user0/rust
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

auto merge of #10621 : Florob/rust/unicode63, r=cmr

Browse source 
This update the unicode.rs file to the latest Unicode version released 2013-09-30.
This commit is contained in:
bors 2013-11-27 16:47:14 -08:00
commit 503e5df3f2
5 changed files with 1340 additions and 675 deletions
Download patch file Download diff file Expand all files Collapse all files

51
src/test/pretty/block-comment-wchar.pp
View file

@ -51,34 +51,34 @@ fn f() {
CR4+2: (should align)
*/
/*
// (NEL deliberately omitted)
NEL4+2: (should align)
*/
/*
Ogham Space Mark 4+2: (should align)
*/
/*
Mongolian Vowel Separator 4+2: (should align)
Ogham Space Mark 4+2: (should align)
*/
/*
Four-per-em space 4+2: (should align)
*/
/*
Mongolian Vowel Sep count 1: (should align)
Mongolian Vowel Sep count 2: (should align)
Mongolian Vowel Sep count 3: (should align)
Mongolian Vowel Sep count 4: (should align)
Mongolian Vowel Sep count 5: (should align)
Mongolian Vowel Sep count 6: (should align)
Mongolian Vowel Sep count 7: (should align)
Mongolian Vowel Sep count 8: (should align)
Mongolian Vowel Sep count 9: (should align)
Mongolian Vowel Sep count A: (should align)
Mongolian Vowel Sep count B: (should align)
Mongolian Vowel Sep count C: (should align)
Mongolian Vowel Sep count D: (should align)
Mongolian Vowel Sep count E: (should align)
Mongolian Vowel Sep count F: (should align)
Ogham Space Mark count 1: (should align)
Ogham Space Mark count 2: (should align)
Ogham Space Mark count 3: (should align)
Ogham Space Mark count 4: (should align)
Ogham Space Mark count 5: (should align)
Ogham Space Mark count 6: (should align)
Ogham Space Mark count 7: (should align)
Ogham Space Mark count 8: (should align)
Ogham Space Mark count 9: (should align)
Ogham Space Mark count A: (should align)
Ogham Space Mark count B: (should align)
Ogham Space Mark count C: (should align)
Ogham Space Mark count D: (should align)
Ogham Space Mark count E: (should align)
Ogham Space Mark count F: (should align)
*/
@ -88,26 +88,25 @@ fn f() {
/*
Hello from offset 6
Space 6+2: compare A
Mongolian Vowel Separator 6+2: compare B
Ogham Space Mark 6+2: compare B
*/
/*᠎*/
/* */
/*
Hello from another offset 6 with wchars establishing column offset
Space 6+2: compare C
Mongolian Vowel Separator 6+2: compare D
Ogham Space Mark 6+2: compare D
*/
}
fn main() {
// Taken from http://en.wikipedia.org/wiki/Whitespace_character
// Taken from http://www.unicode.org/Public/UNIDATA/PropList.txt
let chars =
['\x0A', '\x0B', '\x0C', '\x0D', '\x20',
// '\x85', // for some reason Rust thinks NEL isn't whitespace
'\xA0', '\u1680', '\u180E', '\u2000', '\u2001', '\u2002', '\u2003',
'\u2004', '\u2005', '\u2006', '\u2007', '\u2008', '\u2009', '\u200A',
'\u2028', '\u2029', '\u202F', '\u205F', '\u3000'];
['\x0A', '\x0B', '\x0C', '\x0D', '\x20', '\x85', '\xA0', '\u1680',
'\u2000', '\u2001', '\u2002', '\u2003', '\u2004', '\u2005', '\u2006',
'\u2007', '\u2008', '\u2009', '\u200A', '\u2028', '\u2029', '\u202F',
'\u205F', '\u3000'];
for c in chars.iter() {
let ws = c.is_whitespace();
println!("{:?} {:?}" , c , ws);

47
src/test/pretty/block-comment-wchar.rs
View file

@ -51,55 +51,54 @@ fn f() {
CR4+2: (should align)
*/
/*
// (NEL deliberately omitted)
………… NEL4+2: (should align)
*/
/*
     Ogham Space Mark 4+2: (should align)
*/
/*
᠎᠎᠎᠎ Mongolian Vowel Separator 4+2: (should align)
     Ogham Space Mark 4+2: (should align)
*/
/*
     Four-per-em space 4+2: (should align)
*/
/*
᠎ Mongolian Vowel Sep count 1: (should align)
᠎ Mongolian Vowel Sep count 2: (should align)
᠎᠎ Mongolian Vowel Sep count 3: (should align)
᠎ Mongolian Vowel Sep count 4: (should align)
᠎ ᠎ Mongolian Vowel Sep count 5: (should align)
᠎᠎ Mongolian Vowel Sep count 6: (should align)
᠎᠎᠎ Mongolian Vowel Sep count 7: (should align)
᠎ Mongolian Vowel Sep count 8: (should align)
᠎ ᠎ Mongolian Vowel Sep count 9: (should align)
᠎ ᠎ Mongolian Vowel Sep count A: (should align)
᠎ ᠎᠎ Mongolian Vowel Sep count B: (should align)
᠎᠎ Mongolian Vowel Sep count C: (should align)
᠎᠎ ᠎ Mongolian Vowel Sep count D: (should align)
᠎᠎᠎ Mongolian Vowel Sep count E: (should align)
᠎᠎᠎᠎ Mongolian Vowel Sep count F: (should align)
  Ogham Space Mark count 1: (should align)
  Ogham Space Mark count 2: (should align)
   Ogham Space Mark count 3: (should align)
  Ogham Space Mark count 4: (should align)
    Ogham Space Mark count 5: (should align)
   Ogham Space Mark count 6: (should align)
    Ogham Space Mark count 7: (should align)
  Ogham Space Mark count 8: (should align)
    Ogham Space Mark count 9: (should align)
    Ogham Space Mark count A: (should align)
     Ogham Space Mark count B: (should align)
   Ogham Space Mark count C: (should align)
     Ogham Space Mark count D: (should align)
    Ogham Space Mark count E: (should align)
     Ogham Space Mark count F: (should align)
*/
/* */ /*
Hello from offset 6
Space 6+2: compare A
᠎᠎᠎᠎᠎᠎ Mongolian Vowel Separator 6+2: compare B
       Ogham Space Mark 6+2: compare B
*/
/*᠎*/ /*
/* */ /*
Hello from another offset 6 with wchars establishing column offset
Space 6+2: compare C
᠎᠎᠎᠎᠎᠎ Mongolian Vowel Separator 6+2: compare D
       Ogham Space Mark 6+2: compare D
*/
}
fn main() {
// Taken from http://en.wikipedia.org/wiki/Whitespace_character
// Taken from http://www.unicode.org/Public/UNIDATA/PropList.txt
let chars =
['\x0A', '\x0B', '\x0C', '\x0D', '\x20',
// '\x85', // for some reason Rust thinks NEL isn't whitespace
'\xA0', '\u1680', '\u180E', '\u2000', '\u2001', '\u2002', '\u2003',
['\x0A', '\x0B', '\x0C', '\x0D', '\x20', '\x85',
'\xA0', '\u1680', '\u2000', '\u2001', '\u2002', '\u2003',
'\u2004', '\u2005', '\u2006', '\u2007', '\u2008', '\u2009', '\u200A',
'\u2028', '\u2029', '\u202F', '\u205F', '\u3000'];
for c in chars.iter() {