diff options
Diffstat (limited to 'node_modules/locutus/php/strings/strlen.js')
| -rw-r--r-- | node_modules/locutus/php/strings/strlen.js | 76 |
1 files changed, 76 insertions, 0 deletions
diff --git a/node_modules/locutus/php/strings/strlen.js b/node_modules/locutus/php/strings/strlen.js new file mode 100644 index 0000000..7c664d2 --- /dev/null +++ b/node_modules/locutus/php/strings/strlen.js @@ -0,0 +1,76 @@ +'use strict'; + +module.exports = function strlen(string) { + // discuss at: http://locutus.io/php/strlen/ + // original by: Kevin van Zonneveld (http://kvz.io) + // improved by: Sakimori + // improved by: Kevin van Zonneveld (http://kvz.io) + // input by: Kirk Strobeck + // bugfixed by: Onno Marsman (https://twitter.com/onnomarsman) + // revised by: Brett Zamir (http://brett-zamir.me) + // note 1: May look like overkill, but in order to be truly faithful to handling all Unicode + // note 1: characters and to this function in PHP which does not count the number of bytes + // note 1: but counts the number of characters, something like this is really necessary. + // example 1: strlen('Kevin van Zonneveld') + // returns 1: 19 + // example 2: ini_set('unicode.semantics', 'on') + // example 2: strlen('A\ud87e\udc04Z') + // returns 2: 3 + + var str = string + ''; + + var iniVal = (typeof require !== 'undefined' ? require('../info/ini_get')('unicode.semantics') : undefined) || 'off'; + if (iniVal === 'off') { + return str.length; + } + + var i = 0; + var lgth = 0; + + var getWholeChar = function getWholeChar(str, i) { + var code = str.charCodeAt(i); + var next = ''; + var prev = ''; + if (code >= 0xD800 && code <= 0xDBFF) { + // High surrogate (could change last hex to 0xDB7F to + // treat high private surrogates as single characters) + if (str.length <= i + 1) { + throw new Error('High surrogate without following low surrogate'); + } + next = str.charCodeAt(i + 1); + if (next < 0xDC00 || next > 0xDFFF) { + throw new Error('High surrogate without following low surrogate'); + } + return str.charAt(i) + str.charAt(i + 1); + } else if (code >= 0xDC00 && code <= 0xDFFF) { + // Low surrogate + if (i === 0) { + throw new Error('Low surrogate without preceding high surrogate'); + } + prev = str.charCodeAt(i - 1); + if (prev < 0xD800 || prev > 0xDBFF) { + // (could change last hex to 0xDB7F to treat high private surrogates + // as single characters) + throw new Error('Low surrogate without preceding high surrogate'); + } + // We can pass over low surrogates now as the second + // component in a pair which we have already processed + return false; + } + return str.charAt(i); + }; + + for (i = 0, lgth = 0; i < str.length; i++) { + if (getWholeChar(str, i) === false) { + continue; + } + // Adapt this line at the top of any loop, passing in the whole string and + // the current iteration and returning a variable to represent the individual character; + // purpose is to treat the first part of a surrogate pair as the whole character and then + // ignore the second part + lgth++; + } + + return lgth; +}; +//# sourceMappingURL=strlen.js.map
\ No newline at end of file |