|
| 1 | +function RegexMatch(word: string, regex: RegExp): boolean { |
| 2 | + const words = word.trim(); |
| 3 | + const barisdata: string[] = []; |
| 4 | + |
| 5 | + if (words) { |
| 6 | + for (let index = 0; index < words.length; index++) { |
| 7 | + const datacocok = barisdata.join("").toLowerCase(); |
| 8 | + |
| 9 | + if (datacocok.match(regex)) { |
| 10 | + return true; |
| 11 | + } else { |
| 12 | + let modifiedWord = words[index]; |
| 13 | + |
| 14 | + if (modifiedWord.includes("3")) { |
| 15 | + modifiedWord = modifiedWord.replace("3", "e"); |
| 16 | + } else if (modifiedWord.includes("0")) { |
| 17 | + modifiedWord = modifiedWord.replace("0", "o"); |
| 18 | + } else if (modifiedWord.includes("4")) { |
| 19 | + modifiedWord = modifiedWord.replace("4", "a"); |
| 20 | + } else if (modifiedWord.includes("5")) { |
| 21 | + modifiedWord = modifiedWord.replace("5", "s"); |
| 22 | + } else if (modifiedWord.includes("8")) { |
| 23 | + modifiedWord = modifiedWord.replace("8", "b"); |
| 24 | + } |
| 25 | + |
| 26 | + if (datacocok.replace(/1/gi, "i").match(regex) || |
| 27 | + datacocok.replace(/1/gi, "l").match(regex) || |
| 28 | + datacocok.replace(/6/gi, "b").match(regex) || |
| 29 | + datacocok.replace(/6/gi, "g").match(regex)) { |
| 30 | + return true; |
| 31 | + } |
| 32 | + } |
| 33 | + |
| 34 | + barisdata.push(words[index].trim()); |
| 35 | + } |
| 36 | + } |
| 37 | + |
| 38 | + return false; |
| 39 | +} |
| 40 | + |
| 41 | +function escapeRegExp(strings: string): string { |
| 42 | + const data = strings.trim().toLowerCase().split("|").filter(Boolean); |
| 43 | + |
| 44 | + for (let index = 0; index < data.length; index++) { |
| 45 | + const element = data[index]; |
| 46 | + |
| 47 | + if (!((element.includes("(") && element.includes(")")) || |
| 48 | + (element.includes("[") && element.includes("]")))) { |
| 49 | + data[index] = data[index] |
| 50 | + .replace(/[.*+?^${}()|[\]\\]/g, '\\$&') |
| 51 | + .replace(/[a4]/g, "[a4]") |
| 52 | + .replace(/[s5]/g, "[s5]") |
| 53 | + .replace("i", "[i1]") |
| 54 | + .replace("l", "[l1]") |
| 55 | + .replace(/[o0]/g, "[o0]") |
| 56 | + .replace(/[e3]/g, "[e3]") |
| 57 | + .replace(/[b8]/g, "[b8]") |
| 58 | + .replace(/[kx]/g, "[kx]"); |
| 59 | + } |
| 60 | + } |
| 61 | + |
| 62 | + return new RegExp(data.join("|")).source; |
| 63 | +} |
| 64 | + |
| 65 | +function validateInput(type: string, value: string): boolean { |
| 66 | + let regex: RegExp; |
| 67 | + |
| 68 | + switch (type) { |
| 69 | + case 'email': |
| 70 | + regex = /^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.(com|net|org|edu|gov|mil|co|info|io|biz|id|us|uk|ca|au|de|fr|es|it|jp|cn|br|in|ru|mx|kr|za|nl|se|no|fi|dk|pl|pt|ar|ch|hk|sg|my|th|vn|ae|at|be|cz|hu|ro|bg|gr|lt|lv|sk|si|ee|cy)(\.[a-zA-Z]{2,})?$/; |
| 71 | + break; |
| 72 | + case 'phone': |
| 73 | + regex = /^(?:\+?(\d{1,3}))?[-. ]?(\(?\d{1,4}?\)?)[-.\s]?(\d{1,4})[-.\s]?(\d{1,4})[-.\s]?(\d{1,9})$/; |
| 74 | + break; |
| 75 | + case 'url': |
| 76 | + regex = /^(https?:\/\/)?(www\.)?([a-zA-Z0-9-]+\.[a-zA-Z]{2,})(\/[^\s]*)?$/; |
| 77 | + break; |
| 78 | + default: |
| 79 | + return false; // Invalid type |
| 80 | + } |
| 81 | + |
| 82 | + return regex.test(value); |
| 83 | +} |
| 84 | + |
| 85 | +class FilterBadWord { |
| 86 | + protected _text: string; |
| 87 | + protected _filt: RegExp; |
| 88 | + protected _subfilter: RegExp; |
| 89 | + protected __subtxic: [string, string][]; |
| 90 | + protected _st: boolean; |
| 91 | + |
| 92 | + constructor(text: string = "", customFilter: string = "", customSubFilter: string = "") { |
| 93 | + this._text = text; |
| 94 | + this._filt = /b[a4][s5]hfu[l1][l1]|k[i1][l1][l1]|fuck[*]?|dr[uo]g[*]?|d[i1]ck[*]?|[a4][s5][s5]|[l1][i1]p|pu[s5][s5]y[*]?|fk/gi; |
| 95 | + this._subfilter = /[a4][s5][s5]|[l1][i1]p|pu[s5][s5]y[*]?|[s5]uck[*]?|m[o0]th[e3]r[*]?|m[o0]m[*]?|d[o0]g[*]?|l[o0]w[*]?|s[e3]x[*]?/gi; |
| 96 | + |
| 97 | + if (customFilter.length > 3) { |
| 98 | + this._filt = new RegExp(this._filt.source + "|" + escapeRegExp(customFilter), "gi"); |
| 99 | + } |
| 100 | + |
| 101 | + if (customSubFilter.length > 3) { |
| 102 | + this._subfilter = new RegExp(this._subfilter.source + "|" + escapeRegExp(customSubFilter), "gi"); |
| 103 | + } |
| 104 | + |
| 105 | + this.__subtxic = []; |
| 106 | + this._st = false; |
| 107 | + } |
| 108 | + |
| 109 | + private getBoundPosition(word: string, position: number): string { |
| 110 | + let paragraph = word; |
| 111 | + |
| 112 | + while (position > 0 && paragraph[position] === " ") position--; |
| 113 | + |
| 114 | + position = paragraph.lastIndexOf(" ", position) + 1; |
| 115 | + let end = paragraph.indexOf(" ", position); |
| 116 | + |
| 117 | + if (end === -1) { |
| 118 | + end = paragraph.length; |
| 119 | + } |
| 120 | + |
| 121 | + return paragraph.substring(position, end); |
| 122 | + } |
| 123 | + |
| 124 | + private positionStatic(word: string, filters: RegExp): number[] { |
| 125 | + const wordlist_ = word.toLowerCase().split(' '); |
| 126 | + const positions: number[] = []; |
| 127 | + |
| 128 | + wordlist_.forEach((word, index) => { |
| 129 | + const pos = index && wordlist_[index - 1].length + positions.length + 1; |
| 130 | + |
| 131 | + if (word.match(filters) || RegexMatch(word, filters)) { |
| 132 | + positions.push(pos); |
| 133 | + } |
| 134 | + }); |
| 135 | + |
| 136 | + return positions; |
| 137 | + } |
| 138 | + |
| 139 | + public position(): number[] { |
| 140 | + return this.positionStatic(this._text.toString(), this._filt); |
| 141 | + } |
| 142 | + |
| 143 | + public get thisToxic(): (string | number)[] | false { |
| 144 | + const check = this.position(); |
| 145 | + const arry: (string | number)[] = []; |
| 146 | + |
| 147 | + if (check.length > 0) { |
| 148 | + const word = this._text.toLowerCase(); |
| 149 | + function before_str(number , key){ |
| 150 | + |
| 151 | + return word.substring(number, word.indexOf(key));//nomer dan keyword |
| 152 | + |
| 153 | + }; |
| 154 | + |
| 155 | + function after_str(w, spec){ |
| 156 | + let data =word.substring( word.indexOf(w), spec.length+word.length ); |
| 157 | + return data.replace(w, "").trim(); //, word.indexOf(spec)); |
| 158 | + }; |
| 159 | + |
| 160 | + for (const index of check) { |
| 161 | + const word_s = this.getBoundPosition(this._text.toLowerCase(), index); |
| 162 | + const before = word.substring(0, word.indexOf(word_s)).trim().split(" "); |
| 163 | + const after = word.substring(word.indexOf(word_s) + word_s.length).trim().split(" "); |
| 164 | + |
| 165 | + // Check before |
| 166 | + before.forEach(d => { |
| 167 | + if (d.match(this._subfilter)) { |
| 168 | + this.__subtxic.push([d, '*'.repeat(d.length)]); |
| 169 | + } |
| 170 | + }); |
| 171 | + |
| 172 | + // Check after |
| 173 | + after.forEach(d => { |
| 174 | + if (d.match(this._subfilter)) { |
| 175 | + this.__subtxic.push([d, '*'.repeat(d.length)]); |
| 176 | + } |
| 177 | + }); |
| 178 | + |
| 179 | + // Add toxic word if found in before or after |
| 180 | + if (before.length && before[before.length - 1].match(this._subfilter)) { |
| 181 | + arry.push("Toxic", 1, before[before.length - 1]); |
| 182 | + return arry; |
| 183 | + } |
| 184 | + |
| 185 | + if (after.length && after[0].match(this._subfilter)) { |
| 186 | + arry.push("Toxic", 1, after[0]); |
| 187 | + return arry; |
| 188 | + } |
| 189 | + |
| 190 | + if (after.length > 1 && after[1].match(this._subfilter)) { |
| 191 | + arry.push("Toxic", 1, after[1]); |
| 192 | + return arry; |
| 193 | + } |
| 194 | + } |
| 195 | + |
| 196 | + arry.push("Notoxic", 0); |
| 197 | + return arry; |
| 198 | + } |
| 199 | + |
| 200 | + return false; |
| 201 | + } |
| 202 | + |
| 203 | + set thisToxic(key: any) { |
| 204 | + throw key; |
| 205 | + } |
| 206 | + |
| 207 | + public clean(position: number[]): string { |
| 208 | + let words = this._text.split(" "); |
| 209 | + const sensor = "*"; |
| 210 | + |
| 211 | + position.forEach((number) => { |
| 212 | + const getWord = this.getBoundPosition(this._text, number); |
| 213 | + words = words.map(word => word.replace(getWord, sensor.repeat(getWord.length))); |
| 214 | + }); |
| 215 | + this.__subtxic.forEach(([oldWord, newWord]) => { |
| 216 | + words = words.map(word => { |
| 217 | + return !(validateInput("email", word) || validateInput("url", word)) && this._st |
| 218 | + ? word.replace(oldWord, newWord): word; |
| 219 | + }); |
| 220 | + }); |
| 221 | + return words.join(" "); |
| 222 | + } |
| 223 | +} |
| 224 | + |
| 225 | +class filters_badword extends FilterBadWord { |
| 226 | + protected _cl: boolean; |
| 227 | + protected _st: boolean; |
| 228 | + |
| 229 | + public text_o(text: string): void { |
| 230 | + this._text = text.toString(); |
| 231 | + } |
| 232 | + |
| 233 | + public config(cl: boolean = true, smart: boolean = true, customFilter: string = "", customSubFilter: string = ""): void { |
| 234 | + this._cl = cl; |
| 235 | + this._st = smart; |
| 236 | + |
| 237 | + if (customFilter.length > 3) { |
| 238 | + this._filt = new RegExp(this._filt.source + "|" + escapeRegExp(customFilter), "gi"); |
| 239 | + } |
| 240 | + if (customSubFilter.length > 3) { |
| 241 | + this._subfilter = new RegExp(this._subfilter.source + "|" + escapeRegExp(customSubFilter), "gi"); |
| 242 | + } |
| 243 | + } |
| 244 | + |
| 245 | + public get cleans(): string { |
| 246 | + if (this._cl) { |
| 247 | + if (this.thisToxic){ |
| 248 | + if (this.thisToxic[1] === 1 && this.thisToxic.length > 2) { |
| 249 | + return this.clean(this.position()); |
| 250 | + }; |
| 251 | + }; |
| 252 | + return this.clean(this.position()); |
| 253 | + }; |
| 254 | + return this._text.trim(); |
| 255 | + } |
| 256 | + |
| 257 | + set cleans(value: string) { |
| 258 | + throw value; |
| 259 | + } |
| 260 | +} |
| 261 | + |
| 262 | +export { |
| 263 | + /** |
| 264 | + * FilterBadWord class: class for filtering bad words |
| 265 | + *@param {string} text - The text to filter |
| 266 | + *@param {string} customFilter - List of bad words |
| 267 | + *@param {string} customSubFilter - List of bad sub words |
| 268 | + */ |
| 269 | + FilterBadWord, |
| 270 | + /** |
| 271 | + * filters_badword class: a simpler class to filter bad words |
| 272 | + * which uses the FilterBadWord class. To use it you have to call the config function |
| 273 | + */ |
| 274 | + filters_badword |
| 275 | +}; |
0 commit comments