Home Reference Source

src/string.js

import {
  typeOf,
  isUnset,
  isString,
  assert,
} from './base'
import { _padStart } from './internal/_pad'

/**
 * @see https://www.cnblogs.com/dearxinli/p/7657512.html
 * 计算字符串所占的内存字节数,默认使用UTF-8的编码方式计算,也可制定为UTF-16
 * UTF-8 是一种可变长度的 Unicode 编码格式,使用一至四个字节为每个字符编码
 * 
 * 000000 - 00007F(128个代码)      0zzzzzzz(00-7F)                             一个字节
 * 000080 - 0007FF(1920个代码)     110yyyyy(C0-DF) 10zzzzzz(80-BF)             两个字节
 * 000800 - 00D7FF 
   00E000 - 00FFFF(61440个代码)    1110xxxx(E0-EF) 10yyyyyy 10zzzzzz           三个字节
  * 010000 - 10FFFF(1048576个代码)  11110www(F0-F7) 10xxxxxx 10yyyyyy 10zzzzzz  四个字节
  * 
  * 注: Unicode在范围 D800-DFFF 中不存在任何字符
  * @see http://zh.wikipedia.org/wiki/UTF-8
  * 
  * UTF-16 大部分使用两个字节编码,编码超出 65535 的使用四个字节
  * 000000 - 00FFFF  两个字节
  * 010000 - 10FFFF  四个字节
  * 
  * @see http://zh.wikipedia.org/wiki/UTF-16
  * @param  {String} str 
  * @param  {String} charset utf-8, utf-16
  * @return {Number}
  */
export function charLength(str, charset) {
  let total = 0
  let charCode, i, len

  charset = charset ? charset.toLowerCase() : ''
  if (charset === 'utf-16' || charset === 'utf16') {
    for (i = 0, len = str.length; i < len; i++) {
      charCode = str.charCodeAt(i)
      if (charCode <= 0xffff) {
        total += 2
      } else {
        total += 4
      }
    }
  } else {
    for (i = 0, len = str.length; i < len; i++) {
      charCode = str.charCodeAt(i)
      if (charCode <= 0x007f) {
        total += 1
      } else if (charCode <= 0x07ff) {
        total += 2
      } else if (charCode <= 0xffff) {
        total += 3
      } else {
        total += 4
      }
    }
  }
  return total
}

/**
 * 
 * @param {String} str - a string that to be trim spaces at begin or end of the string.
 * @returns {String} a string without spaces at begin or end of itself.
 */
export function trim(str) {
  if (isUnset(str)) { // if str is undefined or null, return empty string
    return ''
  }
  return (str + '').replace(/^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g, '')
}


export function dashToCamel(dashStr) {
  assert(isString(dashStr), `dashToCamel(dashStr): expect dashStr to be type of String, but got ${typeOf(dashStr)}`)

  if (dashStr.indexOf('-') === -1) {
    return dashStr
  }
  let camelStr = dashStr
  camelStr = trim(camelStr)
  // remove the dash at begin or end
  camelStr = camelStr.replace(/^-|-$/g, '')

  camelStr = camelStr.replace(/-(\w)/g, (m, w) => w.toUpperCase())

  return camelStr
}

/**
 * 
 * @param {Number|String} num - the number going to be padded
 * @param {NUmber} [size] - the length of the return string after padding
 * @returns {String} - the padded string
 */
export function padZero(num, size = 2) {
  return _padStart(num, size, 0)
}