gs-search 0.1.2 → 0.1.3

package/lib/index.cjs

@@ -1 +1 @@
-"use strict";Object.create,Object.defineProperty,Object.getOwnPropertyDescriptor,Object.getOwnPropertyNames,Object.getPrototypeOf,Object.prototype.hasOwnProperty;class t{#t;constructor(t){this.#t=t}async#e(){return await(await navigator.storage.getDirectory()).getDirectoryHandle(this.#t,{create:!0})}async write(t,e){const s=await(await(await this.#e()).getFileHandle(t,{create:!0})).createWritable();await s.write(e),await s.close()}async append(t,e){const s=await this.#e();let i;try{i=await s.getFileHandle(t,{create:!0})}catch{i=await s.getFileHandle(t,{create:!0})}const n=await i.getFile(),a=await i.createWritable({keepExistingData:!0});await a.seek(n.size),await a.write(e),await a.close()}async read(t){const e=await this.#e();try{return await(await(await e.getFileHandle(t)).getFile()).arrayBuffer()}catch{return null}}async readRange(t,e,s){const i=await this.#e();try{return await(await(await i.getFileHandle(t)).getFile()).slice(e,s).arrayBuffer()}catch{return null}}async remove(t){const e=await this.#e();try{await e.removeEntry(t)}catch{}}async listFiles(){const t=await this.#e(),e=[];for await(const s of t.keys())e.push(s);return e}async clearAll(){const t=await this.#e();for await(const e of t.keys())await t.removeEntry(e,{recursive:!0})}async getFileSize(t){const e=await this.#e();try{return(await(await e.getFileHandle(t)).getFile()).size}catch{return 0}}}class e{#s=null;#i=null;#t;#n="";constructor(t){this.#t=t}async#a(){if(this.#s)return;const t=await import("node:fs"),e=await import("node:path");this.#s=t.promises,this.#i=e.default||e,this.#n=this.#i.join(process.cwd(),this.#t);try{await this.#s.access(this.#n)}catch{await this.#s.mkdir(this.#n,{recursive:!0})}}#r(t){return this.#i.join(this.#n,t)}async write(t,e){await this.#a(),await this.#s.writeFile(this.#r(t),Buffer.from(e))}async append(t,e){await this.#a(),await this.#s.appendFile(this.#r(t),Buffer.from(e))}async read(t){await this.#a();try{const e=await this.#s.readFile(this.#r(t));return e.buffer.slice(e.byteOffset,e.byteOffset+e.byteLength)}catch{return null}}async readRange(t,e,s){await this.#a();try{const i=await this.#s.open(this.#r(t),"r"),n=s-e,a=Buffer.alloc(n);return await i.read(a,0,n,e),await i.close(),a.buffer.slice(a.byteOffset,a.byteOffset+a.byteLength)}catch{return null}}async remove(t){await this.#a();try{await this.#s.unlink(this.#r(t))}catch{}}async listFiles(){await this.#a();try{return await this.#s.readdir(this.#n)}catch{return[]}}async clearAll(){await this.#a();try{const t=await this.#s.readdir(this.#n);for(const e of t)await this.#s.unlink(this.#i.join(this.#n,e))}catch{}}async getFileSize(t){await this.#a();try{return(await this.#s.stat(this.#r(t))).size}catch{return 0}}}const s="search_meta.json",i="deleted_ids.bin",n="added_ids.bin";class a{#o;#h={wordSegments:[],charSegments:[]};#c=new Set;#d=new Set;constructor(t){this.#o=t}async load(){const t=await this.#o.read(s);if(t){const e=(new TextDecoder).decode(t);this.#h=JSON.parse(e)}else this.#h={wordSegments:[],charSegments:[]};const e=await this.#o.read(i);if(e){const t=new DataView(e);let s=0;const i=e.byteLength;for(;s<i&&!(s+4>i);){const e=t.getUint32(s,!0);this.#c.add(e),s+=4,s<i&&30===t.getUint8(s)&&(s+=1)}}const a=await this.#o.read(n);if(a){const t=new DataView(a);let e=0;const s=a.byteLength;for(;e<s&&!(e+4>s);){const i=t.getUint32(e,!0);this.#d.add(i),e+=4,e<s&&30===t.getUint8(e)&&(e+=1)}}}async save(){const t=JSON.stringify(this.#h);if(await this.#o.write(s,(new TextEncoder).encode(t).buffer),0===this.#c.size)await this.#o.remove(i);else{const t=4*this.#c.size+this.#c.size,e=new ArrayBuffer(t),s=new DataView(e);let n=0;for(const t of this.#c)s.setUint32(n,t,!0),n+=4,s.setUint8(n,30),n+=1;await this.#o.write(i,e)}if(0===this.#d.size)await this.#o.remove(n);else{const t=4*this.#d.size+this.#d.size,e=new ArrayBuffer(t),s=new DataView(e);let i=0;for(const t of this.#d)s.setUint32(i,t,!0),i+=4,s.setUint8(i,30),i+=1;await this.#o.write(n,e)}}getSegments(t){return"word"===t?this.#h.wordSegments:this.#h.charSegments}getDeletedIds(){return this.#c}addDeletedId(t){this.#c.add(t)}isDeleted(t){return this.#c.has(t)}addAddedId(t){this.#d.add(t)}removeAddedId(t){this.#d.delete(t)}isAdded(t){return this.#d.has(t)}getAddedIds(){return this.#d}hasDocument(t){return this.#d.has(t)||this.#c.has(t)}getLastSegmentInfo(t){const e=this.getSegments(t);return 0===e.length?null:e[e.length-1]}updateSegment(t,e,s,i,n,a){const r="word"===t?this.#h.wordSegments:this.#h.charSegments;if(a)r.push({filename:e,start:s,end:i,tokenCount:n});else{const t=r[r.length-1];t&&t.filename===e&&(t.end=i,t.tokenCount=n)}}reset(){this.#h={wordSegments:[],charSegments:[]},this.#c.clear(),this.#d.clear()}}class r{static SEPARATOR=30;#o;constructor(t){this.#o=t}async appendBatch(t,e){if(0===e.length)return await this.#o.getFileSize(t);const s=new TextEncoder;let i=0;for(const t of e){i+=8;for(const e of t.tokens){i+=2+Math.min(s.encode(e).byteLength,65535)}i+=1}const n=new Uint8Array(i);let a=0;for(const t of e){const e=[];for(const i of t.tokens){const t=s.encode(i),n=t.byteLength>65535?t.slice(0,65535):t;e.push(n)}const i=new DataView(n.buffer,a);i.setUint32(0,t.id,!0),i.setUint32(4,e.length,!0),a+=8;for(const t of e)new DataView(n.buffer,a).setUint16(0,t.byteLength,!0),a+=2,n.set(t,a),a+=t.byteLength;n[a++]=r.SEPARATOR}return await this.#o.append(t,n.buffer),await this.#o.getFileSize(t)}async readRange(t,e,s){const i=await this.#o.readRange(t,e,s);if(!i||0===i.byteLength)return[];const n=new DataView(i),a=new Uint8Array(i),o=new TextDecoder,h=[];let c=0;const d=i.byteLength;for(;c<d&&!(c+8>d);){const t=n.getUint32(c,!0);c+=4;const e=n.getUint32(c,!0);c+=4;const s=[];for(let t=0;t<e&&!(c+2>d);t++){const t=n.getUint16(c,!0);if(c+=2,c+t>d)break;const e=new Uint8Array(i,c,t);s.push(o.decode(e)),c+=t}c<d&&a[c]===r.SEPARATOR&&(c+=1),h.push({id:t,tokens:s})}return h}async getCurrentSize(t){return await this.#o.getFileSize(t)}}class o{#g;#o;#l=null;#f=null;static hash(t){let e=5381;for(let s=0;s<t.length;s++)e=(e<<5)+e^t.charCodeAt(s);return e>>>0}constructor(t,e){this.#g=t,this.#o=e}async loadIndex(){return!!this.#l||(this.#l=await this.#o.read(this.#g),!!this.#l&&(this.#f=new DataView(this.#l),!0))}async buildAndSave(t){const e=new Map;for(const s of t){const t=new Map;for(const i of s.tokens)if(!t.has(i)){t.set(i,!0);const n=o.hash(i);e.has(n)||e.set(n,[]),e.get(n).push(s.id)}}const s=Array.from(e.keys()).sort((t,e)=>t-e);let i=0;const n=new Array(s.length);for(let t=0;t<s.length;t++){const a=s[t],r=e.get(a);n[t]=r,i+=r.length}const a=12*s.length,r=new ArrayBuffer(8+a+4*i),h=new DataView(r);h.setUint32(0,1229866072),h.setUint32(4,s.length);let c=8,d=8+a;for(let t=0;t<s.length;t++){const e=s[t],i=n[t];h.setUint32(c,e),h.setUint32(c+4,d),h.setUint32(c+8,i.length),c+=12;for(let t=0;t<i.length;t++)h.setUint32(d,i[t],!0),d+=4}await this.#o.write(this.#g,r),this.#l=r,this.#f=h}search(t){if(!this.#f||!this.#l)return[];const e=o.hash(t);let s=0,i=this.#f.getUint32(4)-1;for(;s<=i;){const t=s+i>>>1,n=8+12*t,a=this.#f.getUint32(n);if(a<e)s=t+1;else{if(!(a>e)){const t=this.#f.getUint32(n+4),e=this.#f.getUint32(n+8),s=[];for(let i=0;i<e;i++)s.push(this.#f.getUint32(t+4*i,!0));return s}i=t-1}}return[]}}const h="word_cache.bin",c="char_cache.bin";class d{#o;#h;#w;#u;#m=!1;#y;#p=!1;#D={word:0,char:0};constructor(s){if(!s.baseDir)throw new Error("SearchEngine requires 'baseDir' in config.");if(this.#y={wordSegmentTokenThreshold:1e5,charSegmentTokenThreshold:5e5,minWordTokenSave:0,minCharTokenSave:0,...s},(this.#y.minWordTokenSave||0)>=(this.#y.wordSegmentTokenThreshold||1e5))throw new Error("minWordTokenSave must be less than wordSegmentTokenThreshold");if((this.#y.minCharTokenSave||0)>=(this.#y.charSegmentTokenThreshold||5e5))throw new Error("minCharTokenSave must be less than charSegmentTokenThreshold");let i=null;if(this.#y.storage&&("object"==typeof this.#y.storage?i=this.#y.storage:"browser"===this.#y.storage?i=new t(this.#y.baseDir):"node"===this.#y.storage&&(i=new e(this.#y.baseDir))),!i){const s=typeof navigator<"u"&&navigator?.storage?.getDirectory instanceof Function,n=typeof process<"u"&&null!=process.versions&&null!=process.versions.node;s?i=new t(this.#y.baseDir):n&&(i=new e(this.#y.baseDir))}if(!i)throw new Error('Storage initialization failed. Please configure "storage" explicitly or ensure you are in a supported environment (Browser/Node).');this.#o=i,this.#h=new a(this.#o),this.#w=new r(this.#o),this.#u=new Map}async init(){if(this.#m)return;await this.#h.load();const t=[...this.#h.getSegments("word"),...this.#h.getSegments("char")];for(const e of t)this.#u.has(e.filename)||this.#u.set(e.filename,new o(e.filename,this.#o)),await this.#u.get(e.filename).loadIndex();this.#m=!0}startBatch(){this.#p=!0,this.#D={word:0,char:0}}async endBatch(){this.#p=!1,this.#D.word>0&&await this.#S("word",this.#D.word),this.#D.char>0&&await this.#S("char",this.#D.char),this.#D={word:0,char:0},await this.#h.save()}#k(t){try{if(typeof Intl<"u"&&"function"==typeof Intl.Segmenter&&"function"==typeof Array.from){const e=new Intl.Segmenter([],{granularity:"word"}).segment(t);if("object"==typeof e&&null!==e)return Array.from(e).filter(t=>t?.isWordLike).map(t=>t?.segment?.toLowerCase()||"")}}catch{}return t.toLowerCase().split(/[^a-z0-9\u4e00-\u9fa5]+/g).filter(t=>t.length>0)}#I(t){return this.#y.indexingTokenizer?this.#y.indexingTokenizer(t):this.#k(t.text)}#b(t){return this.#y.searchTokenizer?this.#y.searchTokenizer(t):this.#I(t)}async addDocument(t){return this.addDocuments([t])}async addDocumentIfMissing(t){return this.addDocumentsIfMissing([t])}async addDocumentsIfMissing(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[],n=[];for(const a of t){if(e.has(a.id)||this.#h.isAdded(a.id))continue;const t=this.#I(a),r=[],o=[];for(const e of t)e.length>1?r.push(e):1===e.length&&o.push(e);r.length>0&&s.push({id:a.id,tokens:r}),o.length>0&&i.push({id:a.id,tokens:o}),n.push(a)}if(0===n.length)return;let a=0,r=0;if(s.length>0){await this.#w.appendBatch(h,s);for(const t of s)a+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(c,i);for(const t of i)r+=t.tokens.length}for(const t of n)this.#h.addAddedId(t.id);this.#p?(this.#D.word+=a,this.#D.char+=r):(a>0&&await this.#S("word",a),r>0&&await this.#S("char",r),await this.#h.save())}async addDocuments(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[];for(const n of t){if(e.has(n.id))throw new Error(`Document ID ${n.id} has been deleted and cannot be re-added.`);if(this.#h.isAdded(n.id))throw new Error(`Document ID ${n.id} already exists.`);const t=this.#I(n),a=[],r=[];for(const e of t)e.length>1?a.push(e):1===e.length&&r.push(e);a.length>0&&s.push({id:n.id,tokens:a}),r.length>0&&i.push({id:n.id,tokens:r})}let n=0,a=0;if(s.length>0){await this.#w.appendBatch(h,s);for(const t of s)n+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(c,i);for(const t of i)a+=t.tokens.length}for(const e of t)this.#h.addAddedId(e.id);this.#p?(this.#D.word+=n,this.#D.char+=a):(n>0&&await this.#S("word",n),a>0&&await this.#S("char",a),await this.#h.save())}async#S(t,e){const s="word"===t?h:c,i=await this.#w.getCurrentSize(s),n="word"===t?this.#y.wordSegmentTokenThreshold||1e5:this.#y.charSegmentTokenThreshold||5e5,a="word"===t?this.#y.minWordTokenSave||0:this.#y.minCharTokenSave||0,r=this.#h.getLastSegmentInfo(t);let d,g,l,f;const w=()=>{const e=this.#h.getSegments(t).length+1;return`${t}_seg_${e}.bin`};if(r){const t=r.tokenCount;t>=n||t+e>=n?(d=w(),l=!0,g=r.end,f=e):(d=r.filename,l=!1,g=r.start,f=t+e)}else d=w(),l=!0,g=0,f=e;if(f<a)return void this.#h.updateSegment(t,d,g,i,f,l);const u=await this.#w.readRange(s,g,i);let m=this.#u.get(d);m||(m=new o(d,this.#o),this.#u.set(d,m)),await m.buildAndSave(u),this.#h.updateSegment(t,d,g,i,f,l)}async search(t,e){this.#m||await this.init();const s="string"==typeof t?{text:t}:t,i=this.#b(s),n=i.filter(t=>t.length>1),a=i.filter(t=>1===t.length),r=this.#h.getDeletedIds(),h=new Map,c=new Map,d=t=>{const e=this.#h.getSegments(t);for(const t of e){const e=t.filename;!this.#u.has(e)&&!c.has(e)&&c.set(e,new o(e,this.#o))}};d("word"),d("char"),await Promise.all(Array.from(c.entries()).map(([t,e])=>e.loadIndex().then(s=>{s&&this.#u.set(t,e)})));const g=async(t,e)=>{if(0===e.length)return;const s=this.#h.getSegments(t);for(const t of s){const s=t.filename,i=this.#u.get(s);if(i)for(const t of e){const e=i.search(t),s=1+.1*t.length;for(const i of e)if(!r.has(i))if(h.has(i)){const e=h.get(i);e.score+=s,e.tokens.add(t)}else h.set(i,{score:0,tokens:new Set([t])})}}};await g("word",n),await g("char",a);const l=[];return h.forEach((t,e)=>{l.push({id:e,score:t.score,tokens:Array.from(t.tokens)})}),l.sort((t,e)=>e.score-t.score),"number"==typeof e&&e>0?l.slice(0,e):l}async removeDocument(t){this.#m||await this.init(),this.#h.addDeletedId(t),this.#h.removeAddedId(t),await this.#h.save()}async clearAll(){await this.#o.clearAll(),this.#u.clear(),this.#h.reset(),this.#m=!1,this.#p=!1,this.#D={word:0,char:0}}async getStatus(){return this.#m||await this.init(),{wordSegments:this.#h.getSegments("word").length,charSegments:this.#h.getSegments("char").length,deleted:this.#h.getDeletedIds().size,wordCacheSize:await this.#w.getCurrentSize(h),charCacheSize:await this.#w.getCurrentSize(c),inBatch:this.#p}}async hasDocument(t){return this.#m||await this.init(),this.#h.hasDocument(t)}}exports.BrowserStorage=t,exports.NodeStorage=e,exports.SearchEngine=d,exports.SimpleSearch=class{static#T=null;static#v={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(t){const e={...this.#v,...t};this.#T=new d(e)}static#z(){return this.#T||(this.#T=new d(this.#v)),this.#T}static async startBatch(){this.#z().startBatch()}static async endBatch(){return this.#z().endBatch()}static async addDocument(t){return this.#z().addDocument(t)}static async addDocumentIfMissing(t){return this.#z().addDocumentIfMissing(t)}static async addDocuments(t){return this.#z().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#z().addDocumentsIfMissing(t)}static async search(t,e){return this.#z().search(t,e)}static async removeDocument(t){return this.#z().removeDocument(t)}static async clearAll(){return this.#z().clearAll()}static async getStatus(){return this.#z().getStatus()}static async hasDocument(t){return this.#z().hasDocument(t)}};
+"use strict";Object.create,Object.defineProperty,Object.getOwnPropertyDescriptor,Object.getOwnPropertyNames,Object.getPrototypeOf,Object.prototype.hasOwnProperty;class t{#t;constructor(t){this.#t=t}async#e(){return await(await navigator.storage.getDirectory()).getDirectoryHandle(this.#t,{create:!0})}async write(t,e){const s=await(await(await this.#e()).getFileHandle(t,{create:!0})).createWritable();await s.write(e),await s.close()}async append(t,e){const s=await this.#e();let i;try{i=await s.getFileHandle(t,{create:!0})}catch{i=await s.getFileHandle(t,{create:!0})}const n=await i.getFile(),a=await i.createWritable({keepExistingData:!0});await a.seek(n.size),await a.write(e),await a.close()}async read(t){const e=await this.#e();try{return await(await(await e.getFileHandle(t)).getFile()).arrayBuffer()}catch{return null}}async readRange(t,e,s){const i=await this.#e();try{return await(await(await i.getFileHandle(t)).getFile()).slice(e,s).arrayBuffer()}catch{return null}}async remove(t){const e=await this.#e();try{await e.removeEntry(t)}catch{}}async listFiles(){const t=await this.#e(),e=[];for await(const s of t.keys())e.push(s);return e}async clearAll(){const t=await this.#e();for await(const e of t.keys())await t.removeEntry(e,{recursive:!0})}async getFileSize(t){const e=await this.#e();try{return(await(await e.getFileHandle(t)).getFile()).size}catch{return 0}}}class e{#s=null;#i=null;#t;#n="";constructor(t){this.#t=t}async#a(){if(this.#s)return;const t=await import("node:fs"),e=await import("node:path");this.#s=t.promises,this.#i=e.default||e,this.#n=this.#i.join(process.cwd(),this.#t);try{await this.#s.access(this.#n)}catch{await this.#s.mkdir(this.#n,{recursive:!0})}}#r(t){return this.#i.join(this.#n,t)}async write(t,e){await this.#a(),await this.#s.writeFile(this.#r(t),Buffer.from(e))}async append(t,e){await this.#a(),await this.#s.appendFile(this.#r(t),Buffer.from(e))}async read(t){await this.#a();try{const e=await this.#s.readFile(this.#r(t));return e.buffer.slice(e.byteOffset,e.byteOffset+e.byteLength)}catch{return null}}async readRange(t,e,s){await this.#a();try{const i=await this.#s.open(this.#r(t),"r"),n=s-e,a=Buffer.alloc(n);return await i.read(a,0,n,e),await i.close(),a.buffer.slice(a.byteOffset,a.byteOffset+a.byteLength)}catch{return null}}async remove(t){await this.#a();try{await this.#s.unlink(this.#r(t))}catch{}}async listFiles(){await this.#a();try{return await this.#s.readdir(this.#n)}catch{return[]}}async clearAll(){await this.#a();try{const t=await this.#s.readdir(this.#n);for(const e of t)await this.#s.unlink(this.#i.join(this.#n,e))}catch{}}async getFileSize(t){await this.#a();try{return(await this.#s.stat(this.#r(t))).size}catch{return 0}}}const s="search_meta.json",i="deleted_ids.bin",n="added_ids.bin";class a{#o;#h={wordSegments:[],charSegments:[]};#c=new Set;#d=new Set;constructor(t){this.#o=t}async load(){const t=await this.#o.read(s);if(t){const e=(new TextDecoder).decode(t);this.#h=JSON.parse(e)}else this.#h={wordSegments:[],charSegments:[]};const e=await this.#o.read(i);if(e){const t=new DataView(e);let s=0;const i=e.byteLength;for(;s<i&&!(s+4>i);){const e=t.getUint32(s,!0);this.#c.add(e),s+=4,s<i&&30===t.getUint8(s)&&(s+=1)}}const a=await this.#o.read(n);if(a){const t=new DataView(a);let e=0;const s=a.byteLength;for(;e<s&&!(e+4>s);){const i=t.getUint32(e,!0);this.#d.add(i),e+=4,e<s&&30===t.getUint8(e)&&(e+=1)}}}async save(){const t=JSON.stringify(this.#h);if(await this.#o.write(s,(new TextEncoder).encode(t).buffer),0===this.#c.size)await this.#o.remove(i);else{const t=4*this.#c.size+this.#c.size,e=new ArrayBuffer(t),s=new DataView(e);let n=0;for(const t of this.#c)s.setUint32(n,t,!0),n+=4,s.setUint8(n,30),n+=1;await this.#o.write(i,e)}if(0===this.#d.size)await this.#o.remove(n);else{const t=4*this.#d.size+this.#d.size,e=new ArrayBuffer(t),s=new DataView(e);let i=0;for(const t of this.#d)s.setUint32(i,t,!0),i+=4,s.setUint8(i,30),i+=1;await this.#o.write(n,e)}}getSegments(t){return"word"===t?this.#h.wordSegments:this.#h.charSegments}getDeletedIds(){return this.#c}addDeletedId(t){this.#c.add(t)}isDeleted(t){return this.#c.has(t)}addAddedId(t){this.#d.add(t)}removeAddedId(t){this.#d.delete(t)}isAdded(t){return this.#d.has(t)}getAddedIds(){return this.#d}hasDocument(t){return this.#d.has(t)||this.#c.has(t)}getLastSegmentInfo(t){const e=this.getSegments(t);return 0===e.length?null:e[e.length-1]}updateSegment(t,e,s,i,n,a){const r="word"===t?this.#h.wordSegments:this.#h.charSegments;if(a)r.push({filename:e,start:s,end:i,tokenCount:n});else{const t=r[r.length-1];t&&t.filename===e&&(t.end=i,t.tokenCount=n)}}reset(){this.#h={wordSegments:[],charSegments:[]},this.#c.clear(),this.#d.clear()}}class r{static SEPARATOR=30;#o;constructor(t){this.#o=t}async appendBatch(t,e){if(0===e.length)return await this.#o.getFileSize(t);const s=new TextEncoder;let i=0;for(const t of e){i+=8;for(const e of t.tokens){i+=2+Math.min(s.encode(e).byteLength,65535)}i+=1}const n=new Uint8Array(i);let a=0;for(const t of e){const e=[];for(const i of t.tokens){const t=s.encode(i),n=t.byteLength>65535?t.slice(0,65535):t;e.push(n)}const i=new DataView(n.buffer,a);i.setUint32(0,t.id,!0),i.setUint32(4,e.length,!0),a+=8;for(const t of e)new DataView(n.buffer,a).setUint16(0,t.byteLength,!0),a+=2,n.set(t,a),a+=t.byteLength;n[a++]=r.SEPARATOR}return await this.#o.append(t,n.buffer),await this.#o.getFileSize(t)}async readRange(t,e,s){const i=await this.#o.readRange(t,e,s);if(!i||0===i.byteLength)return[];const n=new DataView(i),a=new Uint8Array(i),o=new TextDecoder,h=[];let c=0;const d=i.byteLength;for(;c<d&&!(c+8>d);){const t=n.getUint32(c,!0);c+=4;const e=n.getUint32(c,!0);c+=4;const s=[];for(let t=0;t<e&&!(c+2>d);t++){const t=n.getUint16(c,!0);if(c+=2,c+t>d)break;const e=new Uint8Array(i,c,t);s.push(o.decode(e)),c+=t}c<d&&a[c]===r.SEPARATOR&&(c+=1),h.push({id:t,tokens:s})}return h}async getCurrentSize(t){return await this.#o.getFileSize(t)}}function o(t,e=305419896){const s=t.length,i=s>>2;let n=0;for(;n<i;){let s=255&t.charCodeAt(n)|(255&t.charCodeAt(++n))<<8|(255&t.charCodeAt(++n))<<16|(255&t.charCodeAt(++n))<<24;++n,s=3432918353*(65535&s)+((3432918353*(s>>>16)&65535)<<16)&4294967295,s=s<<15|s>>>17,s=461845907*(65535&s)+((461845907*(s>>>16)&65535)<<16)&4294967295,e=27492+(65535&(e=5*(65535&(e=(e^=s)<<13|e>>>19))+((5*(e>>>16)&65535)<<16)&4294967295))+(((e>>>16)+58964&65535)<<16)}let a=0;const r=3&s;return r>0&&(r>=3&&(a^=(255&t.charCodeAt(n+2))<<16),r>=2&&(a^=(255&t.charCodeAt(n+1))<<8),r>=1&&(a^=255&t.charCodeAt(n)),a=3432918353*(65535&a)+((3432918353*(a>>>16)&65535)<<16)&4294967295,a=a<<15|a>>>17,a=461845907*(65535&a)+((461845907*(a>>>16)&65535)<<16)&4294967295,e^=a),e^=s,e=2246822507*(65535&(e^=e>>>16))+((2246822507*(e>>>16)&65535)<<16)&4294967295,e=3266489909*(65535&(e^=e>>>13))+((3266489909*(e>>>16)&65535)<<16)&4294967295,(e^=e>>>16)>>>0}class h{#g;#o;#l=null;#f=null;static hash(t){return o(t)}constructor(t,e){this.#g=t,this.#o=e}async loadIndex(){return!!this.#l||(this.#l=await this.#o.read(this.#g),!!this.#l&&(this.#f=new DataView(this.#l),!0))}async buildAndSave(t){const e=new Map;for(const s of t){const t=new Map;for(const i of s.tokens)t.has(i)||(t.set(i,!0),e.has(i)||e.set(i,{hash:h.hash(i),postings:[]}),e.get(i).postings.push(s.id))}const s=Array.from(e.entries());s.sort(([t,{hash:e}],[s,{hash:i}])=>e!==i?e-i:t.localeCompare(s));let i=0,n=0;for(const[t,{postings:e}]of s)i+=e.length,n+=t.length+1;const a=20*s.length,r=12+a+4*i,o=new ArrayBuffer(r+n),c=new DataView(o);c.setUint32(0,1229866072),c.setUint32(4,s.length),c.setUint32(8,r);let d=12,g=12+a,l=r;for(const[t,{hash:e,postings:i}]of s){c.setUint32(d,e),c.setUint32(d+4,t.length),c.setUint32(d+8,l),c.setUint32(d+12,g),c.setUint32(d+16,i.length),d+=20;for(let t=0;t<i.length;t++)c.setUint32(g,i[t],!0),g+=4;const s=(new TextEncoder).encode(t);for(let t=0;t<s.length;t++)c.setUint8(l++,s[t]);c.setUint8(l++,0)}await this.#o.write(this.#g,o),this.#l=o,this.#f=c}search(t){if(!this.#f||!this.#l)return[];const e=h.hash(t),s=this.#f.getUint32(4);let i=0,n=s-1;const a=12,r=20,o=new TextDecoder;for(;i<=n;){const h=i+n>>>1,c=a+h*r,d=this.#f.getUint32(c);if(d<e)i=h+1;else{if(!(d>e)){if(!(h>0&&this.#f.getUint32(a+(h-1)*r)===e||h<s-1&&this.#f.getUint32(a+(h+1)*r)===e)){const t=this.#f.getUint32(a+h*r+12),e=this.#f.getUint32(a+h*r+16),s=[];for(let i=0;i<e;i++)s.push(this.#f.getUint32(t+4*i,!0));return s}let i=h;for(;i>0;){const t=a+(i-1)*r;if(this.#f.getUint32(t)!==e)break;i--}for(let n=i;n<s;n++){const s=a+n*r;if(this.#f.getUint32(s)!==e)break;const i=this.#f.getUint32(s+4),h=this.#f.getUint32(s+8),c=new Uint8Array(this.#l,h,i);if(o.decode(c)===t){const t=this.#f.getUint32(s+12),e=this.#f.getUint32(s+16),i=[];for(let s=0;s<e;s++)i.push(this.#f.getUint32(t+4*s,!0));return i}}return[]}n=h-1}}return[]}}const c="word_cache.bin",d="char_cache.bin";class g{#o;#h;#w;#u;#m=!1;#p;#y=!1;#D={word:0,char:0};constructor(s){if(!s.baseDir)throw new Error("SearchEngine requires 'baseDir' in config.");if(this.#p={wordSegmentTokenThreshold:1e5,charSegmentTokenThreshold:5e5,minWordTokenSave:0,minCharTokenSave:0,...s},(this.#p.minWordTokenSave||0)>=(this.#p.wordSegmentTokenThreshold||1e5))throw new Error("minWordTokenSave must be less than wordSegmentTokenThreshold");if((this.#p.minCharTokenSave||0)>=(this.#p.charSegmentTokenThreshold||5e5))throw new Error("minCharTokenSave must be less than charSegmentTokenThreshold");let i=null;if(this.#p.storage&&("object"==typeof this.#p.storage?i=this.#p.storage:"browser"===this.#p.storage?i=new t(this.#p.baseDir):"node"===this.#p.storage&&(i=new e(this.#p.baseDir))),!i){const s=typeof navigator<"u"&&navigator?.storage?.getDirectory instanceof Function,n=typeof process<"u"&&null!=process.versions&&null!=process.versions.node;s?i=new t(this.#p.baseDir):n&&(i=new e(this.#p.baseDir))}if(!i)throw new Error('Storage initialization failed. Please configure "storage" explicitly or ensure you are in a supported environment (Browser/Node).');this.#o=i,this.#h=new a(this.#o),this.#w=new r(this.#o),this.#u=new Map}async init(){if(this.#m)return;await this.#h.load();const t=[...this.#h.getSegments("word"),...this.#h.getSegments("char")];for(const e of t)this.#u.has(e.filename)||this.#u.set(e.filename,new h(e.filename,this.#o)),await this.#u.get(e.filename).loadIndex();this.#m=!0}startBatch(){this.#y=!0,this.#D={word:0,char:0}}async endBatch(){this.#y=!1,this.#D.word>0&&await this.#S("word",this.#D.word),this.#D.char>0&&await this.#S("char",this.#D.char),this.#D={word:0,char:0},await this.#h.save()}#k(t){try{if(typeof Intl<"u"&&"function"==typeof Intl.Segmenter&&"function"==typeof Array.from){const e=new Intl.Segmenter([],{granularity:"word"}).segment(t);if("object"==typeof e&&null!==e)return Array.from(e).filter(t=>t?.isWordLike).map(t=>t?.segment?.toLowerCase()||"")}}catch{}return t.toLowerCase().split(/[^a-z0-9\u4e00-\u9fa5]+/g).filter(t=>t.length>0)}#I(t){return this.#p.indexingTokenizer?this.#p.indexingTokenizer(t):this.#k(t.text)}#b(t){return this.#p.searchTokenizer?this.#p.searchTokenizer(t):this.#I(t)}async addDocument(t){return this.addDocuments([t])}async addDocumentIfMissing(t){return this.addDocumentsIfMissing([t])}async addDocumentsIfMissing(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[],n=[];for(const a of t){if(e.has(a.id)||this.#h.isAdded(a.id))continue;const t=this.#I(a),r=[],o=[];for(const e of t)e.length>1?r.push(e):1===e.length&&o.push(e);r.length>0&&s.push({id:a.id,tokens:r}),o.length>0&&i.push({id:a.id,tokens:o}),n.push(a)}if(0===n.length)return;let a=0,r=0;if(s.length>0){await this.#w.appendBatch(c,s);for(const t of s)a+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(d,i);for(const t of i)r+=t.tokens.length}for(const t of n)this.#h.addAddedId(t.id);this.#y?(this.#D.word+=a,this.#D.char+=r):(a>0&&await this.#S("word",a),r>0&&await this.#S("char",r),await this.#h.save())}async addDocuments(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[];for(const n of t){if(e.has(n.id))throw new Error(`Document ID ${n.id} has been deleted and cannot be re-added.`);if(this.#h.isAdded(n.id))throw new Error(`Document ID ${n.id} already exists.`);const t=this.#I(n),a=[],r=[];for(const e of t)e.length>1?a.push(e):1===e.length&&r.push(e);a.length>0&&s.push({id:n.id,tokens:a}),r.length>0&&i.push({id:n.id,tokens:r})}let n=0,a=0;if(s.length>0){await this.#w.appendBatch(c,s);for(const t of s)n+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(d,i);for(const t of i)a+=t.tokens.length}for(const e of t)this.#h.addAddedId(e.id);this.#y?(this.#D.word+=n,this.#D.char+=a):(n>0&&await this.#S("word",n),a>0&&await this.#S("char",a),await this.#h.save())}async#S(t,e){const s="word"===t?c:d,i=await this.#w.getCurrentSize(s),n="word"===t?this.#p.wordSegmentTokenThreshold||1e5:this.#p.charSegmentTokenThreshold||5e5,a="word"===t?this.#p.minWordTokenSave||0:this.#p.minCharTokenSave||0,r=this.#h.getLastSegmentInfo(t);let o,g,l,f;const w=()=>{const e=this.#h.getSegments(t).length+1;return`${t}_seg_${e}.bin`};if(r){const t=r.tokenCount;t>=n||t+e>=n?(o=w(),l=!0,g=r.end,f=e):(o=r.filename,l=!1,g=r.start,f=t+e)}else o=w(),l=!0,g=0,f=e;if(f<a)return void this.#h.updateSegment(t,o,g,i,f,l);const u=await this.#w.readRange(s,g,i);let m=this.#u.get(o);m||(m=new h(o,this.#o),this.#u.set(o,m)),await m.buildAndSave(u),this.#h.updateSegment(t,o,g,i,f,l)}async search(t,e){this.#m||await this.init();const s="string"==typeof t?{text:t}:t,i=this.#b(s),n=i.filter(t=>t.length>1),a=i.filter(t=>1===t.length),r=this.#h.getDeletedIds(),o=new Map,c=new Map,d=t=>{const e=this.#h.getSegments(t);for(const t of e){const e=t.filename;!this.#u.has(e)&&!c.has(e)&&c.set(e,new h(e,this.#o))}};d("word"),d("char"),await Promise.all(Array.from(c.entries()).map(([t,e])=>e.loadIndex().then(s=>{s&&this.#u.set(t,e)})));const g=async(t,e)=>{if(0===e.length)return;const s=this.#h.getSegments(t);for(const t of s){const s=t.filename,i=this.#u.get(s);if(i)for(const t of e){const e=i.search(t),s=1+.1*t.length;for(const i of e)if(!r.has(i))if(o.has(i)){const e=o.get(i);e.score+=s,e.tokens.add(t)}else o.set(i,{score:0,tokens:new Set([t])})}}};await g("word",n),await g("char",a);const l=[];return o.forEach((t,e)=>{l.push({id:e,score:t.score,tokens:Array.from(t.tokens)})}),l.sort((t,e)=>e.score-t.score),"number"==typeof e&&e>0?l.slice(0,e):l}async removeDocument(t){this.#m||await this.init(),this.#h.addDeletedId(t),this.#h.removeAddedId(t),await this.#h.save()}async clearAll(){await this.#o.clearAll(),this.#u.clear(),this.#h.reset(),this.#m=!1,this.#y=!1,this.#D={word:0,char:0}}async getStatus(){return this.#m||await this.init(),{wordSegments:this.#h.getSegments("word").length,charSegments:this.#h.getSegments("char").length,deleted:this.#h.getDeletedIds().size,wordCacheSize:await this.#w.getCurrentSize(c),charCacheSize:await this.#w.getCurrentSize(d),inBatch:this.#y}}async hasDocument(t){return this.#m||await this.init(),this.#h.hasDocument(t)}}exports.BrowserStorage=t,exports.NodeStorage=e,exports.SearchEngine=g,exports.SimpleSearch=class{static#T=null;static#v={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(t){const e={...this.#v,...t};this.#T=new g(e)}static#U(){return this.#T||(this.#T=new g(this.#v)),this.#T}static async startBatch(){this.#U().startBatch()}static async endBatch(){return this.#U().endBatch()}static async addDocument(t){return this.#U().addDocument(t)}static async addDocumentIfMissing(t){return this.#U().addDocumentIfMissing(t)}static async addDocuments(t){return this.#U().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#U().addDocumentsIfMissing(t)}static async search(t,e){return this.#U().search(t,e)}static async removeDocument(t){return this.#U().removeDocument(t)}static async clearAll(){return this.#U().clearAll()}static async getStatus(){return this.#U().getStatus()}static async hasDocument(t){return this.#U().hasDocument(t)}},exports.hash=o,exports.murmur3_32=o;

package/lib/index.d.ts

@@ -221,5 +221,17 @@ declare class NodeStorage implements IStorage {
     getFileSize(filename: string): Promise<number>;
 }
 
-export { BrowserStorage, NodeStorage, SearchEngine, SimpleSearch };
+/**
+ * MurmurHash3 32位实现
+ * 高效的非加密哈希函数，适用于哈希表等数据结构
+ */
+/**
+ * 计算字符串的32位MurmurHash3哈希值
+ * @param str 要哈希的字符串
+ * @param h
+ * @returns 32位无符号哈希值
+ */
+declare function murmur3_32(str: string, h?: number): number;
+
+export { BrowserStorage, NodeStorage, SearchEngine, SimpleSearch, murmur3_32 as hash, murmur3_32 };
 export type { IDocument, IDocumentBase, IIndexMeta, IResult, ISearchEngineConfig, ISegmentMeta, IStorage, ITokenizedDoc, IndexType };

package/lib/index.js

@@ -1 +1 @@
-class t{#t;constructor(t){this.#t=t}async#e(){return await(await navigator.storage.getDirectory()).getDirectoryHandle(this.#t,{create:!0})}async write(t,e){const s=await(await(await this.#e()).getFileHandle(t,{create:!0})).createWritable();await s.write(e),await s.close()}async append(t,e){const s=await this.#e();let i;try{i=await s.getFileHandle(t,{create:!0})}catch{i=await s.getFileHandle(t,{create:!0})}const n=await i.getFile(),a=await i.createWritable({keepExistingData:!0});await a.seek(n.size),await a.write(e),await a.close()}async read(t){const e=await this.#e();try{return await(await(await e.getFileHandle(t)).getFile()).arrayBuffer()}catch{return null}}async readRange(t,e,s){const i=await this.#e();try{return await(await(await i.getFileHandle(t)).getFile()).slice(e,s).arrayBuffer()}catch{return null}}async remove(t){const e=await this.#e();try{await e.removeEntry(t)}catch{}}async listFiles(){const t=await this.#e(),e=[];for await(const s of t.keys())e.push(s);return e}async clearAll(){const t=await this.#e();for await(const e of t.keys())await t.removeEntry(e,{recursive:!0})}async getFileSize(t){const e=await this.#e();try{return(await(await e.getFileHandle(t)).getFile()).size}catch{return 0}}}class e{#s=null;#i=null;#t;#n="";constructor(t){this.#t=t}async#a(){if(this.#s)return;const t=await import("node:fs"),e=await import("node:path");this.#s=t.promises,this.#i=e.default||e,this.#n=this.#i.join(process.cwd(),this.#t);try{await this.#s.access(this.#n)}catch{await this.#s.mkdir(this.#n,{recursive:!0})}}#r(t){return this.#i.join(this.#n,t)}async write(t,e){await this.#a(),await this.#s.writeFile(this.#r(t),Buffer.from(e))}async append(t,e){await this.#a(),await this.#s.appendFile(this.#r(t),Buffer.from(e))}async read(t){await this.#a();try{const e=await this.#s.readFile(this.#r(t));return e.buffer.slice(e.byteOffset,e.byteOffset+e.byteLength)}catch{return null}}async readRange(t,e,s){await this.#a();try{const i=await this.#s.open(this.#r(t),"r"),n=s-e,a=Buffer.alloc(n);return await i.read(a,0,n,e),await i.close(),a.buffer.slice(a.byteOffset,a.byteOffset+a.byteLength)}catch{return null}}async remove(t){await this.#a();try{await this.#s.unlink(this.#r(t))}catch{}}async listFiles(){await this.#a();try{return await this.#s.readdir(this.#n)}catch{return[]}}async clearAll(){await this.#a();try{const t=await this.#s.readdir(this.#n);for(const e of t)await this.#s.unlink(this.#i.join(this.#n,e))}catch{}}async getFileSize(t){await this.#a();try{return(await this.#s.stat(this.#r(t))).size}catch{return 0}}}const s="search_meta.json",i="deleted_ids.bin",n="added_ids.bin";class a{#o;#h={wordSegments:[],charSegments:[]};#c=new Set;#d=new Set;constructor(t){this.#o=t}async load(){const t=await this.#o.read(s);if(t){const e=(new TextDecoder).decode(t);this.#h=JSON.parse(e)}else this.#h={wordSegments:[],charSegments:[]};const e=await this.#o.read(i);if(e){const t=new DataView(e);let s=0;const i=e.byteLength;for(;s<i&&!(s+4>i);){const e=t.getUint32(s,!0);this.#c.add(e),s+=4,s<i&&30===t.getUint8(s)&&(s+=1)}}const a=await this.#o.read(n);if(a){const t=new DataView(a);let e=0;const s=a.byteLength;for(;e<s&&!(e+4>s);){const i=t.getUint32(e,!0);this.#d.add(i),e+=4,e<s&&30===t.getUint8(e)&&(e+=1)}}}async save(){const t=JSON.stringify(this.#h);if(await this.#o.write(s,(new TextEncoder).encode(t).buffer),0===this.#c.size)await this.#o.remove(i);else{const t=4*this.#c.size+this.#c.size,e=new ArrayBuffer(t),s=new DataView(e);let n=0;for(const t of this.#c)s.setUint32(n,t,!0),n+=4,s.setUint8(n,30),n+=1;await this.#o.write(i,e)}if(0===this.#d.size)await this.#o.remove(n);else{const t=4*this.#d.size+this.#d.size,e=new ArrayBuffer(t),s=new DataView(e);let i=0;for(const t of this.#d)s.setUint32(i,t,!0),i+=4,s.setUint8(i,30),i+=1;await this.#o.write(n,e)}}getSegments(t){return"word"===t?this.#h.wordSegments:this.#h.charSegments}getDeletedIds(){return this.#c}addDeletedId(t){this.#c.add(t)}isDeleted(t){return this.#c.has(t)}addAddedId(t){this.#d.add(t)}removeAddedId(t){this.#d.delete(t)}isAdded(t){return this.#d.has(t)}getAddedIds(){return this.#d}hasDocument(t){return this.#d.has(t)||this.#c.has(t)}getLastSegmentInfo(t){const e=this.getSegments(t);return 0===e.length?null:e[e.length-1]}updateSegment(t,e,s,i,n,a){const r="word"===t?this.#h.wordSegments:this.#h.charSegments;if(a)r.push({filename:e,start:s,end:i,tokenCount:n});else{const t=r[r.length-1];t&&t.filename===e&&(t.end=i,t.tokenCount=n)}}reset(){this.#h={wordSegments:[],charSegments:[]},this.#c.clear(),this.#d.clear()}}class r{static SEPARATOR=30;#o;constructor(t){this.#o=t}async appendBatch(t,e){if(0===e.length)return await this.#o.getFileSize(t);const s=new TextEncoder;let i=0;for(const t of e){i+=8;for(const e of t.tokens){i+=2+Math.min(s.encode(e).byteLength,65535)}i+=1}const n=new Uint8Array(i);let a=0;for(const t of e){const e=[];for(const i of t.tokens){const t=s.encode(i),n=t.byteLength>65535?t.slice(0,65535):t;e.push(n)}const i=new DataView(n.buffer,a);i.setUint32(0,t.id,!0),i.setUint32(4,e.length,!0),a+=8;for(const t of e)new DataView(n.buffer,a).setUint16(0,t.byteLength,!0),a+=2,n.set(t,a),a+=t.byteLength;n[a++]=r.SEPARATOR}return await this.#o.append(t,n.buffer),await this.#o.getFileSize(t)}async readRange(t,e,s){const i=await this.#o.readRange(t,e,s);if(!i||0===i.byteLength)return[];const n=new DataView(i),a=new Uint8Array(i),o=new TextDecoder,h=[];let c=0;const d=i.byteLength;for(;c<d&&!(c+8>d);){const t=n.getUint32(c,!0);c+=4;const e=n.getUint32(c,!0);c+=4;const s=[];for(let t=0;t<e&&!(c+2>d);t++){const t=n.getUint16(c,!0);if(c+=2,c+t>d)break;const e=new Uint8Array(i,c,t);s.push(o.decode(e)),c+=t}c<d&&a[c]===r.SEPARATOR&&(c+=1),h.push({id:t,tokens:s})}return h}async getCurrentSize(t){return await this.#o.getFileSize(t)}}class o{#g;#o;#l=null;#f=null;static hash(t){let e=5381;for(let s=0;s<t.length;s++)e=(e<<5)+e^t.charCodeAt(s);return e>>>0}constructor(t,e){this.#g=t,this.#o=e}async loadIndex(){return!!this.#l||(this.#l=await this.#o.read(this.#g),!!this.#l&&(this.#f=new DataView(this.#l),!0))}async buildAndSave(t){const e=new Map;for(const s of t){const t=new Map;for(const i of s.tokens)if(!t.has(i)){t.set(i,!0);const n=o.hash(i);e.has(n)||e.set(n,[]),e.get(n).push(s.id)}}const s=Array.from(e.keys()).sort((t,e)=>t-e);let i=0;const n=new Array(s.length);for(let t=0;t<s.length;t++){const a=s[t],r=e.get(a);n[t]=r,i+=r.length}const a=12*s.length,r=new ArrayBuffer(8+a+4*i),h=new DataView(r);h.setUint32(0,1229866072),h.setUint32(4,s.length);let c=8,d=8+a;for(let t=0;t<s.length;t++){const e=s[t],i=n[t];h.setUint32(c,e),h.setUint32(c+4,d),h.setUint32(c+8,i.length),c+=12;for(let t=0;t<i.length;t++)h.setUint32(d,i[t],!0),d+=4}await this.#o.write(this.#g,r),this.#l=r,this.#f=h}search(t){if(!this.#f||!this.#l)return[];const e=o.hash(t);let s=0,i=this.#f.getUint32(4)-1;for(;s<=i;){const t=s+i>>>1,n=8+12*t,a=this.#f.getUint32(n);if(a<e)s=t+1;else{if(!(a>e)){const t=this.#f.getUint32(n+4),e=this.#f.getUint32(n+8),s=[];for(let i=0;i<e;i++)s.push(this.#f.getUint32(t+4*i,!0));return s}i=t-1}}return[]}}const h="word_cache.bin",c="char_cache.bin";class d{#o;#h;#w;#u;#m=!1;#y;#p=!1;#D={word:0,char:0};constructor(s){if(!s.baseDir)throw new Error("SearchEngine requires 'baseDir' in config.");if(this.#y={wordSegmentTokenThreshold:1e5,charSegmentTokenThreshold:5e5,minWordTokenSave:0,minCharTokenSave:0,...s},(this.#y.minWordTokenSave||0)>=(this.#y.wordSegmentTokenThreshold||1e5))throw new Error("minWordTokenSave must be less than wordSegmentTokenThreshold");if((this.#y.minCharTokenSave||0)>=(this.#y.charSegmentTokenThreshold||5e5))throw new Error("minCharTokenSave must be less than charSegmentTokenThreshold");let i=null;if(this.#y.storage&&("object"==typeof this.#y.storage?i=this.#y.storage:"browser"===this.#y.storage?i=new t(this.#y.baseDir):"node"===this.#y.storage&&(i=new e(this.#y.baseDir))),!i){const s=typeof navigator<"u"&&navigator?.storage?.getDirectory instanceof Function,n=typeof process<"u"&&null!=process.versions&&null!=process.versions.node;s?i=new t(this.#y.baseDir):n&&(i=new e(this.#y.baseDir))}if(!i)throw new Error('Storage initialization failed. Please configure "storage" explicitly or ensure you are in a supported environment (Browser/Node).');this.#o=i,this.#h=new a(this.#o),this.#w=new r(this.#o),this.#u=new Map}async init(){if(this.#m)return;await this.#h.load();const t=[...this.#h.getSegments("word"),...this.#h.getSegments("char")];for(const e of t)this.#u.has(e.filename)||this.#u.set(e.filename,new o(e.filename,this.#o)),await this.#u.get(e.filename).loadIndex();this.#m=!0}startBatch(){this.#p=!0,this.#D={word:0,char:0}}async endBatch(){this.#p=!1,this.#D.word>0&&await this.#S("word",this.#D.word),this.#D.char>0&&await this.#S("char",this.#D.char),this.#D={word:0,char:0},await this.#h.save()}#k(t){try{if(typeof Intl<"u"&&"function"==typeof Intl.Segmenter&&"function"==typeof Array.from){const e=new Intl.Segmenter([],{granularity:"word"}).segment(t);if("object"==typeof e&&null!==e)return Array.from(e).filter(t=>t?.isWordLike).map(t=>t?.segment?.toLowerCase()||"")}}catch{}return t.toLowerCase().split(/[^a-z0-9\u4e00-\u9fa5]+/g).filter(t=>t.length>0)}#I(t){return this.#y.indexingTokenizer?this.#y.indexingTokenizer(t):this.#k(t.text)}#b(t){return this.#y.searchTokenizer?this.#y.searchTokenizer(t):this.#I(t)}async addDocument(t){return this.addDocuments([t])}async addDocumentIfMissing(t){return this.addDocumentsIfMissing([t])}async addDocumentsIfMissing(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[],n=[];for(const a of t){if(e.has(a.id)||this.#h.isAdded(a.id))continue;const t=this.#I(a),r=[],o=[];for(const e of t)e.length>1?r.push(e):1===e.length&&o.push(e);r.length>0&&s.push({id:a.id,tokens:r}),o.length>0&&i.push({id:a.id,tokens:o}),n.push(a)}if(0===n.length)return;let a=0,r=0;if(s.length>0){await this.#w.appendBatch(h,s);for(const t of s)a+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(c,i);for(const t of i)r+=t.tokens.length}for(const t of n)this.#h.addAddedId(t.id);this.#p?(this.#D.word+=a,this.#D.char+=r):(a>0&&await this.#S("word",a),r>0&&await this.#S("char",r),await this.#h.save())}async addDocuments(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[];for(const n of t){if(e.has(n.id))throw new Error(`Document ID ${n.id} has been deleted and cannot be re-added.`);if(this.#h.isAdded(n.id))throw new Error(`Document ID ${n.id} already exists.`);const t=this.#I(n),a=[],r=[];for(const e of t)e.length>1?a.push(e):1===e.length&&r.push(e);a.length>0&&s.push({id:n.id,tokens:a}),r.length>0&&i.push({id:n.id,tokens:r})}let n=0,a=0;if(s.length>0){await this.#w.appendBatch(h,s);for(const t of s)n+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(c,i);for(const t of i)a+=t.tokens.length}for(const e of t)this.#h.addAddedId(e.id);this.#p?(this.#D.word+=n,this.#D.char+=a):(n>0&&await this.#S("word",n),a>0&&await this.#S("char",a),await this.#h.save())}async#S(t,e){const s="word"===t?h:c,i=await this.#w.getCurrentSize(s),n="word"===t?this.#y.wordSegmentTokenThreshold||1e5:this.#y.charSegmentTokenThreshold||5e5,a="word"===t?this.#y.minWordTokenSave||0:this.#y.minCharTokenSave||0,r=this.#h.getLastSegmentInfo(t);let d,g,l,f;const w=()=>{const e=this.#h.getSegments(t).length+1;return`${t}_seg_${e}.bin`};if(r){const t=r.tokenCount;t>=n||t+e>=n?(d=w(),l=!0,g=r.end,f=e):(d=r.filename,l=!1,g=r.start,f=t+e)}else d=w(),l=!0,g=0,f=e;if(f<a)return void this.#h.updateSegment(t,d,g,i,f,l);const u=await this.#w.readRange(s,g,i);let m=this.#u.get(d);m||(m=new o(d,this.#o),this.#u.set(d,m)),await m.buildAndSave(u),this.#h.updateSegment(t,d,g,i,f,l)}async search(t,e){this.#m||await this.init();const s="string"==typeof t?{text:t}:t,i=this.#b(s),n=i.filter(t=>t.length>1),a=i.filter(t=>1===t.length),r=this.#h.getDeletedIds(),h=new Map,c=new Map,d=t=>{const e=this.#h.getSegments(t);for(const t of e){const e=t.filename;!this.#u.has(e)&&!c.has(e)&&c.set(e,new o(e,this.#o))}};d("word"),d("char"),await Promise.all(Array.from(c.entries()).map(([t,e])=>e.loadIndex().then(s=>{s&&this.#u.set(t,e)})));const g=async(t,e)=>{if(0===e.length)return;const s=this.#h.getSegments(t);for(const t of s){const s=t.filename,i=this.#u.get(s);if(i)for(const t of e){const e=i.search(t),s=1+.1*t.length;for(const i of e)if(!r.has(i))if(h.has(i)){const e=h.get(i);e.score+=s,e.tokens.add(t)}else h.set(i,{score:0,tokens:new Set([t])})}}};await g("word",n),await g("char",a);const l=[];return h.forEach((t,e)=>{l.push({id:e,score:t.score,tokens:Array.from(t.tokens)})}),l.sort((t,e)=>e.score-t.score),"number"==typeof e&&e>0?l.slice(0,e):l}async removeDocument(t){this.#m||await this.init(),this.#h.addDeletedId(t),this.#h.removeAddedId(t),await this.#h.save()}async clearAll(){await this.#o.clearAll(),this.#u.clear(),this.#h.reset(),this.#m=!1,this.#p=!1,this.#D={word:0,char:0}}async getStatus(){return this.#m||await this.init(),{wordSegments:this.#h.getSegments("word").length,charSegments:this.#h.getSegments("char").length,deleted:this.#h.getDeletedIds().size,wordCacheSize:await this.#w.getCurrentSize(h),charCacheSize:await this.#w.getCurrentSize(c),inBatch:this.#p}}async hasDocument(t){return this.#m||await this.init(),this.#h.hasDocument(t)}}class g{static#T=null;static#v={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(t){const e={...this.#v,...t};this.#T=new d(e)}static#z(){return this.#T||(this.#T=new d(this.#v)),this.#T}static async startBatch(){this.#z().startBatch()}static async endBatch(){return this.#z().endBatch()}static async addDocument(t){return this.#z().addDocument(t)}static async addDocumentIfMissing(t){return this.#z().addDocumentIfMissing(t)}static async addDocuments(t){return this.#z().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#z().addDocumentsIfMissing(t)}static async search(t,e){return this.#z().search(t,e)}static async removeDocument(t){return this.#z().removeDocument(t)}static async clearAll(){return this.#z().clearAll()}static async getStatus(){return this.#z().getStatus()}static async hasDocument(t){return this.#z().hasDocument(t)}}export{t as BrowserStorage,e as NodeStorage,d as SearchEngine,g as SimpleSearch};
+class t{#t;constructor(t){this.#t=t}async#e(){return await(await navigator.storage.getDirectory()).getDirectoryHandle(this.#t,{create:!0})}async write(t,e){const s=await(await(await this.#e()).getFileHandle(t,{create:!0})).createWritable();await s.write(e),await s.close()}async append(t,e){const s=await this.#e();let i;try{i=await s.getFileHandle(t,{create:!0})}catch{i=await s.getFileHandle(t,{create:!0})}const n=await i.getFile(),a=await i.createWritable({keepExistingData:!0});await a.seek(n.size),await a.write(e),await a.close()}async read(t){const e=await this.#e();try{return await(await(await e.getFileHandle(t)).getFile()).arrayBuffer()}catch{return null}}async readRange(t,e,s){const i=await this.#e();try{return await(await(await i.getFileHandle(t)).getFile()).slice(e,s).arrayBuffer()}catch{return null}}async remove(t){const e=await this.#e();try{await e.removeEntry(t)}catch{}}async listFiles(){const t=await this.#e(),e=[];for await(const s of t.keys())e.push(s);return e}async clearAll(){const t=await this.#e();for await(const e of t.keys())await t.removeEntry(e,{recursive:!0})}async getFileSize(t){const e=await this.#e();try{return(await(await e.getFileHandle(t)).getFile()).size}catch{return 0}}}class e{#s=null;#i=null;#t;#n="";constructor(t){this.#t=t}async#a(){if(this.#s)return;const t=await import("node:fs"),e=await import("node:path");this.#s=t.promises,this.#i=e.default||e,this.#n=this.#i.join(process.cwd(),this.#t);try{await this.#s.access(this.#n)}catch{await this.#s.mkdir(this.#n,{recursive:!0})}}#r(t){return this.#i.join(this.#n,t)}async write(t,e){await this.#a(),await this.#s.writeFile(this.#r(t),Buffer.from(e))}async append(t,e){await this.#a(),await this.#s.appendFile(this.#r(t),Buffer.from(e))}async read(t){await this.#a();try{const e=await this.#s.readFile(this.#r(t));return e.buffer.slice(e.byteOffset,e.byteOffset+e.byteLength)}catch{return null}}async readRange(t,e,s){await this.#a();try{const i=await this.#s.open(this.#r(t),"r"),n=s-e,a=Buffer.alloc(n);return await i.read(a,0,n,e),await i.close(),a.buffer.slice(a.byteOffset,a.byteOffset+a.byteLength)}catch{return null}}async remove(t){await this.#a();try{await this.#s.unlink(this.#r(t))}catch{}}async listFiles(){await this.#a();try{return await this.#s.readdir(this.#n)}catch{return[]}}async clearAll(){await this.#a();try{const t=await this.#s.readdir(this.#n);for(const e of t)await this.#s.unlink(this.#i.join(this.#n,e))}catch{}}async getFileSize(t){await this.#a();try{return(await this.#s.stat(this.#r(t))).size}catch{return 0}}}const s="search_meta.json",i="deleted_ids.bin",n="added_ids.bin";class a{#o;#h={wordSegments:[],charSegments:[]};#c=new Set;#d=new Set;constructor(t){this.#o=t}async load(){const t=await this.#o.read(s);if(t){const e=(new TextDecoder).decode(t);this.#h=JSON.parse(e)}else this.#h={wordSegments:[],charSegments:[]};const e=await this.#o.read(i);if(e){const t=new DataView(e);let s=0;const i=e.byteLength;for(;s<i&&!(s+4>i);){const e=t.getUint32(s,!0);this.#c.add(e),s+=4,s<i&&30===t.getUint8(s)&&(s+=1)}}const a=await this.#o.read(n);if(a){const t=new DataView(a);let e=0;const s=a.byteLength;for(;e<s&&!(e+4>s);){const i=t.getUint32(e,!0);this.#d.add(i),e+=4,e<s&&30===t.getUint8(e)&&(e+=1)}}}async save(){const t=JSON.stringify(this.#h);if(await this.#o.write(s,(new TextEncoder).encode(t).buffer),0===this.#c.size)await this.#o.remove(i);else{const t=4*this.#c.size+this.#c.size,e=new ArrayBuffer(t),s=new DataView(e);let n=0;for(const t of this.#c)s.setUint32(n,t,!0),n+=4,s.setUint8(n,30),n+=1;await this.#o.write(i,e)}if(0===this.#d.size)await this.#o.remove(n);else{const t=4*this.#d.size+this.#d.size,e=new ArrayBuffer(t),s=new DataView(e);let i=0;for(const t of this.#d)s.setUint32(i,t,!0),i+=4,s.setUint8(i,30),i+=1;await this.#o.write(n,e)}}getSegments(t){return"word"===t?this.#h.wordSegments:this.#h.charSegments}getDeletedIds(){return this.#c}addDeletedId(t){this.#c.add(t)}isDeleted(t){return this.#c.has(t)}addAddedId(t){this.#d.add(t)}removeAddedId(t){this.#d.delete(t)}isAdded(t){return this.#d.has(t)}getAddedIds(){return this.#d}hasDocument(t){return this.#d.has(t)||this.#c.has(t)}getLastSegmentInfo(t){const e=this.getSegments(t);return 0===e.length?null:e[e.length-1]}updateSegment(t,e,s,i,n,a){const r="word"===t?this.#h.wordSegments:this.#h.charSegments;if(a)r.push({filename:e,start:s,end:i,tokenCount:n});else{const t=r[r.length-1];t&&t.filename===e&&(t.end=i,t.tokenCount=n)}}reset(){this.#h={wordSegments:[],charSegments:[]},this.#c.clear(),this.#d.clear()}}class r{static SEPARATOR=30;#o;constructor(t){this.#o=t}async appendBatch(t,e){if(0===e.length)return await this.#o.getFileSize(t);const s=new TextEncoder;let i=0;for(const t of e){i+=8;for(const e of t.tokens){i+=2+Math.min(s.encode(e).byteLength,65535)}i+=1}const n=new Uint8Array(i);let a=0;for(const t of e){const e=[];for(const i of t.tokens){const t=s.encode(i),n=t.byteLength>65535?t.slice(0,65535):t;e.push(n)}const i=new DataView(n.buffer,a);i.setUint32(0,t.id,!0),i.setUint32(4,e.length,!0),a+=8;for(const t of e)new DataView(n.buffer,a).setUint16(0,t.byteLength,!0),a+=2,n.set(t,a),a+=t.byteLength;n[a++]=r.SEPARATOR}return await this.#o.append(t,n.buffer),await this.#o.getFileSize(t)}async readRange(t,e,s){const i=await this.#o.readRange(t,e,s);if(!i||0===i.byteLength)return[];const n=new DataView(i),a=new Uint8Array(i),o=new TextDecoder,h=[];let c=0;const d=i.byteLength;for(;c<d&&!(c+8>d);){const t=n.getUint32(c,!0);c+=4;const e=n.getUint32(c,!0);c+=4;const s=[];for(let t=0;t<e&&!(c+2>d);t++){const t=n.getUint16(c,!0);if(c+=2,c+t>d)break;const e=new Uint8Array(i,c,t);s.push(o.decode(e)),c+=t}c<d&&a[c]===r.SEPARATOR&&(c+=1),h.push({id:t,tokens:s})}return h}async getCurrentSize(t){return await this.#o.getFileSize(t)}}function o(t,e=305419896){const s=t.length,i=s>>2;let n=0;for(;n<i;){let s=255&t.charCodeAt(n)|(255&t.charCodeAt(++n))<<8|(255&t.charCodeAt(++n))<<16|(255&t.charCodeAt(++n))<<24;++n,s=3432918353*(65535&s)+((3432918353*(s>>>16)&65535)<<16)&4294967295,s=s<<15|s>>>17,s=461845907*(65535&s)+((461845907*(s>>>16)&65535)<<16)&4294967295,e=27492+(65535&(e=5*(65535&(e=(e^=s)<<13|e>>>19))+((5*(e>>>16)&65535)<<16)&4294967295))+(((e>>>16)+58964&65535)<<16)}let a=0;const r=3&s;return r>0&&(r>=3&&(a^=(255&t.charCodeAt(n+2))<<16),r>=2&&(a^=(255&t.charCodeAt(n+1))<<8),r>=1&&(a^=255&t.charCodeAt(n)),a=3432918353*(65535&a)+((3432918353*(a>>>16)&65535)<<16)&4294967295,a=a<<15|a>>>17,a=461845907*(65535&a)+((461845907*(a>>>16)&65535)<<16)&4294967295,e^=a),e^=s,e=2246822507*(65535&(e^=e>>>16))+((2246822507*(e>>>16)&65535)<<16)&4294967295,e=3266489909*(65535&(e^=e>>>13))+((3266489909*(e>>>16)&65535)<<16)&4294967295,(e^=e>>>16)>>>0}class h{#g;#o;#l=null;#f=null;static hash(t){return o(t)}constructor(t,e){this.#g=t,this.#o=e}async loadIndex(){return!!this.#l||(this.#l=await this.#o.read(this.#g),!!this.#l&&(this.#f=new DataView(this.#l),!0))}async buildAndSave(t){const e=new Map;for(const s of t){const t=new Map;for(const i of s.tokens)t.has(i)||(t.set(i,!0),e.has(i)||e.set(i,{hash:h.hash(i),postings:[]}),e.get(i).postings.push(s.id))}const s=Array.from(e.entries());s.sort(([t,{hash:e}],[s,{hash:i}])=>e!==i?e-i:t.localeCompare(s));let i=0,n=0;for(const[t,{postings:e}]of s)i+=e.length,n+=t.length+1;const a=20*s.length,r=12+a+4*i,o=new ArrayBuffer(r+n),c=new DataView(o);c.setUint32(0,1229866072),c.setUint32(4,s.length),c.setUint32(8,r);let d=12,g=12+a,l=r;for(const[t,{hash:e,postings:i}]of s){c.setUint32(d,e),c.setUint32(d+4,t.length),c.setUint32(d+8,l),c.setUint32(d+12,g),c.setUint32(d+16,i.length),d+=20;for(let t=0;t<i.length;t++)c.setUint32(g,i[t],!0),g+=4;const s=(new TextEncoder).encode(t);for(let t=0;t<s.length;t++)c.setUint8(l++,s[t]);c.setUint8(l++,0)}await this.#o.write(this.#g,o),this.#l=o,this.#f=c}search(t){if(!this.#f||!this.#l)return[];const e=h.hash(t),s=this.#f.getUint32(4);let i=0,n=s-1;const a=12,r=20,o=new TextDecoder;for(;i<=n;){const h=i+n>>>1,c=a+h*r,d=this.#f.getUint32(c);if(d<e)i=h+1;else{if(!(d>e)){if(!(h>0&&this.#f.getUint32(a+(h-1)*r)===e||h<s-1&&this.#f.getUint32(a+(h+1)*r)===e)){const t=this.#f.getUint32(a+h*r+12),e=this.#f.getUint32(a+h*r+16),s=[];for(let i=0;i<e;i++)s.push(this.#f.getUint32(t+4*i,!0));return s}let i=h;for(;i>0;){const t=a+(i-1)*r;if(this.#f.getUint32(t)!==e)break;i--}for(let n=i;n<s;n++){const s=a+n*r;if(this.#f.getUint32(s)!==e)break;const i=this.#f.getUint32(s+4),h=this.#f.getUint32(s+8),c=new Uint8Array(this.#l,h,i);if(o.decode(c)===t){const t=this.#f.getUint32(s+12),e=this.#f.getUint32(s+16),i=[];for(let s=0;s<e;s++)i.push(this.#f.getUint32(t+4*s,!0));return i}}return[]}n=h-1}}return[]}}const c="word_cache.bin",d="char_cache.bin";class g{#o;#h;#w;#u;#m=!1;#y;#p=!1;#D={word:0,char:0};constructor(s){if(!s.baseDir)throw new Error("SearchEngine requires 'baseDir' in config.");if(this.#y={wordSegmentTokenThreshold:1e5,charSegmentTokenThreshold:5e5,minWordTokenSave:0,minCharTokenSave:0,...s},(this.#y.minWordTokenSave||0)>=(this.#y.wordSegmentTokenThreshold||1e5))throw new Error("minWordTokenSave must be less than wordSegmentTokenThreshold");if((this.#y.minCharTokenSave||0)>=(this.#y.charSegmentTokenThreshold||5e5))throw new Error("minCharTokenSave must be less than charSegmentTokenThreshold");let i=null;if(this.#y.storage&&("object"==typeof this.#y.storage?i=this.#y.storage:"browser"===this.#y.storage?i=new t(this.#y.baseDir):"node"===this.#y.storage&&(i=new e(this.#y.baseDir))),!i){const s=typeof navigator<"u"&&navigator?.storage?.getDirectory instanceof Function,n=typeof process<"u"&&null!=process.versions&&null!=process.versions.node;s?i=new t(this.#y.baseDir):n&&(i=new e(this.#y.baseDir))}if(!i)throw new Error('Storage initialization failed. Please configure "storage" explicitly or ensure you are in a supported environment (Browser/Node).');this.#o=i,this.#h=new a(this.#o),this.#w=new r(this.#o),this.#u=new Map}async init(){if(this.#m)return;await this.#h.load();const t=[...this.#h.getSegments("word"),...this.#h.getSegments("char")];for(const e of t)this.#u.has(e.filename)||this.#u.set(e.filename,new h(e.filename,this.#o)),await this.#u.get(e.filename).loadIndex();this.#m=!0}startBatch(){this.#p=!0,this.#D={word:0,char:0}}async endBatch(){this.#p=!1,this.#D.word>0&&await this.#S("word",this.#D.word),this.#D.char>0&&await this.#S("char",this.#D.char),this.#D={word:0,char:0},await this.#h.save()}#k(t){try{if(typeof Intl<"u"&&"function"==typeof Intl.Segmenter&&"function"==typeof Array.from){const e=new Intl.Segmenter([],{granularity:"word"}).segment(t);if("object"==typeof e&&null!==e)return Array.from(e).filter(t=>t?.isWordLike).map(t=>t?.segment?.toLowerCase()||"")}}catch{}return t.toLowerCase().split(/[^a-z0-9\u4e00-\u9fa5]+/g).filter(t=>t.length>0)}#I(t){return this.#y.indexingTokenizer?this.#y.indexingTokenizer(t):this.#k(t.text)}#b(t){return this.#y.searchTokenizer?this.#y.searchTokenizer(t):this.#I(t)}async addDocument(t){return this.addDocuments([t])}async addDocumentIfMissing(t){return this.addDocumentsIfMissing([t])}async addDocumentsIfMissing(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[],n=[];for(const a of t){if(e.has(a.id)||this.#h.isAdded(a.id))continue;const t=this.#I(a),r=[],o=[];for(const e of t)e.length>1?r.push(e):1===e.length&&o.push(e);r.length>0&&s.push({id:a.id,tokens:r}),o.length>0&&i.push({id:a.id,tokens:o}),n.push(a)}if(0===n.length)return;let a=0,r=0;if(s.length>0){await this.#w.appendBatch(c,s);for(const t of s)a+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(d,i);for(const t of i)r+=t.tokens.length}for(const t of n)this.#h.addAddedId(t.id);this.#p?(this.#D.word+=a,this.#D.char+=r):(a>0&&await this.#S("word",a),r>0&&await this.#S("char",r),await this.#h.save())}async addDocuments(t){if(this.#m||await this.init(),0===t.length)return;const e=this.#h.getDeletedIds(),s=[],i=[];for(const n of t){if(e.has(n.id))throw new Error(`Document ID ${n.id} has been deleted and cannot be re-added.`);if(this.#h.isAdded(n.id))throw new Error(`Document ID ${n.id} already exists.`);const t=this.#I(n),a=[],r=[];for(const e of t)e.length>1?a.push(e):1===e.length&&r.push(e);a.length>0&&s.push({id:n.id,tokens:a}),r.length>0&&i.push({id:n.id,tokens:r})}let n=0,a=0;if(s.length>0){await this.#w.appendBatch(c,s);for(const t of s)n+=t.tokens.length}if(i.length>0){await this.#w.appendBatch(d,i);for(const t of i)a+=t.tokens.length}for(const e of t)this.#h.addAddedId(e.id);this.#p?(this.#D.word+=n,this.#D.char+=a):(n>0&&await this.#S("word",n),a>0&&await this.#S("char",a),await this.#h.save())}async#S(t,e){const s="word"===t?c:d,i=await this.#w.getCurrentSize(s),n="word"===t?this.#y.wordSegmentTokenThreshold||1e5:this.#y.charSegmentTokenThreshold||5e5,a="word"===t?this.#y.minWordTokenSave||0:this.#y.minCharTokenSave||0,r=this.#h.getLastSegmentInfo(t);let o,g,l,f;const w=()=>{const e=this.#h.getSegments(t).length+1;return`${t}_seg_${e}.bin`};if(r){const t=r.tokenCount;t>=n||t+e>=n?(o=w(),l=!0,g=r.end,f=e):(o=r.filename,l=!1,g=r.start,f=t+e)}else o=w(),l=!0,g=0,f=e;if(f<a)return void this.#h.updateSegment(t,o,g,i,f,l);const u=await this.#w.readRange(s,g,i);let m=this.#u.get(o);m||(m=new h(o,this.#o),this.#u.set(o,m)),await m.buildAndSave(u),this.#h.updateSegment(t,o,g,i,f,l)}async search(t,e){this.#m||await this.init();const s="string"==typeof t?{text:t}:t,i=this.#b(s),n=i.filter(t=>t.length>1),a=i.filter(t=>1===t.length),r=this.#h.getDeletedIds(),o=new Map,c=new Map,d=t=>{const e=this.#h.getSegments(t);for(const t of e){const e=t.filename;!this.#u.has(e)&&!c.has(e)&&c.set(e,new h(e,this.#o))}};d("word"),d("char"),await Promise.all(Array.from(c.entries()).map(([t,e])=>e.loadIndex().then(s=>{s&&this.#u.set(t,e)})));const g=async(t,e)=>{if(0===e.length)return;const s=this.#h.getSegments(t);for(const t of s){const s=t.filename,i=this.#u.get(s);if(i)for(const t of e){const e=i.search(t),s=1+.1*t.length;for(const i of e)if(!r.has(i))if(o.has(i)){const e=o.get(i);e.score+=s,e.tokens.add(t)}else o.set(i,{score:0,tokens:new Set([t])})}}};await g("word",n),await g("char",a);const l=[];return o.forEach((t,e)=>{l.push({id:e,score:t.score,tokens:Array.from(t.tokens)})}),l.sort((t,e)=>e.score-t.score),"number"==typeof e&&e>0?l.slice(0,e):l}async removeDocument(t){this.#m||await this.init(),this.#h.addDeletedId(t),this.#h.removeAddedId(t),await this.#h.save()}async clearAll(){await this.#o.clearAll(),this.#u.clear(),this.#h.reset(),this.#m=!1,this.#p=!1,this.#D={word:0,char:0}}async getStatus(){return this.#m||await this.init(),{wordSegments:this.#h.getSegments("word").length,charSegments:this.#h.getSegments("char").length,deleted:this.#h.getDeletedIds().size,wordCacheSize:await this.#w.getCurrentSize(c),charCacheSize:await this.#w.getCurrentSize(d),inBatch:this.#p}}async hasDocument(t){return this.#m||await this.init(),this.#h.hasDocument(t)}}class l{static#T=null;static#v={baseDir:"simple_search_data",wordSegmentTokenThreshold:1e5,minWordTokenSave:0};static configure(t){const e={...this.#v,...t};this.#T=new g(e)}static#U(){return this.#T||(this.#T=new g(this.#v)),this.#T}static async startBatch(){this.#U().startBatch()}static async endBatch(){return this.#U().endBatch()}static async addDocument(t){return this.#U().addDocument(t)}static async addDocumentIfMissing(t){return this.#U().addDocumentIfMissing(t)}static async addDocuments(t){return this.#U().addDocuments(t)}static async addDocumentsIfMissing(t){return this.#U().addDocumentsIfMissing(t)}static async search(t,e){return this.#U().search(t,e)}static async removeDocument(t){return this.#U().removeDocument(t)}static async clearAll(){return this.#U().clearAll()}static async getStatus(){return this.#U().getStatus()}static async hasDocument(t){return this.#U().hasDocument(t)}}export{t as BrowserStorage,e as NodeStorage,g as SearchEngine,l as SimpleSearch,o as hash,o as murmur3_32};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gs-search",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "type": "module",
   "main": "lib/index.cjs",
   "module": "lib/index.js",