@lokascript/semantic 1.2.1 → 2.0.0

package/dist/languages/qu.d.ts

@@ -1,47 +1,9 @@
-import { B as BaseTokenizer, T as TokenStream, a as TokenKind, L as LanguageProfile } from '../types-BY3Id07j.js';
-
 /**
- * Quechua Tokenizer
+ * Quechua Language Module
  *
- * Tokenizes Quechua (Runasimi) hyperscript input.
- * Quechua characteristics:
- * - SOV word order
- * - Agglutinative/polysynthetic morphology
- * - Postpositions (suffixes)
- * - Case suffixes: -ta (accusative), -man (allative), -manta (ablative), etc.
- * - Evidential markers
+ * Self-registering module for Quechua language support.
+ * Importing this module registers Quechua tokenizer and profile.
  */
-
-declare class QuechuaTokenizer extends BaseTokenizer {
-    readonly language = "qu";
-    readonly direction: "ltr";
-    constructor();
-    tokenize(input: string): TokenStream;
-    classifyToken(token: string): TokenKind;
-    private trySuffix;
-    /**
-     * Split a selector token if it has a Quechua suffix attached.
-     * E.g., ".openta" -> [".open", "-ta"]
-     * Returns array with 1 token (no suffix) or 2 tokens (selector + suffix)
-     */
-    private splitSelectorSuffix;
-    /**
-     * Try to match multi-word keywords that should be treated as a single unit.
-     * E.g., "mana qhawachiy" (not focus = blur)
-     */
-    private tryMultiWordKeyword;
-    private extractWord;
-    private extractNumber;
-}
-declare const quechuaTokenizer: QuechuaTokenizer;
-
-/**
- * Quechua Language Profile
- *
- * SOV word order, postpositions (suffixes), polysynthetic/agglutinative.
- * Indigenous language of the Andean region with rich morphology.
- */
-
-declare const quechuaProfile: LanguageProfile;
-
-export { quechuaProfile, quechuaTokenizer };
+export { quechuaTokenizer } from '../tokenizers/quechua';
+export { quechuaProfile } from '../generators/profiles/quechua';
+//# sourceMappingURL=qu.d.ts.map

package/dist/languages/qu.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"qu.d.ts","sourceRoot":"","sources":["../../src/languages/qu.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAMH,OAAO,EAAE,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AACzD,OAAO,EAAE,cAAc,EAAE,MAAM,gCAAgC,CAAC"}

package/dist/languages/qu.js

@@ -8,7 +8,7 @@ function registerLanguage(code, tokenizer, profile) {
   patternCache.delete(code);
 }
 
-// src/tokenizers/base.ts
+// src/tokenizers/token-utils.ts
 var TokenStreamImpl = class {
   constructor(tokens, language) {
     this.pos = 0;
@@ -74,17 +74,14 @@ function createToken(value, kind, position, normalizedOrOptions) {
   }
   if (normalizedOrOptions) {
     const { normalized, stem, stemConfidence } = normalizedOrOptions;
-    const token = { value, kind, position };
-    if (normalized !== void 0) {
-      token.normalized = normalized;
-    }
-    if (stem !== void 0) {
-      token.stem = stem;
-      if (stemConfidence !== void 0) {
-        token.stemConfidence = stemConfidence;
-      }
-    }
-    return token;
+    return {
+      value,
+      kind,
+      position,
+      ...normalized !== void 0 && { normalized },
+      ...stem !== void 0 && { stem },
+      ...stemConfidence !== void 0 && { stemConfidence }
+    };
   }
   return { value, kind, position };
 }
@@ -106,11 +103,15 @@ function isAsciiLetter(char) {
 function isAsciiIdentifierChar(char) {
   return /[a-zA-Z0-9_-]/.test(char);
 }
+
+// src/tokenizers/char-classifiers.ts
 function createLatinCharClassifiers(letterPattern) {
   const isLetter = (char) => letterPattern.test(char);
   const isIdentifierChar = (char) => isLetter(char) || /[0-9_-]/.test(char);
   return { isLetter, isIdentifierChar };
 }
+
+// src/tokenizers/extractors.ts
 function extractCssSelector(input, startPos) {
   if (startPos >= input.length) return null;
   const char = input[startPos];
@@ -368,6 +369,8 @@ function extractNumber(input, startPos) {
   }
   return number;
 }
+
+// src/tokenizers/base-tokenizer.ts
 var _BaseTokenizer = class _BaseTokenizer {
   constructor() {
     /** Keywords derived from profile, sorted longest-first for greedy matching */
@@ -375,6 +378,34 @@ var _BaseTokenizer = class _BaseTokenizer {
     /** Map for O(1) keyword lookups by lowercase native word */
     this.profileKeywordMap = /* @__PURE__ */ new Map();
   }
+  /**
+   * Check if current position is a property access (obj.prop) vs CSS selector (.active).
+   * Property access: no whitespace before '.', previous token is identifier/keyword/selector.
+   * Also detects standalone method calls: .identifier( pattern.
+   *
+   * Returns true if '.' was emitted as an operator token and pos should advance by 1.
+   * Returns false if this is a CSS selector and should be handled by trySelector().
+   */
+  tryPropertyAccess(input, pos, tokens) {
+    if (input[pos] !== ".") return false;
+    const lastToken = tokens[tokens.length - 1];
+    const hasWhitespaceBefore = lastToken && lastToken.position.end < pos;
+    const isPropertyAccess = lastToken && !hasWhitespaceBefore && (lastToken.kind === "identifier" || lastToken.kind === "keyword" || lastToken.kind === "selector");
+    if (isPropertyAccess) {
+      tokens.push(createToken(".", "operator", createPosition(pos, pos + 1)));
+      return true;
+    }
+    const methodStart = pos + 1;
+    let methodEnd = methodStart;
+    while (methodEnd < input.length && isAsciiIdentifierChar(input[methodEnd])) {
+      methodEnd++;
+    }
+    if (methodEnd < input.length && input[methodEnd] === "(") {
+      tokens.push(createToken(".", "operator", createPosition(pos, pos + 1)));
+      return true;
+    }
+    return false;
+  }
   /**
    * Initialize keyword mappings from a language profile.
    * Builds a list of native→english mappings from:
@@ -410,6 +441,11 @@ var _BaseTokenizer = class _BaseTokenizer {
       for (const [normalized, native] of Object.entries(profile.references)) {
         keywordMap.set(native, { native, normalized });
       }
+      for (const canonical of Object.keys(profile.references)) {
+        if (!keywordMap.has(canonical)) {
+          keywordMap.set(canonical, { native: canonical, normalized: canonical });
+        }
+      }
     }
     if (profile.roleMarkers) {
       for (const [role, marker] of Object.entries(profile.roleMarkers)) {
@@ -819,24 +855,28 @@ var quechuaProfile = {
     }
   },
   roleMarkers: {
-    patient: { primary: "-ta", position: "after" },
-    destination: { primary: "-man", position: "after" },
-    source: { primary: "-manta", position: "after" },
-    style: { primary: "-wan", position: "after" },
-    event: { primary: "-ta", position: "after" }
-    // Event as accusative
+    patient: { primary: "ta", position: "after" },
+    destination: { primary: "man", alternatives: ["pa"], position: "after" },
+    source: { primary: "manta", position: "after" },
+    style: { primary: "wan", position: "after" },
+    event: { primary: "pi", position: "after" }
+    // Locative: event occurs "at" (pi)
   },
   keywords: {
     toggle: { primary: "t'ikray", alternatives: ["tikray", "kutichiy"], normalized: "toggle" },
     add: { primary: "yapay", alternatives: ["yapaykuy"], normalized: "add" },
     remove: { primary: "qichuy", alternatives: ["hurquy", "anchuchiy"], normalized: "remove" },
     put: { primary: "churay", alternatives: ["tiyachiy"], normalized: "put" },
-    append: { primary: "qatichiy", normalized: "append" },
+    append: { primary: "qatichiy", alternatives: ["qhipaman_yapay"], normalized: "append" },
     prepend: { primary: "\xF1awpachiy", normalized: "prepend" },
     take: { primary: "hapiy", normalized: "take" },
     make: { primary: "ruray", alternatives: ["kamay"], normalized: "make" },
     clone: { primary: "kikinchay", alternatives: ["qillqay"], normalized: "clone" },
-    swap: { primary: "t'inkuy", alternatives: ["rantikunakuy"], normalized: "swap" },
+    swap: {
+      primary: "t'inkuy",
+      alternatives: ["rantikunakuy", "rantin_tikray"],
+      normalized: "swap"
+    },
     morph: { primary: "tikray", alternatives: ["kutichiy"], normalized: "morph" },
     set: { primary: "churay", alternatives: ["kamaykuy"], normalized: "set" },
     get: { primary: "taripay", normalized: "get" },
@@ -847,10 +887,10 @@ var quechuaProfile = {
     hide: { primary: "pakay", alternatives: ["pakakuy"], normalized: "hide" },
     transition: { primary: "tikray", alternatives: ["kuyuchiy"], normalized: "transition" },
     on: { primary: "chaypim", alternatives: ["kaypi"], normalized: "on" },
-    trigger: { primary: "qallarichiy", normalized: "trigger" },
+    trigger: { primary: "qallarichiy", alternatives: ["kichay"], normalized: "trigger" },
     send: { primary: "kachay", alternatives: ["apachiy"], normalized: "send" },
-    focus: { primary: "qhawachiy", normalized: "focus" },
-    blur: { primary: "mana qhawachiy", normalized: "blur" },
+    focus: { primary: "qhawachiy", alternatives: ["qhaway"], normalized: "focus" },
+    blur: { primary: "paqariy", alternatives: ["mana qhawachiy"], normalized: "blur" },
     go: { primary: "riy", alternatives: ["puriy"], normalized: "go" },
     wait: { primary: "suyay", normalized: "wait" },
     fetch: { primary: "apamuy", alternatives: ["taripakaramuy"], normalized: "fetch" },
@@ -865,7 +905,7 @@ var quechuaProfile = {
     continue: { primary: "qatipay", normalized: "continue" },
     halt: { primary: "sayay", alternatives: ["tukuy"], normalized: "halt" },
     throw: { primary: "chanqay", normalized: "throw" },
-    call: { primary: "waqyay", normalized: "call" },
+    call: { primary: "waqyay", alternatives: ["qayay"], normalized: "call" },
     return: { primary: "kutichiy", alternatives: ["kutimuy"], normalized: "return" },
     then: { primary: "chaymantataq", alternatives: ["hinaspa", "chaymanta"], normalized: "then" },
     and: { primary: "hinallataq", alternatives: ["ima", "chaymantawan"], normalized: "and" },
@@ -878,13 +918,31 @@ var quechuaProfile = {
     behavior: { primary: "ruwana", normalized: "behavior" },
     install: { primary: "churay", normalized: "install" },
     measure: { primary: "tupuy", normalized: "measure" },
+    beep: { primary: "waqay", normalized: "beep" },
+    break: { primary: "p'akiy", normalized: "break" },
+    copy: { primary: "qillqay", normalized: "copy" },
+    exit: { primary: "lluqsiy", normalized: "exit" },
+    pick: { primary: "akllay", normalized: "pick" },
+    render: { primary: "rikuchiy", normalized: "render" },
     into: { primary: "ukuman", normalized: "into" },
     before: { primary: "\xF1awpaq", normalized: "before" },
     after: { primary: "qhipa", normalized: "after" },
     // Event modifiers (for repeat until event)
-    until: { primary: "-kama", alternatives: ["kama"], normalized: "until" },
+    until: { primary: "kama", alternatives: ["-kama"], normalized: "until" },
     event: { primary: "ruwakuq", alternatives: ["imayna"], normalized: "event" },
-    from: { primary: "-manta", normalized: "from" }
+    from: { primary: "manta", alternatives: ["-manta"], normalized: "from" },
+    // Common event names (for event handler pattern matching)
+    click: { primary: "\xF1itiy", normalized: "click" },
+    load: { primary: "apakuy", normalized: "load" },
+    submit: { primary: "kachay", normalized: "submit" },
+    hover: { primary: "hawachiy", normalized: "hover" },
+    input: { primary: "yaykuchiy", normalized: "input" },
+    change: { primary: "tikray", normalized: "change" }
+  },
+  eventHandler: {
+    keyword: { primary: "pi", alternatives: ["kaqtin"] },
+    sourceMarker: { primary: "manta", position: "after" },
+    eventMarker: { primary: "pi", alternatives: ["kaqtin", "kaqpi"], position: "after" }
   }
 };
 
@@ -907,8 +965,18 @@ var SUFFIXES = /* @__PURE__ */ new Set([
   // limitative (until, up to)
   "-rayku",
   // causative (because of)
-  "-hina"
+  "-hina",
   // simulative (like, as)
+  // Standalone (unhyphenated) forms — used when written as separate words
+  "ta",
+  "man",
+  "manta",
+  "pi",
+  "wan",
+  "paq",
+  "kama",
+  "hina",
+  "pa"
 ]);
 var QUECHUA_EXTRAS = [
   // Values/Literals
@@ -925,6 +993,7 @@ var QUECHUA_EXTRAS = [
   { native: "qhipa", normalized: "last" },
   { native: "hamuq", normalized: "next" },
   { native: "\xF1awpaq kaq", normalized: "previous" },
+  { native: "\xF1awpaq_kaq", normalized: "previous" },
   { native: "aswan qayllaqa", normalized: "closest" },
   { native: "tayta", normalized: "parent" },
   // Events
@@ -1001,6 +1070,10 @@ var QuechuaTokenizer = class extends BaseTokenizer {
           pos = modifierToken.position.end;
           continue;
         }
+        if (this.tryPropertyAccess(input, pos, tokens)) {
+          pos++;
+          continue;
+        }
         const selectorToken = this.trySelector(input, pos);
         if (selectorToken) {
           const selectorWithSuffix = this.splitSelectorSuffix(selectorToken);
@@ -1081,7 +1154,8 @@ var QuechuaTokenizer = class extends BaseTokenizer {
     const lower = token.toLowerCase();
     if (SUFFIXES.has(lower)) return "particle";
     if (this.isKeyword(lower)) return "keyword";
-    if (token.startsWith("#") || token.startsWith(".") || token.startsWith("[")) return "selector";
+    if (token.startsWith("#") || token.startsWith(".") || token.startsWith("[") || token.startsWith("*") || token.startsWith("<"))
+      return "selector";
     if (token.startsWith('"') || token.startsWith("'")) return "literal";
     if (/^\d/.test(token)) return "literal";
     return "identifier";
@@ -1167,6 +1241,9 @@ var QuechuaTokenizer = class extends BaseTokenizer {
     }
     if (!word) return null;
     const lower = word.toLowerCase();
+    if (SUFFIXES.has(lower)) {
+      return createToken(word, "particle", createPosition(startPos, pos));
+    }
     const keywordEntry = this.lookupKeyword(lower);
     if (keywordEntry) {
       return createToken(word, "keyword", createPosition(startPos, pos), keywordEntry.normalized);