time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

main.js (3547B)

      1 /**
      2 * @license Apache-2.0
      3 *
      4 * Copyright (c) 2020 The Stdlib Authors.
      5 *
      6 * Licensed under the Apache License, Version 2.0 (the "License");
      7 * you may not use this file except in compliance with the License.
      8 * You may obtain a copy of the License at
      9 *
     10 *    http://www.apache.org/licenses/LICENSE-2.0
     11 *
     12 * Unless required by applicable law or agreed to in writing, software
     13 * distributed under the License is distributed on an "AS IS" BASIS,
     14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     15 * See the License for the specific language governing permissions and
     16 * limitations under the License.
     17 */
     18 
     19 'use strict';
     20 
     21 // MODULES //
     22 
     23 var isString = require( '@stdlib/assert/is-string' ).isPrimitive;
     24 var isInteger = require( '@stdlib/assert/is-integer' ).isPrimitive;
     25 var codePointAt = require( './../../code-point-at' );
     26 var hasUTF16SurrogatePairAt = require( '@stdlib/assert/has-utf16-surrogate-pair-at' );
     27 var grapheme = require( './../../tools/grapheme-cluster-break' );
     28 var format = require( './../../format' );
     29 
     30 
     31 // VARIABLES //
     32 
     33 var breakType = grapheme.breakType;
     34 var breakProperty = grapheme.breakProperty;
     35 var emojiProperty = grapheme.emojiProperty;
     36 
     37 
     38 // MAIN //
     39 
     40 /**
     41 * Returns the next extended grapheme cluster break in a string after a specified position.
     42 *
     43 * @param {string} str - input string
     44 * @param {integer} [fromIndex=0] - position
     45 * @throws {TypeError} first argument must be a string
     46 * @throws {TypeError} second argument must be an integer
     47 * @returns {NonNegativeInteger} next grapheme break position
     48 *
     49 * @example
     50 * var out = nextGraphemeClusterBreak( 'last man standing', 4 );
     51 * // returns 5
     52 *
     53 * @example
     54 * var out = nextGraphemeClusterBreak( 'presidential election', 8 );
     55 * // returns 9
     56 *
     57 * @example
     58 * var out = nextGraphemeClusterBreak( 'अनुच्छेद', 1 );
     59 * // returns 3
     60 *
     61 * @example
     62 * var out = nextGraphemeClusterBreak( '🌷' );
     63 * // returns -1
     64 */
     65 function nextGraphemeClusterBreak( str, fromIndex ) {
     66 	var breaks;
     67 	var emoji;
     68 	var len;
     69 	var idx;
     70 	var cp;
     71 	var i;
     72 
     73 	if ( !isString( str ) ) {
     74 		throw new TypeError( format( 'invalid argument. First argument must be a string. Value: `%s`.', str ) );
     75 	}
     76 	if ( arguments.length > 1 ) {
     77 		if ( !isInteger( fromIndex ) ) {
     78 			throw new TypeError( format( 'invalid argument. Second argument must be an integer. Value: `%s`.', fromIndex ) );
     79 		}
     80 		idx = fromIndex;
     81 	} else {
     82 		idx = 0;
     83 	}
     84 	len = str.length;
     85 	if ( idx < 0 ) {
     86 		idx += len;
     87 		if ( idx < 0 ) {
     88 			idx = 0;
     89 		}
     90 	}
     91 	if ( len === 0 || idx >= len ) {
     92 		return -1;
     93 	}
     94 	// Initialize caches for storing grapheme break and emoji properties:
     95 	breaks = [];
     96 	emoji = [];
     97 
     98 	// Get the code point for the starting index:
     99 	cp = codePointAt( str, idx );
    100 
    101 	// Get the corresponding grapheme break and emoji properties:
    102 	breaks.push( breakProperty( cp ) );
    103 	emoji.push( emojiProperty( cp ) );
    104 
    105 	// Begin searching for the next grapheme cluster break...
    106 	for ( i = idx+1; i < len; i++ ) {
    107 		// If the current character is part of a surrogate pair, move along...
    108 		if ( hasUTF16SurrogatePairAt( str, i-1 ) ) {
    109 			continue;
    110 		}
    111 		// Get the next code point:
    112 		cp = codePointAt( str, i );
    113 
    114 		// Get the corresponding grapheme break and emoji properties:
    115 		breaks.push( breakProperty( cp ) );
    116 		emoji.push( emojiProperty( cp ) );
    117 
    118 		// Determine if we've encountered a grapheme cluster break...
    119 		if ( breakType( breaks, emoji ) > 0 ) {
    120 			// We've found a break!
    121 			return i;
    122 		}
    123 	}
    124 	// Unable to find a grapheme cluster break:
    125 	return -1;
    126 }
    127 
    128 
    129 // EXPORTS //
    130 
    131 module.exports = nextGraphemeClusterBreak;