Source: strings.js

  1. 'use strict'
  2. /**
  3. * @module strings
  4. */
  5. export const strings = {};
  6. /**
  7. * Escapes characters with special meaning in {@link RegExp}.
  8. *
  9. * @param {string} str the string to escape.
  10. * @return {string} the escaped string.
  11. * @memberOf module:strings
  12. */
  13. strings.escapeCharactersWithSpecialMeaningInRegExp = function (str) {
  14. return str ? ('' + str).replace(/[.*+?^${}()|[\]\\]/g, '\\$&' /* the whole matched string */) : '';
  15. }
  16. /**
  17. * Converts a string to a {@link RegExp} literal.
  18. *
  19. * @param {string} str the string to convert.
  20. * @param {string} flags the flags of the regular expression.
  21. * @return {RegExp} a {@link RegExp}.
  22. * @memberOf module:strings
  23. */
  24. strings.toRegExp = function (str, flags) {
  25. // As of 2020-01-06, the DOT_ALL flag is not available on Firefox
  26. // If truly needed, use [^]* that reads "match any character that is not nothing"
  27. const newFlags = flags ? flags : 'im';
  28. const escapedString = strings.escapeCharactersWithSpecialMeaningInRegExp(str).split(/[\s\u00a0]+/).join(
  29. '(\\s|\u00a0)*');
  30. return new RegExp(escapedString, newFlags);
  31. }
  32. /**
  33. * Removes diacritical marks from a string.
  34. *
  35. * @param {string} str the string to clean.
  36. * @param {boolean} preserveStringLength true iif the original string length must be preserved.
  37. * @return {string} the cleaned text i.e. without diacritical marks.
  38. * @memberOf module:strings
  39. * @preserve The code is extracted from https://web.archive.org/web/20121231230126/http://lehelk.com:80/2011/05/06/script-to-remove-diacritics/.
  40. */
  41. strings.removeDiacritics = function (str, preserveStringLength) {
  42. str = str ? '' + str : '';
  43. const diacritics = [{
  44. base: 'A',
  45. letters: /[\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F]/g
  46. }, {
  47. base: 'B', letters: /[\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181]/g
  48. }, {
  49. base: 'C', letters: /[\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E]/g
  50. }, {
  51. base: 'D', letters: /[\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779]/g
  52. }, {
  53. base: 'E',
  54. letters: /[\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E]/g
  55. }, {
  56. base: 'F', letters: /[\u0046\u24BB\uFF26\u1E1E\u0191\uA77B]/g
  57. }, {
  58. base: 'G', letters: /[\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E]/g
  59. }, {
  60. base: 'H', letters: /[\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D]/g
  61. }, {
  62. base: 'I',
  63. letters: /[\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197]/g
  64. }, {base: 'J', letters: /[\u004A\u24BF\uFF2A\u0134\u0248]/g}, {
  65. base: 'K', letters: /[\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2]/g
  66. }, {
  67. base: 'L',
  68. letters: /[\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780]/g
  69. }, {
  70. base: 'M', letters: /[\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C]/g
  71. }, {
  72. base: 'N',
  73. letters: /[\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4]/g
  74. }, {
  75. base: 'O',
  76. letters: /[\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C]/g
  77. }, {
  78. base: 'P', letters: /[\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754]/g
  79. }, {
  80. base: 'Q', letters: /[\u0051\u24C6\uFF31\uA756\uA758\u024A]/g
  81. }, {
  82. base: 'R',
  83. letters: /[\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782]/g
  84. }, {
  85. base: 'S',
  86. letters: /[\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784]/g
  87. }, {
  88. base: 'T', letters: /[\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786]/g
  89. }, {
  90. base: 'U',
  91. letters: /[\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244]/g
  92. }, {
  93. base: 'V', letters: /[\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245]/g
  94. }, {
  95. base: 'W', letters: /[\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72]/g
  96. }, {base: 'X', letters: /[\u0058\u24CD\uFF38\u1E8A\u1E8C]/g}, {
  97. base: 'Y', letters: /[\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE]/g
  98. }, {
  99. base: 'Z', letters: /[\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762]/g
  100. }, {
  101. base: 'a',
  102. letters: /[\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250]/g
  103. }, {
  104. base: 'b', letters: /[\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253]/g
  105. }, {
  106. base: 'c', letters: /[\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184]/g
  107. }, {
  108. base: 'd', letters: /[\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A]/g
  109. }, {
  110. base: 'e',
  111. letters: /[\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD]/g
  112. }, {
  113. base: 'f', letters: /[\u0066\u24D5\uFF46\u1E1F\u0192\uA77C]/g
  114. }, {
  115. base: 'g', letters: /[\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F]/g
  116. }, {
  117. base: 'h', letters: /[\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265]/g
  118. }, {
  119. base: 'i',
  120. letters: /[\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131]/g
  121. }, {
  122. base: 'j', letters: /[\u006A\u24D9\uFF4A\u0135\u01F0\u0249]/g
  123. }, {
  124. base: 'k', letters: /[\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3]/g
  125. }, {
  126. base: 'l',
  127. letters: /[\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747]/g
  128. }, {
  129. base: 'm', letters: /[\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F]/g
  130. }, {
  131. base: 'n',
  132. letters: /[\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5]/g
  133. }, {
  134. base: 'o',
  135. letters: /[\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275]/g
  136. }, {
  137. base: 'p', letters: /[\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755]/g
  138. }, {
  139. base: 'q', letters: /[\u0071\u24E0\uFF51\u024B\uA757\uA759]/g
  140. }, {
  141. base: 'r',
  142. letters: /[\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783]/g
  143. }, {
  144. base: 's',
  145. letters: /[\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B]/g
  146. }, {
  147. base: 't',
  148. letters: /[\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787]/g
  149. }, {
  150. base: 'u',
  151. letters: /[\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289]/g
  152. }, {
  153. base: 'v', letters: /[\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C]/g
  154. }, {
  155. base: 'w', letters: /[\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73]/g
  156. }, {base: 'x', letters: /[\u0078\u24E7\uFF58\u1E8B\u1E8D]/g}, {
  157. base: 'y',
  158. letters: /[\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF]/g
  159. }, {
  160. base: 'z', letters: /[\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763]/g
  161. }];
  162. if (preserveStringLength === undefined || preserveStringLength === true) {
  163. diacritics.push({base: 'AA', letters: /\uA732/g}, {base: 'AE', letters: /[\u00C6\u01FC\u01E2]/g},
  164. {base: 'AO', letters: /\uA734/g}, {base: 'AU', letters: /\uA736/g}, {base: 'AV', letters: /[\uA738\uA73A]/g},
  165. {base: 'AY', letters: /\uA73C/g}, {base: 'DZ', letters: /[\u01F1\u01C4]/g},
  166. {base: 'Dz', letters: /[\u01F2\u01C5]/g}, {base: 'LJ', letters: /\u01C7/g}, {base: 'Lj', letters: /\u01C8/g},
  167. {base: 'NJ', letters: /\u01CA/g}, {base: 'Nj', letters: /\u01CB/g}, {base: 'OI', letters: /\u01A2/g},
  168. {base: 'OO', letters: /\uA74E/g}, {base: 'OU', letters: /\u0222/g}, {base: 'TZ', letters: /\uA728/g},
  169. {base: 'VY', letters: /\uA760/g}, {base: 'aa', letters: /\uA733/g},
  170. {base: 'ae', letters: /[\u00E6\u01FD\u01E3]/g}, {base: 'ao', letters: /\uA735/g},
  171. {base: 'au', letters: /\uA737/g}, {base: 'av', letters: /[\uA739\uA73B]/g}, {base: 'ay', letters: /\uA73D/g},
  172. {base: 'dz', letters: /[\u01F3\u01C6]/g}, {base: 'hv', letters: /\u0195/g}, {base: 'lj', letters: /\u01C9/g},
  173. {base: 'nj', letters: /\u01CC/g}, {base: 'oi', letters: /\u01A3/g}, {base: 'ou', letters: /\u0223/g},
  174. {base: 'oo', letters: /\uA74F/g}, {base: 'tz', letters: /\uA729/g}, {base: 'vy', letters: /\uA761/g});
  175. }
  176. for (let i = 0; i < diacritics.length; i++) {
  177. str = str.replace(diacritics[i].letters, diacritics[i].base);
  178. }
  179. return str;
  180. }
  181. /**
  182. * The Pattern type.
  183. *
  184. * @param {RegExp} regexp the pattern to match.
  185. * @param {string} color the highlight color as a hexadecimal string.
  186. * @memberOf module:strings
  187. * @constructor
  188. * @struct
  189. * @final
  190. */
  191. strings.Pattern = function (regexp, color) {
  192. this.regexp = regexp;
  193. this.color = color;
  194. }
  195. /**
  196. * The Highlight type.
  197. *
  198. * @param {string} matchedText the matched text fragment.
  199. * @param {number} matchedPage the page number (1-based) from which the snippet was extracted.
  200. * @param {string} rawSnippet a snippet of text surrounding the matched text fragment (about 300 characters).
  201. * @param {string} highlightedSnippet a snippet of text surrounding the matched and highlighted text fragment (about 300 characters).
  202. * @memberOf module:strings
  203. * @constructor
  204. * @struct
  205. * @final
  206. */
  207. strings.Highlight = function (matchedText, matchedPage, rawSnippet, highlightedSnippet) {
  208. this.matchedText = matchedText;
  209. this.matchedPage = matchedPage;
  210. this.rawSnippet = rawSnippet
  211. this.highlightedSnippet = highlightedSnippet;
  212. }
  213. /**
  214. * The HighlightedText type.
  215. *
  216. * @param {string} text the whole text, highlighted.
  217. * @param {Array<strings.Highlight>} snippets the snippet associated with each highlighted text fragment.
  218. * @memberOf module:strings
  219. * @constructor
  220. * @struct
  221. * @final
  222. */
  223. strings.HighlightedText = function (text, snippets) {
  224. this.text = text;
  225. this.snippets = snippets;
  226. }
  227. /**
  228. * Highlights all occurrences of a given set of patterns in a string.
  229. *
  230. * @param {string} text the text to highlight.
  231. * @param {Array<strings.Pattern>} patterns a set of patterns to match and highlight.
  232. * @return {strings.HighlightedText} the highlighted text.
  233. * @memberOf module:strings
  234. */
  235. strings.highlight = function (text, patterns) {
  236. text = text ? '' + text : '';
  237. if (!patterns || patterns.length <= 0 || strings.isNullOrBlank(text)) {
  238. return new strings.HighlightedText(text, []);
  239. }
  240. let highlightedText = text;
  241. text = strings.removeDiacritics(text, true);
  242. if (text.length !== highlightedText.length) {
  243. highlightedText = text;
  244. }
  245. const highlights = patterns.flatMap(pattern => {
  246. const matcher = pattern.regexp;
  247. const matches = [];
  248. let match = null;
  249. while (match = matcher.exec(text)) {
  250. matches.push({
  251. start: match.index, end: match.index + match[0].length, color: pattern.color
  252. });
  253. }
  254. return matches;
  255. }).sort((a, b) => {
  256. if (a.start < b.start) {
  257. return 1;
  258. }
  259. if (a.start > b.start) {
  260. return -1;
  261. }
  262. return 0;
  263. }).map(position => {
  264. // TODO : deal with overlaps?
  265. const prefix = highlightedText.substring(0, position.start);
  266. const infix = highlightedText.substring(position.start, position.end);
  267. const suffix = highlightedText.substring(position.end);
  268. highlightedText = `${prefix}<mark style="border-radius:3px;background:${position.color}">${infix}</mark>${suffix}`;
  269. const begin = Math.max(0, prefix.length - 50);
  270. const end = Math.min(150, suffix.length);
  271. const rawSnippet = `${prefix.substring(begin)}${infix}${suffix.substring(0, end)}`;
  272. let highlightedSnippet = `${prefix.substring(
  273. begin)}<mark style="border-radius:3px;background:${position.color}">${infix}</mark>${suffix.substring(0, end)}`;
  274. const pages = prefix.split('\f' /* page separator */).map((page, index) => index);
  275. const beginMark = highlightedSnippet.lastIndexOf('<m');
  276. const endMark = highlightedSnippet.lastIndexOf('</mark>');
  277. if (beginMark && (!endMark || beginMark > endMark)) {
  278. highlightedSnippet = highlightedSnippet.substring(0, beginMark);
  279. }
  280. return new strings.Highlight(infix, pages.length, rawSnippet, highlightedSnippet);
  281. });
  282. return new strings.HighlightedText(highlightedText, highlights);
  283. }
  284. /**
  285. * Returns true iif a string is either null or blank, false otherwise.
  286. *
  287. * @param {string} str the string to check.
  288. * @return {boolean} true if the string is null or blank, false otherwise.
  289. * @memberOf module:strings
  290. */
  291. strings.isNullOrBlank = function (str) {
  292. return !(typeof str === 'string' && str.trim() !== '');
  293. }
  294. /**
  295. * Prepends '0' to a string or number until a given length is reached.
  296. *
  297. * @param {string|number} str a string or number.
  298. * @param {number} targetLength the string target length.
  299. * @return {string} a padded string.
  300. * @memberOf module:strings
  301. */
  302. strings.pad = function (str, targetLength) {
  303. return (str ? '' + str : '').padStart(targetLength, '0');
  304. }
  305. /**
  306. * Removes all '0' from the beginning of a string.
  307. *
  308. * @param {string} str a string.
  309. * @return {string} an un-padded string.
  310. * @memberOf module:strings
  311. */
  312. strings.unpad = function (str) {
  313. str = str ? '' + str : '';
  314. let i = 0;
  315. for (; i < str.length && str[i] === '0'; i++) {
  316. }
  317. return str.substring(i);
  318. }
  319. /**
  320. * Checks if a string represents a numeric value.
  321. *
  322. * @param {string} str the string to check.
  323. * @return {boolean} true if the string is a number, false otherwise.
  324. * @memberOf module:strings
  325. * @preserve The code is extracted from https://stackoverflow.com/a/175787.
  326. */
  327. strings.isNumeric = function (str) {
  328. return typeof str === 'string' ? !isNaN(str) && !isNaN(parseFloat(str)) : false;
  329. }
  330. /**
  331. * Formats null or blank values.
  332. *
  333. * @param {string|number} str the value to format.
  334. * @param {string} defaultValue the string to return if the value is either null or empty.
  335. * @return {string} the formatted value.
  336. */
  337. strings.formatNullOrBlank = function (str, defaultValue) {
  338. str = str ? '' + str : '';
  339. return strings.isNullOrBlank(str) ? defaultValue : str;
  340. }
  341. /**
  342. * Returns true iif a string starts with 'MASKED_', false otherwise.
  343. *
  344. * @param {string} str the string to check.
  345. * @return {boolean} true iif the string starts with 'MASKED_', false otherwise.
  346. */
  347. strings.isMasked = function (str) {
  348. return typeof str === 'string' ? str.trim().toUpperCase().startsWith('MASKED_') : false;
  349. }
  350. /**
  351. * Convert a string from camel case to snake case.
  352. *
  353. * @param {string} str the string in camel case.
  354. * @returns {string} the string in snake case.
  355. */
  356. strings.camelToSnakeCase = function (str) {
  357. return typeof str === 'string' ? str.replace(/[A-Z]/g,
  358. (letter, idx) => idx === 0 ? letter.toLowerCase() : `_${letter.toLowerCase()}`) : null;
  359. }
  360. /**
  361. * Convert a string from snake case to camel case.
  362. *
  363. * @param {string} str the string in snake case.
  364. * @returns {string} the string in camel case.
  365. */
  366. strings.snakeCaseToCamelCase = function (str) {
  367. return typeof str === 'string' ? str.replace(/_[a-z]/g,
  368. (group, idx) => idx === 0 ? group.replace('_', '') : group.toUpperCase().replace('_', '')) : null;
  369. }