '.escape_default().count(), 1);
assert_eq!('\\'.escape_default().count(), 2);
assert_eq!('\''.escape_default().count(), 2);
// Check nth
// Check that OoB is handled correctly
assert_eq!('\n'.escape_default().nth(2), None);
assert_eq!('c'.escape_default().nth(1), None);
assert_eq!(' '.escape_default().nth(1), None);
assert_eq!('\\'.escape_default().nth(2), None);
assert_eq!('\''.escape_default().nth(2), None);
// Check the first char
assert_eq!('\n'.escape_default().nth(0), Some('\\'));
assert_eq!('c'.escape_default().nth(0), Some('c'));
assert_eq!(' '.escape_default().nth(0), Some(' '));
assert_eq!('\\'.escape_default().nth(0), Some('\\'));
assert_eq!('\''.escape_default().nth(0), Some('\\'));
// Check the second char
assert_eq!('\n'.escape_default().nth(1), Some('n'));
assert_eq!('\\'.escape_default().nth(1), Some('\\'));
assert_eq!('\''.escape_default().nth(1), Some('\''));
// Check the last char
assert_eq!('\n'.escape_default().last(), Some('n'));
assert_eq!('c'.escape_default().last(), Some('c'));
assert_eq!(' '.escape_default().last(), Some(' '));
assert_eq!('\\'.escape_default().last(), Some('\\'));
assert_eq!('\''.escape_default().last(), Some('\''));
}