terlik.js 2.3.0 → 2.4.1

package/dist/index.js

@@ -181,18 +181,45 @@ function compilePatterns(entries, suffixes, charClasses, normalizeFn) {
   for (const [, entry] of entries) {
     const allForms = [entry.root, ...entry.variants];
     const sortedForms = allForms.map((w) => normalizeFn(w)).filter((w) => w.length > 0).filter((w, i, arr) => arr.indexOf(w) === i).sort((a, b) => b.length - a.length);
-    const formPatterns = sortedForms.map(
-      (w) => wordToPattern(w, charClasses, normalizeFn)
-    );
-    const combined = formPatterns.join("|");
     const useSuffix = entry.suffixable && suffixGroup.length > 0;
     let pattern;
     if (useSuffix) {
+      const formPatterns = sortedForms.map(
+        (w) => wordToPattern(w, charClasses, normalizeFn)
+      );
+      const combined = formPatterns.join("|");
       pattern = `${WORD_BOUNDARY_BEHIND}(?:${combined})${suffixGroup}{0,${MAX_SUFFIX_CHAIN}}${WORD_BOUNDARY_AHEAD}`;
+    } else if (suffixGroup.length > 0) {
+      const MIN_VARIANT_SUFFIX_LEN = 4;
+      const strictForms = [];
+      const suffixableForms = [];
+      for (const w of sortedForms) {
+        if (w.length >= MIN_VARIANT_SUFFIX_LEN) {
+          suffixableForms.push(wordToPattern(w, charClasses, normalizeFn));
+        } else {
+          strictForms.push(wordToPattern(w, charClasses, normalizeFn));
+        }
+      }
+      const parts = [];
+      if (suffixableForms.length > 0) {
+        parts.push(`(?:${suffixableForms.join("|")})${suffixGroup}{0,${MAX_SUFFIX_CHAIN}}`);
+      }
+      if (strictForms.length > 0) {
+        parts.push(`(?:${strictForms.join("|")})`);
+      }
+      pattern = `${WORD_BOUNDARY_BEHIND}(?:${parts.join("|")})${WORD_BOUNDARY_AHEAD}`;
     } else {
+      const formPatterns = sortedForms.map(
+        (w) => wordToPattern(w, charClasses, normalizeFn)
+      );
+      const combined = formPatterns.join("|");
       pattern = `${WORD_BOUNDARY_BEHIND}(?:${combined})${WORD_BOUNDARY_AHEAD}`;
     }
-    if (pattern.length > MAX_PATTERN_LENGTH && useSuffix) {
+    if (pattern.length > MAX_PATTERN_LENGTH) {
+      const formPatterns = sortedForms.map(
+        (w) => wordToPattern(w, charClasses, normalizeFn)
+      );
+      const combined = formPatterns.join("|");
       pattern = `${WORD_BOUNDARY_BEHIND}(?:${combined})${WORD_BOUNDARY_AHEAD}`;
     }
     try {
@@ -206,7 +233,8 @@ function compilePatterns(entries, suffixes, charClasses, normalizeFn) {
     } catch (err) {
       if (useSuffix) {
         try {
-          const fallbackPattern = `${WORD_BOUNDARY_BEHIND}(?:${combined})${WORD_BOUNDARY_AHEAD}`;
+          const fallbackForms = sortedForms.map((w) => wordToPattern(w, charClasses, normalizeFn)).join("|");
+          const fallbackPattern = `${WORD_BOUNDARY_BEHIND}(?:${fallbackForms})${WORD_BOUNDARY_AHEAD}`;
           const regex = new RegExp(fallbackPattern, "gi");
           patterns.push({
             root: entry.root,
@@ -418,13 +446,16 @@ var Detector = class _Detector {
       while ((match = pattern.regex.exec(searchText)) !== null) {
         const matchedText = match[0];
         const matchIndex = match.index;
+        if (whitelist.has(matchedText)) continue;
         const normalizedMatch = this.normalizeFn(matchedText);
         if (whitelist.has(normalizedMatch)) continue;
         const surrounding = this.getSurroundingWord(searchText, matchIndex, matchedText.length);
+        if (whitelist.has(surrounding)) continue;
         const normalizedSurrounding = this.normalizeFn(surrounding);
         if (whitelist.has(normalizedSurrounding)) continue;
         if (isNormalized) {
           const mapped = this.mapNormalizedToOriginal(originalText, matchIndex, matchedText);
+          if (mapped && whitelist.has(mapped.word.toLowerCase())) continue;
           if (mapped && !existingIndices.has(mapped.index)) {
             results.push({
               word: mapped.word,
@@ -698,7 +729,18 @@ var dictionary_default = {
         "sikti\u011Fimin",
         "sikermisiniz",
         "sikermisin",
-        "siktirmi\u015Fcesine"
+        "siktirmi\u015Fcesine",
+        "sktr",
+        "siki\u015Fse",
+        "siki\u015Fecek",
+        "siki\u015Fen",
+        "siki\u015Fme",
+        "siki\u015Fmek",
+        "sikeceksin",
+        "sikecekler",
+        "sikece\u011Fim",
+        "sikmi\u015Fler",
+        "sikilecek"
       ],
       severity: "high",
       category: "sexual",
@@ -706,14 +748,31 @@ var dictionary_default = {
     },
     {
       root: "amk",
-      variants: ["amk", "amina", "aminakoyim", "aminakoydugum", "amq"],
+      variants: [
+        "amk",
+        "amina",
+        "aminakoyim",
+        "aminakoydugum",
+        "amq",
+        "aminakoyayim",
+        "aminakoydum",
+        "aminakoydugumun",
+        "aq"
+      ],
       severity: "high",
       category: "sexual",
       suffixable: false
     },
     {
       root: "orospu",
-      variants: ["orospucocugu", "orosbucocugu", "orspu", "oruspu", "orosbu"],
+      variants: [
+        "orospucocugu",
+        "orosbucocugu",
+        "orspu",
+        "oruspu",
+        "orosbu",
+        "orospucocuklari"
+      ],
       severity: "high",
       category: "insult",
       suffixable: true
@@ -727,7 +786,16 @@ var dictionary_default = {
     },
     {
       root: "yarrak",
-      variants: ["yarak", "yarrak", "yarakli", "dalyarak", "dalyarrak"],
+      variants: [
+        "yarak",
+        "yarrak",
+        "yarakli",
+        "dalyarak",
+        "dalyarrak",
+        "yarrani",
+        "yarragimi",
+        "yarragini"
+      ],
       severity: "high",
       category: "sexual",
       suffixable: true
@@ -745,7 +813,8 @@ var dictionary_default = {
         "gotler",
         "gotlu",
         "gotunden",
-        "gotune"
+        "gotune",
+        "gotos"
       ],
       severity: "high",
       category: "sexual",
@@ -890,6 +959,104 @@ var dictionary_default = {
       severity: "high",
       category: "insult",
       suffixable: true
+    },
+    {
+      root: "s\xFCrt\xFCk",
+      variants: ["surtuk"],
+      severity: "high",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "kaltak",
+      variants: [],
+      severity: "high",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "fahi\u015Fe",
+      variants: ["fahise"],
+      severity: "high",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "keva\u015Fe",
+      variants: ["kevase"],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "o\u011Flanc\u0131",
+      variants: ["oglanci"],
+      severity: "high",
+      category: "slur",
+      suffixable: true
+    },
+    {
+      root: "dingil",
+      variants: [],
+      severity: "low",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "avanak",
+      variants: [],
+      severity: "low",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "manyak",
+      variants: [],
+      severity: "low",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "h\xF6d\xFCk",
+      variants: ["hoduk"],
+      severity: "low",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "kepaze",
+      variants: [],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "rezil",
+      variants: [],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "kalle\u015F",
+      variants: ["kalles"],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "namussuz",
+      variants: [],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "ahlaks\u0131z",
+      variants: ["ahlaksiz"],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
     }
   ],
   whitelist: [
@@ -911,6 +1078,10 @@ var dictionary_default = {
     "amonyak",
     "amper",
     "ampul",
+    "amazon",
+    "ambargo",
+    "amblem",
+    "amfibi",
     "boks\xF6r",
     "bokser",
     "bokluk",
@@ -922,6 +1093,7 @@ var dictionary_default = {
     "mallorca",
     "malta",
     "malt",
+    "malum",
     "gotan",
     "gotik",
     "gotham",
@@ -939,12 +1111,22 @@ var dictionary_default = {
     "dolunay",
     "dolum",
     "doluluk",
+    "dolap",
+    "dolar",
+    "dolma",
+    "dolmus",
     "ama",
     "ami",
     "amen",
     "amir",
     "amil",
-    "dolmen"
+    "dolmen",
+    "namus",
+    "namuslu",
+    "ahlak",
+    "ahlaki",
+    "s\u0131k\u0131c\u0131",
+    "s\u0131kerler"
   ]
 };
 
@@ -1028,6 +1210,24 @@ function validateDictionary(data) {
   }
   return data;
 }
+function mergeDictionaries(base, ext) {
+  const existingRoots = new Set(base.entries.map((e) => e.root.toLowerCase()));
+  const mergedEntries = [...base.entries];
+  for (const entry of ext.entries) {
+    if (!existingRoots.has(entry.root.toLowerCase())) {
+      mergedEntries.push(entry);
+      existingRoots.add(entry.root.toLowerCase());
+    }
+  }
+  const mergedSuffixes = [.../* @__PURE__ */ new Set([...base.suffixes, ...ext.suffixes])];
+  const mergedWhitelist = [.../* @__PURE__ */ new Set([...base.whitelist, ...ext.whitelist])];
+  return {
+    version: base.version,
+    suffixes: mergedSuffixes,
+    entries: mergedEntries,
+    whitelist: mergedWhitelist
+  };
+}
 
 // src/lang/tr/config.ts
 var validatedData = validateDictionary(dictionary_default);
@@ -1106,21 +1306,21 @@ var dictionary_default2 = {
   entries: [
     {
       root: "fuck",
-      variants: ["fucking", "fucker", "fucked", "fuckers", "fucks", "fck", "fuk", "fuking", "fcking", "stfu", "motherfucker", "motherfucking", "fuckface", "fuckwit", "clusterfuck", "mindfuck"],
+      variants: ["fucking", "fucker", "fucked", "fuckers", "fucks", "fck", "fuk", "fuking", "fcking", "stfu", "motherfucker", "motherfucking", "fuckface", "fuckwit", "clusterfuck", "mindfuck", "fuckboy", "fucktard", "fuckhead", "wtf", "mofo"],
       severity: "high",
       category: "sexual",
       suffixable: true
     },
     {
       root: "shit",
-      variants: ["shitty", "bullshit", "shitting", "sht", "shits", "shite", "shithead", "shitstorm", "dipshit", "horseshit", "batshit", "apeshit", "shithole", "shitface", "shitshow"],
+      variants: ["shitty", "bullshit", "shitting", "sht", "shits", "shite", "shithead", "shitstorm", "dipshit", "horseshit", "batshit", "apeshit", "shithole", "shitface", "shitshow", "shitbag", "shitload", "shithouse", "shitlist"],
       severity: "high",
       category: "general",
       suffixable: true
     },
     {
       root: "ass",
-      variants: ["asses", "arse", "arses", "asshat", "asswipe", "smartass", "dumbass", "fatass", "badass", "jackass", "lardass", "kickass"],
+      variants: ["asses", "arse", "arses", "asshat", "asswipe", "smartass", "dumbass", "fatass", "badass", "jackass", "lardass", "kickass", "asscrack", "assclown"],
       severity: "medium",
       category: "insult",
       suffixable: false
@@ -1134,7 +1334,7 @@ var dictionary_default2 = {
     },
     {
       root: "bitch",
-      variants: ["bitches", "bitchy", "biatch", "bitching", "bitchass", "sonofabitch"],
+      variants: ["bitches", "bitchy", "biatch", "bitching", "bitchass", "sonofabitch", "bitchslap"],
       severity: "high",
       category: "insult",
       suffixable: true
@@ -1155,7 +1355,7 @@ var dictionary_default2 = {
     },
     {
       root: "cock",
-      variants: ["cocks", "cocksucker", "cocksucking", "cockhead"],
+      variants: ["cocks", "cocksucker", "cocksucking", "cockhead", "cockblock"],
       severity: "high",
       category: "sexual",
       suffixable: false
@@ -1264,17 +1464,113 @@ var dictionary_default2 = {
       severity: "medium",
       category: "insult",
       suffixable: false
+    },
+    {
+      root: "spic",
+      variants: ["spick", "spics", "spicks"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "kike",
+      variants: ["kikes"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "chink",
+      variants: ["chinks", "chinky"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "gook",
+      variants: ["gooks"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "tranny",
+      variants: ["trannies", "trannie"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "dyke",
+      variants: ["dykes"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "coon",
+      variants: ["coons"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "wetback",
+      variants: ["wetbacks"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "bellend",
+      variants: ["bellends"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "skank",
+      variants: ["skanks", "skanky"],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "scumbag",
+      variants: ["scumbags"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "turd",
+      variants: ["turds"],
+      severity: "low",
+      category: "general",
+      suffixable: false
+    },
+    {
+      root: "bugger",
+      variants: ["buggered", "buggering", "buggers", "buggery"],
+      severity: "medium",
+      category: "general",
+      suffixable: true
     }
   ],
   whitelist: [
     "assembly",
     "assist",
     "assassin",
+    "assassinate",
+    "assistant",
+    "assessment",
     "bass",
     "class",
     "classic",
     "classify",
+    "classroom",
     "grass",
+    "grasshopper",
     "mass",
     "massive",
     "pass",
@@ -1292,11 +1588,18 @@ var dictionary_default2 = {
     "dickens",
     "cocktail",
     "cockatoo",
+    "cockatiel",
+    "cockpit",
+    "cockroach",
+    "cockney",
     "peacock",
     "hancock",
+    "shuttlecock",
+    "woodcock",
     "scrap",
     "scrappy",
     "shitake",
+    "shiitake",
     "document",
     "buckle",
     "piston",
@@ -1308,7 +1611,13 @@ var dictionary_default2 = {
     "massage",
     "compass",
     "trespass",
-    "harass"
+    "harass",
+    "cocoon",
+    "raccoon",
+    "tycoon",
+    "dike",
+    "vandyke",
+    "scunthorpe"
   ]
 };
 
@@ -1373,7 +1682,7 @@ var dictionary_default3 = {
     },
     {
       root: "puta",
-      variants: ["putas", "putada", "puto", "putos", "hijoputa", "hijaputa", "putero", "puton", "putear"],
+      variants: ["putas", "putada", "puto", "putos", "hijoputa", "hijaputa", "putero", "puton", "putear", "putazo", "puteada"],
       severity: "high",
       category: "insult",
       suffixable: true
@@ -1394,7 +1703,7 @@ var dictionary_default3 = {
     },
     {
       root: "co\xF1o",
-      variants: ["cono", "conos", "co\xF1os"],
+      variants: ["cono", "conos", "co\xF1os", "co\xF1azo"],
       severity: "high",
       category: "sexual",
       suffixable: false
@@ -1408,7 +1717,7 @@ var dictionary_default3 = {
     },
     {
       root: "chingar",
-      variants: ["chingado", "chingada", "chingados", "chinga", "chingas", "chingo", "chingon", "chingona", "chingadera"],
+      variants: ["chingado", "chingada", "chingados", "chinga", "chingas", "chingo", "chingon", "chingona", "chingadera", "chingue", "chingues"],
       severity: "high",
       category: "general",
       suffixable: true
@@ -1485,7 +1794,7 @@ var dictionary_default3 = {
     },
     {
       root: "mamada",
-      variants: ["mamadas", "mamazo", "mamon", "mamona", "mamones"],
+      variants: ["mamadas", "mamazo", "mamon", "mamona", "mamones", "mamonazo"],
       severity: "medium",
       category: "sexual",
       suffixable: false
@@ -1496,6 +1805,76 @@ var dictionary_default3 = {
       severity: "medium",
       category: "general",
       suffixable: false
+    },
+    {
+      root: "culero",
+      variants: ["culeros", "culera", "culeras"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "cojones",
+      variants: ["cojon", "cojonudo"],
+      severity: "medium",
+      category: "sexual",
+      suffixable: false
+    },
+    {
+      root: "polla",
+      variants: ["pollas", "pollon"],
+      severity: "high",
+      category: "sexual",
+      suffixable: false
+    },
+    {
+      root: "follar",
+      variants: ["follando", "follado", "follada"],
+      severity: "high",
+      category: "sexual",
+      suffixable: true
+    },
+    {
+      root: "capullo",
+      variants: ["capullos"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "guarro",
+      variants: ["guarros", "guarra", "guarras", "guarrada"],
+      severity: "medium",
+      category: "insult",
+      suffixable: true
+    },
+    {
+      root: "boludo",
+      variants: ["boludos", "boluda", "boludez"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "pelotudo",
+      variants: ["pelotudos", "pelotuda", "pelotudez"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "hostia",
+      variants: ["hostias"],
+      severity: "medium",
+      category: "general",
+      suffixable: false
+    },
+    {
+      root: "soplapollas",
+      variants: [],
+      severity: "high",
+      category: "insult",
+      suffixable: false
     }
   ],
   whitelist: [
@@ -1513,7 +1892,13 @@ var dictionary_default3 = {
     "vehicular",
     "particular",
     "articulo",
-    "maricopa"
+    "maricopa",
+    "pollo",
+    "pollito",
+    "polleria",
+    "polluelo",
+    "folleto",
+    "follaje"
   ]
 };
 
@@ -1584,21 +1969,21 @@ var dictionary_default4 = {
   entries: [
     {
       root: "schei\xDFe",
-      variants: ["scheisse", "scheiss", "scheisser", "scheisserei", "beschissen"],
+      variants: ["scheisse", "scheiss", "scheisser", "scheisserei", "beschissen", "scheissegal"],
       severity: "high",
       category: "general",
       suffixable: true
     },
     {
       root: "fick",
-      variants: ["ficken", "ficker", "gefickt", "fickend", "fickerei", "abgefickt"],
+      variants: ["ficken", "ficker", "gefickt", "fickend", "fickerei", "abgefickt", "verfickt", "fickfehler"],
       severity: "high",
       category: "sexual",
       suffixable: true
     },
     {
       root: "arsch",
-      variants: ["arschloch", "arscher", "arschgeige", "arschgesicht", "arschkriecher"],
+      variants: ["arschloch", "arscher", "arschgeige", "arschgesicht", "arschkriecher", "arschbacke", "arschl\xF6cher", "arschlocher"],
       severity: "high",
       category: "insult",
       suffixable: true
@@ -1626,7 +2011,7 @@ var dictionary_default4 = {
     },
     {
       root: "wichser",
-      variants: ["wichsern", "wichse", "wichsen", "gewichst"],
+      variants: ["wichsern", "wichse", "wichsen", "gewichst", "wixer"],
       severity: "high",
       category: "sexual",
       suffixable: false
@@ -1640,7 +2025,7 @@ var dictionary_default4 = {
     },
     {
       root: "schlampe",
-      variants: ["schlampen", "schlampig"],
+      variants: ["schlampen", "schlampig", "schlamperei"],
       severity: "high",
       category: "insult",
       suffixable: true
@@ -1696,7 +2081,7 @@ var dictionary_default4 = {
     },
     {
       root: "dreck",
-      variants: ["dreckig", "dreckiger", "dreckiges"],
+      variants: ["dreckig", "dreckiger", "dreckiges", "drecksack", "dreckst\xFCck", "dreckstuck"],
       severity: "medium",
       category: "general",
       suffixable: true
@@ -1707,12 +2092,85 @@ var dictionary_default4 = {
       severity: "low",
       category: "insult",
       suffixable: false
+    },
+    {
+      root: "schwuchtel",
+      variants: ["schwuchteln"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "spast",
+      variants: ["spasten", "spasti"],
+      severity: "high",
+      category: "slur",
+      suffixable: false
+    },
+    {
+      root: "mistst\xFCck",
+      variants: ["miststueck"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "bastard",
+      variants: ["bastarde"],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "penner",
+      variants: ["penners"],
+      severity: "low",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "bl\xF6dmann",
+      variants: ["blodmann", "bl\xF6dm\xE4nner"],
+      severity: "low",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "vollpfosten",
+      variants: [],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "hackfresse",
+      variants: [],
+      severity: "high",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "pissnelke",
+      variants: [],
+      severity: "medium",
+      category: "insult",
+      suffixable: false
+    },
+    {
+      root: "spacken",
+      variants: [],
+      severity: "low",
+      category: "insult",
+      suffixable: false
     }
   ],
   whitelist: [
     "ficktion",
     "arschen",
-    "schwanzen"
+    "schwanzen",
+    "schwanger",
+    "schwangerschaft",
+    "geschichte"
   ]
 };
 
@@ -1930,12 +2388,17 @@ var Terlik = class _Terlik {
       leetMap: langConfig.leetMap,
       numberExpansions: langConfig.numberExpansions
     });
+    let dictData = langConfig.dictionary;
+    if (options?.extendDictionary) {
+      validateDictionary(options.extendDictionary);
+      dictData = mergeDictionaries(dictData, options.extendDictionary);
+    }
     this.dictionary = new Dictionary(
-      langConfig.dictionary,
+      dictData,
       options?.customList,
       options?.whitelist
     );
-    const hasCustomDict = !!(options?.customList?.length || options?.whitelist?.length);
+    const hasCustomDict = !!(options?.customList?.length || options?.whitelist?.length || options?.extendDictionary);
     this.detector = new Detector(
       this.dictionary,
       normalizeFn,