@gukhanmun/stdict-cdb 0.4.0-dev.236 → 0.4.0-dev.248

package/dist/index.d.ts

@@ -1,77 +1,12 @@
-//#region ../types/dist/index.d.ts
-
+import { FileDictionarySource, FileDictionarySource as FileDictionarySource$1, SourceRole } from "@gukhanmun/types";
 /**
- * Specifies a dictionary loaded from a binary file or URL.
+ * URL of the bundled, gzip-compressed Standard Korean Language Dictionary CDB.
  *
- * The `data` field accepts:
- * - A `BufferSource` (`ArrayBuffer` or `ArrayBufferView`) — supported in all
- *   environments.
- * - A `URL` — resolved via `fetch` in browsers; via `node:fs/promises`
- *   in Node.js, Deno 2.0+, and Bun.
- * - A `string` — treated as a filesystem path; supported in Node.js,
- *   Deno 2.0+, and Bun only.  Throws in browser environments.
- *
- * At runtime, a `FileDictionarySource` is distinguished from other values by
- * the absence of an `entries` property (`"entries" in source` selects a
- * {@link MapDictionarySource}).
+ * The URL now points to `stdict.cdb.gz` to fit registry per-file limits.
+ * {@link stdictCdbBytes} transparently returns the decompressed CDB bytes.
+ * The npm package also retains its raw `stdict.cdb` file export.
  */
-interface FileDictionarySource {
-  /**
-   * The binary dictionary data or a reference to where it can be loaded.
-   *
-   * Pass a `BufferSource` for data already in memory, a `URL` for a remote
-   * or local URL (resolved via `fetch` or `readFile`), or a path `string`
-   * for filesystem paths (Node.js / Deno 2.0+ / Bun only).
-   */
-  readonly data: ArrayBuffer | ArrayBufferView | URL | string;
-  /**
-   * The on-disk format of the dictionary file.
-   *
-   * - `"fst"` — Gukhanmun FST file (`*.gukfst`); preferred for small
-   *   WebAssembly bundles.  Supported in all runtimes.
-   * - `"cdb"` — Gukhanmun CDB-trie file (`*.gukcdb`); preferred when code
-   *   auditability or trivial mmap support matters.  Requires a filesystem
-   *   or in-memory bytes; supported in Node-API and (with `from_bytes`) in
-   *   WASM builds that include the `cdb` feature.
-   *
-   * The `"tsv"` format is reserved and never accepted.  Pass entries in memory
-   * through {@link MapDictionarySource} instead of compiling a table.
-   */
-  readonly format: "fst" | "cdb";
-}
-/**
- * A dictionary built from entries computed at runtime, such as per-document
- * reading overrides.
- *
- * Use this instead of compiling a TSV file with `gukhanmun-mkdict` when the
- * entries do not exist on disk, for example in a browser, an edge runtime, or a
- * site generator that derives entries per document.
- *
- * A source is distinguished from a {@link FileDictionarySource} by the presence
- * of an `entries` property.
- *
- * @example
- * ```ts
- * import { stdictFst } from "@gukhanmun/stdict-fst";
- * const g = await load({
- *   dictionaries: [
- *     {
- *       entries: [
- *         { hanja: "高橋", reading: "다카하시" },
- *         { hanja: "東京", reading: "도쿄", preference: 10 },
- *         { hanja: "年代", reading: "연대", suffixReading: "년대" },
- *       ],
- *     },
- *     await stdictFst(),
- *   ],
- * });
- * ```
- */
-//#endregion
-//#region index.d.ts
-
-/** URL of the bundled Standard Korean Language Dictionary CDB binary. */
-declare const stdictCdbUrl: URL;
+export declare const stdictCdbUrl: URL;
 /**
  * Loads the bundled Standard Korean Language Dictionary as raw bytes.
  *
@@ -86,17 +21,19 @@ declare const stdictCdbUrl: URL;
  * wrongly take the `node:fs` path and `readFile` would reject the `https:`
  * URL with "The URL must be of scheme file".
  *
- * @param url Location of the CDB binary to read.  Defaults to the bundled
+ * Gzip is detected from the payload's magic bytes, so compressed files are
+ * inflated transparently and relocated raw CDB files remain supported.
+ *
+ * @param url Location of the raw or gzip-compressed CDB to read. Defaults to the bundled
  *   {@link stdictCdbUrl}; pass another URL to load a relocated copy.
  * @returns The CDB binary as a `Uint8Array`.
  */
-declare function stdictCdbBytes(url?: URL): Promise<Uint8Array<ArrayBuffer>>;
+export declare function stdictCdbBytes(url?: URL): Promise<Uint8Array<ArrayBuffer>>;
 /**
  * Loads the bundled Standard Korean Language Dictionary as a
  * {@link FileDictionarySource} ready to pass to `load({ dictionaries: [...] })`.
  *
- * @returns A `FileDictionarySource` with `format: "cdb"`.
+ * @returns A `FileDictionarySource` with `format: "cdb"` and `role: "reference"`.
  */
-declare function stdictCdb(): Promise<FileDictionarySource>;
-//#endregion
-export { type FileDictionarySource, stdictCdb, stdictCdbBytes, stdictCdbUrl };
+export declare function stdictCdb(): Promise<FileDictionarySource$1>;
+export type { FileDictionarySource, SourceRole };

package/dist/index.js

@@ -1,6 +1,12 @@
-//#region index.ts
-/** URL of the bundled Standard Korean Language Dictionary CDB binary. */
-const stdictCdbUrl = new URL("./stdict.cdb", import.meta.url);
+// index.ts
+/**
+* URL of the bundled, gzip-compressed Standard Korean Language Dictionary CDB.
+*
+* The URL now points to `stdict.cdb.gz` to fit registry per-file limits.
+* {@link stdictCdbBytes} transparently returns the decompressed CDB bytes.
+* The npm package also retains its raw `stdict.cdb` file export.
+*/
+const stdictCdbUrl = new URL("./stdict.cdb.gz", import.meta.url);
 /**
 * Loads the bundled Standard Korean Language Dictionary as raw bytes.
 *
@@ -15,7 +21,10 @@ const stdictCdbUrl = new URL("./stdict.cdb", import.meta.url);
 * wrongly take the `node:fs` path and `readFile` would reject the `https:`
 * URL with "The URL must be of scheme file".
 *
-* @param url Location of the CDB binary to read.  Defaults to the bundled
+* Gzip is detected from the payload's magic bytes, so compressed files are
+* inflated transparently and relocated raw CDB files remain supported.
+*
+* @param url Location of the raw or gzip-compressed CDB to read. Defaults to the bundled
 *   {@link stdictCdbUrl}; pass another URL to load a relocated copy.
 * @returns The CDB binary as a `Uint8Array`.
 */
@@ -25,23 +34,28 @@ async function stdictCdbBytes(url = stdictCdbUrl) {
 			/* webpackIgnore: true */
 			"node:fs/promises"
 )).readFile(url);
-		return new Uint8Array(buf.buffer, buf.byteOffset, buf.byteLength);
+		return inflateIfGzip(new Uint8Array(buf.buffer, buf.byteOffset, buf.byteLength));
 	}
 	const response = await fetch(url);
 	if (!response.ok) throw new Error(`Failed to fetch stdict CDB: HTTP ${response.status}`);
-	return new Uint8Array(await response.arrayBuffer());
+	return inflateIfGzip(new Uint8Array(await response.arrayBuffer()));
+}
+async function inflateIfGzip(bytes) {
+	if (bytes.length < 2 || bytes[0] !== 31 || bytes[1] !== 139) return bytes;
+	const stream = new Blob([bytes]).stream().pipeThrough(new DecompressionStream("gzip"));
+	return new Uint8Array(await new Response(stream).arrayBuffer());
 }
 /**
 * Loads the bundled Standard Korean Language Dictionary as a
 * {@link FileDictionarySource} ready to pass to `load({ dictionaries: [...] })`.
 *
-* @returns A `FileDictionarySource` with `format: "cdb"`.
+* @returns A `FileDictionarySource` with `format: "cdb"` and `role: "reference"`.
 */
 async function stdictCdb() {
 	return {
 		data: await stdictCdbBytes(),
-		format: "cdb"
+		format: "cdb",
+		role: "reference"
 	};
 }
-//#endregion
 export { stdictCdb, stdictCdbBytes, stdictCdbUrl };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gukhanmun/stdict-cdb",
-  "version": "0.4.0-dev.236",
+  "version": "0.4.0-dev.248",
   "description": "Standard Korean Language Dictionary bundled as a CDB binary for @gukhanmun/wasm and @gukhanmun/napi.",
   "type": "module",
   "exports": {
@@ -9,7 +9,8 @@
       "import": "./dist/index.js",
       "default": "./dist/index.js"
     },
-    "./stdict.cdb": "./dist/stdict.cdb"
+    "./stdict.cdb": "./dist/stdict.cdb",
+    "./stdict.cdb.gz": "./dist/stdict.cdb.gz"
   },
   "files": [
     "dist"
@@ -55,9 +56,9 @@
     "@gukhanmun/types": "*"
   },
   "devDependencies": {
-    "@gukhanmun/types": "0.4.0-dev.236+75afc34"
+    "@gukhanmun/types": "0.4.0-dev.248+36997e7"
   },
   "scripts": {
-    "build": "tsdown && node -e \"require('node:fs').copyFileSync('stdict.cdb','dist/stdict.cdb')\""
+    "build": "tsdown && node -e \"const fs=require('node:fs');for(const f of ['stdict.cdb','stdict.cdb.gz'])fs.copyFileSync(f,'dist/'+f)\""
   }
 }