[ Index ] |
PHP Cross Reference of WordPress Trunk (Updated Daily) |
[Summary view] [Print] [Text view]
1 /** 2 * Word or character counting functionality. Count words or characters in a 3 * provided text string. 4 * 5 * @namespace wp.utils 6 * 7 * @since 2.6.0 8 * @output wp-admin/js/word-count.js 9 */ 10 11 ( function() { 12 /** 13 * Word counting utility 14 * 15 * @namespace wp.utils.wordcounter 16 * @memberof wp.utils 17 * 18 * @class 19 * 20 * @param {Object} settings Optional. Key-value object containing overrides for 21 * settings. 22 * @param {RegExp} settings.HTMLRegExp Optional. Regular expression to find HTML elements. 23 * @param {RegExp} settings.HTMLcommentRegExp Optional. Regular expression to find HTML comments. 24 * @param {RegExp} settings.spaceRegExp Optional. Regular expression to find irregular space 25 * characters. 26 * @param {RegExp} settings.HTMLEntityRegExp Optional. Regular expression to find HTML entities. 27 * @param {RegExp} settings.connectorRegExp Optional. Regular expression to find connectors that 28 * split words. 29 * @param {RegExp} settings.removeRegExp Optional. Regular expression to find remove unwanted 30 * characters to reduce false-positives. 31 * @param {RegExp} settings.astralRegExp Optional. Regular expression to find unwanted 32 * characters when searching for non-words. 33 * @param {RegExp} settings.wordsRegExp Optional. Regular expression to find words by spaces. 34 * @param {RegExp} settings.characters_excluding_spacesRegExp Optional. Regular expression to find characters which 35 * are non-spaces. 36 * @param {RegExp} settings.characters_including_spacesRegExp Optional. Regular expression to find characters 37 * including spaces. 38 * @param {RegExp} settings.shortcodesRegExp Optional. Regular expression to find shortcodes. 39 * @param {Object} settings.l10n Optional. Localization object containing specific 40 * configuration for the current localization. 41 * @param {string} settings.l10n.type Optional. Method of finding words to count. 42 * @param {Array} settings.l10n.shortcodes Optional. Array of shortcodes that should be removed 43 * from the text. 44 * 45 * @return {void} 46 */ 47 function WordCounter( settings ) { 48 var key, 49 shortcodes; 50 51 // Apply provided settings to object settings. 52 if ( settings ) { 53 for ( key in settings ) { 54 55 // Only apply valid settings. 56 if ( settings.hasOwnProperty( key ) ) { 57 this.settings[ key ] = settings[ key ]; 58 } 59 } 60 } 61 62 shortcodes = this.settings.l10n.shortcodes; 63 64 // If there are any localization shortcodes, add this as type in the settings. 65 if ( shortcodes && shortcodes.length ) { 66 this.settings.shortcodesRegExp = new RegExp( '\\[\\/?(?:' + shortcodes.join( '|' ) + ')[^\\]]*?\\]', 'g' ); 67 } 68 } 69 70 // Default settings. 71 WordCounter.prototype.settings = { 72 HTMLRegExp: /<\/?[a-z][^>]*?>/gi, 73 HTMLcommentRegExp: /<!--[\s\S]*?-->/g, 74 spaceRegExp: / | /gi, 75 HTMLEntityRegExp: /&\S+?;/g, 76 77 // \u2014 = em-dash. 78 connectorRegExp: /--|\u2014/g, 79 80 // Characters to be removed from input text. 81 removeRegExp: new RegExp( [ 82 '[', 83 84 // Basic Latin (extract). 85 '\u0021-\u0040\u005B-\u0060\u007B-\u007E', 86 87 // Latin-1 Supplement (extract). 88 '\u0080-\u00BF\u00D7\u00F7', 89 90 /* 91 * The following range consists of: 92 * General Punctuation 93 * Superscripts and Subscripts 94 * Currency Symbols 95 * Combining Diacritical Marks for Symbols 96 * Letterlike Symbols 97 * Number Forms 98 * Arrows 99 * Mathematical Operators 100 * Miscellaneous Technical 101 * Control Pictures 102 * Optical Character Recognition 103 * Enclosed Alphanumerics 104 * Box Drawing 105 * Block Elements 106 * Geometric Shapes 107 * Miscellaneous Symbols 108 * Dingbats 109 * Miscellaneous Mathematical Symbols-A 110 * Supplemental Arrows-A 111 * Braille Patterns 112 * Supplemental Arrows-B 113 * Miscellaneous Mathematical Symbols-B 114 * Supplemental Mathematical Operators 115 * Miscellaneous Symbols and Arrows 116 */ 117 '\u2000-\u2BFF', 118 119 // Supplemental Punctuation. 120 '\u2E00-\u2E7F', 121 ']' 122 ].join( '' ), 'g' ), 123 124 // Remove UTF-16 surrogate points, see https://en.wikipedia.org/wiki/UTF-16#U.2BD800_to_U.2BDFFF 125 astralRegExp: /[\uD800-\uDBFF][\uDC00-\uDFFF]/g, 126 wordsRegExp: /\S\s+/g, 127 characters_excluding_spacesRegExp: /\S/g, 128 129 /* 130 * Match anything that is not a formatting character, excluding: 131 * \f = form feed 132 * \n = new line 133 * \r = carriage return 134 * \t = tab 135 * \v = vertical tab 136 * \u00AD = soft hyphen 137 * \u2028 = line separator 138 * \u2029 = paragraph separator 139 */ 140 characters_including_spacesRegExp: /[^\f\n\r\t\v\u00AD\u2028\u2029]/g, 141 l10n: window.wordCountL10n || {} 142 }; 143 144 /** 145 * Counts the number of words (or other specified type) in the specified text. 146 * 147 * @since 2.6.0 148 * 149 * @memberof wp.utils.wordcounter 150 * 151 * @param {string} text Text to count elements in. 152 * @param {string} type Optional. Specify type to use. 153 * 154 * @return {number} The number of items counted. 155 */ 156 WordCounter.prototype.count = function( text, type ) { 157 var count = 0; 158 159 // Use default type if none was provided. 160 type = type || this.settings.l10n.type; 161 162 // Sanitize type to one of three possibilities: 'words', 'characters_excluding_spaces' or 'characters_including_spaces'. 163 if ( type !== 'characters_excluding_spaces' && type !== 'characters_including_spaces' ) { 164 type = 'words'; 165 } 166 167 // If we have any text at all. 168 if ( text ) { 169 text = text + '\n'; 170 171 // Replace all HTML with a new-line. 172 text = text.replace( this.settings.HTMLRegExp, '\n' ); 173 174 // Remove all HTML comments. 175 text = text.replace( this.settings.HTMLcommentRegExp, '' ); 176 177 // If a shortcode regular expression has been provided use it to remove shortcodes. 178 if ( this.settings.shortcodesRegExp ) { 179 text = text.replace( this.settings.shortcodesRegExp, '\n' ); 180 } 181 182 // Normalize non-breaking space to a normal space. 183 text = text.replace( this.settings.spaceRegExp, ' ' ); 184 185 if ( type === 'words' ) { 186 187 // Remove HTML Entities. 188 text = text.replace( this.settings.HTMLEntityRegExp, '' ); 189 190 // Convert connectors to spaces to count attached text as words. 191 text = text.replace( this.settings.connectorRegExp, ' ' ); 192 193 // Remove unwanted characters. 194 text = text.replace( this.settings.removeRegExp, '' ); 195 } else { 196 197 // Convert HTML Entities to "a". 198 text = text.replace( this.settings.HTMLEntityRegExp, 'a' ); 199 200 // Remove surrogate points. 201 text = text.replace( this.settings.astralRegExp, 'a' ); 202 } 203 204 // Match with the selected type regular expression to count the items. 205 text = text.match( this.settings[ type + 'RegExp' ] ); 206 207 // If we have any matches, set the count to the number of items found. 208 if ( text ) { 209 count = text.length; 210 } 211 } 212 213 return count; 214 }; 215 216 // Add the WordCounter to the WP Utils. 217 window.wp = window.wp || {}; 218 window.wp.utils = window.wp.utils || {}; 219 window.wp.utils.WordCounter = WordCounter; 220 } )();
title
Description
Body
title
Description
Body
title
Description
Body
title
Body
Generated : Thu Nov 21 08:20:01 2024 | Cross-referenced by PHPXref |