thaizip 0.7.4 → 0.7.6

package/dist/index.cjs

@@ -35,6 +35,10 @@ function extractTrigramsNormalized(text) {
 }
 
 // src/core/indexer.ts
+var MAX_TOTAL_ROWS = 5e4;
+var MAX_NAME_LENGTH = 256;
+var MAX_ZIP_LENGTH = 32;
+var MAX_POSTING_BUDGET = 1e6;
 function typeErr(table, id, field, expected, value) {
   return new TypeError(`[thaizip] ${table} ${id}: expected ${expected} for ${field}, got ${typeof value}`);
 }
@@ -55,32 +59,42 @@ function validateRawData(data) {
   if (!Array.isArray(tambons)) {
     throw new TypeError(`[thaizip] RawData.tambons must be an array, got ${typeName(tambons)}`);
   }
-  const seenProvinceIds = /* @__PURE__ */ new Set();
+  if (provinces.length + amphures.length + tambons.length > MAX_TOTAL_ROWS) {
+    throw new RangeError(`[thaizip] RawData row limit exceeded (${MAX_TOTAL_ROWS})`);
+  }
+  const provinceById = /* @__PURE__ */ new Map();
   for (let i = 0; i < provinces.length; i++) {
     const p = provinces[i];
     if (p === null || typeof p !== "object") {
       throw new TypeError(`[thaizip] province[${i}]: expected object, got ${typeName(p)}`);
     }
     if (typeof p.id !== "number") throw typeErr("province", p.id, "id", "number", p.id);
-    if (seenProvinceIds.has(p.id)) throw new TypeError(`[thaizip] duplicate province id: ${p.id}`);
-    seenProvinceIds.add(p.id);
+    if (provinceById.has(p.id)) throw new TypeError(`[thaizip] duplicate province id: ${p.id}`);
+    provinceById.set(p.id, p);
     if (typeof p.name_th !== "string") throw typeErr("province", p.id, "name_th", "string", p.name_th);
     if (typeof p.name_en !== "string") throw typeErr("province", p.id, "name_en", "string", p.name_en);
+    if (p.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] province ${p.id}: name_th too long`);
+    if (p.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] province ${p.id}: name_en too long`);
   }
-  const seenAmphureIds = /* @__PURE__ */ new Set();
+  const amphureById = /* @__PURE__ */ new Map();
   for (let i = 0; i < amphures.length; i++) {
     const a = amphures[i];
     if (a === null || typeof a !== "object") {
       throw new TypeError(`[thaizip] amphure[${i}]: expected object, got ${typeName(a)}`);
     }
     if (typeof a.id !== "number") throw typeErr("amphure", a.id, "id", "number", a.id);
-    if (seenAmphureIds.has(a.id)) throw new TypeError(`[thaizip] duplicate amphure id: ${a.id}`);
-    seenAmphureIds.add(a.id);
+    if (amphureById.has(a.id)) throw new TypeError(`[thaizip] duplicate amphure id: ${a.id}`);
+    amphureById.set(a.id, a);
     if (typeof a.name_th !== "string") throw typeErr("amphure", a.id, "name_th", "string", a.name_th);
     if (typeof a.name_en !== "string") throw typeErr("amphure", a.id, "name_en", "string", a.name_en);
     if (typeof a.province_id !== "number") throw typeErr("amphure", a.id, "province_id", "number", a.province_id);
+    if (a.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] amphure ${a.id}: name_th too long`);
+    if (a.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] amphure ${a.id}: name_en too long`);
   }
   const seenTambonIds = /* @__PURE__ */ new Set();
+  const provinceTrigramCounts = /* @__PURE__ */ new Map();
+  const amphureTrigramCounts = /* @__PURE__ */ new Map();
+  let postingBudget = 0;
   for (let i = 0; i < tambons.length; i++) {
     const t = tambons[i];
     if (t === null || typeof t !== "object") {
@@ -91,11 +105,33 @@ function validateRawData(data) {
     seenTambonIds.add(t.id);
     if (typeof t.name_th !== "string") throw typeErr("tambon", t.id, "name_th", "string", t.name_th);
     if (typeof t.name_en !== "string") throw typeErr("tambon", t.id, "name_en", "string", t.name_en);
+    if (t.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: name_th too long`);
+    if (t.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: name_en too long`);
     const zipType = typeof t.zip_code;
     if (zipType !== "string" && zipType !== "number") {
       throw typeErr("tambon", t.id, "zip_code", "string or number", t.zip_code);
     }
     if (typeof t.amphure_id !== "number") throw typeErr("tambon", t.id, "amphure_id", "number", t.amphure_id);
+    const zipLength = String(t.zip_code).length;
+    if (zipLength > MAX_ZIP_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: zip_code too long`);
+    if (t.deleted_at) continue;
+    const amphure = amphureById.get(t.amphure_id);
+    const province = amphure && provinceById.get(amphure.province_id);
+    if (!amphure || amphure.deleted_at || !province || province.deleted_at) continue;
+    let provinceGrams = provinceTrigramCounts.get(province.id);
+    if (provinceGrams === void 0) {
+      provinceGrams = combinedTrigrams(province.name_th, province.name_en).size;
+      provinceTrigramCounts.set(province.id, provinceGrams);
+    }
+    let amphureGrams = amphureTrigramCounts.get(amphure.id);
+    if (amphureGrams === void 0) {
+      amphureGrams = combinedTrigrams(amphure.name_th, amphure.name_en).size;
+      amphureTrigramCounts.set(amphure.id, amphureGrams);
+    }
+    postingBudget += t.name_th.length + t.name_en.length + zipLength + provinceGrams + amphureGrams;
+    if (postingBudget > MAX_POSTING_BUDGET) {
+      throw new RangeError(`[thaizip] estimated trigram posting budget exceeded (${MAX_POSTING_BUDGET})`);
+    }
   }
 }
 function addTrigrams(map, trigrams, idx) {
@@ -126,13 +162,7 @@ function buildThaiAddressIndex(data, options) {
     amphures.filter((a) => !a.deleted_at).map((a) => [a.id, a])
   );
   const provTrigrams = /* @__PURE__ */ new Map();
-  for (const [id, prov] of provMap) {
-    provTrigrams.set(id, combinedTrigrams(prov.name_th, prov.name_en));
-  }
   const ampTrigrams = /* @__PURE__ */ new Map();
-  for (const [id, amp] of ampMap) {
-    ampTrigrams.set(id, combinedTrigrams(amp.name_th, amp.name_en));
-  }
   const records = [];
   const map = /* @__PURE__ */ new Map();
   const zipIndex = /* @__PURE__ */ new Map();
@@ -182,8 +212,18 @@ function buildThaiAddressIndex(data, options) {
     normTambonEn.push(normEn);
     addTrigrams(map, extractTrigramsNormalized(normEn), idx);
     addTrigrams(map, extractTrigrams(record.zipCode), idx);
-    addTrigrams(map, provTrigrams.get(province.id), idx);
-    addTrigrams(map, ampTrigrams.get(amphure.id), idx);
+    let provinceGrams = provTrigrams.get(province.id);
+    if (!provinceGrams) {
+      provinceGrams = combinedTrigrams(province.name_th, province.name_en);
+      provTrigrams.set(province.id, provinceGrams);
+    }
+    let amphureGrams = ampTrigrams.get(amphure.id);
+    if (!amphureGrams) {
+      amphureGrams = combinedTrigrams(amphure.name_th, amphure.name_en);
+      ampTrigrams.set(amphure.id, amphureGrams);
+    }
+    addTrigrams(map, provinceGrams, idx);
+    addTrigrams(map, amphureGrams, idx);
   }
   const sortedZipKeys = [...zipIndex.keys()].sort();
   const sortedZipPostings = sortedZipKeys.map((z) => zipIndex.get(z));

package/dist/index.d.cts

@@ -161,10 +161,9 @@ type RawData = {
  * private datasets) who want to fail fast with a descriptive error instead of an
  * opaque crash deep inside the normalizer, or silent `"undefined"` labels.
  *
- * Throws a `TypeError` (message prefixed `[thaizip]`) naming the table, the
- * offending record's `id`, the field, and the actual `typeof` on the first bad
- * field found. Does not filter soft-deleted rows first — validates every row as
- * provided.
+ * Throws a `TypeError` for bad shapes or duplicate IDs and a `RangeError` for
+ * resource limits (all prefixed `[thaizip]`). Does not filter soft-deleted rows
+ * before shape checks — validates every row as provided.
  *
  * IDs must be unique within each table (duplicates throw, they are not silently
  * discarded — two suggestions sharing an id would resolve to the wrong record).

package/dist/index.d.ts

@@ -161,10 +161,9 @@ type RawData = {
  * private datasets) who want to fail fast with a descriptive error instead of an
  * opaque crash deep inside the normalizer, or silent `"undefined"` labels.
  *
- * Throws a `TypeError` (message prefixed `[thaizip]`) naming the table, the
- * offending record's `id`, the field, and the actual `typeof` on the first bad
- * field found. Does not filter soft-deleted rows first — validates every row as
- * provided.
+ * Throws a `TypeError` for bad shapes or duplicate IDs and a `RangeError` for
+ * resource limits (all prefixed `[thaizip]`). Does not filter soft-deleted rows
+ * before shape checks — validates every row as provided.
  *
  * IDs must be unique within each table (duplicates throw, they are not silently
  * discarded — two suggestions sharing an id would resolve to the wrong record).

package/dist/index.js

@@ -33,6 +33,10 @@ function extractTrigramsNormalized(text) {
 }
 
 // src/core/indexer.ts
+var MAX_TOTAL_ROWS = 5e4;
+var MAX_NAME_LENGTH = 256;
+var MAX_ZIP_LENGTH = 32;
+var MAX_POSTING_BUDGET = 1e6;
 function typeErr(table, id, field, expected, value) {
   return new TypeError(`[thaizip] ${table} ${id}: expected ${expected} for ${field}, got ${typeof value}`);
 }
@@ -53,32 +57,42 @@ function validateRawData(data) {
   if (!Array.isArray(tambons)) {
     throw new TypeError(`[thaizip] RawData.tambons must be an array, got ${typeName(tambons)}`);
   }
-  const seenProvinceIds = /* @__PURE__ */ new Set();
+  if (provinces.length + amphures.length + tambons.length > MAX_TOTAL_ROWS) {
+    throw new RangeError(`[thaizip] RawData row limit exceeded (${MAX_TOTAL_ROWS})`);
+  }
+  const provinceById = /* @__PURE__ */ new Map();
   for (let i = 0; i < provinces.length; i++) {
     const p = provinces[i];
     if (p === null || typeof p !== "object") {
       throw new TypeError(`[thaizip] province[${i}]: expected object, got ${typeName(p)}`);
     }
     if (typeof p.id !== "number") throw typeErr("province", p.id, "id", "number", p.id);
-    if (seenProvinceIds.has(p.id)) throw new TypeError(`[thaizip] duplicate province id: ${p.id}`);
-    seenProvinceIds.add(p.id);
+    if (provinceById.has(p.id)) throw new TypeError(`[thaizip] duplicate province id: ${p.id}`);
+    provinceById.set(p.id, p);
     if (typeof p.name_th !== "string") throw typeErr("province", p.id, "name_th", "string", p.name_th);
     if (typeof p.name_en !== "string") throw typeErr("province", p.id, "name_en", "string", p.name_en);
+    if (p.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] province ${p.id}: name_th too long`);
+    if (p.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] province ${p.id}: name_en too long`);
   }
-  const seenAmphureIds = /* @__PURE__ */ new Set();
+  const amphureById = /* @__PURE__ */ new Map();
   for (let i = 0; i < amphures.length; i++) {
     const a = amphures[i];
     if (a === null || typeof a !== "object") {
       throw new TypeError(`[thaizip] amphure[${i}]: expected object, got ${typeName(a)}`);
     }
     if (typeof a.id !== "number") throw typeErr("amphure", a.id, "id", "number", a.id);
-    if (seenAmphureIds.has(a.id)) throw new TypeError(`[thaizip] duplicate amphure id: ${a.id}`);
-    seenAmphureIds.add(a.id);
+    if (amphureById.has(a.id)) throw new TypeError(`[thaizip] duplicate amphure id: ${a.id}`);
+    amphureById.set(a.id, a);
     if (typeof a.name_th !== "string") throw typeErr("amphure", a.id, "name_th", "string", a.name_th);
     if (typeof a.name_en !== "string") throw typeErr("amphure", a.id, "name_en", "string", a.name_en);
     if (typeof a.province_id !== "number") throw typeErr("amphure", a.id, "province_id", "number", a.province_id);
+    if (a.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] amphure ${a.id}: name_th too long`);
+    if (a.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] amphure ${a.id}: name_en too long`);
   }
   const seenTambonIds = /* @__PURE__ */ new Set();
+  const provinceTrigramCounts = /* @__PURE__ */ new Map();
+  const amphureTrigramCounts = /* @__PURE__ */ new Map();
+  let postingBudget = 0;
   for (let i = 0; i < tambons.length; i++) {
     const t = tambons[i];
     if (t === null || typeof t !== "object") {
@@ -89,11 +103,33 @@ function validateRawData(data) {
     seenTambonIds.add(t.id);
     if (typeof t.name_th !== "string") throw typeErr("tambon", t.id, "name_th", "string", t.name_th);
     if (typeof t.name_en !== "string") throw typeErr("tambon", t.id, "name_en", "string", t.name_en);
+    if (t.name_th.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: name_th too long`);
+    if (t.name_en.length > MAX_NAME_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: name_en too long`);
     const zipType = typeof t.zip_code;
     if (zipType !== "string" && zipType !== "number") {
       throw typeErr("tambon", t.id, "zip_code", "string or number", t.zip_code);
     }
     if (typeof t.amphure_id !== "number") throw typeErr("tambon", t.id, "amphure_id", "number", t.amphure_id);
+    const zipLength = String(t.zip_code).length;
+    if (zipLength > MAX_ZIP_LENGTH) throw new RangeError(`[thaizip] tambon ${t.id}: zip_code too long`);
+    if (t.deleted_at) continue;
+    const amphure = amphureById.get(t.amphure_id);
+    const province = amphure && provinceById.get(amphure.province_id);
+    if (!amphure || amphure.deleted_at || !province || province.deleted_at) continue;
+    let provinceGrams = provinceTrigramCounts.get(province.id);
+    if (provinceGrams === void 0) {
+      provinceGrams = combinedTrigrams(province.name_th, province.name_en).size;
+      provinceTrigramCounts.set(province.id, provinceGrams);
+    }
+    let amphureGrams = amphureTrigramCounts.get(amphure.id);
+    if (amphureGrams === void 0) {
+      amphureGrams = combinedTrigrams(amphure.name_th, amphure.name_en).size;
+      amphureTrigramCounts.set(amphure.id, amphureGrams);
+    }
+    postingBudget += t.name_th.length + t.name_en.length + zipLength + provinceGrams + amphureGrams;
+    if (postingBudget > MAX_POSTING_BUDGET) {
+      throw new RangeError(`[thaizip] estimated trigram posting budget exceeded (${MAX_POSTING_BUDGET})`);
+    }
   }
 }
 function addTrigrams(map, trigrams, idx) {
@@ -124,13 +160,7 @@ function buildThaiAddressIndex(data, options) {
     amphures.filter((a) => !a.deleted_at).map((a) => [a.id, a])
   );
   const provTrigrams = /* @__PURE__ */ new Map();
-  for (const [id, prov] of provMap) {
-    provTrigrams.set(id, combinedTrigrams(prov.name_th, prov.name_en));
-  }
   const ampTrigrams = /* @__PURE__ */ new Map();
-  for (const [id, amp] of ampMap) {
-    ampTrigrams.set(id, combinedTrigrams(amp.name_th, amp.name_en));
-  }
   const records = [];
   const map = /* @__PURE__ */ new Map();
   const zipIndex = /* @__PURE__ */ new Map();
@@ -180,8 +210,18 @@ function buildThaiAddressIndex(data, options) {
     normTambonEn.push(normEn);
     addTrigrams(map, extractTrigramsNormalized(normEn), idx);
     addTrigrams(map, extractTrigrams(record.zipCode), idx);
-    addTrigrams(map, provTrigrams.get(province.id), idx);
-    addTrigrams(map, ampTrigrams.get(amphure.id), idx);
+    let provinceGrams = provTrigrams.get(province.id);
+    if (!provinceGrams) {
+      provinceGrams = combinedTrigrams(province.name_th, province.name_en);
+      provTrigrams.set(province.id, provinceGrams);
+    }
+    let amphureGrams = ampTrigrams.get(amphure.id);
+    if (!amphureGrams) {
+      amphureGrams = combinedTrigrams(amphure.name_th, amphure.name_en);
+      ampTrigrams.set(amphure.id, amphureGrams);
+    }
+    addTrigrams(map, provinceGrams, idx);
+    addTrigrams(map, amphureGrams, idx);
   }
   const sortedZipKeys = [...zipIndex.keys()].sort();
   const sortedZipPostings = sortedZipKeys.map((z) => zipIndex.get(z));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "thaizip",
-  "version": "0.7.4",
+  "version": "0.7.6",
   "description": "Fast, fuzzy Thai address autocomplete library (headless + React)",
   "keywords": [
     "thai",