UnicodeUtilsExtra.js 5.86 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
/**
 * Copyright (c) 2013-present, Facebook, Inc.
 *
 * This source code is licensed under the MIT license found in the
 * LICENSE file in the root directory of this source tree.
 *
 * @typechecks
 */

/**
 * Unicode-enabled extra utility functions not always needed.
 */
'use strict';

var UnicodeUtils = require("./UnicodeUtils");
/**
 * @param {number} codePoint  Valid Unicode code-point
 * @param {number} len        Zero-padded minimum width of result
 * @return {string}           A zero-padded hexadecimal string (00XXXX)
 */


function zeroPaddedHex(codePoint, len) {
  var codePointHex = codePoint.toString(16).toUpperCase();
  var numZeros = Math.max(0, len - codePointHex.length);
  var result = '';

  for (var i = 0; i < numZeros; i++) {
    result += '0';
  }

  result += codePointHex;
  return result;
}
/**
 * @param {number} codePoint  Valid Unicode code-point
 * @return {string}           A formatted Unicode code-point string
 *                            of the format U+XXXX, U+XXXXX, or U+XXXXXX
 */


function formatCodePoint(codePoint) {
  codePoint = codePoint || 0; // NaN --> 0

  var formatted = '';

  if (codePoint <= 0xFFFF) {
    formatted = zeroPaddedHex(codePoint, 4);
  } else {
    formatted = codePoint.toString(16).toUpperCase();
  }

  return 'U+' + formatted;
}
/**
 * Get a list of formatted (string) Unicode code-points from a String
 *
 * @param {string} str        Valid Unicode string
 * @return {array<string>}    A list of formatted code-point strings
 */


function getCodePointsFormatted(str) {
  var codePoints = UnicodeUtils.getCodePoints(str);
  return codePoints.map(formatCodePoint);
}

var specialEscape = {
  0x07: '\\a',
  0x08: '\\b',
  0x0C: '\\f',
  0x0A: '\\n',
  0x0D: '\\r',
  0x09: '\\t',
  0x0B: '\\v',
  0x22: '\\"',
  0x5c: '\\\\'
};
/**
 * Returns a double-quoted PHP string with all non-printable and
 * non-US-ASCII sequences escaped.
 *
 * @param {string} str Valid Unicode string
 * @return {string}    Double-quoted string with Unicode sequences escaped
 */

function phpEscape(s) {
  var result = '"';
  var _iteratorNormalCompletion = true;
  var _didIteratorError = false;
  var _iteratorError = undefined;

  try {
    for (var _iterator = UnicodeUtils.getCodePoints(s)[Symbol.iterator](), _step; !(_iteratorNormalCompletion = (_step = _iterator.next()).done); _iteratorNormalCompletion = true) {
      var cp = _step.value;
      var special = specialEscape[cp];

      if (special !== undefined) {
        result += special;
      } else if (cp >= 0x20 && cp <= 0x7e) {
        result += String.fromCodePoint(cp);
      } else if (cp <= 0xFFFF) {
        result += "\\u{" + zeroPaddedHex(cp, 4) + '}';
      } else {
        result += "\\u{" + zeroPaddedHex(cp, 6) + '}';
      }
    }
  } catch (err) {
    _didIteratorError = true;
    _iteratorError = err;
  } finally {
    try {
      if (!_iteratorNormalCompletion && _iterator["return"] != null) {
        _iterator["return"]();
      }
    } finally {
      if (_didIteratorError) {
        throw _iteratorError;
      }
    }
  }

  result += '"';
  return result;
}
/**
 * Returns a double-quoted Java or JavaScript string with all
 * non-printable and non-US-ASCII sequences escaped.
 *
 * @param {string} str Valid Unicode string
 * @return {string}    Double-quoted string with Unicode sequences escaped
 */


function jsEscape(s) {
  var result = '"';

  for (var i = 0; i < s.length; i++) {
    var cp = s.charCodeAt(i);
    var special = specialEscape[cp];

    if (special !== undefined) {
      result += special;
    } else if (cp >= 0x20 && cp <= 0x7e) {
      result += String.fromCodePoint(cp);
    } else {
      result += "\\u" + zeroPaddedHex(cp, 4);
    }
  }

  result += '"';
  return result;
}

function c11Escape(s) {
  var result = '';
  var _iteratorNormalCompletion2 = true;
  var _didIteratorError2 = false;
  var _iteratorError2 = undefined;

  try {
    for (var _iterator2 = UnicodeUtils.getCodePoints(s)[Symbol.iterator](), _step2; !(_iteratorNormalCompletion2 = (_step2 = _iterator2.next()).done); _iteratorNormalCompletion2 = true) {
      var cp = _step2.value;
      var special = specialEscape[cp];

      if (special !== undefined) {
        result += special;
      } else if (cp >= 0x20 && cp <= 0x7e) {
        result += String.fromCodePoint(cp);
      } else if (cp <= 0xFFFF) {
        result += "\\u" + zeroPaddedHex(cp, 4);
      } else {
        result += "\\U" + zeroPaddedHex(cp, 8);
      }
    }
  } catch (err) {
    _didIteratorError2 = true;
    _iteratorError2 = err;
  } finally {
    try {
      if (!_iteratorNormalCompletion2 && _iterator2["return"] != null) {
        _iterator2["return"]();
      }
    } finally {
      if (_didIteratorError2) {
        throw _iteratorError2;
      }
    }
  }

  return result;
}
/**
 * Returns a double-quoted C string with all non-printable and
 * non-US-ASCII sequences escaped.
 *
 * @param {string} str Valid Unicode string
 * @return {string}    Double-quoted string with Unicode sequences escaped
 */


function cEscape(s) {
  return 'u8"' + c11Escape(s) + '"';
}
/**
 * Returns a double-quoted Objective-C string with all non-printable
 * and non-US-ASCII sequences escaped.
 *
 * @param {string} str Valid Unicode string
 * @return {string}    Double-quoted string with Unicode sequences escaped
 */


function objcEscape(s) {
  return '@"' + c11Escape(s) + '"';
}
/**
 * Returns a double-quoted Python string with all non-printable
 * and non-US-ASCII sequences escaped.
 *
 * @param {string} str Valid Unicode string
 * @return {string}    Double-quoted string with Unicode sequences escaped
 */


function pyEscape(s) {
  return 'u"' + c11Escape(s) + '"';
}

var UnicodeUtilsExtra = {
  formatCodePoint: formatCodePoint,
  getCodePointsFormatted: getCodePointsFormatted,
  zeroPaddedHex: zeroPaddedHex,
  phpEscape: phpEscape,
  jsEscape: jsEscape,
  cEscape: cEscape,
  objcEscape: objcEscape,
  pyEscape: pyEscape
};
module.exports = UnicodeUtilsExtra;