@bhanquier/template-core 0.1.1

package/dist/index.cjs

@@ -0,0 +1,160 @@
+"use strict";
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+
+// src/index.ts
+var index_exports = {};
+__export(index_exports, {
+  computeRequiredCoverage: () => computeRequiredCoverage,
+  lexicalSimilarityScore: () => lexicalSimilarityScore,
+  mergeTokens: () => mergeTokens,
+  normalizeFreeText: () => normalizeFreeText,
+  normalizeTokenValue: () => normalizeTokenValue,
+  suggestFieldByLexicalRules: () => suggestFieldByLexicalRules,
+  tokenKey: () => tokenKey,
+  tokenize: () => tokenize
+});
+module.exports = __toCommonJS(index_exports);
+
+// src/token-normalization.ts
+function normalizeTokenValue(value) {
+  return value.trim().replace(/\s+/g, " ");
+}
+function tokenKey(syntax, rawToken) {
+  return `${syntax}:${normalizeTokenValue(rawToken)}`;
+}
+function mergeTokens(tokens) {
+  const merged = /* @__PURE__ */ new Map();
+  for (const token of tokens) {
+    const key = tokenKey(token.syntax, token.rawToken);
+    const existing = merged.get(key);
+    if (existing) {
+      existing.occurrences += token.occurrences;
+    } else {
+      merged.set(key, {
+        ...token,
+        rawToken: normalizeTokenValue(token.rawToken)
+      });
+    }
+  }
+  return [...merged.values()].sort((a, b) => {
+    if (b.occurrences !== a.occurrences) return b.occurrences - a.occurrences;
+    return tokenKey(a.syntax, a.rawToken).localeCompare(tokenKey(b.syntax, b.rawToken));
+  });
+}
+
+// src/mapping-progress.ts
+function computeRequiredCoverage(mappings, requiredFieldNames) {
+  const mappedFields = new Set(
+    mappings.filter((m) => m.status !== "ignored" && m.mappedField).map((m) => m.mappedField)
+  );
+  const missingRequired = requiredFieldNames.filter((name) => !mappedFields.has(name));
+  const requiredMapped = requiredFieldNames.length - missingRequired.length;
+  const requiredTotal = requiredFieldNames.length;
+  const coverageScore = requiredTotal > 0 ? Math.round(requiredMapped / requiredTotal * 100) : 100;
+  return {
+    requiredTotal,
+    requiredMapped,
+    coverageScore,
+    missingRequired,
+    complete: missingRequired.length === 0
+  };
+}
+
+// src/lexical.ts
+function normalizeFreeText(value) {
+  return value.normalize("NFD").replace(/[\u0300-\u036f]/g, "").toLowerCase().replace(/[^a-z0-9]+/g, " ").trim();
+}
+function tokenize(value) {
+  return value.split(" ").map((token) => token.trim()).filter((token) => token.length >= 2);
+}
+function lexicalSimilarityScore(normalizedRaw, rawTokens, normalizedCandidate, canonicalize) {
+  if (!normalizedCandidate) return 0;
+  if (normalizedRaw === normalizedCandidate) return 0.98;
+  if (canonicalize && canonicalize(normalizedRaw) === canonicalize(normalizedCandidate)) return 0.97;
+  if (normalizedCandidate.includes(normalizedRaw) || normalizedRaw.includes(normalizedCandidate)) {
+    return 0.75;
+  }
+  const candidateTokens = new Set(tokenize(normalizedCandidate));
+  const intersection = new Set(Array.from(rawTokens).filter((t) => candidateTokens.has(t))).size;
+  const union = (/* @__PURE__ */ new Set([...rawTokens, ...candidateTokens])).size;
+  if (union === 0) return 0;
+  return intersection / union;
+}
+
+// src/suggestion.ts
+function suggestFieldByLexicalRules(input) {
+  const exact = input.resolveExactField(input.rawToken);
+  if (exact) {
+    return {
+      field: exact,
+      confidence: 1,
+      reason: "Correspondance exacte"
+    };
+  }
+  const normalizedText = normalizeFreeText(input.rawToken);
+  if (!normalizedText) {
+    return { field: null, confidence: null, reason: null };
+  }
+  for (const rule of input.keywordRules) {
+    if (rule.pattern.test(normalizedText)) {
+      return { field: rule.field, confidence: rule.confidence, reason: rule.reason };
+    }
+  }
+  const rawTokens = new Set(tokenize(normalizedText));
+  let bestField = null;
+  let bestScore = 0;
+  for (const field of input.candidateFields) {
+    const candidates = [field.name, field.label ?? "", ...field.aliases ?? []];
+    const candidateScore = candidates.reduce((best, candidate) => {
+      const normalizedCandidate = normalizeFreeText(candidate);
+      const score = lexicalSimilarityScore(
+        normalizedText,
+        rawTokens,
+        normalizedCandidate,
+        input.canonicalizeFieldName
+      );
+      return Math.max(best, score);
+    }, 0);
+    if (candidateScore > bestScore) {
+      bestScore = candidateScore;
+      bestField = field.name;
+    }
+  }
+  const minimumScore = input.minimumScore ?? 0.45;
+  if (!bestField || bestScore < minimumScore) {
+    return { field: null, confidence: null, reason: null };
+  }
+  const confidence = Math.min(0.85, Math.max(0.5, bestScore + 0.15));
+  return {
+    field: bestField,
+    confidence: Number(confidence.toFixed(2)),
+    reason: "Similarit\xE9 lexicale"
+  };
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  computeRequiredCoverage,
+  lexicalSimilarityScore,
+  mergeTokens,
+  normalizeFreeText,
+  normalizeTokenValue,
+  suggestFieldByLexicalRules,
+  tokenKey,
+  tokenize
+});

package/dist/index.js

@@ -0,0 +1,126 @@
+// src/token-normalization.ts
+function normalizeTokenValue(value) {
+  return value.trim().replace(/\s+/g, " ");
+}
+function tokenKey(syntax, rawToken) {
+  return `${syntax}:${normalizeTokenValue(rawToken)}`;
+}
+function mergeTokens(tokens) {
+  const merged = /* @__PURE__ */ new Map();
+  for (const token of tokens) {
+    const key = tokenKey(token.syntax, token.rawToken);
+    const existing = merged.get(key);
+    if (existing) {
+      existing.occurrences += token.occurrences;
+    } else {
+      merged.set(key, {
+        ...token,
+        rawToken: normalizeTokenValue(token.rawToken)
+      });
+    }
+  }
+  return [...merged.values()].sort((a, b) => {
+    if (b.occurrences !== a.occurrences) return b.occurrences - a.occurrences;
+    return tokenKey(a.syntax, a.rawToken).localeCompare(tokenKey(b.syntax, b.rawToken));
+  });
+}
+
+// src/mapping-progress.ts
+function computeRequiredCoverage(mappings, requiredFieldNames) {
+  const mappedFields = new Set(
+    mappings.filter((m) => m.status !== "ignored" && m.mappedField).map((m) => m.mappedField)
+  );
+  const missingRequired = requiredFieldNames.filter((name) => !mappedFields.has(name));
+  const requiredMapped = requiredFieldNames.length - missingRequired.length;
+  const requiredTotal = requiredFieldNames.length;
+  const coverageScore = requiredTotal > 0 ? Math.round(requiredMapped / requiredTotal * 100) : 100;
+  return {
+    requiredTotal,
+    requiredMapped,
+    coverageScore,
+    missingRequired,
+    complete: missingRequired.length === 0
+  };
+}
+
+// src/lexical.ts
+function normalizeFreeText(value) {
+  return value.normalize("NFD").replace(/[\u0300-\u036f]/g, "").toLowerCase().replace(/[^a-z0-9]+/g, " ").trim();
+}
+function tokenize(value) {
+  return value.split(" ").map((token) => token.trim()).filter((token) => token.length >= 2);
+}
+function lexicalSimilarityScore(normalizedRaw, rawTokens, normalizedCandidate, canonicalize) {
+  if (!normalizedCandidate) return 0;
+  if (normalizedRaw === normalizedCandidate) return 0.98;
+  if (canonicalize && canonicalize(normalizedRaw) === canonicalize(normalizedCandidate)) return 0.97;
+  if (normalizedCandidate.includes(normalizedRaw) || normalizedRaw.includes(normalizedCandidate)) {
+    return 0.75;
+  }
+  const candidateTokens = new Set(tokenize(normalizedCandidate));
+  const intersection = new Set(Array.from(rawTokens).filter((t) => candidateTokens.has(t))).size;
+  const union = (/* @__PURE__ */ new Set([...rawTokens, ...candidateTokens])).size;
+  if (union === 0) return 0;
+  return intersection / union;
+}
+
+// src/suggestion.ts
+function suggestFieldByLexicalRules(input) {
+  const exact = input.resolveExactField(input.rawToken);
+  if (exact) {
+    return {
+      field: exact,
+      confidence: 1,
+      reason: "Correspondance exacte"
+    };
+  }
+  const normalizedText = normalizeFreeText(input.rawToken);
+  if (!normalizedText) {
+    return { field: null, confidence: null, reason: null };
+  }
+  for (const rule of input.keywordRules) {
+    if (rule.pattern.test(normalizedText)) {
+      return { field: rule.field, confidence: rule.confidence, reason: rule.reason };
+    }
+  }
+  const rawTokens = new Set(tokenize(normalizedText));
+  let bestField = null;
+  let bestScore = 0;
+  for (const field of input.candidateFields) {
+    const candidates = [field.name, field.label ?? "", ...field.aliases ?? []];
+    const candidateScore = candidates.reduce((best, candidate) => {
+      const normalizedCandidate = normalizeFreeText(candidate);
+      const score = lexicalSimilarityScore(
+        normalizedText,
+        rawTokens,
+        normalizedCandidate,
+        input.canonicalizeFieldName
+      );
+      return Math.max(best, score);
+    }, 0);
+    if (candidateScore > bestScore) {
+      bestScore = candidateScore;
+      bestField = field.name;
+    }
+  }
+  const minimumScore = input.minimumScore ?? 0.45;
+  if (!bestField || bestScore < minimumScore) {
+    return { field: null, confidence: null, reason: null };
+  }
+  const confidence = Math.min(0.85, Math.max(0.5, bestScore + 0.15));
+  return {
+    field: bestField,
+    confidence: Number(confidence.toFixed(2)),
+    reason: "Similarit\xE9 lexicale"
+  };
+}
+export {
+  computeRequiredCoverage,
+  lexicalSimilarityScore,
+  mergeTokens,
+  normalizeFreeText,
+  normalizeTokenValue,
+  suggestFieldByLexicalRules,
+  tokenKey,
+  tokenize
+};

package/package.json

@@ -0,0 +1,40 @@
+{
+  "name": "@bhanquier/template-core",
+  "version": "0.1.1",
+  "description": "Canonical types and pure utilities for templating engines",
+  "type": "module",
+  "sideEffects": false,
+  "main": "./dist/index.js",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js",
+      "require": "./dist/index.cjs"
+    }
+  },
+  "files": [
+    "dist"
+  ],
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/TrustAkt/trustakt-templating.git"
+  },
+  "scripts": {
+    "build": "tsup src/index.ts --format esm,cjs --out-dir dist --clean && tsc --noEmit",
+    "dev": "tsup src/index.ts --format esm,cjs --out-dir dist --watch",
+    "test": "vitest run",
+    "typecheck": "tsc --noEmit"
+  },
+  "devDependencies": {
+    "@types/node": "^20.10.0",
+    "tsup": "^8.5.1",
+    "typescript": "^5.3.0",
+    "vitest": "^4.0.15"
+  },
+  "license": "UNLICENSED"
+}