rust/src/libunicode/normalize.rs

150 lines
4.4 KiB
Rust
Raw Normal View History

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
// Copyright 2012-2014 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.
//! Functions for computing canonical and compatible decompositions for Unicode characters.
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
use core::cmp::Ordering::{Equal, Less, Greater};
use core::option::Option;
use core::option::Option::{Some, None};
use core::slice;
use core::slice::SliceExt;
use tables::normalization::{canonical_table, compatibility_table, composition_table};
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
fn bsearch_table<T>(c: char, r: &'static [(char, &'static [T])]) -> Option<&'static [T]> {
match r.binary_search(|&(val, _)| {
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
if c == val { Equal }
else if val < c { Less }
else { Greater }
}) {
2014-11-26 12:21:45 -06:00
slice::BinarySearchResult::Found(idx) => {
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
let (_, result) = r[idx];
Some(result)
}
2014-11-26 12:21:45 -06:00
slice::BinarySearchResult::NotFound(_) => None
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
}
}
/// Compute canonical Unicode decomposition for character
pub fn decompose_canonical(c: char, i: |char|) { d(c, i, false); }
/// Compute canonical or compatible Unicode decomposition for character
pub fn decompose_compatible(c: char, i: |char|) { d(c, i, true); }
fn d(c: char, i: |char|, k: bool) {
// 7-bit ASCII never decomposes
if c <= '\x7f' { i(c); return; }
// Perform decomposition for Hangul
if (c as u32) >= S_BASE && (c as u32) < (S_BASE + S_COUNT) {
decompose_hangul(c, i);
return;
}
// First check the canonical decompositions
match bsearch_table(c, canonical_table) {
Some(canon) => {
for x in canon.iter() {
d(*x, |b| i(b), k);
}
return;
}
None => ()
}
// Bottom out if we're not doing compat.
if !k { i(c); return; }
// Then check the compatibility decompositions
match bsearch_table(c, compatibility_table) {
Some(compat) => {
for x in compat.iter() {
d(*x, |b| i(b), k);
}
return;
}
None => ()
}
// Finally bottom out.
i(c);
}
pub fn compose(a: char, b: char) -> Option<char> {
compose_hangul(a, b).or_else(|| {
match bsearch_table(a, composition_table) {
None => None,
Some(candidates) => {
match candidates.binary_search(|&(val, _)| {
if b == val { Equal }
else if val < b { Less }
else { Greater }
}) {
2014-11-26 12:21:45 -06:00
slice::BinarySearchResult::Found(idx) => {
let (_, result) = candidates[idx];
Some(result)
}
2014-11-26 12:21:45 -06:00
slice::BinarySearchResult::NotFound(_) => None
}
}
}
})
}
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
// Constants from Unicode 6.3.0 Section 3.12 Conjoining Jamo Behavior
const S_BASE: u32 = 0xAC00;
const L_BASE: u32 = 0x1100;
const V_BASE: u32 = 0x1161;
const T_BASE: u32 = 0x11A7;
const L_COUNT: u32 = 19;
const V_COUNT: u32 = 21;
const T_COUNT: u32 = 28;
const N_COUNT: u32 = (V_COUNT * T_COUNT);
const S_COUNT: u32 = (L_COUNT * N_COUNT);
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
// Decompose a precomposed Hangul syllable
#[inline(always)]
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
fn decompose_hangul(s: char, f: |char|) {
use core::mem::transmute;
let si = s as u32 - S_BASE;
let li = si / N_COUNT;
unsafe {
f(transmute(L_BASE + li));
let vi = (si % N_COUNT) / T_COUNT;
f(transmute(V_BASE + vi));
let ti = si % T_COUNT;
if ti > 0 {
f(transmute(T_BASE + ti));
}
}
}
// Compose a pair of Hangul Jamo
#[inline(always)]
fn compose_hangul(a: char, b: char) -> Option<char> {
use core::mem::transmute;
let l = a as u32;
let v = b as u32;
// Compose an LPart and a VPart
if L_BASE <= l && l < (L_BASE + L_COUNT) && V_BASE <= v && v < (V_BASE + V_COUNT) {
let r = S_BASE + (l - L_BASE) * N_COUNT + (v - V_BASE) * T_COUNT;
return unsafe { Some(transmute(r)) };
}
// Compose an LVPart and a TPart
if S_BASE <= l && l <= (S_BASE+S_COUNT-T_COUNT) && T_BASE <= v && v < (T_BASE+T_COUNT) {
let r = l + (v - T_BASE);
return unsafe { Some(transmute(r)) };
}
None
}