gs-search 0.1.4 → 0.1.6

package/lib/node.cjs

@@ -1 +1,99 @@
-"use strict";Object.create,Object.defineProperty,Object.getOwnPropertyDescriptor,Object.getOwnPropertyNames,Object.getPrototypeOf,Object.prototype.hasOwnProperty;exports.NodeStorage=class{#t=null;#i=null;#a;#s="";constructor(t){this.#a=t}async#e(){if(this.#t)return;const t=await import("fs/promises"),i=await import("path");this.#t=t,this.#i=i,this.#s=this.#i.join(process.cwd(),this.#a);try{await this.#t.access(this.#s)}catch{await this.#t.mkdir(this.#s,{recursive:!0})}}#r(t){return this.#i.join(this.#s,t)}async write(t,i){await this.#e(),await this.#t.writeFile(this.#r(t),Buffer.from(i))}async append(t,i){await this.#e(),await this.#t.appendFile(this.#r(t),Buffer.from(i))}async read(t){await this.#e();try{const i=await this.#t.readFile(this.#r(t));return i.buffer.slice(i.byteOffset,i.byteOffset+i.byteLength)}catch{return null}}async readRange(t,i,a){await this.#e();try{const s=await this.#t.open(this.#r(t),"r"),e=a-i,r=Buffer.alloc(e);return await s.read(r,0,e,i),await s.close(),r.buffer.slice(r.byteOffset,r.byteOffset+r.byteLength)}catch{return null}}async remove(t){await this.#e();try{await this.#t.unlink(this.#r(t))}catch{}}async listFiles(){await this.#e();try{return await this.#t.readdir(this.#s)}catch{return[]}}async clearAll(){await this.#e();try{const t=await this.#t.readdir(this.#s);for(const i of t)await this.#t.unlink(this.#i.join(this.#s,i))}catch{}}async getFileSize(t){await this.#e();try{return(await this.#t.stat(this.#r(t))).size}catch{return 0}}};
+"use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf, __hasOwnProp = Object.prototype.hasOwnProperty;
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from == "object" || typeof from == "function")
+    for (let key of __getOwnPropNames(from))
+      !__hasOwnProp.call(to, key) && key !== except && __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: !0 }) : target,
+  mod
+));
+class NodeStorage {
+  #fs = null;
+  #path = null;
+  #baseDir;
+  #fullDataDir = "";
+  constructor(baseDir) {
+    this.#baseDir = baseDir;
+  }
+  async #init() {
+    if (this.#fs) return;
+    const fsModule = await import("fs/promises"), pathModule = await import("path");
+    this.#fs = fsModule, this.#path = pathModule, this.#fullDataDir = this.#path.join(process.cwd(), this.#baseDir);
+    try {
+      await this.#fs.access(this.#fullDataDir);
+    } catch {
+      await this.#fs.mkdir(this.#fullDataDir, { recursive: !0 });
+    }
+  }
+  #p(filename) {
+    return this.#path.join(this.#fullDataDir, filename);
+  }
+  async write(filename, data) {
+    await this.#init(), await this.#fs.writeFile(this.#p(filename), Buffer.from(data));
+  }
+  async append(filename, data) {
+    await this.#init(), await this.#fs.appendFile(this.#p(filename), Buffer.from(data));
+  }
+  async read(filename) {
+    await this.#init();
+    try {
+      const buf = await this.#fs.readFile(this.#p(filename));
+      return buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength);
+    } catch {
+      return null;
+    }
+  }
+  async readRange(filename, start, end) {
+    await this.#init();
+    try {
+      const fd = await this.#fs.open(this.#p(filename), "r"), len = end - start, buf = Buffer.alloc(len);
+      return await fd.read(buf, 0, len, start), await fd.close(), buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength);
+    } catch {
+      return null;
+    }
+  }
+  async remove(filename) {
+    await this.#init();
+    try {
+      await this.#fs.unlink(this.#p(filename));
+    } catch {
+    }
+  }
+  async listFiles() {
+    await this.#init();
+    try {
+      return await this.#fs.readdir(this.#fullDataDir);
+    } catch {
+      return [];
+    }
+  }
+  async clearAll() {
+    await this.#init();
+    try {
+      const files = await this.#fs.readdir(this.#fullDataDir);
+      for (const f of files)
+        await this.#fs.unlink(this.#path.join(this.#fullDataDir, f));
+    } catch {
+    }
+  }
+  async getFileSize(filename) {
+    await this.#init();
+    try {
+      return (await this.#fs.stat(this.#p(filename))).size;
+    } catch {
+      return 0;
+    }
+  }
+}
+exports.NodeStorage = NodeStorage;

package/lib/node.js

@@ -1 +1,81 @@
-class t{#t=null;#i=null;#a;#s="";constructor(t){this.#a=t}async#r(){if(this.#t)return;const t=await import("fs/promises"),i=await import("path");this.#t=t,this.#i=i,this.#s=this.#i.join(process.cwd(),this.#a);try{await this.#t.access(this.#s)}catch{await this.#t.mkdir(this.#s,{recursive:!0})}}#e(t){return this.#i.join(this.#s,t)}async write(t,i){await this.#r(),await this.#t.writeFile(this.#e(t),Buffer.from(i))}async append(t,i){await this.#r(),await this.#t.appendFile(this.#e(t),Buffer.from(i))}async read(t){await this.#r();try{const i=await this.#t.readFile(this.#e(t));return i.buffer.slice(i.byteOffset,i.byteOffset+i.byteLength)}catch{return null}}async readRange(t,i,a){await this.#r();try{const s=await this.#t.open(this.#e(t),"r"),r=a-i,e=Buffer.alloc(r);return await s.read(e,0,r,i),await s.close(),e.buffer.slice(e.byteOffset,e.byteOffset+e.byteLength)}catch{return null}}async remove(t){await this.#r();try{await this.#t.unlink(this.#e(t))}catch{}}async listFiles(){await this.#r();try{return await this.#t.readdir(this.#s)}catch{return[]}}async clearAll(){await this.#r();try{const t=await this.#t.readdir(this.#s);for(const i of t)await this.#t.unlink(this.#i.join(this.#s,i))}catch{}}async getFileSize(t){await this.#r();try{return(await this.#t.stat(this.#e(t))).size}catch{return 0}}}export{t as NodeStorage};
+class NodeStorage {
+  #fs = null;
+  #path = null;
+  #baseDir;
+  #fullDataDir = "";
+  constructor(baseDir) {
+    this.#baseDir = baseDir;
+  }
+  async #init() {
+    if (this.#fs) return;
+    const fsModule = await import("fs/promises"), pathModule = await import("path");
+    this.#fs = fsModule, this.#path = pathModule, this.#fullDataDir = this.#path.join(process.cwd(), this.#baseDir);
+    try {
+      await this.#fs.access(this.#fullDataDir);
+    } catch {
+      await this.#fs.mkdir(this.#fullDataDir, { recursive: !0 });
+    }
+  }
+  #p(filename) {
+    return this.#path.join(this.#fullDataDir, filename);
+  }
+  async write(filename, data) {
+    await this.#init(), await this.#fs.writeFile(this.#p(filename), Buffer.from(data));
+  }
+  async append(filename, data) {
+    await this.#init(), await this.#fs.appendFile(this.#p(filename), Buffer.from(data));
+  }
+  async read(filename) {
+    await this.#init();
+    try {
+      const buf = await this.#fs.readFile(this.#p(filename));
+      return buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength);
+    } catch {
+      return null;
+    }
+  }
+  async readRange(filename, start, end) {
+    await this.#init();
+    try {
+      const fd = await this.#fs.open(this.#p(filename), "r"), len = end - start, buf = Buffer.alloc(len);
+      return await fd.read(buf, 0, len, start), await fd.close(), buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength);
+    } catch {
+      return null;
+    }
+  }
+  async remove(filename) {
+    await this.#init();
+    try {
+      await this.#fs.unlink(this.#p(filename));
+    } catch {
+    }
+  }
+  async listFiles() {
+    await this.#init();
+    try {
+      return await this.#fs.readdir(this.#fullDataDir);
+    } catch {
+      return [];
+    }
+  }
+  async clearAll() {
+    await this.#init();
+    try {
+      const files = await this.#fs.readdir(this.#fullDataDir);
+      for (const f of files)
+        await this.#fs.unlink(this.#path.join(this.#fullDataDir, f));
+    } catch {
+    }
+  }
+  async getFileSize(filename) {
+    await this.#init();
+    try {
+      return (await this.#fs.stat(this.#p(filename))).size;
+    } catch {
+      return 0;
+    }
+  }
+}
+export {
+  NodeStorage
+};

package/lib/simple.cjs

@@ -1 +1,64 @@
-"use strict";var t=require('./core');exports.SimpleSearch=class{static#t=null;static#e={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(e){const n={...this.#e,...e};this.#t=new t.SearchEngine(n)}static#n(){return this.#t||(this.#t=new t.SearchEngine(this.#e)),this.#t}static async startBatch(){this.#n().startBatch()}static async endBatch(){return this.#n().endBatch()}static async addDocument(t){return this.#n().addDocument(t)}static async addDocumentIfMissing(t){return this.#n().addDocumentIfMissing(t)}static async addDocuments(t){return this.#n().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#n().addDocumentsIfMissing(t)}static async search(t,e){return this.#n().search(t,e)}static async removeDocument(t){return this.#n().removeDocument(t)}static async clearAll(){return this.#n().clearAll()}static async getStatus(){return this.#n().getStatus()}static async hasDocument(t){return this.#n().hasDocument(t)}};
+"use strict";
+var core = require('./core'), browser = require('./browser'), node = require('./node');
+const DefaultOption = Object.freeze({
+  wordSegmentTokenThreshold: 1e5,
+  minWordTokenSave: 0
+}), DefaultPath = "simple-search";
+class SimpleSearch {
+  static #instance = null;
+  static #config;
+  static get config() {
+    if (this.#config)
+      return this.#config;
+    const config = { ...DefaultOption };
+    return typeof navigator < "u" && navigator?.storage?.getDirectory instanceof Function ? config.storage = new browser.BrowserStorage(DefaultPath) : config.storage = new node.NodeStorage(DefaultPath), this.#config = config;
+  }
+  /**
+   * 配置并初始化单例
+   */
+  static configure(config) {
+    this.#config = { ...this.config, ...config }, this.#instance && (this.#instance = new core.SearchEngine(this.config));
+  }
+  static async startBatch() {
+    this.#getInstance().startBatch();
+  }
+  static async endBatch() {
+    return this.#getInstance().endBatch();
+  }
+  static async addDocument(doc) {
+    return this.#getInstance().addDocument(doc);
+  }
+  static async addDocumentIfMissing(doc) {
+    return this.#getInstance().addDocumentIfMissing(doc);
+  }
+  static async addDocuments(docs) {
+    return this.#getInstance().addDocuments(docs);
+  }
+  static async addDocumentsIfMissing(docs) {
+    return this.#getInstance().addDocumentsIfMissing(docs);
+  }
+  static async search(query, limit) {
+    return this.#getInstance().search(query, limit);
+  }
+  static async removeDocument(id) {
+    return this.#getInstance().removeDocument(id);
+  }
+  static async clearAll() {
+    return this.#getInstance().clearAll();
+  }
+  static async getStatus() {
+    return this.#getInstance().getStatus();
+  }
+  /**
+   * 检查文档ID是否曾经添加过（包括已删除的）
+   * @param id 文档ID
+   * @returns 文档是否曾经添加过的布尔值
+   */
+  static async hasDocument(id) {
+    return this.#getInstance().hasDocument(id);
+  }
+  static #getInstance() {
+    return this.#instance || (this.#instance = new core.SearchEngine(this.config)), this.#instance;
+  }
+}
+exports.SimpleSearch = SimpleSearch;

package/lib/simple.d.ts

@@ -1,5 +1,5 @@
 import * as ___type from './type';
-import { ISearchEngineConfig, IDocument, IDocumentBase } from './type';
+import { ISearchEngineOption, IDocument, IDocumentBase } from './type';
 
 /**
  * 快速使用封装
@@ -7,27 +7,21 @@ import { ISearchEngineConfig, IDocument, IDocumentBase } from './type';
  */
 declare class SimpleSearch {
     #private;
+    static get config(): ISearchEngineOption;
     /**
      * 配置并初始化单例
      */
-    static configure(config: Partial<ISearchEngineConfig>): void;
+    static configure(config: Partial<ISearchEngineOption>): void;
     static startBatch(): Promise<void>;
     static endBatch(): Promise<void>;
     static addDocument<T extends IDocument = IDocument>(doc: T): Promise<void>;
     static addDocumentIfMissing<T extends IDocument = IDocument>(doc: T): Promise<void>;
     static addDocuments<T extends IDocument = IDocument>(docs: T[]): Promise<void>;
     static addDocumentsIfMissing<T extends IDocument = IDocument>(docs: T[]): Promise<void>;
-    static search<T extends IDocumentBase = IDocumentBase>(query: T | string, limit?: number): Promise<___type.IResult[]>;
+    static search<T extends IDocumentBase = any>(query: T | string, limit?: number): Promise<___type.IResult[]>;
     static removeDocument(id: number): Promise<void>;
     static clearAll(): Promise<void>;
-    static getStatus(): Promise<{
-        wordSegments: number;
-        charSegments: number;
-        deleted: number;
-        wordCacheSize: number;
-        charCacheSize: number;
-        inBatch: boolean;
-    }>;
+    static getStatus(): Promise<___type.ISearchEngineStatus>;
     /**
      * 检查文档ID是否曾经添加过（包括已删除的）
      * @param id 文档ID

package/lib/simple.js

@@ -1 +1,67 @@
-import{SearchEngine as t}from'./core';class s{static#t=null;static#s={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(s){const n={...this.#s,...s};this.#t=new t(n)}static#n(){return this.#t||(this.#t=new t(this.#s)),this.#t}static async startBatch(){this.#n().startBatch()}static async endBatch(){return this.#n().endBatch()}static async addDocument(t){return this.#n().addDocument(t)}static async addDocumentIfMissing(t){return this.#n().addDocumentIfMissing(t)}static async addDocuments(t){return this.#n().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#n().addDocumentsIfMissing(t)}static async search(t,s){return this.#n().search(t,s)}static async removeDocument(t){return this.#n().removeDocument(t)}static async clearAll(){return this.#n().clearAll()}static async getStatus(){return this.#n().getStatus()}static async hasDocument(t){return this.#n().hasDocument(t)}}export{s as SimpleSearch};
+import { SearchEngine } from './core';
+import { BrowserStorage } from './browser';
+import { NodeStorage } from './node';
+const DefaultOption = Object.freeze({
+  wordSegmentTokenThreshold: 1e5,
+  minWordTokenSave: 0
+}), DefaultPath = "simple-search";
+class SimpleSearch {
+  static #instance = null;
+  static #config;
+  static get config() {
+    if (this.#config)
+      return this.#config;
+    const config = { ...DefaultOption };
+    return typeof navigator < "u" && navigator?.storage?.getDirectory instanceof Function ? config.storage = new BrowserStorage(DefaultPath) : config.storage = new NodeStorage(DefaultPath), this.#config = config;
+  }
+  /**
+   * 配置并初始化单例
+   */
+  static configure(config) {
+    this.#config = { ...this.config, ...config }, this.#instance && (this.#instance = new SearchEngine(this.config));
+  }
+  static async startBatch() {
+    this.#getInstance().startBatch();
+  }
+  static async endBatch() {
+    return this.#getInstance().endBatch();
+  }
+  static async addDocument(doc) {
+    return this.#getInstance().addDocument(doc);
+  }
+  static async addDocumentIfMissing(doc) {
+    return this.#getInstance().addDocumentIfMissing(doc);
+  }
+  static async addDocuments(docs) {
+    return this.#getInstance().addDocuments(docs);
+  }
+  static async addDocumentsIfMissing(docs) {
+    return this.#getInstance().addDocumentsIfMissing(docs);
+  }
+  static async search(query, limit) {
+    return this.#getInstance().search(query, limit);
+  }
+  static async removeDocument(id) {
+    return this.#getInstance().removeDocument(id);
+  }
+  static async clearAll() {
+    return this.#getInstance().clearAll();
+  }
+  static async getStatus() {
+    return this.#getInstance().getStatus();
+  }
+  /**
+   * 检查文档ID是否曾经添加过（包括已删除的）
+   * @param id 文档ID
+   * @returns 文档是否曾经添加过的布尔值
+   */
+  static async hasDocument(id) {
+    return this.#getInstance().hasDocument(id);
+  }
+  static #getInstance() {
+    return this.#instance || (this.#instance = new SearchEngine(this.config)), this.#instance;
+  }
+}
+export {
+  SimpleSearch
+};

package/lib/type.cjs

@@ -1 +1,3 @@
 "use strict";
+const _ = "";
+exports._ = "";

package/lib/type.d.ts

@@ -66,12 +66,9 @@ interface IStorage {
  */
 type IndexType = 'word' | 'char';
 
-interface ISearchEngineConfig {
-    /**
-     * 数据存储的基础目录 (必填)
-     * 用于区分不同的搜索引擎实例
-     */
-    baseDir: string;
+type IndexingTokenizer = <T extends IDocument = IDocument>(doc: T) => string[];
+type SearchTokenizer = <T extends IDocumentBase = IDocumentBase>(doc: T) => string[];
+interface ISearchEngineOption {
     /**
      * 存储实现配置 (可选)
      * - 'browser': 强制使用 OPFS (BrowserStorage)
@@ -79,7 +76,7 @@ interface ISearchEngineConfig {
      * - IStorage: 传入自定义的存储实例
      * - undefined: 自动检测环境
      */
-    storage?: 'browser' | 'node' | IStorage;
+    storage: IStorage;
     /**
      * 索引时使用的分词器 (算法核心配置)
      * - 作用: 将文档文本转换为索引用的token序列
@@ -87,7 +84,7 @@ interface ISearchEngineConfig {
      * - 建议: 针对不同语言(中文/英文/日文等)使用专门的分词实现
      * - 影响: 直接决定索引的粒度和搜索的准确性
      */
-    indexingTokenizer?: <T extends IDocument = IDocument>(doc: T) => string[];
+    indexingTokenizer?: IndexingTokenizer;
     /**
      * 搜索时使用的分词器 (算法核心配置)
      * - 作用: 将查询文本转换为搜索用的token序列
@@ -95,7 +92,7 @@ interface ISearchEngineConfig {
      * - 建议: 与indexingTokenizer保持一致的分词策略以确保搜索准确性
      * - 影响: 直接决定搜索匹配的范围和结果的相关性
      */
-    searchTokenizer?: <T extends IDocumentBase = IDocumentBase>(doc: T) => string[];
+    searchTokenizer?: SearchTokenizer;
     /**
      * 词索引分段阈值 (Token数) - 分段算法配置
      * - 作用: 控制词索引文件的大小，超过阈值时创建新的索引段
@@ -130,6 +127,52 @@ interface ISearchEngineConfig {
     minCharTokenSave?: number;
 }
 
+interface ISearchEngineStatus {
+    wordSegments: number;
+    charSegments: number;
+    deleted: number;
+    wordCacheSize: number;
+    charCacheSize: number;
+    inBatch: boolean;
+}
+/**
+ * 核心搜索引擎
+ */
+interface ISearchEngine {
+    /**
+     * 开启批处理
+     * 批处理期间 addDocuments 只写入缓存，不触发索引段构建
+     */
+    startBatch(): void;
+    /**
+     * 结束批处理
+     * 触发索引构建检查并保存元数据
+     */
+    endBatch(): Promise<void>;
+    addDocument<T extends IDocument = IDocument>(doc: T): Promise<void>;
+    /**
+     * 添加单个文档，如果文档ID已存在则跳过
+     * 用于在批量添加中途出错后的恢复添加行为，也可直接用于单个文档添加
+     */
+    addDocumentIfMissing<T extends IDocument = IDocument>(doc: T): Promise<void>;
+    /**
+     * 添加多个文档，跳过已存在的文档ID
+     * 用于在批量添加中途出错后的恢复添加行为，也可直接用于批量添加
+     */
+    addDocumentsIfMissing<T extends IDocument = IDocument>(docs: T[]): Promise<void>;
+    addDocuments<T extends IDocument = IDocument>(docs: T[]): Promise<void>;
+    search<T extends IDocumentBase | string = any>(query: string, limit?: number): Promise<IResult[]>;
+    removeDocument(id: number): Promise<void>;
+    clearAll(): Promise<void>;
+    getStatus(): Promise<ISearchEngineStatus>;
+    /**
+     * 检查文档ID是否曾经添加过（包括已删除的）
+     * @param id 文档ID
+     * @returns 文档是否曾经添加过的布尔值
+     */
+    hasDocument(id: number): Promise<boolean>;
+}
+
 
 
-export type { IDocument, IDocumentBase, IIndexMeta, IResult, ISearchEngineConfig, ISegmentMeta, IStorage, ITokenizedDoc, IndexType };
+export type { IDocument, IDocumentBase, IIndexMeta, IResult, ISearchEngine, ISearchEngineOption, ISearchEngineStatus, ISegmentMeta, IStorage, ITokenizedDoc, IndexType, IndexingTokenizer, SearchTokenizer };

package/lib/type.js

@@ -0,0 +1 @@
+const _ = "";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gs-search",
-  "version": "0.1.4",
+  "version": "0.1.6",
   "type": "module",
   "main": "lib/index.cjs",
   "module": "lib/index.js",