@delali/narsil 0.1.14 → 0.2.0

package/dist/languages/german.mjs

@@ -1,176 +1,440 @@
-// src/languages/german.ts
-var VOWELS = "aeiouy\xE4\xF6\xFC";
-function isVowel(ch) {
-  return VOWELS.includes(ch);
-}
-function findRegions(word) {
-  let r1 = word.length;
-  let r2 = word.length;
-  let i = 1;
-  while (i < word.length) {
-    if (!isVowel(word[i]) && isVowel(word[i - 1])) {
-      r1 = i + 1;
-      break;
-    }
-    i++;
-  }
-  if (r1 < 3) r1 = 3;
-  i = r1;
-  while (i < word.length) {
-    if (!isVowel(word[i]) && i > 0 && isVowel(word[i - 1])) {
-      r2 = i + 1;
-      break;
-    }
-    i++;
-  }
-  return { r1, r2 };
-}
-function markConsonantUY(word) {
-  const chars = word.split("");
-  for (let i = 1; i < chars.length - 1; i++) {
-    if (chars[i] === "u" && isVowel(chars[i - 1]) && isVowel(chars[i + 1])) {
-      chars[i] = "U";
+import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
+import { BaseStemmer } from '../chunk-U2BKYEC7.mjs';
+
+// src/languages/snowball/german.ts
+var a_0 = [
+  ["", 5],
+  ["ae", 2, 1],
+  ["oe", 3, 2],
+  ["qu", -1, 3],
+  ["ue", 4, 4],
+  ["\xDF", 1, 5]
+];
+var a_1 = [
+  ["", 5],
+  ["U", 2, 1],
+  ["Y", 1, 2],
+  ["\xE4", 3, 3],
+  ["\xF6", 4, 4],
+  ["\xFC", 2, 5]
+];
+var a_2 = [
+  ["e", 3],
+  ["em", 1],
+  ["en", 3],
+  ["erinnen", 2, 1],
+  ["erin", 2],
+  ["ln", 5],
+  ["ern", 2],
+  ["er", 2],
+  ["s", 4],
+  ["es", 3, 1],
+  ["lns", 5, 2]
+];
+var a_3 = [
+  ["tick", -1],
+  ["plan", -1],
+  ["geordn", -1],
+  ["intern", -1],
+  ["tr", -1]
+];
+var a_4 = [
+  ["en", 1],
+  ["er", 1],
+  ["et", 3],
+  ["st", 2],
+  ["est", 1, 1]
+];
+var a_5 = [
+  ["ig", 1],
+  ["lich", 1]
+];
+var a_6 = [
+  ["end", 1],
+  ["ig", 2],
+  ["ung", 1],
+  ["lich", 3],
+  ["isch", 2],
+  ["ik", 2],
+  ["heit", 3],
+  ["keit", 4]
+];
+var a_7 = [
+  ["'", 1],
+  ["'sch", 1],
+  ["'s", 1]
+];
+var g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32, 8];
+var g_et_ending = [1, 128, 198, 227, 32, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128];
+var g_s_ending = [117, 30, 5];
+var g_st_ending = [117, 30, 4];
+var GermanStemmer = class extends BaseStemmer {
+  #stem() {
+    let a;
+    let I_x;
+    let I_p2;
+    let I_p1;
+    const v_1 = this.c;
+    {
+      const v_2 = this.c;
+      while (true) {
+        const v_3 = this.c;
+        lab1: {
+          while (true) {
+            const v_4 = this.c;
+            lab3: {
+              if (!this.in_grouping(g_v, 97, 252)) break lab3;
+              this.bra = this.c;
+              lab4: {
+                const v_5 = this.c;
+                lab5: {
+                  if (!this.eq_s("u")) break lab5;
+                  this.ket = this.c;
+                  if (!this.in_grouping(g_v, 97, 252)) break lab5;
+                  this.slice_from("U");
+                  break lab4;
+                }
+                this.c = v_5;
+                if (!this.eq_s("y")) break lab3;
+                this.ket = this.c;
+                if (!this.in_grouping(g_v, 97, 252)) break lab3;
+                this.slice_from("Y");
+              }
+              this.c = v_4;
+              break;
+            }
+            this.c = v_4;
+            if (this.c >= this.limit) break lab1;
+            this.c++;
+          }
+          continue;
+        }
+        this.c = v_3;
+        break;
+      }
+      this.c = v_2;
+      while (true) {
+        const v_6 = this.c;
+        lab6: {
+          this.bra = this.c;
+          a = this.find_among(a_0);
+          this.ket = this.c;
+          switch (a) {
+            case 1: {
+              this.slice_from("ss");
+              break;
+            }
+            case 2: {
+              this.slice_from("\xE4");
+              break;
+            }
+            case 3: {
+              this.slice_from("\xF6");
+              break;
+            }
+            case 4: {
+              this.slice_from("\xFC");
+              break;
+            }
+            case 5: {
+              if (this.c >= this.limit) break lab6;
+              this.c++;
+              break;
+            }
+          }
+          continue;
+        }
+        this.c = v_6;
+        break;
+      }
     }
-    if (chars[i] === "y" && isVowel(chars[i - 1]) && isVowel(chars[i + 1])) {
-      chars[i] = "Y";
+    this.c = v_1;
+    const v_7 = this.c;
+    lab7: {
+      I_p1 = this.limit;
+      I_p2 = this.limit;
+      const v_8 = this.c;
+      if (this.c + 3 > this.limit) break lab7;
+      this.c += 3;
+      I_x = this.c;
+      this.c = v_8;
+      if (!this.go_out_grouping(g_v, 97, 252)) break lab7;
+      this.c++;
+      if (!this.go_in_grouping(g_v, 97, 252)) break lab7;
+      this.c++;
+      I_p1 = this.c;
+      lab8: {
+        if (
+          /**@type {boolean}*/
+          I_p1 >= I_x
+        ) break lab8;
+        I_p1 = I_x;
+      }
+      if (!this.go_out_grouping(g_v, 97, 252)) break lab7;
+      this.c++;
+      if (!this.go_in_grouping(g_v, 97, 252)) break lab7;
+      this.c++;
+      I_p2 = this.c;
     }
-  }
-  return chars.join("");
-}
-var S_ENDING_VALID = "bdfghklmnrt";
-function isValidSEnding(word, beforeSuffix) {
-  if (beforeSuffix <= 0) return false;
-  return S_ENDING_VALID.includes(word[beforeSuffix - 1]);
-}
-var ST_ENDING_VALID = "bdfghklmnt";
-var STEP1_SUFFIXES = ["em", "ern", "er", "en", "es", "e", "s"];
-var STEP2_SUFFIXES = ["est", "en", "er", "st"];
-var RE_ESZETT = /ß/g;
-var RE_UPPER_Y = /Y/g;
-var RE_UPPER_U = /U/g;
-var RE_UMLAUT_A = /ä/g;
-var RE_UMLAUT_O = /ö/g;
-var RE_UMLAUT_U = /ü/g;
-function isValidStEnding(word, beforeSuffix) {
-  if (beforeSuffix <= 0) return false;
-  return ST_ENDING_VALID.includes(word[beforeSuffix - 1]);
-}
-function step1(word, r1) {
-  for (const suffix of STEP1_SUFFIXES) {
-    if (word.endsWith(suffix) && word.length - suffix.length >= r1) {
-      if (suffix === "s") {
-        const cutPos = word.length - 1;
-        if (isValidSEnding(word, cutPos)) {
-          return word.slice(0, cutPos);
+    this.c = v_7;
+    this.limit_backward = this.c;
+    this.c = this.limit;
+    {
+      const v_9 = this.limit - this.c;
+      lab10: {
+        this.ket = this.c;
+        a = this.find_among_b(a_2);
+        if (a === 0) break lab10;
+        this.bra = this.c;
+        if (
+          /**@type {boolean}*/
+          I_p1 > this.c
+        ) break lab10;
+        switch (a) {
+          case 1: {
+            lab11: {
+              if (!this.eq_s_b("syst")) break lab11;
+              break lab10;
+            }
+            this.slice_del();
+            break;
+          }
+          case 2: {
+            this.slice_del();
+            break;
+          }
+          case 3: {
+            this.slice_del();
+            const v_10 = this.limit - this.c;
+            lab12: {
+              this.ket = this.c;
+              if (!this.eq_s_b("s")) {
+                this.c = this.limit - v_10;
+                break lab12;
+              }
+              this.bra = this.c;
+              if (!this.eq_s_b("nis")) {
+                this.c = this.limit - v_10;
+                break lab12;
+              }
+              this.slice_del();
+            }
+            break;
+          }
+          case 4: {
+            if (!this.in_grouping_b(g_s_ending, 98, 116)) break lab10;
+            this.slice_del();
+            break;
+          }
+          case 5: {
+            this.slice_from("l");
+            break;
+          }
         }
-        return word;
       }
-      const stripped = word.slice(0, word.length - suffix.length);
-      if (suffix === "en" || suffix === "e" || suffix === "es") {
-        if (stripped.endsWith("niss")) {
-          return stripped.slice(0, -1);
+      this.c = this.limit - v_9;
+      const v_11 = this.limit - this.c;
+      lab13: {
+        this.ket = this.c;
+        a = this.find_among_b(a_4);
+        if (a === 0) break lab13;
+        this.bra = this.c;
+        if (
+          /**@type {boolean}*/
+          I_p1 > this.c
+        ) break lab13;
+        switch (a) {
+          case 1: {
+            this.slice_del();
+            break;
+          }
+          case 2: {
+            if (!this.in_grouping_b(g_st_ending, 98, 116)) break lab13;
+            if (this.c - 3 < this.limit_backward) break lab13;
+            this.c -= 3;
+            this.slice_del();
+            break;
+          }
+          case 3: {
+            const v_12 = this.limit - this.c;
+            if (!this.in_grouping_b(g_et_ending, 85, 228)) break lab13;
+            this.c = this.limit - v_12;
+            {
+              const v_13 = this.limit - this.c;
+              lab14: {
+                if (this.find_among_b(a_3) === 0) break lab14;
+                break lab13;
+              }
+              this.c = this.limit - v_13;
+            }
+            this.slice_del();
+            break;
+          }
         }
       }
-      return stripped;
-    }
-  }
-  return word;
-}
-function step2(word, r1) {
-  for (const suffix of STEP2_SUFFIXES) {
-    if (word.endsWith(suffix) && word.length - suffix.length >= r1) {
-      if (suffix === "st") {
-        const cutPos = word.length - 2;
-        if (cutPos >= 3 && isValidStEnding(word, cutPos)) {
-          return word.slice(0, cutPos);
+      this.c = this.limit - v_11;
+      const v_14 = this.limit - this.c;
+      lab15: {
+        this.ket = this.c;
+        a = this.find_among_b(a_6);
+        if (a === 0) break lab15;
+        this.bra = this.c;
+        if (
+          /**@type {boolean}*/
+          I_p2 > this.c
+        ) break lab15;
+        switch (a) {
+          case 1: {
+            this.slice_del();
+            const v_15 = this.limit - this.c;
+            lab16: {
+              this.ket = this.c;
+              if (!this.eq_s_b("ig")) {
+                this.c = this.limit - v_15;
+                break lab16;
+              }
+              this.bra = this.c;
+              lab17: {
+                if (!this.eq_s_b("e")) break lab17;
+                this.c = this.limit - v_15;
+                break lab16;
+              }
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) {
+                this.c = this.limit - v_15;
+                break lab16;
+              }
+              this.slice_del();
+            }
+            break;
+          }
+          case 2: {
+            lab18: {
+              if (!this.eq_s_b("e")) break lab18;
+              break lab15;
+            }
+            this.slice_del();
+            break;
+          }
+          case 3: {
+            this.slice_del();
+            const v_16 = this.limit - this.c;
+            lab19: {
+              this.ket = this.c;
+              lab20: {
+                lab21: {
+                  if (!this.eq_s_b("er")) break lab21;
+                  break lab20;
+                }
+                if (!this.eq_s_b("en")) {
+                  this.c = this.limit - v_16;
+                  break lab19;
+                }
+              }
+              this.bra = this.c;
+              if (
+                /**@type {boolean}*/
+                I_p1 > this.c
+              ) {
+                this.c = this.limit - v_16;
+                break lab19;
+              }
+              this.slice_del();
+            }
+            break;
+          }
+          case 4: {
+            this.slice_del();
+            const v_17 = this.limit - this.c;
+            lab22: {
+              this.ket = this.c;
+              if (this.find_among_b(a_5) === 0) {
+                this.c = this.limit - v_17;
+                break lab22;
+              }
+              this.bra = this.c;
+              if (
+                /**@type {boolean}*/
+                I_p2 > this.c
+              ) {
+                this.c = this.limit - v_17;
+                break lab22;
+              }
+              this.slice_del();
+            }
+            break;
+          }
         }
-        return word;
       }
-      return word.slice(0, word.length - suffix.length);
-    }
-  }
-  return word;
-}
-function step3(word, r1, r2) {
-  if (word.endsWith("keit") && word.length - 4 >= r2) {
-    word = word.slice(0, -4);
-    if (word.endsWith("lich") && word.length - 4 >= r2) {
-      return word.slice(0, -4);
-    }
-    if (word.endsWith("ig") && word.length - 2 >= r2) {
-      return word.slice(0, -2);
-    }
-    return word;
-  }
-  if (word.endsWith("heit") && word.length - 4 >= r2) {
-    word = word.slice(0, -4);
-    if (word.endsWith("er") && word.length - 2 >= r1) {
-      return word.slice(0, -2);
-    }
-    if (word.endsWith("en") && word.length - 2 >= r1) {
-      return word.slice(0, -2);
-    }
-    return word;
-  }
-  if (word.endsWith("isch") && word.length - 4 >= r2) {
-    if (!word.endsWith("eisch")) {
-      return word.slice(0, -4);
-    }
-    return word;
-  }
-  if (word.endsWith("lich") && word.length - 4 >= r2) {
-    word = word.slice(0, -4);
-    if (word.endsWith("er") && word.length - 2 >= r1) {
-      return word.slice(0, -2);
-    }
-    if (word.endsWith("en") && word.length - 2 >= r1) {
-      return word.slice(0, -2);
-    }
-    return word;
-  }
-  if (word.endsWith("end") && word.length - 3 >= r2) {
-    word = word.slice(0, -3);
-    if (word.endsWith("ig") && word.length - 2 >= r2 && !word.endsWith("eig")) {
-      return word.slice(0, -2);
-    }
-    return word;
-  }
-  if (word.endsWith("ung") && word.length - 3 >= r2) {
-    word = word.slice(0, -3);
-    if (word.endsWith("ig") && word.length - 2 >= r2 && !word.endsWith("eig")) {
-      return word.slice(0, -2);
+      this.c = this.limit - v_14;
+      const v_18 = this.limit - this.c;
+      lab23: {
+        this.ket = this.c;
+        if (this.find_among_b(a_7) === 0) break lab23;
+        this.bra = this.c;
+        if (this.c <= this.limit_backward) break lab23;
+        this.c--;
+        if (
+          /**@type {boolean}*/
+          this.c <= this.limit_backward
+        ) break lab23;
+        this.slice_del();
+      }
+      this.c = this.limit - v_18;
     }
-    return word;
-  }
-  if (word.endsWith("ig") && word.length - 2 >= r2) {
-    if (!word.endsWith("eig")) {
-      return word.slice(0, -2);
+    this.c = this.limit_backward;
+    const v_19 = this.c;
+    while (true) {
+      const v_20 = this.c;
+      lab25: {
+        this.bra = this.c;
+        a = this.find_among(a_1);
+        this.ket = this.c;
+        switch (a) {
+          case 1: {
+            this.slice_from("y");
+            break;
+          }
+          case 2: {
+            this.slice_from("u");
+            break;
+          }
+          case 3: {
+            this.slice_from("a");
+            break;
+          }
+          case 4: {
+            this.slice_from("o");
+            break;
+          }
+          case 5: {
+            if (this.c >= this.limit) break lab25;
+            this.c++;
+            break;
+          }
+        }
+        continue;
+      }
+      this.c = v_20;
+      break;
     }
-    return word;
+    this.c = v_19;
+    return true;
   }
-  if (word.endsWith("ik") && word.length - 2 >= r2) {
-    if (!word.endsWith("eik")) {
-      return word.slice(0, -2);
-    }
-    return word;
+  stem(input) {
+    this.setCurrent(input);
+    this.#stem();
+    return this.getCurrent();
   }
-  return word;
-}
-function restoreLowercase(word) {
-  return word.replace(RE_UPPER_Y, "y").replace(RE_UPPER_U, "u").replace(RE_UMLAUT_A, "a").replace(RE_UMLAUT_O, "o").replace(RE_UMLAUT_U, "u");
-}
-function stem(word) {
-  if (word.length < 3) return word;
-  word = word.toLowerCase();
-  word = word.replace(RE_ESZETT, "ss");
-  word = markConsonantUY(word);
-  const { r1, r2 } = findRegions(word);
-  word = step1(word, r1);
-  word = step2(word, r1);
-  word = step3(word, r1, r2);
-  word = restoreLowercase(word);
-  return word;
+};
+var shared = new GermanStemmer();
+function stem(token) {
+  return shared.stem(token);
 }
+
+// src/languages/german.ts
 var stopWords = /* @__PURE__ */ new Set([
   "aber",
   "alle",
@@ -404,11 +668,17 @@ var stopWords = /* @__PURE__ */ new Set([
   "zwar",
   "zwischen"
 ]);
+var SHARP_S = /\u00DF/g;
+function normalize(token) {
+  return token.replace(SHARP_S, "ss");
+}
 var german = {
   name: "german",
+  revision: "ff10b0dd9feeb7cb",
   stemmer: stem,
-  stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9äöüß]+/gi }
+  stopWords: withNormalisedSpellings(stopWords, normalize),
+  normalizer: normalize,
+  tokenizer: { splitPattern: /[^a-z0-9äöüßé]+/gi }
 };
 
 export { german };

package/dist/languages/greek.d.ts

@@ -1,4 +1,4 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-CmJBHf1j.js';
 
 declare const greek: LanguageModule;