Question

请帮我创建一个函数来解析下面的数组，并返回一个包含最常出现的字符不区分大小写的数组，并排除特殊字符，计数输入

    $sentences = [
    0 => 'The tiger is the national animal of India',
    1 => 'The tiger is a large carnivorous mammal that roams the forests',
    2 => 'The tiger feeds on animals that also live in the forest',
    3 => 'The tiger does have a coat of orange with black stripes',
    4 => 'Tigers, regardless of their subspecies, are carnivorous animals',
    5 => 'The tiger is a protected species',
    ];

The code should output the following result: 

    Array
    (
    [0] => Array
    (
    [sentence] => The tiger is the national animal of India
    [character] => i
    [occurrences] => 6
    )

    [1] => Array
    (
    [sentence] => The tiger is a large carnivorous mammal that roams the forests
    [character] => a
    [occurrences] => 7
    )

    [2] => Array
    (
    [sentence] => The tiger feeds on animals that also live in the forest
    [character] => e
    [occurrences] => 7
    )

    [3] => Array
    (
    [sentence] => The tiger does have a coat of orange with black stripes
    [character] => e
    [occurrences] => 6
    )

    [4] => Array
    (
    [sentence] => Tigers, regardless of their subspecies, are carnivorous animals
    [character] => s
    [occurrences] => 8
    )

    [5] => Array
    (
    [sentence] => The tiger is a protected species
    [character] => e
    [occurrences] => 6
    )

    )

我试过

foreach($sentences as $sentence) {
    $value = array_count_values($sentence);
}

请帮我为上述目的制作一个功能

Answer 1

您可以使用array_map()对每个项目应用功能。在此函数中，您可以将字符串转换为小写，将数组拆分为数组（并array_filter()以删除空格），以便使用array_count_values()。然后，您可以使用arsort()对数组进行排序，以保持键关联并在顶部获取最常用的字符。最后，您可以使用array_keys()和reset()来获取第一个键和数组的第一个值：

$sentences = [
  0 => 'The tiger is the national animal of India',
  1 => 'The tiger is a large carnivorous mammal that roams the forests',
  2 => 'The tiger feeds on animals that also live in the forest',
  3 => 'The tiger does have a coat of orange with black stripes',
  4 => 'Tigers, regardless of their subspecies, are carnivorous animals',
  5 => 'The tiger is a protected species',
];

$out = array_map(function($value) {
    $chars = array_filter(str_split(strtolower($value)),'trim');
    $vals = array_count_values($chars);
    arsort($vals);
    $keys = array_keys($vals);
    return [
        'sentence' => $value,
        'character' => reset($keys),
        'occurrences' => reset($vals),
    ];
}, $sentences);
print_r($out) ;

输出：

Array (
    [0] => Array (
            [sentence] => The tiger is the national animal of India
            [character] => i
            [occurrences] => 6
        )
    [1] => Array (
            [sentence] => The tiger is a large carnivorous mammal that roams the forests
            [character] => a
            [occurrences] => 7
        )
    [2] => Array (
            [sentence] => The tiger feeds on animals that also live in the forest
            [character] => e
            [occurrences] => 7
        )

    [3] => Array (
            [sentence] => The tiger does have a coat of orange with black stripes
            [character] => e
            [occurrences] => 6
        )

    [4] => Array (
            [sentence] => Tigers, regardless of their subspecies, are carnivorous animals
            [character] => s
            [occurrences] => 8
        )

    [5] => Array (
            [sentence] => The tiger is a protected species
            [character] => e
            [occurrences] => 6
        )
)

删除特殊字符：

$chars = array_filter(str_split(strtolower($value)),function($val){
    return trim(preg_replace('~\W+~', '', $val));
});

Answer 2

我使用preg_match_all()模式一次匹配一个字母或数字以提取字符数组，然后找到array_count_values()出现的次数，按出现次数对数组进行排序降序，然后提取第一个键和第一个值（表示最高出现的字母的字符和计数）。

代码:(演示：https://3v4l.org/7OZ5d）

$sentences = [
    0 => 'The tiger is the national animal of India',
    1 => 'The tiger is a large carnivorous mammal that roams the forests',
    2 => 'The tiger feeds on animals that also live in the forest',
    3 => 'The tiger does have a coat of orange with black stripes',
    4 => 'Tigers, regardless of their subspecies, are carnivorous animals',
    5 => 'The tiger is a protected species',
 ];

foreach  ($sentences as $sentence) {
    $alphanums = preg_match_all ('~[a-z\d]~', strtolower($sentence), $out) ? $out[0] : [];
    // or:  $alphanums = preg_split('~[^a-z\d]*~', strtolower($sentence), null, PREG_SPLIT_NO_EMPTY);
    $occurrences = array_count_values($alphanums);
    arsort($occurrences);
    $result[] = [
        "sentence" => $sentence,
        "character" => key($occurrences), 
        "occurrences" => current($occurrences)
    ];
}
var_export($result);

Answer 3

使用count_chars

$sentences = [
0 => 'The tiger is the national animal of India',
1 => 'The tiger is a large carnivorous mammal that roams the forests',
2 => 'The tiger feeds on animals that also live in the forest',
3 => 'The tiger does have a coat of orange with **a** black stripe',
4 => 'Tigers, regardless of their subspecies, are carnivorous animals',
5 => 'The tiger is a protected species',
];

我通过使用count_chars（）到$ count来记录事件，并使用max（）获取最大值。如果出现次数小于max（，因为可能有多个字符具有相同的出现次数），则从数组中删除ASCII代码。

通过起诉chr（）

将剩余的ASII代码转换回字符

<?php
    foreach ($sentences as $sentence){
    $string = strtolower(preg_replace('/\s+/', '', $sentence));
    $counts = count_chars($string, 1);
    $max = max($counts);
    foreach ($counts as $key => $count) {
        if ($count < $max) {
            unset($counts[$key]);
        }
    }
    $characters = array_map(function($item){
           return chr($item);
        }, array_keys($counts));
    $result[] = [
        'sentence' => $sentence,
        'character' => implode(',', $characters),
        'occurrences' => $max
    ];
}

echo '<pre>', print_r($result) ,'<pre>';

输出：

    Array
(
    [0] => Array
        (
        [sentence] => The tiger is the national animal of India
        [character] => i
        [occurrences] => 6
    )

    [1] => Array
        (
            [sentence] => The tiger is a large carnivorous mammal that roams the forests
            [character] => a
            [occurrences] => 7
        )

    [2] => Array
        (
            [sentence] => The tiger feeds on animals that also live in the forest
            [character] => e
            [occurrences] => 7
        )

    [3] => Array
        (
            [sentence] => The tiger does have a coat of orange with a black stripe
            [character] => a,e **<== multiple characters**
            [occurrences] => 6
        )

    [4] => Array
        (
            [sentence] => Tigers, regardless of their subspecies, are carnivorous animals
            [character] => s
            [occurrences] => 8
        )

    [5] => Array
        (
            [sentence] => The tiger is a protected species
            [character] => e
            [occurrences] => 6
        )

)

仅计算字母数字：

$string = strtolower(preg_replace('/[^A-Za-z]/', '', $sentence));

DEMO：http://sandbox.onlinephpfunctions.com/code/e2fb793031cd172507d8a464b1096b1b2bb73046

数组php中最常出现的字符？

3 个答案: