| 1 | import helper from './helper.js' |
| 2 | import {findWord} from 'most-common-words-by-language' |
| 3 | import WordsNinjaPack from 'wordsninja' |
| 4 | const WordsNinja = new WordsNinjaPack() |
| 5 | |
| 6 | function most_common1 (all_words, temp_words) { |
| 7 | const temp_list = [] |
| 8 | Object.keys(all_words).forEach(function (key) { |
| 9 | all_words[key].forEach(function (item) { |
| 10 | if (!temp_list.includes(item) && item.length > 1) { |
| 11 | temp_list.push(item) |
| 12 | const temp = findWord(item) |
| 13 | if (Object.keys(temp).length !== 0) { |
| 14 | const languages = Object.keys(temp).map(function (key) { |
| 15 | return [key, temp[key]] |
| 16 | }) |
| 17 | languages.sort(function (first, second) { |
| 18 | return second[1] - first[1] |
| 19 | }).reverse() |
| 20 | temp_words.push({ |
| 21 | word: item, |
| 22 | languages: languages.map(e => e.join(':')).join(' ') |
| 23 | }) |
| 24 | } |
| 25 | } |
| 26 | }) |
| 27 | }) |
| 28 | } |
| 29 | |
| 30 | async function most_common (all_words, temp_words) { |
| 31 | const temp_list = [] |
| 32 | Object.keys(all_words).forEach(function (key) { |
| 33 | all_words[key].forEach(function (item) { |
| 34 | if (!temp_list.includes(item) && item.length > 1) { |
| 35 | temp_list.push(item) |
| 36 | const temp = findWord(item) |
| 37 | if (Object.keys(temp).length !== 0) { |
| 38 | const languages = Object.keys(temp).map(function (key) { |
| 39 | return [key, temp[key]] |
| 40 | }) |
| 41 | languages.sort(function (first, second) { |
| 42 | return second[1] - first[1] |
| 43 | }).reverse() |
| 44 | temp_words.push({ |
| 45 | word: item, |
| 46 | languages: languages.map(e => e[0]).join(', ') |
| 47 | }) |
| 48 | } |
| 49 | } |
| 50 | }) |
| 51 | }) |
| 52 | } |
| 53 | |
| 54 | function find_other (req, all_words) { |
| 55 | const words = WordsNinja.splitSentence(req.body.string) |
| 56 | |
| 57 | words.forEach(function (word) { |
| 58 | let value = false |
| 59 | Object.keys(all_words).forEach(function (key) { |
| 60 | if (all_words[key].includes(word)) { |
| 61 | value = true |
| 62 | } |
| 63 | }) |
| 64 | |
| 65 | if (!value && !all_words.maybe.includes(word)) { |
| 66 | all_words.maybe.push(word) |
| 67 | } |
| 68 | }) |
| 69 | } |
| 70 | |
| 71 | function remove_word (str, sub_string) { |
| 72 | const part1 = str.substring(0, str.indexOf(sub_string)) |
| 73 | const part2 = str.substring(str.indexOf(sub_string) + sub_string.length, str.length) |
| 74 | const temp = (part1 + part2).replace(/[ \[\]:"\\|,.<>\/?~`!@#$%^&*()_+\-={};"]/gi, '') |
| 75 | return temp |
| 76 | } |
| 77 | |
| 78 | async function analyze_string (req, all_words) { |
| 79 | helper.log_to_file_queue(req.body.uuid, '[Starting] String analysis') |
| 80 | let temp_rr_names = [] |
| 81 | const string_to_check = req.body.string |
| 82 | helper.parsed_json.prefix.forEach(function (item, index) { |
| 83 | if (string_to_check.indexOf(item) === 0 && !all_words.prefix.includes(item)) { |
| 84 | all_words.prefix.push(item) |
| 85 | const temp = remove_word(string_to_check, item) |
| 86 | if (temp !== null && temp !== '' && !all_words.unknown.includes(temp) && !all_words.maybe.includes(temp) && temp.length > 1) { |
| 87 | all_words.unknown.push(temp) |
| 88 | } |
| 89 | } |
| 90 | }) |
| 91 | helper.parsed_json.m_names.forEach(function (item, index) { |
| 92 | if (string_to_check.indexOf(item) >= 0 && !all_words.name.includes(item)) { |
| 93 | all_words.name.push(item) |
| 94 | const temp = remove_word(string_to_check, item) |
| 95 | if (temp !== null && temp !== '' && !all_words.unknown.includes(temp) && !all_words.maybe.includes(temp) && temp.length > 1) { |
| 96 | all_words.unknown.push(temp) |
| 97 | } |
| 98 | } |
| 99 | }) |
| 100 | helper.parsed_json.f_names.forEach(function (item, index) { |
| 101 | if (string_to_check.indexOf(item) >= 0 && !all_words.name.includes(item)) { |
| 102 | all_words.name.push(item) |
| 103 | const temp = remove_word(string_to_check, item) |
| 104 | if (temp !== null && temp !== '' && !all_words.unknown.includes(temp) && !all_words.maybe.includes(temp) && temp.length > 1) { |
| 105 | all_words.unknown.push(temp) |
| 106 | } |
| 107 | } |
| 108 | }) |
| 109 | |
| 110 | all_words.prefix.forEach(function (h_item, index) { |
| 111 | all_words.unknown.forEach(function (r_item, index) { |
| 112 | if (r_item.indexOf(h_item) === 0) { |
| 113 | const temp = remove_word(r_item, h_item) |
| 114 | if (temp !== null && temp !== '' && !temp_rr_names.includes(temp) && !all_words.maybe.includes(temp) && temp.length > 1) { |
| 115 | temp_rr_names.push(temp) |
| 116 | } |
| 117 | } |
| 118 | }) |
| 119 | }) |
| 120 | |
| 121 | let temp_r_concat = all_words.unknown.concat(temp_rr_names.filter((item) => all_words.unknown.indexOf(item) < 0)) |
| 122 | |
| 123 | all_words.unknown = temp_r_concat |
| 124 | temp_rr_names = [] |
| 125 | |
| 126 | all_words.number.forEach(function (n_item, index) { |
| 127 | all_words.unknown.forEach(function (r_item, index) { |
| 128 | if (r_item.indexOf(n_item) >= 0) { |
| 129 | const temp = remove_word(r_item, n_item) |
| 130 | if (temp !== null && temp !== '' && !temp_rr_names.includes(temp) && !all_words.maybe.includes(temp) && temp.length > 1) { |
| 131 | temp_rr_names.push(temp) |
| 132 | } |
| 133 | } |
| 134 | }) |
| 135 | }) |
| 136 | |
| 137 | temp_r_concat = all_words.unknown.concat(temp_rr_names.filter((item) => all_words.unknown.indexOf(item) < 0)) |
| 138 | all_words.unknown = temp_r_concat |
| 139 | helper.log_to_file_queue(req.body.uuid, '[Done] String analysis') |
| 140 | } |
| 141 | |
| 142 | async function split_comma (req, all_words) { |
| 143 | try { |
| 144 | req.body.string.split(',').forEach((item) => { |
| 145 | if (item.length > 1 && !all_words.unknown.includes(item) && !all_words.maybe.includes(item)) { |
| 146 | all_words.unknown.push(item.toLowerCase()) |
| 147 | } |
| 148 | }) |
| 149 | } catch (err) {} |
| 150 | } |
| 151 | |
| 152 | async function split_upper_case (req, all_words) { |
| 153 | try { |
| 154 | req.body.string.match(/[A-Z][a-z]+/g).forEach((item) => { |
| 155 | if (item.length > 1 && !all_words.unknown.includes(item) && !all_words.maybe.includes(item)) { |
| 156 | all_words.unknown.push(item.toLowerCase()) |
| 157 | } |
| 158 | }) |
| 159 | } catch (err) {} |
| 160 | } |
| 161 | |
| 162 | async function split_alphabet_case (req, all_words) { |
| 163 | try { |
| 164 | req.body.string.match(/[A-Za-z]+/g).forEach((item) => { |
| 165 | if (item.length > 1 && !all_words.unknown.includes(item) && !all_words.maybe.includes(item)) { |
| 166 | all_words.unknown.push(item.toLowerCase()) |
| 167 | } |
| 168 | }) |
| 169 | } catch (err) {} |
| 170 | } |
| 171 | |
| 172 | async function find_symbols (req, all_words) { |
| 173 | try { |
| 174 | req.body.string.match(/[ \[\]:"\\|,.<>\/?~`!@#$%^&*()_+\-={};']/gi).forEach((item) => { |
| 175 | if (item !== ' ' && !all_words.symbol.includes(item)) { |
| 176 | all_words.symbol.push(item) |
| 177 | } |
| 178 | }) |
| 179 | } catch (err) {} |
| 180 | } |
| 181 | |
| 182 | async function find_numbers (req, all_words) { |
| 183 | try { |
| 184 | req.body.string.match(/(\d+)/g).forEach((item) => { |
| 185 | if (!all_words.number.includes(item)) { |
| 186 | all_words.number.push(item) |
| 187 | } |
| 188 | }) |
| 189 | } catch (err) {} |
| 190 | } |
| 191 | |
| 192 | async function convert_numbers (req) { |
| 193 | try { |
| 194 | const numbers_to_letters = { |
| 195 | 4: 'a', |
| 196 | 8: 'b', |
| 197 | 3: 'e', |
| 198 | 1: 'l', |
| 199 | 0: 'o', |
| 200 | 5: 's', |
| 201 | 7: 't', |
| 202 | 2: 'z' |
| 203 | } |
| 204 | |
| 205 | let temp_value = '' |
| 206 | for (let i = 0; i < req.body.string.length; i++) { |
| 207 | const _temp = numbers_to_letters[req.body.string.charAt(i)] |
| 208 | if (_temp !== undefined) { |
| 209 | temp_value += numbers_to_letters[req.body.string.charAt(i)] |
| 210 | } else { |
| 211 | temp_value += req.body.string.charAt(i) |
| 212 | } |
| 213 | } |
| 214 | req.body.string = temp_value |
| 215 | } catch (err) {} |
| 216 | } |
| 217 | |
| 218 | async function get_maybe_words (req, all_words) { |
| 219 | await WordsNinja.loadDictionary() |
| 220 | all_words.maybe = await WordsNinja.splitSentence(req.body.string).filter(function (elem, index, self) { |
| 221 | return index === self.indexOf(elem) |
| 222 | }).filter(word => word.length > 1) |
| 223 | } |
| 224 | |
| 225 | async function guess_age_from_string(req) { |
| 226 | let results = [] |
| 227 | |
| 228 | try { |
| 229 | let age_4_numbers = /\d{4}|\d{2}/g |
| 230 | let current_year = new Date().getFullYear() |
| 231 | while ((match = age_4_numbers.exec(req.body.string)) != null) { |
| 232 | let temp_dict = {"found":"","year":"","age":""} |
| 233 | let found = 0 |
| 234 | let year = 0 |
| 235 | let age = 0 |
| 236 | temp_dict.found = match[0] |
| 237 | found = parseInt(match[0]) |
| 238 | if (found >= 50 && found <= 99){ |
| 239 | year = found + 1900 |
| 240 | age = current_year - year |
| 241 | if (age <= 75){ |
| 242 | temp_dict.year = year.toString() |
| 243 | temp_dict.age = age.toString() |
| 244 | } |
| 245 | } |
| 246 | if (found >= 14 && found <= 49){ |
| 247 | year = current_year - found |
| 248 | age = found |
| 249 | if (age <= 75){ |
| 250 | temp_dict.year = year.toString() |
| 251 | temp_dict.age = age.toString() |
| 252 | } |
| 253 | } |
| 254 | if (found >= 1950){ |
| 255 | year = found |
| 256 | age = current_year - year |
| 257 | if (age <= 75){ |
| 258 | temp_dict.year = year.toString() |
| 259 | temp_dict.age = age.toString() |
| 260 | } |
| 261 | } |
| 262 | |
| 263 | results.push(temp_dict) |
| 264 | } |
| 265 | |
| 266 | } catch (err) { |
| 267 | } |
| 268 | |
| 269 | return results |
| 270 | } |
| 271 | |
| 272 | export default{ |
| 273 | get_maybe_words, |
| 274 | find_symbols, |
| 275 | find_numbers, |
| 276 | convert_numbers, |
| 277 | split_comma, |
| 278 | split_upper_case, |
| 279 | split_alphabet_case, |
| 280 | most_common, |
| 281 | find_other, |
| 282 | analyze_string, |
| 283 | guess_age_from_string |
| 284 | } |
| 285 |