1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
// 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.

//! Unicode-intensive string manipulations.
//!
//! This module provides functionality to `str` that requires the Unicode
//! methods provided by the unicode parts of the CharExt trait.

use core::char;
use core::iter::{Filter, FusedIterator};
use core::str::Split;

/// An iterator over the non-whitespace substrings of a string,
/// separated by any amount of whitespace.
///
/// This struct is created by the [`split_whitespace`] method on [`str`].
/// See its documentation for more.
///
/// [`split_whitespace`]: ../../std/primitive.str.html#method.split_whitespace
/// [`str`]: ../../std/primitive.str.html
#[stable(feature = "split_whitespace", since = "1.1.0")]
#[derive(Clone, Debug)]
pub struct SplitWhitespace<'a> {
    inner: Filter<Split<'a, IsWhitespace>, IsNotEmpty>,
}

/// Methods for Unicode string slices
#[allow(missing_docs)] // docs in liballoc
pub trait UnicodeStr {
    fn split_whitespace<'a>(&'a self) -> SplitWhitespace<'a>;
    fn is_whitespace(&self) -> bool;
    fn is_alphanumeric(&self) -> bool;
    fn trim(&self) -> &str;
    fn trim_left(&self) -> &str;
    fn trim_right(&self) -> &str;
}

impl UnicodeStr for str {
    #[inline]
    fn split_whitespace(&self) -> SplitWhitespace {
        SplitWhitespace { inner: self.split(IsWhitespace).filter(IsNotEmpty) }
    }

    #[inline]
    fn is_whitespace(&self) -> bool {
        self.chars().all(|c| c.is_whitespace())
    }

    #[inline]
    fn is_alphanumeric(&self) -> bool {
        self.chars().all(|c| c.is_alphanumeric())
    }

    #[inline]
    fn trim(&self) -> &str {
        self.trim_matches(|c: char| c.is_whitespace())
    }

    #[inline]
    fn trim_left(&self) -> &str {
        self.trim_left_matches(|c: char| c.is_whitespace())
    }

    #[inline]
    fn trim_right(&self) -> &str {
        self.trim_right_matches(|c: char| c.is_whitespace())
    }
}

/// Iterator adaptor for encoding `char`s to UTF-16.
#[derive(Clone)]
#[allow(missing_debug_implementations)]
pub struct Utf16Encoder<I> {
    chars: I,
    extra: u16,
}

impl<I> Utf16Encoder<I> {
    /// Create a UTF-16 encoder from any `char` iterator.
    pub fn new(chars: I) -> Utf16Encoder<I>
        where I: Iterator<Item = char>
    {
        Utf16Encoder {
            chars,
            extra: 0,
        }
    }
}

impl<I> Iterator for Utf16Encoder<I>
    where I: Iterator<Item = char>
{
    type Item = u16;

    #[inline]
    fn next(&mut self) -> Option<u16> {
        if self.extra != 0 {
            let tmp = self.extra;
            self.extra = 0;
            return Some(tmp);
        }

        let mut buf = [0; 2];
        self.chars.next().map(|ch| {
            let n = CharExt::encode_utf16(ch, &mut buf).len();
            if n == 2 {
                self.extra = buf[1];
            }
            buf[0]
        })
    }

    #[inline]
    fn size_hint(&self) -> (usize, Option<usize>) {
        let (low, high) = self.chars.size_hint();
        // every char gets either one u16 or two u16,
        // so this iterator is between 1 or 2 times as
        // long as the underlying iterator.
        (low, high.and_then(|n| n.checked_mul(2)))
    }
}

impl<I> FusedIterator for Utf16Encoder<I>
    where I: FusedIterator<Item = char> {}

#[derive(Clone)]
struct IsWhitespace;

impl FnOnce<(char, )> for IsWhitespace {
    type Output = bool;

    #[inline]
    extern "rust-call" fn call_once(mut self, arg: (char, )) -> bool {
        self.call_mut(arg)
    }
}

impl FnMut<(char, )> for IsWhitespace {
    #[inline]
    extern "rust-call" fn call_mut(&mut self, arg: (char, )) -> bool {
        arg.0.is_whitespace()
    }
}

#[derive(Clone)]
struct IsNotEmpty;

impl<'a, 'b> FnOnce<(&'a &'b str, )> for IsNotEmpty {
    type Output = bool;

    #[inline]
    extern "rust-call" fn call_once(mut self, arg: (&&str, )) -> bool {
        self.call_mut(arg)
    }
}

impl<'a, 'b> FnMut<(&'a &'b str, )> for IsNotEmpty {
    #[inline]
    extern "rust-call" fn call_mut(&mut self, arg: (&&str, )) -> bool {
        !arg.0.is_empty()
    }
}


#[stable(feature = "split_whitespace", since = "1.1.0")]
impl<'a> Iterator for SplitWhitespace<'a> {
    type Item = &'a str;

    fn next(&mut self) -> Option<&'a str> {
        self.inner.next()
    }
}

#[stable(feature = "split_whitespace", since = "1.1.0")]
impl<'a> DoubleEndedIterator for SplitWhitespace<'a> {
    fn next_back(&mut self) -> Option<&'a str> {
        self.inner.next_back()
    }
}

#[stable(feature = "fused", since = "1.26.0")]
impl<'a> FusedIterator for SplitWhitespace<'a> {}