rust/src/libcoretest/char.rs

226 lines
6.5 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.
//
// ignore-lexer-test FIXME #15679
use core::char::{escape_unicode, escape_default};
#[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!('\u2007'.is_whitespace());
assert!('\t'.is_whitespace());
assert!('\n'.is_whitespace());
assert!(!'a'.is_whitespace());
assert!(!'_'.is_whitespace());
assert!(!'\u0000'.is_whitespace());
}
#[test]
fn test_to_digit() {
assert_eq!('0'.to_digit(10u), Some(0u));
assert_eq!('1'.to_digit(2u), Some(1u));
assert_eq!('2'.to_digit(3u), Some(2u));
assert_eq!('9'.to_digit(10u), Some(9u));
assert_eq!('a'.to_digit(16u), Some(10u));
assert_eq!('A'.to_digit(16u), Some(10u));
assert_eq!('b'.to_digit(16u), Some(11u));
assert_eq!('B'.to_digit(16u), Some(11u));
assert_eq!('z'.to_digit(36u), Some(35u));
assert_eq!('Z'.to_digit(36u), Some(35u));
assert_eq!(' '.to_digit(10u), None);
assert_eq!('$'.to_digit(36u), None);
}
#[test]
fn test_to_lowercase() {
assert_eq!('A'.to_lowercase(), 'a');
assert_eq!('Ö'.to_lowercase(), 'ö');
assert_eq!('ß'.to_lowercase(), 'ß');
assert_eq!('Ü'.to_lowercase(), 'ü');
assert_eq!('💩'.to_lowercase(), '💩');
assert_eq!('Σ'.to_lowercase(), 'σ');
assert_eq!('Τ'.to_lowercase(), 'τ');
assert_eq!('Ι'.to_lowercase(), 'ι');
assert_eq!('Γ'.to_lowercase(), 'γ');
assert_eq!('Μ'.to_lowercase(), 'μ');
assert_eq!('Α'.to_lowercase(), 'α');
assert_eq!('Σ'.to_lowercase(), 'σ');
}
#[test]
fn test_to_uppercase() {
assert_eq!('a'.to_uppercase(), 'A');
assert_eq!('ö'.to_uppercase(), 'Ö');
assert_eq!('ß'.to_uppercase(), 'ß'); // not ẞ: Latin capital letter sharp s
assert_eq!('ü'.to_uppercase(), 'Ü');
assert_eq!('💩'.to_uppercase(), '💩');
assert_eq!('σ'.to_uppercase(), 'Σ');
assert_eq!('τ'.to_uppercase(), 'Τ');
assert_eq!('ι'.to_uppercase(), 'Ι');
assert_eq!('γ'.to_uppercase(), 'Γ');
assert_eq!('μ'.to_uppercase(), 'Μ');
assert_eq!('α'.to_uppercase(), 'Α');
assert_eq!('ς'.to_uppercase(), 'Σ');
}
#[test]
fn test_is_control() {
assert!('\u0000'.is_control());
assert!('\u0003'.is_control());
assert!('\u0006'.is_control());
assert!('\u0009'.is_control());
assert!('\u007f'.is_control());
assert!('\u0092'.is_control());
assert!(!'\u0020'.is_control());
assert!(!'\u0055'.is_control());
assert!(!'\u0068'.is_control());
}
#[test]
fn test_is_digit() {
assert!('2'.is_digit());
assert!('7'.is_digit());
assert!(!'c'.is_digit());
assert!(!'i'.is_digit());
assert!(!'z'.is_digit());
assert!(!'Q'.is_digit());
}
#[test]
fn test_escape_default() {
fn string(c: char) -> String {
let mut result = String::new();
Clean up rustc warnings. compiletest: compact "linux" "macos" etc.as "unix". liballoc: remove a superfluous "use". libcollections: remove invocations of deprecated methods in favor of their suggested replacements and use "_" for a loop counter. libcoretest: remove invocations of deprecated methods; also add "allow(deprecated)" for testing a deprecated method itself. libglob: use "cfg_attr". libgraphviz: add a test for one of data constructors. libgreen: remove a superfluous "use". libnum: "allow(type_overflow)" for type cast into u8 in a test code. librustc: names of static variables should be in upper case. libserialize: v[i] instead of get(). libstd/ascii: to_lowercase() instead of to_lower(). libstd/bitflags: modify AnotherSetOfFlags to use i8 as its backend. It will serve better for testing various aspects of bitflags!. libstd/collections: "allow(deprecated)" for testing a deprecated method itself. libstd/io: remove invocations of deprecated methods and superfluous "use". Also add #[test] where it was missing. libstd/num: introduce a helper function to effectively remove invocations of a deprecated method. libstd/path and rand: remove invocations of deprecated methods and superfluous "use". libstd/task and libsync/comm: "allow(deprecated)" for testing a deprecated method itself. libsync/deque: remove superfluous "unsafe". libsync/mutex and once: names of static variables should be in upper case. libterm: introduce a helper function to effectively remove invocations of a deprecated method. We still see a few warnings about using obsoleted native::task::spawn() in the test modules for libsync. I'm not sure how I should replace them with std::task::TaksBuilder and native::task::NativeTaskBuilder (dependency to libstd?) Signed-off-by: NODA, Kai <nodakai@gmail.com>
2014-10-05 05:11:17 -05:00
escape_default(c, |c| { result.push(c); });
return result;
}
let s = string('\n');
assert_eq!(s.as_slice(), "\\n");
let s = string('\r');
assert_eq!(s.as_slice(), "\\r");
let s = string('\'');
assert_eq!(s.as_slice(), "\\'");
let s = string('"');
assert_eq!(s.as_slice(), "\\\"");
let s = string(' ');
assert_eq!(s.as_slice(), " ");
let s = string('a');
assert_eq!(s.as_slice(), "a");
let s = string('~');
assert_eq!(s.as_slice(), "~");
let s = string('\x00');
assert_eq!(s.as_slice(), "\\x00");
let s = string('\x1f');
assert_eq!(s.as_slice(), "\\x1f");
let s = string('\x7f');
assert_eq!(s.as_slice(), "\\x7f");
let s = string('\u00ff');
assert_eq!(s.as_slice(), "\\u00ff");
let s = string('\u011b');
assert_eq!(s.as_slice(), "\\u011b");
let s = string('\U0001d4b6');
assert_eq!(s.as_slice(), "\\U0001d4b6");
}
#[test]
fn test_escape_unicode() {
fn string(c: char) -> String {
let mut result = String::new();
Clean up rustc warnings. compiletest: compact "linux" "macos" etc.as "unix". liballoc: remove a superfluous "use". libcollections: remove invocations of deprecated methods in favor of their suggested replacements and use "_" for a loop counter. libcoretest: remove invocations of deprecated methods; also add "allow(deprecated)" for testing a deprecated method itself. libglob: use "cfg_attr". libgraphviz: add a test for one of data constructors. libgreen: remove a superfluous "use". libnum: "allow(type_overflow)" for type cast into u8 in a test code. librustc: names of static variables should be in upper case. libserialize: v[i] instead of get(). libstd/ascii: to_lowercase() instead of to_lower(). libstd/bitflags: modify AnotherSetOfFlags to use i8 as its backend. It will serve better for testing various aspects of bitflags!. libstd/collections: "allow(deprecated)" for testing a deprecated method itself. libstd/io: remove invocations of deprecated methods and superfluous "use". Also add #[test] where it was missing. libstd/num: introduce a helper function to effectively remove invocations of a deprecated method. libstd/path and rand: remove invocations of deprecated methods and superfluous "use". libstd/task and libsync/comm: "allow(deprecated)" for testing a deprecated method itself. libsync/deque: remove superfluous "unsafe". libsync/mutex and once: names of static variables should be in upper case. libterm: introduce a helper function to effectively remove invocations of a deprecated method. We still see a few warnings about using obsoleted native::task::spawn() in the test modules for libsync. I'm not sure how I should replace them with std::task::TaksBuilder and native::task::NativeTaskBuilder (dependency to libstd?) Signed-off-by: NODA, Kai <nodakai@gmail.com>
2014-10-05 05:11:17 -05:00
escape_unicode(c, |c| { result.push(c); });
return result;
}
let s = string('\x00');
assert_eq!(s.as_slice(), "\\x00");
let s = string('\n');
assert_eq!(s.as_slice(), "\\x0a");
let s = string(' ');
assert_eq!(s.as_slice(), "\\x20");
let s = string('a');
assert_eq!(s.as_slice(), "\\x61");
let s = string('\u011b');
assert_eq!(s.as_slice(), "\\u011b");
let s = string('\U0001d4b6');
assert_eq!(s.as_slice(), "\\U0001d4b6");
}
#[test]
fn test_encode_utf8() {
fn check(input: char, expect: &[u8]) {
let mut buf = [0u8, ..4];
let n = input.encode_utf8(buf.as_mut_slice()).unwrap_or(0);
assert_eq!(buf[..n], expect);
}
check('x', [0x78]);
check('\u00e9', [0xc3, 0xa9]);
check('\ua66e', [0xea, 0x99, 0xae]);
check('\U0001f4a9', [0xf0, 0x9f, 0x92, 0xa9]);
}
#[test]
fn test_encode_utf16() {
fn check(input: char, expect: &[u16]) {
let mut buf = [0u16, ..2];
let n = input.encode_utf16(buf.as_mut_slice()).unwrap_or(0);
assert_eq!(buf[..n], expect);
}
check('x', [0x0078]);
check('\u00e9', [0x00e9]);
check('\ua66e', [0xa66e]);
check('\U0001f4a9', [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_width() {
assert_eq!('\x00'.width(false),Some(0));
assert_eq!('\x00'.width(true),Some(0));
assert_eq!('\x0A'.width(false),None);
assert_eq!('\x0A'.width(true),None);
assert_eq!('w'.width(false),Some(1));
assert_eq!('w'.width(true),Some(1));
assert_eq!(''.width(false),Some(2));
assert_eq!(''.width(true),Some(2));
assert_eq!('\u00AD'.width(false),Some(1));
assert_eq!('\u00AD'.width(true),Some(1));
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
assert_eq!('\u1160'.width(false),Some(0));
assert_eq!('\u1160'.width(true),Some(0));
assert_eq!('\u00a1'.width(false),Some(1));
assert_eq!('\u00a1'.width(true),Some(2));
assert_eq!('\u0300'.width(false),Some(0));
assert_eq!('\u0300'.width(true),Some(0));
}