thaizip 0.7.5 → 0.7.6

package/README.md

@@ -28,7 +28,7 @@ npm install thaizip
 import { loadDefaultIndex } from 'thaizip/data'
 import { searchThaiAddress, formatThaiAddressSuggestion, resolveThaiAddress } from 'thaizip'
 
-const index = await loadDefaultIndex() // ~40ms of synchronous work, cached after
+const index = await loadDefaultIndex() // ~50ms on the measured device, cached after
 
 searchThaiAddress(index, 'ลาดพร้าว')
 searchThaiAddress(index, 'bang rak')
@@ -39,7 +39,8 @@ formatThaiAddressSuggestion(record, { locale: 'en' })
 resolveThaiAddress(record)                           // for saving
 ```
 
-Call `loadDefaultIndex()` at mount or route load — deferring it to the user's first keystroke costs ~2 dropped frames.
+Call `loadDefaultIndex()` at mount or route load — deferring it to the user's first keystroke can block the UI briefly.
+The cached default index is shared. Ordinary writes to its records and lookup structures throw; build a separate index with `buildThaiAddressIndex` if you need to edit address data. This is protection against accidental changes, not a security boundary against hostile code already running in the same JavaScript realm.
 
 ## Search
 
@@ -135,9 +136,9 @@ const index = buildThaiAddressIndex({ provinces, amphures, tambons }, {
 })
 ```
 
-Input is validated by default, so a stray non-string field fails with `[thaizip] tambon 100404: expected string for name_th, got number` instead of crashing inside the normalizer. It costs nothing measurable on a full-size dataset. `validateRawData(data)` runs the same checks standalone.
+Input is validated by default, so a stray non-string field fails with `[thaizip] tambon 100404: expected string for name_th, got number` instead of crashing inside the normalizer. `validateRawData(data)` runs the same checks standalone.
 
-`RawData` is meant to be trusted, application-controlled input — your own dataset, not arbitrary end-user uploads. `buildThaiAddressIndex` has no built-in cap on row count or field length; build cost scales linearly with total input size, but an unbounded or maliciously oversized payload (e.g. an admin importer fed directly to this function) can still cost real time and memory with nothing to stop it. If you ever build an index from untrusted input, enforce your own size limits (row count, field length) before calling `buildThaiAddressIndex`.
+Validation also rejects more than 50,000 total rows, names longer than 256 UTF-16 code units, ZIP values longer than 32 code units, or an estimated trigram posting cost above 1,000,000. The estimate counts each province/district's unique trigrams once for every active child subdistrict, so it catches parent-name fan-out. These bounds are suitable for the bundled-size dataset, not a guarantee that arbitrary uploads are safe to process. For larger trusted datasets, pass `{ validate: false }` and apply your own resource limits before building.
 
 Types: `RawData`, `RawProvince`, `RawAmphure`, `RawTambon`.
 

package/dist/data.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));
@@ -194,6 +234,40 @@ function buildThaiAddressIndex(data, options) {
 var cached = null;
 var inflightPromise = null;
 var loadGeneration = 0;
+function rejectDefaultIndexMutation() {
+  throw new TypeError("[thaizip] the shared default index is read-only");
+}
+var readOnlyMapPrototype = Object.create(Map.prototype);
+var readOnlySetPrototype = Object.create(Set.prototype);
+for (const [prototype, methods] of [
+  [readOnlyMapPrototype, ["set", "delete", "clear"]],
+  [readOnlySetPrototype, ["add", "delete", "clear"]]
+]) {
+  for (const method of methods) {
+    Object.defineProperty(prototype, method, { value: rejectDefaultIndexMutation });
+  }
+}
+function lockMapValues(map, lockValue) {
+  for (const value of map.values()) lockValue(value);
+  Object.setPrototypeOf(map, readOnlyMapPrototype);
+  Object.freeze(map);
+}
+function lockDefaultIndex(index) {
+  for (const record of index.records) Object.freeze(record);
+  Object.freeze(index.records);
+  Object.freeze(index.normTambon);
+  Object.freeze(index.normTambonEn);
+  if (index.sortedZipKeys) Object.freeze(index.sortedZipKeys);
+  if (index.sortedZipPostings) Object.freeze(index.sortedZipPostings);
+  lockMapValues(index.map, (set) => {
+    Object.setPrototypeOf(set, readOnlySetPrototype);
+    Object.freeze(set);
+  });
+  lockMapValues(index.zipIndex, Object.freeze);
+  lockMapValues(index.byProvince, Object.freeze);
+  lockMapValues(index.byAmphure, Object.freeze);
+  return Object.freeze(index);
+}
 function clearDefaultIndex() {
   cached = null;
   inflightPromise = null;
@@ -207,11 +281,11 @@ async function loadDefaultIndex() {
   if (!inflightPromise) {
     const gen = loadGeneration;
     inflightPromise = import('./defaultData.js').then(({ p, a, t }) => {
-      const index = buildThaiAddressIndex({
+      const index = lockDefaultIndex(buildThaiAddressIndex({
         provinces: p.map(([id, name_th, name_en]) => ({ id, name_th, name_en, geography_id: 0, deleted_at: null })),
         amphures: a.map(([id, name_th, name_en, province_id]) => ({ id, name_th, name_en, province_id, deleted_at: null })),
         tambons: t.map(([id, name_th, name_en, amphure_id, zip_code]) => ({ id, name_th, name_en, amphure_id, zip_code, deleted_at: null }))
-      }, { validate: false });
+      }, { validate: false }));
       if (loadGeneration === gen) {
         cached = index;
         inflightPromise = null;

package/dist/data.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));
@@ -192,6 +232,40 @@ function buildThaiAddressIndex(data, options) {
 var cached = null;
 var inflightPromise = null;
 var loadGeneration = 0;
+function rejectDefaultIndexMutation() {
+  throw new TypeError("[thaizip] the shared default index is read-only");
+}
+var readOnlyMapPrototype = Object.create(Map.prototype);
+var readOnlySetPrototype = Object.create(Set.prototype);
+for (const [prototype, methods] of [
+  [readOnlyMapPrototype, ["set", "delete", "clear"]],
+  [readOnlySetPrototype, ["add", "delete", "clear"]]
+]) {
+  for (const method of methods) {
+    Object.defineProperty(prototype, method, { value: rejectDefaultIndexMutation });
+  }
+}
+function lockMapValues(map, lockValue) {
+  for (const value of map.values()) lockValue(value);
+  Object.setPrototypeOf(map, readOnlyMapPrototype);
+  Object.freeze(map);
+}
+function lockDefaultIndex(index) {
+  for (const record of index.records) Object.freeze(record);
+  Object.freeze(index.records);
+  Object.freeze(index.normTambon);
+  Object.freeze(index.normTambonEn);
+  if (index.sortedZipKeys) Object.freeze(index.sortedZipKeys);
+  if (index.sortedZipPostings) Object.freeze(index.sortedZipPostings);
+  lockMapValues(index.map, (set) => {
+    Object.setPrototypeOf(set, readOnlySetPrototype);
+    Object.freeze(set);
+  });
+  lockMapValues(index.zipIndex, Object.freeze);
+  lockMapValues(index.byProvince, Object.freeze);
+  lockMapValues(index.byAmphure, Object.freeze);
+  return Object.freeze(index);
+}
 function clearDefaultIndex() {
   cached = null;
   inflightPromise = null;
@@ -205,11 +279,11 @@ async function loadDefaultIndex() {
   if (!inflightPromise) {
     const gen = loadGeneration;
     inflightPromise = import('./defaultData.js').then(({ p, a, t }) => {
-      const index = buildThaiAddressIndex({
+      const index = lockDefaultIndex(buildThaiAddressIndex({
         provinces: p.map(([id, name_th, name_en]) => ({ id, name_th, name_en, geography_id: 0, deleted_at: null })),
         amphures: a.map(([id, name_th, name_en, province_id]) => ({ id, name_th, name_en, province_id, deleted_at: null })),
         tambons: t.map(([id, name_th, name_en, amphure_id, zip_code]) => ({ id, name_th, name_en, amphure_id, zip_code, deleted_at: null }))
-      }, { validate: false });
+      }, { validate: false }));
       if (loadGeneration === gen) {
         cached = index;
         inflightPromise = null;

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": "0.7.5",
+  "version": "0.7.6",
   "description": "Fast, fuzzy Thai address autocomplete library (headless + React)",
   "keywords": [
     "thai",