unicode_normalization/
lookups.rs

1// Copyright 2019 The Rust Project Developers. See the COPYRIGHT
2// file at the top-level directory of this distribution and at
3// http://rust-lang.org/COPYRIGHT.
4//
5// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
6// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
7// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
8// option. This file may not be copied, modified, or distributed
9// except according to those terms.
10
11//! Lookups of unicode properties using minimal perfect hashing.
12
13use crate::perfect_hash::mph_lookup;
14use crate::tables::*;
15
16/// Look up the canonical combining class for a codepoint.
17///
18/// The value returned is as defined in the Unicode Character Database.
19pub fn canonical_combining_class(c: char) -> u8 {
20    mph_lookup(
21        c.into(),
22        CANONICAL_COMBINING_CLASS_SALT,
23        CANONICAL_COMBINING_CLASS_KV,
24        u8_lookup_fk,
25        u8_lookup_fv,
26        0,
27    )
28}
29
30pub(crate) fn composition_table(c1: char, c2: char) -> Option<char> {
31    if c1 < '\u{10000}' && c2 < '\u{10000}' {
32        mph_lookup(
33            (c1 as u32) << 16 | (c2 as u32),
34            COMPOSITION_TABLE_SALT,
35            COMPOSITION_TABLE_KV,
36            pair_lookup_fk,
37            pair_lookup_fv_opt,
38            None,
39        )
40    } else {
41        composition_table_astral(c1, c2)
42    }
43}
44
45pub(crate) fn canonical_fully_decomposed(c: char) -> Option<&'static [char]> {
46    mph_lookup(
47        c.into(),
48        CANONICAL_DECOMPOSED_SALT,
49        CANONICAL_DECOMPOSED_KV,
50        pair_lookup_fk,
51        pair_lookup_fv_opt,
52        None,
53    )
54}
55
56pub(crate) fn compatibility_fully_decomposed(c: char) -> Option<&'static [char]> {
57    mph_lookup(
58        c.into(),
59        COMPATIBILITY_DECOMPOSED_SALT,
60        COMPATIBILITY_DECOMPOSED_KV,
61        pair_lookup_fk,
62        pair_lookup_fv_opt,
63        None,
64    )
65}
66
67pub(crate) fn cjk_compat_variants_fully_decomposed(c: char) -> Option<&'static [char]> {
68    mph_lookup(
69        c.into(),
70        CJK_COMPAT_VARIANTS_DECOMPOSED_SALT,
71        CJK_COMPAT_VARIANTS_DECOMPOSED_KV,
72        pair_lookup_fk,
73        pair_lookup_fv_opt,
74        None,
75    )
76}
77
78/// Return whether the given character is a combining mark (`General_Category=Mark`)
79pub fn is_combining_mark(c: char) -> bool {
80    mph_lookup(
81        c.into(),
82        COMBINING_MARK_SALT,
83        COMBINING_MARK_KV,
84        bool_lookup_fk,
85        bool_lookup_fv,
86        false,
87    )
88}
89
90pub fn stream_safe_trailing_nonstarters(c: char) -> usize {
91    mph_lookup(
92        c.into(),
93        TRAILING_NONSTARTERS_SALT,
94        TRAILING_NONSTARTERS_KV,
95        u8_lookup_fk,
96        u8_lookup_fv,
97        0,
98    ) as usize
99}
100
101/// Extract the key in a 24 bit key and 8 bit value packed in a u32.
102#[inline]
103fn u8_lookup_fk(kv: u32) -> u32 {
104    kv >> 8
105}
106
107/// Extract the value in a 24 bit key and 8 bit value packed in a u32.
108#[inline]
109fn u8_lookup_fv(kv: u32) -> u8 {
110    (kv & 0xff) as u8
111}
112
113/// Extract the key for a boolean lookup.
114#[inline]
115fn bool_lookup_fk(kv: u32) -> u32 {
116    kv
117}
118
119/// Extract the value for a boolean lookup.
120#[inline]
121fn bool_lookup_fv(_kv: u32) -> bool {
122    true
123}
124
125/// Extract the key in a pair.
126#[inline]
127fn pair_lookup_fk<T>(kv: (u32, T)) -> u32 {
128    kv.0
129}
130
131/// Extract the value in a pair, returning an option.
132#[inline]
133fn pair_lookup_fv_opt<T>(kv: (u32, T)) -> Option<T> {
134    Some(kv.1)
135}
unicode_normalization/lookups.rs

unicode_normalization/
lookups.rs
