gutenberg / lib / experimental / l10n.php

l10n.php in Gutenberg 21.7.0, at lib/experimental/l10n.php

140 lines 5.9 KB

Raw Download Zip

1	<?php
2	/**
3	* PHP and WordPress configuration compatibility functions for the Gutenberg
4	* editor plugin changes related to i18n.
5	*
6	* @package gutenberg
7	*/
8
9	/**
10	* Override core's wp_get_word_count_type() introduced in WordPress 6.2.
11	* Originally, get_word_count_type() method of the WP_Locale class is executed,
12	* but the process is simulated here.
13	*
14	* This function should not be backported to core.
15	*/
16	if ( ! function_exists( 'wp_get_word_count_type' ) ) {
17	/**
18	* Retrieves the word count type based on the locale.
19	*
20	* @return string Locale-specific word count type.
21	*/
22	function wp_get_word_count_type() {
23	$word_count_type = _x( 'words', 'Word count type. Do not translate!', 'gutenberg' );
24
25	// Check for valid types.
26	if ( 'characters_excluding_spaces' !== $word_count_type && 'characters_including_spaces' !== $word_count_type ) {
27	// Defaults to 'words'.
28	$word_count_type = 'words';
29	}
30	return $word_count_type;
31	}
32	}
33
34	if ( ! function_exists( 'wp_word_count' ) ) {
35	/**
36	* Count words or characters in a provided text string.
37	*
38	* @param string $text Text to count elements in.
39	* @param string $type The type of count. Accepts 'words', 'characters_excluding_spaces', or 'characters_including_spaces'.
40	* @param array $settings {
41	* Optional. Array of arguments used to overrides for settings.
42	*
43	* @type string $html_regexp Optional. Regular expression to find HTML elements.
44	* @type string $html_comment_regexp Optional. Regular expression to find HTML comments.
45	* @type string $space_regexp Optional. Regular expression to find irregular space
46	* characters.
47	* @type string $html_entity_regexp Optional. Regular expression to find HTML entities.
48	* @type string $connector_regexp Optional. Regular expression to find connectors that
49	* split words.
50	* @type string $remove_regexp Optional. Regular expression to find remove unwanted
51	* characters to reduce false-positives.
52	* @type string $astral_regexp Optional. Regular expression to find unwanted
53	* characters when searching for non-words.
54	* @type string $words_regexp Optional. Regular expression to find words by spaces.
55	* @type string $characters_excluding_spaces_regexp Optional. Regular expression to find characters which
56	* are non-spaces.
57	* @type string $characters_including_spaces_regexp Optional. Regular expression to find characters
58	* including spaces.
59	* @type array $shortcodes Optional. Array of shortcodes that should be removed
60	* from the text.
61	* }
62	* @return int The word or character count.
63	*/
64	function wp_word_count( $text, $type, $settings = array() ) {
65	$defaults = array(
66	'html_regexp' => '/<\/?[a-z][^>]*?>/i',
67	'html_comment_regexp' => '/<!--[\s\S]*?-->/',
68	'space_regexp' => '/ \| /i',
69	'html_entity_regexp' => '/&\S+?;/',
70	'connector_regexp' => "/--\|\x{2014}/u",
71	'remove_regexp' => "/[\x{0021}-\x{0040}\x{005B}-\x{0060}\x{007B}-\x{007E}\x{0080}-\x{00BF}\x{00D7}\x{00F7}\x{2000}-\x{2BFF}\x{2E00}-\x{2E7F}]/u",
72	'astral_regexp' => "/[\x{010000}-\x{10FFFF}]/u",
73	'words_regexp' => '/\S\s+/u',
74	'characters_excluding_spaces_regexp' => '/\S/u',
75	'characters_including_spaces_regexp' => "/[^\f\n\r\t\v\x{00AD}\x{2028}\x{2029}]/u",
76	'shortcodes' => array(),
77	);
78
79	$count = 0;
80
81	if ( ! $text ) {
82	return $count;
83	}
84
85	$settings = wp_parse_args( $settings, $defaults );
86
87	// If there are any shortcodes, add this as a shortcode regular expression.
88	if ( is_array( $settings['shortcodes'] ) && ! empty( $settings['shortcodes'] ) ) {
89	$settings['shortcodes_regexp'] = '/\\[\\/?(?:' . implode( '\|', $settings['shortcodes'] ) . ')[^\\]]*?\\]/';
90	}
91
92	// Sanitize type to one of three possibilities: 'words', 'characters_excluding_spaces' or 'characters_including_spaces'.
93	if ( 'characters_excluding_spaces' !== $type && 'characters_including_spaces' !== $type ) {
94	$type = 'words';
95	}
96
97	$text .= "\n";
98
99	// Replace all HTML with a new-line.
100	$text = preg_replace( $settings['html_regexp'], "\n", $text );
101
102	// Remove all HTML comments.
103	$text = preg_replace( $settings['html_comment_regexp'], '', $text );
104
105	// If a shortcode regular expression has been provided use it to remove shortcodes.
106	if ( ! empty( $settings['shortcodes_regexp'] ) ) {
107	$text = preg_replace( $settings['shortcodes_regexp'], "\n", $text );
108	}
109
110	// Normalize non-breaking space to a normal space.
111	$text = preg_replace( $settings['space_regexp'], ' ', $text );
112
113	if ( 'words' === $type ) {
114	// Remove HTML Entities.
115	$text = preg_replace( $settings['html_entity_regexp'], '', $text );
116
117	// Convert connectors to spaces to count attached text as words.
118	$text = preg_replace( $settings['connector_regexp'], ' ', $text );
119
120	// Remove unwanted characters.
121	$text = preg_replace( $settings['remove_regexp'], '', $text );
122	} else {
123	// Convert HTML Entities to "a".
124	$text = preg_replace( $settings['html_entity_regexp'], 'a', $text );
125
126	// Remove surrogate points.
127	$text = preg_replace( $settings['astral_regexp'], 'a', $text );
128	}
129
130	// Match with the selected type regular expression to count the items.
131	preg_match_all( $settings[ $type . '_regexp' ], $text, $matches );
132
133	if ( $matches ) {
134	return count( $matches[0] );
135	}
136
137	return $count;
138	}
139	}
140